diff options
Diffstat (limited to 'arch')
399 files changed, 6552 insertions, 7933 deletions
diff --git a/arch/Kconfig b/arch/Kconfig index c47b328eada0..e8d19c3cb91f 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -260,6 +260,14 @@ config ARCH_HAS_SET_MEMORY config ARCH_HAS_SET_DIRECT_MAP bool +# +# Select if arch has an uncached kernel segment and provides the +# uncached_kernel_address / cached_kernel_address symbols to use it +# +config ARCH_HAS_UNCACHED_SEGMENT + select ARCH_HAS_DMA_PREP_COHERENT + bool + # Select if arch init_task must go in the __init_task_data section config ARCH_TASK_STRUCT_ON_STACK bool diff --git a/arch/alpha/Makefile b/arch/alpha/Makefile index b3314e0dcb6f..12dee59b011c 100644 --- a/arch/alpha/Makefile +++ b/arch/alpha/Makefile @@ -8,8 +8,6 @@ # Copyright (C) 1994 by Linus Torvalds # -KBUILD_DEFCONFIG := defconfig - NM := $(NM) -B LDFLAGS_vmlinux := -static -N #-relax diff --git a/arch/alpha/include/asm/pgalloc.h b/arch/alpha/include/asm/pgalloc.h index 02f9f91bb4f0..71ded3b7d82d 100644 --- a/arch/alpha/include/asm/pgalloc.h +++ b/arch/alpha/include/asm/pgalloc.h @@ -5,6 +5,8 @@ #include <linux/mm.h> #include <linux/mmzone.h> +#include <asm-generic/pgalloc.h> /* for pte_{alloc,free}_one */ + /* * Allocate and free page tables. The xxx_kernel() versions are * used to allocate a kernel page table - this turns on ASN bits @@ -41,7 +43,7 @@ pgd_free(struct mm_struct *mm, pgd_t *pgd) static inline pmd_t * pmd_alloc_one(struct mm_struct *mm, unsigned long address) { - pmd_t *ret = (pmd_t *)__get_free_page(GFP_KERNEL|__GFP_ZERO); + pmd_t *ret = (pmd_t *)__get_free_page(GFP_PGTABLE_USER); return ret; } @@ -51,42 +53,6 @@ pmd_free(struct mm_struct *mm, pmd_t *pmd) free_page((unsigned long)pmd); } -static inline pte_t * -pte_alloc_one_kernel(struct mm_struct *mm) -{ - pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_ZERO); - return pte; -} - -static inline void -pte_free_kernel(struct mm_struct *mm, pte_t *pte) -{ - free_page((unsigned long)pte); -} - -static inline pgtable_t -pte_alloc_one(struct mm_struct *mm) -{ - pte_t *pte = pte_alloc_one_kernel(mm); - struct page *page; - - if (!pte) - return NULL; - page = virt_to_page(pte); - if (!pgtable_page_ctor(page)) { - __free_page(page); - return NULL; - } - return page; -} - -static inline void -pte_free(struct mm_struct *mm, pgtable_t page) -{ - pgtable_page_dtor(page); - __free_page(page); -} - #define check_pgt_cache() do { } while (0) #endif /* _ALPHA_PGALLOC_H */ diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index 1c8137e7247b..8383155c8c82 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -7,6 +7,7 @@ config ARC def_bool y select ARC_TIMERS select ARCH_HAS_DMA_COHERENT_TO_PFN + select ARCH_HAS_DMA_PREP_COHERENT select ARCH_HAS_PTE_SPECIAL select ARCH_HAS_SETUP_DMA_OPS select ARCH_HAS_SYNC_DMA_FOR_CPU @@ -16,6 +17,7 @@ config ARC select BUILDTIME_EXTABLE_SORT select CLONE_BACKWARDS select COMMON_CLK + select DMA_DIRECT_REMAP select GENERIC_ATOMIC64 if !ISA_ARCV2 || !(ARC_HAS_LL64 && ARC_HAS_LLSC) select GENERIC_CLOCKEVENTS select GENERIC_FIND_FIRST_BIT diff --git a/arch/arc/Makefile b/arch/arc/Makefile index 03a0b19c92cd..ee6d1184c2b1 100644 --- a/arch/arc/Makefile +++ b/arch/arc/Makefile @@ -19,7 +19,7 @@ ifdef CONFIG_ARC_CURR_IN_REG # any kernel headers, and missing the r25 global register # Can't do unconditionally because of recursive include issues # due to <linux/thread_info.h> -LINUXINCLUDE += -include ${src}/arch/arc/include/asm/current.h +LINUXINCLUDE += -include $(srctree)/arch/arc/include/asm/current.h endif cflags-y += -fsection-anchors diff --git a/arch/arc/configs/tb10x_defconfig b/arch/arc/configs/tb10x_defconfig index 5b5119d2b5d5..dc739bd093e3 100644 --- a/arch/arc/configs/tb10x_defconfig +++ b/arch/arc/configs/tb10x_defconfig @@ -94,6 +94,7 @@ CONFIG_CONFIGFS_FS=y CONFIG_DEBUG_INFO=y CONFIG_STRIP_ASM_SYMS=y CONFIG_DEBUG_FS=y +CONFIG_HEADERS_INSTALL=y CONFIG_HEADERS_CHECK=y CONFIG_DEBUG_SECTION_MISMATCH=y CONFIG_MAGIC_SYSRQ=y diff --git a/arch/arc/mm/dma.c b/arch/arc/mm/dma.c index 0bf1468c35a3..62c210e7ee4c 100644 --- a/arch/arc/mm/dma.c +++ b/arch/arc/mm/dma.c @@ -8,51 +8,15 @@ #include <asm/cacheflush.h> /* - * ARCH specific callbacks for generic noncoherent DMA ops (dma/noncoherent.c) + * ARCH specific callbacks for generic noncoherent DMA ops * - hardware IOC not available (or "dma-coherent" not set for device in DT) * - But still handle both coherent and non-coherent requests from caller * * For DMA coherent hardware (IOC) generic code suffices */ -void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, - gfp_t gfp, unsigned long attrs) -{ - unsigned long order = get_order(size); - struct page *page; - phys_addr_t paddr; - void *kvaddr; - bool need_coh = !(attrs & DMA_ATTR_NON_CONSISTENT); - - /* - * __GFP_HIGHMEM flag is cleared by upper layer functions - * (in include/linux/dma-mapping.h) so we should never get a - * __GFP_HIGHMEM here. - */ - BUG_ON(gfp & __GFP_HIGHMEM); - - page = alloc_pages(gfp | __GFP_ZERO, order); - if (!page) - return NULL; - - /* This is linear addr (0x8000_0000 based) */ - paddr = page_to_phys(page); - - *dma_handle = paddr; - - /* - * A coherent buffer needs MMU mapping to enforce non-cachability. - * kvaddr is kernel Virtual address (0x7000_0000 based). - */ - if (need_coh) { - kvaddr = ioremap_nocache(paddr, size); - if (kvaddr == NULL) { - __free_pages(page, order); - return NULL; - } - } else { - kvaddr = (void *)(u32)paddr; - } +void arch_dma_prep_coherent(struct page *page, size_t size) +{ /* * Evict any existing L1 and/or L2 lines for the backing page * in case it was used earlier as a normal "cached" page. @@ -63,28 +27,7 @@ void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, * Currently flush_cache_vmap nukes the L1 cache completely which * will be optimized as a separate commit */ - if (need_coh) - dma_cache_wback_inv(paddr, size); - - return kvaddr; -} - -void arch_dma_free(struct device *dev, size_t size, void *vaddr, - dma_addr_t dma_handle, unsigned long attrs) -{ - phys_addr_t paddr = dma_handle; - struct page *page = virt_to_page(paddr); - - if (!(attrs & DMA_ATTR_NON_CONSISTENT)) - iounmap((void __force __iomem *)vaddr); - - __free_pages(page, get_order(size)); -} - -long arch_dma_coherent_to_pfn(struct device *dev, void *cpu_addr, - dma_addr_t dma_addr) -{ - return __phys_to_pfn(dma_addr); + dma_cache_wback_inv(page_to_phys(page), size); } /* @@ -161,3 +104,9 @@ void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, dev_info(dev, "use %sncoherent DMA ops\n", dev->dma_coherent ? "" : "non"); } + +static int __init atomic_pool_init(void) +{ + return dma_atomic_pool_init(GFP_KERNEL, pgprot_noncached(PAGE_KERNEL)); +} +postcore_initcall(atomic_pool_init); diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index d850feb5cc0a..2bf1ce39a96d 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -75,6 +75,7 @@ config ARM select HAVE_DYNAMIC_FTRACE_WITH_REGS if HAVE_DYNAMIC_FTRACE select HAVE_EFFICIENT_UNALIGNED_ACCESS if (CPU_V6 || CPU_V6K || CPU_V7) && MMU select HAVE_EXIT_THREAD + select HAVE_FAST_GUP if ARM_LPAE select HAVE_FTRACE_MCOUNT_RECORD if !XIP_KERNEL select HAVE_FUNCTION_GRAPH_TRACER if !THUMB2_KERNEL && !CC_IS_CLANG select HAVE_FUNCTION_TRACER if !XIP_KERNEL @@ -1622,16 +1623,9 @@ config ARCH_SPARSEMEM_ENABLE config ARCH_SPARSEMEM_DEFAULT def_bool ARCH_SPARSEMEM_ENABLE -config ARCH_SELECT_MEMORY_MODEL - def_bool ARCH_SPARSEMEM_ENABLE - config HAVE_ARCH_PFN_VALID def_bool ARCH_HAS_HOLES_MEMORYMODEL || !SPARSEMEM -config HAVE_GENERIC_GUP - def_bool y - depends on ARM_LPAE - config HIGHMEM bool "High Memory Support" depends on MMU diff --git a/arch/arm/include/asm/kvm_emulate.h b/arch/arm/include/asm/kvm_emulate.h index 6b7644a383f6..40002416efec 100644 --- a/arch/arm/include/asm/kvm_emulate.h +++ b/arch/arm/include/asm/kvm_emulate.h @@ -271,6 +271,16 @@ static inline unsigned long kvm_vcpu_get_mpidr_aff(struct kvm_vcpu *vcpu) return vcpu_cp15(vcpu, c0_MPIDR) & MPIDR_HWID_BITMASK; } +static inline bool kvm_arm_get_vcpu_workaround_2_flag(struct kvm_vcpu *vcpu) +{ + return false; +} + +static inline void kvm_arm_set_vcpu_workaround_2_flag(struct kvm_vcpu *vcpu, + bool flag) +{ +} + static inline void kvm_vcpu_set_be(struct kvm_vcpu *vcpu) { *vcpu_cpsr(vcpu) |= PSR_E_BIT; diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h index f80418ddeb60..8a37c8e89777 100644 --- a/arch/arm/include/asm/kvm_host.h +++ b/arch/arm/include/asm/kvm_host.h @@ -15,7 +15,6 @@ #include <asm/kvm_asm.h> #include <asm/kvm_mmio.h> #include <asm/fpstate.h> -#include <asm/smp_plat.h> #include <kvm/arm_arch_timer.h> #define __KVM_HAVE_ARCH_INTC_INITIALIZED @@ -147,11 +146,10 @@ struct kvm_host_data { typedef struct kvm_host_data kvm_host_data_t; -static inline void kvm_init_host_cpu_context(struct kvm_cpu_context *cpu_ctxt, - int cpu) +static inline void kvm_init_host_cpu_context(struct kvm_cpu_context *cpu_ctxt) { /* The host's MPIDR is immutable, so let's set it up at boot time */ - cpu_ctxt->cp15[c0_MPIDR] = cpu_logical_map(cpu); + cpu_ctxt->cp15[c0_MPIDR] = read_cpuid_mpidr(); } struct vcpu_reset_state { @@ -362,7 +360,11 @@ static inline void kvm_vcpu_pmu_restore_host(struct kvm_vcpu *vcpu) {} static inline void kvm_arm_vhe_guest_enter(void) {} static inline void kvm_arm_vhe_guest_exit(void) {} -static inline bool kvm_arm_harden_branch_predictor(void) +#define KVM_BP_HARDEN_UNKNOWN -1 +#define KVM_BP_HARDEN_WA_NEEDED 0 +#define KVM_BP_HARDEN_NOT_REQUIRED 1 + +static inline int kvm_arm_harden_branch_predictor(void) { switch(read_cpuid_part()) { #ifdef CONFIG_HARDEN_BRANCH_PREDICTOR @@ -370,10 +372,12 @@ static inline bool kvm_arm_harden_branch_predictor(void) case ARM_CPU_PART_CORTEX_A12: case ARM_CPU_PART_CORTEX_A15: case ARM_CPU_PART_CORTEX_A17: - return true; + return KVM_BP_HARDEN_WA_NEEDED; #endif + case ARM_CPU_PART_CORTEX_A7: + return KVM_BP_HARDEN_NOT_REQUIRED; default: - return false; + return KVM_BP_HARDEN_UNKNOWN; } } diff --git a/arch/arm/include/asm/kvm_hyp.h b/arch/arm/include/asm/kvm_hyp.h index 71ac1c8d101c..40e9034db601 100644 --- a/arch/arm/include/asm/kvm_hyp.h +++ b/arch/arm/include/asm/kvm_hyp.h @@ -82,13 +82,14 @@ #define VFP_FPEXC __ACCESS_VFP(FPEXC) /* AArch64 compatibility macros, only for the timer so far */ -#define read_sysreg_el0(r) read_sysreg(r##_el0) -#define write_sysreg_el0(v, r) write_sysreg(v, r##_el0) +#define read_sysreg_el0(r) read_sysreg(r##_EL0) +#define write_sysreg_el0(v, r) write_sysreg(v, r##_EL0) + +#define SYS_CNTP_CTL_EL0 CNTP_CTL +#define SYS_CNTP_CVAL_EL0 CNTP_CVAL +#define SYS_CNTV_CTL_EL0 CNTV_CTL +#define SYS_CNTV_CVAL_EL0 CNTV_CVAL -#define cntp_ctl_el0 CNTP_CTL -#define cntp_cval_el0 CNTP_CVAL -#define cntv_ctl_el0 CNTV_CTL -#define cntv_cval_el0 CNTV_CVAL #define cntvoff_el2 CNTVOFF #define cnthctl_el2 CNTHCTL diff --git a/arch/arm/include/asm/pgalloc.h b/arch/arm/include/asm/pgalloc.h index c038cff6fdd3..a2a68b751971 100644 --- a/arch/arm/include/asm/pgalloc.h +++ b/arch/arm/include/asm/pgalloc.h @@ -54,8 +54,6 @@ static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd) extern pgd_t *pgd_alloc(struct mm_struct *mm); extern void pgd_free(struct mm_struct *mm, pgd_t *pgd); -#define PGALLOC_GFP (GFP_KERNEL | __GFP_ZERO) - static inline void clean_pte_table(pte_t *pte) { clean_dcache_area(pte + PTE_HWTABLE_PTRS, PTE_HWTABLE_SIZE); @@ -77,54 +75,41 @@ static inline void clean_pte_table(pte_t *pte) * | h/w pt 1 | * +------------+ */ + +#define __HAVE_ARCH_PTE_ALLOC_ONE_KERNEL +#define __HAVE_ARCH_PTE_ALLOC_ONE +#include <asm-generic/pgalloc.h> + static inline pte_t * pte_alloc_one_kernel(struct mm_struct *mm) { - pte_t *pte; + pte_t *pte = __pte_alloc_one_kernel(mm); - pte = (pte_t *)__get_free_page(PGALLOC_GFP); if (pte) clean_pte_table(pte); return pte; } +#ifdef CONFIG_HIGHPTE +#define PGTABLE_HIGHMEM __GFP_HIGHMEM +#else +#define PGTABLE_HIGHMEM 0 +#endif + static inline pgtable_t pte_alloc_one(struct mm_struct *mm) { struct page *pte; -#ifdef CONFIG_HIGHPTE - pte = alloc_pages(PGALLOC_GFP | __GFP_HIGHMEM, 0); -#else - pte = alloc_pages(PGALLOC_GFP, 0); -#endif + pte = __pte_alloc_one(mm, GFP_PGTABLE_USER | PGTABLE_HIGHMEM); if (!pte) return NULL; if (!PageHighMem(pte)) clean_pte_table(page_address(pte)); - if (!pgtable_page_ctor(pte)) { - __free_page(pte); - return NULL; - } return pte; } -/* - * Free one PTE table. - */ -static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) -{ - if (pte) - free_page((unsigned long)pte); -} - -static inline void pte_free(struct mm_struct *mm, pgtable_t pte) -{ - pgtable_page_dtor(pte); - __free_page(pte); -} - static inline void __pmd_populate(pmd_t *pmdp, phys_addr_t pte, pmdval_t prot) { diff --git a/arch/arm/include/asm/ptdump.h b/arch/arm/include/asm/ptdump.h index 3ebf9718288d..0c2d3d0d4cc6 100644 --- a/arch/arm/include/asm/ptdump.h +++ b/arch/arm/include/asm/ptdump.h @@ -21,13 +21,10 @@ struct ptdump_info { void ptdump_walk_pgd(struct seq_file *s, struct ptdump_info *info); #ifdef CONFIG_ARM_PTDUMP_DEBUGFS -int ptdump_debugfs_register(struct ptdump_info *info, const char *name); +void ptdump_debugfs_register(struct ptdump_info *info, const char *name); #else -static inline int ptdump_debugfs_register(struct ptdump_info *info, - const char *name) -{ - return 0; -} +static inline void ptdump_debugfs_register(struct ptdump_info *info, + const char *name) { } #endif /* CONFIG_ARM_PTDUMP_DEBUGFS */ void ptdump_check_wx(void); diff --git a/arch/arm/include/uapi/asm/kvm.h b/arch/arm/include/uapi/asm/kvm.h index 4602464ebdfb..a4217c1a5d01 100644 --- a/arch/arm/include/uapi/asm/kvm.h +++ b/arch/arm/include/uapi/asm/kvm.h @@ -214,6 +214,18 @@ struct kvm_vcpu_events { #define KVM_REG_ARM_FW_REG(r) (KVM_REG_ARM | KVM_REG_SIZE_U64 | \ KVM_REG_ARM_FW | ((r) & 0xffff)) #define KVM_REG_ARM_PSCI_VERSION KVM_REG_ARM_FW_REG(0) +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1 KVM_REG_ARM_FW_REG(1) + /* Higher values mean better protection. */ +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_AVAIL 0 +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_AVAIL 1 +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_REQUIRED 2 +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2 KVM_REG_ARM_FW_REG(2) + /* Higher values mean better protection. */ +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL 0 +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_UNKNOWN 1 +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL 2 +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_REQUIRED 3 +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED (1U << 4) /* Device Control API: ARM VGIC */ #define KVM_DEV_ARM_VGIC_GRP_ADDR 0 diff --git a/arch/arm/kernel/efi.c b/arch/arm/kernel/efi.c index ed005870671a..e57dbcc89123 100644 --- a/arch/arm/kernel/efi.c +++ b/arch/arm/kernel/efi.c @@ -8,8 +8,7 @@ #include <asm/mach/map.h> #include <asm/mmu_context.h> -static int __init set_permissions(pte_t *ptep, pgtable_t token, - unsigned long addr, void *data) +static int __init set_permissions(pte_t *ptep, unsigned long addr, void *data) { efi_memory_desc_t *md = data; pte_t pte = *ptep; diff --git a/arch/arm/mach-omap1/clock.c b/arch/arm/mach-omap1/clock.c index 406fd2a9a88f..bd5be82101f3 100644 --- a/arch/arm/mach-omap1/clock.c +++ b/arch/arm/mach-omap1/clock.c @@ -987,84 +987,44 @@ static int debug_clock_show(struct seq_file *s, void *unused) DEFINE_SHOW_ATTRIBUTE(debug_clock); -static int clk_debugfs_register_one(struct clk *c) +static void clk_debugfs_register_one(struct clk *c) { - int err; struct dentry *d; struct clk *pa = c->parent; d = debugfs_create_dir(c->name, pa ? pa->dent : clk_debugfs_root); - if (!d) - return -ENOMEM; c->dent = d; - d = debugfs_create_u8("usecount", S_IRUGO, c->dent, &c->usecount); - if (!d) { - err = -ENOMEM; - goto err_out; - } - d = debugfs_create_ulong("rate", S_IRUGO, c->dent, &c->rate); - if (!d) { - err = -ENOMEM; - goto err_out; - } - d = debugfs_create_x8("flags", S_IRUGO, c->dent, &c->flags); - if (!d) { - err = -ENOMEM; - goto err_out; - } - return 0; - -err_out: - debugfs_remove_recursive(c->dent); - return err; + debugfs_create_u8("usecount", S_IRUGO, c->dent, &c->usecount); + debugfs_create_ulong("rate", S_IRUGO, c->dent, &c->rate); + debugfs_create_x8("flags", S_IRUGO, c->dent, &c->flags); } -static int clk_debugfs_register(struct clk *c) +static void clk_debugfs_register(struct clk *c) { - int err; struct clk *pa = c->parent; - if (pa && !pa->dent) { - err = clk_debugfs_register(pa); - if (err) - return err; - } + if (pa && !pa->dent) + clk_debugfs_register(pa); - if (!c->dent) { - err = clk_debugfs_register_one(c); - if (err) - return err; - } - return 0; + if (!c->dent) + clk_debugfs_register_one(c); } static int __init clk_debugfs_init(void) { struct clk *c; struct dentry *d; - int err; d = debugfs_create_dir("clock", NULL); - if (!d) - return -ENOMEM; clk_debugfs_root = d; - list_for_each_entry(c, &clocks, node) { - err = clk_debugfs_register(c); - if (err) - goto err_out; - } + list_for_each_entry(c, &clocks, node) + clk_debugfs_register(c); - d = debugfs_create_file("summary", S_IRUGO, - d, NULL, &debug_clock_fops); - if (!d) - return -ENOMEM; + debugfs_create_file("summary", S_IRUGO, d, NULL, &debug_clock_fops); return 0; -err_out: - debugfs_remove_recursive(clk_debugfs_root); - return err; } late_initcall(clk_debugfs_init); diff --git a/arch/arm/mach-omap1/pm.c b/arch/arm/mach-omap1/pm.c index 998075d3ef86..d068958d6f8a 100644 --- a/arch/arm/mach-omap1/pm.c +++ b/arch/arm/mach-omap1/pm.c @@ -539,11 +539,8 @@ static void omap_pm_init_debugfs(void) struct dentry *d; d = debugfs_create_dir("pm_debug", NULL); - if (!d) - return; - - (void) debugfs_create_file("omap_pm", S_IWUSR | S_IRUGO, - d, NULL, &omap_pm_debug_fops); + debugfs_create_file("omap_pm", S_IWUSR | S_IRUGO, d, NULL, + &omap_pm_debug_fops); } #endif /* CONFIG_DEBUG_FS */ diff --git a/arch/arm/mach-omap2/pm-debug.c b/arch/arm/mach-omap2/pm-debug.c index fe6ec9b580b9..fceb1e525d26 100644 --- a/arch/arm/mach-omap2/pm-debug.c +++ b/arch/arm/mach-omap2/pm-debug.c @@ -190,9 +190,8 @@ static int __init pwrdms_setup(struct powerdomain *pwrdm, void *dir) return 0; d = debugfs_create_dir(pwrdm->name, (struct dentry *)dir); - if (d) - (void) debugfs_create_file("suspend", S_IRUGO|S_IWUSR, d, - (void *)pwrdm, &pwrdm_suspend_fops); + debugfs_create_file("suspend", S_IRUGO|S_IWUSR, d, pwrdm, + &pwrdm_suspend_fops); return 0; } @@ -230,16 +229,14 @@ static int __init pm_dbg_init(void) return 0; d = debugfs_create_dir("pm_debug", NULL); - if (!d) - return -EINVAL; - (void) debugfs_create_file("count", 0444, d, NULL, &pm_dbg_counters_fops); - (void) debugfs_create_file("time", 0444, d, NULL, &pm_dbg_timers_fops); + debugfs_create_file("count", 0444, d, NULL, &pm_dbg_counters_fops); + debugfs_create_file("time", 0444, d, NULL, &pm_dbg_timers_fops); pwrdm_for_each(pwrdms_setup, (void *)d); - (void) debugfs_create_file("enable_off_mode", S_IRUGO | S_IWUSR, d, - &enable_off_mode, &pm_dbg_option_fops); + debugfs_create_file("enable_off_mode", S_IRUGO | S_IWUSR, d, + &enable_off_mode, &pm_dbg_option_fops); pm_dbg_init_done = 1; return 0; diff --git a/arch/arm/mm/dma-mapping-nommu.c b/arch/arm/mm/dma-mapping-nommu.c index 1aea01ba1262..52b82559d99b 100644 --- a/arch/arm/mm/dma-mapping-nommu.c +++ b/arch/arm/mm/dma-mapping-nommu.c @@ -35,18 +35,7 @@ static void *arm_nommu_dma_alloc(struct device *dev, size_t size, unsigned long attrs) { - void *ret; - - /* - * Try generic allocator first if we are advertised that - * consistency is not required. - */ - - if (attrs & DMA_ATTR_NON_CONSISTENT) - return dma_direct_alloc_pages(dev, size, dma_handle, gfp, - attrs); - - ret = dma_alloc_from_global_coherent(size, dma_handle); + void *ret = dma_alloc_from_global_coherent(size, dma_handle); /* * dma_alloc_from_global_coherent() may fail because: @@ -66,16 +55,9 @@ static void arm_nommu_dma_free(struct device *dev, size_t size, void *cpu_addr, dma_addr_t dma_addr, unsigned long attrs) { - if (attrs & DMA_ATTR_NON_CONSISTENT) { - dma_direct_free_pages(dev, size, cpu_addr, dma_addr, attrs); - } else { - int ret = dma_release_from_global_coherent(get_order(size), - cpu_addr); - - WARN_ON_ONCE(ret == 0); - } + int ret = dma_release_from_global_coherent(get_order(size), cpu_addr); - return; + WARN_ON_ONCE(ret == 0); } static int arm_nommu_dma_mmap(struct device *dev, struct vm_area_struct *vma, diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index 439bb6a59a04..4789c60a86e3 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -216,25 +216,7 @@ EXPORT_SYMBOL(arm_coherent_dma_ops); static int __dma_supported(struct device *dev, u64 mask, bool warn) { - unsigned long max_dma_pfn; - - /* - * If the mask allows for more memory than we can address, - * and we actually have that much memory, then we must - * indicate that DMA to this device is not supported. - */ - if (sizeof(mask) != sizeof(dma_addr_t) && - mask > (dma_addr_t)~0 && - dma_to_pfn(dev, ~0) < max_pfn - 1) { - if (warn) { - dev_warn(dev, "Coherent DMA mask %#llx is larger than dma_addr_t allows\n", - mask); - dev_warn(dev, "Driver did not use or check the return value from dma_set_coherent_mask()?\n"); - } - return 0; - } - - max_dma_pfn = min(max_pfn, arm_dma_pfn_limit); + unsigned long max_dma_pfn = min(max_pfn, arm_dma_pfn_limit); /* * Translate the device's DMA mask to a PFN limit. This @@ -493,8 +475,7 @@ void __init dma_contiguous_remap(void) } } -static int __dma_update_pte(pte_t *pte, pgtable_t token, unsigned long addr, - void *data) +static int __dma_update_pte(pte_t *pte, unsigned long addr, void *data) { struct page *page = virt_to_page(addr); pgprot_t prot = *(pgprot_t *)data; diff --git a/arch/arm/mm/dump.c b/arch/arm/mm/dump.c index 006d27ee4fc6..7d6291f23251 100644 --- a/arch/arm/mm/dump.c +++ b/arch/arm/mm/dump.c @@ -446,7 +446,7 @@ void ptdump_check_wx(void) static int ptdump_init(void) { ptdump_initialize(); - return ptdump_debugfs_register(&kernel_ptdump_info, - "kernel_page_tables"); + ptdump_debugfs_register(&kernel_ptdump_info, "kernel_page_tables"); + return 0; } __initcall(ptdump_init); diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index 1aa2586fa597..d9a0038774a6 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -729,7 +729,7 @@ static void __init *early_alloc(unsigned long sz) static void *__init late_alloc(unsigned long sz) { - void *ptr = (void *)__get_free_pages(PGALLOC_GFP, get_order(sz)); + void *ptr = (void *)__get_free_pages(GFP_PGTABLE_KERNEL, get_order(sz)); if (!ptr || !pgtable_page_ctor(virt_to_page(ptr))) BUG(); diff --git a/arch/arm/mm/pageattr.c b/arch/arm/mm/pageattr.c index 0f5faf30d9bf..d546efad7e97 100644 --- a/arch/arm/mm/pageattr.c +++ b/arch/arm/mm/pageattr.c @@ -14,8 +14,7 @@ struct page_change_data { pgprot_t clear_mask; }; -static int change_page_range(pte_t *ptep, pgtable_t token, unsigned long addr, - void *data) +static int change_page_range(pte_t *ptep, unsigned long addr, void *data) { struct page_change_data *cdata = data; pte_t pte = *ptep; diff --git a/arch/arm/mm/ptdump_debugfs.c b/arch/arm/mm/ptdump_debugfs.c index be8d87be4b93..598b636615a2 100644 --- a/arch/arm/mm/ptdump_debugfs.c +++ b/arch/arm/mm/ptdump_debugfs.c @@ -24,11 +24,7 @@ static const struct file_operations ptdump_fops = { .release = single_release, }; -int ptdump_debugfs_register(struct ptdump_info *info, const char *name) +void ptdump_debugfs_register(struct ptdump_info *info, const char *name) { - struct dentry *pe; - - pe = debugfs_create_file(name, 0400, NULL, info, &ptdump_fops); - return pe ? 0 : -ENOMEM; - + debugfs_create_file(name, 0400, NULL, info, &ptdump_fops); } diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index c085aec9459b..a36ff61321ce 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -143,6 +143,7 @@ config ARM64 select HAVE_DMA_CONTIGUOUS select HAVE_DYNAMIC_FTRACE select HAVE_EFFICIENT_UNALIGNED_ACCESS + select HAVE_FAST_GUP select HAVE_FTRACE_MCOUNT_RECORD select HAVE_FUNCTION_TRACER select HAVE_FUNCTION_GRAPH_TRACER @@ -267,9 +268,6 @@ config ZONE_DMA32 bool "Support DMA32 zone" if EXPERT default y -config HAVE_GENERIC_GUP - def_bool y - config ARCH_ENABLE_MEMORY_HOTPLUG def_bool y diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index e3d3fd0a4268..bb1f1dbb34e8 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -30,8 +30,6 @@ LDFLAGS_vmlinux += --fix-cortex-a53-843419 endif endif -KBUILD_DEFCONFIG := defconfig - # Check for binutils support for specific extensions lseinstr := $(call as-instr,.arch_extension lse,-DCONFIG_AS_LSE=1) diff --git a/arch/arm64/boot/dts/freescale/imx8mn-pinfunc.h b/arch/arm64/boot/dts/freescale/imx8mn-pinfunc.h new file mode 100644 index 000000000000..faf1e69e742b --- /dev/null +++ b/arch/arm64/boot/dts/freescale/imx8mn-pinfunc.h @@ -0,0 +1,646 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * Copyright 2018-2019 NXP + */ + +#ifndef __DTS_IMX8MN_PINFUNC_H +#define __DTS_IMX8MN_PINFUNC_H + +/* + * The pin function ID is a tuple of + * <mux_reg conf_reg input_reg mux_mode input_val> + */ + +#define MX8MN_IOMUXC_BOOT_MODE2_CCMSRCGPCMIX_BOOT_MODE2 0x020 0x25C 0x000 0x0 0x0 +#define MX8MN_IOMUXC_BOOT_MODE2_I2C1_SCL 0x020 0x25C 0x55C 0x1 0x3 +#define MX8MN_IOMUXC_BOOT_MODE3_CCMSRCGPCMIX_BOOT_MODE3 0x024 0x260 0x000 0x0 0x0 +#define MX8MN_IOMUXC_BOOT_MODE3_I2C1_SDA 0x024 0x260 0x56C 0x1 0x3 +#define MX8MN_IOMUXC_GPIO1_IO00_GPIO1_IO0 0x028 0x290 0x000 0x0 0x0 +#define MX8MN_IOMUXC_GPIO1_IO00_CCMSRCGPCMIX_ENET_PHY_REF_CLK_ROOT 0x028 0x290 0x000 0x1 0x0 +#define MX8MN_IOMUXC_GPIO1_IO00_ANAMIX_REF_CLK_32K 0x028 0x290 0x000 0x5 0x0 +#define MX8MN_IOMUXC_GPIO1_IO00_CCMSRCGPCMIX_EXT_CLK1 0x028 0x290 0x000 0x6 0x0 +#define MX8MN_IOMUXC_GPIO1_IO01_GPIO1_IO1 0x02C 0x294 0x000 0x0 0x0 +#define MX8MN_IOMUXC_GPIO1_IO01_PWM1_OUT 0x02C 0x294 0x000 0x1 0x0 +#define MX8MN_IOMUXC_GPIO1_IO01_ANAMIX_REF_CLK_24M 0x02C 0x294 0x000 0x5 0x0 +#define MX8MN_IOMUXC_GPIO1_IO01_CCMSRCGPCMIX_EXT_CLK2 0x02C 0x294 0x000 0x6 0x0 +#define MX8MN_IOMUXC_GPIO1_IO02_GPIO1_IO2 0x030 0x298 0x000 0x0 0x0 +#define MX8MN_IOMUXC_GPIO1_IO02_WDOG1_WDOG_B 0x030 0x298 0x000 0x1 0x0 +#define MX8MN_IOMUXC_GPIO1_IO02_WDOG1_WDOG_ANY 0x030 0x298 0x000 0x5 0x0 +#define MX8MN_IOMUXC_GPIO1_IO03_GPIO1_IO3 0x034 0x29C 0x000 0x0 0x0 +#define MX8MN_IOMUXC_GPIO1_IO03_USDHC1_VSELECT 0x034 0x29C 0x000 0x1 0x0 +#define MX8MN_IOMUXC_GPIO1_IO03_SDMA1_EXT_EVENT0 0x034 0x29C 0x000 0x5 0x0 +#define MX8MN_IOMUXC_GPIO1_IO03_ANAMIX_XTAL_OK 0x034 0x29C 0x000 0x6 0x0 +#define MX8MN_IOMUXC_GPIO1_IO04_GPIO1_IO4 0x038 0x2A0 0x000 0x0 0x0 +#define MX8MN_IOMUXC_GPIO1_IO04_USDHC2_VSELECT 0x038 0x2A0 0x000 0x1 0x0 +#define MX8MN_IOMUXC_GPIO1_IO04_SDMA1_EXT_EVENT1 0x038 0x2A0 0x000 0x5 0x0 +#define MX8MN_IOMUXC_GPIO1_IO04_ANAMIX_XTAL_OK_LV 0x038 0x2A0 0x000 0x6 0x0 +#define MX8MN_IOMUXC_GPIO1_IO05_GPIO1_IO5 0x03C 0x2A4 0x000 0x0 0x0 +#define MX8MN_IOMUXC_GPIO1_IO05_M4_NMI 0x03C 0x2A4 0x000 0x1 0x0 +#define MX8MN_IOMUXC_GPIO1_IO05_CCMSRCGPCMIX_PMIC_READY 0x03C 0x2A4 0x4BC 0x5 0x0 +#define MX8MN_IOMUXC_GPIO1_IO05_CCMSRCGPCMIX_INT_BOOT 0x03C 0x2A4 0x000 0x6 0x0 +#define MX8MN_IOMUXC_GPIO1_IO06_GPIO1_IO6 0x040 0x2A8 0x000 0x0 0x0 +#define MX8MN_IOMUXC_GPIO1_IO06_ENET1_MDC 0x040 0x2A8 0x000 0x1 0x0 +#define MX8MN_IOMUXC_GPIO1_IO06_USDHC1_CD_B 0x040 0x2A8 0x000 0x5 0x0 +#define MX8MN_IOMUXC_GPIO1_IO06_CCMSRCGPCMIX_EXT_CLK3 0x040 0x2A8 0x000 0x6 0x0 +#define MX8MN_IOMUXC_GPIO1_IO07_GPIO1_IO7 0x044 0x2AC 0x000 0x0 0x0 +#define MX8MN_IOMUXC_GPIO1_IO07_ENET1_MDIO 0x044 0x2AC 0x4C0 0x1 0x0 +#define MX8MN_IOMUXC_GPIO1_IO07_USDHC1_WP 0x044 0x2AC 0x000 0x5 0x0 +#define MX8MN_IOMUXC_GPIO1_IO07_CCMSRCGPCMIX_EXT_CLK4 0x044 0x2AC 0x000 0x6 0x0 +#define MX8MN_IOMUXC_GPIO1_IO08_GPIO1_IO8 0x048 0x2B0 0x000 0x0 0x0 +#define MX8MN_IOMUXC_GPIO1_IO08_ENET1_1588_EVENT0_IN 0x048 0x2B0 0x000 0x1 0x0 +#define MX8MN_IOMUXC_GPIO1_IO08_PWM1_OUT 0x048 0x2B0 0x000 0x2 0x0 +#define MX8MN_IOMUXC_GPIO1_IO08_USDHC2_RESET_B 0x048 0x2B0 0x000 0x5 0x0 +#define MX8MN_IOMUXC_GPIO1_IO08_CCMSRCGPCMIX_WAIT 0x048 0x2B0 0x000 0x6 0x0 +#define MX8MN_IOMUXC_GPIO1_IO09_GPIO1_IO9 0x04C 0x2B4 0x000 0x0 0x0 +#define MX8MN_IOMUXC_GPIO1_IO09_ENET1_1588_EVENT0_OUT 0x04C 0x2B4 0x000 0x1 0x0 +#define MX8MN_IOMUXC_GPIO1_IO09_PWM2_OUT 0x04C 0x2B4 0x000 0x2 0x0 +#define MX8MN_IOMUXC_GPIO1_IO09_USDHC3_RESET_B 0x04C 0x2B4 0x000 0x4 0x0 +#define MX8MN_IOMUXC_GPIO1_IO09_SDMA2_EXT_EVENT0 0x04C 0x2B4 0x000 0x5 0x0 +#define MX8MN_IOMUXC_GPIO1_IO09_CCMSRCGPCMIX_STOP 0x04C 0x2B4 0x000 0x6 0x0 +#define MX8MN_IOMUXC_GPIO1_IO10_GPIO1_IO10 0x050 0x2B8 0x000 0x0 0x0 +#define MX8MN_IOMUXC_GPIO1_IO10_USB1_OTG_ID 0x050 0x2B8 0x000 0x1 0x0 +#define MX8MN_IOMUXC_GPIO1_IO10_PWM3_OUT 0x050 0x2B8 0x000 0x2 0x0 +#define MX8MN_IOMUXC_GPIO1_IO11_GPIO1_IO11 0x054 0x2BC 0x000 0x0 0x0 +#define MX8MN_IOMUXC_GPIO1_IO11_PWM2_OUT 0x054 0x2BC 0x000 0x1 0x0 +#define MX8MN_IOMUXC_GPIO1_IO11_USDHC3_VSELECT 0x054 0x2BC 0x000 0x4 0x0 +#define MX8MN_IOMUXC_GPIO1_IO11_CCMSRCGPCMIX_PMIC_READY 0x054 0x2BC 0x4BC 0x5 0x1 +#define MX8MN_IOMUXC_GPIO1_IO11_CCMSRCGPCMIX_OUT0 0x054 0x2BC 0x000 0x6 0x0 +#define MX8MN_IOMUXC_GPIO1_IO12_GPIO1_IO12 0x058 0x2C0 0x000 0x0 0x0 +#define MX8MN_IOMUXC_GPIO1_IO12_USB1_OTG_PWR 0x058 0x2C0 0x000 0x1 0x0 +#define MX8MN_IOMUXC_GPIO1_IO12_SDMA2_EXT_EVENT1 0x058 0x2C0 0x000 0x5 0x0 +#define MX8MN_IOMUXC_GPIO1_IO12_CCMSRCGPCMIX_OUT1 0x058 0x2C0 0x000 0x6 0x0 +#define MX8MN_IOMUXC_GPIO1_IO13_GPIO1_IO13 0x05C 0x2C4 0x000 0x0 0x0 +#define MX8MN_IOMUXC_GPIO1_IO13_USB1_OTG_OC 0x05C 0x2C4 0x000 0x1 0x0 +#define MX8MN_IOMUXC_GPIO1_IO13_PWM2_OUT 0x05C 0x2C4 0x000 0x5 0x0 +#define MX8MN_IOMUXC_GPIO1_IO13_CCMSRCGPCMIX_OUT2 0x05C 0x2C4 0x000 0x6 0x0 +#define MX8MN_IOMUXC_GPIO1_IO14_GPIO1_IO14 0x060 0x2C8 0x000 0x0 0x0 +#define MX8MN_IOMUXC_GPIO1_IO14_USDHC3_CD_B 0x060 0x2C8 0x598 0x4 0x2 +#define MX8MN_IOMUXC_GPIO1_IO14_PWM3_OUT 0x060 0x2C8 0x000 0x5 0x0 +#define MX8MN_IOMUXC_GPIO1_IO14_CCMSRCGPCMIX_CLKO1 0x060 0x2C8 0x000 0x6 0x0 +#define MX8MN_IOMUXC_GPIO1_IO15_GPIO1_IO15 0x064 0x2CC 0x000 0x0 0x0 +#define MX8MN_IOMUXC_GPIO1_IO15_USDHC3_WP 0x064 0x2CC 0x5B8 0x4 0x2 +#define MX8MN_IOMUXC_GPIO1_IO15_PWM4_OUT 0x064 0x2CC 0x000 0x5 0x0 +#define MX8MN_IOMUXC_GPIO1_IO15_CCMSRCGPCMIX_CLKO2 0x064 0x2CC 0x000 0x6 0x0 +#define MX8MN_IOMUXC_ENET_MDC_ENET1_MDC 0x068 0x2D0 0x000 0x0 0x0 +#define MX8MN_IOMUXC_ENET_MDC_SAI6_TX_DATA0 0x068 0x2D0 0x000 0x2 0x0 +#define MX8MN_IOMUXC_ENET_MDC_PDM_BIT_STREAM3 0x068 0x2D0 0x540 0x3 0x1 +#define MX8MN_IOMUXC_ENET_MDC_SPDIF1_OUT 0x068 0x2D0 0x000 0x4 0x0 +#define MX8MN_IOMUXC_ENET_MDC_GPIO1_IO16 0x068 0x2D0 0x000 0x5 0x0 +#define MX8MN_IOMUXC_ENET_MDC_USDHC3_STROBE 0x068 0x2D0 0x59C 0x6 0x1 +#define MX8MN_IOMUXC_ENET_MDIO_ENET1_MDIO 0x06C 0x2D4 0x4C0 0x0 0x1 +#define MX8MN_IOMUXC_ENET_MDIO_SAI6_TX_SYNC 0x06C 0x2D4 0x000 0x2 0x0 +#define MX8MN_IOMUXC_ENET_MDIO_PDM_BIT_STREAM2 0x06C 0x2D4 0x53C 0x3 0x1 +#define MX8MN_IOMUXC_ENET_MDIO_SPDIF1_IN 0x06C 0x2D4 0x5CC 0x4 0x1 +#define MX8MN_IOMUXC_ENET_MDIO_GPIO1_IO17 0x06C 0x2D4 0x000 0x5 0x0 +#define MX8MN_IOMUXC_ENET_MDIO_USDHC3_DATA5 0x06C 0x2D4 0x550 0x6 0x1 +#define MX8MN_IOMUXC_ENET_TD3_ENET1_RGMII_TD3 0x070 0x2D8 0x000 0x0 0x0 +#define MX8MN_IOMUXC_ENET_TD3_SAI6_TX_BCLK 0x070 0x2D8 0x000 0x2 0x0 +#define MX8MN_IOMUXC_ENET_TD3_PDM_BIT_STREAM1 0x070 0x2D8 0x538 0x3 0x1 +#define MX8MN_IOMUXC_ENET_TD3_SPDIF1_EXT_CLK 0x070 0x2D8 0x568 0x4 0x1 +#define MX8MN_IOMUXC_ENET_TD3_GPIO1_IO18 0x070 0x2D8 0x000 0x5 0x0 +#define MX8MN_IOMUXC_ENET_TD3_USDHC3_DATA6 0x070 0x2D8 0x584 0x6 0x1 +#define MX8MN_IOMUXC_ENET_TD2_ENET1_RGMII_TD2 0x074 0x2DC 0x000 0x0 0x0 +#define MX8MN_IOMUXC_ENET_TD2_ENET1_TX_CLK 0x074 0x2DC 0x5A4 0x1 0x0 +#define MX8MN_IOMUXC_ENET_TD2_CCMSRCGPCMIX_ENET_REF_CLK_ROOT 0x074 0x2DC 0x5A4 0x1 0x0 +#define MX8MN_IOMUXC_ENET_TD2_SAI6_RX_DATA0 0x074 0x2DC 0x000 0x2 0x0 +#define MX8MN_IOMUXC_ENET_TD2_PDM_BIT_STREAM3 0x074 0x2DC 0x540 0x3 0x2 +#define MX8MN_IOMUXC_ENET_TD2_GPIO1_IO19 0x074 0x2DC 0x000 0x5 0x0 +#define MX8MN_IOMUXC_ENET_TD2_USDHC3_DATA7 0x074 0x2DC 0x54C 0x6 0x1 +#define MX8MN_IOMUXC_ENET_TD1_ENET1_RGMII_TD1 0x078 0x2E0 0x000 0x0 0x0 +#define MX8MN_IOMUXC_ENET_TD1_SAI6_RX_SYNC 0x078 0x2E0 0x000 0x2 0x0 +#define MX8MN_IOMUXC_ENET_TD1_PDM_BIT_STREAM2 0x078 0x2E0 0x53C 0x3 0x2 +#define MX8MN_IOMUXC_ENET_TD1_GPIO1_IO20 0x078 0x2E0 0x000 0x5 0x0 +#define MX8MN_IOMUXC_ENET_TD1_USDHC3_CD_B 0x078 0x2E0 0x598 0x6 0x3 +#define MX8MN_IOMUXC_ENET_TD0_ENET1_RGMII_TD0 0x07C 0x2E4 0x000 0x0 0x0 +#define MX8MN_IOMUXC_ENET_TD0_SAI6_RX_BCLK 0x07C 0x2E4 0x000 0x2 0x0 +#define MX8MN_IOMUXC_ENET_TD0_PDM_BIT_STREAM1 0x07C 0x2E4 0x538 0x3 0x2 +#define MX8MN_IOMUXC_ENET_TD0_GPIO1_IO21 0x07C 0x2E4 0x000 0x5 0x0 +#define MX8MN_IOMUXC_ENET_TD0_USDHC3_WP 0x07C 0x2E4 0x5B8 0x6 0x3 +#define MX8MN_IOMUXC_ENET_TX_CTL_ENET1_RGMII_TX_CTL 0x080 0x2E8 0x000 0x0 0x0 +#define MX8MN_IOMUXC_ENET_TX_CTL_SAI6_MCLK 0x080 0x2E8 0x000 0x2 0x0 +#define MX8MN_IOMUXC_ENET_TX_CTL_GPIO1_IO22 0x080 0x2E8 0x000 0x5 0x0 +#define MX8MN_IOMUXC_ENET_TX_CTL_USDHC3_DATA0 0x080 0x2E8 0x5B4 0x6 0x1 +#define MX8MN_IOMUXC_ENET_TXC_ENET1_RGMII_TXC 0x084 0x2EC 0x000 0x0 0x0 +#define MX8MN_IOMUXC_ENET_TXC_ENET1_TX_ER 0x084 0x2EC 0x000 0x1 0x0 +#define MX8MN_IOMUXC_ENET_TXC_SAI7_TX_DATA0 0x084 0x2EC 0x000 0x2 0x0 +#define MX8MN_IOMUXC_ENET_TXC_GPIO1_IO23 0x084 0x2EC 0x000 0x5 0x0 +#define MX8MN_IOMUXC_ENET_TXC_USDHC3_DATA1 0x084 0x2EC 0x5B0 0x6 0x1 +#define MX8MN_IOMUXC_ENET_RX_CTL_ENET1_RGMII_RX_CTL 0x088 0x2F0 0x574 0x0 0x0 +#define MX8MN_IOMUXC_ENET_RX_CTL_SAI7_TX_SYNC 0x088 0x2F0 0x000 0x2 0x0 +#define MX8MN_IOMUXC_ENET_RX_CTL_PDM_BIT_STREAM3 0x088 0x2F0 0x540 0x3 0x3 +#define MX8MN_IOMUXC_ENET_RX_CTL_GPIO1_IO24 0x088 0x2F0 0x000 0x5 0x0 +#define MX8MN_IOMUXC_ENET_RX_CTL_USDHC3_DATA2 0x088 0x2F0 0x5E4 0x6 0x1 +#define MX8MN_IOMUXC_ENET_RXC_ENET1_RGMII_RXC 0x08C 0x2F4 0x000 0x0 0x0 +#define MX8MN_IOMUXC_ENET_RXC_ENET1_RX_ER 0x08C 0x2F4 0x5C8 0x1 0x0 +#define MX8MN_IOMUXC_ENET_RXC_SAI7_TX_BCLK 0x08C 0x2F4 0x000 0x2 0x0 +#define MX8MN_IOMUXC_ENET_RXC_PDM_BIT_STREAM2 0x08C 0x2F4 0x53C 0x3 0x3 +#define MX8MN_IOMUXC_ENET_RXC_GPIO1_IO25 0x08C 0x2F4 0x000 0x5 0x0 +#define MX8MN_IOMUXC_ENET_RXC_USDHC3_DATA3 0x08C 0x2F4 0x5E0 0x6 0x1 +#define MX8MN_IOMUXC_ENET_RD0_ENET1_RGMII_RD0 0x090 0x2F8 0x57C 0x0 0x0 +#define MX8MN_IOMUXC_ENET_RD0_SAI7_RX_DATA0 0x090 0x2F8 0x000 0x2 0x0 +#define MX8MN_IOMUXC_ENET_RD0_PDM_BIT_STREAM1 0x090 0x2F8 0x538 0x3 0x3 +#define MX8MN_IOMUXC_ENET_RD0_GPIO1_IO26 0x090 0x2F8 0x000 0x5 0x0 +#define MX8MN_IOMUXC_ENET_RD0_USDHC3_DATA4 0x090 0x2F8 0x558 0x6 0x1 +#define MX8MN_IOMUXC_ENET_RD1_ENET1_RGMII_RD1 0x094 0x2FC 0x554 0x0 0x0 +#define MX8MN_IOMUXC_ENET_RD1_SAI7_RX_SYNC 0x094 0x2FC 0x000 0x2 0x0 +#define MX8MN_IOMUXC_ENET_RD1_PDM_BIT_STREAM0 0x094 0x2FC 0x534 0x3 0x1 +#define MX8MN_IOMUXC_ENET_RD1_GPIO1_IO27 0x094 0x2FC 0x000 0x5 0x0 +#define MX8MN_IOMUXC_ENET_RD1_USDHC3_RESET_B 0x094 0x2FC 0x000 0x6 0x0 +#define MX8MN_IOMUXC_ENET_RD2_ENET1_RGMII_RD2 0x098 0x300 0x000 0x0 0x0 +#define MX8MN_IOMUXC_ENET_RD2_SAI7_RX_BCLK 0x098 0x300 0x000 0x2 0x0 +#define MX8MN_IOMUXC_ENET_RD2_PDM_CLK 0x098 0x300 0x000 0x3 0x0 +#define MX8MN_IOMUXC_ENET_RD2_GPIO1_IO28 0x098 0x300 0x000 0x5 0x0 +#define MX8MN_IOMUXC_ENET_RD2_USDHC3_CLK 0x098 0x300 0x5A0 0x6 0x1 +#define MX8MN_IOMUXC_ENET_RD3_ENET1_RGMII_RD3 0x09C 0x304 0x000 0x0 0x0 +#define MX8MN_IOMUXC_ENET_RD3_SAI7_MCLK 0x09C 0x304 0x000 0x2 0x0 +#define MX8MN_IOMUXC_ENET_RD3_SPDIF1_IN 0x09C 0x304 0x5CC 0x3 0x5 +#define MX8MN_IOMUXC_ENET_RD3_GPIO1_IO29 0x09C 0x304 0x000 0x5 0x0 +#define MX8MN_IOMUXC_ENET_RD3_USDHC3_CMD 0x09C 0x304 0x5DC 0x6 0x1 +#define MX8MN_IOMUXC_SD1_CLK_USDHC1_CLK 0x0A0 0x308 0x000 0x0 0x0 +#define MX8MN_IOMUXC_SD1_CLK_ENET1_MDC 0x0A0 0x308 0x000 0x1 0x0 +#define MX8MN_IOMUXC_SD1_CLK_UART1_DCE_TX 0x0A0 0x308 0x000 0x4 0x0 +#define MX8MN_IOMUXC_SD1_CLK_UART1_DTE_RX 0x0A0 0x308 0x4F4 0x4 0x4 +#define MX8MN_IOMUXC_SD1_CLK_GPIO2_IO0 0x0A0 0x308 0x000 0x5 0x0 +#define MX8MN_IOMUXC_SD1_CMD_USDHC1_CMD 0x0A4 0x30C 0x000 0x0 0x0 +#define MX8MN_IOMUXC_SD1_CMD_ENET1_MDIO 0x0A4 0x30C 0x4C0 0x1 0x3 +#define MX8MN_IOMUXC_SD1_CMD_UART1_DCE_RX 0x0A4 0x30C 0x4F4 0x4 0x5 +#define MX8MN_IOMUXC_SD1_CMD_UART1_DTE_TX 0x0A4 0x30C 0x000 0x4 0x0 +#define MX8MN_IOMUXC_SD1_CMD_GPIO2_IO1 0x0A4 0x30C 0x000 0x5 0x0 +#define MX8MN_IOMUXC_SD1_DATA0_USDHC1_DATA0 0x0A8 0x310 0x000 0x0 0x0 +#define MX8MN_IOMUXC_SD1_DATA0_ENET1_RGMII_TD1 0x0A8 0x310 0x000 0x1 0x0 +#define MX8MN_IOMUXC_SD1_DATA0_UART1_DCE_RTS_B 0x0A8 0x310 0x4F0 0x4 0x4 +#define MX8MN_IOMUXC_SD1_DATA0_UART1_DTE_CTS_B 0x0A8 0x310 0x000 0x4 0x0 +#define MX8MN_IOMUXC_SD1_DATA0_GPIO2_IO2 0x0A8 0x310 0x000 0x5 0x0 +#define MX8MN_IOMUXC_SD1_DATA1_USDHC1_DATA1 0x0AC 0x314 0x000 0x0 0x0 +#define MX8MN_IOMUXC_SD1_DATA1_ENET1_RGMII_TD0 0x0AC 0x314 0x000 0x1 0x0 +#define MX8MN_IOMUXC_SD1_DATA1_UART1_DCE_CTS_B 0x0AC 0x314 0x000 0x4 0x0 +#define MX8MN_IOMUXC_SD1_DATA1_UART1_DTE_RTS_B 0x0AC 0x314 0x4F0 0x4 0x5 +#define MX8MN_IOMUXC_SD1_DATA1_GPIO2_IO3 0x0AC 0x314 0x000 0x5 0x0 +#define MX8MN_IOMUXC_SD1_DATA2_USDHC1_DATA2 0x0B0 0x318 0x000 0x0 0x0 +#define MX8MN_IOMUXC_SD1_DATA2_ENET1_RGMII_RD0 0x0B0 0x318 0x57C 0x1 0x1 +#define MX8MN_IOMUXC_SD1_DATA2_UART2_DCE_TX 0x0B0 0x318 0x000 0x4 0x0 +#define MX8MN_IOMUXC_SD1_DATA2_UART2_DTE_RX 0x0B0 0x318 0x4FC 0x4 0x4 +#define MX8MN_IOMUXC_SD1_DATA2_GPIO2_IO4 0x0B0 0x318 0x000 0x5 0x0 +#define MX8MN_IOMUXC_SD1_DATA3_USDHC1_DATA3 0x0B4 0x31C 0x000 0x0 0x0 +#define MX8MN_IOMUXC_SD1_DATA3_ENET1_RGMII_RD1 0x0B4 0x31C 0x554 0x1 0x1 +#define MX8MN_IOMUXC_SD1_DATA3_UART2_DCE_RX 0x0B4 0x31C 0x4FC 0x4 0x5 +#define MX8MN_IOMUXC_SD1_DATA3_UART2_DTE_TX 0x0B4 0x31C 0x000 0x4 0x0 +#define MX8MN_IOMUXC_SD1_DATA3_GPIO2_IO5 0x0B4 0x31C 0x000 0x5 0x0 +#define MX8MN_IOMUXC_SD1_DATA4_USDHC1_DATA4 0x0B8 0x320 0x000 0x0 0x0 +#define MX8MN_IOMUXC_SD1_DATA4_ENET1_RGMII_TX_CTL 0x0B8 0x320 0x000 0x1 0x0 +#define MX8MN_IOMUXC_SD1_DATA4_I2C1_SCL 0x0B8 0x320 0x55C 0x3 0x1 +#define MX8MN_IOMUXC_SD1_DATA4_UART2_DCE_RTS_B 0x0B8 0x320 0x4F8 0x4 0x4 +#define MX8MN_IOMUXC_SD1_DATA4_UART2_DTE_CTS_B 0x0B8 0x320 0x000 0x4 0x0 +#define MX8MN_IOMUXC_SD1_DATA4_GPIO2_IO6 0x0B8 0x320 0x000 0x5 0x0 +#define MX8MN_IOMUXC_SD1_DATA5_USDHC1_DATA5 0x0BC 0x324 0x000 0x0 0x0 +#define MX8MN_IOMUXC_SD1_DATA5_ENET1_TX_ER 0x0BC 0x324 0x000 0x1 0x0 +#define MX8MN_IOMUXC_SD1_DATA5_I2C1_SDA 0x0BC 0x324 0x56C 0x3 0x1 +#define MX8MN_IOMUXC_SD1_DATA5_UART2_DCE_CTS_B 0x0BC 0x324 0x000 0x4 0x0 +#define MX8MN_IOMUXC_SD1_DATA5_UART2_DTE_RTS_B 0x0BC 0x324 0x4F8 0x4 0x5 +#define MX8MN_IOMUXC_SD1_DATA5_GPIO2_IO7 0x0BC 0x324 0x000 0x5 0x0 +#define MX8MN_IOMUXC_SD1_DATA6_USDHC1_DATA6 0x0C0 0x328 0x000 0x0 0x0 +#define MX8MN_IOMUXC_SD1_DATA6_ENET1_RGMII_RX_CTL 0x0C0 0x328 0x574 0x1 0x1 +#define MX8MN_IOMUXC_SD1_DATA6_I2C2_SCL 0x0C0 0x328 0x5D0 0x3 0x1 +#define MX8MN_IOMUXC_SD1_DATA6_UART3_DCE_TX 0x0C0 0x328 0x000 0x4 0x0 +#define MX8MN_IOMUXC_SD1_DATA6_UART3_DTE_RX 0x0C0 0x328 0x504 0x4 0x4 +#define MX8MN_IOMUXC_SD1_DATA6_GPIO2_IO8 0x0C0 0x328 0x000 0x5 0x0 +#define MX8MN_IOMUXC_SD1_DATA7_USDHC1_DATA7 0x0C4 0x32C 0x000 0x0 0x0 +#define MX8MN_IOMUXC_SD1_DATA7_ENET1_RX_ER 0x0C4 0x32C 0x5C8 0x1 0x1 +#define MX8MN_IOMUXC_SD1_DATA7_I2C2_SDA 0x0C4 0x32C 0x560 0x3 0x1 +#define MX8MN_IOMUXC_SD1_DATA7_UART3_DCE_RX 0x0C4 0x32C 0x504 0x4 0x5 +#define MX8MN_IOMUXC_SD1_DATA7_UART3_DTE_TX 0x0C4 0x32C 0x000 0x4 0x0 +#define MX8MN_IOMUXC_SD1_DATA7_GPIO2_IO9 0x0C4 0x32C 0x000 0x5 0x0 +#define MX8MN_IOMUXC_SD1_RESET_B_USDHC1_RESET_B 0x0C8 0x330 0x000 0x0 0x0 +#define MX8MN_IOMUXC_SD1_RESET_B_ENET1_TX_CLK 0x0C8 0x330 0x5A4 0x1 0x1 +#define MX8MN_IOMUXC_SD1_RESET_B_CCMSRCGPCMIX_ENET_REF_CLK_ROOT 0x0C8 0x330 0x5A4 0x1 0x0 +#define MX8MN_IOMUXC_SD1_RESET_B_I2C3_SCL 0x0C8 0x330 0x588 0x3 0x1 +#define MX8MN_IOMUXC_SD1_RESET_B_UART3_DCE_RTS_B 0x0C8 0x330 0x500 0x4 0x2 +#define MX8MN_IOMUXC_SD1_RESET_B_UART3_DTE_CTS_B 0x0C8 0x330 0x000 0x4 0x0 +#define MX8MN_IOMUXC_SD1_RESET_B_GPIO2_IO10 0x0C8 0x330 0x000 0x5 0x0 +#define MX8MN_IOMUXC_SD1_STROBE_USDHC1_STROBE 0x0CC 0x334 0x000 0x0 0x0 +#define MX8MN_IOMUXC_SD1_STROBE_I2C3_SDA 0x0CC 0x334 0x5BC 0x3 0x1 +#define MX8MN_IOMUXC_SD1_STROBE_UART3_DCE_CTS_B 0x0CC 0x334 0x000 0x4 0x0 +#define MX8MN_IOMUXC_SD1_STROBE_UART3_DTE_RTS_B 0x0CC 0x334 0x500 0x4 0x3 +#define MX8MN_IOMUXC_SD1_STROBE_GPIO2_IO11 0x0CC 0x334 0x000 0x5 0x0 +#define MX8MN_IOMUXC_SD2_CD_B_USDHC2_CD_B 0x0D0 0x338 0x000 0x0 0x0 +#define MX8MN_IOMUXC_SD2_CD_B_GPIO2_IO12 0x0D0 0x338 0x000 0x5 0x0 +#define MX8MN_IOMUXC_SD2_CD_B_CCMSRCGPCMIX_TESTER_ACK 0x0D0 0x338 0x000 0x6 0x0 +#define MX8MN_IOMUXC_SD2_CLK_USDHC2_CLK 0x0D4 0x33C 0x000 0x0 0x0 +#define MX8MN_IOMUXC_SD2_CLK_SAI5_RX_SYNC 0x0D4 0x33C 0x4E4 0x1 0x1 +#define MX8MN_IOMUXC_SD2_CLK_ECSPI2_SCLK 0x0D4 0x33C 0x580 0x2 0x1 +#define MX8MN_IOMUXC_SD2_CLK_UART4_DCE_RX 0x0D4 0x33C 0x50C 0x3 0x4 +#define MX8MN_IOMUXC_SD2_CLK_UART4_DTE_TX 0x0D4 0x33C 0x000 0x3 0x0 +#define MX8MN_IOMUXC_SD2_CLK_SAI5_MCLK 0x0D4 0x33C 0x594 0x4 0x1 +#define MX8MN_IOMUXC_SD2_CLK_GPIO2_IO13 0x0D4 0x33C 0x000 0x5 0x0 +#define MX8MN_IOMUXC_SD2_CLK_CCMSRCGPCMIX_OBSERVE0 0x0D4 0x33C 0x000 0x6 0x0 +#define MX8MN_IOMUXC_SD2_CMD_USDHC2_CMD 0x0D8 0x340 0x000 0x0 0x0 +#define MX8MN_IOMUXC_SD2_CMD_SAI5_RX_BCLK 0x0D8 0x340 0x4D0 0x1 0x1 +#define MX8MN_IOMUXC_SD2_CMD_ECSPI2_MOSI 0x0D8 0x340 0x590 0x2 0x1 +#define MX8MN_IOMUXC_SD2_CMD_UART4_DCE_TX 0x0D8 0x340 0x000 0x3 0x0 +#define MX8MN_IOMUXC_SD2_CMD_UART4_DTE_RX 0x0D8 0x340 0x50C 0x3 0x5 +#define MX8MN_IOMUXC_SD2_CMD_PDM_CLK 0x0D8 0x340 0x000 0x4 0x0 +#define MX8MN_IOMUXC_SD2_CMD_GPIO2_IO14 0x0D8 0x340 0x000 0x5 0x0 +#define MX8MN_IOMUXC_SD2_CMD_CCMSRCGPCMIX_OBSERVE1 0x0D8 0x340 0x000 0x6 0x0 +#define MX8MN_IOMUXC_SD2_DATA0_USDHC2_DATA0 0x0DC 0x344 0x000 0x0 0x0 +#define MX8MN_IOMUXC_SD2_DATA0_SAI5_RX_DATA0 0x0DC 0x344 0x4D4 0x1 0x1 +#define MX8MN_IOMUXC_SD2_DATA0_I2C4_SDA 0x0DC 0x344 0x58C 0x2 0x1 +#define MX8MN_IOMUXC_SD2_DATA0_UART2_DCE_RX 0x0DC 0x344 0x4FC 0x3 0x6 +#define MX8MN_IOMUXC_SD2_DATA0_UART2_DTE_TX 0x0DC 0x344 0x000 0x3 0x0 +#define MX8MN_IOMUXC_SD2_DATA0_PDM_BIT_STREAM0 0x0DC 0x344 0x534 0x4 0x2 +#define MX8MN_IOMUXC_SD2_DATA0_GPIO2_IO15 0x0DC 0x344 0x000 0x5 0x0 +#define MX8MN_IOMUXC_SD2_DATA0_CCMSRCGPCMIX_OBSERVE2 0x0DC 0x344 0x000 0x6 0x0 +#define MX8MN_IOMUXC_SD2_DATA1_USDHC2_DATA1 0x0E0 0x348 0x000 0x0 0x0 +#define MX8MN_IOMUXC_SD2_DATA1_SAI5_TX_SYNC 0x0E0 0x348 0x4EC 0x1 0x1 +#define MX8MN_IOMUXC_SD2_DATA1_I2C4_SCL 0x0E0 0x348 0x5D4 0x2 0x1 +#define MX8MN_IOMUXC_SD2_DATA1_UART2_DCE_TX 0x0E0 0x348 0x000 0x3 0x0 +#define MX8MN_IOMUXC_SD2_DATA1_UART2_DTE_RX 0x0E0 0x348 0x4FC 0x3 0x7 +#define MX8MN_IOMUXC_SD2_DATA1_PDM_BIT_STREAM1 0x0E0 0x348 0x538 0x4 0x4 +#define MX8MN_IOMUXC_SD2_DATA1_GPIO2_IO16 0x0E0 0x348 0x000 0x5 0x0 +#define MX8MN_IOMUXC_SD2_DATA1_CCMSRCGPCMIX_WAIT 0x0E0 0x348 0x000 0x6 0x0 +#define MX8MN_IOMUXC_SD2_DATA2_USDHC2_DATA2 0x0E4 0x34C 0x000 0x0 0x0 +#define MX8MN_IOMUXC_SD2_DATA2_SAI5_TX_BCLK 0x0E4 0x34C 0x4E8 0x1 0x1 +#define MX8MN_IOMUXC_SD2_DATA2_ECSPI2_SS0 0x0E4 0x34C 0x570 0x2 0x2 +#define MX8MN_IOMUXC_SD2_DATA2_SPDIF1_OUT 0x0E4 0x34C 0x000 0x3 0x0 +#define MX8MN_IOMUXC_SD2_DATA2_PDM_BIT_STREAM2 0x0E4 0x34C 0x53C 0x4 0x4 +#define MX8MN_IOMUXC_SD2_DATA2_GPIO2_IO17 0x0E4 0x34C 0x000 0x5 0x0 +#define MX8MN_IOMUXC_SD2_DATA2_CCMSRCGPCMIX_STOP 0x0E4 0x34C 0x000 0x6 0x0 +#define MX8MN_IOMUXC_SD2_DATA3_USDHC2_DATA3 0x0E8 0x350 0x000 0x0 0x0 +#define MX8MN_IOMUXC_SD2_DATA3_SAI5_TX_DATA0 0x0E8 0x350 0x000 0x1 0x0 +#define MX8MN_IOMUXC_SD2_DATA3_ECSPI2_MISO 0x0E8 0x350 0x578 0x2 0x1 +#define MX8MN_IOMUXC_SD2_DATA3_SPDIF1_IN 0x0E8 0x350 0x5CC 0x3 0x2 +#define MX8MN_IOMUXC_SD2_DATA3_PDM_BIT_STREAM3 0x0E8 0x350 0x540 0x4 0x4 +#define MX8MN_IOMUXC_SD2_DATA3_GPIO2_IO18 0x0E8 0x350 0x000 0x5 0x0 +#define MX8MN_IOMUXC_SD2_DATA3_CCMSRCGPCMIX_EARLY_RESET 0x0E8 0x350 0x000 0x6 0x0 +#define MX8MN_IOMUXC_SD2_RESET_B_USDHC2_RESET_B 0x0EC 0x354 0x000 0x0 0x0 +#define MX8MN_IOMUXC_SD2_RESET_B_GPIO2_IO19 0x0EC 0x354 0x000 0x5 0x0 +#define MX8MN_IOMUXC_SD2_RESET_B_CCMSRCGPCMIX_SYSTEM_RESET 0x0EC 0x354 0x000 0x6 0x0 +#define MX8MN_IOMUXC_SD2_WP_USDHC2_WP 0x0F0 0x358 0x000 0x0 0x0 +#define MX8MN_IOMUXC_SD2_WP_GPIO2_IO20 0x0F0 0x358 0x000 0x5 0x0 +#define MX8MN_IOMUXC_SD2_WP_CORESIGHT_EVENTI 0x0F0 0x358 0x000 0x6 0x0 +#define MX8MN_IOMUXC_NAND_ALE_RAWNAND_ALE 0x0F4 0x35C 0x000 0x0 0x0 +#define MX8MN_IOMUXC_NAND_ALE_QSPI_A_SCLK 0x0F4 0x35C 0x000 0x1 0x0 +#define MX8MN_IOMUXC_NAND_ALE_PDM_BIT_STREAM0 0x0F4 0x35C 0x534 0x3 0x3 +#define MX8MN_IOMUXC_NAND_ALE_UART3_DCE_RX 0x0F4 0x35C 0x504 0x4 0x6 +#define MX8MN_IOMUXC_NAND_ALE_UART3_DTE_TX 0x0F4 0x35C 0x000 0x4 0x0 +#define MX8MN_IOMUXC_NAND_ALE_GPIO3_IO0 0x0F4 0x35C 0x000 0x5 0x0 +#define MX8MN_IOMUXC_NAND_ALE_CORESIGHT_TRACE_CLK 0x0F4 0x35C 0x000 0x6 0x0 +#define MX8MN_IOMUXC_NAND_CE0_B_RAWNAND_CE0_B 0x0F8 0x360 0x000 0x0 0x0 +#define MX8MN_IOMUXC_NAND_CE0_B_QSPI_A_SS0_B 0x0F8 0x360 0x000 0x1 0x0 +#define MX8MN_IOMUXC_NAND_CE0_B_PDM_BIT_STREAM1 0x0F8 0x360 0x538 0x3 0x5 +#define MX8MN_IOMUXC_NAND_CE0_B_UART3_DCE_TX 0x0F8 0x360 0x000 0x4 0x0 +#define MX8MN_IOMUXC_NAND_CE0_B_UART3_DTE_RX 0x0F8 0x360 0x504 0x4 0x7 +#define MX8MN_IOMUXC_NAND_CE0_B_GPIO3_IO1 0x0F8 0x360 0x000 0x5 0x0 +#define MX8MN_IOMUXC_NAND_CE0_B_CORESIGHT_TRACE_CTL 0x0F8 0x360 0x000 0x6 0x0 +#define MX8MN_IOMUXC_NAND_CE1_B_RAWNAND_CE1_B 0x0FC 0x364 0x000 0x0 0x0 +#define MX8MN_IOMUXC_NAND_CE1_B_QSPI_A_SS1_B 0x0FC 0x364 0x000 0x1 0x0 +#define MX8MN_IOMUXC_NAND_CE1_B_USDHC3_STROBE 0x0FC 0x364 0x59C 0x2 0x0 +#define MX8MN_IOMUXC_NAND_CE1_B_PDM_BIT_STREAM0 0x0FC 0x364 0x534 0x3 0x4 +#define MX8MN_IOMUXC_NAND_CE1_B_I2C4_SCL 0x0FC 0x364 0x5D4 0x4 0x2 +#define MX8MN_IOMUXC_NAND_CE1_B_GPIO3_IO2 0x0FC 0x364 0x000 0x5 0x0 +#define MX8MN_IOMUXC_NAND_CE1_B_CORESIGHT_TRACE0 0x0FC 0x364 0x000 0x6 0x0 +#define MX8MN_IOMUXC_NAND_CE2_B_RAWNAND_CE2_B 0x100 0x368 0x000 0x0 0x0 +#define MX8MN_IOMUXC_NAND_CE2_B_QSPI_B_SS0_B 0x100 0x368 0x000 0x1 0x0 +#define MX8MN_IOMUXC_NAND_CE2_B_USDHC3_DATA5 0x100 0x368 0x550 0x2 0x0 +#define MX8MN_IOMUXC_NAND_CE2_B_PDM_BIT_STREAM1 0x100 0x368 0x538 0x3 0x6 +#define MX8MN_IOMUXC_NAND_CE2_B_I2C4_SDA 0x100 0x368 0x58C 0x4 0x2 +#define MX8MN_IOMUXC_NAND_CE2_B_GPIO3_IO3 0x100 0x368 0x000 0x5 0x0 +#define MX8MN_IOMUXC_NAND_CE2_B_CORESIGHT_TRACE1 0x100 0x368 0x000 0x6 0x0 +#define MX8MN_IOMUXC_NAND_CE3_B_RAWNAND_CE3_B 0x104 0x36C 0x000 0x0 0x0 +#define MX8MN_IOMUXC_NAND_CE3_B_QSPI_B_SS1_B 0x104 0x36C 0x000 0x1 0x0 +#define MX8MN_IOMUXC_NAND_CE3_B_USDHC3_DATA6 0x104 0x36C 0x584 0x2 0x0 +#define MX8MN_IOMUXC_NAND_CE3_B_PDM_BIT_STREAM2 0x104 0x36C 0x53C 0x3 0x5 +#define MX8MN_IOMUXC_NAND_CE3_B_I2C3_SDA 0x104 0x36C 0x5BC 0x4 0x2 +#define MX8MN_IOMUXC_NAND_CE3_B_GPIO3_IO4 0x104 0x36C 0x000 0x5 0x0 +#define MX8MN_IOMUXC_NAND_CE3_B_CORESIGHT_TRACE2 0x104 0x36C 0x000 0x6 0x0 +#define MX8MN_IOMUXC_NAND_CLE_RAWNAND_CLE 0x108 0x370 0x000 0x0 0x0 +#define MX8MN_IOMUXC_NAND_CLE_QSPI_B_SCLK 0x108 0x370 0x000 0x1 0x0 +#define MX8MN_IOMUXC_NAND_CLE_USDHC3_DATA7 0x108 0x370 0x54C 0x2 0x0 +#define MX8MN_IOMUXC_NAND_CLE_GPIO3_IO5 0x108 0x370 0x000 0x5 0x0 +#define MX8MN_IOMUXC_NAND_CLE_CORESIGHT_TRACE3 0x108 0x370 0x000 0x6 0x0 +#define MX8MN_IOMUXC_NAND_DATA00_RAWNAND_DATA00 0x10C 0x374 0x000 0x0 0x0 +#define MX8MN_IOMUXC_NAND_DATA00_QSPI_A_DATA0 0x10C 0x374 0x000 0x1 0x0 +#define MX8MN_IOMUXC_NAND_DATA00_PDM_BIT_STREAM2 0x10C 0x374 0x53C 0x3 0x6 +#define MX8MN_IOMUXC_NAND_DATA00_UART4_DCE_RX 0x10C 0x374 0x50C 0x4 0x6 +#define MX8MN_IOMUXC_NAND_DATA00_UART4_DTE_TX 0x10C 0x374 0x000 0x4 0x0 +#define MX8MN_IOMUXC_NAND_DATA00_GPIO3_IO6 0x10C 0x374 0x000 0x5 0x0 +#define MX8MN_IOMUXC_NAND_DATA00_CORESIGHT_TRACE4 0x10C 0x374 0x000 0x6 0x0 +#define MX8MN_IOMUXC_NAND_DATA01_RAWNAND_DATA01 0x110 0x378 0x000 0x0 0x0 +#define MX8MN_IOMUXC_NAND_DATA01_QSPI_A_DATA1 0x110 0x378 0x000 0x1 0x0 +#define MX8MN_IOMUXC_NAND_DATA01_PDM_BIT_STREAM3 0x110 0x378 0x540 0x3 0x5 +#define MX8MN_IOMUXC_NAND_DATA01_UART4_DCE_TX 0x110 0x378 0x000 0x4 0x0 +#define MX8MN_IOMUXC_NAND_DATA01_UART4_DTE_RX 0x110 0x378 0x50C 0x4 0x7 +#define MX8MN_IOMUXC_NAND_DATA01_GPIO3_IO7 0x110 0x378 0x000 0x5 0x0 +#define MX8MN_IOMUXC_NAND_DATA01_CORESIGHT_TRACE5 0x110 0x378 0x000 0x6 0x0 +#define MX8MN_IOMUXC_NAND_DATA02_RAWNAND_DATA02 0x114 0x37C 0x000 0x0 0x0 +#define MX8MN_IOMUXC_NAND_DATA02_QSPI_A_DATA2 0x114 0x37C 0x000 0x1 0x0 +#define MX8MN_IOMUXC_NAND_DATA02_USDHC3_CD_B 0x114 0x37C 0x598 0x2 0x0 +#define MX8MN_IOMUXC_NAND_DATA02_I2C4_SDA 0x114 0x37C 0x58C 0x4 0x3 +#define MX8MN_IOMUXC_NAND_DATA02_GPIO3_IO8 0x114 0x37C 0x000 0x5 0x0 +#define MX8MN_IOMUXC_NAND_DATA02_CORESIGHT_TRACE6 0x114 0x37C 0x000 0x6 0x0 +#define MX8MN_IOMUXC_NAND_DATA03_RAWNAND_DATA03 0x118 0x380 0x000 0x0 0x0 +#define MX8MN_IOMUXC_NAND_DATA03_QSPI_A_DATA3 0x118 0x380 0x000 0x1 0x0 +#define MX8MN_IOMUXC_NAND_DATA03_USDHC3_WP 0x118 0x380 0x5B8 0x2 0x0 +#define MX8MN_IOMUXC_NAND_DATA03_GPIO3_IO9 0x118 0x380 0x000 0x5 0x0 +#define MX8MN_IOMUXC_NAND_DATA03_CORESIGHT_TRACE7 0x118 0x380 0x000 0x6 0x0 +#define MX8MN_IOMUXC_NAND_DATA04_RAWNAND_DATA04 0x11C 0x384 0x000 0x0 0x0 +#define MX8MN_IOMUXC_NAND_DATA04_QSPI_B_DATA0 0x11C 0x384 0x000 0x1 0x0 +#define MX8MN_IOMUXC_NAND_DATA04_USDHC3_DATA0 0x11C 0x384 0x5B4 0x2 0x0 +#define MX8MN_IOMUXC_NAND_DATA04_GPIO3_IO10 0x11C 0x384 0x000 0x5 0x0 +#define MX8MN_IOMUXC_NAND_DATA04_CORESIGHT_TRACE8 0x11C 0x384 0x000 0x6 0x0 +#define MX8MN_IOMUXC_NAND_DATA05_RAWNAND_DATA05 0x120 0x388 0x000 0x0 0x0 +#define MX8MN_IOMUXC_NAND_DATA05_QSPI_B_DATA1 0x120 0x388 0x000 0x1 0x0 +#define MX8MN_IOMUXC_NAND_DATA05_USDHC3_DATA1 0x120 0x388 0x5B0 0x2 0x0 +#define MX8MN_IOMUXC_NAND_DATA05_GPIO3_IO11 0x120 0x388 0x000 0x5 0x0 +#define MX8MN_IOMUXC_NAND_DATA05_CORESIGHT_TRACE9 0x120 0x388 0x000 0x6 0x0 +#define MX8MN_IOMUXC_NAND_DATA06_RAWNAND_DATA06 0x124 0x38C 0x000 0x0 0x0 +#define MX8MN_IOMUXC_NAND_DATA06_QSPI_B_DATA2 0x124 0x38C 0x000 0x1 0x0 +#define MX8MN_IOMUXC_NAND_DATA06_USDHC3_DATA2 0x124 0x38C 0x5E4 0x2 0x0 +#define MX8MN_IOMUXC_NAND_DATA06_GPIO3_IO12 0x124 0x38C 0x000 0x5 0x0 +#define MX8MN_IOMUXC_NAND_DATA06_CORESIGHT_TRACE10 0x124 0x38C 0x000 0x6 0x0 +#define MX8MN_IOMUXC_NAND_DATA07_RAWNAND_DATA07 0x128 0x390 0x000 0x0 0x0 +#define MX8MN_IOMUXC_NAND_DATA07_QSPI_B_DATA3 0x128 0x390 0x000 0x1 0x0 +#define MX8MN_IOMUXC_NAND_DATA07_USDHC3_DATA3 0x128 0x390 0x5E0 0x2 0x0 +#define MX8MN_IOMUXC_NAND_DATA07_GPIO3_IO13 0x128 0x390 0x000 0x5 0x0 +#define MX8MN_IOMUXC_NAND_DATA07_CORESIGHT_TRACE11 0x128 0x390 0x000 0x6 0x0 +#define MX8MN_IOMUXC_NAND_DQS_RAWNAND_DQS 0x12C 0x394 0x000 0x0 0x0 +#define MX8MN_IOMUXC_NAND_DQS_QSPI_A_DQS 0x12C 0x394 0x000 0x1 0x0 +#define MX8MN_IOMUXC_NAND_DQS_PDM_CLK 0x12C 0x394 0x000 0x3 0x0 +#define MX8MN_IOMUXC_NAND_DQS_I2C3_SCL 0x12C 0x394 0x588 0x4 0x2 +#define MX8MN_IOMUXC_NAND_DQS_GPIO3_IO14 0x12C 0x394 0x000 0x5 0x0 +#define MX8MN_IOMUXC_NAND_DQS_CORESIGHT_TRACE12 0x12C 0x394 0x000 0x6 0x0 +#define MX8MN_IOMUXC_NAND_RE_B_RAWNAND_RE_B 0x130 0x398 0x000 0x0 0x0 +#define MX8MN_IOMUXC_NAND_RE_B_QSPI_B_DQS 0x130 0x398 0x000 0x1 0x0 +#define MX8MN_IOMUXC_NAND_RE_B_USDHC3_DATA4 0x130 0x398 0x558 0x2 0x0 +#define MX8MN_IOMUXC_NAND_RE_B_PDM_BIT_STREAM1 0x130 0x398 0x538 0x3 0x7 +#define MX8MN_IOMUXC_NAND_RE_B_GPIO3_IO15 0x130 0x398 0x000 0x5 0x0 +#define MX8MN_IOMUXC_NAND_RE_B_CORESIGHT_TRACE13 0x130 0x398 0x000 0x6 0x0 +#define MX8MN_IOMUXC_NAND_READY_B_RAWNAND_READY_B 0x134 0x39C 0x000 0x0 0x0 +#define MX8MN_IOMUXC_NAND_READY_B_USDHC3_RESET_B 0x134 0x39C 0x000 0x2 0x0 +#define MX8MN_IOMUXC_NAND_READY_B_PDM_BIT_STREAM3 0x134 0x39C 0x540 0x3 0x6 +#define MX8MN_IOMUXC_NAND_READY_B_I2C3_SCL 0x134 0x39C 0x588 0x4 0x3 +#define MX8MN_IOMUXC_NAND_READY_B_GPIO3_IO16 0x134 0x39C 0x000 0x5 0x0 +#define MX8MN_IOMUXC_NAND_READY_B_CORESIGHT_TRACE14 0x134 0x39C 0x000 0x6 0x0 +#define MX8MN_IOMUXC_NAND_WE_B_RAWNAND_WE_B 0x138 0x3A0 0x000 0x0 0x0 +#define MX8MN_IOMUXC_NAND_WE_B_USDHC3_CLK 0x138 0x3A0 0x5A0 0x2 0x0 +#define MX8MN_IOMUXC_NAND_WE_B_I2C3_SDA 0x138 0x3A0 0x5BC 0x4 0x3 +#define MX8MN_IOMUXC_NAND_WE_B_GPIO3_IO17 0x138 0x3A0 0x000 0x5 0x0 +#define MX8MN_IOMUXC_NAND_WE_B_CORESIGHT_TRACE15 0x138 0x3A0 0x000 0x6 0x0 +#define MX8MN_IOMUXC_NAND_WP_B_RAWNAND_WP_B 0x13C 0x3A4 0x000 0x0 0x0 +#define MX8MN_IOMUXC_NAND_WP_B_USDHC3_CMD 0x13C 0x3A4 0x5DC 0x2 0x0 +#define MX8MN_IOMUXC_NAND_WP_B_I2C4_SDA 0x13C 0x3A4 0x58C 0x4 0x4 +#define MX8MN_IOMUXC_NAND_WP_B_GPIO3_IO18 0x13C 0x3A4 0x000 0x5 0x0 +#define MX8MN_IOMUXC_NAND_WP_B_CORESIGHT_EVENTO 0x13C 0x3A4 0x000 0x6 0x0 +#define MX8MN_IOMUXC_SAI5_RXFS_SAI5_RX_SYNC 0x140 0x3A8 0x4E4 0x0 0x0 +#define MX8MN_IOMUXC_SAI5_RXFS_GPIO3_IO19 0x140 0x3A8 0x000 0x5 0x0 +#define MX8MN_IOMUXC_SAI5_RXC_SAI5_RX_BCLK 0x144 0x3AC 0x4D0 0x0 0x0 +#define MX8MN_IOMUXC_SAI5_RXC_PDM_CLK 0x144 0x3AC 0x000 0x4 0x0 +#define MX8MN_IOMUXC_SAI5_RXC_GPIO3_IO20 0x144 0x3AC 0x000 0x5 0x0 +#define MX8MN_IOMUXC_SAI5_RXD0_SAI5_RX_DATA0 0x148 0x3B0 0x4D4 0x0 0x0 +#define MX8MN_IOMUXC_SAI5_RXD0_PDM_BIT_STREAM0 0x148 0x3B0 0x534 0x4 0x0 +#define MX8MN_IOMUXC_SAI5_RXD0_GPIO3_IO21 0x148 0x3B0 0x000 0x5 0x0 +#define MX8MN_IOMUXC_SAI5_RXD1_SAI5_RX_DATA1 0x14C 0x3B4 0x4D8 0x0 0x0 +#define MX8MN_IOMUXC_SAI5_RXD1_SAI5_TX_SYNC 0x14C 0x3B4 0x4EC 0x3 0x0 +#define MX8MN_IOMUXC_SAI5_RXD1_PDM_BIT_STREAM1 0x14C 0x3B4 0x538 0x4 0x0 +#define MX8MN_IOMUXC_SAI5_RXD1_GPIO3_IO22 0x14C 0x3B4 0x000 0x5 0x0 +#define MX8MN_IOMUXC_SAI5_RXD2_SAI5_RX_DATA2 0x150 0x3B8 0x4DC 0x0 0x0 +#define MX8MN_IOMUXC_SAI5_RXD2_SAI5_TX_BCLK 0x150 0x3B8 0x4E8 0x3 0x0 +#define MX8MN_IOMUXC_SAI5_RXD2_PDM_BIT_STREAM2 0x150 0x3B8 0x53C 0x4 0x0 +#define MX8MN_IOMUXC_SAI5_RXD2_GPIO3_IO23 0x150 0x3B8 0x000 0x5 0x0 +#define MX8MN_IOMUXC_SAI5_RXD3_SAI5_RX_DATA3 0x154 0x3BC 0x4E0 0x0 0x0 +#define MX8MN_IOMUXC_SAI5_RXD3_SAI5_TX_DATA0 0x154 0x3BC 0x000 0x3 0x0 +#define MX8MN_IOMUXC_SAI5_RXD3_PDM_BIT_STREAM3 0x154 0x3BC 0x540 0x4 0x0 +#define MX8MN_IOMUXC_SAI5_RXD3_GPIO3_IO24 0x154 0x3BC 0x000 0x5 0x0 +#define MX8MN_IOMUXC_SAI5_MCLK_SAI5_MCLK 0x158 0x3C0 0x594 0x0 0x0 +#define MX8MN_IOMUXC_SAI5_MCLK_GPIO3_IO25 0x158 0x3C0 0x000 0x5 0x0 +#define MX8MN_IOMUXC_SAI2_RXFS_SAI2_RX_SYNC 0x1B0 0x418 0x000 0x0 0x0 +#define MX8MN_IOMUXC_SAI2_RXFS_SAI5_TX_SYNC 0x1B0 0x418 0x4EC 0x1 0x2 +#define MX8MN_IOMUXC_SAI2_RXFS_SAI5_TX_DATA1 0x1B0 0x418 0x000 0x2 0x0 +#define MX8MN_IOMUXC_SAI2_RXFS_SAI2_RX_DATA1 0x1B0 0x418 0x5AC 0x3 0x0 +#define MX8MN_IOMUXC_SAI2_RXFS_UART1_DCE_TX 0x1B0 0x418 0x000 0x4 0x0 +#define MX8MN_IOMUXC_SAI2_RXFS_UART1_DTE_RX 0x1B0 0x418 0x4F4 0x4 0x2 +#define MX8MN_IOMUXC_SAI2_RXFS_GPIO4_IO21 0x1B0 0x418 0x000 0x5 0x0 +#define MX8MN_IOMUXC_SAI2_RXFS_PDM_BIT_STREAM2 0x1B0 0x418 0x53C 0x6 0x7 +#define MX8MN_IOMUXC_SAI2_RXC_SAI2_RX_BCLK 0x1B4 0x41C 0x000 0x0 0x0 +#define MX8MN_IOMUXC_SAI2_RXC_SAI5_TX_BCLK 0x1B4 0x41C 0x4E8 0x1 0x2 +#define MX8MN_IOMUXC_SAI2_RXC_UART1_DCE_RX 0x1B4 0x41C 0x4F4 0x4 0x3 +#define MX8MN_IOMUXC_SAI2_RXC_UART1_DTE_TX 0x1B4 0x41C 0x000 0x4 0x0 +#define MX8MN_IOMUXC_SAI2_RXC_GPIO4_IO22 0x1B4 0x41C 0x000 0x5 0x0 +#define MX8MN_IOMUXC_SAI2_RXC_PDM_BIT_STREAM1 0x1B4 0x41C 0x538 0x6 0x8 +#define MX8MN_IOMUXC_SAI2_RXD0_SAI2_RX_DATA0 0x1B8 0x420 0x000 0x0 0x0 +#define MX8MN_IOMUXC_SAI2_RXD0_SAI5_TX_DATA0 0x1B8 0x420 0x000 0x1 0x0 +#define MX8MN_IOMUXC_SAI2_RXD0_SAI2_TX_DATA1 0x1B8 0x420 0x000 0x3 0x0 +#define MX8MN_IOMUXC_SAI2_RXD0_UART1_DCE_RTS_B 0x1B8 0x420 0x4F0 0x4 0x2 +#define MX8MN_IOMUXC_SAI2_RXD0_UART1_DTE_CTS_B 0x1B8 0x420 0x000 0x4 0x0 +#define MX8MN_IOMUXC_SAI2_RXD0_GPIO4_IO23 0x1B8 0x420 0x000 0x5 0x0 +#define MX8MN_IOMUXC_SAI2_RXD0_PDM_BIT_STREAM3 0x1B8 0x420 0x540 0x6 0x7 +#define MX8MN_IOMUXC_SAI2_TXFS_SAI2_TX_SYNC 0x1BC 0x424 0x000 0x0 0x0 +#define MX8MN_IOMUXC_SAI2_TXFS_SAI5_TX_DATA1 0x1BC 0x424 0x000 0x1 0x0 +#define MX8MN_IOMUXC_SAI2_TXFS_SAI2_TX_DATA1 0x1BC 0x424 0x000 0x3 0x0 +#define MX8MN_IOMUXC_SAI2_TXFS_UART1_DCE_CTS_B 0x1BC 0x424 0x000 0x4 0x0 +#define MX8MN_IOMUXC_SAI2_TXFS_UART1_DTE_RTS_B 0x1BC 0x424 0x4F0 0x4 0x3 +#define MX8MN_IOMUXC_SAI2_TXFS_GPIO4_IO24 0x1BC 0x424 0x000 0x5 0x0 +#define MX8MN_IOMUXC_SAI2_TXFS_PDM_BIT_STREAM2 0x1BC 0x424 0x53C 0x6 0x8 +#define MX8MN_IOMUXC_SAI2_TXC_SAI2_TX_BCLK 0x1C0 0x428 0x000 0x0 0x0 +#define MX8MN_IOMUXC_SAI2_TXC_SAI5_TX_DATA2 0x1C0 0x428 0x000 0x1 0x0 +#define MX8MN_IOMUXC_SAI2_TXC_GPIO4_IO25 0x1C0 0x428 0x000 0x5 0x0 +#define MX8MN_IOMUXC_SAI2_TXC_PDM_BIT_STREAM1 0x1C0 0x428 0x538 0x6 0x9 +#define MX8MN_IOMUXC_SAI2_TXD0_SAI2_TX_DATA0 0x1C4 0x42C 0x000 0x0 0x0 +#define MX8MN_IOMUXC_SAI2_TXD0_SAI5_TX_DATA3 0x1C4 0x42C 0x000 0x1 0x0 +#define MX8MN_IOMUXC_SAI2_TXD0_GPIO4_IO26 0x1C4 0x42C 0x000 0x5 0x0 +#define MX8MN_IOMUXC_SAI2_TXD0_CCMSRCGPCMIX_BOOT_MODE4 0x1C4 0x42C 0x540 0x6 0x8 +#define MX8MN_IOMUXC_SAI2_MCLK_SAI2_MCLK 0x1C8 0x430 0x000 0x0 0x0 +#define MX8MN_IOMUXC_SAI2_MCLK_SAI5_MCLK 0x1C8 0x430 0x594 0x1 0x2 +#define MX8MN_IOMUXC_SAI2_MCLK_GPIO4_IO27 0x1C8 0x430 0x000 0x5 0x0 +#define MX8MN_IOMUXC_SAI2_MCLK_SAI3_MCLK 0x1C8 0x430 0x5C0 0x6 0x1 +#define MX8MN_IOMUXC_SAI3_RXFS_SAI3_RX_SYNC 0x1CC 0x434 0x000 0x0 0x0 +#define MX8MN_IOMUXC_SAI3_RXFS_GPT1_CAPTURE1 0x1CC 0x434 0x5F0 0x1 0x0 +#define MX8MN_IOMUXC_SAI3_RXFS_SAI5_RX_SYNC 0x1CC 0x434 0x4E4 0x2 0x2 +#define MX8MN_IOMUXC_SAI3_RXFS_SAI3_RX_DATA1 0x1CC 0x434 0x000 0x3 0x0 +#define MX8MN_IOMUXC_SAI3_RXFS_SPDIF1_IN 0x1CC 0x434 0x5CC 0x4 0x3 +#define MX8MN_IOMUXC_SAI3_RXFS_GPIO4_IO28 0x1CC 0x434 0x000 0x5 0x0 +#define MX8MN_IOMUXC_SAI3_RXFS_PDM_BIT_STREAM0 0x1CC 0x434 0x534 0x6 0x5 +#define MX8MN_IOMUXC_SAI3_RXC_SAI3_RX_BCLK 0x1D0 0x438 0x000 0x0 0x0 +#define MX8MN_IOMUXC_SAI3_RXC_GPT1_CLK 0x1D0 0x438 0x5E8 0x1 0x0 +#define MX8MN_IOMUXC_SAI3_RXC_SAI5_RX_BCLK 0x1D0 0x438 0x4D0 0x2 0x2 +#define MX8MN_IOMUXC_SAI3_RXC_SAI2_RX_DATA1 0x1D0 0x438 0x5AC 0x3 0x2 +#define MX8MN_IOMUXC_SAI3_RXC_UART2_DCE_CTS_B 0x1D0 0x438 0x000 0x4 0x0 +#define MX8MN_IOMUXC_SAI3_RXC_UART2_DTE_RTS_B 0x1D0 0x438 0x4F8 0x4 0x2 +#define MX8MN_IOMUXC_SAI3_RXC_GPIO4_IO29 0x1D0 0x438 0x000 0x5 0x0 +#define MX8MN_IOMUXC_SAI3_RXC_PDM_CLK 0x1D0 0x438 0x000 0x6 0x0 +#define MX8MN_IOMUXC_SAI3_RXD_SAI3_RX_DATA0 0x1D4 0x43C 0x000 0x0 0x0 +#define MX8MN_IOMUXC_SAI3_RXD_GPT1_COMPARE1 0x1D4 0x43C 0x000 0x1 0x0 +#define MX8MN_IOMUXC_SAI3_RXD_SAI5_RX_DATA0 0x1D4 0x43C 0x4D4 0x2 0x2 +#define MX8MN_IOMUXC_SAI3_RXD_SAI3_TX_DATA1 0x1D4 0x43C 0x000 0x3 0x0 +#define MX8MN_IOMUXC_SAI3_RXD_UART2_DCE_RTS_B 0x1D4 0x43C 0x4F8 0x4 0x3 +#define MX8MN_IOMUXC_SAI3_RXD_UART2_DTE_CTS_B 0x1D4 0x43C 0x000 0x4 0x0 +#define MX8MN_IOMUXC_SAI3_RXD_GPIO4_IO30 0x1D4 0x43C 0x000 0x5 0x0 +#define MX8MN_IOMUXC_SAI3_RXD_PDM_BIT_STREAM1 0x1D4 0x43C 0x538 0x6 0x10 +#define MX8MN_IOMUXC_SAI3_TXFS_SAI3_TX_SYNC 0x1D8 0x440 0x000 0x0 0x0 +#define MX8MN_IOMUXC_SAI3_TXFS_GPT1_CAPTURE2 0x1D8 0x440 0x5EC 0x1 0x0 +#define MX8MN_IOMUXC_SAI3_TXFS_SAI5_RX_DATA1 0x1D8 0x440 0x4D8 0x2 0x1 +#define MX8MN_IOMUXC_SAI3_TXFS_SAI3_TX_DATA1 0x1D8 0x440 0x000 0x3 0x0 +#define MX8MN_IOMUXC_SAI3_TXFS_UART2_DCE_RX 0x1D8 0x440 0x4FC 0x4 0x2 +#define MX8MN_IOMUXC_SAI3_TXFS_UART2_DTE_TX 0x1D8 0x440 0x000 0x4 0x0 +#define MX8MN_IOMUXC_SAI3_TXFS_GPIO4_IO31 0x1D8 0x440 0x000 0x5 0x0 +#define MX8MN_IOMUXC_SAI3_TXFS_PDM_BIT_STREAM3 0x1D8 0x440 0x540 0x6 0x9 +#define MX8MN_IOMUXC_SAI3_TXC_SAI3_TX_BCLK 0x1DC 0x444 0x000 0x0 0x0 +#define MX8MN_IOMUXC_SAI3_TXC_GPT1_COMPARE2 0x1DC 0x444 0x000 0x1 0x0 +#define MX8MN_IOMUXC_SAI3_TXC_SAI5_RX_DATA2 0x1DC 0x444 0x4DC 0x2 0x1 +#define MX8MN_IOMUXC_SAI3_TXC_SAI2_TX_DATA1 0x1DC 0x444 0x000 0x3 0x0 +#define MX8MN_IOMUXC_SAI3_TXC_UART2_DCE_TX 0x1DC 0x444 0x000 0x4 0x0 +#define MX8MN_IOMUXC_SAI3_TXC_UART2_DTE_RX 0x1DC 0x444 0x4FC 0x4 0x3 +#define MX8MN_IOMUXC_SAI3_TXC_GPIO5_IO0 0x1DC 0x444 0x000 0x5 0x0 +#define MX8MN_IOMUXC_SAI3_TXC_PDM_BIT_STREAM2 0x1DC 0x444 0x53C 0x6 0x9 +#define MX8MN_IOMUXC_SAI3_TXD_SAI3_TX_DATA0 0x1E0 0x448 0x000 0x0 0x0 +#define MX8MN_IOMUXC_SAI3_TXD_GPT1_COMPARE3 0x1E0 0x448 0x000 0x1 0x0 +#define MX8MN_IOMUXC_SAI3_TXD_SAI5_RX_DATA3 0x1E0 0x448 0x4E0 0x2 0x1 +#define MX8MN_IOMUXC_SAI3_TXD_SPDIF1_EXT_CLK 0x1E0 0x448 0x568 0x4 0x2 +#define MX8MN_IOMUXC_SAI3_TXD_GPIO5_IO1 0x1E0 0x448 0x000 0x5 0x0 +#define MX8MN_IOMUXC_SAI3_TXD_CCMSRCGPCMIX_BOOT_MODE5 0x1E0 0x448 0x000 0x6 0x0 +#define MX8MN_IOMUXC_SAI3_MCLK_SAI3_MCLK 0x1E4 0x44C 0x5C0 0x0 0x0 +#define MX8MN_IOMUXC_SAI3_MCLK_PWM4_OUT 0x1E4 0x44C 0x000 0x1 0x0 +#define MX8MN_IOMUXC_SAI3_MCLK_SAI5_MCLK 0x1E4 0x44C 0x594 0x2 0x3 +#define MX8MN_IOMUXC_SAI3_MCLK_SPDIF1_OUT 0x1E4 0x44C 0x000 0x4 0x0 +#define MX8MN_IOMUXC_SAI3_MCLK_GPIO5_IO2 0x1E4 0x44C 0x000 0x5 0x0 +#define MX8MN_IOMUXC_SAI3_MCLK_SPDIF1_IN 0x1E4 0x44C 0x5CC 0x6 0x4 +#define MX8MN_IOMUXC_SPDIF_TX_SPDIF1_OUT 0x1E8 0x450 0x000 0x0 0x0 +#define MX8MN_IOMUXC_SPDIF_TX_PWM3_OUT 0x1E8 0x450 0x000 0x1 0x0 +#define MX8MN_IOMUXC_SPDIF_TX_GPIO5_IO3 0x1E8 0x450 0x000 0x5 0x0 +#define MX8MN_IOMUXC_SPDIF_RX_SPDIF1_IN 0x1EC 0x454 0x5CC 0x0 0x0 +#define MX8MN_IOMUXC_SPDIF_RX_PWM2_OUT 0x1EC 0x454 0x000 0x1 0x0 +#define MX8MN_IOMUXC_SPDIF_RX_GPIO5_IO4 0x1EC 0x454 0x000 0x5 0x0 +#define MX8MN_IOMUXC_SPDIF_EXT_CLK_SPDIF1_EXT_CLK 0x1F0 0x458 0x568 0x0 0x0 +#define MX8MN_IOMUXC_SPDIF_EXT_CLK_PWM1_OUT 0x1F0 0x458 0x000 0x1 0x0 +#define MX8MN_IOMUXC_SPDIF_EXT_CLK_GPIO5_IO5 0x1F0 0x458 0x000 0x5 0x0 +#define MX8MN_IOMUXC_ECSPI1_SCLK_ECSPI1_SCLK 0x1F4 0x45C 0x5D8 0x0 0x0 +#define MX8MN_IOMUXC_ECSPI1_SCLK_UART3_DCE_RX 0x1F4 0x45C 0x504 0x1 0x0 +#define MX8MN_IOMUXC_ECSPI1_SCLK_UART3_DTE_TX 0x1F4 0x45C 0x000 0x1 0x0 +#define MX8MN_IOMUXC_ECSPI1_SCLK_I2C1_SCL 0x1F4 0x45C 0x55C 0x2 0x2 +#define MX8MN_IOMUXC_ECSPI1_SCLK_SAI5_RX_SYNC 0x1F4 0x45C 0x4DC 0x3 0x2 +#define MX8MN_IOMUXC_ECSPI1_SCLK_GPIO5_IO6 0x1F4 0x45C 0x000 0x5 0x0 +#define MX8MN_IOMUXC_ECSPI1_MOSI_ECSPI1_MOSI 0x1F8 0x460 0x5A8 0x0 0x0 +#define MX8MN_IOMUXC_ECSPI1_MOSI_UART3_DCE_TX 0x1F8 0x460 0x000 0x1 0x0 +#define MX8MN_IOMUXC_ECSPI1_MOSI_UART3_DTE_RX 0x1F8 0x460 0x504 0x1 0x1 +#define MX8MN_IOMUXC_ECSPI1_MOSI_I2C1_SDA 0x1F8 0x460 0x56C 0x2 0x2 +#define MX8MN_IOMUXC_ECSPI1_MOSI_SAI5_RX_BCLK 0x1F8 0x460 0x4D0 0x3 0x3 +#define MX8MN_IOMUXC_ECSPI1_MOSI_GPIO5_IO7 0x1F8 0x460 0x000 0x5 0x0 +#define MX8MN_IOMUXC_ECSPI1_MISO_ECSPI1_MISO 0x1FC 0x464 0x5C4 0x0 0x0 +#define MX8MN_IOMUXC_ECSPI1_MISO_UART3_DCE_CTS_B 0x1FC 0x464 0x000 0x1 0x0 +#define MX8MN_IOMUXC_ECSPI1_MISO_UART3_DTE_RTS_B 0x1FC 0x464 0x500 0x1 0x0 +#define MX8MN_IOMUXC_ECSPI1_MISO_I2C2_SCL 0x1FC 0x464 0x5D0 0x2 0x2 +#define MX8MN_IOMUXC_ECSPI1_MISO_SAI5_RX_DATA0 0x1FC 0x464 0x4D4 0x3 0x3 +#define MX8MN_IOMUXC_ECSPI1_MISO_GPIO5_IO8 0x1FC 0x464 0x000 0x5 0x0 +#define MX8MN_IOMUXC_ECSPI1_SS0_ECSPI1_SS0 0x200 0x468 0x564 0x0 0x0 +#define MX8MN_IOMUXC_ECSPI1_SS0_UART3_DCE_RTS_B 0x200 0x468 0x500 0x1 0x1 +#define MX8MN_IOMUXC_ECSPI1_SS0_UART3_DTE_CTS_B 0x200 0x468 0x000 0x1 0x0 +#define MX8MN_IOMUXC_ECSPI1_SS0_I2C2_SDA 0x200 0x468 0x560 0x2 0x2 +#define MX8MN_IOMUXC_ECSPI1_SS0_SAI5_RX_DATA1 0x200 0x468 0x4D8 0x3 0x2 +#define MX8MN_IOMUXC_ECSPI1_SS0_SAI5_TX_SYNC 0x200 0x468 0x4EC 0x4 0x3 +#define MX8MN_IOMUXC_ECSPI1_SS0_GPIO5_IO9 0x200 0x468 0x000 0x5 0x0 +#define MX8MN_IOMUXC_ECSPI2_SCLK_ECSPI2_SCLK 0x204 0x46C 0x580 0x0 0x0 +#define MX8MN_IOMUXC_ECSPI2_SCLK_UART4_DCE_RX 0x204 0x46C 0x50C 0x1 0x0 +#define MX8MN_IOMUXC_ECSPI2_SCLK_UART4_DTE_TX 0x204 0x46C 0x000 0x1 0x0 +#define MX8MN_IOMUXC_ECSPI2_SCLK_I2C3_SCL 0x204 0x46C 0x588 0x2 0x4 +#define MX8MN_IOMUXC_ECSPI2_SCLK_SAI5_RX_DATA2 0x204 0x46C 0x000 0x3 0x0 +#define MX8MN_IOMUXC_ECSPI2_SCLK_SAI5_TX_BCLK 0x204 0x46C 0x4E8 0x4 0x3 +#define MX8MN_IOMUXC_ECSPI2_SCLK_GPIO5_IO10 0x204 0x46C 0x000 0x5 0x0 +#define MX8MN_IOMUXC_ECSPI2_MOSI_ECSPI2_MOSI 0x208 0x470 0x590 0x0 0x0 +#define MX8MN_IOMUXC_ECSPI2_MOSI_UART4_DCE_TX 0x208 0x470 0x000 0x1 0x0 +#define MX8MN_IOMUXC_ECSPI2_MOSI_UART4_DTE_RX 0x208 0x470 0x50C 0x1 0x1 +#define MX8MN_IOMUXC_ECSPI2_MOSI_I2C3_SDA 0x208 0x470 0x5BC 0x2 0x4 +#define MX8MN_IOMUXC_ECSPI2_MOSI_SAI5_RX_DATA3 0x208 0x470 0x4E0 0x3 0x2 +#define MX8MN_IOMUXC_ECSPI2_MOSI_SAI5_TX_DATA0 0x208 0x470 0x000 0x4 0x0 +#define MX8MN_IOMUXC_ECSPI2_MOSI_GPIO5_IO11 0x208 0x470 0x000 0x5 0x0 +#define MX8MN_IOMUXC_ECSPI2_MISO_ECSPI2_MISO 0x20C 0x474 0x578 0x0 0x0 +#define MX8MN_IOMUXC_ECSPI2_MISO_UART4_DCE_CTS_B 0x20C 0x474 0x000 0x1 0x0 +#define MX8MN_IOMUXC_ECSPI2_MISO_UART4_DTE_RTS_B 0x20C 0x474 0x508 0x1 0x0 +#define MX8MN_IOMUXC_ECSPI2_MISO_I2C4_SCL 0x20C 0x474 0x5D4 0x2 0x3 +#define MX8MN_IOMUXC_ECSPI2_MISO_SAI5_MCLK 0x20C 0x474 0x594 0x3 0x4 +#define MX8MN_IOMUXC_ECSPI2_MISO_GPIO5_IO12 0x20C 0x474 0x000 0x5 0x0 +#define MX8MN_IOMUXC_ECSPI2_SS0_ECSPI2_SS0 0x210 0x478 0x570 0x0 0x0 +#define MX8MN_IOMUXC_ECSPI2_SS0_UART4_DCE_RTS_B 0x210 0x478 0x508 0x1 0x1 +#define MX8MN_IOMUXC_ECSPI2_SS0_UART4_DTE_CTS_B 0x210 0x478 0x000 0x1 0x0 +#define MX8MN_IOMUXC_ECSPI2_SS0_I2C4_SDA 0x210 0x478 0x58C 0x2 0x5 +#define MX8MN_IOMUXC_ECSPI2_SS0_GPIO5_IO13 0x210 0x478 0x000 0x5 0x0 +#define MX8MN_IOMUXC_I2C1_SCL_I2C1_SCL 0x214 0x47C 0x55C 0x0 0x0 +#define MX8MN_IOMUXC_I2C1_SCL_ENET1_MDC 0x214 0x47C 0x000 0x1 0x0 +#define MX8MN_IOMUXC_I2C1_SCL_ECSPI1_SCLK 0x214 0x47C 0x5D8 0x3 0x1 +#define MX8MN_IOMUXC_I2C1_SCL_GPIO5_IO14 0x214 0x47C 0x000 0x5 0x0 +#define MX8MN_IOMUXC_I2C1_SDA_I2C1_SDA 0x218 0x480 0x56C 0x0 0x0 +#define MX8MN_IOMUXC_I2C1_SDA_ENET1_MDIO 0x218 0x480 0x4C0 0x1 0x2 +#define MX8MN_IOMUXC_I2C1_SDA_ECSPI1_MOSI 0x218 0x480 0x5A8 0x3 0x1 +#define MX8MN_IOMUXC_I2C1_SDA_GPIO5_IO15 0x218 0x480 0x000 0x5 0x0 +#define MX8MN_IOMUXC_I2C2_SCL_I2C2_SCL 0x21C 0x484 0x5D0 0x0 0x0 +#define MX8MN_IOMUXC_I2C2_SCL_ENET1_1588_EVENT1_IN 0x21C 0x484 0x000 0x1 0x0 +#define MX8MN_IOMUXC_I2C2_SCL_USDHC3_CD_B 0x21C 0x484 0x598 0x2 0x1 +#define MX8MN_IOMUXC_I2C2_SCL_ECSPI1_MISO 0x21C 0x484 0x5C4 0x3 0x1 +#define MX8MN_IOMUXC_I2C2_SCL_GPIO5_IO16 0x21C 0x484 0x000 0x5 0x0 +#define MX8MN_IOMUXC_I2C2_SDA_I2C2_SDA 0x220 0x488 0x560 0x0 0x0 +#define MX8MN_IOMUXC_I2C2_SDA_ENET1_1588_EVENT1_OUT 0x220 0x488 0x000 0x1 0x0 +#define MX8MN_IOMUXC_I2C2_SDA_USDHC3_WP 0x220 0x488 0x5B8 0x2 0x1 +#define MX8MN_IOMUXC_I2C2_SDA_ECSPI1_SS0 0x220 0x488 0x564 0x3 0x1 +#define MX8MN_IOMUXC_I2C2_SDA_GPIO5_IO17 0x220 0x488 0x000 0x5 0x0 +#define MX8MN_IOMUXC_I2C3_SCL_I2C3_SCL 0x224 0x48C 0x588 0x0 0x0 +#define MX8MN_IOMUXC_I2C3_SCL_PWM4_OUT 0x224 0x48C 0x000 0x1 0x0 +#define MX8MN_IOMUXC_I2C3_SCL_GPT2_CLK 0x224 0x48C 0x000 0x2 0x0 +#define MX8MN_IOMUXC_I2C3_SCL_ECSPI2_SCLK 0x224 0x48C 0x580 0x3 0x2 +#define MX8MN_IOMUXC_I2C3_SCL_GPIO5_IO18 0x224 0x48C 0x000 0x5 0x0 +#define MX8MN_IOMUXC_I2C3_SDA_I2C3_SDA 0x228 0x490 0x5BC 0x0 0x0 +#define MX8MN_IOMUXC_I2C3_SDA_PWM3_OUT 0x228 0x490 0x000 0x1 0x0 +#define MX8MN_IOMUXC_I2C3_SDA_GPT3_CLK 0x228 0x490 0x000 0x2 0x0 +#define MX8MN_IOMUXC_I2C3_SDA_ECSPI2_MOSI 0x228 0x490 0x590 0x3 0x2 +#define MX8MN_IOMUXC_I2C3_SDA_GPIO5_IO19 0x228 0x490 0x000 0x5 0x0 +#define MX8MN_IOMUXC_I2C4_SCL_I2C4_SCL 0x22C 0x494 0x5D4 0x0 0x0 +#define MX8MN_IOMUXC_I2C4_SCL_PWM2_OUT 0x22C 0x494 0x000 0x1 0x0 +#define MX8MN_IOMUXC_I2C4_SCL_ECSPI2_MISO 0x22C 0x494 0x578 0x3 0x2 +#define MX8MN_IOMUXC_I2C4_SCL_GPIO5_IO20 0x22C 0x494 0x000 0x5 0x0 +#define MX8MN_IOMUXC_I2C4_SDA_I2C4_SDA 0x230 0x498 0x58C 0x0 0x0 +#define MX8MN_IOMUXC_I2C4_SDA_PWM1_OUT 0x230 0x498 0x000 0x1 0x0 +#define MX8MN_IOMUXC_I2C4_SDA_ECSPI2_SS0 0x230 0x498 0x570 0x3 0x1 +#define MX8MN_IOMUXC_I2C4_SDA_GPIO5_IO21 0x230 0x498 0x000 0x5 0x0 +#define MX8MN_IOMUXC_UART1_RXD_UART1_DCE_RX 0x234 0x49C 0x4F4 0x0 0x0 +#define MX8MN_IOMUXC_UART1_RXD_UART1_DTE_TX 0x234 0x49C 0x000 0x0 0x0 +#define MX8MN_IOMUXC_UART1_RXD_ECSPI3_SCLK 0x234 0x49C 0x000 0x1 0x0 +#define MX8MN_IOMUXC_UART1_RXD_GPIO5_IO22 0x234 0x49C 0x000 0x5 0x0 +#define MX8MN_IOMUXC_UART1_TXD_UART1_DCE_TX 0x238 0x4A0 0x000 0x0 0x0 +#define MX8MN_IOMUXC_UART1_TXD_UART1_DTE_RX 0x238 0x4A0 0x4F4 0x0 0x1 +#define MX8MN_IOMUXC_UART1_TXD_ECSPI3_MOSI 0x238 0x4A0 0x000 0x1 0x0 +#define MX8MN_IOMUXC_UART1_TXD_GPIO5_IO23 0x238 0x4A0 0x000 0x5 0x0 +#define MX8MN_IOMUXC_UART2_RXD_UART2_DCE_RX 0x23C 0x4A4 0x4FC 0x0 0x0 +#define MX8MN_IOMUXC_UART2_RXD_UART2_DTE_TX 0x23C 0x4A4 0x000 0x0 0x0 +#define MX8MN_IOMUXC_UART2_RXD_ECSPI3_MISO 0x23C 0x4A4 0x000 0x1 0x0 +#define MX8MN_IOMUXC_UART2_RXD_GPT1_COMPARE3 0x23C 0x4A4 0x000 0x3 0x0 +#define MX8MN_IOMUXC_UART2_RXD_GPIO5_IO24 0x23C 0x4A4 0x000 0x5 0x0 +#define MX8MN_IOMUXC_UART2_TXD_UART2_DCE_TX 0x240 0x4A8 0x000 0x0 0x0 +#define MX8MN_IOMUXC_UART2_TXD_UART2_DTE_RX 0x240 0x4A8 0x4FC 0x0 0x1 +#define MX8MN_IOMUXC_UART2_TXD_ECSPI3_SS0 0x240 0x4A8 0x000 0x1 0x0 +#define MX8MN_IOMUXC_UART2_TXD_GPT1_COMPARE2 0x240 0x4A8 0x000 0x3 0x0 +#define MX8MN_IOMUXC_UART2_TXD_GPIO5_IO25 0x240 0x4A8 0x000 0x5 0x0 +#define MX8MN_IOMUXC_UART3_RXD_UART3_DCE_RX 0x244 0x4AC 0x504 0x0 0x2 +#define MX8MN_IOMUXC_UART3_RXD_UART3_DTE_TX 0x244 0x4AC 0x000 0x0 0x0 +#define MX8MN_IOMUXC_UART3_RXD_UART1_DCE_CTS_B 0x244 0x4AC 0x000 0x1 0x0 +#define MX8MN_IOMUXC_UART3_RXD_UART1_DTE_RTS_B 0x244 0x4AC 0x4F0 0x1 0x0 +#define MX8MN_IOMUXC_UART3_RXD_USDHC3_RESET_B 0x244 0x4AC 0x000 0x2 0x0 +#define MX8MN_IOMUXC_UART3_RXD_GPT1_CAPTURE2 0x244 0x4AC 0x5EC 0x3 0x1 +#define MX8MN_IOMUXC_UART3_RXD_GPIO5_IO26 0x244 0x4AC 0x000 0x5 0x0 +#define MX8MN_IOMUXC_UART3_TXD_UART3_DCE_TX 0x248 0x4B0 0x000 0x0 0x0 +#define MX8MN_IOMUXC_UART3_TXD_UART3_DTE_RX 0x248 0x4B0 0x504 0x0 0x3 +#define MX8MN_IOMUXC_UART3_TXD_UART1_DCE_RTS_B 0x248 0x4B0 0x4F0 0x1 0x1 +#define MX8MN_IOMUXC_UART3_TXD_UART1_DTE_CTS_B 0x248 0x4B0 0x000 0x1 0x0 +#define MX8MN_IOMUXC_UART3_TXD_USDHC3_VSELECT 0x248 0x4B0 0x000 0x2 0x0 +#define MX8MN_IOMUXC_UART3_TXD_GPT1_CLK 0x248 0x4B0 0x5E8 0x3 0x1 +#define MX8MN_IOMUXC_UART3_TXD_GPIO5_IO27 0x248 0x4B0 0x000 0x5 0x0 +#define MX8MN_IOMUXC_UART4_RXD_UART4_DCE_RX 0x24C 0x4B4 0x50C 0x0 0x2 +#define MX8MN_IOMUXC_UART4_RXD_UART4_DTE_TX 0x24C 0x4B4 0x000 0x0 0x0 +#define MX8MN_IOMUXC_UART4_RXD_UART2_DCE_CTS_B 0x24C 0x4B4 0x000 0x1 0x0 +#define MX8MN_IOMUXC_UART4_RXD_UART2_DTE_RTS_B 0x24C 0x4B4 0x4F8 0x1 0x0 +#define MX8MN_IOMUXC_UART4_RXD_GPT1_COMPARE1 0x24C 0x4B4 0x000 0x3 0x0 +#define MX8MN_IOMUXC_UART4_RXD_GPIO5_IO28 0x24C 0x4B4 0x000 0x5 0x0 +#define MX8MN_IOMUXC_UART4_TXD_UART4_DCE_TX 0x250 0x4B8 0x000 0x0 0x0 +#define MX8MN_IOMUXC_UART4_TXD_UART4_DTE_RX 0x250 0x4B8 0x50C 0x0 0x3 +#define MX8MN_IOMUXC_UART4_TXD_UART2_DCE_RTS_B 0x250 0x4B8 0x4F8 0x1 0x1 +#define MX8MN_IOMUXC_UART4_TXD_UART2_DTE_CTS_B 0x250 0x4B8 0x000 0x1 0x0 +#define MX8MN_IOMUXC_UART4_TXD_GPT1_CAPTURE1 0x250 0x4B8 0x5F0 0x3 0x1 +#define MX8MN_IOMUXC_UART4_TXD_GPIO5_IO29 0x250 0x4B8 0x000 0x5 0x0 + +#endif /* __DTS_IMX8MN_PINFUNC_H */ diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h index 570d195a184d..e3a15c751b13 100644 --- a/arch/arm64/include/asm/assembler.h +++ b/arch/arm64/include/asm/assembler.h @@ -96,7 +96,11 @@ * RAS Error Synchronization barrier */ .macro esb +#ifdef CONFIG_ARM64_RAS_EXTN hint #16 +#else + nop +#endif .endm /* diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index 3d8db50d9ae2..407e2bf23676 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -620,6 +620,12 @@ static inline bool system_has_prio_mask_debugging(void) system_uses_irq_prio_masking(); } +#define ARM64_BP_HARDEN_UNKNOWN -1 +#define ARM64_BP_HARDEN_WA_NEEDED 0 +#define ARM64_BP_HARDEN_NOT_REQUIRED 1 + +int get_spectre_v2_workaround_state(void); + #define ARM64_SSBD_UNKNOWN -1 #define ARM64_SSBD_FORCE_DISABLE 0 #define ARM64_SSBD_KERNEL 1 diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h index 2ca437ef59fa..44a243754c1b 100644 --- a/arch/arm64/include/asm/kvm_asm.h +++ b/arch/arm64/include/asm/kvm_asm.h @@ -30,6 +30,12 @@ {ARM_EXCEPTION_TRAP, "TRAP" }, \ {ARM_EXCEPTION_HYP_GONE, "HYP_GONE" } +/* + * Size of the HYP vectors preamble. kvm_patch_vector_branch() generates code + * that jumps over this. + */ +#define KVM_VECTOR_PREAMBLE (2 * AARCH64_INSN_SIZE) + #ifndef __ASSEMBLY__ #include <linux/mm.h> diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index 034dadec7168..d69c1efc63e7 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -126,7 +126,7 @@ static inline unsigned long *__vcpu_elr_el1(const struct kvm_vcpu *vcpu) static inline unsigned long vcpu_read_elr_el1(const struct kvm_vcpu *vcpu) { if (vcpu->arch.sysregs_loaded_on_cpu) - return read_sysreg_el1(elr); + return read_sysreg_el1(SYS_ELR); else return *__vcpu_elr_el1(vcpu); } @@ -134,7 +134,7 @@ static inline unsigned long vcpu_read_elr_el1(const struct kvm_vcpu *vcpu) static inline void vcpu_write_elr_el1(const struct kvm_vcpu *vcpu, unsigned long v) { if (vcpu->arch.sysregs_loaded_on_cpu) - write_sysreg_el1(v, elr); + write_sysreg_el1(v, SYS_ELR); else *__vcpu_elr_el1(vcpu) = v; } @@ -186,7 +186,7 @@ static inline unsigned long vcpu_read_spsr(const struct kvm_vcpu *vcpu) return vcpu_read_spsr32(vcpu); if (vcpu->arch.sysregs_loaded_on_cpu) - return read_sysreg_el1(spsr); + return read_sysreg_el1(SYS_SPSR); else return vcpu_gp_regs(vcpu)->spsr[KVM_SPSR_EL1]; } @@ -199,7 +199,7 @@ static inline void vcpu_write_spsr(struct kvm_vcpu *vcpu, unsigned long v) } if (vcpu->arch.sysregs_loaded_on_cpu) - write_sysreg_el1(v, spsr); + write_sysreg_el1(v, SYS_SPSR); else vcpu_gp_regs(vcpu)->spsr[KVM_SPSR_EL1] = v; } @@ -353,6 +353,20 @@ static inline unsigned long kvm_vcpu_get_mpidr_aff(struct kvm_vcpu *vcpu) return vcpu_read_sys_reg(vcpu, MPIDR_EL1) & MPIDR_HWID_BITMASK; } +static inline bool kvm_arm_get_vcpu_workaround_2_flag(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.workaround_flags & VCPU_WORKAROUND_2_FLAG; +} + +static inline void kvm_arm_set_vcpu_workaround_2_flag(struct kvm_vcpu *vcpu, + bool flag) +{ + if (flag) + vcpu->arch.workaround_flags |= VCPU_WORKAROUND_2_FLAG; + else + vcpu->arch.workaround_flags &= ~VCPU_WORKAROUND_2_FLAG; +} + static inline void kvm_vcpu_set_be(struct kvm_vcpu *vcpu) { if (vcpu_mode_is_32bit(vcpu)) { @@ -451,13 +465,13 @@ static inline void kvm_skip_instr(struct kvm_vcpu *vcpu, bool is_wide_instr) */ static inline void __hyp_text __kvm_skip_instr(struct kvm_vcpu *vcpu) { - *vcpu_pc(vcpu) = read_sysreg_el2(elr); - vcpu->arch.ctxt.gp_regs.regs.pstate = read_sysreg_el2(spsr); + *vcpu_pc(vcpu) = read_sysreg_el2(SYS_ELR); + vcpu->arch.ctxt.gp_regs.regs.pstate = read_sysreg_el2(SYS_SPSR); kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu)); - write_sysreg_el2(vcpu->arch.ctxt.gp_regs.regs.pstate, spsr); - write_sysreg_el2(*vcpu_pc(vcpu), elr); + write_sysreg_el2(vcpu->arch.ctxt.gp_regs.regs.pstate, SYS_SPSR); + write_sysreg_el2(*vcpu_pc(vcpu), SYS_ELR); } #endif /* __ARM64_KVM_EMULATE_H__ */ diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 9f19c354b165..f656169db8c3 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -19,12 +19,12 @@ #include <asm/arch_gicv3.h> #include <asm/barrier.h> #include <asm/cpufeature.h> +#include <asm/cputype.h> #include <asm/daifflags.h> #include <asm/fpsimd.h> #include <asm/kvm.h> #include <asm/kvm_asm.h> #include <asm/kvm_mmio.h> -#include <asm/smp_plat.h> #include <asm/thread_info.h> #define __KVM_HAVE_ARCH_INTC_INITIALIZED @@ -484,11 +484,10 @@ struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr); DECLARE_PER_CPU(kvm_host_data_t, kvm_host_data); -static inline void kvm_init_host_cpu_context(struct kvm_cpu_context *cpu_ctxt, - int cpu) +static inline void kvm_init_host_cpu_context(struct kvm_cpu_context *cpu_ctxt) { /* The host's MPIDR is immutable, so let's set it up at boot time */ - cpu_ctxt->sys_regs[MPIDR_EL1] = cpu_logical_map(cpu); + cpu_ctxt->sys_regs[MPIDR_EL1] = read_cpuid_mpidr(); } void __kvm_enable_ssbs(void); @@ -621,9 +620,21 @@ static inline void kvm_arm_vhe_guest_exit(void) isb(); } -static inline bool kvm_arm_harden_branch_predictor(void) +#define KVM_BP_HARDEN_UNKNOWN -1 +#define KVM_BP_HARDEN_WA_NEEDED 0 +#define KVM_BP_HARDEN_NOT_REQUIRED 1 + +static inline int kvm_arm_harden_branch_predictor(void) { - return cpus_have_const_cap(ARM64_HARDEN_BRANCH_PREDICTOR); + switch (get_spectre_v2_workaround_state()) { + case ARM64_BP_HARDEN_WA_NEEDED: + return KVM_BP_HARDEN_WA_NEEDED; + case ARM64_BP_HARDEN_NOT_REQUIRED: + return KVM_BP_HARDEN_NOT_REQUIRED; + case ARM64_BP_HARDEN_UNKNOWN: + default: + return KVM_BP_HARDEN_UNKNOWN; + } } #define KVM_SSBD_UNKNOWN -1 diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h index 286f7e7e1be4..86825aa20852 100644 --- a/arch/arm64/include/asm/kvm_hyp.h +++ b/arch/arm64/include/asm/kvm_hyp.h @@ -18,7 +18,7 @@ #define read_sysreg_elx(r,nvh,vh) \ ({ \ u64 reg; \ - asm volatile(ALTERNATIVE("mrs %0, " __stringify(r##nvh),\ + asm volatile(ALTERNATIVE(__mrs_s("%0", r##nvh), \ __mrs_s("%0", r##vh), \ ARM64_HAS_VIRT_HOST_EXTN) \ : "=r" (reg)); \ @@ -28,7 +28,7 @@ #define write_sysreg_elx(v,r,nvh,vh) \ do { \ u64 __val = (u64)(v); \ - asm volatile(ALTERNATIVE("msr " __stringify(r##nvh) ", %x0",\ + asm volatile(ALTERNATIVE(__msr_s(r##nvh, "%x0"), \ __msr_s(r##vh, "%x0"), \ ARM64_HAS_VIRT_HOST_EXTN) \ : : "rZ" (__val)); \ @@ -37,55 +37,15 @@ /* * Unified accessors for registers that have a different encoding * between VHE and non-VHE. They must be specified without their "ELx" - * encoding. + * encoding, but with the SYS_ prefix, as defined in asm/sysreg.h. */ -#define read_sysreg_el2(r) \ - ({ \ - u64 reg; \ - asm volatile(ALTERNATIVE("mrs %0, " __stringify(r##_EL2),\ - "mrs %0, " __stringify(r##_EL1),\ - ARM64_HAS_VIRT_HOST_EXTN) \ - : "=r" (reg)); \ - reg; \ - }) - -#define write_sysreg_el2(v,r) \ - do { \ - u64 __val = (u64)(v); \ - asm volatile(ALTERNATIVE("msr " __stringify(r##_EL2) ", %x0",\ - "msr " __stringify(r##_EL1) ", %x0",\ - ARM64_HAS_VIRT_HOST_EXTN) \ - : : "rZ" (__val)); \ - } while (0) #define read_sysreg_el0(r) read_sysreg_elx(r, _EL0, _EL02) #define write_sysreg_el0(v,r) write_sysreg_elx(v, r, _EL0, _EL02) #define read_sysreg_el1(r) read_sysreg_elx(r, _EL1, _EL12) #define write_sysreg_el1(v,r) write_sysreg_elx(v, r, _EL1, _EL12) - -/* The VHE specific system registers and their encoding */ -#define sctlr_EL12 sys_reg(3, 5, 1, 0, 0) -#define cpacr_EL12 sys_reg(3, 5, 1, 0, 2) -#define ttbr0_EL12 sys_reg(3, 5, 2, 0, 0) -#define ttbr1_EL12 sys_reg(3, 5, 2, 0, 1) -#define tcr_EL12 sys_reg(3, 5, 2, 0, 2) -#define afsr0_EL12 sys_reg(3, 5, 5, 1, 0) -#define afsr1_EL12 sys_reg(3, 5, 5, 1, 1) -#define esr_EL12 sys_reg(3, 5, 5, 2, 0) -#define far_EL12 sys_reg(3, 5, 6, 0, 0) -#define mair_EL12 sys_reg(3, 5, 10, 2, 0) -#define amair_EL12 sys_reg(3, 5, 10, 3, 0) -#define vbar_EL12 sys_reg(3, 5, 12, 0, 0) -#define contextidr_EL12 sys_reg(3, 5, 13, 0, 1) -#define cntkctl_EL12 sys_reg(3, 5, 14, 1, 0) -#define cntp_tval_EL02 sys_reg(3, 5, 14, 2, 0) -#define cntp_ctl_EL02 sys_reg(3, 5, 14, 2, 1) -#define cntp_cval_EL02 sys_reg(3, 5, 14, 2, 2) -#define cntv_tval_EL02 sys_reg(3, 5, 14, 3, 0) -#define cntv_ctl_EL02 sys_reg(3, 5, 14, 3, 1) -#define cntv_cval_EL02 sys_reg(3, 5, 14, 3, 2) -#define spsr_EL12 sys_reg(3, 5, 4, 0, 0) -#define elr_EL12 sys_reg(3, 5, 4, 0, 1) +#define read_sysreg_el2(r) read_sysreg_elx(r, _EL2, _EL1) +#define write_sysreg_el2(v,r) write_sysreg_elx(v, r, _EL2, _EL1) /** * hyp_alternate_select - Generates patchable code sequences that are diff --git a/arch/arm64/include/asm/pgalloc.h b/arch/arm64/include/asm/pgalloc.h index cdced518378d..14d0bc44d451 100644 --- a/arch/arm64/include/asm/pgalloc.h +++ b/arch/arm64/include/asm/pgalloc.h @@ -13,18 +13,23 @@ #include <asm/cacheflush.h> #include <asm/tlbflush.h> +#include <asm-generic/pgalloc.h> /* for pte_{alloc,free}_one */ + #define check_pgt_cache() do { } while (0) -#define PGALLOC_GFP (GFP_KERNEL | __GFP_ZERO) #define PGD_SIZE (PTRS_PER_PGD * sizeof(pgd_t)) #if CONFIG_PGTABLE_LEVELS > 2 static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr) { + gfp_t gfp = GFP_PGTABLE_USER; struct page *page; - page = alloc_page(PGALLOC_GFP); + if (mm == &init_mm) + gfp = GFP_PGTABLE_KERNEL; + + page = alloc_page(gfp); if (!page) return NULL; if (!pgtable_pmd_page_ctor(page)) { @@ -61,7 +66,7 @@ static inline void __pud_populate(pud_t *pudp, phys_addr_t pmdp, pudval_t prot) static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr) { - return (pud_t *)__get_free_page(PGALLOC_GFP); + return (pud_t *)__get_free_page(GFP_PGTABLE_USER); } static inline void pud_free(struct mm_struct *mm, pud_t *pudp) @@ -89,42 +94,6 @@ static inline void __pgd_populate(pgd_t *pgdp, phys_addr_t pudp, pgdval_t prot) extern pgd_t *pgd_alloc(struct mm_struct *mm); extern void pgd_free(struct mm_struct *mm, pgd_t *pgdp); -static inline pte_t * -pte_alloc_one_kernel(struct mm_struct *mm) -{ - return (pte_t *)__get_free_page(PGALLOC_GFP); -} - -static inline pgtable_t -pte_alloc_one(struct mm_struct *mm) -{ - struct page *pte; - - pte = alloc_pages(PGALLOC_GFP, 0); - if (!pte) - return NULL; - if (!pgtable_page_ctor(pte)) { - __free_page(pte); - return NULL; - } - return pte; -} - -/* - * Free a PTE table. - */ -static inline void pte_free_kernel(struct mm_struct *mm, pte_t *ptep) -{ - if (ptep) - free_page((unsigned long)ptep); -} - -static inline void pte_free(struct mm_struct *mm, pgtable_t pte) -{ - pgtable_page_dtor(pte); - __free_page(pte); -} - static inline void __pmd_populate(pmd_t *pmdp, phys_addr_t ptep, pmdval_t prot) { diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h index 81693244f58d..b1dd039023ef 100644 --- a/arch/arm64/include/asm/ptrace.h +++ b/arch/arm64/include/asm/ptrace.h @@ -223,11 +223,12 @@ static inline void forget_syscall(struct pt_regs *regs) #define fast_interrupts_enabled(regs) \ (!((regs)->pstate & PSR_F_BIT)) -#define GET_USP(regs) \ - (!compat_user_mode(regs) ? (regs)->sp : (regs)->compat_sp) - -#define SET_USP(ptregs, value) \ - (!compat_user_mode(regs) ? ((regs)->sp = value) : ((regs)->compat_sp = value)) +static inline unsigned long user_stack_pointer(struct pt_regs *regs) +{ + if (compat_user_mode(regs)) + return regs->compat_sp; + return regs->sp; +} extern int regs_query_register_offset(const char *name); extern unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, @@ -326,13 +327,20 @@ static inline unsigned long regs_get_kernel_argument(struct pt_regs *regs, struct task_struct; int valid_user_regs(struct user_pt_regs *regs, struct task_struct *task); -#define GET_IP(regs) ((unsigned long)(regs)->pc) -#define SET_IP(regs, value) ((regs)->pc = ((u64) (value))) - -#define GET_FP(ptregs) ((unsigned long)(ptregs)->regs[29]) -#define SET_FP(ptregs, value) ((ptregs)->regs[29] = ((u64) (value))) +static inline unsigned long instruction_pointer(struct pt_regs *regs) +{ + return regs->pc; +} +static inline void instruction_pointer_set(struct pt_regs *regs, + unsigned long val) +{ + regs->pc = val; +} -#include <asm-generic/ptrace.h> +static inline unsigned long frame_pointer(struct pt_regs *regs) +{ + return regs->regs[29]; +} #define procedure_link_pointer(regs) ((regs)->regs[30]) @@ -342,7 +350,6 @@ static inline void procedure_link_pointer_set(struct pt_regs *regs, procedure_link_pointer(regs) = val; } -#undef profile_pc extern unsigned long profile_pc(struct pt_regs *regs); #endif /* __ASSEMBLY__ */ diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h index d0bd4ffcf2c4..a7522fca1105 100644 --- a/arch/arm64/include/asm/sysreg.h +++ b/arch/arm64/include/asm/sysreg.h @@ -191,6 +191,9 @@ #define SYS_APGAKEYLO_EL1 sys_reg(3, 0, 2, 3, 0) #define SYS_APGAKEYHI_EL1 sys_reg(3, 0, 2, 3, 1) +#define SYS_SPSR_EL1 sys_reg(3, 0, 4, 0, 0) +#define SYS_ELR_EL1 sys_reg(3, 0, 4, 0, 1) + #define SYS_ICC_PMR_EL1 sys_reg(3, 0, 4, 6, 0) #define SYS_AFSR0_EL1 sys_reg(3, 0, 5, 1, 0) @@ -382,6 +385,9 @@ #define SYS_CNTP_CTL_EL0 sys_reg(3, 3, 14, 2, 1) #define SYS_CNTP_CVAL_EL0 sys_reg(3, 3, 14, 2, 2) +#define SYS_CNTV_CTL_EL0 sys_reg(3, 3, 14, 3, 1) +#define SYS_CNTV_CVAL_EL0 sys_reg(3, 3, 14, 3, 2) + #define SYS_AARCH32_CNTP_TVAL sys_reg(0, 0, 14, 2, 0) #define SYS_AARCH32_CNTP_CTL sys_reg(0, 0, 14, 2, 1) #define SYS_AARCH32_CNTP_CVAL sys_reg(0, 2, 0, 14, 0) @@ -392,14 +398,17 @@ #define __TYPER_CRm(n) (0xc | (((n) >> 3) & 0x3)) #define SYS_PMEVTYPERn_EL0(n) sys_reg(3, 3, 14, __TYPER_CRm(n), __PMEV_op2(n)) -#define SYS_PMCCFILTR_EL0 sys_reg (3, 3, 14, 15, 7) +#define SYS_PMCCFILTR_EL0 sys_reg(3, 3, 14, 15, 7) #define SYS_ZCR_EL2 sys_reg(3, 4, 1, 2, 0) - #define SYS_DACR32_EL2 sys_reg(3, 4, 3, 0, 0) +#define SYS_SPSR_EL2 sys_reg(3, 4, 4, 0, 0) +#define SYS_ELR_EL2 sys_reg(3, 4, 4, 0, 1) #define SYS_IFSR32_EL2 sys_reg(3, 4, 5, 0, 1) +#define SYS_ESR_EL2 sys_reg(3, 4, 5, 2, 0) #define SYS_VSESR_EL2 sys_reg(3, 4, 5, 2, 3) #define SYS_FPEXC32_EL2 sys_reg(3, 4, 5, 3, 0) +#define SYS_FAR_EL2 sys_reg(3, 4, 6, 0, 0) #define SYS_VDISR_EL2 sys_reg(3, 4, 12, 1, 1) #define __SYS__AP0Rx_EL2(x) sys_reg(3, 4, 12, 8, x) @@ -444,7 +453,29 @@ #define SYS_ICH_LR15_EL2 __SYS__LR8_EL2(7) /* VHE encodings for architectural EL0/1 system registers */ +#define SYS_SCTLR_EL12 sys_reg(3, 5, 1, 0, 0) +#define SYS_CPACR_EL12 sys_reg(3, 5, 1, 0, 2) #define SYS_ZCR_EL12 sys_reg(3, 5, 1, 2, 0) +#define SYS_TTBR0_EL12 sys_reg(3, 5, 2, 0, 0) +#define SYS_TTBR1_EL12 sys_reg(3, 5, 2, 0, 1) +#define SYS_TCR_EL12 sys_reg(3, 5, 2, 0, 2) +#define SYS_SPSR_EL12 sys_reg(3, 5, 4, 0, 0) +#define SYS_ELR_EL12 sys_reg(3, 5, 4, 0, 1) +#define SYS_AFSR0_EL12 sys_reg(3, 5, 5, 1, 0) +#define SYS_AFSR1_EL12 sys_reg(3, 5, 5, 1, 1) +#define SYS_ESR_EL12 sys_reg(3, 5, 5, 2, 0) +#define SYS_FAR_EL12 sys_reg(3, 5, 6, 0, 0) +#define SYS_MAIR_EL12 sys_reg(3, 5, 10, 2, 0) +#define SYS_AMAIR_EL12 sys_reg(3, 5, 10, 3, 0) +#define SYS_VBAR_EL12 sys_reg(3, 5, 12, 0, 0) +#define SYS_CONTEXTIDR_EL12 sys_reg(3, 5, 13, 0, 1) +#define SYS_CNTKCTL_EL12 sys_reg(3, 5, 14, 1, 0) +#define SYS_CNTP_TVAL_EL02 sys_reg(3, 5, 14, 2, 0) +#define SYS_CNTP_CTL_EL02 sys_reg(3, 5, 14, 2, 1) +#define SYS_CNTP_CVAL_EL02 sys_reg(3, 5, 14, 2, 2) +#define SYS_CNTV_TVAL_EL02 sys_reg(3, 5, 14, 3, 0) +#define SYS_CNTV_CTL_EL02 sys_reg(3, 5, 14, 3, 1) +#define SYS_CNTV_CVAL_EL02 sys_reg(3, 5, 14, 3, 2) /* Common SCTLR_ELx flags. */ #define SCTLR_ELx_DSSBS (_BITUL(44)) diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h index d819a3e8b552..9a507716ae2f 100644 --- a/arch/arm64/include/uapi/asm/kvm.h +++ b/arch/arm64/include/uapi/asm/kvm.h @@ -229,6 +229,16 @@ struct kvm_vcpu_events { #define KVM_REG_ARM_FW_REG(r) (KVM_REG_ARM64 | KVM_REG_SIZE_U64 | \ KVM_REG_ARM_FW | ((r) & 0xffff)) #define KVM_REG_ARM_PSCI_VERSION KVM_REG_ARM_FW_REG(0) +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1 KVM_REG_ARM_FW_REG(1) +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_AVAIL 0 +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_AVAIL 1 +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_REQUIRED 2 +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2 KVM_REG_ARM_FW_REG(2) +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL 0 +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_UNKNOWN 1 +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL 2 +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_REQUIRED 3 +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED (1U << 4) /* SVE registers */ #define KVM_REG_ARM64_SVE (0x15 << KVM_REG_ARM_COPROC_SHIFT) diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index ca11ff7bf55e..1e43ba5c79b7 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -554,6 +554,17 @@ cpu_enable_cache_maint_trap(const struct arm64_cpu_capabilities *__unused) static bool __hardenbp_enab = true; static bool __spectrev2_safe = true; +int get_spectre_v2_workaround_state(void) +{ + if (__spectrev2_safe) + return ARM64_BP_HARDEN_NOT_REQUIRED; + + if (!__hardenbp_enab) + return ARM64_BP_HARDEN_UNKNOWN; + + return ARM64_BP_HARDEN_WA_NEEDED; +} + /* * List of CPUs that do not need any Spectre-v2 mitigation at all. */ @@ -854,13 +865,15 @@ ssize_t cpu_show_spectre_v1(struct device *dev, struct device_attribute *attr, ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr, char *buf) { - if (__spectrev2_safe) + switch (get_spectre_v2_workaround_state()) { + case ARM64_BP_HARDEN_NOT_REQUIRED: return sprintf(buf, "Not affected\n"); - - if (__hardenbp_enab) + case ARM64_BP_HARDEN_WA_NEEDED: return sprintf(buf, "Mitigation: Branch predictor hardening\n"); - - return sprintf(buf, "Vulnerable\n"); + case ARM64_BP_HARDEN_UNKNOWN: + default: + return sprintf(buf, "Vulnerable\n"); + } } ssize_t cpu_show_spec_store_bypass(struct device *dev, diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c index 3c33d0dd8e0e..d0cf596db82c 100644 --- a/arch/arm64/kernel/efi.c +++ b/arch/arm64/kernel/efi.c @@ -82,8 +82,7 @@ int __init efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md) return 0; } -static int __init set_permissions(pte_t *ptep, pgtable_t token, - unsigned long addr, void *data) +static int __init set_permissions(pte_t *ptep, unsigned long addr, void *data) { efi_memory_desc_t *md = data; pte_t pte = READ_ONCE(*ptep); diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index 7e541f947b4c..9c4bad7d7131 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -283,6 +283,11 @@ void __init setup_arch(char **cmdline_p) setup_machine_fdt(__fdt_pointer); + /* + * Initialise the static keys early as they may be enabled by the + * cpufeature code and early parameters. + */ + jump_label_init(); parse_early_param(); /* diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index 9286ee6749e8..ea90d3bd9253 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -420,11 +420,6 @@ void __init smp_cpus_done(unsigned int max_cpus) void __init smp_prepare_boot_cpu(void) { set_my_cpu_offset(per_cpu_offset(smp_processor_id())); - /* - * Initialise the static keys early as they may be enabled by the - * cpufeature code. - */ - jump_label_init(); cpuinfo_store_boot_cpu(); /* diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index 678af745d881..8c03456dade6 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -871,6 +871,10 @@ bool arm64_is_fatal_ras_serror(struct pt_regs *regs, unsigned int esr) /* * The CPU can't make progress. The exception may have * been imprecise. + * + * Neoverse-N1 #1349291 means a non-KVM SError reported as + * Unrecoverable should be treated as Uncontainable. We + * call arm64_serror_panic() in both cases. */ return true; diff --git a/arch/arm64/kvm/hyp/entry.S b/arch/arm64/kvm/hyp/entry.S index bd34016354ba..e5cc8d66bf53 100644 --- a/arch/arm64/kvm/hyp/entry.S +++ b/arch/arm64/kvm/hyp/entry.S @@ -6,6 +6,7 @@ #include <linux/linkage.h> +#include <asm/alternative.h> #include <asm/asm-offsets.h> #include <asm/assembler.h> #include <asm/fpsimdmacros.h> @@ -52,6 +53,20 @@ ENTRY(__guest_enter) // Store the host regs save_callee_saved_regs x1 + // Now the host state is stored if we have a pending RAS SError it must + // affect the host. If any asynchronous exception is pending we defer + // the guest entry. The DSB isn't necessary before v8.2 as any SError + // would be fatal. +alternative_if ARM64_HAS_RAS_EXTN + dsb nshst + isb +alternative_else_nop_endif + mrs x1, isr_el1 + cbz x1, 1f + mov x0, #ARM_EXCEPTION_IRQ + ret + +1: add x18, x0, #VCPU_CONTEXT // Macro ptrauth_switch_to_guest format: @@ -127,8 +142,8 @@ ENTRY(__guest_exit) alternative_if ARM64_HAS_RAS_EXTN // If we have the RAS extensions we can consume a pending error - // without an unmask-SError and isb. - esb + // without an unmask-SError and isb. The ESB-instruction consumed any + // pending guest error when we took the exception from the guest. mrs_s x2, SYS_DISR_EL1 str x2, [x1, #(VCPU_FAULT_DISR - VCPU_CONTEXT)] cbz x2, 1f @@ -136,8 +151,16 @@ alternative_if ARM64_HAS_RAS_EXTN orr x0, x0, #(1<<ARM_EXIT_WITH_SERROR_BIT) 1: ret alternative_else - // If we have a pending asynchronous abort, now is the - // time to find out. From your VAXorcist book, page 666: + dsb sy // Synchronize against in-flight ld/st + isb // Prevent an early read of side-effect free ISR + mrs x2, isr_el1 + tbnz x2, #8, 2f // ISR_EL1.A + ret + nop +2: +alternative_endif + // We know we have a pending asynchronous abort, now is the + // time to flush it out. From your VAXorcist book, page 666: // "Threaten me not, oh Evil one! For I speak with // the power of DEC, and I command thee to show thyself!" mrs x2, elr_el2 @@ -145,10 +168,7 @@ alternative_else mrs x4, spsr_el2 mov x5, x0 - dsb sy // Synchronize against in-flight ld/st - nop msr daifclr, #4 // Unmask aborts -alternative_endif // This is our single instruction exception window. A pending // SError is guaranteed to occur at the earliest when we unmask @@ -161,6 +181,8 @@ abort_guest_exit_start: .global abort_guest_exit_end abort_guest_exit_end: + msr daifset, #4 // Mask aborts + // If the exception took place, restore the EL1 exception // context so that we can report some information. // Merge the exception code with the SError pending bit. diff --git a/arch/arm64/kvm/hyp/hyp-entry.S b/arch/arm64/kvm/hyp/hyp-entry.S index b8e045615961..ffa68d5713f1 100644 --- a/arch/arm64/kvm/hyp/hyp-entry.S +++ b/arch/arm64/kvm/hyp/hyp-entry.S @@ -216,17 +216,34 @@ ENDPROC(\label) .align 11 +.macro check_preamble_length start, end +/* kvm_patch_vector_branch() generates code that jumps over the preamble. */ +.if ((\end-\start) != KVM_VECTOR_PREAMBLE) + .error "KVM vector preamble length mismatch" +.endif +.endm + .macro valid_vect target .align 7 +661: + esb stp x0, x1, [sp, #-16]! +662: b \target + +check_preamble_length 661b, 662b .endm .macro invalid_vect target .align 7 +661: b \target + nop +662: ldp x0, x1, [sp], #16 b \target + +check_preamble_length 661b, 662b .endm ENTRY(__kvm_hyp_vector) @@ -254,13 +271,14 @@ ENDPROC(__kvm_hyp_vector) #ifdef CONFIG_KVM_INDIRECT_VECTORS .macro hyp_ventry .align 7 -1: .rept 27 +1: esb + .rept 26 nop .endr /* * The default sequence is to directly branch to the KVM vectors, * using the computed offset. This applies for VHE as well as - * !ARM64_HARDEN_EL2_VECTORS. + * !ARM64_HARDEN_EL2_VECTORS. The first vector must always run the preamble. * * For ARM64_HARDEN_EL2_VECTORS configurations, this gets replaced * with: @@ -271,12 +289,13 @@ ENDPROC(__kvm_hyp_vector) * movk x0, #((addr >> 32) & 0xffff), lsl #32 * br x0 * - * Where addr = kern_hyp_va(__kvm_hyp_vector) + vector-offset + 4. + * Where: + * addr = kern_hyp_va(__kvm_hyp_vector) + vector-offset + KVM_VECTOR_PREAMBLE. * See kvm_patch_vector_branch for details. */ alternative_cb kvm_patch_vector_branch - b __kvm_hyp_vector + (1b - 0b) - nop + stp x0, x1, [sp, #-16]! + b __kvm_hyp_vector + (1b - 0b + KVM_VECTOR_PREAMBLE) nop nop nop @@ -301,6 +320,7 @@ ENTRY(__bp_harden_hyp_vecs_end) .popsection ENTRY(__smccc_workaround_1_smc_start) + esb sub sp, sp, #(8 * 4) stp x2, x3, [sp, #(8 * 0)] stp x0, x1, [sp, #(8 * 2)] diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c index 58f281b6ca4a..adaf266d8de8 100644 --- a/arch/arm64/kvm/hyp/switch.c +++ b/arch/arm64/kvm/hyp/switch.c @@ -284,7 +284,7 @@ static bool __hyp_text __populate_fault_info(struct kvm_vcpu *vcpu) if (ec != ESR_ELx_EC_DABT_LOW && ec != ESR_ELx_EC_IABT_LOW) return true; - far = read_sysreg_el2(far); + far = read_sysreg_el2(SYS_FAR); /* * The HPFAR can be invalid if the stage 2 fault did not @@ -401,7 +401,7 @@ static bool __hyp_text __hyp_handle_fpsimd(struct kvm_vcpu *vcpu) static bool __hyp_text fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code) { if (ARM_EXCEPTION_CODE(*exit_code) != ARM_EXCEPTION_IRQ) - vcpu->arch.fault.esr_el2 = read_sysreg_el2(esr); + vcpu->arch.fault.esr_el2 = read_sysreg_el2(SYS_ESR); /* * We're using the raw exception code in order to only process @@ -697,8 +697,8 @@ static void __hyp_text __hyp_call_panic_nvhe(u64 spsr, u64 elr, u64 par, asm volatile("ldr %0, =__hyp_panic_string" : "=r" (str_va)); __hyp_do_panic(str_va, - spsr, elr, - read_sysreg(esr_el2), read_sysreg_el2(far), + spsr, elr, + read_sysreg(esr_el2), read_sysreg_el2(SYS_FAR), read_sysreg(hpfar_el2), par, vcpu); } @@ -713,15 +713,15 @@ static void __hyp_call_panic_vhe(u64 spsr, u64 elr, u64 par, panic(__hyp_panic_string, spsr, elr, - read_sysreg_el2(esr), read_sysreg_el2(far), + read_sysreg_el2(SYS_ESR), read_sysreg_el2(SYS_FAR), read_sysreg(hpfar_el2), par, vcpu); } NOKPROBE_SYMBOL(__hyp_call_panic_vhe); void __hyp_text __noreturn hyp_panic(struct kvm_cpu_context *host_ctxt) { - u64 spsr = read_sysreg_el2(spsr); - u64 elr = read_sysreg_el2(elr); + u64 spsr = read_sysreg_el2(SYS_SPSR); + u64 elr = read_sysreg_el2(SYS_ELR); u64 par = read_sysreg(par_el1); if (!has_vhe()) diff --git a/arch/arm64/kvm/hyp/sysreg-sr.c b/arch/arm64/kvm/hyp/sysreg-sr.c index c283f7cbc702..7ddbc849b580 100644 --- a/arch/arm64/kvm/hyp/sysreg-sr.c +++ b/arch/arm64/kvm/hyp/sysreg-sr.c @@ -43,33 +43,33 @@ static void __hyp_text __sysreg_save_user_state(struct kvm_cpu_context *ctxt) static void __hyp_text __sysreg_save_el1_state(struct kvm_cpu_context *ctxt) { ctxt->sys_regs[CSSELR_EL1] = read_sysreg(csselr_el1); - ctxt->sys_regs[SCTLR_EL1] = read_sysreg_el1(sctlr); + ctxt->sys_regs[SCTLR_EL1] = read_sysreg_el1(SYS_SCTLR); ctxt->sys_regs[ACTLR_EL1] = read_sysreg(actlr_el1); - ctxt->sys_regs[CPACR_EL1] = read_sysreg_el1(cpacr); - ctxt->sys_regs[TTBR0_EL1] = read_sysreg_el1(ttbr0); - ctxt->sys_regs[TTBR1_EL1] = read_sysreg_el1(ttbr1); - ctxt->sys_regs[TCR_EL1] = read_sysreg_el1(tcr); - ctxt->sys_regs[ESR_EL1] = read_sysreg_el1(esr); - ctxt->sys_regs[AFSR0_EL1] = read_sysreg_el1(afsr0); - ctxt->sys_regs[AFSR1_EL1] = read_sysreg_el1(afsr1); - ctxt->sys_regs[FAR_EL1] = read_sysreg_el1(far); - ctxt->sys_regs[MAIR_EL1] = read_sysreg_el1(mair); - ctxt->sys_regs[VBAR_EL1] = read_sysreg_el1(vbar); - ctxt->sys_regs[CONTEXTIDR_EL1] = read_sysreg_el1(contextidr); - ctxt->sys_regs[AMAIR_EL1] = read_sysreg_el1(amair); - ctxt->sys_regs[CNTKCTL_EL1] = read_sysreg_el1(cntkctl); + ctxt->sys_regs[CPACR_EL1] = read_sysreg_el1(SYS_CPACR); + ctxt->sys_regs[TTBR0_EL1] = read_sysreg_el1(SYS_TTBR0); + ctxt->sys_regs[TTBR1_EL1] = read_sysreg_el1(SYS_TTBR1); + ctxt->sys_regs[TCR_EL1] = read_sysreg_el1(SYS_TCR); + ctxt->sys_regs[ESR_EL1] = read_sysreg_el1(SYS_ESR); + ctxt->sys_regs[AFSR0_EL1] = read_sysreg_el1(SYS_AFSR0); + ctxt->sys_regs[AFSR1_EL1] = read_sysreg_el1(SYS_AFSR1); + ctxt->sys_regs[FAR_EL1] = read_sysreg_el1(SYS_FAR); + ctxt->sys_regs[MAIR_EL1] = read_sysreg_el1(SYS_MAIR); + ctxt->sys_regs[VBAR_EL1] = read_sysreg_el1(SYS_VBAR); + ctxt->sys_regs[CONTEXTIDR_EL1] = read_sysreg_el1(SYS_CONTEXTIDR); + ctxt->sys_regs[AMAIR_EL1] = read_sysreg_el1(SYS_AMAIR); + ctxt->sys_regs[CNTKCTL_EL1] = read_sysreg_el1(SYS_CNTKCTL); ctxt->sys_regs[PAR_EL1] = read_sysreg(par_el1); ctxt->sys_regs[TPIDR_EL1] = read_sysreg(tpidr_el1); ctxt->gp_regs.sp_el1 = read_sysreg(sp_el1); - ctxt->gp_regs.elr_el1 = read_sysreg_el1(elr); - ctxt->gp_regs.spsr[KVM_SPSR_EL1]= read_sysreg_el1(spsr); + ctxt->gp_regs.elr_el1 = read_sysreg_el1(SYS_ELR); + ctxt->gp_regs.spsr[KVM_SPSR_EL1]= read_sysreg_el1(SYS_SPSR); } static void __hyp_text __sysreg_save_el2_return_state(struct kvm_cpu_context *ctxt) { - ctxt->gp_regs.regs.pc = read_sysreg_el2(elr); - ctxt->gp_regs.regs.pstate = read_sysreg_el2(spsr); + ctxt->gp_regs.regs.pc = read_sysreg_el2(SYS_ELR); + ctxt->gp_regs.regs.pstate = read_sysreg_el2(SYS_SPSR); if (cpus_have_const_cap(ARM64_HAS_RAS_EXTN)) ctxt->sys_regs[DISR_EL1] = read_sysreg_s(SYS_VDISR_EL2); @@ -109,35 +109,35 @@ static void __hyp_text __sysreg_restore_common_state(struct kvm_cpu_context *ctx static void __hyp_text __sysreg_restore_user_state(struct kvm_cpu_context *ctxt) { - write_sysreg(ctxt->sys_regs[TPIDR_EL0], tpidr_el0); - write_sysreg(ctxt->sys_regs[TPIDRRO_EL0], tpidrro_el0); + write_sysreg(ctxt->sys_regs[TPIDR_EL0], tpidr_el0); + write_sysreg(ctxt->sys_regs[TPIDRRO_EL0], tpidrro_el0); } static void __hyp_text __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt) { write_sysreg(ctxt->sys_regs[MPIDR_EL1], vmpidr_el2); write_sysreg(ctxt->sys_regs[CSSELR_EL1], csselr_el1); - write_sysreg_el1(ctxt->sys_regs[SCTLR_EL1], sctlr); - write_sysreg(ctxt->sys_regs[ACTLR_EL1], actlr_el1); - write_sysreg_el1(ctxt->sys_regs[CPACR_EL1], cpacr); - write_sysreg_el1(ctxt->sys_regs[TTBR0_EL1], ttbr0); - write_sysreg_el1(ctxt->sys_regs[TTBR1_EL1], ttbr1); - write_sysreg_el1(ctxt->sys_regs[TCR_EL1], tcr); - write_sysreg_el1(ctxt->sys_regs[ESR_EL1], esr); - write_sysreg_el1(ctxt->sys_regs[AFSR0_EL1], afsr0); - write_sysreg_el1(ctxt->sys_regs[AFSR1_EL1], afsr1); - write_sysreg_el1(ctxt->sys_regs[FAR_EL1], far); - write_sysreg_el1(ctxt->sys_regs[MAIR_EL1], mair); - write_sysreg_el1(ctxt->sys_regs[VBAR_EL1], vbar); - write_sysreg_el1(ctxt->sys_regs[CONTEXTIDR_EL1],contextidr); - write_sysreg_el1(ctxt->sys_regs[AMAIR_EL1], amair); - write_sysreg_el1(ctxt->sys_regs[CNTKCTL_EL1], cntkctl); + write_sysreg_el1(ctxt->sys_regs[SCTLR_EL1], SYS_SCTLR); + write_sysreg(ctxt->sys_regs[ACTLR_EL1], actlr_el1); + write_sysreg_el1(ctxt->sys_regs[CPACR_EL1], SYS_CPACR); + write_sysreg_el1(ctxt->sys_regs[TTBR0_EL1], SYS_TTBR0); + write_sysreg_el1(ctxt->sys_regs[TTBR1_EL1], SYS_TTBR1); + write_sysreg_el1(ctxt->sys_regs[TCR_EL1], SYS_TCR); + write_sysreg_el1(ctxt->sys_regs[ESR_EL1], SYS_ESR); + write_sysreg_el1(ctxt->sys_regs[AFSR0_EL1], SYS_AFSR0); + write_sysreg_el1(ctxt->sys_regs[AFSR1_EL1], SYS_AFSR1); + write_sysreg_el1(ctxt->sys_regs[FAR_EL1], SYS_FAR); + write_sysreg_el1(ctxt->sys_regs[MAIR_EL1], SYS_MAIR); + write_sysreg_el1(ctxt->sys_regs[VBAR_EL1], SYS_VBAR); + write_sysreg_el1(ctxt->sys_regs[CONTEXTIDR_EL1],SYS_CONTEXTIDR); + write_sysreg_el1(ctxt->sys_regs[AMAIR_EL1], SYS_AMAIR); + write_sysreg_el1(ctxt->sys_regs[CNTKCTL_EL1], SYS_CNTKCTL); write_sysreg(ctxt->sys_regs[PAR_EL1], par_el1); write_sysreg(ctxt->sys_regs[TPIDR_EL1], tpidr_el1); write_sysreg(ctxt->gp_regs.sp_el1, sp_el1); - write_sysreg_el1(ctxt->gp_regs.elr_el1, elr); - write_sysreg_el1(ctxt->gp_regs.spsr[KVM_SPSR_EL1],spsr); + write_sysreg_el1(ctxt->gp_regs.elr_el1, SYS_ELR); + write_sysreg_el1(ctxt->gp_regs.spsr[KVM_SPSR_EL1],SYS_SPSR); } static void __hyp_text @@ -160,8 +160,8 @@ __sysreg_restore_el2_return_state(struct kvm_cpu_context *ctxt) if (!