diff options
Diffstat (limited to 'arch/powerpc')
221 files changed, 8141 insertions, 5848 deletions
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index d8dcd8820369..3e56c9c2f16e 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -128,14 +128,15 @@ config PPC 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 + select ARCH_HAS_PMEM_API select ARCH_HAS_PTE_DEVMAP if PPC_BOOK3S_64 select ARCH_HAS_PTE_SPECIAL select ARCH_HAS_MEMBARRIER_CALLBACKS - select ARCH_HAS_SCALED_CPUTIME if VIRT_CPU_ACCOUNTING_NATIVE && PPC64 + select ARCH_HAS_SCALED_CPUTIME if VIRT_CPU_ACCOUNTING_NATIVE && PPC_BOOK3S_64 select ARCH_HAS_STRICT_KERNEL_RWX if ((PPC_BOOK3S_64 || PPC32) && !RELOCATABLE && !HIBERNATION) select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST - select ARCH_HAS_UACCESS_FLUSHCACHE if PPC64 + select ARCH_HAS_UACCESS_FLUSHCACHE + select ARCH_HAS_UACCESS_MCSAFE if PPC64 select ARCH_HAS_UBSAN_SANITIZE_ALL select ARCH_HAVE_NMI_SAFE_CMPXCHG select ARCH_KEEP_MEMBLOCK @@ -177,11 +178,13 @@ config PPC select HAVE_ARCH_NVRAM_OPS select HAVE_ARCH_SECCOMP_FILTER select HAVE_ARCH_TRACEHOOK + select HAVE_ASM_MODVERSIONS 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) select HAVE_CONTEXT_TRACKING if PPC64 + select HAVE_COPY_THREAD_TLS select HAVE_DEBUG_KMEMLEAK select HAVE_DEBUG_STACKOVERFLOW select HAVE_DYNAMIC_FTRACE @@ -511,6 +514,7 @@ config KEXEC_FILE select KEXEC_CORE select HAVE_IMA_KEXEC select BUILD_BIN2C + select KEXEC_ELF depends on PPC64 depends on CRYPTO=y depends on CRYPTO_SHA256=y @@ -566,7 +570,7 @@ config CRASH_DUMP config FA_DUMP bool "Firmware-assisted dump" - depends on PPC64 && PPC_RTAS + depends on PPC64 && (PPC_RTAS || PPC_POWERNV) select CRASH_CORE select CRASH_DUMP help @@ -577,7 +581,26 @@ config FA_DUMP is meant to be a kdump replacement offering robustness and speed not possible without system firmware assistance. - If unsure, say "N" + If unsure, say "y". Only special kernels like petitboot may + need to say "N" here. + +config PRESERVE_FA_DUMP + bool "Preserve Firmware-assisted dump" + depends on PPC64 && PPC_POWERNV && !FA_DUMP + help + On a kernel with FA_DUMP disabled, this option helps to preserve + crash data from a previously crash'ed kernel. Useful when the next + memory preserving kernel boot would process this crash data. + Petitboot kernel is the typical usecase for this option. + +config OPAL_CORE + bool "Export OPAL memory as /sys/firmware/opal/core" + depends on PPC64 && PPC_POWERNV + help + This option uses the MPIPL support in firmware to provide an + ELF core of OPAL memory after a crash. The ELF core is exported + as /sys/firmware/opal/core file which is helpful in debugging + OPAL crashes using GDB. config IRQ_ALL_CPUS bool "Distribute interrupts on all CPUs by default" @@ -1138,18 +1161,6 @@ config TASK_SIZE default "0x80000000" if PPC_8xx default "0xc0000000" -config CONSISTENT_SIZE_BOOL - bool "Set custom consistent memory pool size" - depends on ADVANCED_OPTIONS && NOT_COHERENT_CACHE - help - This option allows you to set the size of the - consistent memory pool. This pool of virtual memory - is used to make consistent memory allocations. - -config CONSISTENT_SIZE - hex "Size of consistent memory pool" if CONSISTENT_SIZE_BOOL - default "0x00200000" if NOT_COHERENT_CACHE - config PIN_TLB bool "Pinned Kernel TLBs (860 ONLY)" depends on ADVANCED_OPTIONS && PPC_8xx && \ diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index c345b79414a9..83522c9fc7b6 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -39,13 +39,11 @@ endif uname := $(shell uname -m) KBUILD_DEFCONFIG := $(if $(filter ppc%,$(uname)),$(uname),ppc64)_defconfig -ifdef CONFIG_PPC64 new_nm := $(shell if $(NM) --help 2>&1 | grep -- '--synthetic' > /dev/null; then echo y; else echo n; fi) ifeq ($(new_nm),y) NM := $(NM) --synthetic endif -endif # BITS is used as extension for files which are available in a 32 bit # and a 64 bit version to simplify shared Makefiles. @@ -67,7 +65,7 @@ UTS_MACHINE := $(subst $(space),,$(machine-y)) ifdef CONFIG_PPC32 KBUILD_LDFLAGS_MODULE += arch/powerpc/lib/crtsavres.o else -KBUILD_LDFLAGS_MODULE += -T $(srctree)/arch/powerpc/kernel/module.lds +KBUILD_LDS_MODULE += $(srctree)/arch/powerpc/kernel/module.lds ifeq ($(call ld-ifversion, -ge, 225000000, y),y) # Have the linker provide sfpr if possible. # There is a corresponding test in arch/powerpc/lib/Makefile @@ -112,7 +110,6 @@ ifeq ($(HAS_BIARCH),y) KBUILD_CFLAGS += -m$(BITS) KBUILD_AFLAGS += -m$(BITS) -Wl,-a$(BITS) KBUILD_LDFLAGS += -m elf$(BITS)$(LDEMULATION) -KBUILD_ARFLAGS += --target=elf$(BITS)-$(GNUTARGET) endif cflags-$(CONFIG_STACKPROTECTOR) += -mstack-protector-guard=tls diff --git a/arch/powerpc/Makefile.postlink b/arch/powerpc/Makefile.postlink index 83f8e5ba2722..134f12f89b92 100644 --- a/arch/powerpc/Makefile.postlink +++ b/arch/powerpc/Makefile.postlink @@ -18,7 +18,7 @@ quiet_cmd_relocs_check = CHKREL $@ ifdef CONFIG_PPC_BOOK3S_64 cmd_relocs_check = \ $(CONFIG_SHELL) $(srctree)/arch/powerpc/tools/relocs_check.sh "$(OBJDUMP)" "$@" ; \ - $(CONFIG_SHELL) $(srctree)/arch/powerpc/tools/unrel_branch_check.sh "$(OBJDUMP)" "$@" + $(BASH) $(srctree)/arch/powerpc/tools/unrel_branch_check.sh "$(OBJDUMP)" "$@" else cmd_relocs_check = \ $(CONFIG_SHELL) $(srctree)/arch/powerpc/tools/relocs_check.sh "$(OBJDUMP)" "$@" diff --git a/arch/powerpc/boot/main.c b/arch/powerpc/boot/main.c index 102cc546444d..a9d209135975 100644 --- a/arch/powerpc/boot/main.c +++ b/arch/powerpc/boot/main.c @@ -146,6 +146,46 @@ static struct addr_range prep_initrd(struct addr_range vmlinux, void *chosen, return (struct addr_range){(void *)initrd_addr, initrd_size}; } +#ifdef __powerpc64__ +static void prep_esm_blob(struct addr_range vmlinux, void *chosen) +{ + unsigned long esm_blob_addr, esm_blob_size; + + /* Do we have an ESM (Enter Secure Mode) blob? */ + if (_esm_blob_end <= _esm_blob_start) + return; + + printf("Attached ESM blob at 0x%p-0x%p\n\r", + _esm_blob_start, _esm_blob_end); + esm_blob_addr = (unsigned long)_esm_blob_start; + esm_blob_size = _esm_blob_end - _esm_blob_start; + + /* + * If the ESM blob is too low it will be clobbered when the + * kernel relocates to its final location. In this case, + * allocate a safer place and move it. + */ + if (esm_blob_addr < vmlinux.size) { + void *old_addr = (void *)esm_blob_addr; + + printf("Allocating 0x%lx bytes for esm_blob ...\n\r", + esm_blob_size); + esm_blob_addr = (unsigned long)malloc(esm_blob_size); + if (!esm_blob_addr) + fatal("Can't allocate memory for ESM blob !\n\r"); + printf("Relocating ESM blob 0x%lx <- 0x%p (0x%lx bytes)\n\r", + esm_blob_addr, old_addr, esm_blob_size); + memmove((void *)esm_blob_addr, old_addr, esm_blob_size); + } + + /* Tell the kernel ESM blob address via device tree. */ + setprop_val(chosen, "linux,esm-blob-start", (u32)(esm_blob_addr)); + setprop_val(chosen, "linux,esm-blob-end", (u32)(esm_blob_addr + esm_blob_size)); +} +#else +static inline void prep_esm_blob(struct addr_range vmlinux, void *chosen) { } +#endif + /* A buffer that may be edited by tools operating on a zImage binary so as to * edit the command line passed to vmlinux (by setting /chosen/bootargs). * The buffer is put in it's own section so that tools may locate it easier. @@ -214,6 +254,7 @@ void start(void) vmlinux = prep_kernel(); initrd = prep_initrd(vmlinux, chosen, loader_info.initrd_addr, loader_info.initrd_size); + prep_esm_blob(vmlinux, chosen); prep_cmdline(chosen); printf("Finalizing device tree..."); diff --git a/arch/powerpc/boot/ops.h b/arch/powerpc/boot/ops.h index cd043726ed88..e0606766480f 100644 --- a/arch/powerpc/boot/ops.h +++ b/arch/powerpc/boot/ops.h @@ -251,6 +251,8 @@ extern char _initrd_start[]; extern char _initrd_end[]; extern char _dtb_start[]; extern char _dtb_end[]; +extern char _esm_blob_start[]; +extern char _esm_blob_end[]; static inline __attribute__((const)) int __ilog2_u32(u32 n) diff --git a/arch/powerpc/boot/wrapper b/arch/powerpc/boot/wrapper index 5148ac271f28..ed6266367bc0 100755 --- a/arch/powerpc/boot/wrapper +++ b/arch/powerpc/boot/wrapper @@ -13,6 +13,7 @@ # -i initrd specify initrd file # -d devtree specify device-tree blob # -s tree.dts specify device-tree source file (needs dtc installed) +# -e esm_blob specify ESM blob for secure images # -c cache $kernel.strip.gz (use if present & newer, else make) # -C prefix specify command prefix for cross-building tools # (strip, objcopy, ld) @@ -37,6 +38,7 @@ platform=of initrd= dtb= dts= +esm_blob= cacheit= binary= compression=.gz @@ -60,9 +62,9 @@ tmpdir=. usage() { echo 'Usage: wrapper [-o output] [-p platform] [-i initrd]' >&2 - echo ' [-d devtree] [-s tree.dts] [-c] [-C cross-prefix]' >&2 - echo ' [-D datadir] [-W workingdir] [-Z (gz|xz|none)]' >&2 - echo ' [--no-compression] [vmlinux]' >&2 + echo ' [-d devtree] [-s tree.dts] [-e esm_blob]' >&2 + echo ' [-c] [-C cross-prefix] [-D datadir] [-W workingdir]' >&2 + echo ' [-Z (gz|xz|none)] [--no-compression] [vmlinux]' >&2 exit 1 } @@ -105,6 +107,11 @@ while [ "$#" -gt 0 ]; do [ "$#" -gt 0 ] || usage dtb="$1" ;; + -e) + shift + [ "$#" -gt 0 ] || usage + esm_blob="$1" + ;; -s) shift [ "$#" -gt 0 ] || usage @@ -218,9 +225,16 @@ objflags=-S tmp=$tmpdir/zImage.$$.o ksection=.kernel:vmlinux.strip isection=.kernel:initrd +esection=.kernel:esm_blob link_address='0x400000' make_space=y + +if [ -n "$esm_blob" -a "$platform" != "pseries" ]; then + echo "ESM blob not support on non-pseries platforms" >&2 + exit 1 +fi + case "$platform" in of) platformo="$object/of.o $object/epapr.o" @@ -477,6 +491,10 @@ if [ -n "$dtb" ]; then fi fi +if [ -n "$esm_blob" ]; then + addsec $tmp "$esm_blob" $esection +fi + if [ "$platform" != "miboot" ]; then if [ -n "$link_address" ] ; then text_start="-Ttext $link_address" diff --git a/arch/powerpc/boot/zImage.lds.S b/arch/powerpc/boot/zImage.lds.S index 4ac1e36edfe7..a21f3a76e06f 100644 --- a/arch/powerpc/boot/zImage.lds.S +++ b/arch/powerpc/boot/zImage.lds.S @@ -68,6 +68,14 @@ SECTIONS _initrd_end = .; } + . = ALIGN(4096); + .kernel:esm_blob : + { + _esm_blob_start = .; + *(.kernel:esm_blob) + _esm_blob_end = .; + } + #ifdef CONFIG_PPC64_BOOT_WRAPPER . = ALIGN(256); .got : diff --git a/arch/powerpc/configs/pmac32_defconfig b/arch/powerpc/configs/pmac32_defconfig index 7e6654848531..4e6e95f92646 100644 --- a/arch/powerpc/configs/pmac32_defconfig +++ b/arch/powerpc/configs/pmac32_defconfig @@ -20,7 +20,6 @@ CONFIG_CPU_FREQ=y CONFIG_CPU_FREQ_GOV_POWERSAVE=y CONFIG_CPU_FREQ_GOV_USERSPACE=y CONFIG_CPU_FREQ_PMAC=y -CONFIG_PPC601_SYNC_FIX=y CONFIG_GEN_RTC=y CONFIG_HIGHMEM=y CONFIG_BINFMT_MISC=m diff --git a/arch/powerpc/configs/powernv_defconfig b/arch/powerpc/configs/powernv_defconfig index 34219d555e8a..6658cceb928c 100644 --- a/arch/powerpc/configs/powernv_defconfig +++ b/arch/powerpc/configs/powernv_defconfig @@ -38,7 +38,7 @@ CONFIG_MODULE_UNLOAD=y CONFIG_MODVERSIONS=y CONFIG_MODULE_SRCVERSION_ALL=y CONFIG_PARTITION_ADVANCED=y -CONFIG_SCOM_DEBUGFS=y +# CONFIG_SCOM_DEBUGFS is not set CONFIG_OPAL_PRD=y CONFIG_PPC_MEMTRACE=y # CONFIG_PPC_PSERIES is not set diff --git a/arch/powerpc/configs/ppc40x_defconfig b/arch/powerpc/configs/ppc40x_defconfig index 8f136b52198b..a5f683aed328 100644 --- a/arch/powerpc/configs/ppc40x_defconfig +++ b/arch/powerpc/configs/ppc40x_defconfig @@ -84,4 +84,3 @@ CONFIG_CRYPTO_ECB=y CONFIG_CRYPTO_PCBC=y CONFIG_CRYPTO_MD5=y CONFIG_CRYPTO_DES=y -CONFIG_PPC4xx_OCM=y diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig index dc83fefa04f7..b250e6f5a7ca 100644 --- a/arch/powerpc/configs/ppc64_defconfig +++ b/arch/powerpc/configs/ppc64_defconfig @@ -29,6 +29,7 @@ CONFIG_DTL=y CONFIG_SCANLOG=m CONFIG_PPC_SMLPAR=y CONFIG_IBMEBUS=y +CONFIG_PPC_SVM=y CONFIG_PPC_MAPLE=y CONFIG_PPC_PASEMI=y CONFIG_PPC_PASEMI_IOMMU=y diff --git a/arch/powerpc/configs/pseries_defconfig b/arch/powerpc/configs/pseries_defconfig index 38abc9c1770a..26126b4d4de3 100644 --- a/arch/powerpc/configs/pseries_defconfig +++ b/arch/powerpc/configs/pseries_defconfig @@ -42,6 +42,7 @@ CONFIG_DTL=y CONFIG_SCANLOG=m CONFIG_PPC_SMLPAR=y CONFIG_IBMEBUS=y +CONFIG_PPC_SVM=y # CONFIG_PPC_PMAC is not set CONFIG_RTAS_FLASH=m CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y diff --git a/arch/powerpc/configs/skiroot_defconfig b/arch/powerpc/configs/skiroot_defconfig index 557b530b2f70..1253482a67c0 100644 --- a/arch/powerpc/configs/skiroot_defconfig +++ b/arch/powerpc/configs/skiroot_defconfig @@ -213,6 +213,7 @@ CONFIG_IPMI_WATCHDOG=y CONFIG_HW_RANDOM=y CONFIG_TCG_TPM=y CONFIG_TCG_TIS_I2C_NUVOTON=y +# CONFIG_DEVPORT is not set CONFIG_I2C=y # CONFIG_I2C_COMPAT is not set CONFIG_I2C_CHARDEV=y diff --git a/arch/powerpc/include/asm/Kbuild b/arch/powerpc/include/asm/Kbuild index 9a1d2fc6ceb7..64870c7be4a3 100644 --- a/arch/powerpc/include/asm/Kbuild +++ b/arch/powerpc/include/asm/Kbuild @@ -11,4 +11,3 @@ generic-y += mcs_spinlock.h generic-y += preempt.h generic-y += vtime.h generic-y += msi.h -generic-y += simd.h diff --git a/arch/powerpc/include/asm/asm-prototypes.h b/arch/powerpc/include/asm/asm-prototypes.h index ec1c97a8e8cb..8561498e653c 100644 --- a/arch/powerpc/include/asm/asm-prototypes.h +++ b/arch/powerpc/include/asm/asm-prototypes.h @@ -15,6 +15,7 @@ #include <asm/epapr_hcalls.h> #include <asm/dcr.h> #include <asm/mmu_context.h> +#include <asm/ultravisor-api.h> #include <uapi/asm/ucontext.h> @@ -34,6 +35,16 @@ extern struct static_key hcall_tracepoint_key; void __trace_hcall_entry(unsigned long opcode, unsigned long *args); void __trace_hcall_exit(long opcode, long retval, unsigned long *retbuf); +/* Ultravisor */ +#if defined(CONFIG_PPC_POWERNV) || defined(CONFIG_PPC_SVM) +long ucall_norets(unsigned long opcode, ...); +#else +static inline long ucall_norets(unsigned long opcode, ...) +{ + return U_NOT_AVAILABLE; +} +#endif + /* OPAL */ int64_t __opal_call(int64_t a0, int64_t a1, int64_t a2, int64_t a3, int64_t a4, int64_t a5, int64_t a6, int64_t a7, @@ -123,7 +134,8 @@ extern int __ucmpdi2(u64, u64); /* tracing */ void _mcount(void); -unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip); +unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip, + unsigned long sp); void pnv_power9_force_smt4_catch(void); void pnv_power9_force_smt4_release(void); diff --git a/arch/powerpc/include/asm/book3s/32/pgtable.h b/arch/powerpc/include/asm/book3s/32/pgtable.h index 838de59f6754..0796533d37dd 100644 --- a/arch/powerpc/include/asm/book3s/32/pgtable.h +++ b/arch/powerpc/include/asm/book3s/32/pgtable.h @@ -148,23 +148,21 @@ int map_kernel_page(unsigned long va, phys_addr_t pa, pgprot_t prot); */ #include <asm/fixmap.h> -#ifdef CONFIG_HIGHMEM -#define KVIRT_TOP PKMAP_BASE -#else -#define KVIRT_TOP FIXADDR_START -#endif - /* * ioremap_bot starts at that address. Early ioremaps move down from there, * until mem_init() at which point this becomes the top of the vmalloc * and ioremap space */ -#ifdef CONFIG_NOT_COHERENT_CACHE -#define IOREMAP_TOP ((KVIRT_TOP - CONFIG_CONSISTENT_SIZE) & PAGE_MASK) +#ifdef CONFIG_HIGHMEM +#define IOREMAP_TOP PKMAP_BASE #else -#define IOREMAP_TOP KVIRT_TOP +#define IOREMAP_TOP FIXADDR_START #endif +/* PPC32 shares vmalloc area with ioremap */ +#define IOREMAP_START VMALLOC_START +#define IOREMAP_END VMALLOC_END + /* * Just any arbitrary offset to the start of the vmalloc VM area: the * current 16MB value just means that there will be a 64MB "hole" after the @@ -201,8 +199,6 @@ int map_kernel_page(unsigned long va, phys_addr_t pa, pgprot_t prot); #include <linux/sched.h> #include <linux/threads.h> -extern unsigned long ioremap_bot; - /* Bits to mask out from a PGD to get to the PUD page */ #define PGD_MASKED_BITS 0 diff --git a/arch/powerpc/include/asm/book3s/64/mmu.h b/arch/powerpc/include/asm/book3s/64/mmu.h index 23b83d3593e2..bb3deb76c951 100644 --- a/arch/powerpc/include/asm/book3s/64/mmu.h +++ b/arch/powerpc/include/asm/book3s/64/mmu.h @@ -206,7 +206,6 @@ extern int mmu_io_psize; void mmu_early_init_devtree(void); void hash__early_init_devtree(void); void radix__early_init_devtree(void); -extern void radix_init_native(void); extern void hash__early_init_mmu(void); extern void radix__early_init_mmu(void); static inline void early_init_mmu(void) @@ -238,9 +237,6 @@ static inline void setup_initial_memory_limit(phys_addr_t first_memblock_base, first_memblock_size); } -extern int (*register_process_table)(unsigned long base, unsigned long page_size, - unsigned long tbl_size); - #ifdef CONFIG_PPC_PSERIES extern void radix_init_pseries(void); #else diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index 8308f32e9782..b01624e5c467 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -289,7 +289,6 @@ extern unsigned long __kernel_io_end; #define KERN_IO_END __kernel_io_end extern struct page *vmemmap; -extern unsigned long ioremap_bot; extern unsigned long pci_io_base; #endif /* __ASSEMBLY__ */ @@ -317,6 +316,7 @@ extern unsigned long pci_io_base; #define PHB_IO_BASE (ISA_IO_END) #define PHB_IO_END (KERN_IO_START + FULL_IO_SIZE) #define IOREMAP_BASE (PHB_IO_END) +#define IOREMAP_START (ioremap_bot) #define IOREMAP_END (KERN_IO_END) /* Advertise special mapping type for AGP */ @@ -608,8 +608,10 @@ static inline bool pte_access_permitted(pte_t pte, bool write) */ static inline pte_t pfn_pte(unsigned long pfn, pgprot_t pgprot) { - return __pte((((pte_basic_t)(pfn) << PAGE_SHIFT) & PTE_RPN_MASK) | - pgprot_val(pgprot)); + VM_BUG_ON(pfn >> (64 - PAGE_SHIFT)); + VM_BUG_ON((pfn << PAGE_SHIFT) & ~PTE_RPN_MASK); + + return __pte(((pte_basic_t)pfn << PAGE_SHIFT) | pgprot_val(pgprot)); } static inline unsigned long pte_pfn(pte_t pte) diff --git a/arch/powerpc/include/asm/book3s/64/radix.h b/arch/powerpc/include/asm/book3s/64/radix.h index e04a839cb5b9..574eca33f893 100644 --- a/arch/powerpc/include/asm/book3s/64/radix.h +++ b/arch/powerpc/include/asm/book3s/64/radix.h @@ -266,9 +266,6 @@ 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/book3s/64/tlbflush-radix.h b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h index 05147cecb8df..4ce795d30377 100644 --- a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h +++ b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h @@ -17,8 +17,8 @@ extern void radix__flush_tlb_lpid_page(unsigned int lpid, unsigned long addr, unsigned long page_size); extern void radix__flush_pwc_lpid(unsigned int lpid); -extern void radix__flush_tlb_lpid(unsigned int lpid); -extern void radix__local_flush_tlb_lpid_guest(unsigned int lpid); +extern void radix__flush_all_lpid(unsigned int lpid); +extern void radix__flush_all_lpid_guest(unsigned int lpid); #else static inline void radix__tlbiel_all(unsigned int action) { WARN_ON(1); }; static inline void radix__flush_tlb_lpid_page(unsigned int lpid, @@ -31,11 +31,7 @@ static inline void radix__flush_pwc_lpid(unsigned int lpid) { WARN_ON(1); } -static inline void radix__flush_tlb_lpid(unsigned int lpid) -{ - WARN_ON(1); -} -static inline void radix__local_flush_tlb_lpid_guest(unsigned int lpid) +static inline void radix__flush_all_lpid(unsigned int lpid) { WARN_ON(1); } @@ -73,6 +69,4 @@ extern void radix__flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr); extern void radix__flush_tlb_collapsed_pmd(struct mm_struct *mm, unsigned long addr); extern void radix__flush_tlb_all(void); -extern void radix__local_flush_tlb_lpid(unsigned int lpid); - #endif diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush.h b/arch/powerpc/include/asm/book3s/64/tlbflush.h index ebf572ea621e..7aa8195b6cff 100644 --- a/arch/powerpc/include/asm/book3s/64/tlbflush.h +++ b/arch/powerpc/include/asm/book3s/64/tlbflush.h @@ -162,4 +162,13 @@ static inline void flush_tlb_pgtable(struct mmu_gather *tlb, unsigned long addre radix__flush_tlb_pwc(tlb, address); } + +extern bool tlbie_capable; +extern bool tlbie_enabled; + +static inline bool cputlb_use_tlbie(void) +{ + return tlbie_enabled; +} + #endif /* _ASM_POWERPC_BOOK3S_64_TLBFLUSH_H */ diff --git a/arch/powerpc/include/asm/book3s/pgtable.h b/arch/powerpc/include/asm/book3s/pgtable.h index 6436b65ac7bc..0e1263455d73 100644 --- a/arch/powerpc/include/asm/book3s/pgtable.h +++ b/arch/powerpc/include/asm/book3s/pgtable.h @@ -26,5 +26,16 @@ extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, unsigned long size, pgprot_t vma_prot); #define __HAVE_PHYS_MEM_ACCESS_PROT +/* + * This gets called at the end of handling a page fault, when + * the kernel has put a new PTE into the page table for the process. + * We use it to ensure coherency between the i-cache and d-cache + * for the page which has just been mapped in. + * On machines which use an MMU hash table, we use this to put a + * corresponding HPTE into the hash table ahead of time, instead of + * waiting for the inevitable extra hash-table miss exception. + */ +void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep); + #endif /* __ASSEMBLY__ */ #endif diff --git a/arch/powerpc/include/asm/bug.h b/arch/powerpc/include/asm/bug.h index fed7e6241349..f47e6ff6554d 100644 --- a/arch/powerpc/include/asm/bug.h +++ b/arch/powerpc/include/asm/bug.h @@ -5,14 +5,6 @@ #include <asm/asm-compat.h> -/* - * Define an illegal instr to trap on the bug. - * We don't use 0 because that marks the end of a function - * in the ELF ABI. That's "Boo Boo" in case you wonder... - */ -#define BUG_OPCODE .long 0x00b00b00 /* For asm */ -#define BUG_ILLEGAL_INSTR "0x00b00b00" /* For BUG macro */ - #ifdef CONFIG_BUG #ifdef __ASSEMBLY__ diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h index d05f0c28e515..a1ebcbc3931f 100644 --- a/arch/powerpc/include/asm/cputable.h +++ b/arch/powerpc/include/asm/cputable.h @@ -145,12 +145,10 @@ static inline void cpu_feature_keys_init(void) { } /* Definitions for features that only exist on 32-bit chips */ #ifdef CONFIG_PPC32 -#define CPU_FTR_601 ASM_CONST(0x00001000) #define CPU_FTR_L2CR ASM_CONST(0x00002000) #define CPU_FTR_SPEC7450 ASM_CONST(0x00004000) #define CPU_FTR_TAU ASM_CONST(0x00008000) #define CPU_FTR_CAN_DOZE ASM_CONST(0x00010000) -#define CPU_FTR_USE_RTC ASM_CONST(0x00020000) #define CPU_FTR_L3CR ASM_CONST(0x00040000) #define CPU_FTR_L3_DISABLE_NAP ASM_CONST(0x00080000) #define CPU_FTR_NAP_DISABLE_L2_PR ASM_CONST(0x00100000) @@ -160,14 +158,12 @@ static inline void cpu_feature_keys_init(void) { } #define CPU_FTR_NEED_COHERENT ASM_CONST(0x01000000) #define CPU_FTR_NO_BTIC ASM_CONST(0x02000000) #define CPU_FTR_PPC_LE ASM_CONST(0x04000000) -#define CPU_FTR_UNIFIED_ID_CACHE ASM_CONST(0x08000000) #define CPU_FTR_SPE ASM_CONST(0x10000000) #define CPU_FTR_NEED_PAIRED_STWCX ASM_CONST(0x20000000) #define CPU_FTR_INDEXED_DCR ASM_CONST(0x40000000) #else /* CONFIG_PPC32 */ /* Define these to 0 for the sake of tests in common code */ -#define CPU_FTR_601 (0) #define CPU_FTR_PPC_LE (0) #endif @@ -294,8 +290,8 @@ static inline void cpu_feature_keys_init(void) { } #define CPU_FTR_MAYBE_CAN_NAP 0 #endif -#define CPU_FTRS_PPC601 (CPU_FTR_COMMON | CPU_FTR_601 | \ - CPU_FTR_COHERENT_ICACHE | CPU_FTR_UNIFIED_ID_CACHE | CPU_FTR_USE_RTC) +#define CPU_FTRS_PPC601 (CPU_FTR_COMMON | \ + CPU_FTR_COHERENT_ICACHE) #define CPU_FTRS_603 (CPU_FTR_COMMON | CPU_FTR_MAYBE_CAN_DOZE | \ CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_PPC_LE | CPU_FTR_NOEXECUTE) #define CPU_FTRS_604 (CPU_FTR_COMMON | CPU_FTR_PPC_LE) @@ -386,7 +382,7 @@ static inline void cpu_feature_keys_init(void) { } #define CPU_FTRS_47X (CPU_FTRS_440x6) #define CPU_FTRS_E200 (CPU_FTR_SPE_COMP | \ CPU_FTR_NODSISRALIGN | CPU_FTR_COHERENT_ICACHE | \ - CPU_FTR_UNIFIED_ID_CACHE | CPU_FTR_NOEXECUTE | \ + CPU_FTR_NOEXECUTE | \ CPU_FTR_DEBUG_LVL_EXC) #define CPU_FTRS_E500 (CPU_FTR_MAYBE_CAN_DOZE | \ CPU_FTR_SPE_COMP | CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_NODSISRALIGN | \ @@ -498,7 +494,9 @@ static inline void cpu_feature_keys_init(void) { } #else enum { CPU_FTRS_POSSIBLE = -#ifdef CONFIG_PPC_BOOK3S_32 +#ifdef CONFIG_PPC_BOOK3S_601 + CPU_FTRS_PPC601 | +#elif defined(CONFIG_PPC_BOOK3S_32) CPU_FTRS_PPC601 | CPU_FTRS_603 | CPU_FTRS_604 | CPU_FTRS_740_NOTAU | CPU_FTRS_740 | CPU_FTRS_750 | CPU_FTRS_750FX1 | CPU_FTRS_750FX2 | CPU_FTRS_750FX | CPU_FTRS_750GX | @@ -574,8 +572,10 @@ enum { #else enum { CPU_FTRS_ALWAYS = -#ifdef CONFIG_PPC_BOOK3S_32 - CPU_FTRS_PPC601 & CPU_FTRS_603 & CPU_FTRS_604 & CPU_FTRS_740_NOTAU & +#ifdef CONFIG_PPC_BOOK3S_601 + CPU_FTRS_PPC601 & +#elif defined(CONFIG_PPC_BOOK3S_32) + CPU_FTRS_603 & CPU_FTRS_604 & CPU_FTRS_740_NOTAU & CPU_FTRS_740 & CPU_FTRS_750 & CPU_FTRS_750FX1 & CPU_FTRS_750FX2 & CPU_FTRS_750FX & CPU_FTRS_750GX & CPU_FTRS_7400_NOTAU & CPU_FTRS_7400 & CPU_FTRS_7450_20 & diff --git a/arch/powerpc/include/asm/current.h b/arch/powerpc/include/asm/current.h index 297827b76169..bbfb94800415 100644 --- a/arch/powerpc/include/asm/current.h +++ b/arch/powerpc/include/asm/current.h @@ -16,7 +16,8 @@ static inline struct task_struct *get_current(void) { struct task_struct *task; - __asm__ __volatile__("ld %0,%1(13)" + /* get_current can be cached by the compiler, so no volatile */ + asm ("ld %0,%1(13)" : "=r" (task) : "i" (offsetof(struct paca_struct, __current))); diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h index 8aa7c76c2130..6f9b2a12540a 100644 --- a/arch/powerpc/include/asm/eeh.h +++ b/arch/powerpc/include/asm/eeh.h @@ -88,6 +88,19 @@ struct eeh_pe { struct list_head child_list; /* List of PEs below this PE */ struct list_head child; /* Memb. child_list/eeh_phb_pe */ struct list_head edevs; /* List of eeh_dev in this PE */ + +#ifdef CONFIG_STACKTRACE + /* + * Saved stack trace. When we find a PE freeze in eeh_dev_check_failure + * the stack trace is saved here so we can print it in the recovery + * thread if it turns out to due to a real problem rather than + * a hot-remove. + * + * A max of 64 entries might be overkill, but it also might not be. + */ + unsigned long stack_trace[64]; + int trace_entries; +#endif /* CONFIG_STACKTRACE */ }; #define eeh_pe_for_each_dev(pe, edev, tmp) \ @@ -121,6 +134,8 @@ static inline bool eeh_pe_passed(struct eeh_pe *pe) struct eeh_dev { int mode; /* EEH mode */ int class_code; /* Class code of the device */ + int bdfn; /* bdfn of device (for cfg ops) */ + struct pci_controller *controller; int pe_config_addr; /* PE config address */ u32 config_space[16]; /* Saved PCI config space */ int pcix_cap; /* Saved PCIx capability */ @@ -136,6 +151,17 @@ struct eeh_dev { struct pci_dev *physfn; /* Associated SRIOV PF */ }; +/* "fmt" must be a simple literal string */ +#define EEH_EDEV_PRINT(level, edev, fmt, ...) \ + pr_##level("PCI %04x:%02x:%02x.%x#%04x: EEH: " fmt, \ + (edev)->controller->global_number, PCI_BUSNO((edev)->bdfn), \ + PCI_SLOT((edev)->bdfn), PCI_FUNC((edev)->bdfn), \ + ((edev)->pe ? (edev)->pe_config_addr : 0xffff), ##__VA_ARGS__) +#define eeh_edev_dbg(edev, fmt, ...) EEH_EDEV_PRINT(debug, (edev), fmt, ##__VA_ARGS__) +#define eeh_edev_info(edev, fmt, ...) EEH_EDEV_PRINT(info, (edev), fmt, ##__VA_ARGS__) +#define eeh_edev_warn(edev, fmt, ...) EEH_EDEV_PRINT(warn, (edev), fmt, ##__VA_ARGS__) +#define eeh_edev_err(edev, fmt, ...) EEH_EDEV_PRINT(err, (edev), fmt, ##__VA_ARGS__) + static inline struct pci_dn *eeh_dev_to_pdn(struct eeh_dev *edev) { return edev ? edev->pdn : NULL; @@ -247,7 +273,7 @@ static inline bool eeh_state_active(int state) == (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE); } -typedef void *(*eeh_edev_traverse_func)(struct eeh_dev *edev, void *flag); +typedef void (*eeh_edev_traverse_func)(struct eeh_dev *edev, void *flag); typedef void *(*eeh_pe_traverse_func)(struct eeh_pe *pe, void *flag); void eeh_set_pe_aux_size(int size); int eeh_phb_pe_create(struct pci_controller *phb); @@ -261,20 +287,20 @@ int eeh_rmv_from_parent_pe(struct eeh_dev *edev); void eeh_pe_update_time_stamp(struct eeh_pe *pe); void *eeh_pe_traverse(struct eeh_pe *root, eeh_pe_traverse_func fn, void *flag); -void *eeh_pe_dev_traverse(struct eeh_pe *root, - eeh_edev_traverse_func fn, void *flag); +void eeh_pe_dev_traverse(struct eeh_pe *root, + eeh_edev_traverse_func fn, void *flag); void eeh_pe_restore_bars(struct eeh_pe *pe); const char *eeh_pe_loc_get(struct eeh_pe *pe); struct pci_bus *eeh_pe_bus_get(struct eeh_pe *pe); struct eeh_dev *eeh_dev_init(struct pci_dn *pdn); void eeh_dev_phb_init_dynamic(struct pci_controller *phb); -void eeh_probe_devices(void); +void eeh_show_enabled(void); int __init eeh_ops_register(struct eeh_ops *ops); int __exit eeh_ops_unregister(const char *name); int eeh_check_failure(const volatile void __iomem *token); int eeh_dev_check_failure(struct eeh_dev *edev); -void eeh_addr_cache_build(void); +void eeh_addr_cache_init(void); void eeh_add_device_early(struct pci_dn *); void eeh_add_device_tree_early(struct pci_dn *); void eeh_add_device_late(struct pci_dev *); @@ -316,7 +342,7 @@ static inline bool eeh_enabled(void) return false; } -static inline void eeh_probe_devices(void) { } +static inline void eeh_show_enabled(void) { } static inline void *eeh_dev_init(struct pci_dn *pdn, void *data) { @@ -332,7 +358,7 @@ static inline int eeh_check_failure(const volatile void __iomem *token) #define eeh_dev_check_failure(x) (0) -static inline void eeh_addr_cache_build(void) { } +static inline void eeh_addr_cache_init(void) { } static inline void eeh_add_device_early(struct pci_dn *pdn) { } diff --git a/arch/powerpc/include/asm/elfnote.h b/arch/powerpc/include/asm/elfnote.h new file mode 100644 index 000000000000..a201b6e9ae44 --- /dev/null +++ b/arch/powerpc/include/asm/elfnote.h @@ -0,0 +1,24 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * PowerPC ELF notes. + * + * Copyright 2019, IBM Corporation + */ + +#ifndef __ASM_POWERPC_ELFNOTE_H__ +#define __ASM_POWERPC_ELFNOTE_H__ + +/* + * These note types should live in a SHT_NOTE segment and have + * "PowerPC" in the name field. + */ + +/* + * The capabilities supported/required by this kernel (bitmap). + * + * This type uses a bitmap as "desc" field. Each bit is described + * in arch/powerpc/kernel/note.S + */ +#define PPC_ELFNOTE_CAPABILITIES 1 + +#endif /* __ASM_POWERPC_ELFNOTE_H__ */ diff --git a/arch/powerpc/include/asm/error-injection.h b/arch/powerpc/include/asm/error-injection.h deleted file mode 100644 index 62fd24739852..000000000000 --- a/arch/powerpc/include/asm/error-injection.h +++ /dev/null @@ -1,13 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0+ */ - -#ifndef _ASM_ERROR_INJECTION_H -#define _ASM_ERROR_INJECTION_H - -#include <linux/compiler.h> -#include <linux/linkage.h> -#include <asm/ptrace.h> -#include <asm-generic/error-injection.h> - -void override_function_with_return(struct pt_regs *regs); - -#endif /* _ASM_ERROR_INJECTION_H */ diff --git a/arch/powerpc/include/asm/fadump-internal.h b/arch/powerpc/include/asm/fadump-internal.h new file mode 100644 index 000000000000..c814a2b55389 --- /dev/null +++ b/arch/powerpc/include/asm/fadump-internal.h @@ -0,0 +1,169 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Firmware-Assisted Dump internal code. + * + * Copyright 2011, Mahesh Salgaonkar, IBM Corporation. + * Copyright 2019, Hari Bathini, IBM Corporation. + */ + +#ifndef _ASM_POWERPC_FADUMP_INTERNAL_H +#define _ASM_POWERPC_FADUMP_INTERNAL_H + +/* Maximum number of memory regions kernel supports */ +#define FADUMP_MAX_MEM_REGS 128 + +#ifndef CONFIG_PRESERVE_FA_DUMP + +/* The upper limit percentage for user specified boot memory size (25%) */ +#define MAX_BOOT_MEM_RATIO 4 + +#define memblock_num_regions(memblock_type) (memblock.memblock_type.cnt) + +/* Alignment per CMA requirement. */ +#define FADUMP_CMA_ALIGNMENT (PAGE_SIZE << \ + max_t(unsigned long, MAX_ORDER - 1, \ + pageblock_order)) + +/* FAD commands */ +#define FADUMP_REGISTER 1 +#define FADUMP_UNREGISTER 2 +#define FADUMP_INVALIDATE 3 + +/* + * Copy the ascii values for first 8 characters from a string into u64 + * variable at their respective indexes. + * e.g. + * The string "FADMPINF" will be converted into 0x4641444d50494e46 + */ +static inline u64 fadump_str_to_u64(const char *str) +{ + u64 val = 0; + int i; + + for (i = 0; i < sizeof(val); i++) + val = (*str) ? (val << 8) | *str++ : val << 8; + return val; +} + +#define FADUMP_CPU_UNKNOWN (~((u32)0)) + +#define FADUMP_CRASH_INFO_MAGIC fadump_str_to_u64("FADMPINF") + +/* fadump crash info structure */ +struct fadump_crash_info_header { + u64 magic_number; + u64 elfcorehdr_addr; + u32 crashing_cpu; + struct pt_regs regs; + struct cpumask online_mask; +}; + +struct fadump_memory_range { + u64 base; + u64 size; +}; + +/* fadump memory ranges info */ +struct fadump_mrange_info { + char name[16]; + struct fadump_memory_range *mem_ranges; + u32 mem_ranges_sz; + u32 mem_range_cnt; + u32 max_mem_ranges; +}; + +/* Platform specific callback functions */ +struct fadump_ops; + +/* Firmware-assisted dump configuration details. */ +struct fw_dump { + unsigned long reserve_dump_area_start; + unsigned long reserve_dump_area_size; + /* cmd line option during boot */ + unsigned long reserve_bootvar; + + unsigned long cpu_state_data_size; + u64 cpu_state_dest_vaddr; + u32 cpu_state_data_version; + u32 cpu_state_entry_size; + + unsigned long hpte_region_size; + + unsigned long boot_memory_size; + u64 boot_mem_dest_addr; + u64 boot_mem_addr[FADUMP_MAX_MEM_REGS]; + u64 boot_mem_sz[FADUMP_MAX_MEM_REGS]; + u64 boot_mem_top; + u64 boot_mem_regs_cnt; + + unsigned long fadumphdr_addr; + unsigned long cpu_notes_buf_vaddr; + unsigned long cpu_notes_buf_size; + + /* + * Maximum size supported by firmware to copy from source to + * destination address per entry. + */ + u64 max_copy_size; + u64 kernel_metadata; + + int ibm_configure_kernel_dump; + + unsigned long fadump_enabled:1; + unsigned long fadump_supported:1; + unsigned long dump_active:1; + unsigned long dump_registered:1; + unsigned long nocma:1; + + struct fadump_ops *ops; +}; + +struct fadump_ops { + u64 (*fadump_init_mem_struct)(struct fw_dump *fadump_conf); + u64 (*fadump_get_metadata_size)(void); + int (*fadump_setup_metadata)(struct fw_dump *fadump_conf); + u64 (*fadump_get_bootmem_min)(void); + int (*fadump_register)(struct fw_dump *fadump_conf); + int (*fadump_unregister)(struct fw_dump *fadump_conf); + int (*fadump_invalidate)(struct fw_dump *fadump_conf); + void (*fadump_cleanup)(struct fw_dump *fadump_conf); + int (*fadump_process)(struct fw_dump *fadump_conf); + void (*fadump_region_show)(struct fw_dump *fadump_conf, + struct seq_file *m); + void (*fadump_trigger)(struct fadump_crash_info_header *fdh, + const char *msg); +}; + +/* Helper functions */ +s32 fadump_setup_cpu_notes_buf(u32 num_cpus); +void fadump_free_cpu_notes_buf(void); +u32 *fadump_regs_to_elf_notes(u32 *buf, struct pt_regs *regs); +void fadump_update_elfcore_header(char *bufp); +bool is_fadump_boot_mem_contiguous(void); +bool is_fadump_reserved_mem_contiguous(void); + +#else /* !CONFIG_PRESERVE_FA_DUMP */ + +/* Firmware-assisted dump configuration details. */ +struct fw_dump { + u64 boot_mem_top; + u64 dump_active; +}; + +#endif /* CONFIG_PRESERVE_FA_DUMP */ + +#ifdef CONFIG_PPC_PSERIES +extern void rtas_fadump_dt_scan(struct fw_dump *fadump_conf, u64 node); +#else +static inline void +rtas_fadump_dt_scan(struct fw_dump *fadump_conf, u64 node) { } +#endif + +#ifdef CONFIG_PPC_POWERNV +extern void opal_fadump_dt_scan(struct fw_dump *fadump_conf, u64 node); +#else +static inline void +opal_fadump_dt_scan(struct fw_dump *fadump_conf, u64 node) { } +#endif + +#endif /* _ASM_POWERPC_FADUMP_INTERNAL_H */ diff --git a/arch/powerpc/include/asm/fadump.h b/arch/powerpc/include/asm/fadump.h index 17d9b6acaf63..526a6a647312 100644 --- a/arch/powerpc/include/asm/fadump.h +++ b/arch/powerpc/include/asm/fadump.h @@ -6,196 +6,14 @@ * Author: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> */ -#ifndef __PPC64_FA_DUMP_H__ -#define __PPC64_FA_DUMP_H__ +#ifndef _ASM_POWERPC_FADUMP_H +#define _ASM_POWERPC_FADUMP_H #ifdef CONFIG_FA_DUMP -/* - * The RMA region will be saved for later dumping when kernel crashes. - * RMA is Real Mode Area, the first block of logical memory address owned - * by logical partition, containing the storage that may be accessed with - * translate off. - */ -#define RMA_START 0x0 -#define RMA_END (ppc64_rma_size) - -/* - * On some Power systems where RMO is 128MB, it still requires minimum of - * 256MB for kernel to boot successfully. When kdump infrastructure is - * configured to save vmcore over network, we run into OOM issue while - * loading modules related to network setup. Hence we need aditional 64M - * of memory to avoid OOM issue. - */ -#define MIN_BOOT_MEM (((RMA_END < (0x1UL << 28)) ? (0x1UL << 28) : RMA_END) \ - + (0x1UL << 26)) - -/* The upper limit percentage for user specified boot memory size (25%) */ -#define MAX_BOOT_MEM_RATIO 4 - -#define memblock_num_regions(memblock_type) (memblock.memblock_type.cnt) - -/* Alignement per CMA requirement. */ -#define FADUMP_CMA_ALIGNMENT (PAGE_SIZE << \ - max_t(unsigned long, MAX_ORDER - 1, pageblock_order)) - -/* Firmware provided dump sections */ -#define FADUMP_CPU_STATE_DATA 0x0001 -#define FADUMP_HPTE_REGION 0x0002 -#define FADUMP_REAL_MODE_REGION 0x0011 - -/* Dump request flag */ -#define FADUMP_REQUEST_FLAG 0x00000001 - -/* FAD commands */ -#define FADUMP_REGISTER 1 -#define FADUMP_UNREGISTER 2 -#define FADUMP_INVALIDATE 3 - -/* Dump status flag */ -#define FADUMP_ERROR_FLAG 0x2000 - -#define FADUMP_CPU_ID_MASK ((1UL << 32) - 1) - -#define CPU_UNKNOWN (~((u32)0)) - -/* Utility macros */ -#define SKIP_TO_NEXT_CPU(reg_entry) \ -({ \ - while (be64_to_cpu(reg_entry->reg_id) != REG_ID("CPUEND")) \ - reg_entry++; \ - reg_entry++; \ -}) - extern int crashing_cpu; -/* Kernel Dump section info */ -struct fadump_section { - __be32 request_flag; - __be16 source_data_type; - __be16 error_flags; - __be64 source_address; - __be64 source_len; - __be64 bytes_dumped; - __be64 destination_address; -}; - -/* ibm,configure-kernel-dump header. */ -struct fadump_section_header { - __be32 dump_format_version; - __be16 dump_num_sections; - __be16 dump_status_flag; - __be32 offset_first_dump_section; - - /* Fields for disk dump option. */ - __be32 dd_block_size; - __be64 dd_block_offset; - __be64 dd_num_blocks; - __be32 dd_offset_disk_path; - - /* Maximum time allowed to prevent an automatic dump-reboot. */ - __be32 max_time_auto; -}; - -/* - * Firmware Assisted dump memory structure. This structure is required for - * registering future kernel dump with power firmware through rtas call. - * - * No disk dump option. Hence disk dump path string section is not included. - */ -struct fadump_mem_struct { - struct fadump_section_header header; - - /* Kernel dump sections */ - struct fadump_section cpu_state_data; - struct fadump_section hpte_region; - struct fadump_section rmr_region; -}; - -/* Firmware-assisted dump configuration details. */ -struct fw_dump { - unsigned long cpu_state_data_size; - unsigned long hpte_region_size; - unsigned long boot_memory_size; - unsigned long reserve_dump_area_start; - unsigned long reserve_dump_area_size; - /* cmd line option during boot */ - unsigned long reserve_bootvar; - - unsigned long fadumphdr_addr; - unsigned long cpu_notes_buf; - unsigned long cpu_notes_buf_size; - - int ibm_configure_kernel_dump; - - unsigned long fadump_enabled:1; - unsigned long fadump_supported:1; - unsigned long dump_active:1; - unsigned long dump_registered:1; - unsigned long nocma:1; -}; - -/* - * Copy the ascii values for first 8 characters from a string into u64 - * variable at their respective indexes. - * e.g. - * The string "FADMPINF" will be converted into 0x4641444d50494e46 - */ -static inline u64 str_to_u64(const char *str) -{ - u64 val = 0; - int i; - - for (i = 0; i < sizeof(val); i++) - val = (*str) ? (val << 8) | *str++ : val << 8; - return val; -} -#define STR_TO_HEX(x) str_to_u64(x) -#define REG_ID(x) str_to_u64(x) - -#define FADUMP_CRASH_INFO_MAGIC STR_TO_HEX("FADMPINF") -#define REGSAVE_AREA_MAGIC STR_TO_HEX("REGSAVE") - -/* The firmware-assisted dump format. - * - * The register save area is an area in the partition's memory used to preserve - * the register contents (CPU state data) for the active CPUs during a firmware - * assisted dump. The dump format contains register save area header followed - * by register entries. Each list of registers for a CPU starts with - * "CPUSTRT" and ends with "CPUEND". - */ - -/* Register save area header. */ -struct fadump_reg_save_area_header { - __be64 magic_number; - __be32 version; - __be32 num_cpu_offset; -}; - -/* Register entry. */ -struct fadump_reg_entry { - __be64 reg_id; - __be64 reg_value; -}; - -/* fadump crash info structure */ -struct fadump_crash_info_header { - u64 magic_number; - u64 elfcorehdr_addr; - u32 crashing_cpu; - struct pt_regs regs; - struct cpumask online_mask; -}; - -struct fad_crash_memory_ranges { - unsigned long long base; - unsigned long long size; -}; - extern int is_fadump_memory_area(u64 addr, ulong size); -extern int early_init_dt_scan_fw_dump(unsigned long node, - const char *uname, int depth, void *data); -extern int fadump_reserve_mem(void); extern int setup_fadump(void); extern int is_fadump_active(void); extern int should_fadump_crash(void); @@ -207,5 +25,11 @@ static inline int is_fadump_active(void) { return 0; } static inline int should_fadump_crash(void) { return 0; } static inline void crash_fadump(struct pt_regs *regs, const char *str) { } static inline void fadump_cleanup(void) { } +#endif /* !CONFIG_FA_DUMP */ + +#if defined(CONFIG_FA_DUMP) || defined(CONFIG_PRESERVE_FA_DUMP) +extern int early_init_dt_scan_fw_dump(unsigned long node, const char *uname, + int depth, void *data); +extern int fadump_reserve_mem(void); #endif -#endif +#endif /* _ASM_POWERPC_FADUMP_H */ diff --git a/arch/powerpc/include/asm/firmware.h b/arch/powerpc/include/asm/firmware.h index faeca8b76c8c..b3e214a97f3a 100644 --- a/arch/powerpc/include/asm/firmware.h +++ b/arch/powerpc/include/asm/firmware.h @@ -50,6 +50,7 @@ #define FW_FEATURE_DRC_INFO ASM_CONST(0x0000000800000000) #define FW_FEATURE_BLOCK_REMOVE ASM_CONST(0x0000001000000000) #define FW_FEATURE_PAPR_SCM ASM_CONST(0x0000002000000000) +#define FW_FEATURE_ULTRAVISOR ASM_CONST(0x0000004000000000) #ifndef __ASSEMBLY__ @@ -68,9 +69,9 @@ enum { FW_FEATURE_TYPE1_AFFINITY | FW_FEATURE_PRRN | FW_FEATURE_HPT_RESIZE | FW_FEATURE_DRMEM_V2 | FW_FEATURE_DRC_INFO | FW_FEATURE_BLOCK_REMOVE | - FW_FEATURE_PAPR_SCM, + FW_FEATURE_PAPR_SCM | FW_FEATURE_ULTRAVISOR, FW_FEATURE_PSERIES_ALWAYS = 0, - FW_FEATURE_POWERNV_POSSIBLE = FW_FEATURE_OPAL, + FW_FEATURE_POWERNV_POSSIBLE = FW_FEATURE_OPAL | FW_FEATURE_ULTRAVISOR, FW_FEATURE_POWERNV_ALWAYS = 0, FW_FEATURE_PS3_POSSIBLE = FW_FEATURE_LPAR | FW_FEATURE_PS3_LV1, FW_FEATURE_PS3_ALWAYS = FW_FEATURE_LPAR | FW_FEATURE_PS3_LV1, diff --git a/arch/powerpc/include/asm/ftrace.h b/arch/powerpc/include/asm/ftrace.h index 3dfb80b86561..f54a08a2cd70 100644 --- a/arch/powerpc/include/asm/ftrace.h +++ b/arch/powerpc/include/asm/ftrace.h @@ -8,6 +8,8 @@ #define MCOUNT_ADDR ((unsigned long)(_mcount)) #define MCOUNT_INSN_SIZE 4 /* sizeof mcount call */ +#define HAVE_FUNCTION_GRAPH_RET_ADDR_PTR + #ifdef __ASSEMBLY__ /* Based off of objdump optput from glibc */ diff --git a/arch/powerpc/include/asm/futex.h b/arch/powerpc/include/asm/futex.h index 3a6aa57b9d90..eea28ca679db 100644 --- a/arch/powerpc/include/asm/futex.h +++ b/arch/powerpc/include/asm/futex.h @@ -60,8 +60,7 @@ static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval, pagefault_enable(); - if (!ret) - *oval = oldval; + *oval = oldval; prevent_write_to_user(uaddr, sizeof(*uaddr)); return ret; diff --git a/arch/powerpc/include/asm/head-64.h b/arch/powerpc/include/asm/head-64.h index a466765709a9..2dabcf668292 100644 --- a/arch/powerpc/include/asm/head-64.h +++ b/arch/powerpc/include/asm/head-64.h @@ -169,47 +169,6 @@ name: #define ABS_ADDR(label) (label - fs_label + fs_start) -#define EXC_REAL_BEGIN(name, start, size) \ - FIXED_SECTION_ENTRY_BEGIN_LOCATION(real_vectors, exc_real_##start##_##name, start, size) - -#define EXC_REAL_END(name, start, size) \ - FIXED_SECTION_ENTRY_END_LOCATION(real_vectors, exc_real_##start##_##name, start, size) - -#define EXC_VIRT_BEGIN(name, start, size) \ - FIXED_SECTION_ENTRY_BEGIN_LOCATION(virt_vectors, exc_virt_##start##_##name, start, size) - -#define EXC_VIRT_END(name, start, size) \ - FIXED_SECTION_ENTRY_END_LOCATION(virt_vectors, exc_virt_##start##_##name, start, size) - -#define EXC_COMMON_BEGIN(name) \ - USE_TEXT_SECTION(); \ - .balign IFETCH_ALIGN_BYTES; \ - .global name; \ - _ASM_NOKPROBE_SYMBOL(name); \ - DEFINE_FIXED_SYMBOL(name); \ -name: - -#define TRAMP_REAL_BEGIN(name) \ - FIXED_SECTION_ENTRY_BEGIN(real_trampolines, name) - -#define TRAMP_VIRT_BEGIN(name) \ - FIXED_SECTION_ENTRY_BEGIN(virt_trampolines, name) - -#ifdef CONFIG_KVM_BOOK3S_64_HANDLER -#define TRAMP_KVM_BEGIN(name) \ - TRAMP_VIRT_BEGIN(name) -#else -#define TRAMP_KVM_BEGIN(name) -#endif - -#define EXC_REAL_NONE(start, size) \ - FIXED_SECTION_ENTRY_BEGIN_LOCATION(real_vectors, exc_real_##start##_##unused, start, size); \ - FIXED_SECTION_ENTRY_END_LOCATION(real_vectors, exc_real_##start##_##unused, start, size) - -#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) - #endif /* __ASSEMBLY__ */ #endif /* _ASM_POWERPC_HEAD_64_H */ diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h index 20a101046cff..bd6504c28c2f 100644 --- a/arch/powerpc/include/asm/hugetlb.h +++ b/arch/powerpc/include/asm/hugetlb.h @@ -31,9 +31,6 @@ static inline int is_hugepage_only_range(struct mm_struct *mm, return 0; } -void book3e_hugetlb_preload(struct vm_area_struct *vma, unsigned long ea, - pte_t pte); - #define __HAVE_ARCH_HUGETLB_FREE_PGD_RANGE void hugetlb_free_pgd_range(struct mmu_gather *tlb, unsigned long addr, unsigned long end, unsigned long floor, diff --git a/arch/powerpc/include/asm/io-workarounds.h b/arch/powerpc/include/asm/io-workarounds.h index 01567ea4ceaf..3cce499fbe27 100644 --- a/arch/powerpc/include/asm/io-workarounds.h +++ b/arch/powerpc/include/asm/io-workarounds.h @@ -8,6 +8,7 @@ #ifndef _IO_WORKAROUNDS_H #define _IO_WORKAROUNDS_H +#ifdef CONFIG_PPC_IO_WORKAROUNDS #include <linux/io.h> #include <asm/pci-bridge.h> @@ -32,4 +33,23 @@ extern int spiderpci_iowa_init(struct iowa_bus *, void *); #define SPIDER_PCI_DUMMY_READ 0x0810 #define SPIDER_PCI_DUMMY_READ_BASE 0x0814 +#endif + +#if defined(CONFIG_PPC_IO_WORKAROUNDS) && defined(CONFIG_PPC_INDIRECT_MMIO) +extern bool io_workaround_inited; + +static inline bool iowa_is_active(void) +{ + return unlikely(io_workaround_inited); +} +#else +static inline bool iowa_is_active(void) +{ + return false; +} +#endif + +void __iomem *iowa_ioremap(phys_addr_t addr, unsigned long size, + pgprot_t prot, void *caller); + #endif /* _IO_WORKAROUNDS_H */ diff --git a/arch/powerpc/include/asm/io.h b/arch/powerpc/include/asm/io.h index 23e5d5d16c7e..a63ec938636d 100644 --- a/arch/powerpc/include/asm/io.h +++ b/arch/powerpc/include/asm/io.h @@ -705,16 +705,9 @@ static inline void iosync(void) * create hand-made mappings for use only by the PCI code and cannot * currently be hooked. Must be page aligned. * - * * __ioremap is the low level implementation used by ioremap and - * ioremap_prot and cannot be hooked (but can be used by a hook on one - * of the previous ones) - * * * __ioremap_caller is the same as above but takes an explicit caller * reference rather than using __builtin_return_address(0) * - * * __iounmap, is the low level implementation used by iounmap and cannot - * be hooked (but can be used by a hook on iounmap) - * */ extern void __iomem *ioremap(phys_addr_t address, unsigned long size); extern void __iomem *ioremap_prot(phys_addr_t address, unsigned long size, @@ -729,13 +722,14 @@ void __iomem *ioremap_coherent(phys_addr_t address, unsigned long size); extern void iounmap(volatile void __iomem *addr); -extern void __iomem *__ioremap(phys_addr_t, unsigned long size, - unsigned long flags); +int early_ioremap_range(unsigned long ea, phys_addr_t pa, + unsigned long size, pgprot_t prot); +void __iomem *do_ioremap(phys_addr_t pa, phys_addr_t offset, unsigned long size, + pgprot_t prot, void *caller); + extern void __iomem *__ioremap_caller(phys_addr_t, unsigned long size, pgprot_t prot, void *caller); -extern void __iounmap(volatile void __iomem *addr); - extern void __iomem * __ioremap_at(phys_addr_t pa, void *ea, unsigned long size, pgprot_t prot); extern void __iounmap_at(void *ea, unsigned long size); diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h index 18d342b815e4..350101e11ddb 100644 --- a/arch/powerpc/include/asm/iommu.h +++ b/arch/powerpc/include/asm/iommu.h @@ -48,15 +48,16 @@ struct iommu_table_ops { * returns old TCE and DMA direction mask. * @tce is a physical address. */ - int (*exchange)(struct iommu_table *tbl, + int (*xchg_no_kill)(struct iommu_table *tbl, long index, unsigned long *hpa, - enum dma_data_direction *direction); - /* Real mode */ - int (*exchange_rm)(struct iommu_table *tbl, - long index, - unsigned long *hpa, - enum dma_data_direction *direction); + enum dma_data_direction *direction, + bool realmode); + + void (*tce_kill)(struct iommu_table *tbl, + unsigned long index, + unsigned long pages, + bool realmode); __be64 *(*useraddrptr)(struct iommu_table *tbl, long index, bool alloc); #endif @@ -111,6 +112,8 @@ struct iommu_table { struct iommu_table_ops *it_ops; struct kref it_kref; int it_nid; + unsigned long it_reserved_start; /* Start of not-DMA-able (MMIO) area */ + unsigned long it_reserved_end; }; #define IOMMU_TABLE_USERSPACE_ENTRY_RO(tbl, entry) \ @@ -149,8 +152,9 @@ extern int iommu_tce_table_put(struct iommu_table *tbl); /* Initializes an iommu_table based in values set in the passed-in * structure */ -extern struct iommu_table *iommu_init_table(struct iommu_table * tbl, - int nid); +extern struct iommu_table *iommu_init_table(struct iommu_table *tbl, + int nid, unsigned long res_start, unsigned long res_end); + #define IOMMU_TABLE_GROUP_MAX_TABLES 2 struct iommu_table_group; @@ -206,6 +210,12 @@ extern void iommu_del_device(struct device *dev); extern long iommu_tce_xchg(struct mm_struct *mm, struct iommu_table *tbl, unsigned long entry, unsigned long *hpa, enum dma_data_direction *direction); +extern long iommu_tce_xchg_no_kill(struct mm_struct *mm, + struct iommu_table *tbl, + unsigned long entry, unsigned long *hpa, + enum dma_data_direction *direction); +extern void iommu_tce_kill(struct iommu_table *tbl, + unsigned long entry, unsigned long pages); #else static inline void iommu_register_group(struct iommu_table_group *table_group, int pci_domain_number, diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h index bb7c8cc77f1a..04b2b927bb5a 100644 --- a/arch/powerpc/include/asm/kvm_book3s_64.h +++ b/arch/powerpc/include/asm/kvm_book3s_64.h @@ -535,7 +535,7 @@ static inline void note_hpte_modification(struct kvm *kvm, */ static inline struct kvm_memslots *kvm_memslots_raw(struct kvm *kvm) { - return rcu_dereference_raw_notrace(kvm->memslots[0]); + return rcu_dereference_raw_check(kvm->memslots[0]); } extern void kvmppc_mmu_debugfs_init(struct kvm *kvm); diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index e6e5f59aaa97..6fe6ad64cba5 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -232,11 +232,25 @@ struct revmap_entry { }; /* - * We use the top bit of each memslot->arch.rmap entry as a lock bit, - * and bit 32 as a present flag. The bottom 32 bits are the - * index in the guest HPT of a HPTE that points to the page. + * The rmap array of size number of guest pages is allocated for each memslot. + * This array is used to store usage specific information about the guest page. + * Below are the encodings of the various possible usage types. */ -#define KVMPPC_RMAP_LOCK_BIT 63 +/* Free bits which can be used to define a new usage */ +#define KVMPPC_RMAP_TYPE_MASK 0xff00000000000000 +#define KVMPPC_RMAP_NESTED 0xc000000000000000 /* Nested rmap array */ +#define KVMPPC_RMAP_HPT 0x0100000000000000 /* HPT guest */ + +/* + * rmap usage definition for a hash page table (hpt) guest: + * 0x0000080000000000 Lock bit + * 0x0000018000000000 RC bits + * 0x0000000100000000 Present bit + * 0x00000000ffffffff HPT index bits + * The bottom 32 bits are the index in the guest HPT of a HPTE that points to + * the page. + */ +#define KVMPPC_RMAP_LOCK_BIT 43 #define KVMPPC_RMAP_RC_SHIFT 32 #define KVMPPC_RMAP_REFERENCED (HPTE_R_R << KVMPPC_RMAP_RC_SHIFT) #define KVMPPC_RMAP_PRESENT 0x100000000ul @@ -283,6 +297,7 @@ struct kvm_arch { cpumask_t cpu_in_guest; u8 radix; u8 fwnmi_enabled; + u8 secure_guest; bool threads_indep; bool nested_enable; pgd_t *pgtable; diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index 2484e6a8f5ca..8e8514efb124 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -598,6 +598,7 @@ extern int kvmppc_xive_native_get_vp(struct kvm_vcpu *vcpu, union kvmppc_one_reg *val); extern int kvmppc_xive_native_set_vp(struct kvm_vcpu *vcpu, union kvmppc_one_reg *val); +extern bool kvmppc_xive_native_supported(void); #else static inline int kvmppc_xive_set_xive(struct kvm *kvm, u32 irq, u32 server, diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h index c43d6eca9edd..7bcb64444a39 100644 --- a/arch/powerpc/include/asm/machdep.h +++ b/arch/powerpc/include/asm/machdep.h @@ -3,9 +3,6 @@ #define _ASM_POWERPC_MACHDEP_H #ifdef __KERNEL__ -/* - */ - #include <linux/seq_file.h> #include <linux/init.h> #include <linux/dma-mapping.h> @@ -31,10 +28,6 @@ struct pci_host_bridge; struct machdep_calls { char *name; #ifdef CONFIG_PPC64 - void __iomem * (*ioremap)(phys_addr_t addr, unsigned long size, - pgprot_t prot, void *caller); - void (*iounmap)(volatile void __iomem *token); - #ifdef CONFIG_PM void (*iommu_save)(void); void (*iommu_restore)(void); diff --git a/arch/powerpc/include/asm/mce.h b/arch/powerpc/include/asm/mce.h index a4c6a74ad2fb..6a6ddaabdb34 100644 --- a/arch/powerpc/include/asm/mce.h +++ b/arch/powerpc/include/asm/mce.h @@ -30,6 +30,10 @@ enum MCE_Disposition { enum MCE_Initiator { MCE_INITIATOR_UNKNOWN = 0, MCE_INITIATOR_CPU = 1, + MCE_INITIATOR_PCI = 2, + MCE_INITIATOR_ISA = 3, + MCE_INITIATOR_MEMORY= 4, + MCE_INITIATOR_POWERMGM = 5, }; enum MCE_ErrorType { @@ -41,6 +45,8 @@ enum MCE_ErrorType { MCE_ERROR_TYPE_USER = 5, MCE_ERROR_TYPE_RA = 6, MCE_ERROR_TYPE_LINK = 7, + MCE_ERROR_TYPE_DCACHE = 8, + MCE_ERROR_TYPE_ICACHE = 9, }; enum MCE_ErrorClass { @@ -122,7 +128,8 @@ struct machine_check_event { enum MCE_UeErrorType ue_error_type:8; u8 effective_address_provided; u8 physical_address_provided; - u8 reserved_1[5]; + u8 ignore_event; + u8 reserved_1[4]; u64 effective_address; u64 physical_address; u8 reserved_2[8]; @@ -193,6 +200,7 @@ struct mce_error_info { enum MCE_Initiator initiator:8; enum MCE_ErrorClass error_class:8; bool sync_error; + bool ignore_event; }; #define MAX_MC_EVT 100 diff --git a/arch/powerpc/include/asm/mem_encrypt.h b/arch/powerpc/include/asm/mem_encrypt.h new file mode 100644 index 000000000000..ba9dab07c1be --- /dev/null +++ b/arch/powerpc/include/asm/mem_encrypt.h @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * SVM helper functions + * + * Copyright 2018 IBM Corporation + */ + +#ifndef _ASM_POWERPC_MEM_ENCRYPT_H +#define _ASM_POWERPC_MEM_ENCRYPT_H + +#include <asm/svm.h> + +static inline bool mem_encrypt_active(void) +{ + return is_secure_guest(); +} + +static inline bool force_dma_unencrypted(struct device *dev) +{ + return is_secure_guest(); +} + +int set_memory_encrypted(unsigned long addr, int numpages); +int set_memory_decrypted(unsigned long addr, int numpages); + +#endif /* _ASM_POWERPC_MEM_ENCRYPT_H */ diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h index ba94ce8c22d7..0699cfeeb8c9 100644 --- a/arch/powerpc/include/asm/mmu.h +++ b/arch/powerpc/include/asm/mmu.h @@ -257,7 +257,7 @@ extern void radix__mmu_cleanup_all(void); /* Functions for creating and updating partition table on POWER9 */ extern void mmu_partition_table_init(void); extern void mmu_partition_table_set_entry(unsigned int lpid, unsigned long dw0, - unsigned long dw1); + unsigned long dw1, bool flush); #endif /* CONFIG_PPC64 */ struct mm_struct; diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h index 0284f8f5305f..552b96eef0c8 100644 --- a/arch/powerpc/include/asm/nohash/32/pgtable.h +++ b/arch/powerpc/include/asm/nohash/32/pgtable.h @@ -11,8 +11,6 @@ #include <asm/mmu.h> /* For sub-arch specific PPC_PIN_SIZE */ #include <asm/asm-405.h> -extern unsigned long ioremap_bot; - #ifdef CONFIG_44x extern int icache_44x_need_flush; #endif @@ -78,23 +76,21 @@ int map_kernel_page(unsigned long va, phys_addr_t pa, pgprot_t prot); */ #include <asm/fixmap.h> -#ifdef CONFIG_HIGHMEM -#define KVIRT_TOP PKMAP_BASE -#else -#define KVIRT_TOP FIXADDR_START -#endif - /* * ioremap_bot starts at that address. Early ioremaps move down from there, * until mem_init() at which point this becomes the top of the vmalloc * and ioremap space */ -#ifdef CONFIG_NOT_COHERENT_CACHE -#define IOREMAP_TOP ((KVIRT_TOP - CONFIG_CONSISTENT_SIZE) & PAGE_MASK) +#ifdef CONFIG_HIGHMEM +#define IOREMAP_TOP PKMAP_BASE #else -#define IOREMAP_TOP KVIRT_TOP +#define IOREMAP_TOP FIXADDR_START #endif +/* PPC32 shares vmalloc area with ioremap */ +#define IOREMAP_START VMALLOC_START +#define IOREMAP_END VMALLOC_END + /* * Just any arbitrary offset to the start of the vmalloc VM area: the * current 16MB value just means that there will be a 64MB "hole" after the diff --git a/arch/powerpc/include/asm/nohash/64/pgtable.h b/arch/powerpc/include/asm/nohash/64/pgtable.h index b9f66cf15c31..9a33b8bd842d 100644 --- a/arch/powerpc/include/asm/nohash/64/pgtable.h +++ b/arch/powerpc/include/asm/nohash/64/pgtable.h @@ -53,6 +53,7 @@ #define PHB_IO_BASE (ISA_IO_END) #define PHB_IO_END (KERN_IO_START + FULL_IO_SIZE) #define IOREMAP_BASE (PHB_IO_END) +#define IOREMAP_START (ioremap_bot) #define IOREMAP_END (KERN_VIRT_START + KERN_VIRT_SIZE) diff --git a/arch/powerpc/include/asm/nohash/pgtable.h b/arch/powerpc/include/asm/nohash/pgtable.h index 1ca1c1864b32..7fed9dc0f147 100644 --- a/arch/powerpc/include/asm/nohash/pgtable.h +++ b/arch/powerpc/include/asm/nohash/pgtable.h @@ -293,5 +293,18 @@ static inline int pgd_huge(pgd_t pgd) #define is_hugepd(hpd) (hugepd_ok(hpd)) #endif +/* + * This gets called at the end of handling a page fault, when + * the kernel has put a new PTE into the page table for the process. + * We use it to ensure coherency between the i-cache and d-cache + * for the page which has just been mapped in. + */ +#if defined(CONFIG_PPC_FSL_BOOK3E) && defined(CONFIG_HUGETLB_PAGE) +void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep); +#else +static inline +void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) {} +#endif + #endif /* __ASSEMBLY__ */ #endif diff --git a/arch/powerpc/include/asm/opal-api.h b/arch/powerpc/include/asm/opal-api.h index 383242eb0dea..378e3997845a 100644 --- a/arch/powerpc/include/asm/opal-api.h +++ b/arch/powerpc/include/asm/opal-api.h @@ -208,7 +208,10 @@ #define OPAL_HANDLE_HMI2 166 #define OPAL_NX_COPROC_INIT 167 #define OPAL_XIVE_GET_VP_STATE 170 -#define OPAL_LAST 170 +#define OPAL_MPIPL_UPDATE 173 +#define OPAL_MPIPL_REGISTER_TAG 174 +#define OPAL_MPIPL_QUERY_TAG 175 +#define OPAL_LAST 175 #define QUIESCE_HOLD 1 /* Spin all calls at entry */ #define QUIESCE_REJECT 2 /* Fail all calls with OPAL_BUSY */ @@ -453,6 +456,7 @@ enum opal_msg_type { OPAL_MSG_DPO = 5, OPAL_MSG_PRD = 6, OPAL_MSG_OCC = 7, + OPAL_MSG_PRD2 = 8, OPAL_MSG_TYPE_MAX, }; @@ -1059,6 +1063,7 @@ enum { OPAL_REBOOT_NORMAL = 0, OPAL_REBOOT_PLATFORM_ERROR = 1, OPAL_REBOOT_FULL_IPL = 2, + OPAL_REBOOT_MPIPL = 3, }; /* Argument to OPAL_PCI_TCE_KILL */ @@ -1135,6 +1140,44 @@ enum { #define OPAL_PCI_P2P_LOAD 0x2 #define OPAL_PCI_P2P_STORE 0x4 +/* MPIPL update operations */ +enum opal_mpipl_ops { + OPAL_MPIPL_ADD_RANGE = 0, + OPAL_MPIPL_REMOVE_RANGE = 1, + OPAL_MPIPL_REMOVE_ALL = 2, + OPAL_MPIPL_FREE_PRESERVED_MEMORY = 3, +}; + +/* Tag will point to various metadata area. Kernel will + * use tag to get metadata value. + */ +enum opal_mpipl_tags { + OPAL_MPIPL_TAG_CPU = 0, + OPAL_MPIPL_TAG_OPAL = 1, + OPAL_MPIPL_TAG_KERNEL = 2, + OPAL_MPIPL_TAG_BOOT_MEM = 3, +}; + +/* Preserved memory details */ +struct opal_mpipl_region { + __be64 src; + __be64 dest; + __be64 size; +}; + +/* Structure version */ +#define OPAL_MPIPL_VERSION 0x01 + +struct opal_mpipl_fadump { + u8 version; + u8 reserved[7]; + __be32 crashing_pir; /* OPAL crashing CPU PIR */ + __be32 cpu_data_version; + __be32 cpu_data_size; + __be32 region_cnt; + struct opal_mpipl_region region[]; +} __packed; + #endif /* __ASSEMBLY__ */ #endif /* __OPAL_API_H */ diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h index 57bd029c715e..a0cf8fba4d12 100644 --- a/arch/powerpc/include/asm/opal.h +++ b/arch/powerpc/include/asm/opal.h @@ -39,6 +39,7 @@ int64_t opal_npu_spa_clear_cache(uint64_t phb_id, uint32_t bdfn, uint64_t PE_handle); int64_t opal_npu_tl_set(uint64_t phb_id, uint32_t bdfn, long cap, uint64_t rate_phys, uint32_t size); + int64_t opal_console_write(int64_t term_number, __be64 *length, const uint8_t *buffer); int64_t opal_console_read(int64_t term_number, __be64 *length, @@ -272,7 +273,7 @@ int64_t opal_xive_get_vp_info(uint64_t vp, int64_t opal_xive_set_vp_info(uint64_t vp, uint64_t flags, uint64_t report_cl_pair); -int64_t opal_xive_allocate_irq(uint32_t chip_id); +int64_t opal_xive_allocate_irq_raw(uint32_t chip_id); int64_t opal_xive_free_irq(uint32_t girq); int64_t opal_xive_sync(uint32_t type, uint32_t id); int64_t opal_xive_dump(uint32_t type, uint32_t id); @@ -297,6 +298,10 @@ int opal_sensor_group_clear(u32 group_hndl, int token); int opal_sensor_group_enable(u32 group_hndl, int token, bool enable); int opal_nx_coproc_init(uint32_t chip_id, uint32_t ct); +s64 opal_mpipl_update(enum opal_mpipl_ops op, u64 src, u64 dest, u64 size); +s64 opal_mpipl_register_tag(enum opal_mpipl_tags tag, u64 addr); +s64 opal_mpipl_query_tag(enum opal_mpipl_tags tag, u64 *addr); + s64 opal_signal_system_reset(s32 cpu); s64 opal_quiesce(u64 shutdown_type, s32 cpu); diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h index 0d52f57fca04..c8bb14ff4713 100644 --- a/arch/powerpc/include/asm/page.h +++ b/arch/powerpc/include/asm/page.h @@ -215,9 +215,19 @@ static inline bool pfn_valid(unsigned long pfn) /* * gcc miscompiles (unsigned long)(&static_var) - PAGE_OFFSET * with -mcmodel=medium, so we use & and | instead of - and + on 64-bit. + * This also results in better code generation. */ -#define __va(x) ((void *)(unsigned long)((phys_addr_t)(x) | PAGE_OFFSET)) -#define __pa(x) ((unsigned long)(x) & 0x0fffffffffffffffUL) +#define __va(x) \ +({ \ + VIRTUAL_BUG_ON((unsigned long)(x) >= PAGE_OFFSET); \ + (void *)(unsigned long)((phys_addr_t)(x) | PAGE_OFFSET); \ +}) + +#define __pa(x) \ +({ \ + VIRTUAL_BUG_ON((unsigned long)(x) < PAGE_OFFSET); \ + (unsigned long)(x) & 0x0fffffffffffffffUL; \ +}) #else /* 32-bit, non book E */ #define __va(x) ((void *)(unsigned long)((phys_addr_t)(x) + PAGE_OFFSET - MEMORY_START)) diff --git a/arch/powerpc/include/asm/page_32.h b/arch/powerpc/include/asm/page_32.h index 683dfbc67ca8..d64dfe3ac712 100644 --- a/arch/powerpc/include/asm/page_32.h +++ b/arch/powerpc/include/asm/page_32.h @@ -40,6 +40,8 @@ typedef unsigned long long pte_basic_t; typedef unsigned long pte_basic_t; #endif +#include <asm/bug.h> + /* * Clear page using the dcbz instruction, which doesn't cause any * memory traffic (except to write out any cache lines which get @@ -49,6 +51,8 @@ static inline void clear_page(void *addr) { unsigned int i; + WARN_ON((unsigned long)addr & (L1_CACHE_BYTES - 1)); + for (i = 0; i < PAGE_SIZE / L1_CACHE_BYTES; i++, addr += L1_CACHE_BYTES) dcbz(addr); } diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h index 8dad1fdf4bd2..ea6ec65970ef 100644 --- a/arch/powerpc/include/asm/pci-bridge.h +++ b/arch/powerpc/include/asm/pci-bridge.h @@ -183,6 +183,7 @@ struct iommu_table; struct pci_dn { int flags; #define PCI_DN_FLAG_IOV_VF 0x01 +#define PCI_DN_FLAG_DEAD 0x02 /* Device has been hot-removed */ int busno; /* pci bus number */ int devfn; /* pci device and function number */ diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h index c58ba7963688..8b7865a2d576 100644 --- a/arch/powerpc/include/asm/pgtable.h +++ b/arch/powerpc/include/asm/pgtable.h @@ -68,6 +68,8 @@ extern pgd_t swapper_pg_dir[]; extern void paging_init(void); +extern unsigned long ioremap_bot; + /* * kern_addr_valid is intended to indicate whether an address is a valid * kernel address. Most 32-bit archs define it as always true (like this) @@ -77,18 +79,6 @@ extern void paging_init(void); #include <asm-generic/pgtable.h> - -/* - * This gets called at the end of handling a page fault, when - * the kernel has put a new PTE into the page table for the process. - * We use it to ensure coherency between the i-cache and d-cache - * for the page which has just been mapped in. - * On machines which use an MMU hash table, we use this to put a - * corresponding HPTE into the hash table ahead of time, instead of - * waiting for the inevitable extra hash-table miss exception. - */ -extern void update_mmu_cache(struct vm_area_struct *, unsigned long, pte_t *); - #ifndef CONFIG_TRANSPARENT_HUGEPAGE #define pmd_large(pmd) 0 #endif diff --git a/arch/powerpc/include/asm/plpar_wrappers.h b/arch/powerpc/include/asm/plpar_wrappers.h index cff5a411e595..4497c8afb573 100644 --- a/arch/powerpc/include/asm/plpar_wrappers.h +++ b/arch/powerpc/include/asm/plpar_wrappers.h @@ -340,6 +340,12 @@ static inline long plpar_set_ciabr(unsigned long ciabr) { return 0; } + +static inline long plpar_pte_read_4(unsigned long flags, unsigned long ptex, + unsigned long *ptes) +{ + return 0; +} #endif /* CONFIG_PPC_PSERIES */ #endif /* _ASM_POWERPC_PLPAR_WRAPPERS_H */ diff --git a/arch/powerpc/include/asm/ppc-pci.h b/arch/powerpc/include/asm/ppc-pci.h index cec2d6409515..7f4be5a05eb3 100644 --- a/arch/powerpc/include/asm/ppc-pci.h +++ b/arch/powerpc/include/asm/ppc-pci.h @@ -62,11 +62,6 @@ void eeh_pe_dev_mode_mark(struct eeh_pe *pe, int mode); void eeh_sysfs_add_device(struct pci_dev *pdev); void eeh_sysfs_remove_device(struct pci_dev *pdev); -static inline const char *eeh_pci_name(struct pci_dev *pdev) -{ - return pdev ? pci_name(pdev) : "<null>"; -} - static inline const char *eeh_driver_name(struct pci_dev *pdev) { return (pdev && pdev->driver) ? pdev->driver->name : "<null>"; @@ -74,6 +69,8 @@ static inline const char *eeh_driver_name(struct pci_dev *pdev) #endif /* CONFIG_EEH */ +#define PCI_BUSNO(bdfn) ((bdfn >> 8) & 0xff) + #else /* CONFIG_PCI */ static inline void init_pci_config_tokens(void) { } #endif /* !CONFIG_PCI */ diff --git a/arch/powerpc/include/asm/ppc4xx_ocm.h b/arch/powerpc/include/asm/ppc4xx_ocm.h deleted file mode 100644 index fc4db6dcde84..000000000000 --- a/arch/powerpc/include/asm/ppc4xx_ocm.h +++ /dev/null @@ -1,31 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * PowerPC 4xx OCM memory allocation support - * - * (C) Copyright 2009, Applied Micro Circuits Corporation - * Victor Gallardo (vgallardo@amcc.com) - * - * See file CREDITS for list of people who contributed to this - * project. - */ - -#ifndef __ASM_POWERPC_PPC4XX_OCM_H__ -#define __ASM_POWERPC_PPC4XX_OCM_H__ - -#define PPC4XX_OCM_NON_CACHED 0 -#define PPC4XX_OCM_CACHED 1 - -#if defined(CONFIG_PPC4xx_OCM) - -void *ppc4xx_ocm_alloc(phys_addr_t *phys, int size, int align, - int flags, const char *owner); -void ppc4xx_ocm_free(const void *virt); - -#else - -#define ppc4xx_ocm_alloc(phys, size, align, flags, owner) NULL -#define ppc4xx_ocm_free(addr) ((void)0) - -#endif /* CONFIG_PPC4xx_OCM */ - -#endif /* __ASM_POWERPC_PPC4XX_OCM_H__ */ diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h index e0637730a8e7..6b03dff61a05 100644 --- a/arch/powerpc/include/asm/ppc_asm.h +++ b/arch/powerpc/include/asm/ppc_asm.h @@ -311,18 +311,48 @@ n: addis reg,reg,(name - 0b)@ha; \ addi reg,reg,(name - 0b)@l; -#ifdef __powerpc64__ -#ifdef HAVE_AS_ATHIGH +#if defined(__powerpc64__) && defined(HAVE_AS_ATHIGH) #define __AS_ATHIGH high #else #define __AS_ATHIGH h #endif -#define LOAD_REG_IMMEDIATE(reg,expr) \ - lis reg,(expr)@highest; \ - ori reg,reg,(expr)@higher; \ - rldicr reg,reg,32,31; \ - oris reg,reg,(expr)@__AS_ATHIGH; \ - ori reg,reg,(expr)@l; + +.macro __LOAD_REG_IMMEDIATE_32 r, x + .if (\x) >= 0x8000 || (\x) < -0x8000 + lis \r, (\x)@__AS_ATHIGH + .if (\x) & 0xffff != 0 + ori \r, \r, (\x)@l + .endif + .else + li \r, (\x)@l + .endif +.endm + +.macro __LOAD_REG_IMMEDIATE r, x + .if (\x) >= 0x80000000 || (\x) < -0x80000000 + __LOAD_REG_IMMEDIATE_32 \r, (\x) >> 32 + sldi \r, \r, 32 + .if (\x) & 0xffff0000 != 0 + oris \r, \r, (\x)@__AS_ATHIGH + .endif + .if (\x) & 0xffff != 0 + ori \r, \r, (\x)@l + .endif + .else + __LOAD_REG_IMMEDIATE_32 \r, \x + .endif +.endm + +#ifdef __powerpc64__ + +#define LOAD_REG_IMMEDIATE(reg, expr) __LOAD_REG_IMMEDIATE reg, expr + +#define LOAD_REG_IMMEDIATE_SYM(reg, tmp, expr) \ + lis tmp, (expr)@highest; \ + lis reg, (expr)@__AS_ATHIGH; \ + ori tmp, tmp, (expr)@higher; \ + ori reg, reg, (expr)@l; \ + rldimi reg, tmp, 32, 0 #define LOAD_REG_ADDR(reg,name) \ ld reg,name@got(r2) @@ -335,11 +365,13 @@ n: #else /* 32-bit */ -#define LOAD_REG_IMMEDIATE(reg,expr) \ +#define LOAD_REG_IMMEDIATE(reg, expr) __LOAD_REG_IMMEDIATE_32 reg, expr + +#define LOAD_REG_IMMEDIATE_SYM(reg,expr) \ lis reg,(expr)@ha; \ addi reg,reg,(expr)@l; -#define LOAD_REG_ADDR(reg,name) LOAD_REG_IMMEDIATE(reg, name) +#define LOAD_REG_ADDR(reg,name) LOAD_REG_IMMEDIATE_SYM(reg, name) #define LOAD_REG_ADDRBASE(reg, name) lis reg,name@ha #define ADDROFF(name) name@l @@ -351,19 +383,9 @@ n: /* various errata or part fixups */ #ifdef CONFIG_PPC601_SYNC_FIX -#define SYNC \ -BEGIN_FTR_SECTION \ - sync; \ - isync; \ -END_FTR_SECTION_IFSET(CPU_FTR_601) -#define SYNC_601 \ -BEGIN_FTR_SECTION \ - sync; \ -END_FTR_SECTION_IFSET(CPU_FTR_601) -#define