(mode & PSR_MODE32_BIT) && mode >= PSR_MODE_EL2t) pstate = PSR_MODE_EL2h | PSR_IL_BIT; - write_sysreg_el2(ctxt->gp_regs.regs.pc, elr); - write_sysreg_el2(pstate, spsr); + write_sysreg_el2(ctxt->gp_regs.regs.pc, SYS_ELR); + write_sysreg_el2(pstate, SYS_SPSR); if (cpus_have_const_cap(ARM64_HAS_RAS_EXTN)) write_sysreg_s(ctxt->sys_regs[DISR_EL1], SYS_VDISR_EL2); diff --git a/arch/arm64/kvm/hyp/tlb.c b/arch/arm64/kvm/hyp/tlb.c index 32078b767f63..d49a14497715 100644 --- a/arch/arm64/kvm/hyp/tlb.c +++ b/arch/arm64/kvm/hyp/tlb.c @@ -33,12 +33,12 @@ static void __hyp_text __tlb_switch_to_guest_vhe(struct kvm *kvm, * in the TCR_EL1 register. We also need to prevent it to * allocate IPA->PA walks, so we enable the S1 MMU... */ - val = cxt->tcr = read_sysreg_el1(tcr); + val = cxt->tcr = read_sysreg_el1(SYS_TCR); val |= TCR_EPD1_MASK | TCR_EPD0_MASK; - write_sysreg_el1(val, tcr); - val = cxt->sctlr = read_sysreg_el1(sctlr); + write_sysreg_el1(val, SYS_TCR); + val = cxt->sctlr = read_sysreg_el1(SYS_SCTLR); val |= SCTLR_ELx_M; - write_sysreg_el1(val, sctlr); + write_sysreg_el1(val, SYS_SCTLR); } /* @@ -85,8 +85,8 @@ static void __hyp_text __tlb_switch_to_host_vhe(struct kvm *kvm, if (cpus_have_const_cap(ARM64_WORKAROUND_1165522)) { /* Restore the registers to what they were */ - write_sysreg_el1(cxt->tcr, tcr); - write_sysreg_el1(cxt->sctlr, sctlr); + write_sysreg_el1(cxt->tcr, SYS_TCR); + write_sysreg_el1(cxt->sctlr, SYS_SCTLR); } local_irq_restore(cxt->flags); diff --git a/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c b/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c index ba2aaeb84c6c..29ee1feba4eb 100644 --- a/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c +++ b/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c @@ -16,7 +16,7 @@ static bool __hyp_text __is_be(struct kvm_vcpu *vcpu) { if (vcpu_mode_is_32bit(vcpu)) - return !!(read_sysreg_el2(spsr) & PSR_AA32_E_BIT); + return !!(read_sysreg_el2(SYS_SPSR) & PSR_AA32_E_BIT); return !!(read_sysreg(SCTLR_EL1) & SCTLR_ELx_EE); } diff --git a/arch/arm64/kvm/regmap.c b/arch/arm64/kvm/regmap.c index d66613e6ad08..0d60e4f0af66 100644 --- a/arch/arm64/kvm/regmap.c +++ b/arch/arm64/kvm/regmap.c @@ -152,7 +152,7 @@ unsigned long vcpu_read_spsr32(const struct kvm_vcpu *vcpu) switch (spsr_idx) { case KVM_SPSR_SVC: - return read_sysreg_el1(spsr); + return read_sysreg_el1(SYS_SPSR); case KVM_SPSR_ABT: return read_sysreg(spsr_abt); case KVM_SPSR_UND: @@ -177,7 +177,7 @@ void vcpu_write_spsr32(struct kvm_vcpu *vcpu, unsigned long v) switch (spsr_idx) { case KVM_SPSR_SVC: - write_sysreg_el1(v, spsr); + write_sysreg_el1(v, SYS_SPSR); case KVM_SPSR_ABT: write_sysreg(v, spsr_abt); case KVM_SPSR_UND: diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index ce933f296049..f26e181d881c 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -81,24 +81,24 @@ u64 vcpu_read_sys_reg(const struct kvm_vcpu *vcpu, int reg) */ switch (reg) { case CSSELR_EL1: return read_sysreg_s(SYS_CSSELR_EL1); - case SCTLR_EL1: return read_sysreg_s(sctlr_EL12); + case SCTLR_EL1: return read_sysreg_s(SYS_SCTLR_EL12); case ACTLR_EL1: return read_sysreg_s(SYS_ACTLR_EL1); - case CPACR_EL1: return read_sysreg_s(cpacr_EL12); - case TTBR0_EL1: return read_sysreg_s(ttbr0_EL12); - case TTBR1_EL1: return read_sysreg_s(ttbr1_EL12); - case TCR_EL1: return read_sysreg_s(tcr_EL12); - case ESR_EL1: return read_sysreg_s(esr_EL12); - case AFSR0_EL1: return read_sysreg_s(afsr0_EL12); - case AFSR1_EL1: return read_sysreg_s(afsr1_EL12); - case FAR_EL1: return read_sysreg_s(far_EL12); - case MAIR_EL1: return read_sysreg_s(mair_EL12); - case VBAR_EL1: return read_sysreg_s(vbar_EL12); - case CONTEXTIDR_EL1: return read_sysreg_s(contextidr_EL12); + case CPACR_EL1: return read_sysreg_s(SYS_CPACR_EL12); + case TTBR0_EL1: return read_sysreg_s(SYS_TTBR0_EL12); + case TTBR1_EL1: return read_sysreg_s(SYS_TTBR1_EL12); + case TCR_EL1: return read_sysreg_s(SYS_TCR_EL12); + case ESR_EL1: return read_sysreg_s(SYS_ESR_EL12); + case AFSR0_EL1: return read_sysreg_s(SYS_AFSR0_EL12); + case AFSR1_EL1: return read_sysreg_s(SYS_AFSR1_EL12); + case FAR_EL1: return read_sysreg_s(SYS_FAR_EL12); + case MAIR_EL1: return read_sysreg_s(SYS_MAIR_EL12); + case VBAR_EL1: return read_sysreg_s(SYS_VBAR_EL12); + case CONTEXTIDR_EL1: return read_sysreg_s(SYS_CONTEXTIDR_EL12); case TPIDR_EL0: return read_sysreg_s(SYS_TPIDR_EL0); case TPIDRRO_EL0: return read_sysreg_s(SYS_TPIDRRO_EL0); case TPIDR_EL1: return read_sysreg_s(SYS_TPIDR_EL1); - case AMAIR_EL1: return read_sysreg_s(amair_EL12); - case CNTKCTL_EL1: return read_sysreg_s(cntkctl_EL12); + case AMAIR_EL1: return read_sysreg_s(SYS_AMAIR_EL12); + case CNTKCTL_EL1: return read_sysreg_s(SYS_CNTKCTL_EL12); case PAR_EL1: return read_sysreg_s(SYS_PAR_EL1); case DACR32_EL2: return read_sysreg_s(SYS_DACR32_EL2); case IFSR32_EL2: return read_sysreg_s(SYS_IFSR32_EL2); @@ -124,24 +124,24 @@ void vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, int reg) */ switch (reg) { case CSSELR_EL1: write_sysreg_s(val, SYS_CSSELR_EL1); return; - case SCTLR_EL1: write_sysreg_s(val, sctlr_EL12); return; + case SCTLR_EL1: write_sysreg_s(val, SYS_SCTLR_EL12); return; case ACTLR_EL1: write_sysreg_s(val, SYS_ACTLR_EL1); return; - case CPACR_EL1: write_sysreg_s(val, cpacr_EL12); return; - case TTBR0_EL1: write_sysreg_s(val, ttbr0_EL12); return; - case TTBR1_EL1: write_sysreg_s(val, ttbr1_EL12); return; - case TCR_EL1: write_sysreg_s(val, tcr_EL12); return; - case ESR_EL1: write_sysreg_s(val, esr_EL12); return; - case AFSR0_EL1: write_sysreg_s(val, afsr0_EL12); return; - case AFSR1_EL1: write_sysreg_s(val, afsr1_EL12); return; - case FAR_EL1: write_sysreg_s(val, far_EL12); return; - case MAIR_EL1: write_sysreg_s(val, mair_EL12); return; - case VBAR_EL1: write_sysreg_s(val, vbar_EL12); return; - case CONTEXTIDR_EL1: write_sysreg_s(val, contextidr_EL12); return; + case CPACR_EL1: write_sysreg_s(val, SYS_CPACR_EL12); return; + case TTBR0_EL1: write_sysreg_s(val, SYS_TTBR0_EL12); return; + case TTBR1_EL1: write_sysreg_s(val, SYS_TTBR1_EL12); return; + case TCR_EL1: write_sysreg_s(val, SYS_TCR_EL12); return; + case ESR_EL1: write_sysreg_s(val, SYS_ESR_EL12); return; + case AFSR0_EL1: write_sysreg_s(val, SYS_AFSR0_EL12); return; + case AFSR1_EL1: write_sysreg_s(val, SYS_AFSR1_EL12); return; + case FAR_EL1: write_sysreg_s(val, SYS_FAR_EL12); return; + case MAIR_EL1: write_sysreg_s(val, SYS_MAIR_EL12); return; + case VBAR_EL1: write_sysreg_s(val, SYS_VBAR_EL12); return; + case CONTEXTIDR_EL1: write_sysreg_s(val, SYS_CONTEXTIDR_EL12); return; case TPIDR_EL0: write_sysreg_s(val, SYS_TPIDR_EL0); return; case TPIDRRO_EL0: write_sysreg_s(val, SYS_TPIDRRO_EL0); return; case TPIDR_EL1: write_sysreg_s(val, SYS_TPIDR_EL1); return; - case AMAIR_EL1: write_sysreg_s(val, amair_EL12); return; - case CNTKCTL_EL1: write_sysreg_s(val, cntkctl_EL12); return; + case AMAIR_EL1: write_sysreg_s(val, SYS_AMAIR_EL12); return; + case CNTKCTL_EL1: write_sysreg_s(val, SYS_CNTKCTL_EL12); return; case PAR_EL1: write_sysreg_s(val, SYS_PAR_EL1); return; case DACR32_EL2: write_sysreg_s(val, SYS_DACR32_EL2); return; case IFSR32_EL2: write_sysreg_s(val, SYS_IFSR32_EL2); return; @@ -865,12 +865,12 @@ static bool access_pmcnten(struct kvm_vcpu *vcpu, struct sys_reg_params *p, if (r->Op2 & 0x1) { /* accessing PMCNTENSET_EL0 */ __vcpu_sys_reg(vcpu, PMCNTENSET_EL0) |= val; - kvm_pmu_enable_counter(vcpu, val); + kvm_pmu_enable_counter_mask(vcpu, val); kvm_vcpu_pmu_restore_guest(vcpu); } else { /* accessing PMCNTENCLR_EL0 */ __vcpu_sys_reg(vcpu, PMCNTENSET_EL0) &= ~val; - kvm_pmu_disable_counter(vcpu, val); + kvm_pmu_disable_counter_mask(vcpu, val); } } else { p->regval = __vcpu_sys_reg(vcpu, PMCNTENSET_EL0) & mask; diff --git a/arch/arm64/kvm/va_layout.c b/arch/arm64/kvm/va_layout.c index 2947ab1b0fa5..acd8084f1f2c 100644 --- a/arch/arm64/kvm/va_layout.c +++ b/arch/arm64/kvm/va_layout.c @@ -170,11 +170,10 @@ void kvm_patch_vector_branch(struct alt_instr *alt, addr |= ((u64)origptr & GENMASK_ULL(10, 7)); /* - * Branch to the second instruction in the vectors in order to - * avoid the initial store on the stack (which we already - * perform in the hardening vectors). + * Branch over the preamble in order to avoid the initial store on + * the stack (which we already perform in the hardening vectors). */ - addr += AARCH64_INSN_SIZE; + addr += KVM_VECTOR_PREAMBLE; /* stp x0, x1, [sp, #-16]! */ insn = aarch64_insn_gen_load_store_pair(AARCH64_INSN_REG_0, diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 3645f29bd814..1b49c08dfa2b 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -362,7 +362,7 @@ static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys, static phys_addr_t __pgd_pgtable_alloc(int shift) { - void *ptr = (void *)__get_free_page(PGALLOC_GFP); + void *ptr = (void *)__get_free_page(GFP_PGTABLE_KERNEL); BUG_ON(!ptr); /* Ensure the zeroed page is visible to the page table walker */ diff --git a/arch/arm64/mm/pageattr.c b/arch/arm64/mm/pageattr.c index fcdcf6cd7677..03c53f16ee77 100644 --- a/arch/arm64/mm/pageattr.c +++ b/arch/arm64/mm/pageattr.c @@ -19,8 +19,7 @@ struct page_change_data { bool rodata_full __ro_after_init = IS_ENABLED(CONFIG_RODATA_FULL_DEFAULT_ENABLED); -static int change_page_range(pte_t *ptep, pgtable_t token, unsigned long addr, - void *data) +static int change_page_range(pte_t *ptep, unsigned long addr, void *data) { struct page_change_data *cdata = data; pte_t pte = READ_ONCE(*ptep); diff --git a/arch/arm64/mm/pgd.c b/arch/arm64/mm/pgd.c index 9a0c7d5090d6..7548f9ca1f11 100644 --- a/arch/arm64/mm/pgd.c +++ b/arch/arm64/mm/pgd.c @@ -19,10 +19,12 @@ static struct kmem_cache *pgd_cache __ro_after_init; pgd_t *pgd_alloc(struct mm_struct *mm) { + gfp_t gfp = GFP_PGTABLE_USER; + if (PGD_SIZE == PAGE_SIZE) - return (pgd_t *)__get_free_page(PGALLOC_GFP); + return (pgd_t *)__get_free_page(gfp); else - return kmem_cache_alloc(pgd_cache, PGALLOC_GFP); + return kmem_cache_alloc(pgd_cache, gfp); } void pgd_free(struct mm_struct *mm, pgd_t *pgd) diff --git a/arch/csky/Makefile b/arch/csky/Makefile index f9aab9157c4a..fb1bbbd91954 100644 --- a/arch/csky/Makefile +++ b/arch/csky/Makefile @@ -1,7 +1,6 @@ # SPDX-License-Identifier: GPL-2.0-only OBJCOPYFLAGS :=-O binary GZFLAGS :=-9 -KBUILD_DEFCONFIG := defconfig ifdef CONFIG_CPU_HAS_FPU FPUEXT = f diff --git a/arch/csky/include/asm/pgalloc.h b/arch/csky/include/asm/pgalloc.h index d213bb47b717..98c5716708d6 100644 --- a/arch/csky/include/asm/pgalloc.h +++ b/arch/csky/include/asm/pgalloc.h @@ -8,6 +8,9 @@ #include <linux/mm.h> #include <linux/sched.h> +#define __HAVE_ARCH_PTE_ALLOC_ONE_KERNEL +#include <asm-generic/pgalloc.h> /* for pte_{alloc,free}_one */ + static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, pte_t *pte) { @@ -39,33 +42,6 @@ static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm) return pte; } -static inline struct page *pte_alloc_one(struct mm_struct *mm) -{ - struct page *pte; - - pte = alloc_pages(GFP_KERNEL | __GFP_ZERO, 0); - if (!pte) - return NULL; - - if (!pgtable_page_ctor(pte)) { - __free_page(pte); - return NULL; - } - - return pte; -} - -static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) -{ - free_pages((unsigned long)pte, PTE_ORDER); -} - -static inline void pte_free(struct mm_struct *mm, pgtable_t pte) -{ - pgtable_page_dtor(pte); - __free_pages(pte, PTE_ORDER); -} - static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) { free_pages((unsigned long)pgd, PGD_ORDER); diff --git a/arch/m68k/include/asm/sun3_pgalloc.h b/arch/m68k/include/asm/sun3_pgalloc.h index 1456c5eecbd9..1a8ddbd0d23c 100644 --- a/arch/m68k/include/asm/sun3_pgalloc.h +++ b/arch/m68k/include/asm/sun3_pgalloc.h @@ -13,55 +13,18 @@ #include <asm/tlb.h> +#include <asm-generic/pgalloc.h> /* for pte_{alloc,free}_one */ + extern const char bad_pmd_string[]; #define pmd_alloc_one(mm,address) ({ BUG(); ((pmd_t *)2); }) - -static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) -{ - free_page((unsigned long) pte); -} - -static inline void pte_free(struct mm_struct *mm, pgtable_t page) -{ - pgtable_page_dtor(page); - __free_page(page); -} - #define __pte_free_tlb(tlb,pte,addr) \ do { \ pgtable_page_dtor(pte); \ tlb_remove_page((tlb), pte); \ } while (0) -static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm) -{ - unsigned long page = __get_free_page(GFP_KERNEL); - - if (!page) - return NULL; - - memset((void *)page, 0, PAGE_SIZE); - return (pte_t *) (page); -} - -static inline pgtable_t pte_alloc_one(struct mm_struct *mm) -{ - struct page *page = alloc_pages(GFP_KERNEL, 0); - - if (page == NULL) - return NULL; - - clear_highpage(page); - if (!pgtable_page_ctor(page)) { - __free_page(page); - return NULL; - } - return page; - -} - static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, pte_t *pte) { pmd_val(*pmd) = __pa((unsigned long)pte); diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 70d3200476bf..d50fafd7bf3a 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -34,6 +34,7 @@ config MIPS select GENERIC_SCHED_CLOCK if !CAVIUM_OCTEON_SOC select GENERIC_SMP_IDLE_THREAD select GENERIC_TIME_VSYSCALL + select GUP_GET_PTE_LOW_HIGH if CPU_MIPS32 && PHYS_ADDR_T_64BIT select HANDLE_DOMAIN_IRQ select HAVE_ARCH_COMPILER_H select HAVE_ARCH_JUMP_LABEL @@ -52,6 +53,7 @@ config MIPS select HAVE_DMA_CONTIGUOUS select HAVE_DYNAMIC_FTRACE select HAVE_EXIT_THREAD + select HAVE_FAST_GUP select HAVE_FTRACE_MCOUNT_RECORD select HAVE_FUNCTION_GRAPH_TRACER select HAVE_FUNCTION_TRACER @@ -1119,6 +1121,7 @@ config DMA_NONCOHERENT bool select ARCH_HAS_DMA_MMAP_PGPROT select ARCH_HAS_SYNC_DMA_FOR_DEVICE + select ARCH_HAS_UNCACHED_SEGMENT select NEED_DMA_MAP_STATE select ARCH_HAS_DMA_COHERENT_TO_PFN select DMA_NONCOHERENT_CACHE_SYNC diff --git a/arch/mips/include/asm/page.h b/arch/mips/include/asm/page.h index a25643d258cb..0ba4ce6e2bf3 100644 --- a/arch/mips/include/asm/page.h +++ b/arch/mips/include/asm/page.h @@ -258,9 +258,6 @@ extern bool __virt_addr_valid(const volatile void *kaddr); ((current->personality & READ_IMPLIES_EXEC) ? VM_EXEC : 0) | \ VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC) -#define UNCAC_ADDR(addr) (UNCAC_BASE + __pa(addr)) -#define CAC_ADDR(addr) ((unsigned long)__va((addr) - UNCAC_BASE)) - #include <asm-generic/memory_model.h> #include <asm-generic/getorder.h> diff --git a/arch/mips/include/asm/pgalloc.h b/arch/mips/include/asm/pgalloc.h index 27808d9461f4..aa16b85ddffc 100644 --- a/arch/mips/include/asm/pgalloc.h +++ b/arch/mips/include/asm/pgalloc.h @@ -13,6 +13,8 @@ #include <linux/mm.h> #include <linux/sched.h> +#include <asm-generic/pgalloc.h> /* for pte_{alloc,free}_one */ + static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, pte_t *pte) { @@ -50,37 +52,6 @@ static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) free_pages((unsigned long)pgd, PGD_ORDER); } -static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm) -{ - return (pte_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, PTE_ORDER); -} - -static inline struct page *pte_alloc_one(struct mm_struct *mm) -{ - struct page *pte; - - pte = alloc_pages(GFP_KERNEL, PTE_ORDER); - if (!pte) - return NULL; - clear_highpage(pte); - if (!pgtable_page_ctor(pte)) { - __free_page(pte); - return NULL; - } - return pte; -} - -static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) -{ - free_pages((unsigned long)pte, PTE_ORDER); -} - -static inline void pte_free(struct mm_struct *mm, pgtable_t pte) -{ - pgtable_page_dtor(pte); - __free_pages(pte, PTE_ORDER); -} - #define __pte_free_tlb(tlb,pte,address) \ do { \ pgtable_page_dtor(pte); \ diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h index 4ccb465ef3f2..7d27194e3b45 100644 --- a/arch/mips/include/asm/pgtable.h +++ b/arch/mips/include/asm/pgtable.h @@ -20,6 +20,7 @@ #include <asm/cmpxchg.h> #include <asm/io.h> #include <asm/pgtable-bits.h> +#include <asm/cpu-features.h> struct mm_struct; struct vm_area_struct; @@ -626,6 +627,8 @@ static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ +#define gup_fast_permitted(start, end) (!cpu_has_dc_aliases) + #include <asm-generic/pgtable.h> /* diff --git a/arch/mips/include/asm/ptrace.h b/arch/mips/include/asm/ptrace.h index b6578611dddb..1e76774b36dd 100644 --- a/arch/mips/include/asm/ptrace.h +++ b/arch/mips/include/asm/ptrace.h @@ -56,11 +56,6 @@ static inline unsigned long kernel_stack_pointer(struct pt_regs *regs) return regs->regs[31]; } -/* - * Don't use asm-generic/ptrace.h it defines FP accessors that don't make - * sense on MIPS. We rather want an error if they get invoked. - */ - static inline void instruction_pointer_set(struct pt_regs *regs, unsigned long val) { diff --git a/arch/mips/jazz/jazzdma.c b/arch/mips/jazz/jazzdma.c index bedb5047aff3..1804dc9d8136 100644 --- a/arch/mips/jazz/jazzdma.c +++ b/arch/mips/jazz/jazzdma.c @@ -575,10 +575,6 @@ static void *jazz_dma_alloc(struct device *dev, size_t size, return NULL; } - if (!(attrs & DMA_ATTR_NON_CONSISTENT)) { - dma_cache_wback_inv((unsigned long)ret, size); - ret = (void *)UNCAC_ADDR(ret); - } return ret; } @@ -586,8 +582,6 @@ static void jazz_dma_free(struct device *dev, size_t size, void *vaddr, dma_addr_t dma_handle, unsigned long attrs) { vdma_free(dma_handle); - if (!(attrs & DMA_ATTR_NON_CONSISTENT)) - vaddr = (void *)CAC_ADDR((unsigned long)vaddr); dma_direct_free_pages(dev, size, vaddr, dma_handle, attrs); } diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c index 0369f26ab96d..2cfe839f0b3a 100644 --- a/arch/mips/kvm/mips.c +++ b/arch/mips/kvm/mips.c @@ -123,9 +123,9 @@ int kvm_arch_hardware_setup(void) return 0; } -void kvm_arch_check_processor_compat(void *rtn) +int kvm_arch_check_processor_compat(void) { - *(int *)rtn = 0; + return 0; } int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) diff --git a/arch/mips/mm/Makefile b/arch/mips/mm/Makefile index f34d7ff5eb60..1e8d335025d7 100644 --- a/arch/mips/mm/Makefile +++ b/arch/mips/mm/Makefile @@ -7,7 +7,6 @@ obj-y += cache.o obj-y += context.o obj-y += extable.o obj-y += fault.o -obj-y += gup.o obj-y += init.o obj-y += mmap.o obj-y += page.o diff --git a/arch/mips/mm/cache.c b/arch/mips/mm/cache.c index 3da216988672..33b409391ddb 100644 --- a/arch/mips/mm/cache.c +++ b/arch/mips/mm/cache.c @@ -62,8 +62,6 @@ void (*_dma_cache_wback_inv)(unsigned long start, unsigned long size); void (*_dma_cache_wback)(unsigned long start, unsigned long size); void (*_dma_cache_inv)(unsigned long start, unsigned long size); -EXPORT_SYMBOL(_dma_cache_wback_inv); - #endif /* CONFIG_DMA_NONCOHERENT */ /* diff --git a/arch/mips/mm/dma-noncoherent.c b/arch/mips/mm/dma-noncoherent.c index f9549d2fbea3..ed56c6fa7be2 100644 --- a/arch/mips/mm/dma-noncoherent.c +++ b/arch/mips/mm/dma-noncoherent.c @@ -44,33 +44,25 @@ static inline bool cpu_needs_post_dma_flush(struct device *dev) } } -void *arch_dma_alloc(struct device *dev, size_t size, - dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs) +void arch_dma_prep_coherent(struct page *page, size_t size) { - void *ret; - - ret = dma_direct_alloc_pages(dev, size, dma_handle, gfp, attrs); - if (ret && !(attrs & DMA_ATTR_NON_CONSISTENT)) { - dma_cache_wback_inv((unsigned long) ret, size); - ret = (void *)UNCAC_ADDR(ret); - } + dma_cache_wback_inv((unsigned long)page_address(page), size); +} - return ret; +void *uncached_kernel_address(void *addr) +{ + return (void *)(__pa(addr) + UNCAC_BASE); } -void arch_dma_free(struct device *dev, size_t size, void *cpu_addr, - dma_addr_t dma_addr, unsigned long attrs) +void *cached_kernel_address(void *addr) { - if (!(attrs & DMA_ATTR_NON_CONSISTENT)) - cpu_addr = (void *)CAC_ADDR((unsigned long)cpu_addr); - dma_direct_free_pages(dev, size, cpu_addr, dma_addr, attrs); + return __va(addr) - UNCAC_BASE; } long arch_dma_coherent_to_pfn(struct device *dev, void *cpu_addr, dma_addr_t dma_addr) { - unsigned long addr = CAC_ADDR((unsigned long)cpu_addr); - return page_to_pfn(virt_to_page((void *)addr)); + return page_to_pfn(virt_to_page(cached_kernel_address(cpu_addr))); } pgprot_t arch_dma_mmap_pgprot(struct device *dev, pgprot_t prot, diff --git a/arch/mips/mm/gup.c b/arch/mips/mm/gup.c deleted file mode 100644 index 4c2b4483683c..000000000000 --- a/arch/mips/mm/gup.c +++ /dev/null @@ -1,303 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Lockless get_user_pages_fast for MIPS - * - * Copyright (C) 2008 Nick Piggin - * Copyright (C) 2008 Novell Inc. - * Copyright (C) 2011 Ralf Baechle - */ -#include <linux/sched.h> -#include <linux/mm.h> -#include <linux/vmstat.h> -#include <linux/highmem.h> -#include <linux/swap.h> -#include <linux/hugetlb.h> - -#include <asm/cpu-features.h> -#include <asm/pgtable.h> - -static inline pte_t gup_get_pte(pte_t *ptep) -{ -#if defined(CONFIG_PHYS_ADDR_T_64BIT) && defined(CONFIG_CPU_MIPS32) - pte_t pte; - -retry: - pte.pte_low = ptep->pte_low; - smp_rmb(); - pte.pte_high = ptep->pte_high; - smp_rmb(); - if (unlikely(pte.pte_low != ptep->pte_low)) - goto retry; - - return pte; -#else - return READ_ONCE(*ptep); -#endif -} - -static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end, - int write, struct page **pages, int *nr) -{ - pte_t *ptep = pte_offset_map(&pmd, addr); - do { - pte_t pte = gup_get_pte(ptep); - struct page *page; - - if (!pte_present(pte) || - pte_special(pte) || (write && !pte_write(pte))) { - pte_unmap(ptep); - return 0; - } - VM_BUG_ON(!pfn_valid(pte_pfn(pte))); - page = pte_page(pte); - get_page(page); - SetPageReferenced(page); - pages[*nr] = page; - (*nr)++; - - } while (ptep++, addr += PAGE_SIZE, addr != end); - - pte_unmap(ptep - 1); - return 1; -} - -static inline void get_head_page_multiple(struct page *page, int nr) -{ - VM_BUG_ON(page != compound_head(page)); - VM_BUG_ON(page_count(page) == 0); - page_ref_add(page, nr); - SetPageReferenced(page); -} - -static int gup_huge_pmd(pmd_t pmd, unsigned long addr, unsigned long end, - int write, struct page **pages, int *nr) -{ - pte_t pte = *(pte_t *)&pmd; - struct page *head, *page; - int refs; - - if (write && !pte_write(pte)) - return 0; - /* hugepages are never "special" */ - VM_BUG_ON(pte_special(pte)); - VM_BUG_ON(!pfn_valid(pte_pfn(pte))); - - refs = 0; - head = pte_page(pte); - page = head + ((addr & ~PMD_MASK) >> PAGE_SHIFT); - do { - VM_BUG_ON(compound_head(page) != head); - pages[*nr] = page; - (*nr)++; - page++; - refs++; - } while (addr += PAGE_SIZE, addr != end); - - get_head_page_multiple(head, refs); - return 1; -} - -static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end, - int write, struct page **pages, int *nr) -{ - unsigned long next; - pmd_t *pmdp; - - pmdp = pmd_offset(&pud, addr); - do { - pmd_t pmd = *pmdp; - - next = pmd_addr_end(addr, end); - if (pmd_none(pmd)) - return 0; - if (unlikely(pmd_huge(pmd))) { - if (!gup_huge_pmd(pmd, addr, next, write, pages,nr)) - return 0; - } else { - if (!gup_pte_range(pmd, addr, next, write, pages,nr)) - return 0; - } - } while (pmdp++, addr = next, addr != end); - - return 1; -} - -static int gup_huge_pud(pud_t pud, unsigned long addr, unsigned long end, - int write, struct page **pages, int *nr) -{ - pte_t pte = *(pte_t *)&pud; - struct page *head, *page; - int refs; - - if (write && !pte_write(pte)) - return 0; - /* hugepages are never "special" */ - VM_BUG_ON(pte_special(pte)); - VM_BUG_ON(!pfn_valid(pte_pfn(pte))); - - refs = 0; - head = pte_page(pte); - page = head + ((addr & ~PUD_MASK) >> PAGE_SHIFT); - do { - VM_BUG_ON(compound_head(page) != head); - pages[*nr] = page; - (*nr)++; - page++; - refs++; - } while (addr += PAGE_SIZE, addr != end); - - get_head_page_multiple(head, refs); - return 1; -} - -static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end, - int write, struct page **pages, int *nr) -{ - unsigned long next; - pud_t *pudp; - - pudp = pud_offset(&pgd, addr); - do { - pud_t pud = *pudp; - - next = pud_addr_end(addr, end); - if (pud_none(pud)) - return 0; - if (unlikely(pud_huge(pud))) { - if (!gup_huge_pud(pud, addr, next, write, pages,nr)) - return 0; - } else { - if (!gup_pmd_range(pud, addr, next, write, pages,nr)) - return 0; - } - } while (pudp++, addr = next, addr != end); - - return 1; -} - -/* - * Like get_user_pages_fast() except its IRQ-safe in that it won't fall - * back to the regular GUP. - * Note a difference with get_user_pages_fast: this always returns the - * number of pages pinned, 0 if no pages were pinned. - */ -int __get_user_pages_fast(unsigned long start, int nr_pages, int write, - struct page **pages) -{ - struct mm_struct *mm = current->mm; - unsigned long addr, len, end; - unsigned long next; - unsigned long flags; - pgd_t *pgdp; - int nr = 0; - - start &= PAGE_MASK; - addr = start; - len = (unsigned long) nr_pages << PAGE_SHIFT; - end = start + len; - if (unlikely(!access_ok((void __user *)start, len))) - return 0; - - /* - * XXX: batch / limit 'nr', to avoid large irq off latency - * needs some instrumenting to determine the common sizes used by - * important workloads (eg. DB2), and whether limiting the batch - * size will decrease performance. - * - * It seems like we're in the clear for the moment. Direct-IO is - * the main guy that batches up lots of get_user_pages, and even - * they are limited to 64-at-a-time which is not so many. - */ - /* - * This doesn't prevent pagetable teardown, but does prevent - * the pagetables and pages from being freed. - * - * So long as we atomically load page table pointers versus teardown, - * we can follow the address down to the page and take a ref on it. - */ - local_irq_save(flags); - pgdp = pgd_offset(mm, addr); - do { - pgd_t pgd = *pgdp; - - next = pgd_addr_end(addr, end); - if (pgd_none(pgd)) - break; - if (!gup_pud_range(pgd, addr, next, write, pages, &nr)) - break; - } while (pgdp++, addr = next, addr != end); - local_irq_restore(flags); - - return nr; -} - -/** - * get_user_pages_fast() - pin user pages in memory - * @start: starting user address - * @nr_pages: number of pages from start to pin - * @gup_flags: flags modifying pin behaviour - * @pages: array that receives pointers to the pages pinned. - * Should be at least nr_pages long. - * - * Attempt to pin user pages in memory without taking mm->mmap_sem. - * If not successful, it will fall back to taking the lock and - * calling get_user_pages(). - * - * Returns number of pages pinned. This may be fewer than the number - * requested. If nr_pages is 0 or negative, returns 0. If no pages - * were pinned, returns -errno. - */ -int get_user_pages_fast(unsigned long start, int nr_pages, - unsigned int gup_flags, struct page **pages) -{ - struct mm_struct *mm = current->mm; - unsigned long addr, len, end; - unsigned long next; - pgd_t *pgdp; - int ret, nr = 0; - - start &= PAGE_MASK; - addr = start; - len = (unsigned long) nr_pages << PAGE_SHIFT; - - end = start + len; - if (end < start || cpu_has_dc_aliases) - goto slow_irqon; - - /* XXX: batch / limit 'nr' */ - local_irq_disable(); - pgdp = pgd_offset(mm, addr); - do { - pgd_t pgd = *pgdp; - - next = pgd_addr_end(addr, end); - if (pgd_none(pgd)) - goto slow; - if (!gup_pud_range(pgd, addr, next, gup_flags & FOLL_WRITE, - pages, &nr)) - goto slow; - } while (pgdp++, addr = next, addr != end); - local_irq_enable(); - - VM_BUG_ON(nr != (end - start) >> PAGE_SHIFT); - return nr; -slow: - local_irq_enable(); - -slow_irqon: - /* Try to get the remaining pages with get_user_pages */ - start += nr << PAGE_SHIFT; - pages += nr; - - ret = get_user_pages_unlocked(start, (end - start) >> PAGE_SHIFT, - pages, gup_flags); - - /* Have to be a bit careful with return values */ - if (nr > 0) { - if (ret < 0) - ret = nr; - else - ret += nr; - } - return ret; -} diff --git a/arch/nds32/Kconfig b/arch/nds32/Kconfig index fd0d0639454f..fbd68329737f 100644 --- a/arch/nds32/Kconfig +++ b/arch/nds32/Kconfig @@ -7,12 +7,14 @@ config NDS32 def_bool y select ARCH_32BIT_OFF_T + select ARCH_HAS_DMA_PREP_COHERENT select ARCH_HAS_SYNC_DMA_FOR_CPU select ARCH_HAS_SYNC_DMA_FOR_DEVICE select ARCH_WANT_FRAME_POINTERS if FTRACE select CLKSRC_MMIO select CLONE_BACKWARDS select COMMON_CLK + select DMA_DIRECT_REMAP select GENERIC_ATOMIC64 select GENERIC_CPU_DEVICES select GENERIC_CLOCKEVENTS diff --git a/arch/nds32/Makefile b/arch/nds32/Makefile index 14dab5ad88ef..ccdca7142020 100644 --- a/arch/nds32/Makefile +++ b/arch/nds32/Makefile @@ -2,8 +2,6 @@ LDFLAGS_vmlinux := --no-undefined -X OBJCOPYFLAGS := -O binary -R .note -R .note.gnu.build-id -R .comment -S -KBUILD_DEFCONFIG := defconfig - ifdef CONFIG_FUNCTION_TRACER arch-y += -malways-save-lp -mno-relax endif diff --git a/arch/nds32/configs/defconfig b/arch/nds32/configs/defconfig index 65ce9259081b..40313a635075 100644 --- a/arch/nds32/configs/defconfig +++ b/arch/nds32/configs/defconfig @@ -92,6 +92,7 @@ CONFIG_DEBUG_INFO=y CONFIG_DEBUG_INFO_DWARF4=y CONFIG_GDB_SCRIPTS=y CONFIG_READABLE_ASM=y +CONFIG_HEADERS_INSTALL=y CONFIG_HEADERS_CHECK=y CONFIG_DEBUG_SECTION_MISMATCH=y CONFIG_MAGIC_SYSRQ=y diff --git a/arch/nds32/include/asm/pgalloc.h b/arch/nds32/include/asm/pgalloc.h index 3cbc749c79aa..e78b43d8389f 100644 --- a/arch/nds32/include/asm/pgalloc.h +++ b/arch/nds32/include/asm/pgalloc.h @@ -9,6 +9,9 @@ #include <asm/tlbflush.h> #include <asm/proc-fns.h> +#define __HAVE_ARCH_PTE_ALLOC_ONE +#include <asm-generic/pgalloc.h> /* for pte_{alloc,free}_one */ + /* * Since we have only two-level page tables, these are trivial */ @@ -22,22 +25,11 @@ extern void pgd_free(struct mm_struct *mm, pgd_t * pgd); #define check_pgt_cache() do { } while (0) -static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm) -{ - pte_t *pte; - - pte = - (pte_t *) __get_free_page(GFP_KERNEL | __GFP_RETRY_MAYFAIL | - __GFP_ZERO); - - return pte; -} - static inline pgtable_t pte_alloc_one(struct mm_struct *mm) { pgtable_t pte; - pte = alloc_pages(GFP_KERNEL | __GFP_RETRY_MAYFAIL | __GFP_ZERO, 0); + pte = __pte_alloc_one(mm, GFP_PGTABLE_USER); if (pte) cpu_dcache_wb_page((unsigned long)page_address(pte)); @@ -45,21 +37,6 @@ static inline pgtable_t pte_alloc_one(struct mm_struct *mm) } /* - * Free one PTE table. - */ -static inline void pte_free_kernel(struct mm_struct *mm, pte_t * pte) -{ - if (pte) { - free_page((unsigned long)pte); - } -} - -static inline void pte_free(struct mm_struct *mm, pgtable_t pte) -{ - __free_page(pte); -} - -/* * Populate the pmdp entry with a pointer to the pte. This pmd is part * of the mm address space. * diff --git a/arch/nds32/kernel/dma.c b/arch/nds32/kernel/dma.c index d0dbd4fe9645..490e3720d694 100644 --- a/arch/nds32/kernel/dma.c +++ b/arch/nds32/kernel/dma.c @@ -3,327 +3,13 @@ #include <linux/types.h> #include <linux/mm.h> -#include <linux/string.h> #include <linux/dma-noncoherent.h> -#include <linux/io.h> #include <linux/cache.h> #include <linux/highmem.h> -#include <linux/slab.h> #include <asm/cacheflush.h> #include <asm/tlbflush.h> #include <asm/proc-fns.h> -/* - * This is the page table (2MB) covering uncached, DMA consistent allocations - */ -static pte_t *consistent_pte; -static DEFINE_RAW_SPINLOCK(consistent_lock); - -/* - * VM region handling support. - * - * This should become something generic, handling VM region allocations for - * vmalloc and similar (ioremap, module space, etc). - * - * I envisage vmalloc()'s supporting vm_struct becoming: - * - * struct vm_struct { - * struct vm_region region; - * unsigned long flags; - * struct page **pages; - * unsigned int nr_pages; - * unsigned long phys_addr; - * }; - * - * get_vm_area() would then call vm_region_alloc with an appropriate - * struct vm_region head (eg): - * - * struct vm_region vmalloc_head = { - * .vm_list = LIST_HEAD_INIT(vmalloc_head.vm_list), - * .vm_start = VMALLOC_START, - * .vm_end = VMALLOC_END, - * }; - * - * However, vmalloc_head.vm_start is variable (typically, it is dependent on - * the amount of RAM found at boot time.) I would imagine that get_vm_area() - * would have to initialise this each time prior to calling vm_region_alloc(). - */ -struct arch_vm_region { - struct list_head vm_list; - unsigned long vm_start; - unsigned long vm_end; - struct page *vm_pages; -}; - -static struct arch_vm_region consistent_head = { - .vm_list = LIST_HEAD_INIT(consistent_head.vm_list), - .vm_start = CONSISTENT_BASE, - .vm_end = CONSISTENT_END, -}; - -static struct arch_vm_region *vm_region_alloc(struct arch_vm_region *head, - size_t size, int gfp) -{ - unsigned long addr = head->vm_start, end = head->vm_end - size; - unsigned long flags; - struct arch_vm_region *c, *new; - - new = kmalloc(sizeof(struct arch_vm_region), gfp); - if (!new) - goto out; - - raw_spin_lock_irqsave(&consistent_lock, flags); - - list_for_each_entry(c, &head->vm_list, vm_list) { - if ((addr + size) < addr) - goto nospc; - if ((addr + size) <= c->vm_start) - goto found; - addr = c->vm_end; - if (addr > end) - goto nospc; - } - -found: - /* - * Insert this entry _before_ the one we found. - */ - list_add_tail(&new->vm_list, &c->vm_list); - new->vm_start = addr; - new->vm_end = addr + size; - - raw_spin_unlock_irqrestore(&consistent_lock, flags); - return new; - -nospc: - raw_spin_unlock_irqrestore(&consistent_lock, flags); - kfree(new); -out: - return NULL; -} - -static struct arch_vm_region *vm_region_find(struct arch_vm_region *head, - unsigned long addr) -{ - struct arch_vm_region *c; - - list_for_each_entry(c, &head->vm_list, vm_list) { - if (c->vm_start == addr) - goto out; - } - c = NULL; -out: - return c; -} - -void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, - gfp_t gfp, unsigned long attrs) -{ - struct page *page; - struct arch_vm_region *c; - unsigned long order; - u64 mask = ~0ULL, limit; - pgprot_t prot = pgprot_noncached(PAGE_KERNEL); - - if (!consistent_pte) { - pr_err("%s: not initialized\n", __func__); - dump_stack(); - return NULL; - } - - if (dev) { - mask = dev->coherent_dma_mask; - - /* - * Sanity check the DMA mask - it must be non-zero, and - * must be able to be satisfied by a DMA allocation. - */ - if (mask == 0) { - dev_warn(dev, "coherent DMA mask is unset\n"); - goto no_page; - } - - } - - /* - * Sanity check the allocation size. - */ - size = PAGE_ALIGN(size); - limit = (mask + 1) & ~mask; - if ((limit && size >= limit) || - size >= (CONSISTENT_END - CONSISTENT_BASE)) { - pr_warn("coherent allocation too big " - "(requested %#x mask %#llx)\n", size, mask); - goto no_page; - } - - order = get_order(size); - - if (mask != 0xffffffff) - gfp |= GFP_DMA; - - page = alloc_pages(gfp, order); - if (!page) - goto no_page; - - /* - * Invalidate any data that might be lurking in the - * kernel direct-mapped region for device DMA. - */ - { - unsigned long kaddr = (unsigned long)page_address(page); - memset(page_address(page), 0, size); - cpu_dma_wbinval_range(kaddr, kaddr + size); - } - - /* - * Allocate a virtual address in the consistent mapping region. - */ - c = vm_region_alloc(&consistent_head, size, - gfp & ~(__GFP_DMA | __GFP_HIGHMEM)); - if (c) { - pte_t *pte = consistent_pte + CONSISTENT_OFFSET(c->vm_start); - struct page *end = page + (1 << order); - - c->vm_pages = page; - - /* - * Set the "dma handle" - */ - *handle = page_to_phys(page); - - do { - BUG_ON(!pte_none(*pte)); - - /* - * x86 does not mark the pages reserved... - */ - SetPageReserved(page); - set_pte(pte, mk_pte(page, prot)); - page++; - pte++; - } while (size -= PAGE_SIZE); - - /* - * Free the otherwise unused pages. - */ - while (page < end) { - __free_page(page); - page++; - } - - return (void *)c->vm_start; - } - - if (page) - __free_pages(page, order); -no_page: - *handle = ~0; - return NULL; -} - -void arch_dma_free(struct device *dev, size_t size, void *cpu_addr, - dma_addr_t handle, unsigned long attrs) -{ - struct arch_vm_region *c; - unsigned long flags, addr; - pte_t *ptep; - - size = PAGE_ALIGN(size); - - raw_spin_lock_irqsave(&consistent_lock, flags); - - c = vm_region_find(&consistent_head, (unsigned long)cpu_addr); - if (!c) - goto no_area; - - if ((c->vm_end - c->vm_start) != size) { - pr_err("%s: freeing wrong coherent size (%ld != %d)\n", - __func__, c->vm_end - c->vm_start, size); - dump_stack(); - size = c->vm_end - c->vm_start; - } - - ptep = consistent_pte + CONSISTENT_OFFSET(c->vm_start); - addr = c->vm_start; - do { - pte_t pte = ptep_get_and_clear(&init_mm, addr, ptep); - unsigned long pfn; - - ptep++; - addr += PAGE_SIZE; - - if (!pte_none(pte) && pte_present(pte)) { - pfn = pte_pfn(pte); - - if (pfn_valid(pfn)) { - struct page *page = pfn_to_page(pfn); - - /* - * x86 does not mark the pages reserved... - */ - ClearPageReserved(page); - - __free_page(page); - continue; - } - } - - pr_crit("%s: bad page in kernel page table\n", __func__); - } while (size -= PAGE_SIZE); - - flush_tlb_kernel_range(c->vm_start, c->vm_end); - - list_del(&c->vm_list); - - raw_spin_unlock_irqrestore(&consistent_lock, flags); - - kfree(c); - return; - -no_area: - raw_spin_unlock_irqrestore(&consistent_lock, flags); - pr_err("%s: trying to free invalid coherent area: %p\n", - __func__, cpu_addr); - dump_stack(); -} - -/* - * Initialise the consistent memory allocation. - */ -static int __init consistent_init(void) -{ - pgd_t *pgd; - pmd_t *pmd; - pte_t *pte; - int ret = 0; - - do { - pgd = pgd_offset(&init_mm, CONSISTENT_BASE); - pmd = pmd_alloc(&init_mm, pgd, CONSISTENT_BASE); - if (!pmd) { - pr_err("%s: no pmd tables\n", __func__); - ret = -ENOMEM; - break; - } - /* The first level mapping may be created in somewhere. - * It's not necessary to warn here. */ - /* WARN_ON(!pmd_none(*pmd)); */ - - pte = pte_alloc_kernel(pmd, CONSISTENT_BASE); - if (!pte) { - ret = -ENOMEM; - break; - } - - consistent_pte = pte; - } while (0); - - return ret; -} - -core_initcall(consistent_init); - static inline void cache_op(phys_addr_t paddr, size_t size, void (*fn)(unsigned long start, unsigned long end)) { @@ -389,3 +75,14 @@ void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr, BUG(); } } + +void arch_dma_prep_coherent(struct page *page, size_t size) +{ + cache_op(page_to_phys(page), size, cpu_dma_wbinval_range); +} + +static int __init atomic_pool_init(void) +{ + return dma_atomic_pool_init(GFP_KERNEL, pgprot_noncached(PAGE_KERNEL)); +} +postcore_initcall(atomic_pool_init); diff --git a/arch/nios2/Kconfig b/arch/nios2/Kconfig index 26a9c760a98b..44b5da37e8bd 100644 --- a/arch/nios2/Kconfig +++ b/arch/nios2/Kconfig @@ -4,6 +4,7 @@ config NIOS2 select ARCH_32BIT_OFF_T select ARCH_HAS_SYNC_DMA_FOR_CPU select ARCH_HAS_SYNC_DMA_FOR_DEVICE + select ARCH_HAS_UNCACHED_SEGMENT select ARCH_NO_SWAP select TIMER_OF select GENERIC_ATOMIC64 diff --git a/arch/nios2/Kconfig.debug b/arch/nios2/Kconfig.debug index f1da8a7b17ff..a8bc06e96ef5 100644 --- a/arch/nios2/Kconfig.debug +++ b/arch/nios2/Kconfig.debug @@ -1,8 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 -config TRACE_IRQFLAGS_SUPPORT - def_bool y - config EARLY_PRINTK bool "Activate early kernel debugging" default y diff --git a/arch/nios2/configs/10m50_defconfig b/arch/nios2/configs/10m50_defconfig index 7977ab7e2ca6..1137ef2ed3b0 100644 --- a/arch/nios2/configs/10m50_defconfig +++ b/arch/nios2/configs/10m50_defconfig @@ -35,7 +35,6 @@ CONFIG_IP_PNP_RARP=y # CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_IPV6 is not set # CONFIG_WIRELESS is not set -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_DEVTMPFS=y CONFIG_DEVTMPFS_MOUNT=y # CONFIG_FW_LOADER is not set diff --git a/arch/nios2/configs/3c120_defconfig b/arch/nios2/configs/3c120_defconfig index ceb97cd85ac1..a0f160ba7598 100644 --- a/arch/nios2/configs/3c120_defconfig +++ b/arch/nios2/configs/3c120_defconfig @@ -37,7 +37,6 @@ CONFIG_IP_PNP_RARP=y # CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_IPV6 is not set # CONFIG_WIRELESS is not set -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_DEVTMPFS=y CONFIG_DEVTMPFS_MOUNT=y # CONFIG_FW_LOADER is not set diff --git a/arch/nios2/include/asm/page.h b/arch/nios2/include/asm/page.h index f1fbdc47bdaf..79fcac61f6ef 100644 --- a/arch/nios2/include/asm/page.h +++ b/arch/nios2/include/asm/page.h @@ -101,12 +101,6 @@ static inline bool pfn_valid(unsigned long pfn) # define VM_DATA_DEFAULT_FLAGS (VM_READ | VM_WRITE | \ VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC) -# define UNCAC_ADDR(addr) \ - ((void *)((unsigned)(addr) | CONFIG_NIOS2_IO_REGION_BASE)) -# define CAC_ADDR(addr) \ - ((void *)(((unsigned)(addr) & ~CONFIG_NIOS2_IO_REGION_BASE) | \ - CONFIG_NIOS2_KERNEL_REGION_BASE)) - #include <asm-generic/memory_model.h> #include <asm-generic/getorder.h> diff --git a/arch/nios2/include/asm/pgalloc.h b/arch/nios2/include/asm/pgalloc.h index 3a149ead1207..4bc8cf72067e 100644 --- a/arch/nios2/include/asm/pgalloc.h +++ b/arch/nios2/include/asm/pgalloc.h @@ -12,6 +12,8 @@ #include <linux/mm.h> +#include <asm-generic/pgalloc.h> /* for pte_{alloc,free}_one */ + static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, pte_t *pte) { @@ -37,41 +39,6 @@ static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) free_pages((unsigned long)pgd, PGD_ORDER); } -static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm) -{ - pte_t *pte; - - pte = (pte_t *) __get_free_pages(GFP_KERNEL|__GFP_ZERO, PTE_ORDER); - - return pte; -} - -static inline pgtable_t pte_alloc_one(struct mm_struct *mm) -{ - struct page *pte; - - pte = alloc_pages(GFP_KERNEL, PTE_ORDER); - if (pte) { - if (!pgtable_page_ctor(pte)) { - __free_page(pte); - return NULL; - } - clear_highpage(pte); - } - return pte; -} - -static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) -{ - free_pages((unsigned long)pte, PTE_ORDER); -} - -static inline void pte_free(struct mm_struct *mm, struct page *pte) -{ - pgtable_page_dtor(pte); - __free_pages(pte, PTE_ORDER); -} - #define __pte_free_tlb(tlb, pte, addr) \ do { \ pgtable_page_dtor(pte); \ diff --git a/arch/nios2/mm/dma-mapping.c b/arch/nios2/mm/dma-mapping.c index 4af9e5b5ba1c..9cb238664584 100644 --- a/arch/nios2/mm/dma-mapping.c +++ b/arch/nios2/mm/dma-mapping.c @@ -60,32 +60,28 @@ void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr, } } -void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, - gfp_t gfp, unsigned long attrs) +void arch_dma_prep_coherent(struct page *page, size_t size) { - void *ret; + unsigned long start = (unsigned long)page_address(page); - /* optimized page clearing */ - gfp |= __GFP_ZERO; + flush_dcache_range(start, start + size); +} - if (dev == NULL || (dev->coherent_dma_mask < 0xffffffff)) - gfp |= GFP_DMA; +void *uncached_kernel_address(void *ptr) +{ + unsigned long addr = (unsigned long)ptr; - ret = (void *) __get_free_pages(gfp, get_order(size)); - if (ret != NULL) { - *dma_handle = virt_to_phys(ret); - flush_dcache_range((unsigned long) ret, - (unsigned long) ret + size); - ret = UNCAC_ADDR(ret); - } + addr |= CONFIG_NIOS2_IO_REGION_BASE; - return ret; + return (void *)ptr; } -void arch_dma_free(struct device *dev, size_t size, void *vaddr, - dma_addr_t dma_handle, unsigned long attrs) +void *cached_kernel_address(void *ptr) { - unsigned long addr = (unsigned long) CAC_ADDR((unsigned long) vaddr); + unsigned long addr = (unsigned long)ptr; + + addr &= ~CONFIG_NIOS2_IO_REGION_BASE; + addr |= CONFIG_NIOS2_KERNEL_REGION_BASE; - free_pages(addr, get_order(size)); + return (void *)ptr; } diff --git a/arch/openrisc/kernel/dma.c b/arch/openrisc/kernel/dma.c index 43e340c4cd9c..b41a79fcdbd9 100644 --- a/arch/openrisc/kernel/dma.c +++ b/arch/openrisc/kernel/dma.c @@ -94,15 +94,13 @@ arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, va = (unsigned long)page; - if ((attrs & DMA_ATTR_NON_CONSISTENT) == 0) { - /* - * We need to iterate through the pages, clearing the dcache for - * them and setting the cache-inhibit bit. - */ - if (walk_page_range(va, va + size, &walk)) { - free_pages_exact(page, size); - return NULL; - } + /* + * We need to iterate through the pages, clearing the dcache for + * them and setting the cache-inhibit bit. + */ + if (walk_page_range(va, va + size, &walk)) { + free_pages_exact(page, size); + return NULL; } return (void *)va; @@ -118,10 +116,8 @@ arch_dma_free(struct device *dev, size_t size, void *vaddr, .mm = &init_mm }; - if ((attrs & DMA_ATTR_NON_CONSISTENT) == 0) { - /* walk_page_range shouldn't be able to fail here */ - WARN_ON(walk_page_range(va, va + size, &walk)); - } + /* walk_page_range shouldn't be able to fail here */ + WARN_ON(walk_page_range(va, va + size, &walk)); free_pages_exact(vaddr, size); } diff --git a/arch/parisc/Makefile b/arch/parisc/Makefile index 58d46665cad9..8acb8fa1f8d6 100644 --- a/arch/parisc/Makefile +++ b/arch/parisc/Makefile @@ -120,8 +120,8 @@ PALO := $(shell if (which palo 2>&1); then : ; \ elif [ -x /sbin/palo ]; then echo /sbin/palo; \ fi) -PALOCONF := $(shell if [ -f $(src)/palo.conf ]; then echo $(src)/palo.conf; \ - else echo $(obj)/palo.conf; \ +PALOCONF := $(shell if [ -f $(srctree)/palo.conf ]; then echo $(srctree)/palo.conf; \ + else echo $(objtree)/palo.conf; \ fi) palo lifimage: vmlinuz @@ -131,8 +131,8 @@ palo lifimage: vmlinuz false; \ fi @if test ! -f "$(PALOCONF)"; then \ - cp $(src)/arch/parisc/defpalo.conf $(obj)/palo.conf; \ - echo 'A generic palo config file ($(obj)/palo.conf) has been created for you.'; \ + cp $(srctree)/arch/parisc/defpalo.conf $(objtree)/palo.conf; \ + echo 'A generic palo config file ($(objree)/palo.conf) has been created for you.'; \ echo 'You should check it and re-run "make palo".'; \ echo 'WARNING: the "lifimage" file is now placed in this directory by default!'; \ false; \ @@ -162,10 +162,10 @@ vmlinuz: vmlinux endif install: - $(CONFIG_SHELL) $(src)/arch/parisc/install.sh \ + $(CONFIG_SHELL) $(srctree)/arch/parisc/install.sh \ $(KERNELRELEASE) vmlinux System.map "$(INSTALL_PATH)" zinstall: - $(CONFIG_SHELL) $(src)/arch/parisc/install.sh \ + $(CONFIG_SHELL) $(srctree)/arch/parisc/install.sh \ $(KERNELRELEASE) vmlinuz System.map "$(INSTALL_PATH)" CLEAN_FILES += lifimage diff --git a/arch/parisc/configs/a500_defconfig b/arch/parisc/configs/a500_defconfig index a8859496b0b9..3335734bfadd 100644 --- a/arch/parisc/configs/a500_defconfig +++ b/arch/parisc/configs/a500_defconfig @@ -166,6 +166,7 @@ CONFIG_NLS_ISO8859_1=m CONFIG_NLS_ISO8859_15=m CONFIG_NLS_UTF8=m CONFIG_DEBUG_FS=y +CONFIG_HEADERS_INSTALL=y CONFIG_HEADERS_CHECK=y CONFIG_MAGIC_SYSRQ=y # CONFIG_DEBUG_BUGVERBOSE is not set diff --git a/arch/parisc/configs/b180_defconfig b/arch/parisc/configs/b180_defconfig index 0cae9664bf67..07fde5bd6974 100644 --- a/arch/parisc/configs/b180_defconfig +++ b/arch/parisc/configs/b180_defconfig @@ -90,6 +90,7 @@ CONFIG_NLS_ASCII=m CONFIG_NLS_ISO8859_1=m CONFIG_NLS_ISO8859_15=m CONFIG_NLS_UTF8=m +CONFIG_HEADERS_INSTALL=y CONFIG_HEADERS_CHECK=y CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_KERNEL=y diff --git a/arch/parisc/configs/c3000_defconfig b/arch/parisc/configs/c3000_defconfig index 6c29b841735c..64d45a8b6ca0 100644 --- a/arch/parisc/configs/c3000_defconfig +++ b/arch/parisc/configs/c3000_defconfig @@ -139,6 +139,7 @@ CONFIG_NLS_ISO8859_1=m CONFIG_NLS_ISO8859_15=m CONFIG_NLS_UTF8=m CONFIG_DEBUG_FS=y +CONFIG_HEADERS_INSTALL=y CONFIG_HEADERS_CHECK=y CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_MUTEXES=y diff --git a/arch/parisc/configs/default_defconfig b/arch/parisc/configs/default_defconfig index 6a91cc2623e8..5b877ca34ebf 100644 --- a/arch/parisc/configs/default_defconfig +++ b/arch/parisc/configs/default_defconfig @@ -183,6 +183,7 @@ CONFIG_NLS_KOI8_R=m CONFIG_NLS_KOI8_U=m CONFIG_NLS_UTF8=y CONFIG_DEBUG_FS=y +CONFIG_HEADERS_INSTALL=y CONFIG_HEADERS_CHECK=y CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_KERNEL=y diff --git a/arch/parisc/include/asm/pgalloc.h b/arch/parisc/include/asm/pgalloc.h index ea75cc966dae..4f2059a50fae 100644 --- a/arch/parisc/include/asm/pgalloc.h +++ b/arch/parisc/include/asm/pgalloc.h @@ -10,6 +10,8 @@ #include <asm/cache.h> +#include <asm-generic/pgalloc.h> /* for pte_{alloc,free}_one */ + /* Allocate the top level pgd (page directory) * * Here (for 64 bit kernels) we implement a Hybrid L2/L3 scheme: we @@ -122,37 +124,6 @@ pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, pte_t *pte) pmd_populate_kernel(mm, pmd, page_address(pte_page)) #define pmd_pgtable(pmd) pmd_page(pmd) -static inline pgtable_t -pte_alloc_one(struct mm_struct *mm) -{ - struct page *page = alloc_page(GFP_KERNEL|__GFP_ZERO); - if (!page) - return NULL; - if (!pgtable_page_ctor(page)) { - __free_page(page); - return NULL; - } - return page; -} - -static inline pte_t * -pte_alloc_one_kernel(struct mm_struct *mm) -{ - pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_ZERO); - return pte; -} - -static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) -{ - free_page((unsigned long)pte); -} - -static inline void pte_free(struct mm_struct *mm, struct page *pte) -{ - pgtable_page_dtor(pte); - pte_free_kernel(mm, page_address(pte)); -} - #define check_pgt_cache() do { } while (0) #endif diff --git a/arch/parisc/kernel/pci-dma.c b/arch/parisc/kernel/pci-dma.c index 239162355b58..ca35d9a76e50 100644 --- a/arch/parisc/kernel/pci-dma.c +++ b/arch/parisc/kernel/pci-dma.c @@ -394,17 +394,20 @@ pcxl_dma_init(void) __initcall(pcxl_dma_init); -static void *pcxl_dma_alloc(struct device *dev, size_t size, - dma_addr_t *dma_handle, gfp_t flag, unsigned long attrs) +void *arch_dma_alloc(struct device *dev, size_t size, + dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs) { unsigned long vaddr; unsigned long paddr; int order; + if (boot_cpu_data.cpu_type != pcxl2 && boot_cpu_data.cpu_type != pcxl) + return NULL; + order = get_order(size); size = 1 << (order + PAGE_SHIFT); vaddr = pcxl_alloc_range(size); - paddr = __get_free_pages(flag | __GFP_ZERO, order); + paddr = __get_free_pages(gfp | __GFP_ZERO, order); flush_kernel_dcache_range(paddr, size); paddr = __pa(paddr); map_uncached_pages(vaddr, size, paddr); @@ -421,44 +424,19 @@ static void *pcxl_dma_alloc(struct device *dev, size_t size, return (void *)vaddr; } -static void *pcx_dma_alloc(struct device *dev, size_t size, - dma_addr_t *dma_handle, gfp_t flag, unsigned long attrs) -{ - void *addr; - - if ((attrs & DMA_ATTR_NON_CONSISTENT) == 0) - return NULL; - - addr = (void *)__get_free_pages(flag | __GFP_ZERO, get_order(size)); - if (addr) - *dma_handle = (dma_addr_t)virt_to_phys(addr); - - return addr; -} - -void *arch_dma_alloc(struct device *dev, size_t size, - dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs) -{ - - if (boot_cpu_data.cpu_type == pcxl2 || boot_cpu_data.cpu_type == pcxl) - return pcxl_dma_alloc(dev, size, dma_handle, gfp, attrs); - else - return pcx_dma_alloc(dev, size, dma_handle, gfp, attrs); -} - void arch_dma_free(struct device *dev, size_t size, void *vaddr, dma_addr_t dma_handle, unsigned long attrs) { int order = get_order(size); - if (boot_cpu_data.cpu_type == pcxl2 || boot_cpu_data.cpu_type == pcxl) { - size = 1 << (order + PAGE_SHIFT); - unmap_uncached_pages((unsigned long)vaddr, size); - pcxl_free_range((unsigned long)vaddr, size); + WARN_ON_ONCE(boot_cpu_data.cpu_type != pcxl2 && + boot_cpu_data.cpu_type != pcxl); - vaddr = __va(dma_handle); - } - free_pages((unsigned long)vaddr, get_order(size)); + size = 1 << (order + PAGE_SHIFT); + unmap_uncached_pages((unsigned long)vaddr, size); + pcxl_free_range((unsigned long)vaddr, size); + + free_pages((unsigned long)__va(dma_handle), order); } void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr, diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 3b795a0cab62..f516796dd819 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -48,7 +48,7 @@ config ARCH_MMAP_RND_COMPAT_BITS_MAX # Allow randomisation to consume up to 512MB of address space (2^29). default 11 if PPC_256K_PAGES # 11 = 29 (512MB) - 18 (256K) default 13 if PPC_64K_PAGES # 13 = 29 (512MB) - 16 (64K) - default 15 if PPC_16K_PAGES # 15 = 29 (512MB) - 14 (16K) + default 15 if PPC_16K_PAGES # 15 = 29 (512MB) - 14 (16K) default 17 # 17 = 29 (512MB) - 12 (4K) config ARCH_MMAP_RND_COMPAT_BITS_MIN @@ -125,6 +125,7 @@ config PPC select ARCH_HAS_FORTIFY_SOURCE select ARCH_HAS_GCOV_PROFILE_ALL select ARCH_HAS_KCOV + select ARCH_HAS_HUGEPD if HUGETLB_PAGE select ARCH_HAS_MMIOWB if PPC64 select ARCH_HAS_PHYS_TO_DMA select ARCH_HAS_PMEM_API if PPC64 @@ -167,6 +168,7 @@ config PPC select GENERIC_STRNLEN_USER select GENERIC_TIME_VSYSCALL select HAVE_ARCH_AUDITSYSCALL + select HAVE_ARCH_HUGE_VMAP if PPC_BOOK3S_64 && PPC_RADIX_MMU select HAVE_ARCH_JUMP_LABEL select HAVE_ARCH_KASAN if PPC32 select HAVE_ARCH_KGDB @@ -175,6 +177,7 @@ config PPC select HAVE_ARCH_NVRAM_OPS select HAVE_ARCH_SECCOMP_FILTER select HAVE_ARCH_TRACEHOOK + select HAVE_C_RECORDMCOUNT select HAVE_CBPF_JIT if !PPC64 select HAVE_STACKPROTECTOR if PPC64 && $(cc-option,-mstack-protector-guard=tls -mstack-protector-guard-reg=r13) select HAVE_STACKPROTECTOR if PPC32 && $(cc-option,-mstack-protector-guard=tls -mstack-protector-guard-reg=r2) @@ -185,17 +188,19 @@ config PPC select HAVE_DYNAMIC_FTRACE_WITH_REGS if MPROFILE_KERNEL select HAVE_EBPF_JIT if PPC64 select HAVE_EFFICIENT_UNALIGNED_ACCESS if !(CPU_LITTLE_ENDIAN && POWER7_CPU) + select HAVE_FAST_GUP select HAVE_FTRACE_MCOUNT_RECORD select HAVE_FUNCTION_ERROR_INJECTION select HAVE_FUNCTION_GRAPH_TRACER select HAVE_FUNCTION_TRACER select HAVE_GCC_PLUGINS if GCC_VERSION >= 50200 # plugin support on gcc <= 5.1 is buggy on PPC - select HAVE_GENERIC_GUP select HAVE_HW_BREAKPOINT if PERF_EVENTS && (PPC_BOOK3S || PPC_8xx) select HAVE_IDE select HAVE_IOREMAP_PROT select HAVE_IRQ_EXIT_ON_IRQ_STACK select HAVE_KERNEL_GZIP + select HAVE_KERNEL_LZMA if DEFAULT_UIMAGE + select HAVE_KERNEL_LZO if DEFAULT_UIMAGE select HAVE_KERNEL_XZ if PPC_BOOK3S || 44x select HAVE_KPROBES select HAVE_KPROBES_ON_FTRACE @@ -234,6 +239,7 @@ config PPC select OLD_SIGSUSPEND select PCI_DOMAINS if PCI select PCI_SYSCALL if PCI + select PPC_DAWR if PPC64 select RTC_LIB select SPARSE_IRQ select SYSCTL_EXCEPTION_TRACE @@ -244,9 +250,9 @@ config PPC # config PPC_BARRIER_NOSPEC - bool - default y - depends on PPC_BOOK3S_64 || PPC_FSL_BOOK3E + bool + default y + depends on PPC_BOOK3S_64 || PPC_FSL_BOOK3E config EARLY_PRINTK bool @@ -370,6 +376,9 @@ config PPC_ADV_DEBUG_DAC_RANGE depends on PPC_ADV_DEBUG_REGS && 44x default y +config PPC_DAWR + bool + config ZONE_DMA bool default y if PPC_BOOK3E_64 @@ -398,7 +407,7 @@ config HUGETLB_PAGE_SIZE_VARIABLE config MATH_EMULATION bool "Math emulation" depends on 4xx || PPC_8xx || PPC_MPC832x || BOOKE - ---help--- + help Some PowerPC chips designed for embedded applications do not have a floating-point unit and therefore do not implement the floating-point instructions in the PowerPC instruction set. If you @@ -417,27 +426,27 @@ choice config MATH_EMULATION_FULL bool "Emulate all the floating point instructions" - ---help--- + help Select this option will enable the kernel to support to emulate all the floating point instructions. If your SoC doesn't have a FPU, you should select this. config MATH_EMULATION_HW_UNIMPLEMENTED bool "Just emulate the FPU unimplemented instructions" - ---help--- + help Select this if you know there does have a hardware FPU on your SoC, but some floating point instructions are not implemented by that. endchoice config PPC_TRANSACTIONAL_MEM - bool "Transactional Memory support for POWERPC" - depends on PPC_BOOK3S_64 - depends on SMP - select ALTIVEC - select VSX - ---help--- - Support user-mode Transactional Memory on POWERPC. + bool "Transactional Memory support for POWERPC" + depends on PPC_BOOK3S_64 + depends on SMP + select ALTIVEC + select VSX + help + Support user-mode Transactional Memory on POWERPC. config LD_HEAD_STUB_CATCH bool "Reserve 256 bytes to cope with linker stubs in HEAD text" if EXPERT @@ -457,7 +466,7 @@ config HOTPLUG_CPU bool "Support for enabling/disabling CPUs" depends on SMP && (PPC_PSERIES || \ PPC_PMAC || PPC_POWERNV || FSL_SOC_BOOKE) - ---help--- + help Say Y here to be able to disable and re-enable individual CPUs at runtime on SMP machines. @@ -825,7 +834,7 @@ config PPC_DENORMALISATION bool "PowerPC denormalisation exception handling" depends on PPC_BOOK3S_64 default "y" if PPC_POWERNV - ---help--- + help Add support for handling denormalisation of single precision values. Useful for bare metal only. If unsure say Y here. @@ -938,7 +947,7 @@ config FSL_SOC bool config FSL_PCI - bool + bool select ARCH_HAS_DMA_SET_MASK select PPC_INDIRECT_PCI select PCI_QUIRKS @@ -986,7 +995,7 @@ config FSL_RIO bool "Freescale Embedded SRIO Controller support" depends on RAPIDIO = y && HAVE_RAPIDIO default "n" - ---help--- + help Include support for RapidIO controller on Freescale embedded processors (MPC8548, MPC8641, etc). @@ -1050,14 +1059,14 @@ config DYNAMIC_MEMSTART select NONSTATIC_KERNEL help This option enables the kernel to be loaded at any page aligned - physical address. The kernel creates a mapping from KERNELBASE to + physical address. The kernel creates a mapping from KERNELBASE to the address where the kernel is loaded. The page size here implies the TLB page size of the mapping for kernel on the particular platform. Please refer to the init code for finding the TLB page size. DYNAMIC_MEMSTART is an easy way of implementing pseudo-RELOCATABLE kernel image, where the only restriction is the page aligned kernel - load address. When this option is enabled, the compile time physical + load address. When this option is enabled, the compile time physical address CONFIG_PHYSICAL_START is ignored. This option is overridden by CONFIG_RELOCATABLE diff --git a/arch/powerpc/boot/.gitignore b/arch/powerpc/boot/.gitignore index 32034a0cc554..6610665fcf5e 100644 --- a/arch/powerpc/boot/.gitignore +++ b/arch/powerpc/boot/.gitignore @@ -44,5 +44,3 @@ fdt_sw.c fdt_wip.c libfdt.h libfdt_internal.h -autoconf.h - diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile index 73d1f3562978..6841bd52738b 100644 --- a/arch/powerpc/boot/Makefile +++ b/arch/powerpc/boot/Makefile @@ -20,9 +20,6 @@ all: $(obj)/zImage -compress-$(CONFIG_KERNEL_GZIP) := CONFIG_KERNEL_GZIP -compress-$(CONFIG_KERNEL_XZ) := CONFIG_KERNEL_XZ - ifdef CROSS32_COMPILE BOOTCC := $(CROSS32_COMPILE)gcc BOOTAR := $(CROSS32_COMPILE)ar @@ -34,7 +31,7 @@ endif BOOTCFLAGS := -Wall -Wundef -Wstrict-prototypes -Wno-trigraphs \ -fno-strict-aliasing -O2 -msoft-float -mno-altivec -mno-vsx \ -pipe -fomit-frame-pointer -fno-builtin -fPIC -nostdinc \ - -D$(compress-y) + $(LINUXINCLUDE) ifdef CONFIG_PPC64_BOOT_WRAPPER BOOTCFLAGS += -m64 @@ -51,7 +48,7 @@ BOOTCFLAGS += -mlittle-endian BOOTCFLAGS += $(call cc-option,-mabi=elfv2) endif -BOOTAFLAGS := -D__ASSEMBLY__ $(BOOTCFLAGS) -traditional -nostdinc +BOOTAFLAGS := -D__ASSEMBLY__ $(BOOTCFLAGS) -nostdinc BOOTARFLAGS := -cr$(KBUILD_ARFLAGS) @@ -202,14 +199,9 @@ $(obj)/empty.c: $(obj)/zImage.coff.lds $(obj)/zImage.ps3.lds : $(obj)/%: $(srctree)/$(src)/%.S $(Q)cp $< $@ -$(srctree)/$(src)/serial.c: $(obj)/autoconf.h - -$(obj)/autoconf.h: $(obj)/%: $(objtree)/include/generated/% - $(Q)cp $< $@ - clean-files := $(zlib-) $(zlibheader-) $(zliblinuxheader-) \ $(zlib-decomp-) $(libfdt) $(libfdtheader) \ - autoconf.h empty.c zImage.coff.lds zImage.ps3.lds zImage.lds + empty.c zImage.coff.lds zImage.ps3.lds zImage.lds quiet_cmd_bootcc = BOOTCC $@ cmd_bootcc = $(BOOTCC) -Wp,-MD,$(depfile) $(BOOTCFLAGS) -c -o $@ $< @@ -257,6 +249,8 @@ endif compressor-$(CONFIG_KERNEL_GZIP) := gz compressor-$(CONFIG_KERNEL_XZ) := xz +compressor-$(CONFIG_KERNEL_LZMA) := lzma +compressor-$(CONFIG_KERNEL_LZO) := lzo # args (to if_changed): 1 = (this rule), 2 = platform, 3 = dts 4=dtb 5=initrd quiet_cmd_wrap = WRAP $@ diff --git a/arch/powerpc/boot/serial.c b/arch/powerpc/boot/serial.c index b0491b8c0199..9457863147f9 100644 --- a/arch/powerpc/boot/serial.c +++ b/arch/powerpc/boot/serial.c @@ -18,7 +18,6 @@ #include "stdio.h" #include "io.h" #include "ops.h" -#include "autoconf.h" static int serial_open(void) { diff --git a/arch/powerpc/boot/wrapper b/arch/powerpc/boot/wrapper index 532d45833396..5148ac271f28 100755 --- a/arch/powerpc/boot/wrapper +++ b/arch/powerpc/boot/wrapper @@ -40,6 +40,7 @@ dts= cacheit= binary= compression=.gz +uboot_comp=gzip pie= format= @@ -130,22 +131,29 @@ while [ "$#" -gt 0 ]; do ;; -z) compression=.gz + uboot_comp=gzip ;; -Z) shift [ "$#" -gt 0 ] || usage - [ "$1" != "gz" -o "$1" != "xz" -o "$1" != "none" ] || usage + [ "$1" != "gz" -o "$1" != "xz" -o "$1" != "lzma" -o "$1" != "lzo" -o "$1" != "none" ] || usage compression=".$1" + uboot_comp=$1 if [ $compression = ".none" ]; then compression= + uboot_comp=none fi + if [ $uboot_comp = "gz" ]; then + uboot_comp=gzip + fi ;; --no-gzip) # a "feature" of the the wrapper script is that it can be used outside # the kernel tree. So keeping this around for backwards compatibility. compression= + uboot_comp=none ;; -?) usage @@ -365,9 +373,16 @@ if [ -z "$cacheit" -o ! -f "$vmz$compression" -o "$vmz$compression" -ot "$kernel .gz) gzip -n -f -9 "$vmz.$$" ;; + .lzma) + xz --format=lzma -f -6 "$vmz.$$" + ;; + .lzo) + lzop -f -9 "$vmz.$$" + ;; *) # drop the compression suffix so the stripped vmlinux is used compression= + uboot_comp=none ;; esac @@ -411,7 +426,7 @@ membase=`${CROSS}objdump -p "$kernel" | grep -m 1 LOAD | awk '{print $7}'` case "$platform" in uboot) rm -f "$ofile" - ${MKIMAGE} -A ppc -O linux -T kernel -C gzip -a $membase -e $membase \ + ${MKIMAGE} -A ppc -O linux -T kernel -C $uboot_comp -a $membase -e $membase \ $uboot_version -d "$vmz" "$ofile" if [ -z "$cacheit" ]; then rm -f "$vmz" diff --git a/arch/powerpc/boot/xz_config.h b/arch/powerpc/boot/xz_config.h index e22e5b3770dd..ebfadd39e192 100644 --- a/arch/powerpc/boot/xz_config.h +++ b/arch/powerpc/boot/xz_config.h @@ -20,10 +20,30 @@ static inline uint32_t swab32p(void *p) #ifdef __LITTLE_ENDIAN__ #define get_le32(p) (*((uint32_t *) (p))) +#define cpu_to_be32(x) swab32(x) +static inline u32 be32_to_cpup(const u32 *p) +{ + return swab32p((u32 *)p); +} #else #define get_le32(p) swab32p(p) +#define cpu_to_be32(x) (x) +static inline u32 be32_to_cpup(const u32 *p) +{ + return *p; +} #endif +static inline uint32_t get_unaligned_be32(const void *p) +{ + return be32_to_cpup(p); +} + +static inline void put_unaligned_be32(u32 val, void *p) +{ + *((u32 *)p) = cpu_to_be32(val); +} + #define memeq(a, b, size) (memcmp(a, b, size) == 0) #define memzero(buf, size) memset(buf, 0, size) diff --git a/arch/powerpc/configs/40x/acadia_defconfig b/arch/powerpc/configs/40x/acadia_defconfig index e57344c3b0d7..5a75e4f14273 100644 --- a/arch/powerpc/configs/40x/acadia_defconfig +++ b/arch/powerpc/configs/40x/acadia_defconfig @@ -22,7 +22,6 @@ CONFIG_IP_PNP_BOOTP=y # CONFIG_INET_XFRM_MODE_TUNNEL is not set # CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_IPV6 is not set -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_CONNECTOR=y CONFIG_MTD=y CONFIG_MTD_CMDLINE_PARTS=y diff --git a/arch/powerpc/configs/40x/ep405_defconfig b/arch/powerpc/configs/40x/ep405_defconfig index 0f66f8a87be8..e2691c5db766 100644 --- a/arch/powerpc/configs/40x/ep405_defconfig +++ b/arch/powerpc/configs/40x/ep405_defconfig @@ -21,7 +21,6 @@ CONFIG_IP_PNP_BOOTP=y # CONFIG_INET_XFRM_MODE_TUNNEL is not set # CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_IPV6 is not set -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_CONNECTOR=y CONFIG_MTD=y CONFIG_MTD_CMDLINE_PARTS=y diff --git a/arch/powerpc/configs/40x/kilauea_defconfig b/arch/powerpc/configs/40x/kilauea_defconfig index 3da091f651d6..949989ef2322 100644 --- a/arch/powerpc/configs/40x/kilauea_defconfig +++ b/arch/powerpc/configs/40x/kilauea_defconfig @@ -24,7 +24,6 @@ CONFIG_IP_PNP_BOOTP=y # CONFIG_INET_XFRM_MODE_TUNNEL is not set # CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_IPV6 is not set -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_CONNECTOR=y CONFIG_MTD=y CONFIG_MTD_CMDLINE_PARTS=y diff --git a/arch/powerpc/configs/40x/klondike_defconfig b/arch/powerpc/configs/40x/klondike_defconfig index caab658d1da1..4347a87088dc 100644 --- a/arch/powerpc/configs/40x/klondike_defconfig +++ b/arch/powerpc/configs/40x/klondike_defconfig @@ -14,7 +14,6 @@ CONFIG_APM8018X=y # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set CONFIG_MATH_EMULATION=y # CONFIG_SUSPEND is not set -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_SIZE=35000 CONFIG_SCSI=y diff --git a/arch/powerpc/configs/40x/makalu_defconfig b/arch/powerpc/configs/40x/makalu_defconfig index e0b1489b7c7b..90b759bbf426 100644 --- a/arch/powerpc/configs/40x/makalu_defconfig +++ b/arch/powerpc/configs/40x/makalu_defconfig @@ -21,7 +21,6 @@ CONFIG_IP_PNP_BOOTP=y # CONFIG_INET_XFRM_MODE_TUNNEL is not set # CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_IPV6 is not set -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_CONNECTOR=y CONFIG_MTD=y CONFIG_MTD_CMDLINE_PARTS=y diff --git a/arch/powerpc/configs/40x/obs600_defconfig b/arch/powerpc/configs/40x/obs600_defconfig index 38d3d7769a2f..881c300c011d 100644 --- a/arch/powerpc/configs/40x/obs600_defconfig +++ b/arch/powerpc/configs/40x/obs600_defconfig @@ -24,7 +24,6 @@ CONFIG_IP_PNP_BOOTP=y # CONFIG_INET_XFRM_MODE_TUNNEL is not set # CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_IPV6 is not set -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_CONNECTOR=y CONFIG_MTD=y CONFIG_MTD_CMDLINE_PARTS=y diff --git a/arch/powerpc/configs/40x/virtex_defconfig b/arch/powerpc/configs/40x/virtex_defconfig index a2b2770eee8f..5e7c61d1d7d0 100644 --- a/arch/powerpc/configs/40x/virtex_defconfig +++ b/arch/powerpc/configs/40x/virtex_defconfig @@ -31,7 +31,6 @@ CONFIG_NETFILTER=y CONFIG_IP_NF_IPTABLES=m CONFIG_IP_NF_FILTER=m CONFIG_IP_NF_MANGLE=m -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_SIZE=8192 diff --git a/arch/powerpc/configs/40x/walnut_defconfig b/arch/powerpc/configs/40x/walnut_defconfig index 6faa03cd661c..0ed46704b9fa 100644 --- a/arch/powerpc/configs/40x/walnut_defconfig +++ b/arch/powerpc/configs/40x/walnut_defconfig @@ -19,7 +19,6 @@ CONFIG_IP_PNP_BOOTP=y # CONFIG_INET_XFRM_MODE_TUNNEL is not set # CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_IPV6 is not set -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_CONNECTOR=y CONFIG_MTD=y CONFIG_MTD_CMDLINE_PARTS=y diff --git a/arch/powerpc/configs/44x/akebono_defconfig b/arch/powerpc/configs/44x/akebono_defconfig index 9fcd361607e2..2fa553ebfdc9 100644 --- a/arch/powerpc/configs/44x/akebono_defconfig +++ b/arch/powerpc/configs/44x/akebono_defconfig @@ -33,7 +33,6 @@ CONFIG_IP_PNP_BOOTP=y # CONFIG_INET_XFRM_MODE_TUNNEL is not set # CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_IPV6 is not set -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_DEVTMPFS=y CONFIG_DEVTMPFS_MOUNT=y CONFIG_CONNECTOR=y diff --git a/arch/powerpc/configs/44x/arches_defconfig b/arch/powerpc/configs/44x/arches_defconfig index 6bba1a55b827..5a1b9ee18075 100644 --- a/arch/powerpc/configs/44x/arches_defconfig +++ b/arch/powerpc/configs/44x/arches_defconfig @@ -24,7 +24,6 @@ CONFIG_IP_PNP_BOOTP=y # CONFIG_INET_XFRM_MODE_TUNNEL is not set # CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_IPV6 is not set -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_CONNECTOR=y CONFIG_MTD=y CONFIG_MTD_CMDLINE_PARTS=y diff --git a/arch/powerpc/configs/44x/bamboo_defconfig b/arch/powerpc/configs/44x/bamboo_defconfig index 6f3a6ecc81e7..22e1ef5272ab 100644 --- a/arch/powerpc/configs/44x/bamboo_defconfig +++ b/arch/powerpc/configs/44x/bamboo_defconfig @@ -22,7 +22,6 @@ CONFIG_IP_PNP_BOOTP=y # CONFIG_INET_XFRM_MODE_TUNNEL is not set # CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_IPV6 is not set -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_CONNECTOR=y CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_SIZE=35000 diff --git a/arch/powerpc/configs/44x/bluestone_defconfig b/arch/powerpc/configs/44x/bluestone_defconfig index 6b77aea79b6c..8006a5728afd 100644 --- a/arch/powerpc/configs/44x/bluestone_defconfig +++ b/arch/powerpc/configs/44x/bluestone_defconfig @@ -20,7 +20,6 @@ CONFIG_INET=y CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y CONFIG_IP_PNP_BOOTP=y -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_CONNECTOR=y CONFIG_MTD=y CONFIG_MTD_CMDLINE_PARTS=y diff --git a/arch/powerpc/configs/44x/canyonlands_defconfig b/arch/powerpc/configs/44x/canyonlands_defconfig index d427cee027a6..86f34ea4173a 100644 --- a/arch/powerpc/configs/44x/canyonlands_defconfig +++ b/arch/powerpc/configs/44x/canyonlands_defconfig @@ -24,7 +24,6 @@ CONFIG_IP_PNP_BOOTP=y # CONFIG_INET_XFRM_MODE_TUNNEL is not set # CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_IPV6 is not set -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_CONNECTOR=y CONFIG_MTD=y CONFIG_MTD_CMDLINE_PARTS=y diff --git a/arch/powerpc/configs/44x/currituck_defconfig b/arch/powerpc/configs/44x/currituck_defconfig index 5f1df5fe4453..ce3ec5a2cd15 100644 --- a/arch/powerpc/configs/44x/currituck_defconfig +++ b/arch/powerpc/configs/44x/currituck_defconfig @@ -31,7 +31,6 @@ CONFIG_IP_PNP_BOOTP=y # CONFIG_INET_XFRM_MODE_TUNNEL is not set # CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_IPV6 is not set -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_DEVTMPFS=y CONFIG_DEVTMPFS_MOUNT=y CONFIG_CONNECTOR=y diff --git a/arch/powerpc/configs/44x/ebony_defconfig b/arch/powerpc/configs/44x/ebony_defconfig index e2b6578993d5..f67447c92e6f 100644 --- a/arch/powerpc/configs/44x/ebony_defconfig +++ b/arch/powerpc/configs/44x/ebony_defconfig @@ -20,7 +20,6 @@ CONFIG_IP_PNP_BOOTP=y # CONFIG_INET_XFRM_MODE_TUNNEL is not set # CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_IPV6 is not set -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_CONNECTOR=y CONFIG_MTD=y CONFIG_MTD_BLOCK=y diff --git a/arch/powerpc/configs/44x/eiger_defconfig b/arch/powerpc/configs/44x/eiger_defconfig index f593258806ad..5dbd83a1c11b 100644 --- a/arch/powerpc/configs/44x/eiger_defconfig +++ b/arch/powerpc/configs/44x/eiger_defconfig @@ -25,7 +25,6 @@ CONFIG_IP_PNP_BOOTP=y # CONFIG_INET_XFRM_MODE_TUNNEL is not set # CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_IPV6 is not set -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_CONNECTOR=y CONFIG_MTD=y CONFIG_MTD_CMDLINE_PARTS=y diff --git a/arch/powerpc/configs/44x/fsp2_defconfig b/arch/powerpc/configs/44x/fsp2_defconfig index bae6b26bcfba..e49114f0e526 100644 --- a/arch/powerpc/configs/44x/fsp2_defconfig +++ b/arch/powerpc/configs/44x/fsp2_defconfig @@ -44,7 +44,6 @@ CONFIG_IP_PNP_BOOTP=y # CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_IPV6 is not set CONFIG_VLAN_8021Q=m -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_DEVTMPFS=y CONFIG_DEVTMPFS_MOUNT=y CONFIG_CONNECTOR=y diff --git a/arch/powerpc/configs/44x/icon_defconfig b/arch/powerpc/configs/44x/icon_defconfig index 4453a4590b1a..fa5378af44f9 100644 --- a/arch/powerpc/configs/44x/icon_defconfig +++ b/arch/powerpc/configs/44x/icon_defconfig @@ -24,7 +24,6 @@ CONFIG_IP_PNP_BOOTP=y # CONFIG_INET_XFRM_MODE_TUNNEL is not set # CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_IPV6 is not set -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_CONNECTOR=y CONFIG_MTD=y CONFIG_MTD_CMDLINE_PARTS=y diff --git a/arch/powerpc/configs/44x/iss476-smp_defconfig b/arch/powerpc/configs/44x/iss476-smp_defconfig index d24bfa6ecd62..aae879c21239 100644 --- a/arch/powerpc/configs/44x/iss476-smp_defconfig +++ b/arch/powerpc/configs/44x/iss476-smp_defconfig @@ -33,7 +33,6 @@ CONFIG_IP_PNP_BOOTP=y # CONFIG_INET_XFRM_MODE_TUNNEL is not set # CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_IPV6 is not set -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_CONNECTOR=y CONFIG_MTD=y CONFIG_MTD_BLOCK=y diff --git a/arch/powerpc/configs/44x/katmai_defconfig b/arch/powerpc/configs/44x/katmai_defconfig index 5d3f685a7af8..56eddca998c6 100644 --- a/arch/powerpc/configs/44x/katmai_defconfig +++ b/arch/powerpc/configs/44x/katmai_defconfig @@ -22,7 +22,6 @@ CONFIG_IP_PNP_BOOTP=y # CONFIG_INET_XFRM_MODE_TUNNEL is not set # CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_IPV6 is not set -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_CONNECTOR=y CONFIG_MTD=y CONFIG_MTD_CMDLINE_PARTS=y diff --git a/arch/powerpc/configs/44x/rainier_defconfig b/arch/powerpc/configs/44x/rainier_defconfig index 7b8355a5698d..369bfd2e451d 100644 --- a/arch/powerpc/configs/44x/rainier_defconfig +++ b/arch/powerpc/configs/44x/rainier_defconfig @@ -23,7 +23,6 @@ CONFIG_IP_PNP_BOOTP=y # CONFIG_INET_XFRM_MODE_TUNNEL is not set # CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_IPV6 is not set -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_CONNECTOR=y CONFIG_MTD=y CONFIG_MTD_CMDLINE_PARTS=y diff --git a/arch/powerpc/configs/44x/redwood_defconfig b/arch/powerpc/configs/44x/redwood_defconfig index 918cfb63f0c8..8be95f6fe3a7 100644 --- a/arch/powerpc/configs/44x/redwood_defconfig +++ b/arch/powerpc/configs/44x/redwood_defconfig @@ -25,7 +25,6 @@ CONFIG_IP_PNP_BOOTP=y # CONFIG_INET_XFRM_MODE_TUNNEL is not set # CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_IPV6 is not set -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_CONNECTOR=y CONFIG_MTD=y CONFIG_MTD_CMDLINE_PARTS=y diff --git a/arch/powerpc/configs/44x/sam440ep_defconfig b/arch/powerpc/configs/44x/sam440ep_defconfig index 63302fbd184d..974a4f038cda 100644 --- a/arch/powerpc/configs/44x/sam440ep_defconfig +++ b/arch/powerpc/configs/44x/sam440ep_defconfig @@ -27,7 +27,6 @@ CONFIG_IP_PNP_BOOTP=y # CONFIG_INET_XFRM_MODE_TUNNEL is not set # CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_IPV6 is not set -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_CONNECTOR=y CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_RAM=y diff --git a/arch/powerpc/configs/44x/sequoia_defconfig b/arch/powerpc/configs/44x/sequoia_defconfig index f34fee9464e5..10e517b69fa4 100644 --- a/arch/powerpc/configs/44x/sequoia_defconfig +++ b/arch/powerpc/configs/44x/sequoia_defconfig @@ -24,7 +24,6 @@ CONFIG_IP_PNP_BOOTP=y # CONFIG_INET_XFRM_MODE_TUNNEL is not set # CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_IPV6 is not set -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_CONNECTOR=y CONFIG_MTD=y CONFIG_MTD_CMDLINE_PARTS=y diff --git a/arch/powerpc/configs/44x/taishan_defconfig b/arch/powerpc/configs/44x/taishan_defconfig index 42cc7b4ed95f..cd08f3ddd609 100644 --- a/arch/powerpc/configs/44x/taishan_defconfig +++ b/arch/powerpc/configs/44x/taishan_defconfig @@ -22,7 +22,6 @@ CONFIG_IP_PNP_BOOTP=y # CONFIG_INET_XFRM_MODE_TUNNEL is not set # CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_IPV6 is not set -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_CONNECTOR=y CONFIG_MTD=y CONFIG_MTD_CMDLINE_PARTS=y diff --git a/arch/powerpc/configs/44x/virtex5_defconfig b/arch/powerpc/configs/44x/virtex5_defconfig index 99cc3dc02df1..1f74079e1703 100644 --- a/arch/powerpc/configs/44x/virtex5_defconfig +++ b/arch/powerpc/configs/44x/virtex5_defconfig @@ -30,7 +30,6 @@ CONFIG_NETFILTER=y CONFIG_IP_NF_IPTABLES=m CONFIG_IP_NF_FILTER=m CONFIG_IP_NF_MANGLE=m -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_SIZE=8192 diff --git a/arch/powerpc/configs/44x/warp_defconfig b/arch/powerpc/configs/44x/warp_defconfig index 6ae88d4879bf..af66c69c49fe 100644 --- a/arch/powerpc/configs/44x/warp_defconfig +++ b/arch/powerpc/configs/44x/warp_defconfig @@ -26,7 +26,6 @@ CONFIG_IP_PNP_DHCP=y # CONFIG_IPV6 is not set CONFIG_NETFILTER=y CONFIG_VLAN_8021Q=y -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" # CONFIG_STANDALONE is not set CONFIG_MTD=y CONFIG_MTD_CMDLINE_PARTS=y diff --git a/arch/powerpc/configs/52xx/cm5200_defconfig b/arch/powerpc/configs/52xx/cm5200_defconfig index 73948e88ac82..2412a6bf7ee6 100644 --- a/arch/powerpc/configs/52xx/cm5200_defconfig +++ b/arch/powerpc/configs/52xx/cm5200_defconfig @@ -23,7 +23,6 @@ CONFIG_IP_PNP_DHCP=y CONFIG_IP_PNP_BOOTP=y CONFIG_SYN_COOKIES=y # CONFIG_IPV6 is not set -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" # CONFIG_FW_LOADER is not set CONFIG_MTD=y CONFIG_MTD_CMDLINE_PARTS=y diff --git a/arch/powerpc/configs/52xx/lite5200b_defconfig b/arch/powerpc/configs/52xx/lite5200b_defconfig index 6fc7f786c83c..63368e677506 100644 --- a/arch/powerpc/configs/52xx/lite5200b_defconfig +++ b/arch/powerpc/configs/52xx/lite5200b_defconfig @@ -26,7 +26,6 @@ CONFIG_IP_PNP_DHCP=y CONFIG_IP_PNP_BOOTP=y CONFIG_SYN_COOKIES=y # CONFIG_IPV6 is not set -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" # CONFIG_FW_LOADER is not set CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_RAM=y diff --git a/arch/powerpc/configs/52xx/motionpro_defconfig b/arch/powerpc/configs/52xx/motionpro_defconfig index ae2a1f74103b..72762da94846 100644 --- a/arch/powerpc/configs/52xx/motionpro_defconfig +++ b/arch/powerpc/configs/52xx/motionpro_defconfig @@ -23,7 +23,6 @@ CONFIG_IP_PNP_DHCP=y CONFIG_IP_PNP_BOOTP=y CONFIG_SYN_COOKIES=y # CONFIG_IPV6 is not set -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" # CONFIG_FW_LOADER is not set CONFIG_MTD=y CONFIG_MTD_CMDLINE_PARTS=y diff --git a/arch/powerpc/configs/52xx/pcm030_defconfig b/arch/powerpc/configs/52xx/pcm030_defconfig index 1554de6968ca..303600ff1fdb 100644 --- a/arch/powerpc/configs/52xx/pcm030_defconfig +++ b/arch/powerpc/configs/52xx/pcm030_defconfig @@ -36,7 +36,6 @@ CONFIG_IP_PNP_BOOTP=y # CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_INET_DIAG is not set # CONFIG_IPV6 is not set -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" # CONFIG_FW_LOADER is not set CONFIG_MTD=y CONFIG_MTD_CMDLINE_PARTS=y diff --git a/arch/powerpc/configs/52xx/tqm5200_defconfig b/arch/powerpc/configs/52xx/tqm5200_defconfig index 0777e6efd22d..a3c8ca74032c 100644 --- a/arch/powerpc/configs/52xx/tqm5200_defconfig +++ b/arch/powerpc/configs/52xx/tqm5200_defconfig @@ -27,7 +27,6 @@ CONFIG_IP_PNP_DHCP=y CONFIG_IP_PNP_BOOTP=y CONFIG_SYN_COOKIES=y # CONFIG_IPV6 is not set -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" # CONFIG_FW_LOADER is not set CONFIG_MTD=y CONFIG_MTD_CMDLINE_PARTS=y diff --git a/arch/powerpc/configs/83xx/asp8347_defconfig b/arch/powerpc/configs/83xx/asp8347_defconfig index dd884df32dfd..10192410b33c 100644 --- a/arch/powerpc/configs/83xx/asp8347_defconfig +++ b/arch/powerpc/configs/83xx/asp8347_defconfig @@ -27,7 +27,6 @@ CONFIG_IP_PNP_DHCP=y CONFIG_IP_PNP_BOOTP=y CONFIG_SYN_COOKIES=y # CONFIG_IPV6 is not set -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" # CONFIG_FW_LOADER is not set CONFIG_MTD=y CONFIG_MTD_REDBOOT_PARTS=y diff --git a/arch/powerpc/configs/83xx/mpc8313_rdb_defconfig b/arch/powerpc/configs/83xx/mpc8313_rdb_defconfig index 9dffb2e7f735..16a42e2267fb 100644 --- a/arch/powerpc/configs/83xx/mpc8313_rdb_defconfig +++ b/arch/powerpc/configs/83xx/mpc8313_rdb_defconfig @@ -24,7 +24,6 @@ CONFIG_IP_PNP_DHCP=y CONFIG_IP_PNP_BOOTP=y CONFIG_SYN_COOKIES=y # CONFIG_IPV6 is not set -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" # CONFIG_FW_LOADER is not set CONFIG_MTD=y CONFIG_MTD_BLOCK=y diff --git a/arch/powerpc/configs/83xx/mpc8315_rdb_defconfig b/arch/powerpc/configs/83xx/mpc8315_rdb_defconfig index a42232732c6d..80d40ae668eb 100644 --- a/arch/powerpc/configs/83xx/mpc8315_rdb_defconfig +++ b/arch/powerpc/configs/83xx/mpc8315_rdb_defconfig @@ -24,7 +24,6 @@ CONFIG_IP_PNP_DHCP=y CONFIG_IP_PNP_BOOTP=y CONFIG_SYN_COOKIES=y # CONFIG_IPV6 is not set -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" # CONFIG_FW_LOADER is not set CONFIG_MTD=y CONFIG_MTD_BLOCK=y diff --git a/arch/powerpc/configs/83xx/mpc832x_mds_defconfig b/arch/powerpc/configs/83xx/mpc832x_mds_defconfig index 4f914906ee4b..e94555452fb2 100644 --- a/arch/powerpc/configs/83xx/mpc832x_mds_defconfig +++ b/arch/powerpc/configs/83xx/mpc832x_mds_defconfig @@ -26,7 +26,6 @@ CONFIG_IP_PNP_DHCP=y CONFIG_IP_PNP_BOOTP=y CONFIG_SYN_COOKIES=y # CONFIG_IPV6 is not set -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" # CONFIG_FW_LOADER is not set CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_RAM=y diff --git a/arch/powerpc/configs/83xx/mpc832x_rdb_defconfig b/arch/powerpc/configs/83xx/mpc832x_rdb_defconfig index a484eb8401e8..1715ff547442 100644 --- a/arch/powerpc/configs/83xx/mpc832x_rdb_defconfig +++ b/arch/powerpc/configs/83xx/mpc832x_rdb_defconfig @@ -27,7 +27,6 @@ CONFIG_IP_PNP_DHCP=y CONFIG_IP_PNP_BOOTP=y CONFIG_SYN_COOKIES=y # CONFIG_IPV6 is not set -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" # CONFIG_FW_LOADER is not set CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_RAM=y diff --git a/arch/powerpc/configs/83xx/mpc834x_itx_defconfig b/arch/powerpc/configs/83xx/mpc834x_itx_defconfig index 37f4d93b3f81..e65c0057147f 100644 --- a/arch/powerpc/configs/83xx/mpc834x_itx_defconfig +++ b/arch/powerpc/configs/83xx/mpc834x_itx_defconfig @@ -25,7 +25,6 @@ CONFIG_IP_PNP_DHCP=y CONFIG_IP_PNP_BOOTP=y CONFIG_SYN_COOKIES=y # CONFIG_IPV6 is not set -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" # CONFIG_FW_LOADER is not set CONFIG_MTD=y CONFIG_MTD_CFI=y diff --git a/arch/powerpc/configs/83xx/mpc834x_itxgp_defconfig b/arch/powerpc/configs/83xx/mpc834x_itxgp_defconfig index 7adb6708a761..17714bf0ed40 100644 --- a/arch/powerpc/configs/83xx/mpc834x_itxgp_defconfig +++ b/arch/powerpc/configs/83xx/mpc834x_itxgp_defconfig @@ -25,7 +25,6 @@ CONFIG_IP_PNP_DHCP=y CONFIG_IP_PNP_BOOTP=y CONFIG_SYN_COOKIES=y # CONFIG_IPV6 is not set -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" # CONFIG_FW_LOADER is not set CONFIG_MTD=y CONFIG_MTD_CFI=y diff --git a/arch/powerpc/configs/83xx/mpc834x_mds_defconfig b/arch/powerpc/configs/83xx/mpc834x_mds_defconfig index d7ce3551529d..e2ff684d8792 100644 --- a/arch/powerpc/configs/83xx/mpc834x_mds_defconfig +++ b/arch/powerpc/configs/83xx/mpc834x_mds_defconfig @@ -26,7 +26,6 @@ CONFIG_IP_PNP_DHCP=y CONFIG_IP_PNP_BOOTP=y CONFIG_SYN_COOKIES=y # CONFIG_IPV6 is not set -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" # CONFIG_FW_LOADER is not set CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_RAM=y diff --git a/arch/powerpc/configs/83xx/mpc836x_mds_defconfig b/arch/powerpc/configs/83xx/mpc836x_mds_defconfig index 92134cee3f37..3eceb6db2982 100644 --- a/arch/powerpc/configs/83xx/mpc836x_mds_defconfig +++ b/arch/powerpc/configs/83xx/mpc836x_mds_defconfig @@ -25,7 +25,6 @@ CONFIG_IP_PNP_DHCP=y CONFIG_IP_PNP_BOOTP=y CONFIG_SYN_COOKIES=y # CONFIG_IPV6 is not set -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" # CONFIG_FW_LOADER is not set CONFIG_MTD=y CONFIG_MTD_CMDLINE_PARTS=y diff --git a/arch/powerpc/configs/83xx/mpc836x_rdk_defconfig b/arch/powerpc/configs/83xx/mpc836x_rdk_defconfig index 97f7ea5f205f..093df33f9455 100644 --- a/arch/powerpc/configs/83xx/mpc836x_rdk_defconfig +++ b/arch/powerpc/configs/83xx/mpc836x_rdk_defconfig @@ -24,7 +24,6 @@ CONFIG_IP_PNP_DHCP=y CONFIG_IP_PNP_BOOTP=y CONFIG_SYN_COOKIES=y # CONFIG_IPV6 is not set -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_MTD=y CONFIG_MTD_CMDLINE_PARTS=y CONFIG_MTD_BLOCK=y diff --git a/arch/powerpc/configs/83xx/mpc837x_mds_defconfig b/arch/powerpc/configs/83xx/mpc837x_mds_defconfig index ee7510a33d06..3f5e5d10789f 100644 --- a/arch/powerpc/configs/83xx/mpc837x_mds_defconfig +++ b/arch/powerpc/configs/83xx/mpc837x_mds_defconfig @@ -24,7 +24,6 @@ CONFIG_IP_PNP_DHCP=y CONFIG_IP_PNP_BOOTP=y CONFIG_SYN_COOKIES=y # CONFIG_IPV6 is not set -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" # CONFIG_FW_LOADER is not set CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_RAM=y diff --git a/arch/powerpc/configs/83xx/mpc837x_rdb_defconfig b/arch/powerpc/configs/83xx/mpc837x_rdb_defconfig index 8966a9af4230..dad53ef86b49 100644 --- a/arch/powerpc/configs/83xx/mpc837x_rdb_defconfig +++ b/arch/powerpc/configs/83xx/mpc837x_rdb_defconfig @@ -26,7 +26,6 @@ CONFIG_SYN_COOKIES=y # CONFIG_INET_XFRM_MODE_TUNNEL is not set # CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_IPV6 is not set -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" # CONFIG_FW_LOADER is not set CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_RAM=y diff --git a/arch/powerpc/configs/85xx/ge_imp3a_defconfig b/arch/powerpc/configs/85xx/ge_imp3a_defconfig index d70b60314dad..920f37316fdb 100644 --- a/arch/powerpc/configs/85xx/ge_imp3a_defconfig +++ b/arch/powerpc/configs/85xx/ge_imp3a_defconfig @@ -65,7 +65,6 @@ CONFIG_INET6_AH=m CONFIG_INET6_IPCOMP=m CONFIG_IPV6_TUNNEL=m CONFIG_NET_PKTGEN=m -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_MTD=y CONFIG_MTD_BLOCK=y CONFIG_MTD_CFI=y diff --git a/arch/powerpc/configs/85xx/ksi8560_defconfig b/arch/powerpc/configs/85xx/ksi8560_defconfig index 9ce6f48cfb61..9cb211fb6d1e 100644 --- a/arch/powerpc/configs/85xx/ksi8560_defconfig +++ b/arch/powerpc/configs/85xx/ksi8560_defconfig @@ -23,7 +23,6 @@ CONFIG_IP_PNP_DHCP=y CONFIG_IP_PNP_BOOTP=y CONFIG_SYN_COOKIES=y # CONFIG_IPV6 is not set -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" # CONFIG_FW_LOADER is not set CONFIG_MTD=y CONFIG_MTD_BLOCK=y diff --git a/arch/powerpc/configs/85xx/mpc8540_ads_defconfig b/arch/powerpc/configs/85xx/mpc8540_ads_defconfig index 5fbc3f904046..618e03e0706d 100644 --- a/arch/powerpc/configs/85xx/mpc8540_ads_defconfig +++ b/arch/powerpc/configs/85xx/mpc8540_ads_defconfig @@ -24,7 +24,6 @@ CONFIG_IP_PNP_DHCP=y CONFIG_IP_PNP_BOOTP=y CONFIG_SYN_COOKIES=y # CONFIG_IPV6 is not set -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" # CONFIG_FW_LOADER is not set CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_RAM=y diff --git a/arch/powerpc/configs/85xx/mpc8560_ads_defconfig b/arch/powerpc/configs/85xx/mpc8560_ads_defconfig index ff981d7905c7..9bc6283f2fb2 100644 --- a/arch/powerpc/configs/85xx/mpc8560_ads_defconfig +++ b/arch/powerpc/configs/85xx/mpc8560_ads_defconfig @@ -23,7 +23,6 @@ CONFIG_IP_PNP_DHCP=y CONFIG_IP_PNP_BOOTP=y CONFIG_SYN_COOKIES=y # CONFIG_IPV6 is not set -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" # CONFIG_FW_LOADER is not set CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_RAM=y diff --git a/arch/powerpc/configs/85xx/mpc85xx_cds_defconfig b/arch/powerpc/configs/85xx/mpc85xx_cds_defconfig index 974f0706d777..0683d8c292a8 100644 --- a/arch/powerpc/configs/85xx/mpc85xx_cds_defconfig +++ b/arch/powerpc/configs/85xx/mpc85xx_cds_defconfig @@ -25,7 +25,6 @@ CONFIG_IP_PNP_DHCP=y CONFIG_IP_PNP_BOOTP=y CONFIG_SYN_COOKIES=y # CONFIG_IPV6 is not set -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" # CONFIG_FW_LOADER is not set CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_RAM=y diff --git a/arch/powerpc/configs/85xx/sbc8548_defconfig b/arch/powerpc/configs/85xx/sbc8548_defconfig index 7e3e84a842e4..258881727119 100644 --- a/arch/powerpc/configs/85xx/sbc8548_defconfig +++ b/arch/powerpc/configs/85xx/sbc8548_defconfig @@ -22,7 +22,6 @@ CONFIG_IP_PNP_DHCP=y CONFIG_IP_PNP_BOOTP=y CONFIG_SYN_COOKIES=y # CONFIG_IPV6 is not set -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" # CONFIG_FW_LOADER is not set CONFIG_MTD=y CONFIG_MTD_BLOCK=y diff --git a/arch/powerpc/configs/85xx/stx_gp3_defconfig b/arch/powerpc/configs/85xx/stx_gp3_defconfig index 5b9cc01b9098..ecbcc853307d 100644 --- a/arch/powerpc/configs/85xx/stx_gp3_defconfig +++ b/arch/powerpc/configs/85xx/stx_gp3_defconfig @@ -22,7 +22,6 @@ CONFIG_NETFILTER=y CONFIG_IP_NF_IPTABLES=m CONFIG_IP_NF_FILTER=m CONFIG_NET_PKTGEN=y -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" # CONFIG_FW_LOADER is not set CONFIG_PARPORT=m CONFIG_PARPORT_PC=m diff --git a/arch/powerpc/configs/85xx/tqm8548_defconfig b/arch/powerpc/configs/85xx/tqm8548_defconfig index 1c63cbdc3211..afa1b9b633f8 100644 --- a/arch/powerpc/configs/85xx/tqm8548_defconfig +++ b/arch/powerpc/configs/85xx/tqm8548_defconfig @@ -29,7 +29,6 @@ CONFIG_IP_PNP_DHCP=y CONFIG_IP_PNP_BOOTP=y CONFIG_SYN_COOKIES=y # CONFIG_IPV6 is not set -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" # CONFIG_FW_LOADER is not set CONFIG_MTD=y CONFIG_MTD_CFI=y diff --git a/arch/powerpc/configs/85xx/xes_mpc85xx_defconfig b/arch/powerpc/configs/85xx/xes_mpc85xx_defconfig index 78f5beb2928c..d50aca608736 100644 --- a/arch/powerpc/configs/85xx/xes_mpc85xx_defconfig +++ b/arch/powerpc/configs/85xx/xes_mpc85xx_defconfig @@ -54,7 +54,6 @@ CONFIG_IP_PIMSM_V2=y # CONFIG_INET_XFRM_MODE_TRANSPORT is not set # CONFIG_INET_XFRM_MODE_TUNNEL is not set # CONFIG_INET_XFRM_MODE_BEET is not set -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_MTD=y CONFIG_MTD_REDBOOT_PARTS=y CONFIG_MTD_CMDLINE_PARTS=y diff --git a/arch/powerpc/configs/adder875_defconfig b/arch/powerpc/configs/adder875_defconfig index 935ea3ade7de..f7a803ab2285 100644 --- a/arch/powerpc/configs/adder875_defconfig +++ b/arch/powerpc/configs/adder875_defconfig @@ -26,7 +26,6 @@ CONFIG_SYN_COOKIES=y # CONFIG_INET_XFRM_MODE_TUNNEL is not set # CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_IPV6 is not set -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" # CONFIG_FW_LOADER is not set CONFIG_MTD=y CONFIG_MTD_BLOCK=y diff --git a/arch/powerpc/configs/amigaone_defconfig b/arch/powerpc/configs/amigaone_defconfig index 12f397d403c6..cf94d28d0e31 100644 --- a/arch/powerpc/configs/amigaone_defconfig +++ b/arch/powerpc/configs/amigaone_defconfig @@ -37,7 +37,6 @@ CONFIG_NETFILTER=y # CONFIG_NETFILTER_XT_MATCH_CONNTRACK is not set # CONFIG_NETFILTER_XT_MATCH_STATE is not set # CONFIG_IP_NF_MANGLE is not set -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" # CONFIG_STANDALONE is not set CONFIG_PARPORT=y CONFIG_PARPORT_PC=y diff --git a/arch/powerpc/configs/cell_defconfig b/arch/powerpc/configs/cell_defconfig index 560a93a84efe..2dd1b58a18ae 100644 --- a/arch/powerpc/configs/cell_defconfig +++ b/arch/powerpc/configs/cell_defconfig @@ -102,7 +102,6 @@ CONFIG_IP_NF_RAW=m CONFIG_IP_NF_ARPTABLES=m CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_SIZE=131072 diff --git a/arch/powerpc/configs/chrp32_defconfig b/arch/powerpc/configs/chrp32_defconfig index a203b1cf67d3..9ff493dd8439 100644 --- a/arch/powerpc/configs/chrp32_defconfig +++ b/arch/powerpc/configs/chrp32_defconfig @@ -38,7 +38,6 @@ CONFIG_NETFILTER=y # CONFIG_NETFILTER_XT_MATCH_CONNTRACK is not set # CONFIG_NETFILTER_XT_MATCH_STATE is not set # CONFIG_IP_NF_MANGLE is not set -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" # CONFIG_STANDALONE is not set CONFIG_BLK_DEV_FD=y CONFIG_BLK_DEV_LOOP=y diff --git a/arch/powerpc/configs/ep8248e_defconfig b/arch/powerpc/configs/ep8248e_defconfig index 2e6c8a45ae88..6e08d9502d89 100644 --- a/arch/powerpc/configs/ep8248e_defconfig +++ b/arch/powerpc/configs/ep8248e_defconfig @@ -24,7 +24,6 @@ CONFIG_IP_PNP_DHCP=y CONFIG_IP_PNP_BOOTP=y CONFIG_SYN_COOKIES=y CONFIG_NETFILTER=y -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" # CONFIG_FW_LOADER is not set CONFIG_MTD=y CONFIG_MTD_BLOCK=y diff --git a/arch/powerpc/configs/ep88xc_defconfig b/arch/powerpc/configs/ep88xc_defconfig index 7cb590e8f8fd..b20bd0cf3543 100644 --- a/arch/powerpc/configs/ep88xc_defconfig +++ b/arch/powerpc/configs/ep88xc_defconfig @@ -28,7 +28,6 @@ CONFIG_SYN_COOKIES=y # CONFIG_INET_XFRM_MODE_TUNNEL is not set # CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_IPV6 is not set -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" # CONFIG_FW_LOADER is not set CONFIG_MTD=y CONFIG_MTD_BLOCK=y diff --git a/arch/powerpc/configs/fsl-emb-nonhw.config b/arch/powerpc/configs/fsl-emb-nonhw.config index d592ba27b122..3c7dad19a691 100644 --- a/arch/powerpc/configs/fsl-emb-nonhw.config +++ b/arch/powerpc/configs/fsl-emb-nonhw.config @@ -118,7 +118,6 @@ CONFIG_SYSVIPC=y CONFIG_TMPFS=y CONFIG_UBIFS_FS=y CONFIG_UDF_FS=m -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_UFS_FS=m CONFIG_UIO=y CONFIG_UNIX=y diff --git a/arch/powerpc/configs/g5_defconfig b/arch/powerpc/configs/g5_defconfig index ceb3c770786f..fbfcc85e4dc0 100644 --- a/arch/powerpc/configs/g5_defconfig +++ b/arch/powerpc/configs/g5_defconfig @@ -52,7 +52,6 @@ CONFIG_NF_CONNTRACK_IRC=m CONFIG_NF_CONNTRACK_TFTP=m CONFIG_NF_CT_NETLINK=m CONFIG_NF_CONNTRACK_IPV4=m -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_DEVTMPFS=y CONFIG_DEVTMPFS_MOUNT=y CONFIG_BLK_DEV_LOOP=y @@ -244,7 +243,6 @@ CONFIG_CRC_T10DIF=y CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_KERNEL=y CONFIG_DEBUG_MUTEXES=y -CONFIG_LATENCYTOP=y CONFIG_BOOTX_TEXT=y CONFIG_CRYPTO_TEST=m CONFIG_CRYPTO_PCBC=m diff --git a/arch/powerpc/configs/gamecube_defconfig b/arch/powerpc/configs/gamecube_defconfig index 805b0f87653c..85e73c3bd859 100644 --- a/arch/powerpc/configs/gamecube_defconfig +++ b/arch/powerpc/configs/gamecube_defconfig @@ -35,7 +35,6 @@ CONFIG_IP_PNP_RARP=y # CONFIG_INET_DIAG is not set # CONFIG_IPV6 is not set # CONFIG_WIRELESS is not set -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" # CONFIG_STANDALONE is not set # CONFIG_FW_LOADER is not set CONFIG_BLK_DEV_LOOP=y @@ -91,7 +90,6 @@ CONFIG_CRC_CCITT=y CONFIG_PRINTK_TIME=y CONFIG_DEBUG_SPINLOCK=y CONFIG_DEBUG_MUTEXES=y -CONFIG_LATENCYTOP=y CONFIG_SCHED_TRACER=y CONFIG_DMA_API_DEBUG=y CONFIG_PPC_EARLY_DEBUG=y diff --git a/arch/powerpc/configs/holly_defconfig b/arch/powerpc/configs/holly_defconfig index 71d8d2430b6c..067f433c8f5e 100644 --- a/arch/powerpc/configs/holly_defconfig +++ b/arch/powerpc/configs/holly_defconfig @@ -27,7 +27,6 @@ CONFIG_IP_PNP_DHCP=y CONFIG_IP_PNP_BOOTP=y CONFIG_SYN_COOKIES=y # CONFIG_IPV6 is not set -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" # CONFIG_FW_LOADER is not set CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_RAM=y diff --git a/arch/powerpc/configs/linkstation_defconfig b/arch/powerpc/configs/linkstation_defconfig index 477794c41d50..ea59f3d146df 100644 --- a/arch/powerpc/configs/linkstation_defconfig +++ b/arch/powerpc/configs/linkstation_defconfig @@ -48,7 +48,6 @@ CONFIG_IP_NF_RAW=m CONFIG_IP_NF_ARPTABLES=m CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_MTD=y CONFIG_MTD_CMDLINE_PARTS=y CONFIG_MTD_BLOCK=y diff --git a/arch/powerpc/configs/maple_defconfig b/arch/powerpc/configs/maple_defconfig index c5f2005005d3..2975e64629aa 100644 --- a/arch/powerpc/configs/maple_defconfig +++ b/arch/powerpc/configs/maple_defconfig @@ -36,7 +36,6 @@ CONFIG_IP_MULTICAST=y CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y # CONFIG_IPV6 is not set -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_SIZE=8192 # CONFIG_SCSI_PROC_FS is not set @@ -104,7 +103,6 @@ CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_KERNEL=y CONFIG_DEBUG_STACK_USAGE=y CONFIG_DEBUG_STACKOVERFLOW=y -CONFIG_LATENCYTOP=y CONFIG_XMON=y CONFIG_XMON_DEFAULT=y CONFIG_BOOTX_TEXT=y diff --git a/arch/powerpc/configs/mgcoge_defconfig b/arch/powerpc/configs/mgcoge_defconfig index 5d5f08e5b8d9..6ce4f206eac7 100644 --- a/arch/powerpc/configs/mgcoge_defconfig +++ b/arch/powerpc/configs/mgcoge_defconfig @@ -30,7 +30,6 @@ CONFIG_SYN_COOKIES=y # CONFIG_IPV6 is not set CONFIG_NETFILTER=y CONFIG_TIPC=y -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" # CONFIG_FW_LOADER is not set CONFIG_MTD=y CONFIG_MTD_CMDLINE_PARTS=y diff --git a/arch/powerpc/configs/mpc512x_defconfig b/arch/powerpc/configs/mpc512x_defconfig index e4bf8aa87e60..6203c1093a3a 100644 --- a/arch/powerpc/configs/mpc512x_defconfig +++ b/arch/powerpc/configs/mpc512x_defconfig @@ -35,7 +35,6 @@ CONFIG_CAN_VCAN=y CONFIG_CAN_MSCAN=y CONFIG_CAN_DEBUG_DEVICES=y # CONFIG_WIRELESS is not set -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_DEVTMPFS=y CONFIG_DEVTMPFS_MOUNT=y # CONFIG_PREVENT_FIRMWARE_BUILD is not set diff --git a/arch/powerpc/configs/mpc5200_defconfig b/arch/powerpc/configs/mpc5200_defconfig index 7a2b2aa37def..6f87a5c74960 100644 --- a/arch/powerpc/configs/mpc5200_defconfig +++ b/arch/powerpc/configs/mpc5200_defconfig @@ -27,7 +27,6 @@ CONFIG_IP_PNP_DHCP=y CONFIG_IP_PNP_BOOTP=y CONFIG_SYN_COOKIES=y # CONFIG_IPV6 is not set -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_MTD=y CONFIG_MTD_CMDLINE_PARTS=y CONFIG_MTD_BLOCK=y diff --git a/arch/powerpc/configs/mpc7448_hpc2_defconfig b/arch/powerpc/configs/mpc7448_hpc2_defconfig index 4b14c02b437c..19406a6c2648 100644 --- a/arch/powerpc/configs/mpc7448_hpc2_defconfig +++ b/arch/powerpc/configs/mpc7448_hpc2_defconfig @@ -25,7 +25,6 @@ CONFIG_IP_PNP_DHCP=y CONFIG_IP_PNP_BOOTP=y CONFIG_SYN_COOKIES=y # CONFIG_IPV6 is not set -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" # CONFIG_FW_LOADER is not set CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_RAM=y diff --git a/arch/powerpc/configs/mpc8272_ads_defconfig b/arch/powerpc/configs/mpc8272_ads_defconfig index b1e88b64536b..00a4d2bf43b2 100644 --- a/arch/powerpc/configs/mpc8272_ads_defconfig +++ b/arch/powerpc/configs/mpc8272_ads_defconfig @@ -23,7 +23,6 @@ CONFIG_IP_PNP_DHCP=y CONFIG_IP_PNP_BOOTP=y CONFIG_SYN_COOKIES=y CONFIG_NETFILTER=y -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" # CONFIG_FW_LOADER is not set CONFIG_MTD=y CONFIG_MTD_BLOCK=y diff --git a/arch/powerpc/configs/mpc83xx_defconfig b/arch/powerpc/configs/mpc83xx_defconfig index 005d00020fb9..be125729635c 100644 --- a/arch/powerpc/configs/mpc83xx_defconfig +++ b/arch/powerpc/configs/mpc83xx_defconfig @@ -37,7 +37,6 @@ CONFIG_IP_PNP_BOOTP=y CONFIG_SYN_COOKIES=y CONFIG_INET_ESP=y # CONFIG_IPV6 is not set -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_DEVTMPFS=y CONFIG_DEVTMPFS_MOUNT=y # CONFIG_FW_LOADER is not set diff --git a/arch/powerpc/configs/mpc885_ads_defconfig b/arch/powerpc/configs/mpc885_ads_defconfig index ec3fcc2bf737..285d506c5a76 100644 --- a/arch/powerpc/configs/mpc885_ads_defconfig +++ b/arch/powerpc/configs/mpc885_ads_defconfig @@ -27,7 +27,6 @@ CONFIG_SYN_COOKIES=y # CONFIG_INET_XFRM_MODE_TUNNEL is not set # CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_IPV6 is not set -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" # CONFIG_FW_LOADER is not set CONFIG_MTD=y CONFIG_MTD_BLOCK=y diff --git a/arch/powerpc/configs/mvme5100_defconfig b/arch/powerpc/configs/mvme5100_defconfig index 63e38c7220f1..0a0d046fc445 100644 --- a/arch/powerpc/configs/mvme5100_defconfig +++ b/arch/powerpc/configs/mvme5100_defconfig @@ -58,7 +58,6 @@ CONFIG_IP_NF_ARPTABLES=m CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m CONFIG_LAPB=m -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_COUNT=2 diff --git a/arch/powerpc/configs/pasemi_defconfig b/arch/powerpc/configs/pasemi_defconfig index c0423b2cf7c0..4b6d31d4474e 100644 --- a/arch/powerpc/configs/pasemi_defconfig +++ b/arch/powerpc/configs/pasemi_defconfig @@ -44,7 +44,6 @@ CONFIG_SYN_COOKIES=y CONFIG_INET_AH=y CONFIG_INET_ESP=y # CONFIG_IPV6 is not set -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_DEVTMPFS=y CONFIG_DEVTMPFS_MOUNT=y CONFIG_MTD=y diff --git a/arch/powerpc/configs/pmac32_defconfig b/arch/powerpc/configs/pmac32_defconfig index 50b610b48914..7e6654848531 100644 --- a/arch/powerpc/configs/pmac32_defconfig +++ b/arch/powerpc/configs/pmac32_defconfig @@ -112,7 +112,6 @@ CONFIG_BT_HCIBFUSB=m CONFIG_CFG80211=m CONFIG_MAC80211=m CONFIG_MAC80211_LEDS=y -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" # CONFIG_STANDALONE is not set CONFIG_CONNECTOR=y CONFIG_MAC_FLOPPY=m @@ -293,7 +292,6 @@ CONFIG_CRC_T10DIF=y CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_KERNEL=y CONFIG_DETECT_HUNG_TASK=y -CONFIG_LATENCYTOP=y CONFIG_XMON=y CONFIG_XMON_DEFAULT=y CONFIG_BOOTX_TEXT=y diff --git a/arch/powerpc/configs/powernv_defconfig b/arch/powerpc/configs/powernv_defconfig index ef2ef98d3f28..34219d555e8a 100644 --- a/arch/powerpc/configs/powernv_defconfig +++ b/arch/powerpc/configs/powernv_defconfig @@ -98,7 +98,6 @@ CONFIG_NET_ACT_BPF=m CONFIG_DNS_RESOLVER=y CONFIG_BPF_JIT=y # CONFIG_WIRELESS is not set -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_DEVTMPFS=y CONFIG_DEVTMPFS_MOUNT=y CONFIG_MTD=y @@ -317,7 +316,6 @@ CONFIG_DEBUG_STACK_USAGE=y CONFIG_DEBUG_STACKOVERFLOW=y CONFIG_SOFTLOCKUP_DETECTOR=y CONFIG_HARDLOCKUP_DETECTOR=y -CONFIG_LATENCYTOP=y CONFIG_FUNCTION_TRACER=y CONFIG_SCHED_TRACER=y CONFIG_FTRACE_SYSCALLS=y diff --git a/arch/powerpc/configs/ppc40x_defconfig b/arch/powerpc/configs/ppc40x_defconfig index 689d7e276769..8f136b52198b 100644 --- a/arch/powerpc/configs/ppc40x_defconfig +++ b/arch/powerpc/configs/ppc40x_defconfig @@ -25,7 +25,6 @@ CONFIG_IP_PNP_BOOTP=y # CONFIG_INET_XFRM_MODE_TRANSPORT is not set # CONFIG_INET_XFRM_MODE_TUNNEL is not set # CONFIG_INET_XFRM_MODE_BEET is not set -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_CONNECTOR=y CONFIG_MTD=y CONFIG_MTD_CMDLINE_PARTS=y diff --git a/arch/powerpc/configs/ppc44x_defconfig b/arch/powerpc/configs/ppc44x_defconfig index db48039e0b11..67952819593e 100644 --- a/arch/powerpc/configs/ppc44x_defconfig +++ b/arch/powerpc/configs/ppc44x_defconfig @@ -36,7 +36,6 @@ CONFIG_IP_PNP_BOOTP=y # CONFIG_INET_XFRM_MODE_TUNNEL is not set # CONFIG_INET_XFRM_MODE_BEET is not set CONFIG_BRIDGE=m -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_CONNECTOR=y CONFIG_MTD=y CONFIG_MTD_BLOCK=y diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig index 91fdb619b484..dc83fefa04f7 100644 --- a/arch/powerpc/configs/ppc64_defconfig +++ b/arch/powerpc/configs/ppc64_defconfig @@ -89,7 +89,7 @@ CONFIG_SYN_COOKIES=y CONFIG_INET_AH=m CONFIG_INET_ESP=m CONFIG_INET_IPCOMP=m -# CONFIG_IPV6 is not set +CONFIG_IPV6=y CONFIG_NETFILTER=y # CONFIG_NETFILTER_ADVANCED is not set CONFIG_BRIDGE=m @@ -98,7 +98,6 @@ CONFIG_NET_CLS_BPF=m CONFIG_NET_CLS_ACT=y CONFIG_NET_ACT_BPF=m CONFIG_BPF_JIT=y -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_DEVTMPFS=y CONFIG_DEVTMPFS_MOUNT=y CONFIG_BLK_DEV_FD=y @@ -367,7 +366,6 @@ CONFIG_DEBUG_STACKOVERFLOW=y CONFIG_SOFTLOCKUP_DETECTOR=y CONFIG_HARDLOCKUP_DETECTOR=y CONFIG_DEBUG_MUTEXES=y -CONFIG_LATENCYTOP=y CONFIG_FUNCTION_TRACER=y CONFIG_SCHED_TRACER=y CONFIG_BLK_DEV_IO_TRACE=y diff --git a/arch/powerpc/configs/ppc64e_defconfig b/arch/powerpc/configs/ppc64e_defconfig index 41d85cb3c9a2..0d746774c2bd 100644 --- a/arch/powerpc/configs/ppc64e_defconfig +++ b/arch/powerpc/configs/ppc64e_defconfig @@ -50,7 +50,6 @@ CONFIG_INET_IPCOMP=m CONFIG_NETFILTER=y # CONFIG_NETFILTER_ADVANCED is not set CONFIG_BRIDGE=m -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_DEVTMPFS=y CONFIG_DEVTMPFS_MOUNT=y CONFIG_BLK_DEV_FD=y @@ -223,7 +222,6 @@ CONFIG_DEBUG_STACK_USAGE=y CONFIG_DEBUG_STACKOVERFLOW=y CONFIG_DETECT_HUNG_TASK=y CONFIG_DEBUG_MUTEXES=y -CONFIG_LATENCYTOP=y CONFIG_IRQSOFF_TRACER=y CONFIG_SCHED_TRACER=y CONFIG_BLK_DEV_IO_TRACE=y diff --git a/arch/powerpc/configs/ppc6xx_defconfig b/arch/powerpc/configs/ppc6xx_defconfig index aa51b9b66fa2..9dca4cffa623 100644 --- a/arch/powerpc/configs/ppc6xx_defconfig +++ b/arch/powerpc/configs/ppc6xx_defconfig @@ -345,7 +345,6 @@ CONFIG_MAC80211_LEDS=y CONFIG_MAC80211_DEBUGFS=y CONFIG_NET_9P=m CONFIG_NET_9P_VIRTIO=m -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_DEBUG_DEVRES=y CONFIG_CONNECTOR=y CONFIG_PARPORT=m @@ -1123,6 +1122,7 @@ CONFIG_NLS_KOI8_R=m CONFIG_NLS_KOI8_U=m CONFIG_DEBUG_INFO=y CONFIG_UNUSED_SYMBOLS=y +CONFIG_HEADERS_INSTALL=y CONFIG_HEADERS_CHECK=y CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_KERNEL=y @@ -1147,7 +1147,6 @@ CONFIG_FAIL_MAKE_REQUEST=y CONFIG_FAIL_IO_TIMEOUT=y CONFIG_FAULT_INJECTION_DEBUG_FS=y CONFIG_FAULT_INJECTION_STACKTRACE_FILTER=y -CONFIG_LATENCYTOP=y CONFIG_SCHED_TRACER=y CONFIG_STACK_TRACER=y CONFIG_BLK_DEV_IO_TRACE=y diff --git a/arch/powerpc/configs/pq2fads_defconfig b/arch/powerpc/configs/pq2fads_defconfig index 0ededa8c837d..9d8a76857c6f 100644 --- a/arch/powerpc/configs/pq2fads_defconfig +++ b/arch/powerpc/configs/pq2fads_defconfig @@ -24,7 +24,6 @@ CONFIG_IP_PNP_DHCP=y CONFIG_IP_PNP_BOOTP=y CONFIG_SYN_COOKIES=y CONFIG_NETFILTER=y -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" # CONFIG_FW_LOADER is not set CONFIG_MTD=y CONFIG_MTD_BLOCK=y diff --git a/arch/powerpc/configs/ps3_defconfig b/arch/powerpc/configs/ps3_defconfig index cf8d55f67272..314c63939816 100644 --- a/arch/powerpc/configs/ps3_defconfig +++ b/arch/powerpc/configs/ps3_defconfig @@ -63,7 +63,6 @@ CONFIG_CFG80211=m CONFIG_CFG80211_WEXT=y CONFIG_MAC80211=m # CONFIG_MAC80211_RC_MINSTREL is not set -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_SIZE=65535 diff --git a/arch/powerpc/configs/pseries_defconfig b/arch/powerpc/configs/pseries_defconfig index 62e12f61a3b2..38abc9c1770a 100644 --- a/arch/powerpc/configs/pseries_defconfig +++ b/arch/powerpc/configs/pseries_defconfig @@ -83,7 +83,6 @@ CONFIG_NET_CLS_BPF=m CONFIG_NET_CLS_ACT=y CONFIG_NET_ACT_BPF=m CONFIG_BPF_JIT=y -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_DEVTMPFS=y CONFIG_DEVTMPFS_MOUNT=y CONFIG_PARPORT=m @@ -290,7 +289,6 @@ CONFIG_DEBUG_STACK_USAGE=y CONFIG_DEBUG_STACKOVERFLOW=y CONFIG_SOFTLOCKUP_DETECTOR=y CONFIG_HARDLOCKUP_DETECTOR=y -CONFIG_LATENCYTOP=y CONFIG_FUNCTION_TRACER=y CONFIG_SCHED_TRACER=y CONFIG_BLK_DEV_IO_TRACE=y diff --git a/arch/powerpc/configs/skiroot_defconfig b/arch/powerpc/configs/skiroot_defconfig index a887616e35a2..557b530b2f70 100644 --- a/arch/powerpc/configs/skiroot_defconfig +++ b/arch/powerpc/configs/skiroot_defconfig @@ -68,7 +68,6 @@ CONFIG_SYN_COOKIES=y # CONFIG_INET_XFRM_MODE_BEET is not set CONFIG_DNS_RESOLVER=y # CONFIG_WIRELESS is not set -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_DEVTMPFS=y CONFIG_DEVTMPFS_MOUNT=y CONFIG_MTD=m diff --git a/arch/powerpc/configs/storcenter_defconfig b/arch/powerpc/configs/storcenter_defconfig index 74bca2eccd0f..6c39c52b8e4a 100644 --- a/arch/powerpc/configs/storcenter_defconfig +++ b/arch/powerpc/configs/storcenter_defconfig @@ -26,7 +26,6 @@ CONFIG_IP_PNP_DHCP=y # CONFIG_INET_XFRM_MODE_TUNNEL is not set # CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_IPV6 is not set -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_MTD=y CONFIG_MTD_CMDLINE_PARTS=y CONFIG_MTD_BLOCK=y diff --git a/arch/powerpc/configs/tqm8xx_defconfig b/arch/powerpc/configs/tqm8xx_defconfig index cd72193fac0a..7493f36dd6e9 100644 --- a/arch/powerpc/configs/tqm8xx_defconfig +++ b/arch/powerpc/configs/tqm8xx_defconfig @@ -32,7 +32,6 @@ CONFIG_SYN_COOKIES=y # CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_IPV6 is not set # CONFIG_WIRELESS is not set -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" # CONFIG_FW_LOADER is not set CONFIG_MTD=y CONFIG_MTD_CMDLINE_PARTS=y diff --git a/arch/powerpc/configs/wii_defconfig b/arch/powerpc/configs/wii_defconfig index f5c366b02828..5a04448ad6b5 100644 --- a/arch/powerpc/configs/wii_defconfig +++ b/arch/powerpc/configs/wii_defconfig @@ -41,7 +41,6 @@ CONFIG_BT_BNEP_MC_FILTER=y CONFIG_BT_HIDP=y CONFIG_CFG80211=y CONFIG_MAC80211=y -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" # CONFIG_STANDALONE is not set CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_RAM=y @@ -123,7 +122,6 @@ CONFIG_PRINTK_TIME=y CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_SPINLOCK=y CONFIG_DEBUG_MUTEXES=y -CONFIG_LATENCYTOP=y CONFIG_SCHED_TRACER=y CONFIG_BLK_DEV_IO_TRACE=y CONFIG_DMA_API_DEBUG=y diff --git a/arch/powerpc/include/asm/book3s/64/mmu.h b/arch/powerpc/include/asm/book3s/64/mmu.h index 74d24201fc4f..23b83d3593e2 100644 --- a/arch/powerpc/include/asm/book3s/64/mmu.h +++ b/arch/powerpc/include/asm/book3s/64/mmu.h @@ -116,8 +116,6 @@ typedef struct { /* Number of users of the external (Nest) MMU */ atomic_t copros; - /* NPU NMMU context */ - struct npu_context *npu_context; struct hash_mm_context *hash_context; unsigned long vdso_base; diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index ccf00a8b98c6..62e6ea0a7650 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -274,8 +274,15 @@ extern unsigned long __vmalloc_end; #define VMALLOC_START __vmalloc_start #define VMALLOC_END __vmalloc_end +static inline unsigned int ioremap_max_order(void) +{ + if (radix_enabled()) + return PUD_SHIFT; + return 7 + PAGE_SHIFT; /* default from linux/vmalloc.h */ +} +#define IOREMAP_MAX_ORDER ioremap_max_order() + extern unsigned long __kernel_virt_start; -extern unsigned long __kernel_virt_size; extern unsigned long __kernel_io_start; extern unsigned long __kernel_io_end; #define KERN_VIRT_START __kernel_virt_start @@ -1343,5 +1350,26 @@ static inline bool is_pte_rw_upgrade(unsigned long old_val, unsigned long new_va return false; } +/* + * Like pmd_huge() and pmd_large(), but works regardless of config options + */ +#define pmd_is_leaf pmd_is_leaf +static inline bool pmd_is_leaf(pmd_t pmd) +{ + return !!(pmd_raw(pmd) & cpu_to_be64(_PAGE_PTE)); +} + +#define pud_is_leaf pud_is_leaf +static inline bool pud_is_leaf(pud_t pud) +{ + return !!(pud_raw(pud) & cpu_to_be64(_PAGE_PTE)); +} + +#define pgd_is_leaf pgd_is_leaf +static inline bool pgd_is_leaf(pgd_t pgd) +{ + return !!(pgd_raw(pgd) & cpu_to_be64(_PAGE_PTE)); +} + #endif /* __ASSEMBLY__ */ #endif /* _ASM_POWERPC_BOOK3S_64_PGTABLE_H_ */ diff --git a/arch/powerpc/include/asm/book3s/64/radix.h b/arch/powerpc/include/asm/book3s/64/radix.h index 574eca33f893..e04a839cb5b9 100644 --- a/arch/powerpc/include/asm/book3s/64/radix.h +++ b/arch/powerpc/include/asm/book3s/64/radix.h @@ -266,6 +266,9 @@ extern void radix__vmemmap_remove_mapping(unsigned long start, extern int radix__map_kernel_page(unsigned long ea, unsigned long pa, pgprot_t flags, unsigned int psz); +extern int radix__ioremap_range(unsigned long ea, phys_addr_t pa, + unsigned long size, pgprot_t prot, int nid); + static inline unsigned long radix__get_tree_size(void) { unsigned long rts_field; diff --git a/arch/powerpc/include/asm/cache.h b/arch/powerpc/include/asm/cache.h index 40ea5b3781c6..b3388d95f451 100644 --- a/arch/powerpc/include/asm/cache.h +++ b/arch/powerpc/include/asm/cache.h @@ -33,7 +33,8 @@ #define IFETCH_ALIGN_BYTES (1 << IFETCH_ALIGN_SHIFT) -#if defined(__powerpc64__) && !defined(__ASSEMBLY__) +#if !defined(__ASSEMBLY__) +#ifdef CONFIG_PPC64 struct ppc_cache_info { u32 size; @@ -53,7 +54,28 @@ struct ppc64_caches { }; extern struct ppc64_caches ppc64_caches; -#endif /* __powerpc64__ && ! __ASSEMBLY__ */ + +static inline u32 l1_cache_shift(void) +{ + return ppc64_caches.l1d.log_block_size; +} + +static inline u32 l1_cache_bytes(void) +{ + return ppc64_caches.l1d.block_size; +} +#else +static inline u32 l1_cache_shift(void) +{ + return L1_CACHE_SHIFT; +} + +static inline u32 l1_cache_bytes(void) +{ + return L1_CACHE_BYTES; +} +#endif +#endif /* ! __ASSEMBLY__ */ #if defined(__ASSEMBLY__) /* @@ -85,22 +107,22 @@ extern void _set_L3CR(unsigned long); static inline void dcbz(void *addr) { - __asm__ __volatile__ ("dcbz 0, %0" : : "r"(addr) : "memory"); + __asm__ __volatile__ ("dcbz %y0" : : "Z"(*(u8 *)addr) : "memory"); } static inline void dcbi(void *addr) { - __asm__ __volatile__ ("dcbi 0, %0" : : "r"(addr) : "memory"); + __asm__ __volatile__ ("dcbi %y0" : : "Z"(*(u8 *)addr) : "memory"); } static inline void dcbf(void *addr) { - __asm__ __volatile__ ("dcbf 0, %0" : : "r"(addr) : "memory"); + __asm__ __volatile__ ("dcbf %y0" : : "Z"(*(u8 *)addr) : "memory"); } static inline void dcbst(void *addr) { - __asm__ __volatile__ ("dcbst 0, %0" : : "r"(addr) : "memory"); + __asm__ __volatile__ ("dcbst %y0" : : "Z"(*(u8 *)addr) : "memory"); } #endif /* !__ASSEMBLY__ */ #endif /* __KERNEL__ */ diff --git a/arch/powerpc/include/asm/cacheflush.h b/arch/powerpc/include/asm/cacheflush.h index 74d60cfe8ce5..eef388f2659f 100644 --- a/arch/powerpc/include/asm/cacheflush.h +++ b/arch/powerpc/include/asm/cacheflush.h @@ -29,9 +29,12 @@ * not expect this type of fault. flush_cache_vmap is not exactly the right * place to put this, but it seems to work well enough. */ -#define flush_cache_vmap(start, end) do { asm volatile("ptesync" ::: "memory"); } while (0) +static inline void flush_cache_vmap(unsigned long start, unsigned long end) +{ + asm volatile("ptesync" ::: "memory"); +} #else -#define flush_cache_vmap(start, end) do { } while (0) +static inline void flush_cache_vmap(unsigned long start, unsigned long end) { } #endif #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 @@ -54,20 +57,29 @@ static inline void __flush_dcache_icache_phys(unsigned long physaddr) } #endif -#ifdef CONFIG_PPC32 /* * Write any modified data cache blocks out to memory and invalidate them. * Does not invalidate the corresponding instruction cache blocks. */ static inline void flush_dcache_range(unsigned long start, unsigned long stop) { - void *addr = (void *)(start & ~(L1_CACHE_BYTES - 1)); - unsigned long size = stop - (unsigned long)addr + (L1_CACHE_BYTES - 1); + unsigned long shift = l1_cache_shift(); + unsigned long bytes = l1_cache_bytes(); + void *addr = (void *)(start & ~(bytes - 1)); + unsigned long size = stop - (unsigned long)addr + (bytes - 1); unsigned long i; - for (i = 0; i < size >> L1_CACHE_SHIFT; i++, addr += L1_CACHE_BYTES) + if (IS_ENABLED(CONFIG_PPC64)) { + mb(); /* sync */ + isync(); + } + + for (i = 0; i < size >> shift; i++, addr += bytes) dcbf(addr); mb(); /* sync */ + + if (IS_ENABLED(CONFIG_PPC64)) + isync(); } /* @@ -77,11 +89,13 @@ static inline void flush_dcache_range(unsigned long start, unsigned long stop) */ static inline void clean_dcache_range(unsigned long start, unsigned long stop) { - void *addr = (void *)(start & ~(L1_CACHE_BYTES - 1)); - unsigned long size = stop - (unsigned long)addr + (L1_CACHE_BYTES - 1); + unsigned long shift = l1_cache_shift(); + unsigned long bytes = l1_cache_bytes(); + void *addr = (void *)(start & ~(bytes - 1)); + unsigned long size = stop - (unsigned long)addr + (bytes - 1); unsigned long i; - for (i = 0; i < size >> L1_CACHE_SHIFT; i++, addr += L1_CACHE_BYTES) + for (i = 0; i < size >> shift; i++, addr += bytes) dcbst(addr); mb(); /* sync */ } @@ -94,21 +108,17 @@ static inline void clean_dcache_range(unsigned long start, unsigned long stop) static inline void invalidate_dcache_range(unsigned long start, unsigned long stop) { - void *addr = (void *)(start & ~(L1_CACHE_BYTES - 1)); - unsigned long size = stop - (unsigned long)addr + (L1_CACHE_BYTES - 1); + unsigned long shift = l1_cache_shift(); + unsigned long bytes = l1_cache_bytes(); + void *addr = (void *)(start & ~(bytes - 1)); + unsigned long size = stop - (unsigned long)addr + (bytes - 1); unsigned long i; - for (i = 0; i < size >> L1_CACHE_SHIFT; i++, addr += L1_CACHE_BYTES) + for (i = 0; i < size >> shift; i++, addr += bytes) dcbi(addr); mb(); /* sync */ } -#endif /* CONFIG_PPC32 */ -#ifdef CONFIG_PPC64 -extern void flush_dcache_range(unsigned long start, unsigned long stop); -extern void flush_inval_dcache_range(unsigned long start, unsigned long stop); -#endif - #define copy_to_user_page(vma, page, vaddr, dst, src, len) \ do { \ memcpy(dst, src, len); \ diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h index 841a0be6c1b2..33f4f72eb035 100644 --- a/arch/powerpc/include/asm/exception-64s.h +++ b/arch/powerpc/include/asm/exception-64s.h @@ -30,25 +30,13 @@ * exception handlers (including pSeries LPAR) and iSeries LPAR * implementations as possible. */ -#include <asm/head-64.h> #include <asm/feature-fixups.h> -/* PACA save area offsets (exgen, exmc, etc) */ -#define EX_R9 0 -#define EX_R10 8 -#define EX_R11 16 -#define EX_R12 24 -#define EX_R13 32 -#define EX_DAR 40 -#define EX_DSISR 48 -#define EX_CCR 52 -#define EX_CFAR 56 -#define EX_PPR 64 +/* PACA save area size in u64 units (exgen, exmc, etc) */ #if defined(CONFIG_RELOCATABLE) -#define EX_CTR 72 -#define EX_SIZE 10 /* size in u64 units */ +#define EX_SIZE 10 #else -#define EX_SIZE 9 /* size in u64 units */ +#define EX_SIZE 9 #endif /* @@ -56,12 +44,7 @@ */ #define MAX_MCE_DEPTH 4 -/* - * EX_R3 is only used by the bad_stack handler. bad_stack reloads and - * saves DAR from SPRN_DAR, and EX_DAR is not used. So EX_R3 can overlap - * with EX_DAR. - */ -#define EX_R3 EX_DAR +#ifdef __ASSEMBLY__ #define STF_ENTRY_BARRIER_SLOT \ STF_ENTRY_BARRIER_FIXUP_SECTION; \ @@ -144,588 +127,6 @@ hrfid; \ b hrfi_flush_fallback -#ifdef CONFIG_RELOCATABLE -#define __EXCEPTION_PROLOG_2_RELON(label, h) \ - mfspr r11,SPRN_##h##SRR0; /* save SRR0 */ \ - LOAD_HANDLER(r12,label); \ - mtctr r12; \ - mfspr r12,SPRN_##h##SRR1; /* and SRR1 */ \ - li r10,MSR_RI; \ - mtmsrd r10,1; /* Set RI (EE=0) */ \ - bctr; -#else -/* If not relocatable, we can jump directly -- and save messing with LR */ -#define __EXCEPTION_PROLOG_2_RELON(label, h) \ - mfspr r11,SPRN_##h##SRR0; /* save SRR0 */ \ - mfspr r12,SPRN_##h##SRR1; /* and SRR1 */ \ - li r10,MSR_RI; \ - mtmsrd r10,1; /* Set RI (EE=0) */ \ - b label; -#endif -#define EXCEPTION_PROLOG_2_RELON(label, h) \ - __EXCEPTION_PROLOG_2_RELON(label, h) - -/* - * As EXCEPTION_PROLOG(), except we've already got relocation on so no need to - * rfid. Save LR in case we're CONFIG_RELOCATABLE, in which case - * EXCEPTION_PROLOG_2_RELON will be using LR. - */ -#define EXCEPTION_RELON_PROLOG(area, label, h, extra, vec) \ - SET_SCRATCH0(r13); /* save r13 */ \ - EXCEPTION_PROLOG_0(area); \ - EXCEPTION_PROLOG_1(area, extra, vec); \ - EXCEPTION_PROLOG_2_RELON(label, h) - -/* - * We're short on space and time in the exception prolog, so we can't - * use the normal LOAD_REG_IMMEDIATE macro to load the address of label. - * Instead we get the base of the kernel from paca->kernelbase and or in the low - * part of label. This requires that the label be within 64KB of kernelbase, and - * that kernelbase be 64K aligned. - */ -#define LOAD_HANDLER(reg, label) \ - ld reg,PACAKBASE(r13); /* get high part of &label */ \ - ori reg,reg,FIXED_SYMBOL_ABS_ADDR(label); - -#define __LOAD_HANDLER(reg, label) \ - ld reg,PACAKBASE(r13); \ - ori reg,reg,(ABS_ADDR(label))@l; - -/* - * Branches from unrelocated code (e.g., interrupts) to labels outside - * head-y require >64K offsets. - */ -#define __LOAD_FAR_HANDLER(reg, label) \ - ld reg,PACAKBASE(r13); \ - ori reg,reg,(ABS_ADDR(label))@l; \ - addis reg,reg,(ABS_ADDR(label))@h; - -/* Exception register prefixes */ -#define EXC_HV H -#define EXC_STD - -#if defined(CONFIG_RELOCATABLE) -/* - * If we support interrupts with relocation on AND we're a relocatable kernel, - * we need to use CTR to get to the 2nd level handler. So, save/restore it - * when required. - */ -#define SAVE_CTR(reg, area) mfctr reg ; std reg,area+EX_CTR(r13) -#define GET_CTR(reg, area) ld reg,area+EX_CTR(r13) -#define RESTORE_CTR(reg, area) ld reg,area+EX_CTR(r13) ; mtctr reg -#else -/* ...else CTR is unused and in register. */ -#define SAVE_CTR(reg, area) -#define GET_CTR(reg, area) mfctr reg -#define RESTORE_CTR(reg, area) -#endif - -/* - * PPR save/restore macros used in exceptions_64s.S - * Used for P7 or later processors - */ -#define SAVE_PPR(area, ra) \ -BEGIN_FTR_SECTION_NESTED(940) \ - ld ra,area+EX_PPR(r13); /* Read PPR from paca */ \ - std ra,_PPR(r1); \ -END_FTR_SECTION_NESTED(CPU_FTR_HAS_PPR,CPU_FTR_HAS_PPR,940) - -#define RESTORE_PPR_PACA(area, ra) \ -BEGIN_FTR_SECTION_NESTED(941) \ - ld ra,area+EX_PPR(r13); \ - mtspr SPRN_PPR,ra; \ -END_FTR_SECTION_NESTED(CPU_FTR_HAS_PPR,CPU_FTR_HAS_PPR,941) - -/* - * Get an SPR into a register if the CPU has the given feature - */ -#define OPT_GET_SPR(ra, spr, ftr) \ -BEGIN_FTR_SECTION_NESTED(943) \ - mfspr ra,spr; \ -END_FTR_SECTION_NESTED(ftr,ftr,943) - -/* - * Set an SPR from a register if the CPU has the given feature - */ -#define OPT_SET_SPR(ra, spr, ftr) \ -BEGIN_FTR_SECTION_NESTED(943) \ - mtspr spr,ra; \ -END_FTR_SECTION_NESTED(ftr,ftr,943) - -/* - * Save a register to the PACA if the CPU has the given feature - */ -#define OPT_SAVE_REG_TO_PACA(offset, ra, ftr) \ -BEGIN_FTR_SECTION_NESTED(943) \ - std ra,offset(r13); \ -END_FTR_SECTION_NESTED(ftr,ftr,943) - -#define EXCEPTION_PROLOG_0(area) \ - GET_PACA(r13); \ - std r9,area+EX_R9(r13); /* save r9 */ \ - OPT_GET_SPR(r9, SPRN_PPR, CPU_FTR_HAS_PPR); \ - HMT_MEDIUM; \ - std r10,area+EX_R10(r13); /* save r10 - r12 */ \ - OPT_GET_SPR(r10, SPRN_CFAR, CPU_FTR_CFAR) - -#define __EXCEPTION_PROLOG_1_PRE(area) \ - OPT_SAVE_REG_TO_PACA(area+EX_PPR, r9, CPU_FTR_HAS_PPR); \ - OPT_SAVE_REG_TO_PACA(area+EX_CFAR, r10, CPU_FTR_CFAR); \ - INTERRUPT_TO_KERNEL; \ - SAVE_CTR(r10, area); \ - mfcr r9; - -#define __EXCEPTION_PROLOG_1_POST(area) \ - std r11,area+EX_R11(r13); \ - std r12,area+EX_R12(r13); \ - GET_SCRATCH0(r10); \ - std r10,area+EX_R13(r13) - -/* - * This version of the EXCEPTION_PROLOG_1 will carry - * addition parameter called "bitmask" to support - * checking of the interrupt maskable level in the SOFTEN_TEST. - * Intended to be used in MASKABLE_EXCPETION_* macros. - */ -#define MASKABLE_EXCEPTION_PROLOG_1(area, extra, vec, bitmask) \ - __EXCEPTION_PROLOG_1_PRE(area); \ - extra(vec, bitmask); \ - __EXCEPTION_PROLOG_1_POST(area); - -/* - * This version of the EXCEPTION_PROLOG_1 is intended - * to be used in STD_EXCEPTION* macros - */ -#define _EXCEPTION_PROLOG_1(area, extra, vec) \ - __EXCEPTION_PROLOG_1_PRE(area); \ - extra(vec); \ - __EXCEPTION_PROLOG_1_POST(area); - -#define EXCEPTION_PROLOG_1(area, extra, vec) \ - _EXCEPTION_PROLOG_1(area, extra, vec) - -#define __EXCEPTION_PROLOG_2(label, h) \ - ld r10,PACAKMSR(r13); /* get MSR value for kernel */ \ - mfspr r11,SPRN_##h##SRR0; /* save SRR0 */ \ - LOAD_HANDLER(r12,label) \ - mtspr SPRN_##h##SRR0,r12; \ - mfspr r12,SPRN_##h##SRR1; /* and SRR1 */ \ - mtspr SPRN_##h##SRR1,r10; \ - h##RFI_TO_KERNEL; \ - b . /* prevent speculative execution */ -#define EXCEPTION_PROLOG_2(label, h) \ - __EXCEPTION_PROLOG_2(label, h) - -/* _NORI variant keeps MSR_RI clear */ -#define __EXCEPTION_PROLOG_2_NORI(label, h) \ - ld r10,PACAKMSR(r13); /* get MSR value for kernel */ \ - xori r10,r10,MSR_RI; /* Clear MSR_RI */ \ - mfspr r11,SPRN_##h##SRR0; /* save SRR0 */ \ - LOAD_HANDLER(r12,label) \ - mtspr SPRN_##h##SRR0,r12; \ - mfspr r12,SPRN_##h##SRR1; /* and SRR1 */ \ - mtspr SPRN_##h##SRR1,r10; \ - h##RFI_TO_KERNEL; \ - b . /* prevent speculative execution */ - -#define EXCEPTION_PROLOG_2_NORI(label, h) \ - __EXCEPTION_PROLOG_2_NORI(label, h) - -#define EXCEPTION_PROLOG(area, label, h, extra, vec) \ - SET_SCRATCH0(r13); /* save r13 */ \ - EXCEPTION_PROLOG_0(area); \ - EXCEPTION_PROLOG_1(area, extra, vec); \ - EXCEPTION_PROLOG_2(label, h); - -#define __KVMTEST(h, n) \ - lbz r10,HSTATE_IN_GUEST(r13); \ - cmpwi r10,0; \ - bne do_kvm_##h##n - -#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE -/* - * If hv is possible, interrupts come into to the hv version - * of the kvmppc_interrupt code, which then jumps to the PR handler, - * kvmppc_interrupt_pr, if the guest is a PR guest. - */ -#define kvmppc_interrupt kvmppc_interrupt_hv -#else -#define kvmppc_interrupt kvmppc_interrupt_pr -#endif - -/* - * Branch to label using its 0xC000 address. This results in instruction - * address suitable for MSR[IR]=0 or 1, which allows relocation to be turned - * on using mtmsr rather than rfid. - * - * This could set the 0xc bits for !RELOCATABLE as an immediate, rather than - * load KBASE for a slight optimisation. - */ -#define BRANCH_TO_C000(reg, label) \ - __LOAD_HANDLER(reg, label); \ - mtctr reg; \ - bctr - -#ifdef CONFIG_RELOCATABLE -#define BRANCH_TO_COMMON(reg, label) \ - __LOAD_HANDLER(reg, label); \ - mtctr reg; \ - bctr - -#define BRANCH_LINK_TO_FAR(label) \ - __LOAD_FAR_HANDLER(r12, label); \ - mtctr r12; \ - bctrl - -/* - * KVM requires __LOAD_FAR_HANDLER. - * - * __BRANCH_TO_KVM_EXIT branches are also a special case because they - * explicitly use r9 then reload it from PACA before branching. Hence - * the double-underscore. - */ -#define __BRANCH_TO_KVM_EXIT(area, label) \ - mfctr r9; \ - std r9,HSTATE_SCRATCH1(r13); \ - __LOAD_FAR_HANDLER(r9, label); \ - mtctr r9; \ - ld r9,area+EX_R9(r13); \ - bctr - -#else -#define BRANCH_TO_COMMON(reg, label) \ - b label - -#define BRANCH_LINK_TO_FAR(label) \ - bl label - -#define __BRANCH_TO_KVM_EXIT(area, label) \ - ld r9,area+EX_R9(r13); \ - b label - -#endif - -/* Do not enable RI */ -#define EXCEPTION_PROLOG_NORI(area, label, h, extra, vec) \ - EXCEPTION_PROLOG_0(area); \ - EXCEPTION_PROLOG_1(area, extra, vec); \ - EXCEPTION_PROLOG_2_NORI(label, h); - - -#define __KVM_HANDLER(area, h, n) \ - BEGIN_FTR_SECTION_NESTED(947) \ - ld r10,area+EX_CFAR(r13); \ - std r10,HSTATE_CFAR(r13); \ - END_FTR_SECTION_NESTED(CPU_FTR_CFAR,CPU_FTR_CFAR,947); \ - BEGIN_FTR_SECTION_NESTED(948) \ - ld r10,area+EX_PPR(r13); \ - std r10,HSTATE_PPR(r13); \ - END_FTR_SECTION_NESTED(CPU_FTR_HAS_PPR,CPU_FTR_HAS_PPR,948); \ - ld r10,area+EX_R10(r13); \ - std r12,HSTATE_SCRATCH0(r13); \ - sldi r12,r9,32; \ - ori r12,r12,(n); \ - /* This reloads r9 before branching to kvmppc_interrupt */ \ - __BRANCH_TO_KVM_EXIT(area, kvmppc_interrupt) - -#define __KVM_HANDLER_SKIP(area, h, n) \ - cmpwi r10,KVM_GUEST_MODE_SKIP; \ - beq 89f; \ - BEGIN_FTR_SECTION_NESTED(948) \ - ld r10,area+EX_PPR(r13); \ - std r10,HSTATE_PPR(r13); \ - END_FTR_SECTION_NESTED(CPU_FTR_HAS_PPR,CPU_FTR_HAS_PPR,948); \ - ld r10,area+EX_R10(r13); \ - std r12,HSTATE_SCRATCH0(r13); \ - sldi r12,r9,32; \ - ori r12,r12,(n); \ - /* This reloads r9 before branching to kvmppc_interrupt */ \ - __BRANCH_TO_KVM_EXIT(area, kvmppc_interrupt); \ -89: mtocrf 0x80,r9; \ - ld r9,area+EX_R9(r13); \ - ld r10,area+EX_R10(r13); \ - b kvmppc_skip_##h##interrupt - -#ifdef CONFIG_KVM_BOOK3S_64_HANDLER -#define KVMTEST(h, n) __KVMTEST(h, n) -#define KVM_HANDLER(area, h, n) __KVM_HANDLER(area, h, n) -#define KVM_HANDLER_SKIP(area, h, n) __KVM_HANDLER_SKIP(area, h, n) - -#else -#define KVMTEST(h, n) -#define KVM_HANDLER(area, h, n) -#define KVM_HANDLER_SKIP(area, h, n) -#endif - -#define NOTEST(n) - -#define EXCEPTION_PROLOG_COMMON_1() \ - std r9,_CCR(r1); /* save CR in stackframe */ \ - std r11,_NIP(r1); /* save SRR0 in stackframe */ \ - std r12,_MSR(r1); /* save SRR1 in stackframe */ \ - std r10,0(r1); /* make stack chain pointer */ \ - std r0,GPR0(r1); /* save r0 in stackframe */ \ - std r10,GPR1(r1); /* save r1 in stackframe */ \ - - -/* - * The common exception prolog is used for all except a few exceptions - * such as a segment miss on a kernel address. We have to be prepared - * to take another exception from the point where we first touch the - * kernel stack onwards. - * - * On entry r13 points to the paca, r9-r13 are saved in the paca, - * r9 contains the saved CR, r11 and r12 contain the saved SRR0 and - * SRR1, and relocation is on. - */ -#define EXCEPTION_PROLOG_COMMON(n, area) \ - andi. r10,r12,MSR_PR; /* See if coming from user */ \ - mr r10,r1; /* Save r1 */ \ - subi r1,r1,INT_FRAME_SIZE; /* alloc frame on kernel stack */ \ - beq- 1f; \ - ld r1,PACAKSAVE(r13); /* kernel stack to use */ \ -1: cmpdi cr1,r1,-INT_FRAME_SIZE; /* check if r1 is in userspace */ \ - blt+ cr1,3f; /* abort if it is */ \ - li r1,(n); /* will be reloaded later */ \ - sth r1,PACA_TRAP_SAVE(r13); \ - std r3,area+EX_R3(r13); \ - addi r3,r13,area; /* r3 -> where regs are saved*/ \ - RESTORE_CTR(r1, area); \ - b bad_stack; \ -3: EXCEPTION_PROLOG_COMMON_1(); \ - kuap_save_amr_and_lock r9, r10, cr1, cr0; \ - beq 4f; /* if from kernel mode */ \ - ACCOUNT_CPU_USER_ENTRY(r13, r9, r10); \ - SAVE_PPR(area, r9); \ -4: EXCEPTION_PROLOG_COMMON_2(area) \ - EXCEPTION_PROLOG_COMMON_3(n) \ - ACCOUNT_STOLEN_TIME - -/* Save original regs values from save area to stack frame. */ -#define EXCEPTION_PROLOG_COMMON_2(area) \ - ld r9,area+EX_R9(r13); /* move r9, r10 to stackframe */ \ - ld r10,area+EX_R10(r13); \ - std r9,GPR9(r1); \ - std r10,GPR10(r1); \ - ld r9,area+EX_R11(r13); /* move r11 - r13 to stackframe */ \ - ld r10,area+EX_R12(r13); \ - ld r11,area+EX_R13(r13); \ - std r9,GPR11(r1); \ - std r10,GPR12(r1); \ - std r11,GPR13(r1); \ - BEGIN_FTR_SECTION_NESTED(66); \ - ld r10,area+EX_CFAR(r13); \ - std r10,ORIG_GPR3(r1); \ - END_FTR_SECTION_NESTED(CPU_FTR_CFAR, CPU_FTR_CFAR, 66); \ - GET_CTR(r10, area); \ - std r10,_CTR(r1); - -#define EXCEPTION_PROLOG_COMMON_3(n) \ - std r2,GPR2(r1); /* save r2 in stackframe */ \ - SAVE_4GPRS(3, r1); /* save r3 - r6 in stackframe */ \ - SAVE_2GPRS(7, r1); /* save r7, r8 in stackframe */ \ - mflr r9; /* Get LR, later save to stack */ \ - ld r2,PACATOC(r13); /* get kernel TOC into r2 */ \ - std r9,_LINK(r1); \ - lbz r10,PACAIRQSOFTMASK(r13); \ - mfspr r11,SPRN_XER; /* save XER in stackframe */ \ - std r10,SOFTE(r1); \ - std r11,_XER(r1); \ - li r9,(n)+1; \ - std r9,_TRAP(r1); /* set trap number */ \ - li r10,0; \ - ld r11,exception_marker@toc(r2); \ - std r10,RESULT(r1); /* clear regs->result */ \ - std r11,STACK_FRAME_OVERHEAD-16(r1); /* mark the frame */ - -/* - * Exception vectors. - */ -#define STD_EXCEPTION(vec, label) \ - EXCEPTION_PROLOG(PACA_EXGEN, label, EXC_STD, KVMTEST_PR, vec); - -/* Version of above for when we have to branch out-of-line */ -#define __OOL_EXCEPTION(vec, label, hdlr) \ - SET_SCRATCH0(r13) \ - EXCEPTION_PROLOG_0(PACA_EXGEN) \ - b hdlr; - -#define STD_EXCEPTION_OOL(vec, label) \ - EXCEPTION_PROLOG_1(PACA_EXGEN, KVMTEST_PR, vec); \ - EXCEPTION_PROLOG_2(label, EXC_STD) - -#define STD_EXCEPTION_HV(loc, vec, label) \ - EXCEPTION_PROLOG(PACA_EXGEN, label, EXC_HV, KVMTEST_HV, vec); - -#define STD_EXCEPTION_HV_OOL(vec, label) \ - EXCEPTION_PROLOG_1(PACA_EXGEN, KVMTEST_HV, vec); \ - EXCEPTION_PROLOG_2(label, EXC_HV) - -#define STD_RELON_EXCEPTION(loc, vec, label) \ - /* No guest interrupts come through here */ \ - EXCEPTION_RELON_PROLOG(PACA_EXGEN, label, EXC_STD, NOTEST, vec); - -#define STD_RELON_EXCEPTION_OOL(vec, label) \ - EXCEPTION_PROLOG_1(PACA_EXGEN, NOTEST, vec); \ - EXCEPTION_PROLOG_2_RELON(label, EXC_STD) - -#define STD_RELON_EXCEPTION_HV(loc, vec, label) \ - EXCEPTION_RELON_PROLOG(PACA_EXGEN, label, EXC_HV, KVMTEST_HV, vec); - -#define STD_RELON_EXCEPTION_HV_OOL(vec, label) \ - EXCEPTION_PROLOG_1(PACA_EXGEN, KVMTEST_HV, vec); \ - EXCEPTION_PROLOG_2_RELON(label, EXC_HV) - -/* This associate vector numbers with bits in paca->irq_happened */ -#define SOFTEN_VALUE_0x500 PACA_IRQ_EE -#define SOFTEN_VALUE_0x900 PACA_IRQ_DEC -#define SOFTEN_VALUE_0x980 PACA_IRQ_DEC -#define SOFTEN_VALUE_0xa00 PACA_IRQ_DBELL -#define SOFTEN_VALUE_0xe80 PACA_IRQ_DBELL -#define SOFTEN_VALUE_0xe60 PACA_IRQ_HMI -#define SOFTEN_VALUE_0xea0 PACA_IRQ_EE -#define SOFTEN_VALUE_0xf00 PACA_IRQ_PMI - -#define __SOFTEN_TEST(h, vec, bitmask) \ - lbz r10,PACAIRQSOFTMASK(r13); \ - andi. r10,r10,bitmask; \ - li r10,SOFTEN_VALUE_##vec; \ - bne masked_##h##interrupt - -#define _SOFTEN_TEST(h, vec, bitmask) __SOFTEN_TEST(h, vec, bitmask) - -#define SOFTEN_TEST_PR(vec, bitmask) \ - KVMTEST(EXC_STD, vec); \ - _SOFTEN_TEST(EXC_STD, vec, bitmask) - -#define SOFTEN_TEST_HV(vec, bitmask) \ - KVMTEST(EXC_HV, vec); \ - _SOFTEN_TEST(EXC_HV, vec, bitmask) - -#define KVMTEST_PR(vec) \ - KVMTEST(EXC_STD, vec) - -#define KVMTEST_HV(vec) \ - KVMTEST(EXC_HV, vec) - -#define SOFTEN_NOTEST_PR(vec, bitmask) _SOFTEN_TEST(EXC_STD, vec, bitmask) -#define SOFTEN_NOTEST_HV(vec, bitmask) _SOFTEN_TEST(EXC_HV, vec, bitmask) - -#define __MASKABLE_EXCEPTION(vec, label, h, extra, bitmask) \ - SET_SCRATCH0(r13); /* save r13 */ \ - EXCEPTION_PROLOG_0(PACA_EXGEN); \ - MASKABLE_EXCEPTION_PROLOG_1(PACA_EXGEN, extra, vec, bitmask); \ - EXCEPTION_PROLOG_2(label, h); - -#define MASKABLE_EXCEPTION(vec, label, bitmask) \ - __MASKABLE_EXCEPTION(vec, label, EXC_STD, SOFTEN_TEST_PR, bitmask) - -#define MASKABLE_EXCEPTION_OOL(vec, label, bitmask) \ - MASKABLE_EXCEPTION_PROLOG_1(PACA_EXGEN, SOFTEN_TEST_PR, vec, bitmask);\ - EXCEPTION_PROLOG_2(label, EXC_STD) - -#define MASKABLE_EXCEPTION_HV(vec, label, bitmask) \ - __MASKABLE_EXCEPTION(vec, label, EXC_HV, SOFTEN_TEST_HV, bitmask) - -#define MASKABLE_EXCEPTION_HV_OOL(vec, label, bitmask) \ - MASKABLE_EXCEPTION_PROLOG_1(PACA_EXGEN, SOFTEN_TEST_HV, vec, bitmask);\ - EXCEPTION_PROLOG_2(label, EXC_HV) - -#define __MASKABLE_RELON_EXCEPTION(vec, label, h, extra, bitmask) \ - SET_SCRATCH0(r13); /* save r13 */ \ - EXCEPTION_PROLOG_0(PACA_EXGEN); \ - MASKABLE_EXCEPTION_PROLOG_1(PACA_EXGEN, extra, vec, bitmask); \ - EXCEPTION_PROLOG_2_RELON(label, h) - -#define MASKABLE_RELON_EXCEPTION(vec, label, bitmask) \ - __MASKABLE_RELON_EXCEPTION(vec, label, EXC_STD, SOFTEN_NOTEST_PR, bitmask) - -#define MASKABLE_RELON_EXCEPTION_OOL(vec, label, bitmask) \ - MASKABLE_EXCEPTION_PROLOG_1(PACA_EXGEN, SOFTEN_NOTEST_PR, vec, bitmask);\ - EXCEPTION_PROLOG_2(label, EXC_STD); - -#define MASKABLE_RELON_EXCEPTION_HV(vec, label, bitmask) \ - __MASKABLE_RELON_EXCEPTION(vec, label, EXC_HV, SOFTEN_TEST_HV, bitmask) - -#define MASKABLE_RELON_EXCEPTION_HV_OOL(vec, label, bitmask) \ - MASKABLE_EXCEPTION_PROLOG_1(PACA_EXGEN, SOFTEN_TEST_HV, vec, bitmask);\ - EXCEPTION_PROLOG_2_RELON(label, EXC_HV) - -/* - * Our exception common code can be passed various "additions" - * to specify the behaviour of interrupts, whether to kick the - * runlatch, etc... - */ - -/* - * This addition reconciles our actual IRQ state with the various software - * flags that track it. This may call C code. - */ -#define ADD_RECONCILE RECONCILE_IRQ_STATE(r10,r11) - -#define ADD_NVGPRS \ - bl save_nvgprs - -#define RUNLATCH_ON \ -BEGIN_FTR_SECTION \ - ld r3, PACA_THREAD_INFO(r13); \ - ld r4,TI_LOCAL_FLAGS(r3); \ - andi. r0,r4,_TLF_RUNLATCH; \ - beql ppc64_runlatch_on_trampoline; \ -END_FTR_SECTION_IFSET(CPU_FTR_CTRL) - -#define EXCEPTION_COMMON(area, trap, label, hdlr, ret, additions) \ - EXCEPTION_PROLOG_COMMON(trap, area); \ - /* Volatile regs are potentially clobbered here */ \ - additions; \ - addi r3,r1,STACK_FRAME_OVERHEAD; \ - bl hdlr; \ - b ret - -/* - * Exception where stack is already set in r1, r1 is saved in r10, and it - * continues rather than returns. - */ -#define EXCEPTION_COMMON_NORET_STACK(area, trap, label, hdlr, additions) \ - EXCEPTION_PROLOG_COMMON_1(); \ - kuap_save_amr_and_lock r9, r10, cr1; \ - EXCEPTION_PROLOG_COMMON_2(area); \ - EXCEPTION_PROLOG_COMMON_3(trap); \ - /* Volatile regs are potentially clobbered here */ \ - additions; \ - addi r3,r1,STACK_FRAME_OVERHEAD; \ - bl hdlr - -#define STD_EXCEPTION_COMMON(trap, label, hdlr) \ - EXCEPTION_COMMON(PACA_EXGEN, trap, label, hdlr, \ - ret_from_except, ADD_NVGPRS;ADD_RECONCILE) - -/* - * Like STD_EXCEPTION_COMMON, but for exceptions that can occur - * in the idle task and therefore need the special idle handling - * (finish nap and runlatch) - */ -#define STD_EXCEPTION_COMMON_ASYNC(trap, label, hdlr) \ - EXCEPTION_COMMON(PACA_EXGEN, trap, label, hdlr, \ - ret_from_except_lite, FINISH_NAP;ADD_RECONCILE;RUNLATCH_ON) - -/* - * When the idle code in power4_idle puts the CPU into NAP mode, - * it has to do so in a loop, and relies on the external interrupt - * and decrementer interrupt entry code to get it out of the loop. - * It sets the _TLF_NAPPING bit in current_thread_info()->local_flags - * to signal that it is in the loop and needs help to get out. - */ -#ifdef CONFIG_PPC_970_NAP -#define FINISH_NAP \ -BEGIN_FTR_SECTION \ - ld r11, PACA_THREAD_INFO(r13); \ - ld r9,TI_LOCAL_FLAGS(r11); \ - andi. r10,r9,_TLF_NAPPING; \ - bnel power4_fixup_nap; \ -END_FTR_SECTION_IFSET(CPU_FTR_CAN_NAP) -#else -#define FINISH_NAP -#endif +#endif /* __ASSEMBLY__ */ #endif /* _ASM_POWERPC_EXCEPTION_H */ diff --git a/arch/powerpc/include/asm/head-64.h b/arch/powerpc/include/asm/head-64.h index a4f947888744..a466765709a9 100644 --- a/arch/powerpc/include/asm/head-64.h +++ b/arch/powerpc/include/asm/head-64.h @@ -169,53 +169,6 @@ name: #define ABS_ADDR(label) (label - fs_label + fs_start) -/* - * Following are the BOOK3S exception handler helper macros. - * Handlers come in a number of types, and each type has a number of varieties. - * - * EXC_REAL_* - real, unrelocated exception vectors - * EXC_VIRT_* - virt (AIL), unrelocated exception vectors - * TRAMP_REAL_* - real, unrelocated helpers (virt can call these) - * TRAMP_VIRT_* - virt, unreloc helpers (in practice, real can use) - * TRAMP_KVM - KVM handlers that get put into real, unrelocated - * EXC_COMMON - virt, relocated common handlers - * - * The EXC handlers are given a name, and branch to name_common, or the - * appropriate KVM or masking function. Vector handler verieties are as - * follows: - * - * EXC_{REAL|VIRT}_BEGIN/END - used to open-code the exception - * - * EXC_{REAL|VIRT} - standard exception - * - * EXC_{REAL|VIRT}_suffix - * where _suffix is: - * - _MASKABLE - maskable exception - * - _OOL - out of line with trampoline to common handler - * - _HV - HV exception - * - * There can be combinations, e.g., EXC_VIRT_OOL_MASKABLE_HV - * - * The one unusual case is __EXC_REAL_OOL_HV_DIRECT, which is - * an OOL vector that branches to a specified handler rather than the usual - * trampoline that goes to common. It, and other underscore macros, should - * be used with care. - * - * KVM handlers come in the following verieties: - * TRAMP_KVM - * TRAMP_KVM_SKIP - * TRAMP_KVM_HV - * TRAMP_KVM_HV_SKIP - * - * COMMON handlers come in the following verieties: - * EXC_COMMON_BEGIN/END - used to open-code the handler - * EXC_COMMON - * EXC_COMMON_ASYNC - * - * TRAMP_REAL and TRAMP_VIRT can be used with BEGIN/END. KVM - * and OOL handlers are implemented as types of TRAMP and TRAMP_VIRT handlers. - */ - #define EXC_REAL_BEGIN(name, start, size) \ FIXED_SECTION_ENTRY_BEGIN_LOCATION(real_vectors, exc_real_##start##_##name, start, size) @@ -255,162 +208,7 @@ name: #define EXC_VIRT_NONE(start, size) \ FIXED_SECTION_ENTRY_BEGIN_LOCATION(virt_vectors, exc_virt_##start##_##unused, start, size); \ - FIXED_SECTION_ENTRY_END_LOCATION(virt_vectors, exc_virt_##start##_##unused, start, size); - - -#define EXC_REAL(name, start, size) \ - EXC_REAL_BEGIN(name, start, size); \ - STD_EXCEPTION(start, name##_common); \ - EXC_REAL_END(name, start, size); - -#define EXC_VIRT(name, start, size, realvec) \ - EXC_VIRT_BEGIN(name, start, size); \ - STD_RELON_EXCEPTION(start, realvec, name##_common); \ - EXC_VIRT_END(name, start, size); - -#define EXC_REAL_MASKABLE(name, start, size, bitmask) \ - EXC_REAL_BEGIN(name, start, size); \ - MASKABLE_EXCEPTION(start, name##_common, bitmask); \ - EXC_REAL_END(name, start, size); - -#define EXC_VIRT_MASKABLE(name, start, size, realvec, bitmask) \ - EXC_VIRT_BEGIN(name, start, size); \ - MASKABLE_RELON_EXCEPTION(realvec, name##_common, bitmask); \ - EXC_VIRT_END(name, start, size); - -#define EXC_REAL_HV(name, start, size) \ - EXC_REAL_BEGIN(name, start, size); \ - STD_EXCEPTION_HV(start, start, name##_common); \ - EXC_REAL_END(name, start, size); - -#define EXC_VIRT_HV(name, start, size, realvec) \ - EXC_VIRT_BEGIN(name, start, size); \ - STD_RELON_EXCEPTION_HV(start, realvec, name##_common); \ - EXC_VIRT_END(name, start, size); - -#define __EXC_REAL_OOL(name, start, size) \ - EXC_REAL_BEGIN(name, start, size); \ - __OOL_EXCEPTION(start, label, tramp_real_##name); \ - EXC_REAL_END(name, start, size); - -#define __TRAMP_REAL_OOL(name, vec) \ - TRAMP_REAL_BEGIN(tramp_real_##name); \ - STD_EXCEPTION_OOL(vec, name##_common); - -#define EXC_REAL_OOL(name, start, size) \ - __EXC_REAL_OOL(name, start, size); \ - __TRAMP_REAL_OOL(name, start); - -#define __EXC_REAL_OOL_MASKABLE(name, start, size) \ - __EXC_REAL_OOL(name, start, size); - -#define __TRAMP_REAL_OOL_MASKABLE(name, vec, bitmask) \ - TRAMP_REAL_BEGIN(tramp_real_##name); \ - MASKABLE_EXCEPTION_OOL(vec, name##_common, bitmask); - -#define EXC_REAL_OOL_MASKABLE(name, start, size, bitmask) \ - __EXC_REAL_OOL_MASKABLE(name, start, size); \ - __TRAMP_REAL_OOL_MASKABLE(name, start, bitmask); - -#define __EXC_REAL_OOL_HV_DIRECT(name, start, size, handler) \ - EXC_REAL_BEGIN(name, start, size); \ - __OOL_EXCEPTION(start, label, handler); \ - EXC_REAL_END(name, start, size); - -#define __EXC_REAL_OOL_HV(name, start, size) \ - __EXC_REAL_OOL(name, start, size); - -#define __TRAMP_REAL_OOL_HV(name, vec) \ - TRAMP_REAL_BEGIN(tramp_real_##name); \ - STD_EXCEPTION_HV_OOL(vec, name##_common); \ - -#define EXC_REAL_OOL_HV(name, start, size) \ - __EXC_REAL_OOL_HV(name, start, size); \ - __TRAMP_REAL_OOL_HV(name, start); - -#define __EXC_REAL_OOL_MASKABLE_HV(name, start, size) \ - __EXC_REAL_OOL(name, start, size); - -#define __TRAMP_REAL_OOL_MASKABLE_HV(name, vec, bitmask) \ - TRAMP_REAL_BEGIN(tramp_real_##name); \ - MASKABLE_EXCEPTION_HV_OOL(vec, name##_common, bitmask); \ - -#define EXC_REAL_OOL_MASKABLE_HV(name, start, size, bitmask) \ - __EXC_REAL_OOL_MASKABLE_HV(name, start, size); \ - __TRAMP_REAL_OOL_MASKABLE_HV(name, start, bitmask); - -#define __EXC_VIRT_OOL(name, start, size) \ - EXC_VIRT_BEGIN(name, start, size); \ - __OOL_EXCEPTION(start, label, tramp_virt_##name); \ - EXC_VIRT_END(name, start, size); - -#define __TRAMP_VIRT_OOL(name, realvec) \ - TRAMP_VIRT_BEGIN(tramp_virt_##name); \ - STD_RELON_EXCEPTION_OOL(realvec, name##_common); - -#define EXC_VIRT_OOL(name, start, size, realvec) \ - __EXC_VIRT_OOL(name, start, size); \ - __TRAMP_VIRT_OOL(name, realvec); - -#define __EXC_VIRT_OOL_MASKABLE(name, start, size) \ - __EXC_VIRT_OOL(name, start, size); - -#define __TRAMP_VIRT_OOL_MASKABLE(name, realvec, bitmask) \ - TRAMP_VIRT_BEGIN(tramp_virt_##name); \ - MASKABLE_RELON_EXCEPTION_OOL(realvec, name##_common, bitmask); - -#define EXC_VIRT_OOL_MASKABLE(name, start, size, realvec, bitmask) \ - __EXC_VIRT_OOL_MASKABLE(name, start, size); \ - __TRAMP_VIRT_OOL_MASKABLE(name, realvec, bitmask); - -#define __EXC_VIRT_OOL_HV(name, start, size) \ - __EXC_VIRT_OOL(name, start, size); - -#define __TRAMP_VIRT_OOL_HV(name, realvec) \ - TRAMP_VIRT_BEGIN(tramp_virt_##name); \ - STD_RELON_EXCEPTION_HV_OOL(realvec, name##_common); \ - -#define EXC_VIRT_OOL_HV(name, start, size, realvec) \ - __EXC_VIRT_OOL_HV(name, start, size); \ - __TRAMP_VIRT_OOL_HV(name, realvec); - -#define __EXC_VIRT_OOL_MASKABLE_HV(name, start, size) \ - __EXC_VIRT_OOL(name, start, size); - -#define __TRAMP_VIRT_OOL_MASKABLE_HV(name, realvec, bitmask) \ - TRAMP_VIRT_BEGIN(tramp_virt_##name); \ - MASKABLE_RELON_EXCEPTION_HV_OOL(realvec, name##_common, bitmask);\ - -#define EXC_VIRT_OOL_MASKABLE_HV(name, start, size, realvec, bitmask) \ - __EXC_VIRT_OOL_MASKABLE_HV(name, start, size); \ - __TRAMP_VIRT_OOL_MASKABLE_HV(name, realvec, bitmask); - -#define TRAMP_KVM(area, n) \ - TRAMP_KVM_BEGIN(do_kvm_##n); \ - KVM_HANDLER(area, EXC_STD, n); \ - -#define TRAMP_KVM_SKIP(area, n) \ - TRAMP_KVM_BEGIN(do_kvm_##n); \ - KVM_HANDLER_SKIP(area, EXC_STD, n); \ - -/* - * HV variant exceptions get the 0x2 bit added to their trap number. - */ -#define TRAMP_KVM_HV(area, n) \ - TRAMP_KVM_BEGIN(do_kvm_H##n); \ - KVM_HANDLER(area, EXC_HV, n + 0x2); \ - -#define TRAMP_KVM_HV_SKIP(area, n) \ - TRAMP_KVM_BEGIN(do_kvm_H##n); \ - KVM_HANDLER_SKIP(area, EXC_HV, n + 0x2); \ - -#define EXC_COMMON(name, realvec, hdlr) \ - EXC_COMMON_BEGIN(name); \ - STD_EXCEPTION_COMMON(realvec, name, hdlr); \ - -#define EXC_COMMON_ASYNC(name, realvec, hdlr) \ - EXC_COMMON_BEGIN(name); \ - STD_EXCEPTION_COMMON_ASYNC(realvec, name, hdlr); \ + FIXED_SECTION_ENTRY_END_LOCATION(virt_vectors, exc_virt_##start##_##unused, start, size) #endif /* __ASSEMBLY__ */ diff --git a/arch/powerpc/include/asm/hw_breakpoint.h b/arch/powerpc/include/asm/hw_breakpoint.h index 78202d5fb13a..67e2da195eae 100644 --- a/arch/powerpc/include/asm/hw_breakpoint.h +++ b/arch/powerpc/include/asm/hw_breakpoint.h @@ -76,18 +76,25 @@ static inline void hw_breakpoint_disable(void) extern void thread_change_pc(struct task_struct *tsk, struct pt_regs *regs); int hw_breakpoint_handler(struct die_args *args); -extern int set_dawr(struct arch_hw_breakpoint *brk); +#else /* CONFIG_HAVE_HW_BREAKPOINT */ +static inline void hw_breakpoint_disable(void) { } +static inline void thread_change_pc(struct task_struct *tsk, + struct pt_regs *regs) { } + +#endif /* CONFIG_HAVE_HW_BREAKPOINT */ + + +#ifdef CONFIG_PPC_DAWR extern bool dawr_force_enable; static inline bool dawr_enabled(void) { return dawr_force_enable; } - -#else /* CONFIG_HAVE_HW_BREAKPOINT */ -static inline void hw_breakpoint_disable(void) { } -static inline void thread_change_pc(struct task_struct *tsk, - struct pt_regs *regs) { } +int set_dawr(struct arch_hw_breakpoint *brk); +#else static inline bool dawr_enabled(void) { return false; } -#endif /* CONFIG_HAVE_HW_BREAKPOINT */ +static inline int set_dawr(struct arch_hw_breakpoint *brk) { return -1; } +#endif + #endif /* __KERNEL__ */ #endif /* _PPC_BOOK3S_64_HW_BREAKPOINT_H */ diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h index 2c1845e5e851..18d342b815e4 100644 --- a/arch/powerpc/include/asm/iommu.h +++ b/arch/powerpc/include/asm/iommu.h @@ -314,13 +314,5 @@ extern bool iommu_fixed_is_weak; extern const struct dma_map_ops dma_iommu_ops; -static inline unsigned long device_to_mask(struct device *dev) -{ - if (dev->dma_mask && *dev->dma_mask) - return *dev->dma_mask; - /* Assume devices without mask can take 32 bit addresses */ - return 0xfffffffful; -} - #endif /* __KERNEL__ */ #endif /* _ASM_IOMMU_H */ diff --git a/arch/powerpc/include/asm/lppaca.h b/arch/powerpc/include/asm/lppaca.h index 806494283e2a..3b4b305796ae 100644 --- a/arch/powerpc/include/asm/lppaca.h +++ b/arch/powerpc/include/asm/lppaca.h @@ -5,6 +5,29 @@ */ #ifndef _ASM_POWERPC_LPPACA_H #define _ASM_POWERPC_LPPACA_H + +/* + * The below VPHN macros are outside the __KERNEL__ check since these are + * used for compiling the vphn selftest in userspace + */ + +/* The H_HOME_NODE_ASSOCIATIVITY h_call returns 6 64-bit registers. */ +#define VPHN_REGISTER_COUNT 6 + +/* + * 6 64-bit registers unpacked into up to 24 be32 associativity values. To + * form the complete property we have to add the length in the first cell. + */ +#define VPHN_ASSOC_BUFSIZE (VPHN_REGISTER_COUNT*sizeof(u64)/sizeof(u16) + 1) + +/* + * The H_HOME_NODE_ASSOCIATIVITY hcall takes two values for flags: + * 1 for retrieving associativity information for a guest cpu + * 2 for retrieving associativity information for a host/hypervisor cpu + */ +#define VPHN_FLAG_VCPU 1 +#define VPHN_FLAG_PCPU 2 + #ifdef __KERNEL__ /* @@ -19,6 +42,7 @@ */ #include <linux/cache.h> #include <linux/threads.h> +#include <linux/spinlock_types.h> #include <asm/types.h> #include <asm/mmu.h> #include <asm/firmware.h> @@ -141,7 +165,19 @@ struct dtl_entry { #define DISPATCH_LOG_BYTES 4096 /* bytes per cpu */ #define N_DISPATCH_LOG (DISPATCH_LOG_BYTES / sizeof(struct dtl_entry)) +/* + * Dispatch trace log event enable mask: + * 0x1: voluntary virtual processor waits + * 0x2: time-slice preempts + * 0x4: virtual partition memory page faults + */ +#define DTL_LOG_CEDE 0x1 +#define DTL_LOG_PREEMPT 0x2 +#define DTL_LOG_FAULT 0x4 +#define DTL_LOG_ALL (DTL_LOG_CEDE | DTL_LOG_PREEMPT | DTL_LOG_FAULT) + extern struct kmem_cache *dtl_cache; +extern rwlock_t dtl_access_lock; /* * When CONFIG_VIRT_CPU_ACCOUNTING_NATIVE = y, the cpu accounting code controls @@ -151,6 +187,10 @@ extern struct kmem_cache *dtl_cache; */ extern void (*dtl_consumer)(struct dtl_entry *entry, u64 index); +extern void register_dtl_buffer(int cpu); +extern void alloc_dtl_buffers(unsigned long *time_limit); +extern long hcall_vphn(unsigned long cpu, u64 flags, __be32 *associativity); + #endif /* CONFIG_PPC_BOOK3S */ #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_LPPACA_H */ diff --git a/arch/powerpc/include/asm/opal-api.h b/arch/powerpc/include/asm/opal-api.h index 09a8553833d1..383242eb0dea 100644 --- a/arch/powerpc/include/asm/opal-api.h +++ b/arch/powerpc/include/asm/opal-api.h @@ -564,6 +564,7 @@ enum OpalHMI_XstopType { CHECKSTOP_TYPE_UNKNOWN = 0, CHECKSTOP_TYPE_CORE = 1, CHECKSTOP_TYPE_NX = 2, + CHECKSTOP_TYPE_NPU = 3 }; enum OpalHMI_CoreXstopReason { diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h index 4ed5d57f2359..57bd029c715e 100644 --- a/arch/powerpc/include/asm/opal.h +++ b/arch/powerpc/include/asm/opal.h @@ -283,8 +283,6 @@ int64_t opal_xive_set_queue_state(uint64_t vp, uint32_t prio, uint32_t qtoggle, uint32_t qindex); int64_t opal_xive_get_vp_state(uint64_t vp, __be64 *out_w01); -int64_t opal_pci_set_p2p(uint64_t phb_init, uint64_t phb_target, - uint64_t desc, uint16_t pe_number); int64_t opal_imc_counters_init(uint32_t type, uint64_t address, uint64_t cpu_pir); diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h index 9bd2326bef6f..e3cc9eb9204d 100644 --- a/arch/powerpc/include/asm/paca.h +++ b/arch/powerpc/include/asm/paca.h @@ -166,7 +166,9 @@ struct paca_struct { u64 kstack; /* Saved Kernel stack addr */ u64 saved_r1; /* r1 save for RTAS calls or PM or EE=0 */ u64 saved_msr; /* MSR saved here by enter_rtas */ +#ifdef CONFIG_PPC_BOOK3E u16 trap_save; /* Used when bad stack is encountered */ +#endif u8 irq_soft_mask; /* mask for irq soft masking */ u8 irq_happened; /* irq happened while soft-disabled */ u8 irq_work_pending; /* IRQ_WORK interrupt while soft-disable */ diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h index 3f53be60fb01..c58ba7963688 100644 --- a/arch/powerpc/include/asm/pgtable.h +++ b/arch/powerpc/include/asm/pgtable.h @@ -140,6 +140,44 @@ static inline void pte_frag_set(mm_context_t *ctx, void *p) } #endif +#ifndef pmd_is_leaf +#define pmd_is_leaf pmd_is_leaf +static inline bool pmd_is_leaf(pmd_t pmd) +{ + return false; +} +#endif + +#ifndef pud_is_leaf +#define pud_is_leaf pud_is_leaf +static inline bool pud_is_leaf(pud_t pud) +{ + return false; +} +#endif + +#ifndef pgd_is_leaf +#define pgd_is_leaf pgd_is_leaf +static inline bool pgd_is_leaf(pgd_t pgd) +{ + return false; +} +#endif + +#ifdef CONFIG_PPC64 +#define is_ioremap_addr is_ioremap_addr +static inline bool is_ioremap_addr(const void *x) +{ +#ifdef CONFIG_MMU + unsigned long addr = (unsigned long)x; + + return addr >= IOREMAP_BASE && addr < IOREMAP_END; +#else + return false; +#endif +} +#endif /* CONFIG_PPC64 */ + #endif /* __ASSEMBLY__ */ #endif /* _ASM_POWERPC_PGTABLE_H */ diff --git a/arch/powerpc/include/asm/pnv-ocxl.h b/arch/powerpc/include/asm/pnv-ocxl.h index 208b5503f4ed..7de82647e761 100644 --- a/arch/powerpc/include/asm/pnv-ocxl.h +++ b/arch/powerpc/include/asm/pnv-ocxl.h @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0+ +/* SPDX-License-Identifier: GPL-2.0+ */ // Copyright 2017 IBM Corp. #ifndef _ASM_PNV_OCXL_H #define _ASM_PNV_OCXL_H diff --git a/arch/powerpc/include/asm/pnv-pci.h b/arch/powerpc/include/asm/pnv-pci.h index b5a85f1bb305..edcb1fc50aeb 100644 --- a/arch/powerpc/include/asm/pnv-pci.h +++ b/arch/powerpc/include/asm/pnv-pci.h @@ -22,15 +22,9 @@ extern int pnv_pci_get_presence_state(uint64_t id, uint8_t *state); extern int pnv_pci_get_power_state(uint64_t id, uint8_t *state); extern int pnv_pci_set_power_state(uint64_t id, uint8_t state, struct opal_msg *msg); -extern int pnv_pci_set_p2p(struct pci_dev *initiator, struct pci_dev *target, - u64 desc); -extern int pnv_pci_enable_tunnel(struct pci_dev *dev, uint64_t *asnind); -extern int pnv_pci_disable_tunnel(struct pci_dev *dev); extern int pnv_pci_set_tunnel_bar(struct pci_dev *dev, uint64_t addr, int enable); -extern int pnv_pci_get_as_notify_info(struct task_struct *task, u32 *lpid, - u32 *pid, u32 *tid); int pnv_phb_to_cxl_mode(struct pci_dev *dev, uint64_t mode); int pnv_cxl_ioda_msi_setup(struct pci_dev *dev, unsigned int hwirq, unsigned int virq); diff --git a/arch/powerpc/include/asm/powernv.h b/arch/powerpc/include/asm/powernv.h index bc69ed2d952c..e1a858718716 100644 --- a/arch/powerpc/include/asm/powernv.h +++ b/arch/powerpc/include/asm/powernv.h @@ -7,35 +7,13 @@ #define _ASM_POWERNV_H #ifdef CONFIG_PPC_POWERNV -#define NPU2_WRITE 1 extern void powernv_set_nmmu_ptcr(unsigned long ptcr); -extern struct npu_context *pnv_npu2_init_context(struct pci_dev *gpdev, - unsigned long flags, - void (*cb)(struct npu_context *, void *), - void *priv); -extern void pnv_npu2_destroy_context(struct npu_context *context, - struct pci_dev *gpdev); -extern int pnv_npu2_handle_fault(struct npu_context *context, uintptr_t *ea, - unsigned long *flags, unsigned long *status, - int count); void pnv_program_cpu_hotplug_lpcr(unsigned int cpu, u64 lpcr_val); void pnv_tm_init(void); #else static inline void powernv_set_nmmu_ptcr(unsigned long ptcr) { } -static inline struct npu_context *pnv_npu2_init_context(struct pci_dev *gpdev, - unsigned long flags, - struct npu_context *(*cb)(struct npu_context *, void *), - void *priv) { return ERR_PTR(-ENODEV); } -static inline void pnv_npu2_destroy_context(struct npu_context *context, - struct pci_dev *gpdev) { } - -static inline int pnv_npu2_handle_fault(struct npu_context *context, - uintptr_t *ea, unsigned long *flags, - unsigned long *status, int count) { - return -ENODEV; -} static inline void pnv_tm_init(void) { } #endif diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h index 2291daf39cd1..c1df75edde44 100644 --- a/arch/powerpc/include/asm/ppc-opcode.h +++ b/arch/powerpc/include/asm/ppc-opcode.h @@ -410,6 +410,15 @@ #define __PPC_RC21 (0x1 << 10) /* + * Both low and high 16 bits are added as SIGNED additions, so if low 16 bits + * has high bit set, high 16 bits must be adjusted. These macros do that (stolen + * from binutils). + */ +#define PPC_LO(v) ((v) & 0xffff) +#define PPC_HI(v) (((v) >> 16) & 0xffff) +#define PPC_HA(v) PPC_HI((v) + 0x8000) + +/* * Only use the larx hint bit on 64bit CPUs. e500v1/v2 based CPUs will treat a * larx with EH set as an illegal instruction. */ @@ -588,7 +597,16 @@ #define PPC_SLBIA(IH) stringify_in_c(.long PPC_INST_SLBIA | \ ((IH & 0x7) << 21)) -#define PPC_INVALIDATE_ERAT PPC_SLBIA(7) + +/* + * These may only be used on ISA v3.0 or later (aka. CPU_FTR_ARCH_300, radix + * implies CPU_FTR_ARCH_300). USER/GUEST invalidates may only be used by radix + * mode (on HPT these would also invalidate various SLBEs which may not be + * desired). + */ +#define PPC_ISA_3_0_INVALIDATE_ERAT PPC_SLBIA(7) +#define PPC_RADIX_INVALIDATE_ERAT_USER PPC_SLBIA(3) +#define PPC_RADIX_INVALIDATE_ERAT_GUEST PPC_SLBIA(6) #define VCMPEQUD_RC(vrt, vra, vrb) stringify_in_c(.long PPC_INST_VCMPEQUD | \ ___PPC_RT(vrt) | ___PPC_RA(vra) | \ diff --git a/arch/powerpc/include/asm/ps3stor.h b/arch/powerpc/include/asm/ps3stor.h index d9f6589bc107..1d8279014f22 100644 --- a/arch/powerpc/include/asm/ps3stor.h +++ b/arch/powerpc/include/asm/ps3stor.h @@ -39,7 +39,7 @@ struct ps3_storage_device { unsigned int num_regions; unsigned long accessible_regions; unsigned int region_idx; /* first accessible region */ - struct ps3_storage_region regions[0]; /* Must be last */ + struct ps3_storage_region regions[]; /* Must be last */ }; static inline struct ps3_storage_device *to_ps3_storage_device(struct device *dev) diff --git a/arch/powerpc/include/asm/pte-walk.h b/arch/powerpc/include/asm/pte-walk.h index 2d633e9d686c..33fa5dd8ee6a 100644 --- a/arch/powerpc/include/asm/pte-walk.h +++ b/arch/powerpc/include/asm/pte-walk.h @@ -10,8 +10,20 @@ extern pte_t *__find_linux_pte(pgd_t *pgdir, unsigned long ea, static inline pte_t *find_linux_pte(pgd_t *pgdir, unsigned long ea, bool *is_thp, unsigned *hshift) { + pte_t *pte; + VM_WARN(!arch_irqs_disabled(), "%s called with irq enabled\n", __func__); - return __find_linux_pte(pgdir, ea, is_thp, hshift); + pte = __find_linux_pte(pgdir, ea, is_thp, hshift); + +#if defined(CONFIG_DEBUG_VM) && \ + !(defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)) + /* + * We should not find huge page if these configs are not enabled. + */ + if (hshift) + WARN_ON(*hshift); +#endif + return pte; } static inline pte_t *find_init_mm_pte(unsigned long ea, unsigned *hshift) @@ -26,10 +38,22 @@ static inline pte_t *find_init_mm_pte(unsigned long ea, unsigned *hshift) static inline pte_t *find_current_mm_pte(pgd_t *pgdir, unsigned long ea, bool *is_thp, unsigned *hshift) { + pte_t *pte; + VM_WARN(!arch_irqs_disabled(), "%s called with irq enabled\n", __func__); VM_WARN(pgdir != current->mm->pgd, "%s lock less page table lookup called on wrong mm\n", __func__); - return __find_linux_pte(pgdir, ea, is_thp, hshift); + pte = __find_linux_pte(pgdir, ea, is_thp, hshift); + +#if defined(CONFIG_DEBUG_VM) && \ + !(defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)) + /* + * We should not find huge page if these configs are not enabled. + */ + if (hshift) + WARN_ON(*hshift); +#endif + return pte; } #endif /* _ASM_POWERPC_PTE_WALK_H */ diff --git a/arch/powerpc/include/asm/ptrace.h b/arch/powerpc/include/asm/ptrace.h index faa5a338ac5a..feee1b21bbd5 100644 --- a/arch/powerpc/include/asm/ptrace.h +++ b/arch/powerpc/include/asm/ptrace.h @@ -111,18 +111,33 @@ struct pt_regs #ifndef __ASSEMBLY__ -#define GET_IP(regs) ((regs)->nip) -#define GET_USP(regs) ((regs)->gpr[1]) -#define GET_FP(regs) (0) -#define SET_FP(regs, val) +static inline unsigned long instruction_pointer(struct pt_regs *regs) +{ + return regs->nip; +} + +static inline void instruction_pointer_set(struct pt_regs *regs, + unsigned long val) +{ + regs->nip = val; +} + +static inline unsigned long user_stack_pointer(struct pt_regs *regs) +{ + return regs->gpr[1]; +} + +static inline unsigned long frame_pointer(struct pt_regs *regs) +{ + return 0; +} #ifdef CONFIG_SMP extern unsigned long profile_pc(struct pt_regs *regs); -#define profile_pc profile_pc +#else +#define profile_pc(regs) instruction_pointer(regs) #endif -#include <asm-generic/ptrace.h> - #define kernel_stack_pointer(regs) ((regs)->gpr[1]) static inline int is_syscall_success(struct pt_regs *regs) { diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h index f85e2b01c3df..2f7e1ea5089e 100644 --- a/arch/powerpc/include/asm/topology.h +++ b/arch/powerpc/include/asm/topology.h @@ -35,6 +35,7 @@ static inline int pcibus_to_node(struct pci_bus *bus) cpu_all_mask : \ cpumask_of_node(pcibus_to_node(bus))) +extern int cpu_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc); extern int __node_distance(int, int); #define node_distance(a, b) __node_distance(a, b) @@ -84,6 +85,11 @@ static inline int numa_update_cpu_topology(bool cpus_locked) static inline void update_numa_cpu_lookup_table(unsigned int cpu, int node) {} +static inline int cpu_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc) +{ + return 0; +} + #endif /* CONFIG_NUMA */ #if defined(CONFIG_NUMA) && defined(CONFIG_PPC_SPLPAR) diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h index 76f34346b642..8b03eb44e876 100644 --- a/arch/powerpc/include/asm/uaccess.h +++ b/arch/powerpc/include/asm/uaccess.h @@ -312,6 +312,7 @@ raw_copy_in_user(void __user *to, const void __user *from, unsigned long n) { unsigned long ret; + barrier_nospec(); allow_user_access(to, from, n); ret = __copy_tofrom_user(to, from, n); prevent_user_access(to, from, n); diff --git a/arch/powerpc/include/asm/vas.h b/arch/powerpc/include/asm/vas.h index da0b19870570..f93e6b0f5c84 100644 --- a/arch/powerpc/include/asm/vas.h +++ b/arch/powerpc/include/asm/vas.h @@ -163,14 +163,4 @@ int vas_copy_crb(void *crb, int offset); */ int vas_paste_crb(struct vas_window *win, int offset, bool re); -/* - * Return a system-wide unique id for the VAS window @win. - */ -extern u32 vas_win_id(struct vas_window *win); - -/* - * Return the power bus paste address associated with @win so the caller - * can map that address into their address space. - */ -extern u64 vas_win_paste_addr(struct vas_window *win); #endif /* __ASM_POWERPC_VAS_H */ diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index 0ea6c4aa3a20..56dfa7a2a6f2 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -56,6 +56,7 @@ obj-$(CONFIG_PPC64) += setup_64.o sys_ppc32.o \ obj-$(CONFIG_VDSO32) += vdso32/ obj-$(CONFIG_PPC_WATCHDOG) += watchdog.o obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o +obj-$(CONFIG_PPC_DAWR) += dawr.o obj-$(CONFIG_PPC_BOOK3S_64) += cpu_setup_ppc970.o cpu_setup_pa6t.o obj-$(CONFIG_PPC_BOOK3S_64) += cpu_setup_power.o obj-$(CONFIG_PPC_BOOK3S_64) += mce.o mce_power.o diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 31dc7e64cbfc..4ccb6b3a7fbd 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -266,7 +266,9 @@ int main(void) OFFSET(ACCOUNT_STARTTIME_USER, paca_struct, accounting.starttime_user); OFFSET(ACCOUNT_USER_TIME, paca_struct, accounting.utime); OFFSET(ACCOUNT_SYSTEM_TIME, paca_struct, accounting.stime); +#ifdef CONFIG_PPC_BOOK3E OFFSET(PACA_TRAP_SAVE, paca_struct, trap_save); +#endif OFFSET(PACA_SPRG_VDSO, paca_struct, sprg_vdso); #else /* CONFIG_PPC64 */ #ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE diff --git a/arch/powerpc/kernel/cacheinfo.c b/arch/powerpc/kernel/cacheinfo.c index 9fbb9d12e0c0..470336277c67 100644 --- a/arch/powerpc/kernel/cacheinfo.c +++ b/arch/powerpc/kernel/cacheinfo.c @@ -891,4 +891,25 @@ void cacheinfo_cpu_offline(unsigned int cpu_id) if (cache) cache_cpu_clear(cache, cpu_id); } + +void cacheinfo_teardown(void) +{ + unsigned int cpu; + + lockdep_assert_cpus_held(); + + for_each_online_cpu(cpu) + cacheinfo_cpu_offline(cpu); +} + +void cacheinfo_rebuild(void) +{ + unsigned int cpu; + + lockdep_assert_cpus_held(); + + for_each_online_cpu(cpu) + cacheinfo_cpu_online(cpu); +} + #endif /* (CONFIG_PPC_PSERIES && CONFIG_SUSPEND) || CONFIG_HOTPLUG_CPU */ diff --git a/arch/powerpc/kernel/cacheinfo.h b/arch/powerpc/kernel/cacheinfo.h index 955f5e999f1b..52bd3fc6642d 100644 --- a/arch/powerpc/kernel/cacheinfo.h +++ b/arch/powerpc/kernel/cacheinfo.h @@ -6,4 +6,8 @@ extern void cacheinfo_cpu_online(unsigned int cpu_id); extern void cacheinfo_cpu_offline(unsigned int cpu_id); +/* Allow migration/suspend to tear down and rebuild the hierarchy. */ +extern void cacheinfo_teardown(void); +extern void cacheinfo_rebuild(void); + #endif /* _PPC_CACHEINFO_H */ diff --git a/arch/powerpc/kernel/dawr.c b/arch/powerpc/kernel/dawr.c new file mode 100644 index 000000000000..5f66b95b6858 --- /dev/null +++ b/arch/powerpc/kernel/dawr.c @@ -0,0 +1,101 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * DAWR infrastructure + * + * Copyright 2019, Michael Neuling, IBM Corporation. + */ + +#include <linux/types.h> +#include <linux/export.h> +#include <linux/fs.h> +#include <linux/debugfs.h> +#include <asm/debugfs.h> +#include <asm/machdep.h> +#include <asm/hvcall.h> + +bool dawr_force_enable; +EXPORT_SYMBOL_GPL(dawr_force_enable); + +int set_dawr(struct arch_hw_breakpoint *brk) +{ + unsigned long dawr, dawrx, mrd; + + dawr = brk->address; + + dawrx = (brk->type & (HW_BRK_TYPE_READ | HW_BRK_TYPE_WRITE)) + << (63 - 58); + dawrx |= ((brk->type & (HW_BRK_TYPE_TRANSLATE)) >> 2) << (63 - 59); + dawrx |= (brk->type & (HW_BRK_TYPE_PRIV_ALL)) >> 3; + /* + * DAWR length is stored in field MDR bits 48:53. Matches range in + * doublewords (64 bits) baised by -1 eg. 0b000000=1DW and + * 0b111111=64DW. + * brk->len is in bytes. + * This aligns up to double word size, shifts and does the bias. + */ + mrd = ((brk->len + 7) >> 3) - 1; + dawrx |= (mrd & 0x3f) << (63 - 53); + + if (ppc_md.set_dawr) + return ppc_md.set_dawr(dawr, dawrx); + + mtspr(SPRN_DAWR, dawr); + mtspr(SPRN_DAWRX, dawrx); + + return 0; +} + +static void set_dawr_cb(void *info) +{ + set_dawr(info); +} + +static ssize_t dawr_write_file_bool(struct file *file, + const char __user *user_buf, + size_t count, loff_t *ppos) +{ + struct arch_hw_breakpoint null_brk = {0, 0, 0}; + size_t rc; + + /* Send error to user if they hypervisor won't allow us to write DAWR */ + if (!dawr_force_enable && + firmware_has_feature(FW_FEATURE_LPAR) && + set_dawr(&null_brk) != H_SUCCESS) + return -ENODEV; + + rc = debugfs_write_file_bool(file, user_buf, count, ppos); + if (rc) + return rc; + + /* If we are clearing, make sure all CPUs have the DAWR cleared */ + if (!dawr_force_enable) + smp_call_function(set_dawr_cb, &null_brk, 0); + + return rc; +} + +static const struct file_operations dawr_enable_fops = { + .read = debugfs_read_file_bool, + .write = dawr_write_file_bool, + .open = simple_open, + .llseek = default_llseek, +}; + +static int __init dawr_force_setup(void) +{ + if (cpu_has_feature(CPU_FTR_DAWR)) { + /* Don't setup sysfs file for user control on P8 */ + dawr_force_enable = true; + return 0; + } + + if (PVR_VER(mfspr(SPRN_PVR)) == PVR_POWER9) { + /* Turn DAWR off by default, but allow admin to turn it on */ + debugfs_create_file_unsafe("dawr_enable_dangerous", 0600, + powerpc_debugfs_root, + &dawr_force_enable, + &dawr_enable_fops); + } + return 0; +} +arch_initcall(dawr_force_setup); diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c index 09231ef06d01..a0879674a9c8 100644 --- a/arch/powerpc/kernel/dma-iommu.c +++ b/arch/powerpc/kernel/dma-iommu.c @@ -71,7 +71,7 @@ static dma_addr_t dma_iommu_map_page(struct device *dev, struct page *page, return dma_direct_map_page(dev, page, offset, size, direction, attrs); return iommu_map_page(dev, get_iommu_table_base(dev), page, offset, - size, device_to_mask(dev), direction, attrs); + size, dma_get_mask(dev), direction, attrs); } @@ -82,6 +82,8 @@ static void dma_iommu_unmap_page(struct device *dev, dma_addr_t dma_handle, if (!dma_iommu_map_bypass(dev, attrs)) iommu_unmap_page(get_iommu_table_base(dev), dma_handle, size, direction, attrs); + else + dma_direct_unmap_page(dev, dma_handle, size, direction, attrs); } @@ -92,7 +94,7 @@ static int dma_iommu_map_sg(struct device *dev, struct scatterlist *sglist, if (dma_iommu_map_bypass(dev, attrs)) return dma_direct_map_sg(dev, sglist, nelems, direction, attrs); return ppc_iommu_map_sg(dev, get_iommu_table_base(dev), sglist, nelems, - device_to_mask(dev), direction, attrs); + dma_get_mask(dev), direction, attrs); } static void dma_iommu_unmap_sg(struct device *dev, struct scatterlist *sglist, @@ -102,6 +104,8 @@ static void dma_iommu_unmap_sg(struct device *dev, struct scatterlist *sglist, if (!dma_iommu_map_bypass(dev, attrs)) ppc_iommu_unmap_sg(get_iommu_table_base(dev), sglist, nelems, direction, attrs); + else + dma_direct_unmap_sg(dev, sglist, nelems, direction, attrs); } static bool dma_iommu_bypass_supported(struct device *dev, u64 mask) @@ -163,6 +167,34 @@ u64 dma_iommu_get_required_mask(struct device *dev) return mask; } +static void dma_iommu_sync_for_cpu(struct device *dev, dma_addr_t addr, + size_t size, enum dma_data_direction dir) +{ + if (dma_iommu_alloc_bypass(dev)) + dma_direct_sync_single_for_cpu(dev, addr, size, dir); +} + +static void dma_iommu_sync_for_device(struct device *dev, dma_addr_t addr, + size_t sz, enum dma_data_direction dir) +{ + if (dma_iommu_alloc_bypass(dev)) + dma_direct_sync_single_for_device(dev, addr, sz, dir); +} + +extern void dma_iommu_sync_sg_for_cpu(struct device *dev, + struct scatterlist *sgl, int nents, enum dma_data_direction dir) +{ + if (dma_iommu_alloc_bypass(dev)) + dma_direct_sync_sg_for_cpu(dev, sgl, nents, dir); +} + +extern void dma_iommu_sync_sg_for_device(struct device *dev, + struct scatterlist *sgl, int nents, enum dma_data_direction dir) +{ + if (dma_iommu_alloc_bypass(dev)) + dma_direct_sync_sg_for_device(dev, sgl, nents, dir); +} + const struct dma_map_ops dma_iommu_ops = { .alloc = dma_iommu_alloc_coherent, .free = dma_iommu_free_coherent, @@ -172,4 +204,8 @@ const struct dma_map_ops dma_iommu_ops = { .map_page = dma_iommu_map_page, .unmap_page = dma_iommu_unmap_page, .get_required_mask = dma_iommu_get_required_mask, + .sync_single_for_cpu = dma_iommu_sync_for_cpu, + .sync_single_for_device = dma_iommu_sync_for_device, + .sync_sg_for_cpu = dma_iommu_sync_sg_for_cpu, + .sync_sg_for_device = dma_iommu_sync_sg_for_device, }; diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index f192d57db47d..c0e4b73191f3 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -354,10 +354,19 @@ static inline unsigned long eeh_token_to_phys(unsigned long token) ptep = find_init_mm_pte(token, &hugepage_shift); if (!ptep) return token; - WARN_ON(hugepage_shift); - pa = pte_pfn(*ptep) << PAGE_SHIFT; - return pa | (token & (PAGE_SIZE-1)); + pa = pte_pfn(*ptep); + + /* On radix we can do hugepage mappings for io, so handle that */ + if (hugepage_shift) { + pa <<= hugepage_shift; + pa |= token & ((1ul << hugepage_shift) - 1); + } else { + pa <<= PAGE_SHIFT; + pa |= token & (PAGE_SIZE - 1); + } + + return pa; } /* diff --git a/arch/powerpc/kernel/eeh_cache.c b/arch/powerpc/kernel/eeh_cache.c index 320472373122..05ffd32b3416 100644 --- a/arch/powerpc/kernel/eeh_cache.c +++ b/arch/powerpc/kernel/eeh_cache.c @@ -18,6 +18,8 @@ /** + * DOC: Overview + * * The pci address cache subsystem. This subsystem places * PCI device address resources into a red-black tree, sorted * according to the address range, so that given only an i/o @@ -34,6 +36,7 @@ * than any hash algo I could think of for this problem, even * with the penalty of slow pointer chases for d-cache misses). */ + struct pci_io_addr_range { struct rb_node rb_node; resource_size_t addr_lo; diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 73ba246ca11d..eee5bef736c8 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -21,6 +21,698 @@ #include <asm/feature-fixups.h> #include <asm/kup.h> +/* PACA save area offsets (exgen, exmc, etc) */ +#define EX_R9 0 +#define EX_R10 8 +#define EX_R11 16 +#define EX_R12 24 +#define EX_R13 32 +#define EX_DAR 40 +#define EX_DSISR 48 +#define EX_CCR 52 +#define EX_CFAR 56 +#define EX_PPR 64 +#if defined(CONFIG_RELOCATABLE) +#define EX_CTR 72 +.if EX_SIZE != 10 + .error "EX_SIZE is wrong" +.endif +#else +.if EX_SIZE != 9 + .error "EX_SIZE is wrong" +.endif +#endif + +/* + * We're short on space and time in the exception prolog, so we can't + * use the normal LOAD_REG_IMMEDIATE macro to load the address of label. + * Instead we get the base of the kernel from paca->kernelbase and or in the low + * part of label. This requires that the label be within 64KB of kernelbase, and + * that kernelbase be 64K aligned. + */ +#define LOAD_HANDLER(reg, label) \ + ld reg,PACAKBASE(r13); /* get high part of &label */ \ + ori reg,reg,FIXED_SYMBOL_ABS_ADDR(label) + +#define __LOAD_HANDLER(reg, label) \ + ld reg,PACAKBASE(r13); \ + ori reg,reg,(ABS_ADDR(label))@l + +/* + * Branches from unrelocated code (e.g., interrupts) to labels outside + * head-y require >64K offsets. + */ +#define __LOAD_FAR_HANDLER(reg, label) \ + ld reg,PACAKBASE(r13); \ + ori reg,reg,(ABS_ADDR(label))@l; \ + addis reg,reg,(ABS_ADDR(label))@h + +/* Exception register prefixes */ +#define EXC_HV 1 +#define EXC_STD 0 + +#if defined(CONFIG_RELOCATABLE) +/* + * If we support interrupts with relocation on AND we're a relocatable kernel, + * we need to use CTR to get to the 2nd level handler. So, save/restore it + * when required. + */ +#define SAVE_CTR(reg, area) mfctr reg ; std reg,area+EX_CTR(r13) +#define GET_CTR(reg, area) ld reg,area+EX_CTR(r13) +#define RESTORE_CTR(reg, area) ld reg,area+EX_CTR(r13) ; mtctr reg +#else +/* ...else CTR is unused and in register. */ +#define SAVE_CTR(reg, area) +#define GET_CTR(reg, area) mfctr reg +#define RESTORE_CTR(reg, area) +#endif + +/* + * PPR save/restore macros used in exceptions-64s.S + * Used for P7 or later processors + */ +#define SAVE_PPR(area, ra) \ +BEGIN_FTR_SECTION_NESTED(940) \ + ld ra,area+EX_PPR(r13); /* Read PPR from paca */ \ + std ra,_PPR(r1); \ +END_FTR_SECTION_NESTED(CPU_FTR_HAS_PPR,CPU_FTR_HAS_PPR,940) + +#define RESTORE_PPR_PACA(area, ra) \ +BEGIN_FTR_SECTION_NESTED(941) \ + ld ra,area+EX_PPR(r13); \ + mtspr SPRN_PPR,ra; \ +END_FTR_SECTION_NESTED(CPU_FTR_HAS_PPR,CPU_FTR_HAS_PPR,941) + +/* + * Get an SPR into a register if the CPU has the given feature + */ +#define OPT_GET_SPR(ra, spr, ftr) \ +BEGIN_FTR_SECTION_NESTED(943) \ + mfspr ra,spr; \ +END_FTR_SECTION_NESTED(ftr,ftr,943) + +/* + * Set an SPR from a register if the CPU has the given feature + */ +#define OPT_SET_SPR(ra, spr, ftr) \ +BEGIN_FTR_SECTION_NESTED(943) \ + mtspr spr,ra; \ +END_FTR_SECTION_NESTED(ftr,ftr,943) + +/* + * Save a register to the PACA if the CPU has the given feature + */ +#define OPT_SAVE_REG_TO_PACA(offset, ra, ftr) \ +BEGIN_FTR_SECTION_NESTED(943) \ + std ra,offset(r13); \ +END_FTR_SECTION_NESTED(ftr,ftr,943) + +.macro EXCEPTION_PROLOG_0 area + SET_SCRATCH0(r13) /* save r13 */ + GET_PACA(r13) + std r9,\area\()+EX_R9(r13) /* save r9 */ + OPT_GET_SPR(r9, SPRN_PPR, CPU_FTR_HAS_PPR) + HMT_MEDIUM + std r10,\area\()+EX_R10(r13) /* save r10 - r12 */ + OPT_GET_SPR(r10, SPRN_CFAR, CPU_FTR_CFAR) +.endm + +.macro EXCEPTION_PROLOG_1 hsrr, area, kvm, vec, dar, dsisr, bitmask + OPT_SAVE_REG_TO_PACA(\area\()+EX_PPR, r9, CPU_FTR_HAS_PPR) + OPT_SAVE_REG_TO_PACA(\area\()+EX_CFAR, r10, CPU_FTR_CFAR) + INTERRUPT_TO_KERNEL + SAVE_CTR(r10, \area\()) + mfcr r9 + .if \kvm + KVMTEST \hsrr \vec + .endif + .if \bitmask + lbz r10,PACAIRQSOFTMASK(r13) + andi. r10,r10,\bitmask + /* Associate vector numbers with bits in paca->irq_happened */ + .if \vec == 0x500 || \vec == 0xea0 + li r10,PACA_IRQ_EE + .elseif \vec == 0x900 + li r10,PACA_IRQ_DEC + .elseif \vec == 0xa00 || \vec == 0xe80 + li r10,PACA_IRQ_DBELL + .elseif \vec == 0xe60 + li r10,PACA_IRQ_HMI + .elseif \vec == 0xf00 + li r10,PACA_IRQ_PMI + .else + .abort "Bad maskable vector" + .endif + + .if \hsrr + bne masked_Hinterrupt + .else + bne masked_interrupt + .endif + .endif + + std r11,\area\()+EX_R11(r13) + std r12,\area\()+EX_R12(r13) + + /* + * DAR/DSISR, SCRATCH0 must be read before setting MSR[RI], + * because a d-side MCE will clobber those registers so is + * not recoverable if they are live. + */ + GET_SCRATCH0(r10) + std r10,\area\()+EX_R13(r13) + .if \dar + mfspr r10,SPRN_DAR + std r10,\area\()+EX_DAR(r13) + .endif + .if \dsisr + mfspr r10,SPRN_DSISR + stw r10,\area\()+EX_DSISR(r13) + .endif +.endm + +.macro EXCEPTION_PROLOG_2_REAL label, hsrr, set_ri + ld r10,PACAKMSR(r13) /* get MSR value for kernel */ + .if ! \set_ri + xori r10,r10,MSR_RI /* Clear MSR_RI */ + .endif + .if \hsrr + mfspr r11,SPRN_HSRR0 /* save HSRR0 */ + mfspr r12,SPRN_HSRR1 /* and HSRR1 */ + mtspr SPRN_HSRR1,r10 + .else + mfspr r11,SPRN_SRR0 /* save SRR0 */ + mfspr r12,SPRN_SRR1 /* and SRR1 */ + mtspr SPRN_SRR1,r10 + .endif + LOAD_HANDLER(r10, \label\()) + .if \hsrr + mtspr SPRN_HSRR0,r10 + HRFI_TO_KERNEL + .else + mtspr SPRN_SRR0,r10 + RFI_TO_KERNEL + .endif + b . /* prevent speculative execution */ +.endm + +.macro EXCEPTION_PROLOG_2_VIRT label, hsrr +#ifdef CONFIG_RELOCATABLE + .if \hsrr + mfspr r11,SPRN_HSRR0 /* save HSRR0 */ + .else + mfspr r11,SPRN_SRR0 /* save SRR0 */ + .endif + LOAD_HANDLER(r12, \label\()) + mtctr r12 + .if \hsrr + mfspr r12,SPRN_HSRR1 /* and HSRR1 */ + .else + mfspr r12,SPRN_SRR1 /* and HSRR1 */ + .endif + li r10,MSR_RI + mtmsrd r10,1 /* Set RI (EE=0) */ + bctr +#else + .if \hsrr + mfspr r11,SPRN_HSRR0 /* save HSRR0 */ + mfspr r12,SPRN_HSRR1 /* and HSRR1 */ + .else + mfspr r11,SPRN_SRR0 /* save SRR0 */ + mfspr r12,SPRN_SRR1 /* and SRR1 */ + .endif + li r10,MSR_RI + mtmsrd r10,1 /* Set RI (EE=0) */ + b \label +#endif +.endm + +/* + * Branch to label using its 0xC000 address. This results in instruction + * address suitable for MSR[IR]=0 or 1, which allows relocation to be turned + * on using mtmsr rather than rfid. + * + * This could set the 0xc bits for !RELOCATABLE as an immediate, rather than + * load KBASE for a slight optimisation. + */ +#define BRANCH_TO_C000(reg, label) \ + __LOAD_FAR_HANDLER(reg, label); \ + mtctr reg; \ + bctr + +#ifdef CONFIG_KVM_BOOK3S_64_HANDLER +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE +/* + * If hv is possible, interrupts come into to the hv version + * of the kvmppc_interrupt code, which then jumps to the PR handler, + * kvmppc_interrupt_pr, if the guest is a PR guest. + */ +#define kvmppc_interrupt kvmppc_interrupt_hv +#else +#define kvmppc_interrupt kvmppc_interrupt_pr +#endif + +.macro KVMTEST hsrr, n + lbz r10,HSTATE_IN_GUEST(r13) + cmpwi r10,0 + .if \hsrr + bne do_kvm_H\n + .else + bne do_kvm_\n + .endif +.endm + +.macro KVM_HANDLER area, hsrr, n, skip + .if \skip + cmpwi r10,KVM_GUEST_MODE_SKIP + beq 89f + .else +BEGIN_FTR_SECTION_NESTED(947) + ld r10,\area+EX_CFAR(r13) + std r10,HSTATE_CFAR(r13) +END_FTR_SECTION_NESTED(CPU_FTR_CFAR,CPU_FTR_CFAR,947) + .endif + +BEGIN_FTR_SECTION_NESTED(948) + ld r10,\area+EX_PPR(r13) + std r10,HSTATE_PPR(r13) +END_FTR_SECTION_NESTED(CPU_FTR_HAS_PPR,CPU_FTR_HAS_PPR,948) + ld r10,\area+EX_R10(r13) + std r12,HSTATE_SCRATCH0(r13) + sldi r12,r9,32 + /* HSRR variants have the 0x2 bit added to their trap number */ + .if \hsrr + ori r12,r12,(\n + 0x2) + .else + ori r12,r12,(\n) + .endif + +#ifdef CONFIG_RELOCATABLE + /* + * KVM requires __LOAD_FAR_HANDLER beause kvmppc_interrupt lives + * outside the head section. CONFIG_RELOCATABLE KVM expects CTR + * to be saved in HSTATE_SCRATCH1. + */ + mfctr r9 + std r9,HSTATE_SCRATCH1(r13) + __LOAD_FAR_HANDLER(r9, kvmppc_interrupt) + mtctr r9 + ld r9,\area+EX_R9(r13) + bctr +#else + ld r9,\area+EX_R9(r13) + b kvmppc_interrupt +#endif + + + .if \skip +89: mtocrf 0x80,r9 + ld r9,\area+EX_R9(r13) + ld r10,\area+EX_R10(r13) + .if \hsrr + b kvmppc_skip_Hinterrupt + .else + b kvmppc_skip_interrupt + .endif + .endif +.endm + +#else +.macro KVMTEST hsrr, n +.endm +.macro KVM_HANDLER area, hsrr, n, skip +.endm +#endif + +#define EXCEPTION_PROLOG_COMMON_1() \ + std r9,_CCR(r1); /* save CR in stackframe */ \ + std r11,_NIP(r1); /* save SRR0 in stackframe */ \ + std r12,_MSR(r1); /* save SRR1 in stackframe */ \ + std r10,0(r1); /* make stack chain pointer */ \ + std r0,GPR0(r1); /* save r0 in stackframe */ \ + std r10,GPR1(r1); /* save r1 in stackframe */ \ + +/* Save original regs values from save area to stack frame. */ +#define EXCEPTION_PROLOG_COMMON_2(area) \ + ld r9,area+EX_R9(r13); /* move r9, r10 to stackframe */ \ + ld r10,area+EX_R10(r13); \ + std r9,GPR9(r1); \ + std r10,GPR10(r1); \ + ld r9,area+EX_R11(r13); /* move r11 - r13 to stackframe */ \ + ld r10,area+EX_R12(r13); \ + ld r11,area+EX_R13(r13); \ + std r9,GPR11(r1); \ + std r10,GPR12(r1); \ + std r11,GPR13(r1); \ +BEGIN_FTR_SECTION_NESTED(66); \ + ld r10,area+EX_CFAR(r13); \ + std r10,ORIG_GPR3(r1); \ +END_FTR_SECTION_NESTED(CPU_FTR_CFAR, CPU_FTR_CFAR, 66); \ + GET_CTR(r10, area); \ + std r10,_CTR(r1); + +#define EXCEPTION_PROLOG_COMMON_3(trap) \ + std r2,GPR2(r1); /* save r2 in stackframe */ \ + SAVE_4GPRS(3, r1); /* save r3 - r6 in stackframe */ \ + SAVE_2GPRS(7, r1); /* save r7, r8 in stackframe */ \ + mflr r9; /* Get LR, later save to stack */ \ + ld r2,PACATOC(r13); /* get kernel TOC into r2 */ \ + std r9,_LINK(r1); \ + lbz r10,PACAIRQSOFTMASK(r13); \ + mfspr r11,SPRN_XER; /* save XER in stackframe */ \ + std r10,SOFTE(r1); \ + std r11,_XER(r1); \ + li r9,(trap)+1; \ + std r9,_TRAP(r1); /* set trap number */ \ + li r10,0; \ + ld r11,exception_marker@toc(r2); \ + std r10,RESULT(r1); /* clear regs->result */ \ + std r11,STACK_FRAME_OVERHEAD-16(r1); /* mark the frame */ + +/* + * On entry r13 points to the paca, r9-r13 are saved in the paca, + * r9 contains the saved CR, r11 and r12 contain the saved SRR0 and + * SRR1, and relocation is on. + */ +#define EXCEPTION_COMMON(area, trap) \ + andi. r10,r12,MSR_PR; /* See if coming from user */ \ + mr r10,r1; /* Save r1 */ \ + subi r1,r1,INT_FRAME_SIZE; /* alloc frame on kernel stack */ \ + beq- 1f; \ + ld r1,PACAKSAVE(r13); /* kernel stack to use */ \ +1: tdgei r1,-INT_FRAME_SIZE; /* trap if r1 is in userspace */ \ + EMIT_BUG_ENTRY 1b,__FILE__,__LINE__,0; \ +3: EXCEPTION_PROLOG_COMMON_1(); \ + kuap_save_amr_and_lock r9, r10, cr1, cr0; \ + beq 4f; /* if from kernel mode */ \ + ACCOUNT_CPU_USER_ENTRY(r13, r9, r10); \ + SAVE_PPR(area, r9); \ +4: EXCEPTION_PROLOG_COMMON_2(area); \ + EXCEPTION_PROLOG_COMMON_3(trap); \ + ACCOUNT_STOLEN_TIME + +/* + * Exception where stack is already set in r1, r1 is saved in r10. + * PPR save and CPU accounting is not done (for some reason). + */ +#define EXCEPTION_COMMON_STACK(area, trap) \ + EXCEPTION_PROLOG_COMMON_1(); \ + kuap_save_amr_and_lock r9, r10, cr1; \ + EXCEPTION_PROLOG_COMMON_2(area); \ + EXCEPTION_PROLOG_COMMON_3(trap) + +/* + * Restore all registers including H/SRR0/1 saved in a stack frame of a + * standard exception. + */ +.macro EXCEPTION_RESTORE_REGS hsrr + /* Move original SRR0 and SRR1 into the respective regs */ + ld r9,_MSR(r1) + .if \hsrr + mtspr SPRN_HSRR1,r9 + .else + mtspr SPRN_SRR1,r9 + .endif + ld r9,_NIP(r1) + .if \hsrr + mtspr SPRN_HSRR0,r9 + .else + mtspr SPRN_SRR0,r9 + .endif + ld r9,_CTR(r1) + mtctr r9 + ld r9,_XER(r1) + mtxer r9 + ld r9,_LINK(r1) + mtlr r9 + ld r9,_CCR(r1) + mtcr r9 + REST_8GPRS(2, r1) + REST_4GPRS(10, r1) + REST_GPR(0, r1) + /* restore original r1. */ + ld r1,GPR1(r1) +.endm + +#define RUNLATCH_ON \ +BEGIN_FTR_SECTION \ + ld r3, PACA_THREAD_INFO(r13); \ + ld r4,TI_LOCAL_FLAGS(r3); \ + andi. r0,r4,_TLF_RUNLATCH; \ + beql ppc64_runlatch_on_trampoline; \ +END_FTR_SECTION_IFSET(CPU_FTR_CTRL) + +/* + * When the idle code in power4_idle puts the CPU into NAP mode, + * it has to do so in a loop, and relies on the external interrupt + * and decrementer interrupt entry code to get it out of the loop. + * It sets the _TLF_NAPPING bit in current_thread_info()->local_flags + * to signal that it is in the loop and needs help to get out. + */ +#ifdef CONFIG_PPC_970_NAP +#define FINISH_NAP \ +BEGIN_FTR_SECTION \ + ld r11, PACA_THREAD_INFO(r13); \ + ld r9,TI_LOCAL_FLAGS(r11); \ + andi. r10,r9,_TLF_NAPPING; \ + bnel power4_fixup_nap; \ +END_FTR_SECTION_IFSET(CPU_FTR_CAN_NAP) +#else +#define FINISH_NAP +#endif + +/* + * Following are the BOOK3S exception handler helper macros. + * Handlers come in a number of types, and each type has a number of varieties. + * + * EXC_REAL_* - real, unrelocated exception vectors + * EXC_VIRT_* - virt (AIL), unrelocated exception vectors + * TRAMP_REAL_* - real, unrelocated helpers (virt can call these) + * TRAMP_VIRT_* - virt, unreloc helpers (in practice, real can use) + * TRAMP_KVM - KVM handlers that get put into real, unrelocated + * EXC_COMMON - virt, relocated common handlers + * + * The EXC handlers are given a name, and branch to name_common, or the + * appropriate KVM or masking function. Vector handler verieties are as + * follows: + * + * EXC_{REAL|VIRT}_BEGIN/END - used to open-code the exception + * + * EXC_{REAL|VIRT} - standard exception + * + * EXC_{REAL|VIRT}_suffix + * where _suffix is: + * - _MASKABLE - maskable exception + * - _OOL - out of line with trampoline to common handler + * - _HV - HV exception + * + * There can be combinations, e.g., EXC_VIRT_OOL_MASKABLE_HV + * + * KVM handlers come in the following verieties: + * TRAMP_KVM + * TRAMP_KVM_SKIP + * TRAMP_KVM_HV + * TRAMP_KVM_HV_SKIP + * + * COMMON handlers come in the following verieties: + * EXC_COMMON_BEGIN/END - used to open-code the handler + * EXC_COMMON + * EXC_COMMON_ASYNC + * + * TRAMP_REAL and TRAMP_VIRT can be used with BEGIN/END. KVM + * and OOL handlers are implemented as types of TRAMP and TRAMP_VIRT handlers. + */ + +#define __EXC_REAL(name, start, size, area) \ + EXC_REAL_BEGIN(name, start, size); \ + EXCEPTION_PROLOG_0 area ; \ + EXCEPTION_PROLOG_1 EXC_STD, area, 1, start, 0, 0, 0 ; \ + EXCEPTION_PROLOG_2_REAL name##_common, EXC_STD, 1 ; \ + EXC_REAL_END(name, start, size) + +#define EXC_REAL(name, start, size) \ + __EXC_REAL(name, start, size, PACA_EXGEN) + +#define __EXC_VIRT(name, start, size, realvec, area) \ + EXC_VIRT_BEGIN(name, start, size); \ + EXCEPTION_PROLOG_0 area ; \ + EXCEPTION_PROLOG_1 EXC_STD, area, 0, realvec, 0, 0, 0; \ + EXCEPTION_PROLOG_2_VIRT name##_common, EXC_STD ; \ + EXC_VIRT_END(name, start, size) + +#define EXC_VIRT(name, start, size, realvec) \ + __EXC_VIRT(name, start, size, realvec, PACA_EXGEN) + +#define EXC_REAL_MASKABLE(name, start, size, bitmask) \ + EXC_REAL_BEGIN(name, start, size); \ + EXCEPTION_PROLOG_0 PACA_EXGEN ; \ + EXCEPTION_PROLOG_1 EXC_STD, PACA_EXGEN, 1, start, 0, 0, bitmask ; \ + EXCEPTION_PROLOG_2_REAL name##_common, EXC_STD, 1 ; \ + EXC_REAL_END(name, start, size) + +#define EXC_VIRT_MASKABLE(name, start, size, realvec, bitmask) \ + EXC_VIRT_BEGIN(name, start, size); \ + EXCEPTION_PROLOG_0 PACA_EXGEN ; \ + EXCEPTION_PROLOG_1 EXC_STD, PACA_EXGEN, 0, realvec, 0, 0, bitmask ; \ + EXCEPTION_PROLOG_2_VIRT name##_common, EXC_STD ; \ + EXC_VIRT_END(name, start, size) + +#define EXC_REAL_HV(name, start, size) \ + EXC_REAL_BEGIN(name, start, size); \ + EXCEPTION_PROLOG_0 PACA_EXGEN; \ + EXCEPTION_PROLOG_1 EXC_HV, PACA_EXGEN, 1, start, 0, 0, 0 ; \ + EXCEPTION_PROLOG_2_REAL name##_common, EXC_HV, 1 ; \ + EXC_REAL_END(name, start, size) + +#define EXC_VIRT_HV(name, start, size, realvec) \ + EXC_VIRT_BEGIN(name, start, size); \ + EXCEPTION_PROLOG_0 PACA_EXGEN; \ + EXCEPTION_PROLOG_1 EXC_HV, PACA_EXGEN, 1, realvec, 0, 0, 0 ; \ + EXCEPTION_PROLOG_2_VIRT name##_common, EXC_HV ; \ + EXC_VIRT_END(name, start, size) + +#define __EXC_REAL_OOL(name, start, size) \ + EXC_REAL_BEGIN(name, start, size); \ + EXCEPTION_PROLOG_0 PACA_EXGEN ; \ + b tramp_real_##name ; \ + EXC_REAL_END(name, start, size) + +#define __TRAMP_REAL_OOL(name, vec) \ + TRAMP_REAL_BEGIN(tramp_real_##name); \ + EXCEPTION_PROLOG_1 EXC_STD, PACA_EXGEN, 1, vec, 0, 0, 0 ; \ + EXCEPTION_PROLOG_2_REAL name##_common, EXC_STD, 1 + +#define EXC_REAL_OOL(name, start, size) \ + __EXC_REAL_OOL(name, start, size); \ + __TRAMP_REAL_OOL(name, start) + +#define __EXC_REAL_OOL_MASKABLE(name, start, size) \ + __EXC_REAL_OOL(name, start, size) + +#define __TRAMP_REAL_OOL_MASKABLE(name, vec, bitmask) \ + TRAMP_REAL_BEGIN(tramp_real_##name); \ + EXCEPTION_PROLOG_1 EXC_STD, PACA_EXGEN, 1, vec, 0, 0, bitmask ; \ + EXCEPTION_PROLOG_2_REAL name##_common, EXC_STD, 1 + +#define EXC_REAL_OOL_MASKABLE(name, start, size, bitmask) \ + __EXC_REAL_OOL_MASKABLE(name, start, size); \ + __TRAMP_REAL_OOL_MASKABLE(name, start, bitmask) + +#define __EXC_REAL_OOL_HV(name, start, size) \ + __EXC_REAL_OOL(name, start, size) + +#define __TRAMP_REAL_OOL_HV(name, vec) \ + TRAMP_REAL_BEGIN(tramp_real_##name); \ + EXCEPTION_PROLOG_1 EXC_HV, PACA_EXGEN, 1, vec, 0, 0, 0 ; \ + EXCEPTION_PROLOG_2_REAL name##_common, EXC_HV, 1 + +#define EXC_REAL_OOL_HV(name, start, size) \ + __EXC_REAL_OOL_HV(name, start, size); \ + __TRAMP_REAL_OOL_HV(name, start) + +#define __EXC_REAL_OOL_MASKABLE_HV(name, start, size) \ + __EXC_REAL_OOL(name, start, size) + +#define __TRAMP_REAL_OOL_MASKABLE_HV(name, vec, bitmask) \ + TRAMP_REAL_BEGIN(tramp_real_##name); \ + EXCEPTION_PROLOG_1 EXC_HV, PACA_EXGEN, 1, vec, 0, 0, bitmask ; \ + EXCEPTION_PROLOG_2_REAL name##_common, EXC_HV, 1 + +#define EXC_REAL_OOL_MASKABLE_HV(name, start, size, bitmask) \ + __EXC_REAL_OOL_MASKABLE_HV(name, start, size); \ + __TRAMP_REAL_OOL_MASKABLE_HV(name, start, bitmask) + +#define __EXC_VIRT_OOL(name, start, size) \ + EXC_VIRT_BEGIN(name, start, size); \ + EXCEPTION_PROLOG_0 PACA_EXGEN ; \ + b tramp_virt_##name; \ + EXC_VIRT_END(name, start, size) + +#define __TRAMP_VIRT_OOL(name, realvec) \ + TRAMP_VIRT_BEGIN(tramp_virt_##name); \ + EXCEPTION_PROLOG_1 EXC_STD, PACA_EXGEN, 0, vec, 0, 0, 0 ; \ + EXCEPTION_PROLOG_2_VIRT name##_common, EXC_STD + +#define EXC_VIRT_OOL(name, start, size, realvec) \ + __EXC_VIRT_OOL(name, start, size); \ + __TRAMP_VIRT_OOL(name, realvec) + +#define __EXC_VIRT_OOL_MASKABLE(name, start, size) \ + __EXC_VIRT_OOL(name, start, size) + +#define __TRAMP_VIRT_OOL_MASKABLE(name, realvec, bitmask) \ + TRAMP_VIRT_BEGIN(tramp_virt_##name); \ + EXCEPTION_PROLOG_1 EXC_STD, PACA_EXGEN, 0, realvec, 0, 0, bitmask ; \ + EXCEPTION_PROLOG_2_REAL name##_common, EXC_STD, 1 + +#define EXC_VIRT_OOL_MASKABLE(name, start, size, realvec, bitmask) \ + __EXC_VIRT_OOL_MASKABLE(name, start, size); \ + __TRAMP_VIRT_OOL_MASKABLE(name, realvec, bitmask) + +#define __EXC_VIRT_OOL_HV(name, start, size) \ + __EXC_VIRT_OOL(name, start, size) + +#define __TRAMP_VIRT_OOL_HV(name, realvec) \ + TRAMP_VIRT_BEGIN(tramp_virt_##name); \ + EXCEPTION_PROLOG_1 EXC_HV, PACA_EXGEN, 1, realvec, 0, 0, 0 ; \ + EXCEPTION_PROLOG_2_VIRT name##_common, EXC_HV + +#define EXC_VIRT_OOL_HV(name, start, size, realvec) \ + __EXC_VIRT_OOL_HV(name, start, size); \ + __TRAMP_VIRT_OOL_HV(name, realvec) + +#define __EXC_VIRT_OOL_MASKABLE_HV(name, start, size) \ + __EXC_VIRT_OOL(name, start, size) + +#define __TRAMP_VIRT_OOL_MASKABLE_HV(name, realvec, bitmask) \ + TRAMP_VIRT_BEGIN(tramp_virt_##name); \ + EXCEPTION_PROLOG_1 EXC_HV, PACA_EXGEN, 1, realvec, 0, 0, bitmask ; \ + EXCEPTION_PROLOG_2_VIRT name##_common, EXC_HV + +#define EXC_VIRT_OOL_MASKABLE_HV(name, start, size, realvec, bitmask) \ + __EXC_VIRT_OOL_MASKABLE_HV(name, start, size); \ + __TRAMP_VIRT_OOL_MASKABLE_HV(name, realvec, bitmask) + +#define TRAMP_KVM(area, n) \ + TRAMP_KVM_BEGIN(do_kvm_##n); \ + KVM_HANDLER area, EXC_STD, n, 0 + +#define TRAMP_KVM_SKIP(area, n) \ + TRAMP_KVM_BEGIN(do_kvm_##n); \ + KVM_HANDLER area, EXC_STD, n, 1 + +#define TRAMP_KVM_HV(area, n) \ + TRAMP_KVM_BEGIN(do_kvm_H##n); \ + KVM_HANDLER area, EXC_HV, n, 0 + +#define TRAMP_KVM_HV_SKIP(area, n) \ + TRAMP_KVM_BEGIN(do_kvm_H##n); \ + KVM_HANDLER area, EXC_HV, n, 1 + +#define EXC_COMMON(name, realvec, hdlr) \ + EXC_COMMON_BEGIN(name); \ + EXCEPTION_COMMON(PACA_EXGEN, realvec); \ + bl save_nvgprs; \ + RECONCILE_IRQ_STATE(r10, r11); \ + addi r3,r1,STACK_FRAME_OVERHEAD; \ + bl hdlr; \ + b ret_from_except + +/* + * Like EXC_COMMON, but