ISYNC_601 \ -BEGIN_FTR_SECTION \ - isync; \ -END_FTR_SECTION_IFSET(CPU_FTR_601) +#define SYNC sync; isync +#define SYNC_601 sync +#define ISYNC_601 isync #else #define SYNC #define SYNC_601 @@ -389,15 +411,11 @@ END_FTR_SECTION_NESTED(CPU_FTR_CELL_TB_BUG, CPU_FTR_CELL_TB_BUG, 96) #define MFTBU(dest) mfspr dest, SPRN_TBRU #endif -#ifndef CONFIG_SMP -#define TLBSYNC -#else /* CONFIG_SMP */ /* tlbsync is not implemented on 601 */ -#define TLBSYNC \ -BEGIN_FTR_SECTION \ - tlbsync; \ - sync; \ -END_FTR_SECTION_IFCLR(CPU_FTR_601) +#if !defined(CONFIG_SMP) || defined(CONFIG_PPC_BOOK3S_601) +#define TLBSYNC +#else +#define TLBSYNC tlbsync; sync #endif #ifdef CONFIG_PPC64 diff --git a/arch/powerpc/include/asm/ptrace.h b/arch/powerpc/include/asm/ptrace.h index feee1b21bbd5..ee3ada66deb5 100644 --- a/arch/powerpc/include/asm/ptrace.h +++ b/arch/powerpc/include/asm/ptrace.h @@ -203,7 +203,11 @@ do { \ #endif /* __powerpc64__ */ #define arch_has_single_step() (1) -#define arch_has_block_step() (!cpu_has_feature(CPU_FTR_601)) +#ifndef CONFIG_BOOK3S_601 +#define arch_has_block_step() (true) +#else +#define arch_has_block_step() (false) +#endif #define ARCH_HAS_USER_SINGLE_STEP_REPORT /* diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index 10caa145f98b..ec3714cf0989 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -38,6 +38,7 @@ #define MSR_TM_LG 32 /* Trans Mem Available */ #define MSR_VEC_LG 25 /* Enable AltiVec */ #define MSR_VSX_LG 23 /* Enable VSX */ +#define MSR_S_LG 22 /* Secure state */ #define MSR_POW_LG 18 /* Enable Power Management */ #define MSR_WE_LG 18 /* Wait State Enable */ #define MSR_TGPR_LG 17 /* TLB Update registers in use */ @@ -71,11 +72,13 @@ #define MSR_SF __MASK(MSR_SF_LG) /* Enable 64 bit mode */ #define MSR_ISF __MASK(MSR_ISF_LG) /* Interrupt 64b mode valid on 630 */ #define MSR_HV __MASK(MSR_HV_LG) /* Hypervisor state */ +#define MSR_S __MASK(MSR_S_LG) /* Secure state */ #else /* so tests for these bits fail on 32-bit */ #define MSR_SF 0 #define MSR_ISF 0 #define MSR_HV 0 +#define MSR_S 0 #endif /* diff --git a/arch/powerpc/include/asm/scom.h b/arch/powerpc/include/asm/scom.h deleted file mode 100644 index 08c44396e54a..000000000000 --- a/arch/powerpc/include/asm/scom.h +++ /dev/null @@ -1,154 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * Copyright 2010 Benjamin Herrenschmidt, IBM Corp - * <benh@kernel.crashing.org> - * and David Gibson, IBM Corporation. - */ - -#ifndef _ASM_POWERPC_SCOM_H -#define _ASM_POWERPC_SCOM_H - -#ifdef __KERNEL__ -#ifndef __ASSEMBLY__ -#ifdef CONFIG_PPC_SCOM - -/* - * The SCOM bus is a sideband bus used for accessing various internal - * registers of the processor or the chipset. The implementation details - * differ between processors and platforms, and the access method as - * well. - * - * This API allows to "map" ranges of SCOM register numbers associated - * with a given SCOM controller. The later must be represented by a - * device node, though some implementations might support NULL if there - * is no possible ambiguity - * - * Then, scom_read/scom_write can be used to accesses registers inside - * that range. The argument passed is a register number relative to - * the beginning of the range mapped. - */ - -typedef void *scom_map_t; - -/* Value for an invalid SCOM map */ -#define SCOM_MAP_INVALID (NULL) - -/* The scom_controller data structure is what the platform passes - * to the core code in scom_init, it provides the actual implementation - * of all the SCOM functions - */ -struct scom_controller { - scom_map_t (*map)(struct device_node *ctrl_dev, u64 reg, u64 count); - void (*unmap)(scom_map_t map); - - int (*read)(scom_map_t map, u64 reg, u64 *value); - int (*write)(scom_map_t map, u64 reg, u64 value); -}; - -extern const struct scom_controller *scom_controller; - -/** - * scom_init - Initialize the SCOM backend, called by the platform - * @controller: The platform SCOM controller - */ -static inline void scom_init(const struct scom_controller *controller) -{ - scom_controller = controller; -} - -/** - * scom_map_ok - Test is a SCOM mapping is successful - * @map: The result of scom_map to test - */ -static inline int scom_map_ok(scom_map_t map) -{ - return map != SCOM_MAP_INVALID; -} - -/** - * scom_map - Map a block of SCOM registers - * @ctrl_dev: Device node of the SCOM controller - * some implementations allow NULL here - * @reg: first SCOM register to map - * @count: Number of SCOM registers to map - */ - -static inline scom_map_t scom_map(struct device_node *ctrl_dev, - u64 reg, u64 count) -{ - return scom_controller->map(ctrl_dev, reg, count); -} - -/** - * scom_find_parent - Find the SCOM controller for a device - * @dev: OF node of the device - * - * This is not meant for general usage, but in combination with - * scom_map() allows to map registers not represented by the - * device own scom-reg property. Useful for applying HW workarounds - * on things not properly represented in the device-tree for example. - */ -struct device_node *scom_find_parent(struct device_node *dev); - - -/** - * scom_map_device - Map a device's block of SCOM registers - * @dev: OF node of the device - * @index: Register bank index (index in "scom-reg" property) - * - * This function will use the device-tree binding for SCOM which - * is to follow "scom-parent" properties until it finds a node with - * a "scom-controller" property to find the controller. It will then - * use the "scom-reg" property which is made of reg/count pairs, - * each of them having a size defined by the controller's #scom-cells - * property - */ -extern scom_map_t scom_map_device(struct device_node *dev, int index); - - -/** - * scom_unmap - Unmap a block of SCOM registers - * @map: Result of scom_map is to be unmapped - */ -static inline void scom_unmap(scom_map_t map) -{ - if (scom_map_ok(map)) - scom_controller->unmap(map); -} - -/** - * scom_read - Read a SCOM register - * @map: Result of scom_map - * @reg: Register index within that map - * @value: Updated with the value read - * - * Returns 0 (success) or a negative error code - */ -static inline int scom_read(scom_map_t map, u64 reg, u64 *value) -{ - int rc; - - rc = scom_controller->read(map, reg, value); - if (rc) - *value = 0xfffffffffffffffful; - return rc; -} - -/** - * scom_write - Write to a SCOM register - * @map: Result of scom_map - * @reg: Register index within that map - * @value: Value to write - * - * Returns 0 (success) or a negative error code - */ -static inline int scom_write(scom_map_t map, u64 reg, u64 value) -{ - return scom_controller->write(map, reg, value); -} - - -#endif /* CONFIG_PPC_SCOM */ -#endif /* __ASSEMBLY__ */ -#endif /* __KERNEL__ */ -#endif /* _ASM_POWERPC_SCOM_H */ diff --git a/arch/powerpc/include/asm/sections.h b/arch/powerpc/include/asm/sections.h index 4a1664a8658d..5a9b6eb651b6 100644 --- a/arch/powerpc/include/asm/sections.h +++ b/arch/powerpc/include/asm/sections.h @@ -61,17 +61,6 @@ static inline int overlaps_kernel_text(unsigned long start, unsigned long end) (unsigned long)_stext < end; } -static inline int overlaps_kvm_tmp(unsigned long start, unsigned long end) -{ -#ifdef CONFIG_KVM_GUEST - extern char kvm_tmp[]; - return start < (unsigned long)kvm_tmp && - (unsigned long)&kvm_tmp[1024 * 1024] < end; -#else - return 0; -#endif -} - #ifdef PPC64_ELF_ABI_v1 #define HAVE_DEREFERENCE_FUNCTION_DESCRIPTOR 1 diff --git a/arch/powerpc/include/asm/setjmp.h b/arch/powerpc/include/asm/setjmp.h index d995061f5f86..e9f81bb3f83b 100644 --- a/arch/powerpc/include/asm/setjmp.h +++ b/arch/powerpc/include/asm/setjmp.h @@ -7,7 +7,7 @@ #define JMP_BUF_LEN 23 -extern long setjmp(long *); -extern void longjmp(long *, long); +extern long setjmp(long *) __attribute__((returns_twice)); +extern void longjmp(long *, long) __attribute__((noreturn)); #endif /* _ASM_POWERPC_SETJMP_H */ diff --git a/arch/powerpc/include/asm/spinlock.h b/arch/powerpc/include/asm/spinlock.h index a47f827bc5f1..e9a960e28f3c 100644 --- a/arch/powerpc/include/asm/spinlock.h +++ b/arch/powerpc/include/asm/spinlock.h @@ -101,15 +101,43 @@ static inline int arch_spin_trylock(arch_spinlock_t *lock) #if defined(CONFIG_PPC_SPLPAR) /* We only yield to the hypervisor if we are in shared processor mode */ -#define SHARED_PROCESSOR (lppaca_shared_proc(local_paca->lppaca_ptr)) -extern void __spin_yield(arch_spinlock_t *lock); -extern void __rw_yield(arch_rwlock_t *lock); +void splpar_spin_yield(arch_spinlock_t *lock); +void splpar_rw_yield(arch_rwlock_t *lock); #else /* SPLPAR */ -#define __spin_yield(x) barrier() -#define __rw_yield(x) barrier() -#define SHARED_PROCESSOR 0 +static inline void splpar_spin_yield(arch_spinlock_t *lock) {}; +static inline void splpar_rw_yield(arch_rwlock_t *lock) {}; #endif +static inline bool is_shared_processor(void) +{ +/* + * LPPACA is only available on Pseries so guard anything LPPACA related to + * allow other platforms (which include this common header) to compile. + */ +#ifdef CONFIG_PPC_PSERIES + return (IS_ENABLED(CONFIG_PPC_SPLPAR) && + lppaca_shared_proc(local_paca->lppaca_ptr)); +#else + return false; +#endif +} + +static inline void spin_yield(arch_spinlock_t *lock) +{ + if (is_shared_processor()) + splpar_spin_yield(lock); + else + barrier(); +} + +static inline void rw_yield(arch_rwlock_t *lock) +{ + if (is_shared_processor()) + splpar_rw_yield(lock); + else + barrier(); +} + static inline void arch_spin_lock(arch_spinlock_t *lock) { while (1) { @@ -117,8 +145,8 @@ static inline void arch_spin_lock(arch_spinlock_t *lock) break; do { HMT_low(); - if (SHARED_PROCESSOR) - __spin_yield(lock); + if (is_shared_processor()) + splpar_spin_yield(lock); } while (unlikely(lock->slock != 0)); HMT_medium(); } @@ -136,8 +164,8 @@ void arch_spin_lock_flags(arch_spinlock_t *lock, unsigned long flags) local_irq_restore(flags); do { HMT_low(); - if (SHARED_PROCESSOR) - __spin_yield(lock); + if (is_shared_processor()) + splpar_spin_yield(lock); } while (unlikely(lock->slock != 0)); HMT_medium(); local_irq_restore(flags_dis); @@ -226,8 +254,8 @@ static inline void arch_read_lock(arch_rwlock_t *rw) break; do { HMT_low(); - if (SHARED_PROCESSOR) - __rw_yield(rw); + if (is_shared_processor()) + splpar_rw_yield(rw); } while (unlikely(rw->lock < 0)); HMT_medium(); } @@ -240,8 +268,8 @@ static inline void arch_write_lock(arch_rwlock_t *rw) break; do { HMT_low(); - if (SHARED_PROCESSOR) - __rw_yield(rw); + if (is_shared_processor()) + splpar_rw_yield(rw); } while (unlikely(rw->lock != 0)); HMT_medium(); } @@ -281,9 +309,9 @@ static inline void arch_write_unlock(arch_rwlock_t *rw) rw->lock = 0; } -#define arch_spin_relax(lock) __spin_yield(lock) -#define arch_read_relax(lock) __rw_yield(lock) -#define arch_write_relax(lock) __rw_yield(lock) +#define arch_spin_relax(lock) spin_yield(lock) +#define arch_read_relax(lock) rw_yield(lock) +#define arch_write_relax(lock) rw_yield(lock) /* See include/linux/spinlock.h */ #define smp_mb__after_spinlock() smp_mb() diff --git a/arch/powerpc/include/asm/string.h b/arch/powerpc/include/asm/string.h index 9bf6dffb4090..b72692702f35 100644 --- a/arch/powerpc/include/asm/string.h +++ b/arch/powerpc/include/asm/string.h @@ -53,7 +53,9 @@ void *__memmove(void *to, const void *from, __kernel_size_t n); #ifndef CONFIG_KASAN #define __HAVE_ARCH_MEMSET32 #define __HAVE_ARCH_MEMSET64 +#define __HAVE_ARCH_MEMCPY_MCSAFE +extern int memcpy_mcsafe(void *dst, const void *src, __kernel_size_t sz); extern void *__memset16(uint16_t *, uint16_t v, __kernel_size_t); extern void *__memset32(uint32_t *, uint32_t v, __kernel_size_t); extern void *__memset64(uint64_t *, uint64_t v, __kernel_size_t); diff --git a/arch/powerpc/include/asm/svm.h b/arch/powerpc/include/asm/svm.h new file mode 100644 index 000000000000..85580b30aba4 --- /dev/null +++ b/arch/powerpc/include/asm/svm.h @@ -0,0 +1,31 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * SVM helper functions + * + * Copyright 2018 Anshuman Khandual, IBM Corporation. + */ + +#ifndef _ASM_POWERPC_SVM_H +#define _ASM_POWERPC_SVM_H + +#ifdef CONFIG_PPC_SVM + +static inline bool is_secure_guest(void) +{ + return mfmsr() & MSR_S; +} + +void dtl_cache_ctor(void *addr); +#define get_dtl_cache_ctor() (is_secure_guest() ? dtl_cache_ctor : NULL) + +#else /* CONFIG_PPC_SVM */ + +static inline bool is_secure_guest(void) +{ + return false; +} + +#define get_dtl_cache_ctor() NULL + +#endif /* CONFIG_PPC_SVM */ +#endif /* _ASM_POWERPC_SVM_H */ diff --git a/arch/powerpc/include/asm/time.h b/arch/powerpc/include/asm/time.h index 54f4ec1f9fab..08dbe3e6831c 100644 --- a/arch/powerpc/include/asm/time.h +++ b/arch/powerpc/include/asm/time.h @@ -41,11 +41,7 @@ struct div_result { /* Accessor functions for the timebase (RTC on 601) registers. */ /* If one day CONFIG_POWER is added just define __USE_RTC as 1 */ -#ifdef CONFIG_PPC_BOOK3S_32 -#define __USE_RTC() (cpu_has_feature(CPU_FTR_USE_RTC)) -#else -#define __USE_RTC() 0 -#endif +#define __USE_RTC() (IS_ENABLED(CONFIG_PPC_BOOK3S_601)) #ifdef CONFIG_PPC64 diff --git a/arch/powerpc/include/asm/timex.h b/arch/powerpc/include/asm/timex.h index 926b9f91a3ef..d2d2c4bd8435 100644 --- a/arch/powerpc/include/asm/timex.h +++ b/arch/powerpc/include/asm/timex.h @@ -17,38 +17,10 @@ typedef unsigned long cycles_t; static inline cycles_t get_cycles(void) { -#ifdef __powerpc64__ + if (IS_ENABLED(CONFIG_BOOK3S_601)) + return 0; + return mftb(); -#else - cycles_t ret; - - /* - * For the "cycle" counter we use the timebase lower half. - * Currently only used on SMP. - */ - - ret = 0; - - __asm__ __volatile__( -#ifdef CONFIG_PPC_8xx - "97: mftb %0\n" -#else - "97: mfspr %0, %2\n" -#endif - "99:\n" - ".section __ftr_fixup,\"a\"\n" - ".align 2\n" - "98:\n" - " .long %1\n" - " .long 0\n" - " .long 97b-98b\n" - " .long 99b-98b\n" - " .long 0\n" - " .long 0\n" - ".previous" - : "=r" (ret) : "i" (CPU_FTR_601), "i" (SPRN_TBRL)); - return ret; -#endif } #endif /* __KERNEL__ */ diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h index 8b03eb44e876..15002b51ff18 100644 --- a/arch/powerpc/include/asm/uaccess.h +++ b/arch/powerpc/include/asm/uaccess.h @@ -387,6 +387,20 @@ static inline unsigned long raw_copy_to_user(void __user *to, return ret; } +static __always_inline unsigned long __must_check +copy_to_user_mcsafe(void __user *to, const void *from, unsigned long n) +{ + if (likely(check_copy_size(from, n, true))) { + if (access_ok(to, n)) { + allow_write_to_user(to, n); + n = memcpy_mcsafe((void *)to, from, n); + prevent_write_to_user(to, n); + } + } + + return n; +} + extern unsigned long __clear_user(void __user *addr, unsigned long size); static inline unsigned long clear_user(void __user *addr, unsigned long size) diff --git a/arch/powerpc/include/asm/ultravisor-api.h b/arch/powerpc/include/asm/ultravisor-api.h new file mode 100644 index 000000000000..4fcda1d5793d --- /dev/null +++ b/arch/powerpc/include/asm/ultravisor-api.h @@ -0,0 +1,33 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Ultravisor API. + * + * Copyright 2019, IBM Corporation. + * + */ +#ifndef _ASM_POWERPC_ULTRAVISOR_API_H +#define _ASM_POWERPC_ULTRAVISOR_API_H + +#include <asm/hvcall.h> + +/* Return codes */ +#define U_BUSY H_BUSY +#define U_FUNCTION H_FUNCTION +#define U_NOT_AVAILABLE H_NOT_AVAILABLE +#define U_P2 H_P2 +#define U_P3 H_P3 +#define U_P4 H_P4 +#define U_P5 H_P5 +#define U_PARAMETER H_PARAMETER +#define U_PERMISSION H_PERMISSION +#define U_SUCCESS H_SUCCESS + +/* opcodes */ +#define UV_WRITE_PATE 0xF104 +#define UV_RETURN 0xF11C +#define UV_ESM 0xF110 +#define UV_SHARE_PAGE 0xF130 +#define UV_UNSHARE_PAGE 0xF134 +#define UV_UNSHARE_ALL_PAGES 0xF140 + +#endif /* _ASM_POWERPC_ULTRAVISOR_API_H */ diff --git a/arch/powerpc/include/asm/ultravisor.h b/arch/powerpc/include/asm/ultravisor.h new file mode 100644 index 000000000000..b1bc2e043ed4 --- /dev/null +++ b/arch/powerpc/include/asm/ultravisor.h @@ -0,0 +1,49 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Ultravisor definitions + * + * Copyright 2019, IBM Corporation. + * + */ +#ifndef _ASM_POWERPC_ULTRAVISOR_H +#define _ASM_POWERPC_ULTRAVISOR_H + +#include <asm/asm-prototypes.h> +#include <asm/ultravisor-api.h> +#include <asm/firmware.h> + +int early_init_dt_scan_ultravisor(unsigned long node, const char *uname, + int depth, void *data); + +/* + * In ultravisor enabled systems, PTCR becomes ultravisor privileged only for + * writing and an attempt to write to it will cause a Hypervisor Emulation + * Assistance interrupt. + */ +static inline void set_ptcr_when_no_uv(u64 val) +{ + if (!firmware_has_feature(FW_FEATURE_ULTRAVISOR)) + mtspr(SPRN_PTCR, val); +} + +static inline int uv_register_pate(u64 lpid, u64 dw0, u64 dw1) +{ + return ucall_norets(UV_WRITE_PATE, lpid, dw0, dw1); +} + +static inline int uv_share_page(u64 pfn, u64 npages) +{ + return ucall_norets(UV_SHARE_PAGE, pfn, npages); +} + +static inline int uv_unshare_page(u64 pfn, u64 npages) +{ + return ucall_norets(UV_UNSHARE_PAGE, pfn, npages); +} + +static inline int uv_unshare_all_pages(void) +{ + return ucall_norets(UV_UNSHARE_ALL_PAGES); +} + +#endif /* _ASM_POWERPC_ULTRAVISOR_H */ diff --git a/arch/powerpc/include/asm/xive.h b/arch/powerpc/include/asm/xive.h index e4016985764e..24cdf97376c4 100644 --- a/arch/powerpc/include/asm/xive.h +++ b/arch/powerpc/include/asm/xive.h @@ -46,7 +46,15 @@ struct xive_irq_data { /* Setup/used by frontend */ int target; + /* + * saved_p means that there is a queue entry for this interrupt + * in some CPU's queue (not including guest vcpu queues), even + * if P is not set in the source ESB. + * stale_p means that there is no queue entry for this interrupt + * in some CPU's queue, even if P is set in the source ESB. + */ bool saved_p; + bool stale_p; }; #define XIVE_IRQ_FLAG_STORE_EOI 0x01 #define XIVE_IRQ_FLAG_LSI 0x02 @@ -91,6 +99,7 @@ extern void xive_flush_interrupt(void); /* xmon hook */ extern void xmon_xive_do_dump(int cpu); +extern int xmon_xive_get_irq_config(u32 hw_irq, struct irq_data *d); /* APIs used by KVM */ extern u32 xive_native_default_eq_shift(void); @@ -127,6 +136,7 @@ extern int xive_native_get_queue_state(u32 vp_id, uint32_t prio, u32 *qtoggle, extern int xive_native_set_queue_state(u32 vp_id, uint32_t prio, u32 qtoggle, u32 qindex); extern int xive_native_get_vp_state(u32 vp_id, u64 *out_state); +extern bool xive_native_has_queue_state_support(void); #else diff --git a/arch/powerpc/kernel/.gitignore b/arch/powerpc/kernel/.gitignore index c5f676c3c224..67ebd3003c05 100644 --- a/arch/powerpc/kernel/.gitignore +++ b/arch/powerpc/kernel/.gitignore @@ -1 +1,2 @@ +prom_init_check vmlinux.lds diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index 56dfa7a2a6f2..a7ca8fe62368 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -52,7 +52,7 @@ obj-y := cputable.o ptrace.o syscalls.o \ of_platform.o prom_parse.o obj-$(CONFIG_PPC64) += setup_64.o sys_ppc32.o \ signal_64.o ptrace32.o \ - paca.o nvram_64.o firmware.o + paca.o nvram_64.o firmware.o note.o obj-$(CONFIG_VDSO32) += vdso32/ obj-$(CONFIG_PPC_WATCHDOG) += watchdog.o obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o @@ -78,7 +78,9 @@ obj-$(CONFIG_EEH) += eeh.o eeh_pe.o eeh_dev.o eeh_cache.o \ eeh_driver.o eeh_event.o eeh_sysfs.o obj-$(CONFIG_GENERIC_TBSYNC) += smp-tbsync.o obj-$(CONFIG_CRASH_DUMP) += crash_dump.o -obj-$(CONFIG_FA_DUMP) += fadump.o +ifneq ($(CONFIG_FA_DUMP)$(CONFIG_PRESERVE_FA_DUMP),) +obj-y += fadump.o +endif ifdef CONFIG_PPC32 obj-$(CONFIG_E500) += idle_e500.o endif @@ -155,6 +157,9 @@ endif obj-$(CONFIG_EPAPR_PARAVIRT) += epapr_paravirt.o epapr_hcalls.o obj-$(CONFIG_KVM_GUEST) += kvm.o kvm_emul.o +ifneq ($(CONFIG_PPC_POWERNV)$(CONFIG_PPC_SVM),) +obj-y += ucall.o +endif # Disable GCOV, KCOV & sanitizers in odd or sensitive code GCOV_PROFILE_prom_init.o := n @@ -184,15 +189,13 @@ extra-$(CONFIG_ALTIVEC) += vector.o extra-$(CONFIG_PPC64) += entry_64.o extra-$(CONFIG_PPC_OF_BOOT_TRAMPOLINE) += prom_init.o -ifdef CONFIG_PPC_OF_BOOT_TRAMPOLINE -$(obj)/built-in.a: prom_init_check +extra-$(CONFIG_PPC_OF_BOOT_TRAMPOLINE) += prom_init_check -quiet_cmd_prom_init_check = CALL $< - cmd_prom_init_check = $(CONFIG_SHELL) $< "$(NM)" "$(obj)/prom_init.o" +quiet_cmd_prom_init_check = PROMCHK $@ + cmd_prom_init_check = $(CONFIG_SHELL) $< "$(NM)" $(obj)/prom_init.o; touch $@ -PHONY += prom_init_check -prom_init_check: $(src)/prom_init_check.sh $(obj)/prom_init.o - $(call cmd,prom_init_check) -endif +$(obj)/prom_init_check: $(src)/prom_init_check.sh $(obj)/prom_init.o FORCE + $(call if_changed,prom_init_check) +targets += prom_init_check clean-files := vmlinux.lds diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 4ccb6b3a7fbd..484f54dab247 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -506,6 +506,7 @@ int main(void) OFFSET(KVM_VRMA_SLB_V, kvm, arch.vrma_slb_v); OFFSET(KVM_RADIX, kvm, arch.radix); OFFSET(KVM_FWNMI, kvm, arch.fwnmi_enabled); + OFFSET(KVM_SECURE_GUEST, kvm, arch.secure_guest); OFFSET(VCPU_DSISR, kvm_vcpu, arch.shregs.dsisr); OFFSET(VCPU_DAR, kvm_vcpu, arch.shregs.dar); OFFSET(VCPU_VPA, kvm_vcpu, arch.vpa.pinned_addr); diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index bfe5f4a2886b..e745abc5457a 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -569,7 +569,7 @@ static struct cpu_spec __initdata cpu_specs[] = { #endif /* CONFIG_PPC_BOOK3S_64 */ #ifdef CONFIG_PPC32 -#ifdef CONFIG_PPC_BOOK3S_32 +#ifdef CONFIG_PPC_BOOK3S_601 { /* 601 */ .pvr_mask = 0xffff0000, .pvr_value = 0x00010000, @@ -583,6 +583,8 @@ static struct cpu_spec __initdata cpu_specs[] = { .machine_check = machine_check_generic, .platform = "ppc601", }, +#endif /* CONFIG_PPC_BOOK3S_601 */ +#ifdef CONFIG_PPC_BOOK3S_6xx { /* 603 */ .pvr_mask = 0xffff0000, .pvr_value = 0x00030000, @@ -1212,7 +1214,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .machine_check = machine_check_generic, .platform = "ppc603", }, -#endif /* CONFIG_PPC_BOOK3S_32 */ +#endif /* CONFIG_PPC_BOOK3S_6xx */ #ifdef CONFIG_PPC_8xx { /* 8xx */ .pvr_mask = 0xffff0000, diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c index a0879674a9c8..e486d1d78de2 100644 --- a/arch/powerpc/kernel/dma-iommu.c +++ b/arch/powerpc/kernel/dma-iommu.c @@ -122,18 +122,17 @@ int dma_iommu_dma_supported(struct device *dev, u64 mask) { struct iommu_table *tbl = get_iommu_table_base(dev); - if (!tbl) { - dev_info(dev, "Warning: IOMMU dma not supported: mask 0x%08llx" - ", table unavailable\n", mask); - return 0; - } - if (dev_is_pci(dev) && dma_iommu_bypass_supported(dev, mask)) { dev->archdata.iommu_bypass = true; dev_dbg(dev, "iommu: 64-bit OK, using fixed ops\n"); return 1; } + if (!tbl) { + dev_err(dev, "Warning: IOMMU dma not supported: mask 0x%08llx, table unavailable\n", mask); + return 0; + } + if (tbl->it_offset > (mask >> tbl->it_page_shift)) { dev_info(dev, "Warning: IOMMU offset too big for device mask\n"); dev_info(dev, "mask: 0x%08llx, table offset: 0x%08lx\n", @@ -208,4 +207,6 @@ const struct dma_map_ops dma_iommu_ops = { .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, + .mmap = dma_common_mmap, + .get_sgtable = dma_common_get_sgtable, }; diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index c0e4b73191f3..0a91dee51245 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -150,6 +150,16 @@ static int __init eeh_setup(char *str) } __setup("eeh=", eeh_setup); +void eeh_show_enabled(void) +{ + if (eeh_has_flag(EEH_FORCE_DISABLED)) + pr_info("EEH: Recovery disabled by kernel parameter.\n"); + else if (eeh_has_flag(EEH_ENABLED)) + pr_info("EEH: Capable adapter found: recovery enabled.\n"); + else + pr_info("EEH: No capable adapters found: recovery disabled.\n"); +} + /* * This routine captures assorted PCI configuration space data * for the indicated PCI device, and puts them into a buffer @@ -410,11 +420,9 @@ static int eeh_phb_check_failure(struct eeh_pe *pe) eeh_pe_mark_isolated(phb_pe); eeh_serialize_unlock(flags); - pr_err("EEH: PHB#%x failure detected, location: %s\n", + pr_debug("EEH: PHB#%x failure detected, location: %s\n", phb_pe->phb->global_number, eeh_pe_loc_get(phb_pe)); - dump_stack(); eeh_send_failure_event(phb_pe); - return 1; out: eeh_serialize_unlock(flags); @@ -441,7 +449,7 @@ int eeh_dev_check_failure(struct eeh_dev *edev) unsigned long flags; struct device_node *dn; struct pci_dev *dev; - struct eeh_pe *pe, *parent_pe, *phb_pe; + struct eeh_pe *pe, *parent_pe; int rc = 0; const char *location = NULL; @@ -460,8 +468,7 @@ int eeh_dev_check_failure(struct eeh_dev *edev) /* Access to IO BARs might get this far and still not want checking. */ if (!pe) { eeh_stats.ignored_check++; - pr_debug("EEH: Ignored check for %s\n", - eeh_pci_name(dev)); + eeh_edev_dbg(edev, "Ignored check\n"); return 0; } @@ -501,12 +508,11 @@ int eeh_dev_check_failure(struct eeh_dev *edev) if (dn) location = of_get_property(dn, "ibm,loc-code", NULL); - printk(KERN_ERR "EEH: %d reads ignored for recovering device at " - "location=%s driver=%s pci addr=%s\n", + eeh_edev_err(edev, "%d reads ignored for recovering device at location=%s driver=%s\n", pe->check_count, location ? location : "unknown", - eeh_driver_name(dev), eeh_pci_name(dev)); - printk(KERN_ERR "EEH: Might be infinite loop in %s driver\n", + eeh_driver_name(dev)); + eeh_edev_err(edev, "Might be infinite loop in %s driver\n", eeh_driver_name(dev)); dump_stack(); } @@ -573,13 +579,8 @@ int eeh_dev_check_failure(struct eeh_dev *edev) * a stack trace will help the device-driver authors figure * out what happened. So print that out. */ - phb_pe = eeh_phb_pe_get(pe->phb); - pr_err("EEH: Frozen PHB#%x-PE#%x detected\n", - pe->phb->global_number, pe->addr); - pr_err("EEH: PE location: %s, PHB location: %s\n", - eeh_pe_loc_get(pe), eeh_pe_loc_get(phb_pe)); - dump_stack(); - + pr_debug("EEH: %s: Frozen PHB#%x-PE#%x detected\n", + __func__, pe->phb->global_number, pe->addr); eeh_send_failure_event(pe); return 1; @@ -697,7 +698,7 @@ int eeh_pci_enable(struct eeh_pe *pe, int function) return rc; } -static void *eeh_disable_and_save_dev_state(struct eeh_dev *edev, +static void eeh_disable_and_save_dev_state(struct eeh_dev *edev, void *userdata) { struct pci_dev *pdev = eeh_dev_to_pci_dev(edev); @@ -708,7 +709,7 @@ static void *eeh_disable_and_save_dev_state(struct eeh_dev *edev, * state for the specified device */ if (!pdev || pdev == dev) - return NULL; + return; /* Ensure we have D0 power state */ pci_set_power_state(pdev, PCI_D0); @@ -721,18 +722,16 @@ static void *eeh_disable_and_save_dev_state(struct eeh_dev *edev, * interrupt from the device */ pci_write_config_word(pdev, PCI_COMMAND, PCI_COMMAND_INTX_DISABLE); - - return NULL; } -static void *eeh_restore_dev_state(struct eeh_dev *edev, void *userdata) +static void eeh_restore_dev_state(struct eeh_dev *edev, void *userdata) { struct pci_dn *pdn = eeh_dev_to_pdn(edev); struct pci_dev *pdev = eeh_dev_to_pci_dev(edev); struct pci_dev *dev = userdata; if (!pdev) - return NULL; + return; /* Apply customization from firmware */ if (pdn && eeh_ops->restore_config) @@ -741,8 +740,6 @@ static void *eeh_restore_dev_state(struct eeh_dev *edev, void *userdata) /* The caller should restore state for the specified device */ if (pdev != dev) pci_restore_state(pdev); - - return NULL; } int eeh_restore_vf_config(struct pci_dn *pdn) @@ -868,7 +865,7 @@ int pcibios_set_pcie_reset_state(struct pci_dev *dev, enum pcie_reset_state stat * the indicated device and its children so that the bunch of the * devices could be reset properly. */ -static void *eeh_set_dev_freset(struct eeh_dev *edev, void *flag) +static void eeh_set_dev_freset(struct eeh_dev *edev, void *flag) { struct pci_dev *dev; unsigned int *freset = (unsigned int *)flag; @@ -876,8 +873,6 @@ static void *eeh_set_dev_freset(struct eeh_dev *edev, void *flag) dev = eeh_dev_to_pci_dev(edev); if (dev) *freset |= dev->needs_freset; - - return NULL; } static void eeh_pe_refreeze_passed(struct eeh_pe *root) @@ -1063,23 +1058,6 @@ static struct notifier_block eeh_reboot_nb = { .notifier_call = eeh_reboot_notifier, }; -void eeh_probe_devices(void) -{ - struct pci_controller *hose, *tmp; - struct pci_dn *pdn; - - /* Enable EEH for all adapters */ - list_for_each_entry_safe(hose, tmp, &hose_list, list_node) { - pdn = hose->pci_data; - traverse_pci_dn(pdn, eeh_ops->probe, NULL); - } - if (eeh_enabled()) - pr_info("EEH: PCI Enhanced I/O Error Handling Enabled\n"); - else - pr_info("EEH: No capable adapters found\n"); - -} - /** * eeh_init - EEH initialization * @@ -1120,6 +1098,8 @@ static int eeh_init(void) list_for_each_entry_safe(hose, tmp, &hose_list, list_node) eeh_dev_phb_init_dynamic(hose); + eeh_addr_cache_init(); + /* Initialize EEH event */ return eeh_event_init(); } @@ -1190,15 +1170,14 @@ void eeh_add_device_late(struct pci_dev *dev) struct pci_dn *pdn; struct eeh_dev *edev; - if (!dev || !eeh_enabled()) + if (!dev) return; - pr_debug("EEH: Adding device %s\n", pci_name(dev)); - pdn = pci_get_pdn_by_devfn(dev->bus, dev->devfn); edev = pdn_to_eeh_dev(pdn); + eeh_edev_dbg(edev, "Adding device\n"); if (edev->pdev == dev) { - pr_debug("EEH: Already referenced !\n"); + eeh_edev_dbg(edev, "Device already referenced!\n"); return; } @@ -1246,6 +1225,8 @@ void eeh_add_device_tree_late(struct pci_bus *bus) { struct pci_dev *dev; + if (eeh_has_flag(EEH_FORCE_DISABLED)) + return; list_for_each_entry(dev, &bus->devices, bus_list) { eeh_add_device_late(dev); if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE) { @@ -1299,10 +1280,10 @@ void eeh_remove_device(struct pci_dev *dev) edev = pci_dev_to_eeh_dev(dev); /* Unregister the device with the EEH/PCI address search system */ - pr_debug("EEH: Removing device %s\n", pci_name(dev)); + dev_dbg(&dev->dev, "EEH: Removing device\n"); if (!edev || !edev->pdev || !edev->pe) { - pr_debug("EEH: Not referenced !\n"); + dev_dbg(&dev->dev, "EEH: Device not referenced!\n"); return; } @@ -1890,6 +1871,198 @@ static const struct file_operations eeh_force_recover_fops = { .llseek = no_llseek, .write = eeh_force_recover_write, }; + +static ssize_t eeh_debugfs_dev_usage(struct file *filp, + char __user *user_buf, + size_t count, loff_t *ppos) +{ + static const char usage[] = "input format: <domain>:<bus>:<dev>.<fn>\n"; + + return simple_read_from_buffer(user_buf, count, ppos, + usage, sizeof(usage) - 1); +} + +static ssize_t eeh_dev_check_write(struct file *filp, + const char __user *user_buf, + size_t count, loff_t *ppos) +{ + uint32_t domain, bus, dev, fn; + struct pci_dev *pdev; + struct eeh_dev *edev; + char buf[20]; + int ret; + + memset(buf, 0, sizeof(buf)); + ret = simple_write_to_buffer(buf, sizeof(buf)-1, ppos, user_buf, count); + if (!ret) + return -EFAULT; + + ret = sscanf(buf, "%x:%x:%x.%x", &domain, &bus, &dev, &fn); + if (ret != 4) { + pr_err("%s: expected 4 args, got %d\n", __func__, ret); + return -EINVAL; + } + + pdev = pci_get_domain_bus_and_slot(domain, bus, (dev << 3) | fn); + if (!pdev) + return -ENODEV; + + edev = pci_dev_to_eeh_dev(pdev); + if (!edev) { + pci_err(pdev, "No eeh_dev for this device!\n"); + pci_dev_put(pdev); + return -ENODEV; + } + + ret = eeh_dev_check_failure(edev); + pci_info(pdev, "eeh_dev_check_failure(%04x:%02x:%02x.%01x) = %d\n", + domain, bus, dev, fn, ret); + + pci_dev_put(pdev); + + return count; +} + +static const struct file_operations eeh_dev_check_fops = { + .open = simple_open, + .llseek = no_llseek, + .write = eeh_dev_check_write, + .read = eeh_debugfs_dev_usage, +}; + +static int eeh_debugfs_break_device(struct pci_dev *pdev) +{ + struct resource *bar = NULL; + void __iomem *mapped; + u16 old, bit; + int i, pos; + + /* Do we have an MMIO BAR to disable? */ + for (i = 0; i <= PCI_STD_RESOURCE_END; i++) { + struct resource *r = &pdev->resource[i]; + + if (!r->flags || !r->start) + continue; + if (r->flags & IORESOURCE_IO) + continue; + if (r->flags & IORESOURCE_UNSET) + continue; + + bar = r; + break; + } + + if (!bar) { + pci_err(pdev, "Unable to find Memory BAR to cause EEH with\n"); + return -ENXIO; + } + + pci_err(pdev, "Going to break: %pR\n", bar); + + if (pdev->is_virtfn) { +#ifndef CONFIG_IOV + return -ENXIO; +#else + /* + * VFs don't have a per-function COMMAND register, so the best + * we can do is clear the Memory Space Enable bit in the PF's + * SRIOV control reg. + * + * Unfortunately, this requires that we have a PF (i.e doesn't + * work for a passed-through VF) and it has the potential side + * effect of also causing an EEH on every other VF under the + * PF. Oh well. + */ + pdev = pdev->physfn; + if (!pdev) + return -ENXIO; /* passed through VFs have no PF */ + + pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_SRIOV); + pos += PCI_SRIOV_CTRL; + bit = PCI_SRIOV_CTRL_MSE; +#endif /* !CONFIG_IOV */ + } else { + bit = PCI_COMMAND_MEMORY; + pos = PCI_COMMAND; + } + + /* + * Process here is: + * + * 1. Disable Memory space. + * + * 2. Perform an MMIO to the device. This should result in an error + * (CA / UR) being raised by the device which results in an EEH + * PE freeze. Using the in_8() accessor skips the eeh detection hook + * so the freeze hook so the EEH Detection machinery won't be + * triggered here. This is to match the usual behaviour of EEH + * where the HW will asyncronously freeze a PE and it's up to + * the kernel to notice and deal with it. + * + * 3. Turn Memory space back on. This is more important for VFs + * since recovery will probably fail if we don't. For normal + * the COMMAND register is reset as a part of re-initialising + * the device. + * + * Breaking stuff is the point so who cares if it's racy ;) + */ + pci_read_config_word(pdev, pos, &old); + + mapped = ioremap(bar->start, PAGE_SIZE); + if (!mapped) { + pci_err(pdev, "Unable to map MMIO BAR %pR\n", bar); + return -ENXIO; + } + + pci_write_config_word(pdev, pos, old & ~bit); + in_8(mapped); + pci_write_config_word(pdev, pos, old); + + iounmap(mapped); + + return 0; +} + +static ssize_t eeh_dev_break_write(struct file *filp, + const char __user *user_buf, + size_t count, loff_t *ppos) +{ + uint32_t domain, bus, dev, fn; + struct pci_dev *pdev; + char buf[20]; + int ret; + + memset(buf, 0, sizeof(buf)); + ret = simple_write_to_buffer(buf, sizeof(buf)-1, ppos, user_buf, count); + if (!ret) + return -EFAULT; + + ret = sscanf(buf, "%x:%x:%x.%x", &domain, &bus, &dev, &fn); + if (ret != 4) { + pr_err("%s: expected 4 args, got %d\n", __func__, ret); + return -EINVAL; + } + + pdev = pci_get_domain_bus_and_slot(domain, bus, (dev << 3) | fn); + if (!pdev) + return -ENODEV; + + ret = eeh_debugfs_break_device(pdev); + pci_dev_put(pdev); + + if (ret < 0) + return ret; + + return count; +} + +static const struct file_operations eeh_dev_break_fops = { + .open = simple_open, + .llseek = no_llseek, + .write = eeh_dev_break_write, + .read = eeh_debugfs_dev_usage, +}; + #endif static int __init eeh_init_proc(void) @@ -1905,6 +2078,12 @@ static int __init eeh_init_proc(void) debugfs_create_bool("eeh_disable_recovery", 0600, powerpc_debugfs_root, &eeh_debugfs_no_recover); + debugfs_create_file_unsafe("eeh_dev_check", 0600, + powerpc_debugfs_root, NULL, + &eeh_dev_check_fops); + debugfs_create_file_unsafe("eeh_dev_break", 0600, + powerpc_debugfs_root, NULL, + &eeh_dev_break_fops); debugfs_create_file_unsafe("eeh_force_recover", 0600, powerpc_debugfs_root, NULL, &eeh_force_recover_fops); diff --git a/arch/powerpc/kernel/eeh_cache.c b/arch/powerpc/kernel/eeh_cache.c index 05ffd32b3416..cf11277ebd02 100644 --- a/arch/powerpc/kernel/eeh_cache.c +++ b/arch/powerpc/kernel/eeh_cache.c @@ -148,8 +148,8 @@ eeh_addr_cache_insert(struct pci_dev *dev, resource_size_t alo, piar->pcidev = dev; piar->flags = flags; - pr_debug("PIAR: insert range=[%pap:%pap] dev=%s\n", - &alo, &ahi, pci_name(dev)); + eeh_edev_dbg(piar->edev, "PIAR: insert range=[%pap:%pap]\n", + &alo, &ahi); rb_link_node(&piar->rb_node, parent, p); rb_insert_color(&piar->rb_node, &pci_io_addr_cache_root.rb_root); @@ -229,8 +229,8 @@ restart: piar = rb_entry(n, struct pci_io_addr_range, rb_node); if (piar->pcidev == dev) { - pr_debug("PIAR: remove range=[%pap:%pap] dev=%s\n", - &piar->addr_lo, &piar->addr_hi, pci_name(dev)); + eeh_edev_dbg(piar->edev, "PIAR: remove range=[%pap:%pap]\n", + &piar->addr_lo, &piar->addr_hi); rb_erase(n, &pci_io_addr_cache_root.rb_root); kfree(piar); goto restart; @@ -258,37 +258,14 @@ void eeh_addr_cache_rmv_dev(struct pci_dev *dev) } /** - * eeh_addr_cache_build - Build a cache of I/O addresses + * eeh_addr_cache_init - Initialize a cache of I/O addresses * - * Build a cache of pci i/o addresses. This cache will be used to + * Initialize a cache of pci i/o addresses. This cache will be used to * find the pci device that corresponds to a given address. - * This routine scans all pci busses to build the cache. - * Must be run late in boot process, after the pci controllers - * have been scanned for devices (after all device resources are known). */ -void eeh_addr_cache_build(void) +void eeh_addr_cache_init(void) { - struct pci_dn *pdn; - struct eeh_dev *edev; - struct pci_dev *dev = NULL; - spin_lock_init(&pci_io_addr_cache_root.piar_lock); - - for_each_pci_dev(dev) { - pdn = pci_get_pdn_by_devfn(dev->bus, dev->devfn); - if (!pdn) - continue; - - edev = pdn_to_eeh_dev(pdn); - if (!edev) - continue; - - dev->dev.archdata.edev = edev; - edev->pdev = dev; - - eeh_addr_cache_insert_dev(dev); - eeh_sysfs_add_device(dev); - } } static int eeh_addr_cache_show(struct seq_file *s, void *v) diff --git a/arch/powerpc/kernel/eeh_dev.c b/arch/powerpc/kernel/eeh_dev.c index c4317c452d98..7370185c7a05 100644 --- a/arch/powerpc/kernel/eeh_dev.c +++ b/arch/powerpc/kernel/eeh_dev.c @@ -47,6 +47,8 @@ struct eeh_dev *eeh_dev_init(struct pci_dn *pdn) /* Associate EEH device with OF node */ pdn->edev = edev; edev->pdn = pdn; + edev->bdfn = (pdn->busno << 8) | pdn->devfn; + edev->controller = pdn->phb; return edev; } diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index 89623962c727..d9279d0ee9f5 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -27,6 +27,7 @@ #include <linux/irq.h> #include <linux/module.h> #include <linux/pci.h> +#include <linux/pci_hotplug.h> #include <asm/eeh.h> #include <asm/eeh_event.h> #include <asm/ppc-pci.h> @@ -81,23 +82,6 @@ static const char *pci_ers_result_name(enum pci_ers_result result) } }; -static __printf(2, 3) void eeh_edev_info(const struct eeh_dev *edev, - const char *fmt, ...) -{ - struct va_format vaf; - va_list args; - - va_start(args, fmt); - - vaf.fmt = fmt; - vaf.va = &args; - - printk(KERN_INFO "EEH: PE#%x (PCI %s): %pV\n", edev->pe_config_addr, - edev->pdev ? dev_name(&edev->pdev->dev) : "none", &vaf); - - va_end(args); -} - static enum pci_ers_result pci_ers_merge_result(enum pci_ers_result old, enum pci_ers_result new) { @@ -113,8 +97,16 @@ static bool eeh_dev_removed(struct eeh_dev *edev) static bool eeh_edev_actionable(struct eeh_dev *edev) { - return (edev->pdev && !eeh_dev_removed(edev) && - !eeh_pe_passed(edev->pe)); + if (!edev->pdev) + return false; + if (edev->pdev->error_state == pci_channel_io_perm_failure) + return false; + if (eeh_dev_removed(edev)) + return false; + if (eeh_pe_passed(edev->pe)) + return false; + + return true; } /** @@ -214,12 +206,12 @@ static void eeh_enable_irq(struct eeh_dev *edev) } } -static void *eeh_dev_save_state(struct eeh_dev *edev, void *userdata) +static void eeh_dev_save_state(struct eeh_dev *edev, void *userdata) { struct pci_dev *pdev; if (!edev) - return NULL; + return; /* * We cannot access the config space on some adapters. @@ -229,14 +221,13 @@ static void *eeh_dev_save_state(struct eeh_dev *edev, void *userdata) * device is created. */ if (edev->pe && (edev->pe->state & EEH_PE_CFG_RESTRICTED)) - return NULL; + return; pdev = eeh_dev_to_pci_dev(edev); if (!pdev) - return NULL; + return; pci_save_state(pdev); - return NULL; } static void eeh_set_channel_state(struct eeh_pe *root, enum pci_channel_state s) @@ -274,20 +265,27 @@ static void eeh_set_irq_state(struct eeh_pe *root, bool enable) } typedef enum pci_ers_result (*eeh_report_fn)(struct eeh_dev *, + struct pci_dev *, struct pci_driver *); static void eeh_pe_report_edev(struct eeh_dev *edev, eeh_report_fn fn, enum pci_ers_result *result) { + struct pci_dev *pdev; struct pci_driver *driver; enum pci_ers_result new_result; - if (!edev->pdev) { + pci_lock_rescan_remove(); + pdev = edev->pdev; + if (pdev) + get_device(&pdev->dev); + pci_unlock_rescan_remove(); + if (!pdev) { eeh_edev_info(edev, "no device"); return; } - device_lock(&edev->pdev->dev); + device_lock(&pdev->dev); if (eeh_edev_actionable(edev)) { - driver = eeh_pcid_get(edev->pdev); + driver = eeh_pcid_get(pdev); if (!driver) eeh_edev_info(edev, "no driver"); @@ -296,7 +294,7 @@ static void eeh_pe_report_edev(struct eeh_dev *edev, eeh_report_fn fn, else if (edev->mode & EEH_DEV_NO_HANDLER) eeh_edev_info(edev, "driver bound too late"); else { - new_result = fn(edev, driver); + new_result = fn(edev, pdev, driver); eeh_edev_info(edev, "%s driver reports: '%s'", driver->name, pci_ers_result_name(new_result)); @@ -305,12 +303,15 @@ static void eeh_pe_report_edev(struct eeh_dev *edev, eeh_report_fn fn, new_result); } if (driver) - eeh_pcid_put(edev->pdev); + eeh_pcid_put(pdev); } else { - eeh_edev_info(edev, "not actionable (%d,%d,%d)", !!edev->pdev, + eeh_edev_info(edev, "not actionable (%d,%d,%d)", !!pdev, !eeh_dev_removed(edev), !eeh_pe_passed(edev->pe)); } - device_unlock(&edev->pdev->dev); + device_unlock(&pdev->dev); + if (edev->pdev != pdev) + eeh_edev_warn(edev, "Device changed during processing!\n"); + put_device(&pdev->dev); } static void eeh_pe_report(const char *name, struct eeh_pe *root, @@ -337,20 +338,20 @@ static void eeh_pe_report(const char *name, struct eeh_pe *root, * Report an EEH error to each device driver. */ static enum pci_ers_result eeh_report_error(struct eeh_dev *edev, + struct pci_dev *pdev, struct pci_driver *driver) { enum pci_ers_result rc; - struct pci_dev *dev = edev->pdev; if (!driver->err_handler->error_detected) return PCI_ERS_RESULT_NONE; eeh_edev_info(edev, "Invoking %s->error_detected(IO frozen)", driver->name); - rc = driver->err_handler->error_detected(dev, pci_channel_io_frozen); + rc = driver->err_handler->error_detected(pdev, pci_channel_io_frozen); edev->in_error = true; - pci_uevent_ers(dev, PCI_ERS_RESULT_NONE); + pci_uevent_ers(pdev, PCI_ERS_RESULT_NONE); return rc; } @@ -363,12 +364,13 @@ static enum pci_ers_result eeh_report_error(struct eeh_dev *edev, * are now enabled. */ static enum pci_ers_result eeh_report_mmio_enabled(struct eeh_dev *edev, + struct pci_dev *pdev, struct pci_driver *driver) { if (!driver->err_handler->mmio_enabled) return PCI_ERS_RESULT_NONE; eeh_edev_info(edev, "Invoking %s->mmio_enabled()", driver->name); - return driver->err_handler->mmio_enabled(edev->pdev); + return driver->err_handler->mmio_enabled(pdev); } /** @@ -382,20 +384,21 @@ static enum pci_ers_result eeh_report_mmio_enabled(struct eeh_dev *edev, * driver can work again while the device is recovered. */ static enum pci_ers_result eeh_report_reset(struct eeh_dev *edev, + struct pci_dev *pdev, struct pci_driver *driver) { if (!driver->err_handler->slot_reset || !edev->in_error) return PCI_ERS_RESULT_NONE; eeh_edev_info(edev, "Invoking %s->slot_reset()", driver->name); - return driver->err_handler->slot_reset(edev->pdev); + return driver->err_handler->slot_reset(pdev); } -static void *eeh_dev_restore_state(struct eeh_dev *edev, void *userdata) +static void eeh_dev_restore_state(struct eeh_dev *edev, void *userdata) { struct pci_dev *pdev; if (!edev) - return NULL; + return; /* * The content in the config space isn't saved because @@ -407,15 +410,14 @@ static void *eeh_dev_restore_state(struct eeh_dev *edev, void *userdata) if (list_is_last(&edev->entry, &edev->pe->edevs)) eeh_pe_restore_bars(edev->pe); - return NULL; + return; } pdev = eeh_dev_to_pci_dev(edev); if (!pdev) - return NULL; + return; pci_restore_state(pdev); - return NULL; } /** @@ -428,13 +430,14 @@ static void *eeh_dev_restore_state(struct eeh_dev *edev, void *userdata) * to make the recovered device work again. */ static enum pci_ers_result eeh_report_resume(struct eeh_dev *edev, + struct pci_dev *pdev, struct pci_driver *driver) { if (!driver->err_handler->resume || !edev->in_error) return PCI_ERS_RESULT_NONE; eeh_edev_info(edev, "Invoking %s->resume()", driver->name); - driver->err_handler->resume(edev->pdev); + driver->err_handler->resume(pdev); pci_uevent_ers(edev->pdev, PCI_ERS_RESULT_RECOVERED); #ifdef CONFIG_PCI_IOV @@ -453,6 +456,7 @@ static enum pci_ers_result eeh_report_resume(struct eeh_dev *edev, * dead, and that no further recovery attempts will be made on it. */ static enum pci_ers_result eeh_report_failure(struct eeh_dev *edev, + struct pci_dev *pdev, struct pci_driver *driver) { enum pci_ers_result rc; @@ -462,10 +466,10 @@ static enum pci_ers_result eeh_report_failure(struct eeh_dev *edev, eeh_edev_info(edev, "Invoking %s->error_detected(permanent failure)", driver->name); - rc = driver->err_handler->error_detected(edev->pdev, + rc = driver->err_handler->error_detected(pdev, pci_channel_io_perm_failure); - pci_uevent_ers(edev->pdev, PCI_ERS_RESULT_DISCONNECT); + pci_uevent_ers(pdev, PCI_ERS_RESULT_DISCONNECT); return rc; } @@ -473,12 +477,9 @@ static void *eeh_add_virt_device(struct eeh_dev *edev) { struct pci_driver *driver; struct pci_dev *dev = eeh_dev_to_pci_dev(edev); - struct pci_dn *pdn = eeh_dev_to_pdn(edev); if (!(edev->physfn)) { - pr_warn("%s: EEH dev %04x:%02x:%02x.%01x not for VF\n", - __func__, pdn->phb->global_number, pdn->busno, - PCI_SLOT(pdn->devfn), PCI_FUNC(pdn->devfn)); + eeh_edev_warn(edev, "Not for VF\n"); return NULL; } @@ -492,12 +493,12 @@ static void *eeh_add_virt_device(struct eeh_dev *edev) } #ifdef CONFIG_PCI_IOV - pci_iov_add_virtfn(edev->physfn, pdn->vf_index); + pci_iov_add_virtfn(edev->physfn, eeh_dev_to_pdn(edev)->vf_index); #endif return NULL; } -static void *eeh_rmv_device(struct eeh_dev *edev, void *userdata) +static void eeh_rmv_device(struct eeh_dev *edev, void *userdata) { struct pci_driver *driver; struct pci_dev *dev = eeh_dev_to_pci_dev(edev); @@ -512,7 +513,7 @@ static void *eeh_rmv_device(struct eeh_dev *edev, void *userdata) */ if (!eeh_edev_actionable(edev) || (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE)) - return NULL; + return; if (rmv_data) { driver = eeh_pcid_get(dev); @@ -521,7 +522,7 @@ static void *eeh_rmv_device(struct eeh_dev *edev, void *userdata) driver->err_handler->error_detected && driver->err_handler->slot_reset) { eeh_pcid_put(dev); - return NULL; + return; } eeh_pcid_put(dev); } @@ -554,8 +555,6 @@ static void *eeh_rmv_device(struct eeh_dev *edev, void *userdata) pci_stop_and_remove_bus_device(dev); pci_unlock_rescan_remove(); } - - return NULL; } static void *eeh_pe_detach_dev(struct eeh_pe *pe, void *userdata) @@ -744,6 +743,99 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus, */ #define MAX_WAIT_FOR_RECOVERY 300 + +/* Walks the PE tree after processing an event to remove any stale PEs. + * + * NB: This needs to be recursive to ensure the leaf PEs get removed + * before their parents do. Although this is possible to do recursively + * we don't since this is easier to read and we need to garantee + * the leaf nodes will be handled first. + */ +static void eeh_pe_cleanup(struct eeh_pe *pe) +{ + struct eeh_pe *child_pe, *tmp; + + list_for_each_entry_safe(child_pe, tmp, &pe->child_list, child) + eeh_pe_cleanup(child_pe); + + if (pe->state & EEH_PE_KEEP) + return; + + if (!(pe->state & EEH_PE_INVALID)) + return; + + if (list_empty(&pe->edevs) && list_empty(&pe->child_list)) { + list_del(&pe->child); + kfree(pe); + } +} + +/** + * eeh_check_slot_presence - Check if a device is still present in a slot + * @pdev: pci_dev to check + * + * This function may return a false positive if we can't determine the slot's + * presence state. This might happen for for PCIe slots if the PE containing + * the upstream bridge is also frozen, or the bridge is part of the same PE + * as the device. + * + * This shouldn't happen often, but you might see it if you hotplug a PCIe + * switch. + */ +static bool eeh_slot_presence_check(struct pci_dev *pdev) +{ + const struct hotplug_slot_ops *ops; + struct pci_slot *slot; + u8 state; + int rc; + + if (!pdev) + return false; + + if (pdev->error_state == pci_channel_io_perm_failure) + return false; + + slot = pdev->slot; + if (!slot || !slot->hotplug) + return true; + + ops = slot->hotplug->ops; + if (!ops || !ops->get_adapter_status) + return true; + + /* set the attention indicator while we've got the slot ops */ + if (ops->set_attention_status) + ops->set_attention_status(slot->hotplug, 1); + + rc = ops->get_adapter_status(slot->hotplug, &state); + if (rc) + return true; + + return !!state; +} + +static void eeh_clear_slot_attention(struct pci_dev *pdev) +{ + const struct hotplug_slot_ops *ops; + struct pci_slot *slot; + + if (!pdev) + return; + + if (pdev->error_state == pci_channel_io_perm_failure) + return; + + slot = pdev->slot; + if (!slot || !slot->hotplug) + return; + + ops = slot->hotplug->ops; + if (!ops || !ops->set_attention_status) + return; + + ops->set_attention_status(slot->hotplug, 0); +} + /** * eeh_handle_normal_event - Handle EEH events on a specific PE * @pe: EEH PE - which should not be used after we return, as it may @@ -774,6 +866,7 @@ void eeh_handle_normal_event(struct eeh_pe *pe) enum pci_ers_result result = PCI_ERS_RESULT_NONE; struct eeh_rmv_data rmv_data = {LIST_HEAD_INIT(rmv_data.removed_vf_list), 0}; + int devices = 0; bus = eeh_pe_bus_get(pe); if (!bus) { @@ -782,7 +875,59 @@ void eeh_handle_normal_event(struct eeh_pe *pe) return; } - eeh_pe_state_mark(pe, EEH_PE_RECOVERING); + /* + * When devices are hot-removed we might get an EEH due to + * a driver attempting to touch the MMIO space of a removed + * device. In this case we don't have a device to recover + * so suppress the event if we can't find any present devices. + * + * The hotplug driver should take care of tearing down the + * device itself. + */ + eeh_for_each_pe(pe, tmp_pe) + eeh_pe_for_each_dev(tmp_pe, edev, tmp) + if (eeh_slot_presence_check(edev->pdev)) + devices++; + + if (!devices) { + pr_debug("EEH: Frozen PHB#%x-PE#%x is empty!\n", + pe->phb->global_number, pe->addr); + goto out; /* nothing to recover */ + } + + /* Log the event */ + if (pe->type & EEH_PE_PHB) { + pr_err("EEH: PHB#%x failure detected, location: %s\n", + pe->phb->global_number, eeh_pe_loc_get(pe)); + } else { + struct eeh_pe *phb_pe = eeh_phb_pe_get(pe->phb); + + pr_err("EEH: Frozen PHB#%x-PE#%x detected\n", + pe->phb->global_number, pe->addr); + pr_err("EEH: PE location: %s, PHB location: %s\n", + eeh_pe_loc_get(pe), eeh_pe_loc_get(phb_pe)); + } + +#ifdef CONFIG_STACKTRACE + /* + * Print the saved stack trace now that we've verified there's + * something to recover. + */ + if (pe->trace_entries) { + void **ptrs = (void **) pe->stack_trace; + int i; + + pr_err("EEH: Frozen PHB#%x-PE#%x detected\n", + pe->phb->global_number, pe->addr); + + /* FIXME: Use the same format as dump_stack() */ + pr_err("EEH: Call Trace:\n"); + for (i = 0; i < pe->trace_entries; i++) + pr_err("EEH: [%pK] %pS\n", ptrs[i], ptrs[i]); + + pe->trace_entries = 0; + } +#endif /* CONFIG_STACKTRACE */ eeh_pe_update_time_stamp(pe); pe->freeze_count++; @@ -793,6 +938,10 @@ void eeh_handle_normal_event(struct eeh_pe *pe) result = PCI_ERS_RESULT_DISCONNECT; } + eeh_for_each_pe(pe, tmp_pe) + eeh_pe_for_each_dev(tmp_pe, edev, tmp) + edev->mode &= ~EEH_DEV_NO_HANDLER; + /* Walk the various device drivers attached to this slot through * a reset sequence, giving each an opportunity to do what it needs * to accomplish the reset. Each child gets a report of the @@ -969,6 +1118,19 @@ void eeh_handle_normal_event(struct eeh_pe *pe) return; } } + +out: + /* + * Clean up any PEs without devices. While marked as EEH_PE_RECOVERYING + * we don't want to modify the PE tree structure so we do it here. + */ + eeh_pe_cleanup(pe); + + /* clear the slot attention LED for all recovered devices */ + eeh_for_each_pe(pe, tmp_pe) + eeh_pe_for_each_dev(tmp_pe, edev, tmp) + eeh_clear_slot_attention(edev->pdev); + eeh_pe_state_clear(pe, EEH_PE_RECOVERING, true); } @@ -981,7 +1143,8 @@ void eeh_handle_normal_event(struct eeh_pe *pe) */ void eeh_handle_special_event(void) { - struct eeh_pe *pe, *phb_pe; + struct eeh_pe *pe, *phb_pe, *tmp_pe; + struct eeh_dev *edev, *tmp_edev; struct pci_bus *bus; struct pci_controller *hose; unsigned long flags; @@ -1040,6 +1203,7 @@ void eeh_handle_special_event(void) */ if (rc == EEH_NEXT_ERR_FROZEN_PE || rc == EEH_NEXT_ERR_FENCED_PHB) { + eeh_pe_state_mark(pe, EEH_PE_RECOVERING); eeh_handle_normal_event(pe); } else { pci_lock_rescan_remove(); @@ -1050,6 +1214,10 @@ void eeh_handle_special_event(void) (phb_pe->state & EEH_PE_RECOVERING)) continue; + eeh_for_each_pe(pe, tmp_pe) + eeh_pe_for_each_dev(tmp_pe, edev, tmp_edev) + edev->mode &= ~EEH_DEV_NO_HANDLER; + /* Notify all devices to be down */ eeh_pe_state_clear(pe, EEH_PE_PRI_BUS, true); eeh_set_channel_state(pe, pci_channel_io_perm_failure); diff --git a/arch/powerpc/kernel/eeh_event.c b/arch/powerpc/kernel/eeh_event.c index 64cfbe41174b..a7a8dc182efb 100644 --- a/arch/powerpc/kernel/eeh_event.c +++ b/arch/powerpc/kernel/eeh_event.c @@ -40,7 +40,6 @@ static int eeh_event_handler(void * dummy) { unsigned long flags; struct eeh_event *event; - struct eeh_pe *pe; while (!kthread_should_stop()) { if (wait_for_completion_interruptible(&eeh_eventlist_event)) @@ -59,19 +58,10 @@ static int eeh_event_handler(void * dummy) continue; /* We might have event without binding PE */ - pe = event->pe; - if (pe) { - if (pe->type & EEH_PE_PHB) - pr_info("EEH: Detected error on PHB#%x\n", - pe->phb->global_number); - else - pr_info("EEH: Detected PCI bus error on " - "PHB#%x-PE#%x\n", - pe->phb->global_number, pe->addr); - eeh_handle_normal_event(pe); - } else { + if (event->pe) + eeh_handle_normal_event(event->pe); + else eeh_handle_special_event(); - } kfree(event); } @@ -121,6 +111,24 @@ int __eeh_send_failure_event(struct eeh_pe *pe) } event->pe = pe; + /* + * Mark the PE as recovering before inserting it in the queue. + * This prevents the PE from being free()ed by a hotplug driver + * while the PE is sitting in the event queue. + */ + if (pe) { +#ifdef CONFIG_STACKTRACE + /* + * Save the current stack trace so we can dump it from the + * event handler thread. + */ + pe->trace_entries = stack_trace_save(pe->stack_trace, + ARRAY_SIZE(pe->stack_trace), 0); +#endif /* CONFIG_STACKTRACE */ + + eeh_pe_state_mark(pe, EEH_PE_RECOVERING); + } + /* We may or may not be called in an interrupt context */ spin_lock_irqsave(&eeh_eventlist_lock, flags); list_add(&event->list, &eeh_eventlist); diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c index 854cef7b18f4..177852e39a25 100644 --- a/arch/powerpc/kernel/eeh_pe.c +++ b/arch/powerpc/kernel/eeh_pe.c @@ -231,29 +231,22 @@ void *eeh_pe_traverse(struct eeh_pe *root, * The function is used to traverse the devices of the specified * PE and its child PEs. */ -void *eeh_pe_dev_traverse(struct eeh_pe *root, +void eeh_pe_dev_traverse(struct eeh_pe *root, eeh_edev_traverse_func fn, void *flag) { struct eeh_pe *pe; struct eeh_dev *edev, *tmp; - void *ret; if (!root) { pr_warn("%s: Invalid PE %p\n", __func__, root); - return NULL; + return; } /* Traverse root PE */ - eeh_for_each_pe(root, pe) { - eeh_pe_for_each_dev(pe, edev, tmp) { - ret = fn(edev, flag); - if (ret) - return ret; - } - } - - return NULL; + eeh_for_each_pe(root, pe) + eeh_pe_for_each_dev(pe, edev, tmp) + fn(edev, flag); } /** @@ -379,8 +372,7 @@ int eeh_add_to_parent_pe(struct eeh_dev *edev) /* Check if the PE number is valid */ if (!eeh_has_flag(EEH_VALID_PE_ZERO) && !edev->pe_config_addr) { - pr_err("%s: Invalid PE#0 for edev 0x%x on PHB#%x\n", - __func__, config_addr, pdn->phb->global_number); + eeh_edev_err(edev, "PE#0 is invalid for this PHB!\n"); return -EINVAL; } @@ -391,42 +383,34 @@ int eeh_add_to_parent_pe(struct eeh_dev *edev) * components. */ pe = eeh_pe_get(pdn->phb, edev->pe_config_addr, config_addr); - if (pe && !(pe->type & EEH_PE_INVALID)) { - /* Mark the PE as type of PCI bus */ - pe->type = EEH_PE_BUS; - edev->pe = pe; - - /* Put the edev to PE */ - list_add_tail(&edev->entry, &pe->edevs); - pr_debug("EEH: Add %04x:%02x:%02x.%01x to Bus PE#%x\n", - pdn->phb->global_number, - pdn->busno, - PCI_SLOT(pdn->devfn), - PCI_FUNC(pdn->devfn), - pe->addr); - return 0; - } else if (pe && (pe->type & EEH_PE_INVALID)) { - list_add_tail(&edev->entry, &pe->edevs); - edev->pe = pe; - /* - * We're running to here because of PCI hotplug caused by - * EEH recovery. We need clear EEH_PE_INVALID until the top. - */ - parent = pe; - while (parent) { - if (!(parent->type & EEH_PE_INVALID)) - break; - parent->type &= ~EEH_PE_INVALID; - parent = parent->parent; - } + if (pe) { + if (pe->type & EEH_PE_INVALID) { + list_add_tail(&edev->entry, &pe->edevs); + edev->pe = pe; + /* + * We're running to here because of PCI hotplug caused by + * EEH recovery. We need clear EEH_PE_INVALID until the top. + */ + parent = pe; + while (parent) { + if (!(parent->type & EEH_PE_INVALID)) + break; + parent->type &= ~EEH_PE_INVALID; + parent = parent->parent; + } + + eeh_edev_dbg(edev, + "Added to device PE (parent: PE#%x)\n", + pe->parent->addr); + } else { + /* Mark the PE as type of PCI bus */ + pe->type = EEH_PE_BUS; + edev->pe = pe; - pr_debug("EEH: Add %04x:%02x:%02x.%01x to Device " - "PE#%x, Parent PE#%x\n", - pdn->phb->global_number, - pdn->busno, - PCI_SLOT(pdn->devfn), - PCI_FUNC(pdn->devfn), - pe->addr, pe->parent->addr); + /* Put the edev to PE */ + list_add_tail(&edev->entry, &pe->edevs); + eeh_edev_dbg(edev, "Added to bus PE\n"); + } return 0; } @@ -468,13 +452,8 @@ int eeh_add_to_parent_pe(struct eeh_dev *edev) list_add_tail(&pe->child, &parent->child_list); list_add_tail(&edev->entry, &pe->edevs); edev->pe = pe; - pr_debug("EEH: Add %04x:%02x:%02x.%01x to " - "Device PE#%x, Parent PE#%x\n", - pdn->phb->global_number, - pdn->busno, - PCI_SLOT(pdn->devfn), - PCI_FUNC(pdn->devfn), - pe->addr, pe->parent->addr); + eeh_edev_dbg(edev, "Added to device PE (parent: PE#%x)\n", + pe->parent->addr); return 0; } @@ -491,16 +470,12 @@ int eeh_add_to_parent_pe(struct eeh_dev *edev) int eeh_rmv_from_parent_pe(struct eeh_dev *edev) { struct eeh_pe *pe, *parent, *child; + bool keep, recover; int cnt; - struct pci_dn *pdn = eeh_dev_to_pdn(edev); pe = eeh_dev_to_pe(edev); if (!pe) { - pr_debug("%s: No PE found for device %04x:%02x:%02x.%01x\n", - __func__, pdn->phb->global_number, - pdn->busno, - PCI_SLOT(pdn->devfn), - PCI_FUNC(pdn->devfn)); + eeh_edev_dbg(edev, "No PE found for device.\n"); return -EEXIST; } @@ -516,10 +491,21 @@ int eeh_rmv_from_parent_pe(struct eeh_dev *edev) */ while (1) { parent = pe->parent; + + /* PHB PEs should never be removed */ if (pe->type & EEH_PE_PHB) break; - if (!(pe->state & EEH_PE_KEEP)) { + /* + * XXX: KEEP is set while resetting a PE. I don't think it's + * ever set without RECOVERING also being set. I could + * be wrong though so catch that with a WARN. + */ + keep = !!(pe->state & EEH_PE_KEEP); + recover = !!(pe->state & EEH_PE_RECOVERING); + WARN_ON(keep && !recover); + + if (!keep && !recover) { if (list_empty(&pe->edevs) && list_empty(&pe->child_list)) { list_del(&pe->child); @@ -528,6 +514,15 @@ int eeh_rmv_from_parent_pe(struct eeh_dev *edev) break; } } else { + /* + * Mark the PE as invalid. At the end of the recovery + * process any invalid PEs will be garbage collected. + * + * We need to delay the free()ing of them since we can + * remove edev's while traversing the PE tree which + * might trigger the removal of a PE and we can't + * deal with that (yet). + */ if (list_empty(&pe->edevs)) { cnt = 0; list_for_each_entry(child, &pe->child_list, child) { @@ -623,13 +618,11 @@ void eeh_pe_mark_isolated(struct eeh_pe *root) } EXPORT_SYMBOL_GPL(eeh_pe_mark_isolated); -static void *__eeh_pe_dev_mode_mark(struct eeh_dev *edev, void *flag) +static void __eeh_pe_dev_mode_mark(struct eeh_dev *edev, void *flag) { int mode = *((int *)flag); edev->mode |= mode; - - return NULL; } /** @@ -717,17 +710,13 @@ static void eeh_bridge_check_link(struct eeh_dev *edev) if (!(edev->mode & (EEH_DEV_ROOT_PORT | EEH_DEV_DS_PORT))) return; - pr_debug("%s: Check PCIe link for %04x:%02x:%02x.%01x ...\n", - __func__, pdn->phb->global_number, - pdn->busno, - PCI_SLOT(pdn->devfn), - PCI_FUNC(pdn->devfn)); + eeh_edev_dbg(edev, "Checking PCIe link...\n"); /* Check slot status */ cap = edev->pcie_cap; eeh_ops->read_config(pdn, cap + PCI_EXP_SLTSTA, 2, &val); if (!(val & PCI_EXP_SLTSTA_PDS)) { - pr_debug(" No card in the slot (0x%04x) !\n", val); + eeh_edev_dbg(edev, "No card in the slot (0x%04x) !\n", val); return; } @@ -736,7 +725,7 @@ static void eeh_bridge_check_link(struct eeh_dev *edev) if (val & PCI_EXP_SLTCAP_PCP) { eeh_ops->read_config(pdn, cap + PCI_EXP_SLTCTL, 2, &val); if (val & PCI_EXP_SLTCTL_PCC) { - pr_debug(" In power-off state, power it on ...\n"); + eeh_edev_dbg(edev, "In power-off state, power it on ...\n"); val &= ~(PCI_EXP_SLTCTL_PCC | PCI_EXP_SLTCTL_PIC); val |= (0x0100 & PCI_EXP_SLTCTL_PIC); eeh_ops->write_config(pdn, cap + PCI_EXP_SLTCTL, 2, val); @@ -752,7 +741,7 @@ static void eeh_bridge_check_link(struct eeh_dev *edev) /* Check link */ eeh_ops->read_config(pdn, cap + PCI_EXP_LNKCAP, 4, &val); if (!(val & PCI_EXP_LNKCAP_DLLLARC)) { - pr_debug(" No link reporting capability (0x%08x) \n", val); + eeh_edev_dbg(edev, "No link reporting capability (0x%08x) \n", val); msleep(1000); return; } @@ -769,10 +758,10 @@ static void eeh_bridge_check_link(struct eeh_dev *edev) } if (val & PCI_EXP_LNKSTA_DLLLA) - pr_debug(" Link up (%s)\n", + eeh_edev_dbg(edev, "Link up (%s)\n", (val & PCI_EXP_LNKSTA_CLS_2_5GB) ? "2.5GB" : "5GB"); else - pr_debug(" Link not ready (0x%04x)\n", val); + eeh_edev_dbg(edev, "Link not ready (0x%04x)\n", val); } #define BYTE_SWAP(OFF) (8*((OFF)/4)+3-(OFF)) @@ -852,7 +841,7 @@ static void eeh_restore_device_bars(struct eeh_dev *edev) * the expansion ROM base address, the latency timer, and etc. * from the saved values in the device node. */ -static void *eeh_restore_one_device_bars(struct eeh_dev *edev, void *flag) +static void eeh_restore_one_device_bars(struct eeh_dev *edev, void *flag) { struct pci_dn *pdn = eeh_dev_to_pdn(edev); @@ -864,8 +853,6 @@ static void *eeh_restore_one_device_bars(struct eeh_dev *edev, void *flag) if (eeh_ops->restore_config && pdn) eeh_ops->restore_config(pdn); - - return NULL; } /** diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S index 54fab22c9a43..d60908ea37fb 100644 --- a/arch/powerpc/kernel/entry_32.S +++ b/arch/powerpc/kernel/entry_32.S @@ -230,7 +230,7 @@ transfer_to_handler_cont: */ lis r12,reenable_mmu@h ori r12,r12,reenable_mmu@l - LOAD_MSR_KERNEL(r0, MSR_KERNEL) + LOAD_REG_IMMEDIATE(r0, MSR_KERNEL) mtspr SPRN_SRR0,r12 mtspr SPRN_SRR1,r0 SYNC @@ -304,7 +304,7 @@ stack_ovf: addi r1,r1,THREAD_SIZE-STACK_FRAME_OVERHEAD lis r9,StackOverflow@ha addi r9,r9,StackOverflow@l - LOAD_MSR_KERNEL(r10,MSR_KERNEL) + LOAD_REG_IMMEDIATE(r10,MSR_KERNEL) #if defined(CONFIG_PPC_8xx) && defined(CONFIG_PERF_EVENTS) mtspr SPRN_NRI, r0 #endif @@ -324,7 +324,7 @@ trace_syscall_entry_irq_off: bl trace_hardirqs_on /* Now enable for real */ - LOAD_MSR_KERNEL(r10, MSR_KERNEL | MSR_EE) + LOAD_REG_IMMEDIATE(r10, MSR_KERNEL | MSR_EE) mtmsr r10 REST_GPR(0, r1) @@ -394,7 +394,7 @@ ret_from_syscall: #endif mr r6,r3 /* disable interrupts so current_thread_info()->flags can't change */ - LOAD_MSR_KERNEL(r10,MSR_KERNEL) /* doesn't include MSR_EE */ + LOAD_REG_IMMEDIATE(r10,MSR_KERNEL) /* doesn't include MSR_EE */ /* Note: We don't bother telling lockdep about it */ SYNC MTMSRD(r10) @@ -777,11 +777,19 @@ fast_exception_return: 1: lis r3,exc_exit_restart_end@ha addi r3,r3,exc_exit_restart_end@l cmplw r12,r3 +#if CONFIG_PPC_BOOK3S_601 + bge 2b +#else bge 3f +#endif lis r4,exc_exit_restart@ha addi r4,r4,exc_exit_restart@l cmplw r12,r4 +#if CONFIG_PPC_BOOK3S_601 + blt 2b +#else blt 3f +#endif lis r3,fee_restarts@ha tophys(r3,r3) lwz r5,fee_restarts@l(r3) @@ -800,9 +808,6 @@ fee_restarts: /* aargh, we don't know which trap this is */ /* but the 601 doesn't implement the RI bit, so assume it's OK */ 3: -BEGIN_FTR_SECTION - b 2b -END_FTR_SECTION_IFSET(CPU_FTR_601) li r10,-1 stw r10,_TRAP(r11) addi r3,r1,STACK_FRAME_OVERHEAD @@ -824,7 +829,7 @@ ret_from_except: * can't change between when we test it and when we return * from the interrupt. */ /* Note: We don't bother telling lockdep about it */ - LOAD_MSR_KERNEL(r10,MSR_KERNEL) + LOAD_REG_IMMEDIATE(r10,MSR_KERNEL) SYNC /* Some chip revs have problems here... */ MTMSRD(r10) /* disable interrupts */ @@ -991,7 +996,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_NEED_PAIRED_STWCX) * can restart the exception exit path at the label * exc_exit_restart below. -- paulus */ - LOAD_MSR_KERNEL(r10,MSR_KERNEL & ~MSR_RI) + LOAD_REG_IMMEDIATE(r10,MSR_KERNEL & ~MSR_RI) SYNC MTMSRD(r10) /* clear the RI bit */ .globl exc_exit_restart @@ -1066,7 +1071,7 @@ exc_exit_restart_end: REST_NVGPRS(r1); \ lwz r3,_MSR(r1); \ andi. r3,r3,MSR_PR; \ - LOAD_MSR_KERNEL(r10,MSR_KERNEL); \ + LOAD_REG_IMMEDIATE(r10,MSR_KERNEL); \ bne user_exc_return; \ lwz r0,GPR0(r1); \ lwz r2,GPR2(r1); \ @@ -1236,7 +1241,7 @@ recheck: * neither. Those disable/enable cycles used to peek at * TI_FLAGS aren't advertised. */ - LOAD_MSR_KERNEL(r10,MSR_KERNEL) + LOAD_REG_IMMEDIATE(r10,MSR_KERNEL) SYNC MTMSRD(r10) /* disable interrupts */ lwz r9,TI_FLAGS(r2) @@ -1270,11 +1275,19 @@ nonrecoverable: lis r10,exc_exit_restart_end@ha addi r10,r10,exc_exit_restart_end@l cmplw r12,r10 +#ifdef CONFIG_PPC_BOOK3S_601 + bgelr +#else bge 3f +#endif lis r11,exc_exit_restart@ha addi r11,r11,exc_exit_restart@l cmplw r12,r11 +#ifdef CONFIG_PPC_BOOK3S_601 + bltlr +#else blt 3f +#endif lis r10,ee_restarts@ha lwz r12,ee_restarts@l(r10) addi r12,r12,1 @@ -1283,9 +1296,6 @@ nonrecoverable: blr 3: /* OK, we can't recover, kill this process */ /* but the 601 doesn't implement the RI bit, so assume it's OK */ -BEGIN_FTR_SECTION - blr -END_FTR_SECTION_IFSET(CPU_FTR_601) lwz r3,_TRAP(r1) andi. r0,r3,1 beq 5f @@ -1329,7 +1339,7 @@ _GLOBAL(enter_rtas) lwz r4,RTASBASE(r4) mfmsr r9 stw r9,8(r1) - LOAD_MSR_KERNEL(r0,MSR_KERNEL) + LOAD_REG_IMMEDIATE(r0,MSR_KERNEL) SYNC /* disable interrupts so SRR0/1 */ MTMSRD(r0) /* don't get trashed */ li r9,MSR_KERNEL & ~(MSR_IR|MSR_DR) diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index 0a0b5310f54a..6467bdab8d40 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -69,24 +69,20 @@ BEGIN_FTR_SECTION bne .Ltabort_syscall END_FTR_SECTION_IFSET(CPU_FTR_TM) #endif - andi. r10,r12,MSR_PR mr r10,r1 - addi r1,r1,-INT_FRAME_SIZE - beq- 1f ld r1,PACAKSAVE(r13) -1: std r10,0(r1) + std r10,0(r1) std r11,_NIP(r1) std r12,_MSR(r1) std r0,GPR0(r1) std r10,GPR1(r1) - beq 2f /* if from kernel mode */ #ifdef CONFIG_PPC_FSL_BOOK3E START_BTB_FLUSH_SECTION BTB_FLUSH(r10) END_BTB_FLUSH_SECTION #endif ACCOUNT_CPU_USER_ENTRY(r13, r10, r11) -2: std r2,GPR2(r1) + std r2,GPR2(r1) std r3,GPR3(r1) mfcr r2 std r4,GPR4(r1) @@ -122,14 +118,13 @@ END_BTB_FLUSH_SECTION #if defined(CONFIG_VIRT_CPU_ACCOUNTING_NATIVE) && defined(CONFIG_PPC_SPLPAR) BEGIN_FW_FTR_SECTION - beq 33f - /* if from user, see if there are any DTL entries to process */ + /* see if there are any DTL entries to process */ ld r10,PACALPPACAPTR(r13) /* get ptr to VPA */ ld r11,PACA_DTL_RIDX(r13) /* get log read index */ addi r10,r10,LPPACA_DTLIDX LDX_BE r10,0,r10 /* get log write index */ - cmpd cr1,r11,r10 - beq+ cr1,33f + cmpd r11,r10 + beq+ 33f bl accumulate_stolen_time REST_GPR(0,r1) REST_4GPRS(3,r1) @@ -203,6 +198,7 @@ system_call: /* label this so stack traces look sane */ mtctr r12 bctrl /* Call handler */ + /* syscall_exit can exit to kernel mode, via ret_from_kernel_thread */ .Lsyscall_exit: std r3,RESULT(r1) @@ -216,11 +212,6 @@ system_call: /* label this so stack traces look sane */ ld r12, PACA_THREAD_INFO(r13) ld r8,_MSR(r1) -#ifdef CONFIG_PPC_BOOK3S - /* No MSR:RI on BookE */ - andi. r10,r8,MSR_RI - beq- .Lunrecov_restore -#endif /* * This is a few instructions into the actual syscall exit path (which actually diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S index 1cfb3da4a84a..829950b96d29 100644 --- a/arch/powerpc/kernel/exceptions-64e.S +++ b/arch/powerpc/kernel/exceptions-64e.S @@ -750,12 +750,14 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) ld r15,PACATOC(r13) ld r14,interrupt_base_book3e@got(r15) ld r15,__end_interrupts@got(r15) -#else - LOAD_REG_IMMEDIATE(r14,interrupt_base_book3e) - LOAD_REG_IMMEDIATE(r15,__end_interrupts) -#endif cmpld cr0,r10,r14 cmpld cr1,r10,r15 +#else + LOAD_REG_IMMEDIATE_SYM(r14, r15, interrupt_base_book3e) + cmpld cr0, r10, r14 + LOAD_REG_IMMEDIATE_SYM(r14, r15, __end_interrupts) + cmpld cr1, r10, r14 +#endif blt+ cr0,1f bge+ cr1,1f @@ -820,12 +822,14 @@ kernel_dbg_exc: ld r15,PACATOC(r13) ld r14,interrupt_base_book3e@got(r15) ld r15,__end_interrupts@got(r15) -#else - LOAD_REG_IMMEDIATE(r14,interrupt_base_book3e) - LOAD_REG_IMMEDIATE(r15,__end_interrupts) -#endif cmpld cr0,r10,r14 cmpld cr1,r10,r15 +#else + LOAD_REG_IMMEDIATE_SYM(r14, r15, interrupt_base_book3e) + cmpld cr0, r10, r14 + LOAD_REG_IMMEDIATE_SYM(r14, r15,__end_interrupts) + cmpld cr1, r10, r14 +#endif blt+ cr0,1f bge+ cr1,1f @@ -1449,7 +1453,7 @@ a2_tlbinit_code_start: a2_tlbinit_after_linear_map: /* Now we branch the new virtual address mapped by this entry */ - LOAD_REG_IMMEDIATE(r3,1f) + LOAD_REG_IMMEDIATE_SYM(r3, r5, 1f) mtctr r3 bctr diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 6ba3cc2ef8ab..d0018dd17e0a 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -44,6 +44,58 @@ #endif /* + * Following are fixed section helper macros. + * + * EXC_REAL_BEGIN/END - real, unrelocated exception vectors + * EXC_VIRT_BEGIN/END - virt (AIL), unrelocated exception vectors + * TRAMP_REAL_BEGIN - real, unrelocated helpers (virt may call these) + * TRAMP_VIRT_BEGIN - virt, unreloc helpers (in practice, real can use) + * TRAMP_KVM_BEGIN - KVM handlers, these are put into real, unrelocated + * EXC_COMMON - After switching to virtual, relocated mode. + */ + +#define EXC_REAL_BEGIN(name, start, size) \ + FIXED_SECTION_ENTRY_BEGIN_LOCATION(real_vectors, exc_real_##start##_##name, start, size) + +#define EXC_REAL_END(name, start, size) \ + FIXED_SECTION_ENTRY_END_LOCATION(real_vectors, exc_real_##start##_##name, start, size) + +#define EXC_VIRT_BEGIN(name, start, size) \ + FIXED_SECTION_ENTRY_BEGIN_LOCATION(virt_vectors, exc_virt_##start##_##name, start, size) + +#define EXC_VIRT_END(name, start, size) \ + FIXED_SECTION_ENTRY_END_LOCATION(virt_vectors, exc_virt_##start##_##name, start, size) + +#define EXC_COMMON_BEGIN(name) \ + USE_TEXT_SECTION(); \ + .balign IFETCH_ALIGN_BYTES; \ + .global name; \ + _ASM_NOKPROBE_SYMBOL(name); \ + DEFINE_FIXED_SYMBOL(name); \ +name: + +#define TRAMP_REAL_BEGIN(name) \ + FIXED_SECTION_ENTRY_BEGIN(real_trampolines, name) + +#define TRAMP_VIRT_BEGIN(name) \ + FIXED_SECTION_ENTRY_BEGIN(virt_trampolines, name) + +#ifdef CONFIG_KVM_BOOK3S_64_HANDLER +#define TRAMP_KVM_BEGIN(name) \ + TRAMP_VIRT_BEGIN(name) +#else +#define TRAMP_KVM_BEGIN(name) +#endif + +#define EXC_REAL_NONE(start, size) \ + FIXED_SECTION_ENTRY_BEGIN_LOCATION(real_vectors, exc_real_##start##_##unused, start, size); \ + FIXED_SECTION_ENTRY_END_LOCATION(real_vectors, exc_real_##start##_##unused, start, size) + +#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) + +/* * 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 @@ -68,6 +120,7 @@ addis reg,reg,(ABS_ADDR(label))@h /* Exception register prefixes */ +#define EXC_HV_OR_STD 2 /* depends on HVMODE */ #define EXC_HV 1 #define EXC_STD 0 @@ -127,126 +180,6 @@ 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 @@ -260,6 +193,11 @@ END_FTR_SECTION_NESTED(ftr,ftr,943) mtctr reg; \ bctr +.macro INT_KVM_HANDLER name, vec, hsrr, area, skip + TRAMP_KVM_BEGIN(\name\()_kvm) + KVM_HANDLER \vec, \hsrr, \area, \skip +.endm + #ifdef CONFIG_KVM_BOOK3S_64_HANDLER #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE /* @@ -272,17 +210,13 @@ END_FTR_SECTION_NESTED(ftr,ftr,943) #define kvmppc_interrupt kvmppc_interrupt_pr #endif -.macro KVMTEST hsrr, n +.macro KVMTEST name, hsrr, n lbz r10,HSTATE_IN_GUEST(r13) cmpwi r10,0 - .if \hsrr - bne do_kvm_H\n - .else - bne do_kvm_\n - .endif + bne \name\()_kvm .endm -.macro KVM_HANDLER area, hsrr, n, skip +.macro KVM_HANDLER vec, hsrr, area, skip .if \skip cmpwi r10,KVM_GUEST_MODE_SKIP beq 89f @@ -301,10 +235,16 @@ END_FTR_SECTION_NESTED(CPU_FTR_HAS_PPR,CPU_FTR_HAS_PPR,948) 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) + .if \hsrr == EXC_HV_OR_STD + BEGIN_FTR_SECTION + ori r12,r12,(\vec + 0x2) + FTR_SECTION_ELSE + ori r12,r12,(\vec) + ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206) + .elseif \hsrr + ori r12,r12,(\vec + 0x2) .else - ori r12,r12,(\n) + ori r12,r12,(\vec) .endif #ifdef CONFIG_RELOCATABLE @@ -329,7 +269,13 @@ END_FTR_SECTION_NESTED(CPU_FTR_HAS_PPR,CPU_FTR_HAS_PPR,948) 89: mtocrf 0x80,r9 ld r9,\area+EX_R9(r13) ld r10,\area+EX_R10(r13) - .if \hsrr + .if \hsrr == EXC_HV_OR_STD + BEGIN_FTR_SECTION + b kvmppc_skip_Hinterrupt + FTR_SECTION_ELSE + b kvmppc_skip_interrupt + ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206) + .elseif \hsrr b kvmppc_skip_Hinterrupt .else b kvmppc_skip_interrupt @@ -338,88 +284,328 @@ END_FTR_SECTION_NESTED(CPU_FTR_HAS_PPR,CPU_FTR_HAS_PPR,948) .endm #else -.macro KVMTEST hsrr, n +.macro KVMTEST name, hsrr, n +.endm +.macro KVM_HANDLER name, vec, hsrr, area, skip .endm -.macro KVM_HANDLER area, hsrr, n, skip +#endif + +.macro INT_SAVE_SRR_AND_JUMP 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 == EXC_HV_OR_STD + BEGIN_FTR_SECTION + mfspr r11,SPRN_HSRR0 /* save HSRR0 */ + mfspr r12,SPRN_HSRR1 /* and HSRR1 */ + mtspr SPRN_HSRR1,r10 + FTR_SECTION_ELSE + mfspr r11,SPRN_SRR0 /* save SRR0 */ + mfspr r12,SPRN_SRR1 /* and SRR1 */ + mtspr SPRN_SRR1,r10 + ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206) + .elseif \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 == EXC_HV_OR_STD + BEGIN_FTR_SECTION + mtspr SPRN_HSRR0,r10 + HRFI_TO_KERNEL + FTR_SECTION_ELSE + mtspr SPRN_SRR0,r10 + RFI_TO_KERNEL + ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206) + .elseif \hsrr + mtspr SPRN_HSRR0,r10 + HRFI_TO_KERNEL + .else + mtspr SPRN_SRR0,r10 + RFI_TO_KERNEL + .endif + b . /* prevent speculative execution */ .endm + +/* INT_SAVE_SRR_AND_JUMP works for real or virt, this is faster but virt only */ +.macro INT_VIRT_SAVE_SRR_AND_JUMP label, hsrr +#ifdef CONFIG_RELOCATABLE + .if \hsrr == EXC_HV_OR_STD + BEGIN_FTR_SECTION + mfspr r11,SPRN_HSRR0 /* save HSRR0 */ + FTR_SECTION_ELSE + mfspr r11,SPRN_SRR0 /* save SRR0 */ + ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206) + .elseif \hsrr + mfspr r11,SPRN_HSRR0 /* save HSRR0 */ + .else + mfspr r11,SPRN_SRR0 /* save SRR0 */ + .endif + LOAD_HANDLER(r12, \label\()) + mtctr r12 + .if \hsrr == EXC_HV_OR_STD + BEGIN_FTR_SECTION + mfspr r12,SPRN_HSRR1 /* and HSRR1 */ + FTR_SECTION_ELSE + mfspr r12,SPRN_SRR1 /* and HSRR1 */ + ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206) + .elseif \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 == EXC_HV_OR_STD + BEGIN_FTR_SECTION + mfspr r11,SPRN_HSRR0 /* save HSRR0 */ + mfspr r12,SPRN_HSRR1 /* and HSRR1 */ + FTR_SECTION_ELSE + mfspr r11,SPRN_SRR0 /* save SRR0 */ + mfspr r12,SPRN_SRR1 /* and SRR1 */ + ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206) + .elseif \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 -#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 */ +/* + * This is the BOOK3S interrupt entry code macro. + * + * This can result in one of several things happening: + * - Branch to the _common handler, relocated, in virtual mode. + * These are normal interrupts (synchronous and asynchronous) handled by + * the kernel. + * - Branch to KVM, relocated but real mode interrupts remain in real mode. + * These occur when HSTATE_IN_GUEST is set. The interrupt may be caused by + * / intended for host or guest kernel, but KVM must always be involved + * because the machine state is set for guest execution. + * - Branch to the masked handler, unrelocated. + * These occur when maskable asynchronous interrupts are taken with the + * irq_soft_mask set. + * - Branch to an "early" handler in real mode but relocated. + * This is done if early=1. MCE and HMI use these to handle errors in real + * mode. + * - Fall through and continue executing in real, unrelocated mode. + * This is done if early=2. + */ +.macro INT_HANDLER name, vec, ool=0, early=0, virt=0, hsrr=0, area=PACA_EXGEN, ri=1, dar=0, dsisr=0, bitmask=0, kvm=0 + 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) + .if \ool + .if !