for exceptions that can occur in the idle task and + * therefore need the special idle handling (finish nap and runlatch) + */ +#define EXC_COMMON_ASYNC(name, realvec, hdlr) \ + EXC_COMMON_BEGIN(name); \ + EXCEPTION_COMMON(PACA_EXGEN, realvec); \ + FINISH_NAP; \ + RECONCILE_IRQ_STATE(r10, r11); \ + RUNLATCH_ON; \ + addi r3,r1,STACK_FRAME_OVERHEAD; \ + bl hdlr; \ + b ret_from_except_lite + + /* * There are a few constraints to be concerned with. * - Real mode exceptions code/data must be located at their physical location. @@ -107,6 +799,7 @@ __start_interrupts: EXC_VIRT_NONE(0x4000, 0x100) +EXC_REAL_BEGIN(system_reset, 0x100, 0x100) #ifdef CONFIG_PPC_P7_NAP /* * If running native on arch 2.06 or later, check if we are waking up @@ -114,60 +807,72 @@ EXC_VIRT_NONE(0x4000, 0x100) * bits 46:47. A non-0 value indicates that we are coming from a power * saving state. The idle wakeup handler initially runs in real mode, * but we branch to the 0xc000... address so we can turn on relocation - * with mtmsr. + * with mtmsrd later, after SPRs are restored. + * + * Careful to minimise cost for the fast path (idle wakeup) while + * also avoiding clobbering CFAR for the debug path (non-idle). + * + * For the idle wake case volatile registers can be clobbered, which + * is why we use those initially. If it turns out to not be an idle + * wake, carefully put everything back the way it was, so we can use + * common exception macros to handle it. */ -#define IDLETEST(n) \ - BEGIN_FTR_SECTION ; \ - mfspr r10,SPRN_SRR1 ; \ - rlwinm. r10,r10,47-31,30,31 ; \ - beq- 1f ; \ - cmpwi cr1,r10,2 ; \ - mfspr r3,SPRN_SRR1 ; \ - bltlr cr1 ; /* no state loss, return to idle caller */ \ - BRANCH_TO_C000(r10, system_reset_idle_common) ; \ -1: \ - KVMTEST_PR(n) ; \ - END_FTR_SECTION_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206) -#else -#define IDLETEST NOTEST +BEGIN_FTR_SECTION + SET_SCRATCH0(r13) + GET_PACA(r13) + std r3,PACA_EXNMI+0*8(r13) + std r4,PACA_EXNMI+1*8(r13) + std r5,PACA_EXNMI+2*8(r13) + mfspr r3,SPRN_SRR1 + mfocrf r4,0x80 + rlwinm. r5,r3,47-31,30,31 + bne+ system_reset_idle_wake + /* Not powersave wakeup. Restore regs for regular interrupt handler. */ + mtocrf 0x80,r4 + ld r3,PACA_EXNMI+0*8(r13) + ld r4,PACA_EXNMI+1*8(r13) + ld r5,PACA_EXNMI+2*8(r13) + GET_SCRATCH0(r13) +END_FTR_SECTION_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206) #endif -EXC_REAL_BEGIN(system_reset, 0x100, 0x100) - SET_SCRATCH0(r13) + EXCEPTION_PROLOG_0 PACA_EXNMI + EXCEPTION_PROLOG_1 EXC_STD, PACA_EXNMI, 1, 0x100, 0, 0, 0 + EXCEPTION_PROLOG_2_REAL system_reset_common, EXC_STD, 0 /* * MSR_RI is not enabled, because PACA_EXNMI and nmi stack is * being used, so a nested NMI exception would corrupt it. + * + * In theory, we should not enable relocation here if it was disabled + * in SRR1, because the MMU may not be configured to support it (e.g., + * SLB may have been cleared). In practice, there should only be a few + * small windows where that's the case, and sreset is considered to + * be dangerous anyway. */ - EXCEPTION_PROLOG_NORI(PACA_EXNMI, system_reset_common, EXC_STD, - IDLETEST, 0x100) - EXC_REAL_END(system_reset, 0x100, 0x100) + EXC_VIRT_NONE(0x4100, 0x100) TRAMP_KVM(PACA_EXNMI, 0x100) #ifdef CONFIG_PPC_P7_NAP -EXC_COMMON_BEGIN(system_reset_idle_common) - /* - * This must be a direct branch (without linker branch stub) because - * we can not use TOC at this point as r2 may not be restored yet. - */ - b idle_return_gpr_loss +TRAMP_REAL_BEGIN(system_reset_idle_wake) + /* We are waking up from idle, so may clobber any volatile register */ + cmpwi cr1,r5,2 + bltlr cr1 /* no state loss, return to idle caller with r3=SRR1 */ + BRANCH_TO_C000(r12, DOTSYM(idle_return_gpr_loss)) #endif +#ifdef CONFIG_PPC_PSERIES /* - * Set IRQS_ALL_DISABLED unconditionally so arch_irqs_disabled does - * the right thing. We do not want to reconcile because that goes - * through irq tracing which we don't want in NMI. - * - * Save PACAIRQHAPPENED because some code will do a hard disable - * (e.g., xmon). So we want to restore this back to where it was - * when we return. DAR is unused in the stack, so save it there. + * Vectors for the FWNMI option. Share common code. */ -#define ADD_RECONCILE_NMI \ - li r10,IRQS_ALL_DISABLED; \ - stb r10,PACAIRQSOFTMASK(r13); \ - lbz r10,PACAIRQHAPPENED(r13); \ - std r10,_DAR(r1) +TRAMP_REAL_BEGIN(system_reset_fwnmi) + /* See comment at system_reset exception, don't turn on RI */ + EXCEPTION_PROLOG_0 PACA_EXNMI + EXCEPTION_PROLOG_1 EXC_STD, PACA_EXNMI, 0, 0x100, 0, 0, 0 + EXCEPTION_PROLOG_2_REAL system_reset_common, EXC_STD, 0 + +#endif /* CONFIG_PPC_PSERIES */ EXC_COMMON_BEGIN(system_reset_common) /* @@ -185,15 +890,27 @@ EXC_COMMON_BEGIN(system_reset_common) mr r10,r1 ld r1,PACA_NMI_EMERG_SP(r13) subi r1,r1,INT_FRAME_SIZE - EXCEPTION_COMMON_NORET_STACK(PACA_EXNMI, 0x100, - system_reset, system_reset_exception, - ADD_NVGPRS;ADD_RECONCILE_NMI) + EXCEPTION_COMMON_STACK(PACA_EXNMI, 0x100) + bl save_nvgprs + /* + * Set IRQS_ALL_DISABLED unconditionally so arch_irqs_disabled does + * the right thing. We do not want to reconcile because that goes + * through irq tracing which we don't want in NMI. + * + * Save PACAIRQHAPPENED because some code will do a hard disable + * (e.g., xmon). So we want to restore this back to where it was + * when we return. DAR is unused in the stack, so save it there. + */ + li r10,IRQS_ALL_DISABLED + stb r10,PACAIRQSOFTMASK(r13) + lbz r10,PACAIRQHAPPENED(r13) + std r10,_DAR(r1) + + addi r3,r1,STACK_FRAME_OVERHEAD + bl system_reset_exception - /* This (and MCE) can be simplified with mtmsrd L=1 */ /* Clear MSR_RI before setting SRR0 and SRR1. */ - li r0,MSR_RI - mfmsr r9 - andc r9,r9,r0 + li r9,0 mtmsrd r9,1 /* @@ -211,52 +928,16 @@ EXC_COMMON_BEGIN(system_reset_common) ld r10,SOFTE(r1) stb r10,PACAIRQSOFTMASK(r13) - /* - * Keep below code in synch with MACHINE_CHECK_HANDLER_WINDUP. - * Should share common bits... - */ - - /* Move original SRR0 and SRR1 into the respective regs */ - ld r9,_MSR(r1) - mtspr SPRN_SRR1,r9 - ld r3,_NIP(r1) - mtspr SPRN_SRR0,r3 - ld r9,_CTR(r1) - mtctr r9 - ld r9,_XER(r1) - mtxer r9 - ld r9,_LINK(r1) - mtlr r9 - REST_GPR(0, r1) - REST_8GPRS(2, r1) - REST_GPR(10, r1) - ld r11,_CCR(r1) - mtcr r11 - REST_GPR(11, r1) - REST_2GPRS(12, r1) - /* restore original r1. */ - ld r1,GPR1(r1) + EXCEPTION_RESTORE_REGS EXC_STD RFI_TO_USER_OR_KERNEL -#ifdef CONFIG_PPC_PSERIES -/* - * Vectors for the FWNMI option. Share common code. - */ -TRAMP_REAL_BEGIN(system_reset_fwnmi) - SET_SCRATCH0(r13) /* save r13 */ - /* See comment at system_reset exception */ - EXCEPTION_PROLOG_NORI(PACA_EXNMI, system_reset_common, EXC_STD, - NOTEST, 0x100) -#endif /* CONFIG_PPC_PSERIES */ - EXC_REAL_BEGIN(machine_check, 0x200, 0x100) /* This is moved out of line as it can be patched by FW, but * some code path might still want to branch into the original * vector */ - SET_SCRATCH0(r13) /* save r13 */ - EXCEPTION_PROLOG_0(PACA_EXMC) + EXCEPTION_PROLOG_0 PACA_EXMC BEGIN_FTR_SECTION b machine_check_common_early FTR_SECTION_ELSE @@ -265,7 +946,7 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE) EXC_REAL_END(machine_check, 0x200, 0x100) EXC_VIRT_NONE(0x4200, 0x100) TRAMP_REAL_BEGIN(machine_check_common_early) - EXCEPTION_PROLOG_1(PACA_EXMC, NOTEST, 0x200) + EXCEPTION_PROLOG_1 EXC_STD, PACA_EXMC, 0, 0x200, 0, 0, 0 /* * Register contents: * R13 = PACA @@ -344,19 +1025,18 @@ END_FTR_SECTION_IFSET(CPU_FTR_HVMODE) TRAMP_REAL_BEGIN(machine_check_pSeries) .globl machine_check_fwnmi machine_check_fwnmi: - SET_SCRATCH0(r13) /* save r13 */ - EXCEPTION_PROLOG_0(PACA_EXMC) + EXCEPTION_PROLOG_0 PACA_EXMC BEGIN_FTR_SECTION b machine_check_common_early END_FTR_SECTION_IFCLR(CPU_FTR_HVMODE) machine_check_pSeries_0: - EXCEPTION_PROLOG_1(PACA_EXMC, KVMTEST_PR, 0x200) + EXCEPTION_PROLOG_1 EXC_STD, PACA_EXMC, 1, 0x200, 1, 1, 0 /* * MSR_RI is not enabled, because PACA_EXMC is being used, so a * nested machine check corrupts it. machine_check_common enables * MSR_RI. */ - EXCEPTION_PROLOG_2_NORI(machine_check_common, EXC_STD) + EXCEPTION_PROLOG_2_REAL machine_check_common, EXC_STD, 0 TRAMP_KVM_SKIP(PACA_EXMC, 0x200) @@ -365,11 +1045,7 @@ EXC_COMMON_BEGIN(machine_check_common) * Machine check is different because we use a different * save area: PACA_EXMC instead of PACA_EXGEN. */ - mfspr r10,SPRN_DAR - std r10,PACA_EXMC+EX_DAR(r13) - mfspr r10,SPRN_DSISR - stw r10,PACA_EXMC+EX_DSISR(r13) - EXCEPTION_PROLOG_COMMON(0x200, PACA_EXMC) + EXCEPTION_COMMON(PACA_EXMC, 0x200) FINISH_NAP RECONCILE_IRQ_STATE(r10, r11) ld r3,PACA_EXMC+EX_DAR(r13) @@ -386,34 +1062,13 @@ EXC_COMMON_BEGIN(machine_check_common) #define MACHINE_CHECK_HANDLER_WINDUP \ /* Clear MSR_RI before setting SRR0 and SRR1. */\ - li r0,MSR_RI; \ - mfmsr r9; /* get MSR value */ \ - andc r9,r9,r0; \ + li r9,0; \ mtmsrd r9,1; /* Clear MSR_RI */ \ - /* Move original SRR0 and SRR1 into the respective regs */ \ - ld r9,_MSR(r1); \ - mtspr SPRN_SRR1,r9; \ - ld r3,_NIP(r1); \ - mtspr SPRN_SRR0,r3; \ - ld r9,_CTR(r1); \ - mtctr r9; \ - ld r9,_XER(r1); \ - mtxer r9; \ - ld r9,_LINK(r1); \ - mtlr r9; \ - REST_GPR(0, r1); \ - REST_8GPRS(2, r1); \ - REST_GPR(10, r1); \ - ld r11,_CCR(r1); \ - mtcr r11; \ - /* Decrement paca->in_mce. */ \ + /* Decrement paca->in_mce now RI is clear. */ \ lhz r12,PACA_IN_MCE(r13); \ subi r12,r12,1; \ sth r12,PACA_IN_MCE(r13); \ - REST_GPR(11, r1); \ - REST_2GPRS(12, r1); \ - /* restore original r1. */ \ - ld r1,GPR1(r1) + EXCEPTION_RESTORE_REGS EXC_STD #ifdef CONFIG_PPC_P7_NAP /* @@ -472,10 +1127,10 @@ END_FTR_SECTION_IFCLR(CPU_FTR_HVMODE) * * Go back to nap/sleep/winkle mode again if (b) is true. */ - BEGIN_FTR_SECTION +BEGIN_FTR_SECTION rlwinm. r11,r12,47-31,30,31 bne machine_check_idle_common - END_FTR_SECTION_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206) +END_FTR_SECTION_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206) #endif /* @@ -557,8 +1212,7 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE) 9: /* Deliver the machine check to host kernel in V mode. */ MACHINE_CHECK_HANDLER_WINDUP - SET_SCRATCH0(r13) /* save r13 */ - EXCEPTION_PROLOG_0(PACA_EXMC) + EXCEPTION_PROLOG_0 PACA_EXMC b machine_check_pSeries_0 EXC_COMMON_BEGIN(unrecover_mce) @@ -582,33 +1236,18 @@ EXC_COMMON_BEGIN(mce_return) b . EXC_REAL_BEGIN(data_access, 0x300, 0x80) -SET_SCRATCH0(r13) /* save r13 */ -EXCEPTION_PROLOG_0(PACA_EXGEN) + EXCEPTION_PROLOG_0 PACA_EXGEN b tramp_real_data_access EXC_REAL_END(data_access, 0x300, 0x80) TRAMP_REAL_BEGIN(tramp_real_data_access) -EXCEPTION_PROLOG_1(PACA_EXGEN, KVMTEST_PR, 0x300) - /* - * DAR/DSISR must be read before setting MSR[RI], because - * a d-side MCE will clobber those registers so is not - * recoverable if they are live. - */ - mfspr r10,SPRN_DAR - mfspr r11,SPRN_DSISR - std r10,PACA_EXGEN+EX_DAR(r13) - stw r11,PACA_EXGEN+EX_DSISR(r13) -EXCEPTION_PROLOG_2(data_access_common, EXC_STD) + EXCEPTION_PROLOG_1 EXC_STD, PACA_EXGEN, 1, 0x300, 1, 1, 0 + EXCEPTION_PROLOG_2_REAL data_access_common, EXC_STD, 1 EXC_VIRT_BEGIN(data_access, 0x4300, 0x80) -SET_SCRATCH0(r13) /* save r13 */ -EXCEPTION_PROLOG_0(PACA_EXGEN) -EXCEPTION_PROLOG_1(PACA_EXGEN, NOTEST, 0x300) - mfspr r10,SPRN_DAR - mfspr r11,SPRN_DSISR - std r10,PACA_EXGEN+EX_DAR(r13) - stw r11,PACA_EXGEN+EX_DSISR(r13) -EXCEPTION_PROLOG_2_RELON(data_access_common, EXC_STD) + EXCEPTION_PROLOG_0 PACA_EXGEN + EXCEPTION_PROLOG_1 EXC_STD, PACA_EXGEN, 0, 0x300, 1, 1, 0 +EXCEPTION_PROLOG_2_VIRT data_access_common, EXC_STD EXC_VIRT_END(data_access, 0x4300, 0x80) TRAMP_KVM_SKIP(PACA_EXGEN, 0x300) @@ -620,7 +1259,7 @@ EXC_COMMON_BEGIN(data_access_common) * r9 - r13 are saved in paca->exgen. * EX_DAR and EX_DSISR have saved DAR/DSISR */ - EXCEPTION_PROLOG_COMMON(0x300, PACA_EXGEN) + EXCEPTION_COMMON(PACA_EXGEN, 0x300) RECONCILE_IRQ_STATE(r10, r11) ld r12,_MSR(r1) ld r3,PACA_EXGEN+EX_DAR(r13) @@ -636,30 +1275,24 @@ ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX) EXC_REAL_BEGIN(data_access_slb, 0x380, 0x80) -SET_SCRATCH0(r13) /* save r13 */ -EXCEPTION_PROLOG_0(PACA_EXSLB) + EXCEPTION_PROLOG_0 PACA_EXSLB b tramp_real_data_access_slb EXC_REAL_END(data_access_slb, 0x380, 0x80) TRAMP_REAL_BEGIN(tramp_real_data_access_slb) -EXCEPTION_PROLOG_1(PACA_EXSLB, KVMTEST_PR, 0x380) - mfspr r10,SPRN_DAR - std r10,PACA_EXSLB+EX_DAR(r13) -EXCEPTION_PROLOG_2(data_access_slb_common, EXC_STD) + EXCEPTION_PROLOG_1 EXC_STD, PACA_EXSLB, 1, 0x380, 1, 0, 0 + EXCEPTION_PROLOG_2_REAL data_access_slb_common, EXC_STD, 1 EXC_VIRT_BEGIN(data_access_slb, 0x4380, 0x80) -SET_SCRATCH0(r13) /* save r13 */ -EXCEPTION_PROLOG_0(PACA_EXSLB) -EXCEPTION_PROLOG_1(PACA_EXSLB, NOTEST, 0x380) - mfspr r10,SPRN_DAR - std r10,PACA_EXSLB+EX_DAR(r13) -EXCEPTION_PROLOG_2_RELON(data_access_slb_common, EXC_STD) + EXCEPTION_PROLOG_0 PACA_EXSLB + EXCEPTION_PROLOG_1 EXC_STD, PACA_EXSLB, 0, 0x380, 1, 0, 0 + EXCEPTION_PROLOG_2_VIRT data_access_slb_common, EXC_STD EXC_VIRT_END(data_access_slb, 0x4380, 0x80) TRAMP_KVM_SKIP(PACA_EXSLB, 0x380) EXC_COMMON_BEGIN(data_access_slb_common) - EXCEPTION_PROLOG_COMMON(0x380, PACA_EXSLB) + EXCEPTION_COMMON(PACA_EXSLB, 0x380) ld r4,PACA_EXSLB+EX_DAR(r13) std r4,_DAR(r1) addi r3,r1,STACK_FRAME_OVERHEAD @@ -689,7 +1322,7 @@ EXC_VIRT(instruction_access, 0x4400, 0x80, 0x400) TRAMP_KVM(PACA_EXGEN, 0x400) EXC_COMMON_BEGIN(instruction_access_common) - EXCEPTION_PROLOG_COMMON(0x400, PACA_EXGEN) + EXCEPTION_COMMON(PACA_EXGEN, 0x400) RECONCILE_IRQ_STATE(r10, r11) ld r12,_MSR(r1) ld r3,_NIP(r1) @@ -704,18 +1337,12 @@ MMU_FTR_SECTION_ELSE ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX) -EXC_REAL_BEGIN(instruction_access_slb, 0x480, 0x80) -EXCEPTION_PROLOG(PACA_EXSLB, instruction_access_slb_common, EXC_STD, KVMTEST_PR, 0x480); -EXC_REAL_END(instruction_access_slb, 0x480, 0x80) - -EXC_VIRT_BEGIN(instruction_access_slb, 0x4480, 0x80) -EXCEPTION_RELON_PROLOG(PACA_EXSLB, instruction_access_slb_common, EXC_STD, NOTEST, 0x480); -EXC_VIRT_END(instruction_access_slb, 0x4480, 0x80) - +__EXC_REAL(instruction_access_slb, 0x480, 0x80, PACA_EXSLB) +__EXC_VIRT(instruction_access_slb, 0x4480, 0x80, 0x480, PACA_EXSLB) TRAMP_KVM(PACA_EXSLB, 0x480) EXC_COMMON_BEGIN(instruction_access_slb_common) - EXCEPTION_PROLOG_COMMON(0x480, PACA_EXSLB) + EXCEPTION_COMMON(PACA_EXSLB, 0x480) ld r4,_NIP(r1) addi r3,r1,STACK_FRAME_OVERHEAD BEGIN_MMU_FTR_SECTION @@ -740,25 +1367,25 @@ ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX) EXC_REAL_BEGIN(hardware_interrupt, 0x500, 0x100) - .globl hardware_interrupt_hv; -hardware_interrupt_hv: - BEGIN_FTR_SECTION - MASKABLE_EXCEPTION_HV(0x500, hardware_interrupt_common, IRQS_DISABLED) - FTR_SECTION_ELSE - MASKABLE_EXCEPTION(0x500, hardware_interrupt_common, IRQS_DISABLED) - ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206) + EXCEPTION_PROLOG_0 PACA_EXGEN +BEGIN_FTR_SECTION + EXCEPTION_PROLOG_1 EXC_HV, PACA_EXGEN, 1, 0x500, 0, 0, IRQS_DISABLED + EXCEPTION_PROLOG_2_REAL hardware_interrupt_common, EXC_HV, 1 +FTR_SECTION_ELSE + EXCEPTION_PROLOG_1 EXC_STD, PACA_EXGEN, 1, 0x500, 0, 0, IRQS_DISABLED + EXCEPTION_PROLOG_2_REAL hardware_interrupt_common, EXC_STD, 1 +ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206) EXC_REAL_END(hardware_interrupt, 0x500, 0x100) EXC_VIRT_BEGIN(hardware_interrupt, 0x4500, 0x100) - .globl hardware_interrupt_relon_hv; -hardware_interrupt_relon_hv: - BEGIN_FTR_SECTION - MASKABLE_RELON_EXCEPTION_HV(0x500, hardware_interrupt_common, - IRQS_DISABLED) - FTR_SECTION_ELSE - __MASKABLE_RELON_EXCEPTION(0x500, hardware_interrupt_common, - EXC_STD, SOFTEN_TEST_PR, IRQS_DISABLED) - ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE) + EXCEPTION_PROLOG_0 PACA_EXGEN +BEGIN_FTR_SECTION + EXCEPTION_PROLOG_1 EXC_HV, PACA_EXGEN, 1, 0x500, 0, 0, IRQS_DISABLED + EXCEPTION_PROLOG_2_VIRT hardware_interrupt_common, EXC_HV +FTR_SECTION_ELSE + EXCEPTION_PROLOG_1 EXC_STD, PACA_EXGEN, 1, 0x500, 0, 0, IRQS_DISABLED + EXCEPTION_PROLOG_2_VIRT hardware_interrupt_common, EXC_STD +ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE) EXC_VIRT_END(hardware_interrupt, 0x4500, 0x100) TRAMP_KVM(PACA_EXGEN, 0x500) @@ -767,30 +1394,20 @@ EXC_COMMON_ASYNC(hardware_interrupt_common, 0x500, do_IRQ) EXC_REAL_BEGIN(alignment, 0x600, 0x100) -SET_SCRATCH0(r13) /* save r13 */ -EXCEPTION_PROLOG_0(PACA_EXGEN) -EXCEPTION_PROLOG_1(PACA_EXGEN, KVMTEST_PR, 0x600) - mfspr r10,SPRN_DAR - mfspr r11,SPRN_DSISR - std r10,PACA_EXGEN+EX_DAR(r13) - stw r11,PACA_EXGEN+EX_DSISR(r13) -EXCEPTION_PROLOG_2(alignment_common, EXC_STD) + EXCEPTION_PROLOG_0 PACA_EXGEN + EXCEPTION_PROLOG_1 EXC_STD, PACA_EXGEN, 1, 0x600, 1, 1, 0 + EXCEPTION_PROLOG_2_REAL alignment_common, EXC_STD, 1 EXC_REAL_END(alignment, 0x600, 0x100) EXC_VIRT_BEGIN(alignment, 0x4600, 0x100) -SET_SCRATCH0(r13) /* save r13 */ -EXCEPTION_PROLOG_0(PACA_EXGEN) -EXCEPTION_PROLOG_1(PACA_EXGEN, NOTEST, 0x600) - mfspr r10,SPRN_DAR - mfspr r11,SPRN_DSISR - std r10,PACA_EXGEN+EX_DAR(r13) - stw r11,PACA_EXGEN+EX_DSISR(r13) -EXCEPTION_PROLOG_2_RELON(alignment_common, EXC_STD) + EXCEPTION_PROLOG_0 PACA_EXGEN + EXCEPTION_PROLOG_1 EXC_STD, PACA_EXGEN, 0, 0x600, 1, 1, 0 + EXCEPTION_PROLOG_2_VIRT alignment_common, EXC_STD EXC_VIRT_END(alignment, 0x4600, 0x100) TRAMP_KVM(PACA_EXGEN, 0x600) EXC_COMMON_BEGIN(alignment_common) - EXCEPTION_PROLOG_COMMON(0x600, PACA_EXGEN) + EXCEPTION_COMMON(PACA_EXGEN, 0x600) ld r3,PACA_EXGEN+EX_DAR(r13) lwz r4,PACA_EXGEN+EX_DSISR(r13) std r3,_DAR(r1) @@ -814,21 +1431,25 @@ EXC_COMMON_BEGIN(program_check_common) * we switch to the emergency stack if we're taking a TM Bad Thing from * the kernel. */ - li r10,MSR_PR /* Build a mask of MSR_PR .. */ - oris r10,r10,0x200000@h /* .. and SRR1_PROGTM */ - and r10,r10,r12 /* Mask SRR1 with that. */ - srdi r10,r10,8 /* Shift it so we can compare */ - cmpldi r10,(0x200000 >> 8) /* .. with an immediate. */ - bne 1f /* If != go to normal path. */ - - /* SRR1 had PR=0 and SRR1_PROGTM=1, so use the emergency stack */ - andi. r10,r12,MSR_PR; /* Set CR0 correctly for label */ + + andi. r10,r12,MSR_PR + bne 2f /* If userspace, go normal path */ + + andis. r10,r12,(SRR1_PROGTM)@h + bne 1f /* If TM, emergency */ + + cmpdi r1,-INT_FRAME_SIZE /* check if r1 is in userspace */ + blt 2f /* normal path if not */ + + /* Use the emergency stack */ +1: andi. r10,r12,MSR_PR /* Set CR0 correctly for label */ /* 3 in EXCEPTION_PROLOG_COMMON */ mr r10,r1 /* Save r1 */ ld r1,PACAEMERGSP(r13) /* Use emergency stack */ subi r1,r1,INT_FRAME_SIZE /* alloc stack frame */ b 3f /* Jump into the macro !! */ -1: EXCEPTION_PROLOG_COMMON(0x700, PACA_EXGEN) +2: + EXCEPTION_COMMON(PACA_EXGEN, 0x700) bl save_nvgprs RECONCILE_IRQ_STATE(r10, r11) addi r3,r1,STACK_FRAME_OVERHEAD @@ -840,7 +1461,7 @@ EXC_REAL(fp_unavailable, 0x800, 0x100) EXC_VIRT(fp_unavailable, 0x4800, 0x100, 0x800) TRAMP_KVM(PACA_EXGEN, 0x800) EXC_COMMON_BEGIN(fp_unavailable_common) - EXCEPTION_PROLOG_COMMON(0x800, PACA_EXGEN) + EXCEPTION_COMMON(PACA_EXGEN, 0x800) bne 1f /* if from user, just load it up */ bl save_nvgprs RECONCILE_IRQ_STATE(r10, r11) @@ -932,6 +1553,7 @@ EXC_COMMON(trap_0b_common, 0xb00, unknown_exception) * without saving, though xer is not a good idea to use, as hardware may * interpret some bits so it may be costly to change them. */ +.macro SYSTEM_CALL virt #ifdef CONFIG_KVM_BOOK3S_64_HANDLER /* * There is a little bit of juggling to get syscall and hcall @@ -941,95 +1563,67 @@ EXC_COMMON(trap_0b_common, 0xb00, unknown_exception) * Userspace syscalls have already saved the PPR, hcalls must save * it before setting HMT_MEDIUM. */ -#define SYSCALL_KVMTEST \ - mtctr r13; \ - GET_PACA(r13); \ - std r10,PACA_EXGEN+EX_R10(r13); \ - INTERRUPT_TO_KERNEL; \ - KVMTEST_PR(0xc00); /* uses r10, branch to do_kvm_0xc00_system_call */ \ - HMT_MEDIUM; \ - mfctr r9; - + mtctr r13 + GET_PACA(r13) + std r10,PACA_EXGEN+EX_R10(r13) + INTERRUPT_TO_KERNEL + KVMTEST EXC_STD 0xc00 /* uses r10, branch to do_kvm_0xc00_system_call */ + mfctr r9 #else -#define SYSCALL_KVMTEST \ - HMT_MEDIUM; \ - mr r9,r13; \ - GET_PACA(r13); \ - INTERRUPT_TO_KERNEL; + mr r9,r13 + GET_PACA(r13) + INTERRUPT_TO_KERNEL #endif - -#define LOAD_SYSCALL_HANDLER(reg) \ - __LOAD_HANDLER(reg, system_call_common) - -/* - * After SYSCALL_KVMTEST, we reach here with PACA in r13, r13 in r9, - * and HMT_MEDIUM. - */ -#define SYSCALL_REAL \ - mfspr r11,SPRN_SRR0 ; \ - mfspr r12,SPRN_SRR1 ; \ - LOAD_SYSCALL_HANDLER(r10) ; \ - mtspr SPRN_SRR0,r10 ; \ - ld r10,PACAKMSR(r13) ; \ - mtspr SPRN_SRR1,r10 ; \ - RFI_TO_KERNEL ; \ - b . ; /* prevent speculative execution */ #ifdef CONFIG_PPC_FAST_ENDIAN_SWITCH -#define SYSCALL_FASTENDIAN_TEST \ -BEGIN_FTR_SECTION \ - cmpdi r0,0x1ebe ; \ - beq- 1f ; \ -END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE) \ - -#define SYSCALL_FASTENDIAN \ - /* Fast LE/BE switch system call */ \ -1: mfspr r12,SPRN_SRR1 ; \ - xori r12,r12,MSR_LE ; \ - mtspr SPRN_SRR1,r12 ; \ - mr r13,r9 ; \ - RFI_TO_USER ; /* return to userspace */ \ - b . ; /* prevent speculative execution */ -#else -#define SYSCALL_FASTENDIAN_TEST -#define SYSCALL_FASTENDIAN -#endif /* CONFIG_PPC_FAST_ENDIAN_SWITCH */ +BEGIN_FTR_SECTION + cmpdi r0,0x1ebe + beq- 1f +END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE) +#endif -#if defined(CONFIG_RELOCATABLE) - /* - * We can't branch directly so we do it via the CTR which - * is volatile across system calls. - */ -#define SYSCALL_VIRT \ - LOAD_SYSCALL_HANDLER(r10) ; \ - mtctr r10 ; \ - mfspr r11,SPRN_SRR0 ; \ - mfspr r12,SPRN_SRR1 ; \ - li r10,MSR_RI ; \ - mtmsrd r10,1 ; \ - bctr ; + /* We reach here with PACA in r13, r13 in r9. */ + mfspr r11,SPRN_SRR0 + mfspr r12,SPRN_SRR1 + + HMT_MEDIUM + + .if ! \virt + __LOAD_HANDLER(r10, system_call_common) + mtspr SPRN_SRR0,r10 + ld r10,PACAKMSR(r13) + mtspr SPRN_SRR1,r10 + RFI_TO_KERNEL + b . /* prevent speculative execution */ + .else + li r10,MSR_RI + mtmsrd r10,1 /* Set RI (EE=0) */ +#ifdef CONFIG_RELOCATABLE + __LOAD_HANDLER(r10, system_call_common) + mtctr r10 + bctr #else - /* We can branch directly */ -#define SYSCALL_VIRT \ - mfspr r11,SPRN_SRR0 ; \ - mfspr r12,SPRN_SRR1 ; \ - li r10,MSR_RI ; \ - mtmsrd r10,1 ; /* Set RI (EE=0) */ \ - b system_call_common ; + b system_call_common +#endif + .endif + +#ifdef CONFIG_PPC_FAST_ENDIAN_SWITCH + /* Fast LE/BE switch system call */ +1: mfspr r12,SPRN_SRR1 + xori r12,r12,MSR_LE + mtspr SPRN_SRR1,r12 + mr r13,r9 + RFI_TO_USER /* return to userspace */ + b . /* prevent speculative execution */ #endif +.endm EXC_REAL_BEGIN(system_call, 0xc00, 0x100) - SYSCALL_KVMTEST /* loads PACA into r13, and saves r13 to r9 */ - SYSCALL_FASTENDIAN_TEST - SYSCALL_REAL - SYSCALL_FASTENDIAN + SYSTEM_CALL 0 EXC_REAL_END(system_call, 0xc00, 0x100) EXC_VIRT_BEGIN(system_call, 0x4c00, 0x100) - SYSCALL_KVMTEST /* loads PACA into r13, and saves r13 to r9 */ - SYSCALL_FASTENDIAN_TEST - SYSCALL_VIRT - SYSCALL_FASTENDIAN + SYSTEM_CALL 1 EXC_VIRT_END(system_call, 0x4c00, 0x100) #ifdef CONFIG_KVM_BOOK3S_64_HANDLER @@ -1053,7 +1647,7 @@ TRAMP_KVM_BEGIN(do_kvm_0xc00) SET_SCRATCH0(r10) std r9,PACA_EXGEN+EX_R9(r13) mfcr r9 - KVM_HANDLER(PACA_EXGEN, EXC_STD, 0xc00) + KVM_HANDLER PACA_EXGEN, EXC_STD, 0xc00, 0 #endif @@ -1070,7 +1664,7 @@ EXC_COMMON_BEGIN(h_data_storage_common) std r10,PACA_EXGEN+EX_DAR(r13) mfspr r10,SPRN_HDSISR stw r10,PACA_EXGEN+EX_DSISR(r13) - EXCEPTION_PROLOG_COMMON(0xe00, PACA_EXGEN) + EXCEPTION_COMMON(PACA_EXGEN, 0xe00) bl save_nvgprs RECONCILE_IRQ_STATE(r10, r11) addi r3,r1,STACK_FRAME_OVERHEAD @@ -1104,65 +1698,55 @@ EXC_COMMON(emulation_assist_common, 0xe40, emulation_assist_interrupt) * first, and then eventaully from there to the trampoline to get into virtual * mode. */ -__EXC_REAL_OOL_HV_DIRECT(hmi_exception, 0xe60, 0x20, hmi_exception_early) -__TRAMP_REAL_OOL_MASKABLE_HV(hmi_exception, 0xe60, IRQS_DISABLED) +EXC_REAL_BEGIN(hmi_exception, 0xe60, 0x20) + EXCEPTION_PROLOG_0 PACA_EXGEN + b hmi_exception_early +EXC_REAL_END(hmi_exception, 0xe60, 0x20) EXC_VIRT_NONE(0x4e60, 0x20) TRAMP_KVM_HV(PACA_EXGEN, 0xe60) TRAMP_REAL_BEGIN(hmi_exception_early) - EXCEPTION_PROLOG_1(PACA_EXGEN, KVMTEST_HV, 0xe60) + EXCEPTION_PROLOG_1 EXC_HV, PACA_EXGEN, 1, 0xe60, 0, 0, 0 + mfctr r10 /* save ctr, even for !RELOCATABLE */ + BRANCH_TO_C000(r11, hmi_exception_early_common) + +EXC_COMMON_BEGIN(hmi_exception_early_common) + mtctr r10 /* Restore ctr */ + mfspr r11,SPRN_HSRR0 /* Save HSRR0 */ + mfspr r12,SPRN_HSRR1 /* Save HSRR1 */ mr r10,r1 /* Save r1 */ ld r1,PACAEMERGSP(r13) /* Use emergency stack for realmode */ subi r1,r1,INT_FRAME_SIZE /* alloc stack frame */ - mfspr r11,SPRN_HSRR0 /* Save HSRR0 */ - mfspr r12,SPRN_HSRR1 /* Save HSRR1 */ EXCEPTION_PROLOG_COMMON_1() /* We don't touch AMR here, we never go to virtual mode */ EXCEPTION_PROLOG_COMMON_2(PACA_EXGEN) EXCEPTION_PROLOG_COMMON_3(0xe60) addi r3,r1,STACK_FRAME_OVERHEAD - BRANCH_LINK_TO_FAR(DOTSYM(hmi_exception_realmode)) /* Function call ABI */ + bl hmi_exception_realmode cmpdi cr0,r3,0 - - /* Windup the stack. */ - /* Move original HSRR0 and HSRR1 into the respective regs */ - ld r9,_MSR(r1) - mtspr SPRN_HSRR1,r9 - ld r3,_NIP(r1) - mtspr SPRN_HSRR0,r3 - ld r9,_CTR(r1) - mtctr r9 - ld r9,_XER(r1) - mtxer r9 - ld r9,_LINK(r1) - mtlr r9 - REST_GPR(0, r1) - REST_8GPRS(2, r1) - REST_GPR(10, r1) - ld r11,_CCR(r1) - REST_2GPRS(12, r1) bne 1f - mtcr r11 - REST_GPR(11, r1) - ld r1,GPR1(r1) - HRFI_TO_USER_OR_KERNEL -1: mtcr r11 - REST_GPR(11, r1) - ld r1,GPR1(r1) + EXCEPTION_RESTORE_REGS EXC_HV + HRFI_TO_USER_OR_KERNEL +1: /* * Go to virtual mode and pull the HMI event information from * firmware. */ - .globl hmi_exception_after_realmode -hmi_exception_after_realmode: - SET_SCRATCH0(r13) - EXCEPTION_PROLOG_0(PACA_EXGEN) - b tramp_real_hmi_exception + EXCEPTION_RESTORE_REGS EXC_HV + EXCEPTION_PROLOG_0 PACA_EXGEN + EXCEPTION_PROLOG_1 EXC_HV, PACA_EXGEN, 1, 0xe60, 0, 0, IRQS_DISABLED + EXCEPTION_PROLOG_2_REAL hmi_exception_common, EXC_HV, 1 EXC_COMMON_BEGIN(hmi_exception_common) -EXCEPTION_COMMON(PACA_EXGEN, 0xe60, hmi_exception_common, handle_hmi_exception, - ret_from_except, FINISH_NAP;ADD_NVGPRS;ADD_RECONCILE;RUNLATCH_ON) + EXCEPTION_COMMON(PACA_EXGEN, 0xe60) + FINISH_NAP + bl save_nvgprs + RECONCILE_IRQ_STATE(r10, r11) + RUNLATCH_ON + addi r3,r1,STACK_FRAME_OVERHEAD + bl handle_hmi_exception + b ret_from_except EXC_REAL_OOL_MASKABLE_HV(h_doorbell, 0xe80, 0x20, IRQS_DISABLED) EXC_VIRT_OOL_MASKABLE_HV(h_doorbell, 0x4e80, 0x20, 0xe80, IRQS_DISABLED) @@ -1196,7 +1780,7 @@ EXC_REAL_OOL(altivec_unavailable, 0xf20, 0x20) EXC_VIRT_OOL(altivec_unavailable, 0x4f20, 0x20, 0xf20) TRAMP_KVM(PACA_EXGEN, 0xf20) EXC_COMMON_BEGIN(altivec_unavailable_common) - EXCEPTION_PROLOG_COMMON(0xf20, PACA_EXGEN) + EXCEPTION_COMMON(PACA_EXGEN, 0xf20) #ifdef CONFIG_ALTIVEC BEGIN_FTR_SECTION beq 1f @@ -1233,7 +1817,7 @@ EXC_REAL_OOL(vsx_unavailable, 0xf40, 0x20) EXC_VIRT_OOL(vsx_unavailable, 0x4f40, 0x20, 0xf40) TRAMP_KVM(PACA_EXGEN, 0xf40) EXC_COMMON_BEGIN(vsx_unavailable_common) - EXCEPTION_PROLOG_COMMON(0xf40, PACA_EXGEN) + EXCEPTION_COMMON(PACA_EXGEN, 0xf40) #ifdef CONFIG_VSX BEGIN_FTR_SECTION beq 1f @@ -1309,9 +1893,8 @@ EXC_REAL_NONE(0x1400, 0x100) EXC_VIRT_NONE(0x5400, 0x100) EXC_REAL_BEGIN(denorm_exception_hv, 0x1500, 0x100) - mtspr SPRN_SPRG_HSCRATCH0,r13 - EXCEPTION_PROLOG_0(PACA_EXGEN) - EXCEPTION_PROLOG_1(PACA_EXGEN, NOTEST, 0x1500) + EXCEPTION_PROLOG_0 PACA_EXGEN + EXCEPTION_PROLOG_1 EXC_HV, PACA_EXGEN, 0, 0x1500, 0, 0, 0 #ifdef CONFIG_PPC_DENORMALISATION mfspr r10,SPRN_HSRR1 @@ -1319,8 +1902,8 @@ EXC_REAL_BEGIN(denorm_exception_hv, 0x1500, 0x100) bne+ denorm_assist #endif - KVMTEST_HV(0x1500) - EXCEPTION_PROLOG_2(denorm_common, EXC_HV) + KVMTEST EXC_HV 0x1500 + EXCEPTION_PROLOG_2_REAL denorm_common, EXC_HV, 1 EXC_REAL_END(denorm_exception_hv, 0x1500, 0x100) #ifdef CONFIG_PPC_DENORMALISATION @@ -1346,12 +1929,11 @@ BEGIN_FTR_SECTION mtmsrd r10 sync -#define FMR2(n) fmr (n), (n) ; fmr n+1, n+1 -#define FMR4(n) FMR2(n) ; FMR2(n+2) -#define FMR8(n) FMR4(n) ; FMR4(n+4) -#define FMR16(n) FMR8(n) ; FMR8(n+8) -#define FMR32(n) FMR16(n) ; FMR16(n+16) - FMR32(0) + .Lreg=0 + .rept 32 + fmr .Lreg,.Lreg + .Lreg=.Lreg+1 + .endr FTR_SECTION_ELSE /* @@ -1363,12 +1945,11 @@ FTR_SECTION_ELSE mtmsrd r10 sync -#define XVCPSGNDP2(n) XVCPSGNDP(n,n,n) ; XVCPSGNDP(n+1,n+1,n+1) -#define XVCPSGNDP4(n) XVCPSGNDP2(n) ; XVCPSGNDP2(n+2) -#define XVCPSGNDP8(n) XVCPSGNDP4(n) ; XVCPSGNDP4(n+4) -#define XVCPSGNDP16(n) XVCPSGNDP8(n) ; XVCPSGNDP8(n+8) -#define XVCPSGNDP32(n) XVCPSGNDP16(n) ; XVCPSGNDP16(n+16) - XVCPSGNDP32(0) + .Lreg=0 + .rept 32 + XVCPSGNDP(.Lreg,.Lreg,.Lreg) + .Lreg=.Lreg+1 + .endr ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_206) @@ -1379,7 +1960,12 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S) * To denormalise we need to move a copy of the register to itself. * For POWER8 we need to do that for all 64 VSX registers */ - XVCPSGNDP32(32) + .Lreg=32 + .rept 32 + XVCPSGNDP(.Lreg,.Lreg,.Lreg) + .Lreg=.Lreg+1 + .endr + denorm_done: mfspr r11,SPRN_HSRR0 subi r11,r11,4 @@ -1442,7 +2028,7 @@ EXC_VIRT_NONE(0x5800, 0x100) std r12,PACA_EXGEN+EX_R12(r13); \ GET_SCRATCH0(r10); \ std r10,PACA_EXGEN+EX_R13(r13); \ - EXCEPTION_PROLOG_2(soft_nmi_common, _H) + EXCEPTION_PROLOG_2_REAL soft_nmi_common, _H, 1 /* * Branch to soft_nmi_interrupt using the emergency stack. The emergency @@ -1457,9 +2043,11 @@ EXC_COMMON_BEGIN(soft_nmi_common) mr r10,r1 ld r1,PACAEMERGSP(r13) subi r1,r1,INT_FRAME_SIZE - EXCEPTION_COMMON_NORET_STACK(PACA_EXGEN, 0x900, - system_reset, soft_nmi_interrupt, - ADD_NVGPRS;ADD_RECONCILE) + EXCEPTION_COMMON_STACK(PACA_EXGEN, 0x900) + bl save_nvgprs + RECONCILE_IRQ_STATE(r10, r11) + addi r3,r1,STACK_FRAME_OVERHEAD + bl soft_nmi_interrupt b ret_from_except #else /* CONFIG_PPC_WATCHDOG */ @@ -1477,35 +2065,50 @@ EXC_COMMON_BEGIN(soft_nmi_common) * - Else it is one of PACA_IRQ_MUST_HARD_MASK, so hard disable and return. * This is called with r10 containing the value to OR to the paca field. */ -#define MASKED_INTERRUPT(_H) \ -masked_##_H##interrupt: \ - std r11,PACA_EXGEN+EX_R11(r13); \ - lbz r11,PACAIRQHAPPENED(r13); \ - or r11,r11,r10; \ - stb r11,PACAIRQHAPPENED(r13); \ - cmpwi r10,PACA_IRQ_DEC; \ - bne 1f; \ - lis r10,0x7fff; \ - ori r10,r10,0xffff; \ - mtspr SPRN_DEC,r10; \ - b MASKED_DEC_HANDLER_LABEL; \ -1: andi. r10,r10,PACA_IRQ_MUST_HARD_MASK; \ - beq 2f; \ - mfspr r10,SPRN_##_H##SRR1; \ - xori r10,r10,MSR_EE; /* clear MSR_EE */ \ - mtspr SPRN_##_H##SRR1,r10; \ - ori r11,r11,PACA_IRQ_HARD_DIS; \ - stb r11,PACAIRQHAPPENED(r13); \ -2: /* done */ \ - mtcrf 0x80,r9; \ - std r1,PACAR1(r13); \ - ld r9,PACA_EXGEN+EX_R9(r13); \ - ld r10,PACA_EXGEN+EX_R10(r13); \ - ld r11,PACA_EXGEN+EX_R11(r13); \ - /* returns to kernel where r13 must be set up, so don't restore it */ \ - ##_H##RFI_TO_KERNEL; \ - b .; \ - MASKED_DEC_HANDLER(_H) +.macro MASKED_INTERRUPT hsrr + .if \hsrr +masked_Hinterrupt: + .else +masked_interrupt: + .endif + std r11,PACA_EXGEN+EX_R11(r13) + lbz r11,PACAIRQHAPPENED(r13) + or r11,r11,r10 + stb r11,PACAIRQHAPPENED(r13) + cmpwi r10,PACA_IRQ_DEC + bne 1f + lis r10,0x7fff + ori r10,r10,0xffff + mtspr SPRN_DEC,r10 + b MASKED_DEC_HANDLER_LABEL +1: andi. r10,r10,PACA_IRQ_MUST_HARD_MASK + beq 2f + .if \hsrr + mfspr r10,SPRN_HSRR1 + xori r10,r10,MSR_EE /* clear MSR_EE */ + mtspr SPRN_HSRR1,r10 + .else + mfspr r10,SPRN_SRR1 + xori r10,r10,MSR_EE /* clear MSR_EE */ + mtspr SPRN_SRR1,r10 + .endif + ori r11,r11,PACA_IRQ_HARD_DIS + stb r11,PACAIRQHAPPENED(r13) +2: /* done */ + mtcrf 0x80,r9 + std r1,PACAR1(r13) + ld r9,PACA_EXGEN+EX_R9(r13) + ld r10,PACA_EXGEN+EX_R10(r13) + ld r11,PACA_EXGEN+EX_R11(r13) + /* returns to kernel where r13 must be set up, so don't restore it */ + .if \hsrr + HRFI_TO_KERNEL + .else + RFI_TO_KERNEL + .endif + b . + MASKED_DEC_HANDLER(\hsrr\()) +.endm TRAMP_REAL_BEGIN(stf_barrier_fallback) std r9,PACA_EXRFI+EX_R9(r13) @@ -1612,8 +2215,8 @@ TRAMP_REAL_BEGIN(hrfi_flush_fallback) * cannot reach these if they are put there. */ USE_FIXED_SECTION(virt_trampolines) - MASKED_INTERRUPT() - MASKED_INTERRUPT(H) + MASKED_INTERRUPT EXC_STD + MASKED_INTERRUPT EXC_HV #ifdef CONFIG_KVM_BOOK3S_64_HANDLER TRAMP_REAL_BEGIN(kvmppc_skip_interrupt) @@ -1746,7 +2349,7 @@ handle_page_fault: addi r3,r1,STACK_FRAME_OVERHEAD bl do_page_fault cmpdi r3,0 - beq+ 12f + beq+ ret_from_except_lite bl save_nvgprs mr r5,r3 addi r3,r1,STACK_FRAME_OVERHEAD @@ -1761,7 +2364,12 @@ handle_dabr_fault: ld r5,_DSISR(r1) addi r3,r1,STACK_FRAME_OVERHEAD bl do_break -12: b ret_from_except_lite + /* + * do_break() may have changed the NV GPRS while handling a breakpoint. + * If so, we need to restore them with their updated values. Don't use + * ret_from_except_lite here. + */ + b ret_from_except #ifdef CONFIG_PPC_BOOK3S_64 @@ -1791,67 +2399,6 @@ handle_dabr_fault: b ret_from_except /* - * Here we have detected that the kernel stack pointer is bad. - * R9 contains the saved CR, r13 points to the paca, - * r10 contains the (bad) kernel stack pointer, - * r11 and r12 contain the saved SRR0 and SRR1. - * We switch to using an emergency stack, save the registers there, - * and call kernel_bad_stack(), which panics. - */ -bad_stack: - ld r1,PACAEMERGSP(r13) - subi r1,r1,64+INT_FRAME_SIZE - std r9,_CCR(r1) - std r10,GPR1(r1) - std r11,_NIP(r1) - std r12,_MSR(r1) - mfspr r11,SPRN_DAR - mfspr r12,SPRN_DSISR - std r11,_DAR(r1) - std r12,_DSISR(r1) - mflr r10 - mfctr r11 - mfxer r12 - std r10,_LINK(r1) - std r11,_CTR(r1) - std r12,_XER(r1) - SAVE_GPR(0,r1) - SAVE_GPR(2,r1) - ld r10,EX_R3(r3) - std r10,GPR3(r1) - SAVE_GPR(4,r1) - SAVE_4GPRS(5,r1) - ld r9,EX_R9(r3) - ld r10,EX_R10(r3) - SAVE_2GPRS(9,r1) - ld r9,EX_R11(r3) - ld r10,EX_R12(r3) - ld r11,EX_R13(r3) - std r9,GPR11(r1) - std r10,GPR12(r1) - std r11,GPR13(r1) -BEGIN_FTR_SECTION - ld r10,EX_CFAR(r3) - std r10,ORIG_GPR3(r1) -END_FTR_SECTION_IFSET(CPU_FTR_CFAR) - SAVE_8GPRS(14,r1) - SAVE_10GPRS(22,r1) - lhz r12,PACA_TRAP_SAVE(r13) - std r12,_TRAP(r1) - addi r11,r1,INT_FRAME_SIZE - std r11,0(r1) - li r12,0 - std r12,0(r11) - ld r2,PACATOC(r13) - ld r11,exception_marker@toc(r2) - std r12,RESULT(r1) - std r11,STACK_FRAME_OVERHEAD-16(r1) -1: addi r3,r1,STACK_FRAME_OVERHEAD - bl kernel_bad_stack - b 1b -_ASM_NOKPROBE_SYMBOL(bad_stack); - -/* * When doorbell is triggered from system reset wakeup, the message is * not cleared, so it would fire again when EE is enabled. * diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S index b5a5c6896019..91d297e696dd 100644 --- a/arch/powerpc/kernel/head_64.S +++ b/arch/powerpc/kernel/head_64.S @@ -900,6 +900,7 @@ p_toc: .8byte __toc_start + 0x8000 - 0b /* * This is where the main kernel code starts. */ +__REF start_here_multiplatform: /* set up the TOC */ bl relative_toc @@ -975,6 +976,7 @@ start_here_multiplatform: RFI b . /* prevent speculative execution */ + .previous /* This is where all platforms converge execution */ start_here_common: diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c index a293a53b4365..c8d1fa2e9d53 100644 --- a/arch/powerpc/kernel/hw_breakpoint.c +++ b/arch/powerpc/kernel/hw_breakpoint.c @@ -366,59 +366,3 @@ void hw_breakpoint_pmu_read(struct perf_event *bp) { /* TODO */ } - -bool dawr_force_enable; -EXPORT_SYMBOL_GPL(dawr_force_enable); - -static ssize_t dawr_write_file_bool(struct file *file, - const char __user *user_buf, - size_t count, loff_t *ppos) -{ - struct arch_hw_breakpoint null_brk = {0, 0, 0}; - size_t rc; - - /* Send error to user if they hypervisor won't allow us to write DAWR */ - if ((!dawr_force_enable) && - (firmware_has_feature(FW_FEATURE_LPAR)) && - (set_dawr(&null_brk) != H_SUCCESS)) - return -1; - - rc = debugfs_write_file_bool(file, user_buf, count, ppos); - if (rc) - return rc; - - /* If we are clearing, make sure all CPUs have the DAWR cleared */ - if (!dawr_force_enable) - smp_call_function((smp_call_func_t)set_dawr, &null_brk, 0); - - return rc; -} - -static const struct file_operations dawr_enable_fops = { - .read = debugfs_read_file_bool, - .write = dawr_write_file_bool, - .open = simple_open, - .llseek = default_llseek, -}; - -static int __init dawr_force_setup(void) -{ - dawr_force_enable = false; - - if (cpu_has_feature(CPU_FTR_DAWR)) { - /* Don't setup sysfs file for user control on P8 */ - dawr_force_enable = true; - return 0; - } - - if (PVR_VER(mfspr(SPRN_PVR)) == PVR_POWER9) { - /* Turn DAWR off by default, but allow admin to turn it on */ - dawr_force_enable = false; - debugfs_create_file_unsafe("dawr_enable_dangerous", 0600, - powerpc_debugfs_root, - &dawr_force_enable, - &dawr_enable_fops); - } - return 0; -} -arch_initcall(dawr_force_setup); diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index bc68c53af67c..5645bc9cbc09 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -255,7 +255,7 @@ notrace void arch_local_irq_restore(unsigned long mask) irq_happened = get_irq_happened(); if (!irq_happened) { #ifdef CONFIG_PPC_IRQ_SOFT_MASK_DEBUG - WARN_ON(!(mfmsr() & MSR_EE)); + WARN_ON_ONCE(!(mfmsr() & MSR_EE)); #endif return; } @@ -268,7 +268,7 @@ notrace void arch_local_irq_restore(unsigned long mask) */ if (!(irq_happened & PACA_IRQ_HARD_DIS)) { #ifdef CONFIG_PPC_IRQ_SOFT_MASK_DEBUG - WARN_ON(!(mfmsr() & MSR_EE)); + WARN_ON_ONCE(!(mfmsr() & MSR_EE)); #endif __hard_irq_disable(); #ifdef CONFIG_PPC_IRQ_SOFT_MASK_DEBUG @@ -279,7 +279,7 @@ notrace void arch_local_irq_restore(unsigned long mask) * warn if we are wrong. Only do that when IRQ tracing * is enabled as mfmsr() can be costly. */ - if (WARN_ON(mfmsr() & MSR_EE)) + if (WARN_ON_ONCE(mfmsr() & MSR_EE)) __hard_irq_disable(); #endif } diff --git a/arch/powerpc/kernel/mce_power.c b/arch/powerpc/kernel/mce_power.c index e39536aad30d..a814d2dfb5b0 100644 --- a/arch/powerpc/kernel/mce_power.c +++ b/arch/powerpc/kernel/mce_power.c @@ -82,8 +82,7 @@ static void flush_erat(void) return; } #endif - /* PPC_INVALIDATE_ERAT can only be used on ISA v3 and newer */ - asm volatile(PPC_INVALIDATE_ERAT : : :"memory"); + asm volatile(PPC_ISA_3_0_INVALIDATE_ERAT : : :"memory"); } #define MCE_FLUSH_SLB 1 diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S index 1ad4089dd110..b55a7b4cb543 100644 --- a/arch/powerpc/kernel/misc_64.S +++ b/arch/powerpc/kernel/misc_64.S @@ -110,58 +110,6 @@ _ASM_NOKPROBE_SYMBOL(flush_icache_range) EXPORT_SYMBOL(flush_icache_range) /* - * Like above, but only do the D-cache. - * - * flush_dcache_range(unsigned long start, unsigned long stop) - * - * flush all bytes from start to stop-1 inclusive - */ -_GLOBAL_TOC(flush_dcache_range) - -/* - * Flush the data cache to memory - * - * Different systems have different cache line sizes - */ - ld r10,PPC64_CACHES@toc(r2) - lwz r7,DCACHEL1BLOCKSIZE(r10) /* Get dcache block size */ - addi r5,r7,-1 - andc r6,r3,r5 /* round low to line bdy */ - subf r8,r6,r4 /* compute length */ - add r8,r8,r5 /* ensure we get enough */ - lwz r9,DCACHEL1LOGBLOCKSIZE(r10) /* Get log-2 of dcache block size */ - srw. r8,r8,r9 /* compute line count */ - beqlr /* nothing to do? */ - mtctr r8 -0: dcbst 0,r6 - add r6,r6,r7 - bdnz 0b - sync - blr -EXPORT_SYMBOL(flush_dcache_range) - -_GLOBAL(flush_inval_dcache_range) - ld r10,PPC64_CACHES@toc(r2) - lwz r7,DCACHEL1BLOCKSIZE(r10) /* Get dcache block size */ - addi r5,r7,-1 - andc r6,r3,r5 /* round low to line bdy */ - subf r8,r6,r4 /* compute length */ - add r8,r8,r5 /* ensure we get enough */ - lwz r9,DCACHEL1LOGBLOCKSIZE(r10)/* Get log-2 of dcache block size */ - srw. r8,r8,r9 /* compute line count */ - beqlr /* nothing to do? */ - sync - isync - mtctr r8 -0: dcbf 0,r6 - add r6,r6,r7 - bdnz 0b - sync - isync - blr - - -/* * Flush a particular page from the data cache to RAM. * Note: this is necessary because the instruction cache does *not* * snoop from the data cache. diff --git a/arch/powerpc/kernel/module_32.c b/arch/powerpc/kernel/module_32.c index 991d396fb50d..d7134c614c16 100644 --- a/arch/powerpc/kernel/module_32.c +++ b/arch/powerpc/kernel/module_32.c @@ -160,10 +160,12 @@ int module_frob_arch_sections(Elf32_Ehdr *hdr, static inline int entry_matches(struct ppc_plt_entry *entry, Elf32_Addr val) { - if (entry->jump[0] == 0x3d800000 + ((val + 0x8000) >> 16) - && entry->jump[1] == 0x398c0000 + (val & 0xffff)) - return 1; - return 0; + if (entry->jump[0] != (PPC_INST_ADDIS | __PPC_RT(R12) | PPC_HA(val))) + return 0; + if (entry->jump[1] != (PPC_INST_ADDI | __PPC_RT(R12) | __PPC_RA(R12) | + PPC_LO(val))) + return 0; + return 1; } /* Set up a trampoline in the PLT to bounce us to the distant function */ @@ -188,10 +190,16 @@ static uint32_t do_plt_call(void *location, entry++; } - entry->jump[0] = 0x3d800000+((val+0x8000)>>16); /* lis r12,sym@ha */ - entry->jump[1] = 0x398c0000 + (val&0xffff); /* addi r12,r12,sym@l*/ - entry->jump[2] = 0x7d8903a6; /* mtctr r12 */ - entry->jump[3] = 0x4e800420; /* bctr */ + /* + * lis r12, sym@ha + * addi r12, r12, sym@l + * mtctr r12 + * bctr + */ + entry->jump[0] = PPC_INST_ADDIS | __PPC_RT(R12) | PPC_HA(val); + entry->jump[1] = PPC_INST_ADDI | __PPC_RT(R12) | __PPC_RA(R12) | PPC_LO(val); + entry->jump[2] = PPC_INST_MTCTR | __PPC_RS(R12); + entry->jump[3] = PPC_INST_BCTR; pr_debug("Initialized plt for 0x%x at %p\n", val, entry); return (uint32_t)entry; diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c index a93b10c48000..007606a48fd9 100644 --- a/arch/powerpc/kernel/module_64.c +++ b/arch/powerpc/kernel/module_64.c @@ -121,20 +121,27 @@ struct ppc64_stub_entry * the stub, but it's significantly shorter to put these values at the * end of the stub code, and patch the stub address (32-bits relative * to the TOC ptr, r2) into the stub. + * + * addis r11,r2, <high> + * addi r11,r11, <low> + * std r2,R2_STACK_OFFSET(r1) + * ld r12,32(r11) + * ld r2,40(r11) + * mtctr r12 + * bctr */ - static u32 ppc64_stub_insns[] = { - 0x3d620000, /* addis r11,r2, <high> */ - 0x396b0000, /* addi r11,r11, <low> */ + PPC_INST_ADDIS | __PPC_RT(R11) | __PPC_RA(R2), + PPC_INST_ADDI | __PPC_RT(R11) | __PPC_RA(R11), /* Save current r2 value in magic place on the stack. */ - 0xf8410000|R2_STACK_OFFSET, /* std r2,R2_STACK_OFFSET(r1) */ - 0xe98b0020, /* ld r12,32(r11) */ + PPC_INST_STD | __PPC_RS(R2) | __PPC_RA(R1) | R2_STACK_OFFSET, + PPC_INST_LD | __PPC_RT(R12) | __PPC_RA(R11) | 32, #ifdef PPC64_ELF_ABI_v1 /* Set up new r2 from function descriptor */ - 0xe84b0028, /* ld r2,40(r11) */ + PPC_INST_LD | __PPC_RT(R2) | __PPC_RA(R11) | 40, #endif - 0x7d8903a6, /* mtctr r12 */ - 0x4e800420 /* bctr */ + PPC_INST_MTCTR | __PPC_RS(R12), + PPC_INST_BCTR, }; #ifdef CONFIG_DYNAMIC_FTRACE @@ -388,13 +395,6 @@ static inline unsigned long my_r2(const Elf64_Shdr *sechdrs, struct module *me) return (sechdrs[me->arch.toc_section].sh_addr & ~0xfful) + 0x8000; } -/* Both low and high 16 bits are added as SIGNED additions, so if low - 16 bits has high bit set, high 16 bits must be adjusted. These - macros do that (stolen from binutils). */ -#define PPC_LO(v) ((v) & 0xffff) -#define PPC_HI(v) (((v) >> 16) & 0xffff) -#define PPC_HA(v) PPC_HI ((v) + 0x8000) - /* Patch stub to reference function and correct r2 value. */ static inline int create_stub(const Elf64_Shdr *sechdrs, struct ppc64_stub_entry *entry, @@ -699,18 +699,21 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, * ld r2, ...(r12) * add r2, r2, r12 */ - if ((((uint32_t *)location)[0] & ~0xfffc) - != 0xe84c0000) + if ((((uint32_t *)location)[0] & ~0xfffc) != + (PPC_INST_LD | __PPC_RT(R2) | __PPC_RA(R12))) break; - if (((uint32_t *)location)[1] != 0x7c426214) + if (((uint32_t *)location)[1] != + (PPC_INST_ADD | __PPC_RT(R2) | __PPC_RA(R2) | __PPC_RB(R12))) break; /* * If found, replace it with: * addis r2, r12, (.TOC.-func)@ha - * addi r2, r12, (.TOC.-func)@l + * addi r2, r2, (.TOC.-func)@l */ - ((uint32_t *)location)[0] = 0x3c4c0000 + PPC_HA(value); - ((uint32_t *)location)[1] = 0x38420000 + PPC_LO(value); + ((uint32_t *)location)[0] = PPC_INST_ADDIS | __PPC_RT(R2) | + __PPC_RA(R12) | PPC_HA(value); + ((uint32_t *)location)[1] = PPC_INST_ADDI | __PPC_RT(R2) | + __PPC_RA(R2) | PPC_LO(value); break; case R_PPC64_REL16_HA: @@ -764,12 +767,19 @@ static unsigned long create_ftrace_stub(const Elf64_Shdr *sechdrs, { struct ppc64_stub_entry *entry; unsigned int i, num_stubs; + /* + * ld r12,PACATOC(r13) + * addis r12,r12,<high> + * addi r12,r12,<low> + * mtctr r12 + * bctr + */ static u32 stub_insns[] = { - 0xe98d0000 | PACATOC, /* ld r12,PACATOC(r13) */ - 0x3d8c0000, /* addis r12,r12,<high> */ - 0x398c0000, /* addi r12,r12,<low> */ - 0x7d8903a6, /* mtctr r12 */ - 0x4e800420, /* bctr */ + PPC_INST_LD | __PPC_RT(R12) | __PPC_RA(R13) | PACATOC, + PPC_INST_ADDIS | __PPC_RT(R12) | __PPC_RA(R12), + PPC_INST_ADDI | __PPC_RT(R12) | __PPC_RA(R12), + PPC_INST_MTCTR | __PPC_RS(R12), + PPC_INST_BCTR, }; long reladdr; diff --git a/arch/powerpc/kernel/pci_of_scan.c b/arch/powerpc/kernel/pci_of_scan.c index 24522aa37665..409c6c1beabf 100644 --- a/arch/powerpc/kernel/pci_of_scan.c +++ b/arch/powerpc/kernel/pci_of_scan.c @@ -42,6 +42,8 @@ unsigned int pci_parse_of_flags(u32 addr0, int bridge) if (addr0 & 0x02000000) { flags = IORESOURCE_MEM | PCI_BASE_ADDRESS_SPACE_MEMORY; flags |= (addr0 >> 22) & PCI_BASE_ADDRESS_MEM_TYPE_64; + if (flags & PCI_BASE_ADDRESS_MEM_TYPE_64) + flags |= IORESOURCE_MEM_64; flags |= (addr0 >> 28) & PCI_BASE_ADDRESS_MEM_TYPE_1M; if (addr0 & 0x40000000) flags |= IORESOURCE_PREFETCH @@ -77,10 +79,16 @@ static void of_pci_parse_addrs(struct device_node *node, struct pci_dev *dev) const __be32 *addrs; u32 i; int proplen; + bool mark_unset = false; addrs = of_get_property(node, "assigned-addresses", &proplen); - if (!addrs) - return; + if (!addrs || !proplen) { + addrs = of_get_property(node, "reg", &proplen); + if (!addrs || !proplen) + return; + mark_unset = true; + } + pr_debug(" parse addresses (%d bytes) @ %p\n", proplen, addrs); for (; proplen >= 20; proplen -= 20, addrs += 5) { flags = pci_parse_of_flags(of_read_number(addrs, 1), 0); @@ -105,6 +113,8 @@ static void of_pci_parse_addrs(struct device_node *node, struct pci_dev *dev) continue; } res->flags = flags; + if (mark_unset) + res->flags |= IORESOURCE_UNSET; res->name = pci_name(dev); region.start = base; region.end = base + size - 1; diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index b448b0938299..8fc4de0d22b4 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -793,34 +793,6 @@ static inline int set_dabr(struct arch_hw_breakpoint *brk) return __set_dabr(dabr, dabrx); } -int set_dawr(struct arch_hw_breakpoint *brk) -{ - unsigned long dawr, dawrx, mrd; - - dawr = brk->address; - - dawrx = (brk->type & (HW_BRK_TYPE_READ | HW_BRK_TYPE_WRITE)) \ - << (63 - 58); //* read/write bits */ - dawrx |= ((brk->type & (HW_BRK_TYPE_TRANSLATE)) >> 2) \ - << (63 - 59); //* translate */ - dawrx |= (brk->type & (HW_BRK_TYPE_PRIV_ALL)) \ - >> 3; //* PRIM bits */ - /* dawr length is stored in field MDR bits 48:53. Matches range in - doublewords (64 bits) baised by -1 eg. 0b000000=1DW and - 0b111111=64DW. - brk->len is in bytes. - This aligns up to double word size, shifts and does the bias. - */ - mrd = ((brk->len + 7) >> 3) - 1; - dawrx |= (mrd & 0x3f) << (63 - 53); - - if (ppc_md.set_dawr) - return ppc_md.set_dawr(dawr, dawrx); - mtspr(SPRN_DAWR, dawr); - mtspr(SPRN_DAWRX, dawrx); - return 0; -} - void __set_breakpoint(struct arch_hw_breakpoint *brk) { memcpy(this_cpu_ptr(¤t_brk), brk, sizeof(*brk)); diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index ed446b7ea164..514707ef6779 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -168,6 +168,7 @@ static unsigned long __prombss prom_tce_alloc_end; #ifdef CONFIG_PPC_PSERIES static bool __prombss prom_radix_disable; +static bool __prombss prom_xive_disable; #endif struct platform_support { @@ -804,6 +805,12 @@ static void __init early_cmdline_parse(void) } if (prom_radix_disable) prom_debug("Radix disabled from cmdline\n"); + + opt = prom_strstr(prom_cmd_line, "xive=off"); + if (opt) { + prom_xive_disable = true; + prom_debug("XIVE disabled from cmdline\n"); + } #endif /* CONFIG_PPC_PSERIES */ } @@ -1212,10 +1219,17 @@ static void __init prom_parse_xive_model(u8 val, switch (val) { case OV5_FEAT(OV5_XIVE_EITHER): /* Either Available */ prom_debug("XIVE - either mode supported\n"); - support->xive = true; + support->xive = !prom_xive_disable; break; case OV5_FEAT(OV5_XIVE_EXPLOIT): /* Only Exploitation mode */ prom_debug("XIVE - exploitation mode supported\n"); + if (prom_xive_disable) { + /* + * If we __have__ to do XIVE, we're better off ignoring + * the command line rather than not booting. + */ + prom_printf("WARNING: Ignoring cmdline option xive=off\n"); + } support->xive = true; break; case OV5_FEAT(OV5_XIVE_LEGACY): /* Only Legacy mode */ @@ -1562,9 +1576,6 @@ static void __init reserve_mem(u64 base, u64 size) static void __init prom_init_mem(void) { phandle node; -#ifdef DEBUG_PROM - char *path; -#endif char type[64]; unsigned int plen; cell_t *p, *endp; @@ -1586,9 +1597,6 @@ static void __init prom_init_mem(void) prom_debug("root_size_cells: %x\n", rsc); prom_debug("scanning memory:\n"); -#ifdef DEBUG_PROM - path = prom_scratch; -#endif for (node = 0; prom_next_node(&node); ) { type[0] = 0; @@ -1613,9 +1621,10 @@ static void __init prom_init_mem(void) endp = p + (plen / sizeof(cell_t)); #ifdef DEBUG_PROM - memset(path, 0, sizeof(prom_scratch)); - call_prom("package-to-path", 3, 1, node, path, sizeof(prom_scratch) - 1); - prom_debug(" node %s :\n", path); + memset(prom_scratch, 0, sizeof(prom_scratch)); + call_prom("package-to-path", 3, 1, node, prom_scratch, + sizeof(prom_scratch) - 1); + prom_debug(" node %s :\n", prom_scratch); #endif /* DEBUG_PROM */ while ((endp - p) >= (rac + rsc)) { diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c index 0ab4c72515c4..5faf0a64c92b 100644 --- a/arch/powerpc/kernel/rtas.c +++ b/arch/powerpc/kernel/rtas.c @@ -980,10 +980,9 @@ int rtas_ibm_suspend_me(u64 handle) cpu_hotplug_disable(); /* Check if we raced with a CPU-Offline Operation */ - if (unlikely(!cpumask_equal(cpu_present_mask, cpu_online_mask))) { - pr_err("%s: Raced against a concurrent CPU-Offline\n", - __func__); - atomic_set(&data.error, -EBUSY); + if (!cpumask_equal(cpu_present_mask, cpu_online_mask)) { + pr_info("%s: Raced against a concurrent CPU-Offline\n", __func__); + atomic_set(&data.error, -EAGAIN); goto out_hotplug_enable; } diff --git a/arch/powerpc/kernel/swsusp_32.S b/arch/powerpc/kernel/swsusp_32.S index 7a919e9a3400..cbdf86228eaa 100644 --- a/arch/powerpc/kernel/swsusp_32.S +++ b/arch/powerpc/kernel/swsusp_32.S @@ -25,11 +25,19 @@ #define SL_IBAT2 0x48 #define SL_DBAT3 0x50 #define SL_IBAT3 0x58 -#define SL_TB 0x60 -#define SL_R2 0x68 -#define SL_CR 0x6c -#define SL_LR 0x70 -#define SL_R12 0x74 /* r12 to r31 */ +#define SL_DBAT4 0x60 +#define SL_IBAT4 0x68 +#define SL_DBAT5 0x70 +#define SL_IBAT5 0x78 +#define SL_DBAT6 0x80 +#define SL_IBAT6 0x88 +#define SL_DBAT7 0x90 +#define SL_IBAT7 0x98 +#define SL_TB 0xa0 +#define SL_R2 0xa8 +#define SL_CR 0xac +#define SL_LR 0xb0 +#define SL_R12 0xb4 /* r12 to r31 */ #define SL_SIZE (SL_R12 + 80) .section .data @@ -114,6 +122,41 @@ _GLOBAL(swsusp_arch_suspend) mfibatl r4,3 stw r4,SL_IBAT3+4(r11) +BEGIN_MMU_FTR_SECTION + mfspr r4,SPRN_DBAT4U + stw r4,SL_DBAT4(r11) + mfspr r4,SPRN_DBAT4L + stw r4,SL_DBAT4+4(r11) + mfspr r4,SPRN_DBAT5U + stw r4,SL_DBAT5(r11) + mfspr r4,SPRN_DBAT5L + stw r4,SL_DBAT5+4(r11) + mfspr r4,SPRN_DBAT6U + stw r4,SL_DBAT6(r11) + mfspr r4,SPRN_DBAT6L + stw r4,SL_DBAT6+4(r11) + mfspr r4,SPRN_DBAT7U + stw r4,SL_DBAT7(r11) + mfspr r4,SPRN_DBAT7L + stw r4,SL_DBAT7+4(r11) + mfspr r4,SPRN_IBAT4U + stw r4,SL_IBAT4(r11) + mfspr r4,SPRN_IBAT4L + stw r4,SL_IBAT4+4(r11) + mfspr r4,SPRN_IBAT5U + stw r4,SL_IBAT5(r11) + mfspr r4,SPRN_IBAT5L + stw r4,SL_IBAT5+4(r11) + mfspr r4,SPRN_IBAT6U + stw r4,SL_IBAT6(r11) + mfspr r4,SPRN_IBAT6L + stw r4,SL_IBAT6+4(r11) + mfspr r4,SPRN_IBAT7U + stw r4,SL_IBAT7(r11) + mfspr r4,SPRN_IBAT7L + stw r4,SL_IBAT7+4(r11) +END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS) + #if 0 /* Backup various CPU config stuffs */ bl __save_cpu_setup @@ -279,27 +322,41 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) mtibatu 3,r4 lwz r4,SL_IBAT3+4(r11) mtibatl 3,r4 -#endif - BEGIN_MMU_FTR_SECTION - li r4,0 + lwz r4,SL_DBAT4(r11) mtspr SPRN_DBAT4U,r4 + lwz r4,SL_DBAT4+4(r11) mtspr SPRN_DBAT4L,r4 + lwz r4,SL_DBAT5(r11) mtspr SPRN_DBAT5U,r4 + lwz r4,SL_DBAT5+4(r11) mtspr SPRN_DBAT5L,r4 + lwz r4,SL_DBAT6(r11) mtspr SPRN_DBAT6U,r4 + lwz r4,SL_DBAT6+4(r11) mtspr SPRN_DBAT6L,r4 + lwz r4,SL_DBAT7(r11) mtspr SPRN_DBAT7U,r4 + lwz r4,SL_DBAT7+4(r11) mtspr SPRN_DBAT7L,r4 + lwz r4,SL_IBAT4(r11) mtspr SPRN_IBAT4U,r4 + lwz r4,SL_IBAT4+4(r11) mtspr SPRN_IBAT4L,r4 + lwz r4,SL_IBAT5(r11) mtspr SPRN_IBAT5U,r4 + lwz r4,SL_IBAT5+4(r11) mtspr SPRN_IBAT5L,r4 + lwz r4,SL_IBAT6(r11) mtspr SPRN_IBAT6U,r4 + lwz r4,SL_IBAT6+4(r11) mtspr SPRN_IBAT6L,r4 + lwz r4,SL_IBAT7(r11) mtspr SPRN_IBAT7U,r4 + lwz r4,SL_IBAT7+4(r11) mtspr SPRN_IBAT7L,r4 END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS) +#endif /* Flush all TLBs */ lis r4,0x1000 diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S index 9fabdce255cd..6ba0fdd1e7f8 100644 --- a/arch/powerpc/kernel/tm.S +++ b/arch/powerpc/kernel/tm.S @@ -148,7 +148,7 @@ _GLOBAL(tm_reclaim) /* Stash the stack pointer away for use after reclaim */ std r1, PACAR1(r13) - /* Clear MSR RI since we are about to change r1, EE is already off. */ + /* Clear MSR RI since we are about to use SCRATCH0, EE is already off */ li r5, 0 mtmsrd r5, 1 @@ -474,7 +474,7 @@ restore_gprs: REST_GPR(7, r7) - /* Clear MSR RI since we are about to change r1. EE is already off */ + /* Clear MSR RI since we are about to use SCRATCH0. EE is already off */ li r5, 0 mtmsrd r5, 1 diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c index 517662a56bdc..be1ca98fce5c 100644 --- a/arch/powerpc/kernel/trace/ftrace.c +++ b/arch/powerpc/kernel/trace/ftrace.c @@ -866,10 +866,6 @@ void arch_ftrace_update_code(int command) #ifdef CONFIG_PPC64 #define PACATOC offsetof(struct paca_struct, kernel_toc) -#define PPC_LO(v) ((v) & 0xffff) -#define PPC_HI(v) (((v) >> 16) & 0xffff) -#define PPC_HA(v) PPC_HI ((v) + 0x8000) - extern unsigned int ftrace_tramp_text[], ftrace_tramp_init[]; int __init ftrace_dyn_arch_init(void) diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig index f53997a8ca62..711fca9bc6f0 100644 --- a/arch/powerpc/kvm/Kconfig +++ b/arch/powerpc/kvm/Kconfig @@ -38,6 +38,7 @@ config KVM_BOOK3S_32_HANDLER config KVM_BOOK3S_64_HANDLER bool select KVM_BOOK3S_HANDLER + select PPC_DAWR_FORCE_ENABLE config KVM_BOOK3S_PR_POSSIBLE bool @@ -183,9 +184,9 @@ config KVM_MPIC select HAVE_KVM_MSI help Enable support for emulating MPIC devices inside the - host kernel, rather than relying on userspace to emulate. - Currently, support is limited to certain versions of - Freescale's MPIC implementation. + host kernel, rather than relying on userspace to emulate. + Currently, support is limited to certain versions of + Freescale's MPIC implementation. config KVM_XICS bool "KVM in-kernel XICS emulation" diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c index 08b2dfbc5305..2d415c36a61d 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_radix.c +++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c @@ -361,12 +361,6 @@ static void kvmppc_pte_free(pte_t *ptep) kmem_cache_free(kvm_pte_cache, ptep); } -/* Like pmd_huge() and pmd_large(), but works regardless of config options */ -static inline int pmd_is_leaf(pmd_t pmd) -{ - return !!(pmd_val(pmd) & _PAGE_PTE); -} - static pmd_t *kvmppc_pmd_alloc(void) { return kmem_cache_alloc(kvm_pmd_cache, GFP_KERNEL); @@ -487,7 +481,7 @@ static void kvmppc_unmap_free_pud(struct kvm *kvm, pud_t *pud, for (iu = 0; iu < PTRS_PER_PUD; ++iu, ++p) { if (!pud_present(*p)) continue; - if (pud_huge(*p)) { + if (pud_is_leaf(*p)) { pud_clear(p); } else { pmd_t *pmd; @@ -586,7 +580,7 @@ int kvmppc_create_pte(struct kvm *kvm, pgd_t *pgtable, pte_t pte, new_pud = pud_alloc_one(kvm->mm, gpa); pmd = NULL; - if (pud && pud_present(*pud) && !pud_huge(*pud)) + if (pud && pud_present(*pud) && !pud_is_leaf(*pud)) pmd = pmd_offset(pud, gpa); else if (level <= 1) new_pmd = kvmppc_pmd_alloc(); @@ -609,7 +603,7 @@ int kvmppc_create_pte(struct kvm *kvm, pgd_t *pgtable, pte_t pte, new_pud = NULL; } pud = pud_offset(pgd, gpa); - if (pud_huge(*pud)) { + if (pud_is_leaf(*pud)) { unsigned long hgpa = gpa & PUD_MASK; /* Check if we raced and someone else has set the same thing */ diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 76b1801aa44a..ec1804f822af 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -3603,6 +3603,8 @@ int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit, vcpu->arch.slb_max = 0; dec = mfspr(SPRN_DEC); + if (!(lpcr & LPCR_LD)) /* Sign extend if not using large decrementer */ + dec = (s32) dec; tb = mftb(); vcpu->arch.dec_expires = dec + tb; vcpu->cpu = -1; @@ -4122,8 +4124,15 @@ int kvmhv_run_single_vcpu(struct kvm_run *kvm_run, preempt_enable(); - /* cancel pending decrementer exception if DEC is now positive */ - if (get_tb() < vcpu->arch.dec_expires && kvmppc_core_pending_dec(vcpu)) + /* + * cancel pending decrementer exception if DEC is now positive, or if + * entering a nested guest in which case the decrementer is now owned + * by L2 and the L1 decrementer is provided in hdec_expires + */ + if (kvmppc_core_pending_dec(vcpu) && + ((get_tb() < vcpu->arch.dec_expires) || + (trap == BOOK3S_INTERRUPT_SYSCALL && + kvmppc_get_gpr(vcpu, 3) == H_ENTER_NESTED))) kvmppc_core_dequeue_dec(vcpu); trace_kvm_guest_exit(vcpu); diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c index cb05ccc8bc6a..7c1909657b55 100644 --- a/arch/powerpc/kvm/book3s_hv_builtin.c +++ b/arch/powerpc/kvm/book3s_hv_builtin.c @@ -820,6 +820,8 @@ static void flush_guest_tlb(struct kvm *kvm) : : "r" (rb), "i" (1), "i" (1), "i" (0), "r" (0) : "memory"); } + asm volatile("ptesync": : :"memory"); + asm volatile(PPC_RADIX_INVALIDATE_ERAT_GUEST : : :"memory"); } else { for (set = 0; set < kvm->arch.tlb_sets; ++set) { /* R=0 PRS=0 RIC=0 */ @@ -828,9 +830,9 @@ static void flush_guest_tlb(struct kvm *kvm) "r" (0) : "memory"); rb += PPC_BIT(51); /* increment set number */ } + asm volatile("ptesync": : :"memory"); + asm volatile(PPC_ISA_3_0_INVALIDATE_ERAT : : :"memory"); } - asm volatile("ptesync": : :"memory"); - asm volatile(PPC_INVALIDATE_ERAT : : :"memory"); } void kvmppc_check_need_tlb_flush(struct kvm *kvm, int pcpu, diff --git a/arch/powerpc/kvm/book3s_hv_tm.c b/arch/powerpc/kvm/book3s_hv_tm.c index 229496e2652e..0db937497169 100644 --- a/arch/powerpc/kvm/book3s_hv_tm.c +++ b/arch/powerpc/kvm/book3s_hv_tm.c @@ -128,7 +128,7 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu) } /* Set CR0 to indicate previous transactional state */ vcpu->arch.regs.ccr = (vcpu->arch.regs.ccr & 0x0fffffff) | - (((msr & MSR_TS_MASK) >> MSR_TS_S_LG) << 28); + (((msr & MSR_TS_MASK) >> MSR_TS_S_LG) << 29); /* L=1 => tresume, L=0 => tsuspend */ if (instr & (1 << 21)) { if (MSR_TM_SUSPENDED(msr)) @@ -172,7 +172,7 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu) /* Set CR0 to indicate previous transactional state */ vcpu->arch.regs.ccr = (vcpu->arch.regs.ccr & 0x0fffffff) | - (((msr & MSR_TS_MASK) >> MSR_TS_S_LG) << 28); + (((msr & MSR_TS_MASK) >> MSR_TS_S_LG) << 29); vcpu->arch.shregs.msr &= ~MSR_TS_MASK; return RESUME_GUEST; @@ -202,7 +202,7 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu) /* Set CR0 to indicate previous transactional state */ vcpu->arch.regs.ccr = (vcpu->arch.regs.ccr & 0x0fffffff) | - (((msr & MSR_TS_MASK) >> MSR_TS_S_LG) << 28); + (((msr & MSR_TS_MASK) >> MSR_TS_S_LG) << 29); vcpu->arch.shregs.msr = msr | MSR_TS_S; return RESUME_GUEST; } diff --git a/arch/powerpc/kvm/book3s_xics.c b/arch/powerpc/kvm/book3s_xics.c index e8276161872e..381bf8dea193 100644 --- a/arch/powerpc/kvm/book3s_xics.c +++ b/arch/powerpc/kvm/book3s_xics.c @@ -827,7 +827,7 @@ static noinline int kvmppc_h_eoi(struct kvm_vcpu *vcpu, unsigned long xirr) * * Note: If EOI is incorrectly used by SW to lower the CPPR * value (ie more favored), we do not check for rejection of - * a pending interrupt, this is a SW error and PAPR sepcifies + * a pending interrupt, this is a SW error and PAPR specifies * that we don't have to deal with it. * * The sending of an EOI to the ICS is handled after the diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 6d704ad2472b..0dba7eb24f92 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -414,9 +414,9 @@ int kvm_arch_hardware_setup(void) return 0; } -void kvm_arch_check_processor_compat(void *rtn) +int kvm_arch_check_processor_compat(void) { - *(int *)rtn = kvmppc_core_check_processor_compat(); + return kvmppc_core_check_processor_compat(); } int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile index c55f9c27bf79..eebc782d89a5 100644 --- a/arch/powerpc/lib/Makefile +++ b/arch/powerpc/lib/Makefile @@ -49,7 +49,8 @@ obj64-$(CONFIG_KPROBES_SANITY_TEST) += test_emulate_step.o \ obj-y += checksum_$(BITS).o checksum_wrappers.o \ string_$(BITS).o -obj-y += sstep.o ldstfp.o quad.o +obj-y += sstep.o +obj-$(CONFIG_PPC_FPU) += ldstfp.o obj64-y += quad.o obj-$(CONFIG_PPC_LIB_RHEAP) += rheap.o diff --git a/arch/powerpc/lib/ldstfp.S b/arch/powerpc/lib/ldstfp.S index e32f477d4426..e00abeabc54d 100644 --- a/arch/powerpc/lib/ldstfp.S +++ b/arch/powerpc/lib/ldstfp.S @@ -14,8 +14,6 @@ #include <asm/asm-compat.h> #include <linux/errno.h> -#ifdef CONFIG_PPC_FPU - #define STKFRM (PPC_MIN_STKFRM + 16) /* Get the contents of frN into *p; N is in r3 and p is in r4. */ @@ -237,5 +235,3 @@ _GLOBAL(conv_dp_to_sp) MTMSRD(r6) isync blr - -#endif /* CONFIG_PPC_FPU */ diff --git a/arch/powerpc/lib/pmem.c b/arch/powerpc/lib/pmem.c index 3c6c134224f8..377712e85605 100644 --- a/arch/powerpc/lib/pmem.c +++ b/arch/powerpc/lib/pmem.c @@ -15,14 +15,14 @@ void arch_wb_cache_pmem(void *addr, size_t size) { unsigned long start = (unsigned long) addr; - flush_inval_dcache_range(start, start + size); + flush_dcache_range(start, start + size); } EXPORT_SYMBOL(arch_wb_cache_pmem); void arch_invalidate_pmem(void *addr, size_t size) { unsigned long start = (unsigned long) addr; - flush_inval_dcache_range(start, start + size); + flush_dcache_range(start, start + size); } EXPORT_SYMBOL(arch_invalidate_pmem); @@ -35,7 +35,7 @@ long __copy_from_user_flushcache(void *dest, const void __user *src, unsigned long copied, start = (unsigned long) dest; copied = __copy_from_user(dest, src, size); - flush_inval_dcache_range(start, start + size); + flush_dcache_range(start, start + size); return copied; } @@ -45,7 +45,7 @@ void *memcpy_flushcache(void *dest, const void *src, size_t size) unsigned long start = (unsigned long) dest; memcpy(dest, src, size); - flush_inval_dcache_range(start, start + size); + flush_dcache_range(start, start + size); return dest; } diff --git a/arch/powerpc/mm/book3s64/Makefile b/arch/powerpc/mm/book3s64/Makefile index 974b4fc19f4f..fd393b8be14f 100644 --- a/arch/powerpc/mm/book3s64/Makefile +++ b/arch/powerpc/mm/book3s64/Makefile @@ -10,7 +10,6 @@ obj-$(CONFIG_PPC_NATIVE) += hash_native.o obj-$(CONFIG_PPC_RADIX_MMU) += radix_pgtable.o radix_tlb.o obj-$(CONFIG_PPC_4K_PAGES) += hash_4k.o obj-$(CONFIG_PPC_64K_PAGES) += hash_64k.o -obj-$(CONFIG_PPC_SPLPAR) += vphn.o obj-$(CONFIG_HUGETLB_PAGE) += hash_hugetlbpage.o ifdef CONFIG_HUGETLB_PAGE obj-$(CONFIG_PPC_RADIX_MMU) += radix_hugetlbpage.o diff --git a/arch/powerpc/mm/book3s64/hash_native.c b/arch/powerpc/mm/book3s64/hash_native.c index 30d62ffe3310..90ab4f31e2b3 100644 --- a/arch/powerpc/mm/book3s64/hash_native.c +++ b/arch/powerpc/mm/book3s64/hash_native.c @@ -41,7 +41,7 @@ #define HPTE_LOCK_BIT (56+3) #endif -DEFINE_RAW_SPINLOCK(native_tlbie_lock); +static DEFINE_RAW_SPINLOCK(native_tlbie_lock); static inline void tlbiel_hash_set_isa206(unsigned int set, unsigned int is) { @@ -56,7 +56,7 @@ static inline void tlbiel_hash_set_isa206(unsigned int set, unsigned int is) * tlbiel instruction for hash, set invalidation * i.e., r=1 and is=01 or is=10 or is=11 */ -static inline void tlbiel_hash_set_isa300(unsigned int set, unsigned int is, +static __always_inline void tlbiel_hash_set_isa300(unsigned int set, unsigned int is, unsigned int pid, unsigned int ric, unsigned int prs) { @@ -112,7 +112,7 @@ static void tlbiel_all_isa300(unsigned int num_sets, unsigned int is) asm volatile("ptesync": : :"memory"); - asm volatile(PPC_INVALIDATE_ERAT "; isync" : : :"memory"); + asm volatile(PPC_ISA_3_0_INVALIDATE_ERAT "; isync" : : :"memory"); } void hash__tlbiel_all(unsigned int action) diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c index 28ced26f2a00..9a5963e07a82 100644 --- a/arch/powerpc/mm/book3s64/hash_utils.c +++ b/arch/powerpc/mm/book3s64/hash_utils.c @@ -684,10 +684,8 @@ static void __init htab_init_page_sizes(void) if (mmu_psize_defs[MMU_PAGE_16M].shift && memblock_phys_mem_size() >= 0x40000000) mmu_vmemmap_psize = MMU_PAGE_16M; - else if (mmu_psize_defs[MMU_PAGE_64K].shift) - mmu_vmemmap_psize = MMU_PAGE_64K; else - mmu_vmemmap_psize = MMU_PAGE_4K; + mmu_vmemmap_psize = mmu_virtual_psize; #endif /* CONFIG_SPARSEMEM_VMEMMAP */ printk(KERN_DEBUG "Page orders: linear mapping = %d, " @@ -981,7 +979,7 @@ void __init hash__early_init_devtree(void) htab_scan_page_sizes(); } -struct hash_mm_context init_hash_mm_context; +static struct hash_mm_context init_hash_mm_context; void __init hash__early_init_mmu(void) { #ifndef CONFIG_PPC_64K_PAGES diff --git a/arch/powerpc/mm/book3s64/mmu_context.c b/arch/powerpc/mm/book3s64/mmu_context.c index 794404d50a85..2d0cb5ba9a47 100644 --- a/arch/powerpc/mm/book3s64/mmu_context.c +++ b/arch/powerpc/mm/book3s64/mmu_context.c @@ -174,7 +174,6 @@ static int radix__init_new_context(struct mm_struct *mm) */ asm volatile("ptesync;isync" : : : "memory"); - mm->context.npu_context = NULL; mm->context.hash_context = NULL; return index; diff --git a/arch/powerpc/mm/book3s64/pgtable.c b/arch/powerpc/mm/book3s64/pgtable.c index 01bc9663360d..7d0e0d0d22c4 100644 --- a/arch/powerpc/mm/book3s64/pgtable.c +++ b/arch/powerpc/mm/book3s64/pgtable.c @@ -72,7 +72,7 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr, WARN_ON(pte_hw_valid(pmd_pte(*pmdp)) && !pte_protnone(pmd_pte(*pmdp))); assert_spin_locked(pmd_lockptr(mm, pmdp)); - WARN_ON(!(pmd_large(pmd) || pmd_devmap(pmd))); + WARN_ON(!(pmd_large(pmd))); #endif trace_hugepage_set_pmd(addr, pmd_val(pmd)); return set_pte_at(mm, addr, pmdp_ptep(pmdp), pmd_pte(pmd)); @@ -446,3 +446,24 @@ int pmd_move_must_withdraw(struct spinlock *new_pmd_ptl, return true; } + +int ioremap_range(unsigned long ea, phys_addr_t pa, unsigned long size, pgprot_t prot, int nid) +{ + unsigned long i; + + if (radix_enabled()) + return radix__ioremap_range(ea, pa, size, prot, nid); + + for (i = 0; i < size; i += PAGE_SIZE) { + int err = map_kernel_page(ea + i, pa + i, prot); + if (err) { + if (slab_is_available()) + unmap_kernel_range(ea, size); + else + WARN_ON_ONCE(1); /* Should clean up */ + return err; + } + } + + return 0; +} diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c index 273ae66a9a45..65c2ba1e1783 100644 --- a/arch/powerpc/mm/book3s64/radix_pgtable.c +++ b/arch/powerpc/mm/book3s64/radix_pgtable.c @@ -7,6 +7,7 @@ #define pr_fmt(fmt) "radix-mmu: " fmt +#include <linux/io.h> #include <linux/kernel.h> #include <linux/sched/mm.h> #include <linux/memblock.h> @@ -198,14 +199,14 @@ void radix__change_memory_range(unsigned long start, unsigned long end, pudp = pud_alloc(&init_mm, pgdp, idx); if (!pudp) continue; - if (pud_huge(*pudp)) { + if (pud_is_leaf(*pudp)) { ptep = (pte_t *)pudp; goto update_the_pte; } pmdp = pmd_alloc(&init_mm, pudp, idx); if (!pmdp) continue; - if (pmd_huge(*pmdp)) { + if (pmd_is_leaf(*pmdp)) { ptep = pmdp_ptep(pmdp); goto update_the_pte; } @@ -319,7 +320,7 @@ static int __meminit create_physical_mapping(unsigned long start, return 0; } -void __init radix_init_pgtable(void) +static void __init radix_init_pgtable(void) { unsigned long rts_field; struct memblock_region *reg; @@ -515,14 +516,6 @@ void __init radix__early_init_devtree(void) mmu_psize_defs[MMU_PAGE_64K].shift = 16; mmu_psize_defs[MMU_PAGE_64K].ap = 0x5; found: -#ifdef CONFIG_SPARSEMEM_VMEMMAP - if (mmu_psize_defs[MMU_PAGE_2M].shift) { - /* - * map vmemmap using 2M if available - */ - mmu_vmemmap_psize = MMU_PAGE_2M; - } -#endif /* CONFIG_SPARSEMEM_VMEMMAP */ return; } @@ -587,7 +580,13 @@ void __init radix__early_init_mmu(void) #ifdef CONFIG_SPARSEMEM_VMEMMAP /* vmemmap mapping */ - mmu_vmemmap_psize = mmu_virtual_psize; + if (mmu_psize_defs[MMU_PAGE_2M].shift) { + /* + * map vmemmap using 2M if available + */ + mmu_vmemmap_psize = MMU_PAGE_2M; + } else + mmu_vmemmap_psize = mmu_virtual_psize; #endif /* * initialize page table size @@ -832,7 +831,7 @@ static void remove_pmd_table(pmd_t *pmd_start, unsigned long addr, if (!pmd_present(*pmd)) continue; - if (pmd_huge(*pmd)) { + if (pmd_is_leaf(*pmd)) { split_kernel_mapping(addr, end, PMD_SIZE, (pte_t *)pmd); continue; } @@ -857,7 +856,7 @@ static void remove_pud_table(pud_t *pud_start, unsigned long addr, if (!pud_present(*pud)) continue; - if (pud_huge(*pud)) { + if (pud_is_leaf(*pud)) { split_kernel_mapping(addr, end, PUD_SIZE, (pte_t *)pud); continue; } @@ -883,7 +882,7 @@ static void __meminit remove_pagetable(unsigned long start, unsigned long end) if (!pgd_present(*pgd)) continue; - if (pgd_huge(*pgd)) { + if (pgd_is_leaf(*pgd)) { split_kernel_mapping(addr, end, PGDIR_SIZE, (pte_t *)pgd); continue; } @@ -1118,3 +1117,123 @@ void radix__ptep_modify_prot_commit(struct vm_area_struct *vma, set_pte_at(mm, addr, ptep, pte); } + +int __init arch_ioremap_pud_supported(void) +{ + /* HPT does not cope with large pages in the vmalloc area */ + return radix_enabled(); +} + +int __init arch_ioremap_pmd_supported(void) +{ + return radix_enabled(); +} + +int p4d_free_pud_page(p4d_t *p4d, unsigned long addr) +{ + return 0; +} + +int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot) +{ + pte_t *ptep = (pte_t *)pud; + pte_t new_pud = pfn_pte(__phys_to_pfn(addr), prot); + + if (!radix_enabled()) + return 0; + + set_pte_at(&init_mm, 0 /* radix unused */, ptep, new_pud); + + return 1; +} + +int pud_clear_huge(pud_t *pud) +{ + if (pud_huge(*pud)) { + pud_clear(pud); + return 1; + } + + return 0; +} + +int pud_free_pmd_page(pud_t *pud, unsigned long addr) +{ + pmd_t *pmd; + int i; + + pmd = (pmd_t *)pud_page_vaddr(*pud); + pud_clear(pud); + + flush_tlb_kernel_range(addr, addr + PUD_SIZE); + + for (i = 0; i < PTRS_PER_PMD; i++) { + if (!pmd_none(pmd[i])) { + pte_t *pte; + pte = (pte_t *)pmd_page_vaddr(pmd[i]); + + pte_free_kernel(&init_mm, pte); + } + } + + pmd_free(&init_mm, pmd); + + return 1; +} + +int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot) +{ + pte_t *ptep = (pte_t *)pmd; + pte_t new_pmd = pfn_pte(__phys_to_pfn(addr), prot); + + if (!radix_enabled()) + return 0; + + set_pte_at(&init_mm, 0 /* radix unused */, ptep, new_pmd); + + return 1; +} + +int pmd_clear_huge(pmd_t *pmd) +{ + if (pmd_huge(*pmd)) { + pmd_clear(pmd); + return 1; + } + + return 0; +} + +int pmd_free_pte_page(pmd_t *pmd, unsigned long addr) +{ + pte_t *pte; + + pte = (pte_t *)pmd_page_vaddr(*pmd); + pmd_clear(pmd); + + flush_tlb_kernel_range(addr, addr + PMD_SIZE); + + pte_free_kernel(&init_mm, pte); + + return 1; +} + +int radix__ioremap_range(unsigned long ea, phys_addr_t pa, unsigned long size, + pgprot_t prot, int nid) +{ + if (likely(slab_is_available())) { + int err = ioremap_page_range(ea, ea + size, pa, prot); + if (err) + unmap_kernel_range(ea, size); + return err; + } else { + unsigned long i; + + for (i = 0; i < size; i += PAGE_SIZE) { + int err = map_kernel_page(ea + i, pa + i, prot); + if (WARN_ON_ONCE(err)) /* Should clean up */ + return err; + } + return 0; + } +} diff --git a/arch/powerpc/mm/book3s64/radix_tlb.c b/arch/powerpc/mm/book3s64/radix_tlb.c index ce8a77fae6a7..71f7fede2fa4 100644 --- a/arch/powerpc/mm/book3s64/radix_tlb.c +++ b/arch/powerpc/mm/book3s64/radix_tlb.c @@ -25,7 +25,7 @@ * tlbiel instruction for radix, set invalidation * i.e., r=1 and is=01 or is=10 or is=11 */ -static inline void tlbiel_radix_set_isa300(unsigned int set, unsigned int is, +static __always_inline void tlbiel_radix_set_isa300(unsigned int set, unsigned int is, unsigned int pid, unsigned int ric, unsigned int prs) { @@ -83,7 +83,7 @@ void radix__tlbiel_all(unsigned int action) else WARN(1, "%s called on pre-POWER9 CPU\n", __func__); - asm volatile(PPC_INVALIDATE_ERAT "; isync" : : :"memory"); + asm volatile(PPC_ISA_3_0_INVALIDATE_ERAT "; isync" : : :"memory"); } static __always_inline void __tlbiel_pid(unsigned long pid, int set, @@ -146,8 +146,8 @@ static __always_inline void __tlbie_lpid(unsigned long lpid, unsigned long ric) trace_tlbie(lpid, 0, rb, rs, ric, prs, r); } -static inline void __tlbiel_lpid_guest(unsigned long lpid, int set, - unsigned long ric) +static __always_inline void __tlbiel_lpid_guest(unsigned long lpid, int set, + unsigned long ric) { unsigned long rb,rs,prs,r; @@ -163,8 +163,8 @@ static inline void __tlbiel_lpid_guest(unsigned long lpid, int set, } -static inline void __tlbiel_va(unsigned long va, unsigned long pid, - unsigned long ap, unsigned long ric) +static __always_inline void __tlbiel_va(unsigned long va, unsigned long pid, + unsigned long ap, unsigned long ric) { unsigned long rb,rs,prs,r; @@ -179,8 +179,8 @@ static inline void __tlbiel_va(unsigned long va, unsigned long pid, trace_tlbie(0, 1, rb, rs, ric, prs, r); } -static inline void __tlbie_va(unsigned long va, unsigned long pid, - unsigned long ap, unsigned long ric) +static __always_inline void __tlbie_va(unsigned long va, unsigned long pid, + unsigned long ap, unsigned long ric) { unsigned long rb,rs,prs,r; @@ -195,8 +195,8 @@ static inline void __tlbie_va(unsigned long va, unsigned long pid, trace_tlbie(0, 0, rb, rs, ric, prs, r); } -static inline void __tlbie_lpid_va(unsigned long va, unsigned long lpid, - unsigned long ap, unsigned long ric) +static __always_inline void __tlbie_lpid_va(unsigned long va, unsigned long lpid, + unsigned long ap, unsigned long ric) { unsigned long rb,rs,prs,r; @@ -235,7 +235,7 @@ static inline void fixup_tlbie_lpid(unsigned long lpid) /* * We use 128 set in radix mode and 256 set in hpt mode. */ -static inline void _tlbiel_pid(unsigned long pid, unsigned long ric) +static __always_inline void _tlbiel_pid(unsigned long pid, unsigned long ric) { int set; @@ -258,7 +258,7 @@ static inline void _tlbiel_pid(unsigned long pid, unsigned long ric) __tlbiel_pid(pid, set, RIC_FLUSH_TLB); asm volatile("ptesync": : :"memory"); - asm volatile(PPC_INVALIDATE_ERAT "; isync" : : :"memory"); + asm volatile(PPC_RADIX_INVALIDATE_ERAT_USER "; isync" : : :"memory"); } static inline void _tlbie_pid(unsigned long pid, unsigned long ric) @@ -310,7 +310,7 @@ static inline void _tlbiel_lpid(unsigned long lpid, unsigned long ric) __tlbiel_lpid(lpid, set, RIC_FLUSH_TLB); asm volatile("ptesync": : :"memory"); - asm volatile(PPC_INVALIDATE_ERAT "; isync" : : :"memory"); + asm volatile(PPC_RADIX_INVALIDATE_ERAT_GUEST "; isync" : : :"memory"); } static inline void _tlbie_lpid(unsigned long lpid, unsigned long ric) @@ -337,7 +337,7 @@ static inline void _tlbie_lpid(unsigned long lpid, unsigned long ric) asm volatile("eieio; tlbsync; ptesync": : :"memory"); } -static inline void _tlbiel_lpid_guest(unsigned long lpid, unsigned long ric) +static __always_inline void _tlbiel_lpid_guest(unsigned long lpid, unsigned long ric) { int set; @@ -362,7 +362,7 @@ static inline void _tlbiel_lpid_guest(unsigned long lpid, unsigned long ric) __tlbiel_lpid_guest(lpid, set, RIC_FLUSH_TLB); asm volatile("ptesync": : :"memory"); - asm volatile(PPC_INVALIDATE_ERAT : : :"memory"); + asm volatile(PPC_RADIX_INVALIDATE_ERAT_GUEST : : :"memory"); } @@ -377,8 +377,8 @@ static inline void __tlbiel_va_range(unsigned long start, unsigned long end, __tlbiel_va(addr, pid, ap, RIC_FLUSH_TLB); } -static inline void _tlbiel_va(unsigned long va, unsigned long pid, - unsigned long psize, unsigned long ric) +static __always_inline void _tlbiel_va(unsigned long va, unsigned long pid, + unsigned long psize, unsigned long ric) { unsigned long ap = mmu_get_ap(psize); @@ -409,8 +409,8 @@ static inline void __tlbie_va_range(unsigned long start, unsigned long end, __tlbie_va(addr, pid, ap, RIC_FLUSH_TLB); } -static inline void _tlbie_va(unsigned long va, unsigned long pid, - unsigned long psize, unsigned long ric) +static __always_inline void _tlbie_va(unsigned long va, unsigned long pid, + unsigned long psize, unsigned long ric) { unsigned long ap = mmu_get_ap(psize); @@ -420,7 +420,7 @@ static inline void _tlbie_va(unsigned long va, unsigned long pid, asm volatile("eieio; tlbsync; ptesync": : :"memory"); } -static inline void _tlbie_lpid_va(unsigned long va, unsigned long lpid, +static __always_inline void _tlbie_lpid_va(unsigned long va, unsigned long lpid, unsigned long psize, unsigned long ric) { unsigned long ap = mmu_get_ap(psize); diff --git a/arch/powerpc/mm/book3s64/vphn.h b/arch/powerpc/mm/book3s64/vphn.h deleted file mode 100644 index f0b93c2dd578..000000000000 --- a/arch/powerpc/mm/book3s64/vphn.h +++ /dev/null @@ -1,16 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _ARCH_POWERPC_MM_VPHN_H_ -#define _ARCH_POWERPC_MM_VPHN_H_ - -/* The H_HOME_NODE_ASSOCIATIVITY h_call returns 6 64-bit registers. */ -#define VPHN_REGISTER_COUNT 6 - -/* - * 6 64-bit registers unpacked into up to 24 be32 associativity values. To - * form the complete property we have to add the length in the first cell. - */ -#define VPHN_ASSOC_BUFSIZE (VPHN_REGISTER_COUNT*sizeof(u64)/sizeof(u16) + 1) - -extern int vphn_unpack_associativity(const long *packed, __be32 *unpacked); - -#endif diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index b5d92dc32844..a8953f108808 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -61,12 +61,17 @@ static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp, num_hugepd = 1; } + if (!cachep) { + WARN_ONCE(1, "No page table cache created for hugetlb tables"); + return -ENOMEM; + } + new = kmem_cache_alloc(cachep, pgtable_gfp_flags(mm, GFP_KERNEL)); BUG_ON(pshift > HUGEPD_SHIFT_MASK); BUG_ON((unsigned long)new & HUGEPD_SHIFT_MASK); - if (! new) + if (!new) return -ENOMEM; /* @@ -130,6 +135,8 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz } else { pdshift = PUD_SHIFT; pu = pud_alloc(mm, pg, addr); + if (!pu) + return NULL; if (pshift == PUD_SHIFT) return (pte_t *)pu; else if (pshift > PMD_SHIFT) { @@ -138,6 +145,8 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz } else { pdshift = PMD_SHIFT; pm = pmd_alloc(mm, pu, addr); + if (!pm) + return NULL; if (pshift == PMD_SHIFT) /* 16MB hugepage */ return (pte_t *)pm; @@ -154,12 +163,16 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz } else { pdshift = PUD_SHIFT; pu = pud_alloc(mm, pg, addr); + if (!pu) + return NULL; if (pshift >= PUD_SHIFT) { ptl = pud_lockptr(mm, pu); hpdp = (hugepd_t *)pu; } else { pdshift = PMD_SHIFT; pm = pmd_alloc(mm, pu, addr); + if (!pm) + return NULL; ptl = pmd_lockptr(mm, pm); hpdp = (hugepd_t *)pm; } @@ -511,13 +524,6 @@ retry: return page; } -static unsigned long hugepte_addr_end(unsigned long addr, unsigned long end, - unsigned long sz) -{ - unsigned long __boundary = (addr + sz) & ~(sz-1); - return (__boundary - 1 < end - 1) ? __boundary : end; -} - #ifdef CONFIG_PPC_MM_SLICES unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, @@ -588,6 +594,7 @@ __setup("hugepagesz=", hugepage_setup_sz); static int __init hugetlbpage_init(void) { + bool configured = false; int psize; if (hugetlb_disabled) { @@ -638,10 +645,15 @@ static int __init hugetlbpage_init(void) pgtable_cache_add(pdshift - shift); else if (IS_ENABLED(CONFIG_PPC_FSL_BOOK3E) || IS_ENABLED(CONFIG_PPC_8xx)) pgtable_cache_add(PTE_T_ORDER); + + configured = true; } - if (IS_ENABLED(CONFIG_HUGETLB_PAGE_SIZE_VARIABLE)) - hugetlbpage_init_default(); + if (configured) { + if (IS_ENABLED(CONFIG_HUGETLB_PAGE_SIZE_VARIABLE)) + hugetlbpage_init_default(); + } else + pr_info("Failed to initialize. Disabling HugeTLB"); return 0; } @@ -665,68 +677,3 @@ void flush_dcache_icache_hugepage(struct page *page) } } } - -static int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr, - unsigned long end, int write, struct page **pages, int *nr) -{ - unsigned long pte_end; - struct page *head, *page; - pte_t pte; - int refs; - - pte_end = (addr + sz) & ~(sz-1); - if (pte_end < end) - end = pte_end; - - pte = READ_ONCE(*ptep); - - if (!pte_access_permitted(pte, write)) - return 0; - - /* hugepages are never "special" */ - VM_BUG_ON(!pfn_valid(pte_pfn(pte))); - - refs = 0; - head = pte_page(pte); - - page = head + ((addr & (sz-1)) >> PAGE_SHIFT); - do { - VM_BUG_ON(compound_head(page) != head); - pages[*nr] = page; - (*nr)++; - page++; - refs++; - } while (addr += PAGE_SIZE, addr != end); - - if (!page_cache_add_speculative(head, refs)) { - *nr -= refs; - return 0; - } - - if (unlikely(pte_val(pte) != pte_val(*ptep))) { - /* Could be optimized better */ - *nr -= refs; - while (refs--) - put_page(head); - return 0; - } - - return 1; -} - -int gup_huge_pd(hugepd_t hugepd, unsigned long addr, unsigned int pdshift, - unsigned long end, int write, struct page **pages, int *nr) -{ - pte_t *ptep; - unsigned long sz = 1UL << hugepd_shift(hugepd); - unsigned long next; - - ptep = hugepte_offset(hugepd, addr, pdshift); - do { - next = hugepte_addr_end(addr, end, sz); - if (!gup_hugepte(ptep, sz, addr, end, write, pages, nr)) - return 0; - } while (ptep++, addr = next, addr != end); - - return 1; -} diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c index a4e17a979e45..a44f6281ca3a 100644 --- a/arch/powerpc/mm/init_64.c +++ b/arch/powerpc/mm/init_64.c @@ -194,8 +194,11 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, * fail due to alignment issues when using 16MB hugepages, so * fall back to system memory if the altmap allocation fail. */ - if (altmap) + if (altmap) { p = altmap_alloc_block_buf(page_size, altmap); + if (!p) + pr_debug("altmap block allocation failed, falling back to system memory"); + } if (!p) p = vmemmap_alloc_block_buf(page_size, node); if (!p) diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 2540d3b2588c..6d5f0fc76666 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -120,7 +120,7 @@ int __ref arch_add_memory(int nid, u64 start, u64 size, start, start + size, rc); return -EFAULT; } - flush_inval_dcache_range(start, start + size); + flush_dcache_range(start, start + size); return __add_pages(nid, start_pfn, nr_pages, restrictions); } @@ -146,7 +146,7 @@ void __ref arch_remove_memory(int nid, u64 start, u64 size, /* Remove htab bolted mappings for this section of memory */ start = (unsigned long)__va(start); - flush_inval_dcache_range(start, start + size); + flush_dcache_range(start, start + size); ret = remove_section_mapping(start, start + size); WARN_ON_ONCE(ret); diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index 917904d2fe97..50d68d21ddcc 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -163,6 +163,22 @@ static void unmap_cpu_from_node(unsigned long cpu) } #endif /* CONFIG_HOTPLUG_CPU || CONFIG_PPC_SPLPAR */ +int cpu_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc) +{ + int dist = 0; + + int i, index; + + for (i = 0; i < distance_ref_points_depth; i++) { + index = be32_to_cpu(distance_ref_points[i]); + if (cpu1_assoc[index] == cpu2_assoc[index]) + break; + dist++; + } + + return dist; +} + /* must hold reference to node during call */ static const __be32 *of_get_associativity(struct device_node *dev) { @@ -212,7 +228,7 @@ static int associativity_to_nid(const __be32 *associativity) { int nid = NUMA_NO_NODE; - if (min_common_depth == -1) + if (!numa_enabled) goto out; if (of_read_number(associativity, 1) >= min_common_depth) @@ -416,17 +432,19 @@ static int of_get_assoc_arrays(struct assoc_arrays *aa) static int of_drconf_to_nid_single(struct drmem_lmb *lmb) { struct assoc_arrays aa = { .arrays = NULL }; - int default_nid = 0; + int default_nid = NUMA_NO_NODE; int nid = default_nid; int rc, index; + if ((min_common_depth < 0) || !numa_enabled) + return default_nid; + rc = of_get_assoc_arrays(&aa); if (rc) return default_nid; - if (min_common_depth > 0 && min_common_depth <= aa.array_sz && - !(lmb->flags & DRCONF_MEM_AI_INVALID) && - lmb->aa_index < aa.n_arrays) { + if (min_common_depth <= aa.array_sz && + !(lmb->flags & DRCONF_MEM_AI_INVALID) && lmb->aa_index < aa.n_arrays) { index = lmb->aa_index * aa.array_sz + min_common_depth - 1; nid = of_read_number(&aa.arrays[index], 1); @@ -626,8 +644,14 @@ static int __init parse_numa_properties(void) min_common_depth = find_min_common_depth(); - if (min_common_depth < 0) + if (min_common_depth < 0) { + /* + * if we fail to parse min_common_depth from device tree + * mark the numa disabled, boot with numa disabled. + */ + numa_enabled = false; return min_common_depth; + } dbg("NUMA associativity depth for CPU/Memory: %d\n", min_common_depth); @@ -743,7 +767,7 @@ void __init dump_numa_cpu_topology(void) unsigned int node; unsigned int cpu, count; - if (min_common_depth == -1 || !numa_enabled) + if (!numa_enabled) return; for_each_online_node(node) { @@ -808,7 +832,7 @@ static void __init find_possible_nodes(void) struct device_node *rtas; u32 numnodes, i; - if (min_common_depth <= 0) + if (!numa_enabled) return; rtas = of_find_node_by_path("/rtas"); @@ -1010,7 +1034,7 @@ int hot_add_scn_to_nid(unsigned long scn_addr) struct device_node *memory = NULL; int nid; - if (!numa_enabled || (min_common_depth < 0)) + if (!numa_enabled) return first_online_node; memory = of_find_node_by_path("/ibm,dynamic-reconfiguration-memory"); @@ -1063,9 +1087,6 @@ u64 memory_hotplug_max(void) /* Virtual Processor Home Node (VPHN) support */ #ifdef CONFIG_PPC_SPLPAR - -#include "book3s64/vphn.h" - struct topology_update_data { struct topology_update_data *next; unsigned int cpu; @@ -1161,25 +1182,13 @@ static int update_cpu_associativity_changes_mask(void) * Retrieve the new associativity information for a virtual processor's * home node. */ -static long hcall_vphn(unsigned long cpu, __be32 *associativity) -{ - long rc; - long retbuf[PLPAR_HCALL9_BUFSIZE] = {0}; - u64 flags = 1; - int hwcpu = get_hard_smp_processor_id(cpu); - - rc = plpar_hcall9(H_HOME_NODE_ASSOCIATIVITY, retbuf, flags, hwcpu); - vphn_unpack_associativity(retbuf, associativity); - - return rc; -} - static long vphn_get_associativity(unsigned long cpu, __be32 *associativity) { long rc; - rc = hcall_vphn(cpu, associativity); + rc = hcall_vphn(get_hard_smp_processor_id(cpu), + VPHN_FLAG_VCPU, associativity); switch (rc) { case H_FUNCTION: diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c index fc10c0c24f51..e3759b69f81b 100644 --- a/arch/powerpc/mm/pgtable.c +++ b/arch/powerpc/mm/pgtable.c @@ -336,10 +336,11 @@ pte_t *__find_linux_pte(pgd_t *pgdir, unsigned long ea, if (pgd_none(pgd)) return NULL; - if (pgd_huge(pgd)) { + if (pgd_is_leaf(pgd)) { ret_pte = (pte_t *)pgdp; goto out; } + if (is_hugepd(__hugepd(pgd_val(pgd)))) { hpdp = (hugepd_t *)&pgd; goto out_huge; @@ -357,14 +358,16 @@ pte_t *__find_linux_pte(pgd_t *pgdir, unsigned long ea, if (pud_none(pud)) return NULL; - if (pud_huge(pud)) { + if (pud_is_leaf(pud)) { ret_pte = (pte_t *)pudp; goto out; } + if (is_hugepd(__hugepd(pud_val(pud)))) { hpdp = (hugepd_t *)&pud; goto out_huge; } + pdshift = PMD_SHIFT; pmdp = pmd_offset(&pud, ea); pmd = READ_ONCE(*pmdp); @@ -393,15 +396,12 @@ pte_t *__find_linux_pte(pgd_t *pgdir, unsigned long ea, ret_pte = (pte_t *)pmdp; goto out; } - /* - * pmd_large check below will handle the swap pmd pte - * we need to do both the check because they are config - * dependent. - */ - if (pmd_huge(pmd) || pmd_large(pmd)) { + + if (pmd_is_leaf(pmd)) { ret_pte = (pte_t *)pmdp; goto out; } + if (is_hugepd(__hugepd(pmd_val(pmd)))) { hpdp = (hugepd_t *)&pmd; goto out_huge; diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c index d53188dee18f..35cb96cfc258 100644 --- a/arch/powerpc/mm/pgtable_32.c +++ b/arch/powerpc/mm/pgtable_32.c @@ -360,7 +360,7 @@ void mark_initmem_nx(void) unsigned long numpages = PFN_UP((unsigned long)_einittext) - PFN_DOWN((unsigned long)_sinittext); - if (v_block_mapped((unsigned long)_stext) + 1) + if (v_block_mapped((unsigned long)_stext + 1)) mmu_mark_initmem_nx(); else change_page_attr(page, numpages, PAGE_KERNEL); diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c index 12d5e083942d..9ad59b733984 100644 --- a/arch/powerpc/mm/pgtable_64.c +++ b/arch/powerpc/mm/pgtable_64.c @@ -103,14 +103,30 @@ unsigned long ioremap_bot; unsigned long ioremap_bot = IOREMAP_BASE; #endif +int __weak ioremap_range(unsigned long ea, phys_addr_t pa, unsigned long size, pgprot_t prot, int nid) +{ + unsigned long i; + + for (i = 0; i < size; i += PAGE_SIZE) { + int err = map_kernel_page(ea + i, pa + i, prot); + if (err) { + if (slab_is_available()) + unmap_kernel_range(ea, size); + else + WARN_ON_ONCE(1); /* Should clean up */ + return err; + } + } + + return 0; +} + /** * __ioremap_at - Low level function to establish the page tables * for an IO mapping */ void __iomem *__ioremap_at(phys_addr_t pa, void *ea, unsigned long size, pgprot_t prot) { - unsigned long i; - /* We don't support the 4K PFN hack with ioremap */ if (pgprot_val(prot) & H_PAGE_4K_PFN) return NULL; @@ -124,9 +140,8 @@ void __iomem *__ioremap_at(phys_addr_t pa, void *ea, unsigned long size, pgprot_ WARN_ON(((unsigned long)ea) & ~PAGE_MASK); WARN_ON(size & ~PAGE_MASK); - for (i = 0; i < size; i += PAGE_SIZE) - if (map_kernel_page((unsigned long)ea + i, pa + i, prot)) - return NULL; + if (ioremap_range((unsigned long)ea, pa, size, prot, NUMA_NO_NODE)) + return NULL; return (void __iomem *)ea; } @@ -177,8 +192,6 @@ void __iomem * __ioremap_caller(phys_addr_t addr, unsigned long size, area->phys_addr = paligned; ret = __ioremap_at(paligned, area->addr, size, prot); - if (!ret) - vunmap(area->addr); } else { ret = __ioremap_at(paligned, (void *)ioremap_bot, size, prot); if (ret) @@ -291,16 +304,20 @@ EXPORT_SYMBOL(__iounmap_at); /* 4 level page table */ struct page *pgd_page(pgd_t pgd) { - if (pgd_huge(pgd)) + if (pgd_is_leaf(pgd)) { + VM_WARN_ON(!pgd_huge(pgd)); return pte_page(pgd_pte(pgd)); + } return virt_to_page(pgd_page_vaddr(pgd)); } #endif struct page *pud_page(pud_t pud) { - if (pud_huge(pud)) + if (pud_is_leaf(pud)) { + VM_WARN_ON(!pud_huge(pud)); return pte_page(pud_pte(pud)); + } return virt_to_page(pud_page_vaddr(pud)); } @@ -310,8 +327,10 @@ struct page *pud_page(pud_t pud) */ struct page *pmd_page(pmd_t pmd) { - if (pmd_large(pmd) || pmd_huge(pmd) || pmd_devmap(pmd)) + if (pmd_is_leaf(pmd)) { + VM_WARN_ON(!