\virt + b tramp_real_\name + .pushsection .text + TRAMP_REAL_BEGIN(tramp_real_\name) + .else + b tramp_virt_\name + .pushsection .text + TRAMP_VIRT_BEGIN(tramp_virt_\name) + .endif + .endif + + 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 \name \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 == EXC_HV_OR_STD + BEGIN_FTR_SECTION + bne masked_Hinterrupt + FTR_SECTION_ELSE + bne masked_interrupt + ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206) + .elseif \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 + .if \hsrr + mfspr r10,SPRN_HDAR + .else + mfspr r10,SPRN_DAR + .endif + std r10,\area\()+EX_DAR(r13) + .endif + .if \dsisr + .if \hsrr + mfspr r10,SPRN_HDSISR + .else + mfspr r10,SPRN_DSISR + .endif + stw r10,\area\()+EX_DSISR(r13) + .endif + + .if \early == 2 + /* nothing more */ + .elseif \early + mfctr r10 /* save ctr, even for !RELOCATABLE */ + BRANCH_TO_C000(r11, \name\()_early_common) + .elseif !\virt + INT_SAVE_SRR_AND_JUMP \name\()_common, \hsrr, \ri + .else + INT_VIRT_SAVE_SRR_AND_JUMP \name\()_common, \hsrr + .endif + .if \ool + .popsection + .endif +.endm /* * 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. + * + * If stack=0, then the stack is already set in r1, and r1 is saved in r10. + * PPR save and CPU accounting is not done for the !stack case (XXX why not?) */ -#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); \ +.macro INT_COMMON vec, area, stack, kaup, reconcile, dar, dsisr + .if \stack + 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- 100f + ld r1,PACAKSAVE(r13) /* kernel stack to use */ +100: tdgei r1,-INT_FRAME_SIZE /* trap if r1 is in userspace */ + EMIT_BUG_ENTRY 100b,__FILE__,__LINE__,0 + .endif + + 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 */ + + .if \stack + .if \kaup + kuap_save_amr_and_lock r9, r10, cr1, cr0 + .endif + beq 101f /* if from kernel mode */ + ACCOUNT_CPU_USER_ENTRY(r13, r9, r10) + SAVE_PPR(\area, r9) +101: + .else + .if \kaup + kuap_save_amr_and_lock r9, r10, cr1 + .endif + .endif + + /* Save original regs values from save area to stack frame. */ + 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) + .if \dar + .if \dar == 2 + ld r10,_NIP(r1) + .else + ld r10,\area+EX_DAR(r13) + .endif + std r10,_DAR(r1) + .endif + .if \dsisr + .if \dsisr == 2 + ld r10,_MSR(r1) + lis r11,DSISR_SRR1_MATCH_64S@h + and r10,r10,r11 + .else + lwz r10,\area+EX_DSISR(r13) + .endif + std r10,_DSISR(r1) + .endif +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) + 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,(\vec)+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 */ + + .if \stack ACCOUNT_STOLEN_TIME + .endif -/* - * 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) + .if \reconcile + RECONCILE_IRQ_STATE(r10, r11) + .endif +.endm /* * Restore all registers including H/SRR0/1 saved in a stack frame of a @@ -428,6 +614,9 @@ END_FTR_SECTION_NESTED(CPU_FTR_CFAR, CPU_FTR_CFAR, 66); \ .macro EXCEPTION_RESTORE_REGS hsrr /* Move original SRR0 and SRR1 into the respective regs */ ld r9,_MSR(r1) + .if \hsrr == EXC_HV_OR_STD + .error "EXC_HV_OR_STD Not implemented for EXCEPTION_RESTORE_REGS" + .endif .if \hsrr mtspr SPRN_HSRR1,r9 .else @@ -481,219 +670,10 @@ END_FTR_SECTION_IFSET(CPU_FTR_CAN_NAP) #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); \ + INT_COMMON realvec, PACA_EXGEN, 1, 1, 1, 0, 0 ; \ bl save_nvgprs; \ - RECONCILE_IRQ_STATE(r10, r11); \ addi r3,r1,STACK_FRAME_OVERHEAD; \ bl hdlr; \ b ret_from_except @@ -704,9 +684,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_CAN_NAP) */ #define EXC_COMMON_ASYNC(name, realvec, hdlr) \ EXC_COMMON_BEGIN(name); \ - EXCEPTION_COMMON(PACA_EXGEN, realvec); \ + INT_COMMON realvec, PACA_EXGEN, 1, 1, 1, 0, 0 ; \ FINISH_NAP; \ - RECONCILE_IRQ_STATE(r10, r11); \ RUNLATCH_ON; \ addi r3,r1,STACK_FRAME_OVERHEAD; \ bl hdlr; \ @@ -836,9 +815,7 @@ BEGIN_FTR_SECTION END_FTR_SECTION_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206) #endif - 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 + INT_HANDLER system_reset, 0x100, area=PACA_EXNMI, ri=0, kvm=1 /* * MSR_RI is not enabled, because PACA_EXNMI and nmi stack is * being used, so a nested NMI exception would corrupt it. @@ -850,9 +827,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206) * be dangerous anyway. */ EXC_REAL_END(system_reset, 0x100, 0x100) - EXC_VIRT_NONE(0x4100, 0x100) -TRAMP_KVM(PACA_EXNMI, 0x100) +INT_KVM_HANDLER system_reset 0x100, EXC_STD, PACA_EXNMI, 0 #ifdef CONFIG_PPC_P7_NAP TRAMP_REAL_BEGIN(system_reset_idle_wake) @@ -868,9 +844,7 @@ TRAMP_REAL_BEGIN(system_reset_idle_wake) */ 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 + INT_HANDLER system_reset, 0x100, area=PACA_EXNMI, ri=0 #endif /* CONFIG_PPC_PSERIES */ @@ -890,7 +864,7 @@ EXC_COMMON_BEGIN(system_reset_common) mr r10,r1 ld r1,PACA_NMI_EMERG_SP(r13) subi r1,r1,INT_FRAME_SIZE - EXCEPTION_COMMON_STACK(PACA_EXNMI, 0x100) + INT_COMMON 0x100, PACA_EXNMI, 0, 1, 0, 0, 0 bl save_nvgprs /* * Set IRQS_ALL_DISABLED unconditionally so arch_irqs_disabled does @@ -933,26 +907,39 @@ EXC_COMMON_BEGIN(system_reset_common) 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 + INT_HANDLER machine_check, 0x200, early=1, area=PACA_EXMC, dar=1, dsisr=1 + /* + * 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_0 PACA_EXMC -BEGIN_FTR_SECTION - b machine_check_common_early -FTR_SECTION_ELSE - b machine_check_pSeries_0 -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 EXC_STD, PACA_EXMC, 0, 0x200, 0, 0, 0 + +#ifdef CONFIG_PPC_PSERIES +TRAMP_REAL_BEGIN(machine_check_fwnmi) + /* See comment at machine_check exception, don't turn on RI */ + INT_HANDLER machine_check, 0x200, early=1, area=PACA_EXMC, dar=1, dsisr=1 +#endif + +INT_KVM_HANDLER machine_check 0x200, EXC_STD, PACA_EXMC, 1 + +#define MACHINE_CHECK_HANDLER_WINDUP \ + /* Clear MSR_RI before setting SRR0 and SRR1. */\ + li r9,0; \ + mtmsrd r9,1; /* Clear MSR_RI */ \ + /* Decrement paca->in_mce now RI is clear. */ \ + lhz r12,PACA_IN_MCE(r13); \ + subi r12,r12,1; \ + sth r12,PACA_IN_MCE(r13); \ + EXCEPTION_RESTORE_REGS EXC_STD + +EXC_COMMON_BEGIN(machine_check_early_common) + mtctr r10 /* Restore ctr */ + mfspr r11,SPRN_SRR0 + mfspr r12,SPRN_SRR1 + /* - * Register contents: - * R13 = PACA - * R9 = CR - * Original R9 to R13 is saved on PACA_EXMC - * * Switch to mc_emergency stack and handle re-entrancy (we limit * the nested MCE upto level 4 to avoid stack overflow). * Save MCE registers srr1, srr0, dar and dsisr and then set ME=1 @@ -973,103 +960,127 @@ TRAMP_REAL_BEGIN(machine_check_common_early) * the machine check is handled then the idle wakeup code is called * to restore state. */ - mr r11,r1 /* Save r1 */ lhz r10,PACA_IN_MCE(r13) cmpwi r10,0 /* Are we in nested machine check */ - bne 0f /* Yes, we are. */ - /* First machine check entry */ - ld r1,PACAMCEMERGSP(r13) /* Use MC emergency stack */ -0: subi r1,r1,INT_FRAME_SIZE /* alloc stack frame */ + cmpwi cr1,r10,MAX_MCE_DEPTH /* Are we at maximum nesting */ addi r10,r10,1 /* increment paca->in_mce */ sth r10,PACA_IN_MCE(r13) - /* Limit nested MCE to level 4 to avoid stack overflow */ - cmpwi r10,MAX_MCE_DEPTH - bgt 2f /* Check if we hit limit of 4 */ - std r11,GPR1(r1) /* Save r1 on the stack. */ - std r11,0(r1) /* make stack chain pointer */ - mfspr r11,SPRN_SRR0 /* Save SRR0 */ - std r11,_NIP(r1) - mfspr r11,SPRN_SRR1 /* Save SRR1 */ - std r11,_MSR(r1) - mfspr r11,SPRN_DAR /* Save DAR */ - std r11,_DAR(r1) - mfspr r11,SPRN_DSISR /* Save DSISR */ - std r11,_DSISR(r1) - std r9,_CCR(r1) /* Save CR in stackframe */ + + mr r10,r1 /* Save r1 */ + bne 1f + /* First machine check entry */ + ld r1,PACAMCEMERGSP(r13) /* Use MC emergency stack */ +1: /* Limit nested MCE to level 4 to avoid stack overflow */ + bgt cr1,unrecoverable_mce /* Check if we hit limit of 4 */ + subi r1,r1,INT_FRAME_SIZE /* alloc stack frame */ + /* We don't touch AMR here, we never go to virtual mode */ - /* Save r9 through r13 from EXMC save area to stack frame. */ - EXCEPTION_PROLOG_COMMON_2(PACA_EXMC) - mfmsr r11 /* get MSR value */ + INT_COMMON 0x200, PACA_EXMC, 0, 0, 0, 1, 1 + BEGIN_FTR_SECTION - ori r11,r11,MSR_ME /* turn on ME bit */ + bl enable_machine_check END_FTR_SECTION_IFSET(CPU_FTR_HVMODE) - ori r11,r11,MSR_RI /* turn on RI bit */ - LOAD_HANDLER(r12, machine_check_handle_early) -1: mtspr SPRN_SRR0,r12 - mtspr SPRN_SRR1,r11 - RFI_TO_KERNEL - b . /* prevent speculative execution */ -2: - /* Stack overflow. Stay on emergency stack and panic. - * Keep the ME bit off while panic-ing, so that if we hit - * another machine check we checkstop. - */ - addi r1,r1,INT_FRAME_SIZE /* go back to previous stack frame */ - ld r11,PACAKMSR(r13) - LOAD_HANDLER(r12, unrecover_mce) - li r10,MSR_ME - andc r11,r11,r10 /* Turn off MSR_ME */ - b 1b - b . /* prevent speculative execution */ + li r10,MSR_RI + mtmsrd r10,1 + + bl save_nvgprs + addi r3,r1,STACK_FRAME_OVERHEAD + bl machine_check_early + std r3,RESULT(r1) /* Save result */ + ld r12,_MSR(r1) -TRAMP_REAL_BEGIN(machine_check_pSeries) - .globl machine_check_fwnmi -machine_check_fwnmi: - EXCEPTION_PROLOG_0 PACA_EXMC +#ifdef CONFIG_PPC_P7_NAP + /* + * Check if thread was in power saving mode. We come here when any + * of the following is true: + * a. thread wasn't in power saving mode + * b. thread was in power saving mode with no state loss, + * supervisor state loss or hypervisor state loss. + * + * Go back to nap/sleep/winkle mode again if (b) is true. + */ BEGIN_FTR_SECTION - b machine_check_common_early -END_FTR_SECTION_IFCLR(CPU_FTR_HVMODE) -machine_check_pSeries_0: - EXCEPTION_PROLOG_1 EXC_STD, PACA_EXMC, 1, 0x200, 1, 1, 0 + rlwinm. r11,r12,47-31,30,31 + bne machine_check_idle_common +END_FTR_SECTION_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206) +#endif + +#ifdef CONFIG_KVM_BOOK3S_64_HANDLER /* - * MSR_RI is not enabled, because PACA_EXMC is being used, so a - * nested machine check corrupts it. machine_check_common enables - * MSR_RI. + * Check if we are coming from guest. If yes, then run the normal + * exception handler which will take the + * machine_check_kvm->kvmppc_interrupt branch to deliver the MC event + * to guest. */ - EXCEPTION_PROLOG_2_REAL machine_check_common, EXC_STD, 0 + lbz r11,HSTATE_IN_GUEST(r13) + cmpwi r11,0 /* Check if coming from guest */ + bne mce_deliver /* continue if we are. */ +#endif -TRAMP_KVM_SKIP(PACA_EXMC, 0x200) + /* + * Check if we are coming from userspace. If yes, then run the normal + * exception handler which will deliver the MC event to this kernel. + */ + andi. r11,r12,MSR_PR /* See if coming from user. */ + bne mce_deliver /* continue in V mode if we are. */ + + /* + * At this point we are coming from kernel context. + * Queue up the MCE event and return from the interrupt. + * But before that, check if this is an un-recoverable exception. + * If yes, then stay on emergency stack and panic. + */ + andi. r11,r12,MSR_RI + beq unrecoverable_mce + + /* + * Check if we have successfully handled/recovered from error, if not + * then stay on emergency stack and panic. + */ + ld r3,RESULT(r1) /* Load result */ + cmpdi r3,0 /* see if we handled MCE successfully */ + beq unrecoverable_mce /* if !handled then panic */ + + /* + * Return from MC interrupt. + * Queue up the MCE event so that we can log it later, while + * returning from kernel or opal call. + */ + bl machine_check_queue_event + MACHINE_CHECK_HANDLER_WINDUP + RFI_TO_KERNEL + +mce_deliver: + /* + * This is a host user or guest MCE. Restore all registers, then + * run the "late" handler. For host user, this will run the + * machine_check_exception handler in virtual mode like a normal + * interrupt handler. For guest, this will trigger the KVM test + * and branch to the KVM interrupt similarly to other interrupts. + */ +BEGIN_FTR_SECTION + ld r10,ORIG_GPR3(r1) + mtspr SPRN_CFAR,r10 +END_FTR_SECTION_IFSET(CPU_FTR_CFAR) + MACHINE_CHECK_HANDLER_WINDUP + /* See comment at machine_check exception, don't turn on RI */ + INT_HANDLER machine_check, 0x200, area=PACA_EXMC, ri=0, dar=1, dsisr=1, kvm=1 EXC_COMMON_BEGIN(machine_check_common) /* * Machine check is different because we use a different * save area: PACA_EXMC instead of PACA_EXGEN. */ - EXCEPTION_COMMON(PACA_EXMC, 0x200) + INT_COMMON 0x200, PACA_EXMC, 1, 1, 1, 1, 1 FINISH_NAP - RECONCILE_IRQ_STATE(r10, r11) - ld r3,PACA_EXMC+EX_DAR(r13) - lwz r4,PACA_EXMC+EX_DSISR(r13) /* Enable MSR_RI when finished with PACA_EXMC */ li r10,MSR_RI mtmsrd r10,1 - std r3,_DAR(r1) - std r4,_DSISR(r1) bl save_nvgprs addi r3,r1,STACK_FRAME_OVERHEAD bl machine_check_exception b ret_from_except -#define MACHINE_CHECK_HANDLER_WINDUP \ - /* Clear MSR_RI before setting SRR0 and SRR1. */\ - li r9,0; \ - mtmsrd r9,1; /* Clear MSR_RI */ \ - /* Decrement paca->in_mce now RI is clear. */ \ - lhz r12,PACA_IN_MCE(r13); \ - subi r12,r12,1; \ - sth r12,PACA_IN_MCE(r13); \ - EXCEPTION_RESTORE_REGS EXC_STD - #ifdef CONFIG_PPC_P7_NAP /* * This is an idle wakeup. Low level machine check has already been @@ -1101,72 +1112,8 @@ EXC_COMMON_BEGIN(machine_check_idle_common) bltlr cr1 /* no state loss, return to idle caller */ b idle_return_gpr_loss #endif - /* - * Handle machine check early in real mode. We come here with - * ME=1, MMU (IR=0 and DR=0) off and using MC emergency stack. - */ -EXC_COMMON_BEGIN(machine_check_handle_early) - std r0,GPR0(r1) /* Save r0 */ - EXCEPTION_PROLOG_COMMON_3(0x200) - bl save_nvgprs - addi r3,r1,STACK_FRAME_OVERHEAD - bl machine_check_early - std r3,RESULT(r1) /* Save result */ - ld r12,_MSR(r1) -BEGIN_FTR_SECTION - b 4f -END_FTR_SECTION_IFCLR(CPU_FTR_HVMODE) -#ifdef CONFIG_PPC_P7_NAP - /* - * Check if thread was in power saving mode. We come here when any - * of the following is true: - * a. thread wasn't in power saving mode - * b. thread was in power saving mode with no state loss, - * supervisor state loss or hypervisor state loss. - * - * Go back to nap/sleep/winkle mode again if (b) is true. - */ -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) -#endif - - /* - * Check if we are coming from hypervisor userspace. If yes then we - * continue in host kernel in V mode to deliver the MC event. - */ - rldicl. r11,r12,4,63 /* See if MC hit while in HV mode. */ - beq 5f -4: andi. r11,r12,MSR_PR /* See if coming from user. */ - bne 9f /* continue in V mode if we are. */ - -5: -#ifdef CONFIG_KVM_BOOK3S_64_HANDLER -BEGIN_FTR_SECTION - /* - * We are coming from kernel context. Check if we are coming from - * guest. if yes, then we can continue. We will fall through - * do_kvm_200->kvmppc_interrupt to deliver the MC event to guest. - */ - lbz r11,HSTATE_IN_GUEST(r13) - cmpwi r11,0 /* Check if coming from guest */ - bne 9f /* continue if we are. */ -END_FTR_SECTION_IFSET(CPU_FTR_HVMODE) -#endif - /* - * At this point we are not sure about what context we come from. - * Queue up the MCE event and return from the interrupt. - * But before that, check if this is an un-recoverable exception. - * If yes, then stay on emergency stack and panic. - */ - andi. r11,r12,MSR_RI - bne 2f -1: mfspr r11,SPRN_SRR0 - LOAD_HANDLER(r10,unrecover_mce) - mtspr SPRN_SRR0,r10 - ld r10,PACAKMSR(r13) +EXC_COMMON_BEGIN(unrecoverable_mce) /* * We are going down. But there are chances that we might get hit by * another MCE during panic path and we may run into unstable state @@ -1174,84 +1121,36 @@ END_FTR_SECTION_IFSET(CPU_FTR_HVMODE) * when another MCE is hit during panic path, system will checkstop * and hypervisor will get restarted cleanly by SP. */ - li r3,MSR_ME - andc r10,r10,r3 /* Turn off MSR_ME */ - mtspr SPRN_SRR1,r10 - RFI_TO_KERNEL - b . -2: - /* - * Check if we have successfully handled/recovered from error, if not - * then stay on emergency stack and panic. - */ - ld r3,RESULT(r1) /* Load result */ - cmpdi r3,0 /* see if we handled MCE successfully */ - - beq 1b /* if !handled then panic */ BEGIN_FTR_SECTION - /* - * Return from MC interrupt. - * Queue up the MCE event so that we can log it later, while - * returning from kernel or opal call. - */ - bl machine_check_queue_event - MACHINE_CHECK_HANDLER_WINDUP - RFI_TO_USER_OR_KERNEL -FTR_SECTION_ELSE - /* - * pSeries: Return from MC interrupt. Before that stay on emergency - * stack and call machine_check_exception to log the MCE event. - */ - LOAD_HANDLER(r10,mce_return) - mtspr SPRN_SRR0,r10 + li r10,0 /* clear MSR_RI */ + mtmsrd r10,1 + bl disable_machine_check +END_FTR_SECTION_IFSET(CPU_FTR_HVMODE) ld r10,PACAKMSR(r13) - mtspr SPRN_SRR1,r10 - RFI_TO_KERNEL - b . -ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE) -9: - /* Deliver the machine check to host kernel in V mode. */ - MACHINE_CHECK_HANDLER_WINDUP - EXCEPTION_PROLOG_0 PACA_EXMC - b machine_check_pSeries_0 + li r3,MSR_ME + andc r10,r10,r3 + mtmsrd r10 -EXC_COMMON_BEGIN(unrecover_mce) /* Invoke machine_check_exception to print MCE event and panic. */ addi r3,r1,STACK_FRAME_OVERHEAD bl machine_check_exception + /* - * We will not reach here. Even if we did, there is no way out. Call - * unrecoverable_exception and die. + * We will not reach here. Even if we did, there is no way out. + * Call unrecoverable_exception and die. */ -1: addi r3,r1,STACK_FRAME_OVERHEAD - bl unrecoverable_exception - b 1b - -EXC_COMMON_BEGIN(mce_return) - /* Invoke machine_check_exception to print MCE event and return. */ addi r3,r1,STACK_FRAME_OVERHEAD - bl machine_check_exception - MACHINE_CHECK_HANDLER_WINDUP - RFI_TO_KERNEL + bl unrecoverable_exception b . + EXC_REAL_BEGIN(data_access, 0x300, 0x80) - EXCEPTION_PROLOG_0 PACA_EXGEN - b tramp_real_data_access + INT_HANDLER data_access, 0x300, ool=1, dar=1, dsisr=1, kvm=1 EXC_REAL_END(data_access, 0x300, 0x80) - -TRAMP_REAL_BEGIN(tramp_real_data_access) - 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) - 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 + INT_HANDLER data_access, 0x300, virt=1, dar=1, dsisr=1 EXC_VIRT_END(data_access, 0x4300, 0x80) - -TRAMP_KVM_SKIP(PACA_EXGEN, 0x300) - +INT_KVM_HANDLER data_access, 0x300, EXC_STD, PACA_EXGEN, 1 EXC_COMMON_BEGIN(data_access_common) /* * Here r13 points to the paca, r9 contains the saved CR, @@ -1259,15 +1158,12 @@ EXC_COMMON_BEGIN(data_access_common) * r9 - r13 are saved in paca->exgen. * EX_DAR and EX_DSISR have saved DAR/DSISR */ - EXCEPTION_COMMON(PACA_EXGEN, 0x300) - RECONCILE_IRQ_STATE(r10, r11) - ld r12,_MSR(r1) - ld r3,PACA_EXGEN+EX_DAR(r13) - lwz r4,PACA_EXGEN+EX_DSISR(r13) - li r5,0x300 - std r3,_DAR(r1) - std r4,_DSISR(r1) + INT_COMMON 0x300, PACA_EXGEN, 1, 1, 1, 1, 1 + ld r4,_DAR(r1) + ld r5,_DSISR(r1) BEGIN_MMU_FTR_SECTION + ld r6,_MSR(r1) + li r3,0x300 b do_hash_page /* Try to handle as hpte fault */ MMU_FTR_SECTION_ELSE b handle_page_fault @@ -1275,26 +1171,15 @@ ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX) EXC_REAL_BEGIN(data_access_slb, 0x380, 0x80) - EXCEPTION_PROLOG_0 PACA_EXSLB - b tramp_real_data_access_slb + INT_HANDLER data_access_slb, 0x380, ool=1, area=PACA_EXSLB, dar=1, kvm=1 EXC_REAL_END(data_access_slb, 0x380, 0x80) - -TRAMP_REAL_BEGIN(tramp_real_data_access_slb) - 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) - 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 + INT_HANDLER data_access_slb, 0x380, virt=1, area=PACA_EXSLB, dar=1 EXC_VIRT_END(data_access_slb, 0x4380, 0x80) - -TRAMP_KVM_SKIP(PACA_EXSLB, 0x380) - +INT_KVM_HANDLER data_access_slb, 0x380, EXC_STD, PACA_EXSLB, 1 EXC_COMMON_BEGIN(data_access_slb_common) - EXCEPTION_COMMON(PACA_EXSLB, 0x380) - ld r4,PACA_EXSLB+EX_DAR(r13) - std r4,_DAR(r1) + INT_COMMON 0x380, PACA_EXSLB, 1, 1, 0, 1, 0 + ld r4,_DAR(r1) addi r3,r1,STACK_FRAME_OVERHEAD BEGIN_MMU_FTR_SECTION /* HPT case, do SLB fault */ @@ -1317,33 +1202,36 @@ ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX) b ret_from_except -EXC_REAL(instruction_access, 0x400, 0x80) -EXC_VIRT(instruction_access, 0x4400, 0x80, 0x400) -TRAMP_KVM(PACA_EXGEN, 0x400) - +EXC_REAL_BEGIN(instruction_access, 0x400, 0x80) + INT_HANDLER instruction_access, 0x400, kvm=1 +EXC_REAL_END(instruction_access, 0x400, 0x80) +EXC_VIRT_BEGIN(instruction_access, 0x4400, 0x80) + INT_HANDLER instruction_access, 0x400, virt=1 +EXC_VIRT_END(instruction_access, 0x4400, 0x80) +INT_KVM_HANDLER instruction_access, 0x400, EXC_STD, PACA_EXGEN, 0 EXC_COMMON_BEGIN(instruction_access_common) - EXCEPTION_COMMON(PACA_EXGEN, 0x400) - RECONCILE_IRQ_STATE(r10, r11) - ld r12,_MSR(r1) - ld r3,_NIP(r1) - andis. r4,r12,DSISR_SRR1_MATCH_64S@h - li r5,0x400 - std r3,_DAR(r1) - std r4,_DSISR(r1) + INT_COMMON 0x400, PACA_EXGEN, 1, 1, 1, 2, 2 + ld r4,_DAR(r1) + ld r5,_DSISR(r1) BEGIN_MMU_FTR_SECTION + ld r6,_MSR(r1) + li r3,0x400 b do_hash_page /* Try to handle as hpte fault */ MMU_FTR_SECTION_ELSE b handle_page_fault ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX) -__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_REAL_BEGIN(instruction_access_slb, 0x480, 0x80) + INT_HANDLER instruction_access_slb, 0x480, area=PACA_EXSLB, kvm=1 +EXC_REAL_END(instruction_access_slb, 0x480, 0x80) +EXC_VIRT_BEGIN(instruction_access_slb, 0x4480, 0x80) + INT_HANDLER instruction_access_slb, 0x480, virt=1, area=PACA_EXSLB +EXC_VIRT_END(instruction_access_slb, 0x4480, 0x80) +INT_KVM_HANDLER instruction_access_slb, 0x480, EXC_STD, PACA_EXSLB, 0 EXC_COMMON_BEGIN(instruction_access_slb_common) - EXCEPTION_COMMON(PACA_EXSLB, 0x480) - ld r4,_NIP(r1) + INT_COMMON 0x480, PACA_EXSLB, 1, 1, 0, 2, 0 + ld r4,_DAR(r1) addi r3,r1,STACK_FRAME_OVERHEAD BEGIN_MMU_FTR_SECTION /* HPT case, do SLB fault */ @@ -1359,69 +1247,44 @@ ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX) std r3,RESULT(r1) bl save_nvgprs RECONCILE_IRQ_STATE(r10, r11) - ld r4,_NIP(r1) + ld r4,_DAR(r1) ld r5,RESULT(r1) addi r3,r1,STACK_FRAME_OVERHEAD bl do_bad_slb_fault b ret_from_except - EXC_REAL_BEGIN(hardware_interrupt, 0x500, 0x100) - 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) + INT_HANDLER hardware_interrupt, 0x500, hsrr=EXC_HV_OR_STD, bitmask=IRQS_DISABLED, kvm=1 EXC_REAL_END(hardware_interrupt, 0x500, 0x100) - EXC_VIRT_BEGIN(hardware_interrupt, 0x4500, 0x100) - 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) + INT_HANDLER hardware_interrupt, 0x500, virt=1, hsrr=EXC_HV_OR_STD, bitmask=IRQS_DISABLED, kvm=1 EXC_VIRT_END(hardware_interrupt, 0x4500, 0x100) - -TRAMP_KVM(PACA_EXGEN, 0x500) -TRAMP_KVM_HV(PACA_EXGEN, 0x500) +INT_KVM_HANDLER hardware_interrupt, 0x500, EXC_HV_OR_STD, PACA_EXGEN, 0 EXC_COMMON_ASYNC(hardware_interrupt_common, 0x500, do_IRQ) EXC_REAL_BEGIN(alignment, 0x600, 0x100) - 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 + INT_HANDLER alignment, 0x600, dar=1, dsisr=1, kvm=1 EXC_REAL_END(alignment, 0x600, 0x100) - EXC_VIRT_BEGIN(alignment, 0x4600, 0x100) - 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 + INT_HANDLER alignment, 0x600, virt=1, dar=1, dsisr=1 EXC_VIRT_END(alignment, 0x4600, 0x100) - -TRAMP_KVM(PACA_EXGEN, 0x600) +INT_KVM_HANDLER alignment, 0x600, EXC_STD, PACA_EXGEN, 0 EXC_COMMON_BEGIN(alignment_common) - EXCEPTION_COMMON(PACA_EXGEN, 0x600) - ld r3,PACA_EXGEN+EX_DAR(r13) - lwz r4,PACA_EXGEN+EX_DSISR(r13) - std r3,_DAR(r1) - std r4,_DSISR(r1) + INT_COMMON 0x600, PACA_EXGEN, 1, 1, 1, 1, 1 bl save_nvgprs - RECONCILE_IRQ_STATE(r10, r11) addi r3,r1,STACK_FRAME_OVERHEAD bl alignment_exception b ret_from_except -EXC_REAL(program_check, 0x700, 0x100) -EXC_VIRT(program_check, 0x4700, 0x100, 0x700) -TRAMP_KVM(PACA_EXGEN, 0x700) +EXC_REAL_BEGIN(program_check, 0x700, 0x100) + INT_HANDLER program_check, 0x700, kvm=1 +EXC_REAL_END(program_check, 0x700, 0x100) +EXC_VIRT_BEGIN(program_check, 0x4700, 0x100) + INT_HANDLER program_check, 0x700, virt=1 +EXC_VIRT_END(program_check, 0x4700, 0x100) +INT_KVM_HANDLER program_check, 0x700, EXC_STD, PACA_EXGEN, 0 EXC_COMMON_BEGIN(program_check_common) /* * It's possible to receive a TM Bad Thing type program check with @@ -1447,27 +1310,33 @@ EXC_COMMON_BEGIN(program_check_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 !! */ + INT_COMMON 0x700, PACA_EXGEN, 0, 1, 1, 0, 0 + b 3f 2: - EXCEPTION_COMMON(PACA_EXGEN, 0x700) + INT_COMMON 0x700, PACA_EXGEN, 1, 1, 1, 0, 0 +3: bl save_nvgprs - RECONCILE_IRQ_STATE(r10, r11) addi r3,r1,STACK_FRAME_OVERHEAD bl program_check_exception b ret_from_except -EXC_REAL(fp_unavailable, 0x800, 0x100) -EXC_VIRT(fp_unavailable, 0x4800, 0x100, 0x800) -TRAMP_KVM(PACA_EXGEN, 0x800) +EXC_REAL_BEGIN(fp_unavailable, 0x800, 0x100) + INT_HANDLER fp_unavailable, 0x800, kvm=1 +EXC_REAL_END(fp_unavailable, 0x800, 0x100) +EXC_VIRT_BEGIN(fp_unavailable, 0x4800, 0x100) + INT_HANDLER fp_unavailable, 0x800, virt=1 +EXC_VIRT_END(fp_unavailable, 0x4800, 0x100) +INT_KVM_HANDLER fp_unavailable, 0x800, EXC_STD, PACA_EXGEN, 0 EXC_COMMON_BEGIN(fp_unavailable_common) - EXCEPTION_COMMON(PACA_EXGEN, 0x800) + INT_COMMON 0x800, PACA_EXGEN, 1, 1, 0, 0, 0 bne 1f /* if from user, just load it up */ bl save_nvgprs RECONCILE_IRQ_STATE(r10, r11) addi r3,r1,STACK_FRAME_OVERHEAD bl kernel_fp_unavailable_exception - BUG_OPCODE +0: trap + EMIT_BUG_ENTRY 0b, __FILE__, __LINE__, 0 1: #ifdef CONFIG_PPC_TRANSACTIONAL_MEM BEGIN_FTR_SECTION @@ -1490,21 +1359,33 @@ END_FTR_SECTION_IFSET(CPU_FTR_TM) #endif -EXC_REAL_OOL_MASKABLE(decrementer, 0x900, 0x80, IRQS_DISABLED) -EXC_VIRT_MASKABLE(decrementer, 0x4900, 0x80, 0x900, IRQS_DISABLED) -TRAMP_KVM(PACA_EXGEN, 0x900) +EXC_REAL_BEGIN(decrementer, 0x900, 0x80) + INT_HANDLER decrementer, 0x900, ool=1, bitmask=IRQS_DISABLED, kvm=1 +EXC_REAL_END(decrementer, 0x900, 0x80) +EXC_VIRT_BEGIN(decrementer, 0x4900, 0x80) + INT_HANDLER decrementer, 0x900, virt=1, bitmask=IRQS_DISABLED +EXC_VIRT_END(decrementer, 0x4900, 0x80) +INT_KVM_HANDLER decrementer, 0x900, EXC_STD, PACA_EXGEN, 0 EXC_COMMON_ASYNC(decrementer_common, 0x900, timer_interrupt) -EXC_REAL_HV(hdecrementer, 0x980, 0x80) -EXC_VIRT_HV(hdecrementer, 0x4980, 0x80, 0x980) -TRAMP_KVM_HV(PACA_EXGEN, 0x980) +EXC_REAL_BEGIN(hdecrementer, 0x980, 0x80) + INT_HANDLER hdecrementer, 0x980, hsrr=EXC_HV, kvm=1 +EXC_REAL_END(hdecrementer, 0x980, 0x80) +EXC_VIRT_BEGIN(hdecrementer, 0x4980, 0x80) + INT_HANDLER hdecrementer, 0x980, virt=1, hsrr=EXC_HV, kvm=1 +EXC_VIRT_END(hdecrementer, 0x4980, 0x80) +INT_KVM_HANDLER hdecrementer, 0x980, EXC_HV, PACA_EXGEN, 0 EXC_COMMON(hdecrementer_common, 0x980, hdec_interrupt) -EXC_REAL_MASKABLE(doorbell_super, 0xa00, 0x100, IRQS_DISABLED) -EXC_VIRT_MASKABLE(doorbell_super, 0x4a00, 0x100, 0xa00, IRQS_DISABLED) -TRAMP_KVM(PACA_EXGEN, 0xa00) +EXC_REAL_BEGIN(doorbell_super, 0xa00, 0x100) + INT_HANDLER doorbell_super, 0xa00, bitmask=IRQS_DISABLED, kvm=1 +EXC_REAL_END(doorbell_super, 0xa00, 0x100) +EXC_VIRT_BEGIN(doorbell_super, 0x4a00, 0x100) + INT_HANDLER doorbell_super, 0xa00, virt=1, bitmask=IRQS_DISABLED +EXC_VIRT_END(doorbell_super, 0x4a00, 0x100) +INT_KVM_HANDLER doorbell_super, 0xa00, EXC_STD, PACA_EXGEN, 0 #ifdef CONFIG_PPC_DOORBELL EXC_COMMON_ASYNC(doorbell_super_common, 0xa00, doorbell_exception) #else @@ -1512,17 +1393,13 @@ EXC_COMMON_ASYNC(doorbell_super_common, 0xa00, unknown_exception) #endif -EXC_REAL(trap_0b, 0xb00, 0x100) -EXC_VIRT(trap_0b, 0x4b00, 0x100, 0xb00) -TRAMP_KVM(PACA_EXGEN, 0xb00) -EXC_COMMON(trap_0b_common, 0xb00, unknown_exception) +EXC_REAL_NONE(0xb00, 0x100) +EXC_VIRT_NONE(0x4b00, 0x100) /* * system call / hypercall (0xc00, 0x4c00) * * The system call exception is invoked with "sc 0" and does not alter HV bit. - * There is support for kernel code to invoke system calls but there are no - * in-tree users. * * The hypercall is invoked with "sc 1" and sets HV=1. * @@ -1567,7 +1444,7 @@ EXC_COMMON(trap_0b_common, 0xb00, unknown_exception) 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 */ + KVMTEST system_call EXC_STD 0xc00 /* uses r10, branch to system_call_kvm */ mfctr r9 #else mr r9,r13 @@ -1621,7 +1498,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE) EXC_REAL_BEGIN(system_call, 0xc00, 0x100) SYSTEM_CALL 0 EXC_REAL_END(system_call, 0xc00, 0x100) - EXC_VIRT_BEGIN(system_call, 0x4c00, 0x100) SYSTEM_CALL 1 EXC_VIRT_END(system_call, 0x4c00, 0x100) @@ -1634,7 +1510,7 @@ EXC_VIRT_END(system_call, 0x4c00, 0x100) * ctr = orig r13 * orig r10 saved in PACA */ -TRAMP_KVM_BEGIN(do_kvm_0xc00) +TRAMP_KVM_BEGIN(system_call_kvm) /* * Save the PPR (on systems that support it) before changing to * HMT_MEDIUM. That allows the KVM code to save that value into the @@ -1647,32 +1523,33 @@ 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, 0 + KVM_HANDLER 0xc00, EXC_STD, PACA_EXGEN, 0 #endif -EXC_REAL(single_step, 0xd00, 0x100) -EXC_VIRT(single_step, 0x4d00, 0x100, 0xd00) -TRAMP_KVM(PACA_EXGEN, 0xd00) +EXC_REAL_BEGIN(single_step, 0xd00, 0x100) + INT_HANDLER single_step, 0xd00, kvm=1 +EXC_REAL_END(single_step, 0xd00, 0x100) +EXC_VIRT_BEGIN(single_step, 0x4d00, 0x100) + INT_HANDLER single_step, 0xd00, virt=1 +EXC_VIRT_END(single_step, 0x4d00, 0x100) +INT_KVM_HANDLER single_step, 0xd00, EXC_STD, PACA_EXGEN, 0 EXC_COMMON(single_step_common, 0xd00, single_step_exception) -EXC_REAL_OOL_HV(h_data_storage, 0xe00, 0x20) -EXC_VIRT_OOL_HV(h_data_storage, 0x4e00, 0x20, 0xe00) -TRAMP_KVM_HV_SKIP(PACA_EXGEN, 0xe00) + +EXC_REAL_BEGIN(h_data_storage, 0xe00, 0x20) + INT_HANDLER h_data_storage, 0xe00, ool=1, hsrr=EXC_HV, dar=1, dsisr=1, kvm=1 +EXC_REAL_END(h_data_storage, 0xe00, 0x20) +EXC_VIRT_BEGIN(h_data_storage, 0x4e00, 0x20) + INT_HANDLER h_data_storage, 0xe00, ool=1, virt=1, hsrr=EXC_HV, dar=1, dsisr=1, kvm=1 +EXC_VIRT_END(h_data_storage, 0x4e00, 0x20) +INT_KVM_HANDLER h_data_storage, 0xe00, EXC_HV, PACA_EXGEN, 1 EXC_COMMON_BEGIN(h_data_storage_common) - mfspr r10,SPRN_HDAR - std r10,PACA_EXGEN+EX_DAR(r13) - mfspr r10,SPRN_HDSISR - stw r10,PACA_EXGEN+EX_DSISR(r13) - EXCEPTION_COMMON(PACA_EXGEN, 0xe00) + INT_COMMON 0xe00, PACA_EXGEN, 1, 1, 1, 1, 1 bl save_nvgprs - RECONCILE_IRQ_STATE(r10, r11) addi r3,r1,STACK_FRAME_OVERHEAD BEGIN_MMU_FTR_SECTION - ld r4,PACA_EXGEN+EX_DAR(r13) - lwz r5,PACA_EXGEN+EX_DSISR(r13) - std r4,_DAR(r1) - std r5,_DSISR(r1) + ld r4,_DAR(r1) li r5,SIGSEGV bl bad_page_fault MMU_FTR_SECTION_ELSE @@ -1681,15 +1558,23 @@ ALT_MMU_FTR_SECTION_END_IFSET(MMU_FTR_TYPE_RADIX) b ret_from_except -EXC_REAL_OOL_HV(h_instr_storage, 0xe20, 0x20) -EXC_VIRT_OOL_HV(h_instr_storage, 0x4e20, 0x20, 0xe20) -TRAMP_KVM_HV(PACA_EXGEN, 0xe20) +EXC_REAL_BEGIN(h_instr_storage, 0xe20, 0x20) + INT_HANDLER h_instr_storage, 0xe20, ool=1, hsrr=EXC_HV, kvm=1 +EXC_REAL_END(h_instr_storage, 0xe20, 0x20) +EXC_VIRT_BEGIN(h_instr_storage, 0x4e20, 0x20) + INT_HANDLER h_instr_storage, 0xe20, ool=1, virt=1, hsrr=EXC_HV, kvm=1 +EXC_VIRT_END(h_instr_storage, 0x4e20, 0x20) +INT_KVM_HANDLER h_instr_storage, 0xe20, EXC_HV, PACA_EXGEN, 0 EXC_COMMON(h_instr_storage_common, 0xe20, unknown_exception) -EXC_REAL_OOL_HV(emulation_assist, 0xe40, 0x20) -EXC_VIRT_OOL_HV(emulation_assist, 0x4e40, 0x20, 0xe40) -TRAMP_KVM_HV(PACA_EXGEN, 0xe40) +EXC_REAL_BEGIN(emulation_assist, 0xe40, 0x20) + INT_HANDLER emulation_assist, 0xe40, ool=1, hsrr=EXC_HV, kvm=1 +EXC_REAL_END(emulation_assist, 0xe40, 0x20) +EXC_VIRT_BEGIN(emulation_assist, 0x4e40, 0x20) + INT_HANDLER emulation_assist, 0xe40, ool=1, virt=1, hsrr=EXC_HV, kvm=1 +EXC_VIRT_END(emulation_assist, 0x4e40, 0x20) +INT_KVM_HANDLER emulation_assist, 0xe40, EXC_HV, PACA_EXGEN, 0 EXC_COMMON(emulation_assist_common, 0xe40, emulation_assist_interrupt) @@ -1699,16 +1584,10 @@ EXC_COMMON(emulation_assist_common, 0xe40, emulation_assist_interrupt) * mode. */ EXC_REAL_BEGIN(hmi_exception, 0xe60, 0x20) - EXCEPTION_PROLOG_0 PACA_EXGEN - b hmi_exception_early + INT_HANDLER hmi_exception, 0xe60, ool=1, early=1, hsrr=EXC_HV, ri=0, kvm=1 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 EXC_HV, PACA_EXGEN, 1, 0xe60, 0, 0, 0 - mfctr r10 /* save ctr, even for !RELOCATABLE */ - BRANCH_TO_C000(r11, hmi_exception_early_common) - +INT_KVM_HANDLER hmi_exception, 0xe60, EXC_HV, PACA_EXGEN, 0 EXC_COMMON_BEGIN(hmi_exception_early_common) mtctr r10 /* Restore ctr */ mfspr r11,SPRN_HSRR0 /* Save HSRR0 */ @@ -1716,10 +1595,10 @@ EXC_COMMON_BEGIN(hmi_exception_early_common) mr r10,r1 /* Save r1 */ ld r1,PACAEMERGSP(r13) /* Use emergency stack for realmode */ subi r1,r1,INT_FRAME_SIZE /* alloc stack frame */ - 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) + INT_COMMON 0xe60, PACA_EXGEN, 0, 0, 0, 0, 0 + addi r3,r1,STACK_FRAME_OVERHEAD bl hmi_exception_realmode cmpdi cr0,r3,0 @@ -1734,23 +1613,25 @@ EXC_COMMON_BEGIN(hmi_exception_early_common) * firmware. */ 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 + INT_HANDLER hmi_exception, 0xe60, hsrr=EXC_HV, bitmask=IRQS_DISABLED, kvm=1 EXC_COMMON_BEGIN(hmi_exception_common) - EXCEPTION_COMMON(PACA_EXGEN, 0xe60) + INT_COMMON 0xe60, PACA_EXGEN, 1, 1, 1, 0, 0 FINISH_NAP - bl save_nvgprs - RECONCILE_IRQ_STATE(r10, r11) RUNLATCH_ON + bl save_nvgprs 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) -TRAMP_KVM_HV(PACA_EXGEN, 0xe80) + +EXC_REAL_BEGIN(h_doorbell, 0xe80, 0x20) + INT_HANDLER h_doorbell, 0xe80, ool=1, hsrr=EXC_HV, bitmask=IRQS_DISABLED, kvm=1 +EXC_REAL_END(h_doorbell, 0xe80, 0x20) +EXC_VIRT_BEGIN(h_doorbell, 0x4e80, 0x20) + INT_HANDLER h_doorbell, 0xe80, ool=1, virt=1, hsrr=EXC_HV, bitmask=IRQS_DISABLED, kvm=1 +EXC_VIRT_END(h_doorbell, 0x4e80, 0x20) +INT_KVM_HANDLER h_doorbell, 0xe80, EXC_HV, PACA_EXGEN, 0 #ifdef CONFIG_PPC_DOORBELL EXC_COMMON_ASYNC(h_doorbell_common, 0xe80, doorbell_exception) #else @@ -1758,9 +1639,13 @@ EXC_COMMON_ASYNC(h_doorbell_common, 0xe80, unknown_exception) #endif -EXC_REAL_OOL_MASKABLE_HV(h_virt_irq, 0xea0, 0x20, IRQS_DISABLED) -EXC_VIRT_OOL_MASKABLE_HV(h_virt_irq, 0x4ea0, 0x20, 0xea0, IRQS_DISABLED) -TRAMP_KVM_HV(PACA_EXGEN, 0xea0) +EXC_REAL_BEGIN(h_virt_irq, 0xea0, 0x20) + INT_HANDLER h_virt_irq, 0xea0, ool=1, hsrr=EXC_HV, bitmask=IRQS_DISABLED, kvm=1 +EXC_REAL_END(h_virt_irq, 0xea0, 0x20) +EXC_VIRT_BEGIN(h_virt_irq, 0x4ea0, 0x20) + INT_HANDLER h_virt_irq, 0xea0, ool=1, virt=1, hsrr=EXC_HV, bitmask=IRQS_DISABLED, kvm=1 +EXC_VIRT_END(h_virt_irq, 0x4ea0, 0x20) +INT_KVM_HANDLER h_virt_irq, 0xea0, EXC_HV, PACA_EXGEN, 0 EXC_COMMON_ASYNC(h_virt_irq_common, 0xea0, do_IRQ) @@ -1770,17 +1655,25 @@ EXC_REAL_NONE(0xee0, 0x20) EXC_VIRT_NONE(0x4ee0, 0x20) -EXC_REAL_OOL_MASKABLE(performance_monitor, 0xf00, 0x20, IRQS_PMI_DISABLED) -EXC_VIRT_OOL_MASKABLE(performance_monitor, 0x4f00, 0x20, 0xf00, IRQS_PMI_DISABLED) -TRAMP_KVM(PACA_EXGEN, 0xf00) +EXC_REAL_BEGIN(performance_monitor, 0xf00, 0x20) + INT_HANDLER performance_monitor, 0xf00, ool=1, bitmask=IRQS_PMI_DISABLED, kvm=1 +EXC_REAL_END(performance_monitor, 0xf00, 0x20) +EXC_VIRT_BEGIN(performance_monitor, 0x4f00, 0x20) + INT_HANDLER performance_monitor, 0xf00, ool=1, virt=1, bitmask=IRQS_PMI_DISABLED +EXC_VIRT_END(performance_monitor, 0x4f00, 0x20) +INT_KVM_HANDLER performance_monitor, 0xf00, EXC_STD, PACA_EXGEN, 0 EXC_COMMON_ASYNC(performance_monitor_common, 0xf00, performance_monitor_exception) -EXC_REAL_OOL(altivec_unavailable, 0xf20, 0x20) -EXC_VIRT_OOL(altivec_unavailable, 0x4f20, 0x20, 0xf20) -TRAMP_KVM(PACA_EXGEN, 0xf20) +EXC_REAL_BEGIN(altivec_unavailable, 0xf20, 0x20) + INT_HANDLER altivec_unavailable, 0xf20, ool=1, kvm=1 +EXC_REAL_END(altivec_unavailable, 0xf20, 0x20) +EXC_VIRT_BEGIN(altivec_unavailable, 0x4f20, 0x20) + INT_HANDLER altivec_unavailable, 0xf20, ool=1, virt=1 +EXC_VIRT_END(altivec_unavailable, 0x4f20, 0x20) +INT_KVM_HANDLER altivec_unavailable, 0xf20, EXC_STD, PACA_EXGEN, 0 EXC_COMMON_BEGIN(altivec_unavailable_common) - EXCEPTION_COMMON(PACA_EXGEN, 0xf20) + INT_COMMON 0xf20, PACA_EXGEN, 1, 1, 0, 0, 0 #ifdef CONFIG_ALTIVEC BEGIN_FTR_SECTION beq 1f @@ -1813,11 +1706,15 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) b ret_from_except -EXC_REAL_OOL(vsx_unavailable, 0xf40, 0x20) -EXC_VIRT_OOL(vsx_unavailable, 0x4f40, 0x20, 0xf40) -TRAMP_KVM(PACA_EXGEN, 0xf40) +EXC_REAL_BEGIN(vsx_unavailable, 0xf40, 0x20) + INT_HANDLER vsx_unavailable, 0xf40, ool=1, kvm=1 +EXC_REAL_END(vsx_unavailable, 0xf40, 0x20) +EXC_VIRT_BEGIN(vsx_unavailable, 0x4f40, 0x20) + INT_HANDLER vsx_unavailable, 0xf40, ool=1, virt=1 +EXC_VIRT_END(vsx_unavailable, 0x4f40, 0x20) +INT_KVM_HANDLER vsx_unavailable, 0xf40, EXC_STD, PACA_EXGEN, 0 EXC_COMMON_BEGIN(vsx_unavailable_common) - EXCEPTION_COMMON(PACA_EXGEN, 0xf40) + INT_COMMON 0xf40, PACA_EXGEN, 1, 1, 0, 0, 0 #ifdef CONFIG_VSX BEGIN_FTR_SECTION beq 1f @@ -1849,15 +1746,23 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX) b ret_from_except -EXC_REAL_OOL(facility_unavailable, 0xf60, 0x20) -EXC_VIRT_OOL(facility_unavailable, 0x4f60, 0x20, 0xf60) -TRAMP_KVM(PACA_EXGEN, 0xf60) +EXC_REAL_BEGIN(facility_unavailable, 0xf60, 0x20) + INT_HANDLER facility_unavailable, 0xf60, ool=1, kvm=1 +EXC_REAL_END(facility_unavailable, 0xf60, 0x20) +EXC_VIRT_BEGIN(facility_unavailable, 0x4f60, 0x20) + INT_HANDLER facility_unavailable, 0xf60, ool=1, virt=1 +EXC_VIRT_END(facility_unavailable, 0x4f60, 0x20) +INT_KVM_HANDLER facility_unavailable, 0xf60, EXC_STD, PACA_EXGEN, 0 EXC_COMMON(facility_unavailable_common, 0xf60, facility_unavailable_exception) -EXC_REAL_OOL_HV(h_facility_unavailable, 0xf80, 0x20) -EXC_VIRT_OOL_HV(h_facility_unavailable, 0x4f80, 0x20, 0xf80) -TRAMP_KVM_HV(PACA_EXGEN, 0xf80) +EXC_REAL_BEGIN(h_facility_unavailable, 0xf80, 0x20) + INT_HANDLER h_facility_unavailable, 0xf80, ool=1, hsrr=EXC_HV, kvm=1 +EXC_REAL_END(h_facility_unavailable, 0xf80, 0x20) +EXC_VIRT_BEGIN(h_facility_unavailable, 0x4f80, 0x20) + INT_HANDLER h_facility_unavailable, 0xf80, ool=1, virt=1, hsrr=EXC_HV, kvm=1 +EXC_VIRT_END(h_facility_unavailable, 0x4f80, 0x20) +INT_KVM_HANDLER h_facility_unavailable, 0xf80, EXC_HV, PACA_EXGEN, 0 EXC_COMMON(h_facility_unavailable_common, 0xf80, facility_unavailable_exception) @@ -1874,9 +1779,11 @@ EXC_REAL_NONE(0x1100, 0x100) EXC_VIRT_NONE(0x5100, 0x100) #ifdef CONFIG_CBE_RAS -EXC_REAL_HV(cbe_system_error, 0x1200, 0x100) +EXC_REAL_BEGIN(cbe_system_error, 0x1200, 0x100) + INT_HANDLER cbe_system_error, 0x1200, ool=1, hsrr=EXC_HV, kvm=1 +EXC_REAL_END(cbe_system_error, 0x1200, 0x100) EXC_VIRT_NONE(0x5200, 0x100) -TRAMP_KVM_HV_SKIP(PACA_EXGEN, 0x1200) +INT_KVM_HANDLER cbe_system_error, 0x1200, EXC_HV, PACA_EXGEN, 1 EXC_COMMON(cbe_system_error_common, 0x1200, cbe_system_error_exception) #else /* CONFIG_CBE_RAS */ EXC_REAL_NONE(0x1200, 0x100) @@ -1884,37 +1791,43 @@ EXC_VIRT_NONE(0x5200, 0x100) #endif -EXC_REAL(instruction_breakpoint, 0x1300, 0x100) -EXC_VIRT(instruction_breakpoint, 0x5300, 0x100, 0x1300) -TRAMP_KVM_SKIP(PACA_EXGEN, 0x1300) +EXC_REAL_BEGIN(instruction_breakpoint, 0x1300, 0x100) + INT_HANDLER instruction_breakpoint, 0x1300, kvm=1 +EXC_REAL_END(instruction_breakpoint, 0x1300, 0x100) +EXC_VIRT_BEGIN(instruction_breakpoint, 0x5300, 0x100) + INT_HANDLER instruction_breakpoint, 0x1300, virt=1 +EXC_VIRT_END(instruction_breakpoint, 0x5300, 0x100) +INT_KVM_HANDLER instruction_breakpoint, 0x1300, EXC_STD, PACA_EXGEN, 1 EXC_COMMON(instruction_breakpoint_common, 0x1300, instruction_breakpoint_exception) + EXC_REAL_NONE(0x1400, 0x100) EXC_VIRT_NONE(0x5400, 0x100) EXC_REAL_BEGIN(denorm_exception_hv, 0x1500, 0x100) - EXCEPTION_PROLOG_0 PACA_EXGEN - EXCEPTION_PROLOG_1 EXC_HV, PACA_EXGEN, 0, 0x1500, 0, 0, 0 - + INT_HANDLER denorm_exception_hv, 0x1500, early=2, hsrr=EXC_HV #ifdef CONFIG_PPC_DENORMALISATION mfspr r10,SPRN_HSRR1 andis. r10,r10,(HSRR1_DENORM)@h /* denorm? */ bne+ denorm_assist #endif - - KVMTEST EXC_HV 0x1500 - EXCEPTION_PROLOG_2_REAL denorm_common, EXC_HV, 1 + KVMTEST denorm_exception_hv, EXC_HV 0x1500 + INT_SAVE_SRR_AND_JUMP denorm_common, EXC_HV, 1 EXC_REAL_END(denorm_exception_hv, 0x1500, 0x100) #ifdef CONFIG_PPC_DENORMALISATION EXC_VIRT_BEGIN(denorm_exception, 0x5500, 0x100) - b exc_real_0x1500_denorm_exception_hv + INT_HANDLER denorm_exception, 0x1500, 0, 2, 1, EXC_HV, PACA_EXGEN, 1, 0, 0, 0, 0 + mfspr r10,SPRN_HSRR1 + andis. r10,r10,(HSRR1_DENORM)@h /* denorm? */ + bne+ denorm_assist + INT_VIRT_SAVE_SRR_AND_JUMP denorm_common, EXC_HV EXC_VIRT_END(denorm_exception, 0x5500, 0x100) #else EXC_VIRT_NONE(0x5500, 0x100) #endif -TRAMP_KVM_HV(PACA_EXGEN, 0x1500) +INT_KVM_HANDLER denorm_exception_hv, 0x1500, EXC_HV, PACA_EXGEN, 0 #ifdef CONFIG_PPC_DENORMALISATION TRAMP_REAL_BEGIN(denorm_assist) @@ -1989,9 +1902,11 @@ EXC_COMMON(denorm_common, 0x1500, unknown_exception) #ifdef CONFIG_CBE_RAS -EXC_REAL_HV(cbe_maintenance, 0x1600, 0x100) +EXC_REAL_BEGIN(cbe_maintenance, 0x1600, 0x100) + INT_HANDLER cbe_maintenance, 0x1600, ool=1, hsrr=EXC_HV, kvm=1 +EXC_REAL_END(cbe_maintenance, 0x1600, 0x100) EXC_VIRT_NONE(0x5600, 0x100) -TRAMP_KVM_HV_SKIP(PACA_EXGEN, 0x1600) +INT_KVM_HANDLER cbe_maintenance, 0x1600, EXC_HV, PACA_EXGEN, 1 EXC_COMMON(cbe_maintenance_common, 0x1600, cbe_maintenance_exception) #else /* CONFIG_CBE_RAS */ EXC_REAL_NONE(0x1600, 0x100) @@ -1999,9 +1914,13 @@ EXC_VIRT_NONE(0x5600, 0x100) #endif -EXC_REAL(altivec_assist, 0x1700, 0x100) -EXC_VIRT(altivec_assist, 0x5700, 0x100, 0x1700) -TRAMP_KVM(PACA_EXGEN, 0x1700) +EXC_REAL_BEGIN(altivec_assist, 0x1700, 0x100) + INT_HANDLER altivec_assist, 0x1700, kvm=1 +EXC_REAL_END(altivec_assist, 0x1700, 0x100) +EXC_VIRT_BEGIN(altivec_assist, 0x5700, 0x100) + INT_HANDLER altivec_assist, 0x1700, virt=1 +EXC_VIRT_END(altivec_assist, 0x5700, 0x100) +INT_KVM_HANDLER altivec_assist, 0x1700, EXC_STD, PACA_EXGEN, 0 #ifdef CONFIG_ALTIVEC EXC_COMMON(altivec_assist_common, 0x1700, altivec_assist_exception) #else @@ -2010,15 +1929,18 @@ EXC_COMMON(altivec_assist_common, 0x1700, unknown_exception) #ifdef CONFIG_CBE_RAS -EXC_REAL_HV(cbe_thermal, 0x1800, 0x100) +EXC_REAL_BEGIN(cbe_thermal, 0x1800, 0x100) + INT_HANDLER cbe_thermal, 0x1800, ool=1, hsrr=EXC_HV, kvm=1 +EXC_REAL_END(cbe_thermal, 0x1800, 0x100) EXC_VIRT_NONE(0x5800, 0x100) -TRAMP_KVM_HV_SKIP(PACA_EXGEN, 0x1800) +INT_KVM_HANDLER cbe_thermal, 0x1800, EXC_HV, PACA_EXGEN, 1 EXC_COMMON(cbe_thermal_common, 0x1800, cbe_thermal_exception) #else /* CONFIG_CBE_RAS */ EXC_REAL_NONE(0x1800, 0x100) EXC_VIRT_NONE(0x5800, 0x100) #endif + #ifdef CONFIG_PPC_WATCHDOG #define MASKED_DEC_HANDLER_LABEL 3f @@ -2028,7 +1950,7 @@ 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_REAL soft_nmi_common, _H, 1 + INT_SAVE_SRR_AND_JUMP soft_nmi_common, _H, 1 /* * Branch to soft_nmi_interrupt using the emergency stack. The emergency @@ -2043,9 +1965,8 @@ EXC_COMMON_BEGIN(soft_nmi_common) mr r10,r1 ld r1,PACAEMERGSP(r13) subi r1,r1,INT_FRAME_SIZE - EXCEPTION_COMMON_STACK(PACA_EXGEN, 0x900) + INT_COMMON 0x900, PACA_EXGEN, 0, 1, 1, 0, 0 bl save_nvgprs - RECONCILE_IRQ_STATE(r10, r11) addi r3,r1,STACK_FRAME_OVERHEAD bl soft_nmi_interrupt b ret_from_except @@ -2302,6 +2223,35 @@ CLOSE_FIXED_SECTION(virt_trampolines); USE_TEXT_SECTION() +/* MSR[RI] should be clear because this uses SRR[01] */ +enable_machine_check: + mflr r0 + bcl 20,31,$+4 +0: mflr r3 + addi r3,r3,(1f - 0b) + mtspr SPRN_SRR0,r3 + mfmsr r3 + ori r3,r3,MSR_ME + mtspr SPRN_SRR1,r3 + RFI_TO_KERNEL +1: mtlr r0 + blr + +/* MSR[RI] should be clear because this uses SRR[01] */ +disable_machine_check: + mflr r0 + bcl 20,31,$+4 +0: mflr r3 + addi r3,r3,(1f - 0b) + mtspr SPRN_SRR0,r3 + mfmsr r3 + li r4,MSR_ME + andc r3,r3,r4 + mtspr SPRN_SRR1,r3 + RFI_TO_KERNEL +1: mtlr r0 + blr + /* * Hash table stuff */ @@ -2310,7 +2260,7 @@ do_hash_page: #ifdef CONFIG_PPC_BOOK3S_64 lis r0,(DSISR_BAD_FAULT_64S | DSISR_DABRMATCH | DSISR_KEYFAULT)@h ori r0,r0,DSISR_BAD_FAULT_64S@l - and. r0,r4,r0 /* weird error? */ + and. r0,r5,r0 /* weird error? */ bne- handle_page_fault /* if not, try to insert a HPTE */ ld r11, PACA_THREAD_INFO(r13) lwz r0,TI_PREEMPT(r11) /* If we're in an "NMI" */ @@ -2318,15 +2268,13 @@ do_hash_page: bne 77f /* then don't call hash_page now */ /* - * r3 contains the faulting address - * r4 msr - * r5 contains the trap number - * r6 contains dsisr + * r3 contains the trap number + * r4 contains the faulting address + * r5 contains dsisr + * r6 msr * * at return r3 = 0 for success, 1 for page fault, negative for error */ - mr r4,r12 - ld r6,_DSISR(r1) bl __hash_page /* build HPTE if possible */ cmpdi r3,0 /* see if __hash_page succeeded */ @@ -2336,16 +2284,15 @@ do_hash_page: /* Error */ blt- 13f - /* Reload DSISR into r4 for the DABR check below */ - ld r4,_DSISR(r1) + /* Reload DAR/DSISR into r4/r5 for the DABR check below */ + ld r4,_DAR(r1) + ld r5,_DSISR(r1) #endif /* CONFIG_PPC_BOOK3S_64 */ /* Here we have a page fault that hash_page can't handle. */ handle_page_fault: -11: andis. r0,r4,DSISR_DABRMATCH@h +11: andis. r0,r5,DSISR_DABRMATCH@h bne- handle_dabr_fault - ld r4,_DAR(r1) - ld r5,_DSISR(r1) addi r3,r1,STACK_FRAME_OVERHEAD bl do_page_fault cmpdi r3,0 @@ -2353,7 +2300,7 @@ handle_page_fault: bl save_nvgprs mr r5,r3 addi r3,r1,STACK_FRAME_OVERHEAD - lwz r4,_DAR(r1) + ld r4,_DAR(r1) bl bad_page_fault b ret_from_except @@ -2392,7 +2339,6 @@ handle_dabr_fault: * the access, or panic if there isn't a handler. */ 77: bl save_nvgprs - mr r4,r3 addi r3,r1,STACK_FRAME_OVERHEAD li r5,SIGSEGV bl bad_page_fault diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c index 4eab97292cc2..ed59855430b9 100644 --- a/arch/powerpc/kernel/fadump.c +++ b/arch/powerpc/kernel/fadump.c @@ -28,24 +28,22 @@ #include <asm/debugfs.h> #include <asm/page.h> #include <asm/prom.h> -#include <asm/rtas.h> #include <asm/fadump.h> +#include <asm/fadump-internal.h> #include <asm/setup.h> static struct fw_dump fw_dump; -static struct fadump_mem_struct fdm; -static const struct fadump_mem_struct *fdm_active; -#ifdef CONFIG_CMA -static struct cma *fadump_cma; -#endif +static void __init fadump_reserve_crash_area(u64 base); + +#ifndef CONFIG_PRESERVE_FA_DUMP static DEFINE_MUTEX(fadump_mutex); -struct fad_crash_memory_ranges *crash_memory_ranges; -int crash_memory_ranges_size; -int crash_mem_ranges; -int max_crash_mem_ranges; +struct fadump_mrange_info crash_mrange_info = { "crash", NULL, 0, 0, 0 }; +struct fadump_mrange_info reserved_mrange_info = { "reserved", NULL, 0, 0, 0 }; #ifdef CONFIG_CMA +static struct cma *fadump_cma; + /* * fadump_cma_init() - Initialize CMA area from a fadump reserved memory * @@ -107,84 +105,45 @@ static int __init fadump_cma_init(void) { return 1; } #endif /* CONFIG_CMA */ /* Scan the Firmware Assisted dump configuration details. */ -int __init early_init_dt_scan_fw_dump(unsigned long node, - const char *uname, int depth, void *data) +int __init early_init_dt_scan_fw_dump(unsigned long node, const char *uname, + int depth, void *data) { - const __be32 *sections; - int i, num_sections; - int size; - const __be32 *token; - - if (depth != 1 || strcmp(uname, "rtas") != 0) + if (depth != 1) return 0; - /* - * Check if Firmware Assisted dump is supported. if yes, check - * if dump has been initiated on last reboot. - */ - token = of_get_flat_dt_prop(node, "ibm,configure-kernel-dump", NULL); - if (!token) + if (strcmp(uname, "rtas") == 0) { + rtas_fadump_dt_scan(&fw_dump, node); return 1; + } - fw_dump.fadump_supported = 1; - fw_dump.ibm_configure_kernel_dump = be32_to_cpu(*token); - - /* - * The 'ibm,kernel-dump' rtas node is present only if there is - * dump data waiting for us. - */ - fdm_active = of_get_flat_dt_prop(node, "ibm,kernel-dump", NULL); - if (fdm_active) - fw_dump.dump_active = 1; - - /* Get the sizes required to store dump data for the firmware provided - * dump sections. - * For each dump section type supported, a 32bit cell which defines - * the ID of a supported section followed by two 32 bit cells which - * gives teh size of the section in bytes. - */ - sections = of_get_flat_dt_prop(node, "ibm,configure-kernel-dump-sizes", - &size); - - if (!sections) + if (strcmp(uname, "ibm,opal") == 0) { + opal_fadump_dt_scan(&fw_dump, node); return 1; - - num_sections = size / (3 * sizeof(u32)); - - for (i = 0; i < num_sections; i++, sections += 3) { - u32 type = (u32)of_read_number(sections, 1); - - switch (type) { - case FADUMP_CPU_STATE_DATA: - fw_dump.cpu_state_data_size = - of_read_ulong(§ions[1], 2); - break; - case FADUMP_HPTE_REGION: - fw_dump.hpte_region_size = - of_read_ulong(§ions[1], 2); - break; - } } - return 1; + return 0; } /* * If fadump is registered, check if the memory provided * falls within boot memory area and reserved memory area. */ -int is_fadump_memory_area(u64 addr, ulong size) +int is_fadump_memory_area(u64 addr, unsigned long size) { - u64 d_start = fw_dump.reserve_dump_area_start; - u64 d_end = d_start + fw_dump.reserve_dump_area_size; + u64 d_start, d_end; if (!fw_dump.dump_registered) return 0; + if (!size) + return 0; + + d_start = fw_dump.reserve_dump_area_start; + d_end = d_start + fw_dump.reserve_dump_area_size; if (((addr + size) > d_start) && (addr <= d_end)) return 1; - return (addr + size) > RMA_START && addr <= fw_dump.boot_memory_size; + return (addr <= fw_dump.boot_mem_top); } int should_fadump_crash(void) @@ -200,31 +159,29 @@ int is_fadump_active(void) } /* - * Returns 1, if there are no holes in boot memory area, - * 0 otherwise. + * Returns true, if there are no holes in memory area between d_start to d_end, + * false otherwise. */ -static int is_boot_memory_area_contiguous(void) +static bool is_fadump_mem_area_contiguous(u64 d_start, u64 d_end) { struct memblock_region *reg; - unsigned long tstart, tend; - unsigned long start_pfn = PHYS_PFN(RMA_START); - unsigned long end_pfn = PHYS_PFN(RMA_START + fw_dump.boot_memory_size); - unsigned int ret = 0; + bool ret = false; + u64 start, end; for_each_memblock(memory, reg) { - tstart = max(start_pfn, memblock_region_memory_base_pfn(reg)); - tend = min(end_pfn, memblock_region_memory_end_pfn(reg)); - if (tstart < tend) { - /* Memory hole from start_pfn to tstart */ - if (tstart > start_pfn) + start = max_t(u64, d_start, reg->base); + end = min_t(u64, d_end, (reg->base + reg->size)); + if (d_start < end) { + /* Memory hole from d_start to start */ + if (start > d_start) break; - if (tend == end_pfn) { - ret = 1; + if (end == d_end) { + ret = true; break; } - start_pfn = tend + 1; + d_start = end + 1; } } @@ -232,37 +189,45 @@ static int is_boot_memory_area_contiguous(void) } /* - * Returns true, if there are no holes in reserved memory area, + * Returns true, if there are no holes in boot memory area, * false otherwise. */ -static bool is_reserved_memory_area_contiguous(void) +bool is_fadump_boot_mem_contiguous(void) { - struct memblock_region *reg; - unsigned long start, end; - unsigned long d_start = fw_dump.reserve_dump_area_start; - unsigned long d_end = d_start + fw_dump.reserve_dump_area_size; - - for_each_memblock(memory, reg) { - start = max(d_start, (unsigned long)reg->base); - end = min(d_end, (unsigned long)(reg->base + reg->size)); - if (d_start < end) { - /* Memory hole from d_start to start */ - if (start > d_start) - break; + unsigned long d_start, d_end; + bool ret = false; + int i; - if (end == d_end) - return true; + for (i = 0; i < fw_dump.boot_mem_regs_cnt; i++) { + d_start = fw_dump.boot_mem_addr[i]; + d_end = d_start + fw_dump.boot_mem_sz[i]; - d_start = end + 1; - } + ret = is_fadump_mem_area_contiguous(d_start, d_end); + if (!ret) + break; } - return false; + return ret; +} + +/* + * Returns true, if there are no holes in reserved memory area, + * false otherwise. + */ +bool is_fadump_reserved_mem_contiguous(void) +{ + u64 d_start, d_end; + + d_start = fw_dump.reserve_dump_area_start; + d_end = d_start + fw_dump.reserve_dump_area_size; + return is_fadump_mem_area_contiguous(d_start, d_end); } /* Print firmware assisted dump configurations for debugging purpose. */ static void fadump_show_config(void) { + int i; + pr_debug("Support for firmware-assisted dump (fadump): %s\n", (fw_dump.fadump_supported ? "present" : "no support")); @@ -276,62 +241,13 @@ static void fadump_show_config(void) pr_debug("Dump section sizes:\n"); pr_debug(" CPU state data size: %lx\n", fw_dump.cpu_state_data_size); pr_debug(" HPTE region size : %lx\n", fw_dump.hpte_region_size); - pr_debug("Boot memory size : %lx\n", fw_dump.boot_memory_size); -} - -static unsigned long init_fadump_mem_struct(struct fadump_mem_struct *fdm, - unsigned long addr) -{ - if (!fdm) - return 0; - - memset(fdm, 0, sizeof(struct fadump_mem_struct)); - addr = addr & PAGE_MASK; - - fdm->header.dump_format_version = cpu_to_be32(0x00000001); - fdm->header.dump_num_sections = cpu_to_be16(3); - fdm->header.dump_status_flag = 0; - fdm->header.offset_first_dump_section = - cpu_to_be32((u32)offsetof(struct fadump_mem_struct, cpu_state_data)); - - /* - * Fields for disk dump option. - * We are not using disk dump option, hence set these fields to 0. - */ - fdm->header.dd_block_size = 0; - fdm->header.dd_block_offset = 0; - fdm->header.dd_num_blocks = 0; - fdm->header.dd_offset_disk_path = 0; - - /* set 0 to disable an automatic dump-reboot. */ - fdm->header.max_time_auto = 0; - - /* Kernel dump sections */ - /* cpu state data section. */ - fdm->cpu_state_data.request_flag = cpu_to_be32(FADUMP_REQUEST_FLAG); - fdm->cpu_state_data.source_data_type = cpu_to_be16(FADUMP_CPU_STATE_DATA); - fdm->cpu_state_data.source_address = 0; - fdm->cpu_state_data.source_len = cpu_to_be64(fw_dump.cpu_state_data_size); - fdm->cpu_state_data.destination_address = cpu_to_be64(addr); - addr += fw_dump.cpu_state_data_size; - - /* hpte region section */ - fdm->hpte_region.request_flag = cpu_to_be32(FADUMP_REQUEST_FLAG); - fdm->hpte_region.source_data_type = cpu_to_be16(FADUMP_HPTE_REGION); - fdm->hpte_region.source_address = 0; - fdm->hpte_region.source_len = cpu_to_be64(fw_dump.hpte_region_size); - fdm->hpte_region.destination_address = cpu_to_be64(addr); - addr += fw_dump.hpte_region_size; - - /* RMA region section */ - fdm->rmr_region.request_flag = cpu_to_be32(FADUMP_REQUEST_FLAG); - fdm->rmr_region.source_data_type = cpu_to_be16(FADUMP_REAL_MODE_REGION); - fdm->rmr_region.source_address = cpu_to_be64(RMA_START); - fdm->rmr_region.source_len = cpu_to_be64(fw_dump.boot_memory_size); - fdm->rmr_region.destination_address = cpu_to_be64(addr); - addr += fw_dump.boot_memory_size; - - return addr; + pr_debug(" Boot memory size : %lx\n", fw_dump.boot_memory_size); + pr_debug(" Boot memory top : %llx\n", fw_dump.boot_mem_top); + pr_debug("Boot memory regions cnt: %llx\n", fw_dump.boot_mem_regs_cnt); + for (i = 0; i < fw_dump.boot_mem_regs_cnt; i++) { + pr_debug("[%03d] base = %llx, size = %llx\n", i, + fw_dump.boot_mem_addr[i], fw_dump.boot_mem_sz[i]); + } } /** @@ -349,10 +265,10 @@ static unsigned long init_fadump_mem_struct(struct fadump_mem_struct *fdm, * that is required for a kernel to boot successfully. * */ -static inline unsigned long fadump_calculate_reserve_size(void) +static inline u64 fadump_calculate_reserve_size(void) { + u64 base, size, bootmem_min; int ret; - unsigned long long base, size; if (fw_dump.reserve_bootvar) pr_warn("'fadump_reserve_mem=' parameter is deprecated in favor of 'crashkernel=' parameter.\n"); @@ -402,7 +318,8 @@ static inline unsigned long fadump_calculate_reserve_size(void) if (memory_limit && size > memory_limit) size = memory_limit; - return (size > MIN_BOOT_MEM ? size : MIN_BOOT_MEM); + bootmem_min = fw_dump.ops->fadump_get_bootmem_min(); + return (size > bootmem_min ? size : bootmem_min); } /* @@ -423,57 +340,136 @@ static unsigned long get_fadump_area_size(void) size += sizeof(struct elf_phdr) * (memblock_num_regions(memory) + 2); size = PAGE_ALIGN(size); + + /* This is to hold kernel metadata on platforms that support it */ + size += (fw_dump.ops->fadump_get_metadata_size ? + fw_dump.ops->fadump_get_metadata_size() : 0); return size; } -static void __init fadump_reserve_crash_area(unsigned long base, - unsigned long size) +static int __init add_boot_mem_region(unsigned long rstart, + unsigned long rsize) +{ + int i = fw_dump.boot_mem_regs_cnt++; + + if (fw_dump.boot_mem_regs_cnt > FADUMP_MAX_MEM_REGS) { + fw_dump.boot_mem_regs_cnt = FADUMP_MAX_MEM_REGS; + return 0; + } + + pr_debug("Added boot memory range[%d] [%#016lx-%#016lx)\n", + i, rstart, (rstart + rsize)); + fw_dump.boot_mem_addr[i] = rstart; + fw_dump.boot_mem_sz[i] = rsize; + return 1; +} + +/* + * Firmware usually has a hard limit on the data it can copy per region. + * Honour that by splitting a memory range into multiple regions. + */ +static int __init add_boot_mem_regions(unsigned long mstart, + unsigned long msize) { + unsigned long rstart, rsize, max_size; + int ret = 1; + + rstart = mstart; + max_size = fw_dump.max_copy_size ? fw_dump.max_copy_size : msize; + while (msize) { + if (msize > max_size) + rsize = max_size; + else + rsize = msize; + + ret = add_boot_mem_region(rstart, rsize); + if (!ret) + break; + + msize -= rsize; + rstart += rsize; + } + + return ret; +} + +static int __init fadump_get_boot_mem_regions(void) +{ + unsigned long base, size, cur_size, hole_size, last_end; + unsigned long mem_size = fw_dump.boot_memory_size; struct memblock_region *reg; - unsigned long mstart, mend, msize; + int ret = 1; + + fw_dump.boot_mem_regs_cnt = 0; + last_end = 0; + hole_size = 0; + cur_size = 0; for_each_memblock(memory, reg) { - mstart = max_t(unsigned long, base, reg->base); - mend = reg->base + reg->size; - mend = min(base + size, mend); - - if (mstart < mend) { - msize = mend - mstart; - memblock_reserve(mstart, msize); - pr_info("Reserved %ldMB of memory at %#016lx for saving crash dump\n", - (msize >> 20), mstart); + base = reg->base; + size = reg->size; + hole_size += (base - last_end); + + if ((cur_size + size) >= mem_size) { + size = (mem_size - cur_size); + ret = add_boot_mem_regions(base, size); + break; } + + mem_size -= size; + cur_size += size; + ret = add_boot_mem_regions(base, size); + if (!ret) + break; + + last_end = base + size; } + fw_dump.boot_mem_top = PAGE_ALIGN(fw_dump.boot_memory_size + hole_size); + + return ret; } int __init fadump_reserve_mem(void) { - unsigned long base, size, memory_boundary; + u64 base, size, mem_boundary, bootmem_min, align = PAGE_SIZE; + bool is_memblock_bottom_up = memblock_bottom_up(); + int ret = 1; if (!fw_dump.fadump_enabled) return 0; if (!fw_dump.fadump_supported) { - printk(KERN_INFO "Firmware-assisted dump is not supported on" - " this hardware\n"); - fw_dump.fadump_enabled = 0; - return 0; + pr_info("Firmware-Assisted Dump is not supported on this hardware\n"); + goto error_out; } + /* * Initialize boot memory size * If dump is active then we have already calculated the size during * first kernel. */ - if (fdm_active) - fw_dump.boot_memory_size = be64_to_cpu(fdm_active->rmr_region.source_len); - else { - fw_dump.boot_memory_size = fadump_calculate_reserve_size(); + if (!fw_dump.dump_active) { + fw_dump.boot_memory_size = + PAGE_ALIGN(fadump_calculate_reserve_size()); #ifdef CONFIG_CMA - if (!fw_dump.nocma) + if (!fw_dump.nocma) { + align = FADUMP_CMA_ALIGNMENT; fw_dump.boot_memory_size = - ALIGN(fw_dump.boot_memory_size, - FADUMP_CMA_ALIGNMENT); + ALIGN(fw_dump.boot_memory_size, align); + } #endif + + bootmem_min = fw_dump.ops->fadump_get_bootmem_min(); + if (fw_dump.boot_memory_size < bootmem_min) { + pr_err("Can't enable fadump with boot memory size (0x%lx) less than 0x%llx\n", + fw_dump.boot_memory_size, bootmem_min); + goto error_out; + } + + if (!fadump_get_boot_mem_regions()) { + pr_err("Too many holes in boot memory area to enable fadump\n"); + goto error_out; + } } /* @@ -493,10 +489,13 @@ int __init fadump_reserve_mem(void) " dump, now %#016llx\n", memory_limit); } if (memory_limit) - memory_boundary = memory_limit; + mem_boundary = memory_limit; else - memory_boundary = memblock_end_of_DRAM(); + mem_boundary = memblock_end_of_DRAM(); + base = fw_dump.boot_mem_top; + size = get_fadump_area_size(); + fw_dump.reserve_dump_area_size = size; if (fw_dump.dump_active) { pr_info("Firmware-assisted dump is active.\n"); @@ -510,58 +509,55 @@ int __init fadump_reserve_mem(void) #endif /* * If last boot has crashed then reserve all the memory - * above boot_memory_size so that we don't touch it until + * above boot memory size so that we don't touch it until * dump is written to disk by userspace tool. This memory - * will be released for general use once the dump is saved. + * can be released for general use by invalidating fadump. */ - base = fw_dump.boot_memory_size; - size = memory_boundary - base; - fadump_reserve_crash_area(base, size); - - fw_dump.fadumphdr_addr = - be64_to_cpu(fdm_active->rmr_region.destination_address) + - be64_to_cpu(fdm_active->rmr_region.source_len); - pr_debug("fadumphdr_addr = %pa\n", &fw_dump.fadumphdr_addr); - fw_dump.reserve_dump_area_start = base; - fw_dump.reserve_dump_area_size = size; - } else { - size = get_fadump_area_size(); + fadump_reserve_crash_area(base); + pr_debug("fadumphdr_addr = %#016lx\n", fw_dump.fadumphdr_addr); + pr_debug("Reserve dump area start address: 0x%lx\n", + fw_dump.reserve_dump_area_start); + } else { /* * Reserve memory at an offset closer to bottom of the RAM to - * minimize the impact of memory hot-remove operation. We can't - * use memblock_find_in_range() here since it doesn't allocate - * from bottom to top. + * minimize the impact of memory hot-remove operation. */ - for (base = fw_dump.boot_memory_size; - base <= (memory_boundary - size); - base += size) { - if (memblock_is_region_memory(base, size) && - !memblock_is_region_reserved(base, size)) - break; + memblock_set_bottom_up(true); + base = memblock_find_in_range(base, mem_boundary, size, align); + + /* Restore the previous allocation mode */ + memblock_set_bottom_up(is_memblock_bottom_up); + + if (!base) { + pr_err("Failed to find memory chunk for reservation!\n"); + goto error_out; } - if ((base > (memory_boundary - size)) || - memblock_reserve(base, size)) { - pr_err("Failed to reserve memory\n"); - return 0; + fw_dump.reserve_dump_area_start = base; + + /* + * Calculate the kernel metadata address and register it with + * f/w if the platform supports. + */ + if (fw_dump.ops->fadump_setup_metadata && + (fw_dump.ops->fadump_setup_metadata(&fw_dump) < 0)) + goto error_out; + + if (memblock_reserve(base, size)) { + pr_err("Failed to reserve memory!\n"); + goto error_out; } - pr_info("Reserved %ldMB of memory at %ldMB for firmware-" - "assisted dump (System RAM: %ldMB)\n", - (unsigned long)(size >> 20), - (unsigned long)(base >> 20), - (unsigned long)(memblock_phys_mem_size() >> 20)); + pr_info("Reserved %lldMB of memory at %#016llx (System RAM: %lldMB)\n", + (size >> 20), base, (memblock_phys_mem_size() >> 20)); - fw_dump.reserve_dump_area_start = base; - fw_dump.reserve_dump_area_size = size; - return fadump_cma_init(); + ret = fadump_cma_init(); } - return 1; -} -unsigned long __init arch_reserved_kernel_pages(void) -{ - return memblock_reserved_size() / PAGE_SIZE; + return ret; +error_out: + fw_dump.fadump_enabled = 0; + return 0; } /* Look for fadump= cmdline option. */ @@ -596,61 +592,6 @@ static int __init early_fadump_reserve_mem(char *p) } early_param("fadump_reserve_mem", early_fadump_reserve_mem); -static int register_fw_dump(struct fadump_mem_struct *fdm) -{ - int rc, err; - unsigned int wait_time; - - pr_debug("Registering for firmware-assisted kernel dump...\n"); - - /* TODO: Add upper time limit for the delay */ - do { - rc = rtas_call(fw_dump.ibm_configure_kernel_dump, 3, 1, NULL, - FADUMP_REGISTER, fdm, - sizeof(struct fadump_mem_struct)); - - wait_time = rtas_busy_delay_time(rc); - if (wait_time) - mdelay(wait_time); - - } while (wait_time); - - err = -EIO; - switch (rc) { - default: - pr_err("Failed to register. Unknown Error(%d).\n", rc); - break; - case -1: - printk(KERN_ERR "Failed to register firmware-assisted kernel" - " dump. Hardware Error(%d).\n", rc); - break; - case -3: - if (!is_boot_memory_area_contiguous()) - pr_err("Can't have holes in boot memory area while registering fadump\n"); - else if (!is_reserved_memory_area_contiguous()) - pr_err("Can't have holes in reserved memory area while" - " registering fadump\n"); - - printk(KERN_ERR "Failed to register firmware-assisted kernel" - " dump. Parameter Error(%d).\n", rc); - err = -EINVAL; - break; - case -9: - printk(KERN_ERR "firmware-assisted kernel dump is already " - " registered."); - fw_dump.dump_registered = 1; - err = -EEXIST; - break; - case 0: - printk(KERN_INFO "firmware-assisted kernel dump registration" - " is successful\n"); - fw_dump.dump_registered = 1; - err = 0; - break; - } - return err; -} - void crash_fadump(struct pt_regs *regs, const char *str) { struct fadump_crash_info_header *fdh = NULL; @@ -693,71 +634,10 @@ void crash_fadump(struct pt_regs *regs, const char *str) fdh->online_mask = *cpu_online_mask; - /* Call ibm,os-term rtas call to trigger firmware assisted dump */ - rtas_os_term((char *)str); -} - -#define GPR_MASK 0xffffff0000000000 -static inline int fadump_gpr_index(u64 id) -{ - int i = -1; - char str[3]; - - if ((id & GPR_MASK) == REG_ID("GPR")) { - /* get the digits at the end */ - id &= ~GPR_MASK; - id >>= 24; - str[2] = '\0'; - str[1] = id & 0xff; - str[0] = (id >> 8) & 0xff; - sscanf(str, "%d", &i); - if (i > 31) - i = -1; - } - return i; -} - -static inline void fadump_set_regval(struct pt_regs *regs, u64 reg_id, - u64 reg_val) -{ - int i; - - i = fadump_gpr_index(reg_id); - if (i >= 0) - regs->gpr[i] = (unsigned long)reg_val; - else if (reg_id == REG_ID("NIA")) - regs->nip = (unsigned long)reg_val; - else if (reg_id == REG_ID("MSR")) - regs->msr = (unsigned long)reg_val; - else if (reg_id == REG_ID("CTR")) - regs->ctr = (unsigned long)reg_val; - else if (reg_id == REG_ID("LR")) - regs->link = (unsigned long)reg_val; - else if (reg_id == REG_ID("XER")) - regs->xer = (unsigned long)reg_val; - else if (reg_id == REG_ID("CR")) - regs->ccr = (unsigned long)reg_val; - else if (reg_id == REG_ID("DAR")) - regs->dar = (unsigned long)reg_val; - else if (reg_id == REG_ID("DSISR")) - regs->dsisr = (unsigned long)reg_val; -} - -static struct fadump_reg_entry* -fadump_read_registers(struct fadump_reg_entry *reg_entry, struct pt_regs *regs) -{ - memset(regs, 0, sizeof(struct pt_regs)); - - while (be64_to_cpu(reg_entry->reg_id) != REG_ID("CPUEND")) { - fadump_set_regval(regs, be64_to_cpu(reg_entry->reg_id), - be64_to_cpu(reg_entry->reg_value)); - reg_entry++; - } - reg_entry++; - return reg_entry; + fw_dump.ops->fadump_trigger(fdh, str); } -static u32 *fadump_regs_to_elf_notes(u32 *buf, struct pt_regs *regs) +u32 *fadump_regs_to_elf_notes(u32 *buf, struct pt_regs *regs) { struct elf_prstatus prstatus; @@ -772,7 +652,7 @@ static u32 *fadump_regs_to_elf_notes(u32 *buf, struct pt_regs *regs) return buf; } -static void fadump_update_elfcore_header(char *bufp) +void fadump_update_elfcore_header(char *bufp) { struct elfhdr *elf; struct elf_phdr *phdr; @@ -784,7 +664,7 @@ static void fadump_update_elfcore_header(char *bufp) phdr = (struct elf_phdr *)bufp; if (phdr->p_type == PT_NOTE) { - phdr->p_paddr = fw_dump.cpu_notes_buf; + phdr->p_paddr = __pa(fw_dump.cpu_notes_buf_vaddr); phdr->p_offset = phdr->p_paddr; phdr->p_filesz = fw_dump.cpu_notes_buf_size; phdr->p_memsz = fw_dump.cpu_notes_buf_size; @@ -792,228 +672,100 @@ static void fadump_update_elfcore_header(char *bufp) return; } -static void *fadump_cpu_notes_buf_alloc(unsigned long size) +static void *fadump_alloc_buffer(unsigned long size) { - void *vaddr; + unsigned long count, i; struct page *page; - unsigned long order, count, i; + void *vaddr; - order = get_order(size); - vaddr = (void *)__get_free_pages(GFP_KERNEL|__GFP_ZERO, order); + vaddr = alloc_pages_exact(size, GFP_KERNEL | __GFP_ZERO); if (!vaddr) return NULL; - count = 1 << order; + count = PAGE_ALIGN(size) / PAGE_SIZE; page = virt_to_page(vaddr); for (i = 0; i < count; i++) - SetPageReserved(page + i); + mark_page_reserved(page + i); return vaddr; } -static void fadump_cpu_notes_buf_free(unsigned long vaddr, unsigned long size) +static void fadump_free_buffer(unsigned long vaddr, unsigned long size) { - struct page *page; - unsigned long order, count, i; - - order = get_order(size); - count = 1 << order; - page = virt_to_page(vaddr); - for (i = 0; i < count; i++) - ClearPageReserved(page + i); - __free_pages(page, order); + free_reserved_area((void *)vaddr, (void *)(vaddr + size), -1, NULL); } -/* - * Read CPU state dump data and convert it into ELF notes. - * The CPU dump starts with magic number "REGSAVE". NumCpusOffset should be - * used to access the data to allow for additional fields to be added without - * affecting compatibility. Each list of registers for a CPU starts with - * "CPUSTRT" and ends with "CPUEND". Each register entry is of 16 bytes, - * 8 Byte ASCII identifier and 8 Byte register value. The register entry - * with identifier "CPUSTRT" and "CPUEND" contains 4 byte cpu id as part - * of register value. For more details refer to PAPR document. - * - * Only for the crashing cpu we ignore the CPU dump data and get exact - * state from fadump crash info structure populated by first kernel at the - * time of crash. - */ -static int __init fadump_build_cpu_notes(const struct fadump_mem_struct *fdm) +s32 fadump_setup_cpu_notes_buf(u32 num_cpus) { - struct fadump_reg_save_area_header *reg_header; - struct fadump_reg_entry *reg_entry; - struct fadump_crash_info_header *fdh = NULL; - void *vaddr; - unsigned long addr; - u32 num_cpus, *note_buf; - struct pt_regs regs; - int i, rc = 0, cpu = 0; - - if (!fdm->cpu_state_data.bytes_dumped) - return -EINVAL; - - addr = be64_to_cpu(fdm->cpu_state_data.destination_address); - vaddr = __va(addr); - - reg_header = vaddr; - if (be64_to_cpu(reg_header->magic_number) != REGSAVE_AREA_MAGIC) { - printk(KERN_ERR "Unable to read register save area.\n"); - return -ENOENT; - } - pr_debug("--------CPU State Data------------\n"); - pr_debug("Magic Number: %llx\n", be64_to_cpu(reg_header->magic_number)); - pr_debug("NumCpuOffset: %x\n", be32_to_cpu(reg_header->num_cpu_offset)); - - vaddr += be32_to_cpu(reg_header->num_cpu_offset); - num_cpus = be32_to_cpu(*((__be32 *)(vaddr))); - pr_debug("NumCpus : %u\n", num_cpus); - vaddr += sizeof(u32); - reg_entry = (struct fadump_reg_entry *)vaddr; - /* Allocate buffer to hold cpu crash notes. */ fw_dump.cpu_notes_buf_size = num_cpus * sizeof(note_buf_t); fw_dump.cpu_notes_buf_size = PAGE_ALIGN(fw_dump.cpu_notes_buf_size); - note_buf = fadump_cpu_notes_buf_alloc(fw_dump.cpu_notes_buf_size); - if (!note_buf) { - printk(KERN_ERR "Failed to allocate 0x%lx bytes for " - "cpu notes buffer\n", fw_dump.cpu_notes_buf_size); + fw_dump.cpu_notes_buf_vaddr = + (unsigned long)fadump_alloc_buffer(fw_dump.cpu_notes_buf_size); + if (!fw_dump.cpu_notes_buf_vaddr) { + pr_err("Failed to allocate %ld bytes for CPU notes buffer\n", + fw_dump.cpu_notes_buf_size); return -ENOMEM; } - fw_dump.cpu_notes_buf = __pa(note_buf); - - pr_debug("Allocated buffer for cpu notes of size %ld at %p\n", - (num_cpus * sizeof(note_buf_t)), note_buf); - if (fw_dump.fadumphdr_addr) - fdh = __va(fw_dump.fadumphdr_addr); - - for (i = 0; i < num_cpus; i++) { - if (be64_to_cpu(reg_entry->reg_id) != REG_ID("CPUSTRT")) { - printk(KERN_ERR "Unable to read CPU state data\n"); - rc = -ENOENT; - goto error_out; - } - /* Lower 4 bytes of reg_value contains logical cpu id */ - cpu = be64_to_cpu(reg_entry->reg_value) & FADUMP_CPU_ID_MASK; - if (fdh && !cpumask_test_cpu(cpu, &fdh->online_mask)) { - SKIP_TO_NEXT_CPU(reg_entry); - continue; - } - pr_debug("Reading register data for cpu %d...\n", cpu); - if (fdh && fdh->crashing_cpu == cpu) { - regs = fdh->regs; - note_buf = fadump_regs_to_elf_notes(note_buf, ®s); - SKIP_TO_NEXT_CPU(reg_entry); - } else { - reg_entry++; - reg_entry = fadump_read_registers(reg_entry, ®s); - note_buf = fadump_regs_to_elf_notes(note_buf, ®s); - } - } - final_note(note_buf); - - if (fdh) { - pr_debug("Updating elfcore header (%llx) with cpu notes\n", - fdh->elfcorehdr_addr); - fadump_update_elfcore_header((char *)__va(fdh->elfcorehdr_addr)); - } + pr_debug("Allocated buffer for cpu notes of size %ld at 0x%lx\n", + fw_dump.cpu_notes_buf_size, + fw_dump.cpu_notes_buf_vaddr); return 0; - -error_out: - fadump_cpu_notes_buf_free((unsigned long)__va(fw_dump.cpu_notes_buf), - fw_dump.cpu_notes_buf_size); - fw_dump.cpu_notes_buf = 0; - fw_dump.cpu_notes_buf_size = 0; - return rc; - } -/* - * Validate and process the dump data stored by firmware before exporting - * it through '/proc/vmcore'. - */ -static int __init process_fadump(const struct fadump_mem_struct *fdm_active) +void fadump_free_cpu_notes_buf(void) { - struct fadump_crash_info_header *fdh; - int rc = 0; - - if (!fdm_active || !fw_dump.fadumphdr_addr) - return -EINVAL; - - /* Check if the dump data is valid. */ - if ((be16_to_cpu(fdm_active->header.dump_status_flag) == FADUMP_ERROR_FLAG) || - (fdm_active->cpu_state_data.error_flags != 0) || - (fdm_active->rmr_region.error_flags != 0)) { - printk(KERN_ERR "Dump taken by platform is not valid\n"); - return -EINVAL; - } - if ((fdm_active->rmr_region.bytes_dumped != - fdm_active->rmr_region.source_len) || - !fdm_active->cpu_state_data.bytes_dumped) { - printk(KERN_ERR "Dump taken by platform is incomplete\n"); - return -EINVAL; - } - - /* Validate the fadump crash info header */ - fdh = __va(fw_dump.fadumphdr_addr); - if (fdh->magic_number != FADUMP_CRASH_INFO_MAGIC) { - printk(KERN_ERR "Crash info header is not valid.\n"); - return -EINVAL; - } - - rc = fadump_build_cpu_notes(fdm_active); - if (rc) - return rc; - - /* - * We are done validating dump info and elfcore header is now ready - * to be exported. set elfcorehdr_addr so that vmcore module will - * export the elfcore header through '/proc/vmcore'. - */ - elfcorehdr_addr = fdh->elfcorehdr_addr; + if (!fw_dump.cpu_notes_buf_vaddr) + return; - return 0; + fadump_free_buffer(fw_dump.cpu_notes_buf_vaddr, + fw_dump.cpu_notes_buf_size); + fw_dump.cpu_notes_buf_vaddr = 0; + fw_dump.cpu_notes_buf_size = 0; } -static void free_crash_memory_ranges(void) +static void fadump_free_mem_ranges(struct fadump_mrange_info *mrange_info) { - kfree(crash_memory_ranges); - crash_memory_ranges = NULL; - crash_memory_ranges_size = 0; - max_crash_mem_ranges = 0; + kfree(mrange_info->mem_ranges); + mrange_info->mem_ranges = NULL; + mrange_info->mem_ranges_sz = 0; + mrange_info->max_mem_ranges = 0; } /* - * Allocate or reallocate crash memory ranges array in incremental units + * Allocate or reallocate mem_ranges array in incremental units * of PAGE_SIZE. */ -static int allocate_crash_memory_ranges(void) +static int fadump_alloc_mem_ranges(struct fadump_mrange_info *mrange_info) { - struct fad_crash_memory_ranges *new_array; + struct fadump_memory_range *new_array; u64 new_size; - new_size = crash_memory_ranges_size + PAGE_SIZE; - pr_debug("Allocating %llu bytes of memory for crash memory ranges\n", - new_size); + new_size = mrange_info->mem_ranges_sz + PAGE_SIZE; + pr_debug("Allocating %llu bytes of memory for %s memory ranges\n", + new_size, mrange_info->name); - new_array = krealloc(crash_memory_ranges, new_size, GFP_KERNEL); + new_array = krealloc(mrange_info->mem_ranges, new_size, GFP_KERNEL); if (new_array == NULL) { - pr_err("Insufficient memory for setting up crash memory ranges\n"); - free_crash_memory_ranges(); + pr_err("Insufficient memory for setting up %s memory ranges\n", + mrange_info->name); + fadump_free_mem_ranges(mrange_info); return -ENOMEM; } - crash_memory_ranges = new_array; - crash_memory_ranges_size = new_size; - max_crash_mem_ranges = (new_size / - sizeof(struct fad_crash_memory_ranges)); + mrange_info->mem_ranges = new_array; + mrange_info->mem_ranges_sz = new_size; + mrange_info->max_mem_ranges = (new_size / + sizeof(struct fadump_memory_range)); return 0; } -static inline int fadump_add_crash_memory(unsigned long long base, - unsigned long long end) +static inline int fadump_add_mem_range(struct fadump_mrange_info *mrange_info, + u64 base, u64 end) { - u64 start, size; + struct fadump_memory_range *mem_ranges = mrange_info->mem_ranges; bool is_adjacent = false; + u64 start, size; if (base == end) return 0; @@ -1022,38 +774,41 @@ static inline int fadump_add_crash_memory(unsigned long long base, * Fold adjacent memory ranges to bring down the memory ranges/ * PT_LOAD segments count. */ - if (crash_mem_ranges) { - start = crash_memory_ranges[crash_mem_ranges - 1].base; - size = crash_memory_ranges[crash_mem_ranges - 1].size; + if (mrange_info->mem_range_cnt) { + start = mem_ranges[mrange_info->mem_range_cnt - 1].base; + size = mem_ranges[mrange_info->mem_range_cnt - 1].size; if ((start + size) == base) is_adjacent = true; } if (!is_adjacent) { /* resize the array on reaching the limit */ - if (crash_mem_ranges == max_crash_mem_ranges) { + if (mrange_info->mem_range_cnt == mrange_info->max_mem_ranges) { int ret; - ret = allocate_crash_memory_ranges(); + ret = fadump_alloc_mem_ranges(mrange_info); if (ret) return ret; + + /* Update to the new resized array */ + mem_ranges = mrange_info->mem_ranges; } start = base; - crash_memory_ranges[crash_mem_ranges].base = start; - crash_mem_ranges++; + mem_ranges[mrange_info->mem_range_cnt].base = start; + mrange_info->mem_range_cnt++; } - crash_memory_ranges[crash_mem_ranges - 1].size = (end - start); - pr_debug("crash_memory_range[%d] [%#016llx-%#016llx], %#llx bytes\n", - (crash_mem_ranges - 1), start, end - 1, (end - start)); + mem_ranges[mrange_info->mem_range_cnt - 1].size = (end - start); + pr_debug("%s_memory_range[%d] [%#016llx-%#016llx], %#llx bytes\n", + mrange_info->name, (mrange_info->mem_range_cnt - 1), + start, end - 1, (end - start)); return 0; } -static int fadump_exclude_reserved_area(unsigned long long start, - unsigned long long end) +static int fadump_exclude_reserved_area(u64 start, u64 end) { - unsigned long long ra_start, ra_end; + u64 ra_start, ra_end; int ret = 0; ra_start = fw_dump.reserve_dump_area_start; @@ -1061,18 +816,22 @@ static int fadump_exclude_reserved_area(unsigned long long start, if ((ra_start < end) && (ra_end > start)) { if ((start < ra_start) && (end > ra_end)) { - ret = fadump_add_crash_memory(start, ra_start); + ret = fadump_add_mem_range(&crash_mrange_info, + start, ra_start); if (ret) return ret; - ret = fadump_add_crash_memory(ra_end, end); + ret = fadump_add_mem_range(&crash_mrange_info, + ra_end, end); } else if (start < ra_start) { - ret = fadump_add_crash_memory(start, ra_start); + ret = fadump_add_mem_range(&crash_mrange_info, + start, ra_start); } else if (ra_end < end) { - ret = fadump_add_crash_memory(ra_end, end); + ret = fadump_add_mem_range(&crash_mrange_info, + ra_end, end); } } else - ret = fadump_add_crash_memory(start, end); + ret = fadump_add_mem_range(&crash_mrange_info, start, end); return ret; } @@ -1117,36 +876,36 @@ static int fadump_init_elfcore_header(char *bufp) static int fadump_setup_crash_memory_ranges(void) { struct memblock_region *reg; - unsigned long long start, end; - int ret; + u64 start, end; + int i, ret; pr_debug("Setup crash memory ranges.\n"); - crash_mem_ranges = 0; + crash_mrange_info.mem_range_cnt = 0; /* - * add the first memory chunk (RMA_START through boot_memory_size) as - * a separate memory chunk. The reason is, at the time crash firmware - * will move the content of this memory chunk to different location - * specified during fadump registration. We need to create a separate - * program header for this chunk with the correct offset. + * Boot memory region(s) registered with firmware are moved to + * different location at the time of crash. Create separate program + * header(s) for this memory chunk(s) with the correct offset. */ - ret = fadump_add_crash_memory(RMA_START, fw_dump.boot_memory_size); - if (ret) - return ret; + for (i = 0; i < fw_dump.boot_mem_regs_cnt; i++) { + start = fw_dump.boot_mem_addr[i]; + end = start + fw_dump.boot_mem_sz[i]; + ret = fadump_add_mem_range(&crash_mrange_info, start, end); + if (ret) + return ret; + } for_each_memblock(memory, reg) { - start = (unsigned long long)reg->base; - end = start + (unsigned long long)reg->size; + start = (u64)reg->base; + end = start + (u64)reg->size; /* - * skip the first memory chunk that is already added (RMA_START - * through boot_memory_size). This logic needs a relook if and - * when RMA_START changes to a non-zero value. + * skip the memory chunk that is already added + * (0 through boot_memory_top). */ - BUILD_BUG_ON(RMA_START != 0); - if (start < fw_dump.boot_memory_size) { - if (end > fw_dump.boot_memory_size) - start = fw_dump.boot_memory_size; + if (start < fw_dump.boot_mem_top) { + if (end > fw_dump.boot_mem_top) + start = fw_dump.boot_mem_top; else continue; } @@ -1167,17 +926,35 @@ static int fadump_setup_crash_memory_ranges(void) */ static inline unsigned long fadump_relocate(unsigned long paddr) { - if (paddr > RMA_START && paddr < fw_dump.boot_memory_size) - return be64_to_cpu(fdm.rmr_region.destination_address) + paddr; - else - return paddr; + unsigned long raddr, rstart, rend, rlast, hole_size; + int i; + + hole_size = 0; + rlast = 0; + raddr = paddr; + for (i = 0; i < fw_dump.boot_mem_regs_cnt; i++) { + rstart = fw_dump.boot_mem_addr[i]; + rend = rstart + fw_dump.boot_mem_sz[i]; + hole_size += (rstart - rlast); + + if (paddr >= rstart && paddr < rend) { + raddr += fw_dump.boot_mem_dest_addr - hole_size; + break; + } + + rlast = rend; + } + + pr_debug("vmcoreinfo: paddr = 0x%lx, raddr = 0x%lx\n", paddr, raddr); + return raddr; } static int fadump_create_elfcore_headers(char *bufp) { - struct elfhdr *elf; + unsigned long long raddr, offset; struct elf_phdr *phdr; - int i; + struct elfhdr *elf; + int i, j; fadump_init_elfcore_header(bufp); elf = (struct elfhdr *)bufp; @@ -1220,12 +997,14 @@ static int fadump_create_elfcore_headers(char *bufp) (elf->e_phnum)++; /* setup PT_LOAD sections. */ - - for (i = 0; i < crash_mem_ranges; i++) { - unsigned long long mbase, msize; - mbase = crash_memory_ranges[i].base; - msize = crash_memory_ranges[i].size; - + j = 0; + offset = 0; + raddr = fw_dump.boot_mem_addr[0]; + for (i = 0; i < crash_mrange_info.mem_range_cnt; i++) { + u64 mbase, msize; + + mbase = crash_mrange_info.mem_ranges[i].base; + msize = crash_mrange_info.mem_ranges[i].size; if (!msize) continue; @@ -1235,13 +1014,17 @@ static int fadump_create_elfcore_headers(char *bufp) phdr->p_flags = PF_R|PF_W|PF_X; phdr->p_offset = mbase; - if (mbase == RMA_START) { + if (mbase == raddr) { /* - * The entire RMA region will be moved by firmware - * to the specified destination_address. Hence set - * the correct offset. + * The entire real memory region will be moved by + * firmware to the specified destination_address. + * Hence set the correct offset. */ - phdr->p_offset = be64_to_cpu(fdm.rmr_region.destination_address); + phdr->p_offset = fw_dump.boot_mem_dest_addr + offset; + if (j < (fw_dump.boot_mem_regs_cnt - 1)) { + offset += fw_dump.boot_mem_sz[j]; + raddr = fw_dump.boot_mem_addr[++j]; + } } phdr->p_paddr = mbase; @@ -1263,7 +1046,6 @@ static unsigned long init_fadump_header(unsigned long addr) if (!addr) return 0; - fw_dump.fadumphdr_addr = addr; fdh = __va(addr); addr += sizeof(struct fadump_crash_info_header); @@ -1271,7 +1053,7 @@ static unsigned long init_fadump_header(unsigned long addr) fdh->magic_number = FADUMP_CRASH_INFO_MAGIC; fdh->elfcorehdr_addr = addr; /* We will set the crashing cpu id in crash_fadump() during crash. */ - fdh->crashing_cpu = CPU_UNKNOWN; + fdh->crashing_cpu = FADUMP_CPU_UNKNOWN; return addr; } @@ -1293,7 +1075,8 @@ static int register_fadump(void) if (ret) return ret; - addr = be64_to_cpu(fdm.rmr_region.destination_address) + be64_to_cpu(fdm.rmr_region.source_len); + addr = fw_dump.fadumphdr_addr; + /* Initialize fadump crash info header. */ addr = init_fadump_header(addr); vaddr = __va(addr); @@ -1302,74 +1085,27 @@ static int register_fadump(void) fadump_create_elfcore_headers(vaddr); /* register the future kernel dump with firmware. */ - return register_fw_dump(&fdm); -} - -static int fadump_unregister_dump(struct fadump_mem_struct *fdm) -{ - int rc = 0; - unsigned int wait_time; - - pr_debug("Un-register firmware-assisted dump\n"); - - /* TODO: Add upper time limit for the delay */ - do { - rc = rtas_call(fw_dump.ibm_configure_kernel_dump, 3, 1, NULL, - FADUMP_UNREGISTER, fdm, - sizeof(struct fadump_mem_struct)); - - wait_time = rtas_busy_delay_time(rc); - if (wait_time) - mdelay(wait_time); - } while (wait_time); - - if (rc) { - printk(KERN_ERR "Failed to un-register firmware-assisted dump." - " unexpected error(%d).\n", rc); - return rc; - } - fw_dump.dump_registered = 0; - return 0; -} - -static int fadump_invalidate_dump(const struct fadump_mem_struct *fdm) -{ - int rc = 0; - unsigned int wait_time; - - pr_debug("Invalidating firmware-assisted dump registration\n"); - - /* TODO: Add upper time limit for the delay */ - do { - rc = rtas_call(fw_dump.ibm_configure_kernel_dump, 3, 1, NULL, - FADUMP_INVALIDATE, fdm, - sizeof(struct fadump_mem_struct)); - - wait_time = rtas_busy_delay_time(rc); - if (wait_time) - mdelay(wait_time); - } while (wait_time); - - if (rc) { - pr_err("Failed to invalidate firmware-assisted dump registration. Unexpected error (%d).\n", rc); - return rc; - } - fw_dump.dump_active = 0; - fdm_active = NULL; - return 0; + pr_debug("Registering for firmware-assisted kernel dump...\n"); + return fw_dump.ops->fadump_register(&fw_dump); } void fadump_cleanup(void) { + if (!fw_dump.fadump_supported) + return; + /* Invalidate the registration only if dump is active. */ if (fw_dump.dump_active) { - /* pass the same memory dump structure provided by platform */ - fadump_invalidate_dump(fdm_active); + pr_debug("Invalidating firmware-assisted dump registration\n"); + fw_dump.ops->fadump_invalidate(&fw_dump); } else if (fw_dump.dump_registered) { /* Un-register Firmware-assisted dump if it was registered. */ - fadump_unregister_dump(&fdm); - free_crash_memory_ranges(); + fw_dump.ops->fadump_unregister(&fw_dump); + fadump_free_mem_ranges(&crash_mrange_info); } + + if (fw_dump.ops->fadump_cleanup) + fw_dump.ops->fadump_cleanup(&fw_dump); } static void fadump_free_reserved_memory(unsigned long start_pfn, @@ -1394,90 +1130,197 @@ static void fadump_free_reserved_memory(unsigned long start_pfn, /* * Skip memory holes and free memory that was actually reserved. */ -static void fadump_release_reserved_area(unsigned long start, unsigned long end) +static void fadump_release_reserved_area(u64 start, u64 end) { + u64 tstart, tend, spfn, epfn; struct memblock_region *reg; - unsigned long tstart, tend; - unsigned long start_pfn = PHYS_PFN(start); - unsigned long end_pfn = PHYS_PFN(end); + spfn = PHYS_PFN(start); + epfn = PHYS_PFN(end); for_each_memblock(memory, reg) { - tstart = max(start_pfn, memblock_region_memory_base_pfn(reg)); - tend = min(end_pfn, memblock_region_memory_end_pfn(reg)); + tstart = max_t(u64, spfn, memblock_region_memory_base_pfn(reg)); + tend = min_t(u64, epfn, memblock_region_memory_end_pfn(reg)); if (tstart < tend) { fadump_free_reserved_memory(tstart, tend); - if (tend == end_pfn) + if (tend == epfn) break; - start_pfn = tend + 1; + spfn = tend; } } } /* - * Release the memory that was reserved in early boot to preserve the memory - * contents. The released memory will be available for general use. + * Sort the mem ranges in-place and merge adjacent ranges + * to minimize the memory ranges count. */ -static void fadump_release_memory(unsigned long begin, unsigned long end) +static void sort_and_merge_mem_ranges(struct fadump_mrange_info *mrange_info) { - unsigned long ra_start, ra_end; + struct fadump_memory_range *mem_ranges; + struct fadump_memory_range tmp_range; + u64 base, size; + int i, j, idx; + + if (!reserved_mrange_info.mem_range_cnt) + return; + + /* Sort the memory ranges */ + mem_ranges = mrange_info->mem_ranges; + for (i = 0; i < mrange_info->mem_range_cnt; i++) { + idx = i; + for (j = (i + 1); j < mrange_info->mem_range_cnt; j++) { + if (mem_ranges[idx].base > mem_ranges[j].base) + idx = j; + } + if (idx != i) { + tmp_range = mem_ranges[idx]; + mem_ranges[idx] = mem_ranges[i]; + mem_ranges[i] = tmp_range; + } + } + + /* Merge adjacent reserved ranges */ + idx = 0; + for (i = 1; i < mrange_info->mem_range_cnt; i++) { + base = mem_ranges[i-1].base; + size = mem_ranges[i-1].size; + if (mem_ranges[i].base == (base + size)) + mem_ranges[idx].size += mem_ranges[i].size; + else { + idx++; + if (i == idx) + continue; + + mem_ranges[idx] = mem_ranges[i]; + } + } + mrange_info->mem_range_cnt = idx + 1; +} + +/* + * Scan reserved-ranges to consider them while reserving/releasing + * memory for FADump. + */ +static inline int fadump_scan_reserved_mem_ranges(void) +{ + struct device_node *root; + const __be32 *prop; + int len, ret = -1; + unsigned long i; + + root = of_find_node_by_path("/"); + if (!root) + return ret; + + prop = of_get_property(root, "reserved-ranges", &len); + if (!prop) + return ret; + + /* + * Each reserved range is an (address,size) pair, 2 cells each, + * totalling 4 cells per range. + */ + for (i = 0; i < len / (sizeof(*prop) * 4); i++) { + u64 base, size; + + base = of_read_number(prop + (i * 4) + 0, 2); + size = of_read_number(prop + (i * 4) + 2, 2); + + if (size) { + ret = fadump_add_mem_range(&reserved_mrange_info, + base, base + size); + if (ret < 0) { + pr_warn("some reserved ranges are ignored!\n"); + break; + } + } + } + + return ret; +} + +/* + * Release the memory that was reserved during early boot to preserve the + * crash'ed kernel's memory contents except reserved dump area (permanent + * reservation) and reserved ranges used by F/W. The released memory will + * be available for general use. + */ +static void fadump_release_memory(u64 begin, u64 end) +{ + u64 ra_start, ra_end, tstart; + int i, ret; + + fadump_scan_reserved_mem_ranges(); ra_start = fw_dump.reserve_dump_area_start; ra_end = ra_start + fw_dump.reserve_dump_area_size; /* - * exclude the dump reserve area. Will reuse it for next - * fadump registration. + * Add reserved dump area to reserved ranges list + * and exclude all these ranges while releasing memory. */ - if (begin < ra_end && end > ra_start) { - if (begin < ra_start) - fadump_release_reserved_area(begin, ra_start); - if (end > ra_end) - fadump_release_reserved_area(ra_end, end); - } else - fadump_release_reserved_area(begin, end); + ret = fadump_add_mem_range(&reserved_mrange_info, ra_start, ra_end); + if (ret != 0) { + /* + * Not enough memory to setup reserved ranges but the system is + * running shortage of memory. So, release all the memory except + * Reserved dump area (reused for next fadump registration). + */ + if (begin < ra_end && end > ra_start) { + if (begin < ra_start) + fadump_release_reserved_area(begin, ra_start); + if (end > ra_end) + fadump_release_reserved_area(ra_end, end); + } else + fadump_release_reserved_area(begin, end); + + return; + } + + /* Get the reserved ranges list in order first. */ + sort_and_merge_mem_ranges(&reserved_mrange_info); + + /* Exclude reserved ranges and release remaining memory */ + tstart = begin; + for (i = 0; i < reserved_mrange_info.mem_range_cnt; i++) { + ra_start = reserved_mrange_info.mem_ranges[i].base; + ra_end = ra_start + reserved_mrange_info.mem_ranges[i].size; + + if (tstart >= ra_end) + continue; + + if (tstart < ra_start) + fadump_release_reserved_area(tstart, ra_start); + tstart = ra_end; + } + + if (tstart < end) + fadump_release_reserved_area(tstart, end); } static void fadump_invalidate_release_mem(void) { - unsigned long reserved_area_start, reserved_area_end; - unsigned long destination_address; - mutex_lock(&fadump_mutex); if (!fw_dump.dump_active) { mutex_unlock(&fadump_mutex); return; } - destination_address = be64_to_cpu(fdm_active->cpu_state_data.destination_address); fadump_cleanup(); mutex_unlock(&fadump_mutex); + fadump_release_memory(fw_dump.boot_mem_top, memblock_end_of_DRAM()); + fadump_free_cpu_notes_buf(); + /* - * Save the current reserved memory bounds we will require them - * later for releasing the memory for general use. - */ - reserved_area_start = fw_dump.reserve_dump_area_start; - reserved_area_end = reserved_area_start + - fw_dump.reserve_dump_area_size; - /* - * Setup reserve_dump_area_start and its size so that we can - * reuse this reserved memory for Re-registration. + * Setup kernel metadata and initialize the kernel dump + * memory structure for FADump re-registration. */ - fw_dump.reserve_dump_area_start = destination_address; - fw_dump.reserve_dump_area_size = get_fadump_area_size(); - - fadump_release_memory(reserved_area_start, reserved_area_end); - if (fw_dump.cpu_notes_buf) { - fadump_cpu_notes_buf_free( - (unsigned long)__va(fw_dump.cpu_notes_buf), - fw_dump.cpu_notes_buf_size); - fw_dump.cpu_notes_buf = 0; - fw_dump.cpu_notes_buf_size = 0; - } - /* Initialize the kernel dump memory structure for FAD registration. */ - init_fadump_mem_struct(&fdm, fw_dump.reserve_dump_area_start); + if (fw_dump.ops->fadump_setup_metadata && + (fw_dump.ops->fadump_setup_metadata(&fw_dump) < 0)) + pr_warn("Failed to setup kernel metadata!\n"); + fw_dump.ops->fadump_init_mem_struct(&fw_dump); } static ssize_t fadump_release_memory_store(struct kobject *kobj, @@ -1528,7 +1371,7 @@ static ssize_t fadump_register_store(struct kobject *kobj, int ret = 0; int input = -1; - if (!fw_dump.fadump_enabled || fdm_active) + if (!fw_dump.fadump_enabled || fw_dump.dump_active) return -EPERM; if (kstrtoint(buf, 0, &input)) @@ -1541,13 +1384,15 @@ static ssize_t fadump_register_store(struct kobject *kobj, if (fw_dump.dump_registered == 0) { goto unlock_out; } + /* Un-register Firmware-assisted dump */ - fadump_unregister_dump(&fdm); + pr_debug("Un-register firmware-assisted dump\n"); + fw_dump.ops->fadump_unregister(&fw_dump); break; case 1: if (fw_dump.dump_registered == 1) { /* Un-register Firmware-assisted dump */ - fadump_unregister_dump(&fdm); + fw_dump.ops->fadump_unregister(&fw_dump); } /* Register Firmware-assisted dump */ ret = register_fadump(); @@ -1564,62 +1409,12 @@ unlock_out: static int fadump_region_show(struct seq_file *m, void *private) { - const struct fadump_mem_struct *fdm_ptr; - if (!fw_dump.fadump_enabled) return 0; mutex_lock(&fadump_mutex); - if (fdm_active) - fdm_ptr = fdm_active; - else { - mutex_unlock(&fadump_mutex); - fdm_ptr = &fdm; - } - - seq_printf(m, - "CPU : [%#016llx-%#016llx] %#llx bytes, " - "Dumped: %#llx\n", - be64_to_cpu(fdm_ptr->cpu_state_data.destination_address), - be64_to_cpu(fdm_ptr->cpu_state_data.destination_address) + - be64_to_cpu(fdm_ptr->cpu_state_data.source_len) - 1, - be64_to_cpu(fdm_ptr->cpu_state_data.source_len), - be64_to_cpu(fdm_ptr->cpu_state_data.bytes_dumped)); - seq_printf(m, - "HPTE: [%#016llx-%#016llx] %#llx bytes, " - "Dumped: %#llx\n", - be64_to_cpu(fdm_ptr->hpte_region.destination_address), - be64_to_cpu(fdm_ptr->hpte_region.destination_address) + - be64_to_cpu(fdm_ptr->hpte_region.source_len) - 1, - be64_to_cpu(fdm_ptr->hpte_region.source_len), - be64_to_cpu(fdm_ptr->hpte_region.bytes_dumped)); - seq_printf(m, - "DUMP: [%#016llx-%#016llx] %#llx bytes, " - "Dumped: %#llx\n", - be64_to_cpu(fdm_ptr->rmr_region.destination_address), - be64_to_cpu(fdm_ptr->rmr_region.destination_address) + - be64_to_cpu(fdm_ptr->rmr_region.source_len) - 1, - be64_to_cpu(fdm_ptr->rmr_region.source_len), - be64_to_cpu(fdm_ptr->rmr_region.bytes_dumped)); - - if (!fdm_active || - (fw_dump.reserve_dump_area_start == - be64_to_cpu(fdm_ptr->cpu_state_data.destination_address))) - goto out; - - /* Dump is active. Show reserved memory region. */ - seq_printf(m, - " : [%#016llx-%#016llx] %#llx bytes, " - "Dumped: %#llx\n", - (unsigned long long)fw_dump.reserve_dump_area_start, - be64_to_cpu(fdm_ptr->cpu_state_data.destination_address) - 1, - be64_to_cpu(fdm_ptr->cpu_state_data.destination_address) - - fw_dump.reserve_dump_area_start, - be64_to_cpu(fdm_ptr->cpu_state_data.destination_address) - - fw_dump.reserve_dump_area_start); -out: - if (fdm_active) - mutex_unlock(&fadump_mutex); + fw_dump.ops->fadump_region_show(&fw_dump, m); + mutex_unlock(&fadump_mutex); return 0; } @@ -1690,14 +1485,77 @@ int __init setup_fadump(void) * if dump process fails then invalidate the registration * and release memory before proceeding for re-registration. */ - if (process_fadump(fdm_active) < 0) + if (fw_dump.ops->fadump_process(&fw_dump) < 0) fadump_invalidate_release_mem(); } /* Initialize the kernel dump memory structure for FAD registration. */ else if (fw_dump.reserve_dump_area_size) - init_fadump_mem_struct(&fdm, fw_dump.reserve_dump_area_start); + fw_dump.ops->fadump_init_mem_struct(&fw_dump); + fadump_init_files(); return 1; } subsys_initcall(setup_fadump); +#else /* !CONFIG_PRESERVE_FA_DUMP */ + +/* Scan the Firmware Assisted dump configuration details. */ +int __init early_init_dt_scan_fw_dump(unsigned long node, const char *uname, + int depth, void *data) +{ + if ((depth != 1) || (strcmp(uname, "ibm,opal") != 0)) + return 0; + + opal_fadump_dt_scan(&fw_dump, node); + return 1; +} + +/* + * When dump is active but PRESERVE_FA_DUMP is enabled on the kernel, + * preserve crash data. The subsequent memory preserving kernel boot + * is likely to process this crash data. + */ +int __init fadump_reserve_mem(void) +{ + if (fw_dump.dump_active) { + /* + * If last boot has crashed then reserve all the memory + * above boot memory to preserve crash data. + */ + pr_info("Preserving crash data for processing in next boot.\n"); + fadump_reserve_crash_area(fw_dump.boot_mem_top); + } else + pr_debug("FADump-aware kernel..\n"); + + return 1; +} +#endif /* CONFIG_PRESERVE_FA_DUMP */ + +/* Preserve everything above the base address */ +static void __init fadump_reserve_crash_area(u64 base) +{ + struct memblock_region *reg; + u64 mstart, msize; + + for_each_memblock(memory, reg) { + mstart = reg->base; + msize = reg->size; + + if ((mstart + msize) < base) + continue; + + if (mstart < base) { + msize -= (base - mstart); + mstart = base; + } + + pr_info("Reserving %lluMB of memory at %#016llx for preserving crash data", + (msize >> 20), mstart); + memblock_reserve(mstart, msize); + } +} + +unsigned long __init arch_reserved_kernel_pages(void) +{ + return memblock_reserved_size() / PAGE_SIZE; +} diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S index f255e22184b4..4a24f8f026c7 100644 --- a/arch/powerpc/kernel/head_32.S +++ b/arch/powerpc/kernel/head_32.S @@ -34,7 +34,16 @@ #include "head_32.h" -/* 601 only have IBAT; cr0.eq is set on 601 when using this macro */ +/* 601 only have IBAT */ +#ifdef CONFIG_PPC_BOOK3S_601 +#define LOAD_BAT(n, reg, RA, RB) \ + li RA,0; \ + mtspr SPRN_IBAT##n##U,RA; \ + lwz RA,(n*16)+0(reg); \ + lwz RB,(n*16)+4(reg); \ + mtspr SPRN_IBAT##n##U,RA; \ + mtspr SPRN_IBAT##n##L,RB +#else #define LOAD_BAT(n, reg, RA, RB) \ /* see the comment for clear_bats() -- Cort */ \ li RA,0; \ @@ -44,12 +53,11 @@ lwz RB,(n*16)+4(reg); \ mtspr SPRN_IBAT##n##U,RA; \ mtspr SPRN_IBAT##n##L,RB; \ - beq 1f; \ lwz RA,(n*16)+8(reg); \ lwz RB,(n*16)+12(reg); \ mtspr SPRN_DBAT##n##U,RA; \ - mtspr SPRN_DBAT##n##L,RB; \ -1: + mtspr SPRN_DBAT##n##L,RB +#endif __HEAD .stabs "arch/powerpc/kernel/",N_SO,0,0,0f @@ -557,9 +565,9 @@ DataStoreTLBMiss: cmplw 0,r1,r3 mfspr r2, SPRN_SPRG_PGDIR #ifdef CONFIG_SWAP - li r1, _PAGE_RW | _PAGE_PRESENT | _PAGE_ACCESSED + li r1, _PAGE_RW | _PAGE_DIRTY | _PAGE_PRESENT | _PAGE_ACCESSED #else - li r1, _PAGE_RW | _PAGE_PRESENT + li r1, _PAGE_RW | _PAGE_DIRTY | _PAGE_PRESENT #endif bge- 112f lis r2, (swapper_pg_dir - PAGE_OFFSET)@ha /* if kernel address, use */ @@ -820,9 +828,6 @@ load_up_mmu: /* Load the BAT registers with the values set up by MMU_init. MMU_init takes care of whether we're on a 601 or not. */ - mfpvr r3 - srwi r3,r3,16 - cmpwi r3,1 lis r3,BATS@ha addi r3,r3,BATS@l tophys(r3,r3) @@ -897,9 +902,11 @@ start_here: bl machine_init bl __save_cpu_setup bl MMU_init +#ifdef CONFIG_KASAN BEGIN_MMU_FTR_SECTION bl MMU_init_hw_patch END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE) +#endif /* * Go back to running unmapped so we can load up new values @@ -996,11 +1003,8 @@ EXPORT_SYMBOL(switch_mmu_context) */ clear_bats: li r10,0 - mfspr r9,SPRN_PVR - rlwinm r9,r9,16,16,31 /* r9 = 1 for 601, 4 for 604 */ - cmpwi r9, 1 - beq 1f +#ifndef CONFIG_PPC_BOOK3S_601 mtspr SPRN_DBAT0U,r10 mtspr SPRN_DBAT0L,r10 mtspr SPRN_DBAT1U,r10 @@ -1009,7 +1013,7 @@ clear_bats: mtspr SPRN_DBAT2L,r10 mtspr SPRN_DBAT3U,r10 mtspr SPRN_DBAT3L,r10 -1: +#endif mtspr SPRN_IBAT0U,r10 mtspr SPRN_IBAT0L,r10 mtspr SPRN_IBAT1U,r10 @@ -1104,10 +1108,7 @@ mmu_off: */ initial_bats: lis r11,PAGE_OFFSET@h - mfspr r9,SPRN_PVR - rlwinm r9,r9,16,16,31 /* r9 = 1 for 601, 4 for 604 */ - cmpwi 0,r9,1 - bne 4f +#ifdef CONFIG_PPC_BOOK3S_601 ori r11,r11,4 /* set up BAT registers for 601 */ li r8,0x7f /* valid, block length = 8MB */ mtspr SPRN_IBAT0U,r11 /* N.B. 601 has valid bit in */ @@ -1120,10 +1121,8 @@ initial_bats: addis r8,r8,0x800000@h mtspr SPRN_IBAT2U,r11 mtspr SPRN_IBAT2L,r8 - isync - blr - -4: tophys(r8,r11) +#else + tophys(r8,r11) #ifdef CONFIG_SMP ori r8,r8,0x12 /* R/W access, M=1 */ #else @@ -1135,10 +1134,10 @@ initial_bats: mtspr SPRN_DBAT0U,r11 /* bit in upper BAT register */ mtspr SPRN_IBAT0L,r8 mtspr SPRN_IBAT0U,r11 +#endif isync blr - #ifdef CONFIG_BOOTX_TEXT setup_disp_bat: /* @@ -1153,15 +1152,13 @@ setup_disp_bat: beqlr lwz r11,0(r8) lwz r8,4(r8) - mfspr r9,SPRN_PVR - rlwinm r9,r9,16,16,31 /* r9 = 1 for 601, 4 for 604 */ - cmpwi 0,r9,1 - beq 1f +#ifndef CONFIG_PPC_BOOK3S_601 mtspr SPRN_DBAT3L,r8 mtspr SPRN_DBAT3U,r11 - blr -1: mtspr SPRN_IBAT3L,r8 +#else + mtspr SPRN_IBAT3L,r8 mtspr SPRN_IBAT3U,r11 +#endif blr #endif /* CONFIG_BOOTX_TEXT */ diff --git a/arch/powerpc/kernel/head_32.h b/arch/powerpc/kernel/head_32.h index 4a692553651f..8abc7783dbe5 100644 --- a/arch/powerpc/kernel/head_32.h +++ b/arch/powerpc/kernel/head_32.h @@ -5,19 +5,6 @@ #include <asm/ptrace.h> /* for STACK_FRAME_REGS_MARKER */ /* - * MSR_KERNEL is > 0x8000 on 4xx/Book-E since it include MSR_CE. - */ -.macro __LOAD_MSR_KERNEL r, x -.if \x >= 0x8000 - lis \r, (\x)@h - ori \r, \r, (\x)@l -.else - li \r, (\x) -.endif -.endm -#define LOAD_MSR_KERNEL(r, x) __LOAD_MSR_KERNEL r, x - -/* * Exception entry code. This code runs with address translation * turned off, i.e. using physical addresses. * We assume sprg3 has the physical address of the current @@ -92,7 +79,7 @@ #ifdef CONFIG_40x rlwinm r9,r9,0,14,12 /* clear MSR_WE (necessary?) */ #else - LOAD_MSR_KERNEL(r10, MSR_KERNEL & ~(MSR_IR|MSR_DR)) /* can take exceptions */ + LOAD_REG_IMMEDIATE(r10, MSR_KERNEL & ~(MSR_IR|MSR_DR)) /* can take exceptions */ MTMSRD(r10) /* (except for mach check in rtas) */ #endif lis r10,STACK_FRAME_REGS_MARKER@ha /* exception frame marker */ @@ -140,10 +127,10 @@ * otherwise we might risk taking an interrupt before we tell lockdep * they are enabled. */ - LOAD_MSR_KERNEL(r10, MSR_KERNEL) + LOAD_REG_IMMEDIATE(r10, MSR_KERNEL) rlwimi r10, r9, 0, MSR_EE #else - LOAD_MSR_KERNEL(r10, MSR_KERNEL | MSR_EE) + LOAD_REG_IMMEDIATE(r10, MSR_KERNEL | MSR_EE) #endif #if defined(CONFIG_PPC_8xx) && defined(CONFIG_PERF_EVENTS) mtspr SPRN_NRI, r0 @@ -187,7 +174,7 @@ label: #define EXC_XFER_TEMPLATE(hdlr, trap, msr, tfer, ret) \ li r10,trap; \ stw r10,_TRAP(r11); \ - LOAD_MSR_KERNEL(r10, msr); \ + LOAD_REG_IMMEDIATE(r10, msr); \ bl tfer; \ .long hdlr; \ .long ret diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S index 91d297e696dd..ad79fddb974d 100644 --- a/arch/powerpc/kernel/head_64.S +++ b/arch/powerpc/kernel/head_64.S @@ -182,7 +182,8 @@ __secondary_hold: isync bctr #else - BUG_OPCODE +0: trap + EMIT_BUG_ENTRY 0b, __FILE__, __LINE__, 0 #endif CLOSE_FIXED_SECTION(first_256B) @@ -635,7 +636,7 @@ __after_prom_start: sub r5,r5,r11 #else /* just copy interrupts */ - LOAD_REG_IMMEDIATE(r5, FIXED_SYMBOL_ABS_ADDR(__end_interrupts)) + LOAD_REG_IMMEDIATE_SYM(r5, r11, FIXED_SYMBOL_ABS_ADDR(__end_interrupts)) #endif b 5f 3: @@ -998,7 +999,8 @@ start_here_common: bl start_kernel /* Not reached */ - BUG_OPCODE + trap + EMIT_BUG_ENTRY 0b, __FILE__, __LINE__, 0 /* * We put a few things here that have to be page-aligned. diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S index 5ab9178c2347..19f583e18402 100644 --- a/arch/powerpc/kernel/head_8xx.S +++ b/arch/powerpc/kernel/head_8xx.S @@ -15,6 +15,7 @@ */ #include <linux/init.h> +#include <linux/magic.h> #include <asm/processor.h> #include <asm/page.h> #include <asm/mmu.h> @@ -574,8 +575,6 @@ InstructionBreakpoint: * by decoding the registers used by the dcbx instruction and adding them. * DAR is set to the calculated address. */ - /* define if you don't want to use self modifying code */ -#define NO_SELF_MODIFYING_CODE FixupDAR:/* Entry point for dcbx workaround. */ mtspr SPRN_M_TW, r10 /* fetch instruction from memory. */ @@ -639,27 +638,6 @@ FixupDAR:/* Entry point for dcbx workaround. */ rlwinm r10, r10,0,7,5 /* Clear store bit for buggy dcbst insn */ mtspr SPRN_DSISR, r10 142: /* continue, it was a dcbx, dcbi instruction. */ -#ifndef NO_SELF_MODIFYING_CODE - andis. r10,r11,0x1f /* test if reg RA is r0 */ - li r10,modified_instr@l - dcbtst r0,r10 /* touch for store */ - rlwinm r11,r11,0,0,20 /* Zero lower 10 bits */ - oris r11,r11,640 /* Transform instr. to a "add r10,RA,RB" */ - ori r11,r11,532 - stw r11,0(r10) /* store add/and instruction */ - dcbf 0,r10 /* flush new instr. to memory. */ - icbi 0,r10 /* invalidate instr. cache line */ - mfspr r11, SPRN_SPRG_SCRATCH1 /* restore r11 */ - mfspr r10, SPRN_SPRG_SCRATCH0 /* restore r10 */ - isync /* Wait until new instr is loaded from memory */ -modified_instr: - .space 4 /* this is where the add instr. is stored */ - bne+ 143f - subf r10,r0,r10 /* r10=r10-r0, only if reg RA is r0 */ -143: mtdar r10 /* store faulting EA in DAR */ - mfspr r10,SPRN_M_TW - b DARFixed /* Go back to normal TLB handling */ -#else mfctr r10 mtdar r10 /* save ctr reg in DAR */ rlwinm r10, r11, 24, 24, 28 /* offset into jump table for reg RB */ @@ -723,7 +701,6 @@ modified_instr: add r10, r10, r11 /* add it */ mfctr r11 /* restore r11 */ b 151b -#endif /* * This is where the main kernel code starts. @@ -741,6 +718,9 @@ start_here: /* stack */ lis r1,init_thread_union@ha addi r1,r1,init_thread_union@l + lis r0, STACK_END_MAGIC@h + ori r0, r0, STACK_END_MAGIC@l + stw r0, 0(r1) li r0,0 stwu r0,THREAD_SIZE-STACK_FRAME_OVERHEAD(r1) diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c index c8d1fa2e9d53..1007ec36b4cb 100644 --- a/arch/powerpc/kernel/hw_breakpoint.c +++ b/arch/powerpc/kernel/hw_breakpoint.c @@ -195,18 +195,63 @@ void thread_change_pc(struct task_struct *tsk, struct pt_regs *regs) tsk->thread.last_hit_ubp = NULL; } +static bool is_larx_stcx_instr(struct pt_regs *regs, unsigned int instr) +{ + int ret, type; + struct instruction_op op; + + ret = analyse_instr(&op, regs, instr); + type = GETTYPE(op.type); + return (!ret && (type == LARX || type == STCX)); +} + /* * Handle debug exception notifications. */ +static bool stepping_handler(struct pt_regs *regs, struct perf_event *bp, + unsigned long addr) +{ + unsigned int instr = 0; + + if (__get_user_inatomic(instr, (unsigned int *)regs->nip)) + goto fail; + + if (is_larx_stcx_instr(regs, instr)) { + printk_ratelimited("Breakpoint hit on instruction that can't be emulated." + " Breakpoint at 0x%lx will be disabled.\n", addr); + goto disable; + } + + /* Do not emulate user-space instructions, instead single-step them */ + if (user_mode(regs)) { + current->thread.last_hit_ubp = bp; + regs->msr |= MSR_SE; + return false; + } + + if (!emulate_step(regs, instr)) + goto fail; + + return true; + +fail: + /* + * We've failed in reliably handling the hw-breakpoint. Unregister + * it and throw a warning message to let the user know about it. + */ + WARN(1, "Unable to handle hardware breakpoint. Breakpoint at " + "0x%lx will be disabled.", addr); + +disable: + perf_event_disable_inatomic(bp); + return false; +} + int hw_breakpoint_handler(struct die_args *args) { int rc = NOTIFY_STOP; struct perf_event *bp; struct pt_regs *regs = args->regs; -#ifndef CONFIG_PPC_8xx - int stepped = 1; - unsigned int instr; -#endif struct arch_hw_breakpoint *info; unsigned long dar = regs->dar; @@ -251,32 +296,10 @@ int hw_breakpoint_handler(struct die_args *args) (dar - bp->attr.bp_addr < bp->attr.bp_len))) info->type |= HW_BRK_TYPE_EXTRANEOUS_IRQ; -#ifndef CONFIG_PPC_8xx - /* Do not emulate user-space instructions, instead single-step them */ - if (user_mode(regs)) { - current->thread.last_hit_ubp = bp; - regs->msr |= MSR_SE; + if (!IS_ENABLED(CONFIG_PPC_8xx) && !stepping_handler(regs, bp, info->address)) goto out; - } - - stepped = 0; - instr = 0; - if (!__get_user_inatomic(instr, (unsigned int *) regs->nip)) - stepped = emulate_step(regs, instr); /* - * emulate_step() could not execute it. We've failed in reliably - * handling the hw-breakpoint. Unregister it and throw a warning - * message to let the user know about it. - */ - if (!stepped) { - WARN(1, "Unable to handle hardware breakpoint. Breakpoint at " - "0x%lx will be disabled.", info->address); - perf_event_disable_inatomic(bp); - goto out; - } -#endif - /* * As a policy, the callback is invoked in a 'trigger-after-execute' * fashion */ diff --git a/arch/powerpc/kernel/io-workarounds.c b/arch/powerpc/kernel/io-workarounds.c index fbd2d0007c52..0276bc8c8969 100644 --- a/arch/powerpc/kernel/io-workarounds.c +++ b/arch/powerpc/kernel/io-workarounds.c @@ -149,8 +149,8 @@ static const struct ppc_pci_io iowa_pci_io = { }; #ifdef CONFIG_PPC_INDIRECT_MMIO -static void __iomem *iowa_ioremap(phys_addr_t addr, unsigned long size, - pgprot_t prot, void *caller) +void __iomem *iowa_ioremap(phys_addr_t addr, unsigned long size, + pgprot_t prot, void *caller) { struct iowa_bus *bus; void __iomem *res = __ioremap_caller(addr, size, prot, caller); @@ -163,20 +163,17 @@ static void __iomem *iowa_ioremap(phys_addr_t addr, unsigned long size, } return res; } -#else /* CONFIG_PPC_INDIRECT_MMIO */ -#define iowa_ioremap NULL #endif /* !CONFIG_PPC_INDIRECT_MMIO */ +bool io_workaround_inited; + /* Enable IO workaround */ static void io_workaround_init(void) { - static int io_workaround_inited; - if (io_workaround_inited) return; ppc_pci_io = iowa_pci_io; - ppc_md.ioremap = iowa_ioremap; - io_workaround_inited = 1; + io_workaround_inited = true; } /* Register new bus to support workaround */ diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index 0a67ce9f827e..9704f3f76e63 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -633,11 +633,54 @@ static void iommu_table_clear(struct iommu_table *tbl) #endif } +static void iommu_table_reserve_pages(struct iommu_table *tbl, + unsigned long res_start, unsigned long res_end) +{ + int i; + + WARN_ON_ONCE(res_end < res_start); + /* + * Reserve page 0 so it will not be used for any mappings. + * This avoids buggy drivers that consider page 0 to be invalid + * to crash the machine or even lose data. + */ + if (tbl->it_offset == 0) + set_bit(0, tbl->it_map); + + tbl->it_reserved_start = res_start; + tbl->it_reserved_end = res_end; + + /* Check if res_start..res_end isn't empty and overlaps the table */ + if (res_start && res_end && + (tbl->it_offset + tbl->it_size < res_start || + res_end < tbl->it_offset)) + return; + + for (i = tbl->it_reserved_start; i < tbl->it_reserved_end; ++i) + set_bit(i - tbl->it_offset, tbl->it_map); +} + +static void iommu_table_release_pages(struct iommu_table *tbl) +{ + int i; + + /* + * In case we have reserved the first bit, we should not emit + * the warning below. + */ + if (tbl->it_offset == 0) + clear_bit(0, tbl->it_map); + + for (i = tbl->it_reserved_start; i < tbl->it_reserved_end; ++i) + clear_bit(i - tbl->it_offset, tbl->it_map); +} + /* * Build a iommu_table structure. This contains a bit map which * is used to manage allocation of the tce space. */ -struct iommu_table *iommu_init_table(struct iommu_table *tbl, int nid) +struct iommu_table *iommu_init_table(struct iommu_table *tbl, int nid, + unsigned long res_start, unsigned long res_end) { unsigned long sz; static int welcomed = 0; @@ -656,13 +699,7 @@ struct iommu_table *iommu_init_table(struct iommu_table *tbl, int nid) tbl->it_map = page_address(page); memset(tbl->it_map, 0, sz); - /* - * Reserve page 0 so it will not be used for any mappings. - * This avoids buggy drivers that consider page 0 to be invalid - * to crash the machine or even lose data. - */ - if (tbl->it_offset == 0) - set_bit(0, tbl->it_map); + iommu_table_reserve_pages(tbl, res_start, res_end); /* We only split the IOMMU table if we have 1GB or more of space */ if ((tbl->it_size << tbl->it_page_shift) >= (1UL * 1024 * 1024 * 1024)) @@ -714,12 +751,7 @@ static void iommu_table_free(struct kref *kref) return; } - /* - * In case we have reserved the first bit, we should not emit - * the warning below. - */ - if (tbl->it_offset == 0) - clear_bit(0, tbl->it_map); + iommu_table_release_pages(tbl); /* verify that table contains no entries */ if (!bitmap_empty(tbl->it_map, tbl->it_size)) @@ -981,29 +1013,32 @@ int iommu_tce_check_gpa(unsigned long page_shift, unsigned long gpa) } EXPORT_SYMBOL_GPL(iommu_tce_check_gpa); -long iommu_tce_xchg(struct mm_struct *mm, struct iommu_table *tbl, +extern long iommu_tce_xchg_no_kill(struct mm_struct *mm, + struct iommu_table *tbl, unsigned long entry, unsigned long *hpa, enum dma_data_direction *direction) { long ret; unsigned long size = 0; - ret = tbl->it_ops->exchange(tbl, entry, hpa, direction); - + ret = tbl->it_ops->xchg_no_kill(tbl, entry, hpa, direction, false); if (!ret && ((*direction == DMA_FROM_DEVICE) || (*direction == DMA_BIDIRECTIONAL)) && !mm_iommu_is_devmem(mm, *hpa, tbl->it_page_shift, &size)) SetPageDirty(pfn_to_page(*hpa >> PAGE_SHIFT)); - /* if (unlikely(ret)) - pr_err("iommu_tce: %s failed on hwaddr=%lx ioba=%lx kva=%lx ret=%d\n", - __func__, hwaddr, entry << tbl->it_page_shift, - hwaddr, ret); */ - return ret; } -EXPORT_SYMBOL_GPL(iommu_tce_xchg); +EXPORT_SYMBOL_GPL(iommu_tce_xchg_no_kill); + +void iommu_tce_kill(struct iommu_table *tbl, + unsigned long entry, unsigned long pages) +{ + if (tbl->it_ops->tce_kill) + tbl->it_ops->tce_kill(tbl, entry, pages, false); +} +EXPORT_SYMBOL_GPL(iommu_tce_kill); int iommu_take_ownership(struct iommu_table *tbl) { @@ -1017,22 +1052,21 @@ int iommu_take_ownership(struct iommu_table *tbl) * requires exchange() callback defined so if it is not * implemented, we disallow taking ownership over the table. */ - if (!tbl->it_ops->exchange) + if (!tbl->it_ops->xchg_no_kill) return -EINVAL; spin_lock_irqsave(&tbl->large_pool.lock, flags); for (i = 0; i < tbl->nr_pools; i++) spin_lock(&tbl->pools[i].lock); - if (tbl->it_offset == 0) - clear_bit(0, tbl->it_map); + iommu_table_release_pages(tbl); if (!bitmap_empty(tbl->it_map, tbl->it_size)) { pr_err("iommu_tce: it_map is not empty"); ret = -EBUSY; - /* Restore bit#0 set by iommu_init_table() */ - if (tbl->it_offset == 0) - set_bit(0, tbl->it_map); + /* Undo iommu_table_release_pages, i.e. restore bit#0, etc */ + iommu_table_reserve_pages(tbl, tbl->it_reserved_start, + tbl->it_reserved_end); } else { memset(tbl->it_map, 0xff, sz); } @@ -1055,9 +1089,8 @@ void iommu_release_ownership(struct iommu_table *tbl) memset(tbl->it_map, 0, sz); - /* Restore bit#0 set by iommu_init_table() */ - if (tbl->it_offset == 0) - set_bit(0, tbl->it_map); + iommu_table_reserve_pages(tbl, tbl->it_reserved_start, + tbl->it_reserved_end); for (i = 0; i < tbl->nr_pools; i++) spin_unlock(&tbl->pools[i].lock); diff --git a/arch/powerpc/kernel/kexec_elf_64.c b/arch/powerpc/kernel/kexec_elf_64.c index 83cf7b852876..3072fd6dbe94 100644 --- a/arch/powerpc/kernel/kexec_elf_64.c +++ b/arch/powerpc/kernel/kexec_elf_64.c @@ -23,541 +23,6 @@ #include <linux/slab.h> #include <linux/types.h> -#define PURGATORY_STACK_SIZE (16 * 1024) - -#define elf_addr_to_cpu elf64_to_cpu - -#ifndef Elf_Rel -#define Elf_Rel Elf64_Rel -#endif /* Elf_Rel */ - -struct elf_info { - /* - * Where the ELF binary contents are kept. - * Memory managed by the user of the struct. - */ - const char *buffer; - - const struct elfhdr *ehdr; - const struct elf_phdr *proghdrs; - struct elf_shdr *sechdrs; -}; - -static inline bool elf_is_elf_file(const struct elfhdr *ehdr) -{ - return memcmp(ehdr->e_ident, ELFMAG, SELFMAG) == 0; -} - -static uint64_t elf64_to_cpu(const struct elfhdr *ehdr, uint64_t value) -{ - if (ehdr->e_ident[EI_DATA] == ELFDATA2LSB) - value = le64_to_cpu(value); - else if (ehdr->e_ident[EI_DATA] == ELFDATA2MSB) - value = be64_to_cpu(value); - - return value; -} - -static uint16_t elf16_to_cpu(const struct elfhdr *ehdr, uint16_t value) -{ - if (ehdr->e_ident[EI_DATA] == ELFDATA2LSB) - value = le16_to_cpu(value); - else if (ehdr->e_ident[EI_DATA] == ELFDATA2MSB) - value = be16_to_cpu(value); - - return value; -} - -static uint32_t elf32_to_cpu(const struct elfhdr *ehdr, uint32_t value) -{ - if (ehdr->e_ident[EI_DATA] == ELFDATA2LSB) - value = le32_to_cpu(value); - else if (ehdr->e_ident[EI_DATA] == ELFDATA2MSB) - value = be32_to_cpu(value); - - return value; -} - -/** - * elf_is_ehdr_sane - check that it is safe to use the ELF header - * @buf_len: size of the buffer in which the ELF file is loaded. - */ -static bool elf_is_ehdr_sane(const struct elfhdr *ehdr, size_t buf_len) -{ - if (ehdr->e_phnum > 0 && ehdr->e_phentsize != sizeof(struct elf_phdr)) { - pr_debug("Bad program header size.\n"); - return false; - } else if (ehdr->e_shnum > 0 && - ehdr->e_shentsize != sizeof(struct elf_shdr)) { - pr_debug("Bad section header size.\n"); - return false; - } else if (ehdr->e_ident[EI_VERSION] != EV_CURRENT || - ehdr->e_version != EV_CURRENT) { - pr_debug("Unknown ELF version.\n"); - return false; - } - - if (ehdr->e_phoff > 0 && ehdr->e_phnum > 0) { - size_t phdr_size; - - /* - * e_phnum is at most 65535 so calculating the size of the - * program header cannot overflow. - */ - phdr_size = sizeof(struct elf_phdr) * ehdr->e_phnum; - - /* Sanity check the program header table location. */ - if (ehdr->e_phoff + phdr_size < ehdr->e_phoff) { - pr_debug("Program headers at invalid location.\n"); - return false; - } else if (ehdr->e_phoff + phdr_size > buf_len) { - pr_debug("Program headers truncated.\n"); - return false; - } - } - - if (ehdr->e_shoff > 0 && ehdr->e_shnum > 0) { - size_t shdr_size; - - /* - * e_shnum is at most 65536 so calculating - * the size of the section header cannot overflow. - */ - shdr_size = sizeof(struct elf_shdr) * ehdr->e_shnum; - - /* Sanity check the section header table location. */ - if (ehdr->e_shoff + shdr_size < ehdr->e_shoff) { - pr_debug("Section headers at invalid location.\n"); - return false; - } else if (ehdr->e_shoff + shdr_size > buf_len) { - pr_debug("Section headers truncated.\n"); - return false; - } - } - - return true; -} - -static int elf_read_ehdr(const char *buf, size_t len, struct elfhdr *ehdr) -{ - struct elfhdr *buf_ehdr; - - if (len < sizeof(*buf_ehdr)) { - pr_debug("Buffer is too small to hold ELF header.\n"); - return -ENOEXEC; - } - - memset(ehdr, 0, sizeof(*ehdr)); - memcpy(ehdr->e_ident, buf, sizeof(ehdr->e_ident)); - if (!elf_is_elf_file(ehdr)) { - pr_debug("No ELF header magic.\n"); - return -ENOEXEC; - } - - if (ehdr->e_ident[EI_CLASS] != ELF_CLASS) { - pr_debug("Not a supported ELF class.\n"); - return -ENOEXEC; - } else if (ehdr->e_ident[EI_DATA] != ELFDATA2LSB && - ehdr->e_ident[EI_DATA] != ELFDATA2MSB) { - pr_debug("Not a supported ELF data format.\n"); - return -ENOEXEC; - } - - buf_ehdr = (struct elfhdr *) buf; - if (elf16_to_cpu(ehdr, buf_ehdr->e_ehsize) != sizeof(*buf_ehdr)) { - pr_debug("Bad ELF header size.\n"); - return -ENOEXEC; - } - - ehdr->e_type = elf16_to_cpu(ehdr, buf_ehdr->e_type); - ehdr->e_machine = elf16_to_cpu(ehdr, buf_ehdr->e_machine); - ehdr->e_version = elf32_to_cpu(ehdr, buf_ehdr->e_version); - ehdr->e_entry = elf_addr_to_cpu(ehdr, buf_ehdr->e_entry); - ehdr->e_phoff = elf_addr_to_cpu(ehdr, buf_ehdr->e_phoff); - ehdr->e_shoff = elf_addr_to_cpu(ehdr, buf_ehdr->e_shoff); - ehdr->e_flags = elf32_to_cpu(ehdr, buf_ehdr->e_flags); - ehdr->e_phentsize = elf16_to_cpu(ehdr, buf_ehdr->e_phentsize); - ehdr->e_phnum = elf16_to_cpu(ehdr, buf_ehdr->e_phnum); - ehdr->e_shentsize = elf16_to_cpu(ehdr, buf_ehdr->e_shentsize); - ehdr->e_shnum = elf16_to_cpu(ehdr, buf_ehdr->e_shnum); - ehdr->e_shstrndx = elf16_to_cpu(ehdr, buf_ehdr->e_shstrndx); - - return elf_is_ehdr_sane(ehdr, len) ? 0 : -ENOEXEC; -} - -/** - * elf_is_phdr_sane - check that it is safe to use the program header - * @buf_len: size of the buffer in which the ELF file is loaded. - */ -static bool elf_is_phdr_sane(const struct elf_phdr *phdr, size_t buf_len) -{ - - if (phdr->p_offset + phdr->p_filesz < phdr->p_offset) { - pr_debug("ELF segment location wraps around.\n"); - return false; - } else if (phdr->p_offset + phdr->p_filesz > buf_len) { - pr_debug("ELF segment not in file.\n"); - return false; - } else if (phdr->p_paddr + phdr->p_memsz < phdr->p_paddr) { - pr_debug("ELF segment address wraps around.\n"); - return false; - } - - return true; -} - -static int elf_read_phdr(const char *buf, size_t len, struct elf_info *elf_info, - int idx) -{ - /* Override the const in proghdrs, we are the ones doing the loading. */ - struct elf_phdr *phdr = (struct elf_phdr *) &elf_info->proghdrs[idx]; - const char *pbuf; - struct elf_phdr *buf_phdr; - - pbuf = buf + elf_info->ehdr->e_phoff + (idx * sizeof(*buf_phdr)); - buf_phdr = (struct elf_phdr *) pbuf; - - phdr->p_type = elf32_to_cpu(elf_info->ehdr, buf_phdr->p_type); - phdr->p_offset = elf_addr_to_cpu(elf_info->ehdr, buf_phdr->p_offset); - phdr->p_paddr = elf_addr_to_cpu(elf_info->ehdr, buf_phdr->p_paddr); - phdr->p_vaddr = elf_addr_to_cpu(elf_info->ehdr, buf_phdr->p_vaddr); - phdr->p_flags = elf32_to_cpu(elf_info->ehdr, buf_phdr->p_flags); - - /* - * The following fields have a type equivalent to Elf_Addr - * both in 32 bit and 64 bit ELF. - */ - phdr->p_filesz = elf_addr_to_cpu(elf_info->ehdr, buf_phdr->p_filesz); - phdr->p_memsz = elf_addr_to_cpu(elf_info->ehdr, buf_phdr->p_memsz); - phdr->p_align = elf_addr_to_cpu(elf_info->ehdr, buf_phdr->p_align); - - return elf_is_phdr_sane(phdr, len) ? 0 : -ENOEXEC; -} - -/** - * elf_read_phdrs - read the program headers from the buffer - * - * This function assumes that the program header table was checked for sanity. - * Use elf_is_ehdr_sane() if it wasn't. - */ -static int elf_read_phdrs(const char *buf, size_t len, - struct elf_info *elf_info) -{ - size_t phdr_size, i; - const struct elfhdr *ehdr = elf_info->ehdr; - - /* - * e_phnum is at most 65535 so calculating the size of the - * program header cannot overflow. - */ - phdr_size = sizeof(struct elf_phdr) * ehdr->e_phnum; - - elf_info->proghdrs = kzalloc(phdr_size, GFP_KERNEL); - if (!elf_info->proghdrs) - return -ENOMEM; - - for (i = 0; i < ehdr->e_phnum; i++) { - int ret; - - ret = elf_read_phdr(buf, len, elf_info, i); - if (ret) { - kfree(elf_info->proghdrs); - elf_info->proghdrs = NULL; - return ret; - } - } - - return 0; -} - -/** - * elf_is_shdr_sane - check that it is safe to use the section header - * @buf_len: size of the buffer in which the ELF file is loaded. - */ -static bool elf_is_shdr_sane(const struct elf_shdr *shdr, size_t buf_len) -{ - bool size_ok; - - /* SHT_NULL headers have undefined values, so we can't check them. */ - if (shdr->sh_type == SHT_NULL) - return true; - - /* Now verify sh_entsize */ - switch (shdr->sh_type) { - case SHT_SYMTAB: - size_ok = shdr->sh_entsize == sizeof(Elf_Sym); - break; - case SHT_RELA: - size_ok = shdr->sh_entsize == sizeof(Elf_Rela); - break; - case SHT_DYNAMIC: - size_ok = shdr->sh_entsize == sizeof(Elf_Dyn); - break; - case SHT_REL: - size_ok = shdr->sh_entsize == sizeof(Elf_Rel); - break; - case SHT_NOTE: - case SHT_PROGBITS: - case SHT_HASH: - case SHT_NOBITS: - default: - /* - * This is a section whose entsize requirements - * I don't care about. If I don't know about - * the section I can't care about it's entsize - * requirements. - */ - size_ok = true; - break; - } - - if (!size_ok) { - pr_debug("ELF section with wrong entry size.\n"); - return false; - } else if (shdr->sh_addr + shdr->sh_size < shdr->sh_addr) { - pr_debug("ELF section address wraps around.\n"); - return false; - } - - if (shdr->sh_type != SHT_NOBITS) { - if (shdr->sh_offset + shdr->sh_size < shdr->sh_offset) { - pr_debug("ELF section location wraps around.\n"); - return false; - } else if (shdr->sh_offset + shdr->sh_size > buf_len) { - pr_debug("ELF section not in file.\n"); - return false; - } - } - - return true; -} - -static int elf_read_shdr(const char *buf, size_t len, struct elf_info *elf_info, - int idx) -{ - struct elf_shdr *shdr = &elf_info->sechdrs[idx]; - const struct elfhdr *ehdr = elf_info->ehdr; - const char *sbuf; - struct elf_shdr *buf_shdr; - - sbuf = buf + ehdr->e_shoff + idx * sizeof(*buf_shdr); - buf_shdr = (struct elf_shdr *) sbuf; - - shdr->sh_name = elf32_to_cpu(ehdr, buf_shdr->sh_name); - shdr->sh_type = elf32_to_cpu(ehdr, buf_shdr->sh_type); - shdr->sh_addr = elf_addr_to_cpu(ehdr, buf_shdr->sh_addr); - shdr->sh_offset = elf_addr_to_cpu(ehdr, buf_shdr->sh_offset); - shdr->sh_link = elf32_to_cpu(ehdr, buf_shdr->sh_link); - shdr->sh_info = elf32_to_cpu(ehdr, buf_shdr->sh_info); - - /* - * The following fields have a type equivalent to Elf_Addr - * both in 32 bit and 64 bit ELF. - */ - shdr->sh_flags = elf_addr_to_cpu(ehdr, buf_shdr->sh_flags); - shdr->sh_size = elf_addr_to_cpu(ehdr, buf_shdr->sh_size); - shdr->sh_addralign = elf_addr_to_cpu(ehdr, buf_shdr->sh_addralign); - shdr->sh_entsize = elf_addr_to_cpu(ehdr, buf_shdr->sh_entsize); - - return elf_is_shdr_sane(shdr, len) ? 0 : -ENOEXEC; -} - -/** - * elf_read_shdrs - read the section headers from the buffer - * - * This function assumes that the section header table was checked for sanity. - * Use elf_is_ehdr_sane() if it wasn't. - */ -static int elf_read_shdrs(const char *buf, size_t len, - struct elf_info *elf_info) -{ - size_t shdr_size, i; - - /* - * e_shnum is at most 65536 so calculating - * the size of the section header cannot overflow. - */ - shdr_size = sizeof(struct elf_shdr) * elf_info->ehdr->e_shnum; - - elf_info->sechdrs = kzalloc(shdr_size, GFP_KERNEL); - if (!elf_info->sechdrs) - return -ENOMEM; - - for (i = 0; i < elf_info->ehdr->e_shnum; i++) { - int ret; - - ret = elf_read_shdr(buf, len, elf_info, i); - if (ret) { - kfree(elf_info->sechdrs); - elf_info->sechdrs = NULL; - return ret; - } - } - - return 0; -} - -/** - * elf_read_from_buffer - read ELF file and sets up ELF header and ELF info - * @buf: Buffer to read ELF file from. - * @len: Size of @buf. - * @ehdr: Pointer to existing struct which will be populated. - * @elf_info: Pointer to existing struct which will be populated. - * - * This function allows reading ELF files with different byte order than - * the kernel, byte-swapping the fields as needed. - * - * Return: - * On success returns 0, and the caller should call elf_free_info(elf_info) to - * free the memory allocated for the section and program headers. - */ -int elf_read_from_buffer(const char *buf, size_t len, struct elfhdr *ehdr, - struct elf_info *elf_info) -{ - int ret; - - ret = elf_read_ehdr(buf, len, ehdr); - if (ret) - return ret; - - elf_info->buffer = buf; - elf_info->ehdr = ehdr; - if (ehdr->e_phoff > 0 && ehdr->e_phnum > 0) { - ret = elf_read_phdrs(buf, len, elf_info); - if (ret) - return ret; - } - if (ehdr->e_shoff > 0 && ehdr->e_shnum > 0) { - ret = elf_read_shdrs(buf, len, elf_info); - if (ret) { - kfree(elf_info->proghdrs); - return ret; - } - } - - return 0; -} - -/** - * elf_free_info - free memory allocated by elf_read_from_buffer - */ -void elf_free_info(struct elf_info *elf_info) -{ - kfree(elf_info->proghdrs); - kfree(elf_info->sechdrs); - memset(elf_info, 0, sizeof(*elf_info)); -} -/** - * build_elf_exec_info - read ELF executable and check that we can use it - */ -static int build_elf_exec_info(const char *buf, size_t len, struct elfhdr *ehdr, - struct elf_info *elf_info) -{ - int i; - int ret; - - ret = elf_read_from_buffer(buf, len, ehdr, elf_info); - if (ret) - return ret; - - /* Big endian vmlinux has type ET_DYN. */ - if (ehdr->e_type != ET_EXEC && ehdr->e_type != ET_DYN) { - pr_err("Not an ELF executable.\n"); - goto error; - } else if (!elf_info->proghdrs) { - pr_err("No ELF program header.\n"); - goto error; - } - - for (i = 0; i < ehdr->e_phnum; i++) { - /* - * Kexec does not support loading interpreters. - * In addition this check keeps us from attempting - * to kexec ordinay executables. - */ - if (elf_info->proghdrs[i].p_type == PT_INTERP) { - pr_err("Requires an ELF interpreter.\n"); - goto error; - } - } - - return 0; -error: - elf_free_info(elf_info); - return -ENOEXEC; -} - -static int elf64_probe(const char *buf, unsigned long len) -{ - struct elfhdr ehdr; - struct elf_info elf_info; - int ret; - - ret = build_elf_exec_info(buf, len, &ehdr, &elf_info); - if (ret) - return ret; - - elf_free_info(&elf_info); - - return elf_check_arch(&ehdr) ? 0 : -ENOEXEC; -} - -/** - * elf_exec_load - load ELF executable image - * @lowest_load_addr: On return, will be the address where the first PT_LOAD - * section will be loaded in memory. - * - * Return: - * 0 on success, negative value on failure. - */ -static int elf_exec_load(struct kimage *image, struct elfhdr *ehdr, - struct elf_info *elf_info, - unsigned long *lowest_load_addr) -{ - unsigned long base = 0, lowest_addr = UINT_MAX; - int ret; - size_t i; - struct kexec_buf kbuf = { .image = image, .buf_max = ppc64_rma_size, - .top_down = false }; - - /* Read in the PT_LOAD segments. */ - for (i = 0; i < ehdr->e_phnum; i++) { - unsigned long load_addr; - size_t size; - const struct elf_phdr *phdr; - - phdr = &elf_info->proghdrs[i]; - if (phdr->p_type != PT_LOAD) - continue; - - size = phdr->p_filesz; - if (size > phdr->p_memsz) - size = phdr->p_memsz; - - kbuf.buffer = (void *) elf_info->buffer + phdr->p_offset; - kbuf.bufsz = size; - kbuf.memsz = phdr->p_memsz; - kbuf.buf_align = phdr->p_align; - kbuf.buf_min = phdr->p_paddr + base; - kbuf.mem = KEXEC_BUF_MEM_UNKNOWN; - ret = kexec_add_buffer(&kbuf); - if (ret) - goto out; - load_addr = kbuf.mem; - - if (load_addr < lowest_addr) - lowest_addr = load_addr; - } - - /* Update entry point to reflect new load address. */ - ehdr->e_entry += base; - - *lowest_load_addr = lowest_addr; - ret = 0; - out: - return ret; -} - static void *elf64_load(struct kimage *image, char *kernel_buf, unsigned long kernel_len, char *initrd, unsigned long initrd_len, char *cmdline, @@ -570,18 +35,18 @@ static void *elf64_load(struct kimage *image, char *kernel_buf, void *fdt; const void *slave_code; struct elfhdr ehdr; - struct elf_info elf_info; + struct kexec_elf_info elf_info; struct kexec_buf kbuf = { .image = image, .buf_min = 0, .buf_max = ppc64_rma_size }; struct kexec_buf pbuf = { .image = image, .buf_min = 0, .buf_max = ppc64_rma_size, .top_down = true, .mem = KEXEC_BUF_MEM_UNKNOWN }; - ret = build_elf_exec_info(kernel_buf, kernel_len, &ehdr, &elf_info); + ret = kexec_build_elf_info(kernel_buf, kernel_len, &ehdr, &elf_info); if (ret) goto out; - ret = elf_exec_load(image, &ehdr, &elf_info, &kernel_load_addr); + ret = kexec_elf_load(image, &ehdr, &elf_info, &kbuf, &kernel_load_addr); if (ret) goto out; @@ -648,13 +113,13 @@ static void *elf64_load(struct kimage *image, char *kernel_buf, pr_err("Error setting up the purgatory.