(pmd_large(pmd) || pmd_huge(pmd))); return pte_page(pmd_pte(pmd)); + } return virt_to_page(pmd_page_vaddr(pmd)); } diff --git a/arch/powerpc/mm/ptdump/ptdump.c b/arch/powerpc/mm/ptdump/ptdump.c index 39bf1e2cba13..6a88a9f585d4 100644 --- a/arch/powerpc/mm/ptdump/ptdump.c +++ b/arch/powerpc/mm/ptdump/ptdump.c @@ -273,7 +273,7 @@ static void walk_pmd(struct pg_state *st, pud_t *pud, unsigned long start) for (i = 0; i < PTRS_PER_PMD; i++, pmd++) { addr = start + i * PMD_SIZE; - if (!pmd_none(*pmd) && !pmd_huge(*pmd)) + if (!pmd_none(*pmd) && !pmd_is_leaf(*pmd)) /* pmd exists */ walk_pte(st, pmd, addr); else @@ -289,7 +289,7 @@ static void walk_pud(struct pg_state *st, pgd_t *pgd, unsigned long start) for (i = 0; i < PTRS_PER_PUD; i++, pud++) { addr = start + i * PUD_SIZE; - if (!pud_none(*pud) && !pud_huge(*pud)) + if (!pud_none(*pud) && !pud_is_leaf(*pud)) /* pud exists */ walk_pmd(st, pud, addr); else @@ -310,7 +310,7 @@ static void walk_pagetables(struct pg_state *st) * the hash pagetable. */ for (i = 0; i < PTRS_PER_PGD; i++, pgd++, addr += PGDIR_SIZE) { - if (!pgd_none(*pgd) && !pgd_huge(*pgd)) + if (!pgd_none(*pgd) && !pgd_is_leaf(*pgd)) /* pgd exists */ walk_pud(st, pgd, addr); else diff --git a/arch/powerpc/perf/hv-24x7.c b/arch/powerpc/perf/hv-24x7.c index faad5b315f49..573e0b309c0c 100644 --- a/arch/powerpc/perf/hv-24x7.c +++ b/arch/powerpc/perf/hv-24x7.c @@ -567,7 +567,7 @@ static int event_uniq_add(struct rb_root *root, const char *name, int nl, struct event_uniq *it; int result; - it = container_of(*new, struct event_uniq, node); + it = rb_entry(*new, struct event_uniq, node); result = ev_uniq_ord(name, nl, domain, it->name, it->nl, it->domain); diff --git a/arch/powerpc/perf/imc-pmu.c b/arch/powerpc/perf/imc-pmu.c index 3bdfc1e32096..dea243185ea4 100644 --- a/arch/powerpc/perf/imc-pmu.c +++ b/arch/powerpc/perf/imc-pmu.c @@ -362,7 +362,14 @@ static int ppc_nest_imc_cpu_offline(unsigned int cpu) */ nid = cpu_to_node(cpu); l_cpumask = cpumask_of_node(nid); - target = cpumask_any_but(l_cpumask, cpu); + target = cpumask_last(l_cpumask); + + /* + * If this(target) is the last cpu in the cpumask for this chip, + * check for any possible online cpu in the chip. + */ + if (unlikely(target == cpu)) + target = cpumask_any_but(l_cpumask, cpu); /* * Update the cpumask with the target cpu and @@ -667,7 +674,10 @@ static int ppc_core_imc_cpu_offline(unsigned int cpu) return 0; /* Find any online cpu in that core except the current "cpu" */ - ncpu = cpumask_any_but(cpu_sibling_mask(cpu), cpu); + ncpu = cpumask_last(cpu_sibling_mask(cpu)); + + if (unlikely(ncpu == cpu)) + ncpu = cpumask_any_but(cpu_sibling_mask(cpu), cpu); if (ncpu >= 0 && ncpu < nr_cpu_ids) { cpumask_set_cpu(ncpu, &core_imc_cpumask); diff --git a/arch/powerpc/platforms/40x/Kconfig b/arch/powerpc/platforms/40x/Kconfig index ad2bb1408b4c..6da813b65b42 100644 --- a/arch/powerpc/platforms/40x/Kconfig +++ b/arch/powerpc/platforms/40x/Kconfig @@ -16,12 +16,12 @@ config EP405 This option enables support for the EP405/EP405PC boards. config HOTFOOT - bool "Hotfoot" + bool "Hotfoot" depends on 40x select PPC40x_SIMPLE select FORCE_PCI - help - This option enables support for the ESTEEM 195E Hotfoot board. + help + This option enables support for the ESTEEM 195E Hotfoot board. config KILAUEA bool "Kilauea" @@ -80,7 +80,6 @@ config OBS600 help This option enables support for PlatHome OpenBlockS 600 server - config PPC40x_SIMPLE bool "Simple PowerPC 40x board support" depends on 40x diff --git a/arch/powerpc/platforms/44x/Kconfig b/arch/powerpc/platforms/44x/Kconfig index 35be81fd2dc2..b369ed4e3675 100644 --- a/arch/powerpc/platforms/44x/Kconfig +++ b/arch/powerpc/platforms/44x/Kconfig @@ -40,12 +40,12 @@ config EBONY This option enables support for the IBM PPC440GP evaluation board. config SAM440EP - bool "Sam440ep" + bool "Sam440ep" depends on 44x - select 440EP - select FORCE_PCI - help - This option enables support for the ACube Sam440ep board. + select 440EP + select FORCE_PCI + help + This option enables support for the ACube Sam440ep board. config SEQUOIA bool "Sequoia" diff --git a/arch/powerpc/platforms/4xx/uic.c b/arch/powerpc/platforms/4xx/uic.c index 31f12ad37a98..36fb66ce54cf 100644 --- a/arch/powerpc/platforms/4xx/uic.c +++ b/arch/powerpc/platforms/4xx/uic.c @@ -154,6 +154,7 @@ static int uic_set_irq_type(struct irq_data *d, unsigned int flow_type) mtdcr(uic->dcrbase + UIC_PR, pr); mtdcr(uic->dcrbase + UIC_TR, tr); + mtdcr(uic->dcrbase + UIC_SR, ~mask); raw_spin_unlock_irqrestore(&uic->lock, flags); diff --git a/arch/powerpc/platforms/85xx/Kconfig b/arch/powerpc/platforms/85xx/Kconfig index d1af0ee2f8c8..fa3d29dcb57e 100644 --- a/arch/powerpc/platforms/85xx/Kconfig +++ b/arch/powerpc/platforms/85xx/Kconfig @@ -147,10 +147,10 @@ config SOCRATES This option enables support for the Socrates board. config KSI8560 - bool "Emerson KSI8560" - select DEFAULT_UIMAGE - help - This option enables support for the Emerson KSI8560 board + bool "Emerson KSI8560" + select DEFAULT_UIMAGE + help + This option enables support for the Emerson KSI8560 board config XES_MPC85xx bool "X-ES single-board computer" diff --git a/arch/powerpc/platforms/86xx/Kconfig b/arch/powerpc/platforms/86xx/Kconfig index 0a610114bc38..07a9d60c618a 100644 --- a/arch/powerpc/platforms/86xx/Kconfig +++ b/arch/powerpc/platforms/86xx/Kconfig @@ -62,9 +62,9 @@ config GEF_SBC610 This option enables support for the GE SBC610. config MVME7100 - bool "Artesyn MVME7100" - help - This option enables support for the Emerson/Artesyn MVME7100 board. + bool "Artesyn MVME7100" + help + This option enables support for the Emerson/Artesyn MVME7100 board. endif diff --git a/arch/powerpc/platforms/8xx/Kconfig b/arch/powerpc/platforms/8xx/Kconfig index d408162d5af4..e0fe670f06f6 100644 --- a/arch/powerpc/platforms/8xx/Kconfig +++ b/arch/powerpc/platforms/8xx/Kconfig @@ -157,6 +157,13 @@ config I2C_SPI_SMC1_UCODE_PATCH help Help not implemented yet, coming soon. +config SMC_UCODE_PATCH + bool "SMC relocation patch" + help + This microcode relocates SMC1 and SMC2 parameter RAMs at + offset 0x1ec0 and 0x1fc0 to allow extended parameter RAM + for SCC3 and SCC4. + endchoice config UCODE_PATCH diff --git a/arch/powerpc/platforms/8xx/Makefile b/arch/powerpc/platforms/8xx/Makefile index 708ab099e886..27a7c6f828e0 100644 --- a/arch/powerpc/platforms/8xx/Makefile +++ b/arch/powerpc/platforms/8xx/Makefile @@ -3,6 +3,8 @@ # Makefile for the PowerPC 8xx linux kernel. # obj-y += m8xx_setup.o machine_check.o pic.o +obj-$(CONFIG_CPM1) += cpm1.o +obj-$(CONFIG_UCODE_PATCH) += micropatch.o obj-$(CONFIG_MPC885ADS) += mpc885ads_setup.o obj-$(CONFIG_MPC86XADS) += mpc86xads_setup.o obj-$(CONFIG_PPC_EP88XC) += ep88xc.o diff --git a/arch/powerpc/sysdev/cpm1.c b/arch/powerpc/platforms/8xx/cpm1.c index 4f8dcf124828..0f65c51271db 100644 --- a/arch/powerpc/sysdev/cpm1.c +++ b/arch/powerpc/platforms/8xx/cpm1.c @@ -88,7 +88,8 @@ int cpm_get_irq(void) { int cpm_vec; - /* Get the vector by setting the ACK bit and then reading + /* + * Get the vector by setting the ACK bit and then reading * the register. */ out_be16(&cpic_reg->cpic_civr, 1); @@ -108,7 +109,8 @@ static int cpm_pic_host_map(struct irq_domain *h, unsigned int virq, return 0; } -/* The CPM can generate the error interrupt when there is a race condition +/* + * The CPM can generate the error interrupt when there is a race condition * between generating and masking interrupts. All we have to do is ACK it * and return. This is a no-op function so we don't need any special * tests in the interrupt handler. @@ -208,12 +210,10 @@ void __init cpm_reset(void) cpmp = &mpc8xx_immr->im_cpm; #ifndef CONFIG_PPC_EARLY_DEBUG_CPM - /* Perform a reset. - */ + /* Perform a reset. */ out_be16(&cpmp->cp_cpcr, CPM_CR_RST | CPM_CR_FLG); - /* Wait for it. - */ + /* Wait for it. */ while (in_be16(&cpmp->cp_cpcr) & CPM_CR_FLG); #endif @@ -221,7 +221,8 @@ void __init cpm_reset(void) cpm_load_patch(cpmp); #endif - /* Set SDMA Bus Request priority 5. + /* + * Set SDMA Bus Request priority 5. * On 860T, this also enables FEC priority 6. I am not sure * this is what we really want for some applications, but the * manual recommends it. @@ -263,7 +264,8 @@ out: } EXPORT_SYMBOL(cpm_command); -/* Set a baud rate generator. This needs lots of work. There are +/* + * Set a baud rate generator. This needs lots of work. There are * four BRGs, any of which can be wired to any channel. * The internal baud rate clock is the system clock divided by 16. * This assumes the baudrate is 16x oversampled by the uart. @@ -277,11 +279,11 @@ cpm_setbrg(uint brg, uint rate) { u32 __iomem *bp; - /* This is good enough to get SMCs running..... - */ + /* This is good enough to get SMCs running..... */ bp = &cpmp->cp_brgc1; bp += brg; - /* The BRG has a 12-bit counter. For really slow baud rates (or + /* + * The BRG has a 12-bit counter. For really slow baud rates (or * really fast processors), we may have to further divide by 16. */ if (((BRG_UART_CLK / rate) - 1) < 4096) diff --git a/arch/powerpc/platforms/8xx/micropatch.c b/arch/powerpc/platforms/8xx/micropatch.c new file mode 100644 index 000000000000..c80bd7afd6c5 --- /dev/null +++ b/arch/powerpc/platforms/8xx/micropatch.c @@ -0,0 +1,378 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Microcode patches for the CPM as supplied by Motorola. + * This is the one for IIC/SPI. There is a newer one that + * also relocates SMC2, but this would require additional changes + * to uart.c, so I am holding off on that for a moment. + */ +#include <linux/init.h> +#include <linux/errno.h> +#include <linux/sched.h> +#include <linux/kernel.h> +#include <linux/param.h> +#include <linux/string.h> +#include <linux/mm.h> +#include <linux/interrupt.h> +#include <asm/irq.h> +#include <asm/page.h> +#include <asm/pgtable.h> +#include <asm/8xx_immap.h> +#include <asm/cpm.h> +#include <asm/cpm1.h> + +struct patch_params { + ushort rccr; + ushort cpmcr1; + ushort cpmcr2; + ushort cpmcr3; + ushort cpmcr4; +}; + +/* + * I2C/SPI relocation patch arrays. + */ + +#ifdef CONFIG_I2C_SPI_UCODE_PATCH + +static char patch_name[] __initdata = "I2C/SPI"; + +static struct patch_params patch_params __initdata = { + 1, 0x802a, 0x8028, 0x802e, 0x802c, +}; + +static uint patch_2000[] __initdata = { + 0x7FFFEFD9, 0x3FFD0000, 0x7FFB49F7, 0x7FF90000, + 0x5FEFADF7, 0x5F89ADF7, 0x5FEFAFF7, 0x5F89AFF7, + 0x3A9CFBC8, 0xE7C0EDF0, 0x77C1E1BB, 0xF4DC7F1D, + 0xABAD932F, 0x4E08FDCF, 0x6E0FAFF8, 0x7CCF76CF, + 0xFD1FF9CF, 0xABF88DC6, 0xAB5679F7, 0xB0937383, + 0xDFCE79F7, 0xB091E6BB, 0xE5BBE74F, 0xB3FA6F0F, + 0x6FFB76CE, 0xEE0DF9CF, 0x2BFBEFEF, 0xCFEEF9CF, + 0x76CEAD24, 0x90B2DF9A, 0x7FDDD0BF, 0x4BF847FD, + 0x7CCF76CE, 0xCFEF7E1F, 0x7F1D7DFD, 0xF0B6EF71, + 0x7FC177C1, 0xFBC86079, 0xE722FBC8, 0x5FFFDFFF, + 0x5FB2FFFB, 0xFBC8F3C8, 0x94A67F01, 0x7F1D5F39, + 0xAFE85F5E, 0xFFDFDF96, 0xCB9FAF7D, 0x5FC1AFED, + 0x8C1C5FC1, 0xAFDD5FC3, 0xDF9A7EFD, 0xB0B25FB2, + 0xFFFEABAD, 0x5FB2FFFE, 0x5FCE600B, 0xE6BB600B, + 0x5FCEDFC6, 0x27FBEFDF, 0x5FC8CFDE, 0x3A9CE7C0, + 0xEDF0F3C8, 0x7F0154CD, 0x7F1D2D3D, 0x363A7570, + 0x7E0AF1CE, 0x37EF2E68, 0x7FEE10EC, 0xADF8EFDE, + 0xCFEAE52F, 0x7D0FE12B, 0xF1CE5F65, 0x7E0A4DF8, + 0xCFEA5F72, 0x7D0BEFEE, 0xCFEA5F74, 0xE522EFDE, + 0x5F74CFDA, 0x0B627385, 0xDF627E0A, 0x30D8145B, + 0xBFFFF3C8, 0x5FFFDFFF, 0xA7F85F5E, 0xBFFE7F7D, + 0x10D31450, 0x5F36BFFF, 0xAF785F5E, 0xBFFDA7F8, + 0x5F36BFFE, 0x77FD30C0, 0x4E08FDCF, 0xE5FF6E0F, + 0xAFF87E1F, 0x7E0FFD1F, 0xF1CF5F1B, 0xABF80D5E, + 0x5F5EFFEF, 0x79F730A2, 0xAFDD5F34, 0x47F85F34, + 0xAFED7FDD, 0x50B24978, 0x47FD7F1D, 0x7DFD70AD, + 0xEF717EC1, 0x6BA47F01, 0x2D267EFD, 0x30DE5F5E, + 0xFFFD5F5E, 0xFFEF5F5E, 0xFFDF0CA0, 0xAFED0A9E, + 0xAFDD0C3A, 0x5F3AAFBD, 0x7FBDB082, 0x5F8247F8 +}; + +static uint patch_2f00[] __initdata = { + 0x3E303430, 0x34343737, 0xABF7BF9B, 0x994B4FBD, + 0xBD599493, 0x349FFF37, 0xFB9B177D, 0xD9936956, + 0xBBFDD697, 0xBDD2FD11, 0x31DB9BB3, 0x63139637, + 0x93733693, 0x193137F7, 0x331737AF, 0x7BB9B999, + 0xBB197957, 0x7FDFD3D5, 0x73B773F7, 0x37933B99, + 0x1D115316, 0x99315315, 0x31694BF4, 0xFBDBD359, + 0x31497353, 0x76956D69, 0x7B9D9693, 0x13131979, + 0x79376935 +}; + +static uint patch_2e00[] __initdata = {}; +#endif + +/* + * I2C/SPI/SMC1 relocation patch arrays. + */ + +#ifdef CONFIG_I2C_SPI_SMC1_UCODE_PATCH + +static char patch_name[] __initdata = "I2C/SPI/SMC1"; + +static struct patch_params patch_params __initdata = { + 3, 0x8080, 0x808a, 0x8028, 0x802a, +}; + +static uint patch_2000[] __initdata = { + 0x3fff0000, 0x3ffd0000, 0x3ffb0000, 0x3ff90000, + 0x5f13eff8, 0x5eb5eff8, 0x5f88adf7, 0x5fefadf7, + 0x3a9cfbc8, 0x77cae1bb, 0xf4de7fad, 0xabae9330, + 0x4e08fdcf, 0x6e0faff8, 0x7ccf76cf, 0xfdaff9cf, + 0xabf88dc8, 0xab5879f7, 0xb0925d8d, 0xdfd079f7, + 0xb090e6bb, 0xe5bbe74f, 0x9e046f0f, 0x6ffb76ce, + 0xee0cf9cf, 0x2bfbefef, 0xcfeef9cf, 0x76cead23, + 0x90b3df99, 0x7fddd0c1, 0x4bf847fd, 0x7ccf76ce, + 0xcfef77ca, 0x7eaf7fad, 0x7dfdf0b7, 0xef7a7fca, + 0x77cafbc8, 0x6079e722, 0xfbc85fff, 0xdfff5fb3, + 0xfffbfbc8, 0xf3c894a5, 0xe7c9edf9, 0x7f9a7fad, + 0x5f36afe8, 0x5f5bffdf, 0xdf95cb9e, 0xaf7d5fc3, + 0xafed8c1b, 0x5fc3afdd, 0x5fc5df99, 0x7efdb0b3, + 0x5fb3fffe, 0xabae5fb3, 0xfffe5fd0, 0x600be6bb, + 0x600b5fd0, 0xdfc827fb, 0xefdf5fca, 0xcfde3a9c, + 0xe7c9edf9, 0xf3c87f9e, 0x54ca7fed, 0x2d3a3637, + 0x756f7e9a, 0xf1ce37ef, 0x2e677fee, 0x10ebadf8, + 0xefdecfea, 0xe52f7d9f, 0xe12bf1ce, 0x5f647e9a, + 0x4df8cfea, 0x5f717d9b, 0xefeecfea, 0x5f73e522, + 0xefde5f73, 0xcfda0b61, 0x5d8fdf61, 0xe7c9edf9, + 0x7e9a30d5, 0x1458bfff, 0xf3c85fff, 0xdfffa7f8, + 0x5f5bbffe, 0x7f7d10d0, 0x144d5f33, 0xbfffaf78, + 0x5f5bbffd, 0xa7f85f33, 0xbffe77fd, 0x30bd4e08, + 0xfdcfe5ff, 0x6e0faff8, 0x7eef7e9f, 0xfdeff1cf, + 0x5f17abf8, 0x0d5b5f5b, 0xffef79f7, 0x309eafdd, + 0x5f3147f8, 0x5f31afed, 0x7fdd50af, 0x497847fd, + 0x7f9e7fed, 0x7dfd70a9, 0xef7e7ece, 0x6ba07f9e, + 0x2d227efd, 0x30db5f5b, 0xfffd5f5b, 0xffef5f5b, + 0xffdf0c9c, 0xafed0a9a, 0xafdd0c37, 0x5f37afbd, + 0x7fbdb081, 0x5f8147f8, 0x3a11e710, 0xedf0ccdd, + 0xf3186d0a, 0x7f0e5f06, 0x7fedbb38, 0x3afe7468, + 0x7fedf4fc, 0x8ffbb951, 0xb85f77fd, 0xb0df5ddd, + 0xdefe7fed, 0x90e1e74d, 0x6f0dcbf7, 0xe7decfed, + 0xcb74cfed, 0xcfeddf6d, 0x91714f74, 0x5dd2deef, + 0x9e04e7df, 0xefbb6ffb, 0xe7ef7f0e, 0x9e097fed, + 0xebdbeffa, 0xeb54affb, 0x7fea90d7, 0x7e0cf0c3, + 0xbffff318, 0x5fffdfff, 0xac59efea, 0x7fce1ee5, + 0xe2ff5ee1, 0xaffbe2ff, 0x5ee3affb, 0xf9cc7d0f, + 0xaef8770f, 0x7d0fb0c6, 0xeffbbfff, 0xcfef5ede, + 0x7d0fbfff, 0x5ede4cf8, 0x7fddd0bf, 0x49f847fd, + 0x7efdf0bb, 0x7fedfffd, 0x7dfdf0b7, 0xef7e7e1e, + 0x5ede7f0e, 0x3a11e710, 0xedf0ccab, 0xfb18ad2e, + 0x1ea9bbb8, 0x74283b7e, 0x73c2e4bb, 0x2ada4fb8, + 0xdc21e4bb, 0xb2a1ffbf, 0x5e2c43f8, 0xfc87e1bb, + 0xe74ffd91, 0x6f0f4fe8, 0xc7ba32e2, 0xf396efeb, + 0x600b4f78, 0xe5bb760b, 0x53acaef8, 0x4ef88b0e, + 0xcfef9e09, 0xabf8751f, 0xefef5bac, 0x741f4fe8, + 0x751e760d, 0x7fdbf081, 0x741cafce, 0xefcc7fce, + 0x751e70ac, 0x741ce7bb, 0x3372cfed, 0xafdbefeb, + 0xe5bb760b, 0x53f2aef8, 0xafe8e7eb, 0x4bf8771e, + 0x7e247fed, 0x4fcbe2cc, 0x7fbc30a9, 0x7b0f7a0f, + 0x34d577fd, 0x308b5db7, 0xde553e5f, 0xaf78741f, + 0x741f30f0, 0xcfef5e2c, 0x741f3eac, 0xafb8771e, + 0x5e677fed, 0x0bd3e2cc, 0x741ccfec, 0xe5ca53cd, + 0x6fcb4f74, 0x5dadde4b, 0x2ab63d38, 0x4bb3de30, + 0x751f741c, 0x6c42effa, 0xefea7fce, 0x6ffc30be, + 0xefec3fca, 0x30b3de2e, 0xadf85d9e, 0xaf7daefd, + 0x5d9ede2e, 0x5d9eafdd, 0x761f10ac, 0x1da07efd, + 0x30adfffe, 0x4908fb18, 0x5fffdfff, 0xafbb709b, + 0x4ef85e67, 0xadf814ad, 0x7a0f70ad, 0xcfef50ad, + 0x7a0fde30, 0x5da0afed, 0x3c12780f, 0xefef780f, + 0xefef790f, 0xa7f85e0f, 0xffef790f, 0xefef790f, + 0x14adde2e, 0x5d9eadfd, 0x5e2dfffb, 0xe79addfd, + 0xeff96079, 0x607ae79a, 0xddfceff9, 0x60795dff, + 0x607acfef, 0xefefefdf, 0xefbfef7f, 0xeeffedff, + 0xebffe7ff, 0xafefafdf, 0xafbfaf7f, 0xaeffadff, + 0xabffa7ff, 0x6fef6fdf, 0x6fbf6f7f, 0x6eff6dff, + 0x6bff67ff, 0x2fef2fdf, 0x2fbf2f7f, 0x2eff2dff, + 0x2bff27ff, 0x4e08fd1f, 0xe5ff6e0f, 0xaff87eef, + 0x7e0ffdef, 0xf11f6079, 0xabf8f542, 0x7e0af11c, + 0x37cfae3a, 0x7fec90be, 0xadf8efdc, 0xcfeae52f, + 0x7d0fe12b, 0xf11c6079, 0x7e0a4df8, 0xcfea5dc4, + 0x7d0befec, 0xcfea5dc6, 0xe522efdc, 0x5dc6cfda, + 0x4e08fd1f, 0x6e0faff8, 0x7c1f761f, 0xfdeff91f, + 0x6079abf8, 0x761cee24, 0xf91f2bfb, 0xefefcfec, + 0xf91f6079, 0x761c27fb, 0xefdf5da7, 0xcfdc7fdd, + 0xd09c4bf8, 0x47fd7c1f, 0x761ccfcf, 0x7eef7fed, + 0x7dfdf093, 0xef7e7f1e, 0x771efb18, 0x6079e722, + 0xe6bbe5bb, 0xae0ae5bb, 0x600bae85, 0xe2bbe2bb, + 0xe2bbe2bb, 0xaf02e2bb, 0xe2bb2ff9, 0x6079e2bb +}; + +static uint patch_2f00[] __initdata = { + 0x30303030, 0x3e3e3434, 0xabbf9b99, 0x4b4fbdbd, + 0x59949334, 0x9fff37fb, 0x9b177dd9, 0x936956bb, + 0xfbdd697b, 0xdd2fd113, 0x1db9f7bb, 0x36313963, + 0x79373369, 0x3193137f, 0x7331737a, 0xf7bb9b99, + 0x9bb19795, 0x77fdfd3d, 0x573b773f, 0x737933f7, + 0xb991d115, 0x31699315, 0x31531694, 0xbf4fbdbd, + 0x35931497, 0x35376956, 0xbd697b9d, 0x96931313, + 0x19797937, 0x6935af78, 0xb9b3baa3, 0xb8788683, + 0x368f78f7, 0x87778733, 0x3ffffb3b, 0x8e8f78b8, + 0x1d118e13, 0xf3ff3f8b, 0x6bd8e173, 0xd1366856, + 0x68d1687b, 0x3daf78b8, 0x3a3a3f87, 0x8f81378f, + 0xf876f887, 0x77fd8778, 0x737de8d6, 0xbbf8bfff, + 0xd8df87f7, 0xfd876f7b, 0x8bfff8bd, 0x8683387d, + 0xb873d87b, 0x3b8fd7f8, 0xf7338883, 0xbb8ee1f8, + 0xef837377, 0x3337b836, 0x817d11f8, 0x7378b878, + 0xd3368b7d, 0xed731b7d, 0x833731f3, 0xf22f3f23 +}; + +static uint patch_2e00[] __initdata = { + 0x27eeeeee, 0xeeeeeeee, 0xeeeeeeee, 0xeeeeeeee, + 0xee4bf4fb, 0xdbd259bb, 0x1979577f, 0xdfd2d573, + 0xb773f737, 0x4b4fbdbd, 0x25b9b177, 0xd2d17376, + 0x956bbfdd, 0x697bdd2f, 0xff9f79ff, 0xff9ff22f +}; +#endif + +/* + * USB SOF patch arrays. + */ + +#ifdef CONFIG_USB_SOF_UCODE_PATCH + +static char patch_name[] __initdata = "USB SOF"; + +static struct patch_params patch_params __initdata = { + 9, +}; + +static uint patch_2000[] __initdata = { + 0x7fff0000, 0x7ffd0000, 0x7ffb0000, 0x49f7ba5b, + 0xba383ffb, 0xf9b8b46d, 0xe5ab4e07, 0xaf77bffe, + 0x3f7bbf79, 0xba5bba38, 0xe7676076, 0x60750000 +}; + +static uint patch_2f00[] __initdata = { + 0x3030304c, 0xcab9e441, 0xa1aaf220 +}; + +static uint patch_2e00[] __initdata = {}; +#endif + +/* + * SMC relocation patch arrays. + */ + +#ifdef CONFIG_SMC_UCODE_PATCH + +static char patch_name[] __initdata = "SMC"; + +static struct patch_params patch_params __initdata = { + 2, 0x8080, 0x8088, +}; + +static uint patch_2000[] __initdata = { + 0x3fff0000, 0x3ffd0000, 0x3ffb0000, 0x3ff90000, + 0x5fefeff8, 0x5f91eff8, 0x3ff30000, 0x3ff10000, + 0x3a11e710, 0xedf0ccb9, 0xf318ed66, 0x7f0e5fe2, + 0x7fedbb38, 0x3afe7468, 0x7fedf4d8, 0x8ffbb92d, + 0xb83b77fd, 0xb0bb5eb9, 0xdfda7fed, 0x90bde74d, + 0x6f0dcbd3, 0xe7decfed, 0xcb50cfed, 0xcfeddf6d, + 0x914d4f74, 0x5eaedfcb, 0x9ee0e7df, 0xefbb6ffb, + 0xe7ef7f0e, 0x9ee57fed, 0xebb7effa, 0xeb30affb, + 0x7fea90b3, 0x7e0cf09f, 0xbffff318, 0x5fffdfff, + 0xac35efea, 0x7fce1fc1, 0xe2ff5fbd, 0xaffbe2ff, + 0x5fbfaffb, 0xf9a87d0f, 0xaef8770f, 0x7d0fb0a2, + 0xeffbbfff, 0xcfef5fba, 0x7d0fbfff, 0x5fba4cf8, + 0x7fddd09b, 0x49f847fd, 0x7efdf097, 0x7fedfffd, + 0x7dfdf093, 0xef7e7e1e, 0x5fba7f0e, 0x3a11e710, + 0xedf0cc87, 0xfb18ad0a, 0x1f85bbb8, 0x74283b7e, + 0x7375e4bb, 0x2ab64fb8, 0x5c7de4bb, 0x32fdffbf, + 0x5f0843f8, 0x7ce3e1bb, 0xe74f7ded, 0x6f0f4fe8, + 0xc7ba32be, 0x73f2efeb, 0x600b4f78, 0xe5bb760b, + 0x5388aef8, 0x4ef80b6a, 0xcfef9ee5, 0xabf8751f, + 0xefef5b88, 0x741f4fe8, 0x751e760d, 0x7fdb70dd, + 0x741cafce, 0xefcc7fce, 0x751e7088, 0x741ce7bb, + 0x334ecfed, 0xafdbefeb, 0xe5bb760b, 0x53ceaef8, + 0xafe8e7eb, 0x4bf8771e, 0x7e007fed, 0x4fcbe2cc, + 0x7fbc3085, 0x7b0f7a0f, 0x34b177fd, 0xb0e75e93, + 0xdf313e3b, 0xaf78741f, 0x741f30cc, 0xcfef5f08, + 0x741f3e88, 0xafb8771e, 0x5f437fed, 0x0bafe2cc, + 0x741ccfec, 0xe5ca53a9, 0x6fcb4f74, 0x5e89df27, + 0x2a923d14, 0x4b8fdf0c, 0x751f741c, 0x6c1eeffa, + 0xefea7fce, 0x6ffc309a, 0xefec3fca, 0x308fdf0a, + 0xadf85e7a, 0xaf7daefd, 0x5e7adf0a, 0x5e7aafdd, + 0x761f1088, 0x1e7c7efd, 0x3089fffe, 0x4908fb18, + 0x5fffdfff, 0xafbbf0f7, 0x4ef85f43, 0xadf81489, + 0x7a0f7089, 0xcfef5089, 0x7a0fdf0c, 0x5e7cafed, + 0xbc6e780f, 0xefef780f, 0xefef790f, 0xa7f85eeb, + 0xffef790f, 0xefef790f, 0x1489df0a, 0x5e7aadfd, + 0x5f09fffb, 0xe79aded9, 0xeff96079, 0x607ae79a, + 0xded8eff9, 0x60795edb, 0x607acfef, 0xefefefdf, + 0xefbfef7f, 0xeeffedff, 0xebffe7ff, 0xafefafdf, + 0xafbfaf7f, 0xaeffadff, 0xabffa7ff, 0x6fef6fdf, + 0x6fbf6f7f, 0x6eff6dff, 0x6bff67ff, 0x2fef2fdf, + 0x2fbf2f7f, 0x2eff2dff, 0x2bff27ff, 0x4e08fd1f, + 0xe5ff6e0f, 0xaff87eef, 0x7e0ffdef, 0xf11f6079, + 0xabf8f51e, 0x7e0af11c, 0x37cfae16, 0x7fec909a, + 0xadf8efdc, 0xcfeae52f, 0x7d0fe12b, 0xf11c6079, + 0x7e0a4df8, 0xcfea5ea0, 0x7d0befec, 0xcfea5ea2, + 0xe522efdc, 0x5ea2cfda, 0x4e08fd1f, 0x6e0faff8, + 0x7c1f761f, 0xfdeff91f, 0x6079abf8, 0x761cee00, + 0xf91f2bfb, 0xefefcfec, 0xf91f6079, 0x761c27fb, + 0xefdf5e83, 0xcfdc7fdd, 0x50f84bf8, 0x47fd7c1f, + 0x761ccfcf, 0x7eef7fed, 0x7dfd70ef, 0xef7e7f1e, + 0x771efb18, 0x6079e722, 0xe6bbe5bb, 0x2e66e5bb, + 0x600b2ee1, 0xe2bbe2bb, 0xe2bbe2bb, 0x2f5ee2bb, + 0xe2bb2ff9, 0x6079e2bb, +}; + +static uint patch_2f00[] __initdata = { + 0x30303030, 0x3e3e3030, 0xaf79b9b3, 0xbaa3b979, + 0x9693369f, 0x79f79777, 0x97333fff, 0xfb3b9e9f, + 0x79b91d11, 0x9e13f3ff, 0x3f9b6bd9, 0xe173d136, + 0x695669d1, 0x697b3daf, 0x79b93a3a, 0x3f979f91, + 0x379ff976, 0xf99777fd, 0x9779737d, 0xe9d6bbf9, + 0xbfffd9df, 0x97f7fd97, 0x6f7b9bff, 0xf9bd9683, + 0x397db973, 0xd97b3b9f, 0xd7f9f733, 0x9993bb9e, + 0xe1f9ef93, 0x73773337, 0xb936917d, 0x11f87379, + 0xb979d336, 0x8b7ded73, 0x1b7d9337, 0x31f3f22f, + 0x3f2327ee, 0xeeeeeeee, 0xeeeeeeee, 0xeeeeeeee, + 0xeeeeee4b, 0xf4fbdbd2, 0x58bb1878, 0x577fdfd2, + 0xd573b773, 0xf7374b4f, 0xbdbd25b8, 0xb177d2d1, + 0x7376856b, 0xbfdd687b, 0xdd2fff8f, 0x78ffff8f, + 0xf22f0000, +}; + +static uint patch_2e00[] __initdata = {}; +#endif + +static void __init cpm_write_patch(cpm8xx_t *cp, int offset, uint *patch, int len) +{ + if (!len) + return; + memcpy_toio(cp->cp_dpmem + offset, patch, len); +} + +void __init cpm_load_patch(cpm8xx_t *cp) +{ + out_be16(&cp->cp_rccr, 0); + + cpm_write_patch(cp, 0, patch_2000, sizeof(patch_2000)); + cpm_write_patch(cp, 0xf00, patch_2f00, sizeof(patch_2f00)); + cpm_write_patch(cp, 0xe00, patch_2e00, sizeof(patch_2e00)); + + if (IS_ENABLED(CONFIG_I2C_SPI_UCODE_PATCH) || + IS_ENABLED(CONFIG_I2C_SPI_SMC1_UCODE_PATCH)) { + u16 rpbase = 0x500; + iic_t *iip; + struct spi_pram *spp; + + iip = (iic_t *)&cp->cp_dparam[PROFF_IIC]; + out_be16(&iip->iic_rpbase, rpbase); + + /* Put SPI above the IIC, also 32-byte aligned. */ + spp = (struct spi_pram *)&cp->cp_dparam[PROFF_SPI]; + out_be16(&spp->rpbase, (rpbase + sizeof(iic_t) + 31) & ~31); + + if (IS_ENABLED(CONFIG_I2C_SPI_SMC1_UCODE_PATCH)) { + smc_uart_t *smp; + + smp = (smc_uart_t *)&cp->cp_dparam[PROFF_SMC1]; + out_be16(&smp->smc_rpbase, 0x1FC0); + } + } + + if (IS_ENABLED(CONFIG_SMC_UCODE_PATCH)) { + smc_uart_t *smp; + + smp = (smc_uart_t *)&cp->cp_dparam[PROFF_SMC1]; + out_be16(&smp->smc_rpbase, 0x1ec0); + smp = (smc_uart_t *)&cp->cp_dparam[PROFF_SMC2]; + out_be16(&smp->smc_rpbase, 0x1fc0); + } + + out_be16(&cp->cp_cpmcr1, patch_params.cpmcr1); + out_be16(&cp->cp_cpmcr2, patch_params.cpmcr2); + out_be16(&cp->cp_cpmcr3, patch_params.cpmcr3); + out_be16(&cp->cp_cpmcr4, patch_params.cpmcr4); + + out_be16(&cp->cp_rccr, patch_params.rccr); + + pr_info("%s microcode patch installed\n", patch_name); +} diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype index 2794235e9d3e..56a7c814160d 100644 --- a/arch/powerpc/platforms/Kconfig.cputype +++ b/arch/powerpc/platforms/Kconfig.cputype @@ -330,7 +330,7 @@ config ARCH_ENABLE_SPLIT_PMD_PTLOCK config PPC_RADIX_MMU bool "Radix MMU Support" - depends on PPC_BOOK3S_64 && HUGETLB_PAGE + depends on PPC_BOOK3S_64 select ARCH_HAS_GIGANTIC_PAGE select PPC_HAVE_KUEP select PPC_HAVE_KUAP diff --git a/arch/powerpc/platforms/cell/spufs/file.c b/arch/powerpc/platforms/cell/spufs/file.c index d40253a18b1c..c0f950a3f4e1 100644 --- a/arch/powerpc/platforms/cell/spufs/file.c +++ b/arch/powerpc/platforms/cell/spufs/file.c @@ -446,7 +446,7 @@ static const struct file_operations spufs_cntl_fops = { .release = spufs_cntl_release, .read = simple_attr_read, .write = simple_attr_write, - .llseek = generic_file_llseek, + .llseek = no_llseek, .mmap = spufs_cntl_mmap, }; diff --git a/arch/powerpc/platforms/maple/Kconfig b/arch/powerpc/platforms/maple/Kconfig index 08d530a2a8b1..86ae210bee9a 100644 --- a/arch/powerpc/platforms/maple/Kconfig +++ b/arch/powerpc/platforms/maple/Kconfig @@ -14,5 +14,5 @@ config PPC_MAPLE select MMIO_NVRAM select ATA_NONSTANDARD if ATA help - This option enables support for the Maple 970FX Evaluation Board. + This option enables support for the Maple 970FX Evaluation Board. For more information, refer to <http://www.970eval.com> diff --git a/arch/powerpc/platforms/powermac/sleep.S b/arch/powerpc/platforms/powermac/sleep.S index 6bbcbec97712..bd6085b470b7 100644 --- a/arch/powerpc/platforms/powermac/sleep.S +++ b/arch/powerpc/platforms/powermac/sleep.S @@ -33,10 +33,18 @@ #define SL_IBAT2 0x48 #define SL_DBAT3 0x50 #define SL_IBAT3 0x58 -#define SL_TB 0x60 -#define SL_R2 0x68 -#define SL_CR 0x6c -#define SL_R12 0x70 /* r12 to r31 */ +#define SL_DBAT4 0x60 +#define SL_IBAT4 0x68 +#define SL_DBAT5 0x70 +#define SL_IBAT5 0x78 +#define SL_DBAT6 0x80 +#define SL_IBAT6 0x88 +#define SL_DBAT7 0x90 +#define SL_IBAT7 0x98 +#define SL_TB 0xa0 +#define SL_R2 0xa8 +#define SL_CR 0xac +#define SL_R12 0xb0 /* r12 to r31 */ #define SL_SIZE (SL_R12 + 80) .section .text @@ -121,6 +129,41 @@ _GLOBAL(low_sleep_handler) mfibatl r4,3 stw r4,SL_IBAT3+4(r1) +BEGIN_MMU_FTR_SECTION + mfspr r4,SPRN_DBAT4U + stw r4,SL_DBAT4(r1) + mfspr r4,SPRN_DBAT4L + stw r4,SL_DBAT4+4(r1) + mfspr r4,SPRN_DBAT5U + stw r4,SL_DBAT5(r1) + mfspr r4,SPRN_DBAT5L + stw r4,SL_DBAT5+4(r1) + mfspr r4,SPRN_DBAT6U + stw r4,SL_DBAT6(r1) + mfspr r4,SPRN_DBAT6L + stw r4,SL_DBAT6+4(r1) + mfspr r4,SPRN_DBAT7U + stw r4,SL_DBAT7(r1) + mfspr r4,SPRN_DBAT7L + stw r4,SL_DBAT7+4(r1) + mfspr r4,SPRN_IBAT4U + stw r4,SL_IBAT4(r1) + mfspr r4,SPRN_IBAT4L + stw r4,SL_IBAT4+4(r1) + mfspr r4,SPRN_IBAT5U + stw r4,SL_IBAT5(r1) + mfspr r4,SPRN_IBAT5L + stw r4,SL_IBAT5+4(r1) + mfspr r4,SPRN_IBAT6U + stw r4,SL_IBAT6(r1) + mfspr r4,SPRN_IBAT6L + stw r4,SL_IBAT6+4(r1) + mfspr r4,SPRN_IBAT7U + stw r4,SL_IBAT7(r1) + mfspr r4,SPRN_IBAT7L + stw r4,SL_IBAT7+4(r1) +END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS) + /* Backup various CPU config stuffs */ bl __save_cpu_setup @@ -321,22 +364,37 @@ grackle_wake_up: mtibatl 3,r4 BEGIN_MMU_FTR_SECTION - li r4,0 + lwz r4,SL_DBAT4(r1) mtspr SPRN_DBAT4U,r4 + lwz r4,SL_DBAT4+4(r1) mtspr SPRN_DBAT4L,r4 + lwz r4,SL_DBAT5(r1) mtspr SPRN_DBAT5U,r4 + lwz r4,SL_DBAT5+4(r1) mtspr SPRN_DBAT5L,r4 + lwz r4,SL_DBAT6(r1) mtspr SPRN_DBAT6U,r4 + lwz r4,SL_DBAT6+4(r1) mtspr SPRN_DBAT6L,r4 + lwz r4,SL_DBAT7(r1) mtspr SPRN_DBAT7U,r4 + lwz r4,SL_DBAT7+4(r1) mtspr SPRN_DBAT7L,r4 + lwz r4,SL_IBAT4(r1) mtspr SPRN_IBAT4U,r4 + lwz r4,SL_IBAT4+4(r1) mtspr SPRN_IBAT4L,r4 + lwz r4,SL_IBAT5(r1) mtspr SPRN_IBAT5U,r4 + lwz r4,SL_IBAT5+4(r1) mtspr SPRN_IBAT5L,r4 + lwz r4,SL_IBAT6(r1) mtspr SPRN_IBAT6U,r4 + lwz r4,SL_IBAT6+4(r1) mtspr SPRN_IBAT6L,r4 + lwz r4,SL_IBAT7(r1) mtspr SPRN_IBAT7U,r4 + lwz r4,SL_IBAT7+4(r1) mtspr SPRN_IBAT7L,r4 END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS) diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c index 9ade4489f415..620a986209f5 100644 --- a/arch/powerpc/platforms/powernv/eeh-powernv.c +++ b/arch/powerpc/platforms/powernv/eeh-powernv.c @@ -1,8 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* - * The file intends to implement the platform dependent EEH operations on - * powernv platform. Actually, the powernv was created in order to fully - * hypervisor support. + * PowerNV Platform dependent EEH operations * * Copyright Benjamin Herrenschmidt & Gavin Shan, IBM Corporation 2013. */ diff --git a/arch/powerpc/platforms/powernv/idle.c b/arch/powerpc/platforms/powernv/idle.c index 2f4479b94ac3..09f49eed7fb8 100644 --- a/arch/powerpc/platforms/powernv/idle.c +++ b/arch/powerpc/platforms/powernv/idle.c @@ -716,7 +716,7 @@ static unsigned long power9_idle_stop(unsigned long psscr, bool mmu_on) * to reload MMCR0 (see mmcr0 comment above). */ if (!cpu_has_feature(CPU_FTR_POWER9_DD2_1)) { - asm volatile(PPC_INVALIDATE_ERAT); + asm volatile(PPC_ISA_3_0_INVALIDATE_ERAT); mtspr(SPRN_MMCR0, mmcr0); } @@ -758,7 +758,6 @@ static unsigned long power9_idle_stop(unsigned long psscr, bool mmu_on) mtspr(SPRN_PTCR, sprs.ptcr); mtspr(SPRN_RPR, sprs.rpr); mtspr(SPRN_TSCR, sprs.tscr); - mtspr(SPRN_LDBAR, sprs.ldbar); if (pls >= pnv_first_tb_loss_level) { /* TB loss */ @@ -790,6 +789,7 @@ core_woken: mtspr(SPRN_MMCR0, sprs.mmcr0); mtspr(SPRN_MMCR1, sprs.mmcr1); mtspr(SPRN_MMCR2, sprs.mmcr2); + mtspr(SPRN_LDBAR, sprs.ldbar); mtspr(SPRN_SPRG3, local_paca->sprg_vdso); @@ -1155,10 +1155,10 @@ static void __init pnv_power9_idle_init(void) pnv_deepest_stop_psscr_mask); } - pr_info("cpuidle-powernv: First stop level that may lose SPRs = 0x%lld\n", + pr_info("cpuidle-powernv: First stop level that may lose SPRs = 0x%llx\n", pnv_first_spr_loss_level); - pr_info("cpuidle-powernv: First stop level that may lose timebase = 0x%lld\n", + pr_info("cpuidle-powernv: First stop level that may lose timebase = 0x%llx\n", pnv_first_tb_loss_level); } diff --git a/arch/powerpc/platforms/powernv/npu-dma.c b/arch/powerpc/platforms/powernv/npu-dma.c index c321fdbc2200..c16249d251f1 100644 --- a/arch/powerpc/platforms/powernv/npu-dma.c +++ b/arch/powerpc/platforms/powernv/npu-dma.c @@ -19,18 +19,25 @@ #include "pci.h" -/* - * spinlock to protect initialisation of an npu_context for a particular - * mm_struct. - */ -static DEFINE_SPINLOCK(npu_context_lock); - static struct pci_dev *get_pci_dev(struct device_node *dn) { struct pci_dn *pdn = PCI_DN(dn); + struct pci_dev *pdev; - return pci_get_domain_bus_and_slot(pci_domain_nr(pdn->phb->bus), + pdev = pci_get_domain_bus_and_slot(pci_domain_nr(pdn->phb->bus), pdn->busno, pdn->devfn); + + /* + * pci_get_domain_bus_and_slot() increased the reference count of + * the PCI device, but callers don't need that actually as the PE + * already holds a reference to the device. Since callers aren't + * aware of the reference count change, call pci_dev_put() now to + * avoid leaks. + */ + if (pdev) + pci_dev_put(pdev); + + return pdev; } /* Given a NPU device get the associated PCI device. */ @@ -359,15 +366,6 @@ struct npu_comp { /* An NPU descriptor, valid for POWER9 only */ struct npu { int index; - __be64 *mmio_atsd_regs[NV_NMMU_ATSD_REGS]; - unsigned int mmio_atsd_count; - - /* Bitmask for MMIO register usage */ - unsigned long mmio_atsd_usage; - - /* Do we need to explicitly flush the nest mmu? */ - bool nmmu_flush; - struct npu_comp npucomp; }; @@ -624,534 +622,8 @@ struct iommu_table_group *pnv_npu_compound_attach(struct pnv_ioda_pe *pe) } #endif /* CONFIG_IOMMU_API */ -/* Maximum number of nvlinks per npu */ -#define NV_MAX_LINKS 6 - -/* Maximum index of npu2 hosts in the system. Always < NV_MAX_NPUS */ -static int max_npu2_index; - -struct npu_context { - struct mm_struct *mm; - struct pci_dev *npdev[NV_MAX_NPUS][NV_MAX_LINKS]; - struct mmu_notifier mn; - struct kref kref; - bool nmmu_flush; - - /* Callback to stop translation requests on a given GPU */ - void (*release_cb)(struct npu_context *context, void *priv); - - /* - * Private pointer passed to the above callback for usage by - * device drivers. - */ - void *priv; -}; - -struct mmio_atsd_reg { - struct npu *npu; - int reg; -}; - -/* - * Find a free MMIO ATSD register and mark it in use. Return -ENOSPC - * if none are available. - */ -static int get_mmio_atsd_reg(struct npu *npu) -{ - int i; - - for (i = 0; i < npu->mmio_atsd_count; i++) { - if (!test_bit(i, &npu->mmio_atsd_usage)) - if (!test_and_set_bit_lock(i, &npu->mmio_atsd_usage)) - return i; - } - - return -ENOSPC; -} - -static void put_mmio_atsd_reg(struct npu *npu, int reg) -{ - clear_bit_unlock(reg, &npu->mmio_atsd_usage); -} - -/* MMIO ATSD register offsets */ -#define XTS_ATSD_LAUNCH 0 -#define XTS_ATSD_AVA 1 -#define XTS_ATSD_STAT 2 - -static unsigned long get_atsd_launch_val(unsigned long pid, unsigned long psize) -{ - unsigned long launch = 0; - - if (psize == MMU_PAGE_COUNT) { - /* IS set to invalidate entire matching PID */ - launch |= PPC_BIT(12); - } else { - /* AP set to invalidate region of psize */ - launch |= (u64)mmu_get_ap(psize) << PPC_BITLSHIFT(17); - } - - /* PRS set to process-scoped */ - launch |= PPC_BIT(13); - - /* PID */ - launch |= pid << PPC_BITLSHIFT(38); - - /* Leave "No flush" (bit 39) 0 so every ATSD performs a flush */ - - return launch; -} - -static void mmio_atsd_regs_write(struct mmio_atsd_reg - mmio_atsd_reg[NV_MAX_NPUS], unsigned long offset, - unsigned long val) -{ - struct npu *npu; - int i, reg; - - for (i = 0; i <= max_npu2_index; i++) { - reg = mmio_atsd_reg[i].reg; - if (reg < 0) - continue; - - npu = mmio_atsd_reg[i].npu; - __raw_writeq_be(val, npu->mmio_atsd_regs[reg] + offset); - } -} - -static void mmio_invalidate_pid(struct mmio_atsd_reg mmio_atsd_reg[NV_MAX_NPUS], - unsigned long pid) -{ - unsigned long launch = get_atsd_launch_val(pid, MMU_PAGE_COUNT); - - /* Invalidating the entire process doesn't use a va */ - mmio_atsd_regs_write(mmio_atsd_reg, XTS_ATSD_LAUNCH, launch); -} - -static void mmio_invalidate_range(struct mmio_atsd_reg - mmio_atsd_reg[NV_MAX_NPUS], unsigned long pid, - unsigned long start, unsigned long psize) -{ - unsigned long launch = get_atsd_launch_val(pid, psize); - - /* Write all VAs first */ - mmio_atsd_regs_write(mmio_atsd_reg, XTS_ATSD_AVA, start); - - /* Issue one barrier for all address writes */ - eieio(); - - /* Launch */ - mmio_atsd_regs_write(mmio_atsd_reg, XTS_ATSD_LAUNCH, launch); -} - -#define mn_to_npu_context(x) container_of(x, struct npu_context, mn) - -static void mmio_invalidate_wait( - struct mmio_atsd_reg mmio_atsd_reg[NV_MAX_NPUS]) -{ - struct npu *npu; - int i, reg; - - /* Wait for all invalidations to complete */ - for (i = 0; i <= max_npu2_index; i++) { - if (mmio_atsd_reg[i].reg < 0) - continue; - - /* Wait for completion */ - npu = mmio_atsd_reg[i].npu; - reg = mmio_atsd_reg[i].reg; - while (__raw_readq(npu->mmio_atsd_regs[reg] + XTS_ATSD_STAT)) - cpu_relax(); - } -} - -/* - * Acquires all the address translation shootdown (ATSD) registers required to - * launch an ATSD on all links this npu_context is active on. - */ -static void acquire_atsd_reg(struct npu_context *npu_context, - struct mmio_atsd_reg mmio_atsd_reg[NV_MAX_NPUS]) -{ - int i, j; - struct npu *npu; - struct pci_dev *npdev; - - for (i = 0; i <= max_npu2_index; i++) { - mmio_atsd_reg[i].reg = -1; - for (j = 0; j < NV_MAX_LINKS; j++) { - /* - * There are no ordering requirements with respect to - * the setup of struct npu_context, but to ensure - * consistent behaviour we need to ensure npdev[][] is - * only read once. - */ - npdev = READ_ONCE(npu_context->npdev[i][j]); - if (!npdev) - continue; - - npu = pci_bus_to_host(npdev->bus)->npu; - if (!npu) - continue; - - mmio_atsd_reg[i].npu = npu; - mmio_atsd_reg[i].reg = get_mmio_atsd_reg(npu); - while (mmio_atsd_reg[i].reg < 0) { - mmio_atsd_reg[i].reg = get_mmio_atsd_reg(npu); - cpu_relax(); - } - break; - } - } -} - -/* - * Release previously acquired ATSD registers. To avoid deadlocks the registers - * must be released in the same order they were acquired above in - * acquire_atsd_reg. - */ -static void release_atsd_reg(struct mmio_atsd_reg mmio_atsd_reg[NV_MAX_NPUS]) -{ - int i; - - for (i = 0; i <= max_npu2_index; i++) { - /* - * We can't rely on npu_context->npdev[][] being the same here - * as when acquire_atsd_reg() was called, hence we use the - * values stored in mmio_atsd_reg during the acquire phase - * rather than re-reading npdev[][]. - */ - if (mmio_atsd_reg[i].reg < 0) - continue; - - put_mmio_atsd_reg(mmio_atsd_reg[i].npu, mmio_atsd_reg[i].reg); - } -} - -/* - * Invalidate a virtual address range - */ -static void mmio_invalidate(struct npu_context *npu_context, - unsigned long start, unsigned long size) -{ - struct mmio_atsd_reg mmio_atsd_reg[NV_MAX_NPUS]; - unsigned long pid = npu_context->mm->context.id; - unsigned long atsd_start = 0; - unsigned long end = start + size - 1; - int atsd_psize = MMU_PAGE_COUNT; - - /* - * Convert the input range into one of the supported sizes. If the range - * doesn't fit, use the next larger supported size. Invalidation latency - * is high, so over-invalidation is preferred to issuing multiple - * invalidates. - * - * A 4K page size isn't supported by NPU/GPU ATS, so that case is - * ignored. - */ - if (size == SZ_64K) { - atsd_start = start; - atsd_psize = MMU_PAGE_64K; - } else if (ALIGN_DOWN(start, SZ_2M) == ALIGN_DOWN(end, SZ_2M)) { - atsd_start = ALIGN_DOWN(start, SZ_2M); - atsd_psize = MMU_PAGE_2M; - } else if (ALIGN_DOWN(start, SZ_1G) == ALIGN_DOWN(end, SZ_1G)) { - atsd_start = ALIGN_DOWN(start, SZ_1G); - atsd_psize = MMU_PAGE_1G; - } - - if (npu_context->nmmu_flush) - /* - * Unfortunately the nest mmu does not support flushing specific - * addresses so we have to flush the whole mm once before - * shooting down the GPU translation. - */ - flush_all_mm(npu_context->mm); - - /* - * Loop over all the NPUs this process is active on and launch - * an invalidate. - */ - acquire_atsd_reg(npu_context, mmio_atsd_reg); - - if (atsd_psize == MMU_PAGE_COUNT) - mmio_invalidate_pid(mmio_atsd_reg, pid); - else - mmio_invalidate_range(mmio_atsd_reg, pid, atsd_start, - atsd_psize); - - mmio_invalidate_wait(mmio_atsd_reg); - - /* - * The GPU requires two flush ATSDs to ensure all entries have been - * flushed. We use PID 0 as it will never be used for a process on the - * GPU. - */ - mmio_invalidate_pid(mmio_atsd_reg, 0); - mmio_invalidate_wait(mmio_atsd_reg); - mmio_invalidate_pid(mmio_atsd_reg, 0); - mmio_invalidate_wait(mmio_atsd_reg); - - release_atsd_reg(mmio_atsd_reg); -} - -static void pnv_npu2_mn_release(struct mmu_notifier *mn, - struct mm_struct *mm) -{ - struct npu_context *npu_context = mn_to_npu_context(mn); - - /* Call into device driver to stop requests to the NMMU */ - if (npu_context->release_cb) - npu_context->release_cb(npu_context, npu_context->priv); - - /* - * There should be no more translation requests for this PID, but we - * need to ensure any entries for it are removed from the TLB. - */ - mmio_invalidate(npu_context, 0, ~0UL); -} - -static void pnv_npu2_mn_invalidate_range(struct mmu_notifier *mn, - struct mm_struct *mm, - unsigned long start, unsigned long end) -{ - struct npu_context *npu_context = mn_to_npu_context(mn); - mmio_invalidate(npu_context, start, end - start); -} - -static const struct mmu_notifier_ops nv_nmmu_notifier_ops = { - .release = pnv_npu2_mn_release, - .invalidate_range = pnv_npu2_mn_invalidate_range, -}; - -/* - * Call into OPAL to setup the nmmu context for the current task in - * the NPU. This must be called to setup the context tables before the - * GPU issues ATRs. pdev should be a pointed to PCIe GPU device. - * - * A release callback should be registered to allow a device driver to - * be notified that it should not launch any new translation requests - * as the final TLB invalidate is about to occur. - * - * Returns an error if there no contexts are currently available or a - * npu_context which should be passed to pnv_npu2_handle_fault(). - * - * mmap_sem must be held in write mode and must not be called from interrupt - * context. - */ -struct npu_context *pnv_npu2_init_context(struct pci_dev *gpdev, - unsigned long flags, - void (*cb)(struct npu_context *, void *), - void *priv) -{ - int rc; - u32 nvlink_index; - struct device_node *nvlink_dn; - struct mm_struct *mm = current->mm; - struct npu *npu; - struct npu_context *npu_context; - struct pci_controller *hose; - - /* - * At present we don't support GPUs connected to multiple NPUs and I'm - * not sure the hardware does either. - */ - struct pci_dev *npdev = pnv_pci_get_npu_dev(gpdev, 0); - - if (!npdev) - /* No nvlink associated with this GPU device */ - return ERR_PTR(-ENODEV); - - /* We only support DR/PR/HV in pnv_npu2_map_lpar_dev() */ - if (flags & ~(MSR_DR | MSR_PR | MSR_HV)) - return ERR_PTR(-EINVAL); - - nvlink_dn = of_parse_phandle(npdev->dev.of_node, "ibm,nvlink", 0); - if (WARN_ON(of_property_read_u32(nvlink_dn, "ibm,npu-link-index", - &nvlink_index))) - return ERR_PTR(-ENODEV); - - if (!mm || mm->context.id == 0) { - /* - * Kernel thread contexts are not supported and context id 0 is - * reserved on the GPU. - */ - return ERR_PTR(-EINVAL); - } - - hose = pci_bus_to_host(npdev->bus); - npu = hose->npu; - if (!npu) - return ERR_PTR(-ENODEV); - - /* - * We store the npu pci device so we can more easily get at the - * associated npus. - */ - spin_lock(&npu_context_lock); - npu_context = mm->context.npu_context; - if (npu_context) { - if (npu_context->release_cb != cb || - npu_context->priv != priv) { - spin_unlock(&npu_context_lock); - return ERR_PTR(-EINVAL); - } - - WARN_ON(!kref_get_unless_zero(&npu_context->kref)); - } - spin_unlock(&npu_context_lock); - - if (!npu_context) { - /* - * We can set up these fields without holding the - * npu_context_lock as the npu_context hasn't been returned to - * the caller meaning it can't be destroyed. Parallel allocation - * is protected against by mmap_sem. - */ - rc = -ENOMEM; - npu_context = kzalloc(sizeof(struct npu_context), GFP_KERNEL); - if (npu_context) { - kref_init(&npu_context->kref); - npu_context->mm = mm; - npu_context->mn.ops = &nv_nmmu_notifier_ops; - rc = __mmu_notifier_register(&npu_context->mn, mm); - } - - if (rc) { - kfree(npu_context); - return ERR_PTR(rc); - } - - mm->context.npu_context = npu_context; - } - - npu_context->release_cb = cb; - npu_context->priv = priv; - - /* - * npdev is a pci_dev pointer setup by the PCI code. We assign it to - * npdev[][] to indicate to the mmu notifiers that an invalidation - * should also be sent over this nvlink. The notifiers don't use any - * other fields in npu_context, so we just need to ensure that when they - * deference npu_context->npdev[][] it is either a valid pointer or - * NULL. - */ - WRITE_ONCE(npu_context->npdev[npu->index][nvlink_index], npdev); - - if (!npu->nmmu_flush) { - /* - * If we're not explicitly flushing ourselves we need to mark - * the thread for global flushes - */ - npu_context->nmmu_flush = false; - mm_context_add_copro(mm); - } else - npu_context->nmmu_flush = true; - - return npu_context; -} -EXPORT_SYMBOL(pnv_npu2_init_context); - -static void pnv_npu2_release_context(struct kref *kref) -{ - struct npu_context *npu_context = - container_of(kref, struct npu_context, kref); - - if (!npu_context->nmmu_flush) - mm_context_remove_copro(npu_context->mm); - - npu_context->mm->context.npu_context = NULL; -} - -/* - * Destroy a context on the given GPU. May free the npu_context if it is no - * longer active on any GPUs. Must not be called from interrupt context. - */ -void pnv_npu2_destroy_context(struct npu_context *npu_context, - struct pci_dev *gpdev) -{ - int removed; - struct npu *npu; - struct pci_dev *npdev = pnv_pci_get_npu_dev(gpdev, 0); - struct device_node *nvlink_dn; - u32 nvlink_index; - struct pci_controller *hose; - - if (WARN_ON(!npdev)) - return; - - hose = pci_bus_to_host(npdev->bus); - npu = hose->npu; - if (!npu) - return; - nvlink_dn = of_parse_phandle(npdev->dev.of_node, "ibm,nvlink", 0); - if (WARN_ON(of_property_read_u32(nvlink_dn, "ibm,npu-link-index", - &nvlink_index))) - return; - WRITE_ONCE(npu_context->npdev[npu->index][nvlink_index], NULL); - spin_lock(&npu_context_lock); - removed = kref_put(&npu_context->kref, pnv_npu2_release_context); - spin_unlock(&npu_context_lock); - - /* - * We need to do this outside of pnv_npu2_release_context so that it is - * outside the spinlock as mmu_notifier_destroy uses SRCU. - */ - if (removed) { - mmu_notifier_unregister(&npu_context->mn, - npu_context->mm); - - kfree(npu_context); - } - -} -EXPORT_SYMBOL(pnv_npu2_destroy_context); - -/* - * Assumes mmap_sem is held for the contexts associated mm. - */ -int pnv_npu2_handle_fault(struct npu_context *context, uintptr_t *ea, - unsigned long *flags, unsigned long *status, int count) -{ - u64 rc = 0, result = 0; - int i, is_write; - struct page *page[1]; - const char __user *u; - char c; - - /* mmap_sem should be held so the struct_mm must be present */ - struct mm_struct *mm = context->mm; - - WARN_ON(!rwsem_is_locked(&mm->mmap_sem)); - - for (i = 0; i < count; i++) { - is_write = flags[i] & NPU2_WRITE; - rc = get_user_pages_remote(NULL, mm, ea[i], 1, - is_write ? FOLL_WRITE : 0, - page, NULL, NULL); - - if (rc != 1) { - status[i] = rc; - result = -EFAULT; - continue; - } - - /* Make sure partition scoped tree gets a pte */ - u = page_address(page[0]); - if (__get_user(c, u)) - result = -EFAULT; - - status[i] = 0; - put_page(page[0]); - } - - return result; -} -EXPORT_SYMBOL(pnv_npu2_handle_fault); - int pnv_npu2_init(struct pci_controller *hose) { - unsigned int i; - u64 mmio_atsd; static int npu_index; struct npu *npu; int ret; @@ -1160,33 +632,18 @@ int pnv_npu2_init(struct pci_controller *hose) if (!npu) return -ENOMEM; - npu->nmmu_flush = of_property_read_bool(hose->dn, "ibm,nmmu-flush"); - - for (i = 0; i < ARRAY_SIZE(npu->mmio_atsd_regs) && - !of_property_read_u64_index(hose->dn, "ibm,mmio-atsd", - i, &mmio_atsd); i++) - npu->mmio_atsd_regs[i] = ioremap(mmio_atsd, 32); - - pr_info("NPU%d: Found %d MMIO ATSD registers", hose->global_number, i); - npu->mmio_atsd_count = i; - npu->mmio_atsd_usage = 0; npu_index++; if (WARN_ON(npu_index >= NV_MAX_NPUS)) { ret = -ENOSPC; goto fail_exit; } - max_npu2_index = npu_index; npu->index = npu_index; hose->npu = npu; return 0; fail_exit: - for (i = 0; i < npu->mmio_atsd_count; ++i) - iounmap(npu->mmio_atsd_regs[i]); - kfree(npu); - return ret; } diff --git a/arch/powerpc/platforms/powernv/opal-call.c b/arch/powerpc/platforms/powernv/opal-call.c index 36c8fa3647a2..29ca523c1c79 100644 --- a/arch/powerpc/platforms/powernv/opal-call.c +++ b/arch/powerpc/platforms/powernv/opal-call.c @@ -273,7 +273,6 @@ OPAL_CALL(opal_npu_map_lpar, OPAL_NPU_MAP_LPAR); OPAL_CALL(opal_imc_counters_init, OPAL_IMC_COUNTERS_INIT); OPAL_CALL(opal_imc_counters_start, OPAL_IMC_COUNTERS_START); OPAL_CALL(opal_imc_counters_stop, OPAL_IMC_COUNTERS_STOP); -OPAL_CALL(opal_pci_set_p2p, OPAL_PCI_SET_P2P); OPAL_CALL(opal_get_powercap, OPAL_GET_POWERCAP); OPAL_CALL(opal_set_powercap, OPAL_SET_POWERCAP); OPAL_CALL(opal_get_power_shift_ratio, OPAL_GET_POWER_SHIFT_RATIO); diff --git a/arch/powerpc/platforms/powernv/opal-hmi.c b/arch/powerpc/platforms/powernv/opal-hmi.c index 5cae375525d0..3e1f064a18db 100644 --- a/arch/powerpc/platforms/powernv/opal-hmi.c +++ b/arch/powerpc/platforms/powernv/opal-hmi.c @@ -137,6 +137,43 @@ static void print_nx_checkstop_reason(const char *level, xstop_reason[i].description); } +static void print_npu_checkstop_reason(const char *level, + struct OpalHMIEvent *hmi_evt) +{ + uint8_t reason, reason_count, i; + + /* + * We may not have a checkstop reason on some combination of + * hardware and/or skiboot version + */ + if (!hmi_evt->u.xstop_error.xstop_reason) { + printk("%s NPU checkstop on chip %x\n", level, + be32_to_cpu(hmi_evt->u.xstop_error.u.chip_id)); + return; + } + + /* + * NPU2 has 3 FIRs. Reason encoded on a byte as: + * 2 bits for the FIR number + * 6 bits for the bit number + * It may be possible to find several reasons. + * + * We don't display a specific message per FIR bit as there + * are too many and most are meaningless without the workbook + * and/or hw team help anyway. + */ + reason_count = sizeof(hmi_evt->u.xstop_error.xstop_reason) / + sizeof(reason); + for (i = 0; i < reason_count; i++) { + reason = (hmi_evt->u.xstop_error.xstop_reason >> (8 * i)) & 0xFF; + if (reason) + printk("%s NPU checkstop on chip %x: FIR%d bit %d is set\n", + level, + be32_to_cpu(hmi_evt->u.xstop_error.u.chip_id), + reason >> 6, reason & 0x3F); + } +} + static void print_checkstop_reason(const char *level, struct OpalHMIEvent *hmi_evt) { @@ -148,6 +185,9 @@ static void print_checkstop_reason(const char *level, case CHECKSTOP_TYPE_NX: print_nx_checkstop_reason(level, hmi_evt); break; + case CHECKSTOP_TYPE_NPU: + print_npu_checkstop_reason(level, hmi_evt); + break; default: printk("%s Unknown Malfunction Alert of type %d\n", level, type); diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c index 98c5d94b17fb..aba443be7daa 100644 --- a/arch/powerpc/platforms/powernv/opal.c +++ b/arch/powerpc/platforms/powernv/opal.c @@ -202,16 +202,18 @@ static int __init opal_register_exception_handlers(void) glue = 0x7000; /* - * Check if we are running on newer firmware that exports - * OPAL_HANDLE_HMI token. If yes, then don't ask OPAL to patch - * the HMI interrupt and we catch it directly in Linux. + * Only ancient OPAL firmware requires this. + * Specifically, firmware from FW810.00 (released June 2014) + * through FW810.20 (Released October 2014). * - * For older firmware (i.e currently released POWER8 System Firmware - * as of today <= SV810_087), we fallback to old behavior and let OPAL - * patch the HMI vector and handle it inside OPAL firmware. + * Check if we are running on newer (post Oct 2014) firmware that + * exports the OPAL_HANDLE_HMI token. If yes, then don't ask OPAL to + * patch the HMI interrupt and we catch it directly in Linux. * - * For newer firmware (in development/yet to be released) we will - * start catching/handling HMI directly in Linux. + * For older firmware (i.e < FW810.20), we fallback to old behavior and + * let OPAL patch the HMI vector and handle it inside OPAL firmware. + * + * For newer firmware we catch/handle the HMI directly in Linux. */ if (!opal_check_token(OPAL_HANDLE_HMI)) { pr_info("Old firmware detected, OPAL handles HMIs.\n"); @@ -221,6 +223,11 @@ static int __init opal_register_exception_handlers(void) glue += 128; } + /* + * Only applicable to ancient firmware, all modern + * (post March 2015/skiboot 5.0) firmware will just return + * OPAL_UNSUPPORTED. + */ opal_register_exception_handler(OPAL_SOFTPATCH_HANDLER, 0, glue); #endif diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 10cc42b9e541..d8080558d020 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -50,6 +50,8 @@ static const char * const pnv_phb_names[] = { "IODA1", "IODA2", "NPU_NVLINK", "NPU_OCAPI" }; +static void pnv_pci_ioda2_set_bypass(struct pnv_ioda_pe *pe, bool enable); + void pe_level_printk(const struct pnv_ioda_pe *pe, const char *level, const char *fmt, ...) { @@ -2356,7 +2358,7 @@ static long pnv_pci_ioda2_set_window(struct iommu_table_group *table_group, return 0; } -void pnv_pci_ioda2_set_bypass(struct pnv_ioda_pe *pe, bool enable) +static void pnv_pci_ioda2_set_bypass(struct pnv_ioda_pe *pe, bool enable) { uint16_t window_id = (pe->pe_number << 1 ) + 1; int64_t rc; @@ -2456,6 +2458,14 @@ static long pnv_pci_ioda2_setup_default_config(struct pnv_ioda_pe *pe) if (!pnv_iommu_bypass_disabled) pnv_pci_ioda2_set_bypass(pe, true); + /* + * Set table base for the case of IOMMU DMA use. Usually this is done + * from dma_dev_setup() which is not called when a device is returned + * from VFIO so do it here. + */ + if (pe->pdev) + set_iommu_table_base(&pe->pdev->dev, tbl); + return 0; } @@ -2543,6 +2553,8 @@ static void pnv_ioda2_take_ownership(struct iommu_table_group *table_group) pnv_pci_ioda2_unset_window(&pe->table_group, 0); if (pe->pbus) pnv_ioda_setup_bus_dma(pe, pe->pbus); + else if (pe->pdev) + set_iommu_table_base(&pe->pdev->dev, NULL); iommu_tce_table_put(tbl); } diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c index ff1a33fee8e6..6104418c9ad5 100644 --- a/arch/powerpc/platforms/powernv/pci.c +++ b/arch/powerpc/platforms/powernv/pci.c @@ -34,7 +34,6 @@ #include "powernv.h" #include "pci.h" -static DEFINE_MUTEX(p2p_mutex); static DEFINE_MUTEX(tunnel_mutex); int pnv_pci_get_slot_id(struct device_node *np, uint64_t *id) @@ -857,79 +856,6 @@ void pnv_pci_dma_bus_setup(struct pci_bus *bus) } } -int pnv_pci_set_p2p(struct pci_dev *initiator, struct pci_dev *target, u64 desc) -{ - struct pci_controller *hose; - struct pnv_phb *phb_init, *phb_target; - struct pnv_ioda_pe *pe_init; - int rc; - - if (!opal_check_token(OPAL_PCI_SET_P2P)) - return -ENXIO; - - hose = pci_bus_to_host(initiator->bus); - phb_init = hose->private_data; - - hose = pci_bus_to_host(target->bus); - phb_target = hose->private_data; - - pe_init = pnv_ioda_get_pe(initiator); - if (!pe_init) - return -ENODEV; - - /* - * Configuring the initiator's PHB requires to adjust its - * TVE#1 setting. Since the same device can be an initiator - * several times for different target devices, we need to keep - * a reference count to know when we can restore the default - * bypass setting on its TVE#1 when disabling. Opal is not - * tracking PE states, so we add a reference count on the PE - * in linux. - * - * For the target, the configuration is per PHB, so we keep a - * target reference count on the PHB. - */ - mutex_lock(&p2p_mutex); - - if (desc & OPAL_PCI_P2P_ENABLE) { - /* always go to opal to validate the configuration */ - rc = opal_pci_set_p2p(phb_init->opal_id, phb_target->opal_id, - desc, pe_init->pe_number); - - if (rc != OPAL_SUCCESS) { - rc = -EIO; - goto out; - } - - pe_init->p2p_initiator_count++; - phb_target->p2p_target_count++; - } else { - if (!pe_init->p2p_initiator_count || - !phb_target->p2p_target_count) { - rc = -EINVAL; - goto out; - } - - if (--pe_init->p2p_initiator_count == 0) - pnv_pci_ioda2_set_bypass(pe_init, true); - - if (--phb_target->p2p_target_count == 0) { - rc = opal_pci_set_p2p(phb_init->opal_id, - phb_target->opal_id, desc, - pe_init->pe_number); - if (rc != OPAL_SUCCESS) { - rc = -EIO; - goto out; - } - } - } - rc = 0; -out: - mutex_unlock(&p2p_mutex); - return rc; -} -EXPORT_SYMBOL_GPL(pnv_pci_set_p2p); - struct device_node *pnv_pci_get_phb_node(struct pci_dev *dev) { struct pci_controller *hose = pci_bus_to_host(dev->bus); @@ -938,54 +864,6 @@ struct device_node *pnv_pci_get_phb_node(struct pci_dev *dev) } EXPORT_SYMBOL(pnv_pci_get_phb_node); -int pnv_pci_enable_tunnel(struct pci_dev *dev, u64 *asnind) -{ - struct device_node *np; - const __be32 *prop; - struct pnv_ioda_pe *pe; - uint16_t window_id; - int rc; - - if (!radix_enabled()) - return -ENXIO; - - if (!(np = pnv_pci_get_phb_node(dev))) - return -ENXIO; - - prop = of_get_property(np, "ibm,phb-indications", NULL); - of_node_put(np); - - if (!prop || !prop[1]) - return -ENXIO; - - *asnind = (u64)be32_to_cpu(prop[1]); - pe = pnv_ioda_get_pe(dev); - if (!pe) - return -ENODEV; - - /* Increase real window size to accept as_notify messages. */ - window_id = (pe->pe_number << 1 ) + 1; - rc = opal_pci_map_pe_dma_window_real(pe->phb->opal_id, pe->pe_number, - window_id, pe->tce_bypass_base, - (uint64_t)1 << 48); - return opal_error_code(rc); -} -EXPORT_SYMBOL_GPL(pnv_pci_enable_tunnel); - -int pnv_pci_disable_tunnel(struct pci_dev *dev) -{ - struct pnv_ioda_pe *pe; - - pe = pnv_ioda_get_pe(dev); - if (!pe) - return -ENODEV; - - /* Restore default real window size. */ - pnv_pci_ioda2_set_bypass(pe, true); - return 0; -} -EXPORT_SYMBOL_GPL(pnv_pci_disable_tunnel); - int pnv_pci_set_tunnel_bar(struct pci_dev *dev, u64 addr, int enable) { __be64 val; @@ -1040,29 +918,6 @@ out: } EXPORT_SYMBOL_GPL(pnv_pci_set_tunnel_bar); -#ifdef CONFIG_PPC64 /* for thread.tidr */ -int pnv_pci_get_as_notify_info(struct task_struct *task, u32 *lpid, u32 *pid, - u32 *tid) -{ - struct mm_struct *mm = NULL; - - if (task == NULL) - return -EINVAL; - - mm = get_task_mm(task); - if (mm == NULL) - return -EINVAL; - - *pid = mm->context.id; - mmput(mm); - - *tid = task->thread.tidr; - *lpid = mfspr(SPRN_LPID); - return 0; -} -EXPORT_SYMBOL_GPL(pnv_pci_get_as_notify_info); -#endif - void pnv_pci_shutdown(void) { struct pci_controller *hose; diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h index be26ab3d99e0..469c24463247 100644 --- a/arch/powerpc/platforms/powernv/pci.h +++ b/arch/powerpc/platforms/powernv/pci.h @@ -79,9 +79,6 @@ struct pnv_ioda_pe { struct pnv_ioda_pe *master; struct list_head slaves; - /* PCI peer-to-peer*/ - int p2p_initiator_count; - /* Link in list of PE#s */ struct list_head list; }; @@ -172,8 +169,6 @@ struct pnv_phb { /* PHB and hub diagnostics */ unsigned int diag_data_size; u8 *diag_data; - - int p2p_target_count; }; extern struct pci_ops pnv_pci_ops; @@ -200,7 +195,6 @@ extern int pnv_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type); extern void pnv_teardown_msi_irqs(struct pci_dev *pdev); extern struct pnv_ioda_pe *pnv_ioda_get_pe(struct pci_dev *dev); extern void pnv_set_msi_irq_chip(struct pnv_phb *phb, unsigned int virq); -extern void pnv_pci_ioda2_set_bypass(struct pnv_ioda_pe *pe, bool enable); extern unsigned long pnv_pci_ioda2_get_table_size(__u32 page_shift, __u64 window_size, __u32 levels); extern int pnv_eeh_post_init(void); diff --git a/arch/powerpc/platforms/powernv/vas-window.c b/arch/powerpc/platforms/powernv/vas-window.c index ea5ca0201da8..0c0d27d17976 100644 --- a/arch/powerpc/platforms/powernv/vas-window.c +++ b/arch/powerpc/platforms/powernv/vas-window.c @@ -40,16 +40,6 @@ static void compute_paste_address(struct vas_window *window, u64 *addr, int *len pr_debug("Txwin #%d: Paste addr 0x%llx\n", winid, *addr); } -u64 vas_win_paste_addr(struct vas_window *win) -{ - u64 addr; - - compute_paste_address(win, &addr, NULL); - - return addr; -} -EXPORT_SYMBOL(vas_win_paste_addr); - static inline void get_hvwc_mmio_bar(struct vas_window *window, u64 *start, int *len) { @@ -1264,12 +1254,3 @@ int vas_win_close(struct vas_window *window) return 0; } EXPORT_SYMBOL_GPL(vas_win_close); - -/* - * Return a system-wide unique window id for the window @win. - */ -u32 vas_win_id(struct vas_window *win) -{ - return encode_pswid(win->vinst->vas_id, win->winid); -} -EXPORT_SYMBOL_GPL(vas_win_id); diff --git a/arch/powerpc/platforms/powernv/vas.h b/arch/powerpc/platforms/powernv/vas.h index 9cc5251816db..5574aec9ee88 100644 --- a/arch/powerpc/platforms/powernv/vas.h +++ b/arch/powerpc/platforms/powernv/vas.h @@ -444,26 +444,6 @@ static inline u64 read_hvwc_reg(struct vas_window *win, return in_be64(win->hvwc_map+reg); } -/* - * Encode/decode the Partition Send Window ID (PSWID) for a window in - * a way that we can uniquely identify any window in the system. i.e. - * we should be able to locate the 'struct vas_window' given the PSWID. - * - * Bits Usage - * 0:7 VAS id (8 bits) - * 8:15 Unused, 0 (3 bits) - * 16:31 Window id (16 bits) - */ -static inline u32 encode_pswid(int vasid, int winid) -{ - u32 pswid = 0; - - pswid |= vasid << (31 - 7); - pswid |= winid; - - return pswid; -} - static inline void decode_pswid(u32 pswid, int *vasid, int *winid) { if (vasid) diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig index 9c6b3d860518..f7b484f55553 100644 --- a/arch/powerpc/platforms/pseries/Kconfig +++ b/arch/powerpc/platforms/pseries/Kconfig @@ -23,6 +23,7 @@ config PPC_PSERIES select ARCH_RANDOM select PPC_DOORBELL select FORCE_SMP + select SWIOTLB default y config PPC_SPLPAR @@ -80,19 +81,19 @@ config LPARCFG bool "LPAR Configuration Data" depends on PPC_PSERIES help - Provide system capacity information via human readable - <key word>=<value> pairs through a /proc/ppc64/lparcfg interface. + Provide system capacity information via human readable + <key word>=<value> pairs through a /proc/ppc64/lparcfg interface. config PPC_PSERIES_DEBUG depends on PPC_PSERIES && PPC_EARLY_DEBUG bool "Enable extra debug logging in platforms/pseries" - help + default y + help Say Y here if you want the pseries core to produce a bunch of debug messages to the system log. Select this if you are having a problem with the pseries core and want to see more of what is going on. This does not enable debugging in lpar.c, which must be manually done due to its verbosity. - default y config PPC_SMLPAR bool "Support for shared-memory logical partitions" @@ -117,16 +118,16 @@ config CMM balance memory across many LPARs. config HV_PERF_CTRS - bool "Hypervisor supplied PMU events (24x7 & GPCI)" - default y - depends on PERF_EVENTS && PPC_PSERIES - help + bool "Hypervisor supplied PMU events (24x7 & GPCI)" + default y + depends on PERF_EVENTS && PPC_PSERIES + help Enable access to hypervisor supplied counters in perf. Currently, this enables code that uses the hcall GetPerfCounterInfo and 24x7 interfaces to retrieve counters. GPCI exists on Power 6 and later systems. 24x7 is available on Power 8 and later systems. - If unsure, select Y. + If unsure, select Y. config IBMVIO depends on PPC_PSERIES diff --git a/arch/powerpc/platforms/pseries/Makefile b/arch/powerpc/platforms/pseries/Makefile index a43ec843c8e2..ab3d59aeacca 100644 --- a/arch/powerpc/platforms/pseries/Makefile +++ b/arch/powerpc/platforms/pseries/Makefile @@ -25,6 +25,7 @@ obj-$(CONFIG_LPARCFG) += lparcfg.o obj-$(CONFIG_IBMVIO) += vio.o obj-$(CONFIG_IBMEBUS) += ibmebus.o obj-$(CONFIG_PAPR_SCM) += papr_scm.o +obj-$(CONFIG_PPC_SPLPAR) += vphn.o ifdef CONFIG_PPC_PSERIES obj-$(CONFIG_SUSPEND) += suspend.o diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c index 437a74173db2..16e86ba8aa20 100644 --- a/arch/powerpc/platforms/pseries/dlpar.c +++ b/arch/powerpc/platforms/pseries/dlpar.c @@ -58,6 +58,10 @@ static struct property *dlpar_parse_cc_property(struct cc_workarea *ccwa) name = (char *)ccwa + be32_to_cpu(ccwa->name_offset); prop->name = kstrdup(name, GFP_KERNEL); + if (!prop->name) { + dlpar_free_cc_property(prop); + return NULL; + } prop->length = be32_to_cpu(ccwa->prop_length); value = (char *)ccwa + be32_to_cpu(ccwa->prop_offset); @@ -383,11 +387,11 @@ void queue_hotplug_event(struct pseries_hp_errorlog *hp_errlog) struct pseries_hp_work *work; struct pseries_hp_errorlog *hp_errlog_copy; - hp_errlog_copy = kmalloc(sizeof(struct pseries_hp_errorlog), - GFP_KERNEL); - memcpy(hp_errlog_copy, hp_errlog, sizeof(struct pseries_hp_errorlog)); + hp_errlog_copy = kmemdup(hp_errlog, sizeof(*hp_errlog), GFP_ATOMIC); + if (!hp_errlog_copy) + return; - work = kmalloc(sizeof(struct pseries_hp_work), GFP_KERNEL); + work = kmalloc(sizeof(struct pseries_hp_work), GFP_ATOMIC); if (work) { INIT_WORK((struct work_struct *)work, pseries_hp_work_fn); work->errlog = hp_errlog_copy; diff --git a/arch/powerpc/platforms/pseries/dtl.c b/arch/powerpc/platforms/pseries/dtl.c index ab5de985a787..2b87480f2837 100644 --- a/arch/powerpc/platforms/pseries/dtl.c +++ b/arch/powerpc/platforms/pseries/dtl.c @@ -27,13 +27,7 @@ struct dtl { }; static DEFINE_PER_CPU(struct dtl, cpu_dtl); -/* - * Dispatch trace log event mask: - * 0x7: 0x1: voluntary virtual processor waits - * 0x2: time-slice preempts - * 0x4: virtual partition memory page faults - */ -static u8 dtl_event_mask = 0x7; +static u8 dtl_event_mask = DTL_LOG_ALL; /* @@ -48,7 +42,6 @@ struct dtl_ring { struct dtl_entry *write_ptr; struct dtl_entry *buf; struct dtl_entry *buf_end; - u8 saved_dtl_mask; }; static DEFINE_PER_CPU(struct dtl_ring, dtl_rings); @@ -98,7 +91,6 @@ static int dtl_start(struct dtl *dtl) dtlr->write_ptr = dtl->buf; /* enable event logging */ - dtlr->saved_dtl_mask = lppaca_of(dtl->cpu).dtl_enable_mask; lppaca_of(dtl->cpu).dtl_enable_mask |= dtl_event_mask; dtl_consumer = consume_dtle; @@ -116,7 +108,7 @@ static void dtl_stop(struct dtl *dtl) dtlr->buf = NULL; /* restore dtl_enable_mask */ - lppaca_of(dtl->cpu).dtl_enable_mask = dtlr->saved_dtl_mask; + lppaca_of(dtl->cpu).dtl_enable_mask = DTL_LOG_PREEMPT; if (atomic_dec_and_test(&dtl_count)) dtl_consumer = NULL; @@ -188,11 +180,16 @@ static int dtl_enable(struct dtl *dtl) if (dtl->buf) return -EBUSY; + /* ensure there are no other conflicting dtl users */ + if (!read_trylock(&dtl_access_lock)) + return -EBUSY; + n_entries = dtl_buf_entries; buf = kmem_cache_alloc_node(dtl_cache, GFP_KERNEL, cpu_to_node(dtl->cpu)); if (!buf) { printk(KERN_WARNING "%s: buffer alloc failed for cpu %d\n", __func__, dtl->cpu); + read_unlock(&dtl_access_lock); return -ENOMEM; } @@ -209,8 +206,11 @@ static int dtl_enable(struct dtl *dtl) } spin_unlock(&dtl->lock); - if (rc) + if (rc) { + read_unlock(&dtl_access_lock); kmem_cache_free(dtl_cache, buf); + } + return rc; } @@ -222,6 +222,7 @@ static void dtl_disable(struct dtl *dtl) dtl->buf = NULL; dtl->buf_entries = 0; spin_unlock(&dtl->lock); + read_unlock(&dtl_access_lock); } /* file interface */ diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c index 2ec43b4639a0..46d0d35b9ca4 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -976,6 +976,9 @@ static int pseries_update_drconf_memory(struct of_reconfig_data *pr) if (!memblock_size) return -EINVAL; + if (!pr->old_prop) + return 0; + p = (__be32 *) pr->old_prop->value; if (!p) return -EINVAL; diff --git a/arch/powerpc/platforms/pseries/hvconsole.c b/arch/powerpc/platforms/pseries/hvconsole.c index 1498c6b989e6..1ac52963e08b 100644 --- a/arch/powerpc/platforms/pseries/hvconsole.c +++ b/arch/powerpc/platforms/pseries/hvconsole.c @@ -49,7 +49,7 @@ EXPORT_SYMBOL(hvc_get_chars); * @vtermno: The vtermno or unit_address of the adapter from which the data * originated. * @buf: The character buffer that contains the character data to send to - * firmware. + * firmware. Must be at least 16 bytes, even if count is less than 16. * @count: Send this number of characters. */ int hvc_put_chars(uint32_t vtermno, const char *buf, int count) diff --git a/arch/powerpc/platforms/pseries/ibmebus.c b/arch/powerpc/platforms/pseries/ibmebus.c index 84e8ec4011ba..b91eb0929ed1 100644 --- a/arch/powerpc/platforms/pseries/ibmebus.c +++ b/arch/powerpc/platforms/pseries/ibmebus.c @@ -147,13 +147,13 @@ static const struct dma_map_ops ibmebus_dma_ops = { .unmap_page = ibmebus_unmap_page, }; -static int ibmebus_match_path(struct device *dev, void *data) +static int ibmebus_match_path(struct device *dev, const void *data) { struct device_node *dn = to_platform_device(dev)->dev.of_node; return (of_find_node_by_path(data) == dn); } -static int ibmebus_match_node(struct device *dev, void *data) +static int ibmebus_match_node(struct device *dev, const void *data) { return to_platform_device(dev)->dev.of_node == data; } diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index 73620dfb63a1..09bb878c21e0 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -17,6 +17,10 @@ #include <linux/jump_label.h> #include <linux/delay.h> #include <linux/stop_machine.h> +#include <linux/spinlock.h> +#include <linux/cpuhotplug.h> +#include <linux/workqueue.h> +#include <linux/proc_fs.h> #include <asm/processor.h> #include <asm/mmu.h> #include <asm/page.h> @@ -52,13 +56,591 @@ EXPORT_SYMBOL(plpar_hcall); EXPORT_SYMBOL(plpar_hcall9); EXPORT_SYMBOL(plpar_hcall_norets); +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE +static u8 dtl_mask = DTL_LOG_PREEMPT; +#else +static u8 dtl_mask; +#endif + +void alloc_dtl_buffers(unsigned long *time_limit) +{ + int cpu; + struct paca_struct *pp; + struct dtl_entry *dtl; + + for_each_possible_cpu(cpu) { + pp = paca_ptrs[cpu]; + if (pp->dispatch_log) + continue; + dtl = kmem_cache_alloc(dtl_cache, GFP_KERNEL); + if (!dtl) { + pr_warn("Failed to allocate dispatch trace log for cpu %d\n", + cpu); +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE + pr_warn("Stolen time statistics will be unreliable\n"); +#endif + break; + } + + pp->dtl_ridx = 0; + pp->dispatch_log = dtl; + pp->dispatch_log_end = dtl + N_DISPATCH_LOG; + pp->dtl_curr = dtl; + + if (time_limit && time_after(jiffies, *time_limit)) { + cond_resched(); + *time_limit = jiffies + HZ; + } + } +} + +void register_dtl_buffer(int cpu) +{ + long ret; + struct paca_struct *pp; + struct dtl_entry *dtl; + int hwcpu = get_hard_smp_processor_id(cpu); + + pp = paca_ptrs[cpu]; + dtl = pp->dispatch_log; + if (dtl && dtl_mask) { + pp->dtl_ridx = 0; + pp->dtl_curr = dtl; + lppaca_of(cpu).dtl_idx = 0; + + /* hypervisor reads buffer length from this field */ + dtl->enqueue_to_dispatch_time = cpu_to_be32(DISPATCH_LOG_BYTES); + ret = register_dtl(hwcpu, __pa(dtl)); + if (ret) + pr_err("WARNING: DTL registration of cpu %d (hw %d) failed with %ld\n", + cpu, hwcpu, ret); + + lppaca_of(cpu).dtl_enable_mask = dtl_mask; + } +} + +#ifdef CONFIG_PPC_SPLPAR +struct dtl_worker { + struct delayed_work work; + int cpu; +}; + +struct vcpu_dispatch_data { + int last_disp_cpu; + + int total_disp; + + int same_cpu_disp; + int same_chip_disp; + int diff_chip_disp; + int far_chip_disp; + + int numa_home_disp; + int numa_remote_disp; + int numa_far_disp; +}; + +/* + * This represents the number of cpus in the hypervisor. Since there is no + * architected way to discover the number of processors in the host, we + * provision for dealing with NR_CPUS. This is currently 2048 by default, and + * is sufficient for our purposes. This will need to be tweaked if + * CONFIG_NR_CPUS is changed. + */ +#define NR_CPUS_H NR_CPUS + +DEFINE_RWLOCK(dtl_access_lock); +static DEFINE_PER_CPU(struct vcpu_dispatch_data, vcpu_disp_data); +static DEFINE_PER_CPU(u64, dtl_entry_ridx); +static DEFINE_PER_CPU(struct dtl_worker, dtl_workers); +static enum cpuhp_state dtl_worker_state; +static DEFINE_MUTEX(dtl_enable_mutex); +static int vcpudispatch_stats_on __read_mostly; +static int vcpudispatch_stats_freq = 50; +static __be32 *vcpu_associativity, *pcpu_associativity; + + +static void free_dtl_buffers(unsigned long *time_limit) +{ +#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE + int cpu; + struct paca_struct *pp; + + for_each_possible_cpu(cpu) { + pp = paca_ptrs[cpu]; + if (!pp->dispatch_log) + continue; + kmem_cache_free(dtl_cache, pp->dispatch_log); + pp->dtl_ridx = 0; + pp->dispatch_log = 0; + pp->dispatch_log_end = 0; + pp->dtl_curr = 0; + + if (time_limit && time_after(jiffies, *time_limit)) { + cond_resched(); + *time_limit = jiffies + HZ; + } + } +#endif +} + +static int init_cpu_associativity(void) +{ + vcpu_associativity = kcalloc(num_possible_cpus() / threads_per_core, + VPHN_ASSOC_BUFSIZE * sizeof(__be32), GFP_KERNEL); + pcpu_associativity = kcalloc(NR_CPUS_H / threads_per_core, + VPHN_ASSOC_BUFSIZE * sizeof(__be32), GFP_KERNEL); + + if (!vcpu_associativity || !pcpu_associativity) { + pr_err("error allocating memory for associativity information\n"); + return -ENOMEM; + } + + return 0; +} + +static void destroy_cpu_associativity(void) +{ + kfree(vcpu_associativity); + kfree(pcpu_associativity); + vcpu_associativity = pcpu_associativity = 0; +} + +static __be32 *__get_cpu_associativity(int cpu, __be32 *cpu_assoc, int flag) +{ + __be32 *assoc; + int rc = 0; + + assoc = &cpu_assoc[(int)(cpu / threads_per_core) * VPHN_ASSOC_BUFSIZE]; + if (!assoc[0]) { + rc = hcall_vphn(cpu, flag, &assoc[0]); + if (rc) + return NULL; + } + + return assoc; +} + +static __be32 *get_pcpu_associativity(int cpu) +{ + return __get_cpu_associativity(cpu, pcpu_associativity, VPHN_FLAG_PCPU); +} + +static __be32 *get_vcpu_associativity(int cpu) +{ + return __get_cpu_associativity(cpu, vcpu_associativity, VPHN_FLAG_VCPU); +} + +static int cpu_relative_dispatch_distance(int last_disp_cpu, int cur_disp_cpu) +{ + __be32 *last_disp_cpu_assoc, *cur_disp_cpu_assoc; + + if (last_disp_cpu >= NR_CPUS_H || cur_disp_cpu >= NR_CPUS_H) + return -EINVAL; + + last_disp_cpu_assoc = get_pcpu_associativity(last_disp_cpu); + cur_disp_cpu_assoc = get_pcpu_associativity(cur_disp_cpu); + + if (!last_disp_cpu_assoc || !cur_disp_cpu_assoc) + return -EIO; + + return cpu_distance(last_disp_cpu_assoc, cur_disp_cpu_assoc); +} + +static int cpu_home_node_dispatch_distance(int disp_cpu) +{ + __be32 *disp_cpu_assoc, *vcpu_assoc; + int vcpu_id = smp_processor_id(); + + if (disp_cpu >= NR_CPUS_H) { + pr_debug_ratelimited("vcpu dispatch cpu %d > %d\n", + disp_cpu, NR_CPUS_H); + return -EINVAL; + } + + disp_cpu_assoc = get_pcpu_associativity(disp_cpu); + vcpu_assoc = get_vcpu_associativity(vcpu_id); + + if (!disp_cpu_assoc || !vcpu_assoc) + return -EIO; + + return cpu_distance(disp_cpu_assoc, vcpu_assoc); +} + +static void update_vcpu_disp_stat(int disp_cpu) +{ + struct vcpu_dispatch_data *disp; + int distance; + + disp = this_cpu_ptr(&vcpu_disp_data); + if (disp->last_disp_cpu == -1) { + disp->last_disp_cpu = disp_cpu; + return; + } + + disp->total_disp++; + + if (disp->last_disp_cpu == disp_cpu || + (cpu_first_thread_sibling(disp->last_disp_cpu) == + cpu_first_thread_sibling(disp_cpu))) + disp->same_cpu_disp++; + else { + distance = cpu_relative_dispatch_distance(disp->last_disp_cpu, + disp_cpu); + if (distance < 0) + pr_debug_ratelimited("vcpudispatch_stats: cpu %d: error determining associativity\n", + smp_processor_id()); + else { + switch (distance) { + case 0: + disp->same_chip_disp++; + break; + case 1: + disp->diff_chip_disp++; + break; + case 2: + disp->far_chip_disp++; + break; + default: + pr_debug_ratelimited("vcpudispatch_stats: cpu %d (%d -> %d): unexpected relative dispatch distance %d\n", + smp_processor_id(), + disp->last_disp_cpu, + disp_cpu, + distance); + } + } + } + + distance = cpu_home_node_dispatch_distance(disp_cpu); + if (distance < 0) + pr_debug_ratelimited("vcpudispatch_stats: cpu %d: error determining associativity\n", + smp_processor_id()); + else { + switch (distance) { + case 0: + disp->numa_home_disp++; + break; + case 1: + disp->numa_remote_disp++; + break; + case 2: + disp->numa_far_disp++; + break; + default: + pr_debug_ratelimited("vcpudispatch_stats: cpu %d on %d: unexpected numa dispatch distance %d\n", + smp_processor_id(), + disp_cpu, + distance); + } + } + + disp->last_disp_cpu = disp_cpu; +} + +static void process_dtl_buffer(struct work_struct *work) +{ + struct dtl_entry dtle; + u64 i = __this_cpu_read(dtl_entry_ridx); + struct dtl_entry *dtl = local_paca->dispatch_log + (i % N_DISPATCH_LOG); + struct dtl_entry *dtl_end = local_paca->dispatch_log_end; + struct lppaca *vpa = local_paca->lppaca_ptr; + struct dtl_worker *d = container_of(work, struct dtl_worker, work.work); + + if (!local_paca->dispatch_log) + return; + + /* if we have been migrated away, we cancel ourself */ + if (d->cpu != smp_processor_id()) { + pr_debug("vcpudispatch_stats: cpu %d worker migrated -- canceling worker\n", + smp_processor_id()); + return; + } + + if (i == be64_to_cpu(vpa->dtl_idx)) + goto out; + + while (i < be64_to_cpu(vpa->dtl_idx)) { + dtle = *dtl; + barrier(); + if (i + N_DISPATCH_LOG < be64_to_cpu(vpa->dtl_idx)) { + /* buffer has overflowed */ + pr_debug_ratelimited("vcpudispatch_stats: cpu %d lost %lld DTL samples\n", + d->cpu, + be64_to_cpu(vpa->dtl_idx) - N_DISPATCH_LOG - i); + i = be64_to_cpu(vpa->dtl_idx) - N_DISPATCH_LOG; + dtl = local_paca->dispatch_log + (i % N_DISPATCH_LOG); + continue; + } + update_vcpu_disp_stat(be16_to_cpu(dtle.processor_id)); + ++i; + ++dtl; + if (dtl == dtl_end) + dtl = local_paca->dispatch_log; + } + + __this_cpu_write(dtl_entry_ridx, i); + +out: + schedule_delayed_work_on(d->cpu, to_delayed_work(work), + HZ / vcpudispatch_stats_freq); +} + +static int dtl_worker_online(unsigned int cpu) +{ + struct dtl_worker *d = &per_cpu(dtl_workers, cpu); + + memset(d, 0, sizeof(*d)); + INIT_DELAYED_WORK(&d->work, process_dtl_buffer); + d->cpu = cpu; + +#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE + per_cpu(dtl_entry_ridx, cpu) = 0; + register_dtl_buffer(cpu); +#else + per_cpu(dtl_entry_ridx, cpu) = be64_to_cpu(lppaca_of(cpu).dtl_idx); +#endif + + schedule_delayed_work_on(cpu, &d->work, HZ / vcpudispatch_stats_freq); + return 0; +} + +static int dtl_worker_offline(unsigned int cpu) +{ + struct dtl_worker *d = &per_cpu(dtl_workers, cpu); + + cancel_delayed_work_sync(&d->work); + +#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE + unregister_dtl(get_hard_smp_processor_id(cpu)); +#endif + + return 0; +} + +static void set_global_dtl_mask(u8 mask) +{ + int cpu; + + dtl_mask = mask; + for_each_present_cpu(cpu) + lppaca_of(cpu).dtl_enable_mask = dtl_mask; +} + +static void reset_global_dtl_mask(void) +{ + int cpu; + +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE + dtl_mask = DTL_LOG_PREEMPT; +#else + dtl_mask = 0; +#endif + for_each_present_cpu(cpu) + lppaca_of(cpu).dtl_enable_mask = dtl_mask; +} + +static int dtl_worker_enable(unsigned long *time_limit) +{ + int rc = 0, state; + + if (!write_trylock(&dtl_access_lock)) { + rc = -EBUSY; + goto out; + } + + set_global_dtl_mask(DTL_LOG_ALL); + + /* Setup dtl buffers and register those */ + alloc_dtl_buffers(time_limit); + + state = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "powerpc/dtl:online", + dtl_worker_online, dtl_worker_offline); + if (state < 0) { + pr_err("vcpudispatch_stats: unable to setup workqueue for DTL processing\n"); + free_dtl_buffers(time_limit); + reset_global_dtl_mask(); + write_unlock(&dtl_access_lock); + rc = -EINVAL; + goto out; + } + dtl_worker_state = state; + +out: + return rc; +} + +static void dtl_worker_disable(unsigned long *time_limit) +{ + cpuhp_remove_state(dtl_worker_state); + free_dtl_buffers(time_limit); + reset_global_dtl_mask(); + write_unlock(&dtl_access_lock); +} + +static ssize_t vcpudispatch_stats_write(struct file *file, const char __user *p, + size_t count, loff_t *ppos) +{ + unsigned long time_limit = jiffies + HZ; + struct vcpu_dispatch_data *disp; + int rc, cmd, cpu; + char buf[16]; + + if (count > 15) + return -EINVAL; + + if (copy_from_user(buf, p, count)) + return -EFAULT; + + buf[count] = 0; + rc = kstrtoint(buf, 0, &cmd); + if (rc || cmd < 0 || cmd > 1) { + pr_err("vcpudispatch_stats: please use 0 to disable or 1 to enable dispatch statistics\n"); + return rc ? rc : -EINVAL; + } + + mutex_lock(&dtl_enable_mutex); + + if ((cmd == 0 && !vcpudispatch_stats_on) || + (cmd == 1 && vcpudispatch_stats_on)) + goto out; + + if (cmd) { + rc = init_cpu_associativity(); + if (rc) + goto out; + + for_each_possible_cpu(cpu) { + disp = per_cpu_ptr(&vcpu_disp_data, cpu); + memset(disp, 0, sizeof(*disp)); + disp->last_disp_cpu = -1; + } + + rc = dtl_worker_enable(&time_limit); + if (rc) { + destroy_cpu_associativity(); + goto out; + } + } else { + dtl_worker_disable(&time_limit); + destroy_cpu_associativity(); + } + + vcpudispatch_stats_on = cmd; + +out: + mutex_unlock(&dtl_enable_mutex); + if (rc) + return rc; + return count; +} + +static int vcpudispatch_stats_display(struct seq_file *p, void *v) +{ + int cpu; + struct vcpu_dispatch_data *disp; + + if (!vcpudispatch_stats_on) { + seq_puts(p, "off\n"); + return 0; + } + + for_each_online_cpu(cpu) { + disp = per_cpu_ptr(&vcpu_disp_data, cpu); + seq_printf(p, "cpu%d", cpu); + seq_put_decimal_ull(p, " ", disp->total_disp); + seq_put_decimal_ull(p, " ", disp->same_cpu_disp); + seq_put_decimal_ull(p, " ", disp->same_chip_disp); + seq_put_decimal_ull(p, " ", disp->diff_chip_disp); + seq_put_decimal_ull(p, " ", disp->far_chip_disp); + seq_put_decimal_ull(p, " ", disp->numa_home_disp); + seq_put_decimal_ull(p, " ", disp->numa_remote_disp); + seq_put_decimal_ull(p, " ", disp->numa_far_disp); + seq_puts(p, "\n"); + } + + return 0; +} + +static int vcpudispatch_stats_open(struct inode *inode, struct file *file) +{ + return single_open(file, vcpudispatch_stats_display, NULL); +} + +static const struct file_operations vcpudispatch_stats_proc_ops = { + .open = vcpudispatch_stats_open, + .read = seq_read, + .write = vcpudispatch_stats_write, + .llseek = seq_lseek, + .release = single_release, +}; + +static ssize_t vcpudispatch_stats_freq_write(struct file *file, + const char __user *p, size_t count, loff_t *ppos) +{ + int rc, freq; + char buf[16]; + + if (count > 15) + return -EINVAL; + + if (copy_from_user(buf, p, count)) + return -EFAULT; + + buf[count] = 0; + rc = kstrtoint(buf, 0, &freq); + if (rc || freq < 1 || freq > HZ) { + pr_err("vcpudispatch_stats_freq: please specify a frequency between 1 and %d\n", + HZ); + return rc ? rc : -EINVAL; + } + + vcpudispatch_stats_freq = freq; + + return count; +} + +static int vcpudispatch_stats_freq_display(struct seq_file *p, void *v) +{ + seq_printf(p, "%d\n", vcpudispatch_stats_freq); + return 0; +} + +static int vcpudispatch_stats_freq_open(struct inode *inode, struct file *file) +{ + return single_open(file, vcpudispatch_stats_freq_display, NULL); +} + +static const struct file_operations vcpudispatch_stats_freq_proc_ops = { + .open = vcpudispatch_stats_freq_open, + .read = seq_read, + .write = vcpudispatch_stats_freq_write, + .llseek = seq_lseek, + .release = single_release, +}; + +static int __init vcpudispatch_stats_procfs_init(void) +{ + if (!lppaca_shared_proc(get_lppaca())) + return 0; + + if (!proc_create("powerpc/vcpudispatch_stats", 0600, NULL, + &vcpudispatch_stats_proc_ops)) + pr_err("vcpudispatch_stats: error creating procfs file\n"); + else if (!proc_create("powerpc/vcpudispatch_stats_freq", 0600, NULL, + &vcpudispatch_stats_freq_proc_ops)) + pr_err("vcpudispatch_stats_freq: error creating procfs file\n"); + + return 0; +} + +machine_device_initcall(pseries, vcpudispatch_stats_procfs_init); +#endif /* CONFIG_PPC_SPLPAR */ + void vpa_init(int cpu) { int hwcpu = get_hard_smp_processor_id(cpu); unsigned long addr; long ret; - struct paca_struct *pp; - struct dtl_entry *dtl; /* * The spec says it "may be problematic" if CPU x registers the VPA of @@ -99,22 +681,7 @@ void vpa_init(int cpu) /* * Register dispatch trace log, if one has been allocated. */ - pp = paca_ptrs[cpu]; - dtl = pp->dispatch_log; - if (dtl) { - pp->dtl_ridx = 0; - pp->dtl_curr = dtl; - lppaca_of(cpu).dtl_idx = 0; - - /* hypervisor reads buffer length from this field */ - dtl->enqueue_to_dispatch_time = cpu_to_be32(DISPATCH_LOG_BYTES); - ret = register_dtl(hwcpu, __pa(dtl)); - if (ret) - pr_err("WARNING: DTL registration of cpu %d (hw %d) " - "failed with %ld\n", smp_processor_id(), - hwcpu, ret); - lppaca_of(cpu).dtl_enable_mask = 2; - } + register_dtl_buffer(cpu); } #ifdef CONFIG_PPC_BOOK3S_64 diff --git a/arch/powerpc/platforms/pseries/mobility.c b/arch/powerpc/platforms/pseries/mobility.c index 0c48c8964783..fe812bebdf5e 100644 --- a/arch/powerpc/platforms/pseries/mobility.c +++ b/arch/powerpc/platforms/pseries/mobility.c @@ -6,6 +6,7 @@ * Copyright (C) 2010 IBM Corporation */ +#include <linux/cpu.h> #include <linux/kernel.h> #include <linux/kobject.h> #include <linux/smp.h> @@ -19,6 +20,7 @@ #include <asm/machdep.h> #include <asm/rtas.h> #include "pseries.h" +#include "../../kernel/cacheinfo.h" static struct kobject *mobility_kobj; @@ -335,11 +337,28 @@ void post_mobility_fixup(void) if (rc) printk(KERN_ERR "Post-mobility activate-fw failed: %d\n", rc); + /* + * We don't want CPUs to go online/offline while the device + * tree is being updated. + */ + cpus_read_lock(); + + /* + * It's common for the destination firmware to replace cache + * nodes. Release all of the cacheinfo hierarchy's references + * before updating the device tree. + */ + cacheinfo_teardown(); + rc = pseries_devicetree_update(MIGRATION_SCOPE); if (rc) printk(KERN_ERR "Post-mobility device tree update " "failed: %d\n", rc); + cacheinfo_rebuild(); + + cpus_read_unlock(); + /* Possibly switch to a new RFI flush type */ pseries_setup_rfi_flush(); diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c index 96c53b23e58f..c8ec670ee924 100644 --- a/arch/powerpc/platforms/pseries/papr_scm.c +++ b/arch/powerpc/platforms/pseries/papr_scm.c @@ -28,6 +28,7 @@ struct papr_scm_priv { uint64_t blocks; uint64_t block_size; int metadata_size; + bool is_volatile; uint64_t bound_addr; @@ -96,42 +97,102 @@ static int drc_pmem_unbind(struct papr_scm_priv *p) } static int papr_scm_meta_get(struct papr_scm_priv *p, - struct nd_cmd_get_config_data_hdr *hdr) + struct nd_cmd_get_config_data_hdr *hdr) { unsigned long data[PLPAR_HCALL_BUFSIZE]; + unsigned long offset, data_offset; + int len, read; int64_t ret; - if (hdr->in_offset >= p->metadata_size || hdr->in_length != 1) + if ((hdr->in_offset + hdr->in_length) >= p->metadata_size) return -EINVAL; - ret = plpar_hcall(H_SCM_READ_METADATA, data, p->drc_index, - hdr->in_offset, 1); - - if (ret == H_PARAMETER) /* bad DRC index */ - return -ENODEV; - if (ret) - return -EINVAL; /* other invalid parameter */ - - hdr->out_buf[0] = data[0] & 0xff; - + for (len = hdr->in_length; len; len -= read) { + + data_offset = hdr->in_length - len; + offset = hdr->in_offset + data_offset; + + if (len >= 8) + read = 8; + else if (len >= 4) + read = 4; + else if (len >= 2) + read = 2; + else + read = 1; + + ret = plpar_hcall(H_SCM_READ_METADATA, data, p->drc_index, + offset, read); + + if (ret == H_PARAMETER) /* bad DRC index */ + return -ENODEV; + if (ret) + return -EINVAL; /* other invalid parameter */ + + switch (read) { + case 8: + *(uint64_t *)(hdr->out_buf + data_offset) = be64_to_cpu(data[0]); + break; + case 4: + *(uint32_t *)(hdr->out_buf + data_offset) = be32_to_cpu(data[0] & 0xffffffff); + break; + + case 2: + *(uint16_t *)(hdr->out_buf + data_offset) = be16_to_cpu(data[0] & 0xffff); + break; + + case 1: + *(uint8_t *)(hdr->out_buf + data_offset) = (data[0] & 0xff); + break; + } + } return 0; } static int papr_scm_meta_set(struct papr_scm_priv *p, - struct nd_cmd_set_config_hdr *hdr) + struct nd_cmd_set_config_hdr *hdr) { + unsigned long offset, data_offset; + int len, wrote; + unsigned long data; + __be64 data_be; int64_t ret; - if (hdr->in_offset >= p->metadata_size || hdr->in_length != 1) + if ((hdr->in_offset + hdr->in_length) >= p->metadata_size) return -EINVAL; - ret = plpar_hcall_norets(H_SCM_WRITE_METADATA, - p->drc_index, hdr->in_offset, hdr->in_buf[0], 1); - - if (ret == H_PARAMETER) /* bad DRC index */ - return -ENODEV; - if (ret) - return -EINVAL; /* other invalid parameter */ + for (len = hdr->in_length; len; len -= wrote) { + + data_offset = hdr->in_length - len; + offset = hdr->in_offset + data_offset; + + if (len >= 8) { + data = *(uint64_t *)(hdr->in_buf + data_offset); + data_be = cpu_to_be64(data); + wrote = 8; + } else if (len >= 4) { + data = *(uint32_t *)(hdr->in_buf + data_offset); + data &= 0xffffffff; + data_be = cpu_to_be32(data); + wrote = 4; + } else if (len >= 2) { + data = *(uint16_t *)(hdr->in_buf + data_offset); + data &= 0xffff; + data_be = cpu_to_be16(data); + wrote = 2; + } else { + data_be = *(uint8_t *)(hdr->in_buf + data_offset); + data_be &= 0xff; + wrote = 1; + } + + ret = plpar_hcall_norets(H_SCM_WRITE_METADATA, p->drc_index, + offset, data_be, wrote); + if (ret == H_PARAMETER) /* bad DRC index */ + return -ENODEV; + if (ret) + return -EINVAL; /* other invalid parameter */ + } return 0; } @@ -153,7 +214,7 @@ int papr_scm_ndctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm, get_size_hdr = buf; get_size_hdr->status = 0; - get_size_hdr->max_xfer = 1; + get_size_hdr->max_xfer = 8; get_size_hdr->config_size = p->metadata_size; *cmd_rc = 0; break; @@ -248,7 +309,10 @@ static int papr_scm_nvdimm_init(struct papr_scm_priv *p) ndr_desc.nd_set = &p->nd_set; set_bit(ND_REGION_PAGEMAP, &ndr_desc.flags); - p->region = nvdimm_pmem_region_create(p->bus, &ndr_desc); + if (p->is_volatile) + p->region = nvdimm_volatile_region_create(p->bus, &ndr_desc); + else + p->region = nvdimm_pmem_region_create(p->bus, &ndr_desc); if (!p->region) { dev_err(dev, "Error registering region %pR from %pOF\n", ndr_desc.res, p->dn); @@ -293,6 +357,7 @@ static int papr_scm_probe(struct platform_device *pdev) return -ENODEV; } + p = kzalloc(sizeof(*p), GFP_KERNEL); if (!p) return -ENOMEM; @@ -304,11 +369,19 @@ static int papr_scm_probe(struct platform_device *pdev) p->drc_index = drc_index; p->block_size = block_size; p->blocks = blocks; + p->is_volatile = !of_property_read_bool(dn, "ibm,cache-flush-required"); /* We just need to ensure that set cookies are unique across */ uuid_parse(uuid_str, (uuid_t *) uuid); - p->nd_set.cookie1 = uuid[0]; - p->nd_set.cookie2 = uuid[1]; + /* + * cookie1 and cookie2 are not really little endian + * we store a little endian representation of the + * uuid str so that we can compare this with the label + * area cookie irrespective of the endian config with which + * the kernel is built. + */ + p->nd_set.cookie1 = cpu_to_le64(uuid[0]); + p->nd_set.cookie2 = cpu_to_le64(uuid[1]); /* might be zero */ p->metadata_size = metadata_size; diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 8fa012a65a71..f5940cc71c37 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -38,6 +38,7 @@ #include <linux/of.h> #include <linux/of_pci.h> #include <linux/memblock.h> +#include <linux/swiotlb.h> #include <asm/mmu.h> #include <asm/processor.h> @@ -67,6 +68,7 @@ #include <asm/isa-bridge.h> #include <asm/security_features.h> #include <asm/asm-const.h> +#include <asm/swiotlb.h> #include "pseries.h" #include "../../../../drivers/pci/pci.h" @@ -273,46 +275,16 @@ struct kmem_cache *dtl_cache; */ static int alloc_dispatch_logs(void) { - int cpu, ret; - struct paca_struct *pp; - struct dtl_entry *dtl; - if (!firmware_has_feature(FW_FEATURE_SPLPAR)) return 0; if (!dtl_cache) return 0; - for_each_possible_cpu(cpu) { - pp = paca_ptrs[cpu]; - dtl = kmem_cache_alloc(dtl_cache, GFP_KERNEL); - if (!dtl) { - pr_warn("Failed to allocate dispatch trace log for cpu %d\n", - cpu); - pr_warn("Stolen time statistics will be unreliable\n"); - break; - } - - pp->dtl_ridx = 0; - pp->dispatch_log = dtl; - pp->dispatch_log_end = dtl + N_DISPATCH_LOG; - pp->dtl_curr = dtl; - } + alloc_dtl_buffers(0); /* Register the DTL for the current (boot) cpu */ - dtl = get_paca()->dispatch_log; - get_paca()->dtl_ridx = 0; - get_paca()->dtl_curr = dtl; - get_paca()->lppaca_ptr->dtl_idx = 0; - - /* hypervisor reads buffer length from this field */ - dtl->enqueue_to_dispatch_time = cpu_to_be32(DISPATCH_LOG_BYTES); - ret = register_dtl(hard_smp_processor_id(), __pa(dtl)); - if (ret) - pr_err("WARNING: DTL registration of cpu %d (hw %d) failed " - "with %d\n", smp_processor_id(), - hard_smp_processor_id(), ret); - get_paca()->lppaca_ptr->dtl_enable_mask = 2; + register_dtl_buffer(smp_processor_id()); return 0; } @@ -793,6 +765,9 @@ static void __init pSeries_setup_arch(void) } ppc_md.pcibios_root_bridge_prepare = pseries_root_bridge_prepare; + + if (swiotlb_force == SWIOTLB_FORCE) + ppc_swiotlb_enable = 1; } static void pseries_panic(char *str) diff --git a/arch/powerpc/platforms/pseries/vio.c b/arch/powerpc/platforms/pseries/vio.c index ba758f4be328..6601b9d404dc 100644 --- a/arch/powerpc/platforms/pseries/vio.c +++ b/arch/powerpc/platforms/pseries/vio.c @@ -520,7 +520,7 @@ static dma_addr_t vio_dma_iommu_map_page(struct device *dev, struct page *page, if (vio_cmo_alloc(viodev, roundup(size, IOMMU_PAGE_SIZE(tbl)))) goto out_fail; - ret = iommu_map_page(dev, tbl, page, offset, size, device_to_mask(dev), + ret = iommu_map_page(dev, tbl, page, offset, size, dma_get_mask(dev), direction, attrs); if (unlikely(ret == DMA_MAPPING_ERROR)) goto out_deallocate; @@ -560,7 +560,7 @@ static int vio_dma_iommu_map_sg(struct device *dev, struct scatterlist *sglist, if (vio_cmo_alloc(viodev, alloc_size)) goto out_fail; - ret = ppc_iommu_map_sg(dev, tbl, sglist, nelems, device_to_mask(dev), + ret = ppc_iommu_map_sg(dev, tbl, sglist, nelems, dma_get_mask(dev), direction, attrs); if (unlikely(!ret)) goto out_deallocate; diff --git a/arch/powerpc/mm/book3s64/vphn.c b/arch/powerpc/platforms/pseries/vphn.c index 0ee7734afb50..3f07bf6c670e 100644 --- a/arch/powerpc/mm/book3s64/vphn.c +++ b/arch/powerpc/platforms/pseries/vphn.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <asm/byteorder.h> -#include "vphn.h" +#include <asm/lppaca.h> /* * The associativity domain numbers are returned from the hypervisor as a @@ -22,7 +22,7 @@ * * Convert to the sequence they would appear in the ibm,associativity property. */ -int vphn_unpack_associativity(const long *packed, __be32 *unpacked) +static int vphn_unpack_associativity(const long *packed, __be32 *unpacked) { __be64 be_packed[VPHN_REGISTER_COUNT]; int i, nr_assoc_doms = 0; @@ -71,3 +71,19 @@ int vphn_unpack_associativity(const long *packed, __be32 *unpacked) return nr_assoc_doms; } + +/* NOTE: This file is included by a selftest and built in userspace. */ +#ifdef __KERNEL__ +#include <asm/hvcall.h> + +long hcall_vphn(unsigned long cpu, u64 flags, __be32 *associativity) +{ + long rc; + long retbuf[PLPAR_HCALL9_BUFSIZE] = {0}; + + rc = plpar_hcall9(H_HOME_NODE_ASSOCIATIVITY, retbuf, flags, cpu); + vphn_unpack_associativity(retbuf, associativity); + + return rc; +} +#endif diff --git a/arch/powerpc/sysdev/Makefile b/arch/powerpc/sysdev/Makefile index aaf23283ba0c..9d73dfddf060 100644 --- a/arch/powerpc/sysdev/Makefile +++ b/arch/powerpc/sysdev/Makefile @@ -37,12 +37,10 @@ obj-$(CONFIG_XILINX_PCI) += xilinx_pci.o obj-$(CONFIG_OF_RTC) += of_rtc.o obj-$(CONFIG_CPM) += cpm_common.o -obj-$(CONFIG_CPM1) += cpm1.o obj-$(CONFIG_CPM2) += cpm2.o cpm2_pic.o cpm_gpio.o obj-$(CONFIG_8xx_GPIO) += cpm_gpio.o obj-$(CONFIG_QUICC_ENGINE) += cpm_common.o obj-$(CONFIG_PPC_DCR) += dcr.o -obj-$(CONFIG_UCODE_PATCH) += micropatch.o obj-$(CONFIG_PPC_MPC512x) += mpc5xxx_clocks.o obj-$(CONFIG_PPC_MPC52xx) += mpc5xxx_clocks.o diff --git a/arch/powerpc/sysdev/dart_iommu.c b/arch/powerpc/sysdev/dart_iommu.c index e5519875cf17..21a1fae0714e 100644 --- a/arch/powerpc/sysdev/dart_iommu.c +++ b/arch/powerpc/sysdev/dart_iommu.c @@ -144,7 +144,7 @@ static void dart_cache_sync(unsigned int *base, unsigned int count) unsigned int tmp; /* Perform a standard cache flush */ - flush_inval_dcache_range(start, end); + flush_dcache_range(start, end); /* * Perform the sequence described in the CPC925 manual to diff --git a/arch/powerpc/sysdev/micropatch.c b/arch/powerpc/sysdev/micropatch.c deleted file mode 100644 index 33a9042fca80..000000000000 --- a/arch/powerpc/sysdev/micropatch.c +++ /dev/null @@ -1,749 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 - -/* Microcode patches for the CPM as supplied by Motorola. - * This is the one for IIC/SPI. There is a newer one that - * also relocates SMC2, but this would require additional changes - * to uart.c, so I am holding off on that for a moment. - */ -#include <linux/init.h> -#include <linux/errno.h> -#include <linux/sched.h> -#include <linux/kernel.h> -#include <linux/param.h> -#include <linux/string.h> -#include <linux/mm.h> -#include <linux/interrupt.h> -#include <asm/irq.h> -#include <asm/page.h> -#include <asm/pgtable.h> -#include <asm/8xx_immap.h> -#include <asm/cpm.h> -#include <asm/cpm1.h> - -/* - * I2C/SPI relocation patch arrays. - */ - -#ifdef CONFIG_I2C_SPI_UCODE_PATCH - -static uint patch_2000[] __initdata = { - 0x7FFFEFD9, - 0x3FFD0000, - 0x7FFB49F7, - 0x7FF90000, - 0x5FEFADF7, - 0x5F89ADF7, - 0x5FEFAFF7, - 0x5F89AFF7, - 0x3A9CFBC8, - 0xE7C0EDF0, - 0x77C1E1BB, - 0xF4DC7F1D, - 0xABAD932F, - 0x4E08FDCF, - 0x6E0FAFF8, - 0x7CCF76CF, - 0xFD1FF9CF, - 0xABF88DC6, - 0xAB5679F7, - 0xB0937383, - 0xDFCE79F7, - 0xB091E6BB, - 0xE5BBE74F, - 0xB3FA6F0F, - 0x6FFB76CE, - 0xEE0DF9CF, - 0x2BFBEFEF, - 0xCFEEF9CF, - 0x76CEAD24, - 0x90B2DF9A, - 0x7FDDD0BF, - 0x4BF847FD, - 0x7CCF76CE, - 0xCFEF7E1F, - 0x7F1D7DFD, - 0xF0B6EF71, - 0x7FC177C1, - 0xFBC86079, - 0xE722FBC8, - 0x5FFFDFFF, - 0x5FB2FFFB, - 0xFBC8F3C8, - 0x94A67F01, - 0x7F1D5F39, - 0xAFE85F5E, - 0xFFDFDF96, - 0xCB9FAF7D, - 0x5FC1AFED, - 0x8C1C5FC1, - 0xAFDD5FC3, - 0xDF9A7EFD, - 0xB0B25FB2, - 0xFFFEABAD, - 0x5FB2FFFE, - 0x5FCE600B, - 0xE6BB600B, - 0x5FCEDFC6, - 0x27FBEFDF, - 0x5FC8CFDE, - 0x3A9CE7C0, - 0xEDF0F3C8, - 0x7F0154CD, - 0x7F1D2D3D, - 0x363A7570, - 0x7E0AF1CE, - 0x37EF2E68, - 0x7FEE10EC, - 0xADF8EFDE, - 0xCFEAE52F, - 0x7D0FE12B, - 0xF1CE5F65, - 0x7E0A4DF8, - 0xCFEA5F72, - 0x7D0BEFEE, - 0xCFEA5F74, - 0xE522EFDE, - 0x5F74CFDA, - 0x0B627385, - 0xDF627E0A, - 0x30D8145B, - 0xBFFFF3C8, - 0x5FFFDFFF, - 0xA7F85F5E, - 0xBFFE7F7D, - 0x10D31450, - 0x5F36BFFF, - 0xAF785F5E, - 0xBFFDA7F8, - 0x5F36BFFE, - 0x77FD30C0, - 0x4E08FDCF, - 0xE5FF6E0F, - 0xAFF87E1F, - 0x7E0FFD1F, - 0xF1CF5F1B, - 0xABF80D5E, - 0x5F5EFFEF, - 0x79F730A2, - 0xAFDD5F34, - 0x47F85F34, - 0xAFED7FDD, - 0x50B24978, - 0x47FD7F1D, - 0x7DFD70AD, - 0xEF717EC1, - 0x6BA47F01, - 0x2D267EFD, - 0x30DE5F5E, - 0xFFFD5F5E, - 0xFFEF5F5E, - 0xFFDF0CA0, - 0xAFED0A9E, - 0xAFDD0C3A, - 0x5F3AAFBD, - 0x7FBDB082, - 0x5F8247F8 -}; - -static uint patch_2f00[] __initdata = { - 0x3E303430, - 0x34343737, - 0xABF7BF9B, - 0x994B4FBD, - 0xBD599493, - 0x349FFF37, - 0xFB9B177D, - 0xD9936956, - 0xBBFDD697, - 0xBDD2FD11, - 0x31DB9BB3, - 0x63139637, - 0x93733693, - 0x193137F7, - 0x331737AF, - 0x7BB9B999, - 0xBB197957, - 0x7FDFD3D5, - 0x73B773F7, - 0x37933B99, - 0x1D115316, - 0x99315315, - 0x31694BF4, - 0xFBDBD359, - 0x31497353, - 0x76956D69, - 0x7B9D9693, - 0x13131979, - 0x79376935 -}; -#endif - -/* - * I2C/SPI/SMC1 relocation patch arrays. - */ - -#ifdef CONFIG_I2C_SPI_SMC1_UCODE_PATCH - -static uint patch_2000[] __initdata = { - 0x3fff0000, - 0x3ffd0000, - 0x3ffb0000, - 0x3ff90000, - 0x5f13eff8, - 0x5eb5eff8, - 0x5f88adf7, - 0x5fefadf7, - 0x3a9cfbc8, - 0x77cae1bb, - 0xf4de7fad, - 0xabae9330, - 0x4e08fdcf, - 0x6e0faff8, - 0x7ccf76cf, - 0xfdaff9cf, - 0xabf88dc8, - 0xab5879f7, - 0xb0925d8d, - 0xdfd079f7, - 0xb090e6bb, - 0xe5bbe74f, - 0x9e046f0f, - 0x6ffb76ce, - 0xee0cf9cf, - 0x2bfbefef, - 0xcfeef9cf, - 0x76cead23, - 0x90b3df99, - 0x7fddd0c1, - 0x4bf847fd, - 0x7ccf76ce, - 0xcfef77ca, - 0x7eaf7fad, - 0x7dfdf0b7, - 0xef7a7fca, - 0x77cafbc8, - 0x6079e722, - 0xfbc85fff, - 0xdfff5fb3, - 0xfffbfbc8, - 0xf3c894a5, - 0xe7c9edf9, - 0x7f9a7fad, - 0x5f36afe8, - 0x5f5bffdf, - 0xdf95cb9e, - 0xaf7d5fc3, - 0xafed8c1b, - 0x5fc3afdd, - 0x5fc5df99, - 0x7efdb0b3, - 0x5fb3fffe, - 0xabae5fb3, - 0xfffe5fd0, - 0x600be6bb, - 0x600b5fd0, - 0xdfc827fb, - 0xefdf5fca, - 0xcfde3a9c, - 0xe7c9edf9, - 0xf3c87f9e, - 0x54ca7fed, - 0x2d3a3637, - 0x756f7e9a, - 0xf1ce37ef, - 0x2e677fee, - 0x10ebadf8, - 0xefdecfea, - 0xe52f7d9f, - 0xe12bf1ce, - 0x5f647e9a, - 0x4df8cfea, - 0x5f717d9b, - 0xefeecfea, - 0x5f73e522, - 0xefde5f73, - 0xcfda0b61, - 0x5d8fdf61, - 0xe7c9edf9, - 0x7e9a30d5, - 0x1458bfff, - 0xf3c85fff, - 0xdfffa7f8, - 0x5f5bbffe, - 0x7f7d10d0, - 0x144d5f33, - 0xbfffaf78, - 0x5f5bbffd, - 0xa7f85f33, - 0xbffe77fd, - 0x30bd4e08, - 0xfdcfe5ff, - 0x6e0faff8, - 0x7eef7e9f, - 0xfdeff1cf, - 0x5f17abf8, - 0x0d5b5f5b, - 0xffef79f7, - 0x309eafdd, - 0x5f3147f8, - 0x5f31afed, - 0x7fdd50af, - 0x497847fd, - 0x7f9e7fed, - 0x7dfd70a9, - 0xef7e7ece, - 0x6ba07f9e, - 0x2d227efd, - 0x30db5f5b, - 0xfffd5f5b, - 0xffef5f5b, - 0xffdf0c9c, - 0xafed0a9a, - 0xafdd0c37, - 0x5f37afbd, - 0x7fbdb081, - 0x5f8147f8, - 0x3a11e710, - 0xedf0ccdd, - 0xf3186d0a, - 0x7f0e5f06, - 0x7fedbb38, - 0x3afe7468, - 0x7fedf4fc, - 0x8ffbb951, - 0xb85f77fd, - 0xb0df5ddd, - 0xdefe7fed, - 0x90e1e74d, - 0x6f0dcbf7, - 0xe7decfed, - 0xcb74cfed, - 0xcfeddf6d, - 0x91714f74, - 0x5dd2deef, - 0x9e04e7df, - 0xefbb6ffb, - 0xe7ef7f0e, - 0x9e097fed, - 0xebdbeffa, - 0xeb54affb, - 0x7fea90d7, - 0x7e0cf0c3, - 0xbffff318, - 0x5fffdfff, - 0xac59efea, - 0x7fce1ee5, - 0xe2ff5ee1, - 0xaffbe2ff, - 0x5ee3affb, - 0xf9cc7d0f, - 0xaef8770f, - 0x7d0fb0c6, - 0xeffbbfff, - 0xcfef5ede, - 0x7d0fbfff, - 0x5ede4cf8, - 0x7fddd0bf, - 0x49f847fd, - 0x7efdf0bb, - 0x7fedfffd, - 0x7dfdf0b7, - 0xef7e7e1e, - 0x5ede7f0e, - 0x3a11e710, - 0xedf0ccab, - 0xfb18ad2e, - 0x1ea9bbb8, - 0x74283b7e, - 0x73c2e4bb, - 0x2ada4fb8, - 0xdc21e4bb, - 0xb2a1ffbf, - 0x5e2c43f8, - 0xfc87e1bb, - 0xe74ffd91, - 0x6f0f4fe8, - 0xc7ba32e2, - 0xf396efeb, - 0x600b4f78, - 0xe5bb760b, - 0x53acaef8, - 0x4ef88b0e, - 0xcfef9e09, - 0xabf8751f, - 0xefef5bac, - 0x741f4fe8, - 0x751e760d, - 0x7fdbf081, - 0x741cafce, - 0xefcc7fce, - 0x751e70ac, - 0x741ce7bb, - 0x3372cfed, - 0xafdbefeb, - 0xe5bb760b, - 0x53f2aef8, - 0xafe8e7eb, - 0x4bf8771e, - 0x7e247fed, - 0x4fcbe2cc, - 0x7fbc30a9, - 0x7b0f7a0f, - 0x34d577fd, - 0x308b5db7, - 0xde553e5f, - 0xaf78741f, - 0x741f30f0, - 0xcfef5e2c, - 0x741f3eac, - 0xafb8771e, - 0x5e677fed, - 0x0bd3e2cc, - 0x741ccfec, - 0xe5ca53cd, - 0x6fcb4f74, - 0x5dadde4b, - 0x2ab63d38, - 0x4bb3de30, - 0x751f741c, - 0x6c42effa, - 0xefea7fce, - 0x6ffc30be, - 0xefec3fca, - 0x30b3de2e, - 0xadf85d9e, - 0xaf7daefd, - 0x5d9ede2e, - 0x5d9eafdd, - 0x761f10ac, - 0x1da07efd, - 0x30adfffe, - 0x4908fb18, - 0x5fffdfff, - 0xafbb709b, - 0x4ef85e67, - 0xadf814ad, - 0x7a0f70ad, - 0xcfef50ad, - 0x7a0fde30, - 0x5da0afed, - 0x3c12780f, - 0xefef780f, - 0xefef790f, - 0xa7f85e0f, - 0xffef790f, - 0xefef790f, - 0x14adde2e, - 0x5d9eadfd, - 0x5e2dfffb, - 0xe79addfd, - 0xeff96079, - 0x607ae79a, - 0xddfceff9, - 0x60795dff, - 0x607acfef, - 0xefefefdf, - 0xefbfef7f, - 0xeeffedff, - 0xebffe7ff, - 0xafefafdf, - 0xafbfaf7f, - 0xaeffadff, - 0xabffa7ff, - 0x6fef6fdf, - 0x6fbf6f7f, - 0x6eff6dff, - 0x6bff67ff, - 0x2fef2fdf, - 0x2fbf2f7f, - 0x2eff2dff, - 0x2bff27ff, - 0x4e08fd1f, - 0xe5ff6e0f, - 0xaff87eef, - 0x7e0ffdef, - 0xf11f6079, - 0xabf8f542, - 0x7e0af11c, - 0x37cfae3a, - 0x7fec90be, - 0xadf8efdc, - 0xcfeae52f, - 0x7d0fe12b, - 0xf11c6079, - 0x7e0a4df8, - 0xcfea5dc4, - 0x7d0befec, - 0xcfea5dc6, - 0xe522efdc, - 0x5dc6cfda, - 0x4e08fd1f, - 0x6e0faff8, - 0x7c1f761f, - 0xfdeff91f, - 0x6079abf8, - 0x761cee24, - 0xf91f2bfb, - 0xefefcfec, - 0xf91f6079, - 0x761c27fb, - 0xefdf5da7, - 0xcfdc7fdd, - 0xd09c4bf8, - 0x47fd7c1f, - 0x761ccfcf, - 0x7eef7fed, - 0x7dfdf093, - 0xef7e7f1e, - 0x771efb18, - 0x6079e722, - 0xe6bbe5bb, - 0xae0ae5bb, - 0x600bae85, - 0xe2bbe2bb, - 0xe2bbe2bb, - 0xaf02e2bb, - 0xe2bb2ff9, - 0x6079e2bb -}; - -static uint patch_2f00[] __initdata = { - 0x30303030, - 0x3e3e3434, - 0xabbf9b99, - 0x4b4fbdbd, - 0x59949334, - 0x9fff37fb, - 0x9b177dd9, - 0x936956bb, - 0xfbdd697b, - 0xdd2fd113, - 0x1db9f7bb, - 0x36313963, - 0x79373369, - 0x3193137f, - 0x7331737a, - 0xf7bb9b99, - 0x9bb19795, - 0x77fdfd3d, - 0x573b773f, - 0x737933f7, - 0xb991d115, - 0x31699315, - 0x31531694, - 0xbf4fbdbd, - 0x35931497, - 0x35376956, - 0xbd697b9d, - 0x96931313, - 0x19797937, - 0x6935af78, - 0xb9b3baa3, - 0xb8788683, - 0x368f78f7, - 0x87778733, - 0x3ffffb3b, - 0x8e8f78b8, - 0x1d118e13, - 0xf3ff3f8b, - 0x6bd8e173, - 0xd1366856, - 0x68d1687b, - 0x3daf78b8, - 0x3a3a3f87, - 0x8f81378f, - 0xf876f887, - 0x77fd8778, - 0x737de8d6, - 0xbbf8bfff, - 0xd8df87f7, - 0xfd876f7b, - 0x8bfff8bd, - 0x8683387d, - 0xb873d87b, - 0x3b8fd7f8, - 0xf7338883, - 0xbb8ee1f8, - 0xef837377, - 0x3337b836, - 0x817d11f8, - 0x7378b878, - 0xd3368b7d, - 0xed731b7d, - 0x833731f3, - 0xf22f3f23 -}; - -static uint patch_2e00[] __initdata = { - 0x27eeeeee, - 0xeeeeeeee, - 0xeeeeeeee, - 0xeeeeeeee, - 0xee4bf4fb, - 0xdbd259bb, - 0x1979577f, - 0xdfd2d573, - 0xb773f737, - 0x4b4fbdbd, - 0x25b9b177, - 0xd2d17376, - 0x956bbfdd, - 0x697bdd2f, - 0xff9f79ff, - 0xff9ff22f -}; -#endif - -/* - * USB SOF patch arrays. - */ - -#ifdef CONFIG_USB_SOF_UCODE_PATCH - -static uint patch_2000[] __initdata = { - 0x7fff0000, - 0x7ffd0000, - 0x7ffb0000, - 0x49f7ba5b, - 0xba383ffb, - 0xf9b8b46d, - 0xe5ab4e07, - 0xaf77bffe, - 0x3f7bbf79, - 0xba5bba38, - 0xe7676076, - 0x60750000 -}; - -static uint patch_2f00[] __initdata = { - 0x3030304c, - 0xcab9e441, - 0xa1aaf220 -}; -#endif - -void __init cpm_load_patch(cpm8xx_t *cp) -{ - volatile uint *dp; /* Dual-ported RAM. */ - volatile cpm8xx_t *commproc; -#if defined(CONFIG_I2C_SPI_UCODE_PATCH) || \ - defined(CONFIG_I2C_SPI_SMC1_UCODE_PATCH) - volatile iic_t *iip; - volatile struct spi_pram *spp; -#ifdef CONFIG_I2C_SPI_SMC1_UCODE_PATCH - volatile smc_uart_t *smp; -#endif -#endif - int i; - - commproc = cp; - -#ifdef CONFIG_USB_SOF_UCODE_PATCH - commproc->cp_rccr = 0; - - dp = (uint *)(commproc->cp_dpmem); - for (i=0; i<(sizeof(patch_2000)/4); i++) - *dp++ = patch_2000[i]; - - dp = (uint *)&(commproc->cp_dpmem[0x0f00]); - for (i=0; i<(sizeof(patch_2f00)/4); i++) - *dp++ = patch_2f00[i]; - - commproc->cp_rccr = 0x0009; - - printk("USB SOF microcode patch installed\n"); -#endif /* CONFIG_USB_SOF_UCODE_PATCH */ - -#if defined(CONFIG_I2C_SPI_UCODE_PATCH) || \ - defined(CONFIG_I2C_SPI_SMC1_UCODE_PATCH) - - commproc->cp_rccr = 0; - - dp = (uint *)(commproc->cp_dpmem); - for (i=0; i<(sizeof(patch_2000)/4); i++) - *dp++ = patch_2000[i]; - - dp = (uint *)&(commproc->cp_dpmem[0x0f00]); - for (i=0; i<(sizeof(patch_2f00)/4); i++) - *dp++ = patch_2f00[i]; - - iip = (iic_t *)&commproc->cp_dparam[PROFF_IIC]; -# define RPBASE 0x0500 - iip->iic_rpbase = RPBASE; - - /* Put SPI above the IIC, also 32-byte aligned. - */ - i = (RPBASE + sizeof(iic_t) + 31) & ~31; - spp = (struct spi_pram *)&commproc->cp_dparam[PROFF_SPI]; - spp->rpbase = i; - -# if defined(CONFIG_I2C_SPI_UCODE_PATCH) - commproc->cp_cpmcr1 = 0x802a; - commproc->cp_cpmcr2 = 0x8028; - commproc->cp_cpmcr3 = 0x802e; - commproc->cp_cpmcr4 = 0x802c; - commproc->cp_rccr = 1; - - printk("I2C/SPI microcode patch installed.\n"); -# endif /* CONFIG_I2C_SPI_UCODE_PATCH */ - -# if defined(CONFIG_I2C_SPI_SMC1_UCODE_PATCH) - - dp = (uint *)&(commproc->cp_dpmem[0x0e00]); - for (i=0; i<(sizeof(patch_2e00)/4); i++) - *dp++ = patch_2e00[i]; - - commproc->cp_cpmcr1 = 0x8080; - commproc->cp_cpmcr2 = 0x808a; - commproc->cp_cpmcr3 = 0x8028; - commproc->cp_cpmcr4 = 0x802a; - commproc->cp_rccr = 3; - - smp = (smc_uart_t *)&commproc->cp_dparam[PROFF_SMC1]; - smp->smc_rpbase = 0x1FC0; - - printk("I2C/SPI/SMC1 microcode patch installed.\n"); -# endif /* CONFIG_I2C_SPI_SMC1_UCODE_PATCH) */ - -#endif /* some variation of the I2C/SPI patch was selected */ -} - -/* - * Take this entire routine out, since no one calls it and its - * logic is suspect. - */ - -#if 0 -void -verify_patch(volatile immap_t *immr) -{ - volatile uint *dp; - volatile cpm8xx_t *commproc; - int i; - - commproc = (cpm8xx_t *)&immr->im_cpm; - - printk("cp_rccr %x\n", commproc->cp_rccr); - commproc->cp_rccr = 0; - - dp = (uint *)(commproc->cp_dpmem); - for (i=0; i<(sizeof(patch_2000)/4); i++) - if (*dp++ != patch_2000[i]) { - printk("patch_2000 bad at %d\n", i); - dp--; - printk("found 0x%X, wanted 0x%X\n", *dp, patch_2000[i]); - break; - } - - dp = (uint *)&(commproc->cp_dpmem[0x0f00]); - for (i=0; i<(sizeof(patch_2f00)/4); i++) - if (*dp++ != patch_2f00[i]) { - printk("patch_2f00 bad at %d\n", i); - dp--; - printk("found 0x%X, wanted 0x%X\n", *dp, patch_2f00[i]); - break; - } - - commproc->cp_rccr = 0x0009; -} -#endif diff --git a/arch/powerpc/sysdev/xics/Kconfig b/arch/powerpc/sysdev/xics/Kconfig index 86fee428f5f1..304614c920aa 100644 --- a/arch/powerpc/sysdev/xics/Kconfig +++ b/arch/powerpc/sysdev/xics/Kconfig @@ -1,15 +1,14 @@ # SPDX-License-Identifier: GPL-2.0 config PPC_XICS - def_bool n - select PPC_SMP_MUXED_IPI - select HARDIRQS_SW_RESEND + def_bool n + select PPC_SMP_MUXED_IPI + select HARDIRQS_SW_RESEND config PPC_ICP_NATIVE - def_bool n + def_bool n config PPC_ICP_HV - def_bool n + def_bool n config PPC_ICS_RTAS - def_bool n - + def_bool n diff --git a/arch/powerpc/sysdev/xive/spapr.c b/arch/powerpc/sysdev/xive/spapr.c index cafb5c4df26b..8ef9cf4ebb1c 100644 --- a/arch/powerpc/sysdev/xive/spapr.c +++ b/arch/powerpc/sysdev/xive/spapr.c @@ -16,6 +16,7 @@ #include <linux/cpumask.h> #include <linux/mm.h> #include <linux/delay.h> +#include <linux/libfdt.h> #include <asm/prom.h> #include <asm/io.h> @@ -659,6 +660,55 @@ static bool xive_get_max_prio(u8 *max_prio) return true; } +static const u8 *get_vec5_feature(unsigned int index) +{ + unsigned long root, chosen; + int size; + const u8 *vec5; + + root = of_get_flat_dt_root(); + chosen = of_get_flat_dt_subnode_by_name(root, "chosen"); + if (chosen == -FDT_ERR_NOTFOUND) + return NULL; + + vec5 = of_get_flat_dt_prop(chosen, "ibm,architecture-vec-5", &size); + if (!vec5) + return NULL; + + if (size <= index) + return NULL; + + return vec5 + index; +} + +static bool xive_spapr_disabled(void) +{ + const u8 *vec5_xive; + + vec5_xive = get_vec5_feature(OV5_INDX(OV5_XIVE_SUPPORT)); + if (vec5_xive) { + u8 val; + + val = *vec5_xive & OV5_FEAT(OV5_XIVE_SUPPORT); + switch (val) { + case OV5_FEAT(OV5_XIVE_EITHER): + case OV5_FEAT(OV5_XIVE_LEGACY): + break; + case OV5_FEAT(OV5_XIVE_EXPLOIT): + /* Hypervisor only supports XIVE */ + if (xive_cmdline_disabled) + pr_warn("WARNING: Ignoring cmdline option xive=off\n"); + return false; + default: + pr_warn("%s: Unknown xive support option: 0x%x\n", + __func__, val); + break; + } + } + + return xive_cmdline_disabled; +} + bool __init xive_spapr_init(void) { struct device_node *np; @@ -671,7 +721,7 @@ bool __init xive_spapr_init(void) const __be32 *reg; int i; - if (xive_cmdline_disabled) + if (xive_spapr_disabled()) return false; pr_devel("%s()\n", __func__); diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index d0620d762a5a..14e56c25879f 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -465,8 +465,10 @@ static int xmon_core(struct pt_regs *regs, int fromipi) local_irq_save(flags); hard_irq_disable(); - tracing_enabled = tracing_is_on(); - tracing_off(); + if (!fromipi) { + tracing_enabled = tracing_is_on(); + tracing_off(); + } bp = in_breakpoint_table(regs->nip, &offset); if (bp != NULL) { @@ -2448,7 +2450,9 @@ static void dump_one_paca(int cpu) DUMP(p, canary, "%#-*lx"); #endif DUMP(p, saved_r1, "%#-*llx"); +#ifdef CONFIG_PPC_BOOK3E DUMP(p, trap_save, "%#-*x"); +#endif DUMP(p, irq_soft_mask, "%#-*x"); DUMP(p, irq_happened, "%#-*x"); #ifdef CONFIG_MMIOWB @@ -3090,7 +3094,7 @@ static void show_pte(unsigned long addr) printf("pgd @ 0x%px\n", pgdir); - if (pgd_huge(*pgdp)) { + if (pgd_is_leaf(*pgdp)) { format_pte(pgdp, pgd_val(*pgdp)); return; } @@ -3103,7 +3107,7 @@ static void show_pte(unsigned long addr) return; } - if (pud_huge(*pudp)) { + if (pud_is_leaf(*pudp)) { format_pte(pudp, pud_val(*pudp)); return; } @@ -3117,7 +3121,7 @@ static void show_pte(unsigned long addr) return; } - if (pmd_huge(*pmdp)) { + if (pmd_is_leaf(*pmdp)) { format_pte(pmdp, pmd_val(*pmdp)); return; } diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile index 6b0741c9f348..f8b3b07e4247 100644 --- a/arch/riscv/Makefile +++ b/arch/riscv/Makefile @@ -16,8 +16,6 @@ endif KBUILD_AFLAGS_MODULE += -fPIC KBUILD_CFLAGS_MODULE += -fPIC -KBUILD_DEFCONFIG = defconfig - export BITS ifeq ($(CONFIG_ARCH_RV64I),y) BITS := 64 diff --git a/arch/riscv/include/asm/pgalloc.h b/arch/riscv/include/asm/pgalloc.h index eb8b0195f27f..56a67d66f72f 100644 --- a/arch/riscv/include/asm/pgalloc.h +++ b/arch/riscv/include/asm/pgalloc.h @@ -10,6 +10,8 @@ #include <linux/mm.h> #include <asm/tlb.h> +#include <asm-generic/pgalloc.h> /* for pte_{alloc,free}_one */ + static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, pte_t *pte) { @@ -74,33 +76,6 @@ static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd) #endif /* __PAGETABLE_PMD_FOLDED */ -static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm) -{ - return (pte_t *)__get_free_page( - GFP_KERNEL | __GFP_RETRY_MAYFAIL | __GFP_ZERO); -} - -static inline struct page *pte_alloc_one(struct mm_struct *mm) -{ - struct page *pte; - - pte = alloc_page(GFP_KERNEL | __GFP_RETRY_MAYFAIL | __GFP_ZERO); - if (likely(pte != NULL)) - pgtable_page_ctor(pte); - return pte; -} - -static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) -{ - free_page((unsigned long)pte); -} - -static inline void pte_free(struct mm_struct *mm, pgtable_t pte) -{ - pgtable_page_dtor(pte); - __free_page(pte); -} - #define __pte_free_tlb(tlb, pte, buf) \ do { \ pgtable_page_dtor(pte); \ diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index fdb4246265a5..5d8570ed6cab 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -139,6 +139,7 @@ config S390 select HAVE_DMA_CONTIGUOUS select HAVE_DYNAMIC_FTRACE select HAVE_DYNAMIC_FTRACE_WITH_REGS + select HAVE_FAST_GUP select HAVE_EFFICIENT_UNALIGNED_ACCESS select HAVE_FENTRY select HAVE_FTRACE_MCOUNT_RECORD @@ -146,7 +147,6 @@ config S390 select HAVE_FUNCTION_TRACER select HAVE_FUTEX_CMPXCHG if FUTEX select HAVE_GCC_PLUGINS - select HAVE_GENERIC_GUP select HAVE_KERNEL_BZIP2 select HAVE_KERNEL_GZIP select HAVE_KERNEL_LZ4 @@ -641,9 +641,6 @@ config ARCH_SPARSEMEM_ENABLE config ARCH_SPARSEMEM_DEFAULT def_bool y -config ARCH_SELECT_MEMORY_MODEL - def_bool y - config ARCH_ENABLE_MEMORY_HOTPLUG def_bool y if SPARSEMEM diff --git a/arch/s390/Makefile b/arch/s390/Makefile index e48013cf50a2..e0bab7ed4123 100644 --- a/arch/s390/Makefile +++ b/arch/s390/Makefile @@ -10,8 +10,6 @@ # Copyright (C) 1994 by Linus Torvalds # -KBUILD_DEFCONFIG := defconfig - LD_BFD := elf64-s390 KBUILD_LDFLAGS := -m elf64_s390 KBUILD_AFLAGS_MODULE += -fPIC diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index a6dc01a22048..e26d4413d34c 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -588,6 +588,7 @@ CONFIG_GDB_SCRIPTS=y CONFIG_FRAME_WARN=1024 CONFIG_READABLE_ASM=y CONFIG_UNUSED_SYMBOLS=y +CONFIG_HEADERS_INSTALL=y CONFIG_HEADERS_CHECK=y CONFIG_DEBUG_SECTION_MISMATCH=y CONFIG_MAGIC_SYSRQ=y diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index 4a928e2c667b..abe60268335d 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -912,7 +912,6 @@ extern int kvm_s390_gisc_register(struct kvm *kvm, u32 gisc); extern int kvm_s390_gisc_unregister(struct kvm *kvm, u32 gisc); static inline void kvm_arch_hardware_disable(void) {} -static inline void kvm_arch_check_processor_compat(void *rtn) {} static inline void kvm_arch_sync_events(struct kvm *kvm) {} static inline void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) {} static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {} diff --git a/arch/s390/include/asm/pci_insn.h b/arch/s390/include/asm/pci_insn.h index ff81ed19c506..61cf9531f68f 100644 --- a/arch/s390/include/asm/pci_insn.h +++ b/arch/s390/include/asm/pci_insn.h @@ -143,14 +143,4 @@ static inline int zpci_set_irq_ctrl(u16 ctl, u8 isc) return __zpci_set_irq_ctrl(ctl, isc, &iib); } -#ifdef CONFIG_PCI -static inline void enable_mio_ctl(void) -{ - if (static_branch_likely(&have_mio)) - __ctl_set_bit(2, 5); -} -#else /* CONFIG_PCI */ -static inline void enable_mio_ctl(void) {} -#endif /* CONFIG_PCI */ - #endif diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 9f0195d5fa16..9b274fcaacb6 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -1270,14 +1270,8 @@ static inline pte_t *pte_offset(pmd_t *pmd, unsigned long address) #define pte_offset_map(pmd, address) pte_offset_kernel(pmd, address) #define pte_unmap(pte) do { } while (0) -static inline bool gup_fast_permitted(unsigned long start, int nr_pages) +static inline bool gup_fast_permitted(unsigned long start, unsigned long end) { - unsigned long len, end; - - len = (unsigned long) nr_pages << PAGE_SHIFT; - end = start + len; - if (end < start) - return false; return end <= current->mm->context.asce_limit; } #define gup_fast_permitted gup_fast_permitted diff --git a/arch/s390/include/asm/sclp.h b/arch/s390/include/asm/sclp.h index f577c5f6031a..c563f8368b19 100644 --- a/arch/s390/include/asm/sclp.h +++ b/arch/s390/include/asm/sclp.h @@ -80,7 +80,6 @@ struct sclp_info { unsigned char has_gisaf : 1; unsigned char has_diag318 : 1; unsigned char has_sipl : 1; - unsigned char has_sipl_g2 : 1; unsigned char has_dirq : 1; unsigned int ibc; unsigned int mtid; diff --git a/arch/s390/include/uapi/asm/dasd.h b/arch/s390/include/uapi/asm/dasd.h index 832be5c2584f..9ec86fae9980 100644 --- a/arch/s390/include/uapi/asm/dasd.h +++ b/arch/s390/include/uapi/asm/dasd.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -/* +/* * Author(s)......: Holger Smolinski <Holger.Smolinski@de.ibm.com> * Bugreports.to..: <Linux390@de.ibm.com> * Copyright IBM Corp. 1999, 2000 @@ -21,40 +21,40 @@ #define DASD_API_VERSION 6 -/* +/* * struct dasd_information2_t * represents any data about the device, which is visible to userspace. * including foramt and featueres. */ typedef struct dasd_information2_t { - unsigned int devno; /* S/390 devno */ - unsigned int real_devno; /* for aliases */ - unsigned int schid; /* S/390 subchannel identifier */ - unsigned int cu_type : 16; /* from SenseID */ - unsigned int cu_model : 8; /* from SenseID */ - unsigned int dev_type : 16; /* from SenseID */ - unsigned int dev_model : 8; /* from SenseID */ - unsigned int open_count; - unsigned int req_queue_len; - unsigned int chanq_len; /* length of chanq */ - char type[4]; /* from discipline.name, 'none' for unknown */ - unsigned int status; /* current device level */ - unsigned int label_block; /* where to find the VOLSER */ - unsigned int FBA_layout; /* fixed block size (like AIXVOL) */ - unsigned int characteristics_size; - unsigned int confdata_size; - char characteristics[64]; /* from read_device_characteristics */ - char configuration_data[256]; /* from read_configuration_data */ - unsigned int format; /* format info like formatted/cdl/ldl/... */ - unsigned int features; /* dasd features like 'ro',... */ - unsigned int reserved0; /* reserved for further use ,... */ - unsigned int reserved1; /* reserved for further use ,... */ - unsigned int reserved2; /* reserved for further use ,... */ - unsigned int reserved3; /* reserved for further use ,... */ - unsigned int reserved4; /* reserved for further use ,... */ - unsigned int reserved5; /* reserved for further use ,... */ - unsigned int reserved6; /* reserved for further use ,... */ - unsigned int reserved7; /* reserved for further use ,... */ + unsigned int devno; /* S/390 devno */ + unsigned int real_devno; /* for aliases */ + unsigned int schid; /* S/390 subchannel identifier */ + unsigned int cu_type : 16; /* from SenseID */ + unsigned int cu_model : 8; /* from SenseID */ + unsigned int dev_type : 16; /* from SenseID */ + unsigned int dev_model : 8; /* from SenseID */ + unsigned int open_count; + unsigned int req_queue_len; + unsigned int chanq_len; /* length of chanq */ + char type[4]; /* from discipline.name, 'none' for unknown */ + unsigned int status; /* current device level */ + unsigned int label_block; /* where to find the VOLSER */ + unsigned int FBA_layout; /* fixed block size (like AIXVOL) */ + unsigned int characteristics_size; + unsigned int confdata_size; + char characteristics[64]; /* from read_device_characteristics */ + char configuration_data[256]; /* from read_configuration_data */ + unsigned int format; /* format info like formatted/cdl/ldl/... */ + unsigned int features; /* dasd features like 'ro',... */ + unsigned int reserved0; /* reserved for further use ,... */ + unsigned int reserved1; /* reserved for further use ,... */ + unsigned int reserved2; /* reserved for further use ,... */ + unsigned int reserved3; /* reserved for further use ,... */ + unsigned int reserved4; /* reserved for further use ,... */ + unsigned int reserved5; /* reserved for further use ,... */ + unsigned int reserved6; /* reserved for further use ,... */ + unsigned int reserved7; /* reserved for further use ,... */ } dasd_information2_t; /* @@ -92,34 +92,34 @@ typedef struct dasd_information2_t { #define DASD_PARTN_BITS 2 -/* +/* * struct dasd_information_t * represents any data about the data, which is visible to userspace */ typedef struct dasd_information_t { - unsigned int devno; /* S/390 devno */ - unsigned int real_devno; /* for aliases */ - unsigned int schid; /* S/390 subchannel identifier */ - unsigned int cu_type : 16; /* from SenseID */ - unsigned int cu_model : 8; /* from SenseID */ - unsigned int dev_type : 16; /* from SenseID */ - unsigned int dev_model : 8; /* from SenseID */ - unsigned int open_count; - unsigned int req_queue_len; - unsigned int chanq_len; /* length of chanq */ - char type[4]; /* from discipline.name, 'none' for unknown */ - unsigned int status; /* current device level */ - unsigned int label_block; /* where to find the VOLSER */ - unsigned int FBA_layout; /* fixed block size (like AIXVOL) */ - unsigned int characteristics_size; - unsigned int confdata_size; - char characteristics[64]; /* from read_device_characteristics */ - char configuration_data[256]; /* from read_configuration_data */ + unsigned int devno; /* S/390 devno */ + unsigned int real_devno; /* for aliases */ + unsigned int schid; /* S/390 subchannel identifier */ + unsigned int cu_type : 16; /* from SenseID */ + unsigned int cu_model : 8; /* from SenseID */ + unsigned int dev_type : 16; /* from SenseID */ + unsigned int dev_model : 8; /* from SenseID */ + unsigned int open_count; + unsigned int req_queue_len; + unsigned int chanq_len; /* length of chanq */ + char type[4]; /* from discipline.name, 'none' for unknown */ + unsigned int status; /* current device level */ + unsigned int label_block; /* where to find the VOLSER */ + unsigned int FBA_layout; /* fixed block size (like AIXVOL) */ + unsigned int characteristics_size; + unsigned int confdata_size; + char characteristics[64]; /* from read_device_characteristics */ + char configuration_data[256]; /* from read_configuration_data */ } dasd_information_t; /* * Read Subsystem Data - Performance Statistics - */ + */ typedef struct dasd_rssd_perf_stats_t { unsigned char invalid:1; unsigned char format:3; @@ -154,21 +154,21 @@ typedef struct dasd_rssd_perf_stats_t { unsigned char reseved2[96]; } __attribute__((packed)) dasd_rssd_perf_stats_t; -/* +/* * struct profile_info_t - * holds the profinling information + * holds the profinling information */ typedef struct dasd_profile_info_t { - unsigned int dasd_io_reqs; /* number of requests processed at all */ - unsigned int dasd_io_sects; /* number of sectors processed at all */ - unsigned int dasd_io_secs[32]; /* histogram of request's sizes */ - unsigned int dasd_io_times[32]; /* histogram of requests's times */ - unsigned int dasd_io_timps[32]; /* histogram of requests's times per sector */ - unsigned int dasd_io_time1[32]; /* histogram of time from build to start */ - unsigned int dasd_io_time2[32]; /* histogram of time from start to irq */ - unsigned int dasd_io_time2ps[32]; /* histogram of time from start to irq */ - unsigned int dasd_io_time3[32]; /* histogram of time from irq to end */ - unsigned int dasd_io_nr_req[32]; /* histogram of # of requests in chanq */ + unsigned int dasd_io_reqs; /* number of requests processed at all */ + unsigned int dasd_io_sects; /* number of sectors processed at all */ + unsigned int dasd_io_secs[32]; /* histogram of request's sizes */ + unsigned int dasd_io_times[32]; /* histogram of requests's times */ + unsigned int dasd_io_timps[32]; /* histogram of requests's times per sector */ + unsigned int dasd_io_time1[32]; /* histogram of time from build to start */ + unsigned int dasd_io_time2[32]; /* histogram of time from start to irq */ + unsigned int dasd_io_time2ps[32]; /* histogram of time from start to irq */ + unsigned int dasd_io_time3[32]; /* histogram of time from irq to end */ + unsigned int dasd_io_nr_req[32]; /* histogram of # of requests in chanq */ } dasd_profile_info_t; /* @@ -189,10 +189,12 @@ typedef struct format_data_t { * 3/11: also write home address * 4/12: invalidate track */ -#define DASD_FMT_INT_FMT_R0 1 /* write record zero */ -#define DASD_FMT_INT_FMT_HA 2 /* write home address, also set FMT_R0 ! */ -#define DASD_FMT_INT_INVAL 4 /* invalidate tracks */ -#define DASD_FMT_INT_COMPAT 8 /* use OS/390 compatible disk layout */ +#define DASD_FMT_INT_FMT_R0 1 /* write record zero */ +#define DASD_FMT_INT_FMT_HA 2 /* write home address, also set FMT_R0 ! */ +#define DASD_FMT_INT_INVAL 4 /* invalidate tracks */ +#define DASD_FMT_INT_COMPAT 8 /* use OS/390 compatible disk layout */ +#define DASD_FMT_INT_FMT_NOR0 16 /* remove permission to write record zero */ +#define DASD_FMT_INT_ESE_FULL 32 /* release space for entire volume */ /* * struct format_check_t @@ -225,7 +227,7 @@ typedef struct format_check_t { /* If key-length was != 0 */ #define DASD_FMT_ERR_KEY_LENGTH 5 -/* +/* * struct attrib_data_t * represents the operation (cache) bits for the device. * Used in DE to influence caching of the DASD. @@ -281,13 +283,13 @@ struct dasd_snid_ioctl_data { * Here ist how the ioctl-nr should be used: * 0 - 31 DASD driver itself * 32 - 239 still open - * 240 - 255 reserved for EMC + * 240 - 255 reserved for EMC *******************************************************************************/ /* Disable the volume (for Linux) */ -#define BIODASDDISABLE _IO(DASD_IOCTL_LETTER,0) +#define BIODASDDISABLE _IO(DASD_IOCTL_LETTER,0) /* Enable the volume (for Linux) */ -#define BIODASDENABLE _IO(DASD_IOCTL_LETTER,1) +#define BIODASDENABLE _IO(DASD_IOCTL_LETTER,1) /* Issue a reserve/release command, rsp. */ #define BIODASDRSRV _IO(DASD_IOCTL_LETTER,2) /* reserve */ #define BIODASDRLSE _IO(DASD_IOCTL_LETTER,3) /* release */ @@ -295,9 +297,9 @@ struct dasd_snid_ioctl_data { /* reset profiling information of a device */ #define BIODASDPRRST _IO(DASD_IOCTL_LETTER,5) /* Quiesce IO on device */ -#define BIODASDQUIESCE _IO(DASD_IOCTL_LETTER,6) +#define BIODASDQUIESCE _IO(DASD_IOCTL_LETTER,6) /* Resume IO on device */ -#define BIODASDRESUME _IO(DASD_IOCTL_LETTER,7) +#define BIODASDRESUME _IO(DASD_IOCTL_LETTER,7) /* Abort all I/O on a device */ #define BIODASDABORTIO _IO(DASD_IOCTL_LETTER, 240) /* Allow I/O on a device */ @@ -315,13 +317,15 @@ struct dasd_snid_ioctl_data { /* Performance Statistics Read */ #define BIODASDPSRD _IOR(DASD_IOCTL_LETTER,4,dasd_rssd_perf_stats_t) /* Get Attributes (cache operations) */ -#define BIODASDGATTR _IOR(DASD_IOCTL_LETTER,5,attrib_data_t) +#define BIODASDGATTR _IOR(DASD_IOCTL_LETTER,5,attrib_data_t) /* #define BIODASDFORMAT _IOW(IOCTL_LETTER,0,format_data_t) , deprecated */ -#define BIODASDFMT _IOW(DASD_IOCTL_LETTER,1,format_data_t) +#define BIODASDFMT _IOW(DASD_IOCTL_LETTER,1,format_data_t) /* Set Attributes (cache operations) */ -#define BIODASDSATTR _IOW(DASD_IOCTL_LETTER,2,attrib_data_t) +#define BIODASDSATTR _IOW(DASD_IOCTL_LETTER,2,attrib_data_t) +/* Release Allocated Space */ +#define BIODASDRAS _IOW(DASD_IOCTL_LETTER, 3, format_data_t) /* Get Sense Path Group ID (SNID) data */ #define BIODASDSNID _IOWR(DASD_IOCTL_LETTER, 1, struct dasd_snid_ioctl_data) diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c index 629f173f60cd..6312fed48530 100644 --- a/arch/s390/kernel/early.c +++ b/arch/s390/kernel/early.c @@ -30,7 +30,6 @@ #include <asm/sclp.h> #include <asm/facility.h> #include <asm/boot_data.h> -#include <asm/pci_insn.h> #include "entry.h" /* @@ -236,7 +235,6 @@ static __init void detect_machine_facilities(void) clock_comparator_max = -1ULL >> 1; __ctl_set_bit(0, 53); } - enable_mio_ctl(); } static inline void save_vector_registers(void) diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c index d836af3ccc38..2c0a515428d6 100644 --- a/arch/s390/kernel/ipl.c +++ b/arch/s390/kernel/ipl.c @@ -286,12 +286,7 @@ static struct kobj_attribute sys_ipl_secure_attr = static ssize_t ipl_has_secure_show(struct kobject *kobj, struct kobj_attribute *attr, char *page) { - if (MACHINE_IS_LPAR) - return sprintf(page, "%i\n", !!sclp.has_sipl); - else if (MACHINE_IS_VM) - return sprintf(page, "%i\n", !!sclp.has_sipl_g2); - else - return sprintf(page, "%i\n", 0); + return sprintf(page, "%i\n", !!sclp.has_sipl); } static struct kobj_attribute sys_ipl_has_secure_attr = diff --git a/arch/s390/kernel/perf_cpum_cf_events.c b/arch/s390/kernel/perf_cpum_cf_events.c index 34cc96449b30..8b33e03e47b8 100644 --- a/arch/s390/kernel/perf_cpum_cf_events.c +++ b/arch/s390/kernel/perf_cpum_cf_events.c @@ -624,6 +624,8 @@ __init const struct attribute_group **cpumf_cf_event_group(void) break; case 0x3906: case 0x3907: + case 0x8561: + case 0x8562: model = cpumcf_z14_pmu_event_attr; break; default: diff --git a/arch/s390/kernel/unwind_bc.c b/arch/s390/kernel/unwind_bc.c index 3ce8a0808059..8fc9daae47a2 100644 --- a/arch/s390/kernel/unwind_bc.c +++ b/arch/s390/kernel/unwind_bc.c @@ -20,7 +20,7 @@ EXPORT_SYMBOL_GPL(unwind_get_return_address); static bool outside_of_stack(struct unwind_state *state, unsigned long sp) { return (sp <= state->sp) || - (sp + sizeof(struct stack_frame) > state->stack_info.end); + (sp > state->stack_info.end - sizeof(struct stack_frame)); } static bool update_stack_info(struct unwind_state *state, unsigned long sp) diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 1c4113f0f2a8..3f520cd837fb 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -227,6 +227,11 @@ int kvm_arch_hardware_enable(void) return 0; } +int kvm_arch_check_processor_compat(void) +{ + return 0; +} + static void kvm_gmap_notifier(struct gmap *gmap, unsigned long start, unsigned long end); @@ -2418,13 +2423,13 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) kvm->arch.sca = (struct bsca_block *) get_zeroed_page(alloc_flags); if (!kvm->arch.sca) goto out_err; - spin_lock(&kvm_lock); + mutex_lock(&kvm_lock); sca_offset += 16; if (sca_offset + sizeof(struct bsca_block) > PAGE_SIZE) sca_offset = 0; kvm->arch.sca = (struct bsca_block *) ((char *) kvm->arch.sca + sca_offset); - spin_unlock(&kvm_lock); + mutex_unlock(&kvm_lock); sprintf(debug_name, "kvm-%u", current->pid); diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c index b8a64cbb5dea..b0e3b9a0e488 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -890,8 +890,10 @@ static int __init pci_base_init(void) if (!test_facility(69) || !test_facility(71)) return 0; - if (test_facility(153) && !s390_pci_no_mio) + if (test_facility(153) && !s390_pci_no_mio) { static_branch_enable(&have_mio); + ctl_set_bit(2, 5); + } rc = zpci_debug_init(); if (rc) diff --git a/arch/s390/pci/pci_sysfs.c b/arch/s390/pci/pci_sysfs.c index 430c14b006d1..a433ba01a317 100644 --- a/arch/s390/pci/pci_sysfs.c +++ b/arch/s390/pci/pci_sysfs.c @@ -37,6 +37,15 @@ zpci_attr(segment1, "0x%02x\n", pfip[1]); zpci_attr(segment2, "0x%02x\n", pfip[2]); zpci_attr(segment3, "0x%02x\n", pfip[3]); +static ssize_t mio_enabled_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct zpci_dev *zdev = to_zpci(to_pci_dev(dev)); + + return sprintf(buf, zpci_use_mio(zdev) ? "1\n" : "0\n"); +} +static DEVICE_ATTR_RO(mio_enabled); + static ssize_t recover_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { @@ -115,6 +124,7 @@ static struct attribute *zpci_dev_attrs[] = { &dev_attr_vfn.attr, &dev_attr_uid.attr, &dev_attr_recover.attr, + &dev_attr_mio_enabled.attr, NULL, }; static struct attribute_group zpci_attr_group = { diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index c7c99e18d5ff..31a7d12db705 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -15,6 +15,7 @@ config SUPERH select HAVE_ARCH_TRACEHOOK select HAVE_PERF_EVENTS select HAVE_DEBUG_BUGVERBOSE + select HAVE_FAST_GUP if MMU select ARCH_HAVE_CUSTOM_GPIO_H select ARCH_HAVE_NMI_SAFE_CMPXCHG if (GUSA_RB || CPU_SH4A) select ARCH_HAS_GCOV_PROFILE_ALL @@ -64,6 +65,7 @@ config SUPERH config SUPERH32 def_bool "$(ARCH)" = "sh" select ARCH_32BIT_OFF_T + select GUP_GET_PTE_LOW_HIGH if X2TLB select HAVE_KPROBES select HAVE_KRETPROBES select HAVE_IOREMAP_PROT if MMU && !X2TLB diff --git a/arch/sh/configs/hp6xx_defconfig b/arch/sh/configs/hp6xx_defconfig index 4dcf7f552582..91d43e2bffea 100644 --- a/arch/sh/configs/hp6xx_defconfig +++ b/arch/sh/configs/hp6xx_defconfig @@ -40,7 +40,6 @@ CONFIG_FB=y CONFIG_FIRMWARE_EDID=y CONFIG_FB_HIT=y CONFIG_FB_SH_MOBILE_LCDC=y -CONFIG_BACKLIGHT_LCD_SUPPORT=y CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_FONTS=y CONFIG_FONT_PEARL_8x8=y diff --git a/arch/sh/configs/sdk7786_defconfig b/arch/sh/configs/sdk7786_defconfig index 5209889765ad..49a29338789b 100644 --- a/arch/sh/configs/sdk7786_defconfig +++ b/arch/sh/configs/sdk7786_defconfig @@ -191,7 +191,6 @@ CONFIG_CONFIGFS_FS=y CONFIG_JFFS2_FS=m CONFIG_JFFS2_FS_XATTR=y CONFIG_UBIFS_FS=m -CONFIG_LOGFS=m CONFIG_CRAMFS=m CONFIG_SQUASHFS=m CONFIG_ROMFS_FS=m diff --git a/arch/sh/configs/sh2007_defconfig b/arch/sh/configs/sh2007_defconfig index a1cf6447dbb1..cbd6742eb423 100644 --- a/arch/sh/configs/sh2007_defconfig +++ b/arch/sh/configs/sh2007_defconfig @@ -85,7 +85,6 @@ CONFIG_WATCHDOG=y CONFIG_SH_WDT=y CONFIG_SSB=y CONFIG_FB=y -CONFIG_BACKLIGHT_LCD_SUPPORT=y # CONFIG_LCD_CLASS_DEVICE is not set CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y diff --git a/arch/sh/include/asm/io.h b/arch/sh/include/asm/io.h index c28e37a344ad..ac0561960c52 100644 --- a/arch/sh/include/asm/io.h +++ b/arch/sh/include/asm/io.h @@ -369,7 +369,11 @@ static inline int iounmap_fixed(void __iomem *addr) { return -EINVAL; } #define ioremap_nocache ioremap #define ioremap_uc ioremap -#define iounmap __iounmap + +static inline void iounmap(void __iomem *addr) +{ + __iounmap(addr); +} /* * Convert a physical pointer to a virtual kernel pointer for /dev/mem diff --git a/arch/sh/include/asm/pgtable-3level.h b/arch/sh/include/asm/pgtable-3level.h index 7d8587eb65ff..779260b721ca 100644 --- a/arch/sh/include/asm/pgtable-3level.h +++ b/arch/sh/include/asm/pgtable-3level.h @@ -38,6 +38,9 @@ static inline unsigned long pud_page_vaddr(pud_t pud) return pud_val(pud); } +/* only used by the stubbed out hugetlb gup code, should never be called */ +#define pud_page(pud) NULL + #define pmd_index(address) (((address) >> PMD_SHIFT) & (PTRS_PER_PMD-1)) static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address) { diff --git a/arch/sh/include/asm/pgtable.h b/arch/sh/include/asm/pgtable.h index 3587103afe59..9085d1142fa3 100644 --- a/arch/sh/include/asm/pgtable.h +++ b/arch/sh/include/asm/pgtable.h @@ -149,6 +149,43 @@ extern void paging_init(void); extern void page_table_range_init(unsigned long start, unsigned long end, pgd_t *pgd); +static inline bool __pte_access_permitted(pte_t pte, u64 prot) +{ + return (pte_val(pte) & (prot | _PAGE_SPECIAL)) == prot; +} + +#ifdef CONFIG_X2TLB +static inline bool pte_access_permitted(pte_t pte, bool write) +{ + u64 prot = _PAGE_PRESENT; + + prot |= _PAGE_EXT(_PAGE_EXT_KERN_READ | _PAGE_EXT_USER_READ); + if (write) + prot |= _PAGE_EXT(_PAGE_EXT_KERN_WRITE | _PAGE_EXT_USER_WRITE); + return __pte_access_permitted(pte, prot); +} +#elif defined(CONFIG_SUPERH64) +static inline bool pte_access_permitted(pte_t pte, bool write) +{ + u64 prot = _PAGE_PRESENT | _PAGE_USER | _PAGE_READ; + + if (write) + prot |= _PAGE_WRITE; + return __pte_access_permitted(pte, prot); +} +#else +static inline bool pte_access_permitted(pte_t pte, bool write) +{ + u64 prot = _PAGE_PRESENT | _PAGE_USER; + + if (write) + prot |= _PAGE_RW; + return __pte_access_permitted(pte, prot); +} +#endif + +#define pte_access_permitted pte_access_permitted + /* arch/sh/mm/mmap.c */ #define HAVE_ARCH_UNMAPPED_AREA #define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN diff --git a/arch/sh/include/asm/ptrace.h b/arch/sh/include/asm/ptrace.h index 9143c7babcbe..6c89e3e04cee 100644 --- a/arch/sh/include/asm/ptrace.h +++ b/arch/sh/include/asm/ptrace.h @@ -16,8 +16,31 @@ #define user_mode(regs) (((regs)->sr & 0x40000000)==0) #define kernel_stack_pointer(_regs) ((unsigned long)(_regs)->regs[15]) -#define GET_FP(regs) ((regs)->regs[14]) -#define GET_USP(regs) ((regs)->regs[15]) +static inline unsigned long instruction_pointer(struct pt_regs *regs) +{ + return regs->pc; +} +static inline void instruction_pointer_set(struct pt_regs *regs, + unsigned long val) +{ + regs->pc = val; +} + +static inline unsigned long frame_pointer(struct pt_regs *regs) +{ + return regs->regs[14]; +} + +static inline unsigned long user_stack_pointer(struct pt_regs *regs) +{ + return regs->regs[15]; +} + +static inline void user_stack_pointer_set(struct pt_regs *regs, + unsigned long val) +{ + regs->regs[15] = val; +} #define arch_has_single_step() (1) @@ -112,7 +135,5 @@ static inline unsigned long profile_pc(struct pt_regs *regs) return pc; } -#define profile_pc profile_pc -#include <asm-generic/ptrace.h> #endif /* __ASM_SH_PTRACE_H */ diff --git a/arch/sh/kernel/kdebugfs.c b/arch/sh/kernel/kdebugfs.c index 95428e05d212..8b505e1556a5 100644 --- a/arch/sh/kernel/kdebugfs.c +++ b/arch/sh/kernel/kdebugfs.c @@ -9,9 +9,6 @@ EXPORT_SYMBOL(arch_debugfs_dir); static int __init arch_kdebugfs_init(void) { arch_debugfs_dir = debugfs_create_dir("sh", NULL); - if (!arch_debugfs_dir) - return -ENOMEM; - return 0; } arch_initcall(arch_kdebugfs_init); diff --git a/arch/sh/mm/Makefile b/arch/sh/mm/Makefile index fbe5e79751b3..5051b38fd5b6 100644 --- a/arch/sh/mm/Makefile +++ b/arch/sh/mm/Makefile @@ -17,7 +17,7 @@ cacheops-$(CONFIG_CPU_SHX3) += cache-shx3.o obj-y += $(cacheops-y) mmu-y := nommu.o extable_32.o -mmu-$(CONFIG_MMU) := extable_$(BITS).o fault.o gup.o ioremap.o kmap.o \ +mmu-$(CONFIG_MMU) := extable_$(BITS).o fault.o ioremap.o kmap.o \ pgtable.o tlbex_$(BITS).o tlbflush_$(BITS).o obj-y += $(mmu-y) diff --git a/arch/sh/mm/asids-debugfs.c b/arch/sh/mm/asids-debugfs.c index e5539e0f8e3b..4c1ca197e9c5 100644 --- a/arch/sh/mm/asids-debugfs.c +++ b/arch/sh/mm/asids-debugfs.c @@ -63,13 +63,8 @@ static const struct file_operations asids_debugfs_fops = { static int __init asids_debugfs_init(void) { - struct dentry *asids_dentry; - - asids_dentry = debugfs_create_file("asids", S_IRUSR, arch_debugfs_dir, - NULL, &asids_debugfs_fops); - if (!asids_dentry) - return -ENOMEM; - - return PTR_ERR_OR_ZERO(asids_dentry); + debugfs_create_file("asids", S_IRUSR, arch_debugfs_dir, NULL, + &asids_debugfs_fops); + return 0; } device_initcall(asids_debugfs_init); diff --git a/arch/sh/mm/cache-debugfs.c b/arch/sh/mm/cache-debugfs.c index 4eb9d43578b4..17d780794497 100644 --- a/arch/sh/mm/cache-debugfs.c +++ b/arch/sh/mm/cache-debugfs.c @@ -109,22 +109,10 @@ static const struct file_operations cache_debugfs_fops = { static int __init cache_debugfs_init(void) { - struct dentry *dcache_dentry, *icache_dentry; - - dcache_dentry = debugfs_create_file("dcache", S_IRUSR, arch_debugfs_dir, - (unsigned int *)CACHE_TYPE_DCACHE, - &cache_debugfs_fops); - if (!dcache_dentry) - return -ENOMEM; - - icache_dentry = debugfs_create_file("icache", S_IRUSR, arch_debugfs_dir, - (unsigned int *)CACHE_TYPE_ICACHE, - &cache_debugfs_fops); - if (!icache_dentry) { - debugfs_remove(dcache_dentry); - return -ENOMEM; - } - + debugfs_create_file("dcache", S_IRUSR, arch_debugfs_dir, + (void *)CACHE_TYPE_DCACHE, &cache_debugfs_fops); + debugfs_create_file("icache", S_IRUSR, arch_debugfs_dir, + (void *)CACHE_TYPE_ICACHE, &cache_debugfs_fops); return 0; } module_init(cache_debugfs_init); diff --git a/arch/sh/mm/gup.c b/arch/sh/mm/gup.c deleted file mode 100644 index 277c882f7489..000000000000 --- a/arch/sh/mm/gup.c +++ /dev/null @@ -1,277 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Lockless get_user_pages_fast for SuperH - * - * Copyright (C) 2009 - 2010 Paul Mundt - * - * Cloned from the x86 and PowerPC versions, by: - * - * Copyright (C) 2008 Nick Piggin - * Copyright (C) 2008 Novell Inc. - */ -#include <linux/sched.h> -#include <linux/mm.h> -#include <linux/vmstat.h> -#include <linux/highmem.h> -#include <asm/pgtable.h> - -static inline pte_t gup_get_pte(pte_t *ptep) -{ -#ifndef CONFIG_X2TLB - return READ_ONCE(*ptep); -#else - /* - * With get_user_pages_fast, we walk down the pagetables without - * taking any locks. For this we would like to load the pointers - * atomically, but that is not possible with 64-bit PTEs. What - * we do have is the guarantee that a pte will only either go - * from not present to present, or present to not present or both - * -- it will not switch to a completely different present page - * without a TLB flush in between; something that we are blocking - * by holding interrupts off. - * - * Setting ptes from not present to present goes: - * ptep->pte_high = h; - * smp_wmb(); - * ptep->pte_low = l; - * - * And present to not present goes: - * ptep->pte_low = 0; - * smp_wmb(); - * ptep->pte_high = 0; - * - * We must ensure here that the load of pte_low sees l iff pte_high - * sees h. We load pte_high *after* loading pte_low, which ensures we - * don't see an older value of pte_high. *Then* we recheck pte_low, - * which ensures that we haven't picked up a changed pte high. We might - * have got rubbish values from pte_low and pte_high, but we are - * guaranteed that pte_low will not have the present bit set *unless* - * it is 'l'. And get_user_pages_fast only operates on present ptes, so - * we're safe. - * - * gup_get_pte should not be used or copied outside gup.c without being - * very careful -- it does not atomically load the pte or anything that - * is likely to be useful for you. - */ - pte_t pte; - -retry: - pte.pte_low = ptep->pte_low; - smp_rmb(); - pte.pte_high = ptep->pte_high; - smp_rmb(); - if (unlikely(pte.pte_low != ptep->pte_low)) - goto retry; - - return pte; -#endif -} - -/* - * The performance critical leaf functions are made noinline otherwise gcc - * inlines everything into a single function which results in too much - * register pressure. - */ -static noinline int gup_pte_range(pmd_t pmd, unsigned long addr, - unsigned long end, int write, struct page **pages, int *nr) -{ - u64 mask, result; - pte_t *ptep; - -#ifdef CONFIG_X2TLB - result = _PAGE_PRESENT | _PAGE_EXT(_PAGE_EXT_KERN_READ | _PAGE_EXT_USER_READ); - if (write) - result |= _PAGE_EXT(_PAGE_EXT_KERN_WRITE | _PAGE_EXT_USER_WRITE); -#elif defined(CONFIG_SUPERH64) - result = _PAGE_PRESENT | _PAGE_USER | _PAGE_READ; - if (write) - result |= _PAGE_WRITE; -#else - result = _PAGE_PRESENT | _PAGE_USER; - if (write) - result |= _PAGE_RW; -#endif - - mask = result | _PAGE_SPECIAL; - - ptep = pte_offset_map(&pmd, addr); - do { - pte_t pte = gup_get_pte(ptep); - struct page *page; - - if ((pte_val(pte) & mask) != result) { - pte_unmap(ptep); - return 0; - } - VM_BUG_ON(!pfn_valid(pte_pfn(pte))); - page = pte_page(pte); - get_page(page); - __flush_anon_page(page, addr); - flush_dcache_page(page); - pages[*nr] = page; - (*nr)++; - - } while (ptep++, addr += PAGE_SIZE, addr != end); - pte_unmap(ptep - 1); - - return 1; -} - -static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end, - int write, struct page **pages, int *nr) -{ - unsigned long next; - pmd_t *pmdp; - - pmdp = pmd_offset(&pud, addr); - do { - pmd_t pmd = *pmdp; - - next = pmd_addr_end(addr, end); - if (pmd_none(pmd)) - return 0; - if (!gup_pte_range(pmd, addr, next, write, pages, nr)) - return 0; - } while (pmdp++, addr = next, addr != end); - - return 1; -} - -static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end, - int write, struct page **pages, int *nr) -{ - unsigned long next; - pud_t *pudp; - - pudp = pud_offset(&pgd, addr); - do { - pud_t pud = *pudp; - - next = pud_addr_end(addr, end); - if (pud_none(pud)) - return 0; - if (!gup_pmd_range(pud, addr, next, write, pages, nr)) - return 0; - } while (pudp++, addr = next, addr != end); - - return 1; -} - -/* - * Like get_user_pages_fast() except its IRQ-safe in that it won't fall - * back to the regular GUP. - * Note a difference with get_user_pages_fast: this always returns the - * number of pages pinned, 0 if no pages were pinned. - */ -int __get_user_pages_fast(unsigned long start, int nr_pages, int write, - struct page **pages) -{ - struct mm_struct *mm = current->mm; - unsigned long addr, len, end; - unsigned long next; - unsigned long flags; - pgd_t *pgdp; - int nr = 0; - - start &= PAGE_MASK; - addr = start; - len = (unsigned long) nr_pages << PAGE_SHIFT; - end = start + len; - if (unlikely(!access_ok((void __user *)start, len))) - return 0; - - /* - * This doesn't prevent pagetable teardown, but does prevent - * the pagetables and pages from being freed. - */ - local_irq_save(flags); - pgdp = pgd_offset(mm, addr); - do { - pgd_t pgd = *pgdp; - - next = pgd_addr_end(addr, end); - if (pgd_none(pgd)) - break; - if (!gup_pud_range(pgd, addr, next, write, pages, &nr)) - break; - } while (pgdp++, addr = next, addr != end); - local_irq_restore(flags); - - return nr; -} - -/** - * get_user_pages_fast() - pin user pages in memory - * @start: starting user address - * @nr_pages: number of pages from start to pin - * @gup_flags: flags modifying pin behaviour - * @pages: array that receives pointers to the pages pinned. - * Should be at least nr_pages long. - * - * Attempt to pin user pages in memory without taking mm->mmap_sem. - * If not successful, it will fall back to taking the lock and - * calling get_user_pages(). - * - * Returns number of pages pinned. This may be fewer than the number - * requested. If nr_pages is 0 or negative, returns 0. If no pages - * were pinned, returns -errno. - */ -int get_user_pages_fast(unsigned long start, int nr_pages, - unsigned int gup_flags, struct page **pages) -{ - struct mm_struct *mm = current->mm; - unsigned long addr, len, end; - unsigned long next; - pgd_t *pgdp; - int nr = 0; - - start &= PAGE_MASK; - addr = start; - len = (unsigned long) nr_pages << PAGE_SHIFT; - - end = start + len; - if (end < start) - goto slow_irqon; - - local_irq_disable(); - pgdp = pgd_offset(mm, addr); - do { - pgd_t pgd = *pgdp; - - next = pgd_addr_end(addr, end); - if (pgd_none(pgd)) - goto slow; - if (!gup_pud_range(pgd, addr, next, gup_flags & FOLL_WRITE, - pages, &nr)) - goto slow; - } while (pgdp++, addr = next, addr != end); - local_irq_enable(); - - VM_BUG_ON(nr != (end - start) >> PAGE_SHIFT); - return nr; - - { - int ret; - -slow: - local_irq_enable(); -slow_irqon: - /* Try to get the remaining pages with get_user_pages */ - start += nr << PAGE_SHIFT; - pages += nr; - - ret = get_user_pages_unlocked(start, - (end - start) >> PAGE_SHIFT, pages, - gup_flags); - - /* Have to be a bit careful with return values */ - if (nr > 0) { - if (ret < 0) - ret = nr; - else - ret += nr; - } - - return ret; - } -} diff --git a/arch/sh/mm/pmb.c b/arch/sh/mm/pmb.c index a53a040d0054..b59bad86b31e 100644 --- a/arch/sh/mm/pmb.c +++ b/arch/sh/mm/pmb.c @@ -861,13 +861,8 @@ static const struct file_operations pmb_debugfs_fops = { static int __init pmb_debugfs_init(void) { - struct dentry *dentry; - - dentry = debugfs_create_file("pmb", S_IFREG | S_IRUGO, - arch_debugfs_dir, NULL, &pmb_debugfs_fops); - if (!dentry) - return -ENOMEM; - + debugfs_create_file("pmb", S_IFREG | S_IRUGO, arch_debugfs_dir, NULL, + &pmb_debugfs_fops); return 0; } subsys_initcall(pmb_debugfs_init); diff --git a/arch/sh/mm/tlb-debugfs.c b/arch/sh/mm/tlb-debugfs.c index dea637a09246..11c6148283f3 100644 --- a/arch/sh/mm/tlb-debugfs.c +++ b/arch/sh/mm/tlb-debugfs.c @@ -149,22 +149,10 @@ static const struct file_operations tlb_debugfs_fops = { static int __init tlb_debugfs_init(void) { - struct dentry *itlb, *utlb; - - itlb = debugfs_create_file("itlb", S_IRUSR, arch_debugfs_dir, - (unsigned int *)TLB_TYPE_ITLB, - &tlb_debugfs_fops); - if (unlikely(!itlb)) - return -ENOMEM; - - utlb = debugfs_create_file("utlb", S_IRUSR, arch_debugfs_dir, - (unsigned int *)TLB_TYPE_UTLB, - &tlb_debugfs_fops); - if (unlikely(!utlb)) { - debugfs_remove(itlb); - return -ENOMEM; - } - + debugfs_create_file("itlb", S_IRUSR, arch_debugfs_dir, + (void *)TLB_TYPE_ITLB, &tlb_debugfs_fops); + debugfs_create_file("utlb", S_IRUSR, arch_debugfs_dir, + (void *)TLB_TYPE_UTLB, &tlb_debugfs_fops); return 0; } module_init(tlb_debugfs_init); diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index 26ab6f5bbaaf..e9f5d62e9817 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -28,6 +28,7 @@ config SPARC select RTC_DRV_M48T59 select RTC_SYSTOHC select HAVE_ARCH_JUMP_LABEL if SPARC64 + select HAVE_FAST_GUP if SPARC64 select GENERIC_IRQ_SHOW select ARCH_WANT_IPC_PARSE_VERSION select GENERIC_PCI_IOMAP @@ -300,9 +301,6 @@ config NODES_SPAN_OTHER_NODES def_bool y depends on NEED_MULTIPLE_NODES -config ARCH_SELECT_MEMORY_MODEL - def_bool y if SPARC64 - config ARCH_SPARSEMEM_ENABLE def_bool y if SPARC64 select SPARSEMEM_VMEMMAP_ENABLE diff --git a/arch/sparc/configs/sparc32_defconfig b/arch/sparc/configs/sparc32_defconfig index 2d4f34c52c67..7b3efe5edc1a 100644 --- a/arch/sparc/configs/sparc32_defconfig +++ b/arch/sparc/configs/sparc32_defconfig @@ -27,7 +27,6 @@ CONFIG_INET6_ESP=m CONFIG_INET6_IPCOMP=m CONFIG_IPV6_TUNNEL=m CONFIG_NET_PKTGEN=m -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_BLK_DEV_LOOP=m CONFIG_BLK_DEV_CRYPTOLOOP=m CONFIG_BLK_DEV_RAM=y diff --git a/arch/sparc/configs/sparc64_defconfig b/arch/sparc/configs/sparc64_defconfig index ea547d596fcf..6c325d53a20a 100644 --- a/arch/sparc/configs/sparc64_defconfig +++ b/arch/sparc/configs/sparc64_defconfig @@ -57,7 +57,6 @@ CONFIG_IPV6_TUNNEL=m CONFIG_VLAN_8021Q=m CONFIG_NET_PKTGEN=m CONFIG_NET_TCPPROBE=m -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" # CONFIG_PREVENT_FIRMWARE_BUILD is not set CONFIG_CONNECTOR=m CONFIG_BLK_DEV_LOOP=m diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h index 22500c3be7a9..1599de730532 100644 --- a/arch/sparc/include/asm/pgtable_64.h +++ b/arch/sparc/include/asm/pgtable_64.h @@ -864,6 +864,9 @@ static inline unsigned long pud_page_vaddr(pud_t pud) #define pgd_present(pgd) (pgd_val(pgd) != 0U) #define pgd_clear(pgdp) (pgd_val(*(pgdp)) = 0UL) +/* only used by the stubbed out hugetlb gup code, should never be called */ +#define pgd_page(pgd) NULL + static inline unsigned long pud_large(pud_t pud) { pte_t pte = __pte(pud_val(pud)); @@ -1075,6 +1078,46 @@ static inline int io_remap_pfn_range(struct vm_area_struct *vma, } #define io_remap_pfn_range io_remap_pfn_range +static inline unsigned long untagged_addr(unsigned long start) +{ + if (adi_capable()) { + long addr = start; + + /* If userspace has passed a versioned address, kernel + * will not find it in the VMAs since it does not store + * the version tags in the list of VMAs. Storing version + * tags in list of VMAs is impractical since they can be + * changed any time from userspace without dropping into + * kernel. Any address search in VMAs will be done with + * non-versioned addresses. Ensure the ADI version bits + * are dropped here by sign extending the last bit before + * ADI bits. IOMMU does not implement version tags. + */ + return (addr << (long)adi_nbits()) >> (long)adi_nbits(); + } + + return start; +} +#define untagged_addr untagged_addr + +static inline bool pte_access_permitted(pte_t pte, bool write) +{ + u64 prot; + + if (tlb_type == hypervisor) { + prot = _PAGE_PRESENT_4V | _PAGE_P_4V; + if (write) + prot |= _PAGE_WRITE_4V; + } else { + prot = _PAGE_PRESENT_4U | _PAGE_P_4U; + if (write) + prot |= _PAGE_WRITE_4U; + } + + return (pte_val(pte) & (prot | _PAGE_SPECIAL)) == prot; +} +#define pte_access_permitted pte_access_permitted + #include <asm/tlbflush.h> #include <asm-generic/pgtable.h> diff --git a/arch/sparc/include/uapi/asm/openpromio.h b/arch/sparc/include/uapi/asm/openpromio.h index 8817f7d1a70c..d4494b679e99 100644 --- a/arch/sparc/include/uapi/asm/openpromio.h +++ b/arch/sparc/include/uapi/asm/openpromio.h @@ -4,7 +4,6 @@ #include <linux/compiler.h> #include <linux/ioctl.h> -#include <linux/types.h> /* * SunOS and Solaris /dev/openprom definitions. The ioctl values @@ -13,7 +12,7 @@ struct openpromio { - u_int oprom_size; /* Actual size of the oprom_array. */ + unsigned int oprom_size; /* Actual size of the oprom_array. */ char oprom_array[1]; /* Holds property names and values. */ }; diff --git a/arch/sparc/lib/COPYING.LIB b/arch/sparc/lib/COPYING.LIB deleted file mode 100644 index eb685a5ec981..000000000000 --- a/arch/sparc/lib/COPYING.LIB +++ /dev/null @@ -1,481 +0,0 @@ - GNU LIBRARY GENERAL PUBLIC LICENSE - Version 2, June 1991 - - Copyright (C) 1991 Free Software Foundation, Inc. - 675 Mass Ave, Cambridge, MA 02139, USA - Everyone is permitted to copy and distribute verbatim copies - of this license document, but changing it is not allowed. - -[This is the first released version of the library GPL. It is - numbered 2 because it goes with version 2 of the ordinary GPL.] - - Preamble - - The licenses for most software are designed to take away your -freedom to share and change it. By contrast, the GNU General Public -Licenses are intended to guarantee your freedom to share and change -free software--to make sure the software is free for all its users. - - This license, the Library General Public License, applies to some -specially designated Free Software Foundation software, and to any -other libraries whose authors decide to use it. You can use it for -your libraries, too. - - When we speak of free software, we are referring to freedom, not -price. Our General Public Licenses are designed to make sure that you -have the freedom to distribute copies of free software (and charge for -this service if you wish), that you receive source code or can get it -if you want it, that you can change the software or use pieces of it -in new free programs; and that you know you can do these things. - - To protect your rights, we need to make restrictions that forbid -anyone to deny you these rights or to ask you to surrender the rights. -These restrictions translate to certain responsibilities for you if -you distribute copies of the library, or if you modify it. - - For example, if you distribute copies of the library, whether gratis -or for a fee, you must give the recipients all the rights that we gave -you. You must make sure that they, too, receive or can get the source -code. If you link a program with the library, you must provide -complete object files to the recipients so that they can relink them -with the library, after making changes to the library and recompiling -it. And you must show them these terms so they know their rights. - - Our method of protecting your rights has two steps: (1) copyright -the library, and (2) offer you this license which gives you legal -permission to copy, distribute and/or modify the library. - - Also, for each distributor's protection, we want to make certain -that everyone understands that there is no warranty for this free -library. If the library is modified by someone else and passed on, we -want its recipients to know that what they have is not the original -version, so that any problems introduced by others will not reflect on -the original authors' reputations. - - Finally, any free program is threatened constantly by software -patents. We wish to avoid the danger that companies distributing free -software will individually obtain patent licenses, thus in effect -transforming the program into proprietary software. To prevent this, -we have made it clear that any patent must be licensed for everyone's -free use or not licensed at all. - - Most GNU software, including some libraries, is covered by the ordinary -GNU General Public License, which was designed for utility programs. This -license, the GNU Library General Public License, applies to certain -designated libraries. This license is quite different from the ordinary -one; be sure to read it in full, and don't assume that anything in it is -the same as in the ordinary license. - - The reason we have a separate public license for some libraries is that -they blur the distinction we usually make between modifying or adding to a -program and simply using it. Linking a program with a library, without -changing the library, is in some sense simply using the library, and is -analogous to running a utility program or application program. However, in -a textual and legal sense, the linked executable is a combined work, a -derivative of the original library, and the ordinary General Public License -treats it as such. - - Because of this blurred distinction, using the ordinary General -Public License for libraries did not effectively promote software -sharing, because most developers did not use the libraries. We -concluded that weaker conditions might promote sharing better. - - However, unrestricted linking of non-free programs would deprive the -users of those programs of all benefit from the free status of the -libraries themselves. This Library General Public License is intended to -permit developers of non-free programs to use free libraries, while -preserving your freedom as a user of such programs to change the free -libraries that are incorporated in them. (We have not seen how to achieve -this as regards changes in header files, but we have achieved it as regards -changes in the actual functions of the Library.) The hope is that this -will lead to faster development of free libraries. - - The precise terms and conditions for copying, distribution and -modification follow. Pay close attention to the difference between a -"work based on the library" and a "work that uses the library". The -former contains code derived from the library, while the latter only -works together with the library. - - Note that it is possible for a library to be covered by the ordinary -General Public License rather than by this special one. - - GNU LIBRARY GENERAL PUBLIC LICENSE - TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION - - 0. This License Agreement applies to any software library which -contains a notice placed by the copyright holder or other authorized -party saying it may be distributed under the terms of this Library -General Public License (also called "this License"). Each licensee is -addressed as "you". - - A "library" means a collection of software functions and/or data -prepared so as to be conveniently linked with application programs -(which use some of those functions and data) to form executables. - - The "Library", below, refers to any such software library or work -which has been distributed under these terms. A "work based on the -Library" means either the Library or any derivative work under -copyright law: that is to say, a work containing the Library or a -portion of it, either verbatim or with modifications and/or translated -straightforwardly into another language. (Hereinafter, translation is -included without limitation in the term "modification".) - - "Source code" for a work means the preferred form of the work for -making modifications to it. For a library, complete source code means -all the source code for all modules it contains, plus any associated -interface definition files, plus the scripts used to control compilation -and installation of the library. - - Activities other than copying, distribution and modification are not -covered by this License; they are outside its scope. The act of -running a program using the Library is not restricted, and output from -such a program is covered only if its contents constitute a work based -on the Library (independent of the use of the Library in a tool for -writing it). Whether that is true depends on what the Library does -and what the program that uses the Library does. - - 1. You may copy and distribute verbatim copies of the Library's -complete source code as you receive it, in any medium, provided that -you conspicuously and appropriately publish on each copy an -appropriate copyright notice and disclaimer of warranty; keep intact -all the notices that refer to this License and to the absence of any -warranty; and distribute a copy of this License along with the -Library. - - You may charge a fee for the physical act of transferring a copy, -and you may at your option offer warranty protection in exchange for a -fee. - - 2. You may modify your copy or copies of the Library or any portion -of it, thus forming a work based on the Library, and copy and -distribute such modifications or work under the terms of Section 1 -above, provided that you also meet all of these conditions: - - a) The modified work must itself be a software library. - - b) You must cause the files modified to carry prominent notices - stating that you changed the files and the date of any change. - - c) You must cause the whole of the work to be licensed at no - charge to all third parties under the terms of this License. - - d) If a facility in the modified Library refers to a function or a - table of data to be supplied by an application program that uses - the facility, other than as an argument passed when the facility - is invoked, then you must make a good faith effort to ensure that, - in the event an application does not supply such function or - table, the facility still operates, and performs whatever part of - its purpose remains meaningful. - - (For example, a function in a library to compute square roots has - a purpose that is entirely well-defined independent of the - application. Therefore, Subsection 2d requires that any - application-supplied function or table used by this function must - be optional: if the application does not supply it, the square - root function must still compute square roots.) - -These requirements apply to the modified work as a whole. If -identifiable sections of that work are not derived from the Library, -and can be reasonably considered independent and separate works in -themselves, then this License, and its terms, do not apply to those -sections when you distribute them as separate works. But when you -distribute the same sections as part of a whole which is a work based -on the Library, the distribution of the whole must be on the terms of -this License, whose permissions for other licensees extend to the -entire whole, and thus to each and every part regardless of who wrote -it. - -Thus, it is not the intent of this section to claim rights or contest -your rights to work written entirely by you; rather, the intent is to -exercise the right to control the distribution of derivative or -collective works based on the Library. - -In addition, mere aggregation of another work not based on the Library -with the Library (or with a work based on the Library) on a volume of -a storage or distribution medium does not bring the other work under -the scope of this License. - - 3. You may opt to apply the terms of the ordinary GNU General Public -License instead of this License to a given copy of the Library. To do -this, you must alter all the notices that refer to this License, so -that they refer to the ordinary GNU General Public License, version 2, -instead of to this License. (If a newer version than version 2 of the -ordinary GNU General Public License has appeared, then you can specify -that version instead if you wish.) Do not make any other change in -these notices. - - Once this change is made in a given copy, it is irreversible for -that copy, so the ordinary GNU General Public License applies to all -subsequent copies and derivative works made from that copy. - - This option is useful when you wish to copy part of the code of -the Library into a program that is not a library. - - 4. You may copy and distribute the Library (or a portion or -derivative of it, under Section 2) in object code or executable form -under the terms of Sections 1 and 2 above provided that you accompany -it with the complete corresponding machine-readable source code, which -must be distributed under the terms of Sections 1 and 2 above on a -medium customarily used for software interchange. - - If distribution of object code is made by offering access to copy -from a designated place, then offering equivalent access to copy the -source code from the same place satisfies the requirement to -distribute the source code, even though third parties are not -compelled to copy the source along with the object code. - - 5. A program that contains no derivative of any portion of the -Library, but is designed to work with the Library by being compiled or -linked with it, is called a "work that uses the Library". Such a -work, in isolation, is not a derivative work of the Library, and -therefore falls outside the scope of this License. - - However, linking a "work that uses the Library" with the Library -creates an executable that is a derivative of the Library (because it -contains portions of the Library), rather than a "work that uses the -library". The executable is therefore covered by this License. -Section 6 states terms for distribution of such executables. - - When a "work that uses the Library" uses material from a header file -that is part of the Library, the object code for the work may be a -derivative work of the Library even though the source code is not. -Whether this is true is especially significant if the work can be -linked without the Library, or if the work is itself a library. The -threshold for this to be true is not precisely defined by law. - - If such an object file uses only numerical parameters, data -structure layouts and accessors, and small macros and small inline -functions (ten lines or less in length), then the use of the object -file is unrestricted, regardless of whether it is legally a derivative -work. (Executables containing this object code plus portions of the -Library will still fall under Section 6.) - - Otherwise, if the work is a derivative of the Library, you may -distribute the object code for the work under the terms of Section 6. -Any executables containing that work also fall under Section 6, -whether or not they are linked directly with the Library itself. - - 6. As an exception to the Sections above, you may also compile or -link a "work that uses the Library" with the Library to produce a -work containing portions of the Library, and distribute that work -under terms of your choice, provided that the terms permit -modification of the work for the customer's own use and reverse -engineering for debugging such modifications. - - You must give prominent notice with each copy of the work that the -Library is used in it and that the Library and its use are covered by -this License. You must supply a copy of this License. If the work -during execution displays copyright notices, you must include the -copyright notice for the Library among them, as well as a reference -directing the user to the copy of this License. Also, you must do one -of these things: - - a) Accompany the work with the complete corresponding - machine-readable source code for the Library including whatever - changes were used in the work (which must be distributed under - Sections 1 and 2 above); and, if the work is an executable linked - with the Library, with the complete machine-readable "work that - uses the Library", as object code and/or source code, so that the - user can modify the Library and then relink to produce a modified - executable containing the modified Library. (It is understood - that the user who changes the contents of definitions files in the - Library will not necessarily be able to recompile the application - to use the modified definitions.) - - b) Accompany the work with a written offer, valid for at - least three years, to give the same user the materials - specified in Subsection 6a, above, for a charge no more - than the cost of performing this distribution. - - c) If distribution of the work is made by offering access to copy - from a designated place, offer equivalent access to copy the above - specified materials from the same place. - - d) Verify that the user has already received a copy of these - materials or that you have already sent this user a copy. - - For an executable, the required form of the "work that uses the -Library" must include any data and utility programs needed for -reproducing the executable from it. However, as a special exception, -the source code distributed need not include anything that is normally -distributed (in either source or binary form) with the major -components (compiler, kernel, and so on) of the operating system on -which the executable runs, unless that component itself accompanies -the executable. - - It may happen that this requirement contradicts the license -restrictions of other proprietary libraries that do not normally -accompany the operating system. Such a contradiction means you cannot -use both them and the Library together in an executable that you -distribute. - - 7. You may place library facilities that are a work based on the -Library side-by-side in a single library together with other library -facilities not covered by this License, and distribute such a combined -library, provided that the separate distribution of the work based on -the Library and of the other library facilities is otherwise -permitted, and provided that you do these two things: - - a) Accompany the combined library with a copy of the same work - based on the Library, uncombined with any other library - facilities. This must be distributed under the terms of the - Sections above. - - b) Give prominent notice with the combined library of the fact - that part of it is a work based on the Library, and explaining - where to find the accompanying uncombined form of the same work. - - 8. You may not copy, modify, sublicense, link with, or distribute -the Library except as expressly provided under this License. Any -attempt otherwise to copy, modify, sublicense, link with, or -distribute the Library is void, and will automatically terminate your -rights under this License. However, parties who have received copies, -or rights, from you under this License will not have their licenses -terminated so long as such parties remain in full compliance. - - 9. You are not required to accept this License, since you have not -signed it. However, nothing else grants you permission to modify or -distribute the Library or its derivative works. These actions are -prohibited by law if you do not accept this License. Therefore, by -modifying or distributing the Library (or any work based on the -Library), you indicate your acceptance of this License to do so, and -all its terms and conditions for copying, distributing or modifying -the Library or works based on it. - - 10. Each time you redistribute the Library (or any work based on the -Library), the recipient automatically receives a license from the -original licensor to copy, distribute, link with or modify the Library -subject to these terms and conditions. You may not impose any further -restrictions on the recipients' exercise of the rights granted herein. -You are not responsible for enforcing compliance by third parties to -this License. - - 11. If, as a consequence of a court judgment or allegation of patent -infringement or for any other reason (not limited to patent issues), -conditions are imposed on you (whether by court order, agreement or -otherwise) that contradict the conditions of this License, they do not -excuse you from the conditions of this License. If you cannot -distribute so as to satisfy simultaneously your obligations under this -License and any other pertinent obligations, then as a consequence you -may not distribute the Library at all. For example, if a patent -license would not permit royalty-free redistribution of the Library by -all those who receive copies directly or indirectly through you, then -the only way you could satisfy both it and this License would be to -refrain entirely from distribution of the Library. - -If any portion of this section is held invalid or unenforceable under any -particular circumstance, the balance of the section is intended to apply, -and the section as a whole is intended to apply in other circumstances. - -It is not the purpose of this section to induce you to infringe any -patents or other property right claims or to contest validity of any -such claims; this section has the sole purpose of protecting the -integrity of the free software distribution system which is -implemented by public license practices. Many people have made -generous contributions to the wide range of software distributed -through that system in reliance on consistent application of that -system; it is up to the author/donor to decide if he or she is willing -to distribute software through any other system and a licensee cannot -impose that choice. - -This section is intended to make thoroughly clear what is believed to -be a consequence of the rest of this License. - - 12. If the distribution and/or use of the Library is restricted in -certain countries either by patents or by copyrighted interfaces, the -original copyright holder who places the Library under this License may add -an explicit geographical distribution limitation excluding those countries, -so that distribution is permitted only in or among countries not thus -excluded. In such case, this License incorporates the limitation as if -written in the body of this License. - - 13. The Free Software Foundation may publish revised and/or new -versions of the Library General Public License from time to time. -Such new versions will be similar in spirit to the present version, -but may differ in detail to address new problems or concerns. - -Each version is given a distinguishing version number. If the Library -specifies a version number of this License which applies to it and -"any later version", you have the option of following the terms and -conditions either of that version or of any later version published by -the Free Software Foundation. If the Library does not specify a -license version number, you may choose any version ever published by -the Free Software Foundation. - - 14. If you wish to incorporate parts of the Library into other free -programs whose distribution conditions are incompatible with these, -write to the author to ask for permission. For software which is -copyrighted by the Free Software Foundation, write to the Free -Software Foundation; we sometimes make exceptions for this. Our -decision will be guided by the two goals of preserving the free status -of all derivatives of our free software and of promoting the sharing -and reuse of software generally. - - NO WARRANTY - - 15. BECAUSE THE LIBRARY IS LICENSED FREE OF CHARGE, THERE IS NO -WARRANTY FOR THE LIBRARY, TO THE EXTENT PERMITTED BY APPLICABLE LAW. -EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR -OTHER PARTIES PROVIDE THE LIBRARY "AS IS" WITHOUT WARRANTY OF ANY -KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR -PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE -LIBRARY IS WITH YOU. SHOULD THE LIBRARY PROVE DEFECTIVE, YOU ASSUME -THE COST OF ALL NECESSARY SERVICING, REPAIR OR CORRECTION. - - 16. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN -WRITING WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY -AND/OR REDISTRIBUTE THE LIBRARY AS PERMITTED ABOVE, BE LIABLE TO YOU -FOR DAMAGES, INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR -CONSEQUENTIAL DAMAGES ARISING OUT OF THE USE OR INABILITY TO USE THE -LIBRARY (INCLUDING BUT NOT LIMITED TO LOSS OF DATA OR DATA BEING -RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD PARTIES OR A -FAILURE OF THE LIBRARY TO OPERATE WITH ANY OTHER SOFTWARE), EVEN IF -SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH -DAMAGES. - - END OF TERMS AND CONDITIONS - - Appendix: How to Apply These Terms to Your New Libraries - - If you develop a new library, and you want it to be of the greatest -possible use to the public, we recommend making it free software that -everyone can redistribute and change. You can do so by permitting -redistribution under these terms (or, alternatively, under the terms of the -ordinary General Public License). - - To apply these terms, attach the following notices to the library. It is -safest to attach them to the start of each source file to most effectively -convey the exclusion of warranty; and each file should have at least the -"copyright" line and a pointer to where the full notice is found. - - <one line to give the library's name and a brief idea of what it does.> - Copyright (C) <year> <name of author> - - This library is free software; you can redistribute it and/or - modify it under the terms of the GNU Library General Public - License as published by the Free Software Foundation; either - version 2 of the License, or (at your option) any later version. - - This library is distributed in the hope that it will be useful, - but WITHOUT ANY WARRANTY; without even the implied warranty of - MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - Library General Public License for more details. - - You should have received a copy of the GNU Library General Public - License along with this library; if not, write to the Free - Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. - -Also add information on how to contact you by electronic and paper mail. - -You should also get your employer (if you work as a programmer) or your -school, if any, to sign a "copyright disclaimer" for the library, if -necessary. Here is a sample; alter the names: - - Yoyodyne, Inc., hereby disclaims all copyright interest in the - library `Frob' (a library for tweaking knobs) written by James Random Hacker. - - <signature of Ty Coon>, 1 April 1990 - Ty Coon, President of Vice - -That's all there is to it! diff --git a/arch/sparc/lib/NG4clear_page.S b/arch/sparc/lib/NG4clear_page.S index 97e2678d042a..d91d6b5f2444 100644 --- a/arch/sparc/lib/NG4clear_page.S +++ b/arch/sparc/lib/NG4clear_page.S @@ -27,4 +27,4 @@ NG4clear_user_page: /* %o0=dest, %o1=vaddr */ retl nop .size NG4clear_page,.-NG4clear_page - .size NG4clear_user_page,.-NG4clear_user_page
\ No newline at end of file + .size NG4clear_user_page,.-NG4clear_user_page diff --git a/arch/sparc/mm/Makefile b/arch/sparc/mm/Makefile index d39075b1e3b7..b078205b70e0 100644 --- a/arch/sparc/mm/Makefile +++ b/arch/sparc/mm/Makefile @@ -5,7 +5,7 @@ asflags-y := -ansi ccflags-y := -Werror -obj-$(CONFIG_SPARC64) += ultra.o tlb.o tsb.o gup.o +obj-$(CONFIG_SPARC64) += ultra.o tlb.o tsb.o obj-y += fault_$(BITS).o obj-y += init_$(BITS).o obj-$(CONFIG_SPARC32) += extable.o srmmu.o iommu.o io-unit.o diff --git a/arch/sparc/mm/gup.c b/arch/sparc/mm/gup.c deleted file mode 100644 index 1e770a517d4a..000000000000 --- a/arch/sparc/mm/gup.c +++ /dev/null @@ -1,340 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Lockless get_user_pages_fast for sparc, cribbed from powerpc - * - * Copyright (C) 2008 Nick Piggin - * Copyright (C) 2008 Novell Inc. - */ - -#include <linux/sched.h> -#include <linux/mm.h> -#include <linux/vmstat.h> -#include <linux/pagemap.h> -#include <linux/rwsem.h> -#include <asm/pgtable.h> -#include <asm/adi.h> - -/* - * The performance critical leaf functions are made noinline otherwise gcc - * inlines everything into a single function which results in too much - * register pressure. - */ -static noinline int gup_pte_range(pmd_t pmd, unsigned long addr, - unsigned long end, int write, struct page **pages, int *nr) -{ - unsigned long mask, result; - pte_t *ptep; - - if (tlb_type == hypervisor) { - result = _PAGE_PRESENT_4V|_PAGE_P_4V; - if (write) - result |= _PAGE_WRITE_4V; - } else { - result = _PAGE_PRESENT_4U|_PAGE_P_4U; - if (write) - result |= _PAGE_WRITE_4U; - } - mask = result | _PAGE_SPECIAL; - - ptep = pte_offset_kernel(&pmd, addr); - do { - struct page *page, *head; - pte_t pte = *ptep; - - if ((pte_val(pte) & mask) != result) - return 0; - VM_BUG_ON(!pfn_valid(pte_pfn(pte))); - - /* The hugepage case is simplified on sparc64 because - * we encode the sub-page pfn offsets into the - * hugepage PTEs. We could optimize this in the future - * use page_cache_add_speculative() for the hugepage case. - */ - page = pte_page(pte); - head = compound_head(page); - if (!page_cache_get_speculative(head)) - return 0; - if (unlikely(pte_val(pte) != pte_val(*ptep))) { - put_page(head); - return 0; - } - - pages[*nr] = page; - (*nr)++; - } while (ptep++, addr += PAGE_SIZE, addr != end); - - return 1; -} - -static int gup_huge_pmd(pmd_t *pmdp, pmd_t pmd, unsigned long addr, - unsigned long end, int write, struct page **pages, - int *nr) -{ - struct page *head, *page; - int refs; - - if (!(pmd_val(pmd) & _PAGE_VALID)) - return 0; - - if (write && !pmd_write(pmd)) - return 0; - - refs = 0; - page = pmd_page(pmd) + ((addr & ~PMD_MASK) >> PAGE_SHIFT); - head = compound_head(page); - do { - VM_BUG_ON(compound_head(page) != head); - pages[*nr] = page; - (*nr)++; - page++; - refs++; - } while (addr += PAGE_SIZE, addr != end); - - if (!page_cache_add_speculative(head, refs)) { - *nr -= refs; - return 0; - } - - if (unlikely(pmd_val(pmd) != pmd_val(*pmdp))) { - *nr -= refs; - while (refs--) - put_page(head); - return 0; - } - - return 1; -} - -static int gup_huge_pud(pud_t *pudp, pud_t pud, unsigned long addr, - unsigned long end, int write, struct page **pages, - int *nr) -{ - struct page *head, *page; - int refs; - - if (!(pud_val(pud) & _PAGE_VALID)) - return 0; - - if (write && !pud_write(pud)) - return 0; - - refs = 0; - page = pud_page(pud) + ((addr & ~PUD_MASK) >> PAGE_SHIFT); - head = compound_head(page); - do { - VM_BUG_ON(compound_head(page) != head); - pages[*nr] = page; - (*nr)++; - page++; - refs++; - } while (addr += PAGE_SIZE, addr != end); - - if (!page_cache_add_speculative(head, refs)) { - *nr -= refs; - return 0; - } - - if (unlikely(pud_val(pud) != pud_val(*pudp))) { - *nr -= refs; - while (refs--) - put_page(head); - return 0; - } - - return 1; -} - -static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end, - int write, struct page **pages, int *nr) -{ - unsigned long next; - pmd_t *pmdp; - - pmdp = pmd_offset(&pud, addr); - do { - pmd_t pmd = *pmdp; - - next = pmd_addr_end(addr, end); - if (pmd_none(pmd)) - return 0; - if (unlikely(pmd_large(pmd))) { - if (!gup_huge_pmd(pmdp, pmd, addr, next, - write, pages, nr)) - return 0; - } else if (!gup_pte_range(pmd, addr, next, write, - pages, nr)) - return 0; - } while (pmdp++, addr = next, addr != end); - - return 1; -} - -static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end, - int write, struct page **pages, int *nr) -{ - unsigned long next; - pud_t *pudp; - - pudp = pud_offset(&pgd, addr); - do { - pud_t pud = *pudp; - - next = pud_addr_end(addr, end); - if (pud_none(pud)) - return 0; - if (unlikely(pud_large(pud))) { - if (!gup_huge_pud(pudp, pud, addr, next, - write, pages, nr)) - return 0; - } else if (!gup_pmd_range(pud, addr, next, write, pages, nr)) - return 0; - } while (pudp++, addr = next, addr != end); - - return 1; -} - -/* - * Note a difference with get_user_pages_fast: this always returns the - * number of pages pinned, 0 if no pages were pinned. - */ -int __get_user_pages_fast(unsigned long start, int nr_pages, int write, - struct page **pages) -{ - struct mm_struct *mm = current->mm; - unsigned long addr, len, end; - unsigned long next, flags; - pgd_t *pgdp; - int nr = 0; - -#ifdef CONFIG_SPARC64 - if (adi_capable()) { - long addr = start; - - /* If userspace has passed a versioned address, kernel - * will not find it in the VMAs since it does not store - * the version tags in the list of VMAs. Storing version - * tags in list of VMAs is impractical since they can be - * changed any time from userspace without dropping into - * kernel. Any address search in VMAs will be done with - * non-versioned addresses. Ensure the ADI version bits - * are dropped here by sign extending the last bit before - * ADI bits. IOMMU does not implement version tags. - */ - addr = (addr << (long)adi_nbits()) >> (long)adi_nbits(); - start = addr; - } -#endif - start &= PAGE_MASK; - addr = start; - len = (unsigned long) nr_pages << PAGE_SHIFT; - end = start + len; - - local_irq_save(flags); - pgdp = pgd_offset(mm, addr); - do { - pgd_t pgd = *pgdp; - - next = pgd_addr_end(addr, end); - if (pgd_none(pgd)) - break; - if (!gup_pud_range(pgd, addr, next, write, pages, &nr)) - break; - } while (pgdp++, addr = next, addr != end); - local_irq_restore(flags); - - return nr; -} - -int get_user_pages_fast(unsigned long start, int nr_pages, - unsigned int gup_flags, struct page **pages) -{ - struct mm_struct *mm = current->mm; - unsigned long addr, len, end; - unsigned long next; - pgd_t *pgdp; - int nr = 0; - -#ifdef CONFIG_SPARC64 - if (adi_capable()) { - long addr = start; - - /* If userspace has passed a versioned address, kernel - * will not find it in the VMAs since it does not store - * the version tags in the list of VMAs. Storing version - * tags in list of VMAs is impractical since they can be - * changed any time from userspace without dropping into - * kernel. Any address search in VMAs will be done with - * non-versioned addresses. Ensure the ADI version bits - * are dropped here by sign extending the last bit before - * ADI bits. IOMMU does not implements version tags, - */ - addr = (addr << (long)adi_nbits()) >> (long)adi_nbits(); - start = addr; - } -#endif - start &= PAGE_MASK; - addr = start; - len = (unsigned long) nr_pages << PAGE_SHIFT; - end = start + len; - - /* - * XXX: batch / limit 'nr', to avoid large irq off latency - * needs some instrumenting to determine the common sizes used by - * important workloads (eg. DB2), and whether limiting the batch size - * will decrease performance. - * - * It seems like we're in the clear for the moment. Direct-IO is - * the main guy that batches up lots of get_user_pages, and even - * they are limited to 64-at-a-time which is not so many. - */ - /* - * This doesn't prevent pagetable teardown, but does prevent - * the pagetables from being freed on sparc. - * - * So long as we atomically load page table pointers versus teardown, - * we can follow the address down to the the page and take a ref on it. - */ - local_irq_disable(); - - pgdp = pgd_offset(mm, addr); - do { - pgd_t pgd = *pgdp; - - next = pgd_addr_end(addr, end); - if (pgd_none(pgd)) - goto slow; - if (!gup_pud_range(pgd, addr, next, gup_flags & FOLL_WRITE, - pages, &nr)) - goto slow; - } while (pgdp++, addr = next, addr != end); - - local_irq_enable(); - - VM_BUG_ON(nr != (end - start) >> PAGE_SHIFT); - return nr; - - { - int ret; - -slow: - local_irq_enable(); - - /* Try to get the remaining pages with get_user_pages */ - start += nr << PAGE_SHIFT; - pages += nr; - - ret = get_user_pages_unlocked(start, - (end - start) >> PAGE_SHIFT, pages, - gup_flags); - - /* Have to be a bit careful with return values */ - if (nr > 0) { - if (ret < 0) - ret = nr; - else - ret += nr; - } - - return ret; - } -} diff --git a/arch/um/Makefile b/arch/um/Makefile index 273130cf91d1..d2daa206872d 100644 --- a/arch/um/Makefile +++ b/arch/um/Makefile @@ -73,7 +73,7 @@ KBUILD_AFLAGS += $(ARCH_INCLUDE) USER_CFLAGS = $(patsubst $(KERNEL_DEFINES),,$(patsubst -I%,,$(KBUILD_CFLAGS))) \ $(ARCH_INCLUDE) $(MODE_INCLUDE) $(filter -I%,$(CFLAGS)) \ -D_FILE_OFFSET_BITS=64 -idirafter $(srctree)/include \ - -idirafter $(obj)/include -D__KERNEL__ -D__UM_HOST__ + -idirafter $(objtree)/include -D__KERNEL__ -D__UM_HOST__ #This will adjust *FLAGS accordingly to the platform. include $(ARCH_DIR)/Makefile-os-$(OS) diff --git a/arch/um/include/asm/pgalloc.h b/arch/um/include/asm/pgalloc.h index 99eb5682792a..d7b282e9c4d5 100644 --- a/arch/um/include/asm/pgalloc.h +++ b/arch/um/include/asm/pgalloc.h @@ -10,6 +10,8 @@ #include <linux/mm.h> +#include <asm-generic/pgalloc.h> /* for pte_{alloc,free}_one */ + #define pmd_populate_kernel(mm, pmd, pte) \ set_pmd(pmd, __pmd(_PAGE_TABLE + (unsigned long) __pa(pte))) @@ -25,20 +27,6 @@ extern pgd_t *pgd_alloc(struct mm_struct *); extern void pgd_free(struct mm_struct *mm, pgd_t *pgd); -extern pte_t *pte_alloc_one_kernel(struct mm_struct *); -extern pgtable_t pte_alloc_one(struct mm_struct *); - -static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) -{ - free_page((unsigned long) pte); -} - -static inline void pte_free(struct mm_struct *mm, pgtable_t pte) -{ - pgtable_page_dtor(pte); - __free_page(pte); -} - #define __pte_free_tlb(tlb,pte, address) \ do { \ pgtable_page_dtor(pte); \ diff --git a/arch/um/kernel/mem.c b/arch/um/kernel/mem.c index a9c9a94c096f..de58e976b9bc 100644 --- a/arch/um/kernel/mem.c +++ b/arch/um/kernel/mem.c @@ -208,28 +208,6 @@ void pgd_free(struct mm_struct *mm, pgd_t *pgd) free_page((unsigned long) pgd); } -pte_t *pte_alloc_one_kernel(struct mm_struct *mm) -{ - pte_t *pte; - - pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_ZERO); - return pte; -} - -pgtable_t pte_alloc_one(struct mm_struct *mm) -{ - struct page *pte; - - pte = alloc_page(GFP_KERNEL|__GFP_ZERO); - if (!pte) - return NULL; - if (!pgtable_page_ctor(pte)) { - __free_page(pte); - return NULL; - } - return pte; -} - #ifdef CONFIG_3_LEVEL_PGTABLES pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address) { diff --git a/arch/unicore32/Makefile b/arch/unicore32/Makefile index 98a5ca43ae87..390819947c37 100644 --- a/arch/unicore32/Makefile +++ b/arch/unicore32/Makefile @@ -41,8 +41,7 @@ libs-y += arch/unicore32/lib/ boot := arch/unicore32/boot -# Default defconfig and target when executing plain make -KBUILD_DEFCONFIG := $(ARCH)_defconfig +# Default target when executing plain make KBUILD_IMAGE := $(boot)/zImage all: zImage diff --git a/arch/unicore32/configs/unicore32_defconfig b/arch/unicore32/configs/defconfig index 360cc9abcdb0..360cc9abcdb0 100644 --- a/arch/unicore32/configs/unicore32_defconfig +++ b/arch/unicore32/configs/defconfig diff --git a/arch/unicore32/include/asm/pgalloc.h b/arch/unicore32/include/asm/pgalloc.h index ec64834b1c6a..3f0903bd98e9 100644 --- a/arch/unicore32/include/asm/pgalloc.h +++ b/arch/unicore32/include/asm/pgalloc.h @@ -14,6 +14,10 @@ #include <asm/cacheflush.h> #include <asm/tlbflush.h> +#define __HAVE_ARCH_PTE_ALLOC_ONE_KERNEL +#define __HAVE_ARCH_PTE_ALLOC_ONE +#include <asm-generic/pgalloc.h> + #define check_pgt_cache() do { } while (0) #define _PAGE_USER_TABLE (PMD_TYPE_TABLE | PMD_PRESENT) @@ -25,17 +29,14 @@ extern void free_pgd_slow(struct mm_struct *mm, pgd_t *pgd); #define pgd_alloc(mm) get_pgd_slow(mm) #define pgd_free(mm, pgd) free_pgd_slow(mm, pgd) -#define PGALLOC_GFP (GFP_KERNEL | __GFP_ZERO) - /* * Allocate one PTE table. */ static inline pte_t * pte_alloc_one_kernel(struct mm_struct *mm) { - pte_t *pte; + pte_t *pte = __pte_alloc_one_kernel(mm); - pte = (pte_t *)__get_free_page(PGALLOC_GFP); if (pte) clean_dcache_area(pte, PTRS_PER_PTE * sizeof(pte_t)); @@ -47,35 +48,14 @@ pte_alloc_one(struct mm_struct *mm) { struct page *pte; - pte = alloc_pages(PGALLOC_GFP, 0); + pte = __pte_alloc_one(mm, GFP_PGTABLE_USER); if (!pte) return NULL; - if (!PageHighMem(pte)) { - void *page = page_address(pte); - clean_dcache_area(page, PTRS_PER_PTE * sizeof(pte_t)); - } - if (!pgtable_page_ctor(pte)) { - __free_page(pte); - } - + if (!PageHighMem(pte)) + clean_pte_table(page_address(pte)); return pte; } -/* - * Free one PTE table. - */ -static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) -{ - if (pte) - free_page((unsigned long)pte); -} - -static inline void pte_free(struct mm_struct *mm, pgtable_t pte) -{ - pgtable_page_dtor(pte); - __free_page(pte); -} - static inline void __pmd_populate(pmd_t *pmdp, unsigned long pmdval) { set_pmd(pmdp, __pmd(pmdval)); diff --git a/arch/unicore32/include/mach/regs-gpio.h b/arch/unicore32/include/mach/regs-gpio.h index 806350e1ccb6..5fc701ee33e3 100644 --- a/arch/unicore32/include/mach/regs-gpio.h +++ b/arch/unicore32/include/mach/regs-gpio.h @@ -32,7 +32,7 @@ */ #define GPIO_GEDR (PKUNITY_GPIO_BASE + 0x0018) /* - * Sepcial Voltage Detect Reg GPIO_GPIR. + * Special Voltage Detect Reg GPIO_GPIR. */ #define GPIO_GPIR (PKUNITY_GPIO_BASE + 0x0020) diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index dce10b18f4bc..9df2d1cb7a9e 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -123,6 +123,7 @@ config X86 select GENERIC_STRNLEN_USER select GENERIC_TIME_VSYSCALL select GENERIC_GETTIMEOFDAY + select GUP_GET_PTE_LOW_HIGH if X86_PAE select HARDLOCKUP_CHECK_TIMESTAMP if X86_64 select HAVE_ACPI_APEI if ACPI select HAVE_ACPI_APEI_NMI if ACPI @@ -158,6 +159,7 @@ config X86 select HAVE_EFFICIENT_UNALIGNED_ACCESS select HAVE_EISA select HAVE_EXIT_THREAD + select HAVE_FAST_GUP select HAVE_FENTRY if X86_64 || DYNAMIC_FTRACE select HAVE_FTRACE_MCOUNT_RECORD select HAVE_FUNCTION_GRAPH_TRACER @@ -2906,9 +2908,6 @@ config HAVE_ATOMIC_IOMAP config X86_DEV_DMA_OPS bool -config HAVE_GENERIC_GUP - def_bool y - source "drivers/firmware/Kconfig" source "arch/x86/kvm/Kconfig" diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c index 629d1ee05599..1cee10091b9f 100644 --- a/arch/x86/ia32/ia32_signal.c +++ b/arch/x86/ia32/ia32_signal.c @@ -358,7 +358,7 @@ int ia32_setup_rt_frame(int sig, struct ksignal *ksig, put_user_ex(ptr_to_compat(&frame->uc), &frame->puc); /* Create the ucontext. */ - if (boot_cpu_has(X86_FEATURE_XSAVE)) + if (static_cpu_has(X86_FEATURE_XSAVE)) put_user_ex(UC_FP_XSTATE, &frame->uc.uc_flags); else put_user_ex(0, &frame->uc.uc_flags); diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h index 8e790ec219a5..ba15d53c1ca7 100644 --- a/arch/x86/include/asm/bitops.h +++ b/arch/x86/include/asm/bitops.h @@ -49,23 +49,8 @@ #define CONST_MASK_ADDR(nr, addr) WBYTE_ADDR((void *)(addr) + ((nr)>>3)) #define CONST_MASK(nr) (1 << ((nr) & 7)) -/** - * set_bit - Atomically set a bit in memory - * @nr: the bit to set - * @addr: the address to start counting from - * - * This function is atomic and may not be reordered. See __set_bit() - * if you do not require the atomic guarantees. - * - * Note: there are no guarantees that this function will not be reordered - * on non x86 architectures, so if you are writing portable code, - * make sure not to rely on its reordering guarantees. - * - * Note that @nr may be almost arbitrarily large; this function is not - * restricted to acting on a single-word quantity. - */ static __always_inline void -set_bit(long nr, volatile unsigned long *addr) +arch_set_bit(long nr, volatile unsigned long *addr) { if (IS_IMMEDIATE(nr)) { asm volatile(LOCK_PREFIX "orb %1,%0" @@ -78,32 +63,14 @@ set_bit(long nr, volatile unsigned long *addr) } } -/** - * __set_bit - Set a bit in memory - * @nr: the bit to set - * @addr: the address to start counting from - * - * Unlike set_bit(), this function is non-atomic and may be reordered. - * If it's called on the same region of memory simultaneously, the effect - * may be that only one operation succeeds. - */ -static __always_inline void __set_bit(long nr, volatile unsigned long *addr) +static __always_inline void +arch___set_bit(long nr, volatile unsigned long *addr) { asm volatile(__ASM_SIZE(bts) " %1,%0" : : ADDR, "Ir" (nr) : "memory"); } -/** - * clear_bit - Clears a bit in memory - * @nr: Bit to clear - * @addr: Address to start counting from - * - * clear_bit() is atomic and may not be reordered. However, it does - * not contain a memory barrier, so if it is used for locking purposes, - * you should call smp_mb__before_atomic() and/or smp_mb__after_atomic() - * in order to ensure changes are visible on other processors. - */ static __always_inline void -clear_bit(long nr, volatile unsigned long *addr) +arch_clear_bit(long nr, volatile unsigned long *addr) { if (IS_IMMEDIATE(nr)) { asm volatile(LOCK_PREFIX "andb %1,%0" @@ -115,26 +82,21 @@ clear_bit(long nr, volatile unsigned long *addr) } } -/* - * clear_bit_unlock - Clears a bit in memory - * @nr: Bit to clear - * @addr: Address to start counting from - * - * clear_bit() is atomic and implies release semantics before the memory - * operation. It can be used for an unlock. - */ -static __always_inline void clear_bit_unlock(long nr, volatile unsigned long *addr) +static __always_inline void +arch_clear_bit_unlock(long nr, volatile unsigned long *addr) { barrier(); - clear_bit(nr, addr); + arch_clear_bit(nr, addr); } -static __always_inline void __clear_bit(long nr, volatile unsigned long *addr) +static __always_inline void +arch___clear_bit(long nr, volatile unsigned long *addr) { asm volatile(__ASM_SIZE(btr) " %1,%0" : : ADDR, "Ir" (nr) : "memory"); } -static __always_inline bool clear_bit_unlock_is_negative_byte(long nr, volatile unsigned long *addr) +static __always_inline bool +arch_clear_bit_unlock_is_negative_byte(long nr, volatile unsigned long *addr) { bool negative; asm volatile(LOCK_PREFIX "andb %2,%1" @@ -143,48 +105,23 @@ static __always_inline bool clear_bit_unlock_is_negative_byte(long nr, volatile : "ir" ((char) ~(1 << nr)) : "memory"); return negative; } +#define arch_clear_bit_unlock_is_negative_byte \ + arch_clear_bit_unlock_is_negative_byte -// Let everybody know we have it -#define clear_bit_unlock_is_negative_byte clear_bit_unlock_is_negative_byte - -/* - * __clear_bit_unlock - Clears a bit in memory - * @nr: Bit to clear - * @addr: Address to start counting from - * - * __clear_bit() is non-atomic and implies release semantics before the memory - * operation. It can be used for an unlock if no other CPUs can concurrently - * modify other bits in the word. - */ -static __always_inline void __clear_bit_unlock(long nr, volatile unsigned long *addr) +static __always_inline void +arch___clear_bit_unlock(long nr, volatile unsigned long *addr) { - __clear_bit(nr, addr); + arch___clear_bit(nr, addr); } -/** - * __change_bit - Toggle a bit in memory - * @nr: the bit to change - * @addr: the address to start counting from - * - * Unlike change_bit(), this function is non-atomic and may be reordered. - * If it's called on the same region of memory simultaneously, the effect - * may be that only one operation succeeds. - */ -static __always_inline void __change_bit(long nr, volatile unsigned long *addr) +static __always_inline void +arch___change_bit(long nr, volatile unsigned long *addr) { asm volatile(__ASM_SIZE(btc) " %1,%0" : : ADDR, "Ir" (nr) : "memory"); } -/** - * change_bit - Toggle a bit in memory - * @nr: Bit to change - * @addr: Address to start counting from - * - * change_bit() is atomic and may not be reordered. - * Note that @nr may be almost arbitrarily large; this function is not - * restricted to acting on a single-word quantity. - */ -static __always_inline void change_bit(long nr, volatile unsigned long *addr) +static __always_inline void +arch_change_bit(long nr, volatile unsigned long *addr) { if (IS_IMMEDIATE(nr)) { asm volatile(LOCK_PREFIX "xorb %1,%0" @@ -196,42 +133,20 @@ static __always_inline void change_bit(long nr, volatile unsigned long *addr) } } -/** - * test_and_set_bit - Set a bit and return its old value - * @nr: Bit to set - * @addr: Address to count from - * - * This operation is atomic and cannot be reordered. - * It also implies a memory barrier. - */ -static __always_inline bool test_and_set_bit(long nr, volatile unsigned long *addr) +static __always_inline bool +arch_test_and_set_bit(long nr, volatile unsigned long *addr) { return GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(bts), *addr, c, "Ir", nr); } -/** - * test_and_set_bit_lock - Set a bit and return its old value for lock - * @nr: Bit to set - * @addr: Address to count from - * - * This is the same as test_and_set_bit on x86. - */ static __always_inline bool -test_and_set_bit_lock(long nr, volatile unsigned long *addr) +arch_test_and_set_bit_lock(long nr, volatile unsigned long *addr) { - return test_and_set_bit(nr, addr); + return arch_test_and_set_bit(nr, addr); } -/** - * __test_and_set_bit - Set a bit and return its old value - * @nr: Bit to set - * @addr: Address to count from - * - * This operation is non-atomic and can be reordered. - * If two examples of this operation race, one can appear to succeed - * but actually fail. You must protect multiple accesses with a lock. - */ -static __always_inline bool __test_and_set_bit(long nr, volatile unsigned long *addr) +static __always_inline bool +arch___test_and_set_bit(long nr, volatile unsigned long *addr) { bool oldbit; @@ -242,28 +157,13 @@ static __always_inline bool __test_and_set_bit(long nr, volatile unsigned long * return oldbit; } -/** - * test_and_clear_bit - Clear a bit and return its old value - * @nr: Bit to clear - * @addr: Address to count from - * - * This operation is atomic and cannot be reordered. - * It also implies a memory barrier. - */ -static __always_inline bool test_and_clear_bit(long nr, volatile unsigned long *addr) +static __always_inline bool +arch_test_and_clear_bit(long nr, volatile unsigned long *addr) { return GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(btr), *addr, c, "Ir", nr); } -/** - * __test_and_clear_bit - Clear a bit and return its old value - * @nr: Bit to clear - * @addr: Address to count from - * - * This operation is non-atomic and can be reordered. - * If two examples of this operation race, one can appear to succeed - * but actually fail. You must