\n"); out: - elf_free_info(&elf_info); + kexec_free_elf_info(&elf_info); /* Make kimage_file_post_load_cleanup free the fdt buffer for us. */ return ret ? ERR_PTR(ret) : fdt; } const struct kexec_file_ops kexec_elf64_ops = { - .probe = elf64_probe, + .probe = kexec_elf_probe, .load = elf64_load, }; diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c index b7b3a5e4e224..617eba82531c 100644 --- a/arch/powerpc/kernel/kvm.c +++ b/arch/powerpc/kernel/kvm.c @@ -64,16 +64,17 @@ #define KVM_INST_MTSRIN 0x7c0001e4 static bool kvm_patching_worked = true; -char kvm_tmp[1024 * 1024]; +extern char kvm_tmp[]; +extern char kvm_tmp_end[]; static int kvm_tmp_index; -static inline void kvm_patch_ins(u32 *inst, u32 new_inst) +static void __init kvm_patch_ins(u32 *inst, u32 new_inst) { *inst = new_inst; flush_icache_range((ulong)inst, (ulong)inst + 4); } -static void kvm_patch_ins_ll(u32 *inst, long addr, u32 rt) +static void __init kvm_patch_ins_ll(u32 *inst, long addr, u32 rt) { #ifdef CONFIG_64BIT kvm_patch_ins(inst, KVM_INST_LD | rt | (addr & 0x0000fffc)); @@ -82,7 +83,7 @@ static void kvm_patch_ins_ll(u32 *inst, long addr, u32 rt) #endif } -static void kvm_patch_ins_ld(u32 *inst, long addr, u32 rt) +static void __init kvm_patch_ins_ld(u32 *inst, long addr, u32 rt) { #ifdef CONFIG_64BIT kvm_patch_ins(inst, KVM_INST_LD | rt | (addr & 0x0000fffc)); @@ -91,12 +92,12 @@ static void kvm_patch_ins_ld(u32 *inst, long addr, u32 rt) #endif } -static void kvm_patch_ins_lwz(u32 *inst, long addr, u32 rt) +static void __init kvm_patch_ins_lwz(u32 *inst, long addr, u32 rt) { kvm_patch_ins(inst, KVM_INST_LWZ | rt | (addr & 0x0000ffff)); } -static void kvm_patch_ins_std(u32 *inst, long addr, u32 rt) +static void __init kvm_patch_ins_std(u32 *inst, long addr, u32 rt) { #ifdef CONFIG_64BIT kvm_patch_ins(inst, KVM_INST_STD | rt | (addr & 0x0000fffc)); @@ -105,17 +106,17 @@ static void kvm_patch_ins_std(u32 *inst, long addr, u32 rt) #endif } -static void kvm_patch_ins_stw(u32 *inst, long addr, u32 rt) +static void __init kvm_patch_ins_stw(u32 *inst, long addr, u32 rt) { kvm_patch_ins(inst, KVM_INST_STW | rt | (addr & 0x0000fffc)); } -static void kvm_patch_ins_nop(u32 *inst) +static void __init kvm_patch_ins_nop(u32 *inst) { kvm_patch_ins(inst, KVM_INST_NOP); } -static void kvm_patch_ins_b(u32 *inst, int addr) +static void __init kvm_patch_ins_b(u32 *inst, int addr) { #if defined(CONFIG_RELOCATABLE) && defined(CONFIG_PPC_BOOK3S) /* On relocatable kernels interrupts handlers and our code @@ -128,11 +129,11 @@ static void kvm_patch_ins_b(u32 *inst, int addr) kvm_patch_ins(inst, KVM_INST_B | (addr & KVM_INST_B_MASK)); } -static u32 *kvm_alloc(int len) +static u32 * __init kvm_alloc(int len) { u32 *p; - if ((kvm_tmp_index + len) > ARRAY_SIZE(kvm_tmp)) { + if ((kvm_tmp_index + len) > (kvm_tmp_end - kvm_tmp)) { printk(KERN_ERR "KVM: No more space (%d + %d)\n", kvm_tmp_index, len); kvm_patching_worked = false; @@ -151,7 +152,7 @@ extern u32 kvm_emulate_mtmsrd_orig_ins_offs; extern u32 kvm_emulate_mtmsrd_len; extern u32 kvm_emulate_mtmsrd[]; -static void kvm_patch_ins_mtmsrd(u32 *inst, u32 rt) +static void __init kvm_patch_ins_mtmsrd(u32 *inst, u32 rt) { u32 *p; int distance_start; @@ -204,7 +205,7 @@ extern u32 kvm_emulate_mtmsr_orig_ins_offs; extern u32 kvm_emulate_mtmsr_len; extern u32 kvm_emulate_mtmsr[]; -static void kvm_patch_ins_mtmsr(u32 *inst, u32 rt) +static void __init kvm_patch_ins_mtmsr(u32 *inst, u32 rt) { u32 *p; int distance_start; @@ -265,7 +266,7 @@ extern u32 kvm_emulate_wrtee_orig_ins_offs; extern u32 kvm_emulate_wrtee_len; extern u32 kvm_emulate_wrtee[]; -static void kvm_patch_ins_wrtee(u32 *inst, u32 rt, int imm_one) +static void __init kvm_patch_ins_wrtee(u32 *inst, u32 rt, int imm_one) { u32 *p; int distance_start; @@ -322,7 +323,7 @@ extern u32 kvm_emulate_wrteei_0_branch_offs; extern u32 kvm_emulate_wrteei_0_len; extern u32 kvm_emulate_wrteei_0[]; -static void kvm_patch_ins_wrteei_0(u32 *inst) +static void __init kvm_patch_ins_wrteei_0(u32 *inst) { u32 *p; int distance_start; @@ -363,7 +364,7 @@ extern u32 kvm_emulate_mtsrin_orig_ins_offs; extern u32 kvm_emulate_mtsrin_len; extern u32 kvm_emulate_mtsrin[]; -static void kvm_patch_ins_mtsrin(u32 *inst, u32 rt, u32 rb) +static void __init kvm_patch_ins_mtsrin(u32 *inst, u32 rt, u32 rb) { u32 *p; int distance_start; @@ -399,7 +400,7 @@ static void kvm_patch_ins_mtsrin(u32 *inst, u32 rt, u32 rb) #endif -static void kvm_map_magic_page(void *data) +static void __init kvm_map_magic_page(void *data) { u32 *features = data; @@ -414,7 +415,7 @@ static void kvm_map_magic_page(void *data) *features = out[0]; } -static void kvm_check_ins(u32 *inst, u32 features) +static void __init kvm_check_ins(u32 *inst, u32 features) { u32 _inst = *inst; u32 inst_no_rt = _inst & ~KVM_MASK_RT; @@ -658,7 +659,7 @@ static void kvm_check_ins(u32 *inst, u32 features) extern u32 kvm_template_start[]; extern u32 kvm_template_end[]; -static void kvm_use_magic_page(void) +static void __init kvm_use_magic_page(void) { u32 *p; u32 *start, *end; @@ -699,25 +700,13 @@ static void kvm_use_magic_page(void) kvm_patching_worked ? "worked" : "failed"); } -static __init void kvm_free_tmp(void) -{ - /* - * Inform kmemleak about the hole in the .bss section since the - * corresponding pages will be unmapped with DEBUG_PAGEALLOC=y. - */ - kmemleak_free_part(&kvm_tmp[kvm_tmp_index], - ARRAY_SIZE(kvm_tmp) - kvm_tmp_index); - free_reserved_area(&kvm_tmp[kvm_tmp_index], - &kvm_tmp[ARRAY_SIZE(kvm_tmp)], -1, NULL); -} - static int __init kvm_guest_init(void) { if (!kvm_para_available()) - goto free_tmp; + return 0; if (!epapr_paravirt_enabled) - goto free_tmp; + return 0; if (kvm_para_has_feature(KVM_FEATURE_MAGIC_PAGE)) kvm_use_magic_page(); @@ -727,9 +716,6 @@ static int __init kvm_guest_init(void) powersave_nap = 1; #endif -free_tmp: - kvm_free_tmp(); - return 0; } diff --git a/arch/powerpc/kernel/kvm_emul.S b/arch/powerpc/kernel/kvm_emul.S index eb2568f583ae..7af6f8b50c5d 100644 --- a/arch/powerpc/kernel/kvm_emul.S +++ b/arch/powerpc/kernel/kvm_emul.S @@ -192,6 +192,8 @@ kvm_emulate_mtmsr_orig_ins_offs: kvm_emulate_mtmsr_len: .long (kvm_emulate_mtmsr_end - kvm_emulate_mtmsr) / 4 +#ifdef CONFIG_BOOKE + /* also used for wrteei 1 */ .global kvm_emulate_wrtee kvm_emulate_wrtee: @@ -285,6 +287,10 @@ kvm_emulate_wrteei_0_branch_offs: kvm_emulate_wrteei_0_len: .long (kvm_emulate_wrteei_0_end - kvm_emulate_wrteei_0) / 4 +#endif /* CONFIG_BOOKE */ + +#ifdef CONFIG_PPC_BOOK3S_32 + .global kvm_emulate_mtsrin kvm_emulate_mtsrin: @@ -334,5 +340,15 @@ kvm_emulate_mtsrin_orig_ins_offs: kvm_emulate_mtsrin_len: .long (kvm_emulate_mtsrin_end - kvm_emulate_mtsrin) / 4 +#endif /* CONFIG_PPC_BOOK3S_32 */ + + .balign 4 + .global kvm_tmp +kvm_tmp: + .space (64 * 1024) + +.global kvm_tmp_end +kvm_tmp_end: + .global kvm_template_end kvm_template_end: diff --git a/arch/powerpc/kernel/machine_kexec_64.c b/arch/powerpc/kernel/machine_kexec_64.c index 18481b0e2788..04a7cba58eff 100644 --- a/arch/powerpc/kernel/machine_kexec_64.c +++ b/arch/powerpc/kernel/machine_kexec_64.c @@ -29,6 +29,8 @@ #include <asm/smp.h> #include <asm/hw_breakpoint.h> #include <asm/asm-prototypes.h> +#include <asm/svm.h> +#include <asm/ultravisor.h> int default_machine_kexec_prepare(struct kimage *image) { @@ -327,6 +329,13 @@ void default_machine_kexec(struct kimage *image) #ifdef CONFIG_PPC_PSERIES kexec_paca.lppaca_ptr = NULL; #endif + + if (is_secure_guest() && !(image->preserve_context || + image->type == KEXEC_TYPE_CRASH)) { + uv_unshare_all_pages(); + printk("kexec: Unshared all shared pages.\n"); + } + paca_ptrs[kexec_paca.paca_index] = &kexec_paca; setup_paca(&kexec_paca); diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c index b18df633eae9..34c1001e9e8b 100644 --- a/arch/powerpc/kernel/mce.c +++ b/arch/powerpc/kernel/mce.c @@ -33,13 +33,18 @@ static DEFINE_PER_CPU(struct machine_check_event[MAX_MC_EVT], mce_ue_event_queue); static void machine_check_process_queued_event(struct irq_work *work); -void machine_check_ue_event(struct machine_check_event *evt); +static void machine_check_ue_irq_work(struct irq_work *work); +static void machine_check_ue_event(struct machine_check_event *evt); static void machine_process_ue_event(struct work_struct *work); static struct irq_work mce_event_process_work = { .func = machine_check_process_queued_event, }; +static struct irq_work mce_ue_event_irq_work = { + .func = machine_check_ue_irq_work, +}; + DECLARE_WORK(mce_ue_event_work, machine_process_ue_event); static void mce_set_error_info(struct machine_check_event *mce, @@ -144,6 +149,7 @@ void save_mce_event(struct pt_regs *regs, long handled, if (phys_addr != ULONG_MAX) { mce->u.ue_error.physical_address_provided = true; mce->u.ue_error.physical_address = phys_addr; + mce->u.ue_error.ignore_event = mce_err->ignore_event; machine_check_ue_event(mce); } } @@ -199,11 +205,15 @@ void release_mce_event(void) get_mce_event(NULL, true); } +static void machine_check_ue_irq_work(struct irq_work *work) +{ + schedule_work(&mce_ue_event_work); +} /* * Queue up the MCE event which then can be handled later. */ -void machine_check_ue_event(struct machine_check_event *evt) +static void machine_check_ue_event(struct machine_check_event *evt) { int index; @@ -216,7 +226,7 @@ void machine_check_ue_event(struct machine_check_event *evt) memcpy(this_cpu_ptr(&mce_ue_event_queue[index]), evt, sizeof(*evt)); /* Queue work to process this event later. */ - schedule_work(&mce_ue_event_work); + irq_work_queue(&mce_ue_event_irq_work); } /* @@ -257,8 +267,17 @@ static void machine_process_ue_event(struct work_struct *work) /* * This should probably queued elsewhere, but * oh! well + * + * Don't report this machine check because the caller has a + * asked us to ignore the event, it has a fixup handler which + * will do the appropriate error handling and reporting. */ if (evt->error_type == MCE_ERROR_TYPE_UE) { + if (evt->u.ue_error.ignore_event) { + __this_cpu_dec(mce_ue_count); + continue; + } + if (evt->u.ue_error.physical_address_provided) { unsigned long pfn; @@ -292,6 +311,12 @@ static void machine_check_process_queued_event(struct irq_work *work) while (__this_cpu_read(mce_queue_count) > 0) { index = __this_cpu_read(mce_queue_count) - 1; evt = this_cpu_ptr(&mce_event_queue[index]); + + if (evt->error_type == MCE_ERROR_TYPE_UE && + evt->u.ue_error.ignore_event) { + __this_cpu_dec(mce_queue_count); + continue; + } machine_check_print_event_info(evt, false, false); __this_cpu_dec(mce_queue_count); } @@ -300,7 +325,7 @@ static void machine_check_process_queued_event(struct irq_work *work) void machine_check_print_event_info(struct machine_check_event *evt, bool user_mode, bool in_guest) { - const char *level, *sevstr, *subtype, *err_type; + const char *level, *sevstr, *subtype, *err_type, *initiator; uint64_t ea = 0, pa = 0; int n = 0; char dar_str[50]; @@ -385,6 +410,28 @@ void machine_check_print_event_info(struct machine_check_event *evt, break; } + switch(evt->initiator) { + case MCE_INITIATOR_CPU: + initiator = "CPU"; + break; + case MCE_INITIATOR_PCI: + initiator = "PCI"; + break; + case MCE_INITIATOR_ISA: + initiator = "ISA"; + break; + case MCE_INITIATOR_MEMORY: + initiator = "Memory"; + break; + case MCE_INITIATOR_POWERMGM: + initiator = "Power Management"; + break; + case MCE_INITIATOR_UNKNOWN: + default: + initiator = "Unknown"; + break; + } + switch (evt->error_type) { case MCE_ERROR_TYPE_UE: err_type = "UE"; @@ -451,6 +498,14 @@ void machine_check_print_event_info(struct machine_check_event *evt, if (evt->u.link_error.effective_address_provided) ea = evt->u.link_error.effective_address; break; + case MCE_ERROR_TYPE_DCACHE: + err_type = "D-Cache"; + subtype = "Unknown"; + break; + case MCE_ERROR_TYPE_ICACHE: + err_type = "I-Cache"; + subtype = "Unknown"; + break; default: case MCE_ERROR_TYPE_UNKNOWN: err_type = "Unknown"; @@ -483,9 +538,17 @@ void machine_check_print_event_info(struct machine_check_event *evt, level, evt->cpu, evt->srr0, (void *)evt->srr0, pa_str); } + printk("%sMCE: CPU%d: Initiator %s\n", level, evt->cpu, initiator); + subtype = evt->error_class < ARRAY_SIZE(mc_error_class) ? mc_error_class[evt->error_class] : "Unknown"; printk("%sMCE: CPU%d: %s\n", level, evt->cpu, subtype); + +#ifdef CONFIG_PPC_BOOK3S_64 + /* Display faulty slb contents for SLB errors. */ + if (evt->error_type == MCE_ERROR_TYPE_SLB) + slb_dump_contents(local_paca->mce_faulty_slbs); +#endif } EXPORT_SYMBOL_GPL(machine_check_print_event_info); diff --git a/arch/powerpc/kernel/mce_power.c b/arch/powerpc/kernel/mce_power.c index a814d2dfb5b0..1cbf7f1a4e3d 100644 --- a/arch/powerpc/kernel/mce_power.c +++ b/arch/powerpc/kernel/mce_power.c @@ -11,6 +11,7 @@ #include <linux/types.h> #include <linux/ptrace.h> +#include <linux/extable.h> #include <asm/mmu.h> #include <asm/mce.h> #include <asm/machdep.h> @@ -18,6 +19,7 @@ #include <asm/pte-walk.h> #include <asm/sstep.h> #include <asm/exception-64s.h> +#include <asm/extable.h> /* * Convert an address related to an mm to a PFN. NOTE: we are in real @@ -26,7 +28,8 @@ unsigned long addr_to_pfn(struct pt_regs *regs, unsigned long addr) { pte_t *ptep; - unsigned long flags; + unsigned int shift; + unsigned long pfn, flags; struct mm_struct *mm; if (user_mode(regs)) @@ -35,14 +38,23 @@ unsigned long addr_to_pfn(struct pt_regs *regs, unsigned long addr) mm = &init_mm; local_irq_save(flags); - if (mm == current->mm) - ptep = find_current_mm_pte(mm->pgd, addr, NULL, NULL); - else - ptep = find_init_mm_pte(addr, NULL); + ptep = __find_linux_pte(mm->pgd, addr, NULL, &shift); + + if (!ptep || pte_special(*ptep)) { + pfn = ULONG_MAX; + goto out; + } + + if (shift <= PAGE_SHIFT) + pfn = pte_pfn(*ptep); + else { + unsigned long rpnmask = (1ul << shift) - PAGE_SIZE; + pfn = pte_pfn(__pte(pte_val(*ptep) | (addr & rpnmask))); + } + +out: local_irq_restore(flags); - if (!ptep || pte_special(*ptep)) - return ULONG_MAX; - return pte_pfn(*ptep); + return pfn; } /* flush SLBs and reload */ @@ -344,7 +356,7 @@ static const struct mce_derror_table mce_p9_derror_table[] = { MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true }, { 0, false, 0, 0, 0, 0, 0 } }; -static int mce_find_instr_ea_and_pfn(struct pt_regs *regs, uint64_t *addr, +static int mce_find_instr_ea_and_phys(struct pt_regs *regs, uint64_t *addr, uint64_t *phys_addr) { /* @@ -397,6 +409,8 @@ static int mce_handle_ierror(struct pt_regs *regs, /* attempt to correct the error */ switch (table[i].error_type) { case MCE_ERROR_TYPE_SLB: + if (local_paca->in_mce == 1) + slb_save_contents(local_paca->mce_faulty_slbs); handled = mce_flush(MCE_FLUSH_SLB); break; case MCE_ERROR_TYPE_ERAT: @@ -482,6 +496,8 @@ static int mce_handle_derror(struct pt_regs *regs, /* attempt to correct the error */ switch (table[i].error_type) { case MCE_ERROR_TYPE_SLB: + if (local_paca->in_mce == 1) + slb_save_contents(local_paca->mce_faulty_slbs); if (mce_flush(MCE_FLUSH_SLB)) handled = 1; break; @@ -541,7 +557,8 @@ static int mce_handle_derror(struct pt_regs *regs, * kernel/exception-64s.h */ if (get_paca()->in_mce < MAX_MCE_DEPTH) - mce_find_instr_ea_and_pfn(regs, addr, phys_addr); + mce_find_instr_ea_and_phys(regs, addr, + phys_addr); } found = 1; } @@ -558,9 +575,18 @@ static int mce_handle_derror(struct pt_regs *regs, return 0; } -static long mce_handle_ue_error(struct pt_regs *regs) +static long mce_handle_ue_error(struct pt_regs *regs, + struct mce_error_info *mce_err) { long handled = 0; + const struct exception_table_entry *entry; + + entry = search_kernel_exception_table(regs->nip); + if (entry) { + mce_err->ignore_event = true; + regs->nip = extable_fixup(entry); + return 1; + } /* * On specific SCOM read via MMIO we may get a machine check @@ -593,7 +619,7 @@ static long mce_handle_error(struct pt_regs *regs, &phys_addr); if (!handled && mce_err.error_type == MCE_ERROR_TYPE_UE) - handled = mce_handle_ue_error(regs); + handled = mce_handle_ue_error(regs, &mce_err); save_mce_event(regs, handled, &mce_err, regs->nip, addr, phys_addr); diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S index fe4bd321730e..82df4b09e79f 100644 --- a/arch/powerpc/kernel/misc_32.S +++ b/arch/powerpc/kernel/misc_32.S @@ -292,22 +292,20 @@ _GLOBAL(flush_instruction_cache) iccci 0,r3 #endif #elif defined(CONFIG_FSL_BOOKE) -BEGIN_FTR_SECTION +#ifdef CONFIG_E200 mfspr r3,SPRN_L1CSR0 ori r3,r3,L1CSR0_CFI|L1CSR0_CLFC /* msync; isync recommended here */ mtspr SPRN_L1CSR0,r3 isync blr -END_FTR_SECTION_IFSET(CPU_FTR_UNIFIED_ID_CACHE) +#endif mfspr r3,SPRN_L1CSR1 ori r3,r3,L1CSR1_ICFI|L1CSR1_ICLFR mtspr SPRN_L1CSR1,r3 +#elif defined(CONFIG_PPC_BOOK3S_601) + blr /* for 601, do nothing */ #else - mfspr r3,SPRN_PVR - rlwinm r3,r3,16,16,31 - cmpwi 0,r3,1 - beqlr /* for 601, do nothing */ /* 603/604 processor - use invalidate-all bit in HID0 */ mfspr r3,SPRN_HID0 ori r3,r3,HID0_ICFI @@ -326,10 +324,10 @@ EXPORT_SYMBOL(flush_instruction_cache) * flush_icache_range(unsigned long start, unsigned long stop) */ _GLOBAL(flush_icache_range) -BEGIN_FTR_SECTION +#if defined(CONFIG_PPC_BOOK3S_601) || defined(CONFIG_E200) PURGE_PREFETCHED_INS - blr /* for 601, do nothing */ -END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE) + blr /* for 601 and e200, do nothing */ +#else rlwinm r3,r3,0,0,31 - L1_CACHE_SHIFT subf r4,r3,r4 addi r4,r4,L1_CACHE_BYTES - 1 @@ -355,6 +353,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE) sync /* additional sync needed on g4 */ isync blr +#endif _ASM_NOKPROBE_SYMBOL(flush_icache_range) EXPORT_SYMBOL(flush_icache_range) @@ -362,15 +361,15 @@ EXPORT_SYMBOL(flush_icache_range) * 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. - * This is a no-op on the 601 which has a unified cache. + * This is a no-op on the 601 and e200 which have a unified cache. * * void __flush_dcache_icache(void *page) */ _GLOBAL(__flush_dcache_icache) -BEGIN_FTR_SECTION +#if defined(CONFIG_PPC_BOOK3S_601) || defined(CONFIG_E200) PURGE_PREFETCHED_INS blr -END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE) +#else rlwinm r3,r3,0,0,31-PAGE_SHIFT /* Get page base address */ li r4,PAGE_SIZE/L1_CACHE_BYTES /* Number of lines in a page */ mtctr r4 @@ -398,6 +397,7 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_44x) sync isync blr +#endif #ifndef CONFIG_BOOKE /* @@ -409,10 +409,10 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_44x) * void __flush_dcache_icache_phys(unsigned long physaddr) */ _GLOBAL(__flush_dcache_icache_phys) -BEGIN_FTR_SECTION +#if defined(CONFIG_PPC_BOOK3S_601) || defined(CONFIG_E200) PURGE_PREFETCHED_INS - blr /* for 601, do nothing */ -END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE) + blr /* for 601 and e200, do nothing */ +#else mfmsr r10 rlwinm r0,r10,0,28,26 /* clear DR */ mtmsr r0 @@ -433,6 +433,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE) mtmsr r10 /* restore DR */ isync blr +#endif #endif /* CONFIG_BOOKE */ /* @@ -452,7 +453,12 @@ END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE) stwu r9,16(r3) _GLOBAL(copy_page) + rlwinm r5, r3, 0, L1_CACHE_BYTES - 1 addi r3,r3,-4 + +0: twnei r5, 0 /* WARN if r3 is not cache aligned */ + EMIT_BUG_ENTRY 0b,__FILE__,__LINE__, BUGFLAG_WARNING + addi r4,r4,-4 li r5,4 diff --git a/arch/powerpc/kernel/note.S b/arch/powerpc/kernel/note.S new file mode 100644 index 000000000000..bcdad15395dd --- /dev/null +++ b/arch/powerpc/kernel/note.S @@ -0,0 +1,40 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * PowerPC ELF notes. + * + * Copyright 2019, IBM Corporation + */ + +#include <linux/elfnote.h> +#include <asm/elfnote.h> + +/* + * Ultravisor-capable bit (PowerNV only). + * + * Bit 0 indicates that the powerpc kernel binary knows how to run in an + * ultravisor-enabled system. + * + * In an ultravisor-enabled system, some machine resources are now controlled + * by the ultravisor. If the kernel is not ultravisor-capable, but it ends up + * being run on a machine with ultravisor, the kernel will probably crash + * trying to access ultravisor resources. For instance, it may crash in early + * boot trying to set the partition table entry 0. + * + * In an ultravisor-enabled system, a bootloader could warn the user or prevent + * the kernel from being run if the PowerPC ultravisor capability doesn't exist + * or the Ultravisor-capable bit is not set. + */ +#ifdef CONFIG_PPC_POWERNV +#define PPCCAP_ULTRAVISOR_BIT (1 << 0) +#else +#define PPCCAP_ULTRAVISOR_BIT 0 +#endif + +/* + * Add the PowerPC Capabilities in the binary ELF note. It is a bitmap that + * can be used to advertise kernel capabilities to userland. + */ +#define PPC_CAPABILITIES_BITMAP (PPCCAP_ULTRAVISOR_BIT) + +ELFNOTE(PowerPC, PPC_ELFNOTE_CAPABILITIES, + .long PPC_CAPABILITIES_BITMAP) diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c index e3ad8aa4730d..949eceb254d8 100644 --- a/arch/powerpc/kernel/paca.c +++ b/arch/powerpc/kernel/paca.c @@ -14,6 +14,8 @@ #include <asm/sections.h> #include <asm/pgtable.h> #include <asm/kexec.h> +#include <asm/svm.h> +#include <asm/ultravisor.h> #include "setup.h" @@ -52,6 +54,43 @@ static void *__init alloc_paca_data(unsigned long size, unsigned long align, #ifdef CONFIG_PPC_PSERIES +#define LPPACA_SIZE 0x400 + +static void *__init alloc_shared_lppaca(unsigned long size, unsigned long align, + unsigned long limit, int cpu) +{ + size_t shared_lppaca_total_size = PAGE_ALIGN(nr_cpu_ids * LPPACA_SIZE); + static unsigned long shared_lppaca_size; + static void *shared_lppaca; + void *ptr; + + if (!shared_lppaca) { + memblock_set_bottom_up(true); + + shared_lppaca = + memblock_alloc_try_nid(shared_lppaca_total_size, + PAGE_SIZE, MEMBLOCK_LOW_LIMIT, + limit, NUMA_NO_NODE); + if (!shared_lppaca) + panic("cannot allocate shared data"); + + memblock_set_bottom_up(false); + uv_share_page(PHYS_PFN(__pa(shared_lppaca)), + shared_lppaca_total_size >> PAGE_SHIFT); + } + + ptr = shared_lppaca + shared_lppaca_size; + shared_lppaca_size += size; + + /* + * This is very early in boot, so no harm done if the kernel crashes at + * this point. + */ + BUG_ON(shared_lppaca_size >= shared_lppaca_total_size); + + return ptr; +} + /* * See asm/lppaca.h for more detail. * @@ -65,7 +104,7 @@ static inline void init_lppaca(struct lppaca *lppaca) *lppaca = (struct lppaca) { .desc = cpu_to_be32(0xd397d781), /* "LpPa" */ - .size = cpu_to_be16(0x400), + .size = cpu_to_be16(LPPACA_SIZE), .fpregs_in_use = 1, .slb_count = cpu_to_be16(64), .vmxregs_in_use = 0, @@ -75,19 +114,22 @@ static inline void init_lppaca(struct lppaca *lppaca) static struct lppaca * __init new_lppaca(int cpu, unsigned long limit) { struct lppaca *lp; - size_t size = 0x400; - BUILD_BUG_ON(size < sizeof(struct lppaca)); + BUILD_BUG_ON(sizeof(struct lppaca) > LPPACA_SIZE); if (early_cpu_has_feature(CPU_FTR_HVMODE)) return NULL; - lp = alloc_paca_data(size, 0x400, limit, cpu); + if (is_secure_guest()) + lp = alloc_shared_lppaca(LPPACA_SIZE, 0x400, limit, cpu); + else + lp = alloc_paca_data(LPPACA_SIZE, 0x400, limit, cpu); + init_lppaca(lp); return lp; } -#endif /* CONFIG_PPC_BOOK3S */ +#endif /* CONFIG_PPC_PSERIES */ #ifdef CONFIG_PPC_BOOK3S_64 diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index f627e15bb43c..1c448cf25506 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -1379,10 +1379,6 @@ void __init pcibios_resource_survey(void) pr_debug("PCI: Assigning unassigned resources...\n"); pci_assign_unassigned_resources(); } - - /* Call machine dependent fixup */ - if (ppc_md.pcibios_fixup) - ppc_md.pcibios_fixup(); } /* This is used by the PCI hotplug driver to allocate resource diff --git a/arch/powerpc/kernel/pci-hotplug.c b/arch/powerpc/kernel/pci-hotplug.c index 0b0cf8168b47..fc62c4bc47b1 100644 --- a/arch/powerpc/kernel/pci-hotplug.c +++ b/arch/powerpc/kernel/pci-hotplug.c @@ -55,11 +55,18 @@ EXPORT_SYMBOL_GPL(pci_find_bus_by_node); void pcibios_release_device(struct pci_dev *dev) { struct pci_controller *phb = pci_bus_to_host(dev->bus); + struct pci_dn *pdn = pci_get_pdn(dev); eeh_remove_device(dev); if (phb->controller_ops.release_device) phb->controller_ops.release_device(dev); + + /* free()ing the pci_dn has been deferred to us, do it now */ + if (pdn && (pdn->flags & PCI_DN_FLAG_DEAD)) { + pci_dbg(dev, "freeing dead pdn\n"); + kfree(pdn); + } } /** diff --git a/arch/powerpc/kernel/pci_32.c b/arch/powerpc/kernel/pci_32.c index 50942a1d1a5f..b49e1060a3bf 100644 --- a/arch/powerpc/kernel/pci_32.c +++ b/arch/powerpc/kernel/pci_32.c @@ -263,6 +263,10 @@ static int __init pcibios_init(void) /* Call common code to handle resource allocation */ pcibios_resource_survey(); + /* Call machine dependent fixup */ + if (ppc_md.pcibios_fixup) + ppc_md.pcibios_fixup(); + /* Call machine dependent post-init code */ if (ppc_md.pcibios_after_init) ppc_md.pcibios_after_init(); diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c index b7030b1189d0..f83d1f69b1dd 100644 --- a/arch/powerpc/kernel/pci_64.c +++ b/arch/powerpc/kernel/pci_64.c @@ -54,14 +54,20 @@ static int __init pcibios_init(void) pci_add_flags(PCI_ENABLE_PROC_DOMAINS | PCI_COMPAT_DOMAIN_0); /* Scan all of the recorded PCI controllers. */ - list_for_each_entry_safe(hose, tmp, &hose_list, list_node) { + list_for_each_entry_safe(hose, tmp, &hose_list, list_node) pcibios_scan_phb(hose); - pci_bus_add_devices(hose->bus); - } /* Call common code to handle resource allocation */ pcibios_resource_survey(); + /* Add devices. */ + list_for_each_entry_safe(hose, tmp, &hose_list, list_node) + pci_bus_add_devices(hose->bus); + + /* Call machine dependent fixup */ + if (ppc_md.pcibios_fixup) + ppc_md.pcibios_fixup(); + printk(KERN_DEBUG "PCI: Probing PCI hardware done\n"); return 0; diff --git a/arch/powerpc/kernel/pci_dn.c b/arch/powerpc/kernel/pci_dn.c index c4c8c237a106..9524009ca1ae 100644 --- a/arch/powerpc/kernel/pci_dn.c +++ b/arch/powerpc/kernel/pci_dn.c @@ -323,6 +323,7 @@ void pci_remove_device_node_info(struct device_node *dn) { struct pci_dn *pdn = dn ? PCI_DN(dn) : NULL; struct device_node *parent; + struct pci_dev *pdev; #ifdef CONFIG_EEH struct eeh_dev *edev = pdn_to_eeh_dev(pdn); @@ -336,12 +337,28 @@ void pci_remove_device_node_info(struct device_node *dn) WARN_ON(!list_empty(&pdn->child_list)); list_del(&pdn->list); + /* Drop the parent pci_dn's ref to our backing dt node */ parent = of_get_parent(dn); if (parent) of_node_put(parent); - dn->data = NULL; - kfree(pdn); + /* + * At this point we *might* still have a pci_dev that was + * instantiated from this pci_dn. So defer free()ing it until + * the pci_dev's release function is called. + */ + pdev = pci_get_domain_bus_and_slot(pdn->phb->global_number, + pdn->busno, pdn->devfn); + if (pdev) { + /* NB: pdev has a ref to dn */ + pci_dbg(pdev, "marked pdn (from %pOF) as dead\n", dn); + pdn->flags |= PCI_DN_FLAG_DEAD; + } else { + dn->data = NULL; + kfree(pdn); + } + + pci_dev_put(pdev); } EXPORT_SYMBOL_GPL(pci_remove_device_node_info); diff --git a/arch/powerpc/kernel/pci_of_scan.c b/arch/powerpc/kernel/pci_of_scan.c index 409c6c1beabf..f91d7e94872e 100644 --- a/arch/powerpc/kernel/pci_of_scan.c +++ b/arch/powerpc/kernel/pci_of_scan.c @@ -34,31 +34,75 @@ static u32 get_int_prop(struct device_node *np, const char *name, u32 def) * pci_parse_of_flags - Parse the flags cell of a device tree PCI address * @addr0: value of 1st cell of a device tree PCI address. * @bridge: Set this flag if the address is from a bridge 'ranges' property + * + * PCI Bus Binding to IEEE Std 1275-1994 + * + * Bit# 33222222 22221111 11111100 00000000 + * 10987654 32109876 54321098 76543210 + * phys.hi cell: npt000ss bbbbbbbb dddddfff rrrrrrrr + * phys.mid cell: hhhhhhhh hhhhhhhh hhhhhhhh hhhhhhhh + * phys.lo cell: llllllll llllllll llllllll llllllll + * + * where: + * n is 0 if the address is relocatable, 1 otherwise + * p is 1 if the addressable region is "prefetchable", 0 otherwise + * t is 1 if the address is aliased (for non-relocatable I/O), + * below 1 MB (for Memory),or below 64 KB (for relocatable I/O). + * ss is the space code, denoting the address space: + * 00 denotes Configuration Space + * 01 denotes I/O Space + * 10 denotes 32-bit-address Memory Space + * 11 denotes 64-bit-address Memory Space + * bbbbbbbb is the 8-bit Bus Number + * ddddd is the 5-bit Device Number + * fff is the 3-bit Function Number + * rrrrrrrr is the 8-bit Register Number */ +#define OF_PCI_ADDR0_SPACE(ss) (((ss)&3)<<24) +#define OF_PCI_ADDR0_SPACE_CFG OF_PCI_ADDR0_SPACE(0) +#define OF_PCI_ADDR0_SPACE_IO OF_PCI_ADDR0_SPACE(1) +#define OF_PCI_ADDR0_SPACE_MMIO32 OF_PCI_ADDR0_SPACE(2) +#define OF_PCI_ADDR0_SPACE_MMIO64 OF_PCI_ADDR0_SPACE(3) +#define OF_PCI_ADDR0_SPACE_MASK OF_PCI_ADDR0_SPACE(3) +#define OF_PCI_ADDR0_RELOC (1UL<<31) +#define OF_PCI_ADDR0_PREFETCH (1UL<<30) +#define OF_PCI_ADDR0_ALIAS (1UL<<29) +#define OF_PCI_ADDR0_BUS 0x00FF0000UL +#define OF_PCI_ADDR0_DEV 0x0000F800UL +#define OF_PCI_ADDR0_FN 0x00000700UL +#define OF_PCI_ADDR0_BARREG 0x000000FFUL + unsigned int pci_parse_of_flags(u32 addr0, int bridge) { - unsigned int flags = 0; + unsigned int flags = 0, as = addr0 & OF_PCI_ADDR0_SPACE_MASK; - if (addr0 & 0x02000000) { + if (as == OF_PCI_ADDR0_SPACE_MMIO32 || as == OF_PCI_ADDR0_SPACE_MMIO64) { 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 - | PCI_BASE_ADDRESS_MEM_PREFETCH; + + if (as == OF_PCI_ADDR0_SPACE_MMIO64) + flags |= PCI_BASE_ADDRESS_MEM_TYPE_64 | IORESOURCE_MEM_64; + + if (addr0 & OF_PCI_ADDR0_ALIAS) + flags |= PCI_BASE_ADDRESS_MEM_TYPE_1M; + + if (addr0 & OF_PCI_ADDR0_PREFETCH) + flags |= IORESOURCE_PREFETCH | + PCI_BASE_ADDRESS_MEM_PREFETCH; + /* Note: We don't know whether the ROM has been left enabled * by the firmware or not. We mark it as disabled (ie, we do * not set the IORESOURCE_ROM_ENABLE flag) for now rather than * do a config space read, it will be force-enabled if needed */ - if (!bridge && (addr0 & 0xff) == 0x30) + if (!bridge && (addr0 & OF_PCI_ADDR0_BARREG) == PCI_ROM_ADDRESS) flags |= IORESOURCE_READONLY; - } else if (addr0 & 0x01000000) + + } else if (as == OF_PCI_ADDR0_SPACE_IO) flags = IORESOURCE_IO | PCI_BASE_ADDRESS_SPACE_IO; + if (flags) flags |= IORESOURCE_SIZEALIGN; + return flags; } diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 7a84c9f1778e..639ceae7da9d 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -1587,8 +1587,9 @@ static void setup_ksp_vsid(struct task_struct *p, unsigned long sp) /* * Copy architecture-specific thread state */ -int copy_thread(unsigned long clone_flags, unsigned long usp, - unsigned long kthread_arg, struct task_struct *p) +int copy_thread_tls(unsigned long clone_flags, unsigned long usp, + unsigned long kthread_arg, struct task_struct *p, + unsigned long tls) { struct pt_regs *childregs, *kregs; extern void ret_from_fork(void); @@ -1629,10 +1630,10 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, if (clone_flags & CLONE_SETTLS) { #ifdef CONFIG_PPC64 if (!is_32bit_task()) - childregs->gpr[13] = childregs->gpr[6]; + childregs->gpr[13] = tls; else #endif - childregs->gpr[2] = childregs->gpr[6]; + childregs->gpr[2] = tls; } f = ret_from_fork; @@ -2033,10 +2034,8 @@ void show_stack(struct task_struct *tsk, unsigned long *stack) int count = 0; int firstframe = 1; #ifdef CONFIG_FUNCTION_GRAPH_TRACER - struct ftrace_ret_stack *ret_stack; - extern void return_to_handler(void); - unsigned long rth = (unsigned long)return_to_handler; - int curr_frame = 0; + unsigned long ret_addr; + int ftrace_idx = 0; #endif if (tsk == NULL) @@ -2065,15 +2064,10 @@ void show_stack(struct task_struct *tsk, unsigned long *stack) if (!firstframe || ip != lr) { printk("["REG"] ["REG"] %pS", sp, ip, (void *)ip); #ifdef CONFIG_FUNCTION_GRAPH_TRACER - if ((ip == rth) && curr_frame >= 0) { - ret_stack = ftrace_graph_get_ret_stack(current, - curr_frame++); - if (ret_stack) - pr_cont(" (%pS)", - (void *)ret_stack->ret); - else - curr_frame = -1; - } + ret_addr = ftrace_graph_ret_addr(current, + &ftrace_idx, ip, stack); + if (ret_addr != ip) + pr_cont(" (%pS)", (void *)ret_addr); #endif if (firstframe) pr_cont(" (unreliable)"); diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index 7159e791a70d..6620f37abe73 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -55,6 +55,7 @@ #include <asm/firmware.h> #include <asm/dt_cpu_ftrs.h> #include <asm/drmem.h> +#include <asm/ultravisor.h> #include <mm/mmu_decl.h> @@ -702,9 +703,12 @@ void __init early_init_devtree(void *params) #ifdef CONFIG_PPC_POWERNV /* Some machines might need OPAL info for debugging, grab it now. */ of_scan_flat_dt(early_init_dt_scan_opal, NULL); + + /* Scan tree for ultravisor feature */ + of_scan_flat_dt(early_init_dt_scan_ultravisor, NULL); #endif -#ifdef CONFIG_FA_DUMP +#if defined(CONFIG_FA_DUMP) || defined(CONFIG_PRESERVE_FA_DUMP) /* scan tree to see if dump is active during last boot */ of_scan_flat_dt(early_init_dt_scan_fw_dump, NULL); #endif @@ -731,7 +735,7 @@ void __init early_init_devtree(void *params) if (PHYSICAL_START > MEMORY_START) memblock_reserve(MEMORY_START, 0x8000); reserve_kdump_trampoline(); -#ifdef CONFIG_FA_DUMP +#if defined(CONFIG_FA_DUMP) || defined(CONFIG_PRESERVE_FA_DUMP) /* * If we fail to reserve memory for firmware-assisted dump then * fallback to kexec based kdump. diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index 514707ef6779..a4e7762dd286 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -40,6 +40,7 @@ #include <asm/sections.h> #include <asm/machdep.h> #include <asm/asm-prototypes.h> +#include <asm/ultravisor-api.h> #include <linux/linux_logo.h> @@ -94,7 +95,7 @@ static int of_workarounds __prombss; #define PROM_BUG() do { \ prom_printf("kernel BUG at %s line 0x%x!\n", \ __FILE__, __LINE__); \ - __asm__ __volatile__(".long " BUG_ILLEGAL_INSTR); \ + __builtin_trap(); \ } while (0) #ifdef DEBUG_PROM @@ -171,6 +172,10 @@ static bool __prombss prom_radix_disable; static bool __prombss prom_xive_disable; #endif +#ifdef CONFIG_PPC_SVM +static bool __prombss prom_svm_enable; +#endif + struct platform_support { bool hash_mmu; bool radix_mmu; @@ -812,6 +817,17 @@ static void __init early_cmdline_parse(void) prom_debug("XIVE disabled from cmdline\n"); } #endif /* CONFIG_PPC_PSERIES */ + +#ifdef CONFIG_PPC_SVM + opt = prom_strstr(prom_cmd_line, "svm="); + if (opt) { + bool val; + + opt += sizeof("svm=") - 1; + if (!prom_strtobool(opt, &val)) + prom_svm_enable = val; + } +#endif /* CONFIG_PPC_SVM */ } #ifdef CONFIG_PPC_PSERIES @@ -1712,6 +1728,43 @@ static void __init prom_close_stdin(void) } } +#ifdef CONFIG_PPC_SVM +static int prom_rtas_hcall(uint64_t args) +{ + register uint64_t arg1 asm("r3") = H_RTAS; + register uint64_t arg2 asm("r4") = args; + + asm volatile("sc 1\n" : "=r" (arg1) : + "r" (arg1), + "r" (arg2) :); + return arg1; +} + +static struct rtas_args __prombss os_term_args; + +static void __init prom_rtas_os_term(char *str) +{ + phandle rtas_node; + __be32 val; + u32 token; + + prom_debug("%s: start...\n", __func__); + rtas_node = call_prom("finddevice", 1, 1, ADDR("/rtas")); + prom_debug("rtas_node: %x\n", rtas_node); + if (!PHANDLE_VALID(rtas_node)) + return; + + val = 0; + prom_getprop(rtas_node, "ibm,os-term", &val, sizeof(val)); + token = be32_to_cpu(val); + prom_debug("ibm,os-term: %x\n", token); + if (token == 0) + prom_panic("Could not get token for ibm,os-term\n"); + os_term_args.token = cpu_to_be32(token); + prom_rtas_hcall((uint64_t)&os_term_args); +} +#endif /* CONFIG_PPC_SVM */ + /* * Allocate room for and instantiate RTAS */ @@ -3168,6 +3221,46 @@ static void unreloc_toc(void) #endif #endif +#ifdef CONFIG_PPC_SVM +/* + * Perform the Enter Secure Mode ultracall. + */ +static int enter_secure_mode(unsigned long kbase, unsigned long fdt) +{ + register unsigned long r3 asm("r3") = UV_ESM; + register unsigned long r4 asm("r4") = kbase; + register unsigned long r5 asm("r5") = fdt; + + asm volatile("sc 2" : "+r"(r3) : "r"(r4), "r"(r5)); + + return r3; +} + +/* + * Call the Ultravisor to transfer us to secure memory if we have an ESM blob. + */ +static void setup_secure_guest(unsigned long kbase, unsigned long fdt) +{ + int ret; + + if (!prom_svm_enable) + return; + + /* Switch to secure mode. */ + prom_printf("Switching to secure mode.\n"); + + ret = enter_secure_mode(kbase, fdt); + if (ret != U_SUCCESS) { + prom_printf("Returned %d from switching to secure mode.\n", ret); + prom_rtas_os_term("Switch to secure mode failed.\n"); + } +} +#else +static void setup_secure_guest(unsigned long kbase, unsigned long fdt) +{ +} +#endif /* CONFIG_PPC_SVM */ + /* * We enter here early on, when the Open Firmware prom is still * handling exceptions and the MMU hash table for us. @@ -3366,6 +3459,9 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4, unreloc_toc(); #endif + /* Move to secure memory if we're supposed to be secure guests. */ + setup_secure_guest(kbase, hdr); + __start(hdr, kbase, 0, 0, 0, 0, 0); return 0; diff --git a/arch/powerpc/kernel/prom_init_check.sh b/arch/powerpc/kernel/prom_init_check.sh index 160bef0d553d..78bab17b1396 100644 --- a/arch/powerpc/kernel/prom_init_check.sh +++ b/arch/powerpc/kernel/prom_init_check.sh @@ -33,7 +33,7 @@ OBJ="$2" ERROR=0 -function check_section() +check_section() { file=$1 section=$2 diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c index 5faf0a64c92b..c5fa251b8950 100644 --- a/arch/powerpc/kernel/rtas.c +++ b/arch/powerpc/kernel/rtas.c @@ -16,6 +16,7 @@ #include <linux/capability.h> #include <linux/delay.h> #include <linux/cpu.h> +#include <linux/sched.h> #include <linux/smp.h> #include <linux/completion.h> #include <linux/cpumask.h> @@ -871,15 +872,17 @@ static int rtas_cpu_state_change_mask(enum rtas_cpu_state state, return 0; for_each_cpu(cpu, cpus) { + struct device *dev = get_cpu_device(cpu); + switch (state) { case DOWN: - cpuret = cpu_down(cpu); + cpuret = device_offline(dev); break; case UP: - cpuret = cpu_up(cpu); + cpuret = device_online(dev); break; } - if (cpuret) { + if (cpuret < 0) { pr_debug("%s: cpu_%s for cpu#%d returned %d.\n", __func__, ((state == UP) ? "up" : "down"), @@ -896,6 +899,7 @@ static int rtas_cpu_state_change_mask(enum rtas_cpu_state state, cpumask_clear_cpu(cpu, cpus); } } + cond_resched(); } return ret; @@ -922,13 +926,11 @@ int rtas_online_cpus_mask(cpumask_var_t cpus) return ret; } -EXPORT_SYMBOL(rtas_online_cpus_mask); int rtas_offline_cpus_mask(cpumask_var_t cpus) { return rtas_cpu_state_change_mask(DOWN, cpus); } -EXPORT_SYMBOL(rtas_offline_cpus_mask); int rtas_ibm_suspend_me(u64 handle) { @@ -968,6 +970,8 @@ int rtas_ibm_suspend_me(u64 handle) data.token = rtas_token("ibm,suspend-me"); data.complete = &done; + lock_device_hotplug(); + /* All present CPUs must be online */ cpumask_andnot(offline_mask, cpu_present_mask, cpu_online_mask); cpuret = rtas_online_cpus_mask(offline_mask); @@ -1006,6 +1010,7 @@ out_hotplug_enable: __func__); out: + unlock_device_hotplug(); free_cpumask_var(offline_mask); return atomic_read(&data.error); } diff --git a/arch/powerpc/kernel/security.c b/arch/powerpc/kernel/security.c index e1c9cf079503..7cfcb294b11c 100644 --- a/arch/powerpc/kernel/security.c +++ b/arch/powerpc/kernel/security.c @@ -28,7 +28,7 @@ static enum count_cache_flush_type count_cache_flush_type = COUNT_CACHE_FLUSH_NO bool barrier_nospec_enabled; static bool no_nospec; static bool btb_flush_enabled; -#ifdef CONFIG_PPC_FSL_BOOK3E +#if defined(CONFIG_PPC_FSL_BOOK3E) || defined(CONFIG_PPC_BOOK3S_64) static bool no_spectrev2; #endif @@ -114,7 +114,7 @@ static __init int security_feature_debugfs_init(void) device_initcall(security_feature_debugfs_init); #endif /* CONFIG_DEBUG_FS */ -#ifdef CONFIG_PPC_FSL_BOOK3E +#if defined(CONFIG_PPC_FSL_BOOK3E) || defined(CONFIG_PPC_BOOK3S_64) static int __init handle_nospectre_v2(char *p) { no_spectrev2 = true; @@ -122,6 +122,9 @@ static int __init handle_nospectre_v2(char *p) return 0; } early_param("nospectre_v2", handle_nospectre_v2); +#endif /* CONFIG_PPC_FSL_BOOK3E || CONFIG_PPC_BOOK3S_64 */ + +#ifdef CONFIG_PPC_FSL_BOOK3E void setup_spectre_v2(void) { if (no_spectrev2 || cpu_mitigations_off()) @@ -399,7 +402,17 @@ static void toggle_count_cache_flush(bool enable) void setup_count_cache_flush(void) { - toggle_count_cache_flush(true); + bool enable = true; + + if (no_spectrev2 || cpu_mitigations_off()) { + if (security_ftr_enabled(SEC_FTR_BCCTRL_SERIALISED) || + security_ftr_enabled(SEC_FTR_COUNT_CACHE_DISABLED)) + pr_warn("Spectre v2 mitigations not under software control, can't disable\n"); + + enable = false; + } + + toggle_count_cache_flush(enable); } #ifdef CONFIG_DEBUG_FS diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index 1f8db666468d..25aaa3903000 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -778,12 +778,6 @@ void ppc_printk_progress(char *s, unsigned short hex) pr_info("%s\n", s); } -void arch_setup_pdev_archdata(struct platform_device *pdev) -{ - pdev->archdata.dma_mask = DMA_BIT_MASK(32); - pdev->dev.dma_mask = &pdev->archdata.dma_mask; -} - static __init void print_system_info(void) { pr_info("-----------------------------------------------------\n"); @@ -806,9 +800,15 @@ static __init void print_system_info(void) pr_info("mmu_features = 0x%08x\n", cur_cpu_spec->mmu_features); #ifdef CONFIG_PPC64 pr_info("firmware_features = 0x%016lx\n", powerpc_firmware_features); +#ifdef CONFIG_PPC_BOOK3S + pr_info("vmalloc start = 0x%lx\n", KERN_VIRT_START); + pr_info("IO start = 0x%lx\n", KERN_IO_START); + pr_info("vmemmap start = 0x%lx\n", (unsigned long)vmemmap); +#endif #endif - print_system_hash_info(); + if (!early_radix_enabled()) + print_system_hash_info(); if (PHYSICAL_START > 0) pr_info("physical_start = 0x%llx\n", diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c index 94517e4a2723..a7541edf0cdb 100644 --- a/arch/powerpc/kernel/setup_32.c +++ b/arch/powerpc/kernel/setup_32.c @@ -206,6 +206,6 @@ __init void initialize_cache_info(void) dcache_bsize = cur_cpu_spec->dcache_bsize; icache_bsize = cur_cpu_spec->icache_bsize; ucache_bsize = 0; - if (cpu_has_feature(CPU_FTR_UNIFIED_ID_CACHE)) + if (IS_ENABLED(CONFIG_PPC_BOOK3S_601) || IS_ENABLED(CONFIG_E200)) ucache_bsize = icache_bsize = dcache_bsize; } diff --git a/arch/powerpc/kernel/stacktrace.c b/arch/powerpc/kernel/stacktrace.c index 1e2276963f6d..e2a46cfed5fd 100644 --- a/arch/powerpc/kernel/stacktrace.c +++ b/arch/powerpc/kernel/stacktrace.c @@ -182,7 +182,7 @@ static int __save_stack_trace_tsk_reliable(struct task_struct *tsk, * FIXME: IMHO these tests do not belong in * arch-dependent code, they are generic. */ - ip = ftrace_graph_ret_addr(tsk, &graph_idx, ip, NULL); + ip = ftrace_graph_ret_addr(tsk, &graph_idx, ip, stack); #ifdef CONFIG_KPROBES /* * Mark stacktraces with kretprobed functions on them diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c index e2147d7c9e72..80a676da11cb 100644 --- a/arch/powerpc/kernel/sysfs.c +++ b/arch/powerpc/kernel/sysfs.c @@ -19,6 +19,7 @@ #include <asm/smp.h> #include <asm/pmc.h> #include <asm/firmware.h> +#include <asm/svm.h> #include "cacheinfo.h" #include "setup.h" @@ -715,6 +716,23 @@ static struct device_attribute pa6t_attrs[] = { #endif /* HAS_PPC_PMC_PA6T */ #endif /* HAS_PPC_PMC_CLASSIC */ +#ifdef CONFIG_PPC_SVM +static ssize_t show_svm(struct device *dev, struct device_attribute *attr, char *buf) +{ + return sprintf(buf, "%u\n", is_secure_guest()); +} +static DEVICE_ATTR(svm, 0444, show_svm, NULL); + +static void create_svm_file(void) +{ + device_create_file(cpu_subsys.dev_root, &dev_attr_svm); +} +#else +static void create_svm_file(void) +{ +} +#endif /* CONFIG_PPC_SVM */ + static int register_cpu_online(unsigned int cpu) { struct cpu *c = &per_cpu(cpu_devices, cpu); @@ -1058,6 +1076,8 @@ static int __init topology_init(void) sysfs_create_dscr_default(); #endif /* CONFIG_PPC64 */ + create_svm_file(); + return 0; } subsys_initcall(topology_init); diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c index be1ca98fce5c..7ea0ca044b65 100644 --- a/arch/powerpc/kernel/trace/ftrace.c +++ b/arch/powerpc/kernel/trace/ftrace.c @@ -944,7 +944,8 @@ int ftrace_disable_ftrace_graph_caller(void) * Hook the return address and push it in the stack of return addrs * in current thread info. Return the address we want to divert to. */ -unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip) +unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip, + unsigned long sp) { unsigned long return_hooker; @@ -956,7 +957,7 @@ unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip) return_hooker = ppc_function_entry(return_to_handler); - if (!function_graph_enter(parent, ip, 0, NULL)) + if (!function_graph_enter(parent, ip, 0, (unsigned long *)sp)) parent = return_hooker; out: return parent; diff --git a/arch/powerpc/kernel/trace/ftrace_32.S b/arch/powerpc/kernel/trace/ftrace_32.S index 183f608efb81..e023ae59c429 100644 --- a/arch/powerpc/kernel/trace/ftrace_32.S +++ b/arch/powerpc/kernel/trace/ftrace_32.S @@ -50,6 +50,7 @@ _GLOBAL(ftrace_stub) #ifdef CONFIG_FUNCTION_GRAPH_TRACER _GLOBAL(ftrace_graph_caller) + addi r5, r1, 48 /* load r4 with local address */ lwz r4, 44(r1) subi r4, r4, MCOUNT_INSN_SIZE diff --git a/arch/powerpc/kernel/trace/ftrace_64_mprofile.S b/arch/powerpc/kernel/trace/ftrace_64_mprofile.S index 74acbf16a666..f9fd5f743eba 100644 --- a/arch/powerpc/kernel/trace/ftrace_64_mprofile.S +++ b/arch/powerpc/kernel/trace/ftrace_64_mprofile.S @@ -294,6 +294,7 @@ _GLOBAL(ftrace_graph_caller) std r2, 24(r1) ld r2, PACATOC(r13) /* get kernel TOC in r2 */ + addi r5, r1, 112 mfctr r4 /* ftrace_caller has moved local addr here */ std r4, 40(r1) mflr r3 /* ftrace_caller has restored LR from stack */ diff --git a/arch/powerpc/kernel/trace/ftrace_64_pg.S b/arch/powerpc/kernel/trace/ftrace_64_pg.S index e41a7d13c99c..6708e24db0ab 100644 --- a/arch/powerpc/kernel/trace/ftrace_64_pg.S +++ b/arch/powerpc/kernel/trace/ftrace_64_pg.S @@ -41,6 +41,7 @@ _GLOBAL(ftrace_stub) #ifdef CONFIG_FUNCTION_GRAPH_TRACER _GLOBAL(ftrace_graph_caller) + addi r5, r1, 112 /* load r4 with local address */ ld r4, 128(r1) subi r4, r4, MCOUNT_INSN_SIZE diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index 11caa0291254..82f43535e686 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -472,6 +472,7 @@ void system_reset_exception(struct pt_regs *regs) if (debugger(regs)) goto out; + kmsg_dump(KMSG_DUMP_OOPS); /* * A system reset is a request to dump, so we always send * it through the crashdump code (if fadump or kdump are diff --git a/arch/powerpc/kernel/ucall.S b/arch/powerpc/kernel/ucall.S new file mode 100644 index 000000000000..07296bc39166 --- /dev/null +++ b/arch/powerpc/kernel/ucall.S @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Generic code to perform an ultravisor call. + * + * Copyright 2019, IBM Corporation. + * + */ +#include <asm/ppc_asm.h> +#include <asm/export.h> + +_GLOBAL(ucall_norets) +EXPORT_SYMBOL_GPL(ucall_norets) + sc 2 /* Invoke the ultravisor */ + blr /* Return r3 = status */ diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c index d60598113a9f..eae9ddaecbcf 100644 --- a/arch/powerpc/kernel/vdso.c +++ b/arch/powerpc/kernel/vdso.c @@ -94,28 +94,6 @@ static struct vdso_patch_def vdso_patches[] = { CPU_FTR_COHERENT_ICACHE, CPU_FTR_COHERENT_ICACHE, "__kernel_sync_dicache", "__kernel_sync_dicache_p5" }, -#ifdef CONFIG_PPC32 - { - CPU_FTR_USE_RTC, CPU_FTR_USE_RTC, - "__kernel_gettimeofday", NULL - }, - { - CPU_FTR_USE_RTC, CPU_FTR_USE_RTC, - "__kernel_clock_gettime", NULL - }, - { - CPU_FTR_USE_RTC, CPU_FTR_USE_RTC, - "__kernel_clock_getres", NULL - }, - { - CPU_FTR_USE_RTC, CPU_FTR_USE_RTC, - "__kernel_get_tbfreq", NULL - }, - { - CPU_FTR_USE_RTC, CPU_FTR_USE_RTC, - "__kernel_time", NULL - }, -#endif }; /* diff --git a/arch/powerpc/kernel/vdso32/datapage.S b/arch/powerpc/kernel/vdso32/datapage.S index 6984125b9fc0..6c7401bd284e 100644 --- a/arch/powerpc/kernel/vdso32/datapage.S +++ b/arch/powerpc/kernel/vdso32/datapage.S @@ -70,6 +70,7 @@ V_FUNCTION_END(__kernel_get_syscall_map) * * returns the timebase frequency in HZ */ +#ifndef CONFIG_PPC_BOOK3S_601 V_FUNCTION_BEGIN(__kernel_get_tbfreq) .cfi_startproc mflr r12 @@ -82,3 +83,4 @@ V_FUNCTION_BEGIN(__kernel_get_tbfreq) blr .cfi_endproc V_FUNCTION_END(__kernel_get_tbfreq) +#endif diff --git a/arch/powerpc/kernel/vdso32/vdso32.lds.S b/arch/powerpc/kernel/vdso32/vdso32.lds.S index 099a6db14e67..00c025ba4a92 100644 --- a/arch/powerpc/kernel/vdso32/vdso32.lds.S +++ b/arch/powerpc/kernel/vdso32/vdso32.lds.S @@ -144,10 +144,13 @@ VERSION __kernel_datapage_offset; __kernel_get_syscall_map; +#ifndef CONFIG_PPC_BOOK3S_601 __kernel_gettimeofday; __kernel_clock_gettime; __kernel_clock_getres; + __kernel_time; __kernel_get_tbfreq; +#endif __kernel_sync_dicache; __kernel_sync_dicache_p5; __kernel_sigtramp32; @@ -155,7 +158,6 @@ VERSION #ifdef CONFIG_PPC64 __kernel_getcpu; #endif - __kernel_time; local: *; }; diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c index 9524d92bc45d..d7fcdfa7fee4 100644 --- a/arch/powerpc/kvm/book3s.c +++ b/arch/powerpc/kvm/book3s.c @@ -1083,9 +1083,11 @@ static int kvmppc_book3s_init(void) if (xics_on_xive()) { kvmppc_xive_init_module(); kvm_register_device_ops(&kvm_xive_ops, KVM_DEV_TYPE_XICS); - kvmppc_xive_native_init_module(); - kvm_register_device_ops(&kvm_xive_native_ops, - KVM_DEV_TYPE_XIVE); + if (kvmppc_xive_native_supported()) { + kvmppc_xive_native_init_module(); + kvm_register_device_ops(&kvm_xive_native_ops, + KVM_DEV_TYPE_XIVE); + } } else #endif kvm_register_device_ops(&kvm_xics_ops, KVM_DEV_TYPE_XICS); diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c index c4b606fe73eb..5834db0a54c6 100644 --- a/arch/powerpc/kvm/book3s_64_vio.c +++ b/arch/powerpc/kvm/book3s_64_vio.c @@ -416,7 +416,7 @@ static void kvmppc_clear_tce(struct mm_struct *mm, struct iommu_table *tbl, unsigned long hpa = 0; enum dma_data_direction dir = DMA_NONE; - iommu_tce_xchg(mm, tbl, entry, &hpa, &dir); + iommu_tce_xchg_no_kill(mm, tbl, entry, &hpa, &dir); } static long kvmppc_tce_iommu_mapped_dec(struct kvm *kvm, @@ -447,7 +447,8 @@ static long kvmppc_tce_iommu_do_unmap(struct kvm *kvm, unsigned long hpa = 0; long ret; - if (WARN_ON_ONCE(iommu_tce_xchg(kvm->mm, tbl, entry, &hpa, &dir))) + if (WARN_ON_ONCE(iommu_tce_xchg_no_kill(kvm->mm, tbl, entry, &hpa, + &dir))) return H_TOO_HARD; if (dir == DMA_NONE) @@ -455,7 +456,7 @@ static long kvmppc_tce_iommu_do_unmap(struct kvm *kvm, ret = kvmppc_tce_iommu_mapped_dec(kvm, tbl, entry); if (ret != H_SUCCESS) - iommu_tce_xchg(kvm->mm, tbl, entry, &hpa, &dir); + iommu_tce_xchg_no_kill(kvm->mm, tbl, entry, &hpa, &dir); return ret; } @@ -501,7 +502,7 @@ long kvmppc_tce_iommu_do_map(struct kvm *kvm, struct iommu_table *tbl, if (mm_iommu_mapped_inc(mem)) return H_TOO_HARD; - ret = iommu_tce_xchg(kvm->mm, tbl, entry, &hpa, &dir); + ret = iommu_tce_xchg_no_kill(kvm->mm, tbl, entry, &hpa, &dir); if (WARN_ON_ONCE(ret)) { mm_iommu_mapped_dec(mem); return H_TOO_HARD; @@ -579,6 +580,8 @@ long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn, ret = kvmppc_tce_iommu_map(vcpu->kvm, stt, stit->tbl, entry, ua, dir); + iommu_tce_kill(stit->tbl, entry, 1); + if (ret != H_SUCCESS) { kvmppc_clear_tce(vcpu->kvm->mm, stit->tbl, entry); goto unlock_exit; @@ -656,13 +659,13 @@ long kvmppc_h_put_tce_indirect(struct kvm_vcpu *vcpu, */ if (get_user(tce, tces + i)) { ret = H_TOO_HARD; - goto unlock_exit; + goto invalidate_exit; } tce = be64_to_cpu(tce); if (kvmppc_tce_to_ua(vcpu->kvm, tce, &ua)) { ret = H_PARAMETER; - goto unlock_exit; + goto invalidate_exit; } list_for_each_entry_lockless(stit, &stt->iommu_tables, next) { @@ -673,13 +676,17 @@ long kvmppc_h_put_tce_indirect(struct kvm_vcpu *vcpu, if (ret != H_SUCCESS) { kvmppc_clear_tce(vcpu->kvm->mm, stit->tbl, entry); - goto unlock_exit; + goto invalidate_exit; } } kvmppc_tce_put(stt, entry + i, tce); } +invalidate_exit: + list_for_each_entry_lockless(stit, &stt->iommu_tables, next) + iommu_tce_kill(stit->tbl, entry, npages); + unlock_exit: srcu_read_unlock(&vcpu->kvm->srcu, idx); @@ -718,7 +725,7 @@ long kvmppc_h_stuff_tce(struct kvm_vcpu *vcpu, continue; if (ret == H_TOO_HARD) - return ret; + goto invalidate_exit; WARN_ON_ONCE(1); kvmppc_clear_tce(vcpu->kvm->mm, stit->tbl, entry); @@ -728,6 +735,10 @@ long kvmppc_h_stuff_tce(struct kvm_vcpu *vcpu, for (i = 0; i < npages; ++i, ioba += (1ULL << stt->page_shift)) kvmppc_tce_put(stt, ioba >> stt->page_shift, tce_value); - return H_SUCCESS; +invalidate_exit: + list_for_each_entry_lockless(stit, &stt->iommu_tables, next) + iommu_tce_kill(stit->tbl, ioba >> stt->page_shift, npages); + + return ret; } EXPORT_SYMBOL_GPL(kvmppc_h_stuff_tce); diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c index b4f20f13b860..ab6eeb8e753e 100644 --- a/arch/powerpc/kvm/book3s_64_vio_hv.c +++ b/arch/powerpc/kvm/book3s_64_vio_hv.c @@ -218,13 +218,14 @@ static long kvmppc_rm_ioba_validate(struct kvmppc_spapr_tce_table *stt, return H_SUCCESS; } -static long iommu_tce_xchg_rm(struct mm_struct *mm, struct iommu_table *tbl, +static long iommu_tce_xchg_no_kill_rm(struct mm_struct *mm, + struct iommu_table *tbl, unsigned long entry, unsigned long *hpa, enum dma_data_direction *direction) { long ret; - ret = tbl->it_ops->exchange_rm(tbl, entry, hpa, direction); + ret = tbl->it_ops->xchg_no_kill(tbl, entry, hpa, direction, true); if (!ret && ((*direction == DMA_FROM_DEVICE) || (*direction == DMA_BIDIRECTIONAL))) { @@ -240,13 +241,20 @@ static long iommu_tce_xchg_rm(struct mm_struct *mm, struct iommu_table *tbl, return ret; } +extern void iommu_tce_kill_rm(struct iommu_table *tbl, + unsigned long entry, unsigned long pages) +{ + if (tbl->it_ops->tce_kill) + tbl->it_ops->tce_kill(tbl, entry, pages, true); +} + static void kvmppc_rm_clear_tce(struct kvm *kvm, struct iommu_table *tbl, unsigned long entry) { unsigned long hpa = 0; enum dma_data_direction dir = DMA_NONE; - iommu_tce_xchg_rm(kvm->mm, tbl, entry, &hpa, &dir); + iommu_tce_xchg_no_kill_rm(kvm->mm, tbl, entry, &hpa, &dir); } static long kvmppc_rm_tce_iommu_mapped_dec(struct kvm *kvm, @@ -278,7 +286,7 @@ static long kvmppc_rm_tce_iommu_do_unmap(struct kvm *kvm, unsigned long hpa = 0; long ret; - if (iommu_tce_xchg_rm(kvm->mm, tbl, entry, &hpa, &dir)) + if (iommu_tce_xchg_no_kill_rm(kvm->mm, tbl, entry, &hpa, &dir)) /* * real mode xchg can fail if struct page crosses * a page boundary @@ -290,7 +298,7 @@ static long kvmppc_rm_tce_iommu_do_unmap(struct kvm *kvm, ret = kvmppc_rm_tce_iommu_mapped_dec(kvm, tbl, entry); if (ret) - iommu_tce_xchg_rm(kvm->mm, tbl, entry, &hpa, &dir); + iommu_tce_xchg_no_kill_rm(kvm->mm, tbl, entry, &hpa, &dir); return ret; } @@ -336,7 +344,7 @@ static long kvmppc_rm_tce_iommu_do_map(struct kvm *kvm, struct iommu_table *tbl, if (WARN_ON_ONCE_RM(mm_iommu_mapped_inc(mem))) return H_TOO_HARD; - ret = iommu_tce_xchg_rm(kvm->mm, tbl, entry, &hpa, &dir); + ret = iommu_tce_xchg_no_kill_rm(kvm->mm, tbl, entry, &hpa, &dir); if (ret) { mm_iommu_mapped_dec(mem); /* @@ -417,6 +425,8 @@ long kvmppc_rm_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn, ret = kvmppc_rm_tce_iommu_map(vcpu->kvm, stt, stit->tbl, entry, ua, dir); + iommu_tce_kill_rm(stit->tbl, entry, 1); + if (ret != H_SUCCESS) { kvmppc_rm_clear_tce(vcpu->kvm, stit->tbl, entry); return ret; @@ -558,7 +568,7 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu, ua = 0; if (kvmppc_rm_tce_to_ua(vcpu->kvm, tce, &ua, NULL)) { ret = H_PARAMETER; - goto unlock_exit; + goto invalidate_exit; } list_for_each_entry_lockless(stit, &stt->iommu_tables, next) { @@ -569,13 +579,17 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu, if (ret != H_SUCCESS) { kvmppc_rm_clear_tce(vcpu->kvm, stit->tbl, entry); - goto unlock_exit; + goto invalidate_exit; } } kvmppc_rm_tce_put(stt, entry + i, tce); } +invalidate_exit: + list_for_each_entry_lockless(stit, &stt->iommu_tables, next) + iommu_tce_kill_rm(stit->tbl, entry, npages); + unlock_exit: if (rmap) unlock_rmap(rmap); @@ -618,7 +632,7 @@ long kvmppc_rm_h_stuff_tce(struct kvm_vcpu *vcpu, continue; if (ret == H_TOO_HARD) - return ret; + goto invalidate_exit; WARN_ON_ONCE_RM(1); kvmppc_rm_clear_tce(vcpu->kvm, stit->tbl, entry); @@ -628,7 +642,11 @@ long kvmppc_rm_h_stuff_tce(struct kvm_vcpu *vcpu, for (i = 0; i < npages; ++i, ioba += (1ULL << stt->page_shift)) kvmppc_rm_tce_put(stt, ioba >> stt->page_shift, tce_value); - return H_SUCCESS; +invalidate_exit: + list_for_each_entry_lockless(stit, &stt->iommu_tables, next) + iommu_tce_kill_rm(stit->tbl, ioba >> stt->page_shift, npages); + + return ret; } /* This can be called in either virtual mode or real mode */ diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index cde3f5a4b3e4..efd8f93bc9dc 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -1678,7 +1678,14 @@ static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, *val = get_reg_val(id, vcpu->arch.pspb); break; case KVM_REG_PPC_DPDES: - *val = get_reg_val(id, vcpu->arch.vcore->dpdes); + /* + * On POWER9, where we are emulating msgsndp etc., + * we return 1 bit for each vcpu, which can come from + * either vcore->dpdes or doorbell_request. + * On POWER8, doorbell_request is 0. + */ + *val = get_reg_val(id, vcpu->arch.vcore->dpdes | + vcpu->arch.doorbell_request); break; case KVM_REG_PPC_VTB: *val = get_reg_val(id, vcpu->arch.vcore->vtb); @@ -2860,7 +2867,7 @@ static void collect_piggybacks(struct core_info *cip, int target_threads) if (!spin_trylock(&pvc->lock)) continue; prepare_threads(pvc); - if (!pvc->n_runnable) { + if (!pvc->n_runnable || !pvc->kvm->arch.mmu_ready) { list_del_init(&pvc->preempt_list); if (pvc->runner == NULL) { pvc->vcore_state = VCORE_INACTIVE; @@ -2881,15 +2888,20 @@ static void collect_piggybacks(struct core_info *cip, int target_threads) spin_unlock(&lp->lock); } -static bool recheck_signals(struct core_info *cip) +static bool recheck_signals_and_mmu(struct core_info *cip) { int sub, i; struct kvm_vcpu *vcpu; + struct kvmppc_vcore *vc; - for (sub = 0; sub < cip->n_subcores; ++sub) - for_each_runnable_thread(i, vcpu, cip->vc[sub]) + for (sub = 0; sub < cip->n_subcores; ++sub) { + vc = cip->vc[sub]; + if (!vc->kvm->arch.mmu_ready) + return true; + for_each_runnable_thread(i, vcpu, vc) if (signal_pending(vcpu->arch.run_task)) return true; + } return false; } @@ -3119,7 +3131,7 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) local_irq_disable(); hard_irq_disable(); if (lazy_irq_pending() || need_resched() || - recheck_signals(&core_info) || !vc->kvm->arch.mmu_ready) { + recheck_signals_and_mmu(&core_info)) { local_irq_enable(); vc->vcore_state = VCORE_INACTIVE; /* Unlock all except the primary vcore */ @@ -5462,6 +5474,12 @@ static int kvmppc_radix_possible(void) static int kvmppc_book3s_init_hv(void) { int r; + + if (!tlbie_capable) { + pr_err("KVM-HV: Host does not support TLBIE\n"); + return -ENODEV; + } + /* * FIXME!! Do we need to check on all cpus ? */ diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c index 735e0ac6f5b2..fff90f2c3de2 100644 --- a/arch/powerpc/kvm/book3s_hv_nested.c +++ b/arch/powerpc/kvm/book3s_hv_nested.c @@ -398,7 +398,7 @@ static void kvmhv_flush_lpid(unsigned int lpid) long rc; if (!kvmhv_on_pseries()) { - radix__flush_tlb_lpid(lpid); + radix__flush_all_lpid(lpid); return; } @@ -411,7 +411,7 @@ static void kvmhv_flush_lpid(unsigned int lpid) void kvmhv_set_ptbl_entry(unsigned int lpid, u64 dw0, u64 dw1) { if (!kvmhv_on_pseries()) { - mmu_partition_table_set_entry(lpid, dw0, dw1); + mmu_partition_table_set_entry(lpid, dw0, dw1, true); return; } diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c index 63e0ce91e29d..7186c65c61c9 100644 --- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c +++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c @@ -99,7 +99,7 @@ void kvmppc_add_revmap_chain(struct kvm *kvm, struct revmap_entry *rev, } else { rev->forw = rev->back = pte_index; *rmap = (*rmap & ~KVMPPC_RMAP_INDEX) | - pte_index | KVMPPC_RMAP_PRESENT; + pte_index | KVMPPC_RMAP_PRESENT | KVMPPC_RMAP_HPT; } unlock_rmap(rmap); } diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index 337e64468d78..9a05b0d932ef 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -29,6 +29,7 @@ #include <asm/asm-compat.h> #include <asm/feature-fixups.h> #include <asm/cpuidle.h> +#include <asm/ultravisor-api.h> /* Sign-extend HDEC if not on POWER9 */ #define EXTEND_HDEC(reg) \ @@ -942,6 +943,8 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300) ld r11, VCPU_XIVE_SAVED_STATE(r4) li r9, TM_QW1_OS lwz r8, VCPU_XIVE_CAM_WORD(r4) + cmpwi r8, 0 + beq no_xive li r7, TM_QW1_OS + TM_WORD2 mfmsr r0 andi. r0, r0, MSR_DR /* in real mode? */ @@ -1083,16 +1086,10 @@ BEGIN_FTR_SECTION END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) ld r5, VCPU_LR(r4) - ld r6, VCPU_CR(r4) mtlr r5 - mtcr r6 ld r1, VCPU_GPR(R1)(r4) - ld r2, VCPU_GPR(R2)(r4) - ld r3, VCPU_GPR(R3)(r4) ld r5, VCPU_GPR(R5)(r4) - ld r6, VCPU_GPR(R6)(r4) - ld r7, VCPU_GPR(R7)(r4) ld r8, VCPU_GPR(R8)(r4) ld r9, VCPU_GPR(R9)(r4) ld r10, VCPU_GPR(R10)(r4) @@ -1110,10 +1107,42 @@ BEGIN_FTR_SECTION mtspr SPRN_HDSISR, r0 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) + ld r6, VCPU_KVM(r4) + lbz r7, KVM_SECURE_GUEST(r6) + cmpdi r7, 0 + ld r6, VCPU_GPR(R6)(r4) + ld r7, VCPU_GPR(R7)(r4) + bne ret_to_ultra + + lwz r0, VCPU_CR(r4) + mtcr r0 + ld r0, VCPU_GPR(R0)(r4) + ld r2, VCPU_GPR(R2)(r4) + ld r3, VCPU_GPR(R3)(r4) ld r4, VCPU_GPR(R4)(r4) HRFI_TO_GUEST b . +/* + * Use UV_RETURN ultracall to return control back to the Ultravisor after + * processing an hypercall or interrupt that was forwarded (a.k.a. reflected) + * to the Hypervisor. + * + * All registers have already been loaded, except: + * R0 = hcall result + * R2 = SRR1, so UV can detect a synthesized interrupt (if any) + * R3 = UV_RETURN + */ +ret_to_ultra: + lwz r0, VCPU_CR(r4) + mtcr r0 + + ld r0, VCPU_GPR(R3)(r4) + mfspr r2, SPRN_SRR1 + li r3, 0 + ori r3, r3, UV_RETURN + ld r4, VCPU_GPR(R4)(r4) + sc 2 /* * Enter the guest on a P9 or later system where we have exactly @@ -2831,29 +2860,39 @@ kvm_cede_prodded: kvm_cede_exit: ld r9, HSTATE_KVM_VCPU(r13) #ifdef CONFIG_KVM_XICS - /* Abort if we still have a pending escalation */ + /* are we using XIVE with single escalation? */ + ld r10, VCPU_XIVE_ESC_VADDR(r9) + cmpdi r10, 0 + beq 3f + li r6, XIVE_ESB_SET_PQ_00 + /* + * If we still have a pending escalation, abort the cede, + * and we must set PQ to 10 rather than 00 so that we don't + * potentially end up with two entries for the escalation + * interrupt in the XIVE interrupt queue. In that case + * we also don't want to set xive_esc_on to 1 here in + * case we race with xive_esc_irq(). + */ lbz r5, VCPU_XIVE_ESC_ON(r9) cmpwi r5, 0 - beq 1f + beq 4f li r0, 0 stb r0, VCPU_CEDED(r9) -1: /* Enable XIVE escalation */ - li r5, XIVE_ESB_SET_PQ_00 + li r6, XIVE_ESB_SET_PQ_10 + b 5f +4: li r0, 1 + stb r0, VCPU_XIVE_ESC_ON(r9) + /* make sure store to xive_esc_on is seen before xive_esc_irq runs */ + sync +5: /* Enable XIVE escalation */ mfmsr r0 andi. r0, r0, MSR_DR /* in real mode? */ beq 1f - ld r10, VCPU_XIVE_ESC_VADDR(r9) - cmpdi r10, 0 - beq 3f - ldx r0, r10, r5 + ldx r0, r10, r6 b 2f 1: ld r10, VCPU_XIVE_ESC_RADDR(r9) - cmpdi r10, 0 - beq 3f - ldcix r0, r10, r5 + ldcix r0, r10, r6 2: sync - li r0, 1 - stb r0, VCPU_XIVE_ESC_ON(r9) #endif /* CONFIG_KVM_XICS */ 3: b guest_exit_cont diff --git a/arch/powerpc/kvm/book3s_xive.c b/arch/powerpc/kvm/book3s_xive.c index e3ba67095895..591bfb4bfd0f 100644 --- a/arch/powerpc/kvm/book3s_xive.c +++ b/arch/powerpc/kvm/book3s_xive.c @@ -67,8 +67,14 @@ void kvmppc_xive_push_vcpu(struct kvm_vcpu *vcpu) void __iomem *tima = local_paca->kvm_hstate.xive_tima_virt; u64 pq; - if (!tima) + /* + * Nothing to do if the platform doesn't have a XIVE + * or this vCPU doesn't have its own XIVE context + * (e.g. because it's not using an in-kernel interrupt controller). + */ + if (!tima || !vcpu->arch.xive_cam_word) return; + eieio(); __raw_writeq(vcpu->arch.xive_saved_state.w01, tima + TM_QW1_OS); __raw_writel(vcpu->arch.xive_cam_word, tima + TM_QW1_OS + TM_WORD2); @@ -160,6 +166,9 @@ static irqreturn_t xive_esc_irq(int irq, void *data) */ vcpu->arch.xive_esc_on = false; + /* This orders xive_esc_on = false vs. subsequent stale_p = true */ + smp_wmb(); /* goes with smp_mb() in cleanup_single_escalation */ + return IRQ_HANDLED; } @@ -1113,6 +1122,31 @@ void kvmppc_xive_disable_vcpu_interrupts(struct kvm_vcpu *vcpu) vcpu->arch.xive_esc_raddr = 0; } +/* + * In single escalation mode, the escalation interrupt is marked so + * that EOI doesn't re-enable it, but just sets the stale_p flag to + * indicate that the P bit has already been dealt with. However, the + * assembly code that enters the guest sets PQ to 00 without clearing + * stale_p (because it has no easy way to address it). Hence we have + * to adjust stale_p before shutting down the interrupt. + */ +void xive_cleanup_single_escalation(struct kvm_vcpu *vcpu, + struct kvmppc_xive_vcpu *xc, int irq) +{ + struct irq_data *d = irq_get_irq_data(irq); + struct xive_irq_data *xd = irq_data_get_irq_handler_data(d); + + /* + * This slightly odd sequence gives the right result + * (i.e. stale_p set if xive_esc_on is false) even if + * we race with xive_esc_irq() and xive_irq_eoi(). + */ + xd->stale_p = false; + smp_mb(); /* paired with smb_wmb in xive_esc_irq */ + if (!vcpu->arch.xive_esc_on) + xd->stale_p = true; +} + void kvmppc_xive_cleanup_vcpu(struct kvm_vcpu *vcpu) { struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu; @@ -1134,20 +1168,28 @@ void kvmppc_xive_cleanup_vcpu(struct kvm_vcpu *vcpu) /* Mask the VP IPI */ xive_vm_esb_load(&xc->vp_ipi_data, XIVE_ESB_SET_PQ_01); - /* Disable the VP */ - xive_native_disable_vp(xc->vp_id); - - /* Free the queues & associated interrupts */ + /* Free escalations */ for (i = 0; i < KVMPPC_XIVE_Q_COUNT; i++) { - struct xive_q *q = &xc->queues[i]; - - /* Free the escalation irq */ if (xc->esc_virq[i]) { + if (xc->xive->single_escalation) + xive_cleanup_single_escalation(vcpu, xc, + xc->esc_virq[i]); free_irq(xc->esc_virq[i], vcpu); irq_dispose_mapping(xc->esc_virq[i]); kfree(xc->esc_virq_names[i]); } - /* Free the queue */ + } + + /* Disable the VP */ + xive_native_disable_vp(xc->vp_id); + + /* Clear the cam word so guest entry won't try to push context */ + vcpu->arch.xive_cam_word = 0; + + /* Free the queues */ + for (i = 0; i < KVMPPC_XIVE_Q_COUNT; i++) { + struct xive_q *q = &xc->queues[i]; + xive_native_disable_queue(xc->vp_id, q, i); if (q->qpage) { free_pages((unsigned long)q->qpage, diff --git a/arch/powerpc/kvm/book3s_xive.h b/arch/powerpc/kvm/book3s_xive.h index 50494d0ee375..955b820ffd6d 100644 --- a/arch/powerpc/kvm/book3s_xive.h +++ b/arch/powerpc/kvm/book3s_xive.h @@ -282,6 +282,8 @@ int kvmppc_xive_select_target(struct kvm *kvm, u32 *server, u8 prio); int kvmppc_xive_attach_escalation(struct kvm_vcpu *vcpu, u8 prio, bool single_escalation); struct kvmppc_xive *kvmppc_xive_get_device(struct kvm *kvm, u32 type); +void xive_cleanup_single_escalation(struct kvm_vcpu *vcpu, + struct kvmppc_xive_vcpu *xc, int irq); #endif /* CONFIG_KVM_XICS */ #endif /* _KVM_PPC_BOOK3S_XICS_H */ diff --git a/arch/powerpc/kvm/book3s_xive_native.c b/arch/powerpc/kvm/book3s_xive_native.c index a998823f68a3..248c1ea9e788 100644 --- a/arch/powerpc/kvm/book3s_xive_native.c +++ b/arch/powerpc/kvm/book3s_xive_native.c @@ -67,20 +67,28 @@ void kvmppc_xive_native_cleanup_vcpu(struct kvm_vcpu *vcpu) xc->valid = false; kvmppc_xive_disable_vcpu_interrupts(vcpu); - /* Disable the VP */ - xive_native_disable_vp(xc->vp_id); - - /* Free the queues & associated interrupts */ + /* Free escalations */ for (i = 0; i < KVMPPC_XIVE_Q_COUNT; i++) { /* Free the escalation irq */ if (xc->esc_virq[i]) { + if (xc->xive->single_escalation) + xive_cleanup_single_escalation(vcpu, xc, + xc->esc_virq[i]); free_irq(xc->esc_virq[i], vcpu); irq_dispose_mapping(xc->esc_virq[i]); kfree(xc->esc_virq_names[i]); xc->esc_virq[i] = 0; } + } + + /* Disable the VP */ + xive_native_disable_vp(xc->vp_id); + + /* Clear the cam word so guest entry won't try to push context */ + vcpu->arch.xive_cam_word = 0; - /* Free the queue */ + /* Free the queues */ + for (i = 0; i < KVMPPC_XIVE_Q_COUNT; i++) { kvmppc_xive_native_cleanup_queue(vcpu, i); } @@ -1171,6 +1179,11 @@ int kvmppc_xive_native_set_vp(struct kvm_vcpu *vcpu, union kvmppc_one_reg *val) return 0; } +bool kvmppc_xive_native_supported(void) +{ + return xive_native_has_queue_state_support(); +} + static int xive_native_debug_show(struct seq_file *m, void *private) { struct kvmppc_xive *xive = m->private; diff --git a/arch/powerpc/kvm/e500.c b/arch/powerpc/kvm/e500.c index b5a848a55504..00649ca5fa9a 100644 --- a/arch/powerpc/kvm/e500.c +++ b/arch/powerpc/kvm/e500.c @@ -440,6 +440,9 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_e500(struct kvm *kvm, struct kvm_vcpu *vcpu; int err; + BUILD_BUG_ON_MSG(offsetof(struct kvmppc_vcpu_e500, vcpu) != 0, + "struct kvm_vcpu must be at offset 0 for arch usercopy region"); + vcpu_e500 = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL); if (!vcpu_e500) { err = -ENOMEM; diff --git a/arch/powerpc/kvm/emulate.c b/arch/powerpc/kvm/emulate.c index bb4d09c1ad56..6fca38ca791f 100644 --- a/arch/powerpc/kvm/emulate.c +++ b/arch/powerpc/kvm/emulate.c @@ -271,6 +271,7 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu) */ if (inst == KVMPPC_INST_SW_BREAKPOINT) { run->exit_reason = KVM_EXIT_DEBUG; + run->debug.arch.status = 0; run->debug.arch.address = kvmppc_get_pc(vcpu); emulated = EMULATE_EXIT_USER; advance = 0; diff --git a/arch/powerpc/kvm/emulate_loadstore.c b/arch/powerpc/kvm/emulate_loadstore.c index 9208c82ed08d..2e496eb86e94 100644 --- a/arch/powerpc/kvm/emulate_loadstore.c +++ b/arch/powerpc/kvm/emulate_loadstore.c @@ -89,12 +89,6 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu) rs = get_rs(inst); rt = get_rt(inst); - /* - * if mmio_vsx_tx_sx_enabled == 0, copy data between - * VSR[0..31] and memory - * if mmio_vsx_tx_sx_enabled == 1, copy data between - * VSR[32..63] and memory - */ vcpu->arch.mmio_vsx_copy_nums = 0; vcpu->arch.mmio_vsx_offset = 0; vcpu->arch.mmio_copy_type = KVMPPC_VSX_COPY_NONE; diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 3e566c2e6066..3a77bb643452 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -561,7 +561,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) * a POWER9 processor) and the PowerNV platform, as * nested is not yet supported. */ - r = xive_enabled() && !!cpu_has_feature(CPU_FTR_HVMODE); + r = xive_enabled() && !!cpu_has_feature(CPU_FTR_HVMODE) && + kvmppc_xive_native_supported(); break; #endif diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile index eebc782d89a5..b8de3be10eb4 100644 --- a/arch/powerpc/lib/Makefile +++ b/arch/powerpc/lib/Makefile @@ -16,7 +16,7 @@ CFLAGS_code-patching.o += -DDISABLE_BRANCH_PROFILING CFLAGS_feature-fixups.o += -DDISABLE_BRANCH_PROFILING endif -obj-y += alloc.o code-patching.o feature-fixups.o +obj-y += alloc.o code-patching.o feature-fixups.o pmem.o ifndef CONFIG_KASAN obj-y += string.o memcmp_$(BITS).o @@ -39,7 +39,7 @@ obj-$(CONFIG_PPC_BOOK3S_64) += copyuser_power7.o copypage_power7.o \ memcpy_power7.o obj64-y += copypage_64.o copyuser_64.o mem_64.o hweight_64.o \ - memcpy_64.o pmem.o + memcpy_64.o memcpy_mcsafe_64.o obj64-$(CONFIG_SMP) += locks.o obj64-$(CONFIG_ALTIVEC) += vmx-helper.o diff --git a/arch/powerpc/lib/locks.c b/arch/powerpc/lib/locks.c index 6550b9e5ce5f..6440d5943c00 100644 --- a/arch/powerpc/lib/locks.c +++ b/arch/powerpc/lib/locks.c @@ -18,7 +18,7 @@ #include <asm/hvcall.h> #include <asm/smp.h> -void __spin_yield(arch_spinlock_t *lock) +void splpar_spin_yield(arch_spinlock_t *lock) { unsigned int lock_value, holder_cpu, yield_count; @@ -36,14 +36,14 @@ void __spin_yield(arch_spinlock_t *lock) plpar_hcall_norets(H_CONFER, get_hard_smp_processor_id(holder_cpu), yield_count); } -EXPORT_SYMBOL_GPL(__spin_yield); +EXPORT_SYMBOL_GPL(splpar_spin_yield); /* * Waiting for a read lock or a write lock on a rwlock... * This turns out to be the same for read and write locks, since * we only know the holder if it is write-locked. */ -void __rw_yield(arch_rwlock_t *rw) +void splpar_rw_yield(arch_rwlock_t *rw) { int lock_value; unsigned int holder_cpu, yield_count; diff --git a/arch/powerpc/lib/memcpy_mcsafe_64.S b/arch/powerpc/lib/memcpy_mcsafe_64.S new file mode 100644 index 000000000000..cb882d9a6d8a --- /dev/null +++ b/arch/powerpc/lib/memcpy_mcsafe_64.S @@ -0,0 +1,242 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) IBM Corporation, 2011 + * Derived from copyuser_power7.s by Anton Blanchard <anton@au.ibm.com> + * Author - Balbir Singh <bsingharora@gmail.com> + */ +#include <asm/ppc_asm.h> +#include <asm/errno.h> +#include <asm/export.h> + + .macro err1 +100: + EX_TABLE(100b,.Ldo_err1) + .endm + + .macro err2 +200: + EX_TABLE(200b,.Ldo_err2) + .endm + + .macro err3 +300: EX_TABLE(300b,.Ldone) + .endm + +.Ldo_err2: + ld r22,STK_REG(R22)(r1) + ld r21,STK_REG(R21)(r1) + ld r20,STK_REG(R20)(r1) + ld r19,STK_REG(R19)(r1) + ld r18,STK_REG(R18)(r1) + ld r17,STK_REG(R17)(r1) + ld r16,STK_REG(R16)(r1) + ld r15,STK_REG(R15)(r1) + ld r14,STK_REG(R14)(r1) + addi r1,r1,STACKFRAMESIZE +.Ldo_err1: + /* Do a byte by byte copy to get the exact remaining size */ + mtctr r7 +46: +err3; lbz r0,0(r4) + addi r4,r4,1 +err3; stb r0,0(r3) + addi r3,r3,1 + bdnz 46b + li r3,0 + blr + +.Ldone: + mfctr r3 + blr + + +_GLOBAL(memcpy_mcsafe) + mr r7,r5 + cmpldi r5,16 + blt .Lshort_copy + +.Lcopy: + /* Get the source 8B aligned */ + neg r6,r4 + mtocrf 0x01,r6 + clrldi r6,r6,(64-3) + + bf cr7*4+3,1f +err1; lbz r0,0(r4) + addi r4,r4,1 +err1; stb r0,0(r3) + addi r3,r3,1 + subi r7,r7,1 + +1: bf cr7*4+2,2f +err1; lhz r0,0(r4) + addi r4,r4,2 +err1; sth r0,0(r3) + addi r3,r3,2 + subi r7,r7,2 + +2: bf cr7*4+1,3f +err1; lwz r0,0(r4) + addi r4,r4,4 +err1; stw r0,0(r3) + addi r3,r3,4 + subi r7,r7,4 + +3: sub r5,r5,r6 + cmpldi r5,128 + + mflr r0 + stdu r1,-STACKFRAMESIZE(r1) + std r14,STK_REG(R14)(r1) + std r15,STK_REG(R15)(r1) + std r16,STK_REG(R16)(r1) + std r17,STK_REG(R17)(r1) + std r18,STK_REG(R18)(r1) + std r19,STK_REG(R19)(r1) + std r20,STK_REG(R20)(r1) + std r21,STK_REG(R21)(r1) + std r22,STK_REG(R22)(r1) + std r0,STACKFRAMESIZE+16(r1) + + blt 5f + srdi r6,r5,7 + mtctr r6 + + /* Now do cacheline (128B) sized loads and stores. */ + .align 5 +4: +err2; ld r0,0(r4) +err2; ld r6,8(r4) +err2; ld r8,16(r4) +err2; ld r9,24(r4) +err2; ld r10,32(r4) +err2; ld r11,40(r4) +err2; ld r12,48(r4) +err2; ld r14,56(r4) +err2; ld r15,64(r4) +err2; ld r16,72(r4) +err2; ld r17,80(r4) +err2; ld r18,88(r4) +err2; ld r19,96(r4) +err2; ld r20,104(r4) +err2; ld r21,112(r4) +err2; ld r22,120(r4) + addi r4,r4,128 +err2; std r0,0(r3) +err2; std r6,8(r3) +err2; std r8,16(r3) +err2; std r9,24(r3) +err2; std r10,32(r3) +err2; std r11,40(r3) +err2; std r12,48(r3) +err2; std r14,56(r3) +err2; std r15,64(r3) +err2; std r16,72(r3) +err2; std r17,80(r3) +err2; std r18,88(r3) +err2; std r19,96(r3) +err2; std r20,104(r3) +err2; std r21,112(r3) +err2; std r22,120(r3) + addi r3,r3,128 + subi r7,r7,128 + bdnz 4b + + clrldi r5,r5,(64-7) + + /* Up to 127B to go */ +5: srdi r6,r5,4 + mtocrf 0x01,r6 + +6: bf cr7*4+1,7f +err2; ld r0,0(r4) +err2; ld r6,8(r4) +err2; ld r8,16(r4) +err2; ld r9,24(r4) +err2; ld r10,32(r4) +err2; ld r11,40(r4) +err2; ld r12,48(r4) +err2; ld r14,56(r4) + addi r4,r4,64 +err2; std r0,0(r3) +err2; std r6,8(r3) +err2; std r8,16(r3) +err2; std r9,24(r3) +err2; std r10,32(r3) +err2; std r11,40(r3) +err2; std r12,48(r3) +err2; std r14,56(r3) + addi r3,r3,64 + subi r7,r7,64 + +7: ld r14,STK_REG(R14)(r1) + ld r15,STK_REG(R15)(r1) + ld r16,STK_REG(R16)(r1) + ld r17,STK_REG(R17)(r1) + ld r18,STK_REG(R18)(r1) + ld r19,STK_REG(R19)(r1) + ld r20,STK_REG(R20)(r1) + ld r21,STK_REG(R21)(r1) + ld r22,STK_REG(R22)(r1) + addi r1,r1,STACKFRAMESIZE + + /* Up to 63B to go */ + bf cr7*4+2,8f +err1; ld r0,0(r4) +err1; ld r6,8(r4) +err1; ld r8,16(r4) +err1; ld r9,24(r4) + addi r4,r4,32 +err1; std r0,0(r3) +err1; std r6,8(r3) +err1; std r8,16(r3) +err1; std r9,24(r3) + addi r3,r3,32 + subi r7,r7,32 + + /* Up to 31B to go */ +8: bf cr7*4+3,9f +err1; ld r0,0(r4) +err1; ld r6,8(r4) + addi r4,r4,16 +err1; std r0,0(r3) +err1; std r6,8(r3) + addi r3,r3,16 + subi r7,r7,16 + +9: clrldi r5,r5,(64-4) + + /* Up to 15B to go */ +.Lshort_copy: + mtocrf 0x01,r5 + bf cr7*4+0,12f +err1; lwz r0,0(r4) /* Less chance of a reject with word ops */ +err1; lwz r6,4(r4) + addi r4,r4,8 +err1; stw r0,0(r3) +err1; stw r6,4(r3) + addi r3,r3,8 + subi r7,r7,8 + +12: bf cr7*4+1,13f +err1; lwz r0,0(r4) + addi r4,r4,4 +err1; stw r0,0(r3) + addi r3,r3,4 + subi r7,r7,4 + +13: bf cr7*4+2,14f +err1; lhz r0,0(r4) + addi r4,r4,2 +err1; sth r0,0(r3) + addi r3,r3,2 + subi r7,r7,2 + +14: bf cr7*4+3,15f +err1; lbz r0,0(r4) +err1; stb r0,0(r3) + +15: li r3,0 + blr + +EXPORT_SYMBOL_GPL(memcpy_mcsafe); diff --git a/arch/powerpc/mm/Makefile b/arch/powerpc/mm/Makefile index 0f499db315d6..5e147986400d 100644 --- a/arch/powerpc/mm/Makefile +++ b/arch/powerpc/mm/Makefile @@ -7,7 +7,7 @@ ccflags-$(CONFIG_PPC64) := $(NO_MINIMAL_TOC) obj-y := fault.o mem.o pgtable.o mmap.o \ init_$(BITS).o pgtable_$(BITS).o \ - pgtable-frag.o \ + pgtable-frag.o ioremap.o ioremap_$(BITS).o \ init-common.o mmu_context.o drmem.o obj-$(CONFIG_PPC_MMU_NOHASH) += nohash/ obj-$(CONFIG_PPC_BOOK3S_32) += book3s32/ diff --git a/arch/powerpc/mm/book3s32/mmu.c b/arch/powerpc/mm/book3s32/mmu.c index e249fbf6b9c3..84d5fab94f8f 100644 --- a/arch/powerpc/mm/book3s32/mmu.c +++ b/arch/powerpc/mm/book3s32/mmu.c @@ -74,7 +74,7 @@ static int find_free_bat(void) { int b; - if (cpu_has_feature(CPU_FTR_601)) { + if (IS_ENABLED(CONFIG_PPC_BOOK3S_601)) { for (b = 0; b < 4; b++) { struct ppc_bat *bat = BATS[b]; @@ -106,7 +106,7 @@ static int find_free_bat(void) */ static unsigned int block_size(unsigned long base, unsigned long top) { - unsigned int max_size = (cpu_has_feature(CPU_FTR_601) ? 