protect multiple accesses with a lock. - * +/* * Note: the operation is performed atomically with respect to * the local CPU, but not other CPUs. Portable code should not * rely on this behaviour. @@ -271,7 +171,8 @@ static __always_inline bool test_and_clear_bit(long nr, volatile unsigned long * * accessed from a hypervisor on the same CPU if running in a VM: don't change * this without also updating arch/x86/kernel/kvm.c */ -static __always_inline bool __test_and_clear_bit(long nr, volatile unsigned long *addr) +static __always_inline bool +arch___test_and_clear_bit(long nr, volatile unsigned long *addr) { bool oldbit; @@ -282,8 +183,8 @@ static __always_inline bool __test_and_clear_bit(long nr, volatile unsigned long return oldbit; } -/* WARNING: non atomic and it can be reordered! */ -static __always_inline bool __test_and_change_bit(long nr, volatile unsigned long *addr) +static __always_inline bool +arch___test_and_change_bit(long nr, volatile unsigned long *addr) { bool oldbit; @@ -295,15 +196,8 @@ static __always_inline bool __test_and_change_bit(long nr, volatile unsigned lon return oldbit; } -/** - * test_and_change_bit - Change a bit and return its old value - * @nr: Bit to change - * @addr: Address to count from - * - * This operation is atomic and cannot be reordered. - * It also implies a memory barrier. - */ -static __always_inline bool test_and_change_bit(long nr, volatile unsigned long *addr) +static __always_inline bool +arch_test_and_change_bit(long nr, volatile unsigned long *addr) { return GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(btc), *addr, c, "Ir", nr); } @@ -326,16 +220,7 @@ static __always_inline bool variable_test_bit(long nr, volatile const unsigned l return oldbit; } -#if 0 /* Fool kernel-doc since it doesn't do macros yet */ -/** - * test_bit - Determine whether a bit is set - * @nr: bit number to test - * @addr: Address to start counting from - */ -static bool test_bit(int nr, const volatile unsigned long *addr); -#endif - -#define test_bit(nr, addr) \ +#define arch_test_bit(nr, addr) \ (__builtin_constant_p((nr)) \ ? constant_test_bit((nr), (addr)) \ : variable_test_bit((nr), (addr))) @@ -504,6 +389,8 @@ static __always_inline int fls64(__u64 x) #include <asm-generic/bitops/const_hweight.h> +#include <asm-generic/bitops-instrumented.h> + #include <asm-generic/bitops/le.h> #include <asm-generic/bitops/ext2-atomic-setbit.h> diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 26d1eb83f72a..0cc5b611a113 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -686,6 +686,7 @@ struct kvm_vcpu_arch { u32 virtual_tsc_mult; u32 virtual_tsc_khz; s64 ia32_tsc_adjust_msr; + u64 msr_ia32_power_ctl; u64 tsc_scaling_ratio; atomic_t nmi_queued; /* unprocessed asynchronous NMIs */ @@ -752,6 +753,8 @@ struct kvm_vcpu_arch { struct gfn_to_hva_cache data; } pv_eoi; + u64 msr_kvm_poll_control; + /* * Indicate whether the access faults on its page table in guest * which is set when fix page fault and used to detect unhandeable @@ -879,6 +882,7 @@ struct kvm_arch { bool mwait_in_guest; bool hlt_in_guest; bool pause_in_guest; + bool cstate_in_guest; unsigned long irq_sources_bitmap; s64 kvmclock_offset; @@ -926,6 +930,8 @@ struct kvm_arch { bool guest_can_read_msr_platform_info; bool exception_payload_enabled; + + struct kvm_pmu_event_filter *pmu_event_filter; }; struct kvm_vm_stat { @@ -996,7 +1002,7 @@ struct kvm_x86_ops { int (*disabled_by_bios)(void); /* __init */ int (*hardware_enable)(void); void (*hardware_disable)(void); - void (*check_processor_compatibility)(void *rtn); + int (*check_processor_compatibility)(void);/* __init */ int (*hardware_setup)(void); /* __init */ void (*hardware_unsetup)(void); /* __exit */ bool (*cpu_has_accelerated_tpr)(void); @@ -1110,7 +1116,7 @@ struct kvm_x86_ops { int (*check_intercept)(struct kvm_vcpu *vcpu, struct x86_instruction_info *info, enum x86_intercept_stage stage); - void (*handle_external_intr)(struct kvm_vcpu *vcpu); + void (*handle_exit_irqoff)(struct kvm_vcpu *vcpu); bool (*mpx_supported)(void); bool (*xsaves_supported)(void); bool (*umip_emulated)(void); @@ -1529,7 +1535,6 @@ int kvm_pv_send_ipi(struct kvm *kvm, unsigned long ipi_bitmap_low, unsigned long ipi_bitmap_high, u32 min, unsigned long icr, int op_64_bit); -u64 kvm_get_arch_capabilities(void); void kvm_define_shared_msr(unsigned index, u32 msr); int kvm_set_shared_msr(unsigned index, u64 val, u64 mask); diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index f4fa8a9d5d0b..2ef31cc8c529 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -3,84 +3,15 @@ #define _ASM_X86_MSHYPER_H #include <linux/types.h> -#include <linux/atomic.h> #include <linux/nmi.h> #include <asm/io.h> #include <asm/hyperv-tlfs.h> #include <asm/nospec-branch.h> -#define VP_INVAL U32_MAX - -struct ms_hyperv_info { - u32 features; - u32 misc_features; - u32 hints; - u32 nested_features; - u32 max_vp_index; - u32 max_lp_index; -}; - -extern struct ms_hyperv_info ms_hyperv; - - typedef int (*hyperv_fill_flush_list_func)( struct hv_guest_mapping_flush_list *flush, void *data); -/* - * Generate the guest ID. - */ - -static inline __u64 generate_guest_id(__u64 d_info1, __u64 kernel_version, - __u64 d_info2) -{ - __u64 guest_id = 0; - - guest_id = (((__u64)HV_LINUX_VENDOR_ID) << 48); - guest_id |= (d_info1 << 48); - guest_id |= (kernel_version << 16); - guest_id |= d_info2; - - return guest_id; -} - - -/* Free the message slot and signal end-of-message if required */ -static inline void vmbus_signal_eom(struct hv_message *msg, u32 old_msg_type) -{ - /* - * On crash we're reading some other CPU's message page and we need - * to be careful: this other CPU may already had cleared the header - * and the host may already had delivered some other message there. - * In case we blindly write msg->header.message_type we're going - * to lose it. We can still lose a message of the same type but - * we count on the fact that there can only be one - * CHANNELMSG_UNLOAD_RESPONSE and we don't care about other messages - * on crash. - */ - if (cmpxchg(&msg->header.message_type, old_msg_type, - HVMSG_NONE) != old_msg_type) - return; - - /* - * Make sure the write to MessageType (ie set to - * HVMSG_NONE) happens before we read the - * MessagePending and EOMing. Otherwise, the EOMing - * will not deliver any more messages since there is - * no empty slot - */ - mb(); - - if (msg->header.message_flags.msg_pending) { - /* - * This will cause message queue rescan to - * possibly deliver another msg from the - * hypervisor - */ - wrmsrl(HV_X64_MSR_EOM, 0); - } -} - #define hv_init_timer(timer, tick) \ wrmsrl(HV_X64_MSR_STIMER0_COUNT + (2*timer), tick) #define hv_init_timer_config(timer, val) \ @@ -97,6 +28,8 @@ static inline void vmbus_signal_eom(struct hv_message *msg, u32 old_msg_type) #define hv_get_vp_index(index) rdmsrl(HV_X64_MSR_VP_INDEX, index) +#define hv_signal_eom() wrmsrl(HV_X64_MSR_EOM, 0) + #define hv_get_synint_state(int_num, val) \ rdmsrl(HV_X64_MSR_SINT0 + int_num, val) #define hv_set_synint_state(int_num, val) \ @@ -122,13 +55,6 @@ void hyperv_reenlightenment_vector(void); #define trace_hyperv_callback_vector hyperv_callback_vector #endif void hyperv_vector_handler(struct pt_regs *regs); -void hv_setup_vmbus_irq(void (*handler)(void)); -void hv_remove_vmbus_irq(void); - -void hv_setup_kexec_handler(void (*handler)(void)); -void hv_remove_kexec_handler(void); -void hv_setup_crash_handler(void (*handler)(struct pt_regs *regs)); -void hv_remove_crash_handler(void); /* * Routines for stimer0 Direct Mode handling. @@ -136,8 +62,6 @@ void hv_remove_crash_handler(void); */ void hv_stimer0_vector_handler(struct pt_regs *regs); void hv_stimer0_callback_vector(void); -int hv_setup_stimer0_irq(int *irq, int *vector, void (*handler)(void)); -void hv_remove_stimer0_irq(int irq); static inline void hv_enable_stimer0_percpu_irq(int irq) {} static inline void hv_disable_stimer0_percpu_irq(int irq) {} @@ -282,14 +206,6 @@ static inline u64 hv_do_rep_hypercall(u16 code, u16 rep_count, u16 varhead_size, return status; } -/* - * Hypervisor's notion of virtual processor ID is different from - * Linux' notion of CPU ID. This information can only be retrieved - * in the context of the calling CPU. Setup a map for easy access - * to this information. - */ -extern u32 *hv_vp_index; -extern u32 hv_max_vp_index; extern struct hv_vp_assist_page **hv_vp_assist_page; static inline struct hv_vp_assist_page *hv_get_vp_assist_page(unsigned int cpu) @@ -300,63 +216,8 @@ static inline struct hv_vp_assist_page *hv_get_vp_assist_page(unsigned int cpu) return hv_vp_assist_page[cpu]; } -/** - * hv_cpu_number_to_vp_number() - Map CPU to VP. - * @cpu_number: CPU number in Linux terms - * - * This function returns the mapping between the Linux processor - * number and the hypervisor's virtual processor number, useful - * in making hypercalls and such that talk about specific - * processors. - * - * Return: Virtual processor number in Hyper-V terms - */ -static inline int hv_cpu_number_to_vp_number(int cpu_number) -{ - return hv_vp_index[cpu_number]; -} - -static inline int cpumask_to_vpset(struct hv_vpset *vpset, - const struct cpumask *cpus) -{ - int cpu, vcpu, vcpu_bank, vcpu_offset, nr_bank = 1; - - /* valid_bank_mask can represent up to 64 banks */ - if (hv_max_vp_index / 64 >= 64) - return 0; - - /* - * Clear all banks up to the maximum possible bank as hv_tlb_flush_ex - * structs are not cleared between calls, we risk flushing unneeded - * vCPUs otherwise. - */ - for (vcpu_bank = 0; vcpu_bank <= hv_max_vp_index / 64; vcpu_bank++) - vpset->bank_contents[vcpu_bank] = 0; - - /* - * Some banks may end up being empty but this is acceptable. - */ - for_each_cpu(cpu, cpus) { - vcpu = hv_cpu_number_to_vp_number(cpu); - if (vcpu == VP_INVAL) - return -1; - vcpu_bank = vcpu / 64; - vcpu_offset = vcpu % 64; - __set_bit(vcpu_offset, (unsigned long *) - &vpset->bank_contents[vcpu_bank]); - if (vcpu_bank >= nr_bank) - nr_bank = vcpu_bank + 1; - } - vpset->valid_bank_mask = GENMASK_ULL(nr_bank - 1, 0); - return nr_bank; -} - void __init hyperv_init(void); void hyperv_setup_mmu_ops(void); -void hyperv_report_panic(struct pt_regs *regs, long err); -void hyperv_report_panic_msg(phys_addr_t pa, size_t size); -bool hv_is_hyperv_initialized(void); -void hyperv_cleanup(void); void hyperv_reenlightenment_intr(struct pt_regs *regs); void set_hv_tscchange_cb(void (*cb)(void)); @@ -379,8 +240,6 @@ static inline void hv_apic_init(void) {} #else /* CONFIG_HYPERV */ static inline void hyperv_init(void) {} -static inline bool hv_is_hyperv_initialized(void) { return false; } -static inline void hyperv_cleanup(void) {} static inline void hyperv_setup_mmu_ops(void) {} static inline void set_hv_tscchange_cb(void (*cb)(void)) {} static inline void clear_hv_tscchange_cb(void) {} @@ -397,4 +256,7 @@ static inline int hyperv_flush_guest_mapping_range(u64 as, } #endif /* CONFIG_HYPERV */ + +#include <asm-generic/mshyperv.h> + #endif diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h index a281e61ec60c..29aa7859bdee 100644 --- a/arch/x86/include/asm/pgalloc.h +++ b/arch/x86/include/asm/pgalloc.h @@ -6,6 +6,9 @@ #include <linux/mm.h> /* for struct page */ #include <linux/pagemap.h> +#define __HAVE_ARCH_PTE_ALLOC_ONE +#include <asm-generic/pgalloc.h> /* for pte_{alloc,free}_one */ + static inline int __paravirt_pgd_alloc(struct mm_struct *mm) { return 0; } #ifdef CONFIG_PARAVIRT_XXL @@ -47,24 +50,8 @@ extern gfp_t __userpte_alloc_gfp; extern pgd_t *pgd_alloc(struct mm_struct *); extern void pgd_free(struct mm_struct *mm, pgd_t *pgd); -extern pte_t *pte_alloc_one_kernel(struct mm_struct *); extern pgtable_t pte_alloc_one(struct mm_struct *); -/* Should really implement gc for free page table pages. This could be - done with a reference count in struct page. */ - -static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) -{ - BUG_ON((unsigned long)pte & (PAGE_SIZE-1)); - free_page((unsigned long)pte); -} - -static inline void pte_free(struct mm_struct *mm, struct page *pte) -{ - pgtable_page_dtor(pte); - __free_page(pte); -} - extern void ___pte_free_tlb(struct mmu_gather *tlb, struct page *pte); static inline void __pte_free_tlb(struct mmu_gather *tlb, struct page *pte, diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h index f8b1ad2c3828..e3633795fb22 100644 --- a/arch/x86/include/asm/pgtable-3level.h +++ b/arch/x86/include/asm/pgtable-3level.h @@ -285,53 +285,6 @@ static inline pud_t native_pudp_get_and_clear(pud_t *pudp) #define __pte_to_swp_entry(pte) (__swp_entry(__pteval_swp_type(pte), \ __pteval_swp_offset(pte))) -#define gup_get_pte gup_get_pte -/* - * WARNING: only to be used in the get_user_pages_fast() implementation. - * - * With get_user_pages_fast(), we walk down the pagetables without taking - * any locks. For this we would like to load the pointers atomically, - * but that is not possible (without expensive cmpxchg8b) on PAE. What - * we do have is the guarantee that a PTE will only either go from not - * present to present, or present to not present or both -- it will not - * switch to a completely different present page without a TLB flush in - * between; something that we are blocking by holding interrupts off. - * - * Setting ptes from not present to present goes: - * - * ptep->pte_high = h; - * smp_wmb(); - * ptep->pte_low = l; - * - * And present to not present goes: - * - * ptep->pte_low = 0; - * smp_wmb(); - * ptep->pte_high = 0; - * - * We must ensure here that the load of pte_low sees 'l' iff pte_high - * sees 'h'. We load pte_high *after* loading pte_low, which ensures we - * don't see an older value of pte_high. *Then* we recheck pte_low, - * which ensures that we haven't picked up a changed pte high. We might - * have gotten rubbish values from pte_low and pte_high, but we are - * guaranteed that pte_low will not have the present bit set *unless* - * it is 'l'. Because get_user_pages_fast() only operates on present ptes - * we're safe. - */ -static inline pte_t gup_get_pte(pte_t *ptep) -{ - pte_t pte; - - do { - pte.pte_low = ptep->pte_low; - smp_rmb(); - pte.pte_high = ptep->pte_high; - smp_rmb(); - } while (unlikely(pte.pte_low != ptep->pte_low)); - - return pte; -} - #include <asm/pgtable-invert.h> #endif /* _ASM_X86_PGTABLE_3LEVEL_H */ diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h index 0bb566315621..4990d26dfc73 100644 --- a/arch/x86/include/asm/pgtable_64.h +++ b/arch/x86/include/asm/pgtable_64.h @@ -259,14 +259,8 @@ extern void init_extra_mapping_uc(unsigned long phys, unsigned long size); extern void init_extra_mapping_wb(unsigned long phys, unsigned long size); #define gup_fast_permitted gup_fast_permitted -static inline bool gup_fast_permitted(unsigned long start, int nr_pages) +static inline bool gup_fast_permitted(unsigned long start, unsigned long end) { - unsigned long len, end; - - len = (unsigned long)nr_pages << PAGE_SHIFT; - end = start + len; - if (end < start) - return false; if (end >> __VIRTUAL_MASK_SHIFT) return false; return true; diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h index 78cf265c5b58..332eb3525867 100644 --- a/arch/x86/include/asm/ptrace.h +++ b/arch/x86/include/asm/ptrace.h @@ -98,7 +98,6 @@ struct cpuinfo_x86; struct task_struct; extern unsigned long profile_pc(struct pt_regs *regs); -#define profile_pc profile_pc extern unsigned long convert_ip_to_linear(struct task_struct *child, struct pt_regs *regs); @@ -170,11 +169,32 @@ static inline unsigned long kernel_stack_pointer(struct pt_regs *regs) return regs->sp; } -#define GET_IP(regs) ((regs)->ip) -#define GET_FP(regs) ((regs)->bp) -#define GET_USP(regs) ((regs)->sp) +static inline unsigned long instruction_pointer(struct pt_regs *regs) +{ + return regs->ip; +} + +static inline void instruction_pointer_set(struct pt_regs *regs, + unsigned long val) +{ + regs->ip = val; +} + +static inline unsigned long frame_pointer(struct pt_regs *regs) +{ + return regs->bp; +} -#include <asm-generic/ptrace.h> +static inline unsigned long user_stack_pointer(struct pt_regs *regs) +{ + return regs->sp; +} + +static inline void user_stack_pointer_set(struct pt_regs *regs, + unsigned long val) +{ + regs->sp = val; +} /* Query offset/name of register from its name/offset */ extern int regs_query_register_offset(const char *name); diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index d6ab5b4d15e5..e901b0ab116f 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -378,10 +378,11 @@ struct kvm_sync_regs { struct kvm_vcpu_events events; }; -#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_X86_QUIRK_OUT_7E_INC_RIP (1 << 3) +#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_X86_QUIRK_OUT_7E_INC_RIP (1 << 3) +#define KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT (1 << 4) #define KVM_STATE_NESTED_FORMAT_VMX 0 #define KVM_STATE_NESTED_FORMAT_SVM 1 /* unused */ @@ -432,4 +433,14 @@ struct kvm_nested_state { } data; }; +/* for KVM_CAP_PMU_EVENT_FILTER */ +struct kvm_pmu_event_filter { + __u32 action; + __u32 nevents; + __u64 events[0]; +}; + +#define KVM_PMU_EVENT_ALLOW 0 +#define KVM_PMU_EVENT_DENY 1 + #endif /* _ASM_X86_KVM_H */ diff --git a/arch/x86/include/uapi/asm/kvm_para.h b/arch/x86/include/uapi/asm/kvm_para.h index 19980ec1a316..2a8e0b6b9805 100644 --- a/arch/x86/include/uapi/asm/kvm_para.h +++ b/arch/x86/include/uapi/asm/kvm_para.h @@ -29,6 +29,8 @@ #define KVM_FEATURE_PV_TLB_FLUSH 9 #define KVM_FEATURE_ASYNC_PF_VMEXIT 10 #define KVM_FEATURE_PV_SEND_IPI 11 +#define KVM_FEATURE_POLL_CONTROL 12 +#define KVM_FEATURE_PV_SCHED_YIELD 13 #define KVM_HINTS_REALTIME 0 @@ -47,6 +49,7 @@ #define MSR_KVM_ASYNC_PF_EN 0x4b564d02 #define MSR_KVM_STEAL_TIME 0x4b564d03 #define MSR_KVM_PV_EOI_EN 0x4b564d04 +#define MSR_KVM_POLL_CONTROL 0x4b564d05 struct kvm_steal_time { __u64 steal; diff --git a/arch/x86/include/uapi/asm/vmx.h b/arch/x86/include/uapi/asm/vmx.h index d213ec5c3766..f0b0c90dd398 100644 --- a/arch/x86/include/uapi/asm/vmx.h +++ b/arch/x86/include/uapi/asm/vmx.h @@ -146,7 +146,6 @@ #define VMX_ABORT_SAVE_GUEST_MSR_FAIL 1 #define VMX_ABORT_LOAD_HOST_PDPTE_FAIL 2 -#define VMX_ABORT_VMCS_CORRUPTED 3 #define VMX_ABORT_LOAD_HOST_MSR_FAIL 4 #endif /* _UAPIVMX_H */ diff --git a/arch/x86/kernel/kdebugfs.c b/arch/x86/kernel/kdebugfs.c index 7670ac2bda3a..edaa30b20841 100644 --- a/arch/x86/kernel/kdebugfs.c +++ b/arch/x86/kernel/kdebugfs.c @@ -67,33 +67,18 @@ static const struct file_operations fops_setup_data = { .llseek = default_llseek, }; -static int __init +static void __init create_setup_data_node(struct dentry *parent, int no, struct setup_data_node *node) { - struct dentry *d, *type, *data; + struct dentry *d; char buf[16]; sprintf(buf, "%d", no); d = debugfs_create_dir(buf, parent); - if (!d) - return -ENOMEM; - - type = debugfs_create_x32("type", S_IRUGO, d, &node->type); - if (!type) - goto err_dir; - - data = debugfs_create_file("data", S_IRUGO, d, node, &fops_setup_data); - if (!data) - goto err_type; - return 0; - -err_type: - debugfs_remove(type); -err_dir: - debugfs_remove(d); - return -ENOMEM; + debugfs_create_x32("type", S_IRUGO, d, &node->type); + debugfs_create_file("data", S_IRUGO, d, node, &fops_setup_data); } static int __init create_setup_data_nodes(struct dentry *parent) @@ -106,8 +91,6 @@ static int __init create_setup_data_nodes(struct dentry *parent) int no = 0; d = debugfs_create_dir("setup_data", parent); - if (!d) - return -ENOMEM; pa_data = boot_params.hdr.setup_data; @@ -128,19 +111,17 @@ static int __init create_setup_data_nodes(struct dentry *parent) node->paddr = pa_data; node->type = data->type; node->len = data->len; - error = create_setup_data_node(d, no, node); + create_setup_data_node(d, no, node); pa_data = data->next; memunmap(data); - if (error) - goto err_dir; no++; } return 0; err_dir: - debugfs_remove(d); + debugfs_remove_recursive(d); return error; } @@ -151,35 +132,18 @@ static struct debugfs_blob_wrapper boot_params_blob = { static int __init boot_params_kdebugfs_init(void) { - struct dentry *dbp, *version, *data; - int error = -ENOMEM; + struct dentry *dbp; + int error; dbp = debugfs_create_dir("boot_params", arch_debugfs_dir); - if (!dbp) - return -ENOMEM; - - version = debugfs_create_x16("version", S_IRUGO, dbp, - &boot_params.hdr.version); - if (!version) - goto err_dir; - data = debugfs_create_blob("data", S_IRUGO, dbp, - &boot_params_blob); - if (!data) - goto err_version; + debugfs_create_x16("version", S_IRUGO, dbp, &boot_params.hdr.version); + debugfs_create_blob("data", S_IRUGO, dbp, &boot_params_blob); error = create_setup_data_nodes(dbp); if (error) - goto err_data; + debugfs_remove_recursive(dbp); - return 0; - -err_data: - debugfs_remove(data); -err_version: - debugfs_remove(version); -err_dir: - debugfs_remove(dbp); return error; } #endif /* CONFIG_DEBUG_BOOT_PARAMS */ @@ -189,8 +153,6 @@ static int __init arch_kdebugfs_init(void) int error = 0; arch_debugfs_dir = debugfs_create_dir("x86", NULL); - if (!arch_debugfs_dir) - return -ENOMEM; #ifdef CONFIG_DEBUG_BOOT_PARAMS error = boot_params_kdebugfs_init(); diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 5169b8cc35bb..82caf01b63dd 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -527,6 +527,21 @@ static void kvm_setup_pv_ipi(void) pr_info("KVM setup pv IPIs\n"); } +static void kvm_smp_send_call_func_ipi(const struct cpumask *mask) +{ + int cpu; + + native_send_call_func_ipi(mask); + + /* Make sure other vCPUs get a chance to run if they need to. */ + for_each_cpu(cpu, mask) { + if (vcpu_is_preempted(cpu)) { + kvm_hypercall1(KVM_HC_SCHED_YIELD, per_cpu(x86_cpu_to_apicid, cpu)); + break; + } + } +} + static void __init kvm_smp_prepare_cpus(unsigned int max_cpus) { native_smp_prepare_cpus(max_cpus); @@ -638,6 +653,12 @@ static void __init kvm_guest_init(void) #ifdef CONFIG_SMP smp_ops.smp_prepare_cpus = kvm_smp_prepare_cpus; smp_ops.smp_prepare_boot_cpu = kvm_smp_prepare_boot_cpu; + if (kvm_para_has_feature(KVM_FEATURE_PV_SCHED_YIELD) && + !kvm_para_has_hint(KVM_HINTS_REALTIME) && + kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) { + smp_ops.send_call_func_ipi = kvm_smp_send_call_func_ipi; + pr_info("KVM setup pv sched yield\n"); + } if (cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "x86/kvm:online", kvm_cpu_online, kvm_cpu_down_prepare) < 0) pr_err("kvm_guest: Failed to install cpu hotplug callbacks\n"); diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 7cf508f78c8c..8eb7193e158d 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -391,7 +391,7 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig, put_user_ex(&frame->uc, &frame->puc); /* Create the ucontext. */ - if (boot_cpu_has(X86_FEATURE_XSAVE)) + if (static_cpu_has(X86_FEATURE_XSAVE)) put_user_ex(UC_FP_XSTATE, &frame->uc.uc_flags); else put_user_ex(0, &frame->uc.uc_flags); diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index fc042419e670..840e12583b85 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -41,6 +41,7 @@ config KVM select PERF_EVENTS select HAVE_KVM_MSI select HAVE_KVM_CPU_RELAX_INTERCEPT + select HAVE_KVM_NO_POLL select KVM_GENERIC_DIRTYLOG_READ_PROTECT select KVM_VFIO select SRCU diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 4992e7c99588..ead681210306 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -134,6 +134,16 @@ int kvm_update_cpuid(struct kvm_vcpu *vcpu) (best->eax & (1 << KVM_FEATURE_PV_UNHALT))) best->eax &= ~(1 << KVM_FEATURE_PV_UNHALT); + if (!kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT)) { + best = kvm_find_cpuid_entry(vcpu, 0x1, 0); + if (best) { + if (vcpu->arch.ia32_misc_enable_msr & MSR_IA32_MISC_ENABLE_MWAIT) + best->ecx |= F(MWAIT); + else + best->ecx &= ~F(MWAIT); + } + } + /* Update physical-address width */ vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu); kvm_mmu_reset_context(vcpu); @@ -276,19 +286,38 @@ static void cpuid_mask(u32 *word, int wordnum) *word &= boot_cpu_data.x86_capability[wordnum]; } -static void do_cpuid_1_ent(struct kvm_cpuid_entry2 *entry, u32 function, +static void do_host_cpuid(struct kvm_cpuid_entry2 *entry, u32 function, u32 index) { entry->function = function; entry->index = index; + entry->flags = 0; + cpuid_count(entry->function, entry->index, &entry->eax, &entry->ebx, &entry->ecx, &entry->edx); - entry->flags = 0; + + switch (function) { + case 2: + entry->flags |= KVM_CPUID_FLAG_STATEFUL_FUNC; + break; + case 4: + case 7: + case 0xb: + case 0xd: + case 0x14: + case 0x8000001d: + entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; + break; + } } -static int __do_cpuid_ent_emulated(struct kvm_cpuid_entry2 *entry, - u32 func, u32 index, int *nent, int maxnent) +static int __do_cpuid_func_emulated(struct kvm_cpuid_entry2 *entry, + u32 func, int *nent, int maxnent) { + entry->function = func; + entry->index = 0; + entry->flags = 0; + switch (func) { case 0: entry->eax = 7; @@ -300,21 +329,83 @@ static int __do_cpuid_ent_emulated(struct kvm_cpuid_entry2 *entry, break; case 7: entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; - if (index == 0) - entry->ecx = F(RDPID); + entry->eax = 0; + entry->ecx = F(RDPID); ++*nent; default: break; } - entry->function = func; - entry->index = index; - return 0; } -static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, - u32 index, int *nent, int maxnent) +static inline void do_cpuid_7_mask(struct kvm_cpuid_entry2 *entry, int index) +{ + unsigned f_invpcid = kvm_x86_ops->invpcid_supported() ? F(INVPCID) : 0; + unsigned f_mpx = kvm_mpx_supported() ? F(MPX) : 0; + unsigned f_umip = kvm_x86_ops->umip_emulated() ? F(UMIP) : 0; + unsigned f_intel_pt = kvm_x86_ops->pt_supported() ? F(INTEL_PT) : 0; + unsigned f_la57; + + /* cpuid 7.0.ebx */ + const u32 kvm_cpuid_7_0_ebx_x86_features = + F(FSGSBASE) | F(BMI1) | F(HLE) | F(AVX2) | F(SMEP) | + F(BMI2) | F(ERMS) | f_invpcid | F(RTM) | f_mpx | F(RDSEED) | + F(ADX) | F(SMAP) | F(AVX512IFMA) | F(AVX512F) | F(AVX512PF) | + F(AVX512ER) | F(AVX512CD) | F(CLFLUSHOPT) | F(CLWB) | F(AVX512DQ) | + F(SHA_NI) | F(AVX512BW) | F(AVX512VL) | f_intel_pt; + + /* cpuid 7.0.ecx*/ + const u32 kvm_cpuid_7_0_ecx_x86_features = + F(AVX512VBMI) | F(LA57) | F(PKU) | 0 /*OSPKE*/ | + F(AVX512_VPOPCNTDQ) | F(UMIP) | F(AVX512_VBMI2) | F(GFNI) | + F(VAES) | F(VPCLMULQDQ) | F(AVX512_VNNI) | F(AVX512_BITALG) | + F(CLDEMOTE) | F(MOVDIRI) | F(MOVDIR64B); + + /* cpuid 7.0.edx*/ + const u32 kvm_cpuid_7_0_edx_x86_features = + F(AVX512_4VNNIW) | F(AVX512_4FMAPS) | F(SPEC_CTRL) | + F(SPEC_CTRL_SSBD) | F(ARCH_CAPABILITIES) | F(INTEL_STIBP) | + F(MD_CLEAR); + + switch (index) { + case 0: + entry->eax = 0; + entry->ebx &= kvm_cpuid_7_0_ebx_x86_features; + cpuid_mask(&entry->ebx, CPUID_7_0_EBX); + /* TSC_ADJUST is emulated */ + entry->ebx |= F(TSC_ADJUST); + + entry->ecx &= kvm_cpuid_7_0_ecx_x86_features; + f_la57 = entry->ecx & F(LA57); + cpuid_mask(&entry->ecx, CPUID_7_ECX); + /* Set LA57 based on hardware capability. */ + entry->ecx |= f_la57; + entry->ecx |= f_umip; + /* PKU is not yet implemented for shadow paging. */ + if (!tdp_enabled || !boot_cpu_has(X86_FEATURE_OSPKE)) + entry->ecx &= ~F(PKU); + + entry->edx &= kvm_cpuid_7_0_edx_x86_features; + cpuid_mask(&entry->edx, CPUID_7_EDX); + /* + * We emulate ARCH_CAPABILITIES in software even + * if the host doesn't support it. + */ + entry->edx |= F(ARCH_CAPABILITIES); + break; + default: + WARN_ON_ONCE(1); + entry->eax = 0; + entry->ebx = 0; + entry->ecx = 0; + entry->edx = 0; + break; + } +} + +static inline int __do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 function, + int *nent, int maxnent) { int r; unsigned f_nx = is_efer_nx() ? F(NX) : 0; @@ -327,12 +418,8 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, unsigned f_lm = 0; #endif unsigned f_rdtscp = kvm_x86_ops->rdtscp_supported() ? F(RDTSCP) : 0; - unsigned f_invpcid = kvm_x86_ops->invpcid_supported() ? F(INVPCID) : 0; - unsigned f_mpx = kvm_mpx_supported() ? F(MPX) : 0; unsigned f_xsaves = kvm_x86_ops->xsaves_supported() ? F(XSAVES) : 0; - unsigned f_umip = kvm_x86_ops->umip_emulated() ? F(UMIP) : 0; unsigned f_intel_pt = kvm_x86_ops->pt_supported() ? F(INTEL_PT) : 0; - unsigned f_la57 = 0; /* cpuid 1.edx */ const u32 kvm_cpuid_1_edx_x86_features = @@ -377,7 +464,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, /* cpuid 0x80000008.ebx */ const u32 kvm_cpuid_8000_0008_ebx_x86_features = F(WBNOINVD) | F(AMD_IBPB) | F(AMD_IBRS) | F(AMD_SSBD) | F(VIRT_SSBD) | - F(AMD_SSB_NO) | F(AMD_STIBP); + F(AMD_SSB_NO) | F(AMD_STIBP) | F(AMD_STIBP_ALWAYS_ON); /* cpuid 0xC0000001.edx */ const u32 kvm_cpuid_C000_0001_edx_x86_features = @@ -385,31 +472,10 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, F(ACE2) | F(ACE2_EN) | F(PHE) | F(PHE_EN) | F(PMM) | F(PMM_EN); - /* cpuid 7.0.ebx */ - const u32 kvm_cpuid_7_0_ebx_x86_features = - F(FSGSBASE) | F(BMI1) | F(HLE) | F(AVX2) | F(SMEP) | - F(BMI2) | F(ERMS) | f_invpcid | F(RTM) | f_mpx | F(RDSEED) | - F(ADX) | F(SMAP) | F(AVX512IFMA) | F(AVX512F) | F(AVX512PF) | - F(AVX512ER) | F(AVX512CD) | F(CLFLUSHOPT) | F(CLWB) | F(AVX512DQ) | - F(SHA_NI) | F(AVX512BW) | F(AVX512VL) | f_intel_pt; - /* cpuid 0xD.1.eax */ const u32 kvm_cpuid_D_1_eax_x86_features = F(XSAVEOPT) | F(XSAVEC) | F(XGETBV1) | f_xsaves; - /* cpuid 7.0.ecx*/ - const u32 kvm_cpuid_7_0_ecx_x86_features = - F(AVX512VBMI) | F(LA57) | F(PKU) | 0 /*OSPKE*/ | - F(AVX512_VPOPCNTDQ) | F(UMIP) | F(AVX512_VBMI2) | F(GFNI) | - F(VAES) | F(VPCLMULQDQ) | F(AVX512_VNNI) | F(AVX512_BITALG) | - F(CLDEMOTE) | F(MOVDIRI) | F(MOVDIR64B); - - /* cpuid 7.0.edx*/ - const u32 kvm_cpuid_7_0_edx_x86_features = - F(AVX512_4VNNIW) | F(AVX512_4FMAPS) | F(SPEC_CTRL) | - F(SPEC_CTRL_SSBD) | F(ARCH_CAPABILITIES) | F(INTEL_STIBP) | - F(MD_CLEAR); - /* all calls to cpuid_count() should be made on the same cpu */ get_cpu(); @@ -418,12 +484,13 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, if (*nent >= maxnent) goto out; - do_cpuid_1_ent(entry, function, index); + do_host_cpuid(entry, function, 0); ++*nent; switch (function) { case 0: - entry->eax = min(entry->eax, (u32)(f_intel_pt ? 0x14 : 0xd)); + /* Limited to the highest leaf implemented in KVM. */ + entry->eax = min(entry->eax, 0x1fU); break; case 1: entry->edx &= kvm_cpuid_1_edx_x86_features; @@ -441,14 +508,12 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, case 2: { int t, times = entry->eax & 0xff; - entry->flags |= KVM_CPUID_FLAG_STATEFUL_FUNC; entry->flags |= KVM_CPUID_FLAG_STATE_READ_NEXT; for (t = 1; t < times; ++t) { if (*nent >= maxnent) goto out; - do_cpuid_1_ent(&entry[t], function, 0); - entry[t].flags |= KVM_CPUID_FLAG_STATEFUL_FUNC; + do_host_cpuid(&entry[t], function, 0); ++*nent; } break; @@ -458,7 +523,6 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, case 0x8000001d: { int i, cache_type; - entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; /* read more entries until cache_type is zero */ for (i = 1; ; ++i) { if (*nent >= maxnent) @@ -467,9 +531,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, cache_type = entry[i - 1].eax & 0x1f; if (!cache_type) break; - do_cpuid_1_ent(&entry[i], function, i); - entry[i].flags |= - KVM_CPUID_FLAG_SIGNIFCANT_INDEX; + do_host_cpuid(&entry[i], function, i); ++*nent; } break; @@ -480,36 +542,21 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, entry->ecx = 0; entry->edx = 0; break; + /* function 7 has additional index. */ case 7: { - entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; - /* Mask ebx against host capability word 9 */ - if (index == 0) { - entry->ebx &= kvm_cpuid_7_0_ebx_x86_features; - cpuid_mask(&entry->ebx, CPUID_7_0_EBX); - // TSC_ADJUST is emulated - entry->ebx |= F(TSC_ADJUST); - entry->ecx &= kvm_cpuid_7_0_ecx_x86_features; - f_la57 = entry->ecx & F(LA57); - cpuid_mask(&entry->ecx, CPUID_7_ECX); - /* Set LA57 based on hardware capability. */ - entry->ecx |= f_la57; - entry->ecx |= f_umip; - /* PKU is not yet implemented for shadow paging. */ - if (!tdp_enabled || !boot_cpu_has(X86_FEATURE_OSPKE)) - entry->ecx &= ~F(PKU); - entry->edx &= kvm_cpuid_7_0_edx_x86_features; - cpuid_mask(&entry->edx, CPUID_7_EDX); - /* - * We emulate ARCH_CAPABILITIES in software even - * if the host doesn't support it. - */ - entry->edx |= F(ARCH_CAPABILITIES); - } else { - entry->ebx = 0; - entry->ecx = 0; - entry->edx = 0; + int i; + + for (i = 0; ; ) { + do_cpuid_7_mask(&entry[i], i); + if (i == entry->eax) + break; + if (*nent >= maxnent) + goto out; + + ++i; + do_host_cpuid(&entry[i], function, i); + ++*nent; } - entry->eax = 0; break; } case 9: @@ -543,11 +590,14 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, entry->edx = edx.full; break; } - /* function 0xb has additional index. */ + /* + * Per Intel's SDM, the 0x1f is a superset of 0xb, + * thus they can be handled by common code. + */ + case 0x1f: case 0xb: { int i, level_type; - entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; /* read more entries until level_type is zero */ for (i = 1; ; ++i) { if (*nent >= maxnent) @@ -556,9 +606,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, level_type = entry[i - 1].ecx & 0xff00; if (!level_type) break; - do_cpuid_1_ent(&entry[i], function, i); - entry[i].flags |= - KVM_CPUID_FLAG_SIGNIFCANT_INDEX; + do_host_cpuid(&entry[i], function, i); ++*nent; } break; @@ -571,7 +619,6 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, entry->ebx = xstate_required_size(supported, false); entry->ecx = entry->ebx; entry->edx &= supported >> 32; - entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; if (!supported) break; @@ -580,7 +627,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, if (*nent >= maxnent) goto out; - do_cpuid_1_ent(&entry[i], function, idx); + do_host_cpuid(&entry[i], function, idx); if (idx == 1) { entry[i].eax &= kvm_cpuid_D_1_eax_x86_features; cpuid_mask(&entry[i].eax, CPUID_D_1_EAX); @@ -597,8 +644,6 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, } entry[i].ecx = 0; entry[i].edx = 0; - entry[i].flags |= - KVM_CPUID_FLAG_SIGNIFCANT_INDEX; ++*nent; ++i; } @@ -611,12 +656,10 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, if (!f_intel_pt) break; - entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; for (t = 1; t <= times; ++t) { if (*nent >= maxnent) goto out; - do_cpuid_1_ent(&entry[t], function, t); - entry[t].flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; + do_host_cpuid(&entry[t], function, t); ++*nent; } break; @@ -640,7 +683,9 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, (1 << KVM_FEATURE_PV_UNHALT) | (1 << KVM_FEATURE_PV_TLB_FLUSH) | (1 << KVM_FEATURE_ASYNC_PF_VMEXIT) | - (1 << KVM_FEATURE_PV_SEND_IPI); + (1 << KVM_FEATURE_PV_SEND_IPI) | + (1 << KVM_FEATURE_POLL_CONTROL) | + (1 << KVM_FEATURE_PV_SCHED_YIELD); if (sched_info_on()) entry->eax |= (1 << KVM_FEATURE_STEAL_TIME); @@ -730,21 +775,19 @@ out: return r; } -static int do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 func, - u32 idx, int *nent, int maxnent, unsigned int type) +static int do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 func, + int *nent, int maxnent, unsigned int type) { if (type == KVM_GET_EMULATED_CPUID) - return __do_cpuid_ent_emulated(entry, func, idx, nent, maxnent); + return __do_cpuid_func_emulated(entry, func, nent, maxnent); - return __do_cpuid_ent(entry, func, idx, nent, maxnent); + return __do_cpuid_func(entry, func, nent, maxnent); } #undef F struct kvm_cpuid_param { u32 func; - u32 idx; - bool has_leaf_count; bool (*qualifier)(const struct kvm_cpuid_param *param); }; @@ -788,11 +831,10 @@ int kvm_dev_ioctl_get_cpuid(struct kvm_cpuid2 *cpuid, int limit, nent = 0, r = -E2BIG, i; u32 func; static const struct kvm_cpuid_param param[] = { - { .func = 0, .has_leaf_count = true }, - { .func = 0x80000000, .has_leaf_count = true }, - { .func = 0xC0000000, .qualifier = is_centaur_cpu, .has_leaf_count = true }, + { .func = 0 }, + { .func = 0x80000000 }, + { .func = 0xC0000000, .qualifier = is_centaur_cpu }, { .func = KVM_CPUID_SIGNATURE }, - { .func = KVM_CPUID_FEATURES }, }; if (cpuid->nent < 1) @@ -816,19 +858,16 @@ int kvm_dev_ioctl_get_cpuid(struct kvm_cpuid2 *cpuid, if (ent->qualifier && !ent->qualifier(ent)) continue; - r = do_cpuid_ent(&cpuid_entries[nent], ent->func, ent->idx, - &nent, cpuid->nent, type); + r = do_cpuid_func(&cpuid_entries[nent], ent->func, + &nent, cpuid->nent, type); if (r) goto out_free; - if (!ent->has_leaf_count) - continue; - limit = cpuid_entries[nent - 1].eax; for (func = ent->func + 1; func <= limit && nent < cpuid->nent && r == 0; ++func) - r = do_cpuid_ent(&cpuid_entries[nent], func, ent->idx, - &nent, cpuid->nent, type); + r = do_cpuid_func(&cpuid_entries[nent], func, + &nent, cpuid->nent, type); if (r) goto out_free; diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 4a387a235424..8e409ad448f9 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -4258,7 +4258,7 @@ static int check_dr_read(struct x86_emulate_ctxt *ctxt) ulong dr6; ctxt->ops->get_dr(ctxt, 6, &dr6); - dr6 &= ~15; + dr6 &= ~DR_TRAP_BITS; dr6 |= DR6_BD | DR6_RTM; ctxt->ops->set_dr(ctxt, 6, dr6); return emulate_db(ctxt); diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h index d6519a3aa959..7c6233d37c64 100644 --- a/arch/x86/kvm/irq.h +++ b/arch/x86/kvm/irq.h @@ -102,7 +102,6 @@ static inline int irqchip_in_kernel(struct kvm *kvm) return mode != KVM_IRQCHIP_NONE; } -bool kvm_arch_irqfd_allowed(struct kvm *kvm, struct kvm_irqfd *args); void kvm_inject_pending_timer_irqs(struct kvm_vcpu *vcpu); void kvm_inject_apic_timer_irqs(struct kvm_vcpu *vcpu); void kvm_apic_nmi_wd_deliver(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c index 924b3bd5a7b7..8ecd48d31800 100644 --- a/arch/x86/kvm/irq_comm.c +++ b/arch/x86/kvm/irq_comm.c @@ -75,7 +75,7 @@ int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src, if (r < 0) r = 0; r += kvm_apic_set_irq(vcpu, irq, dest_map); - } else if (kvm_lapic_enabled(vcpu)) { + } else if (kvm_apic_sw_enabled(vcpu->arch.apic)) { if (!kvm_vector_hashing_enabled()) { if (!lowest) lowest = vcpu; diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 4dabc318adb8..a232e76d8f23 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -69,6 +69,7 @@ #define X2APIC_BROADCAST 0xFFFFFFFFul #define LAPIC_TIMER_ADVANCE_ADJUST_DONE 100 +#define LAPIC_TIMER_ADVANCE_ADJUST_INIT 1000 /* step-by-step approximation to mitigate fluctuation */ #define LAPIC_TIMER_ADVANCE_ADJUST_STEP 8 @@ -85,11 +86,6 @@ bool kvm_apic_pending_eoi(struct kvm_vcpu *vcpu, int vector) apic_test_vector(vector, apic->regs + APIC_IRR); } -static inline void apic_clear_vector(int vec, void *bitmap) -{ - clear_bit(VEC_POS(vec), (bitmap) + REG_POS(vec)); -} - static inline int __apic_test_and_set_vector(int vec, void *bitmap) { return __test_and_set_bit(VEC_POS(vec), (bitmap) + REG_POS(vec)); @@ -443,12 +439,12 @@ static inline void apic_clear_irr(int vec, struct kvm_lapic *apic) if (unlikely(vcpu->arch.apicv_active)) { /* need to update RVI */ - apic_clear_vector(vec, apic->regs + APIC_IRR); + kvm_lapic_clear_vector(vec, apic->regs + APIC_IRR); kvm_x86_ops->hwapic_irr_update(vcpu, apic_find_highest_irr(apic)); } else { apic->irr_pending = false; - apic_clear_vector(vec, apic->regs + APIC_IRR); + kvm_lapic_clear_vector(vec, apic->regs + APIC_IRR); if (apic_search_irr(apic) != -1) apic->irr_pending = true; } @@ -1053,9 +1049,11 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode, if (apic_test_vector(vector, apic->regs + APIC_TMR) != !!trig_mode) { if (trig_mode) - kvm_lapic_set_vector(vector, apic->regs + APIC_TMR); + kvm_lapic_set_vector(vector, + apic->regs + APIC_TMR); else - apic_clear_vector(vector, apic->regs + APIC_TMR); + kvm_lapic_clear_vector(vector, + apic->regs + APIC_TMR); } if (vcpu->arch.apicv_active) @@ -1313,21 +1311,45 @@ static inline struct kvm_lapic *to_lapic(struct kvm_io_device *dev) return container_of(dev, struct kvm_lapic, dev); } +#define APIC_REG_MASK(reg) (1ull << ((reg) >> 4)) +#define APIC_REGS_MASK(first, count) \ + (APIC_REG_MASK(first) * ((1ull << (count)) - 1)) + int kvm_lapic_reg_read(struct kvm_lapic *apic, u32 offset, int len, void *data) { unsigned char alignment = offset & 0xf; u32 result; /* this bitmask has a bit cleared for each reserved register */ - static const u64 rmask = 0x43ff01ffffffe70cULL; - - if ((alignment + len) > 4) { - apic_debug("KVM_APIC_READ: alignment error %x %d\n", - offset, len); - return 1; - } + u64 valid_reg_mask = + APIC_REG_MASK(APIC_ID) | + APIC_REG_MASK(APIC_LVR) | + APIC_REG_MASK(APIC_TASKPRI) | + APIC_REG_MASK(APIC_PROCPRI) | + APIC_REG_MASK(APIC_LDR) | + APIC_REG_MASK(APIC_DFR) | + APIC_REG_MASK(APIC_SPIV) | + APIC_REGS_MASK(APIC_ISR, APIC_ISR_NR) | + APIC_REGS_MASK(APIC_TMR, APIC_ISR_NR) | + APIC_REGS_MASK(APIC_IRR, APIC_ISR_NR) | + APIC_REG_MASK(APIC_ESR) | + APIC_REG_MASK(APIC_ICR) | + APIC_REG_MASK(APIC_ICR2) | + APIC_REG_MASK(APIC_LVTT) | + APIC_REG_MASK(APIC_LVTTHMR) | + APIC_REG_MASK(APIC_LVTPC) | + APIC_REG_MASK(APIC_LVT0) | + APIC_REG_MASK(APIC_LVT1) | + APIC_REG_MASK(APIC_LVTERR) | + APIC_REG_MASK(APIC_TMICT) | + APIC_REG_MASK(APIC_TMCCT) | + APIC_REG_MASK(APIC_TDCR); + + /* ARBPRI is not valid on x2APIC */ + if (!apic_x2apic_mode(apic)) + valid_reg_mask |= APIC_REG_MASK(APIC_ARBPRI); - if (offset > 0x3f0 || !(rmask & (1ULL << (offset >> 4)))) { + if (offset > 0x3f0 || !(valid_reg_mask & APIC_REG_MASK(offset))) { apic_debug("KVM_APIC_READ: read reserved register %x\n", offset); return 1; @@ -1499,11 +1521,40 @@ static inline void __wait_lapic_expire(struct kvm_vcpu *vcpu, u64 guest_cycles) } } -void wait_lapic_expire(struct kvm_vcpu *vcpu) +static inline void adjust_lapic_timer_advance(struct kvm_vcpu *vcpu, + s64 advance_expire_delta) { struct kvm_lapic *apic = vcpu->arch.apic; u32 timer_advance_ns = apic->lapic_timer.timer_advance_ns; - u64 guest_tsc, tsc_deadline, ns; + u64 ns; + + /* too early */ + if (advance_expire_delta < 0) { + ns = -advance_expire_delta * 1000000ULL; + do_div(ns, vcpu->arch.virtual_tsc_khz); + timer_advance_ns -= min((u32)ns, + timer_advance_ns / LAPIC_TIMER_ADVANCE_ADJUST_STEP); + } else { + /* too late */ + ns = advance_expire_delta * 1000000ULL; + do_div(ns, vcpu->arch.virtual_tsc_khz); + timer_advance_ns += min((u32)ns, + timer_advance_ns / LAPIC_TIMER_ADVANCE_ADJUST_STEP); + } + + if (abs(advance_expire_delta) < LAPIC_TIMER_ADVANCE_ADJUST_DONE) + apic->lapic_timer.timer_advance_adjust_done = true; + if (unlikely(timer_advance_ns > 5000)) { + timer_advance_ns = LAPIC_TIMER_ADVANCE_ADJUST_INIT; + apic->lapic_timer.timer_advance_adjust_done = false; + } + apic->lapic_timer.timer_advance_ns = timer_advance_ns; +} + +void kvm_wait_lapic_expire(struct kvm_vcpu *vcpu) +{ + struct kvm_lapic *apic = vcpu->arch.apic; + u64 guest_tsc, tsc_deadline; if (apic->lapic_timer.expired_tscdeadline == 0) return; @@ -1514,34 +1565,15 @@ void wait_lapic_expire(struct kvm_vcpu *vcpu) tsc_deadline = apic->lapic_timer.expired_tscdeadline; apic->lapic_timer.expired_tscdeadline = 0; guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc()); - trace_kvm_wait_lapic_expire(vcpu->vcpu_id, guest_tsc - tsc_deadline); + apic->lapic_timer.advance_expire_delta = guest_tsc - tsc_deadline; if (guest_tsc < tsc_deadline) __wait_lapic_expire(vcpu, tsc_deadline - guest_tsc); - if (!apic->lapic_timer.timer_advance_adjust_done) { - /* too early */ - if (guest_tsc < tsc_deadline) { - ns = (tsc_deadline - guest_tsc) * 1000000ULL; - do_div(ns, vcpu->arch.virtual_tsc_khz); - timer_advance_ns -= min((u32)ns, - timer_advance_ns / LAPIC_TIMER_ADVANCE_ADJUST_STEP); - } else { - /* too late */ - ns = (guest_tsc - tsc_deadline) * 1000000ULL; - do_div(ns, vcpu->arch.virtual_tsc_khz); - timer_advance_ns += min((u32)ns, - timer_advance_ns / LAPIC_TIMER_ADVANCE_ADJUST_STEP); - } - if (abs(guest_tsc - tsc_deadline) < LAPIC_TIMER_ADVANCE_ADJUST_DONE) - apic->lapic_timer.timer_advance_adjust_done = true; - if (unlikely(timer_advance_ns > 5000)) { - timer_advance_ns = 0; - apic->lapic_timer.timer_advance_adjust_done = true; - } - apic->lapic_timer.timer_advance_ns = timer_advance_ns; - } + if (unlikely(!apic->lapic_timer.timer_advance_adjust_done)) + adjust_lapic_timer_advance(vcpu, apic->lapic_timer.advance_expire_delta); } +EXPORT_SYMBOL_GPL(kvm_wait_lapic_expire); static void start_sw_tscdeadline(struct kvm_lapic *apic) { @@ -2014,7 +2046,7 @@ static int apic_mmio_write(struct kvm_vcpu *vcpu, struct kvm_io_device *this, apic_debug("%s: offset 0x%x with length 0x%x, and value is " "0x%x\n", __func__, offset, len, val); - kvm_lapic_reg_write(apic, offset & 0xff0, val); + kvm_lapic_reg_write(apic, offset, val); return 0; } @@ -2311,7 +2343,7 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu, int timer_advance_ns) HRTIMER_MODE_ABS_PINNED); apic->lapic_timer.timer.function = apic_timer_fn; if (timer_advance_ns == -1) { - apic->lapic_timer.timer_advance_ns = 1000; + apic->lapic_timer.timer_advance_ns = LAPIC_TIMER_ADVANCE_ADJUST_INIT; apic->lapic_timer.timer_advance_adjust_done = false; } else { apic->lapic_timer.timer_advance_ns = timer_advance_ns; @@ -2321,7 +2353,7 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu, int timer_advance_ns) /* * APIC is created enabled. This will prevent kvm_lapic_set_base from - * thinking that APIC satet has changed. + * thinking that APIC state has changed. */ vcpu->arch.apic_base = MSR_IA32_APICBASE_ENABLE; static_key_slow_inc(&apic_sw_disabled.key); /* sw disabled at reset */ @@ -2330,6 +2362,7 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu, int timer_advance_ns) return 0; nomem_free_apic: kfree(apic); + vcpu->arch.apic = NULL; nomem: return -ENOMEM; } diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index d6d049ba3045..36747174e4a8 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -32,6 +32,7 @@ struct kvm_timer { u64 tscdeadline; u64 expired_tscdeadline; u32 timer_advance_ns; + s64 advance_expire_delta; atomic_t pending; /* accumulated triggered timers */ bool hv_timer_in_use; bool timer_advance_adjust_done; @@ -129,6 +130,11 @@ void kvm_lapic_exit(void); #define VEC_POS(v) ((v) & (32 - 1)) #define REG_POS(v) (((v) >> 5) << 4) +static inline void kvm_lapic_clear_vector(int vec, void *bitmap) +{ + clear_bit(VEC_POS(vec), (bitmap) + REG_POS(vec)); +} + static inline void kvm_lapic_set_vector(int vec, void *bitmap) { set_bit(VEC_POS(vec), (bitmap) + REG_POS(vec)); @@ -219,7 +225,7 @@ static inline int kvm_lapic_latched_init(struct kvm_vcpu *vcpu) bool kvm_apic_pending_eoi(struct kvm_vcpu *vcpu, int vector); -void wait_lapic_expire(struct kvm_vcpu *vcpu); +void kvm_wait_lapic_expire(struct kvm_vcpu *vcpu); bool kvm_intr_is_single_vcpu_fast(struct kvm *kvm, struct kvm_lapic_irq *irq, struct kvm_vcpu **dest_vcpu); diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 98f6e4f88b04..9a5814d8d194 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -140,9 +140,6 @@ module_param(dbg, bool, 0644); #include <trace/events/kvm.h> -#define CREATE_TRACE_POINTS -#include "mmutrace.h" - #define SPTE_HOST_WRITEABLE (1ULL << PT_FIRST_AVAIL_BITS_SHIFT) #define SPTE_MMU_WRITEABLE (1ULL << (PT_FIRST_AVAIL_BITS_SHIFT + 1)) @@ -259,11 +256,20 @@ static const u64 shadow_nonpresent_or_rsvd_mask_len = 5; */ static u64 __read_mostly shadow_nonpresent_or_rsvd_lower_gfn_mask; +/* + * The number of non-reserved physical address bits irrespective of features + * that repurpose legal bits, e.g. MKTME. + */ +static u8 __read_mostly shadow_phys_bits; static void mmu_spte_set(u64 *sptep, u64 spte); +static bool is_executable_pte(u64 spte); static union kvm_mmu_page_role kvm_mmu_calc_root_page_role(struct kvm_vcpu *vcpu); +#define CREATE_TRACE_POINTS +#include "mmutrace.h" + static inline bool kvm_available_flush_tlb_with_range(void) { @@ -468,6 +474,21 @@ void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask, } EXPORT_SYMBOL_GPL(kvm_mmu_set_mask_ptes); +static u8 kvm_get_shadow_phys_bits(void) +{ + /* + * boot_cpu_data.x86_phys_bits is reduced when MKTME is detected + * in CPU detection code, but MKTME treats those reduced bits as + * 'keyID' thus they are not reserved bits. Therefore for MKTME + * we should still return physical address bits reported by CPUID. + */ + if (!boot_cpu_has(X86_FEATURE_TME) || + WARN_ON_ONCE(boot_cpu_data.extended_cpuid_level < 0x80000008)) + return boot_cpu_data.x86_phys_bits; + + return cpuid_eax(0x80000008) & 0xff; +} + static void kvm_mmu_reset_all_pte_masks(void) { u8 low_phys_bits; @@ -481,6 +502,8 @@ static void kvm_mmu_reset_all_pte_masks(void) shadow_present_mask = 0; shadow_acc_track_mask = 0; + shadow_phys_bits = kvm_get_shadow_phys_bits(); + /* * If the CPU has 46 or less physical address bits, then set an * appropriate mask to guard against L1TF attacks. Otherwise, it is @@ -650,7 +673,7 @@ static u64 __update_clear_spte_slow(u64 *sptep, u64 spte) /* * The idea using the light way get the spte on x86_32 guest is from - * gup_get_pte(arch/x86/mm/gup.c). + * gup_get_pte (mm/gup.c). * * An spte tlb flush may be pending, because kvm_set_pte_rmapp * coalesces them and we are running out of the MMU lock. Therefore @@ -1073,10 +1096,16 @@ static gfn_t kvm_mmu_page_get_gfn(struct kvm_mmu_page *sp, int index) static void kvm_mmu_page_set_gfn(struct kvm_mmu_page *sp, int index, gfn_t gfn) { - if (sp->role.direct) - BUG_ON(gfn != kvm_mmu_page_get_gfn(sp, index)); - else + if (!sp->role.direct) { sp->gfns[index] = gfn; + return; + } + + if (WARN_ON(gfn != kvm_mmu_page_get_gfn(sp, index))) + pr_err_ratelimited("gfn mismatch under direct page %llx " + "(expected %llx, got %llx)\n", + sp->gfn, + kvm_mmu_page_get_gfn(sp, index), gfn); } /* @@ -3055,10 +3084,7 @@ static int mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, unsigned pte_access, ret = RET_PF_EMULATE; pgprintk("%s: setting spte %llx\n", __func__, *sptep); - pgprintk("instantiating %s PTE (%s) at %llx (%llx) addr %p\n", - is_large_pte(*sptep)? "2MB" : "4kB", - *sptep & PT_WRITABLE_MASK ? "RW" : "R", gfn, - *sptep, sptep); + trace_kvm_mmu_set_spte(level, gfn, sptep); if (!was_rmapped && is_large_pte(*sptep)) ++vcpu->kvm->stat.lpages; @@ -3070,8 +3096,6 @@ static int mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, unsigned pte_access, } } - kvm_release_pfn_clean(pfn); - return ret; } @@ -3106,9 +3130,11 @@ static int direct_pte_prefetch_many(struct kvm_vcpu *vcpu, if (ret <= 0) return -1; - for (i = 0; i < ret; i++, gfn++, start++) + for (i = 0; i < ret; i++, gfn++, start++) { mmu_set_spte(vcpu, start, access, 0, sp->role.level, gfn, page_to_pfn(pages[i]), true, true); + put_page(pages[i]); + } return 0; } @@ -3156,40 +3182,40 @@ static void direct_pte_prefetch(struct kvm_vcpu *vcpu, u64 *sptep) __direct_pte_prefetch(vcpu, sp, sptep); } -static int __direct_map(struct kvm_vcpu *vcpu, int write, int map_writable, - int level, gfn_t gfn, kvm_pfn_t pfn, bool prefault) +static int __direct_map(struct kvm_vcpu *vcpu, gpa_t gpa, int write, + int map_writable, int level, kvm_pfn_t pfn, + bool prefault) { - struct kvm_shadow_walk_iterator iterator; + struct kvm_shadow_walk_iterator it; struct kvm_mmu_page *sp; - int emulate = 0; - gfn_t pseudo_gfn; + int ret; + gfn_t gfn = gpa >> PAGE_SHIFT; + gfn_t base_gfn = gfn; if (!VALID_PAGE(vcpu->arch.mmu->root_hpa)) - return 0; + return RET_PF_RETRY; - for_each_shadow_entry(vcpu, (u64)gfn << PAGE_SHIFT, iterator) { - if (iterator.level == level) { - emulate = mmu_set_spte(vcpu, iterator.sptep, ACC_ALL, - write, level, gfn, pfn, prefault, - map_writable); - direct_pte_prefetch(vcpu, iterator.sptep); - ++vcpu->stat.pf_fixed; + trace_kvm_mmu_spte_requested(gpa, level, pfn); + for_each_shadow_entry(vcpu, gpa, it) { + base_gfn = gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1); + if (it.level == level) break; - } - drop_large_spte(vcpu, iterator.sptep); - if (!is_shadow_present_pte(*iterator.sptep)) { - u64 base_addr = iterator.addr; + drop_large_spte(vcpu, it.sptep); + if (!is_shadow_present_pte(*it.sptep)) { + sp = kvm_mmu_get_page(vcpu, base_gfn, it.addr, + it.level - 1, true, ACC_ALL); - base_addr &= PT64_LVL_ADDR_MASK(iterator.level); - pseudo_gfn = base_addr >> PAGE_SHIFT; - sp = kvm_mmu_get_page(vcpu, pseudo_gfn, iterator.addr, - iterator.level - 1, 1, ACC_ALL); - - link_shadow_page(vcpu, iterator.sptep, sp); + link_shadow_page(vcpu, it.sptep, sp); } } - return emulate; + + ret = mmu_set_spte(vcpu, it.sptep, ACC_ALL, + write, level, base_gfn, pfn, prefault, + map_writable); + direct_pte_prefetch(vcpu, it.sptep); + ++vcpu->stat.pf_fixed; + return ret; } static void kvm_send_hwpoison_signal(unsigned long address, struct task_struct *tsk) @@ -3216,11 +3242,10 @@ static int kvm_handle_bad_page(struct kvm_vcpu *vcpu, gfn_t gfn, kvm_pfn_t pfn) } static void transparent_hugepage_adjust(struct kvm_vcpu *vcpu, - gfn_t *gfnp, kvm_pfn_t *pfnp, + gfn_t gfn, kvm_pfn_t *pfnp, int *levelp) { kvm_pfn_t pfn = *pfnp; - gfn_t gfn = *gfnp; int level = *levelp; /* @@ -3247,8 +3272,6 @@ static void transparent_hugepage_adjust(struct kvm_vcpu *vcpu, mask = KVM_PAGES_PER_HPAGE(level) - 1; VM_BUG_ON((gfn & mask) != (pfn & mask)); if (pfn & mask) { - gfn &= ~mask; - *gfnp = gfn; kvm_release_pfn_clean(pfn); pfn &= ~mask; kvm_get_pfn(pfn); @@ -3505,22 +3528,19 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code, if (handle_abnormal_pfn(vcpu, v, gfn, pfn, ACC_ALL, &r)) return r; + r = RET_PF_RETRY; spin_lock(&vcpu->kvm->mmu_lock); if (mmu_notifier_retry(vcpu->kvm, mmu_seq)) goto out_unlock; if (make_mmu_pages_available(vcpu) < 0) goto out_unlock; if (likely(!force_pt_level)) - transparent_hugepage_adjust(vcpu, &gfn, &pfn, &level); - r = __direct_map(vcpu, write, map_writable, level, gfn, pfn, prefault); - spin_unlock(&vcpu->kvm->mmu_lock); - - return r; - + transparent_hugepage_adjust(vcpu, gfn, &pfn, &level); + r = __direct_map(vcpu, v, write, map_writable, level, pfn, prefault); out_unlock: spin_unlock(&vcpu->kvm->mmu_lock); kvm_release_pfn_clean(pfn); - return RET_PF_RETRY; + return r; } static void mmu_free_root_page(struct kvm *kvm, hpa_t *root_hpa, @@ -4015,19 +4035,6 @@ static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn) return kvm_setup_async_pf(vcpu, gva, kvm_vcpu_gfn_to_hva(vcpu, gfn), &arch); } -bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu) -{ - if (unlikely(!lapic_in_kernel(vcpu) || - kvm_event_needs_reinjection(vcpu) || - vcpu->arch.exception.pending)) - return false; - - if (!vcpu->arch.apf.delivery_as_pf_vmexit && is_guest_mode(vcpu)) - return false; - - return kvm_x86_ops->interrupt_allowed(vcpu); -} - static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, gva_t gva, kvm_pfn_t *pfn, bool write, bool *writable) { @@ -4147,22 +4154,19 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code, if (handle_abnormal_pfn(vcpu, 0, gfn, pfn, ACC_ALL, &r)) return r; + r = RET_PF_RETRY; spin_lock(&vcpu->kvm->mmu_lock); if (mmu_notifier_retry(vcpu->kvm, mmu_seq)) goto out_unlock; if (make_mmu_pages_available(vcpu) < 0) goto out_unlock; if (likely(!force_pt_level)) - transparent_hugepage_adjust(vcpu, &gfn, &pfn, &level); - r = __direct_map(vcpu, write, map_writable, level, gfn, pfn, prefault); - spin_unlock(&vcpu->kvm->mmu_lock); - - return r; - + transparent_hugepage_adjust(vcpu, gfn, &pfn, &level); + r = __direct_map(vcpu, gpa, write, map_writable, level, pfn, prefault); out_unlock: spin_unlock(&vcpu->kvm->mmu_lock); kvm_release_pfn_clean(pfn); - return RET_PF_RETRY; + return r; } static void nonpaging_init_context(struct kvm_vcpu *vcpu, @@ -4494,7 +4498,7 @@ reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context) */ shadow_zero_check = &context->shadow_zero_check; __reset_rsvds_bits_mask(vcpu, shadow_zero_check, - boot_cpu_data.x86_phys_bits, + shadow_phys_bits, context->shadow_root_level, uses_nx, guest_cpuid_has(vcpu, X86_FEATURE_GBPAGES), is_pse(vcpu), true); @@ -4531,13 +4535,13 @@ reset_tdp_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, if (boot_cpu_is_amd()) __reset_rsvds_bits_mask(vcpu, shadow_zero_check, - boot_cpu_data.x86_phys_bits, + shadow_phys_bits, context->shadow_root_level, false, boot_cpu_has(X86_FEATURE_GBPAGES), true, true); else __reset_rsvds_bits_mask_ept(shadow_zero_check, - boot_cpu_data.x86_phys_bits, + shadow_phys_bits, false); if (!shadow_me_mask) @@ -4558,7 +4562,7 @@ reset_ept_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context, bool execonly) { __reset_rsvds_bits_mask_ept(&context->shadow_zero_check, - boot_cpu_data.x86_phys_bits, execonly); + shadow_phys_bits, execonly); } #define BYTE_MASK(access) \ @@ -5935,7 +5939,7 @@ mmu_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) int nr_to_scan = sc->nr_to_scan; unsigned long freed = 0; - spin_lock(&kvm_lock); + mutex_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) { int idx; @@ -5977,7 +5981,7 @@ mmu_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) break; } - spin_unlock(&kvm_lock); + mutex_unlock(&kvm_lock); return freed; } @@ -5999,6 +6003,34 @@ static void mmu_destroy_caches(void) kmem_cache_destroy(mmu_page_header_cache); } +static void kvm_set_mmio_spte_mask(void) +{ + u64 mask; + + /* + * Set the reserved bits and the present bit of an paging-structure + * entry to generate page fault with PFER.RSV = 1. + */ + + /* + * Mask the uppermost physical address bit, which would be reserved as + * long as the supported physical address width is less than 52. + */ + mask = 1ull << 51; + + /* Set the present bit. */ + mask |= 1ull; + + /* + * If reserved bit is not supported, clear the present bit to disable + * mmio page fault. + */ + if (IS_ENABLED(CONFIG_X86_64) && shadow_phys_bits == 52) + mask &= ~1ull; + + kvm_mmu_set_mmio_spte_mask(mask, mask); +} + int kvm_mmu_module_init(void) { int ret = -ENOMEM; @@ -6015,6 +6047,8 @@ int kvm_mmu_module_init(void) kvm_mmu_reset_all_pte_masks(); + kvm_set_mmio_spte_mask(); + pte_list_desc_cache = kmem_cache_create("pte_list_desc", sizeof(struct pte_list_desc), 0, SLAB_ACCOUNT, NULL); diff --git a/arch/x86/kvm/mmutrace.h b/arch/x86/kvm/mmutrace.h index dd30dccd2ad5..d8001b4bca05 100644 --- a/arch/x86/kvm/mmutrace.h +++ b/arch/x86/kvm/mmutrace.h @@ -301,6 +301,65 @@ TRACE_EVENT( __entry->kvm_gen == __entry->spte_gen ) ); + +TRACE_EVENT( + kvm_mmu_set_spte, + TP_PROTO(int level, gfn_t gfn, u64 *sptep), + TP_ARGS(level, gfn, sptep), + + TP_STRUCT__entry( + __field(u64, gfn) + __field(u64, spte) + __field(u64, sptep) + __field(u8, level) + /* These depend on page entry type, so compute them now. */ + __field(bool, r) + __field(bool, x) + __field(u8, u) + ), + + TP_fast_assign( + __entry->gfn = gfn; + __entry->spte = *sptep; + __entry->sptep = virt_to_phys(sptep); + __entry->level = level; + __entry->r = shadow_present_mask || (__entry->spte & PT_PRESENT_MASK); + __entry->x = is_executable_pte(__entry->spte); + __entry->u = shadow_user_mask ? !!(__entry->spte & shadow_user_mask) : -1; + ), + + TP_printk("gfn %llx spte %llx (%s%s%s%s) level %d at %llx", + __entry->gfn, __entry->spte, + __entry->r ? "r" : "-", + __entry->spte & PT_WRITABLE_MASK ? "w" : "-", + __entry->x ? "x" : "-", + __entry->u == -1 ? "" : (__entry->u ? "u" : "-"), + __entry->level, __entry->sptep + ) +); + +TRACE_EVENT( + kvm_mmu_spte_requested, + TP_PROTO(gpa_t addr, int level, kvm_pfn_t pfn), + TP_ARGS(addr, level, pfn), + + TP_STRUCT__entry( + __field(u64, gfn) + __field(u64, pfn) + __field(u8, level) + ), + + TP_fast_assign( + __entry->gfn = addr >> PAGE_SHIFT; + __entry->pfn = pfn | (__entry->gfn & (KVM_PAGES_PER_HPAGE(level) - 1)); + __entry->level = level; + ), + + TP_printk("gfn %llx pfn %llx level %d", + __entry->gfn, __entry->pfn, __entry->level + ) +); + #endif /* _TRACE_KVMMMU_H */ #undef TRACE_INCLUDE_PATH diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index d583bcd119fc..7d5cdb3af594 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -540,6 +540,7 @@ FNAME(prefetch_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, mmu_set_spte(vcpu, spte, pte_access, 0, PT_PAGE_TABLE_LEVEL, gfn, pfn, true, true); + kvm_release_pfn_clean(pfn); return true; } @@ -619,6 +620,7 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, struct kvm_shadow_walk_iterator it; unsigned direct_access, access = gw->pt_access; int top_level, ret; + gfn_t base_gfn; direct_access = gw->pte_access; @@ -663,35 +665,34 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, link_shadow_page(vcpu, it.sptep, sp); } - for (; - shadow_walk_okay(&it) && it.level > hlevel; - shadow_walk_next(&it)) { - gfn_t direct_gfn; + base_gfn = gw->gfn; + + trace_kvm_mmu_spte_requested(addr, gw->level, pfn); + for (; shadow_walk_okay(&it); shadow_walk_next(&it)) { clear_sp_write_flooding_count(it.sptep); + base_gfn = gw->gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1); + if (it.level == hlevel) + break; + validate_direct_spte(vcpu, it.sptep, direct_access); drop_large_spte(vcpu, it.sptep); - if (is_shadow_present_pte(*it.sptep)) - continue; - - direct_gfn = gw->gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1); - - sp = kvm_mmu_get_page(vcpu, direct_gfn, addr, it.level-1, - true, direct_access); - link_shadow_page(vcpu, it.sptep, sp); + if (!is_shadow_present_pte(*it.sptep)) { + sp = kvm_mmu_get_page(vcpu, base_gfn, addr, + it.level - 1, true, direct_access); + link_shadow_page(vcpu, it.sptep, sp); + } } - clear_sp_write_flooding_count(it.sptep); ret = mmu_set_spte(vcpu, it.sptep, gw->pte_access, write_fault, - it.level, gw->gfn, pfn, prefault, map_writable); + it.level, base_gfn, pfn, prefault, map_writable); FNAME(pte_prefetch)(vcpu, gw, it.sptep); - + ++vcpu->stat.pf_fixed; return ret; out_gpte_changed: - kvm_release_pfn_clean(pfn); return RET_PF_RETRY; } @@ -839,6 +840,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code, walker.pte_access &= ~ACC_EXEC_MASK; } + r = RET_PF_RETRY; spin_lock(&vcpu->kvm->mmu_lock); if (mmu_notifier_retry(vcpu->kvm, mmu_seq)) goto out_unlock; @@ -847,19 +849,15 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code, if (make_mmu_pages_available(vcpu) < 0) goto out_unlock; if (!force_pt_level) - transparent_hugepage_adjust(vcpu, &walker.gfn, &pfn, &level); + transparent_hugepage_adjust(vcpu, walker.gfn, &pfn, &level); r = FNAME(fetch)(vcpu, addr, &walker, write_fault, level, pfn, map_writable, prefault); - ++vcpu->stat.pf_fixed; kvm_mmu_audit(vcpu, AUDIT_POST_PAGE_FAULT); - spin_unlock(&vcpu->kvm->mmu_lock); - - return r; out_unlock: spin_unlock(&vcpu->kvm->mmu_lock); kvm_release_pfn_clean(pfn); - return RET_PF_RETRY; + return r; } static gpa_t FNAME(get_level1_sp_gpa)(struct kvm_mmu_page *sp) diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index ab73a9a639ae..aa5a2597305a 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -19,6 +19,9 @@ #include "lapic.h" #include "pmu.h" +/* This keeps the total size of the filter under 4k. */ +#define KVM_PMU_EVENT_FILTER_MAX_EVENTS 63 + /* NOTE: * - Each perf counter is defined as "struct kvm_pmc"; * - There are two types of perf counters: general purpose (gp) and fixed. @@ -141,6 +144,10 @@ void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel) { unsigned config, type = PERF_TYPE_RAW; u8 event_select, unit_mask; + struct kvm *kvm = pmc->vcpu->kvm; + struct kvm_pmu_event_filter *filter; + int i; + bool allow_event = true; if (eventsel & ARCH_PERFMON_EVENTSEL_PIN_CONTROL) printk_once("kvm pmu: pin control bit is ignored\n"); @@ -152,6 +159,22 @@ void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel) if (!(eventsel & ARCH_PERFMON_EVENTSEL_ENABLE) || !pmc_is_enabled(pmc)) return; + filter = srcu_dereference(kvm->arch.pmu_event_filter, &kvm->srcu); + if (filter) { + for (i = 0; i < filter->nevents; i++) + if (filter->events[i] == + (eventsel & AMD64_RAW_EVENT_MASK_NB)) + break; + if (filter->action == KVM_PMU_EVENT_ALLOW && + i == filter->nevents) + allow_event = false; + if (filter->action == KVM_PMU_EVENT_DENY && + i < filter->nevents) + allow_event = false; + } + if (!allow_event) + return; + event_select = eventsel & ARCH_PERFMON_EVENTSEL_EVENT; unit_mask = (eventsel & ARCH_PERFMON_EVENTSEL_UMASK) >> 8; @@ -348,3 +371,43 @@ void kvm_pmu_destroy(struct kvm_vcpu *vcpu) { kvm_pmu_reset(vcpu); } + +int kvm_vm_ioctl_set_pmu_event_filter(struct kvm *kvm, void __user *argp) +{ + struct kvm_pmu_event_filter tmp, *filter; + size_t size; + int r; + + if (copy_from_user(&tmp, argp, sizeof(tmp))) + return -EFAULT; + + if (tmp.action != KVM_PMU_EVENT_ALLOW && + tmp.action != KVM_PMU_EVENT_DENY) + return -EINVAL; + + if (tmp.nevents > KVM_PMU_EVENT_FILTER_MAX_EVENTS) + return -E2BIG; + + size = struct_size(filter, events, tmp.nevents); + filter = kmalloc(size, GFP_KERNEL_ACCOUNT); + if (!filter) + return -ENOMEM; + + r = -EFAULT; + if (copy_from_user(filter, argp, size)) + goto cleanup; + + /* Ensure nevents can't be changed between the user copies. */ + *filter = tmp; + + mutex_lock(&kvm->lock); + rcu_swap_protected(kvm->arch.pmu_event_filter, filter, + mutex_is_locked(&kvm->lock)); + mutex_unlock(&kvm->lock); + + synchronize_srcu_expedited(&kvm->srcu); + r = 0; +cleanup: + kfree(filter); + return r; +} diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h index 22dff661145a..58265f761c3b 100644 --- a/arch/x86/kvm/pmu.h +++ b/arch/x86/kvm/pmu.h @@ -118,6 +118,7 @@ void kvm_pmu_refresh(struct kvm_vcpu *vcpu); void kvm_pmu_reset(struct kvm_vcpu *vcpu); void kvm_pmu_init(struct kvm_vcpu *vcpu); void kvm_pmu_destroy(struct kvm_vcpu *vcpu); +int kvm_vm_ioctl_set_pmu_event_filter(struct kvm *kvm, void __user *argp); bool is_vmware_backdoor_pmc(u32 pmc_idx); diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 48c865a4e5dd..583b9fa656f3 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -364,6 +364,10 @@ static int avic; module_param(avic, int, S_IRUGO); #endif +/* enable/disable Next RIP Save */ +static int nrips = true; +module_param(nrips, int, 0444); + /* enable/disable Virtual VMLOAD VMSAVE */ static int vls = true; module_param(vls, int, 0444); @@ -770,7 +774,7 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); - if (svm->vmcb->control.next_rip != 0) { + if (nrips && svm->vmcb->control.next_rip != 0) { WARN_ON_ONCE(!static_cpu_has(X86_FEATURE_NRIPS)); svm->next_rip = svm->vmcb->control.next_rip; } @@ -807,7 +811,7 @@ static void svm_queue_exception(struct kvm_vcpu *vcpu) kvm_deliver_exception_payload(&svm->vcpu); - if (nr == BP_VECTOR && !static_cpu_has(X86_FEATURE_NRIPS)) { + if (nr == BP_VECTOR && !nrips) { unsigned long rip, old_rip = kvm_rip_read(&svm->vcpu); /* @@ -1364,6 +1368,11 @@ static __init int svm_hardware_setup(void) } else kvm_disable_tdp(); + if (nrips) { + if (!boot_cpu_has(X86_FEATURE_NRIPS)) + nrips = false; + } + if (avic) { if (!npt_enabled || !boot_cpu_has(X86_FEATURE_AVIC) || @@ -3290,7 +3299,7 @@ static int nested_svm_vmexit(struct vcpu_svm *svm) vmcb->control.exit_int_info_err, KVM_ISA_SVM); - rc = kvm_vcpu_map(&svm->vcpu, gfn_to_gpa(svm->nested.vmcb), &map); + rc = kvm_vcpu_map(&svm->vcpu, gpa_to_gfn(svm->nested.vmcb), &map); if (rc) { if (rc == -EINVAL) kvm_inject_gp(&svm->vcpu, 0); @@ -3580,7 +3589,7 @@ static bool nested_svm_vmrun(struct vcpu_svm *svm) vmcb_gpa = svm->vmcb->save.rax; - rc = kvm_vcpu_map(&svm->vcpu, gfn_to_gpa(vmcb_gpa), &map); + rc = kvm_vcpu_map(&svm->vcpu, gpa_to_gfn(vmcb_gpa), &map); if (rc) { if (rc == -EINVAL) kvm_inject_gp(&svm->vcpu, 0); @@ -3935,7 +3944,7 @@ static int rdpmc_interception(struct vcpu_svm *svm) { int err; - if (!static_cpu_has(X86_FEATURE_NRIPS)) + if (!nrips) return emulate_on_interception(svm); err = kvm_rdpmc(&svm->vcpu); @@ -5160,10 +5169,13 @@ static void svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec) kvm_lapic_set_irr(vec, vcpu->arch.apic); smp_mb__after_atomic(); - if (avic_vcpu_is_running(vcpu)) - wrmsrl(SVM_AVIC_DOORBELL, - kvm_cpu_get_apicid(vcpu->cpu)); - else + if (avic_vcpu_is_running(vcpu)) { + int cpuid = vcpu->cpu; + + if (cpuid != get_cpu()) + wrmsrl(SVM_AVIC_DOORBELL, kvm_cpu_get_apicid(cpuid)); + put_cpu(); + } else kvm_vcpu_wake_up(vcpu); } @@ -5640,6 +5652,10 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) clgi(); kvm_load_guest_xcr0(vcpu); + if (lapic_in_kernel(vcpu) && + vcpu->arch.apic->lapic_timer.timer_advance_ns) + kvm_wait_lapic_expire(vcpu); + /* * If this vCPU has touched SPEC_CTRL, restore the guest's value if * it's non-zero. Since vmentry is serialising on affected CPUs, there @@ -5861,9 +5877,9 @@ svm_patch_hypercall(struct kvm_vcpu *vcpu, unsigned char *hypercall) hypercall[2] = 0xd9; } -static void svm_check_processor_compat(void *rtn) +static int __init svm_check_processor_compat(void) { - *(int *)rtn = 0; + return 0; } static bool svm_cpu_has_accelerated_tpr(void) @@ -5875,6 +5891,7 @@ static bool svm_has_emulated_msr(int index) { switch (index) { case MSR_IA32_MCG_EXT_CTL: + case MSR_IA32_VMX_BASIC ... MSR_IA32_VMX_VMFUNC: return false; default: break; @@ -6162,15 +6179,9 @@ out: return ret; } -static void svm_handle_external_intr(struct kvm_vcpu *vcpu) +static void svm_handle_exit_irqoff(struct kvm_vcpu *vcpu) { - local_irq_enable(); - /* - * We must have an instruction with interrupts enabled, so - * the timer interrupt isn't delayed by the interrupt shadow. - */ - asm("nop"); - local_irq_disable(); + } static void svm_sched_in(struct kvm_vcpu *vcpu, int cpu) @@ -7256,7 +7267,7 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .set_tdp_cr3 = set_tdp_cr3, .check_intercept = svm_check_intercept, - .handle_external_intr = svm_handle_external_intr, + .handle_exit_irqoff = svm_handle_exit_irqoff, .request_immediate_exit = __kvm_request_immediate_exit, diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index 4d47a2631d1f..b5c831e79094 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -1365,7 +1365,7 @@ TRACE_EVENT(kvm_hv_timer_state, __entry->vcpu_id = vcpu_id; __entry->hv_timer_in_use = hv_timer_in_use; ), - TP_printk("vcpu_id %x hv_timer %x\n", + TP_printk("vcpu_id %x hv_timer %x", __entry->vcpu_id, __entry->hv_timer_in_use) ); diff --git a/arch/x86/kvm/vmx/evmcs.c b/arch/x86/kvm/vmx/evmcs.c index 5466c6d85cf3..72359709cdc1 100644 --- a/arch/x86/kvm/vmx/evmcs.c +++ b/arch/x86/kvm/vmx/evmcs.c @@ -3,6 +3,7 @@ #include <linux/errno.h> #include <linux/smp.h> +#include "../hyperv.h" #include "evmcs.h" #include "vmcs.h" #include "vmx.h" @@ -313,6 +314,23 @@ void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf) } #endif +bool nested_enlightened_vmentry(struct kvm_vcpu *vcpu, u64 *evmcs_gpa) +{ + struct hv_vp_assist_page assist_page; + + *evmcs_gpa = -1ull; + + if (unlikely(!kvm_hv_get_assist_page(vcpu, &assist_page))) + return false; + + if (unlikely(!assist_page.enlighten_vmentry)) + return false; + + *evmcs_gpa = assist_page.current_nested_vmcs; + + return true; +} + uint16_t nested_get_evmcs_version(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); diff --git a/arch/x86/kvm/vmx/evmcs.h b/arch/x86/kvm/vmx/evmcs.h index e0fcef85b332..39a24eec8884 100644 --- a/arch/x86/kvm/vmx/evmcs.h +++ b/arch/x86/kvm/vmx/evmcs.h @@ -195,6 +195,7 @@ static inline void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf) {} static inline void evmcs_touch_msr_bitmap(void) {} #endif /* IS_ENABLED(CONFIG_HYPERV) */ +bool nested_enlightened_vmentry(struct kvm_vcpu *vcpu, u64 *evmcs_gpa); uint16_t nested_get_evmcs_version(struct kvm_vcpu *vcpu); int nested_enable_evmcs(struct kvm_vcpu *vcpu, uint16_t *vmcs_version); diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 46af3a5e9209..bb509c254939 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -41,15 +41,19 @@ static unsigned long *vmx_bitmap[VMX_BITMAP_NR]; #define vmx_vmread_bitmap (vmx_bitmap[VMX_VMREAD_BITMAP]) #define vmx_vmwrite_bitmap (vmx_bitmap[VMX_VMWRITE_BITMAP]) -static u16 shadow_read_only_fields[] = { -#define SHADOW_FIELD_RO(x) x, +struct shadow_vmcs_field { + u16 encoding; + u16 offset; +}; +static struct shadow_vmcs_field shadow_read_only_fields[] = { +#define SHADOW_FIELD_RO(x, y) { x, offsetof(struct vmcs12, y) }, #include "vmcs_shadow_fields.h" }; static int max_shadow_read_only_fields = ARRAY_SIZE(shadow_read_only_fields); -static u16 shadow_read_write_fields[] = { -#define SHADOW_FIELD_RW(x) x, +static struct shadow_vmcs_field shadow_read_write_fields[] = { +#define SHADOW_FIELD_RW(x, y) { x, offsetof(struct vmcs12, y) }, #include "vmcs_shadow_fields.h" }; static int max_shadow_read_write_fields = @@ -63,34 +67,40 @@ static void init_vmcs_shadow_fields(void) memset(vmx_vmwrite_bitmap, 0xff, PAGE_SIZE); for (i = j = 0; i < max_shadow_read_only_fields; i++) { - u16 field = shadow_read_only_fields[i]; + struct shadow_vmcs_field entry = shadow_read_only_fields[i]; + u16 field = entry.encoding; if (vmcs_field_width(field) == VMCS_FIELD_WIDTH_U64 && (i + 1 == max_shadow_read_only_fields || - shadow_read_only_fields[i + 1] != field + 1)) + shadow_read_only_fields[i + 1].encoding != field + 1)) pr_err("Missing field from shadow_read_only_field %x\n", field + 1); clear_bit(field, vmx_vmread_bitmap); -#ifdef CONFIG_X86_64 if (field & 1) +#ifdef CONFIG_X86_64 continue; +#else + entry.offset += sizeof(u32); #endif - if (j < i) - shadow_read_only_fields[j] = field; - j++; + shadow_read_only_fields[j++] = entry; } max_shadow_read_only_fields = j; for (i = j = 0; i < max_shadow_read_write_fields; i++) { - u16 field = shadow_read_write_fields[i]; + struct shadow_vmcs_field entry = shadow_read_write_fields[i]; + u16 field = entry.encoding; if (vmcs_field_width(field) == VMCS_FIELD_WIDTH_U64 && (i + 1 == max_shadow_read_write_fields || - shadow_read_write_fields[i + 1] != field + 1)) + shadow_read_write_fields[i + 1].encoding != field + 1)) pr_err("Missing field from shadow_read_write_field %x\n", field + 1); + WARN_ONCE(field >= GUEST_ES_AR_BYTES && + field <= GUEST_TR_AR_BYTES, + "Update vmcs12_write_any() to drop reserved bits from AR_BYTES"); + /* * PML and the preemption timer can be emulated, but the * processor cannot vmwrite to fields that don't exist @@ -115,13 +125,13 @@ static void init_vmcs_shadow_fields(void) clear_bit(field, vmx_vmwrite_bitmap); clear_bit(field, vmx_vmread_bitmap); -#ifdef CONFIG_X86_64 if (field & 1) +#ifdef CONFIG_X86_64 continue; +#else + entry.offset += sizeof(u32); #endif - if (j < i) - shadow_read_write_fields[j] = field; - j++; + shadow_read_write_fields[j++] = entry; } max_shadow_read_write_fields = j; } @@ -182,7 +192,7 @@ static void nested_vmx_abort(struct kvm_vcpu *vcpu, u32 indicator) static void vmx_disable_shadow_vmcs(struct vcpu_vmx *vmx) { - vmcs_clear_bits(SECONDARY_VM_EXEC_CONTROL, SECONDARY_EXEC_SHADOW_VMCS); + secondary_exec_controls_clearbit(vmx, SECONDARY_EXEC_SHADOW_VMCS); vmcs_write64(VMCS_LINK_POINTER, -1ull); } @@ -238,22 +248,41 @@ static void free_nested(struct kvm_vcpu *vcpu) free_loaded_vmcs(&vmx->nested.vmcs02); } +static void vmx_sync_vmcs_host_state(struct vcpu_vmx *vmx, + struct loaded_vmcs *prev) +{ + struct vmcs_host_state *dest, *src; + + if (unlikely(!vmx->guest_state_loaded)) + return; + + src = &prev->host_state; + dest = &vmx->loaded_vmcs->host_state; + + vmx_set_host_fs_gs(dest, src->fs_sel, src->gs_sel, src->fs_base, src->gs_base); + dest->ldt_sel = src->ldt_sel; +#ifdef CONFIG_X86_64 + dest->ds_sel = src->ds_sel; + dest->es_sel = src->es_sel; +#endif +} + static void vmx_switch_vmcs(struct kvm_vcpu *vcpu, struct loaded_vmcs *vmcs) { struct vcpu_vmx *vmx = to_vmx(vcpu); + struct loaded_vmcs *prev; int cpu; if (vmx->loaded_vmcs == vmcs) return; cpu = get_cpu(); - vmx_vcpu_put(vcpu); + prev = vmx->loaded_vmcs; vmx->loaded_vmcs = vmcs; - vmx_vcpu_load(vcpu, cpu); + vmx_vcpu_load_vmcs(vcpu, cpu); + vmx_sync_vmcs_host_state(vmx, prev); put_cpu(); - vm_entry_controls_reset_shadow(vmx); - vm_exit_controls_reset_shadow(vmx); vmx_segment_cache_clear(vmx); } @@ -930,8 +959,7 @@ static int nested_vmx_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, bool ne * If PAE paging and EPT are both on, CR3 is not used by the CPU and * must not be dereferenced. */ - if (!is_long_mode(vcpu) && is_pae(vcpu) && is_paging(vcpu) && - !nested_ept) { + if (is_pae_paging(vcpu) && !nested_ept) { if (!load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3)) { *entry_failure_code = ENTRY_FAIL_PDPTE; return -EINVAL; @@ -1105,14 +1133,6 @@ static int vmx_restore_vmx_misc(struct vcpu_vmx *vmx, u64 data) vmx->nested.msrs.misc_low = data; vmx->nested.msrs.misc_high = data >> 32; - /* - * If L1 has read-only VM-exit information fields, use the - * less permissive vmx_vmwrite_bitmap to specify write - * permissions for the shadow VMCS. - */ - if (enable_shadow_vmcs && !nested_cpu_has_vmwrite_any_field(&vmx->vcpu)) - vmcs_write64(VMWRITE_BITMAP, __pa(vmx_vmwrite_bitmap)); - return 0; } @@ -1214,6 +1234,11 @@ int vmx_set_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data) case MSR_IA32_VMX_VMCS_ENUM: vmx->nested.msrs.vmcs_enum = data; return 0; + case MSR_IA32_VMX_VMFUNC: + if (data & ~vmx->nested.msrs.vmfunc_controls) + return -EINVAL; + vmx->nested.msrs.vmfunc_controls = data; + return 0; default: /* * The rest of the VMX capability MSRs do not support restore. @@ -1301,41 +1326,29 @@ int vmx_get_vmx_msr(struct nested_vmx_msrs *msrs, u32 msr_index, u64 *pdata) } /* - * Copy the writable VMCS shadow fields back to the VMCS12, in case - * they have been modified by the L1 guest. Note that the "read-only" - * VM-exit information fields are actually writable if the vCPU is - * configured to support "VMWRITE to any supported field in the VMCS." + * Copy the writable VMCS shadow fields back to the VMCS12, in case they have + * been modified by the L1 guest. Note, "writable" in this context means + * "writable by the guest", i.e. tagged SHADOW_FIELD_RW; the set of + * fields tagged SHADOW_FIELD_RO may or may not align with the "read-only" + * VM-exit information fields (which are actually writable if the vCPU is + * configured to support "VMWRITE to any supported field in the VMCS"). */ static void copy_shadow_to_vmcs12(struct vcpu_vmx *vmx) { - const u16 *fields[] = { - shadow_read_write_fields, - shadow_read_only_fields - }; - const int max_fields[] = { - max_shadow_read_write_fields, - max_shadow_read_only_fields - }; - int i, q; - unsigned long field; - u64 field_value; struct vmcs *shadow_vmcs = vmx->vmcs01.shadow_vmcs; + struct vmcs12 *vmcs12 = get_vmcs12(&vmx->vcpu); + struct shadow_vmcs_field field; + unsigned long val; + int i; preempt_disable(); vmcs_load(shadow_vmcs); - for (q = 0; q < ARRAY_SIZE(fields); q++) { - for (i = 0; i < max_fields[q]; i++) { - field = fields[q][i]; - field_value = __vmcs_readl(field); - vmcs12_write_any(get_vmcs12(&vmx->vcpu), field, field_value); - } - /* - * Skip the VM-exit information fields if they are read-only. - */ - if (!nested_cpu_has_vmwrite_any_field(&vmx->vcpu)) - break; + for (i = 0; i < max_shadow_read_write_fields; i++) { + field = shadow_read_write_fields[i]; + val = __vmcs_readl(field.encoding); + vmcs12_write_any(vmcs12, field.encoding, field.offset, val); } vmcs_clear(shadow_vmcs); @@ -1346,7 +1359,7 @@ static void copy_shadow_to_vmcs12(struct vcpu_vmx *vmx) static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx) { - const u16 *fields[] = { + const struct shadow_vmcs_field *fields[] = { shadow_read_write_fields, shadow_read_only_fields }; @@ -1354,18 +1367,20 @@ static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx) max_shadow_read_write_fields, max_shadow_read_only_fields }; - int i, q; - unsigned long field; - u64 field_value = 0; struct vmcs *shadow_vmcs = vmx->vmcs01.shadow_vmcs; + struct vmcs12 *vmcs12 = get_vmcs12(&vmx->vcpu); + struct shadow_vmcs_field field; + unsigned long val; + int i, q; vmcs_load(shadow_vmcs); for (q = 0; q < ARRAY_SIZE(fields); q++) { for (i = 0; i < max_fields[q]; i++) { field = fields[q][i]; - vmcs12_read_any(get_vmcs12(&vmx->vcpu), field, &field_value); - __vmcs_writel(field, field_value); + val = vmcs12_read_any(vmcs12, field.encoding, + field.offset); + __vmcs_writel(field.encoding, val); } } @@ -1623,7 +1638,7 @@ static int copy_vmcs12_to_enlightened(struct vcpu_vmx *vmx) * evmcs->host_gdtr_base = vmcs12->host_gdtr_base; * evmcs->host_idtr_base = vmcs12->host_idtr_base; * evmcs->host_rsp = vmcs12->host_rsp; - * sync_vmcs12() doesn't read these: + * sync_vmcs02_to_vmcs12() doesn't read these: * evmcs->io_bitmap_a = vmcs12->io_bitmap_a; * evmcs->io_bitmap_b = vmcs12->io_bitmap_b; * evmcs->msr_bitmap = vmcs12->msr_bitmap; @@ -1768,26 +1783,22 @@ static int nested_vmx_handle_enlightened_vmptrld(struct kvm_vcpu *vcpu, bool from_launch) { struct vcpu_vmx *vmx = to_vmx(vcpu); - struct hv_vp_assist_page assist_page; + bool evmcs_gpa_changed = false; + u64 evmcs_gpa; if (likely(!vmx->nested.enlightened_vmcs_enabled)) return 1; - if (unlikely(!kvm_hv_get_assist_page(vcpu, &assist_page))) - return 1; - - if (unlikely(!assist_page.enlighten_vmentry)) + if (!nested_enlightened_vmentry(vcpu, &evmcs_gpa)) return 1; - if (unlikely(assist_page.current_nested_vmcs != - vmx->nested.hv_evmcs_vmptr)) { - + if (unlikely(evmcs_gpa != vmx->nested.hv_evmcs_vmptr)) { if (!vmx->nested.hv_evmcs) vmx->nested.current_vmptr = -1ull; nested_release_evmcs(vcpu); - if (kvm_vcpu_map(vcpu, gpa_to_gfn(assist_page.current_nested_vmcs), + if (kvm_vcpu_map(vcpu, gpa_to_gfn(evmcs_gpa), &vmx->nested.hv_evmcs_map)) return 0; @@ -1822,15 +1833,9 @@ static int nested_vmx_handle_enlightened_vmptrld(struct kvm_vcpu *vcpu, } vmx->nested.dirty_vmcs12 = true; - /* - * As we keep L2 state for one guest only 'hv_clean_fields' mask - * can't be used when we switch between them. Reset it here for - * simplicity. - */ - vmx->nested.hv_evmcs->hv_clean_fields &= - ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL; - vmx->nested.hv_evmcs_vmptr = assist_page.current_nested_vmcs; + vmx->nested.hv_evmcs_vmptr = evmcs_gpa; + evmcs_gpa_changed = true; /* * Unlike normal vmcs12, enlightened vmcs12 is not fully * reloaded from guest's memory (read only fields, fields not @@ -1844,10 +1849,19 @@ static int nested_vmx_handle_enlightened_vmptrld(struct kvm_vcpu *vcpu, } } + + /* + * Clean fields data can't de used on VMLAUNCH and when we switch + * between different L2 guests as KVM keeps a single VMCS12 per L1. + */ + if (from_launch || evmcs_gpa_changed) + vmx->nested.hv_evmcs->hv_clean_fields &= + ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL; + return 1; } -void nested_sync_from_vmcs12(struct kvm_vcpu *vcpu) +void nested_sync_vmcs12_to_shadow(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -1868,7 +1882,7 @@ void nested_sync_from_vmcs12(struct kvm_vcpu *vcpu) copy_vmcs12_to_shadow(vmx); } - vmx->nested.need_vmcs12_sync = false; + vmx->nested.need_vmcs12_to_shadow_sync = false; } static enum hrtimer_restart vmx_preemption_timer_fn(struct hrtimer *timer) @@ -1948,8 +1962,20 @@ static void prepare_vmcs02_constant_state(struct vcpu_vmx *vmx) if (cpu_has_vmx_msr_bitmap()) vmcs_write64(MSR_BITMAP, __pa(vmx->nested.vmcs02.msr_bitmap)); - if (enable_pml) + /* + * The PML address never changes, so it is constant in vmcs02. + * Conceptually we want to copy the PML index from vmcs01 here, + * and then back to vmcs01 on nested vmexit. But since we flush + * the log and reset GUEST_PML_INDEX on each vmexit, the PML + * index is also effectively constant in vmcs02. + */ + if (enable_pml) { vmcs_write64(PML_ADDRESS, page_to_phys(vmx->pml_pg)); + vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1); + } + + if (cpu_has_vmx_encls_vmexit()) + vmcs_write64(ENCLS_EXITING_BITMAP, -1ull); /* * Set the MSR load/store lists to match L0's settings. Only the @@ -1963,7 +1989,7 @@ static void prepare_vmcs02_constant_state(struct vcpu_vmx *vmx) vmx_set_constant_host_state(vmx); } -static void prepare_vmcs02_early_full(struct vcpu_vmx *vmx, +static void prepare_vmcs02_early_rare(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) { prepare_vmcs02_constant_state(vmx); @@ -1984,17 +2010,14 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) u64 guest_efer = nested_vmx_calc_efer(vmx, vmcs12); if (vmx->nested.dirty_vmcs12 || vmx->nested.hv_evmcs) - prepare_vmcs02_early_full(vmx, vmcs12); + prepare_vmcs02_early_rare(vmx, vmcs12); /* * PIN CONTROLS */ - exec_control = vmcs12->pin_based_vm_exec_control; - - /* Preemption timer setting is computed directly in vmx_vcpu_run. */ - exec_control |= vmcs_config.pin_based_exec_ctrl; - exec_control &= ~PIN_BASED_VMX_PREEMPTION_TIMER; - vmx->loaded_vmcs->hv_timer_armed = false; + exec_control = vmx_pin_based_exec_ctrl(vmx); + exec_control |= (vmcs12->pin_based_vm_exec_control & + ~PIN_BASED_VMX_PREEMPTION_TIMER); /* Posted interrupts setting is only taken from vmcs12. */ if (nested_cpu_has_posted_intr(vmcs12)) { @@ -2003,7 +2026,7 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) } else { exec_control &= ~PIN_BASED_POSTED_INTR; } - vmcs_write32(PIN_BASED_VM_EXEC_CONTROL, exec_control); + pin_controls_set(vmx, exec_control); /* * EXEC CONTROLS @@ -2014,28 +2037,31 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) exec_control &= ~CPU_BASED_TPR_SHADOW; exec_control |= vmcs12->cpu_based_vm_exec_control; - /* - * Write an illegal value to VIRTUAL_APIC_PAGE_ADDR. Later, if - * nested_get_vmcs12_pages can't fix it up, the illegal value - * will result in a VM entry failure. - */ - if (exec_control & CPU_BASED_TPR_SHADOW) { - vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, -1ull); + if (exec_control & CPU_BASED_TPR_SHADOW) vmcs_write32(TPR_THRESHOLD, vmcs12->tpr_threshold); - } else { #ifdef CONFIG_X86_64 + else exec_control |= CPU_BASED_CR8_LOAD_EXITING | CPU_BASED_CR8_STORE_EXITING; #endif - } /* * A vmexit (to either L1 hypervisor or L0 userspace) is always needed * for I/O port accesses. */ - exec_control &= ~CPU_BASED_USE_IO_BITMAPS; exec_control |= CPU_BASED_UNCOND_IO_EXITING; - vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, exec_control); + exec_control &= ~CPU_BASED_USE_IO_BITMAPS; + + /* + * This bit will be computed in nested_get_vmcs12_pages, because + * we do not have access to L1's MSR bitmap yet. For now, keep + * the same bit as before, hoping to avoid multiple VMWRITEs that + * only set/clear this bit. + */ + exec_control &= ~CPU_BASED_USE_MSR_BITMAPS; + exec_control |= exec_controls_get(vmx) & CPU_BASED_USE_MSR_BITMAPS; + + exec_controls_set(vmx, exec_control); /* * SECONDARY EXEC CONTROLS @@ -2061,22 +2087,19 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) /* VMCS shadowing for L2 is emulated for now */ exec_control &= ~SECONDARY_EXEC_SHADOW_VMCS; - if (exec_control & SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY) - vmcs_write16(GUEST_INTR_STATUS, - vmcs12->guest_intr_status); - /* - * Write an illegal value to APIC_ACCESS_ADDR. Later, - * nested_get_vmcs12_pages will either fix it up or - * remove the VM execution control. + * Preset *DT exiting when emulating UMIP, so that vmx_set_cr4() + * will not have to rewrite the controls just for this bit. */ - if (exec_control & SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES) - vmcs_write64(APIC_ACCESS_ADDR, -1ull); + if (!boot_cpu_has(X86_FEATURE_UMIP) && vmx_umip_emulated() && + (vmcs12->guest_cr4 & X86_CR4_UMIP)) + exec_control |= SECONDARY_EXEC_DESC; - if (exec_control & SECONDARY_EXEC_ENCLS_EXITING) - vmcs_write64(ENCLS_EXITING_BITMAP, -1ull); + if (exec_control & SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY) + vmcs_write16(GUEST_INTR_STATUS, + vmcs12->guest_intr_status); - vmcs_write32(SECONDARY_VM_EXEC_CONTROL, exec_control); + secondary_exec_controls_set(vmx, exec_control); } /* @@ -2095,7 +2118,7 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) if (guest_efer != host_efer) exec_control |= VM_ENTRY_LOAD_IA32_EFER; } - vm_entry_controls_init(vmx, exec_control); + vm_entry_controls_set(vmx, exec_control); /* * EXIT CONTROLS @@ -2107,17 +2130,7 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) exec_control = vmx_vmexit_ctrl(); if (cpu_has_load_ia32_efer() && guest_efer != host_efer) exec_control |= VM_EXIT_LOAD_IA32_EFER; - vm_exit_controls_init(vmx, exec_control); - - /* - * Conceptually we want to copy the PML address and index from - * vmcs01 here, and then back to vmcs01 on nested vmexit. But, - * since we always flush the log on each vmexit and never change - * the PML address (once set), this happens to be equivalent to - * simply resetting the index in vmcs02. - */ - if (enable_pml) - vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1); + vm_exit_controls_set(vmx, exec_control); /* * Interrupt/Exception Fields @@ -2138,7 +2151,7 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) } } -static void prepare_vmcs02_full(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) +static void prepare_vmcs02_rare(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) { struct hv_enlightened_vmcs *hv_evmcs = vmx->nested.hv_evmcs; @@ -2162,6 +2175,8 @@ static void prepare_vmcs02_full(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) vmcs_write32(GUEST_TR_LIMIT, vmcs12->guest_tr_limit); vmcs_write32(GUEST_GDTR_LIMIT, vmcs12->guest_gdtr_limit); vmcs_write32(GUEST_IDTR_LIMIT, vmcs12->guest_idtr_limit); + vmcs_write32(GUEST_CS_AR_BYTES, vmcs12->guest_cs_ar_bytes); + vmcs_write32(GUEST_SS_AR_BYTES, vmcs12->guest_ss_ar_bytes); vmcs_write32(GUEST_ES_AR_BYTES, vmcs12->guest_es_ar_bytes); vmcs_write32(GUEST_DS_AR_BYTES, vmcs12->guest_ds_ar_bytes); vmcs_write32(GUEST_FS_AR_BYTES, vmcs12->guest_fs_ar_bytes); @@ -2198,6 +2213,10 @@ static void prepare_vmcs02_full(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) vmcs_write64(GUEST_PDPTR2, vmcs12->guest_pdptr2); vmcs_write64(GUEST_PDPTR3, vmcs12->guest_pdptr3); } + + if (kvm_mpx_supported() && vmx->nested.nested_run_pending && + (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS)) + vmcs_write64(GUEST_BNDCFGS, vmcs12->guest_bndcfgs); } if (nested_cpu_has_xsaves(vmcs12)) @@ -2233,14 +2252,6 @@ static void prepare_vmcs02_full(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr); set_cr4_guest_host_mask(vmx); - - 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); - } } /* @@ -2259,20 +2270,15 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, { struct vcpu_vmx *vmx = to_vmx(vcpu); struct hv_enlightened_vmcs *hv_evmcs = vmx->nested.hv_evmcs; + bool load_guest_pdptrs_vmcs12 = false; - if (vmx->nested.dirty_vmcs12 || vmx->nested.hv_evmcs) { - prepare_vmcs02_full(vmx, vmcs12); + if (vmx->nested.dirty_vmcs12 || hv_evmcs) { + prepare_vmcs02_rare(vmx, vmcs12); vmx->nested.dirty_vmcs12 = false; - } - /* - * First, the fields that are shadowed. This must be kept in sync - * with vmcs_shadow_fields.h. - */ - if (!hv_evmcs || !(hv_evmcs->hv_clean_fields & - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2)) { - vmcs_write32(GUEST_CS_AR_BYTES, vmcs12->guest_cs_ar_bytes); - vmcs_write32(GUEST_SS_AR_BYTES, vmcs12->guest_ss_ar_bytes); + load_guest_pdptrs_vmcs12 = !hv_evmcs || + !(hv_evmcs->hv_clean_fields & + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1); } if (vmx->nested.nested_run_pending && @@ -2283,6 +2289,9 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, kvm_set_dr(vcpu, 7, vcpu->arch.dr7); vmcs_write64(GUEST_IA32_DEBUGCTL, vmx->nested.vmcs01_debugctl); } + if (kvm_mpx_supported() && (!vmx->nested.nested_run_pending || + !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS))) + vmcs_write64(GUEST_BNDCFGS, vmx->nested.vmcs01_guest_bndcfgs); vmx_set_rflags(vcpu, vmcs12->guest_rflags); /* EXCEPTION_BITMAP and CR0_GUEST_HOST_MASK should basically be the @@ -2372,6 +2381,15 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, entry_failure_code)) return -EINVAL; + /* Late preparation of GUEST_PDPTRs now that EFER and CRs are set. */ + if (load_guest_pdptrs_vmcs12 && nested_cpu_has_ept(vmcs12) && + is_pae_paging(vcpu)) { + vmcs_write64(GUEST_PDPTR0, vmcs12->guest_pdptr0); + vmcs_write64(GUEST_PDPTR1, vmcs12->guest_pdptr1); + vmcs_write64(GUEST_PDPTR2, vmcs12->guest_pdptr2); + vmcs_write64(GUEST_PDPTR3, vmcs12->guest_pdptr3); + } + if (!enable_ept) vcpu->arch.walk_mmu->inject_page_fault = vmx_inject_page_fault_nested; @@ -2609,6 +2627,30 @@ static int nested_vmx_check_host_state(struct kvm_vcpu *vcpu, !kvm_pat_valid(vmcs12->host_ia32_pat)) return -EINVAL; + ia32e = (vmcs12->vm_exit_controls & + VM_EXIT_HOST_ADDR_SPACE_SIZE) != 0; + + if (vmcs12->host_cs_selector & (SEGMENT_RPL_MASK | SEGMENT_TI_MASK) || + vmcs12->host_ss_selector & (SEGMENT_RPL_MASK | SEGMENT_TI_MASK) || + vmcs12->host_ds_selector & (SEGMENT_RPL_MASK | SEGMENT_TI_MASK) || + vmcs12->host_es_selector & (SEGMENT_RPL_MASK | SEGMENT_TI_MASK) || + vmcs12->host_fs_selector & (SEGMENT_RPL_MASK | SEGMENT_TI_MASK) || + vmcs12->host_gs_selector & (SEGMENT_RPL_MASK | SEGMENT_TI_MASK) || + vmcs12->host_tr_selector & (SEGMENT_RPL_MASK | SEGMENT_TI_MASK) || + vmcs12->host_cs_selector == 0 || + vmcs12->host_tr_selector == 0 || + (vmcs12->host_ss_selector == 0 && !ia32e)) + return -EINVAL; + +#ifdef CONFIG_X86_64 + if (is_noncanonical_address(vmcs12->host_fs_base, vcpu) || + is_noncanonical_address(vmcs12->host_gs_base, vcpu) || + is_noncanonical_address(vmcs12->host_gdtr_base, vcpu) || + is_noncanonical_address(vmcs12->host_idtr_base, vcpu) || + is_noncanonical_address(vmcs12->host_tr_base, vcpu)) + return -EINVAL; +#endif + /* * If the load IA32_EFER VM-exit control is 1, bits reserved in the * IA32_EFER MSR must be 0 in the field for that register. In addition, @@ -2616,8 +2658,6 @@ static int nested_vmx_check_host_state(struct kvm_vcpu *vcpu, * the host address-space size VM-exit control. */ if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_EFER) { - ia32e = (vmcs12->vm_exit_controls & - VM_EXIT_HOST_ADDR_SPACE_SIZE) != 0; if (!kvm_valid_efer(vcpu, vmcs12->host_ia32_efer) || ia32e != !!(vmcs12->host_ia32_efer & EFER_LMA) || ia32e != !!(vmcs12->host_ia32_efer & EFER_LME)) @@ -2781,7 +2821,7 @@ static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu) [launched]"i"(offsetof(struct loaded_vmcs, launched)), [host_state_rsp]"i"(offsetof(struct loaded_vmcs, host_state.rsp)), [wordsize]"i"(sizeof(ulong)) - : "cc", "memory" + : "memory" ); if (vmx->msr_autoload.host.nr) @@ -2851,18 +2891,14 @@ static void nested_get_vmcs12_pages(struct kvm_vcpu *vcpu) hpa = page_to_phys(vmx->nested.apic_access_page); vmcs_write64(APIC_ACCESS_ADDR, hpa); } else { - vmcs_clear_bits(SECONDARY_VM_EXEC_CONTROL, - SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES); + secondary_exec_controls_clearbit(vmx, + SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES); } } if (nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW)) { map = &vmx->nested.virtual_apic_map; - /* - * If translation failed, VM entry will fail because - * prepare_vmcs02 set VIRTUAL_APIC_PAGE_ADDR to -1ull. - */ if (!kvm_vcpu_map(vcpu, gpa_to_gfn(vmcs12->virtual_apic_page_addr), map)) { vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, pfn_to_hpa(map->pfn)); } else if (nested_cpu_has(vmcs12, CPU_BASED_CR8_LOAD_EXITING) && @@ -2876,11 +2912,13 @@ static void nested_get_vmcs12_pages(struct kvm_vcpu *vcpu) * _not_ what the processor does but it's basically the * only possibility we have. */ - vmcs_clear_bits(CPU_BASED_VM_EXEC_CONTROL, - CPU_BASED_TPR_SHADOW); + exec_controls_clearbit(vmx, CPU_BASED_TPR_SHADOW); } else { - printk("bad virtual-APIC page address\n"); - dump_vmcs(); + /* + * Write an illegal value to VIRTUAL_APIC_PAGE_ADDR to + * force VM-Entry to fail. + */ + vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, -1ull); } } @@ -2896,11 +2934,9 @@ static void nested_get_vmcs12_pages(struct kvm_vcpu *vcpu) } } if (nested_vmx_prepare_msr_bitmap(vcpu, vmcs12)) - vmcs_set_bits(CPU_BASED_VM_EXEC_CONTROL, - CPU_BASED_USE_MSR_BITMAPS); + exec_controls_setbit(vmx, CPU_BASED_USE_MSR_BITMAPS); else - vmcs_clear_bits(CPU_BASED_VM_EXEC_CONTROL, - CPU_BASED_USE_MSR_BITMAPS); + exec_controls_clearbit(vmx, CPU_BASED_USE_MSR_BITMAPS); } /* @@ -2953,7 +2989,7 @@ int nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry) u32 exit_reason = EXIT_REASON_INVALID_STATE; u32 exit_qual; - evaluate_pending_interrupts = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL) & + evaluate_pending_interrupts = exec_controls_get(vmx) & (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); @@ -2964,6 +3000,25 @@ int nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry) !