8 : 256) << 20; + unsigned int max_size = IS_ENABLED(CONFIG_PPC_BOOK3S_601) ? SZ_8M : SZ_256M; unsigned int base_shift = (ffs(base) - 1) & 31; unsigned int block_shift = (fls(top - base) - 1) & 31; @@ -189,7 +189,7 @@ void mmu_mark_initmem_nx(void) unsigned long top = (unsigned long)_etext - PAGE_OFFSET; unsigned long size; - if (cpu_has_feature(CPU_FTR_601)) + if (IS_ENABLED(CONFIG_PPC_BOOK3S_601)) return; for (i = 0; i < nb - 1 && base < top && top - base > (128 << 10);) { @@ -227,7 +227,7 @@ void mmu_mark_rodata_ro(void) int nb = mmu_has_feature(MMU_FTR_USE_HIGH_BATS) ? 8 : 4; int i; - if (cpu_has_feature(CPU_FTR_601)) + if (IS_ENABLED(CONFIG_PPC_BOOK3S_601)) return; for (i = 0; i < nb; i++) { @@ -259,7 +259,7 @@ void __init setbat(int index, unsigned long virt, phys_addr_t phys, flags &= ~_PAGE_COHERENT; bl = (size >> 17) - 1; - if (PVR_VER(mfspr(SPRN_PVR)) != 1) { + if (!IS_ENABLED(CONFIG_PPC_BOOK3S_601)) { /* 603, 604, etc. */ /* Do DBAT first */ wimgxpp = flags & (_PAGE_WRITETHRU | _PAGE_NO_CACHE @@ -297,8 +297,7 @@ void __init setbat(int index, unsigned long virt, phys_addr_t phys, /* * Preload a translation in the hash table */ -void hash_preload(struct mm_struct *mm, unsigned long ea, - bool is_exec, unsigned long trap) +void hash_preload(struct mm_struct *mm, unsigned long ea) { pmd_t *pmd; @@ -310,6 +309,39 @@ void hash_preload(struct mm_struct *mm, unsigned long ea, } /* + * This is called at the end of handling a user page fault, when the + * fault has been handled by updating a PTE in the linux page tables. + * We use it to preload an HPTE into the hash table corresponding to + * the updated linux PTE. + * + * This must always be called with the pte lock held. + */ +void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, + pte_t *ptep) +{ + if (!mmu_has_feature(MMU_FTR_HPTE_TABLE)) + return; + /* + * We don't need to worry about _PAGE_PRESENT here because we are + * called with either mm->page_table_lock held or ptl lock held + */ + + /* We only want HPTEs for linux PTEs that have _PAGE_ACCESSED set */ + if (!pte_young(*ptep) || address >= TASK_SIZE) + return; + + /* We have to test for regs NULL since init will get here first thing at boot */ + if (!current->thread.regs) + return; + + /* We also avoid filling the hash if not coming from a fault */ + if (TRAP(current->thread.regs) != 0x300 && TRAP(current->thread.regs) != 0x400) + return; + + hash_preload(vma->vm_mm, address); +} + +/* * Initialize the hash table and patch the instructions in hashtable.S. */ void __init MMU_init_hw(void) @@ -358,6 +390,15 @@ void __init MMU_init_hw(void) hash_mb2 = hash_mb = 32 - LG_HPTEG_SIZE - lg_n_hpteg; if (lg_n_hpteg > 16) hash_mb2 = 16 - LG_HPTEG_SIZE; + + /* + * When KASAN is selected, there is already an early temporary hash + * table and the switch to the final hash table is done later. + */ + if (IS_ENABLED(CONFIG_KASAN)) + return; + + MMU_init_hw_patch(); } void __init MMU_init_hw_patch(void) @@ -400,7 +441,7 @@ void setup_initial_memory_limit(phys_addr_t first_memblock_base, BUG_ON(first_memblock_base != 0); /* 601 can only access 16MB at the moment */ - if (PVR_VER(mfspr(SPRN_PVR)) == 1) + if (IS_ENABLED(CONFIG_PPC_BOOK3S_601)) memblock_set_current_limit(min_t(u64, first_memblock_size, 0x01000000)); else /* Anything else has 256M mapped */ memblock_set_current_limit(min_t(u64, first_memblock_size, 0x10000000)); @@ -418,9 +459,6 @@ void __init setup_kuep(bool disabled) { pr_info("Activating Kernel Userspace Execution Prevention\n"); - if (cpu_has_feature(CPU_FTR_601)) - pr_warn("KUEP is not working on powerpc 601 (No NX bit in Seg Regs)\n"); - if (disabled) pr_warn("KUEP cannot be disabled yet on 6xx when compiled in\n"); } diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c index b8ad14bb1170..3410ea9f4de1 100644 --- a/arch/powerpc/mm/book3s64/hash_utils.c +++ b/arch/powerpc/mm/book3s64/hash_utils.c @@ -34,6 +34,7 @@ #include <linux/libfdt.h> #include <linux/pkeys.h> #include <linux/hugetlb.h> +#include <linux/cpu.h> #include <asm/debugfs.h> #include <asm/processor.h> @@ -61,6 +62,7 @@ #include <asm/ps3.h> #include <asm/pte-walk.h> #include <asm/asm-prototypes.h> +#include <asm/ultravisor.h> #include <mm/mmu_decl.h> @@ -271,10 +273,6 @@ int htab_bolt_mapping(unsigned long vstart, unsigned long vend, if (overlaps_kernel_text(vaddr, vaddr + step)) tprot &= ~HPTE_R_N; - /* Make kvm guest trampolines executable */ - if (overlaps_kvm_tmp(vaddr, vaddr + step)) - tprot &= ~HPTE_R_N; - /* * If relocatable, check if it overlaps interrupt vectors that * are copied down to real 0. For relocatable kernel @@ -823,7 +821,7 @@ static void __init hash_init_partition_table(phys_addr_t hash_table, * For now, UPRT is 0 and we have no segment table. */ htab_size = __ilog2(htab_size) - 18; - mmu_partition_table_set_entry(0, hash_table | htab_size, 0); + mmu_partition_table_set_entry(0, hash_table | htab_size, 0, false); pr_info("Partition table %p\n", partition_tb); } @@ -857,12 +855,6 @@ static void __init htab_initialize(void) /* Using a hypervisor which owns the htab */ htab_address = NULL; _SDR1 = 0; - /* - * On POWER9, we need to do a H_REGISTER_PROC_TBL hcall - * to inform the hypervisor that we wish to use the HPT. - */ - if (cpu_has_feature(CPU_FTR_ARCH_300)) - register_process_table(0, 0, 0); #ifdef CONFIG_FA_DUMP /* * If firmware assisted dump is active firmware preserves @@ -1075,8 +1067,8 @@ void hash__early_init_mmu_secondary(void) if (!cpu_has_feature(CPU_FTR_ARCH_300)) mtspr(SPRN_SDR1, _SDR1); else - mtspr(SPRN_PTCR, - __pa(partition_tb) | (PATB_SIZE_SHIFT - 12)); + set_ptcr_when_no_uv(__pa(partition_tb) | + (PATB_SIZE_SHIFT - 12)); } /* Initialize SLB */ slb_initialize(); @@ -1460,8 +1452,8 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap, } EXPORT_SYMBOL_GPL(hash_page); -int __hash_page(unsigned long ea, unsigned long msr, unsigned long trap, - unsigned long dsisr) +int __hash_page(unsigned long trap, unsigned long ea, unsigned long dsisr, + unsigned long msr) { unsigned long access = _PAGE_PRESENT | _PAGE_READ; unsigned long flags = 0; @@ -1518,8 +1510,8 @@ static bool should_hash_preload(struct mm_struct *mm, unsigned long ea) } #endif -void hash_preload(struct mm_struct *mm, unsigned long ea, - bool is_exec, unsigned long trap) +static void hash_preload(struct mm_struct *mm, unsigned long ea, + bool is_exec, unsigned long trap) { int hugepage_shift; unsigned long vsid; @@ -1599,6 +1591,57 @@ out_exit: local_irq_restore(flags); } +/* + * This is called at the end of handling a user page fault, when the + * fault has been handled by updating a PTE in the linux page tables. + * We use it to preload an HPTE into the hash table corresponding to + * the updated linux PTE. + * + * This must always be called with the pte lock held. + */ +void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, + pte_t *ptep) +{ + /* + * We don't need to worry about _PAGE_PRESENT here because we are + * called with either mm->page_table_lock held or ptl lock held + */ + unsigned long trap; + bool is_exec; + + if (radix_enabled()) { + prefetch((void *)address); + return; + } + + /* We only want HPTEs for linux PTEs that have _PAGE_ACCESSED set */ + if (!pte_young(*ptep) || address >= TASK_SIZE) + return; + + /* + * We try to figure out if we are coming from an instruction + * access fault and pass that down to __hash_page so we avoid + * double-faulting on execution of fresh text. We have to test + * for regs NULL since init will get here first thing at boot. + * + * We also avoid filling the hash if not coming from a fault. + */ + + trap = current->thread.regs ? TRAP(current->thread.regs) : 0UL; + switch (trap) { + case 0x300: + is_exec = false; + break; + case 0x400: + is_exec = true; + break; + default: + return; + } + + hash_preload(vma->vm_mm, address, is_exec, trap); +} + #ifdef CONFIG_PPC_MEM_KEYS /* * Return the protection key associated with the given address and the @@ -1931,10 +1974,16 @@ static int hpt_order_get(void *data, u64 *val) static int hpt_order_set(void *data, u64 val) { + int ret; + if (!mmu_hash_ops.resize_hpt) return -ENODEV; - return mmu_hash_ops.resize_hpt(val); + cpus_read_lock(); + ret = mmu_hash_ops.resize_hpt(val); + cpus_read_unlock(); + + return ret; } DEFINE_DEBUGFS_ATTRIBUTE(fops_hpt_order, hpt_order_get, hpt_order_set, "%llu\n"); @@ -1957,7 +2006,4 @@ void __init print_system_hash_info(void) if (htab_hash_mask) pr_info("htab_hash_mask = 0x%lx\n", htab_hash_mask); - pr_info("kernel vmalloc start = 0x%lx\n", KERN_VIRT_START); - pr_info("kernel IO start = 0x%lx\n", KERN_IO_START); - pr_info("kernel vmemmap start = 0x%lx\n", (unsigned long)vmemmap); } diff --git a/arch/powerpc/mm/book3s64/pgtable.c b/arch/powerpc/mm/book3s64/pgtable.c index 7d0e0d0d22c4..75483b40fcb1 100644 --- a/arch/powerpc/mm/book3s64/pgtable.c +++ b/arch/powerpc/mm/book3s64/pgtable.c @@ -8,10 +8,13 @@ #include <linux/memblock.h> #include <misc/cxl-base.h> +#include <asm/debugfs.h> #include <asm/pgalloc.h> #include <asm/tlb.h> #include <asm/trace.h> #include <asm/powernv.h> +#include <asm/firmware.h> +#include <asm/ultravisor.h> #include <mm/mmu_decl.h> #include <trace/events/thp.h> @@ -21,9 +24,6 @@ EXPORT_SYMBOL(__pmd_frag_nr); unsigned long __pmd_frag_size_shift; EXPORT_SYMBOL(__pmd_frag_size_shift); -int (*register_process_table)(unsigned long base, unsigned long page_size, - unsigned long tbl_size); - #ifdef CONFIG_TRANSPARENT_HUGEPAGE /* * This is called when relaxing access to a hugepage. It's also called in the page @@ -205,37 +205,61 @@ void __init mmu_partition_table_init(void) * 64 K size. */ ptcr = __pa(partition_tb) | (PATB_SIZE_SHIFT - 12); - mtspr(SPRN_PTCR, ptcr); + set_ptcr_when_no_uv(ptcr); powernv_set_nmmu_ptcr(ptcr); } +static void flush_partition(unsigned int lpid, bool radix) +{ + if (radix) { + radix__flush_all_lpid(lpid); + radix__flush_all_lpid_guest(lpid); + } else { + asm volatile("ptesync" : : : "memory"); + asm volatile(PPC_TLBIE_5(%0,%1,2,0,0) : : + "r" (TLBIEL_INVAL_SET_LPID), "r" (lpid)); + /* do we need fixup here ?*/ + asm volatile("eieio; tlbsync; ptesync" : : : "memory"); + trace_tlbie(lpid, 0, TLBIEL_INVAL_SET_LPID, lpid, 2, 0, 0); + } +} + void mmu_partition_table_set_entry(unsigned int lpid, unsigned long dw0, - unsigned long dw1) + unsigned long dw1, bool flush) { unsigned long old = be64_to_cpu(partition_tb[lpid].patb0); + /* + * When ultravisor is enabled, the partition table is stored in secure + * memory and can only be accessed doing an ultravisor call. However, we + * maintain a copy of the partition table in normal memory to allow Nest + * MMU translations to occur (for normal VMs). + * + * Therefore, here we always update partition_tb, regardless of whether + * we are running under an ultravisor or not. + */ partition_tb[lpid].patb0 = cpu_to_be64(dw0); partition_tb[lpid].patb1 = cpu_to_be64(dw1); /* - * Global flush of TLBs and partition table caches for this lpid. - * The type of flush (hash or radix) depends on what the previous - * use of this partition ID was, not the new use. + * If ultravisor is enabled, we do an ultravisor call to register the + * partition table entry (PATE), which also do a global flush of TLBs + * and partition table caches for the lpid. Otherwise, just do the + * flush. The type of flush (hash or radix) depends on what the previous + * use of the partition ID was, not the new use. */ - asm volatile("ptesync" : : : "memory"); - if (old & PATB_HR) { - asm volatile(PPC_TLBIE_5(%0,%1,2,0,1) : : - "r" (TLBIEL_INVAL_SET_LPID), "r" (lpid)); - asm volatile(PPC_TLBIE_5(%0,%1,2,1,1) : : - "r" (TLBIEL_INVAL_SET_LPID), "r" (lpid)); - trace_tlbie(lpid, 0, TLBIEL_INVAL_SET_LPID, lpid, 2, 0, 1); - } else { - asm volatile(PPC_TLBIE_5(%0,%1,2,0,0) : : - "r" (TLBIEL_INVAL_SET_LPID), "r" (lpid)); - trace_tlbie(lpid, 0, TLBIEL_INVAL_SET_LPID, lpid, 2, 0, 0); + if (firmware_has_feature(FW_FEATURE_ULTRAVISOR)) { + uv_register_pate(lpid, dw0, dw1); + pr_info("PATE registered by ultravisor: dw0 = 0x%lx, dw1 = 0x%lx\n", + dw0, dw1); + } else if (flush) { + /* + * Boot does not need to flush, because MMU is off and each + * CPU does a tlbiel_all() before switching them on, which + * flushes everything. + */ + flush_partition(lpid, (old & PATB_HR)); } - /* do we need fixup here ?*/ - asm volatile("eieio; tlbsync; ptesync" : : : "memory"); } EXPORT_SYMBOL_GPL(mmu_partition_table_set_entry); @@ -447,23 +471,48 @@ 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; +/* + * Does the CPU support tlbie? + */ +bool tlbie_capable __read_mostly = true; +EXPORT_SYMBOL(tlbie_capable); - 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; - } +/* + * Should tlbie be used for management of CPU TLBs, for kernel and process + * address spaces? tlbie may still be used for nMMU accelerators, and for KVM + * guest address spaces. + */ +bool tlbie_enabled __read_mostly = true; + +static int __init setup_disable_tlbie(char *str) +{ + if (!radix_enabled()) { + pr_err("disable_tlbie: Unable to disable TLBIE with Hash MMU.\n"); + return 1; } + tlbie_capable = false; + tlbie_enabled = false; + + return 1; +} +__setup("disable_tlbie", setup_disable_tlbie); + +static int __init pgtable_debugfs_setup(void) +{ + if (!tlbie_capable) + return 0; + + /* + * There is no locking vs tlb flushing when changing this value. + * The tlb flushers will see one value or another, and use either + * tlbie or tlbiel with IPIs. In both cases the TLBs will be + * invalidated as expected. + */ + debugfs_create_bool("tlbie_enabled", 0600, + powerpc_debugfs_root, + &tlbie_enabled); + return 0; } +arch_initcall(pgtable_debugfs_setup); diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c index b4ca9e95e678..3a1fbf9cb8f8 100644 --- a/arch/powerpc/mm/book3s64/radix_pgtable.c +++ b/arch/powerpc/mm/book3s64/radix_pgtable.c @@ -27,25 +27,13 @@ #include <asm/sections.h> #include <asm/trace.h> #include <asm/uaccess.h> +#include <asm/ultravisor.h> #include <trace/events/thp.h> unsigned int mmu_pid_bits; unsigned int mmu_base_pid; -static int native_register_process_table(unsigned long base, unsigned long pg_sz, - unsigned long table_size) -{ - unsigned long patb0, patb1; - - patb0 = be64_to_cpu(partition_tb[0].patb0); - patb1 = base | table_size | PATB_GR; - - mmu_partition_table_set_entry(0, patb0, patb1); - - return 0; -} - static __ref void *early_alloc_pgtable(unsigned long size, int nid, unsigned long region_start, unsigned long region_end) { @@ -380,18 +368,6 @@ static void __init radix_init_pgtable(void) */ rts_field = radix__get_tree_size(); process_tb->prtb0 = cpu_to_be64(rts_field | __pa(init_mm.pgd) | RADIX_PGD_INDEX_SIZE); - /* - * Fill in the partition table. We are suppose to use effective address - * of process table here. But our linear mapping also enable us to use - * physical address here. - */ - register_process_table(__pa(process_tb), 0, PRTB_SIZE_SHIFT - 12); - pr_info("Process table %p and radix root for kernel: %p\n", process_tb, init_mm.pgd); - asm volatile("ptesync" : : : "memory"); - asm volatile(PPC_TLBIE_5(%0,%1,2,1,1) : : - "r" (TLBIEL_INVAL_SET_LPID), "r" (0)); - asm volatile("eieio; tlbsync; ptesync" : : : "memory"); - trace_tlbie(0, 0, TLBIEL_INVAL_SET_LPID, 0, 2, 1, 1); /* * The init_mm context is given the first available (non-zero) PID, @@ -412,20 +388,15 @@ static void __init radix_init_pgtable(void) static void __init radix_init_partition_table(void) { - unsigned long rts_field, dw0; + unsigned long rts_field, dw0, dw1; mmu_partition_table_init(); rts_field = radix__get_tree_size(); dw0 = rts_field | __pa(init_mm.pgd) | RADIX_PGD_INDEX_SIZE | PATB_HR; - mmu_partition_table_set_entry(0, dw0, 0); + dw1 = __pa(process_tb) | (PRTB_SIZE_SHIFT - 12) | PATB_GR; + mmu_partition_table_set_entry(0, dw0, dw1, false); pr_info("Initializing Radix MMU\n"); - pr_info("Partition table %p\n", partition_tb); -} - -void __init radix_init_native(void) -{ - register_process_table = native_register_process_table; } static int __init get_idx_from_shift(unsigned int shift) @@ -621,8 +592,9 @@ void __init radix__early_init_mmu(void) __pmd_frag_nr = RADIX_PMD_FRAG_NR; __pmd_frag_size_shift = RADIX_PMD_FRAG_SIZE_SHIFT; + radix_init_pgtable(); + if (!firmware_has_feature(FW_FEATURE_LPAR)) { - radix_init_native(); lpcr = mfspr(SPRN_LPCR); mtspr(SPRN_LPCR, lpcr | LPCR_UPRT | LPCR_HR); radix_init_partition_table(); @@ -633,11 +605,9 @@ void __init radix__early_init_mmu(void) memblock_set_current_limit(MEMBLOCK_ALLOC_ANYWHERE); - radix_init_pgtable(); /* Switch to the guard PID before turning on MMU */ radix__switch_mmu_context(NULL, &init_mm); - if (cpu_has_feature(CPU_FTR_HVMODE)) - tlbiel_all(); + tlbiel_all(); } void radix__early_init_mmu_secondary(void) @@ -650,14 +620,14 @@ void radix__early_init_mmu_secondary(void) lpcr = mfspr(SPRN_LPCR); mtspr(SPRN_LPCR, lpcr | LPCR_UPRT | LPCR_HR); - mtspr(SPRN_PTCR, - __pa(partition_tb) | (PATB_SIZE_SHIFT - 12)); + set_ptcr_when_no_uv(__pa(partition_tb) | + (PATB_SIZE_SHIFT - 12)); + radix_init_amor(); } radix__switch_mmu_context(NULL, &init_mm); - if (cpu_has_feature(CPU_FTR_HVMODE)) - tlbiel_all(); + tlbiel_all(); } void radix__mmu_cleanup_all(void) @@ -667,7 +637,7 @@ void radix__mmu_cleanup_all(void) if (!firmware_has_feature(FW_FEATURE_LPAR)) { lpcr = mfspr(SPRN_LPCR); mtspr(SPRN_LPCR, lpcr & ~LPCR_UPRT); - mtspr(SPRN_PTCR, 0); + set_ptcr_when_no_uv(0); powernv_set_nmmu_ptcr(0); radix__flush_tlb_all(); } @@ -737,8 +707,8 @@ static int __meminit stop_machine_change_mapping(void *data) spin_unlock(&init_mm.page_table_lock); pte_clear(&init_mm, params->aligned_start, params->pte); - create_physical_mapping(params->aligned_start, params->start, -1); - create_physical_mapping(params->end, params->aligned_end, -1); + create_physical_mapping(__pa(params->aligned_start), __pa(params->start), -1); + create_physical_mapping(__pa(params->end), __pa(params->aligned_end), -1); spin_lock(&init_mm.page_table_lock); return 0; } @@ -902,7 +872,7 @@ int __meminit radix__create_section_mapping(unsigned long start, unsigned long e return -1; } - return create_physical_mapping(start, end, nid); + return create_physical_mapping(__pa(start), __pa(end), nid); } int __meminit radix__remove_section_mapping(unsigned long start, unsigned long end) @@ -1218,26 +1188,6 @@ int pmd_free_pte_page(pmd_t *pmd, unsigned long addr) 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; - } -} - int __init arch_ioremap_p4d_supported(void) { return 0; diff --git a/arch/powerpc/mm/book3s64/radix_tlb.c b/arch/powerpc/mm/book3s64/radix_tlb.c index 71f7fede2fa4..631be42abd33 100644 --- a/arch/powerpc/mm/book3s64/radix_tlb.c +++ b/arch/powerpc/mm/book3s64/radix_tlb.c @@ -51,11 +51,15 @@ static void tlbiel_all_isa300(unsigned int num_sets, unsigned int is) * and partition table entries. Then flush the remaining sets of the * TLB. */ - tlbiel_radix_set_isa300(0, is, 0, RIC_FLUSH_ALL, 0); - for (set = 1; set < num_sets; set++) - tlbiel_radix_set_isa300(set, is, 0, RIC_FLUSH_TLB, 0); - /* Do the same for process scoped entries. */ + if (early_cpu_has_feature(CPU_FTR_HVMODE)) { + /* MSR[HV] should flush partition scope translations first. */ + tlbiel_radix_set_isa300(0, is, 0, RIC_FLUSH_ALL, 0); + for (set = 1; set < num_sets; set++) + tlbiel_radix_set_isa300(set, is, 0, RIC_FLUSH_TLB, 0); + } + + /* Flush process scoped entries. */ tlbiel_radix_set_isa300(0, is, 0, RIC_FLUSH_ALL, 1); for (set = 1; set < num_sets; set++) tlbiel_radix_set_isa300(set, is, 0, RIC_FLUSH_TLB, 1); @@ -116,22 +120,6 @@ static __always_inline void __tlbie_pid(unsigned long pid, unsigned long ric) trace_tlbie(0, 0, rb, rs, ric, prs, r); } -static __always_inline void __tlbiel_lpid(unsigned long lpid, int set, - unsigned long ric) -{ - unsigned long rb,rs,prs,r; - - rb = PPC_BIT(52); /* IS = 2 */ - rb |= set << PPC_BITLSHIFT(51); - rs = 0; /* LPID comes from LPIDR */ - prs = 0; /* partition scoped */ - r = 1; /* radix format */ - - asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1) - : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory"); - trace_tlbie(lpid, 1, rb, rs, ric, prs, r); -} - static __always_inline void __tlbie_lpid(unsigned long lpid, unsigned long ric) { unsigned long rb,rs,prs,r; @@ -146,23 +134,20 @@ static __always_inline void __tlbie_lpid(unsigned long lpid, unsigned long ric) trace_tlbie(lpid, 0, rb, rs, ric, prs, r); } -static __always_inline void __tlbiel_lpid_guest(unsigned long lpid, int set, - unsigned long ric) +static __always_inline void __tlbie_lpid_guest(unsigned long lpid, unsigned long ric) { unsigned long rb,rs,prs,r; rb = PPC_BIT(52); /* IS = 2 */ - rb |= set << PPC_BITLSHIFT(51); - rs = 0; /* LPID comes from LPIDR */ + rs = lpid; prs = 1; /* process scoped */ r = 1; /* radix format */ - asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1) + asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1) : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory"); - trace_tlbie(lpid, 1, rb, rs, ric, prs, r); + trace_tlbie(lpid, 0, rb, rs, ric, prs, r); } - static __always_inline void __tlbiel_va(unsigned long va, unsigned long pid, unsigned long ap, unsigned long ric) { @@ -285,32 +270,37 @@ static inline void _tlbie_pid(unsigned long pid, unsigned long ric) asm volatile("eieio; tlbsync; ptesync": : :"memory"); } -static inline void _tlbiel_lpid(unsigned long lpid, unsigned long ric) +struct tlbiel_pid { + unsigned long pid; + unsigned long ric; +}; + +static void do_tlbiel_pid(void *info) { - int set; + struct tlbiel_pid *t = info; - VM_BUG_ON(mfspr(SPRN_LPID) != lpid); + if (t->ric == RIC_FLUSH_TLB) + _tlbiel_pid(t->pid, RIC_FLUSH_TLB); + else if (t->ric == RIC_FLUSH_PWC) + _tlbiel_pid(t->pid, RIC_FLUSH_PWC); + else + _tlbiel_pid(t->pid, RIC_FLUSH_ALL); +} - asm volatile("ptesync": : :"memory"); +static inline void _tlbiel_pid_multicast(struct mm_struct *mm, + unsigned long pid, unsigned long ric) +{ + struct cpumask *cpus = mm_cpumask(mm); + struct tlbiel_pid t = { .pid = pid, .ric = ric }; + on_each_cpu_mask(cpus, do_tlbiel_pid, &t, 1); /* - * Flush the first set of the TLB, and if we're doing a RIC_FLUSH_ALL, - * also flush the entire Page Walk Cache. + * Always want the CPU translations to be invalidated with tlbiel in + * these paths, so while coprocessors must use tlbie, we can not + * optimise away the tlbiel component. */ - __tlbiel_lpid(lpid, 0, ric); - - /* For PWC, only one flush is needed */ - if (ric == RIC_FLUSH_PWC) { - asm volatile("ptesync": : :"memory"); - return; - } - - /* For the remaining sets, just flush the TLB */ - for (set = 1; set < POWER9_TLB_SETS_RADIX ; set++) - __tlbiel_lpid(lpid, set, RIC_FLUSH_TLB); - - asm volatile("ptesync": : :"memory"); - asm volatile(PPC_RADIX_INVALIDATE_ERAT_GUEST "; isync" : : :"memory"); + if (atomic_read(&mm->context.copros) > 0) + _tlbie_pid(pid, RIC_FLUSH_ALL); } static inline void _tlbie_lpid(unsigned long lpid, unsigned long ric) @@ -337,35 +327,28 @@ static inline void _tlbie_lpid(unsigned long lpid, unsigned long ric) asm volatile("eieio; tlbsync; ptesync": : :"memory"); } -static __always_inline void _tlbiel_lpid_guest(unsigned long lpid, unsigned long ric) +static __always_inline void _tlbie_lpid_guest(unsigned long lpid, unsigned long ric) { - int set; - - VM_BUG_ON(mfspr(SPRN_LPID) != lpid); - - asm volatile("ptesync": : :"memory"); - /* - * Flush the first set of the TLB, and if we're doing a RIC_FLUSH_ALL, - * also flush the entire Page Walk Cache. + * Workaround the fact that the "ric" argument to __tlbie_pid + * must be a compile-time contraint to match the "i" constraint + * in the asm statement. */ - __tlbiel_lpid_guest(lpid, 0, ric); - - /* For PWC, only one flush is needed */ - if (ric == RIC_FLUSH_PWC) { - asm volatile("ptesync": : :"memory"); - return; + switch (ric) { + case RIC_FLUSH_TLB: + __tlbie_lpid_guest(lpid, RIC_FLUSH_TLB); + break; + case RIC_FLUSH_PWC: + __tlbie_lpid_guest(lpid, RIC_FLUSH_PWC); + break; + case RIC_FLUSH_ALL: + default: + __tlbie_lpid_guest(lpid, RIC_FLUSH_ALL); } - - /* For the remaining sets, just flush the TLB */ - for (set = 1; set < POWER9_TLB_SETS_RADIX ; set++) - __tlbiel_lpid_guest(lpid, set, RIC_FLUSH_TLB); - - asm volatile("ptesync": : :"memory"); - asm volatile(PPC_RADIX_INVALIDATE_ERAT_GUEST : : :"memory"); + fixup_tlbie_lpid(lpid); + asm volatile("eieio; tlbsync; ptesync": : :"memory"); } - static inline void __tlbiel_va_range(unsigned long start, unsigned long end, unsigned long pid, unsigned long page_size, unsigned long psize) @@ -420,6 +403,53 @@ static __always_inline void _tlbie_va(unsigned long va, unsigned long pid, asm volatile("eieio; tlbsync; ptesync": : :"memory"); } +struct tlbiel_va { + unsigned long pid; + unsigned long va; + unsigned long psize; + unsigned long ric; +}; + +static void do_tlbiel_va(void *info) +{ + struct tlbiel_va *t = info; + + if (t->ric == RIC_FLUSH_TLB) + _tlbiel_va(t->va, t->pid, t->psize, RIC_FLUSH_TLB); + else if (t->ric == RIC_FLUSH_PWC) + _tlbiel_va(t->va, t->pid, t->psize, RIC_FLUSH_PWC); + else + _tlbiel_va(t->va, t->pid, t->psize, RIC_FLUSH_ALL); +} + +static inline void _tlbiel_va_multicast(struct mm_struct *mm, + unsigned long va, unsigned long pid, + unsigned long psize, unsigned long ric) +{ + struct cpumask *cpus = mm_cpumask(mm); + struct tlbiel_va t = { .va = va, .pid = pid, .psize = psize, .ric = ric }; + on_each_cpu_mask(cpus, do_tlbiel_va, &t, 1); + if (atomic_read(&mm->context.copros) > 0) + _tlbie_va(va, pid, psize, RIC_FLUSH_TLB); +} + +struct tlbiel_va_range { + unsigned long pid; + unsigned long start; + unsigned long end; + unsigned long page_size; + unsigned long psize; + bool also_pwc; +}; + +static void do_tlbiel_va_range(void *info) +{ + struct tlbiel_va_range *t = info; + + _tlbiel_va_range(t->start, t->end, t->pid, t->page_size, + t->psize, t->also_pwc); +} + static __always_inline void _tlbie_lpid_va(unsigned long va, unsigned long lpid, unsigned long psize, unsigned long ric) { @@ -443,6 +473,21 @@ static inline void _tlbie_va_range(unsigned long start, unsigned long end, asm volatile("eieio; tlbsync; ptesync": : :"memory"); } +static inline void _tlbiel_va_range_multicast(struct mm_struct *mm, + unsigned long start, unsigned long end, + unsigned long pid, unsigned long page_size, + unsigned long psize, bool also_pwc) +{ + struct cpumask *cpus = mm_cpumask(mm); + struct tlbiel_va_range t = { .start = start, .end = end, + .pid = pid, .page_size = page_size, + .psize = psize, .also_pwc = also_pwc }; + + on_each_cpu_mask(cpus, do_tlbiel_va_range, &t, 1); + if (atomic_read(&mm->context.copros) > 0) + _tlbie_va_range(start, end, pid, page_size, psize, also_pwc); +} + /* * Base TLB flushing operations: * @@ -580,10 +625,14 @@ void radix__flush_tlb_mm(struct mm_struct *mm) goto local; } - if (mm_needs_flush_escalation(mm)) - _tlbie_pid(pid, RIC_FLUSH_ALL); - else - _tlbie_pid(pid, RIC_FLUSH_TLB); + if (cputlb_use_tlbie()) { + if (mm_needs_flush_escalation(mm)) + _tlbie_pid(pid, RIC_FLUSH_ALL); + else + _tlbie_pid(pid, RIC_FLUSH_TLB); + } else { + _tlbiel_pid_multicast(mm, pid, RIC_FLUSH_TLB); + } } else { local: _tlbiel_pid(pid, RIC_FLUSH_TLB); @@ -609,7 +658,10 @@ static void __flush_all_mm(struct mm_struct *mm, bool fullmm) goto local; } } - _tlbie_pid(pid, RIC_FLUSH_ALL); + if (cputlb_use_tlbie()) + _tlbie_pid(pid, RIC_FLUSH_ALL); + else + _tlbiel_pid_multicast(mm, pid, RIC_FLUSH_ALL); } else { local: _tlbiel_pid(pid, RIC_FLUSH_ALL); @@ -644,7 +696,10 @@ void radix__flush_tlb_page_psize(struct mm_struct *mm, unsigned long vmaddr, exit_flush_lazy_tlbs(mm); goto local; } - _tlbie_va(vmaddr, pid, psize, RIC_FLUSH_TLB); + if (cputlb_use_tlbie()) + _tlbie_va(vmaddr, pid, psize, RIC_FLUSH_TLB); + else + _tlbiel_va_multicast(mm, vmaddr, pid, psize, RIC_FLUSH_TLB); } else { local: _tlbiel_va(vmaddr, pid, psize, RIC_FLUSH_TLB); @@ -666,6 +721,24 @@ EXPORT_SYMBOL(radix__flush_tlb_page); #define radix__flush_all_mm radix__local_flush_all_mm #endif /* CONFIG_SMP */ +static void do_tlbiel_kernel(void *info) +{ + _tlbiel_pid(0, RIC_FLUSH_ALL); +} + +static inline void _tlbiel_kernel_broadcast(void) +{ + on_each_cpu(do_tlbiel_kernel, NULL, 1); + if (tlbie_capable) { + /* + * Coherent accelerators don't refcount kernel memory mappings, + * so have to always issue a tlbie for them. This is quite a + * slow path anyway. + */ + _tlbie_pid(0, RIC_FLUSH_ALL); + } +} + /* * If kernel TLBIs ever become local rather than global, then * drivers/misc/ocxl/link.c:ocxl_link_add_pe will need some work, as it @@ -673,7 +746,10 @@ EXPORT_SYMBOL(radix__flush_tlb_page); */ void radix__flush_tlb_kernel_range(unsigned long start, unsigned long end) { - _tlbie_pid(0, RIC_FLUSH_ALL); + if (cputlb_use_tlbie()) + _tlbie_pid(0, RIC_FLUSH_ALL); + else + _tlbiel_kernel_broadcast(); } EXPORT_SYMBOL(radix__flush_tlb_kernel_range); @@ -729,10 +805,14 @@ is_local: if (local) { _tlbiel_pid(pid, RIC_FLUSH_TLB); } else { - if (mm_needs_flush_escalation(mm)) - _tlbie_pid(pid, RIC_FLUSH_ALL); - else - _tlbie_pid(pid, RIC_FLUSH_TLB); + if (cputlb_use_tlbie()) { + if (mm_needs_flush_escalation(mm)) + _tlbie_pid(pid, RIC_FLUSH_ALL); + else + _tlbie_pid(pid, RIC_FLUSH_TLB); + } else { + _tlbiel_pid_multicast(mm, pid, RIC_FLUSH_TLB); + } } } else { bool hflush = flush_all_sizes; @@ -757,8 +837,8 @@ is_local: gflush = false; } - asm volatile("ptesync": : :"memory"); if (local) { + asm volatile("ptesync": : :"memory"); __tlbiel_va_range(start, end, pid, page_size, mmu_virtual_psize); if (hflush) __tlbiel_va_range(hstart, hend, pid, @@ -767,7 +847,8 @@ is_local: __tlbiel_va_range(gstart, gend, pid, PUD_SIZE, MMU_PAGE_1G); asm volatile("ptesync": : :"memory"); - } else { + } else if (cputlb_use_tlbie()) { + asm volatile("ptesync": : :"memory"); __tlbie_va_range(start, end, pid, page_size, mmu_virtual_psize); if (hflush) __tlbie_va_range(hstart, hend, pid, @@ -777,6 +858,15 @@ is_local: PUD_SIZE, MMU_PAGE_1G); fixup_tlbie(); asm volatile("eieio; tlbsync; ptesync": : :"memory"); + } else { + _tlbiel_va_range_multicast(mm, + start, end, pid, page_size, mmu_virtual_psize, false); + if (hflush) + _tlbiel_va_range_multicast(mm, + hstart, hend, pid, PMD_SIZE, MMU_PAGE_2M, false); + if (gflush) + _tlbiel_va_range_multicast(mm, + gstart, gend, pid, PUD_SIZE, MMU_PAGE_1G, false); } } preempt_enable(); @@ -835,32 +925,19 @@ EXPORT_SYMBOL_GPL(radix__flush_pwc_lpid); /* * Flush partition scoped translations from LPID (=LPIDR) */ -void radix__flush_tlb_lpid(unsigned int lpid) +void radix__flush_all_lpid(unsigned int lpid) { _tlbie_lpid(lpid, RIC_FLUSH_ALL); } -EXPORT_SYMBOL_GPL(radix__flush_tlb_lpid); +EXPORT_SYMBOL_GPL(radix__flush_all_lpid); /* - * Flush partition scoped translations from LPID (=LPIDR) + * Flush process scoped translations from LPID (=LPIDR) */ -void radix__local_flush_tlb_lpid(unsigned int lpid) +void radix__flush_all_lpid_guest(unsigned int lpid) { - _tlbiel_lpid(lpid, RIC_FLUSH_ALL); + _tlbie_lpid_guest(lpid, RIC_FLUSH_ALL); } -EXPORT_SYMBOL_GPL(radix__local_flush_tlb_lpid); - -/* - * Flush process scoped translations from LPID (=LPIDR). - * Important difference, the guest normally manages its own translations, - * but some cases e.g., vCPU CPU migration require KVM to flush. - */ -void radix__local_flush_tlb_lpid_guest(unsigned int lpid) -{ - _tlbiel_lpid_guest(lpid, RIC_FLUSH_ALL); -} -EXPORT_SYMBOL_GPL(radix__local_flush_tlb_lpid_guest); - static void radix__flush_tlb_pwc_range_psize(struct mm_struct *mm, unsigned long start, unsigned long end, int psize); @@ -966,16 +1043,26 @@ is_local: if (local) { _tlbiel_pid(pid, also_pwc ? RIC_FLUSH_ALL : RIC_FLUSH_TLB); } else { - if (mm_needs_flush_escalation(mm)) - also_pwc = true; + if (cputlb_use_tlbie()) { + if (mm_needs_flush_escalation(mm)) + also_pwc = true; + + _tlbie_pid(pid, + also_pwc ? RIC_FLUSH_ALL : RIC_FLUSH_TLB); + } else { + _tlbiel_pid_multicast(mm, pid, + also_pwc ? RIC_FLUSH_ALL : RIC_FLUSH_TLB); + } - _tlbie_pid(pid, also_pwc ? RIC_FLUSH_ALL : RIC_FLUSH_TLB); } } else { if (local) _tlbiel_va_range(start, end, pid, page_size, psize, also_pwc); - else + else if (cputlb_use_tlbie()) _tlbie_va_range(start, end, pid, page_size, psize, also_pwc); + else + _tlbiel_va_range_multicast(mm, + start, end, pid, page_size, psize, also_pwc); } preempt_enable(); } @@ -1017,7 +1104,11 @@ void radix__flush_tlb_collapsed_pmd(struct mm_struct *mm, unsigned long addr) exit_flush_lazy_tlbs(mm); goto local; } - _tlbie_va_range(addr, end, pid, PAGE_SIZE, mmu_virtual_psize, true); + if (cputlb_use_tlbie()) + _tlbie_va_range(addr, end, pid, PAGE_SIZE, mmu_virtual_psize, true); + else + _tlbiel_va_range_multicast(mm, + addr, end, pid, PAGE_SIZE, mmu_virtual_psize, true); } else { local: _tlbiel_va_range(addr, end, pid, PAGE_SIZE, mmu_virtual_psize, true); diff --git a/arch/powerpc/mm/dma-noncoherent.c b/arch/powerpc/mm/dma-noncoherent.c index c617282d5b2a..2a82984356f8 100644 --- a/arch/powerpc/mm/dma-noncoherent.c +++ b/arch/powerpc/mm/dma-noncoherent.c @@ -4,310 +4,18 @@ * Copyright (C) 2001 Dan Malek (dmalek@jlc.net) * * Copyright (C) 2000 Russell King - * - * Consistent memory allocators. Used for DMA devices that want to - * share uncached memory with the processor core. The function return - * is the virtual address and 'dma_handle' is the physical address. - * Mostly stolen from the ARM port, with some changes for PowerPC. - * -- Dan - * - * Reorganized to get rid of the arch-specific consistent_* functions - * and provide non-coherent implementations for the DMA API. -Matt - * - * Added in_interrupt() safe dma_alloc_coherent()/dma_free_coherent() - * implementation. This is pulled straight from ARM and barely - * modified. -Matt */ -#include <linux/sched.h> -#include <linux/slab.h> #include <linux/kernel.h> #include <linux/errno.h> -#include <linux/string.h> #include <linux/types.h> #include <linux/highmem.h> #include <linux/dma-direct.h> #include <linux/dma-noncoherent.h> -#include <linux/export.h> #include <asm/tlbflush.h> #include <asm/dma.h> -#include <mm/mmu_decl.h> - -/* - * This address range defaults to a value that is safe for all - * platforms which currently set CONFIG_NOT_COHERENT_CACHE. It - * can be further configured for specific applications under - * the "Advanced Setup" menu. -Matt - */ -#define CONSISTENT_BASE (IOREMAP_TOP) -#define CONSISTENT_END (CONSISTENT_BASE + CONFIG_CONSISTENT_SIZE) -#define CONSISTENT_OFFSET(x) (((unsigned long)(x) - CONSISTENT_BASE) >> PAGE_SHIFT) - -/* - * This is the page table (2MB) covering uncached, DMA consistent allocations - */ -static DEFINE_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 ppc_vm_region { - struct list_head vm_list; - unsigned long vm_start; - unsigned long vm_end; -}; - -static struct ppc_vm_region consistent_head = { - .vm_list = LIST_HEAD_INIT(consistent_head.vm_list), - .vm_start = CONSISTENT_BASE, - .vm_end = CONSISTENT_END, -}; - -static struct ppc_vm_region * -ppc_vm_region_alloc(struct ppc_vm_region *head, size_t size, gfp_t gfp) -{ - unsigned long addr = head->vm_start, end = head->vm_end - size; - unsigned long flags; - struct ppc_vm_region *c, *new; - - new = kmalloc(sizeof(struct ppc_vm_region), gfp); - if (!new) - goto out; - - 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; - - spin_unlock_irqrestore(&consistent_lock, flags); - return new; - - nospc: - spin_unlock_irqrestore(&consistent_lock, flags); - kfree(new); - out: - return NULL; -} - -static struct ppc_vm_region *ppc_vm_region_find(struct ppc_vm_region *head, unsigned long addr) -{ - struct ppc_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; -} - -/* - * Allocate DMA-coherent memory space and return both the kernel remapped - * virtual and bus address for that space. - */ -void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, - gfp_t gfp, unsigned long attrs) -{ - struct page *page; - struct ppc_vm_region *c; - unsigned long order; - u64 mask = ISA_DMA_THRESHOLD, limit; - - 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; - } - - if ((~mask) & ISA_DMA_THRESHOLD) { - dev_warn(dev, "coherent DMA mask %#llx is smaller " - "than system GFP_DMA mask %#llx\n", - mask, (unsigned long long)ISA_DMA_THRESHOLD); - goto no_page; - } - } - - - size = PAGE_ALIGN(size); - limit = (mask + 1) & ~mask; - if ((limit && size >= limit) || - size >= (CONSISTENT_END - CONSISTENT_BASE)) { - printk(KERN_WARNING "coherent allocation too big (requested %#x mask %#Lx)\n", - size, mask); - return NULL; - } - - order = get_order(size); - - /* Might be useful if we ever have a real legacy DMA zone... */ - 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); - flush_dcache_range(kaddr, kaddr + size); - } - - /* - * Allocate a virtual address in the consistent mapping region. - */ - c = ppc_vm_region_alloc(&consistent_head, size, - gfp & ~(__GFP_DMA | __GFP_HIGHMEM)); - if (c) { - unsigned long vaddr = c->vm_start; - struct page *end = page + (1 << order); - - split_page(page, order); - - /* - * Set the "dma handle" - */ - *dma_handle = phys_to_dma(dev, page_to_phys(page)); - - do { - SetPageReserved(page); - map_kernel_page(vaddr, page_to_phys(page), - pgprot_noncached(PAGE_KERNEL)); - page++; - vaddr += PAGE_SIZE; - } 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: - return NULL; -} - -/* - * free a page as defined by the above mapping. - */ -void arch_dma_free(struct device *dev, size_t size, void *vaddr, - dma_addr_t dma_handle, unsigned long attrs) -{ - struct ppc_vm_region *c; - unsigned long flags, addr; - - size = PAGE_ALIGN(size); - - spin_lock_irqsave(&consistent_lock, flags); - - c = ppc_vm_region_find(&consistent_head, (unsigned long)vaddr); - if (!c) - goto no_area; - - if ((c->vm_end - c->vm_start) != size) { - printk(KERN_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; - } - - addr = c->vm_start; - do { - pte_t *ptep; - unsigned long pfn; - - ptep = pte_offset_kernel(pmd_offset(pud_offset(pgd_offset_k(addr), - addr), - addr), - addr); - if (!pte_none(*ptep) && pte_present(*ptep)) { - pfn = pte_pfn(*ptep); - pte_clear(&init_mm, addr, ptep); - if (pfn_valid(pfn)) { - struct page *page = pfn_to_page(pfn); - __free_reserved_page(page); - } - } - addr += PAGE_SIZE; - } while (size -= PAGE_SIZE); - - flush_tlb_kernel_range(c->vm_start, c->vm_end); - - list_del(&c->vm_list); - - spin_unlock_irqrestore(&consistent_lock, flags); - - kfree(c); - return; - - no_area: - spin_unlock_irqrestore(&consistent_lock, flags); - printk(KERN_ERR "%s: trying to free invalid coherent area: %p\n", - __func__, vaddr); - dump_stack(); -} - /* * make an area consistent. */ @@ -408,23 +116,9 @@ void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr, __dma_sync_page(paddr, size, dir); } -/* - * Return the PFN for a given cpu virtual address returned by arch_dma_alloc. - */ -long arch_dma_coherent_to_pfn(struct device *dev, void *vaddr, - dma_addr_t dma_addr) +void arch_dma_prep_coherent(struct page *page, size_t size) { - /* This should always be populated, so we don't test every - * level. If that fails, we'll have a nice crash which - * will be as good as a BUG_ON() - */ - unsigned long cpu_addr = (unsigned long)vaddr; - pgd_t *pgd = pgd_offset_k(cpu_addr); - pud_t *pud = pud_offset(pgd, cpu_addr); - pmd_t *pmd = pmd_offset(pud, cpu_addr); - pte_t *ptep = pte_offset_kernel(pmd, cpu_addr); + unsigned long kaddr = (unsigned long)page_address(page); - if (pte_none(*ptep) || !pte_present(*ptep)) - return 0; - return pte_pfn(*ptep); + flush_dcache_range(kaddr, kaddr + size); } diff --git a/arch/powerpc/mm/ioremap.c b/arch/powerpc/mm/ioremap.c new file mode 100644 index 000000000000..fc669643ce6a --- /dev/null +++ b/arch/powerpc/mm/ioremap.c @@ -0,0 +1,99 @@ +// SPDX-License-Identifier: GPL-2.0-or-later + +#include <linux/io.h> +#include <linux/slab.h> +#include <linux/vmalloc.h> +#include <asm/io-workarounds.h> + +unsigned long ioremap_bot; +EXPORT_SYMBOL(ioremap_bot); + +void __iomem *ioremap(phys_addr_t addr, unsigned long size) +{ + pgprot_t prot = pgprot_noncached(PAGE_KERNEL); + void *caller = __builtin_return_address(0); + + if (iowa_is_active()) + return iowa_ioremap(addr, size, prot, caller); + return __ioremap_caller(addr, size, prot, caller); +} +EXPORT_SYMBOL(ioremap); + +void __iomem *ioremap_wc(phys_addr_t addr, unsigned long size) +{ + pgprot_t prot = pgprot_noncached_wc(PAGE_KERNEL); + void *caller = __builtin_return_address(0); + + if (iowa_is_active()) + return iowa_ioremap(addr, size, prot, caller); + return __ioremap_caller(addr, size, prot, caller); +} +EXPORT_SYMBOL(ioremap_wc); + +void __iomem *ioremap_coherent(phys_addr_t addr, unsigned long size) +{ + pgprot_t prot = pgprot_cached(PAGE_KERNEL); + void *caller = __builtin_return_address(0); + + if (iowa_is_active()) + return iowa_ioremap(addr, size, prot, caller); + return __ioremap_caller(addr, size, prot, caller); +} + +void __iomem *ioremap_prot(phys_addr_t addr, unsigned long size, unsigned long flags) +{ + pte_t pte = __pte(flags); + void *caller = __builtin_return_address(0); + + /* writeable implies dirty for kernel addresses */ + if (pte_write(pte)) + pte = pte_mkdirty(pte); + + /* we don't want to let _PAGE_USER and _PAGE_EXEC leak out */ + pte = pte_exprotect(pte); + pte = pte_mkprivileged(pte); + + if (iowa_is_active()) + return iowa_ioremap(addr, size, pte_pgprot(pte), caller); + return __ioremap_caller(addr, size, pte_pgprot(pte), caller); +} +EXPORT_SYMBOL(ioremap_prot); + +int early_ioremap_range(unsigned long ea, phys_addr_t pa, + unsigned long size, pgprot_t prot) +{ + 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; +} + +void __iomem *do_ioremap(phys_addr_t pa, phys_addr_t offset, unsigned long size, + pgprot_t prot, void *caller) +{ + struct vm_struct *area; + int ret; + unsigned long va; + + area = __get_vm_area_caller(size, VM_IOREMAP, IOREMAP_START, IOREMAP_END, caller); + if (area == NULL) + return NULL; + + area->phys_addr = pa; + va = (unsigned long)area->addr; + + ret = ioremap_page_range(va, va + size, pa, prot); + if (!ret) + return (void __iomem *)area->addr + offset; + + unmap_kernel_range(va, size); + free_vm_area(area); + + return NULL; +} diff --git a/arch/powerpc/mm/ioremap_32.c b/arch/powerpc/mm/ioremap_32.c new file mode 100644 index 000000000000..f36121f25243 --- /dev/null +++ b/arch/powerpc/mm/ioremap_32.c @@ -0,0 +1,92 @@ +// SPDX-License-Identifier: GPL-2.0-or-later + +#include <linux/io.h> +#include <linux/slab.h> +#include <linux/vmalloc.h> + +#include <mm/mmu_decl.h> + +void __iomem *ioremap_wt(phys_addr_t addr, unsigned long size) +{ + pgprot_t prot = pgprot_cached_wthru(PAGE_KERNEL); + + return __ioremap_caller(addr, size, prot, __builtin_return_address(0)); +} +EXPORT_SYMBOL(ioremap_wt); + +void __iomem * +__ioremap_caller(phys_addr_t addr, unsigned long size, pgprot_t prot, void *caller) +{ + unsigned long v; + phys_addr_t p, offset; + int err; + + /* + * Choose an address to map it to. + * Once the vmalloc system is running, we use it. + * Before then, we use space going down from IOREMAP_TOP + * (ioremap_bot records where we're up to). + */ + p = addr & PAGE_MASK; + offset = addr & ~PAGE_MASK; + size = PAGE_ALIGN(addr + size) - p; + + /* + * If the address lies within the first 16 MB, assume it's in ISA + * memory space + */ + if (p < 16 * 1024 * 1024) + p += _ISA_MEM_BASE; + +#ifndef CONFIG_CRASH_DUMP + /* + * Don't allow anybody to remap normal RAM that we're using. + * mem_init() sets high_memory so only do the check after that. + */ + if (slab_is_available() && p <= virt_to_phys(high_memory - 1) && + page_is_ram(__phys_to_pfn(p))) { + pr_warn("%s(): phys addr 0x%llx is RAM lr %ps\n", __func__, + (unsigned long long)p, __builtin_return_address(0)); + return NULL; + } +#endif + + if (size == 0) + return NULL; + + /* + * Is it already mapped? Perhaps overlapped by a previous + * mapping. + */ + v = p_block_mapped(p); + if (v) + return (void __iomem *)v + offset; + + if (slab_is_available()) + return do_ioremap(p, offset, size, prot, caller); + + /* + * Should check if it is a candidate for a BAT mapping + */ + + err = early_ioremap_range(ioremap_bot - size, p, size, prot); + if (err) + return NULL; + ioremap_bot -= size; + + return (void __iomem *)ioremap_bot + offset; +} + +void iounmap(volatile void __iomem *addr) +{ + /* + * If mapped by BATs then there is nothing to do. + * Calling vfree() generates a benign warning. + */ + if (v_block_mapped((unsigned long)addr)) + return; + + if (addr > high_memory && (unsigned long)addr < ioremap_bot) + vunmap((void *)(PAGE_MASK & (unsigned long)addr)); +} +EXPORT_SYMBOL(iounmap); diff --git a/arch/powerpc/mm/ioremap_64.c b/arch/powerpc/mm/ioremap_64.c new file mode 100644 index 000000000000..fd29e51700cd --- /dev/null +++ b/arch/powerpc/mm/ioremap_64.c @@ -0,0 +1,113 @@ +// SPDX-License-Identifier: GPL-2.0-or-later + +#include <linux/io.h> +#include <linux/slab.h> +#include <linux/vmalloc.h> + +/** + * 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) +{ + int ret; + unsigned long va = (unsigned long)ea; + + /* We don't support the 4K PFN hack with ioremap */ + if (pgprot_val(prot) & H_PAGE_4K_PFN) + return NULL; + + if ((ea + size) >= (void *)IOREMAP_END) { + pr_warn("Outside the supported range\n"); + return NULL; + } + + WARN_ON(pa & ~PAGE_MASK); + WARN_ON(((unsigned long)ea) & ~PAGE_MASK); + WARN_ON(size & ~PAGE_MASK); + + if (slab_is_available()) { + ret = ioremap_page_range(va, va + size, pa, prot); + if (ret) + unmap_kernel_range(va, size); + } else { + ret = early_ioremap_range(va, pa, size, prot); + } + + if (ret) + return NULL; + + return (void __iomem *)ea; +} +EXPORT_SYMBOL(__ioremap_at); + +/** + * Low level function to tear down the page tables for an IO mapping. This is + * used for mappings that are manipulated manually, like partial unmapping of + * PCI IOs or ISA space. + */ +void __iounmap_at(void *ea, unsigned long size) +{ + WARN_ON(((unsigned long)ea) & ~PAGE_MASK); + WARN_ON(size & ~PAGE_MASK); + + unmap_kernel_range((unsigned long)ea, size); +} +EXPORT_SYMBOL(__iounmap_at); + +void __iomem *__ioremap_caller(phys_addr_t addr, unsigned long size, + pgprot_t prot, void *caller) +{ + phys_addr_t paligned, offset; + void __iomem *ret; + int err; + + /* We don't support the 4K PFN hack with ioremap */ + if (pgprot_val(prot) & H_PAGE_4K_PFN) + return NULL; + + /* + * Choose an address to map it to. Once the vmalloc system is running, + * we use it. Before that, we map using addresses going up from + * ioremap_bot. vmalloc will use the addresses from IOREMAP_BASE + * through ioremap_bot. + */ + paligned = addr & PAGE_MASK; + offset = addr & ~PAGE_MASK; + size = PAGE_ALIGN(addr + size) - paligned; + + if (size == 0 || paligned == 0) + return NULL; + + if (slab_is_available()) + return do_ioremap(paligned, offset, size, prot, caller); + + err = early_ioremap_range(ioremap_bot, paligned, size, prot); + if (err) + return NULL; + + ret = (void __iomem *)ioremap_bot + offset; + ioremap_bot += size; + + return ret; +} + +/* + * Unmap an IO region and remove it from vmalloc'd list. + * Access to IO memory should be serialized by driver. + */ +void iounmap(volatile void __iomem *token) +{ + void *addr; + + if (!slab_is_available()) + return; + + addr = (void *)((unsigned long __force)PCI_FIX_ADDR(token) & PAGE_MASK); + + if ((unsigned long)addr < ioremap_bot) { + pr_warn("Attempt to iounmap early bolted mapping at 0x%p\n", addr); + return; + } + vunmap(addr); +} +EXPORT_SYMBOL(iounmap); diff --git a/arch/powerpc/mm/kasan/kasan_init_32.c b/arch/powerpc/mm/kasan/kasan_init_32.c index 74f4555a62ba..802387b231ad 100644 --- a/arch/powerpc/mm/kasan/kasan_init_32.c +++ b/arch/powerpc/mm/kasan/kasan_init_32.c @@ -5,6 +5,7 @@ #include <linux/kasan.h> #include <linux/printk.h> #include <linux/memblock.h> +#include <linux/moduleloader.h> #include <linux/sched/task.h> #include <linux/vmalloc.h> #include <asm/pgalloc.h> @@ -46,7 +47,19 @@ static int __ref kasan_init_shadow_page_tables(unsigned long k_start, unsigned l kasan_populate_pte(new, PAGE_READONLY); else kasan_populate_pte(new, PAGE_KERNEL_RO); - pmd_populate_kernel(&init_mm, pmd, new); + + smp_wmb(); /* See comment in __pte_alloc */ + + spin_lock(&init_mm.page_table_lock); + /* Has another populated it ? */ + if (likely((void *)pmd_page_vaddr(*pmd) == kasan_early_shadow_pte)) { + pmd_populate_kernel(&init_mm, pmd, new); + new = NULL; + } + spin_unlock(&init_mm.page_table_lock); + + if (new && slab_is_available()) + pte_free_kernel(&init_mm, new); } return 0; } @@ -74,7 +87,7 @@ static int __ref kasan_init_region(void *start, size_t size) if (!slab_is_available()) block = memblock_alloc(k_end - k_start, PAGE_SIZE); - for (k_cur = k_start; k_cur < k_end; k_cur += PAGE_SIZE) { + for (k_cur = k_start & PAGE_MASK; k_cur < k_end; k_cur += PAGE_SIZE) { pmd_t *pmd = pmd_offset(pud_offset(pgd_offset_k(k_cur), k_cur), k_cur); void *va = block ? block + k_cur - k_start : kasan_get_one_page(); pte_t pte = pfn_pte(PHYS_PFN(__pa(va)), PAGE_KERNEL); @@ -137,7 +150,11 @@ void __init kasan_init(void) #ifdef CONFIG_MODULES void *module_alloc(unsigned long size) { - void *base = vmalloc_exec(size); + void *base; + + base = __vmalloc_node_range(size, MODULE_ALIGN, VMALLOC_START, VMALLOC_END, + GFP_KERNEL, PAGE_KERNEL_EXEC, VM_FLUSH_RESET_PERMS, + NUMA_NO_NODE, __builtin_return_address(0)); if (!base) return NULL; diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 9191a66b3bc5..be941d382c8d 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -302,12 +302,9 @@ void __init mem_init(void) pr_info(" * 0x%08lx..0x%08lx : highmem PTEs\n", PKMAP_BASE, PKMAP_ADDR(LAST_PKMAP)); #endif /* CONFIG_HIGHMEM */ -#ifdef CONFIG_NOT_COHERENT_CACHE - pr_info(" * 0x%08lx..0x%08lx : consistent mem\n", - IOREMAP_TOP, IOREMAP_TOP + CONFIG_CONSISTENT_SIZE); -#endif /* CONFIG_NOT_COHERENT_CACHE */ - pr_info(" * 0x%08lx..0x%08lx : early ioremap\n", - ioremap_bot, IOREMAP_TOP); + if (ioremap_bot != IOREMAP_TOP) + pr_info(" * 0x%08lx..0x%08lx : early ioremap\n", + ioremap_bot, IOREMAP_TOP); pr_info(" * 0x%08lx..0x%08lx : vmalloc & ioremap\n", VMALLOC_START, VMALLOC_END); #endif /* CONFIG_PPC32 */ @@ -407,63 +404,6 @@ void flush_icache_user_range(struct vm_area_struct *vma, struct page *page, EXPORT_SYMBOL(flush_icache_user_range); /* - * This is called at the end of handling a user page fault, when the - * fault has been handled by updating a PTE in the linux page tables. - * We use it to preload an HPTE into the hash table corresponding to - * the updated linux PTE. - * - * This must always be called with the pte lock held. - */ -void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, - pte_t *ptep) -{ -#ifdef CONFIG_PPC_BOOK3S - /* - * We don't need to worry about _PAGE_PRESENT here because we are - * called with either mm->page_table_lock held or ptl lock held - */ - unsigned long trap; - bool is_exec; - - if (radix_enabled()) { - prefetch((void *)address); - return; - } - - /* We only want HPTEs for linux PTEs that have _PAGE_ACCESSED set */ - if (!pte_young(*ptep) || address >= TASK_SIZE) - return; - - /* We try to figure out if we are coming from an instruction - * access fault and pass that down to __hash_page so we avoid - * double-faulting on execution of fresh text. We have to test - * for regs NULL since init will get here first thing at boot - * - * We also avoid filling the hash if not coming from a fault - */ - - trap = current->thread.regs ? TRAP(current->thread.regs) : 0UL; - switch (trap) { - case 0x300: - is_exec = false; - break; - case 0x400: - is_exec = true; - break; - default: - return; - } - - hash_preload(vma->vm_mm, address, is_exec, trap); -#endif /* CONFIG_PPC_BOOK3S */ -#if (defined(CONFIG_PPC_BOOK3E_64) || defined(CONFIG_PPC_FSL_BOOK3E)) \ - && defined(CONFIG_HUGETLB_PAGE) - if (is_vm_hugetlb_page(vma)) - book3e_hugetlb_preload(vma, address, *ptep); -#endif -} - -/* * System memory should not be in /proc/iomem but various tools expect it * (eg kdump). */ diff --git a/arch/powerpc/mm/mmu_decl.h b/arch/powerpc/mm/mmu_decl.h index 32c1a191c28a..c750ac9ec713 100644 --- a/arch/powerpc/mm/mmu_decl.h +++ b/arch/powerpc/mm/mmu_decl.h @@ -82,10 +82,6 @@ static inline void print_system_hash_info(void) {} #else /* CONFIG_PPC_MMU_NOHASH */ -extern void hash_preload(struct mm_struct *mm, unsigned long ea, - bool is_exec, unsigned long trap); - - extern void _tlbie(unsigned long address); extern void _tlbia(void); @@ -95,6 +91,8 @@ void print_system_hash_info(void); #ifdef CONFIG_PPC32 +void hash_preload(struct mm_struct *mm, unsigned long ea); + extern void mapin_ram(void); extern void setbat(int index, unsigned long virt, phys_addr_t phys, unsigned int size, pgprot_t prot); @@ -108,7 +106,6 @@ extern u8 early_hash[]; #endif /* CONFIG_PPC32 */ -extern unsigned long ioremap_bot; extern unsigned long __max_low_memory; extern phys_addr_t __initial_memory_limit_addr; extern phys_addr_t total_memory; diff --git a/arch/powerpc/mm/nohash/book3e_hugetlbpage.c b/arch/powerpc/mm/nohash/book3e_hugetlbpage.c index 61915f4d3c7f..8b88be91b622 100644 --- a/arch/powerpc/mm/nohash/book3e_hugetlbpage.c +++ b/arch/powerpc/mm/nohash/book3e_hugetlbpage.c @@ -122,8 +122,8 @@ static inline int book3e_tlb_exists(unsigned long ea, unsigned long pid) return found; } -void book3e_hugetlb_preload(struct vm_area_struct *vma, unsigned long ea, - pte_t pte) +static void +book3e_hugetlb_preload(struct vm_area_struct *vma, unsigned long ea, pte_t pte) { unsigned long mas1, mas2; u64 mas7_3; @@ -183,6 +183,18 @@ void book3e_hugetlb_preload(struct vm_area_struct *vma, unsigned long ea, local_irq_restore(flags); } +/* + * This is called at the end of handling a user page fault, when the + * fault has been handled by updating a PTE in the linux page tables. + * + * This must always be called with the pte lock held. + */ +void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) +{ + if (is_vm_hugetlb_page(vma)) + book3e_hugetlb_preload(vma, address, *ptep); +} + void flush_hugetlb_page(struct vm_area_struct *vma, unsigned long vmaddr) { struct hstate *hstate = hstate_file(vma->vm_file); diff --git a/arch/powerpc/mm/nohash/tlb.c b/arch/powerpc/mm/nohash/tlb.c index bf60983a58c7..696f568253a0 100644 --- a/arch/powerpc/mm/nohash/tlb.c +++ b/arch/powerpc/mm/nohash/tlb.c @@ -703,6 +703,8 @@ static void __init early_init_mmu_global(void) * for use by the TLB miss code */ linear_map_top = memblock_end_of_DRAM(); + + ioremap_bot = IOREMAP_BASE; } static void __init early_mmu_set_memory_limit(void) diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c index 35cb96cfc258..8ec5dfb65b2e 100644 --- a/arch/powerpc/mm/pgtable_32.c +++ b/arch/powerpc/mm/pgtable_32.c @@ -27,166 +27,13 @@ #include <asm/pgtable.h> #include <asm/pgalloc.h> #include <asm/fixmap.h> -#include <asm/io.h> #include <asm/setup.h> #include <asm/sections.h> #include <mm/mmu_decl.h> -unsigned long ioremap_bot; -EXPORT_SYMBOL(ioremap_bot); /* aka VMALLOC_END */ - extern char etext[], _stext[], _sinittext[], _einittext[]; -void __iomem * -ioremap(phys_addr_t addr, unsigned long size) -{ - pgprot_t prot = pgprot_noncached(PAGE_KERNEL); - - return __ioremap_caller(addr, size, prot, __builtin_return_address(0)); -} -EXPORT_SYMBOL(ioremap); - -void __iomem * -ioremap_wc(phys_addr_t addr, unsigned long size) -{ - pgprot_t prot = pgprot_noncached_wc(PAGE_KERNEL); - - return __ioremap_caller(addr, size, prot, __builtin_return_address(0)); -} -EXPORT_SYMBOL(ioremap_wc); - -void __iomem * -ioremap_wt(phys_addr_t addr, unsigned long size) -{ - pgprot_t prot = pgprot_cached_wthru(PAGE_KERNEL); - - return __ioremap_caller(addr, size, prot, __builtin_return_address(0)); -} -EXPORT_SYMBOL(ioremap_wt); - -void __iomem * -ioremap_coherent(phys_addr_t addr, unsigned long size) -{ - pgprot_t prot = pgprot_cached(PAGE_KERNEL); - - return __ioremap_caller(addr, size, prot, __builtin_return_address(0)); -} -EXPORT_SYMBOL(ioremap_coherent); - -void __iomem * -ioremap_prot(phys_addr_t addr, unsigned long size, unsigned long flags) -{ - pte_t pte = __pte(flags); - - /* writeable implies dirty for kernel addresses */ - if (pte_write(pte)) - pte = pte_mkdirty(pte); - - /* we don't want to let _PAGE_USER and _PAGE_EXEC leak out */ - pte = pte_exprotect(pte); - pte = pte_mkprivileged(pte); - - return __ioremap_caller(addr, size, pte_pgprot(pte), __builtin_return_address(0)); -} -EXPORT_SYMBOL(ioremap_prot); - -void __iomem * -__ioremap(phys_addr_t addr, unsigned long size, unsigned long flags) -{ - return __ioremap_caller(addr, size, __pgprot(flags), __builtin_return_address(0)); -} - -void __iomem * -__ioremap_caller(phys_addr_t addr, unsigned long size, pgprot_t prot, void *caller) -{ - unsigned long v, i; - phys_addr_t p; - int err; - - /* - * Choose an address to map it to. - * Once the vmalloc system is running, we use it. - * Before then, we use space going down from IOREMAP_TOP - * (ioremap_bot records where we're up to). - */ - p = addr & PAGE_MASK; - size = PAGE_ALIGN(addr + size) - p; - - /* - * If the address lies within the first 16 MB, assume it's in ISA - * memory space - */ - if (p < 16*1024*1024) - p += _ISA_MEM_BASE; - -#ifndef CONFIG_CRASH_DUMP - /* - * Don't allow anybody to remap normal RAM that we're using. - * mem_init() sets high_memory so only do the check after that. - */ - if (slab_is_available() && p <= virt_to_phys(high_memory - 1) && - page_is_ram(__phys_to_pfn(p))) { - printk("__ioremap(): phys addr 0x%llx is RAM lr %ps\n", - (unsigned long long)p, __builtin_return_address(0)); - return NULL; - } -#endif - - if (size == 0) - return NULL; - - /* - * Is it already mapped? Perhaps overlapped by a previous - * mapping. - */ - v = p_block_mapped(p); - if (v) - goto out; - - if (slab_is_available()) { - struct vm_struct *area; - area = get_vm_area_caller(size, VM_IOREMAP, caller); - if (area == 0) - return NULL; - area->phys_addr = p; - v = (unsigned long) area->addr; - } else { - v = (ioremap_bot -= size); - } - - /* - * Should check if it is a candidate for a BAT mapping - */ - - err = 0; - for (i = 0; i < size && err == 0; i += PAGE_SIZE) - err = map_kernel_page(v + i, p + i, prot); - if (err) { - if (slab_is_available()) - vunmap((void *)v); - return NULL; - } - -out: - return (void __iomem *) (v + ((unsigned long)addr & ~PAGE_MASK)); -} -EXPORT_SYMBOL(__ioremap); - -void iounmap(volatile void __iomem *addr) -{ - /* - * If mapped by BATs then there is nothing to do. - * Calling vfree() generates a benign warning. - */ - if (v_block_mapped((unsigned long)addr)) - return; - - if (addr > high_memory && (unsigned long) addr < ioremap_bot) - vunmap((void *) (PAGE_MASK & (unsigned long)addr)); -} -EXPORT_SYMBOL(iounmap); - static void __init *early_alloc_pgtable(unsigned long size) { void *ptr = memblock_alloc(size, size); @@ -252,7 +99,7 @@ static void __init __mapin_ram_chunk(unsigned long offset, unsigned long top) map_kernel_page(v, p, ktext ? PAGE_KERNEL_TEXT : PAGE_KERNEL); #ifdef CONFIG_PPC_BOOK3S_32 if (ktext) - hash_preload(&init_mm, v, false, 0x300); + hash_preload(&init_mm, v); #endif v += PAGE_SIZE; p += PAGE_SIZE; diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c index 9ad59b733984..e78832dce7bb 100644 --- a/arch/powerpc/mm/pgtable_64.c +++ b/arch/powerpc/mm/pgtable_64.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* - * This file contains ioremap and related functions for 64-bit machines. + * This file contains pgtable related functions for 64-bit machines. * * Derived from arch/ppc64/mm/init.c * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org) @@ -34,7 +34,6 @@ #include <asm/pgalloc.h> #include <asm/page.h> #include <asm/prom.h> -#include <asm/io.h> #include <asm/mmu_context.h> #include <asm/pgtable.h> #include <asm/mmu.h> @@ -98,208 +97,8 @@ unsigned long __pte_frag_nr; EXPORT_SYMBOL(__pte_frag_nr); unsigned long __pte_frag_size_shift; EXPORT_SYMBOL(__pte_frag_size_shift); -unsigned long ioremap_bot; -#else /* !CONFIG_PPC_BOOK3S_64 */ -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) -{ - /* We don't support the 4K PFN hack with ioremap */ - if (pgprot_val(prot) & H_PAGE_4K_PFN) - return NULL; - - if ((ea + size) >= (void *)IOREMAP_END) { - pr_warn("Outside the supported range\n"); - return NULL; - } - - WARN_ON(pa & ~PAGE_MASK); - WARN_ON(((unsigned long)ea) & ~PAGE_MASK); - WARN_ON(size & ~PAGE_MASK); - - if (ioremap_range((unsigned long)ea, pa, size, prot, NUMA_NO_NODE)) - return NULL; - - return (void __iomem *)ea; -} - -/** - * __iounmap_from - Low level function to tear down the page tables - * for an IO mapping. This is used for mappings that - * are manipulated manually, like partial unmapping of - * PCI IOs or ISA space. - */ -void __iounmap_at(void *ea, unsigned long size) -{ - WARN_ON(((unsigned long)ea) & ~PAGE_MASK); - WARN_ON(size & ~PAGE_MASK); - - unmap_kernel_range((unsigned long)ea, size); -} - -void __iomem * __ioremap_caller(phys_addr_t addr, unsigned long size, - pgprot_t prot, void *caller) -{ - phys_addr_t paligned; - void __iomem *ret; - - /* - * Choose an address to map it to. - * Once the imalloc system is running, we use it. - * Before that, we map using addresses going - * up from ioremap_bot. imalloc will use - * the addresses from ioremap_bot through - * IMALLOC_END - * - */ - paligned = addr & PAGE_MASK; - size = PAGE_ALIGN(addr + size) - paligned; - - if ((size == 0) || (paligned == 0)) - return NULL; - - if (slab_is_available()) { - struct vm_struct *area; - - area = __get_vm_area_caller(size, VM_IOREMAP, - ioremap_bot, IOREMAP_END, - caller); - if (area == NULL) - return NULL; - - area->phys_addr = paligned; - ret = __ioremap_at(paligned, area->addr, size, prot); - } else { - ret = __ioremap_at(paligned, (void *)ioremap_bot, size, prot); - if (ret) - ioremap_bot += size; - } - - if (ret) - ret += addr & ~PAGE_MASK; - return ret; -} - -void __iomem * __ioremap(phys_addr_t addr, unsigned long size, - unsigned long flags) -{ - return __ioremap_caller(addr, size, __pgprot(flags), __builtin_return_address(0)); -} - -void __iomem * ioremap(phys_addr_t addr, unsigned long size) -{ - pgprot_t prot = pgprot_noncached(PAGE_KERNEL); - void *caller = __builtin_return_address(0); - - if (ppc_md.ioremap) - return ppc_md.ioremap(addr, size, prot, caller); - return __ioremap_caller(addr, size, prot, caller); -} - -void __iomem * ioremap_wc(phys_addr_t addr, unsigned long size) -{ - pgprot_t prot = pgprot_noncached_wc(PAGE_KERNEL); - void *caller = __builtin_return_address(0); - - if (ppc_md.ioremap) - return ppc_md.ioremap(addr, size, prot, caller); - return __ioremap_caller(addr, size, prot, caller); -} - -void __iomem *ioremap_coherent(phys_addr_t addr, unsigned long size) -{ - pgprot_t prot = pgprot_cached(PAGE_KERNEL); - void *caller = __builtin_return_address(0); - - if (ppc_md.ioremap) - return ppc_md.ioremap(addr, size, prot, caller); - return __ioremap_caller(addr, size, prot, caller); -} - -void __iomem * ioremap_prot(phys_addr_t addr, unsigned long size, - unsigned long flags) -{ - pte_t pte = __pte(flags); - void *caller = __builtin_return_address(0); - - /* writeable implies dirty for kernel addresses */ - if (pte_write(pte)) - pte = pte_mkdirty(pte); - - /* we don't want to let _PAGE_EXEC leak out */ - pte = pte_exprotect(pte); - /* - * Force kernel mapping. - */ - pte = pte_mkprivileged(pte); - - if (ppc_md.ioremap) - return ppc_md.ioremap(addr, size, pte_pgprot(pte), caller); - return __ioremap_caller(addr, size, pte_pgprot(pte), caller); -} - - -/* - * Unmap an IO region and remove it from imalloc'd list. - * Access to IO memory should be serialized by driver. - */ -void __iounmap(volatile void __iomem *token) -{ - void *addr; - - if (!slab_is_available()) - return; - - addr = (void *) ((unsigned long __force) - PCI_FIX_ADDR(token) & PAGE_MASK); - if ((unsigned long)addr < ioremap_bot) { - printk(KERN_WARNING "Attempt to iounmap early bolted mapping" - " at 0x%p\n", addr); - return; - } - vunmap(addr); -} - -void iounmap(volatile void __iomem *token) -{ - if (ppc_md.iounmap) - ppc_md.iounmap(token); - else - __iounmap(token); -} - -EXPORT_SYMBOL(ioremap); -EXPORT_SYMBOL(ioremap_wc); -EXPORT_SYMBOL(ioremap_prot); -EXPORT_SYMBOL(__ioremap); -EXPORT_SYMBOL(__ioremap_at); -EXPORT_SYMBOL(iounmap); -EXPORT_SYMBOL(__iounmap); -EXPORT_SYMBOL(__iounmap_at); - #ifndef __PAGETABLE_PUD_FOLDED /* 4 level page table */ struct page *pgd_page(pgd_t pgd) diff --git a/arch/powerpc/mm/ptdump/bats.c b/arch/powerpc/mm/ptdump/bats.c index a0d23e96e841..4154feac1da3 100644 --- a/arch/powerpc/mm/ptdump/bats.c +++ b/arch/powerpc/mm/ptdump/bats.c @@ -149,7 +149,7 @@ static int bats_show_603(struct seq_file *m, void *v) static int bats_open(struct inode *inode, struct file *file) { - if (cpu_has_feature(CPU_FTR_601)) + if (IS_ENABLED(CONFIG_PPC_BOOK3S_601)) return single_open(file, bats_show_601, NULL); return single_open(file, bats_show_603, NULL); diff --git a/arch/powerpc/mm/ptdump/hashpagetable.c b/arch/powerpc/mm/ptdump/hashpagetable.c index 72f0e4a3d839..a07278027c6f 100644 --- a/arch/powerpc/mm/ptdump/hashpagetable.c +++ b/arch/powerpc/mm/ptdump/hashpagetable.c @@ -237,7 +237,6 @@ static int native_find(unsigned long ea, int psize, bool primary, u64 *v, u64 return -1; } -#ifdef CONFIG_PPC_PSERIES static int pseries_find(unsigned long ea, int psize, bool primary, u64 *v, u64 *r) { struct hash_pte ptes[4]; @@ -274,7 +273,6 @@ static int pseries_find(unsigned long ea, int psize, bool primary, u64 *v, u64 * } return -1; } -#endif static void decode_r(int bps, unsigned long r, unsigned long *rpn, int *aps, unsigned long *lp_bits) @@ -316,10 +314,9 @@ static void decode_r(int bps, unsigned long r, unsigned long *rpn, int *aps, static int base_hpte_find(unsigned long ea, int psize, bool primary, u64 *v, u64 *r) { -#ifdef CONFIG_PPC_PSERIES - if (firmware_has_feature(FW_FEATURE_LPAR)) + if (IS_ENABLED(CONFIG_PPC_PSERIES) && firmware_has_feature(FW_FEATURE_LPAR)) return pseries_find(ea, psize, primary, v, r); -#endif + return native_find(ea, psize, primary, v, r); } @@ -386,12 +383,13 @@ static void walk_pte(struct pg_state *st, pmd_t *pmd, unsigned long start) psize = mmu_vmalloc_psize; else psize = mmu_io_psize; -#ifdef CONFIG_PPC_64K_PAGES + /* check for secret 4K mappings */ - if (((pteval & H_PAGE_COMBO) == H_PAGE_COMBO) || - ((pteval & H_PAGE_4K_PFN) == H_PAGE_4K_PFN)) + if (IS_ENABLED(CONFIG_PPC_64K_PAGES) && + ((pteval & H_PAGE_COMBO) == H_PAGE_COMBO || + (pteval & H_PAGE_4K_PFN) == H_PAGE_4K_PFN)) psize = mmu_io_psize; -#endif + /* check for hashpte */ status = hpte_find(st, addr, psize); @@ -469,9 +467,10 @@ static void walk_linearmapping(struct pg_state *st) static void walk_vmemmap(struct pg_state *st) { -#ifdef CONFIG_SPARSEMEM_VMEMMAP struct vmemmap_backing *ptr = vmemmap_list; + if (!IS_ENABLED(CONFIG_SPARSEMEM_VMEMMAP)) + return; /* * Traverse the vmemmaped memory and dump pages that are in the hash * pagetable. @@ -481,7 +480,6 @@ static void walk_vmemmap(struct pg_state *st) ptr = ptr->list; } seq_puts(st->seq, "---[ vmemmap end ]---\n"); -#endif } static void populate_markers(void) @@ -495,11 +493,7 @@ static void populate_markers(void) address_markers[6].start_address = PHB_IO_END; address_markers[7].start_address = IOREMAP_BASE; address_markers[8].start_address = IOREMAP_END; -#ifdef CONFIG_PPC_BOOK3S_64 address_markers[9].start_address = H_VMEMMAP_START; -#else - address_markers[9].start_address = VMEMMAP_BASE; -#endif } static int ptdump_show(struct seq_file *m, void *v) diff --git a/arch/powerpc/mm/ptdump/ptdump.c b/arch/powerpc/mm/ptdump/ptdump.c index 6a88a9f585d4..2f9ddc29c535 100644 --- a/arch/powerpc/mm/ptdump/ptdump.c +++ b/arch/powerpc/mm/ptdump/ptdump.c @@ -26,10 +26,6 @@ #include "ptdump.h" -#ifdef CONFIG_PPC32 -#define KERN_VIRT_START PAGE_OFFSET -#endif - /* * To visualise what is happening, * @@ -88,10 +84,6 @@ static struct addr_marker address_markers[] = { #else { 0, "Early I/O remap start" }, { 0, "Early I/O remap end" }, -#ifdef CONFIG_NOT_COHERENT_CACHE - { 0, "Consistent mem start" }, - { 0, "Consistent mem end" }, -#endif #ifdef CONFIG_HIGHMEM { 0, "Highmem PTEs start" }, { 0, "Highmem PTEs end" }, @@ -181,7 +173,7 @@ static void dump_addr(struct pg_state *st, unsigned long addr) static void note_prot_wx(struct pg_state *st, unsigned long addr) { - if (!st->check_wx) + if (!IS_ENABLED(CONFIG_PPC_DEBUG_WX) || !st->check_wx) return; if (!((st->current_flags & pgprot_val(PAGE_KERNEL_X)) == pgprot_val(PAGE_KERNEL_X))) @@ -299,17 +291,15 @@ static void walk_pud(struct pg_state *st, pgd_t *pgd, unsigned long start) static void walk_pagetables(struct pg_state *st) { - pgd_t *pgd = pgd_offset_k(0UL); unsigned int i; - unsigned long addr; - - addr = st->start_address; + unsigned long addr = st->start_address & PGDIR_MASK; + pgd_t *pgd = pgd_offset_k(addr); /* * Traverse the linux pagetable structure and dump pages that are in * the hash pagetable. */ - for (i = 0; i < PTRS_PER_PGD; i++, pgd++, addr += PGDIR_SIZE) { + for (i = pgd_index(addr); i < PTRS_PER_PGD; i++, pgd++, addr += PGDIR_SIZE) { if (!pgd_none(*pgd) && !pgd_is_leaf(*pgd)) /* pgd exists */ walk_pud(st, pgd, addr); @@ -341,11 +331,6 @@ static void populate_markers(void) #else /* !CONFIG_PPC64 */ address_markers[i++].start_address = ioremap_bot; address_markers[i++].start_address = IOREMAP_TOP; -#ifdef CONFIG_NOT_COHERENT_CACHE - address_markers[i++].start_address = IOREMAP_TOP; - address_markers[i++].start_address = IOREMAP_TOP + - CONFIG_CONSISTENT_SIZE; -#endif #ifdef CONFIG_HIGHMEM address_markers[i++].start_address = PKMAP_BASE; address_markers[i++].start_address = PKMAP_ADDR(LAST_PKMAP); @@ -364,12 +349,13 @@ static int ptdump_show(struct seq_file *m, void *v) struct pg_state st = { .seq = m, .marker = address_markers, + .start_address = PAGE_OFFSET, }; - if (radix_enabled()) - st.start_address = PAGE_OFFSET; - else +#ifdef CONFIG_PPC64 + if (!radix_enabled()) st.start_address = KERN_VIRT_START; +#endif /* Traverse kernel page tables */ walk_pagetables(&st); @@ -407,12 +393,13 @@ void ptdump_check_wx(void) .seq = NULL, .marker = address_markers, .check_wx = true, + .start_address = PAGE_OFFSET, }; - if (radix_enabled()) - st.start_address = PAGE_OFFSET; - else +#ifdef CONFIG_PPC64 + if (!radix_enabled()) st.start_address = KERN_VIRT_START; +#endif walk_pagetables(&st); diff --git a/arch/powerpc/perf/imc-pmu.c b/arch/powerpc/perf/imc-pmu.c index dea243185ea4..cb50a9e1fd2d 100644 --- a/arch/powerpc/perf/imc-pmu.c +++ b/arch/powerpc/perf/imc-pmu.c @@ -577,6 +577,7 @@ static int core_imc_mem_init(int cpu, int size) { int nid, rc = 0, core_id = (cpu / threads_per_core); struct imc_mem_info *mem_info; + struct page *page; /* * alloc_pages_node() will allocate memory for core in the @@ -587,11 +588,12 @@ static int core_imc_mem_init(int cpu, int size) mem_info->id = core_id; /* We need only vbase for core counters */ - mem_info->vbase = page_address(alloc_pages_node(nid, - GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE | - __GFP_NOWARN, get_order(size))); - if (!mem_info->vbase) + page = alloc_pages_node(nid, + GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE | + __GFP_NOWARN, get_order(size)); + if (!page) return -ENOMEM; + mem_info->vbase = page_address(page); /* Init the mutex */ core_imc_refc[core_id].id = core_id; @@ -849,15 +851,17 @@ static int thread_imc_mem_alloc(int cpu_id, int size) int nid = cpu_to_node(cpu_id); if (!local_mem) { + struct page *page; /* * This case could happen only once at start, since we dont * free the memory in cpu offline path. */ - local_mem = page_address(alloc_pages_node(nid, + page = alloc_pages_node(nid, GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE | - __GFP_NOWARN, get_order(size))); - if (!local_mem) + __GFP_NOWARN, get_order(size)); + if (!page) return -ENOMEM; + local_mem = page_address(page); per_cpu(thread_imc_mem, cpu_id) = local_mem; } @@ -1095,11 +1099,14 @@ static int trace_imc_mem_alloc(int cpu_id, int size) int core_id = (cpu_id / threads_per_core); if (!local_mem) { - local_mem = page_address(alloc_pages_node(phys_id, - GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE | - __GFP_NOWARN, get_order(size))); - if (!local_mem) + struct page *page; + + page = alloc_pages_node(phys_id, + GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE | + __GFP_NOWARN, get_order(size)); + if (!page) return -ENOMEM; + local_mem = page_address(page); per_cpu(trace_imc_mem, cpu_id) = local_mem; /* Initialise the counters for trace mode */ diff --git a/arch/powerpc/platforms/44x/Kconfig b/arch/powerpc/platforms/44x/Kconfig index b369ed4e3675..25ebe634a661 100644 --- a/arch/powerpc/platforms/44x/Kconfig +++ b/arch/powerpc/platforms/44x/Kconfig @@ -272,14 +272,6 @@ config PPC4xx_GPIO help Enable gpiolib support for ppc440 based boards -config PPC4xx_OCM - bool "PPC4xx On Chip Memory (OCM) support" - depends on 4xx - select PPC_LIB_RHEAP - help - Enable OCM support for PowerPC 4xx platforms with on chip memory, - OCM provides the fast place for memory access to improve performance. - # 44x specific CPU modules, selected based on the board above. config 440EP bool diff --git a/arch/powerpc/platforms/4xx/Makefile b/arch/powerpc/platforms/4xx/Makefile index f5ae27ca131b..d009d2e0b9e8 100644 --- a/arch/powerpc/platforms/4xx/Makefile +++ b/arch/powerpc/platforms/4xx/Makefile @@ -1,6 +1,5 @@ # SPDX-License-Identifier: GPL-2.0-only obj-y += uic.o machine_check.o -obj-$(CONFIG_PPC4xx_OCM) += ocm.o obj-$(CONFIG_4xx_SOC) += soc.o obj-$(CONFIG_PCI) += pci.o obj-$(CONFIG_PPC4xx_HSTA_MSI) += hsta_msi.o diff --git a/arch/powerpc/platforms/4xx/ocm.c b/arch/powerpc/platforms/4xx/ocm.c deleted file mode 100644 index ba3257406ced..000000000000 --- a/arch/powerpc/platforms/4xx/ocm.c +++ /dev/null @@ -1,390 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * PowerPC 4xx OCM memory allocation support - * - * (C) Copyright 2009, Applied Micro Circuits Corporation - * Victor Gallardo (vgallardo@amcc.com) - * - * See file CREDITS for list of people who contributed to this - * project. - */ - -#include <linux/kernel.h> -#include <linux/dma-mapping.h> -#include <linux/of.h> -#include <linux/of_address.h> -#include <asm/rheap.h> -#include <asm/ppc4xx_ocm.h> -#include <linux/slab.h> -#include <linux/debugfs.h> - -#define OCM_DISABLED 0 -#define OCM_ENABLED 1 - -struct ocm_block { - struct list_head list; - void __iomem *addr; - int size; - const char *owner; -}; - -/* non-cached or cached region */ -struct ocm_region { - phys_addr_t phys; - void __iomem *virt; - - int memtotal; - int memfree; - - rh_info_t *rh; - struct list_head list; -}; - -struct ocm_info { - int index; - int status; - int ready; - - phys_addr_t phys; - - int alignment; - int memtotal; - int cache_size; - - struct ocm_region nc; /* non-cached region */ - struct ocm_region c; /* cached region */ -}; - -static struct ocm_info *ocm_nodes; -static int ocm_count; - -static struct ocm_info *ocm_get_node(unsigned int index) -{ - if (index >= ocm_count) { - printk(KERN_ERR "PPC4XX OCM: invalid index"); - return NULL; - } - - return &ocm_nodes[index]; -} - -static int ocm_free_region(struct ocm_region *ocm_reg, const void *addr) -{ - struct ocm_block *blk, *tmp; - unsigned long offset; - - if (!ocm_reg->virt) - return 0; - - list_for_each_entry_safe(blk, tmp, &ocm_reg->list, list) { - if (blk->addr == addr) { - offset = addr - ocm_reg->virt; - ocm_reg->memfree += blk->size; - rh_free(ocm_reg->rh, offset); - list_del(&blk->list); - kfree(blk); - return 1; - } - } - - return 0; -} - -static void __init ocm_init_node(int count, struct device_node *node) -{ - struct ocm_info *ocm; - - const unsigned int *cell_index; - const unsigned int *cache_size; - int len; - - struct resource rsrc; - - ocm = ocm_get_node(count); - - cell_index = of_get_property(node, "cell-index", &len); - if (!cell_index) { - printk(KERN_ERR "PPC4XX OCM: missing cell-index property"); - return; - } - ocm->index = *cell_index; - - if (of_device_is_available(node)) - ocm->status = OCM_ENABLED; - - cache_size = of_get_property(node, "cached-region-size", &len); - if (cache_size) - ocm->cache_size = *cache_size; - - if (of_address_to_resource(node, 0, &rsrc)) { - printk(KERN_ERR "PPC4XX OCM%d: could not get resource address\n", - ocm->index); - return; - } - - ocm->phys = rsrc.start; - ocm->memtotal = (rsrc.end - rsrc.start + 1); - - printk(KERN_INFO "PPC4XX OCM%d: %d Bytes (%s)\n", - ocm->index, ocm->memtotal, - (ocm->status == OCM_DISABLED) ? "disabled" : "enabled"); - - if (ocm->status == OCM_DISABLED) - return; - - /* request region */ - - if (!request_mem_region(ocm->phys, ocm->memtotal, "ppc4xx_ocm")) { - printk(KERN_ERR "PPC4XX OCM%d: could not request region\n", - ocm->index); - return; - } - - /* Configure non-cached and cached regions */ - - ocm->nc.phys = ocm->phys; - ocm->nc.memtotal = ocm->memtotal - ocm->cache_size; - ocm->nc.memfree = ocm->nc.memtotal; - - ocm->c.phys = ocm->phys + ocm->nc.memtotal; - ocm->c.memtotal = ocm->cache_size; - ocm->c.memfree = ocm->c.memtotal; - - if (ocm->nc.memtotal == 0) - ocm->nc.phys = 0; - - if (ocm->c.memtotal == 0) - ocm->c.phys = 0; - - printk(KERN_INFO "PPC4XX OCM%d: %d Bytes (non-cached)\n", - ocm->index, ocm->nc.memtotal); - - printk(KERN_INFO "PPC4XX OCM%d: %d Bytes (cached)\n", - ocm->index, ocm->c.memtotal); - - /* ioremap the non-cached region */ - if (ocm->nc.memtotal) { - ocm->nc.virt = __ioremap(ocm->nc.phys, ocm->nc.memtotal, - _PAGE_EXEC | pgprot_val(PAGE_KERNEL_NCG)); - - if (!ocm->nc.virt) { - printk(KERN_ERR - "PPC4XX OCM%d: failed to ioremap non-cached memory\n", - ocm->index); - ocm->nc.memfree = 0; - return; - } - } - - /* ioremap the cached region */ - - if (ocm->c.memtotal) { - ocm->c.virt = __ioremap(ocm->c.phys, ocm->c.memtotal, - _PAGE_EXEC | pgprot_val(PAGE_KERNEL)); - - if (!ocm->c.virt) { - printk(KERN_ERR - "PPC4XX OCM%d: failed to ioremap cached memory\n", - ocm->index); - ocm->c.memfree = 0; - return; - } - } - - /* Create Remote Heaps */ - - ocm->alignment = 4; /* default 4 byte alignment */ - - if (ocm->nc.virt) { - ocm->nc.rh = rh_create(ocm->alignment); - rh_attach_region(ocm->nc.rh, 0, ocm->nc.memtotal); - } - - if (ocm->c.virt) { - ocm->c.rh = rh_create(ocm->alignment); - rh_attach_region(ocm->c.rh, 0, ocm->c.memtotal); - } - - INIT_LIST_HEAD(&ocm->nc.list); - INIT_LIST_HEAD(&ocm->c.list); - - ocm->ready = 1; -} - -static int ocm_debugfs_show(struct seq_file *m, void *v) -{ - struct ocm_block *blk, *tmp; - unsigned int i; - - for (i = 0; i < ocm_count; i++) { - struct ocm_info *ocm = ocm_get_node(i); - - if (!ocm || !ocm->ready) - continue; - - seq_printf(m, "PPC4XX OCM : %d\n", ocm->index); - seq_printf(m, "PhysAddr : %pa\n", &(ocm->phys)); - seq_printf(m, "MemTotal : %d Bytes\n", ocm->memtotal); - seq_printf(m, "MemTotal(NC) : %d Bytes\n", ocm->nc.memtotal); - seq_printf(m, "MemTotal(C) : %d Bytes\n\n", ocm->c.memtotal); - - seq_printf(m, "NC.PhysAddr : %pa\n", &(ocm->nc.phys)); - seq_printf(m, "NC.VirtAddr : 0x%p\n", ocm->nc.virt); - seq_printf(m, "NC.MemTotal : %d Bytes\n", ocm->nc.memtotal); - seq_printf(m, "NC.MemFree : %d Bytes\n", ocm->nc.memfree); - - list_for_each_entry_safe(blk, tmp, &ocm->nc.list, list) { - seq_printf(m, "NC.MemUsed : %d Bytes (%s)\n", - blk->size, blk->owner); - } - - seq_printf(m, "\nC.PhysAddr : %pa\n", &(ocm->c.phys)); - seq_printf(m, "C.VirtAddr : 0x%p\n", ocm->c.virt); - seq_printf(m, "C.MemTotal : %d Bytes\n", ocm->c.memtotal); - seq_printf(m, "C.MemFree : %d Bytes\n", ocm->c.memfree); - - list_for_each_entry_safe(blk, tmp, &ocm->c.list, list) { - seq_printf(m, "C.MemUsed : %d Bytes (%s)\n", - blk->size, blk->owner); - } - - seq_putc(m, '\n'); - } - - return 0; -} - -static int ocm_debugfs_open(struct inode *inode, struct file *file) -{ - return single_open(file, ocm_debugfs_show, NULL); -} - -static const struct file_operations ocm_debugfs_fops = { - .open = ocm_debugfs_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; - -static int ocm_debugfs_init(void) -{ - struct dentry *junk; - - junk = debugfs_create_dir("ppc4xx_ocm", 0); - if (!junk) { - printk(KERN_ALERT "debugfs ppc4xx ocm: failed to create dir\n"); - return -1; - } - - if (debugfs_create_file("info", 0644, junk, NULL, &ocm_debugfs_fops)) { - printk(KERN_ALERT "debugfs ppc4xx ocm: failed to create file\n"); - return -1; - } - - return 0; -} - -void *ppc4xx_ocm_alloc(phys_addr_t *phys, int size, int align, - int flags, const char *owner) -{ - void __iomem *addr = NULL; - unsigned long offset; - struct ocm_info *ocm; - struct ocm_region *ocm_reg; - struct ocm_block *ocm_blk; - int i; - - for (i = 0; i < ocm_count; i++) { - ocm = ocm_get_node(i); - - if (!ocm || !ocm->ready) - continue; - - if (flags == PPC4XX_OCM_NON_CACHED) - ocm_reg = &ocm->nc; - else - ocm_reg = &ocm->c; - - if (!ocm_reg->virt) - continue; - - if (align < ocm->alignment) - align = ocm->alignment; - - offset = rh_alloc_align(ocm_reg->rh, size, align, NULL); - - if (IS_ERR_VALUE(offset)) - continue; - - ocm_blk = kzalloc(sizeof(*ocm_blk), GFP_KERNEL); - if (!ocm_blk) { - rh_free(ocm_reg->rh, offset); - break; - } - - *phys = ocm_reg->phys + offset; - addr = ocm_reg->virt + offset; - size = ALIGN(size, align); - - ocm_blk->addr = addr; - ocm_blk->size = size; - ocm_blk->owner = owner; - list_add_tail(&ocm_blk->list, &ocm_reg->list); - - ocm_reg->memfree -= size; - - break; - } - - return addr; -} - -void ppc4xx_ocm_free(const void *addr) -{ - int i; - - if (!addr) - return; - - for (i = 0; i < ocm_count; i++) { - struct ocm_info *ocm = ocm_get_node(i); - - if (!ocm || !ocm->ready) - continue; - - if (ocm_free_region(&ocm->nc, addr) || - ocm_free_region(&ocm->c, addr)) - return; - } -} - -static int __init ppc4xx_ocm_init(void) -{ - struct device_node *np; - int count; - - count = 0; - for_each_compatible_node(np, NULL, "ibm,ocm") - count++; - - if (!count) - return 0; - - ocm_nodes = kzalloc((count * sizeof(struct ocm_info)), GFP_KERNEL); - if (!ocm_nodes) - return -ENOMEM; - - ocm_count = count; - count = 0; - - for_each_compatible_node(np, NULL, "ibm,ocm") { - ocm_init_node(count, np); - count++; - } - - ocm_debugfs_init(); - - return 0; -} - -arch_initcall(ppc4xx_ocm_init); diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig index f3fb79fccc72..d82e3664ffdf 100644 --- a/arch/powerpc/platforms/Kconfig +++ b/arch/powerpc/platforms/Kconfig @@ -197,7 +197,8 @@ endmenu config PPC601_SYNC_FIX bool "Workarounds for PPC601 bugs" - depends on PPC_BOOK3S_32 && PPC_PMAC + depends on PPC_BOOK3S_601 && PPC_PMAC + default y help Some versions of the PPC601 (the first PowerPC chip) have bugs which mean that extra synchronization instructions are required near diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype index 56a7c814160d..12543e53fa96 100644 --- a/arch/powerpc/platforms/Kconfig.cputype +++ b/arch/powerpc/platforms/Kconfig.cputype @@ -6,6 +6,9 @@ config PPC64 This option selects whether a 32-bit or a 64-bit kernel will be built. +config PPC_BOOK3S_32 + bool + menu "Processor support" choice prompt "Processor Type" @@ -21,13 +24,20 @@ choice If unsure, select 52xx/6xx/7xx/74xx/82xx/83xx/86xx. -config PPC_BOOK3S_32 - bool "512x/52xx/6xx/7xx/74xx/82xx/83xx/86xx" +config PPC_BOOK3S_6xx + bool "512x/52xx/6xx/7xx/74xx/82xx/83xx/86xx except 601" + select PPC_BOOK3S_32 select PPC_FPU select PPC_HAVE_PMU_SUPPORT select PPC_HAVE_KUEP select PPC_HAVE_KUAP +config PPC_BOOK3S_601 + bool "PowerPC 601" + select PPC_BOOK3S_32 + select PPC_FPU + select PPC_HAVE_KUAP + config PPC_85xx bool "Freescale 85xx" select E500 @@ -450,8 +460,10 @@ config NOT_COHERENT_CACHE depends on 4xx || PPC_8xx || E200 || PPC_MPC512x || \ GAMECUBE_COMMON || AMIGAONE select ARCH_HAS_DMA_COHERENT_TO_PFN + select ARCH_HAS_DMA_PREP_COHERENT select ARCH_HAS_SYNC_DMA_FOR_DEVICE select ARCH_HAS_SYNC_DMA_FOR_CPU + select DMA_DIRECT_REMAP default n if PPC_47x default y diff --git a/arch/powerpc/platforms/cell/iommu.c b/arch/powerpc/platforms/cell/iommu.c index 16dfee29aa41..ca9ffc1c8685 100644 --- a/arch/powerpc/platforms/cell/iommu.c +++ b/arch/powerpc/platforms/cell/iommu.c @@ -486,7 +486,7 @@ cell_iommu_setup_window(struct cbe_iommu *iommu, struct device_node *np, window->table.it_size = size >> window->table.it_page_shift; window->table.it_ops = &cell_iommu_ops; - iommu_init_table(&window->table, iommu->nid); + iommu_init_table(&window->table, iommu->nid, 0, 0); pr_debug("\tioid %d\n", window->ioid); pr_debug("\tblocksize %ld\n", window->table.it_blocksize); diff --git a/arch/powerpc/platforms/pasemi/iommu.c b/arch/powerpc/platforms/pasemi/iommu.c index 77fee09104f8..b500a6e47e6b 100644 --- a/arch/powerpc/platforms/pasemi/iommu.c +++ b/arch/powerpc/platforms/pasemi/iommu.c @@ -146,7 +146,7 @@ static void iommu_table_iobmap_setup(void) */ iommu_table_iobmap.it_blocksize = 4; iommu_table_iobmap.it_ops = &iommu_table_iobmap_ops; - iommu_init_table(&iommu_table_iobmap, 0); + iommu_init_table(&iommu_table_iobmap, 0, 0, 0); pr_debug(" <- %s\n", __func__); } diff --git a/arch/powerpc/platforms/powernv/Kconfig b/arch/powerpc/platforms/powernv/Kconfig index 850eee860cf2..938803eab0ad 100644 --- a/arch/powerpc/platforms/powernv/Kconfig +++ b/arch/powerpc/platforms/powernv/Kconfig @@ -12,7 +12,6 @@ config PPC_POWERNV select EPAPR_BOOT select PPC_INDIRECT_PIO select PPC_UDBG_16550 - select PPC_SCOM select ARCH_RANDOM select CPU_FREQ select PPC_DOORBELL @@ -47,3 +46,7 @@ config PPC_VAS VAS adapters are found in POWER9 based systems. If unsure, say N. + +config SCOM_DEBUGFS + bool "Expose SCOM controllers via debugfs" + depends on DEBUG_FS diff --git a/arch/powerpc/platforms/powernv/Makefile b/arch/powerpc/platforms/powernv/Makefile index da2e99efbd04..a3ac9646119d 100644 --- a/arch/powerpc/platforms/powernv/Makefile +++ b/arch/powerpc/platforms/powernv/Makefile @@ -4,15 +4,19 @@ obj-y += idle.o opal-rtc.o opal-nvram.o opal-lpc.o opal-flash.o obj-y += rng.o opal-elog.o opal-dump.o opal-sysparam.o opal-sensor.o obj-y += opal-msglog.o opal-hmi.o opal-power.o opal-irqchip.o obj-y += opal-kmsg.o opal-powercap.o opal-psr.o opal-sensor-groups.o +obj-y += ultravisor.o obj-$(CONFIG_SMP) += smp.o subcore.o subcore-asm.o +obj-$(CONFIG_FA_DUMP) += opal-fadump.o +obj-$(CONFIG_PRESERVE_FA_DUMP) += opal-fadump.o +obj-$(CONFIG_OPAL_CORE) += opal-core.o obj-$(CONFIG_PCI) += pci.o pci-ioda.o npu-dma.o pci-ioda-tce.o obj-$(CONFIG_CXL_BASE) += pci-cxl.o obj-$(CONFIG_EEH) += eeh-powernv.o -obj-$(CONFIG_PPC_SCOM) += opal-xscom.o obj-$(CONFIG_MEMORY_FAILURE) += opal-memory-errors.o obj-$(CONFIG_OPAL_PRD) += opal-prd.o obj-$(CONFIG_PERF_EVENTS) += opal-imc.o obj-$(CONFIG_PPC_MEMTRACE) += memtrace.o obj-$(CONFIG_PPC_VAS) += vas.o vas-window.o vas-debug.o obj-$(CONFIG_OCXL_BASE) += ocxl.o +obj-$(CONFIG_SCOM_DEBUGFS) += opal-xscom.o diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c index 620a986209f5..6bc24a47e9ef 100644 --- a/arch/powerpc/platforms/powernv/eeh-powernv.c +++ b/arch/powerpc/platforms/powernv/eeh-powernv.c @@ -34,6 +34,7 @@ #include "powernv.h" #include "pci.h" +#include "../../../../drivers/pci/pci.h" static int eeh_event_irq = -EINVAL; @@ -41,13 +42,10 @@ void pnv_pcibios_bus_add_device(struct pci_dev *pdev) { struct pci_dn *pdn = pci_get_pdn(pdev); - if (!pdev->is_virtfn) + if (eeh_has_flag(EEH_FORCE_DISABLED)) return; - /* - * The following operations will fail if VF's sysfs files - * aren't created or its resources aren't finalized. - */ + dev_dbg(&pdev->dev, "EEH: Setting up device\n"); eeh_add_device_early(pdn); eeh_add_device_late(pdev); eeh_sysfs_add_device(pdev); @@ -199,6 +197,25 @@ PNV_EEH_DBGFS_ENTRY(inbB, 0xE10); #endif /* CONFIG_DEBUG_FS */ +void pnv_eeh_enable_phbs(void) +{ + struct pci_controller *hose; + struct pnv_phb *phb; + + list_for_each_entry(hose, &hose_list, list_node) { + phb = hose->private_data; + /* + * If EEH is enabled, we're going to rely on that. + * Otherwise, we restore to conventional mechanism + * to clear frozen PE during PCI config access. + */ + if (eeh_enabled()) + phb->flags |= PNV_PHB_FLAG_EEH; + else + phb->flags &= ~PNV_PHB_FLAG_EEH; + } +} + /** * pnv_eeh_post_init - EEH platform dependent post initialization * @@ -213,9 +230,7 @@ int pnv_eeh_post_init(void) struct pnv_phb *phb; int ret = 0; - /* Probe devices & build address cache */ - eeh_probe_devices(); - eeh_addr_cache_build(); + eeh_show_enabled(); /* Register OPAL event notifier */ eeh_event_irq = opal_event_request(ilog2(OPAL_EVENT_PCI_ERROR)); @@ -237,19 +252,11 @@ int pnv_eeh_post_init(void) if (!eeh_enabled()) disable_irq(eeh_event_irq); + pnv_eeh_enable_phbs(); + list_for_each_entry(hose, &hose_list, list_node) { phb = hose->private_data; - /* - * If EEH is enabled, we're going to rely on that. - * Otherwise, we restore to conventional mechanism - * to clear frozen PE during PCI config access. - */ - if (eeh_enabled()) - phb->flags |= PNV_PHB_FLAG_EEH; - else - phb->flags &= ~PNV_PHB_FLAG_EEH; - /* Create debugfs entries */ #ifdef CONFIG_DEBUG_FS if (phb->has_dbgfs || !phb->dbgfs) @@ -377,6 +384,8 @@ static void *pnv_eeh_probe(struct pci_dn *pdn, void *data) if ((pdn->class_code >> 8) == PCI_CLASS_BRIDGE_ISA) return NULL; + eeh_edev_dbg(edev, "Probing device\n"); + /* Initialize eeh device */ edev->class_code = pdn->class_code; edev->mode &= 0xFFFFFF00; @@ -402,9 +411,7 @@ static void *pnv_eeh_probe(struct pci_dn *pdn, void *data) /* Create PE */ ret = eeh_add_to_parent_pe(edev); if (ret) { - pr_warn("%s: Can't add PCI dev %04x:%02x:%02x.%01x to parent PE (%x)\n", - __func__, hose->global_number, pdn->busno, - PCI_SLOT(pdn->devfn), PCI_FUNC(pdn->devfn), ret); + eeh_edev_warn(edev, "Failed to add device to PE (code %d)\n", ret); return NULL; } @@ -453,11 +460,17 @@ static void *pnv_eeh_probe(struct pci_dn *pdn, void *data) * Enable EEH explicitly so that we will do EEH check * while accessing I/O stuff */ - eeh_add_flag(EEH_ENABLED); + if (!eeh_has_flag(EEH_ENABLED)) { + enable_irq(eeh_event_irq); + pnv_eeh_enable_phbs(); + eeh_add_flag(EEH_ENABLED); + } /* Save memory bars */ eeh_save_bars(edev); + eeh_edev_dbg(edev, "EEH enabled on device\n"); + return NULL; } @@ -837,7 +850,7 @@ static int __pnv_eeh_bridge_reset(struct pci_dev *dev, int option) int aer = edev ? edev->aer_cap : 0; u32 ctrl; - pr_debug("%s: Reset PCI bus %04x:%02x with option %d\n", + pr_debug("%s: Secondary Reset PCI bus %04x:%02x with option %d\n", __func__, pci_domain_nr(dev->bus), dev->bus->number, option); @@ -895,6 +908,10 @@ static int pnv_eeh_bridge_reset(struct pci_dev *pdev, int option) if (!dn || !of_get_property(dn, "ibm,reset-by-firmware", NULL)) return __pnv_eeh_bridge_reset(pdev, option); + pr_debug("%s: FW reset PCI bus %04x:%02x with option %d\n", + __func__, pci_domain_nr(pdev->bus), + pdev->bus->number, option); + switch (option) { case EEH_RESET_FUNDAMENTAL: scope = OPAL_RESET_PCI_FUNDAMENTAL; @@ -1113,17 +1130,37 @@ static int pnv_eeh_reset(struct eeh_pe *pe, int option) return -EIO; } + if (pci_is_root_bus(bus)) + return pnv_eeh_root_reset(hose, option); + /* - * If dealing with the root bus (or the bus underneath the - * root port), we reset the bus underneath the root port. + * For hot resets try use the generic PCI error recovery reset + * functions. These correctly handles the case where the secondary + * bus is behind a hotplug slot and it will use the slot provided + * reset methods to prevent spurious hotplug events during the reset. * - * The cxl driver depends on this behaviour for bi-modal card - * switching. + * Fundemental resets need to be handled internally to EEH since the + * PCI core doesn't really have a concept of a fundemental reset, + * mainly because there's no standard way to generate one. Only a + * few devices require an FRESET so it should be fine. */ - if (pci_is_root_bus(bus) || - pci_is_root_bus(bus->parent)) - return pnv_eeh_root_reset(hose, option); + if (option != EEH_RESET_FUNDAMENTAL) { + /* + * NB: Skiboot and pnv_eeh_bridge_reset() also no-op the + * de-assert step. It's like the OPAL reset API was + * poorly designed or something... + */ + if (option == EEH_RESET_DEACTIVATE) + return 0; + rc = pci_bus_error_reset(bus->self); + if (!rc) + return 0; + } + + /* otherwise, use the generic bridge reset. this might call into FW */ + if (pci_is_root_bus(bus->parent)) + return pnv_eeh_root_reset(hose, option); return pnv_eeh_bridge_reset(bus->self, option); } diff --git a/arch/powerpc/platforms/powernv/idle.c b/arch/powerpc/platforms/powernv/idle.c index 09f49eed7fb8..78599bca66c2 100644 --- a/arch/powerpc/platforms/powernv/idle.c +++ b/arch/powerpc/platforms/powernv/idle.c @@ -675,7 +675,8 @@ static unsigned long power9_idle_stop(unsigned long psscr, bool mmu_on) sprs.ptcr = mfspr(SPRN_PTCR); sprs.rpr = mfspr(SPRN_RPR); sprs.tscr = mfspr(SPRN_TSCR); - sprs.ldbar = mfspr(SPRN_LDBAR); + if (!firmware_has_feature(FW_FEATURE_ULTRAVISOR)) + sprs.ldbar = mfspr(SPRN_LDBAR); sprs_saved = true; @@ -789,7 +790,8 @@ core_woken: mtspr(SPRN_MMCR0, sprs.mmcr0); mtspr(SPRN_MMCR1, sprs.mmcr1); mtspr(SPRN_MMCR2, sprs.mmcr2); - mtspr(SPRN_LDBAR, sprs.ldbar); + if (!firmware_has_feature(FW_FEATURE_ULTRAVISOR)) + mtspr(SPRN_LDBAR, sprs.ldbar); mtspr(SPRN_SPRG3, local_paca->sprg_vdso); diff --git a/arch/powerpc/platforms/powernv/npu-dma.c b/arch/powerpc/platforms/powernv/npu-dma.c index c16249d251f1..b95b9e3c4c98 100644 --- a/arch/powerpc/platforms/powernv/npu-dma.c +++ b/arch/powerpc/platforms/powernv/npu-dma.c @@ -89,6 +89,7 @@ struct pci_dev *pnv_pci_get_npu_dev(struct pci_dev *gpdev, int index) } EXPORT_SYMBOL(pnv_pci_get_npu_dev); +#ifdef CONFIG_IOMMU_API /* * Returns the PE assoicated with the PCI device of the given * NPU. Returns the linked pci device if pci_dev != NULL. @@ -192,106 +193,6 @@ static long pnv_npu_unset_window(struct iommu_table_group *table_group, int num) return 0; } -/* - * Enables 32 bit DMA on NPU. - */ -static void pnv_npu_dma_set_32(struct pnv_ioda_pe *npe) -{ - struct pci_dev *gpdev; - struct pnv_ioda_pe *gpe; - int64_t rc; - - /* - * Find the assoicated PCI devices and get the dma window - * information from there. - */ - if (!npe->pdev || !(npe->flags & PNV_IODA_PE_DEV)) - return; - - gpe = get_gpu_pci_dev_and_pe(npe, &gpdev); - if (!gpe) - return; - - rc = pnv_npu_set_window(&npe->table_group, 0, - gpe->table_group.tables[0]); - - /* - * NVLink devices use the same TCE table configuration as - * their parent device so drivers shouldn't be doing DMA - * operations directly on these devices. - */ - set_dma_ops(&npe->pdev->dev, &dma_dummy_ops); -} - -/* - * Enables bypass mode on the NPU. The NPU only supports one - * window per link, so bypass needs to be explicitly enabled or - * disabled. Unlike for a PHB3 bypass and non-bypass modes can't be - * active at the same time. - */ -static int pnv_npu_dma_set_bypass(struct pnv_ioda_pe *npe) -{ - struct pnv_phb *phb = npe->phb; - int64_t rc = 0; - phys_addr_t top = memblock_end_of_DRAM(); - - if (phb->type != PNV_PHB_NPU_NVLINK || !npe->pdev) - return -EINVAL; - - rc = pnv_npu_unset_window(&npe->table_group, 0); - if (rc != OPAL_SUCCESS) - return rc; - - /* Enable the bypass window */ - - top = roundup_pow_of_two(top); - dev_info(&npe->pdev->dev, "Enabling bypass for PE %x\n", - npe->pe_number); - rc = opal_pci_map_pe_dma_window_real(phb->opal_id, - npe->pe_number, npe->pe_number, - 0 /* bypass base */, top); - - if (rc == OPAL_SUCCESS) - pnv_pci_ioda2_tce_invalidate_entire(phb, false); - - return rc; -} - -void pnv_npu_try_dma_set_bypass(struct pci_dev *gpdev, bool bypass) -{ - int i; - struct pnv_phb *phb; - struct pci_dn *pdn; - struct pnv_ioda_pe *npe; - struct pci_dev *npdev; - - for (i = 0; ; ++i) { - npdev = pnv_pci_get_npu_dev(gpdev, i); - - if (!npdev) - break; - - pdn = pci_get_pdn(npdev); - if (WARN_ON(!pdn || pdn->pe_number == IODA_INVALID_PE)) - return; - - phb = pci_bus_to_host(npdev->bus)->private_data; - - /* We only do bypass if it's enabled on the linked device */ - npe = &phb->ioda.pe_array[pdn->pe_number]; - - if (bypass) { - dev_info(&npdev->dev, - "Using 64-bit DMA iommu bypass\n"); - pnv_npu_dma_set_bypass(npe); - } else { - dev_info(&npdev->dev, "Using 32-bit DMA via iommu\n"); - pnv_npu_dma_set_32(npe); - } - } -} - -#ifdef CONFIG_IOMMU_API /* Switch ownership from platform code to external user (e.g. VFIO) */ static void pnv_npu_take_ownership(struct iommu_table_group *table_group) { diff --git a/arch/powerpc/platforms/powernv/opal-call.c b/arch/powerpc/platforms/powernv/opal-call.c index 29ca523c1c79..a2aa5e433ac8 100644 --- a/arch/powerpc/platforms/powernv/opal-call.c +++ b/arch/powerpc/platforms/powernv/opal-call.c @@ -257,7 +257,7 @@ OPAL_CALL(opal_xive_set_queue_info, OPAL_XIVE_SET_QUEUE_INFO); OPAL_CALL(opal_xive_donate_page, OPAL_XIVE_DONATE_PAGE); OPAL_CALL(opal_xive_alloc_vp_block, OPAL_XIVE_ALLOCATE_VP_BLOCK); OPAL_CALL(opal_xive_free_vp_block, OPAL_XIVE_FREE_VP_BLOCK); -OPAL_CALL(opal_xive_allocate_irq, OPAL_XIVE_ALLOCATE_IRQ); +OPAL_CALL(opal_xive_allocate_irq_raw, OPAL_XIVE_ALLOCATE_IRQ); OPAL_CALL(opal_xive_free_irq, OPAL_XIVE_FREE_IRQ); OPAL_CALL(opal_xive_get_vp_info, OPAL_XIVE_GET_VP_INFO); OPAL_CALL(opal_xive_set_vp_info, OPAL_XIVE_SET_VP_INFO); @@ -287,3 +287,6 @@ OPAL_CALL(opal_pci_set_pbcq_tunnel_bar, OPAL_PCI_SET_PBCQ_TUNNEL_BAR); OPAL_CALL(opal_sensor_read_u64, OPAL_SENSOR_READ_U64); OPAL_CALL(opal_sensor_group_enable, OPAL_SENSOR_GROUP_ENABLE); OPAL_CALL(opal_nx_coproc_init, OPAL_NX_COPROC_INIT); +OPAL_CALL(opal_mpipl_update, OPAL_MPIPL_UPDATE); +OPAL_CALL(opal_mpipl_register_tag, OPAL_MPIPL_REGISTER_TAG); +OPAL_CALL(opal_mpipl_query_tag, OPAL_MPIPL_QUERY_TAG); diff --git a/arch/powerpc/platforms/powernv/opal-core.c b/arch/powerpc/platforms/powernv/opal-core.c new file mode 100644 index 000000000000..ed895d82c048 --- /dev/null +++ b/arch/powerpc/platforms/powernv/opal-core.c @@ -0,0 +1,636 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Interface for exporting the OPAL ELF core. + * Heavily inspired from fs/proc/vmcore.c + * + * Copyright 2019, Hari Bathini, IBM Corporation. + */ + +#define pr_fmt(fmt) "opal core: " fmt + +#include <linux/memblock.h> +#include <linux/uaccess.h> +#include <linux/proc_fs.h> +#include <linux/elf.h> +#include <linux/elfcore.h> +#include <linux/kobject.h> +#include <linux/sysfs.h> +#include <linux/slab.h> +#include <linux/crash_core.h> +#include <linux/of.h> + +#include <asm/page.h> +#include <asm/opal.h> +#include <asm/fadump-internal.h> + +#include "opal-fadump.h" + +#define MAX_PT_LOAD_CNT 8 + +/* NT_AUXV note related info */ +#define AUXV_CNT 1 +#define AUXV_DESC_SZ (((2 * AUXV_CNT) + 1) * sizeof(Elf64_Off)) + +struct opalcore_config { + u32 num_cpus; + /* PIR value of crashing CPU */ + u32 crashing_cpu; + + /* CPU state data info from F/W */ + u64 cpu_state_destination_vaddr; + u64 cpu_state_data_size; + u64 cpu_state_entry_size; + + /* OPAL memory to be exported as PT_LOAD segments */ + u64 ptload_addr[MAX_PT_LOAD_CNT]; + u64 ptload_size[MAX_PT_LOAD_CNT]; + u64 ptload_cnt; + + /* Pointer to the first PT_LOAD in the ELF core file */ + Elf64_Phdr *ptload_phdr; + + /* Total size of opalcore file. */ + size_t opalcore_size; + + /* Buffer for all the ELF core headers and the PT_NOTE */ + size_t opalcorebuf_sz; + char *opalcorebuf; + + /* NT_AUXV buffer */ + char auxv_buf[AUXV_DESC_SZ]; +}; + +struct opalcore { + struct list_head list; + u64 paddr; + size_t size; + loff_t offset; +}; + +static LIST_HEAD(opalcore_list); +static struct opalcore_config *oc_conf; +static const struct opal_mpipl_fadump *opalc_metadata; +static const struct opal_mpipl_fadump *opalc_cpu_metadata; + +/* + * Set crashing CPU's signal to SIGUSR1. if the kernel is triggered + * by kernel, SIGTERM otherwise. + */ +bool kernel_initiated; + +static struct opalcore * __init get_new_element(void) +{ + return kzalloc(sizeof(struct opalcore), GFP_KERNEL); +} + +static inline int is_opalcore_usable(void) +{ + return (oc_conf && oc_conf->opalcorebuf != NULL) ? 1 : 0; +} + +static Elf64_Word *append_elf64_note(Elf64_Word *buf, char *name, + u32 type, void *data, + size_t data_len) +{ + Elf64_Nhdr *note = (Elf64_Nhdr *)buf; + Elf64_Word namesz = strlen(name) + 1; + + note->n_namesz = cpu_to_be32(namesz); + note->n_descsz = cpu_to_be32(data_len); + note->n_type = cpu_to_be32(type); + buf += DIV_ROUND_UP(sizeof(*note), sizeof(Elf64_Word)); + memcpy(buf, name, namesz); + buf += DIV_ROUND_UP(namesz, sizeof(Elf64_Word)); + memcpy(buf, data, data_len); + buf += DIV_ROUND_UP(data_len, sizeof(Elf64_Word)); + + return buf; +} + +static void fill_prstatus(struct elf_prstatus *prstatus, int pir, + struct pt_regs *regs) +{ + memset(prstatus, 0, sizeof(struct elf_prstatus)); + elf_core_copy_kernel_regs(&(prstatus->pr_reg), regs); + + /* + * Overload PID with PIR value. + * As a PIR value could also be '0', add an offset of '100' + * to every PIR to avoid misinterpretations in GDB. + */ + prstatus->pr_pid = cpu_to_be32(100 + pir); + prstatus->pr_ppid = cpu_to_be32(1); + + /* + * Indicate SIGUSR1 for crash initiated from kernel. + * SIGTERM otherwise. + */ + if (pir == oc_conf->crashing_cpu) { + short sig; + + sig = kernel_initiated ? SIGUSR1 : SIGTERM; + prstatus->pr_cursig = cpu_to_be16(sig); + } +} + +static Elf64_Word *auxv_to_elf64_notes(Elf64_Word *buf, + u64 opal_boot_entry) +{ + Elf64_Off *bufp = (Elf64_Off *)oc_conf->auxv_buf; + int idx = 0; + + memset(bufp, 0, AUXV_DESC_SZ); + + /* Entry point of OPAL */ + bufp[idx++] = cpu_to_be64(AT_ENTRY); + bufp[idx++] = cpu_to_be64(opal_boot_entry); + + /* end of vector */ + bufp[idx++] = cpu_to_be64(AT_NULL); + + buf = append_elf64_note(buf, CRASH_CORE_NOTE_NAME, NT_AUXV, + oc_conf->auxv_buf, AUXV_DESC_SZ); + return buf; +} + +/* + * Read from the ELF header and then the crash dump. + * Returns number of bytes read on success, -errno on failure. + */ +static ssize_t read_opalcore(struct file *file, struct kobject *kobj, + struct bin_attribute *bin_attr, char *to, + loff_t pos, size_t count) +{ + struct opalcore *m; + ssize_t tsz, avail; + loff_t tpos = pos; + + if (pos >= oc_conf->opalcore_size) + return 0; + + /* Adjust count if it goes beyond opalcore size */ + avail = oc_conf->opalcore_size - pos; + if (count > avail) + count = avail; + + if (count == 0) + return 0; + + /* Read ELF core header and/or PT_NOTE segment */ + if (tpos < oc_conf->opalcorebuf_sz) { + tsz = min_t(size_t, oc_conf->opalcorebuf_sz - tpos, count); + memcpy(to, oc_conf->opalcorebuf + tpos, tsz); + to += tsz; + tpos += tsz; + count -= tsz; + } + + list_for_each_entry(m, &opalcore_list, list) { + /* nothing more to read here */ + if (count == 0) + break; + + if (tpos < m->offset + m->size) { + void *addr; + + tsz = min_t(size_t, m->offset + m->size - tpos, count); + addr = (void *)(m->paddr + tpos - m->offset); + memcpy(to, __va(addr), tsz); + to += tsz; + tpos += tsz; + count -= tsz; + } + } + + return (tpos - pos); +} + +static struct bin_attribute opal_core_attr = { + .attr = {.name = "core", .mode = 0400}, + .read = read_opalcore +}; + +/* + * Read CPU state dump data and convert it into ELF notes. + * + * Each register entry is of 16 bytes, A numerical identifier along with + * a GPR/SPR flag in the first 8 bytes and the register value in the next + * 8 bytes. For more details refer to F/W documentation. + */ +static Elf64_Word * __init opalcore_append_cpu_notes(Elf64_Word *buf) +{ + u32 thread_pir, size_per_thread, regs_offset, regs_cnt, reg_esize; + struct hdat_fadump_thread_hdr *thdr; + struct elf_prstatus prstatus; + Elf64_Word *first_cpu_note; + struct pt_regs regs; + char *bufp; + int i; + + size_per_thread = oc_conf->cpu_state_entry_size; + bufp = __va(oc_conf->cpu_state_destination_vaddr); + + /* + * Offset for register entries, entry size and registers count is + * duplicated in every thread header in keeping with HDAT format. + * Use these values from the first thread header. + */ + thdr = (struct hdat_fadump_thread_hdr *)bufp; + regs_offset = (offsetof(struct hdat_fadump_thread_hdr, offset) + + be32_to_cpu(thdr->offset)); + reg_esize = be32_to_cpu(thdr->esize); + regs_cnt = be32_to_cpu(thdr->ecnt); + + pr_debug("--------CPU State Data------------\n"); + pr_debug("NumCpus : %u\n", oc_conf->num_cpus); + pr_debug("\tOffset: %u, Entry size: %u, Cnt: %u\n", + regs_offset, reg_esize, regs_cnt); + + /* + * Skip past the first CPU note. Fill this note with the + * crashing CPU's prstatus. + */ + first_cpu_note = buf; + buf = append_elf64_note(buf, CRASH_CORE_NOTE_NAME, NT_PRSTATUS, + &prstatus, sizeof(prstatus)); + + for (i = 0; i < oc_conf->num_cpus; i++, bufp += size_per_thread) { + thdr = (struct hdat_fadump_thread_hdr *)bufp; + thread_pir = be32_to_cpu(thdr->pir); + + pr_debug("[%04d] PIR: 0x%x, core state: 0x%02x\n", + i, thread_pir, thdr->core_state); + + /* + * Register state data of MAX cores is provided by firmware, + * but some of this cores may not be active. So, while + * processing register state data, check core state and + * skip threads that belong to inactive cores. + */ + if (thdr->core_state == HDAT_FADUMP_CORE_INACTIVE) + continue; + + opal_fadump_read_regs((bufp + regs_offset), regs_cnt, + reg_esize, false, ®s); + + pr_debug("PIR 0x%x - R1 : 0x%llx, NIP : 0x%llx\n", thread_pir, + be64_to_cpu(regs.gpr[1]), be64_to_cpu(regs.nip)); + fill_prstatus(&prstatus, thread_pir, ®s); + + if (thread_pir != oc_conf->crashing_cpu) { + buf = append_elf64_note(buf, CRASH_CORE_NOTE_NAME, + NT_PRSTATUS, &prstatus, + sizeof(prstatus)); + } else { + /* + * Add crashing CPU as the first NT_PRSTATUS note for + * GDB to process the core file appropriately. + */ + append_elf64_note(first_cpu_note, CRASH_CORE_NOTE_NAME, + NT_PRSTATUS, &prstatus, + sizeof(prstatus)); + } + } + + return buf; +} + +static int __init create_opalcore(void) +{ + u64 opal_boot_entry, opal_base_addr, paddr; + u32 hdr_size, cpu_notes_size, count; + struct device_node *dn; + struct opalcore *new; + loff_t opalcore_off; + struct page *page; + Elf64_Phdr *phdr; + Elf64_Ehdr *elf; + int i, ret; + char *bufp; + + /* Get size of header & CPU notes for OPAL core */ + hdr_size = (sizeof(Elf64_Ehdr) + + ((oc_conf->ptload_cnt + 1) * sizeof(Elf64_Phdr))); + cpu_notes_size = ((oc_conf->num_cpus * (CRASH_CORE_NOTE_HEAD_BYTES + + CRASH_CORE_NOTE_NAME_BYTES + + CRASH_CORE_NOTE_DESC_BYTES)) + + (CRASH_CORE_NOTE_HEAD_BYTES + + CRASH_CORE_NOTE_NAME_BYTES + AUXV_DESC_SZ)); + + /* Allocate buffer to setup OPAL core */ + oc_conf->opalcorebuf_sz = PAGE_ALIGN(hdr_size + cpu_notes_size); + oc_conf->opalcorebuf = alloc_pages_exact(oc_conf->opalcorebuf_sz, + GFP_KERNEL | __GFP_ZERO); + if (!oc_conf->opalcorebuf) { + pr_err("Not enough memory to setup OPAL core (size: %lu)\n", + oc_conf->opalcorebuf_sz); + oc_conf->opalcorebuf_sz = 0; + return -ENOMEM; + } + count = oc_conf->opalcorebuf_sz / PAGE_SIZE; + page = virt_to_page(oc_conf->opalcorebuf); + for (i = 0; i < count; i++) + mark_page_reserved(page + i); + + pr_debug("opalcorebuf = 0x%llx\n", (u64)oc_conf->opalcorebuf); + + /* Read OPAL related device-tree entries */ + dn = of_find_node_by_name(NULL, "ibm,opal"); + if (dn) { + ret = of_property_read_u64(dn, "opal-base-address", + &opal_base_addr); + pr_debug("opal-base-address: %llx\n", opal_base_addr); + ret |= of_property_read_u64(dn, "opal-boot-address", + &opal_boot_entry); + pr_debug("opal-boot-address: %llx\n", opal_boot_entry); + } + if (!dn || ret) + pr_warn("WARNING: Failed to read OPAL base & entry values\n"); + + /* Use count to keep track of the program headers */ + count = 0; + + bufp = oc_conf->opalcorebuf; + elf = (Elf64_Ehdr *)bufp; + bufp += sizeof(Elf64_Ehdr); + memcpy(elf->e_ident, ELFMAG, SELFMAG); + elf->e_ident[EI_CLASS] = ELF_CLASS; + elf->e_ident[EI_DATA] = ELFDATA2MSB; + elf->e_ident[EI_VERSION] = EV_CURRENT; + elf->e_ident[EI_OSABI] = ELF_OSABI; + memset(elf->e_ident+EI_PAD, 0, EI_NIDENT-EI_PAD); + elf->e_type = cpu_to_be16(ET_CORE); + elf->e_machine = cpu_to_be16(ELF_ARCH); + elf->e_version = cpu_to_be32(EV_CURRENT); + elf->e_entry = 0; + elf->e_phoff = cpu_to_be64(sizeof(Elf64_Ehdr)); + elf->e_shoff = 0; + elf->e_flags = 0; + + elf->e_ehsize = cpu_to_be16(sizeof(Elf64_Ehdr)); + elf->e_phentsize = cpu_to_be16(sizeof(Elf64_Phdr)); + elf->e_phnum = 0; + elf->e_shentsize = 0; + elf->e_shnum = 0; + elf->e_shstrndx = 0; + + phdr = (Elf64_Phdr *)bufp; + bufp += sizeof(Elf64_Phdr); + phdr->p_type = cpu_to_be32(PT_NOTE); + phdr->p_flags = 0; + phdr->p_align = 0; + phdr->p_paddr = phdr->p_vaddr = 0; + phdr->p_offset = cpu_to_be64(hdr_size); + phdr->p_filesz = phdr->p_memsz = cpu_to_be64(cpu_notes_size); + count++; + + opalcore_off = oc_conf->opalcorebuf_sz; + oc_conf->ptload_phdr = (Elf64_Phdr *)bufp; + paddr = 0; + for (i = 0; i < oc_conf->ptload_cnt; i++) { + phdr = (Elf64_Phdr *)bufp; + bufp += sizeof(Elf64_Phdr); + phdr->p_type = cpu_to_be32(PT_LOAD); + phdr->p_flags = cpu_to_be32(PF_R|PF_W|PF_X); + phdr->p_align = 0; + + new = get_new_element(); + if (!new) + return -ENOMEM; + new->paddr = oc_conf->ptload_addr[i]; + new->size = oc_conf->ptload_size[i]; + new->offset = opalcore_off; + list_add_tail(&new->list, &opalcore_list); + + phdr->p_paddr = cpu_to_be64(paddr); + phdr->p_vaddr = cpu_to_be64(opal_base_addr + paddr); + phdr->p_filesz = phdr->p_memsz = + cpu_to_be64(oc_conf->ptload_size[i]); + phdr->p_offset = cpu_to_be64(opalcore_off); + + count++; + opalcore_off += oc_conf->ptload_size[i]; + paddr += oc_conf->ptload_size[i]; + } + + elf->e_phnum = cpu_to_be16(count); + + bufp = (char *)opalcore_append_cpu_notes((Elf64_Word *)bufp); + bufp = (char *)auxv_to_elf64_notes((Elf64_Word *)bufp, opal_boot_entry); + + oc_conf->opalcore_size = opalcore_off; + return 0; +} + +static void opalcore_cleanup(void) +{ + if (oc_conf == NULL) + return; + + /* Remove OPAL core sysfs file */ + sysfs_remove_bin_file(opal_kobj, &opal_core_attr); + oc_conf->ptload_phdr = NULL; + oc_conf->ptload_cnt = 0; + + /* free the buffer used for setting up OPAL core */ + if (oc_conf->opalcorebuf) { + void *end = (void *)((u64)oc_conf->opalcorebuf + + oc_conf->opalcorebuf_sz); + + free_reserved_area(oc_conf->opalcorebuf, end, -1, NULL); + oc_conf->opalcorebuf = NULL; + oc_conf->opalcorebuf_sz = 0; + } + + kfree(oc_conf); + oc_conf = NULL; +} +__exitcall(opalcore_cleanup); + +static void __init opalcore_config_init(void) +{ + u32 idx, cpu_data_version; + struct device_node *np; + const __be32 *prop; + u64 addr = 0; + int i, ret; + + np = of_find_node_by_path("/ibm,opal/dump"); + if (np == NULL) + return; + + if (!of_device_is_compatible(np, "ibm,opal-dump")) { + pr_warn("Support missing for this f/w version!\n"); + return; + } + + /* Check if dump has been initiated on last reboot */ + prop = of_get_property(np, "mpipl-boot", NULL); + if (!prop) { + of_node_put(np); + return; + } + + /* Get OPAL metadata */ + ret = opal_mpipl_query_tag(OPAL_MPIPL_TAG_OPAL, &addr); + if ((ret != OPAL_SUCCESS) || !addr) { + pr_err("Failed to get OPAL metadata (%d)\n", ret); + goto error_out; + } + + addr = be64_to_cpu(addr); + pr_debug("OPAL metadata addr: %llx\n", addr); + opalc_metadata = __va(addr); + + /* Get OPAL CPU metadata */ + ret = opal_mpipl_query_tag(OPAL_MPIPL_TAG_CPU, &addr); + if ((ret != OPAL_SUCCESS) || !addr) { + pr_err("Failed to get OPAL CPU metadata (%d)\n", ret); + goto error_out; + } + + addr = be64_to_cpu(addr); + pr_debug("CPU metadata addr: %llx\n", addr); + opalc_cpu_metadata = __va(addr); + + /* Allocate memory for config buffer */ + oc_conf = kzalloc(sizeof(struct opalcore_config), GFP_KERNEL); + if (oc_conf == NULL) + goto error_out; + + /* Parse OPAL metadata */ + if (opalc_metadata->version != OPAL_MPIPL_VERSION) { + pr_warn("Supported OPAL metadata version: %u, found: %u!\n", + OPAL_MPIPL_VERSION, opalc_metadata->version); + pr_warn("WARNING: F/W using newer OPAL metadata format!!\n"); + } + + oc_conf->ptload_cnt = 0; + idx = be32_to_cpu(opalc_metadata->region_cnt); + if (idx > MAX_PT_LOAD_CNT) { + pr_warn("WARNING: OPAL regions count (%d) adjusted to limit (%d)", + MAX_PT_LOAD_CNT, idx); + idx = MAX_PT_LOAD_CNT; + } + for (i = 0; i < idx; i++) { + oc_conf->ptload_addr[oc_conf->ptload_cnt] = + be64_to_cpu(opalc_metadata->region[i].dest); + oc_conf->ptload_size[oc_conf->ptload_cnt++] = + be64_to_cpu(opalc_metadata->region[i].size); + } + oc_conf->ptload_cnt = i; + oc_conf->crashing_cpu = be32_to_cpu(opalc_metadata->crashing_pir); + + if (!oc_conf->ptload_cnt) { + pr_err("OPAL memory regions not found\n"); + goto error_out; + } + + /* Parse OPAL CPU metadata */ + cpu_data_version = be32_to_cpu(opalc_cpu_metadata->cpu_data_version); + if (cpu_data_version != HDAT_FADUMP_CPU_DATA_VER) { + pr_warn("Supported CPU data version: %u, found: %u!\n", + HDAT_FADUMP_CPU_DATA_VER, cpu_data_version); + pr_warn("WARNING: F/W using newer CPU state data format!!\n"); + } + + addr = be64_to_cpu(opalc_cpu_metadata->region[0].dest); + if (!addr) { + pr_err("CPU state data not found!\n"); + goto error_out; + } + oc_conf->cpu_state_destination_vaddr = (u64)__va(addr); + + oc_conf->cpu_state_data_size = + be64_to_cpu(opalc_cpu_metadata->region[0].size); + oc_conf->cpu_state_entry_size = + be32_to_cpu(opalc_cpu_metadata->cpu_data_size); + + if ((oc_conf->cpu_state_entry_size == 0) || + (oc_conf->cpu_state_entry_size > oc_conf->cpu_state_data_size)) { + pr_err("CPU state data is invalid.\n"); + goto error_out; + } + oc_conf->num_cpus = (oc_conf->cpu_state_data_size / + oc_conf->cpu_state_entry_size); + + of_node_put(np); + return; + +error_out: + pr_err("Could not export /sys/firmware/opal/core\n"); + opalcore_cleanup(); + of_node_put(np); +} + +static ssize_t fadump_release_opalcore_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + int input = -1; + + if (kstrtoint(buf, 0, &input)) + return -EINVAL; + + if (input == 1) { + if (oc_conf == NULL) { + pr_err("'/sys/firmware/opal/core' file not accessible!\n"); + return -EPERM; + } + + /* + * Take away '/sys/firmware/opal/core' and release all memory + * used for exporting this file. + */ + opalcore_cleanup(); + } else + return -EINVAL; + + return count; +} + +static struct kobj_attribute opalcore_rel_attr = __ATTR(fadump_release_opalcore, + 0200, NULL, + fadump_release_opalcore_store); + +static int __init opalcore_init(void) +{ + int rc = -1; + + opalcore_config_init(); + + if (oc_conf == NULL) + return rc; + + create_opalcore(); + + /* + * If oc_conf->opalcorebuf= is set in the 2nd kernel, + * then capture the dump. + */ + if (!(is_opalcore_usable())) { + pr_err("Failed to export /sys/firmware/opal/core\n"); + opalcore_cleanup(); + return rc; + } + + /* Set OPAL core file size */ + opal_core_attr.size = oc_conf->opalcore_size; + + /* Export OPAL core sysfs file */ + rc = sysfs_create_bin_file(opal_kobj, &opal_core_attr); + if (rc != 0) { + pr_err("Failed to export /sys/firmware/opal/core\n"); + opalcore_cleanup(); + return rc; + } + + rc = sysfs_create_file(kernel_kobj, &opalcore_rel_attr.attr); + if (rc) { + pr_warn("unable to create sysfs file fadump_release_opalcore (%d)\n", + rc); + } + + return 0; +} +fs_initcall(opalcore_init); diff --git a/arch/powerpc/platforms/powernv/opal-fadump.c b/arch/powerpc/platforms/powernv/opal-fadump.c new file mode 100644 index 000000000000..d361d37d975f --- /dev/null +++ b/arch/powerpc/platforms/powernv/opal-fadump.c @@ -0,0 +1,716 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Firmware-Assisted Dump support on POWER platform (OPAL). + * + * Copyright 2019, Hari Bathini, IBM Corporation. + */ + +#define pr_fmt(fmt) "opal fadump: " fmt + +#include <linux/string.h> +#include <linux/seq_file.h> +#include <linux/of.h> +#include <linux/of_fdt.h> +#include <linux/libfdt.h> +#include <linux/mm.h> +#include <linux/crash_dump.h> + +#include <asm/page.h> +#include <asm/opal.h> +#include <asm/fadump-internal.h> + +#include "opal-fadump.h" + + +#ifdef CONFIG_PRESERVE_FA_DUMP +/* + * When dump is active but PRESERVE_FA_DUMP is enabled on the kernel, + * ensure crash data is preserved in hope that the subsequent memory + * preserving kernel boot is going to process this crash data. + */ +void __init opal_fadump_dt_scan(struct fw_dump *fadump_conf, u64 node) +{ + const struct opal_fadump_mem_struct *opal_fdm_active; + const __be32 *prop; + unsigned long dn; + u64 addr = 0; + s64 ret; + + dn = of_get_flat_dt_subnode_by_name(node, "dump"); + if (dn == -FDT_ERR_NOTFOUND) + return; + + /* + * Check if dump has been initiated on last reboot. + */ + prop = of_get_flat_dt_prop(dn, "mpipl-boot", NULL); + if (!prop) + return; + + ret = opal_mpipl_query_tag(OPAL_MPIPL_TAG_KERNEL, &addr); + if ((ret != OPAL_SUCCESS) || !addr) { + pr_debug("Could not get Kernel metadata (%lld)\n", ret); + return; + } + + /* + * Preserve memory only if kernel memory regions are registered + * with f/w for MPIPL. + */ + addr = be64_to_cpu(addr); + pr_debug("Kernel metadata addr: %llx\n", addr); + opal_fdm_active = (void *)addr; + if (opal_fdm_active->registered_regions == 0) + return; + + ret = opal_mpipl_query_tag(OPAL_MPIPL_TAG_BOOT_MEM, &addr); + if ((ret != OPAL_SUCCESS) || !addr) { + pr_err("Failed to get boot memory tag (%lld)\n", ret); + return; + } + + /* + * Memory below this address can be used for booting a + * capture kernel or petitboot kernel. Preserve everything + * above this address for processing crashdump. + */ + fadump_conf->boot_mem_top = be64_to_cpu(addr); + pr_debug("Preserve everything above %llx\n", fadump_conf->boot_mem_top); + + pr_info("Firmware-assisted dump is active.\n"); + fadump_conf->dump_active = 1; +} + +#else /* CONFIG_PRESERVE_FA_DUMP */ +static const struct opal_fadump_mem_struct *opal_fdm_active; +static const struct opal_mpipl_fadump *opal_cpu_metadata; +static struct opal_fadump_mem_struct *opal_fdm; + +#ifdef CONFIG_OPAL_CORE +extern bool kernel_initiated; +#endif + +static int opal_fadump_unregister(struct fw_dump *fadump_conf); + +static void opal_fadump_update_config(struct fw_dump *fadump_conf, + const struct opal_fadump_mem_struct *fdm) +{ + pr_debug("Boot memory regions count: %d\n", fdm->region_cnt); + + /* + * The destination address of the first boot memory region is the + * destination address of boot memory regions. + */ + fadump_conf->boot_mem_dest_addr = fdm->rgn[0].dest; + pr_debug("Destination address of boot memory regions: %#016llx\n", + fadump_conf->boot_mem_dest_addr); + + fadump_conf->fadumphdr_addr = fdm->fadumphdr_addr; +} + +/* + * This function is called in the capture kernel to get configuration details + * from metadata setup by the first kernel. + */ +static void opal_fadump_get_config(struct fw_dump *fadump_conf, + const struct opal_fadump_mem_struct *fdm) +{ + unsigned long base, size, last_end, hole_size; + int i; + + if (!fadump_conf->dump_active) + return; + + last_end = 0; + hole_size = 0; + fadump_conf->boot_memory_size = 0; + + pr_debug("Boot memory regions:\n"); + for (i = 0; i < fdm->region_cnt; i++) { + base = fdm->rgn[i].src; + size = fdm->rgn[i].size; + pr_debug("\t[%03d] base: 0x%lx, size: 0x%lx\n", i, base, size); + + fadump_conf->boot_mem_addr[i] = base; + fadump_conf->boot_mem_sz[i] = size; + fadump_conf->boot_memory_size += size; + hole_size += (base - last_end); + + last_end = base + size; + } + + /* + * Start address of reserve dump area (permanent reservation) for + * re-registering FADump after dump capture. + */ + fadump_conf->reserve_dump_area_start = fdm->rgn[0].dest; + + /* + * Rarely, but it can so happen that system crashes before all + * boot memory regions are registered for MPIPL. In such + * cases, warn that the vmcore may not be accurate and proceed + * anyway as that is the best bet considering free pages, cache + * pages, user pages, etc are usually filtered out. + * + * Hope the memory that could not be preserved only has pages + * that are usually filtered out while saving the vmcore. + */ + if (fdm->region_cnt > fdm->registered_regions) { + pr_warn("Not all memory regions were saved!!!\n"); + pr_warn(" Unsaved memory regions:\n"); + i = fdm->registered_regions; + while (i < fdm->region_cnt) { + pr_warn("\t[%03d] base: 0x%llx, size: 0x%llx\n", + i, fdm->rgn[i].src, fdm->rgn[i].size); + i++; + } + + pr_warn("If the unsaved regions only contain pages that are filtered out (eg. free/user pages), the vmcore should still be usable.\n"); + pr_warn("WARNING: If the unsaved regions contain kernel pages, the vmcore will be corrupted.\n"); + } + + fadump_conf->boot_mem_top = (fadump_conf->boot_memory_size + hole_size); + fadump_conf->boot_mem_regs_cnt = fdm->region_cnt; + opal_fadump_update_config(fadump_conf, fdm); +} + +/* Initialize kernel metadata */ +static void opal_fadump_init_metadata(struct opal_fadump_mem_struct *fdm) +{ + fdm->version = OPAL_FADUMP_VERSION; + fdm->region_cnt = 0; + fdm->registered_regions = 0; + fdm->fadumphdr_addr = 0; +} + +static u64 opal_fadump_init_mem_struct(struct fw_dump *fadump_conf) +{ + u64 addr = fadump_conf->reserve_dump_area_start; + int i; + + opal_fdm = __va(fadump_conf->kernel_metadata); + opal_fadump_init_metadata(opal_fdm); + + /* Boot memory regions */ + for (i = 0; i < fadump_conf->boot_mem_regs_cnt; i++) { + opal_fdm->rgn[i].src = fadump_conf->boot_mem_addr[i]; + opal_fdm->rgn[i].dest = addr; + opal_fdm->rgn[i].size = fadump_conf->boot_mem_sz[i]; + + opal_fdm->region_cnt++; + addr += fadump_conf->boot_mem_sz[i]; + } + + /* + * Kernel metadata is passed to f/w and retrieved in capture kerenl. + * So, use it to save fadump header address instead of calculating it. + */ + opal_fdm->fadumphdr_addr = (opal_fdm->rgn[0].dest + + fadump_conf->boot_memory_size); + + opal_fadump_update_config(fadump_conf, opal_fdm); + + return addr; +} + +static u64 opal_fadump_get_metadata_size(void) +{ + return PAGE_ALIGN(sizeof(struct opal_fadump_mem_struct)); +} + +static int opal_fadump_setup_metadata(struct fw_dump *fadump_conf) +{ + int err = 0; + s64 ret; + + /* + * Use the last page(s) in FADump memory reservation for + * kernel metadata. + */ + fadump_conf->kernel_metadata = (fadump_conf->reserve_dump_area_start + + fadump_conf->reserve_dump_area_size - + opal_fadump_get_metadata_size()); + pr_info("Kernel metadata addr: %llx\n", fadump_conf->kernel_metadata); + + /* Initialize kernel metadata before registering the address with f/w */ + opal_fdm = __va(fadump_conf->kernel_metadata); + opal_fadump_init_metadata(opal_fdm); + + /* + * Register metadata address with f/w. Can be retrieved in + * the capture kernel. + */ + ret = opal_mpipl_register_tag(OPAL_MPIPL_TAG_KERNEL, + fadump_conf->kernel_metadata); + if (ret != OPAL_SUCCESS) { + pr_err("Failed to set kernel metadata tag!\n"); + err = -EPERM; + } + + /* + * Register boot memory top address with f/w. Should be retrieved + * by a kernel that intends to preserve crash'ed kernel's memory. + */ + ret = opal_mpipl_register_tag(OPAL_MPIPL_TAG_BOOT_MEM, + fadump_conf->boot_mem_top); + if (ret != OPAL_SUCCESS) { + pr_err("Failed to set boot memory tag!\n"); + err = -EPERM; + } + + return err; +} + +static u64 opal_fadump_get_bootmem_min(void) +{ + return OPAL_FADUMP_MIN_BOOT_MEM; +} + +static int opal_fadump_register(struct fw_dump *fadump_conf) +{ + s64 rc = OPAL_PARAMETER; + int i, err = -EIO; + + for (i = 0; i < opal_fdm->region_cnt; i++) { + rc = opal_mpipl_update(OPAL_MPIPL_ADD_RANGE, + opal_fdm->rgn[i].src, + opal_fdm->rgn[i].dest, + opal_fdm->rgn[i].size); + if (rc != OPAL_SUCCESS) + break; + + opal_fdm->registered_regions++; + } + + switch (rc) { + case OPAL_SUCCESS: + pr_info("Registration is successful!\n"); + fadump_conf->dump_registered = 1; + err = 0; + break; + case OPAL_RESOURCE: + /* If MAX regions limit in f/w is hit, warn and proceed. */ + pr_warn("%d regions could not be registered for MPIPL as MAX limit is reached!\n", + (opal_fdm->region_cnt - opal_fdm->registered_regions)); + fadump_conf->dump_registered = 1; + err = 0; + break; + case OPAL_PARAMETER: + pr_err("Failed to register. Parameter Error(%lld).\n", rc); + break; + case OPAL_HARDWARE: + pr_err("Support not available.\n"); + fadump_conf->fadump_supported = 0; + fadump_conf->fadump_enabled = 0; + break; + default: + pr_err("Failed to register. Unknown Error(%lld).\n", rc); + break; + } + + /* + * If some regions were registered before OPAL_MPIPL_ADD_RANGE + * OPAL call failed, unregister all regions. + */ + if ((err < 0) && (opal_fdm->registered_regions > 0)) + opal_fadump_unregister(fadump_conf); + + return err; +} + +static int opal_fadump_unregister(struct fw_dump *fadump_conf) +{ + s64 rc; + + rc = opal_mpipl_update(OPAL_MPIPL_REMOVE_ALL, 0, 0, 0); + if (rc) { + pr_err("Failed to un-register - unexpected Error(%lld).\n", rc); + return -EIO; + } + + opal_fdm->registered_regions = 0; + fadump_conf->dump_registered = 0; + return 0; +} + +static int opal_fadump_invalidate(struct fw_dump *fadump_conf) +{ + s64 rc; + + rc = opal_mpipl_update(OPAL_MPIPL_FREE_PRESERVED_MEMORY, 0, 0, 0); + if (rc) { + pr_err("Failed to invalidate - unexpected Error(%lld).\n", rc); + return -EIO; + } + + fadump_conf->dump_active = 0; + opal_fdm_active = NULL; + return 0; +} + +static void opal_fadump_cleanup(struct fw_dump *fadump_conf) +{ + s64 ret; + + ret = opal_mpipl_register_tag(OPAL_MPIPL_TAG_KERNEL, 0); + if (ret != OPAL_SUCCESS) + pr_warn("Could not reset (%llu) kernel metadata tag!\n", ret); +} + +/* + * Verify if CPU state data is available. If available, do a bit of sanity + * checking before processing this data. + */ +static bool __init is_opal_fadump_cpu_data_valid(struct fw_dump *fadump_conf) +{ + if (!opal_cpu_metadata) + return false; + + fadump_conf->cpu_state_data_version = + be32_to_cpu(opal_cpu_metadata->cpu_data_version); + fadump_conf->cpu_state_entry_size = + be32_to_cpu(opal_cpu_metadata->cpu_data_size); + fadump_conf->cpu_state_dest_vaddr = + (u64)__va(be64_to_cpu(opal_cpu_metadata->region[0].dest)); + fadump_conf->cpu_state_data_size = + be64_to_cpu(opal_cpu_metadata->region[0].size); + + if (fadump_conf->cpu_state_data_version != HDAT_FADUMP_CPU_DATA_VER) { + pr_warn("Supported CPU state data version: %u, found: %d!\n", + HDAT_FADUMP_CPU_DATA_VER, + fadump_conf->cpu_state_data_version); + pr_warn("WARNING: F/W using newer CPU state data format!!\n"); + } + + if ((fadump_conf->cpu_state_dest_vaddr == 0) || + (fadump_conf->cpu_state_entry_size == 0) || + (fadump_conf->cpu_state_entry_size > + fadump_conf->cpu_state_data_size)) { + pr_err("CPU state data is invalid. Ignoring!\n"); + return false; + } + + return true; +} + +/* + * Convert CPU state data saved at the time of crash into ELF notes. + * + * While the crashing CPU's register data is saved by the kernel, CPU state + * data for all CPUs is saved by f/w. In CPU state data provided by f/w, + * each register entry is of 16 bytes, a numerical identifier along with + * a GPR/SPR flag in the first 8 bytes and the register value in the next + * 8 bytes. For more details refer to F/W documentation. If this data is + * missing or in unsupported format, append crashing CPU's register data + * saved by the kernel in the PT_NOTE, to have something to work with in + * the vmcore file. + */ +static int __init +opal_fadump_build_cpu_notes(struct fw_dump *fadump_conf, + struct fadump_crash_info_header *fdh) +{ + u32 thread_pir, size_per_thread, regs_offset, regs_cnt, reg_esize; + struct hdat_fadump_thread_hdr *thdr; + bool is_cpu_data_valid = false; + u32 num_cpus = 1, *note_buf; + struct pt_regs regs; + char *bufp; + int rc, i; + + if (is_opal_fadump_cpu_data_valid(fadump_conf)) { + size_per_thread = fadump_conf->cpu_state_entry_size; + num_cpus = (fadump_conf->cpu_state_data_size / size_per_thread); + bufp = __va(fadump_conf->cpu_state_dest_vaddr); + is_cpu_data_valid = true; + } + + rc = fadump_setup_cpu_notes_buf(num_cpus); + if (rc != 0) + return rc; + + note_buf = (u32 *)fadump_conf->cpu_notes_buf_vaddr; + if (!is_cpu_data_valid) + goto out; + + /* + * Offset for register entries, entry size and registers count is + * duplicated in every thread header in keeping with HDAT format. + * Use these values from the first thread header. + */ + thdr = (struct hdat_fadump_thread_hdr *)bufp; + regs_offset = (offsetof(struct hdat_fadump_thread_hdr, offset) + + be32_to_cpu(thdr->offset)); + reg_esize = be32_to_cpu(thdr->esize); + regs_cnt = be32_to_cpu(thdr->ecnt); + + pr_debug("--------CPU State Data------------\n"); + pr_debug("NumCpus : %u\n", num_cpus); + pr_debug("\tOffset: %u, Entry size: %u, Cnt: %u\n", + regs_offset, reg_esize, regs_cnt); + + for (i = 0; i < num_cpus; i++, bufp += size_per_thread) { + thdr = (struct hdat_fadump_thread_hdr *)bufp; + + thread_pir = be32_to_cpu(thdr->pir); + pr_debug("[%04d] PIR: 0x%x, core state: 0x%02x\n", + i, thread_pir, thdr->core_state); + + /* + * If this is kernel initiated crash, crashing_cpu would be set + * appropriately and register data of the crashing CPU saved by + * crashing kernel. Add this saved register data of crashing CPU + * to elf notes and populate the pt_regs for the remaining CPUs + * from register state data provided by firmware. + */ + if (fdh->crashing_cpu == thread_pir) { + note_buf = fadump_regs_to_elf_notes(note_buf, + &fdh->regs); + pr_debug("Crashing CPU PIR: 0x%x - R1 : 0x%lx, NIP : 0x%lx\n", + fdh->crashing_cpu, fdh->regs.gpr[1], + fdh->regs.nip); + continue; + } + + /* + * Register state data of MAX cores is provided by firmware, + * but some of this cores may not be active. So, while + * processing register state data, check core state and + * skip threads that belong to inactive cores. + */ + if (thdr->core_state == HDAT_FADUMP_CORE_INACTIVE) + continue; + + opal_fadump_read_regs((bufp + regs_offset), regs_cnt, + reg_esize, true, ®s); + note_buf = fadump_regs_to_elf_notes(note_buf, ®s); + pr_debug("CPU PIR: 0x%x - R1 : 0x%lx, NIP : 0x%lx\n", + thread_pir, regs.gpr[1], regs.nip); + } + +out: + /* + * CPU state data is invalid/unsupported. Try appending crashing CPU's + * register data, if it is saved by the kernel. + */ + if (fadump_conf->cpu_notes_buf_vaddr == (u64)note_buf) { + if (fdh->crashing_cpu == FADUMP_CPU_UNKNOWN) { + fadump_free_cpu_notes_buf(); + return -ENODEV; + } + + pr_warn("WARNING: appending only crashing CPU's register data\n"); + note_buf = fadump_regs_to_elf_notes(note_buf, &(fdh->regs)); + } + + final_note(note_buf); + + pr_debug("Updating elfcore header (%llx) with cpu notes\n", + fdh->elfcorehdr_addr); + fadump_update_elfcore_header(__va(fdh->elfcorehdr_addr)); + return 0; +} + +static int __init opal_fadump_process(struct fw_dump *fadump_conf) +{ + struct fadump_crash_info_header *fdh; + int rc = -EINVAL; + + if (!opal_fdm_active || !fadump_conf->fadumphdr_addr) + return rc; + + /* Validate the fadump crash info header */ + fdh = __va(fadump_conf->fadumphdr_addr); + if (fdh->magic_number != FADUMP_CRASH_INFO_MAGIC) { + pr_err("Crash info header is not valid.\n"); + return rc; + } + +#ifdef CONFIG_OPAL_CORE + /* + * If this is a kernel initiated crash, crashing_cpu would be set + * appropriately and register data of the crashing CPU saved by + * crashing kernel. Add this saved register data of crashing CPU + * to elf notes and populate the pt_regs for the remaining CPUs + * from register state data provided by firmware. + */ + if (fdh->crashing_cpu != FADUMP_CPU_UNKNOWN) + kernel_initiated = true; +#endif + + rc = opal_fadump_build_cpu_notes(fadump_conf, fdh); + if (rc) + return rc; + + /* + * We are done validating dump info and elfcore header is now ready + * to be exported. set elfcorehdr_addr so that vmcore module will + * export the elfcore header through '/proc/vmcore'. + */ + elfcorehdr_addr = fdh->elfcorehdr_addr; + + return rc; +} + +static void opal_fadump_region_show(struct fw_dump *fadump_conf, + struct seq_file *m) +{ + const struct opal_fadump_mem_struct *fdm_ptr; + u64 dumped_bytes = 0; + int i; + + if (fadump_conf->dump_active) + fdm_ptr = opal_fdm_active; + else + fdm_ptr = opal_fdm; + + for (i = 0; i < fdm_ptr->region_cnt; i++) { + /* + * Only regions that are registered for MPIPL + * would have dump data. + */ + if ((fadump_conf->dump_active) && + (i < fdm_ptr->registered_regions)) + dumped_bytes = fdm_ptr->rgn[i].size; + + seq_printf(m, "DUMP: Src: %#016llx, Dest: %#016llx, ", + fdm_ptr->rgn[i].src, fdm_ptr->rgn[i].dest); + seq_printf(m, "Size: %#llx, Dumped: %#llx bytes\n", + fdm_ptr->rgn[i].size, dumped_bytes); + } + + /* Dump is active. Show reserved area start address. */ + if (fadump_conf->dump_active) { + seq_printf(m, "\nMemory above %#016lx is reserved for saving crash dump\n", + fadump_conf->reserve_dump_area_start); + } +} + +static void opal_fadump_trigger(struct fadump_crash_info_header *fdh, + const char *msg) +{ + int rc; + + /* + * Unlike on pSeries platform, logical CPU number is not provided + * with architected register state data. So, store the crashing + * CPU's PIR instead to plug the appropriate register data for + * crashing CPU in the vmcore file. + */ + fdh->crashing_cpu = (u32)mfspr(SPRN_PIR); + + rc = opal_cec_reboot2(OPAL_REBOOT_MPIPL, msg); + if (rc == OPAL_UNSUPPORTED) { + pr_emerg("Reboot type %d not supported.\n", + OPAL_REBOOT_MPIPL); + } else if (rc == OPAL_HARDWARE) + pr_emerg("No backend support for MPIPL!