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS)) vmx->nested.vmcs01_guest_bndcfgs = vmcs_read64(GUEST_BNDCFGS); + /* + * Overwrite vmcs01.GUEST_CR3 with L1's CR3 if EPT is disabled *and* + * nested early checks are disabled. In the event of a "late" VM-Fail, + * i.e. a VM-Fail detected by hardware but not KVM, KVM must unwind its + * software model to the pre-VMEntry host state. When EPT is disabled, + * GUEST_CR3 holds KVM's shadow CR3, not L1's "real" CR3, which causes + * nested_vmx_restore_host_state() to corrupt vcpu->arch.cr3. Stuffing + * vmcs01.GUEST_CR3 results in the unwind naturally setting arch.cr3 to + * the correct value. Smashing vmcs01.GUEST_CR3 is safe because nested + * VM-Exits, and the unwind, reset KVM's MMU, i.e. vmcs01.GUEST_CR3 is + * guaranteed to be overwritten with a shadow CR3 prior to re-entering + * L1. Don't stuff vmcs01.GUEST_CR3 when using nested early checks as + * KVM modifies vcpu->arch.cr3 if and only if the early hardware checks + * pass, and early VM-Fails do not reset KVM's MMU, i.e. the VM-Fail + * path would need to manually save/restore vmcs01.GUEST_CR3. + */ + if (!enable_ept && !nested_early_check) + vmcs_writel(GUEST_CR3, vcpu->arch.cr3); + vmx_switch_vmcs(vcpu, &vmx->nested.vmcs02); prepare_vmcs02_early(vmx, vmcs12); @@ -3059,7 +3114,7 @@ vmentry_fail_vmexit: vmcs12->vm_exit_reason = exit_reason | VMX_EXIT_REASONS_FAILED_VMENTRY; vmcs12->exit_qualification = exit_qual; if (enable_shadow_vmcs || vmx->nested.hv_evmcs) - vmx->nested.need_vmcs12_sync = true; + vmx->nested.need_vmcs12_to_shadow_sync = true; return 1; } @@ -3077,7 +3132,7 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) if (!nested_vmx_check_permission(vcpu)) return 1; - if (!nested_vmx_handle_enlightened_vmptrld(vcpu, true)) + if (!nested_vmx_handle_enlightened_vmptrld(vcpu, launch)) return 1; if (!vmx->nested.hv_evmcs && vmx->nested.current_vmptr == -1ull) @@ -3393,20 +3448,57 @@ static u32 vmx_get_preemption_timer_value(struct kvm_vcpu *vcpu) return value >> VMX_MISC_EMULATED_PREEMPTION_TIMER_RATE; } -/* - * Update the guest state fields of vmcs12 to reflect changes that - * occurred while L2 was running. (The "IA-32e mode guest" bit of the - * VM-entry controls is also updated, since this is really a guest - * state bit.) - */ -static void sync_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) -{ - vmcs12->guest_cr0 = vmcs12_guest_cr0(vcpu, vmcs12); - vmcs12->guest_cr4 = vmcs12_guest_cr4(vcpu, vmcs12); +static bool is_vmcs12_ext_field(unsigned long field) +{ + switch (field) { + case GUEST_ES_SELECTOR: + case GUEST_CS_SELECTOR: + case GUEST_SS_SELECTOR: + case GUEST_DS_SELECTOR: + case GUEST_FS_SELECTOR: + case GUEST_GS_SELECTOR: + case GUEST_LDTR_SELECTOR: + case GUEST_TR_SELECTOR: + case GUEST_ES_LIMIT: + case GUEST_CS_LIMIT: + case GUEST_SS_LIMIT: + case GUEST_DS_LIMIT: + case GUEST_FS_LIMIT: + case GUEST_GS_LIMIT: + case GUEST_LDTR_LIMIT: + case GUEST_TR_LIMIT: + case GUEST_GDTR_LIMIT: + case GUEST_IDTR_LIMIT: + case GUEST_ES_AR_BYTES: + case GUEST_DS_AR_BYTES: + case GUEST_FS_AR_BYTES: + case GUEST_GS_AR_BYTES: + case GUEST_LDTR_AR_BYTES: + case GUEST_TR_AR_BYTES: + case GUEST_ES_BASE: + case GUEST_CS_BASE: + case GUEST_SS_BASE: + case GUEST_DS_BASE: + case GUEST_FS_BASE: + case GUEST_GS_BASE: + case GUEST_LDTR_BASE: + case GUEST_TR_BASE: + case GUEST_GDTR_BASE: + case GUEST_IDTR_BASE: + case GUEST_PENDING_DBG_EXCEPTIONS: + case GUEST_BNDCFGS: + return true; + default: + break; + } - vmcs12->guest_rsp = kvm_rsp_read(vcpu); - vmcs12->guest_rip = kvm_rip_read(vcpu); - vmcs12->guest_rflags = vmcs_readl(GUEST_RFLAGS); + return false; +} + +static void sync_vmcs02_to_vmcs12_rare(struct kvm_vcpu *vcpu, + struct vmcs12 *vmcs12) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); vmcs12->guest_es_selector = vmcs_read16(GUEST_ES_SELECTOR); vmcs12->guest_cs_selector = vmcs_read16(GUEST_CS_SELECTOR); @@ -3427,8 +3519,6 @@ static void sync_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) vmcs12->guest_gdtr_limit = vmcs_read32(GUEST_GDTR_LIMIT); vmcs12->guest_idtr_limit = vmcs_read32(GUEST_IDTR_LIMIT); vmcs12->guest_es_ar_bytes = vmcs_read32(GUEST_ES_AR_BYTES); - vmcs12->guest_cs_ar_bytes = vmcs_read32(GUEST_CS_AR_BYTES); - vmcs12->guest_ss_ar_bytes = vmcs_read32(GUEST_SS_AR_BYTES); vmcs12->guest_ds_ar_bytes = vmcs_read32(GUEST_DS_AR_BYTES); vmcs12->guest_fs_ar_bytes = vmcs_read32(GUEST_FS_AR_BYTES); vmcs12->guest_gs_ar_bytes = vmcs_read32(GUEST_GS_AR_BYTES); @@ -3444,11 +3534,69 @@ static void sync_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) vmcs12->guest_tr_base = vmcs_readl(GUEST_TR_BASE); vmcs12->guest_gdtr_base = vmcs_readl(GUEST_GDTR_BASE); vmcs12->guest_idtr_base = vmcs_readl(GUEST_IDTR_BASE); + vmcs12->guest_pending_dbg_exceptions = + vmcs_readl(GUEST_PENDING_DBG_EXCEPTIONS); + if (kvm_mpx_supported()) + vmcs12->guest_bndcfgs = vmcs_read64(GUEST_BNDCFGS); + + vmx->nested.need_sync_vmcs02_to_vmcs12_rare = false; +} + +static void copy_vmcs02_to_vmcs12_rare(struct kvm_vcpu *vcpu, + struct vmcs12 *vmcs12) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + int cpu; + + if (!vmx->nested.need_sync_vmcs02_to_vmcs12_rare) + return; + + + WARN_ON_ONCE(vmx->loaded_vmcs != &vmx->vmcs01); + + cpu = get_cpu(); + vmx->loaded_vmcs = &vmx->nested.vmcs02; + vmx_vcpu_load(&vmx->vcpu, cpu); + + sync_vmcs02_to_vmcs12_rare(vcpu, vmcs12); + + vmx->loaded_vmcs = &vmx->vmcs01; + vmx_vcpu_load(&vmx->vcpu, cpu); + put_cpu(); +} + +/* + * Update the guest state fields of vmcs12 to reflect changes that + * occurred while L2 was running. (The "IA-32e mode guest" bit of the + * VM-entry controls is also updated, since this is really a guest + * state bit.) + */ +static void sync_vmcs02_to_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + + if (vmx->nested.hv_evmcs) + sync_vmcs02_to_vmcs12_rare(vcpu, vmcs12); + + vmx->nested.need_sync_vmcs02_to_vmcs12_rare = !vmx->nested.hv_evmcs; + + vmcs12->guest_cr0 = vmcs12_guest_cr0(vcpu, vmcs12); + vmcs12->guest_cr4 = vmcs12_guest_cr4(vcpu, vmcs12); + + vmcs12->guest_rsp = kvm_rsp_read(vcpu); + vmcs12->guest_rip = kvm_rip_read(vcpu); + vmcs12->guest_rflags = vmcs_readl(GUEST_RFLAGS); + + vmcs12->guest_cs_ar_bytes = vmcs_read32(GUEST_CS_AR_BYTES); + vmcs12->guest_ss_ar_bytes = vmcs_read32(GUEST_SS_AR_BYTES); + + vmcs12->guest_sysenter_cs = vmcs_read32(GUEST_SYSENTER_CS); + vmcs12->guest_sysenter_esp = vmcs_readl(GUEST_SYSENTER_ESP); + vmcs12->guest_sysenter_eip = vmcs_readl(GUEST_SYSENTER_EIP); vmcs12->guest_interruptibility_info = vmcs_read32(GUEST_INTERRUPTIBILITY_INFO); - vmcs12->guest_pending_dbg_exceptions = - vmcs_readl(GUEST_PENDING_DBG_EXCEPTIONS); + if (vcpu->arch.mp_state == KVM_MP_STATE_HALTED) vmcs12->guest_activity_state = GUEST_ACTIVITY_HLT; else @@ -3469,10 +3617,12 @@ static void sync_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) */ if (enable_ept) { vmcs12->guest_cr3 = vmcs_readl(GUEST_CR3); - vmcs12->guest_pdptr0 = vmcs_read64(GUEST_PDPTR0); - vmcs12->guest_pdptr1 = vmcs_read64(GUEST_PDPTR1); - vmcs12->guest_pdptr2 = vmcs_read64(GUEST_PDPTR2); - vmcs12->guest_pdptr3 = vmcs_read64(GUEST_PDPTR3); + if (nested_cpu_has_ept(vmcs12) && is_pae_paging(vcpu)) { + vmcs12->guest_pdptr0 = vmcs_read64(GUEST_PDPTR0); + vmcs12->guest_pdptr1 = vmcs_read64(GUEST_PDPTR1); + vmcs12->guest_pdptr2 = vmcs_read64(GUEST_PDPTR2); + vmcs12->guest_pdptr3 = vmcs_read64(GUEST_PDPTR3); + } } vmcs12->guest_linear_address = vmcs_readl(GUEST_LINEAR_ADDRESS); @@ -3484,22 +3634,11 @@ static void sync_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) (vmcs12->vm_entry_controls & ~VM_ENTRY_IA32E_MODE) | (vm_entry_controls_get(to_vmx(vcpu)) & VM_ENTRY_IA32E_MODE); - if (vmcs12->vm_exit_controls & VM_EXIT_SAVE_DEBUG_CONTROLS) { + if (vmcs12->vm_exit_controls & VM_EXIT_SAVE_DEBUG_CONTROLS) kvm_get_dr(vcpu, 7, (unsigned long *)&vmcs12->guest_dr7); - vmcs12->guest_ia32_debugctl = vmcs_read64(GUEST_IA32_DEBUGCTL); - } - /* TODO: These cannot have changed unless we have MSR bitmaps and - * the relevant bit asks not to trap the change */ - if (vmcs12->vm_exit_controls & VM_EXIT_SAVE_IA32_PAT) - vmcs12->guest_ia32_pat = vmcs_read64(GUEST_IA32_PAT); if (vmcs12->vm_exit_controls & VM_EXIT_SAVE_IA32_EFER) vmcs12->guest_ia32_efer = vcpu->arch.efer; - vmcs12->guest_sysenter_cs = vmcs_read32(GUEST_SYSENTER_CS); - vmcs12->guest_sysenter_esp = vmcs_readl(GUEST_SYSENTER_ESP); - vmcs12->guest_sysenter_eip = vmcs_readl(GUEST_SYSENTER_EIP); - if (kvm_mpx_supported()) - vmcs12->guest_bndcfgs = vmcs_read64(GUEST_BNDCFGS); } /* @@ -3517,11 +3656,7 @@ static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, u32 exit_reason, u32 exit_intr_info, unsigned long exit_qualification) { - /* update guest state fields: */ - sync_vmcs12(vcpu, vmcs12); - /* update exit information fields: */ - vmcs12->vm_exit_reason = exit_reason; vmcs12->exit_qualification = exit_qualification; vmcs12->vm_exit_intr_info = exit_intr_info; @@ -3775,18 +3910,8 @@ static void nested_vmx_restore_host_state(struct kvm_vcpu *vcpu) vmx_set_cr4(vcpu, vmcs_readl(CR4_READ_SHADOW)); nested_ept_uninit_mmu_context(vcpu); - - /* - * This is only valid if EPT is in use, otherwise the vmcs01 GUEST_CR3 - * points to shadow pages! Fortunately we only get here after a WARN_ON - * if EPT is disabled, so a VMabort is perfectly fine. - */ - if (enable_ept) { - vcpu->arch.cr3 = vmcs_readl(GUEST_CR3); - __set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail); - } else { - nested_vmx_abort(vcpu, VMX_ABORT_VMCS_CORRUPTED); - } + vcpu->arch.cr3 = vmcs_readl(GUEST_CR3); + __set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail); /* * Use ept_save_pdptrs(vcpu) to load the MMU's cached PDPTRs @@ -3794,7 +3919,8 @@ static void nested_vmx_restore_host_state(struct kvm_vcpu *vcpu) * VMFail, like everything else we just need to ensure our * software model is up-to-date. */ - ept_save_pdptrs(vcpu); + if (enable_ept) + ept_save_pdptrs(vcpu); kvm_mmu_reset_context(vcpu); @@ -3882,14 +4008,14 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, vcpu->arch.tsc_offset -= vmcs12->tsc_offset; if (likely(!vmx->fail)) { - if (exit_reason == -1) - sync_vmcs12(vcpu, vmcs12); - else + sync_vmcs02_to_vmcs12(vcpu, vmcs12); + + if (exit_reason != -1) prepare_vmcs12(vcpu, vmcs12, exit_reason, exit_intr_info, exit_qualification); /* - * Must happen outside of sync_vmcs12() as it will + * Must happen outside of sync_vmcs02_to_vmcs12() as it will * also be used to capture vmcs12 cache as part of * capturing nVMX state for snapshot (migration). * @@ -3945,7 +4071,7 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, kvm_make_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu); if ((exit_reason != -1) && (enable_shadow_vmcs || vmx->nested.hv_evmcs)) - vmx->nested.need_vmcs12_sync = true; + vmx->nested.need_vmcs12_to_shadow_sync = true; /* in case we halted in L2 */ vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; @@ -4008,7 +4134,7 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, * #UD or #GP. */ int get_vmx_mem_address(struct kvm_vcpu *vcpu, unsigned long exit_qualification, - u32 vmx_instruction_info, bool wr, gva_t *ret) + u32 vmx_instruction_info, bool wr, int len, gva_t *ret) { gva_t off; bool exn; @@ -4115,7 +4241,7 @@ int get_vmx_mem_address(struct kvm_vcpu *vcpu, unsigned long exit_qualification, */ if (!(s.base == 0 && s.limit == 0xffffffff && ((s.type & 8) || !(s.type & 4)))) - exn = exn || (off + sizeof(u64) > s.limit); + exn = exn || ((u64)off + len - 1 > s.limit); } if (exn) { kvm_queue_exception_e(vcpu, @@ -4134,7 +4260,8 @@ static int nested_vmx_get_vmptr(struct kvm_vcpu *vcpu, gpa_t *vmpointer) struct x86_exception e; if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION), - vmcs_read32(VMX_INSTRUCTION_INFO), false, &gva)) + vmcs_read32(VMX_INSTRUCTION_INFO), false, + sizeof(*vmpointer), &gva)) return 1; if (kvm_read_guest_virt(vcpu, gva, vmpointer, sizeof(*vmpointer), &e)) { @@ -4300,11 +4427,13 @@ static inline void nested_release_vmcs12(struct kvm_vcpu *vcpu) if (vmx->nested.current_vmptr == -1ull) return; + copy_vmcs02_to_vmcs12_rare(vcpu, get_vmcs12(vcpu)); + if (enable_shadow_vmcs) { /* copy to memory all shadowed fields in case they were modified */ copy_shadow_to_vmcs12(vmx); - vmx->nested.need_vmcs12_sync = false; + vmx->nested.need_vmcs12_to_shadow_sync = false; vmx_disable_shadow_vmcs(vmx); } vmx->nested.posted_intr_nv = -1; @@ -4334,6 +4463,7 @@ static int handle_vmclear(struct kvm_vcpu *vcpu) struct vcpu_vmx *vmx = to_vmx(vcpu); u32 zero = 0; gpa_t vmptr; + u64 evmcs_gpa; if (!nested_vmx_check_permission(vcpu)) return 1; @@ -4349,10 +4479,18 @@ static int handle_vmclear(struct kvm_vcpu *vcpu) return nested_vmx_failValid(vcpu, VMXERR_VMCLEAR_VMXON_POINTER); - if (vmx->nested.hv_evmcs_map.hva) { - if (vmptr == vmx->nested.hv_evmcs_vmptr) - nested_release_evmcs(vcpu); - } else { + /* + * When Enlightened VMEntry is enabled on the calling CPU we treat + * memory area pointer by vmptr as Enlightened VMCS (as there's no good + * way to distinguish it from VMCS12) and we must not corrupt it by + * writing to the non-existent 'launch_state' field. The area doesn't + * have to be the currently active EVMCS on the calling CPU and there's + * nothing KVM has to do to transition it from 'active' to 'non-active' + * state. It is possible that the area will stay mapped as + * vmx->nested.hv_evmcs but this shouldn't be a problem. + */ + if (likely(!vmx->nested.enlightened_vmcs_enabled || + !nested_enlightened_vmentry(vcpu, &evmcs_gpa))) { if (vmptr == vmx->nested.current_vmptr) nested_release_vmcs12(vcpu); @@ -4386,8 +4524,10 @@ static int handle_vmread(struct kvm_vcpu *vcpu) u64 field_value; unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION); u32 vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO); + int len; gva_t gva = 0; struct vmcs12 *vmcs12; + short offset; if (!nested_vmx_check_permission(vcpu)) return 1; @@ -4409,11 +4549,18 @@ static int handle_vmread(struct kvm_vcpu *vcpu) /* Decode instruction info and find the field to read */ field = kvm_register_readl(vcpu, (((vmx_instruction_info) >> 28) & 0xf)); - /* Read the field, zero-extended to a u64 field_value */ - if (vmcs12_read_any(vmcs12, field, &field_value) < 0) + + offset = vmcs_field_to_offset(field); + if (offset < 0) return nested_vmx_failValid(vcpu, VMXERR_UNSUPPORTED_VMCS_COMPONENT); + if (!is_guest_mode(vcpu) && is_vmcs12_ext_field(field)) + copy_vmcs02_to_vmcs12_rare(vcpu, vmcs12); + + /* Read the field, zero-extended to a u64 field_value */ + field_value = vmcs12_read_any(vmcs12, field, offset); + /* * Now copy part of this value to register or memory, as requested. * Note that the number of bits actually copied is 32 or 64 depending @@ -4423,21 +4570,45 @@ static int handle_vmread(struct kvm_vcpu *vcpu) kvm_register_writel(vcpu, (((vmx_instruction_info) >> 3) & 0xf), field_value); } else { + len = is_64_bit_mode(vcpu) ? 8 : 4; if (get_vmx_mem_address(vcpu, exit_qualification, - vmx_instruction_info, true, &gva)) + vmx_instruction_info, true, len, &gva)) return 1; /* _system ok, nested_vmx_check_permission has verified cpl=0 */ - kvm_write_guest_virt_system(vcpu, gva, &field_value, - (is_long_mode(vcpu) ? 8 : 4), NULL); + kvm_write_guest_virt_system(vcpu, gva, &field_value, len, NULL); } return nested_vmx_succeed(vcpu); } +static bool is_shadow_field_rw(unsigned long field) +{ + switch (field) { +#define SHADOW_FIELD_RW(x, y) case x: +#include "vmcs_shadow_fields.h" + return true; + default: + break; + } + return false; +} + +static bool is_shadow_field_ro(unsigned long field) +{ + switch (field) { +#define SHADOW_FIELD_RO(x, y) case x: +#include "vmcs_shadow_fields.h" + return true; + default: + break; + } + return false; +} static int handle_vmwrite(struct kvm_vcpu *vcpu) { unsigned long field; + int len; gva_t gva; struct vcpu_vmx *vmx = to_vmx(vcpu); unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION); @@ -4452,6 +4623,7 @@ static int handle_vmwrite(struct kvm_vcpu *vcpu) u64 field_value = 0; struct x86_exception e; struct vmcs12 *vmcs12; + short offset; if (!nested_vmx_check_permission(vcpu)) return 1; @@ -4463,11 +4635,11 @@ static int handle_vmwrite(struct kvm_vcpu *vcpu) field_value = kvm_register_readl(vcpu, (((vmx_instruction_info) >> 3) & 0xf)); else { + len = is_64_bit_mode(vcpu) ? 8 : 4; if (get_vmx_mem_address(vcpu, exit_qualification, - vmx_instruction_info, false, &gva)) + vmx_instruction_info, false, len, &gva)) return 1; - if (kvm_read_guest_virt(vcpu, gva, &field_value, - (is_64_bit_mode(vcpu) ? 8 : 4), &e)) { + if (kvm_read_guest_virt(vcpu, gva, &field_value, len, &e)) { kvm_inject_page_fault(vcpu, &e); return 1; } @@ -4484,9 +4656,16 @@ static int handle_vmwrite(struct kvm_vcpu *vcpu) return nested_vmx_failValid(vcpu, VMXERR_VMWRITE_READ_ONLY_VMCS_COMPONENT); - if (!is_guest_mode(vcpu)) + if (!is_guest_mode(vcpu)) { vmcs12 = get_vmcs12(vcpu); - else { + + /* + * Ensure vmcs12 is up-to-date before any VMWRITE that dirties + * vmcs12, else we may crush a field or consume a stale value. + */ + if (!is_shadow_field_rw(field)) + copy_vmcs02_to_vmcs12_rare(vcpu, vmcs12); + } else { /* * When vmcs->vmcs_link_pointer is -1ull, any VMWRITE * to shadowed-field sets the ALU flags for VMfailInvalid. @@ -4496,28 +4675,46 @@ static int handle_vmwrite(struct kvm_vcpu *vcpu) vmcs12 = get_shadow_vmcs12(vcpu); } - if (vmcs12_write_any(vmcs12, field, field_value) < 0) + offset = vmcs_field_to_offset(field); + if (offset < 0) return nested_vmx_failValid(vcpu, VMXERR_UNSUPPORTED_VMCS_COMPONENT); /* - * Do not track vmcs12 dirty-state if in guest-mode - * as we actually dirty shadow vmcs12 instead of vmcs12. + * Some Intel CPUs intentionally drop the reserved bits of the AR byte + * fields on VMWRITE. Emulate this behavior to ensure consistent KVM + * behavior regardless of the underlying hardware, e.g. if an AR_BYTE + * field is intercepted for VMWRITE but not VMREAD (in L1), then VMREAD + * from L1 will return a different value than VMREAD from L2 (L1 sees + * the stripped down value, L2 sees the full value as stored by KVM). */ - if (!is_guest_mode(vcpu)) { - switch (field) { -#define SHADOW_FIELD_RW(x) case x: -#include "vmcs_shadow_fields.h" - /* - * The fields that can be updated by L1 without a vmexit are - * always updated in the vmcs02, the others go down the slow - * path of prepare_vmcs02. - */ - break; - default: - vmx->nested.dirty_vmcs12 = true; - break; + if (field >= GUEST_ES_AR_BYTES && field <= GUEST_TR_AR_BYTES) + field_value &= 0x1f0ff; + + vmcs12_write_any(vmcs12, field, offset, field_value); + + /* + * Do not track vmcs12 dirty-state if in guest-mode as we actually + * dirty shadow vmcs12 instead of vmcs12. Fields that can be updated + * by L1 without a vmexit are always updated in the vmcs02, i.e. don't + * "dirty" vmcs12, all others go down the prepare_vmcs02() slow path. + */ + if (!is_guest_mode(vcpu) && !is_shadow_field_rw(field)) { + /* + * L1 can read these fields without exiting, ensure the + * shadow VMCS is up-to-date. + */ + if (enable_shadow_vmcs && is_shadow_field_ro(field)) { + preempt_disable(); + vmcs_load(vmx->vmcs01.shadow_vmcs); + + __vmcs_writel(field, field_value); + + vmcs_clear(vmx->vmcs01.shadow_vmcs); + vmcs_load(vmx->loaded_vmcs->vmcs); + preempt_enable(); } + vmx->nested.dirty_vmcs12 = true; } return nested_vmx_succeed(vcpu); @@ -4527,11 +4724,10 @@ static void set_current_vmptr(struct vcpu_vmx *vmx, gpa_t vmptr) { vmx->nested.current_vmptr = vmptr; if (enable_shadow_vmcs) { - vmcs_set_bits(SECONDARY_VM_EXEC_CONTROL, - SECONDARY_EXEC_SHADOW_VMCS); + secondary_exec_controls_setbit(vmx, SECONDARY_EXEC_SHADOW_VMCS); vmcs_write64(VMCS_LINK_POINTER, __pa(vmx->vmcs01.shadow_vmcs)); - vmx->nested.need_vmcs12_sync = true; + vmx->nested.need_vmcs12_to_shadow_sync = true; } vmx->nested.dirty_vmcs12 = true; } @@ -4615,7 +4811,8 @@ static int handle_vmptrst(struct kvm_vcpu *vcpu) if (unlikely(to_vmx(vcpu)->nested.hv_evmcs)) return 1; - if (get_vmx_mem_address(vcpu, exit_qual, instr_info, true, &gva)) + if (get_vmx_mem_address(vcpu, exit_qual, instr_info, + true, sizeof(gpa_t), &gva)) return 1; /* *_system ok, nested_vmx_check_permission has verified cpl=0 */ if (kvm_write_guest_virt_system(vcpu, gva, (void *)¤t_vmptr, @@ -4661,7 +4858,7 @@ static int handle_invept(struct kvm_vcpu *vcpu) * operand is read even if it isn't needed (e.g., for type==global) */ if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION), - vmx_instruction_info, false, &gva)) + vmx_instruction_info, false, sizeof(operand), &gva)) return 1; if (kvm_read_guest_virt(vcpu, gva, &operand, sizeof(operand), &e)) { kvm_inject_page_fault(vcpu, &e); @@ -4670,13 +4867,11 @@ static int handle_invept(struct kvm_vcpu *vcpu) switch (type) { case VMX_EPT_EXTENT_GLOBAL: + case VMX_EPT_EXTENT_CONTEXT: /* - * TODO: track mappings and invalidate - * single context requests appropriately + * TODO: Sync the necessary shadow EPT roots here, rather than + * at the next emulated VM-entry. */ - case VMX_EPT_EXTENT_CONTEXT: - kvm_mmu_sync_roots(vcpu); - kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); break; default: BUG_ON(1); @@ -4723,7 +4918,7 @@ static int handle_invvpid(struct kvm_vcpu *vcpu) * operand is read even if it isn't needed (e.g., for type==global) */ if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION), - vmx_instruction_info, false, &gva)) + vmx_instruction_info, false, sizeof(operand), &gva)) return 1; if (kvm_read_guest_virt(vcpu, gva, &operand, sizeof(operand), &e)) { kvm_inject_page_fault(vcpu, &e); @@ -5284,12 +5479,13 @@ static int vmx_get_nested_state(struct kvm_vcpu *vcpu, * When running L2, the authoritative vmcs12 state is in the * vmcs02. When running L1, the authoritative vmcs12 state is * in the shadow or enlightened vmcs linked to vmcs01, unless - * need_vmcs12_sync is set, in which case, the authoritative + * need_vmcs12_to_shadow_sync is set, in which case, the authoritative * vmcs12 state is in the vmcs12 already. */ if (is_guest_mode(vcpu)) { - sync_vmcs12(vcpu, vmcs12); - } else if (!vmx->nested.need_vmcs12_sync) { + sync_vmcs02_to_vmcs12(vcpu, vmcs12); + sync_vmcs02_to_vmcs12_rare(vcpu, vmcs12); + } else if (!vmx->nested.need_vmcs12_to_shadow_sync) { if (vmx->nested.hv_evmcs) copy_enlightened_to_vmcs12(vmx); else if (enable_shadow_vmcs) @@ -5421,7 +5617,7 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu, * Sync eVMCS upon entry as we may not have * HV_X64_MSR_VP_ASSIST_PAGE set up yet. */ - vmx->nested.need_vmcs12_sync = true; + vmx->nested.need_vmcs12_to_shadow_sync = true; } else { return -EINVAL; } @@ -5489,14 +5685,8 @@ error_guest_mode: void nested_vmx_vcpu_setup(void) { if (enable_shadow_vmcs) { - /* - * At vCPU creation, "VMWRITE to any supported field - * in the VMCS" is supported, so use the more - * permissive vmx_vmread_bitmap to specify both read - * and write permissions for the shadow VMCS. - */ vmcs_write64(VMREAD_BITMAP, __pa(vmx_vmread_bitmap)); - vmcs_write64(VMWRITE_BITMAP, __pa(vmx_vmread_bitmap)); + vmcs_write64(VMWRITE_BITMAP, __pa(vmx_vmwrite_bitmap)); } } @@ -5626,10 +5816,15 @@ void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps, msrs->secondary_ctls_low = 0; msrs->secondary_ctls_high &= SECONDARY_EXEC_DESC | + SECONDARY_EXEC_RDTSCP | SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE | + SECONDARY_EXEC_WBINVD_EXITING | SECONDARY_EXEC_APIC_REGISTER_VIRT | SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY | - SECONDARY_EXEC_WBINVD_EXITING; + SECONDARY_EXEC_RDRAND_EXITING | + SECONDARY_EXEC_ENABLE_INVPCID | + SECONDARY_EXEC_RDSEED_EXITING | + SECONDARY_EXEC_XSAVES; /* * We can emulate "VMCS shadowing," even if the hardware @@ -5749,14 +5944,6 @@ __init int nested_vmx_hardware_setup(int (*exit_handlers[])(struct kvm_vcpu *)) { int i; - /* - * Without EPT it is not possible to restore L1's CR3 and PDPTR on - * VMfail, because they are not available in vmcs01. Just always - * use hardware checks. - */ - if (!enable_ept) - nested_early_check = 1; - if (!cpu_has_vmx_shadow_vmcs()) enable_shadow_vmcs = 0; if (enable_shadow_vmcs) { diff --git a/arch/x86/kvm/vmx/nested.h b/arch/x86/kvm/vmx/nested.h index e847ff1019a2..187d39bf0bf1 100644 --- a/arch/x86/kvm/vmx/nested.h +++ b/arch/x86/kvm/vmx/nested.h @@ -17,11 +17,11 @@ int nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry); bool nested_vmx_exit_reflected(struct kvm_vcpu *vcpu, u32 exit_reason); void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, u32 exit_intr_info, unsigned long exit_qualification); -void nested_sync_from_vmcs12(struct kvm_vcpu *vcpu); +void nested_sync_vmcs12_to_shadow(struct kvm_vcpu *vcpu); int vmx_set_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data); int vmx_get_vmx_msr(struct nested_vmx_msrs *msrs, u32 msr_index, u64 *pdata); int get_vmx_mem_address(struct kvm_vcpu *vcpu, unsigned long exit_qualification, - u32 vmx_instruction_info, bool wr, gva_t *ret); + u32 vmx_instruction_info, bool wr, int len, gva_t *ret); static inline struct vmcs12 *get_vmcs12(struct kvm_vcpu *vcpu) { diff --git a/arch/x86/kvm/vmx/ops.h b/arch/x86/kvm/vmx/ops.h index b8e50f76fefc..2200fb698dd0 100644 --- a/arch/x86/kvm/vmx/ops.h +++ b/arch/x86/kvm/vmx/ops.h @@ -146,7 +146,6 @@ static __always_inline void vmcs_write64(unsigned long field, u64 value) __vmcs_writel(field, value); #ifndef CONFIG_X86_64 - asm volatile (""); __vmcs_writel(field+1, value >> 32); #endif } diff --git a/arch/x86/kvm/vmx/vmcs.h b/arch/x86/kvm/vmx/vmcs.h index cb6079f8a227..481ad879197b 100644 --- a/arch/x86/kvm/vmx/vmcs.h +++ b/arch/x86/kvm/vmx/vmcs.h @@ -42,6 +42,14 @@ struct vmcs_host_state { #endif }; +struct vmcs_controls_shadow { + u32 vm_entry; + u32 vm_exit; + u32 pin; + u32 exec; + u32 secondary_exec; +}; + /* * Track a VMCS that may be loaded on a certain CPU. If it is (cpu!=-1), also * remember whether it was VMLAUNCHed, and maintain a linked list of all VMCSs @@ -53,7 +61,7 @@ struct loaded_vmcs { int cpu; bool launched; bool nmi_known_unmasked; - bool hv_timer_armed; + bool hv_timer_soft_disabled; /* Support for vnmi-less CPUs */ int soft_vnmi_blocked; ktime_t entry_time; @@ -61,6 +69,7 @@ struct loaded_vmcs { unsigned long *msr_bitmap; struct list_head loaded_vmcss_on_cpu_link; struct vmcs_host_state host_state; + struct vmcs_controls_shadow controls_shadow; }; static inline bool is_exception_n(u32 intr_info, u8 vector) @@ -115,6 +124,12 @@ static inline bool is_nmi(u32 intr_info) == (INTR_TYPE_NMI_INTR | INTR_INFO_VALID_MASK); } +static inline bool is_external_intr(u32 intr_info) +{ + return (intr_info & (INTR_INFO_VALID_MASK | INTR_INFO_INTR_TYPE_MASK)) + == (INTR_INFO_VALID_MASK | INTR_TYPE_EXT_INTR); +} + enum vmcs_field_width { VMCS_FIELD_WIDTH_U16 = 0, VMCS_FIELD_WIDTH_U64 = 1, diff --git a/arch/x86/kvm/vmx/vmcs12.h b/arch/x86/kvm/vmx/vmcs12.h index 337718fc8a36..d0c6df373f67 100644 --- a/arch/x86/kvm/vmx/vmcs12.h +++ b/arch/x86/kvm/vmx/vmcs12.h @@ -395,69 +395,48 @@ static inline short vmcs_field_to_offset(unsigned long field) #undef ROL16 -/* - * Read a vmcs12 field. Since these can have varying lengths and we return - * one type, we chose the biggest type (u64) and zero-extend the return value - * to that size. Note that the caller, handle_vmread, might need to use only - * some of the bits we return here (e.g., on 32-bit guests, only 32 bits of - * 64-bit fields are to be returned). - */ -static inline int vmcs12_read_any(struct vmcs12 *vmcs12, - unsigned long field, u64 *ret) +static inline u64 vmcs12_read_any(struct vmcs12 *vmcs12, unsigned long field, + u16 offset) { - short offset = vmcs_field_to_offset(field); - char *p; - - if (offset < 0) - return offset; - - p = (char *)vmcs12 + offset; + char *p = (char *)vmcs12 + offset; switch (vmcs_field_width(field)) { case VMCS_FIELD_WIDTH_NATURAL_WIDTH: - *ret = *((natural_width *)p); - return 0; + return *((natural_width *)p); case VMCS_FIELD_WIDTH_U16: - *ret = *((u16 *)p); - return 0; + return *((u16 *)p); case VMCS_FIELD_WIDTH_U32: - *ret = *((u32 *)p); - return 0; + return *((u32 *)p); case VMCS_FIELD_WIDTH_U64: - *ret = *((u64 *)p); - return 0; + return *((u64 *)p); default: - WARN_ON(1); - return -ENOENT; + WARN_ON_ONCE(1); + return -1; } } -static inline int vmcs12_write_any(struct vmcs12 *vmcs12, - unsigned long field, u64 field_value){ - short offset = vmcs_field_to_offset(field); +static inline void vmcs12_write_any(struct vmcs12 *vmcs12, unsigned long field, + u16 offset, u64 field_value) +{ char *p = (char *)vmcs12 + offset; - if (offset < 0) - return offset; - switch (vmcs_field_width(field)) { case VMCS_FIELD_WIDTH_U16: *(u16 *)p = field_value; - return 0; + break; case VMCS_FIELD_WIDTH_U32: *(u32 *)p = field_value; - return 0; + break; case VMCS_FIELD_WIDTH_U64: *(u64 *)p = field_value; - return 0; + break; case VMCS_FIELD_WIDTH_NATURAL_WIDTH: *(natural_width *)p = field_value; - return 0; + break; default: - WARN_ON(1); - return -ENOENT; + WARN_ON_ONCE(1); + break; } - } #endif /* __KVM_X86_VMX_VMCS12_H */ diff --git a/arch/x86/kvm/vmx/vmcs_shadow_fields.h b/arch/x86/kvm/vmx/vmcs_shadow_fields.h index 132432f375c2..eb1ecd16fd22 100644 --- a/arch/x86/kvm/vmx/vmcs_shadow_fields.h +++ b/arch/x86/kvm/vmx/vmcs_shadow_fields.h @@ -1,8 +1,12 @@ +#if !defined(SHADOW_FIELD_RO) && !defined(SHADOW_FIELD_RW) +BUILD_BUG_ON(1) +#endif + #ifndef SHADOW_FIELD_RO -#define SHADOW_FIELD_RO(x) +#define SHADOW_FIELD_RO(x, y) #endif #ifndef SHADOW_FIELD_RW -#define SHADOW_FIELD_RW(x) +#define SHADOW_FIELD_RW(x, y) #endif /* @@ -28,47 +32,48 @@ */ /* 16-bits */ -SHADOW_FIELD_RW(GUEST_INTR_STATUS) -SHADOW_FIELD_RW(GUEST_PML_INDEX) -SHADOW_FIELD_RW(HOST_FS_SELECTOR) -SHADOW_FIELD_RW(HOST_GS_SELECTOR) +SHADOW_FIELD_RW(GUEST_INTR_STATUS, guest_intr_status) +SHADOW_FIELD_RW(GUEST_PML_INDEX, guest_pml_index) +SHADOW_FIELD_RW(HOST_FS_SELECTOR, host_fs_selector) +SHADOW_FIELD_RW(HOST_GS_SELECTOR, host_gs_selector) /* 32-bits */ -SHADOW_FIELD_RO(VM_EXIT_REASON) -SHADOW_FIELD_RO(VM_EXIT_INTR_INFO) -SHADOW_FIELD_RO(VM_EXIT_INSTRUCTION_LEN) -SHADOW_FIELD_RO(IDT_VECTORING_INFO_FIELD) -SHADOW_FIELD_RO(IDT_VECTORING_ERROR_CODE) -SHADOW_FIELD_RO(VM_EXIT_INTR_ERROR_CODE) -SHADOW_FIELD_RW(CPU_BASED_VM_EXEC_CONTROL) -SHADOW_FIELD_RW(EXCEPTION_BITMAP) -SHADOW_FIELD_RW(VM_ENTRY_EXCEPTION_ERROR_CODE) -SHADOW_FIELD_RW(VM_ENTRY_INTR_INFO_FIELD) -SHADOW_FIELD_RW(VM_ENTRY_INSTRUCTION_LEN) -SHADOW_FIELD_RW(TPR_THRESHOLD) -SHADOW_FIELD_RW(GUEST_CS_AR_BYTES) -SHADOW_FIELD_RW(GUEST_SS_AR_BYTES) -SHADOW_FIELD_RW(GUEST_INTERRUPTIBILITY_INFO) -SHADOW_FIELD_RW(VMX_PREEMPTION_TIMER_VALUE) +SHADOW_FIELD_RO(VM_EXIT_REASON, vm_exit_reason) +SHADOW_FIELD_RO(VM_EXIT_INTR_INFO, vm_exit_intr_info) +SHADOW_FIELD_RO(VM_EXIT_INSTRUCTION_LEN, vm_exit_instruction_len) +SHADOW_FIELD_RO(IDT_VECTORING_INFO_FIELD, idt_vectoring_info_field) +SHADOW_FIELD_RO(IDT_VECTORING_ERROR_CODE, idt_vectoring_error_code) +SHADOW_FIELD_RO(VM_EXIT_INTR_ERROR_CODE, vm_exit_intr_error_code) +SHADOW_FIELD_RO(GUEST_CS_AR_BYTES, guest_cs_ar_bytes) +SHADOW_FIELD_RO(GUEST_SS_AR_BYTES, guest_ss_ar_bytes) +SHADOW_FIELD_RW(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control) +SHADOW_FIELD_RW(PIN_BASED_VM_EXEC_CONTROL, pin_based_vm_exec_control) +SHADOW_FIELD_RW(EXCEPTION_BITMAP, exception_bitmap) +SHADOW_FIELD_RW(VM_ENTRY_EXCEPTION_ERROR_CODE, vm_entry_exception_error_code) +SHADOW_FIELD_RW(VM_ENTRY_INTR_INFO_FIELD, vm_entry_intr_info_field) +SHADOW_FIELD_RW(VM_ENTRY_INSTRUCTION_LEN, vm_entry_instruction_len) +SHADOW_FIELD_RW(TPR_THRESHOLD, tpr_threshold) +SHADOW_FIELD_RW(GUEST_INTERRUPTIBILITY_INFO, guest_interruptibility_info) +SHADOW_FIELD_RW(VMX_PREEMPTION_TIMER_VALUE, vmx_preemption_timer_value) /* Natural width */ -SHADOW_FIELD_RO(EXIT_QUALIFICATION) -SHADOW_FIELD_RO(GUEST_LINEAR_ADDRESS) -SHADOW_FIELD_RW(GUEST_RIP) -SHADOW_FIELD_RW(GUEST_RSP) -SHADOW_FIELD_RW(GUEST_CR0) -SHADOW_FIELD_RW(GUEST_CR3) -SHADOW_FIELD_RW(GUEST_CR4) -SHADOW_FIELD_RW(GUEST_RFLAGS) -SHADOW_FIELD_RW(CR0_GUEST_HOST_MASK) -SHADOW_FIELD_RW(CR0_READ_SHADOW) -SHADOW_FIELD_RW(CR4_READ_SHADOW) -SHADOW_FIELD_RW(HOST_FS_BASE) -SHADOW_FIELD_RW(HOST_GS_BASE) +SHADOW_FIELD_RO(EXIT_QUALIFICATION, exit_qualification) +SHADOW_FIELD_RO(GUEST_LINEAR_ADDRESS, guest_linear_address) +SHADOW_FIELD_RW(GUEST_RIP, guest_rip) +SHADOW_FIELD_RW(GUEST_RSP, guest_rsp) +SHADOW_FIELD_RW(GUEST_CR0, guest_cr0) +SHADOW_FIELD_RW(GUEST_CR3, guest_cr3) +SHADOW_FIELD_RW(GUEST_CR4, guest_cr4) +SHADOW_FIELD_RW(GUEST_RFLAGS, guest_rflags) +SHADOW_FIELD_RW(CR0_GUEST_HOST_MASK, cr0_guest_host_mask) +SHADOW_FIELD_RW(CR0_READ_SHADOW, cr0_read_shadow) +SHADOW_FIELD_RW(CR4_READ_SHADOW, cr4_read_shadow) +SHADOW_FIELD_RW(HOST_FS_BASE, host_fs_base) +SHADOW_FIELD_RW(HOST_GS_BASE, host_gs_base) /* 64-bit */ -SHADOW_FIELD_RO(GUEST_PHYSICAL_ADDRESS) -SHADOW_FIELD_RO(GUEST_PHYSICAL_ADDRESS_HIGH) +SHADOW_FIELD_RO(GUEST_PHYSICAL_ADDRESS, guest_physical_address) +SHADOW_FIELD_RO(GUEST_PHYSICAL_ADDRESS_HIGH, guest_physical_address) #undef SHADOW_FIELD_RO #undef SHADOW_FIELD_RW diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index d98eac371c0a..69536553446d 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -389,6 +389,7 @@ static const struct kvm_vmx_segment_field { }; u64 host_efer; +static unsigned long host_idt_base; /* * Though SYSCALL is only supported in 64-bit mode on Intel CPUs, kvm @@ -1035,6 +1036,33 @@ static void pt_guest_exit(struct vcpu_vmx *vmx) wrmsrl(MSR_IA32_RTIT_CTL, vmx->pt_desc.host.ctl); } +void vmx_set_host_fs_gs(struct vmcs_host_state *host, u16 fs_sel, u16 gs_sel, + unsigned long fs_base, unsigned long gs_base) +{ + if (unlikely(fs_sel != host->fs_sel)) { + if (!(fs_sel & 7)) + vmcs_write16(HOST_FS_SELECTOR, fs_sel); + else + vmcs_write16(HOST_FS_SELECTOR, 0); + host->fs_sel = fs_sel; + } + if (unlikely(gs_sel != host->gs_sel)) { + if (!(gs_sel & 7)) + vmcs_write16(HOST_GS_SELECTOR, gs_sel); + else + vmcs_write16(HOST_GS_SELECTOR, 0); + host->gs_sel = gs_sel; + } + if (unlikely(fs_base != host->fs_base)) { + vmcs_writel(HOST_FS_BASE, fs_base); + host->fs_base = fs_base; + } + if (unlikely(gs_base != host->gs_base)) { + vmcs_writel(HOST_GS_BASE, gs_base); + host->gs_base = gs_base; + } +} + void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -1053,20 +1081,18 @@ void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu) * when guest state is loaded. This happens when guest transitions * to/from long-mode by setting MSR_EFER.LMA. */ - if (!vmx->loaded_cpu_state || vmx->guest_msrs_dirty) { - vmx->guest_msrs_dirty = false; + if (!vmx->guest_msrs_ready) { + vmx->guest_msrs_ready = true; for (i = 0; i < vmx->save_nmsrs; ++i) kvm_set_shared_msr(vmx->guest_msrs[i].index, vmx->guest_msrs[i].data, vmx->guest_msrs[i].mask); } - - if (vmx->loaded_cpu_state) + if (vmx->guest_state_loaded) return; - vmx->loaded_cpu_state = vmx->loaded_vmcs; - host_state = &vmx->loaded_cpu_state->host_state; + host_state = &vmx->loaded_vmcs->host_state; /* * Set host fs and gs selectors. Unfortunately, 22.2.3 does not @@ -1100,42 +1126,20 @@ void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu) gs_base = segment_base(gs_sel); #endif - if (unlikely(fs_sel != host_state->fs_sel)) { - if (!(fs_sel & 7)) - vmcs_write16(HOST_FS_SELECTOR, fs_sel); - else - vmcs_write16(HOST_FS_SELECTOR, 0); - host_state->fs_sel = fs_sel; - } - if (unlikely(gs_sel != host_state->gs_sel)) { - if (!(gs_sel & 7)) - vmcs_write16(HOST_GS_SELECTOR, gs_sel); - else - vmcs_write16(HOST_GS_SELECTOR, 0); - host_state->gs_sel = gs_sel; - } - if (unlikely(fs_base != host_state->fs_base)) { - vmcs_writel(HOST_FS_BASE, fs_base); - host_state->fs_base = fs_base; - } - if (unlikely(gs_base != host_state->gs_base)) { - vmcs_writel(HOST_GS_BASE, gs_base); - host_state->gs_base = gs_base; - } + vmx_set_host_fs_gs(host_state, fs_sel, gs_sel, fs_base, gs_base); + vmx->guest_state_loaded = true; } static void vmx_prepare_switch_to_host(struct vcpu_vmx *vmx) { struct vmcs_host_state *host_state; - if (!vmx->loaded_cpu_state) + if (!vmx->guest_state_loaded) return; - WARN_ON_ONCE(vmx->loaded_cpu_state != vmx->loaded_vmcs); - host_state = &vmx->loaded_cpu_state->host_state; + host_state = &vmx->loaded_vmcs->host_state; ++vmx->vcpu.stat.host_state_reload; - vmx->loaded_cpu_state = NULL; #ifdef CONFIG_X86_64 rdmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base); @@ -1161,13 +1165,15 @@ static void vmx_prepare_switch_to_host(struct vcpu_vmx *vmx) wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_host_kernel_gs_base); #endif load_fixmap_gdt(raw_smp_processor_id()); + vmx->guest_state_loaded = false; + vmx->guest_msrs_ready = false; } #ifdef CONFIG_X86_64 static u64 vmx_read_guest_kernel_gs_base(struct vcpu_vmx *vmx) { preempt_disable(); - if (vmx->loaded_cpu_state) + if (vmx->guest_state_loaded) rdmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base); preempt_enable(); return vmx->msr_guest_kernel_gs_base; @@ -1176,7 +1182,7 @@ static u64 vmx_read_guest_kernel_gs_base(struct vcpu_vmx *vmx) static void vmx_write_guest_kernel_gs_base(struct vcpu_vmx *vmx, u64 data) { preempt_disable(); - if (vmx->loaded_cpu_state) + if (vmx->guest_state_loaded) wrmsrl(MSR_KERNEL_GS_BASE, data); preempt_enable(); vmx->msr_guest_kernel_gs_base = data; @@ -1225,11 +1231,7 @@ static void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu) pi_set_on(pi_desc); } -/* - * Switches to specified vcpu, until a matching vcpu_put(), but assumes - * vcpu mutex is already taken. - */ -void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) +void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); bool already_loaded = vmx->loaded_vmcs->cpu == cpu; @@ -1290,8 +1292,20 @@ void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) if (kvm_has_tsc_control && vmx->current_tsc_ratio != vcpu->arch.tsc_scaling_ratio) decache_tsc_multiplier(vmx); +} + +/* + * Switches to specified vcpu, until a matching vcpu_put(), but assumes + * vcpu mutex is already taken. + */ +void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + + vmx_vcpu_load_vmcs(vcpu, cpu); vmx_vcpu_pi_load(vcpu, cpu); + vmx->host_pkru = read_pkru(); vmx->host_debugctlmsr = get_debugctlmsr(); } @@ -1310,7 +1324,7 @@ static void vmx_vcpu_pi_put(struct kvm_vcpu *vcpu) pi_set_sn(pi_desc); } -void vmx_vcpu_put(struct kvm_vcpu *vcpu) +static void vmx_vcpu_put(struct kvm_vcpu *vcpu) { vmx_vcpu_pi_put(vcpu); @@ -1579,7 +1593,7 @@ static void setup_msrs(struct vcpu_vmx *vmx) move_msr_up(vmx, index, save_nmsrs++); vmx->save_nmsrs = save_nmsrs; - vmx->guest_msrs_dirty = true; + vmx->guest_msrs_ready = false; if (cpu_has_vmx_msr_bitmap()) vmx_update_msr_bitmap(&vmx->vcpu); @@ -1692,9 +1706,6 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_SYSENTER_ESP: msr_info->data = vmcs_readl(GUEST_SYSENTER_ESP); break; - case MSR_IA32_POWER_CTL: - msr_info->data = vmx->msr_ia32_power_ctl; - break; case MSR_IA32_BNDCFGS: if (!kvm_mpx_supported() || (!msr_info->host_initiated && @@ -1718,7 +1729,10 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return vmx_get_vmx_msr(&vmx->nested.msrs, msr_info->index, &msr_info->data); case MSR_IA32_XSS: - if (!vmx_xsaves_supported()) + if (!vmx_xsaves_supported() || + (!msr_info->host_initiated && + !(guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) && + guest_cpuid_has(vcpu, X86_FEATURE_XSAVES)))) return 1; msr_info->data = vcpu->arch.ia32_xss; break; @@ -1817,17 +1831,28 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) break; #endif case MSR_IA32_SYSENTER_CS: + if (is_guest_mode(vcpu)) + get_vmcs12(vcpu)->guest_sysenter_cs = data; vmcs_write32(GUEST_SYSENTER_CS, data); break; case MSR_IA32_SYSENTER_EIP: + if (is_guest_mode(vcpu)) + get_vmcs12(vcpu)->guest_sysenter_eip = data; vmcs_writel(GUEST_SYSENTER_EIP, data); break; case MSR_IA32_SYSENTER_ESP: + if (is_guest_mode(vcpu)) + get_vmcs12(vcpu)->guest_sysenter_esp = data; vmcs_writel(GUEST_SYSENTER_ESP, data); break; - case MSR_IA32_POWER_CTL: - vmx->msr_ia32_power_ctl = data; + case MSR_IA32_DEBUGCTLMSR: + if (is_guest_mode(vcpu) && get_vmcs12(vcpu)->vm_exit_controls & + VM_EXIT_SAVE_DEBUG_CONTROLS) + get_vmcs12(vcpu)->guest_ia32_debugctl = data; + + ret = kvm_set_msr_common(vcpu, msr_info); break; + case MSR_IA32_BNDCFGS: if (!kvm_mpx_supported() || (!msr_info->host_initiated && @@ -1896,9 +1921,14 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) MSR_TYPE_W); break; case MSR_IA32_CR_PAT: + if (!kvm_pat_valid(data)) + return 1; + + if (is_guest_mode(vcpu) && + get_vmcs12(vcpu)->vm_exit_controls & VM_EXIT_SAVE_IA32_PAT) + get_vmcs12(vcpu)->guest_ia32_pat = data; + if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) { - if (!kvm_pat_valid(data)) - return 1; vmcs_write64(GUEST_IA32_PAT, data); vcpu->arch.pat = data; break; @@ -1932,7 +1962,10 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return 1; return vmx_set_vmx_msr(vcpu, msr_index, data); case MSR_IA32_XSS: - if (!vmx_xsaves_supported()) + if (!vmx_xsaves_supported() || + (!msr_info->host_initiated && + !(guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) && + guest_cpuid_has(vcpu, X86_FEATURE_XSAVES)))) return 1; /* * The only supported bit as of Skylake is bit 8, but @@ -2435,6 +2468,7 @@ int alloc_loaded_vmcs(struct loaded_vmcs *loaded_vmcs) return -ENOMEM; loaded_vmcs->shadow_vmcs = NULL; + loaded_vmcs->hv_timer_soft_disabled = false; loaded_vmcs_init(loaded_vmcs); if (cpu_has_vmx_msr_bitmap()) { @@ -2455,6 +2489,8 @@ int alloc_loaded_vmcs(struct loaded_vmcs *loaded_vmcs) } memset(&loaded_vmcs->host_state, 0, sizeof(struct vmcs_host_state)); + memset(&loaded_vmcs->controls_shadow, 0, + sizeof(struct vmcs_controls_shadow)); return 0; @@ -2737,7 +2773,7 @@ static void ept_load_pdptrs(struct kvm_vcpu *vcpu) (unsigned long *)&vcpu->arch.regs_dirty)) return; - if (is_paging(vcpu) && is_pae(vcpu) && !is_long_mode(vcpu)) { + if (is_pae_paging(vcpu)) { vmcs_write64(GUEST_PDPTR0, mmu->pdptrs[0]); vmcs_write64(GUEST_PDPTR1, mmu->pdptrs[1]); vmcs_write64(GUEST_PDPTR2, mmu->pdptrs[2]); @@ -2749,7 +2785,7 @@ void ept_save_pdptrs(struct kvm_vcpu *vcpu) { struct kvm_mmu *mmu = vcpu->arch.walk_mmu; - if (is_paging(vcpu) && is_pae(vcpu) && !is_long_mode(vcpu)) { + if (is_pae_paging(vcpu)) { mmu->pdptrs[0] = vmcs_read64(GUEST_PDPTR0); mmu->pdptrs[1] = vmcs_read64(GUEST_PDPTR1); mmu->pdptrs[2] = vmcs_read64(GUEST_PDPTR2); @@ -2766,22 +2802,20 @@ static void ept_update_paging_mode_cr0(unsigned long *hw_cr0, unsigned long cr0, struct kvm_vcpu *vcpu) { + struct vcpu_vmx *vmx = to_vmx(vcpu); + if (!test_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail)) vmx_decache_cr3(vcpu); if (!(cr0 & X86_CR0_PG)) { /* From paging/starting to nonpaging */ - vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, - vmcs_read32(CPU_BASED_VM_EXEC_CONTROL) | - (CPU_BASED_CR3_LOAD_EXITING | - CPU_BASED_CR3_STORE_EXITING)); + exec_controls_setbit(vmx, CPU_BASED_CR3_LOAD_EXITING | + CPU_BASED_CR3_STORE_EXITING); vcpu->arch.cr0 = cr0; vmx_set_cr4(vcpu, kvm_read_cr4(vcpu)); } else if (!is_paging(vcpu)) { /* From nonpaging to paging */ - vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, - vmcs_read32(CPU_BASED_VM_EXEC_CONTROL) & - ~(CPU_BASED_CR3_LOAD_EXITING | - CPU_BASED_CR3_STORE_EXITING)); + exec_controls_clearbit(vmx, CPU_BASED_CR3_LOAD_EXITING | + CPU_BASED_CR3_STORE_EXITING); vcpu->arch.cr0 = cr0; vmx_set_cr4(vcpu, kvm_read_cr4(vcpu)); } @@ -2881,6 +2915,7 @@ void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) { + struct vcpu_vmx *vmx = to_vmx(vcpu); /* * Pass through host's Machine Check Enable value to hw_cr4, which * is in force while we are in guest mode. Do not let guests control @@ -2891,20 +2926,19 @@ int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) hw_cr4 = (cr4_read_shadow() & X86_CR4_MCE) | (cr4 & ~X86_CR4_MCE); if (enable_unrestricted_guest) hw_cr4 |= KVM_VM_CR4_ALWAYS_ON_UNRESTRICTED_GUEST; - else if (to_vmx(vcpu)->rmode.vm86_active) + else if (vmx->rmode.vm86_active) hw_cr4 |= KVM_RMODE_VM_CR4_ALWAYS_ON; else hw_cr4 |= KVM_PMODE_VM_CR4_ALWAYS_ON; if (!boot_cpu_has(X86_FEATURE_UMIP) && vmx_umip_emulated()) { if (cr4 & X86_CR4_UMIP) { - vmcs_set_bits(SECONDARY_VM_EXEC_CONTROL, - SECONDARY_EXEC_DESC); + secondary_exec_controls_setbit(vmx, SECONDARY_EXEC_DESC); hw_cr4 &= ~X86_CR4_UMIP; } else if (!is_guest_mode(vcpu) || - !nested_cpu_has2(get_vmcs12(vcpu), SECONDARY_EXEC_DESC)) - vmcs_clear_bits(SECONDARY_VM_EXEC_CONTROL, - SECONDARY_EXEC_DESC); + !nested_cpu_has2(get_vmcs12(vcpu), SECONDARY_EXEC_DESC)) { + secondary_exec_controls_clearbit(vmx, SECONDARY_EXEC_DESC); + } } if (cr4 & X86_CR4_VMXE) { @@ -2919,7 +2953,7 @@ int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) return 1; } - if (to_vmx(vcpu)->nested.vmxon && !nested_cr4_valid(vcpu, cr4)) + if (vmx->nested.vmxon && !nested_cr4_valid(vcpu, cr4)) return 1; vcpu->arch.cr4 = cr4; @@ -3537,7 +3571,7 @@ static u8 vmx_msr_bitmap_mode(struct kvm_vcpu *vcpu) u8 mode = 0; if (cpu_has_secondary_exec_ctrls() && - (vmcs_read32(SECONDARY_VM_EXEC_CONTROL) & + (secondary_exec_controls_get(to_vmx(vcpu)) & SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE)) { mode |= MSR_BITMAP_MODE_X2APIC; if (enable_apicv && kvm_vcpu_apicv_active(vcpu)) @@ -3731,7 +3765,6 @@ void vmx_set_constant_host_state(struct vcpu_vmx *vmx) { u32 low32, high32; unsigned long tmpl; - struct desc_ptr dt; unsigned long cr0, cr3, cr4; cr0 = read_cr0(); @@ -3767,9 +3800,7 @@ void vmx_set_constant_host_state(struct vcpu_vmx *vmx) vmcs_write16(HOST_SS_SELECTOR, __KERNEL_DS); /* 22.2.4 */ vmcs_write16(HOST_TR_SELECTOR, GDT_ENTRY_TSS*8); /* 22.2.4 */ - store_idt(&dt); - vmcs_writel(HOST_IDTR_BASE, dt.address); /* 22.2.4 */ - vmx->host_idt_base = dt.address; + vmcs_writel(HOST_IDTR_BASE, host_idt_base); /* 22.2.4 */ vmcs_writel(HOST_RIP, (unsigned long)vmx_vmexit); /* 22.2.5 */ @@ -3798,7 +3829,7 @@ void set_cr4_guest_host_mask(struct vcpu_vmx *vmx) vmcs_writel(CR4_GUEST_HOST_MASK, ~vmx->vcpu.arch.cr4_guest_owned_bits); } -static u32 vmx_pin_based_exec_ctrl(struct vcpu_vmx *vmx) +u32 vmx_pin_based_exec_ctrl(struct vcpu_vmx *vmx) { u32 pin_based_exec_ctrl = vmcs_config.pin_based_exec_ctrl; @@ -3808,8 +3839,9 @@ static u32 vmx_pin_based_exec_ctrl(struct vcpu_vmx *vmx) if (!enable_vnmi) pin_based_exec_ctrl &= ~PIN_BASED_VIRTUAL_NMIS; - /* Enable the preemption timer dynamically */ - pin_based_exec_ctrl &= ~PIN_BASED_VMX_PREEMPTION_TIMER; + if (!enable_preemption_timer) + pin_based_exec_ctrl &= ~PIN_BASED_VMX_PREEMPTION_TIMER; + return pin_based_exec_ctrl; } @@ -3817,14 +3849,14 @@ static void vmx_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - vmcs_write32(PIN_BASED_VM_EXEC_CONTROL, vmx_pin_based_exec_ctrl(vmx)); + pin_controls_set(vmx, vmx_pin_based_exec_ctrl(vmx)); if (cpu_has_secondary_exec_ctrls()) { if (kvm_vcpu_apicv_active(vcpu)) - vmcs_set_bits(SECONDARY_VM_EXEC_CONTROL, + secondary_exec_controls_setbit(vmx, SECONDARY_EXEC_APIC_REGISTER_VIRT | SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY); else - vmcs_clear_bits(SECONDARY_VM_EXEC_CONTROL, + secondary_exec_controls_clearbit(vmx, SECONDARY_EXEC_APIC_REGISTER_VIRT | SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY); } @@ -4015,15 +4047,14 @@ static void vmx_vcpu_setup(struct vcpu_vmx *vmx) vmcs_write64(VMCS_LINK_POINTER, -1ull); /* 22.3.1.5 */ /* Control */ - vmcs_write32(PIN_BASED_VM_EXEC_CONTROL, vmx_pin_based_exec_ctrl(vmx)); + pin_controls_set(vmx, vmx_pin_based_exec_ctrl(vmx)); vmx->hv_deadline_tsc = -1; - vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, vmx_exec_control(vmx)); + exec_controls_set(vmx, vmx_exec_control(vmx)); if (cpu_has_secondary_exec_ctrls()) { vmx_compute_secondary_exec_control(vmx); - vmcs_write32(SECONDARY_VM_EXEC_CONTROL, - vmx->secondary_exec_control); + secondary_exec_controls_set(vmx, vmx->secondary_exec_control); } if (kvm_vcpu_apicv_active(&vmx->vcpu)) { @@ -4081,10 +4112,10 @@ static void vmx_vcpu_setup(struct vcpu_vmx *vmx) ++vmx->nmsrs; } - vm_exit_controls_init(vmx, vmx_vmexit_ctrl()); + vm_exit_controls_set(vmx, vmx_vmexit_ctrl()); /* 22.2.1, 20.8.1 */ - vm_entry_controls_init(vmx, vmx_vmentry_ctrl()); + vm_entry_controls_set(vmx, vmx_vmentry_ctrl()); vmx->vcpu.arch.cr0_guest_owned_bits = X86_CR0_TS; vmcs_writel(CR0_GUEST_HOST_MASK, ~X86_CR0_TS); @@ -4208,8 +4239,7 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) static void enable_irq_window(struct kvm_vcpu *vcpu) { - vmcs_set_bits(CPU_BASED_VM_EXEC_CONTROL, - CPU_BASED_VIRTUAL_INTR_PENDING); + exec_controls_setbit(to_vmx(vcpu), CPU_BASED_VIRTUAL_INTR_PENDING); } static void enable_nmi_window(struct kvm_vcpu *vcpu) @@ -4220,8 +4250,7 @@ static void enable_nmi_window(struct kvm_vcpu *vcpu) return; } - vmcs_set_bits(CPU_BASED_VM_EXEC_CONTROL, - CPU_BASED_VIRTUAL_NMI_PENDING); + exec_controls_setbit(to_vmx(vcpu), CPU_BASED_VIRTUAL_NMI_PENDING); } static void vmx_inject_irq(struct kvm_vcpu *vcpu) @@ -4442,11 +4471,11 @@ static void kvm_machine_check(void) static int handle_machine_check(struct kvm_vcpu *vcpu) { - /* already handled by vcpu_run */ + /* handled by vmx_vcpu_run() */ return 1; } -static int handle_exception(struct kvm_vcpu *vcpu) +static int handle_exception_nmi(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); struct kvm_run *kvm_run = vcpu->run; @@ -4458,11 +4487,8 @@ static int handle_exception(struct kvm_vcpu *vcpu) vect_info = vmx->idt_vectoring_info; intr_info = vmx->exit_intr_info; - if (is_machine_check(intr_info)) - return handle_machine_check(vcpu); - - if (is_nmi(intr_info)) - return 1; /* already handled by vmx_vcpu_run() */ + if (is_machine_check(intr_info) || is_nmi(intr_info)) + return 1; /* handled by handle_exception_nmi_irqoff() */ if (is_invalid_opcode(intr_info)) return handle_ud(vcpu); @@ -4518,7 +4544,7 @@ static int handle_exception(struct kvm_vcpu *vcpu) dr6 = vmcs_readl(EXIT_QUALIFICATION); if (!(vcpu->guest_debug & (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))) { - vcpu->arch.dr6 &= ~15; + vcpu->arch.dr6 &= ~DR_TRAP_BITS; vcpu->arch.dr6 |= dr6 | DR6_RTM; if (is_icebp(intr_info)) skip_emulated_instruction(vcpu); @@ -4763,7 +4789,7 @@ static int handle_dr(struct kvm_vcpu *vcpu) vcpu->run->exit_reason = KVM_EXIT_DEBUG; return 0; } else { - vcpu->arch.dr6 &= ~15; + vcpu->arch.dr6 &= ~DR_TRAP_BITS; vcpu->arch.dr6 |= DR6_BD | DR6_RTM; kvm_queue_exception(vcpu, DB_VECTOR); return 1; @@ -4771,8 +4797,7 @@ static int handle_dr(struct kvm_vcpu *vcpu) } if (vcpu->guest_debug == 0) { - vmcs_clear_bits(CPU_BASED_VM_EXEC_CONTROL, - CPU_BASED_MOV_DR_EXITING); + exec_controls_clearbit(to_vmx(vcpu), CPU_BASED_MOV_DR_EXITING); /* * No more DR vmexits; force a reload of the debug registers @@ -4816,7 +4841,7 @@ static void vmx_sync_dirty_debug_regs(struct kvm_vcpu *vcpu) vcpu->arch.dr7 = vmcs_readl(GUEST_DR7); vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_WONT_EXIT; - vmcs_set_bits(CPU_BASED_VM_EXEC_CONTROL, CPU_BASED_MOV_DR_EXITING); + exec_controls_setbit(to_vmx(vcpu), CPU_BASED_MOV_DR_EXITING); } static void vmx_set_dr7(struct kvm_vcpu *vcpu, unsigned long val) @@ -4876,8 +4901,7 @@ static int handle_tpr_below_threshold(struct kvm_vcpu *vcpu) static int handle_interrupt_window(struct kvm_vcpu *vcpu) { - vmcs_clear_bits(CPU_BASED_VM_EXEC_CONTROL, - CPU_BASED_VIRTUAL_INTR_PENDING); + exec_controls_clearbit(to_vmx(vcpu), CPU_BASED_VIRTUAL_INTR_PENDING); kvm_make_request(KVM_REQ_EVENT, vcpu); @@ -5131,8 +5155,7 @@ static int handle_ept_misconfig(struct kvm_vcpu *vcpu) static int handle_nmi_window(struct kvm_vcpu *vcpu) { WARN_ON_ONCE(!enable_vnmi); - vmcs_clear_bits(CPU_BASED_VM_EXEC_CONTROL, - CPU_BASED_VIRTUAL_NMI_PENDING); + exec_controls_clearbit(to_vmx(vcpu), CPU_BASED_VIRTUAL_NMI_PENDING); ++vcpu->stat.nmi_window_exits; kvm_make_request(KVM_REQ_EVENT, vcpu); @@ -5144,7 +5167,6 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu) struct vcpu_vmx *vmx = to_vmx(vcpu); enum emulation_result err = EMULATE_DONE; int ret = 1; - u32 cpu_exec_ctrl; bool intr_window_requested; unsigned count = 130; @@ -5155,8 +5177,8 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu) */ WARN_ON_ONCE(vmx->emulation_required && vmx->nested.nested_run_pending); - cpu_exec_ctrl = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL); - intr_window_requested = cpu_exec_ctrl & CPU_BASED_VIRTUAL_INTR_PENDING; + intr_window_requested = exec_controls_get(vmx) & + CPU_BASED_VIRTUAL_INTR_PENDING; while (vmx->emulation_required && count-- != 0) { if (intr_window_requested && vmx_interrupt_allowed(vcpu)) @@ -5342,7 +5364,8 @@ static int handle_invpcid(struct kvm_vcpu *vcpu) * is read even if it isn't needed (e.g., for type==all) */ if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION), - vmx_instruction_info, false, &gva)) + vmx_instruction_info, false, + sizeof(operand), &gva)) return 1; if (kvm_read_guest_virt(vcpu, gva, &operand, sizeof(operand), &e)) { @@ -5437,8 +5460,12 @@ static int handle_pml_full(struct kvm_vcpu *vcpu) static int handle_preemption_timer(struct kvm_vcpu *vcpu) { - if (!to_vmx(vcpu)->req_immediate_exit) + struct vcpu_vmx *vmx = to_vmx(vcpu); + + if (!vmx->req_immediate_exit && + !unlikely(vmx->loaded_vmcs->hv_timer_soft_disabled)) kvm_lapic_expired_hv_timer(vcpu); + return 1; } @@ -5469,7 +5496,7 @@ static int handle_encls(struct kvm_vcpu *vcpu) * to be done to userspace and return 0. */ static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = { - [EXIT_REASON_EXCEPTION_NMI] = handle_exception, + [EXIT_REASON_EXCEPTION_NMI] = handle_exception_nmi, [EXIT_REASON_EXTERNAL_INTERRUPT] = handle_external_interrupt, [EXIT_REASON_TRIPLE_FAULT] = handle_triple_fault, [EXIT_REASON_NMI_WINDOW] = handle_nmi_window, @@ -5952,6 +5979,7 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr) void vmx_set_virtual_apic_mode(struct kvm_vcpu *vcpu) { + struct vcpu_vmx *vmx = to_vmx(vcpu); u32 sec_exec_control; if (!lapic_in_kernel(vcpu)) @@ -5963,11 +5991,11 @@ void vmx_set_virtual_apic_mode(struct kvm_vcpu *vcpu) /* Postpone execution until vmcs01 is the current VMCS. */ if (is_guest_mode(vcpu)) { - to_vmx(vcpu)->nested.change_vmcs01_virtual_apic_mode = true; + vmx->nested.change_vmcs01_virtual_apic_mode = true; return; } - sec_exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL); + sec_exec_control = secondary_exec_controls_get(vmx); sec_exec_control &= ~(SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES | SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE); @@ -5989,7 +6017,7 @@ void vmx_set_virtual_apic_mode(struct kvm_vcpu *vcpu) SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE; break; } - vmcs_write32(SECONDARY_VM_EXEC_CONTROL, sec_exec_control); + secondary_exec_controls_set(vmx, sec_exec_control); vmx_update_msr_bitmap(vcpu); } @@ -6107,76 +6135,81 @@ static void vmx_apicv_post_state_restore(struct kvm_vcpu *vcpu) memset(vmx->pi_desc.pir, 0, sizeof(vmx->pi_desc.pir)); } -static void vmx_complete_atomic_exit(struct vcpu_vmx *vmx) +static void handle_exception_nmi_irqoff(struct vcpu_vmx *vmx) { - u32 exit_intr_info = 0; - u16 basic_exit_reason = (u16)vmx->exit_reason; - - if (!(basic_exit_reason == EXIT_REASON_MCE_DURING_VMENTRY - || basic_exit_reason == EXIT_REASON_EXCEPTION_NMI)) - return; - - if (!(vmx->exit_reason & VMX_EXIT_REASONS_FAILED_VMENTRY)) - exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO); - vmx->exit_intr_info = exit_intr_info; + vmx->exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO); /* if exit due to PF check for async PF */ - if (is_page_fault(exit_intr_info)) + if (is_page_fault(vmx->exit_intr_info)) vmx->vcpu.arch.apf.host_apf_reason = kvm_read_and_reset_pf_reason(); /* Handle machine checks before interrupts are enabled */ - if (basic_exit_reason == EXIT_REASON_MCE_DURING_VMENTRY || - is_machine_check(exit_intr_info)) + if (is_machine_check(vmx->exit_intr_info)) kvm_machine_check(); /* We need to handle NMIs before interrupts are enabled */ - if (is_nmi(exit_intr_info)) { + if (is_nmi(vmx->exit_intr_info)) { kvm_before_interrupt(&vmx->vcpu); asm("int $2"); kvm_after_interrupt(&vmx->vcpu); } } -static void vmx_handle_external_intr(struct kvm_vcpu *vcpu) +static void handle_external_interrupt_irqoff(struct kvm_vcpu *vcpu) { - u32 exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO); - - if ((exit_intr_info & (INTR_INFO_VALID_MASK | INTR_INFO_INTR_TYPE_MASK)) - == (INTR_INFO_VALID_MASK | INTR_TYPE_EXT_INTR)) { - unsigned int vector; - unsigned long entry; - gate_desc *desc; - struct vcpu_vmx *vmx = to_vmx(vcpu); + unsigned int vector; + unsigned long entry; #ifdef CONFIG_X86_64 - unsigned long tmp; + unsigned long tmp; #endif + gate_desc *desc; + u32 intr_info; + + intr_info = vmcs_read32(VM_EXIT_INTR_INFO); + if (WARN_ONCE(!is_external_intr(intr_info), + "KVM: unexpected VM-Exit interrupt info: 0x%x", intr_info)) + return; - vector = exit_intr_info & INTR_INFO_VECTOR_MASK; - desc = (gate_desc *)vmx->host_idt_base + vector; - entry = gate_offset(desc); - asm volatile( + vector = intr_info & INTR_INFO_VECTOR_MASK; + desc = (gate_desc *)host_idt_base + vector; + entry = gate_offset(desc); + + kvm_before_interrupt(vcpu); + + asm volatile( #ifdef CONFIG_X86_64 - "mov %%" _ASM_SP ", %[sp]\n\t" - "and $0xfffffffffffffff0, %%" _ASM_SP "\n\t" - "push $%c[ss]\n\t" - "push %[sp]\n\t" + "mov %%" _ASM_SP ", %[sp]\n\t" + "and $0xfffffffffffffff0, %%" _ASM_SP "\n\t" + "push $%c[ss]\n\t" + "push %[sp]\n\t" #endif - "pushf\n\t" - __ASM_SIZE(push) " $%c[cs]\n\t" - CALL_NOSPEC - : + "pushf\n\t" + __ASM_SIZE(push) " $%c[cs]\n\t" + CALL_NOSPEC + : #ifdef CONFIG_X86_64 - [sp]"=&r"(tmp), + [sp]"=&r"(tmp), #endif - ASM_CALL_CONSTRAINT - : - THUNK_TARGET(entry), - [ss]"i"(__KERNEL_DS), - [cs]"i"(__KERNEL_CS) - ); - } + ASM_CALL_CONSTRAINT + : + THUNK_TARGET(entry), + [ss]"i"(__KERNEL_DS), + [cs]"i"(__KERNEL_CS) + ); + + kvm_after_interrupt(vcpu); +} +STACK_FRAME_NON_STANDARD(handle_external_interrupt_irqoff); + +static void vmx_handle_exit_irqoff(struct kvm_vcpu *vcpu) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + + if (vmx->exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT) + handle_external_interrupt_irqoff(vcpu); + else if (vmx->exit_reason == EXIT_REASON_EXCEPTION_NMI) + handle_exception_nmi_irqoff(vmx); } -STACK_FRAME_NON_STANDARD(vmx_handle_external_intr); static bool vmx_has_emulated_msr(int index) { @@ -6187,6 +6220,8 @@ static bool vmx_has_emulated_msr(int index) * real mode. */ return enable_unrestricted_guest || emulate_invalid_guest_state; + case MSR_IA32_VMX_BASIC ... MSR_IA32_VMX_VMFUNC: + return nested; case MSR_AMD64_VIRT_SPEC_CTRL: /* This is AMD only. */ return false; @@ -6332,15 +6367,6 @@ static void atomic_switch_perf_msrs(struct vcpu_vmx *vmx) msrs[i].host, false); } -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); @@ -6348,11 +6374,9 @@ static void vmx_update_hv_timer(struct kvm_vcpu *vcpu) u32 delta_tsc; if (vmx->req_immediate_exit) { - vmx_arm_hv_timer(vmx, 0); - return; - } - - if (vmx->hv_deadline_tsc != -1) { + vmcs_write32(VMX_PREEMPTION_TIMER_VALUE, 0); + vmx->loaded_vmcs->hv_timer_soft_disabled = false; + } else if (vmx->hv_deadline_tsc != -1) { tscl = rdtsc(); if (vmx->hv_deadline_tsc > tscl) /* set_hv_timer ensures the delta fits in 32-bits */ @@ -6361,14 +6385,12 @@ static void vmx_update_hv_timer(struct kvm_vcpu *vcpu) else delta_tsc = 0; - vmx_arm_hv_timer(vmx, delta_tsc); - return; + vmcs_write32(VMX_PREEMPTION_TIMER_VALUE, delta_tsc); + vmx->loaded_vmcs->hv_timer_soft_disabled = false; + } else if (!vmx->loaded_vmcs->hv_timer_soft_disabled) { + vmcs_write32(VMX_PREEMPTION_TIMER_VALUE, -1); + vmx->loaded_vmcs->hv_timer_soft_disabled = true; } - - 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; } void vmx_update_host_rsp(struct vcpu_vmx *vmx, unsigned long host_rsp) @@ -6401,8 +6423,8 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu) vmcs_write32(PLE_WINDOW, vmx->ple_window); } - if (vmx->nested.need_vmcs12_sync) - nested_sync_from_vmcs12(vcpu); + if (vmx->nested.need_vmcs12_to_shadow_sync) + nested_sync_vmcs12_to_shadow(vcpu); if (test_bit(VCPU_REGS_RSP, (unsigned long *)&vcpu->arch.regs_dirty)) vmcs_writel(GUEST_RSP, vcpu->arch.regs[VCPU_REGS_RSP]); @@ -6440,7 +6462,12 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu) atomic_switch_perf_msrs(vmx); - vmx_update_hv_timer(vcpu); + if (enable_preemption_timer) + vmx_update_hv_timer(vcpu); + + if (lapic_in_kernel(vcpu) && + vcpu->arch.apic->lapic_timer.timer_advance_ns) + kvm_wait_lapic_expire(vcpu); /* * If this vCPU has touched SPEC_CTRL, restore the guest's value if @@ -6533,13 +6560,15 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu) vmx->idt_vectoring_info = 0; vmx->exit_reason = vmx->fail ? 0xdead : vmcs_read32(VM_EXIT_REASON); + if ((u16)vmx->exit_reason == EXIT_REASON_MCE_DURING_VMENTRY) + kvm_machine_check(); + if (vmx->fail || (vmx->exit_reason & VMX_EXIT_REASONS_FAILED_VMENTRY)) return; vmx->loaded_vmcs->launched = 1; vmx->idt_vectoring_info = vmcs_read32(IDT_VECTORING_INFO_FIELD); - vmx_complete_atomic_exit(vmx); vmx_recover_nmi_blocking(vmx); vmx_complete_interrupts(vmx); } @@ -6630,6 +6659,12 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_CS, MSR_TYPE_RW); vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_ESP, MSR_TYPE_RW); vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_EIP, MSR_TYPE_RW); + if (kvm_cstate_in_guest(kvm)) { + vmx_disable_intercept_for_msr(msr_bitmap, MSR_CORE_C1_RES, MSR_TYPE_R); + vmx_disable_intercept_for_msr(msr_bitmap, MSR_CORE_C3_RESIDENCY, MSR_TYPE_R); + vmx_disable_intercept_for_msr(msr_bitmap, MSR_CORE_C6_RESIDENCY, MSR_TYPE_R); + vmx_disable_intercept_for_msr(msr_bitmap, MSR_CORE_C7_RESIDENCY, MSR_TYPE_R); + } vmx->msr_bitmap_mode = 0; vmx->loaded_vmcs = &vmx->vmcs01; @@ -6726,22 +6761,22 @@ static int vmx_vm_init(struct kvm *kvm) return 0; } -static void __init vmx_check_processor_compat(void *rtn) +static int __init vmx_check_processor_compat(void) { struct vmcs_config vmcs_conf; struct vmx_capability vmx_cap; - *(int *)rtn = 0; if (setup_vmcs_config(&vmcs_conf, &vmx_cap) < 0) - *(int *)rtn = -EIO; + return -EIO; if (nested) nested_vmx_setup_ctls_msrs(&vmcs_conf.nested, vmx_cap.ept, enable_apicv); if (memcmp(&vmcs_config, &vmcs_conf, sizeof(struct vmcs_config)) != 0) { printk(KERN_ERR "kvm: CPU %d feature inconsistency!\n", smp_processor_id()); - *(int *)rtn = -EIO; + return -EIO; } + return 0; } static u64 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) @@ -6795,7 +6830,7 @@ static int vmx_get_lpage_level(void) return PT_PDPE_LEVEL; } -static void vmcs_set_secondary_exec_control(u32 new_ctl) +static void vmcs_set_secondary_exec_control(struct vcpu_vmx *vmx) { /* * These bits in the secondary execution controls field @@ -6809,10 +6844,10 @@ static void vmcs_set_secondary_exec_control(u32 new_ctl) SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES | SECONDARY_EXEC_DESC; - u32 cur_ctl = vmcs_read32(SECONDARY_VM_EXEC_CONTROL); + u32 new_ctl = vmx->secondary_exec_control; + u32 cur_ctl = secondary_exec_controls_get(vmx); - vmcs_write32(SECONDARY_VM_EXEC_CONTROL, - (new_ctl & ~mask) | (cur_ctl & mask)); + secondary_exec_controls_set(vmx, (new_ctl & ~mask) | (cur_ctl & mask)); } /* @@ -6950,7 +6985,7 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu) if (cpu_has_secondary_exec_ctrls()) { vmx_compute_secondary_exec_control(vmx); - vmcs_set_secondary_exec_control(vmx->secondary_exec_control); + vmcs_set_secondary_exec_control(vmx); } if (nested_vmx_allowed(vcpu)) @@ -7424,10 +7459,14 @@ static bool vmx_need_emulation_on_page_fault(struct kvm_vcpu *vcpu) static __init int hardware_setup(void) { unsigned long host_bndcfgs; + struct desc_ptr dt; int r, i; rdmsrl_safe(MSR_EFER, &host_efer); + store_idt(&dt); + host_idt_base = dt.address; + for (i = 0; i < ARRAY_SIZE(vmx_msr_index); ++i) kvm_define_shared_msr(i, vmx_msr_index[i]); @@ -7531,17 +7570,33 @@ static __init int hardware_setup(void) } if (!cpu_has_vmx_preemption_timer()) - kvm_x86_ops->request_immediate_exit = __kvm_request_immediate_exit; + enable_preemption_timer = false; - if (cpu_has_vmx_preemption_timer() && enable_preemption_timer) { + if (enable_preemption_timer) { + u64 use_timer_freq = 5000ULL * 1000 * 1000; u64 vmx_msr; rdmsrl(MSR_IA32_VMX_MISC, vmx_msr); cpu_preemption_timer_multi = vmx_msr & VMX_MISC_PREEMPTION_TIMER_RATE_MASK; - } else { + + if (tsc_khz) + use_timer_freq = (u64)tsc_khz * 1000; + use_timer_freq >>= cpu_preemption_timer_multi; + + /* + * KVM "disables" the preemption timer by setting it to its max + * value. Don't use the timer if it might cause spurious exits + * at a rate faster than 0.1 Hz (of uninterrupted guest time). + */ + if (use_timer_freq > 0xffffffffu / 10) + enable_preemption_timer = false; + } + + if (!enable_preemption_timer) { kvm_x86_ops->set_hv_timer = NULL; kvm_x86_ops->cancel_hv_timer = NULL; + kvm_x86_ops->request_immediate_exit = __kvm_request_immediate_exit; } kvm_set_posted_intr_wakeup_handler(wakeup_handler); @@ -7683,7 +7738,7 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = { .set_tdp_cr3 = vmx_set_cr3, .check_intercept = vmx_check_intercept, - .handle_external_intr = vmx_handle_external_intr, + .handle_exit_irqoff = vmx_handle_exit_irqoff, .mpx_supported = vmx_mpx_supported, .xsaves_supported = vmx_xsaves_supported, .umip_emulated = vmx_umip_emulated, diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 61128b48c503..82d0bc3a4d52 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -109,14 +109,21 @@ struct nested_vmx { * to guest memory during VM exit. */ struct vmcs12 *cached_shadow_vmcs12; + /* * Indicates if the shadow vmcs or enlightened vmcs must be updated * with the data held by struct vmcs12. */ - bool need_vmcs12_sync; + bool need_vmcs12_to_shadow_sync; bool dirty_vmcs12; /* + * Indicates lazily loaded guest state has not yet been decached from + * vmcs02. + */ + bool need_sync_vmcs02_to_vmcs12_rare; + + /* * vmcs02 has been initialized, i.e. state that is constant for * vmcs02 has been written to the backing VMCS. Initialization * is delayed until L1 actually attempts to run a nested VM. @@ -180,14 +187,24 @@ struct vcpu_vmx { struct kvm_vcpu vcpu; u8 fail; u8 msr_bitmap_mode; + + /* + * If true, host state has been stored in vmx->loaded_vmcs for + * the CPU registers that only need to be switched when transitioning + * to/from the kernel, and the registers have been loaded with guest + * values. If false, host state is loaded in the CPU registers + * and vmx->loaded_vmcs->host_state is invalid. + */ + bool guest_state_loaded; + u32 exit_intr_info; u32 idt_vectoring_info; ulong rflags; + struct shared_msr_entry *guest_msrs; int nmsrs; int save_nmsrs; - bool guest_msrs_dirty; - unsigned long host_idt_base; + bool guest_msrs_ready; #ifdef CONFIG_X86_64 u64 msr_host_kernel_gs_base; u64 msr_guest_kernel_gs_base; @@ -195,21 +212,15 @@ struct vcpu_vmx { u64 spec_ctrl; - u32 vm_entry_controls_shadow; - u32 vm_exit_controls_shadow; u32 secondary_exec_control; /* * loaded_vmcs points to the VMCS currently used in this vcpu. For a * non-nested (L1) guest, it always points to vmcs01. For a nested - * guest (L2), it points to a different VMCS. loaded_cpu_state points - * to the VMCS whose state is loaded into the CPU registers that only - * need to be switched when transitioning to/from the kernel; a NULL - * value indicates that host state is loaded. + * guest (L2), it points to a different VMCS. */ struct loaded_vmcs vmcs01; struct loaded_vmcs *loaded_vmcs; - struct loaded_vmcs *loaded_cpu_state; struct msr_autoload { struct vmx_msrs guest; @@ -260,8 +271,6 @@ struct vcpu_vmx { unsigned long host_debugctlmsr; - u64 msr_ia32_power_ctl; - /* * Only bits masked by msr_ia32_feature_control_valid_bits can be set in * msr_ia32_feature_control. FEATURE_CONTROL_LOCKED is always included @@ -292,12 +301,14 @@ struct kvm_vmx { }; bool nested_vmx_allowed(struct kvm_vcpu *vcpu); +void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu); void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu); -void vmx_vcpu_put(struct kvm_vcpu *vcpu); int allocate_vpid(void); void free_vpid(int vpid); void vmx_set_constant_host_state(struct vcpu_vmx *vmx); void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu); +void vmx_set_host_fs_gs(struct vmcs_host_state *host, u16 fs_sel, u16 gs_sel, + unsigned long fs_base, unsigned long gs_base); int vmx_get_cpl(struct kvm_vcpu *vcpu); unsigned long vmx_get_rflags(struct kvm_vcpu *vcpu); void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags); @@ -376,69 +387,31 @@ static inline u8 vmx_get_rvi(void) return vmcs_read16(GUEST_INTR_STATUS) & 0xff; } -static inline void vm_entry_controls_reset_shadow(struct vcpu_vmx *vmx) -{ - vmx->vm_entry_controls_shadow = vmcs_read32(VM_ENTRY_CONTROLS); -} - -static inline void vm_entry_controls_init(struct vcpu_vmx *vmx, u32 val) -{ - vmcs_write32(VM_ENTRY_CONTROLS, val); - vmx->vm_entry_controls_shadow = val; -} - -static inline void vm_entry_controls_set(struct vcpu_vmx *vmx, u32 val) -{ - if (vmx->vm_entry_controls_shadow != val) - vm_entry_controls_init(vmx, val); -} - -static inline u32 vm_entry_controls_get(struct vcpu_vmx *vmx) -{ - return vmx->vm_entry_controls_shadow; -} - -static inline void vm_entry_controls_setbit(struct vcpu_vmx *vmx, u32 val) -{ - vm_entry_controls_set(vmx, vm_entry_controls_get(vmx) | val); -} - -static inline void vm_entry_controls_clearbit(struct vcpu_vmx *vmx, u32 val) -{ - vm_entry_controls_set(vmx, vm_entry_controls_get(vmx) & ~val); -} - -static inline void vm_exit_controls_reset_shadow(struct vcpu_vmx *vmx) -{ - vmx->vm_exit_controls_shadow = vmcs_read32(VM_EXIT_CONTROLS); -} - -static inline void vm_exit_controls_init(struct vcpu_vmx *vmx, u32 val) -{ - vmcs_write32(VM_EXIT_CONTROLS, val); - vmx->vm_exit_controls_shadow = val; -} - -static inline void vm_exit_controls_set(struct vcpu_vmx *vmx, u32 val) -{ - if (vmx->vm_exit_controls_shadow != val) - vm_exit_controls_init(vmx, val); -} - -static inline u32 vm_exit_controls_get(struct vcpu_vmx *vmx) -{ - return vmx->vm_exit_controls_shadow; -} - -static inline void vm_exit_controls_setbit(struct vcpu_vmx *vmx, u32 val) -{ - vm_exit_controls_set(vmx, vm_exit_controls_get(vmx) | val); -} - -static inline void vm_exit_controls_clearbit(struct vcpu_vmx *vmx, u32 val) -{ - vm_exit_controls_set(vmx, vm_exit_controls_get(vmx) & ~val); +#define BUILD_CONTROLS_SHADOW(lname, uname) \ +static inline void lname##_controls_set(struct vcpu_vmx *vmx, u32 val) \ +{ \ + if (vmx->loaded_vmcs->controls_shadow.lname != val) { \ + vmcs_write32(uname, val); \ + vmx->loaded_vmcs->controls_shadow.lname = val; \ + } \ +} \ +static inline u32 lname##_controls_get(struct vcpu_vmx *vmx) \ +{ \ + return vmx->loaded_vmcs->controls_shadow.lname; \ +} \ +static inline void lname##_controls_setbit(struct vcpu_vmx *vmx, u32 val) \ +{ \ + lname##_controls_set(vmx, lname##_controls_get(vmx) | val); \ +} \ +static inline void lname##_controls_clearbit(struct vcpu_vmx *vmx, u32 val) \ +{ \ + lname##_controls_set(vmx, lname##_controls_get(vmx) & ~val); \ } +BUILD_CONTROLS_SHADOW(vm_entry, VM_ENTRY_CONTROLS) +BUILD_CONTROLS_SHADOW(vm_exit, VM_EXIT_CONTROLS) +BUILD_CONTROLS_SHADOW(pin, PIN_BASED_VM_EXEC_CONTROL) +BUILD_CONTROLS_SHADOW(exec, CPU_BASED_VM_EXEC_CONTROL) +BUILD_CONTROLS_SHADOW(secondary_exec, SECONDARY_VM_EXEC_CONTROL) static inline void vmx_segment_cache_clear(struct vcpu_vmx *vmx) { @@ -468,6 +441,7 @@ static inline u32 vmx_vmexit_ctrl(void) } u32 vmx_exec_control(struct vcpu_vmx *vmx); +u32 vmx_pin_based_exec_ctrl(struct vcpu_vmx *vmx); static inline struct kvm_vmx *to_kvm_vmx(struct kvm *kvm) { diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 63bb1ee8258e..4a0b74ecd1de 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -717,7 +717,7 @@ bool pdptrs_changed(struct kvm_vcpu *vcpu) gfn_t gfn; int r; - if (is_long_mode(vcpu) || !is_pae(vcpu) || !is_paging(vcpu)) + if (!is_pae_paging(vcpu)) return false; if (!test_bit(VCPU_EXREG_PDPTR, @@ -960,8 +960,8 @@ int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) if (is_long_mode(vcpu) && (cr3 & rsvd_bits(cpuid_maxphyaddr(vcpu), 63))) return 1; - else if (is_pae(vcpu) && is_paging(vcpu) && - !load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3)) + else if (is_pae_paging(vcpu) && + !load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3)) return 1; kvm_mmu_new_cr3(vcpu, cr3, skip_tlb_flush); @@ -1174,7 +1174,28 @@ static u32 emulated_msrs[] = { MSR_AMD64_VIRT_SPEC_CTRL, MSR_IA32_POWER_CTL, + /* + * The following list leaves out MSRs whose values are determined + * by arch/x86/kvm/vmx/nested.c based on CPUID or other MSRs. + * We always support the "true" VMX control MSRs, even if the host + * processor does not, so I am putting these registers here rather + * than in msrs_to_save. + */ + MSR_IA32_VMX_BASIC, + MSR_IA32_VMX_TRUE_PINBASED_CTLS, + MSR_IA32_VMX_TRUE_PROCBASED_CTLS, + MSR_IA32_VMX_TRUE_EXIT_CTLS, + MSR_IA32_VMX_TRUE_ENTRY_CTLS, + MSR_IA32_VMX_MISC, + MSR_IA32_VMX_CR0_FIXED0, + MSR_IA32_VMX_CR4_FIXED0, + MSR_IA32_VMX_VMCS_ENUM, + MSR_IA32_VMX_PROCBASED_CTLS2, + MSR_IA32_VMX_EPT_VPID_CAP, + MSR_IA32_VMX_VMFUNC, + MSR_K7_HWCR, + MSR_KVM_POLL_CONTROL, }; static unsigned num_emulated_msrs; @@ -1210,11 +1231,12 @@ static u32 msr_based_features[] = { static unsigned int num_msr_based_features; -u64 kvm_get_arch_capabilities(void) +static u64 kvm_get_arch_capabilities(void) { - u64 data; + u64 data = 0; - rdmsrl_safe(MSR_IA32_ARCH_CAPABILITIES, &data); + if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES)) + rdmsrl(MSR_IA32_ARCH_CAPABILITIES, data); /* * If we're doing cache flushes (either "always" or "cond") @@ -1230,7 +1252,6 @@ u64 kvm_get_arch_capabilities(void) return data; } -EXPORT_SYMBOL_GPL(kvm_get_arch_capabilities); static int kvm_get_msr_feature(struct kvm_msr_entry *msr) { @@ -2545,13 +2566,24 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) } break; case MSR_IA32_MISC_ENABLE: - vcpu->arch.ia32_misc_enable_msr = data; + if (!kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT) && + ((vcpu->arch.ia32_misc_enable_msr ^ data) & MSR_IA32_MISC_ENABLE_MWAIT)) { + if (!guest_cpuid_has(vcpu, X86_FEATURE_XMM3)) + return 1; + vcpu->arch.ia32_misc_enable_msr = data; + kvm_update_cpuid(vcpu); + } else { + vcpu->arch.ia32_misc_enable_msr = data; + } break; case MSR_IA32_SMBASE: if (!msr_info->host_initiated) return 1; vcpu->arch.smbase = data; break; + case MSR_IA32_POWER_CTL: + vcpu->arch.msr_ia32_power_ctl = data; + break; case MSR_IA32_TSC: kvm_write_tsc(vcpu, msr_info); break; @@ -2626,6 +2658,14 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return 1; break; + case MSR_KVM_POLL_CONTROL: + /* only enable bit supported */ + if (data & (-1ULL << 1)) + return 1; + + vcpu->arch.msr_kvm_poll_control = data; + break; + case MSR_IA32_MCG_CTL: case MSR_IA32_MCG_STATUS: case MSR_IA32_MC0_CTL ... MSR_IA32_MCx_CTL(KVM_MAX_MCE_BANKS) - 1: @@ -2803,6 +2843,9 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return 1; msr_info->data = vcpu->arch.arch_capabilities; break; + case MSR_IA32_POWER_CTL: + msr_info->data = vcpu->arch.msr_ia32_power_ctl; + break; case MSR_IA32_TSC: msr_info->data = kvm_scale_tsc(vcpu, rdtsc()) + vcpu->arch.tsc_offset; break; @@ -2875,6 +2918,9 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_KVM_PV_EOI_EN: msr_info->data = vcpu->arch.pv_eoi.msr_val; break; + case MSR_KVM_POLL_CONTROL: + msr_info->data = vcpu->arch.msr_kvm_poll_control; + break; case MSR_IA32_P5_MC_ADDR: case MSR_IA32_P5_MC_TYPE: case MSR_IA32_MCG_CAP: @@ -3084,6 +3130,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_SET_BOOT_CPU_ID: case KVM_CAP_SPLIT_IRQCHIP: case KVM_CAP_IMMEDIATE_EXIT: + case KVM_CAP_PMU_EVENT_FILTER: case KVM_CAP_GET_MSR_FEATURES: case KVM_CAP_MSR_PLATFORM_INFO: case KVM_CAP_EXCEPTION_PAYLOAD: @@ -3096,7 +3143,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) r = KVM_CLOCK_TSC_STABLE; break; case KVM_CAP_X86_DISABLE_EXITS: - r |= KVM_X86_DISABLE_EXITS_HLT | KVM_X86_DISABLE_EXITS_PAUSE; + r |= KVM_X86_DISABLE_EXITS_HLT | KVM_X86_DISABLE_EXITS_PAUSE | + KVM_X86_DISABLE_EXITS_CSTATE; if(kvm_can_mwait_in_guest()) r |= KVM_X86_DISABLE_EXITS_MWAIT; break; @@ -4613,6 +4661,8 @@ split_irqchip_unlock: kvm->arch.hlt_in_guest = true; if (cap->args[0] & KVM_X86_DISABLE_EXITS_PAUSE) kvm->arch.pause_in_guest = true; + if (cap->args[0] & KVM_X86_DISABLE_EXITS_CSTATE) + kvm->arch.cstate_in_guest = true; r = 0; break; case KVM_CAP_MSR_PLATFORM_INFO: @@ -4927,6 +4977,9 @@ set_identity_unlock: r = kvm_vm_ioctl_hv_eventfd(kvm, &hvevfd); break; } + case KVM_SET_PMU_EVENT_FILTER: + r = kvm_vm_ioctl_set_pmu_event_filter(kvm, argp); + break; default: r = -ENOTTY; } @@ -6379,7 +6432,7 @@ static bool kvm_vcpu_check_breakpoint(struct kvm_vcpu *vcpu, int *r) vcpu->arch.db); if (dr6 != 0) { - vcpu->arch.dr6 &= ~15; + vcpu->arch.dr6 &= ~DR_TRAP_BITS; vcpu->arch.dr6 |= dr6 | DR6_RTM; kvm_queue_exception(vcpu, DB_VECTOR); *r = EMULATE_DONE; @@ -6706,7 +6759,7 @@ static void kvm_hyperv_tsc_notifier(void) struct kvm_vcpu *vcpu; int cpu; - spin_lock(&kvm_lock); + mutex_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) kvm_make_mclock_inprogress_request(kvm); @@ -6732,7 +6785,7 @@ static void kvm_hyperv_tsc_notifier(void) spin_unlock(&ka->pvclock_gtod_sync_lock); } - spin_unlock(&kvm_lock); + mutex_unlock(&kvm_lock); } #endif @@ -6783,17 +6836,17 @@ static void __kvmclock_cpufreq_notifier(struct cpufreq_freqs *freq, int cpu) smp_call_function_single(cpu, tsc_khz_changed, freq, 1); - spin_lock(&kvm_lock); + mutex_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) { kvm_for_each_vcpu(i, vcpu, kvm) { if (vcpu->cpu != cpu) continue; kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); - if (vcpu->cpu != smp_processor_id()) + if (vcpu->cpu != raw_smp_processor_id()) send_ipi = 1; } } - spin_unlock(&kvm_lock); + mutex_unlock(&kvm_lock); if (freq->old < freq->new && send_ipi) { /* @@ -6908,35 +6961,6 @@ static struct perf_guest_info_callbacks kvm_guest_cbs = { .handle_intel_pt_intr = kvm_handle_intel_pt_intr, }; -static void kvm_set_mmio_spte_mask(void) -{ - u64 mask; - int maxphyaddr = boot_cpu_data.x86_phys_bits; - - /* - * Set the reserved bits and the present bit of an paging-structure - * entry to generate page fault with PFER.RSV = 1. - */ - - /* - * Mask the uppermost physical address bit, which would be reserved as - * long as the supported physical address width is less than 52. - */ - mask = 1ull << 51; - - /* Set the present bit. */ - mask |= 1ull; - - /* - * If reserved bit is not supported, clear the present bit to disable - * mmio page fault. - */ - if (IS_ENABLED(CONFIG_X86_64) && maxphyaddr == 52) - mask &= ~1ull; - - kvm_mmu_set_mmio_spte_mask(mask, mask); -} - #ifdef CONFIG_X86_64 static void pvclock_gtod_update_fn(struct work_struct *work) { @@ -6945,12 +6969,12 @@ static void pvclock_gtod_update_fn(struct work_struct *work) struct kvm_vcpu *vcpu; int i; - spin_lock(&kvm_lock); + mutex_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) kvm_for_each_vcpu(i, vcpu, kvm) kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu); atomic_set(&kvm_guest_has_master_clock, 0); - spin_unlock(&kvm_lock); + mutex_unlock(&kvm_lock); } static DECLARE_WORK(pvclock_gtod_work, pvclock_gtod_update_fn); @@ -7033,8 +7057,6 @@ int kvm_arch_init(void *opaque) if (r) goto out_free_percpu; - kvm_set_mmio_spte_mask(); - kvm_x86_ops = ops; kvm_mmu_set_mask_ptes(PT_USER_MASK, PT_ACCESSED_MASK, @@ -7173,6 +7195,23 @@ void kvm_vcpu_deactivate_apicv(struct kvm_vcpu *vcpu) kvm_x86_ops->refresh_apicv_exec_ctrl(vcpu); } +static void kvm_sched_yield(struct kvm *kvm, unsigned long dest_id) +{ + struct kvm_vcpu *target = NULL; + struct kvm_apic_map *map; + + rcu_read_lock(); + map = rcu_dereference(kvm->arch.apic_map); + + if (likely(map) && dest_id <= map->max_apic_id && map->phys_map[dest_id]) + target = map->phys_map[dest_id]->vcpu; + + rcu_read_unlock(); + + if (target) + kvm_vcpu_yield_to(target); +} + int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) { unsigned long nr, a0, a1, a2, a3, ret; @@ -7219,6 +7258,10 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) case KVM_HC_SEND_IPI: ret = kvm_pv_send_ipi(vcpu->kvm, a0, a1, a2, a3, op_64_bit); break; + case KVM_HC_SCHED_YIELD: + kvm_sched_yield(vcpu->kvm, a0); + ret = 0; + break; default: ret = -KVM_ENOSYS; break; @@ -7951,9 +7994,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) } trace_kvm_entry(vcpu->vcpu_id); - if (lapic_in_kernel(vcpu) && - vcpu->arch.apic->lapic_timer.timer_advance_ns) - wait_lapic_expire(vcpu); guest_enter_irqoff(); fpregs_assert_state_consistent(); @@ -8002,13 +8042,29 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) vcpu->mode = OUTSIDE_GUEST_MODE; smp_wmb(); - kvm_before_interrupt(vcpu); - kvm_x86_ops->handle_external_intr(vcpu); - kvm_after_interrupt(vcpu); + kvm_x86_ops->handle_exit_irqoff(vcpu); + /* + * Consume any pending interrupts, including the possible source of + * VM-Exit on SVM and any ticks that occur between VM-Exit and now. + * An instruction is required after local_irq_enable() to fully unblock + * interrupts on processors that implement an interrupt shadow, the + * stat.exits increment will do nicely. + */ + kvm_before_interrupt(vcpu); + local_irq_enable(); ++vcpu->stat.exits; + local_irq_disable(); + kvm_after_interrupt(vcpu); guest_exit_irqoff(); + if (lapic_in_kernel(vcpu)) { + s64 delta = vcpu->arch.apic->lapic_timer.advance_expire_delta; + if (delta != S64_MIN) { + trace_kvm_wait_lapic_expire(vcpu->vcpu_id, delta); + vcpu->arch.apic->lapic_timer.advance_expire_delta = S64_MIN; + } + } local_irq_enable(); preempt_enable(); @@ -8594,7 +8650,7 @@ 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) && is_paging(vcpu)) { + if (is_pae_paging(vcpu)) { load_pdptrs(vcpu, vcpu->arch.walk_mmu, kvm_read_cr3(vcpu)); mmu_reset_needed = 1; } @@ -8875,6 +8931,10 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) msr.host_initiated = true; kvm_write_tsc(vcpu, &msr); vcpu_put(vcpu); + + /* poll control enabled by default */ + vcpu->arch.msr_kvm_poll_control = 1; + mutex_unlock(&vcpu->mutex); if (!kvmclock_periodic_sync) @@ -9107,9 +9167,9 @@ void kvm_arch_hardware_unsetup(void) kvm_x86_ops->hardware_unsetup(); } -void kvm_arch_check_processor_compat(void *rtn) +int kvm_arch_check_processor_compat(void) { - kvm_x86_ops->check_processor_compatibility(rtn); + return kvm_x86_ops->check_processor_compatibility(); } bool kvm_vcpu_is_reset_bsp(struct kvm_vcpu *vcpu) @@ -9381,6 +9441,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm) kvm_ioapic_destroy(kvm); kvm_free_vcpus(kvm); kvfree(rcu_dereference_check(kvm->arch.apic_map, 1)); + kfree(srcu_dereference_check(kvm->arch.pmu_event_filter, &kvm->srcu, 1)); kvm_mmu_uninit_vm(kvm); kvm_page_track_cleanup(kvm); kvm_hv_destroy_vm(kvm); @@ -9789,6 +9850,36 @@ static int apf_get_user(struct kvm_vcpu *vcpu, u32 *val) sizeof(u32)); } +static bool kvm_can_deliver_async_pf(struct kvm_vcpu *vcpu) +{ + if (!vcpu->arch.apf.delivery_as_pf_vmexit && is_guest_mode(vcpu)) + return false; + + if (!(vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED) || + (vcpu->arch.apf.send_user_only && + kvm_x86_ops->get_cpl(vcpu) == 0)) + return false; + + return true; +} + +bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu) +{ + if (unlikely(!lapic_in_kernel(vcpu) || + kvm_event_needs_reinjection(vcpu) || + vcpu->arch.exception.pending)) + return false; + + if (kvm_hlt_in_guest(vcpu->kvm) && !kvm_can_deliver_async_pf(vcpu)) + return false; + + /* + * If interrupts are off we cannot even use an artificial + * halt state. + */ + return kvm_x86_ops->interrupt_allowed(vcpu); +} + void kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu, struct kvm_async_pf *work) { @@ -9797,11 +9888,8 @@ void kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu, trace_kvm_async_pf_not_present(work->arch.token, work->gva); kvm_add_async_pf_gfn(vcpu, work->arch.gfn); - if (!(vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED) || - (vcpu->arch.apf.send_user_only && - kvm_x86_ops->get_cpl(vcpu) == 0)) - kvm_make_request(KVM_REQ_APF_HALT, vcpu); - else if (!apf_put_user(vcpu, KVM_PV_REASON_PAGE_NOT_PRESENT)) { + if (kvm_can_deliver_async_pf(vcpu) && + !apf_put_user(vcpu, KVM_PV_REASON_PAGE_NOT_PRESENT)) { fault.vector = PF_VECTOR; fault.error_code_valid = true; fault.error_code = 0; @@ -9809,6 +9897,16 @@ void kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu, fault.address = work->arch.token; fault.async_page_fault = true; kvm_inject_page_fault(vcpu, &fault); + } else { + /* + * It is not possible to deliver a paravirtualized asynchronous + * page fault, but putting the guest in an artificial halt state + * can be beneficial nevertheless: if an interrupt arrives, we + * can deliver it timely and perhaps the guest will schedule + * another process. When the instruction that triggered a page + * fault is retried, hopefully the page will be ready in the host. + */ + kvm_make_request(KVM_REQ_APF_HALT, vcpu); } } @@ -9949,6 +10047,13 @@ bool kvm_vector_hashing_enabled(void) } EXPORT_SYMBOL_GPL(kvm_vector_hashing_enabled); +bool kvm_arch_no_poll(struct kvm_vcpu *vcpu) +{ + return (vcpu->arch.msr_kvm_poll_control & 1) == 0; +} +EXPORT_SYMBOL_GPL(kvm_arch_no_poll); + + EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_exit); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_fast_mmio); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_inj_virq); diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index a470ff0868c5..e08a12892e8b 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -139,6 +139,11 @@ static inline int is_paging(struct kvm_vcpu *vcpu) return likely(kvm_read_cr0_bits(vcpu, X86_CR0_PG)); } +static inline bool is_pae_paging(struct kvm_vcpu *vcpu) +{ + return !is_long_mode(vcpu) && is_pae(vcpu) && is_paging(vcpu); +} + static inline u32 bit(int bitno) { return 1 << (bitno & 31); @@ -333,6 +338,11 @@ static inline bool kvm_pause_in_guest(struct kvm *kvm) return kvm->arch.pause_in_guest; } +static inline bool kvm_cstate_in_guest(struct kvm *kvm) +{ + return kvm->arch.cstate_in_guest; +} + DECLARE_PER_CPU(struct kvm_vcpu *, current_vcpu); static inline void kvm_before_interrupt(struct kvm_vcpu *vcpu) diff --git a/arch/x86/mm/debug_pagetables.c b/arch/x86/mm/debug_pagetables.c index c6f4982d5401..39001a401eff 100644 --- a/arch/x86/mm/debug_pagetables.c +++ b/arch/x86/mm/debug_pagetables.c @@ -26,8 +26,6 @@ static int ptdump_curknl_show(struct seq_file *m, void *v) DEFINE_SHOW_ATTRIBUTE(ptdump_curknl); #ifdef CONFIG_PAGE_TABLE_ISOLATION -static struct dentry *pe_curusr; - static int ptdump_curusr_show(struct seq_file *m, void *v) { if (current->mm->pgd) { @@ -42,8 +40,6 @@ DEFINE_SHOW_ATTRIBUTE(ptdump_curusr); #endif #if defined(CONFIG_EFI) && defined(CONFIG_X86_64) -static struct dentry *pe_efi; - static int ptdump_efi_show(struct seq_file *m, void *v) { if (efi_mm.pgd) @@ -54,41 +50,24 @@ static int ptdump_efi_show(struct seq_file *m, void *v) DEFINE_SHOW_ATTRIBUTE(ptdump_efi); #endif -static struct dentry *dir, *pe_knl, *pe_curknl; +static struct dentry *dir; static int __init pt_dump_debug_init(void) { dir = debugfs_create_dir("page_tables", NULL); - if (!dir) - return -ENOMEM; - - pe_knl = debugfs_create_file("kernel", 0400, dir, NULL, - &ptdump_fops); - if (!pe_knl) - goto err; - pe_curknl = debugfs_create_file("current_kernel", 0400, - dir, NULL, &ptdump_curknl_fops); - if (!pe_curknl) - goto err; + debugfs_create_file("kernel", 0400, dir, NULL, &ptdump_fops); + debugfs_create_file("current_kernel", 0400, dir, NULL, + &ptdump_curknl_fops); #ifdef CONFIG_PAGE_TABLE_ISOLATION - pe_curusr = debugfs_create_file("current_user", 0400, - dir, NULL, &ptdump_curusr_fops); - if (!pe_curusr) - goto err; + debugfs_create_file("current_user", 0400, dir, NULL, + &ptdump_curusr_fops); #endif - #if defined(CONFIG_EFI) && defined(CONFIG_X86_64) - pe_efi = debugfs_create_file("efi", 0400, dir, NULL, &ptdump_efi_fops); - if (!pe_efi) - goto err; + debugfs_create_file("efi", 0400, dir, NULL, &ptdump_efi_fops); #endif - return 0; -err: - debugfs_remove_recursive(dir); - return -ENOMEM; } static void __exit pt_dump_debug_exit(void) diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index 1f67b1e15bf6..44816ff6411f 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -13,33 +13,17 @@ phys_addr_t physical_mask __ro_after_init = (1ULL << __PHYSICAL_MASK_SHIFT) - 1; EXPORT_SYMBOL(physical_mask); #endif -#define PGALLOC_GFP (GFP_KERNEL_ACCOUNT | __GFP_ZERO) - #ifdef CONFIG_HIGHPTE -#define PGALLOC_USER_GFP __GFP_HIGHMEM +#define PGTABLE_HIGHMEM __GFP_HIGHMEM #else -#define PGALLOC_USER_GFP 0 +#define PGTABLE_HIGHMEM 0 #endif -gfp_t __userpte_alloc_gfp = PGALLOC_GFP | PGALLOC_USER_GFP; - -pte_t *pte_alloc_one_kernel(struct mm_struct *mm) -{ - return (pte_t *)__get_free_page(PGALLOC_GFP & ~__GFP_ACCOUNT); -} +gfp_t __userpte_alloc_gfp = GFP_PGTABLE_USER | PGTABLE_HIGHMEM; pgtable_t pte_alloc_one(struct mm_struct *mm) { - struct page *pte; - - pte = alloc_pages(__userpte_alloc_gfp, 0); - if (!pte) - return NULL; - if (!pgtable_page_ctor(pte)) { - __free_page(pte); - return NULL; - } - return pte; + return __pte_alloc_one(mm, __userpte_alloc_gfp); } static int __init setup_userpte(char *arg) @@ -235,7 +219,7 @@ static int preallocate_pmds(struct mm_struct *mm, pmd_t *pmds[], int count) { int i; bool failed = false; - gfp_t gfp = PGALLOC_GFP; + gfp_t gfp = GFP_PGTABLE_USER; if (mm == &init_mm) gfp &= ~__GFP_ACCOUNT; @@ -399,14 +383,14 @@ static inline pgd_t *_pgd_alloc(void) * We allocate one page for pgd. */ if (!SHARED_KERNEL_PMD) - return (pgd_t *)__get_free_pages(PGALLOC_GFP, + return (pgd_t *)__get_free_pages(GFP_PGTABLE_USER, PGD_ALLOCATION_ORDER); /* * Now PAE kernel is not running as a Xen domain. We can allocate * a 32-byte slab for pgd to save memory space. */ - return kmem_cache_alloc(pgd_cache, PGALLOC_GFP); + return kmem_cache_alloc(pgd_cache, GFP_PGTABLE_USER); } static inline void _pgd_free(pgd_t *pgd) @@ -424,7 +408,8 @@ void __init pgd_cache_init(void) static inline pgd_t *_pgd_alloc(void) { - return (pgd_t *)__get_free_pages(PGALLOC_GFP, PGD_ALLOCATION_ORDER); + return (pgd_t *)__get_free_pages(GFP_PGTABLE_USER, + PGD_ALLOCATION_ORDER); } static inline void _pgd_free(pgd_t *pgd) diff --git a/arch/x86/platform/atom/punit_atom_debug.c b/arch/x86/platform/atom/punit_atom_debug.c index 17185d73d649..ee6b0780bea1 100644 --- a/arch/x86/platform/atom/punit_atom_debug.c +++ b/arch/x86/platform/atom/punit_atom_debug.c @@ -104,24 +104,12 @@ DEFINE_SHOW_ATTRIBUTE(punit_dev_state); static struct dentry *punit_dbg_file; -static int punit_dbgfs_register(struct punit_device *punit_device) +static void punit_dbgfs_register(struct punit_device *punit_device) { - struct dentry *dev_state; - punit_dbg_file = debugfs_create_dir("punit_atom", NULL); - if (!punit_dbg_file) - return -ENXIO; - - dev_state = debugfs_create_file("dev_power_state", 0444, - punit_dbg_file, punit_device, - &punit_dev_state_fops); - if (!dev_state) { - pr_err("punit_dev_state register failed\n"); - debugfs_remove(punit_dbg_file); - return -ENXIO; - } - return 0; + debugfs_create_file("dev_power_state", 0444, punit_dbg_file, + punit_device, &punit_dev_state_fops); } static void punit_dbgfs_unregister(void) @@ -145,15 +133,12 @@ MODULE_DEVICE_TABLE(x86cpu, intel_punit_cpu_ids); static int __init punit_atom_debug_init(void) { const struct x86_cpu_id *id; - int ret; id = x86_match_cpu(intel_punit_cpu_ids); if (!id) return -ENODEV; - ret = punit_dbgfs_register((struct punit_device *)id->driver_data); - if (ret < 0) - return ret; + punit_dbgfs_register((struct punit_device *)id->driver_data); return 0; } diff --git a/arch/x86/platform/intel-quark/imr.c b/arch/x86/platform/intel-quark/imr.c index b5420371d32d..6dd25dc5f027 100644 --- a/arch/x86/platform/intel-quark/imr.c +++ b/arch/x86/platform/intel-quark/imr.c @@ -35,7 +35,6 @@ #include <linux/types.h> struct imr_device { - struct dentry *file; bool init; struct mutex lock; int max_imr; @@ -231,13 +230,11 @@ DEFINE_SHOW_ATTRIBUTE(imr_dbgfs_state); * imr_debugfs_register - register debugfs hooks. * * @idev: pointer to imr_device structure. - * @return: 0 on success - errno on failure. */ -static int imr_debugfs_register(struct imr_device *idev) +static void imr_debugfs_register(struct imr_device *idev) { - idev->file = debugfs_create_file("imr_state", 0444, NULL, idev, - &imr_dbgfs_state_fops); - return PTR_ERR_OR_ZERO(idev->file); + debugfs_create_file("imr_state", 0444, NULL, idev, + &imr_dbgfs_state_fops); } /** @@ -582,7 +579,6 @@ static const struct x86_cpu_id imr_ids[] __initconst = { static int __init imr_init(void) { struct imr_device *idev = &imr_dev; - int ret; if (!x86_match_cpu(imr_ids) || !iosf_mbi_available()) return -ENODEV; @@ -592,9 +588,7 @@ static int __init imr_init(void) idev->init = true; mutex_init(&idev->lock); - ret = imr_debugfs_register(idev); - if (ret != 0) - pr_warn("debugfs register failed!\n"); + imr_debugfs_register(idev); imr_fixup_memmap(idev); return 0; } diff --git a/arch/x86/platform/intel/iosf_mbi.c b/arch/x86/platform/intel/iosf_mbi.c index b393eaa798ef..2e796b54cbde 100644 --- a/arch/x86/platform/intel/iosf_mbi.c +++ b/arch/x86/platform/intel/iosf_mbi.c @@ -461,31 +461,16 @@ static struct dentry *iosf_dbg; static void iosf_sideband_debug_init(void) { - struct dentry *d; - iosf_dbg = debugfs_create_dir("iosf_sb", NULL); - if (IS_ERR_OR_NULL(iosf_dbg)) - return; /* mdr */ - d = debugfs_create_x32("mdr", 0660, iosf_dbg, &dbg_mdr); - if (!d) - goto cleanup; + debugfs_create_x32("mdr", 0660, iosf_dbg, &dbg_mdr); /* mcrx */ - d = debugfs_create_x32("mcrx", 0660, iosf_dbg, &dbg_mcrx); - if (!d) - goto cleanup; + debugfs_create_x32("mcrx", 0660, iosf_dbg, &dbg_mcrx); /* mcr - initiates mailbox tranaction */ - d = debugfs_create_file("mcr", 0660, iosf_dbg, &dbg_mcr, &iosf_mcr_fops); - if (!d) - goto cleanup; - - return; - -cleanup: - debugfs_remove_recursive(d); + debugfs_create_file("mcr", 0660, iosf_dbg, &dbg_mcr, &iosf_mcr_fops); } static void iosf_debugfs_init(void) diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c index 0c7dfec4acac..20c389a91b80 100644 --- a/arch/x86/platform/uv/tlb_uv.c +++ b/arch/x86/platform/uv/tlb_uv.c @@ -66,7 +66,6 @@ static struct tunables tunables[] = { }; static struct dentry *tunables_dir; -static struct dentry *tunables_file; /* these correspond to the statistics printed by ptc_seq_show() */ static char *stat_description[] = { @@ -1700,18 +1699,8 @@ static int __init uv_ptc_init(void) } tunables_dir = debugfs_create_dir(UV_BAU_TUNABLES_DIR, NULL); - if (!tunables_dir) { - pr_err("unable to create debugfs directory %s\n", - UV_BAU_TUNABLES_DIR); - return -EINVAL; - } - tunables_file = debugfs_create_file(UV_BAU_TUNABLES_FILE, 0600, - tunables_dir, NULL, &tunables_fops); - if (!tunables_file) { - pr_err("unable to create debugfs file %s\n", - UV_BAU_TUNABLES_FILE); - return -EINVAL; - } + debugfs_create_file(UV_BAU_TUNABLES_FILE, 0600, tunables_dir, NULL, + &tunables_fops); return 0; } diff --git a/arch/x86/xen/debugfs.c b/arch/x86/xen/debugfs.c index 13da87918b4f..532410998684 100644 --- a/arch/x86/xen/debugfs.c +++ b/arch/x86/xen/debugfs.c @@ -9,13 +9,8 @@ static struct dentry *d_xen_debug; struct dentry * __init xen_init_debugfs(void) { - if (!d_xen_debug) { + if (!d_xen_debug) d_xen_debug = debugfs_create_dir("xen", NULL); - - if (!d_xen_debug) - pr_warning("Could not create 'xen' debugfs directory\n"); - } - return d_xen_debug; } diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index beb44e22afdf..f6e5eeecfc69 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -2700,8 +2700,7 @@ struct remap_data { struct mmu_update *mmu_update; }; -static int remap_area_pfn_pte_fn(pte_t *ptep, pgtable_t token, - unsigned long addr, void *data) +static int remap_area_pfn_pte_fn(pte_t *ptep, unsigned long addr, void *data) { struct remap_data *rmd = data; pte_t pte = pte_mkspecial(mfn_pte(*rmd->pfn, rmd->prot)); diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index 95ce9b5be411..0acba2c712ab 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -817,9 +817,6 @@ static int __init xen_p2m_debugfs(void) { struct dentry *d_xen = xen_init_debugfs(); - if (d_xen == NULL) - return -ENOMEM; - d_mmu_debug = debugfs_create_dir("mmu", d_xen); debugfs_create_file("p2m", 0600, d_mmu_debug, NULL, &p2m_dump_fops); diff --git a/arch/xtensa/kernel/pci-dma.c b/arch/xtensa/kernel/pci-dma.c index a87f8a308cc1..65f05776d827 100644 --- a/arch/xtensa/kernel/pci-dma.c +++ b/arch/xtensa/kernel/pci-dma.c @@ -163,10 +163,6 @@ void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, *handle = phys_to_dma(dev, page_to_phys(page)); - if (attrs & DMA_ATTR_NO_KERNEL_MAPPING) { - return page; - } - #ifdef CONFIG_MMU if (PageHighMem(page)) { void *p; @@ -192,9 +188,7 @@ void arch_dma_free(struct device *dev, size_t size, void *vaddr, unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT; struct page *page; - if (attrs & DMA_ATTR_NO_KERNEL_MAPPING) { - page = vaddr; - } else if (platform_vaddr_uncached(vaddr)) { + if (platform_vaddr_uncached(vaddr)) { page = virt_to_page(platform_vaddr_to_cached(vaddr)); } else { #ifdef CONFIG_MMU |