\n"); +} + +static struct fadump_ops opal_fadump_ops = { + .fadump_init_mem_struct = opal_fadump_init_mem_struct, + .fadump_get_metadata_size = opal_fadump_get_metadata_size, + .fadump_setup_metadata = opal_fadump_setup_metadata, + .fadump_get_bootmem_min = opal_fadump_get_bootmem_min, + .fadump_register = opal_fadump_register, + .fadump_unregister = opal_fadump_unregister, + .fadump_invalidate = opal_fadump_invalidate, + .fadump_cleanup = opal_fadump_cleanup, + .fadump_process = opal_fadump_process, + .fadump_region_show = opal_fadump_region_show, + .fadump_trigger = opal_fadump_trigger, +}; + +void __init opal_fadump_dt_scan(struct fw_dump *fadump_conf, u64 node) +{ + const __be32 *prop; + unsigned long dn; + u64 addr = 0; + int i, len; + s64 ret; + + /* + * Check if Firmware-Assisted Dump is supported. if yes, check + * if dump has been initiated on last reboot. + */ + dn = of_get_flat_dt_subnode_by_name(node, "dump"); + if (dn == -FDT_ERR_NOTFOUND) { + pr_debug("FADump support is missing!\n"); + return; + } + + if (!of_flat_dt_is_compatible(dn, "ibm,opal-dump")) { + pr_err("Support missing for this f/w version!\n"); + return; + } + + prop = of_get_flat_dt_prop(dn, "fw-load-area", &len); + if (prop) { + /* + * Each f/w load area is an (address,size) pair, + * 2 cells each, totalling 4 cells per range. + */ + for (i = 0; i < len / (sizeof(*prop) * 4); i++) { + u64 base, end; + + base = of_read_number(prop + (i * 4) + 0, 2); + end = base; + end += of_read_number(prop + (i * 4) + 2, 2); + if (end > OPAL_FADUMP_MIN_BOOT_MEM) { + pr_err("F/W load area: 0x%llx-0x%llx\n", + base, end); + pr_err("F/W version not supported!\n"); + return; + } + } + } + + fadump_conf->ops = &opal_fadump_ops; + fadump_conf->fadump_supported = 1; + + /* + * Firmware supports 32-bit field for size. Align it to PAGE_SIZE + * and request firmware to copy multiple kernel boot memory regions. + */ + fadump_conf->max_copy_size = _ALIGN_DOWN(U32_MAX, PAGE_SIZE); + + /* + * Check if dump has been initiated on last reboot. + */ + prop = of_get_flat_dt_prop(dn, "mpipl-boot", NULL); + if (!prop) + return; + + ret = opal_mpipl_query_tag(OPAL_MPIPL_TAG_KERNEL, &addr); + if ((ret != OPAL_SUCCESS) || !addr) { + pr_err("Failed to get Kernel metadata (%lld)\n", ret); + return; + } + + addr = be64_to_cpu(addr); + pr_debug("Kernel metadata addr: %llx\n", addr); + + opal_fdm_active = __va(addr); + if (opal_fdm_active->version != OPAL_FADUMP_VERSION) { + pr_warn("Supported kernel metadata version: %u, found: %d!\n", + OPAL_FADUMP_VERSION, opal_fdm_active->version); + pr_warn("WARNING: Kernel metadata format mismatch identified! Core file maybe corrupted..\n"); + } + + /* Kernel regions not registered with f/w for MPIPL */ + if (opal_fdm_active->registered_regions == 0) { + opal_fdm_active = NULL; + return; + } + + ret = opal_mpipl_query_tag(OPAL_MPIPL_TAG_CPU, &addr); + if (addr) { + addr = be64_to_cpu(addr); + pr_debug("CPU metadata addr: %llx\n", addr); + opal_cpu_metadata = __va(addr); + } + + pr_info("Firmware-assisted dump is active.\n"); + fadump_conf->dump_active = 1; + opal_fadump_get_config(fadump_conf, opal_fdm_active); +} +#endif /* !CONFIG_PRESERVE_FA_DUMP */ diff --git a/arch/powerpc/platforms/powernv/opal-fadump.h b/arch/powerpc/platforms/powernv/opal-fadump.h new file mode 100644 index 000000000000..f1e9ecf548c5 --- /dev/null +++ b/arch/powerpc/platforms/powernv/opal-fadump.h @@ -0,0 +1,146 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Firmware-Assisted Dump support on POWER platform (OPAL). + * + * Copyright 2019, Hari Bathini, IBM Corporation. + */ + +#ifndef _POWERNV_OPAL_FADUMP_H +#define _POWERNV_OPAL_FADUMP_H + +#include <asm/reg.h> + +/* + * With kernel & initrd loaded at 512MB (with 256MB size), enforce a minimum + * boot memory size of 768MB to ensure f/w loading kernel and initrd doesn't + * mess with crash'ed kernel's memory during MPIPL. + */ +#define OPAL_FADUMP_MIN_BOOT_MEM (0x30000000UL) + +/* + * OPAL FADump metadata structure format version + * + * OPAL FADump kernel metadata structure stores kernel metadata needed to + * register-for/process crash dump. Format version is used to keep a tab on + * the changes in the structure format. The changes, if any, to the format + * are expected to be minimal and backward compatible. + */ +#define OPAL_FADUMP_VERSION 0x1 + +/* + * OPAL FADump kernel metadata + * + * The address of this structure will be registered with f/w for retrieving + * and processing during crash dump. + */ +struct opal_fadump_mem_struct { + u8 version; + u8 reserved[3]; + u16 region_cnt; /* number of regions */ + u16 registered_regions; /* Regions registered for MPIPL */ + u64 fadumphdr_addr; + struct opal_mpipl_region rgn[FADUMP_MAX_MEM_REGS]; +} __packed; + +/* + * CPU state data + * + * CPU state data information is provided by f/w. The format for this data + * is defined in the HDAT spec. Version is used to keep a tab on the changes + * in this CPU state data format. Changes to this format are unlikely, but + * if there are any changes, please refer to latest HDAT specification. + */ +#define HDAT_FADUMP_CPU_DATA_VER 1 + +#define HDAT_FADUMP_CORE_INACTIVE (0x0F) + +/* HDAT thread header for register entries */ +struct hdat_fadump_thread_hdr { + __be32 pir; + /* 0x00 - 0x0F - The corresponding stop state of the core */ + u8 core_state; + u8 reserved[3]; + + __be32 offset; /* Offset to Register Entries array */ + __be32 ecnt; /* Number of entries */ + __be32 esize; /* Alloc size of each array entry in bytes */ + __be32 eactsz; /* Actual size of each array entry in bytes */ +} __packed; + +/* Register types populated by f/w */ +#define HDAT_FADUMP_REG_TYPE_GPR 0x01 +#define HDAT_FADUMP_REG_TYPE_SPR 0x02 + +/* ID numbers used by f/w while populating certain registers */ +#define HDAT_FADUMP_REG_ID_NIP 0x7D0 +#define HDAT_FADUMP_REG_ID_MSR 0x7D1 +#define HDAT_FADUMP_REG_ID_CCR 0x7D2 + +/* HDAT register entry. */ +struct hdat_fadump_reg_entry { + __be32 reg_type; + __be32 reg_num; + __be64 reg_val; +} __packed; + +static inline void opal_fadump_set_regval_regnum(struct pt_regs *regs, + u32 reg_type, u32 reg_num, + u64 reg_val) +{ + if (reg_type == HDAT_FADUMP_REG_TYPE_GPR) { + if (reg_num < 32) + regs->gpr[reg_num] = reg_val; + return; + } + + switch (reg_num) { + case SPRN_CTR: + regs->ctr = reg_val; + break; + case SPRN_LR: + regs->link = reg_val; + break; + case SPRN_XER: + regs->xer = reg_val; + break; + case SPRN_DAR: + regs->dar = reg_val; + break; + case SPRN_DSISR: + regs->dsisr = reg_val; + break; + case HDAT_FADUMP_REG_ID_NIP: + regs->nip = reg_val; + break; + case HDAT_FADUMP_REG_ID_MSR: + regs->msr = reg_val; + break; + case HDAT_FADUMP_REG_ID_CCR: + regs->ccr = reg_val; + break; + } +} + +static inline void opal_fadump_read_regs(char *bufp, unsigned int regs_cnt, + unsigned int reg_entry_size, + bool cpu_endian, + struct pt_regs *regs) +{ + struct hdat_fadump_reg_entry *reg_entry; + u64 val; + int i; + + memset(regs, 0, sizeof(struct pt_regs)); + + for (i = 0; i < regs_cnt; i++, bufp += reg_entry_size) { + reg_entry = (struct hdat_fadump_reg_entry *)bufp; + val = (cpu_endian ? be64_to_cpu(reg_entry->reg_val) : + reg_entry->reg_val); + opal_fadump_set_regval_regnum(regs, + be32_to_cpu(reg_entry->reg_type), + be32_to_cpu(reg_entry->reg_num), + val); + } +} + +#endif /* _POWERNV_OPAL_FADUMP_H */ diff --git a/arch/powerpc/platforms/powernv/opal-imc.c b/arch/powerpc/platforms/powernv/opal-imc.c index 186109bdd41b..e04b20625cb9 100644 --- a/arch/powerpc/platforms/powernv/opal-imc.c +++ b/arch/powerpc/platforms/powernv/opal-imc.c @@ -53,9 +53,9 @@ static void export_imc_mode_and_cmd(struct device_node *node, struct imc_pmu *pmu_ptr) { static u64 loc, *imc_mode_addr, *imc_cmd_addr; - int chip = 0, nid; char mode[16], cmd[16]; u32 cb_offset; + struct imc_mem_info *ptr = pmu_ptr->mem_info; imc_debugfs_parent = debugfs_create_dir("imc", powerpc_debugfs_root); @@ -69,20 +69,20 @@ static void export_imc_mode_and_cmd(struct device_node *node, if (of_property_read_u32(node, "cb_offset", &cb_offset)) cb_offset = IMC_CNTL_BLK_OFFSET; - for_each_node(nid) { - loc = (u64)(pmu_ptr->mem_info[chip].vbase) + cb_offset; + while (ptr->vbase != NULL) { + loc = (u64)(ptr->vbase) + cb_offset; imc_mode_addr = (u64 *)(loc + IMC_CNTL_BLK_MODE_OFFSET); - sprintf(mode, "imc_mode_%d", nid); + sprintf(mode, "imc_mode_%d", (u32)(ptr->id)); if (!imc_debugfs_create_x64(mode, 0600, imc_debugfs_parent, imc_mode_addr)) goto err; imc_cmd_addr = (u64 *)(loc + IMC_CNTL_BLK_CMD_OFFSET); - sprintf(cmd, "imc_cmd_%d", nid); + sprintf(cmd, "imc_cmd_%d", (u32)(ptr->id)); if (!imc_debugfs_create_x64(cmd, 0600, imc_debugfs_parent, imc_cmd_addr)) goto err; - chip++; + ptr++; } return; diff --git a/arch/powerpc/platforms/powernv/opal-msglog.c b/arch/powerpc/platforms/powernv/opal-msglog.c index dc51d03c6370..d26da19a611f 100644 --- a/arch/powerpc/platforms/powernv/opal-msglog.c +++ b/arch/powerpc/platforms/powernv/opal-msglog.c @@ -29,23 +29,23 @@ struct memcons { static struct memcons *opal_memcons = NULL; -ssize_t opal_msglog_copy(char *to, loff_t pos, size_t count) +ssize_t memcons_copy(struct memcons *mc, char *to, loff_t pos, size_t count) { const char *conbuf; ssize_t ret; size_t first_read = 0; uint32_t out_pos, avail; - if (!opal_memcons) + if (!mc) return -ENODEV; - out_pos = be32_to_cpu(READ_ONCE(opal_memcons->out_pos)); + out_pos = be32_to_cpu(READ_ONCE(mc->out_pos)); /* Now we've read out_pos, put a barrier in before reading the new * data it points to in conbuf. */ smp_rmb(); - conbuf = phys_to_virt(be64_to_cpu(opal_memcons->obuf_phys)); + conbuf = phys_to_virt(be64_to_cpu(mc->obuf_phys)); /* When the buffer has wrapped, read from the out_pos marker to the end * of the buffer, and then read the remaining data as in the un-wrapped @@ -53,7 +53,7 @@ ssize_t opal_msglog_copy(char *to, loff_t pos, size_t count) if (out_pos & MEMCONS_OUT_POS_WRAP) { out_pos &= MEMCONS_OUT_POS_MASK; - avail = be32_to_cpu(opal_memcons->obuf_size) - out_pos; + avail = be32_to_cpu(mc->obuf_size) - out_pos; ret = memory_read_from_buffer(to, count, &pos, conbuf + out_pos, avail); @@ -71,7 +71,7 @@ ssize_t opal_msglog_copy(char *to, loff_t pos, size_t count) } /* Sanity check. The firmware should not do this to us. */ - if (out_pos > be32_to_cpu(opal_memcons->obuf_size)) { + if (out_pos > be32_to_cpu(mc->obuf_size)) { pr_err("OPAL: memory console corruption. Aborting read.\n"); return -EINVAL; } @@ -86,6 +86,11 @@ out: return ret; } +ssize_t opal_msglog_copy(char *to, loff_t pos, size_t count) +{ + return memcons_copy(opal_memcons, to, pos, count); +} + static ssize_t opal_msglog_read(struct file *file, struct kobject *kobj, struct bin_attribute *bin_attr, char *to, loff_t pos, size_t count) @@ -98,32 +103,48 @@ static struct bin_attribute opal_msglog_attr = { .read = opal_msglog_read }; -void __init opal_msglog_init(void) +struct memcons *memcons_init(struct device_node *node, const char *mc_prop_name) { u64 mcaddr; struct memcons *mc; - if (of_property_read_u64(opal_node, "ibm,opal-memcons", &mcaddr)) { - pr_warn("OPAL: Property ibm,opal-memcons not found, no message log\n"); - return; + if (of_property_read_u64(node, mc_prop_name, &mcaddr)) { + pr_warn("%s property not found, no message log\n", + mc_prop_name); + goto out_err; } mc = phys_to_virt(mcaddr); if (!mc) { - pr_warn("OPAL: memory console address is invalid\n"); - return; + pr_warn("memory console address is invalid\n"); + goto out_err; } if (be64_to_cpu(mc->magic) != MEMCONS_MAGIC) { - pr_warn("OPAL: memory console version is invalid\n"); - return; + pr_warn("memory console version is invalid\n"); + goto out_err; } - /* Report maximum size */ - opal_msglog_attr.size = be32_to_cpu(mc->ibuf_size) + - be32_to_cpu(mc->obuf_size); + return mc; + +out_err: + return NULL; +} + +u32 memcons_get_size(struct memcons *mc) +{ + return be32_to_cpu(mc->ibuf_size) + be32_to_cpu(mc->obuf_size); +} + +void __init opal_msglog_init(void) +{ + opal_memcons = memcons_init(opal_node, "ibm,opal-memcons"); + if (!opal_memcons) { + pr_warn("OPAL: memcons failed to load from ibm,opal-memcons\n"); + return; + } - opal_memcons = mc; + opal_msglog_attr.size = memcons_get_size(opal_memcons); } void __init opal_msglog_sysfs_init(void) diff --git a/arch/powerpc/platforms/powernv/opal-prd.c b/arch/powerpc/platforms/powernv/opal-prd.c index e072bf157d62..45f4223a790f 100644 --- a/arch/powerpc/platforms/powernv/opal-prd.c +++ b/arch/powerpc/platforms/powernv/opal-prd.c @@ -342,7 +342,7 @@ static int opal_prd_msg_notifier(struct notifier_block *nb, int msg_size, item_size; unsigned long flags; - if (msg_type != OPAL_MSG_PRD) + if (msg_type != OPAL_MSG_PRD && msg_type != OPAL_MSG_PRD2) return 0; /* Calculate total size of the message and item we need to store. The @@ -393,6 +393,12 @@ static int opal_prd_probe(struct platform_device *pdev) return rc; } + rc = opal_message_notifier_register(OPAL_MSG_PRD2, &opal_prd_event_nb); + if (rc) { + pr_err("Couldn't register PRD2 event notifier\n"); + return rc; + } + rc = misc_register(&opal_prd_dev); if (rc) { pr_err("failed to register miscdev\n"); diff --git a/arch/powerpc/platforms/powernv/opal-xscom.c b/arch/powerpc/platforms/powernv/opal-xscom.c index 66430eebe869..fd510d961b8c 100644 --- a/arch/powerpc/platforms/powernv/opal-xscom.c +++ b/arch/powerpc/platforms/powernv/opal-xscom.c @@ -1,7 +1,10 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* - * PowerNV LPC bus handling. + * PowerNV SCOM bus debugfs interface * + * Copyright 2010 Benjamin Herrenschmidt, IBM Corp + * <benh@kernel.crashing.org> + * and David Gibson, IBM Corporation. * Copyright 2013 IBM Corp. */ @@ -10,62 +13,13 @@ #include <linux/bug.h> #include <linux/gfp.h> #include <linux/slab.h> +#include <linux/uaccess.h> #include <asm/machdep.h> #include <asm/firmware.h> #include <asm/opal.h> -#include <asm/scom.h> - -/* - * We could probably fit that inside the scom_map_t - * which is a void* after all but it's really too ugly - * so let's kmalloc it for now - */ -struct opal_scom_map { - uint32_t chip; - uint64_t addr; -}; - -static scom_map_t opal_scom_map(struct device_node *dev, u64 reg, u64 count) -{ - struct opal_scom_map *m; - const __be32 *gcid; - - if (!of_get_property(dev, "scom-controller", NULL)) { - pr_err("%s: device %pOF is not a SCOM controller\n", - __func__, dev); - return SCOM_MAP_INVALID; - } - gcid = of_get_property(dev, "ibm,chip-id", NULL); - if (!gcid) { - pr_err("%s: device %pOF has no ibm,chip-id\n", - __func__, dev); - return SCOM_MAP_INVALID; - } - m = kmalloc(sizeof(*m), GFP_KERNEL); - if (!m) - return NULL; - m->chip = be32_to_cpup(gcid); - m->addr = reg; - - return (scom_map_t)m; -} - -static void opal_scom_unmap(scom_map_t map) -{ - kfree(map); -} - -static int opal_xscom_err_xlate(int64_t rc) -{ - switch(rc) { - case 0: - return 0; - /* Add more translations if necessary */ - default: - return -EIO; - } -} +#include <asm/debugfs.h> +#include <asm/prom.h> static u64 opal_scom_unmangle(u64 addr) { @@ -98,39 +52,154 @@ static u64 opal_scom_unmangle(u64 addr) return addr; } -static int opal_scom_read(scom_map_t map, u64 reg, u64 *value) +static int opal_scom_read(uint32_t chip, uint64_t addr, u64 reg, u64 *value) { - struct opal_scom_map *m = map; int64_t rc; __be64 v; - reg = opal_scom_unmangle(m->addr + reg); - rc = opal_xscom_read(m->chip, reg, (__be64 *)__pa(&v)); + reg = opal_scom_unmangle(addr + reg); + rc = opal_xscom_read(chip, reg, (__be64 *)__pa(&v)); + if (rc) { + *value = 0xfffffffffffffffful; + return -EIO; + } *value = be64_to_cpu(v); - return opal_xscom_err_xlate(rc); + return 0; } -static int opal_scom_write(scom_map_t map, u64 reg, u64 value) +static int opal_scom_write(uint32_t chip, uint64_t addr, u64 reg, u64 value) { - struct opal_scom_map *m = map; int64_t rc; - reg = opal_scom_unmangle(m->addr + reg); - rc = opal_xscom_write(m->chip, reg, value); - return opal_xscom_err_xlate(rc); + reg = opal_scom_unmangle(addr + reg); + rc = opal_xscom_write(chip, reg, value); + if (rc) + return -EIO; + return 0; +} + +struct scom_debug_entry { + u32 chip; + struct debugfs_blob_wrapper path; + char name[16]; +}; + +static ssize_t scom_debug_read(struct file *filp, char __user *ubuf, + size_t count, loff_t *ppos) +{ + struct scom_debug_entry *ent = filp->private_data; + u64 __user *ubuf64 = (u64 __user *)ubuf; + loff_t off = *ppos; + ssize_t done = 0; + u64 reg, reg_base, reg_cnt, val; + int rc; + + if (off < 0 || (off & 7) || (count & 7)) + return -EINVAL; + reg_base = off >> 3; + reg_cnt = count >> 3; + + for (reg = 0; reg < reg_cnt; reg++) { + rc = opal_scom_read(ent->chip, reg_base, reg, &val); + if (!rc) + rc = put_user(val, ubuf64); + if (rc) { + if (!done) + done = rc; + break; + } + ubuf64++; + *ppos += 8; + done += 8; + } + return done; +} + +static ssize_t scom_debug_write(struct file *filp, const char __user *ubuf, + size_t count, loff_t *ppos) +{ + struct scom_debug_entry *ent = filp->private_data; + u64 __user *ubuf64 = (u64 __user *)ubuf; + loff_t off = *ppos; + ssize_t done = 0; + u64 reg, reg_base, reg_cnt, val; + int rc; + + if (off < 0 || (off & 7) || (count & 7)) + return -EINVAL; + reg_base = off >> 3; + reg_cnt = count >> 3; + + for (reg = 0; reg < reg_cnt; reg++) { + rc = get_user(val, ubuf64); + if (!rc) + rc = opal_scom_write(ent->chip, reg_base, reg, val); + if (rc) { + if (!done) + done = rc; + break; + } + ubuf64++; + done += 8; + } + return done; } -static const struct scom_controller opal_scom_controller = { - .map = opal_scom_map, - .unmap = opal_scom_unmap, - .read = opal_scom_read, - .write = opal_scom_write +static const struct file_operations scom_debug_fops = { + .read = scom_debug_read, + .write = scom_debug_write, + .open = simple_open, + .llseek = default_llseek, }; -static int opal_xscom_init(void) +static int scom_debug_init_one(struct dentry *root, struct device_node *dn, + int chip) { - if (firmware_has_feature(FW_FEATURE_OPAL)) - scom_init(&opal_scom_controller); + struct scom_debug_entry *ent; + struct dentry *dir; + + ent = kzalloc(sizeof(*ent), GFP_KERNEL); + if (!ent) + return -ENOMEM; + + ent->chip = chip; + snprintf(ent->name, 16, "%08x", chip); + ent->path.data = (void *)kasprintf(GFP_KERNEL, "%pOF", dn); + ent->path.size = strlen((char *)ent->path.data); + + dir = debugfs_create_dir(ent->name, root); + if (!dir) { + kfree(ent->path.data); + kfree(ent); + return -1; + } + + debugfs_create_blob("devspec", 0400, dir, &ent->path); + debugfs_create_file("access", 0600, dir, ent, &scom_debug_fops); + return 0; } -machine_arch_initcall(powernv, opal_xscom_init); + +static int scom_debug_init(void) +{ + struct device_node *dn; + struct dentry *root; + int chip, rc; + + if (!firmware_has_feature(FW_FEATURE_OPAL)) + return 0; + + root = debugfs_create_dir("scom", powerpc_debugfs_root); + if (!root) + return -1; + + rc = 0; + for_each_node_with_property(dn, "scom-controller") { + chip = of_get_ibm_chip_id(dn); + WARN_ON(chip == -1); + rc |= scom_debug_init_one(root, dn, chip); + } + + return rc; +} +device_initcall(scom_debug_init); diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c index aba443be7daa..38e90270280b 100644 --- a/arch/powerpc/platforms/powernv/opal.c +++ b/arch/powerpc/platforms/powernv/opal.c @@ -58,6 +58,8 @@ static DEFINE_SPINLOCK(opal_write_lock); static struct atomic_notifier_head opal_msg_notifier_head[OPAL_MSG_TYPE_MAX]; static uint32_t opal_heartbeat; static struct task_struct *kopald_tsk; +static struct opal_msg *opal_msg; +static u32 opal_msg_size __ro_after_init; void opal_configure_cores(void) { @@ -271,14 +273,9 @@ static void opal_message_do_notify(uint32_t msg_type, void *msg) static void opal_handle_message(void) { s64 ret; - /* - * TODO: pre-allocate a message buffer depending on opal-msg-size - * value in /proc/device-tree. - */ - static struct opal_msg msg; u32 type; - ret = opal_get_msg(__pa(&msg), sizeof(msg)); + ret = opal_get_msg(__pa(opal_msg), opal_msg_size); /* No opal message pending. */ if (ret == OPAL_RESOURCE) return; @@ -290,14 +287,14 @@ static void opal_handle_message(void) return; } - type = be32_to_cpu(msg.msg_type); + type = be32_to_cpu(opal_msg->msg_type); /* Sanity check */ if (type >= OPAL_MSG_TYPE_MAX) { pr_warn_once("%s: Unknown message type: %u\n", __func__, type); return; } - opal_message_do_notify(type, (void *)&msg); + opal_message_do_notify(type, (void *)opal_msg); } static irqreturn_t opal_message_notify(int irq, void *data) @@ -306,10 +303,24 @@ static irqreturn_t opal_message_notify(int irq, void *data) return IRQ_HANDLED; } -static int __init opal_message_init(void) +static int __init opal_message_init(struct device_node *opal_node) { int ret, i, irq; + ret = of_property_read_u32(opal_node, "opal-msg-size", &opal_msg_size); + if (ret) { + pr_notice("Failed to read opal-msg-size property\n"); + opal_msg_size = sizeof(struct opal_msg); + } + + opal_msg = kmalloc(opal_msg_size, GFP_KERNEL); + if (!opal_msg) { + opal_msg_size = sizeof(struct opal_msg); + /* Try to allocate fixed message size */ + opal_msg = kmalloc(opal_msg_size, GFP_KERNEL); + BUG_ON(opal_msg == NULL); + } + for (i = 0; i < OPAL_MSG_TYPE_MAX; i++) ATOMIC_INIT_NOTIFIER_HEAD(&opal_msg_notifier_head[i]); @@ -705,7 +716,10 @@ static ssize_t symbol_map_read(struct file *fp, struct kobject *kobj, bin_attr->size); } -static BIN_ATTR_RO(symbol_map, 0); +static struct bin_attribute symbol_map_attr = { + .attr = {.name = "symbol_map", .mode = 0400}, + .read = symbol_map_read +}; static void opal_export_symmap(void) { @@ -722,10 +736,10 @@ static void opal_export_symmap(void) return; /* Setup attributes */ - bin_attr_symbol_map.private = __va(be64_to_cpu(syms[0])); - bin_attr_symbol_map.size = be64_to_cpu(syms[1]); + symbol_map_attr.private = __va(be64_to_cpu(syms[0])); + symbol_map_attr.size = be64_to_cpu(syms[1]); - rc = sysfs_create_bin_file(opal_kobj, &bin_attr_symbol_map); + rc = sysfs_create_bin_file(opal_kobj, &symbol_map_attr); if (rc) pr_warn("Error %d creating OPAL symbols file\n", rc); } @@ -910,7 +924,7 @@ static int __init opal_init(void) } /* Initialise OPAL messaging system */ - opal_message_init(); + opal_message_init(opal_node); /* Initialise OPAL asynchronous completion interface */ opal_async_comp_init(); diff --git a/arch/powerpc/platforms/powernv/pci-ioda-tce.c b/arch/powerpc/platforms/powernv/pci-ioda-tce.c index e28f03e1eb5e..a0b9c0c23ed2 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda-tce.c +++ b/arch/powerpc/platforms/powernv/pci-ioda-tce.c @@ -36,7 +36,8 @@ static __be64 *pnv_alloc_tce_level(int nid, unsigned int shift) struct page *tce_mem = NULL; __be64 *addr; - tce_mem = alloc_pages_node(nid, GFP_KERNEL, shift - PAGE_SHIFT); + tce_mem = alloc_pages_node(nid, GFP_ATOMIC | __GFP_NOWARN, + shift - PAGE_SHIFT); if (!tce_mem) { pr_err("Failed to allocate a TCE memory, level shift=%d\n", shift); @@ -48,6 +49,9 @@ static __be64 *pnv_alloc_tce_level(int nid, unsigned int shift) return addr; } +static void pnv_pci_ioda2_table_do_free_pages(__be64 *addr, + unsigned long size, unsigned int levels); + static __be64 *pnv_tce(struct iommu_table *tbl, bool user, long idx, bool alloc) { __be64 *tmp = user ? tbl->it_userspace : (__be64 *) tbl->it_base; @@ -57,9 +61,9 @@ static __be64 *pnv_tce(struct iommu_table *tbl, bool user, long idx, bool alloc) while (level) { int n = (idx & mask) >> (level * shift); - unsigned long tce; + unsigned long oldtce, tce = be64_to_cpu(READ_ONCE(tmp[n])); - if (tmp[n] == 0) { + if (!tce) { __be64 *tmp2; if (!alloc) @@ -70,10 +74,15 @@ static __be64 *pnv_tce(struct iommu_table *tbl, bool user, long idx, bool alloc) if (!tmp2) return NULL; - tmp[n] = cpu_to_be64(__pa(tmp2) | - TCE_PCI_READ | TCE_PCI_WRITE); + tce = __pa(tmp2) | TCE_PCI_READ | TCE_PCI_WRITE; + oldtce = be64_to_cpu(cmpxchg(&tmp[n], 0, + cpu_to_be64(tce))); + if (oldtce) { + pnv_pci_ioda2_table_do_free_pages(tmp2, + ilog2(tbl->it_level_size) + 3, 1); + tce = oldtce; + } } - tce = be64_to_cpu(tmp[n]); tmp = __va(tce & ~(TCE_PCI_READ | TCE_PCI_WRITE)); idx &= ~mask; @@ -161,6 +170,9 @@ void pnv_tce_free(struct iommu_table *tbl, long index, long npages) if (ptce) *ptce = cpu_to_be64(0); + else + /* Skip the rest of the level */ + i |= tbl->it_level_size - 1; } } @@ -260,7 +272,6 @@ long pnv_pci_ioda2_table_alloc_pages(int nid, __u64 bus_offset, unsigned int table_shift = max_t(unsigned int, entries_shift + 3, PAGE_SHIFT); const unsigned long tce_table_size = 1UL << table_shift; - unsigned int tmplevels = levels; if (!levels || (levels > POWERNV_IOMMU_MAX_LEVELS)) return -EINVAL; @@ -268,9 +279,6 @@ long pnv_pci_ioda2_table_alloc_pages(int nid, __u64 bus_offset, if (!is_power_of_2(window_size)) return -EINVAL; - if (alloc_userspace_copy && (window_size > (1ULL << 32))) - tmplevels = 1; - /* Adjust direct table size from window_size and levels */ entries_shift = (entries_shift + levels - 1) / levels; level_shift = entries_shift + 3; @@ -281,7 +289,7 @@ long pnv_pci_ioda2_table_alloc_pages(int nid, __u64 bus_offset, /* Allocate TCE table */ addr = pnv_pci_ioda2_table_do_alloc_pages(nid, level_shift, - tmplevels, tce_table_size, &offset, &total_allocated); + 1, tce_table_size, &offset, &total_allocated); /* addr==NULL means that the first level allocation failed */ if (!addr) @@ -292,18 +300,18 @@ long pnv_pci_ioda2_table_alloc_pages(int nid, __u64 bus_offset, * we did not allocate as much as we wanted, * release partially allocated table. */ - if (tmplevels == levels && offset < tce_table_size) + if (levels == 1 && offset < tce_table_size) goto free_tces_exit; /* Allocate userspace view of the TCE table */ if (alloc_userspace_copy) { offset = 0; uas = pnv_pci_ioda2_table_do_alloc_pages(nid, level_shift, - tmplevels, tce_table_size, &offset, + 1, tce_table_size, &offset, &total_allocated_uas); if (!uas) goto free_tces_exit; - if (tmplevels == levels && (offset < tce_table_size || + if (levels == 1 && (offset < tce_table_size || total_allocated_uas != total_allocated)) goto free_uas_exit; } @@ -318,7 +326,7 @@ long pnv_pci_ioda2_table_alloc_pages(int nid, __u64 bus_offset, pr_debug("Created TCE table: ws=%08llx ts=%lx @%08llx base=%lx uas=%p levels=%d/%d\n", window_size, tce_table_size, bus_offset, tbl->it_base, - tbl->it_userspace, tmplevels, levels); + tbl->it_userspace, 1, levels); return 0; diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index d8080558d020..c28d0d9b7ee0 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -1939,26 +1939,12 @@ static int pnv_ioda1_tce_build(struct iommu_table *tbl, long index, } #ifdef CONFIG_IOMMU_API -static int pnv_ioda1_tce_xchg(struct iommu_table *tbl, long index, - unsigned long *hpa, enum dma_data_direction *direction) +/* Common for IODA1 and IODA2 */ +static int pnv_ioda_tce_xchg_no_kill(struct iommu_table *tbl, long index, + unsigned long *hpa, enum dma_data_direction *direction, + bool realmode) { - long ret = pnv_tce_xchg(tbl, index, hpa, direction, true); - - if (!ret) - pnv_pci_p7ioc_tce_invalidate(tbl, index, 1, false); - - return ret; -} - -static int pnv_ioda1_tce_xchg_rm(struct iommu_table *tbl, long index, - unsigned long *hpa, enum dma_data_direction *direction) -{ - long ret = pnv_tce_xchg(tbl, index, hpa, direction, false); - - if (!ret) - pnv_pci_p7ioc_tce_invalidate(tbl, index, 1, true); - - return ret; + return pnv_tce_xchg(tbl, index, hpa, direction, !realmode); } #endif @@ -1973,8 +1959,8 @@ static void pnv_ioda1_tce_free(struct iommu_table *tbl, long index, static struct iommu_table_ops pnv_ioda1_iommu_ops = { .set = pnv_ioda1_tce_build, #ifdef CONFIG_IOMMU_API - .exchange = pnv_ioda1_tce_xchg, - .exchange_rm = pnv_ioda1_tce_xchg_rm, + .xchg_no_kill = pnv_ioda_tce_xchg_no_kill, + .tce_kill = pnv_pci_p7ioc_tce_invalidate, .useraddrptr = pnv_tce_useraddrptr, #endif .clear = pnv_ioda1_tce_free, @@ -2103,30 +2089,6 @@ static int pnv_ioda2_tce_build(struct iommu_table *tbl, long index, return ret; } -#ifdef CONFIG_IOMMU_API -static int pnv_ioda2_tce_xchg(struct iommu_table *tbl, long index, - unsigned long *hpa, enum dma_data_direction *direction) -{ - long ret = pnv_tce_xchg(tbl, index, hpa, direction, true); - - if (!ret) - pnv_pci_ioda2_tce_invalidate(tbl, index, 1, false); - - return ret; -} - -static int pnv_ioda2_tce_xchg_rm(struct iommu_table *tbl, long index, - unsigned long *hpa, enum dma_data_direction *direction) -{ - long ret = pnv_tce_xchg(tbl, index, hpa, direction, false); - - if (!ret) - pnv_pci_ioda2_tce_invalidate(tbl, index, 1, true); - - return ret; -} -#endif - static void pnv_ioda2_tce_free(struct iommu_table *tbl, long index, long npages) { @@ -2138,8 +2100,8 @@ static void pnv_ioda2_tce_free(struct iommu_table *tbl, long index, static struct iommu_table_ops pnv_ioda2_iommu_ops = { .set = pnv_ioda2_tce_build, #ifdef CONFIG_IOMMU_API - .exchange = pnv_ioda2_tce_xchg, - .exchange_rm = pnv_ioda2_tce_xchg_rm, + .xchg_no_kill = pnv_ioda_tce_xchg_no_kill, + .tce_kill = pnv_pci_ioda2_tce_invalidate, .useraddrptr = pnv_tce_useraddrptr, #endif .clear = pnv_ioda2_tce_free, @@ -2303,7 +2265,7 @@ found: tbl->it_ops = &pnv_ioda1_iommu_ops; pe->table_group.tce32_start = tbl->it_offset << tbl->it_page_shift; pe->table_group.tce32_size = tbl->it_size << tbl->it_page_shift; - iommu_init_table(tbl, phb->hose->node); + iommu_init_table(tbl, phb->hose->node, 0, 0); if (pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL)) pnv_ioda_setup_bus_dma(pe, pe->pbus); @@ -2420,6 +2382,7 @@ static long pnv_pci_ioda2_setup_default_config(struct pnv_ioda_pe *pe) { struct iommu_table *tbl = NULL; long rc; + unsigned long res_start, res_end; /* * crashkernel= specifies the kdump kernel's maximum memory at @@ -2433,19 +2396,46 @@ static long pnv_pci_ioda2_setup_default_config(struct pnv_ioda_pe *pe) * DMA window can be larger than available memory, which will * cause errors later. */ - const u64 window_size = min((u64)pe->table_group.tce32_size, max_memory); + const u64 maxblock = 1UL << (PAGE_SHIFT + MAX_ORDER - 1); + + /* + * We create the default window as big as we can. The constraint is + * the max order of allocation possible. The TCE table is likely to + * end up being multilevel and with on-demand allocation in place, + * the initial use is not going to be huge as the default window aims + * to support crippled devices (i.e. not fully 64bit DMAble) only. + */ + /* iommu_table::it_map uses 1 bit per IOMMU page, hence 8 */ + const u64 window_size = min((maxblock * 8) << PAGE_SHIFT, max_memory); + /* Each TCE level cannot exceed maxblock so go multilevel if needed */ + unsigned long tces_order = ilog2(window_size >> PAGE_SHIFT); + unsigned long tcelevel_order = ilog2(maxblock >> 3); + unsigned int levels = tces_order / tcelevel_order; + + if (tces_order % tcelevel_order) + levels += 1; + /* + * We try to stick to default levels (which is >1 at the moment) in + * order to save memory by relying on on-demain TCE level allocation. + */ + levels = max_t(unsigned int, levels, POWERNV_IOMMU_DEFAULT_LEVELS); - rc = pnv_pci_ioda2_create_table(&pe->table_group, 0, - IOMMU_PAGE_SHIFT_4K, - window_size, - POWERNV_IOMMU_DEFAULT_LEVELS, false, &tbl); + rc = pnv_pci_ioda2_create_table(&pe->table_group, 0, PAGE_SHIFT, + window_size, levels, false, &tbl); if (rc) { pe_err(pe, "Failed to create 32-bit TCE table, err %ld", rc); return rc; } - iommu_init_table(tbl, pe->phb->hose->node); + /* We use top part of 32bit space for MMIO so exclude it from DMA */ + res_start = 0; + res_end = 0; + if (window_size > pe->phb->ioda.m32_pci_base) { + res_start = pe->phb->ioda.m32_pci_base >> tbl->it_page_shift; + res_end = min(window_size, SZ_4G) >> tbl->it_page_shift; + } + iommu_init_table(tbl, pe->phb->hose->node, res_start, res_end); rc = pnv_pci_ioda2_set_window(&pe->table_group, 0, tbl); if (rc) { diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c index 6104418c9ad5..2825d004dece 100644 --- a/arch/powerpc/platforms/powernv/pci.c +++ b/arch/powerpc/platforms/powernv/pci.c @@ -54,7 +54,8 @@ int pnv_pci_get_slot_id(struct device_node *np, uint64_t *id) break; } - if (!of_device_is_compatible(parent, "ibm,ioda2-phb")) { + if (!of_device_is_compatible(parent, "ibm,ioda2-phb") && + !of_device_is_compatible(parent, "ibm,ioda3-phb")) { of_node_put(parent); continue; } diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h index 469c24463247..f914f0b14e4e 100644 --- a/arch/powerpc/platforms/powernv/pci.h +++ b/arch/powerpc/platforms/powernv/pci.h @@ -219,7 +219,7 @@ extern struct iommu_table_group *pnv_npu_compound_attach( struct pnv_ioda_pe *pe); /* pci-ioda-tce.c */ -#define POWERNV_IOMMU_DEFAULT_LEVELS 1 +#define POWERNV_IOMMU_DEFAULT_LEVELS 2 #define POWERNV_IOMMU_MAX_LEVELS 5 extern int pnv_tce_build(struct iommu_table *tbl, long index, long npages, diff --git a/arch/powerpc/platforms/powernv/powernv.h b/arch/powerpc/platforms/powernv/powernv.h index fd4a1c5a6369..1aa51c4fa904 100644 --- a/arch/powerpc/platforms/powernv/powernv.h +++ b/arch/powerpc/platforms/powernv/powernv.h @@ -30,4 +30,9 @@ extern void opal_event_shutdown(void); bool cpu_core_split_required(void); +struct memcons; +ssize_t memcons_copy(struct memcons *mc, char *to, loff_t pos, size_t count); +u32 memcons_get_size(struct memcons *mc); +struct memcons *memcons_init(struct device_node *node, const char *mc_prop_name); + #endif /* _POWERNV_H */ diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c index a5e52f9eed3c..83498604d322 100644 --- a/arch/powerpc/platforms/powernv/setup.c +++ b/arch/powerpc/platforms/powernv/setup.c @@ -24,6 +24,7 @@ #include <linux/bug.h> #include <linux/pci.h> #include <linux/cpufreq.h> +#include <linux/memblock.h> #include <asm/machdep.h> #include <asm/firmware.h> @@ -166,6 +167,14 @@ static void __init pnv_init(void) else #endif add_preferred_console("hvc", 0, NULL); + + if (!radix_enabled()) { + int i; + + /* Allocate per cpu area to save old slb contents during MCE */ + for_each_possible_cpu(i) + paca_ptrs[i]->mce_faulty_slbs = memblock_alloc_node(mmu_slb_size, __alignof__(*paca_ptrs[i]->mce_faulty_slbs), cpu_to_node(i)); + } } static void __init pnv_init_IRQ(void) diff --git a/arch/powerpc/platforms/powernv/ultravisor.c b/arch/powerpc/platforms/powernv/ultravisor.c new file mode 100644 index 000000000000..e4a00ad06f9d --- /dev/null +++ b/arch/powerpc/platforms/powernv/ultravisor.c @@ -0,0 +1,69 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Ultravisor high level interfaces + * + * Copyright 2019, IBM Corporation. + * + */ +#include <linux/init.h> +#include <linux/printk.h> +#include <linux/of_fdt.h> +#include <linux/of.h> + +#include <asm/ultravisor.h> +#include <asm/firmware.h> +#include <asm/machdep.h> + +#include "powernv.h" + +static struct kobject *ultravisor_kobj; + +int __init early_init_dt_scan_ultravisor(unsigned long node, const char *uname, + int depth, void *data) +{ + if (!of_flat_dt_is_compatible(node, "ibm,ultravisor")) + return 0; + + powerpc_firmware_features |= FW_FEATURE_ULTRAVISOR; + pr_debug("Ultravisor detected!\n"); + return 1; +} + +static struct memcons *uv_memcons; + +static ssize_t uv_msglog_read(struct file *file, struct kobject *kobj, + struct bin_attribute *bin_attr, char *to, + loff_t pos, size_t count) +{ + return memcons_copy(uv_memcons, to, pos, count); +} + +static struct bin_attribute uv_msglog_attr = { + .attr = {.name = "msglog", .mode = 0400}, + .read = uv_msglog_read +}; + +static int __init uv_init(void) +{ + struct device_node *node; + + if (!firmware_has_feature(FW_FEATURE_ULTRAVISOR)) + return 0; + + node = of_find_compatible_node(NULL, NULL, "ibm,uv-firmware"); + if (!node) + return -ENODEV; + + uv_memcons = memcons_init(node, "memcons"); + if (!uv_memcons) + return -ENOENT; + + uv_msglog_attr.size = memcons_get_size(uv_memcons); + + ultravisor_kobj = kobject_create_and_add("ultravisor", firmware_kobj); + if (!ultravisor_kobj) + return -ENOMEM; + + return sysfs_create_bin_file(ultravisor_kobj, &uv_msglog_attr); +} +machine_subsys_initcall(powernv, uv_init); diff --git a/arch/powerpc/platforms/ps3/spu.c b/arch/powerpc/platforms/ps3/spu.c index bdaeaecdc06b..1193c294b8d0 100644 --- a/arch/powerpc/platforms/ps3/spu.c +++ b/arch/powerpc/platforms/ps3/spu.c @@ -184,10 +184,7 @@ static void spu_unmap(struct spu *spu) * setup_areas - Map the spu regions into the address space. * * The current HV requires the spu shadow regs to be mapped with the - * PTE page protection bits set as read-only (PP=3). This implementation - * uses the low level __ioremap() to bypass the page protection settings - * inforced by ioremap_prot() to get the needed PTE bits set for the - * shadow regs. + * PTE page protection bits set as read-only. */ static int __init setup_areas(struct spu *spu) @@ -195,9 +192,8 @@ static int __init setup_areas(struct spu *spu) struct table {char* name; unsigned long addr; unsigned long size;}; unsigned long shadow_flags = pgprot_val(pgprot_noncached_wc(PAGE_KERNEL_RO)); - spu_pdata(spu)->shadow = __ioremap(spu_pdata(spu)->shadow_addr, - sizeof(struct spe_shadow), - shadow_flags); + spu_pdata(spu)->shadow = ioremap_prot(spu_pdata(spu)->shadow_addr, + sizeof(struct spe_shadow), shadow_flags); if (!spu_pdata(spu)->shadow) { pr_debug("%s:%d: ioremap shadow failed\n", __func__, __LINE__); goto fail_ioremap; diff --git a/arch/powerpc/platforms/ps3/system-bus.c b/arch/powerpc/platforms/ps3/system-bus.c index 98410119c47b..3542b7bd6a46 100644 --- a/arch/powerpc/platforms/ps3/system-bus.c +++ b/arch/powerpc/platforms/ps3/system-bus.c @@ -686,20 +686,16 @@ static int ps3_dma_supported(struct device *_dev, u64 mask) return mask >= DMA_BIT_MASK(32); } -static u64 ps3_dma_get_required_mask(struct device *_dev) -{ - return DMA_BIT_MASK(32); -} - static const struct dma_map_ops ps3_sb_dma_ops = { .alloc = ps3_alloc_coherent, .free = ps3_free_coherent, .map_sg = ps3_sb_map_sg, .unmap_sg = ps3_sb_unmap_sg, .dma_supported = ps3_dma_supported, - .get_required_mask = ps3_dma_get_required_mask, .map_page = ps3_sb_map_page, .unmap_page = ps3_unmap_page, + .mmap = dma_common_mmap, + .get_sgtable = dma_common_get_sgtable, }; static const struct dma_map_ops ps3_ioc0_dma_ops = { @@ -708,9 +704,10 @@ static const struct dma_map_ops ps3_ioc0_dma_ops = { .map_sg = ps3_ioc0_map_sg, .unmap_sg = ps3_ioc0_unmap_sg, .dma_supported = ps3_dma_supported, - .get_required_mask = ps3_dma_get_required_mask, .map_page = ps3_ioc0_map_page, .unmap_page = ps3_unmap_page, + .mmap = dma_common_mmap, + .get_sgtable = dma_common_get_sgtable, }; /** diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig index f7b484f55553..9e35cddddf73 100644 --- a/arch/powerpc/platforms/pseries/Kconfig +++ b/arch/powerpc/platforms/pseries/Kconfig @@ -145,3 +145,17 @@ config PAPR_SCM tristate "Support for the PAPR Storage Class Memory interface" help Enable access to hypervisor provided storage class memory. + +config PPC_SVM + bool "Secure virtual machine (SVM) support for POWER" + depends on PPC_PSERIES + select SWIOTLB + select ARCH_HAS_MEM_ENCRYPT + select ARCH_HAS_FORCE_DMA_UNENCRYPTED + help + There are certain POWER platforms which support secure guests using + the Protected Execution Facility, with the help of an Ultravisor + executing below the hypervisor layer. This enables support for + those guests. + + If unsure, say "N". diff --git a/arch/powerpc/platforms/pseries/Makefile b/arch/powerpc/platforms/pseries/Makefile index ab3d59aeacca..a3c74a5cf20d 100644 --- a/arch/powerpc/platforms/pseries/Makefile +++ b/arch/powerpc/platforms/pseries/Makefile @@ -26,6 +26,8 @@ obj-$(CONFIG_IBMVIO) += vio.o obj-$(CONFIG_IBMEBUS) += ibmebus.o obj-$(CONFIG_PAPR_SCM) += papr_scm.o obj-$(CONFIG_PPC_SPLPAR) += vphn.o +obj-$(CONFIG_PPC_SVM) += svm.o +obj-$(CONFIG_FA_DUMP) += rtas-fadump.o ifdef CONFIG_PPC_PSERIES obj-$(CONFIG_SUSPEND) += suspend.o diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c index 9edae1863e2f..893ba3f562c4 100644 --- a/arch/powerpc/platforms/pseries/eeh_pseries.c +++ b/arch/powerpc/platforms/pseries/eeh_pseries.c @@ -42,42 +42,44 @@ static int ibm_get_config_addr_info; static int ibm_get_config_addr_info2; static int ibm_configure_pe; -#ifdef CONFIG_PCI_IOV void pseries_pcibios_bus_add_device(struct pci_dev *pdev) { struct pci_dn *pdn = pci_get_pdn(pdev); - struct pci_dn *physfn_pdn; - struct eeh_dev *edev; - if (!pdev->is_virtfn) + if (eeh_has_flag(EEH_FORCE_DISABLED)) return; - pdn->device_id = pdev->device; - pdn->vendor_id = pdev->vendor; - pdn->class_code = pdev->class; - /* - * Last allow unfreeze return code used for retrieval - * by user space in eeh-sysfs to show the last command - * completion from platform. - */ - pdn->last_allow_rc = 0; - physfn_pdn = pci_get_pdn(pdev->physfn); - pdn->pe_number = physfn_pdn->pe_num_map[pdn->vf_index]; - edev = pdn_to_eeh_dev(pdn); + dev_dbg(&pdev->dev, "EEH: Setting up device\n"); +#ifdef CONFIG_PCI_IOV + if (pdev->is_virtfn) { + struct pci_dn *physfn_pdn; - /* - * The following operations will fail if VF's sysfs files - * aren't created or its resources aren't finalized. - */ + pdn->device_id = pdev->device; + pdn->vendor_id = pdev->vendor; + pdn->class_code = pdev->class; + /* + * Last allow unfreeze return code used for retrieval + * by user space in eeh-sysfs to show the last command + * completion from platform. + */ + pdn->last_allow_rc = 0; + physfn_pdn = pci_get_pdn(pdev->physfn); + pdn->pe_number = physfn_pdn->pe_num_map[pdn->vf_index]; + } +#endif eeh_add_device_early(pdn); eeh_add_device_late(pdev); - edev->pe_config_addr = (pdn->busno << 16) | (pdn->devfn << 8); - eeh_rmv_from_parent_pe(edev); /* Remove as it is adding to bus pe */ - eeh_add_to_parent_pe(edev); /* Add as VF PE type */ - eeh_sysfs_add_device(pdev); +#ifdef CONFIG_PCI_IOV + if (pdev->is_virtfn) { + struct eeh_dev *edev = pdn_to_eeh_dev(pdn); -} + edev->pe_config_addr = (pdn->busno << 16) | (pdn->devfn << 8); + eeh_rmv_from_parent_pe(edev); /* Remove as it is adding to bus pe */ + eeh_add_to_parent_pe(edev); /* Add as VF PE type */ + } #endif + eeh_sysfs_add_device(pdev); +} /* * Buffer for reporting slot-error-detail rtas calls. Its here @@ -144,10 +146,8 @@ static int pseries_eeh_init(void) /* Set EEH probe mode */ eeh_add_flag(EEH_PROBE_MODE_DEVTREE | EEH_ENABLE_IO_FOR_LOG); -#ifdef CONFIG_PCI_IOV /* Set EEH machine dependent code */ ppc_md.pcibios_bus_add_device = pseries_pcibios_bus_add_device; -#endif return 0; } @@ -251,6 +251,8 @@ static void *pseries_eeh_probe(struct pci_dn *pdn, void *data) if ((pdn->class_code >> 8) == PCI_CLASS_BRIDGE_ISA) return NULL; + eeh_edev_dbg(edev, "Probing device\n"); + /* * Update class code and mode of eeh device. We need * correctly reflects that current device is root port @@ -280,8 +282,11 @@ static void *pseries_eeh_probe(struct pci_dn *pdn, void *data) pe.config_addr = (pdn->busno << 16) | (pdn->devfn << 8); /* Enable EEH on the device */ + eeh_edev_dbg(edev, "Enabling EEH on device\n"); ret = eeh_ops->set_option(&pe, EEH_OPT_ENABLE); - if (!ret) { + if (ret) { + eeh_edev_dbg(edev, "EEH failed to enable on device (code %d)\n", ret); + } else { /* Retrieve PE address */ edev->pe_config_addr = eeh_ops->get_pe_addr(&pe); pe.addr = edev->pe_config_addr; @@ -297,11 +302,6 @@ static void *pseries_eeh_probe(struct pci_dn *pdn, void *data) if (enable) { eeh_add_flag(EEH_ENABLED); eeh_add_to_parent_pe(edev); - - pr_debug("%s: EEH enabled on %02x:%02x.%01x PHB#%x-PE#%x\n", - __func__, pdn->busno, PCI_SLOT(pdn->devfn), - PCI_FUNC(pdn->devfn), pe.phb->global_number, - pe.addr); } else if (pdn->parent && pdn_to_eeh_dev(pdn->parent) && (pdn_to_eeh_dev(pdn->parent))->pe) { /* This device doesn't support EEH, but it may have an @@ -310,6 +310,8 @@ static void *pseries_eeh_probe(struct pci_dn *pdn, void *data) edev->pe_config_addr = pdn_to_eeh_dev(pdn->parent)->pe_config_addr; eeh_add_to_parent_pe(edev); } + eeh_edev_dbg(edev, "EEH is %s on device (code %d)\n", + (enable ? "enabled" : "unsupported"), ret); } /* Save memory bars */ diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c index 46d0d35b9ca4..8e700390f3d6 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -880,34 +880,44 @@ int dlpar_memory(struct pseries_hp_errorlog *hp_elog) switch (hp_elog->action) { case PSERIES_HP_ELOG_ACTION_ADD: - if (hp_elog->id_type == PSERIES_HP_ELOG_ID_DRC_COUNT) { + switch (hp_elog->id_type) { + case PSERIES_HP_ELOG_ID_DRC_COUNT: count = hp_elog->_drc_u.drc_count; rc = dlpar_memory_add_by_count(count); - } else if (hp_elog->id_type == PSERIES_HP_ELOG_ID_DRC_INDEX) { + break; + case PSERIES_HP_ELOG_ID_DRC_INDEX: drc_index = hp_elog->_drc_u.drc_index; rc = dlpar_memory_add_by_index(drc_index); - } else if (hp_elog->id_type == PSERIES_HP_ELOG_ID_DRC_IC) { + break; + case PSERIES_HP_ELOG_ID_DRC_IC: count = hp_elog->_drc_u.ic.count; drc_index = hp_elog->_drc_u.ic.index; rc = dlpar_memory_add_by_ic(count, drc_index); - } else { + break; + default: rc = -EINVAL; + break; } break; case PSERIES_HP_ELOG_ACTION_REMOVE: - if (hp_elog->id_type == PSERIES_HP_ELOG_ID_DRC_COUNT) { + switch (hp_elog->id_type) { + case PSERIES_HP_ELOG_ID_DRC_COUNT: count = hp_elog->_drc_u.drc_count; rc = dlpar_memory_remove_by_count(count); - } else if (hp_elog->id_type == PSERIES_HP_ELOG_ID_DRC_INDEX) { + break; + case PSERIES_HP_ELOG_ID_DRC_INDEX: drc_index = hp_elog->_drc_u.drc_index; rc = dlpar_memory_remove_by_index(drc_index); - } else if (hp_elog->id_type == PSERIES_HP_ELOG_ID_DRC_IC) { + break; + case PSERIES_HP_ELOG_ID_DRC_IC: count = hp_elog->_drc_u.ic.count; drc_index = hp_elog->_drc_u.ic.index; rc = dlpar_memory_remove_by_ic(count, drc_index); - } else { + break; + default: rc = -EINVAL; + break; } break; diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index 889dc2e44b89..6ba081dd61c9 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -36,6 +36,7 @@ #include <asm/udbg.h> #include <asm/mmzone.h> #include <asm/plpar_wrappers.h> +#include <asm/svm.h> #include "pseries.h" @@ -609,7 +610,7 @@ static void pci_dma_bus_setup_pSeries(struct pci_bus *bus) iommu_table_setparms(pci->phb, dn, tbl); tbl->it_ops = &iommu_table_pseries_ops; - iommu_init_table(tbl, pci->phb->node); + iommu_init_table(tbl, pci->phb->node, 0, 0); /* Divide the rest (1.75GB) among the children */ pci->phb->dma_window_size = 0x80000000ul; @@ -621,7 +622,8 @@ static void pci_dma_bus_setup_pSeries(struct pci_bus *bus) #ifdef CONFIG_IOMMU_API static int tce_exchange_pseries(struct iommu_table *tbl, long index, unsigned - long *tce, enum dma_data_direction *direction) + long *tce, enum dma_data_direction *direction, + bool realmode) { long rc; unsigned long ioba = (unsigned long) index << tbl->it_page_shift; @@ -649,7 +651,7 @@ static int tce_exchange_pseries(struct iommu_table *tbl, long index, unsigned struct iommu_table_ops iommu_table_lpar_multi_ops = { .set = tce_buildmulti_pSeriesLP, #ifdef CONFIG_IOMMU_API - .exchange = tce_exchange_pseries, + .xchg_no_kill = tce_exchange_pseries, #endif .clear = tce_freemulti_pSeriesLP, .get = tce_get_pSeriesLP @@ -690,7 +692,7 @@ static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus) iommu_table_setparms_lpar(ppci->phb, pdn, tbl, ppci->table_group, dma_window); tbl->it_ops = &iommu_table_lpar_multi_ops; - iommu_init_table(tbl, ppci->phb->node); + iommu_init_table(tbl, ppci->phb->node, 0, 0); iommu_register_group(ppci->table_group, pci_domain_nr(bus), 0); pr_debug(" created table: %p\n", ppci->table_group); @@ -719,7 +721,7 @@ static void pci_dma_dev_setup_pSeries(struct pci_dev *dev) tbl = PCI_DN(dn)->table_group->tables[0]; iommu_table_setparms(phb, dn, tbl); tbl->it_ops = &iommu_table_pseries_ops; - iommu_init_table(tbl, phb->node); + iommu_init_table(tbl, phb->node, 0, 0); set_iommu_table_base(&dev->dev, tbl); return; } @@ -1169,7 +1171,7 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev) iommu_table_setparms_lpar(pci->phb, pdn, tbl, pci->table_group, dma_window); tbl->it_ops = &iommu_table_lpar_multi_ops; - iommu_init_table(tbl, pci->phb->node); + iommu_init_table(tbl, pci->phb->node, 0, 0); iommu_register_group(pci->table_group, pci_domain_nr(pci->phb->bus), 0); pr_debug(" created table: %p\n", pci->table_group); @@ -1318,7 +1320,15 @@ void iommu_init_early_pSeries(void) of_reconfig_notifier_register(&iommu_reconfig_nb); register_memory_notifier(&iommu_mem_nb); - set_pci_dma_ops(&dma_iommu_ops); + /* + * Secure guest memory is inacessible to devices so regular DMA isn't + * possible. + * + * In that case keep devices' dma_map_ops as NULL so that the generic + * DMA code path will use SWIOTLB to bounce buffers for DMA. + */ + if (!is_secure_guest()) + set_pci_dma_ops(&dma_iommu_ops); } static int __init disable_multitce(char *str) diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index 09bb878c21e0..36b846f6e74e 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -1413,7 +1413,10 @@ static int pseries_lpar_resize_hpt_commit(void *data) return 0; } -/* Must be called in user context */ +/* + * Must be called in process context. The caller must hold the + * cpus_lock. + */ static int pseries_lpar_resize_hpt(unsigned long shift) { struct hpt_resize_state state = { @@ -1467,7 +1470,8 @@ static int pseries_lpar_resize_hpt(unsigned long shift) t1 = ktime_get(); - rc = stop_machine(pseries_lpar_resize_hpt_commit, &state, NULL); + rc = stop_machine_cpuslocked(pseries_lpar_resize_hpt_commit, + &state, NULL); t2 = ktime_get(); @@ -1527,16 +1531,24 @@ void __init hpte_init_pseries(void) mmu_hash_ops.flush_hash_range = pSeries_lpar_flush_hash_range; mmu_hash_ops.hpte_clear_all = pseries_hpte_clear_all; mmu_hash_ops.hugepage_invalidate = pSeries_lpar_hugepage_invalidate; - register_process_table = pseries_lpar_register_process_table; if (firmware_has_feature(FW_FEATURE_HPT_RESIZE)) mmu_hash_ops.resize_hpt = pseries_lpar_resize_hpt; + + /* + * On POWER9, we need to do a H_REGISTER_PROC_TBL hcall + * to inform the hypervisor that we wish to use the HPT. + */ + if (cpu_has_feature(CPU_FTR_ARCH_300)) + pseries_lpar_register_process_table(0, 0, 0); } void radix_init_pseries(void) { pr_info("Using radix MMU under hypervisor\n"); - register_process_table = pseries_lpar_register_process_table; + + pseries_lpar_register_process_table(__pa(process_tb), + 0, PRTB_SIZE_SHIFT - 12); } #ifdef CONFIG_PPC_SMLPAR diff --git a/arch/powerpc/platforms/pseries/mobility.c b/arch/powerpc/platforms/pseries/mobility.c index fe812bebdf5e..b571285f6c14 100644 --- a/arch/powerpc/platforms/pseries/mobility.c +++ b/arch/powerpc/platforms/pseries/mobility.c @@ -9,6 +9,7 @@ #include <linux/cpu.h> #include <linux/kernel.h> #include <linux/kobject.h> +#include <linux/sched.h> #include <linux/smp.h> #include <linux/stat.h> #include <linux/completion.h> @@ -207,7 +208,11 @@ static int update_dt_node(__be32 phandle, s32 scope) prop_data += vd; } + + cond_resched(); } + + cond_resched(); } while (rtas_rc == 1); of_node_put(dn); @@ -310,8 +315,12 @@ int pseries_devicetree_update(s32 scope) add_dt_node(phandle, drc_index); break; } + + cond_resched(); } } + + cond_resched(); } while (rc == 1); kfree(rtas_buf); diff --git a/arch/powerpc/platforms/pseries/pci.c b/arch/powerpc/platforms/pseries/pci.c index 1eae1d09980c..722830978639 100644 --- a/arch/powerpc/platforms/pseries/pci.c +++ b/arch/powerpc/platforms/pseries/pci.c @@ -229,8 +229,7 @@ void __init pSeries_final_fixup(void) pSeries_request_regions(); - eeh_probe_devices(); - eeh_addr_cache_build(); + eeh_show_enabled(); #ifdef CONFIG_PCI_IOV ppc_md.pcibios_sriov_enable = pseries_pcibios_sriov_enable; diff --git a/arch/powerpc/platforms/pseries/ras.c b/arch/powerpc/platforms/pseries/ras.c index f16fdd0f71f7..3acdcc3bb908 100644 --- a/arch/powerpc/platforms/pseries/ras.c +++ b/arch/powerpc/platforms/pseries/ras.c @@ -76,6 +76,7 @@ struct pseries_mc_errorlog { #define MC_ERROR_TYPE_UE 0x00 #define MC_ERROR_TYPE_SLB 0x01 #define MC_ERROR_TYPE_ERAT 0x02 +#define MC_ERROR_TYPE_UNKNOWN 0x03 #define MC_ERROR_TYPE_TLB 0x04 #define MC_ERROR_TYPE_D_CACHE 0x05 #define MC_ERROR_TYPE_I_CACHE 0x07 @@ -87,6 +88,9 @@ struct pseries_mc_errorlog { #define MC_ERROR_UE_LOAD_STORE 3 #define MC_ERROR_UE_PAGE_TABLE_WALK_LOAD_STORE 4 +#define UE_EFFECTIVE_ADDR_PROVIDED 0x40 +#define UE_LOGICAL_ADDR_PROVIDED 0x20 + #define MC_ERROR_SLB_PARITY 0 #define MC_ERROR_SLB_MULTIHIT 1 #define MC_ERROR_SLB_INDETERMINATE 2 @@ -113,27 +117,6 @@ static inline u8 rtas_mc_error_sub_type(const struct pseries_mc_errorlog *mlog) } } -static -inline u64 rtas_mc_get_effective_addr(const struct pseries_mc_errorlog *mlog) -{ - __be64 addr = 0; - - switch (mlog->error_type) { - case MC_ERROR_TYPE_UE: - if (mlog->sub_err_type & 0x40) - addr = mlog->effective_address; - break; - case MC_ERROR_TYPE_SLB: - case MC_ERROR_TYPE_ERAT: - case MC_ERROR_TYPE_TLB: - if (mlog->sub_err_type & 0x80) - addr = mlog->effective_address; - default: - break; - } - return be64_to_cpu(addr); -} - /* * Enable the hotplug interrupt late because processing them may touch other * devices or systems (e.g. hugepages) that have not been initialized at the @@ -511,160 +494,165 @@ int pSeries_system_reset_exception(struct pt_regs *regs) return 0; /* need to perform reset */ } -#define VAL_TO_STRING(ar, val) \ - (((val) < ARRAY_SIZE(ar)) ? ar[(val)] : "Unknown") -static void pseries_print_mce_info(struct pt_regs *regs, - struct rtas_error_log *errp) +static int mce_handle_error(struct pt_regs *regs, struct rtas_error_log *errp) { - const char *level, *sevstr; + struct mce_error_info mce_err = { 0 }; + unsigned long eaddr = 0, paddr = 0; struct pseries_errorlog *pseries_log; struct pseries_mc_errorlog *mce_log; - u8 error_type, err_sub_type; - u64 addr; - u8 initiator = rtas_error_initiator(errp); int disposition = rtas_error_disposition(errp); + int initiator = rtas_error_initiator(errp); + int severity = rtas_error_severity(errp); + u8 error_type, err_sub_type; - static const char * const initiators[] = { - [0] = "Unknown", - [1] = "CPU", - [2] = "PCI", - [3] = "ISA", - [4] = "Memory", - [5] = "Power Mgmt", - }; - static const char * const mc_err_types[] = { - [0] = "UE", - [1] = "SLB", - [2] = "ERAT", - [3] = "Unknown", - [4] = "TLB", - [5] = "D-Cache", - [6] = "Unknown", - [7] = "I-Cache", - }; - static const char * const mc_ue_types[] = { - [0] = "Indeterminate", - [1] = "Instruction fetch", - [2] = "Page table walk ifetch", - [3] = "Load/Store", - [4] = "Page table walk Load/Store", - }; - - /* SLB sub errors valid values are 0x0, 0x1, 0x2 */ - static const char * const mc_slb_types[] = { - [0] = "Parity", - [1] = "Multihit", - [2] = "Indeterminate", - }; - - /* TLB and ERAT sub errors valid values are 0x1, 0x2, 0x3 */ - static const char * const mc_soft_types[] = { - [0] = "Unknown", - [1] = "Parity", - [2] = "Multihit", - [3] = "Indeterminate", - }; - - if (!rtas_error_extended(errp)) { - pr_err("Machine check interrupt: Missing extended error log\n"); - return; - } + if (initiator == RTAS_INITIATOR_UNKNOWN) + mce_err.initiator = MCE_INITIATOR_UNKNOWN; + else if (initiator == RTAS_INITIATOR_CPU) + mce_err.initiator = MCE_INITIATOR_CPU; + else if (initiator == RTAS_INITIATOR_PCI) + mce_err.initiator = MCE_INITIATOR_PCI; + else if (initiator == RTAS_INITIATOR_ISA) + mce_err.initiator = MCE_INITIATOR_ISA; + else if (initiator == RTAS_INITIATOR_MEMORY) + mce_err.initiator = MCE_INITIATOR_MEMORY; + else if (initiator == RTAS_INITIATOR_POWERMGM) + mce_err.initiator = MCE_INITIATOR_POWERMGM; + else + mce_err.initiator = MCE_INITIATOR_UNKNOWN; + + if (severity == RTAS_SEVERITY_NO_ERROR) + mce_err.severity = MCE_SEV_NO_ERROR; + else if (severity == RTAS_SEVERITY_EVENT) + mce_err.severity = MCE_SEV_WARNING; + else if (severity == RTAS_SEVERITY_WARNING) + mce_err.severity = MCE_SEV_WARNING; + else if (severity == RTAS_SEVERITY_ERROR_SYNC) + mce_err.severity = MCE_SEV_SEVERE; + else if (severity == RTAS_SEVERITY_ERROR) + mce_err.severity = MCE_SEV_SEVERE; + else if (severity == RTAS_SEVERITY_FATAL) + mce_err.severity = MCE_SEV_FATAL; + else + mce_err.severity = MCE_SEV_FATAL; + + if (severity <= RTAS_SEVERITY_ERROR_SYNC) + mce_err.sync_error = true; + else + mce_err.sync_error = false; + + mce_err.error_type = MCE_ERROR_TYPE_UNKNOWN; + mce_err.error_class = MCE_ECLASS_UNKNOWN; + + if (!rtas_error_extended(errp)) + goto out; pseries_log = get_pseries_errorlog(errp, PSERIES_ELOG_SECT_ID_MCE); if (pseries_log == NULL) - return; + goto out; mce_log = (struct pseries_mc_errorlog *)pseries_log->data; - error_type = mce_log->error_type; err_sub_type = rtas_mc_error_sub_type(mce_log); - switch (rtas_error_severity(errp)) { - case RTAS_SEVERITY_NO_ERROR: - level = KERN_INFO; - sevstr = "Harmless"; - break; - case RTAS_SEVERITY_WARNING: - level = KERN_WARNING; - sevstr = ""; - break; - case RTAS_SEVERITY_ERROR: - case RTAS_SEVERITY_ERROR_SYNC: - level = KERN_ERR; - sevstr = "Severe"; - break; - case RTAS_SEVERITY_FATAL: - default: - level = KERN_ERR; - sevstr = "Fatal"; - break; - } + switch (mce_log->error_type) { + case MC_ERROR_TYPE_UE: + mce_err.error_type = MCE_ERROR_TYPE_UE; + switch (err_sub_type) { + case MC_ERROR_UE_IFETCH: + mce_err.u.ue_error_type = MCE_UE_ERROR_IFETCH; + break; + case MC_ERROR_UE_PAGE_TABLE_WALK_IFETCH: + mce_err.u.ue_error_type = MCE_UE_ERROR_PAGE_TABLE_WALK_IFETCH; + break; + case MC_ERROR_UE_LOAD_STORE: + mce_err.u.ue_error_type = MCE_UE_ERROR_LOAD_STORE; + break; + case MC_ERROR_UE_PAGE_TABLE_WALK_LOAD_STORE: + mce_err.u.ue_error_type = MCE_UE_ERROR_PAGE_TABLE_WALK_LOAD_STORE; + break; + case MC_ERROR_UE_INDETERMINATE: + default: + mce_err.u.ue_error_type = MCE_UE_ERROR_INDETERMINATE; + break; + } + if (mce_log->sub_err_type & UE_EFFECTIVE_ADDR_PROVIDED) + eaddr = be64_to_cpu(mce_log->effective_address); -#ifdef CONFIG_PPC_BOOK3S_64 - /* Display faulty slb contents for SLB errors. */ - if (error_type == MC_ERROR_TYPE_SLB) - slb_dump_contents(local_paca->mce_faulty_slbs); -#endif + if (mce_log->sub_err_type & UE_LOGICAL_ADDR_PROVIDED) { + paddr = be64_to_cpu(mce_log->logical_address); + } else if (mce_log->sub_err_type & UE_EFFECTIVE_ADDR_PROVIDED) { + unsigned long pfn; - printk("%s%s Machine check interrupt [%s]\n", level, sevstr, - disposition == RTAS_DISP_FULLY_RECOVERED ? - "Recovered" : "Not recovered"); - if (user_mode(regs)) { - printk("%s NIP: [%016lx] PID: %d Comm: %s\n", level, - regs->nip, current->pid, current->comm); - } else { - printk("%s NIP [%016lx]: %pS\n", level, regs->nip, - (void *)regs->nip); - } - printk("%s Initiator: %s\n", level, - VAL_TO_STRING(initiators, initiator)); + pfn = addr_to_pfn(regs, eaddr); + if (pfn != ULONG_MAX) + paddr = pfn << PAGE_SHIFT; + } - switch (error_type) { - case MC_ERROR_TYPE_UE: - printk("%s Error type: %s [%s]\n", level, - VAL_TO_STRING(mc_err_types, error_type), - VAL_TO_STRING(mc_ue_types, err_sub_type)); break; case MC_ERROR_TYPE_SLB: - printk("%s Error type: %s [%s]\n", level, - VAL_TO_STRING(mc_err_types, error_type), - VAL_TO_STRING(mc_slb_types, err_sub_type)); + mce_err.error_type = MCE_ERROR_TYPE_SLB; + switch (err_sub_type) { + case MC_ERROR_SLB_PARITY: + mce_err.u.slb_error_type = MCE_SLB_ERROR_PARITY; + break; + case MC_ERROR_SLB_MULTIHIT: + mce_err.u.slb_error_type = MCE_SLB_ERROR_MULTIHIT; + break; + case MC_ERROR_SLB_INDETERMINATE: + default: + mce_err.u.slb_error_type = MCE_SLB_ERROR_INDETERMINATE; + break; + } + if (mce_log->sub_err_type & 0x80) + eaddr = be64_to_cpu(mce_log->effective_address); break; case MC_ERROR_TYPE_ERAT: + mce_err.error_type = MCE_ERROR_TYPE_ERAT; + switch (err_sub_type) { + case MC_ERROR_ERAT_PARITY: + mce_err.u.erat_error_type = MCE_ERAT_ERROR_PARITY; + break; + case MC_ERROR_ERAT_MULTIHIT: + mce_err.u.erat_error_type = MCE_ERAT_ERROR_MULTIHIT; + break; + case MC_ERROR_ERAT_INDETERMINATE: + default: + mce_err.u.erat_error_type = MCE_ERAT_ERROR_INDETERMINATE; + break; + } + if (mce_log->sub_err_type & 0x80) + eaddr = be64_to_cpu(mce_log->effective_address); + break; case MC_ERROR_TYPE_TLB: - printk("%s Error type: %s [%s]\n", level, - VAL_TO_STRING(mc_err_types, error_type), - VAL_TO_STRING(mc_soft_types, err_sub_type)); + mce_err.error_type = MCE_ERROR_TYPE_TLB; + switch (err_sub_type) { + case MC_ERROR_TLB_PARITY: + mce_err.u.tlb_error_type = MCE_TLB_ERROR_PARITY; + break; + case MC_ERROR_TLB_MULTIHIT: + mce_err.u.tlb_error_type = MCE_TLB_ERROR_MULTIHIT; + break; + case MC_ERROR_TLB_INDETERMINATE: + default: + mce_err.u.tlb_error_type = MCE_TLB_ERROR_INDETERMINATE; + break; + } + if (mce_log->sub_err_type & 0x80) + eaddr = be64_to_cpu(mce_log->effective_address); + break; + case MC_ERROR_TYPE_D_CACHE: + mce_err.error_type = MCE_ERROR_TYPE_DCACHE; break; + case MC_ERROR_TYPE_I_CACHE: + mce_err.error_type = MCE_ERROR_TYPE_DCACHE; + break; + case MC_ERROR_TYPE_UNKNOWN: default: - printk("%s Error type: %s\n", level, - VAL_TO_STRING(mc_err_types, error_type)); + mce_err.error_type = MCE_ERROR_TYPE_UNKNOWN; break; } - addr = rtas_mc_get_effective_addr(mce_log); - if (addr) - printk("%s Effective address: %016llx\n", level, addr); -} - -static int mce_handle_error(struct rtas_error_log *errp) -{ - struct pseries_errorlog *pseries_log; - struct pseries_mc_errorlog *mce_log; - int disposition = rtas_error_disposition(errp); - u8 error_type; - - if (!rtas_error_extended(errp)) - goto out; - - pseries_log = get_pseries_errorlog(errp, PSERIES_ELOG_SECT_ID_MCE); - if (pseries_log == NULL) - goto out; - - mce_log = (struct pseries_mc_errorlog *)pseries_log->data; - error_type = mce_log->error_type; - #ifdef CONFIG_PPC_BOOK3S_64 if (disposition == RTAS_DISP_NOT_RECOVERED) { switch (error_type) { @@ -682,98 +670,24 @@ static int mce_handle_error(struct rtas_error_log *errp) slb_save_contents(local_paca->mce_faulty_slbs); flush_and_reload_slb(); disposition = RTAS_DISP_FULLY_RECOVERED; - rtas_set_disposition_recovered(errp); break; default: break; } + } else if (disposition == RTAS_DISP_LIMITED_RECOVERY) { + /* Platform corrected itself but could be degraded */ + printk(KERN_ERR "MCE: limited recovery, system may " + "be degraded\n"); + disposition = RTAS_DISP_FULLY_RECOVERED; } #endif out: - return disposition; -} - -#ifdef CONFIG_MEMORY_FAILURE - -static DEFINE_PER_CPU(int, rtas_ue_count); -static DEFINE_PER_CPU(unsigned long, rtas_ue_paddr[MAX_MC_EVT]); + save_mce_event(regs, disposition == RTAS_DISP_FULLY_RECOVERED, + &mce_err, regs->nip, eaddr, paddr); -#define UE_EFFECTIVE_ADDR_PROVIDED 0x40 -#define UE_LOGICAL_ADDR_PROVIDED 0x20 - - -static void pseries_hwpoison_work_fn(struct work_struct *work) -{ - unsigned long paddr; - int index; - - while (__this_cpu_read(rtas_ue_count) > 0) { - index = __this_cpu_read(rtas_ue_count) - 1; - paddr = __this_cpu_read(rtas_ue_paddr[index]); - memory_failure(paddr >> PAGE_SHIFT, 0); - __this_cpu_dec(rtas_ue_count); - } -} - -static DECLARE_WORK(hwpoison_work, pseries_hwpoison_work_fn); - -static void queue_ue_paddr(unsigned long paddr) -{ - int index; - - index = __this_cpu_inc_return(rtas_ue_count) - 1; - if (index >= MAX_MC_EVT) { - __this_cpu_dec(rtas_ue_count); - return; - } - this_cpu_write(rtas_ue_paddr[index], paddr); - schedule_work(&hwpoison_work); -} - -static void pseries_do_memory_failure(struct pt_regs *regs, - struct pseries_mc_errorlog *mce_log) -{ - unsigned long paddr; - - if (mce_log->sub_err_type & UE_LOGICAL_ADDR_PROVIDED) { - paddr = be64_to_cpu(mce_log->logical_address); - } else if (mce_log->sub_err_type & UE_EFFECTIVE_ADDR_PROVIDED) { - unsigned long pfn; - - pfn = addr_to_pfn(regs, - be64_to_cpu(mce_log->effective_address)); - if (pfn == ULONG_MAX) - return; - paddr = pfn << PAGE_SHIFT; - } else { - return; - } - queue_ue_paddr(paddr); -} - -static void pseries_process_ue(struct pt_regs *regs, - struct rtas_error_log *errp) -{ - struct pseries_errorlog *pseries_log; - struct pseries_mc_errorlog *mce_log; - - if (!rtas_error_extended(errp)) - return; - - pseries_log = get_pseries_errorlog(errp, PSERIES_ELOG_SECT_ID_MCE); - if (!pseries_log) - return; - - mce_log = (struct pseries_mc_errorlog *)pseries_log->data; - - if (mce_log->error_type == MC_ERROR_TYPE_UE) - pseries_do_memory_failure(regs, mce_log); + return disposition; } -#else -static inline void pseries_process_ue(struct pt_regs *regs, - struct rtas_error_log *errp) { } -#endif /*CONFIG_MEMORY_FAILURE */ /* * Process MCE rtas errlog event. @@ -795,49 +709,51 @@ static void mce_process_errlog_event(struct irq_work *work) * Return 1 if corrected (or delivered a signal). * Return 0 if there is nothing we can do. */ -static int recover_mce(struct pt_regs *regs, struct rtas_error_log *err) +static int recover_mce(struct pt_regs *regs, struct machine_check_event *evt) { int recovered = 0; - int disposition = rtas_error_disposition(err); - - pseries_print_mce_info(regs, err); if (!(regs->msr & MSR_RI)) { /* If MSR_RI isn't set, we cannot recover */ pr_err("Machine check interrupt unrecoverable: MSR(RI=0)\n"); recovered = 0; - - } else if (disposition == RTAS_DISP_FULLY_RECOVERED) { + } else if (evt->disposition == MCE_DISPOSITION_RECOVERED) { /* Platform corrected itself */ recovered = 1; + } else if (evt->severity == MCE_SEV_FATAL) { + /* Fatal machine check */ + pr_err("Machine check interrupt is fatal\n"); + recovered = 0; + } - } else if (disposition == RTAS_DISP_LIMITED_RECOVERY) { - /* Platform corrected itself but could be degraded */ - printk(KERN_ERR "MCE: limited recovery, system may " - "be degraded\n"); - recovered = 1; - - } else if (user_mode(regs) && !is_global_init(current) && - rtas_error_severity(err) == RTAS_SEVERITY_ERROR_SYNC) { - + if (!recovered && evt->sync_error) { /* - * If we received a synchronous error when in userspace - * kill the task. Firmware may report details of the fail - * asynchronously, so we can't rely on the target and type - * fields being valid here. + * Try to kill processes if we get a synchronous machine check + * (e.g., one caused by execution of this instruction). This + * will devolve into a panic if we try to kill init or are in + * an interrupt etc. + * + * TODO: Queue up this address for hwpoisioning later. + * TODO: This is not quite right for d-side machine + * checks ->nip is not necessarily the important + * address. */ - printk(KERN_ERR "MCE: uncorrectable error, killing task " - "%s:%d\n", current->comm, current->pid); - - _exception(SIGBUS, regs, BUS_MCEERR_AR, regs->nip); - recovered = 1; + if ((user_mode(regs))) { + _exception(SIGBUS, regs, BUS_MCEERR_AR, regs->nip); + recovered = 1; + } else if (die_will_crash()) { + /* + * die() would kill the kernel, so better to go via + * the platform reboot code that will log the + * machine check. + */ + recovered = 0; + } else { + die("Machine check", regs, SIGBUS); + recovered = 1; + } } - pseries_process_ue(regs, err); - - /* Queue irq work to log this rtas event later. */ - irq_work_queue(&mce_errlog_process_work); - return recovered; } @@ -853,14 +769,21 @@ static int recover_mce(struct pt_regs *regs, struct rtas_error_log *err) */ int pSeries_machine_check_exception(struct pt_regs *regs) { - struct rtas_error_log *errp; + struct machine_check_event evt; - if (fwnmi_active) { - fwnmi_release_errinfo(); - errp = fwnmi_get_errlog(); - if (errp && recover_mce(regs, errp)) - return 1; + if (!get_mce_event(&evt, MCE_EVENT_RELEASE)) + return 0; + + /* Print things out */ + if (evt.version != MCE_V1) { + pr_err("Machine Check Exception, Unknown event version %d !\n", + evt.version); + return 0; } + machine_check_print_event_info(&evt, user_mode(regs), false); + + if (recover_mce(regs, &evt)) + return 1; return 0; } @@ -877,7 +800,12 @@ long pseries_machine_check_realmode(struct pt_regs *regs) * to panic. Hence we will call it as soon as we go into * virtual mode. */ - disposition = mce_handle_error(errp); + disposition = mce_handle_error(regs, errp); + fwnmi_release_errinfo(); + + /* Queue irq work to log this rtas event later. */ + irq_work_queue(&mce_errlog_process_work); + if (disposition == RTAS_DISP_FULLY_RECOVERED) return 1; } diff --git a/arch/powerpc/platforms/pseries/rtas-fadump.c b/arch/powerpc/platforms/pseries/rtas-fadump.c new file mode 100644 index 000000000000..70c3013fdd07 --- /dev/null +++ b/arch/powerpc/platforms/pseries/rtas-fadump.c @@ -0,0 +1,550 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Firmware-Assisted Dump support on POWERVM platform. + * + * Copyright 2011, Mahesh Salgaonkar, IBM Corporation. + * Copyright 2019, Hari Bathini, IBM Corporation. + */ + +#define pr_fmt(fmt) "rtas fadump: " fmt + +#include <linux/string.h> +#include <linux/memblock.h> +#include <linux/delay.h> +#include <linux/seq_file.h> +#include <linux/crash_dump.h> + +#include <asm/page.h> +#include <asm/prom.h> +#include <asm/rtas.h> +#include <asm/fadump.h> +#include <asm/fadump-internal.h> + +#include "rtas-fadump.h" + +static struct rtas_fadump_mem_struct fdm; +static const struct rtas_fadump_mem_struct *fdm_active; + +static void rtas_fadump_update_config(struct fw_dump *fadump_conf, + const struct rtas_fadump_mem_struct *fdm) +{ + fadump_conf->boot_mem_dest_addr = + be64_to_cpu(fdm->rmr_region.destination_address); + + fadump_conf->fadumphdr_addr = (fadump_conf->boot_mem_dest_addr + + fadump_conf->boot_memory_size); +} + +/* + * This function is called in the capture kernel to get configuration details + * setup in the first kernel and passed to the f/w. + */ +static void rtas_fadump_get_config(struct fw_dump *fadump_conf, + const struct rtas_fadump_mem_struct *fdm) +{ + fadump_conf->boot_mem_addr[0] = + be64_to_cpu(fdm->rmr_region.source_address); + fadump_conf->boot_mem_sz[0] = be64_to_cpu(fdm->rmr_region.source_len); + fadump_conf->boot_memory_size = fadump_conf->boot_mem_sz[0]; + + fadump_conf->boot_mem_top = fadump_conf->boot_memory_size; + fadump_conf->boot_mem_regs_cnt = 1; + + /* + * Start address of reserve dump area (permanent reservation) for + * re-registering FADump after dump capture. + */ + fadump_conf->reserve_dump_area_start = + be64_to_cpu(fdm->cpu_state_data.destination_address); + + rtas_fadump_update_config(fadump_conf, fdm); +} + +static u64 rtas_fadump_init_mem_struct(struct fw_dump *fadump_conf) +{ + u64 addr = fadump_conf->reserve_dump_area_start; + + memset(&fdm, 0, sizeof(struct rtas_fadump_mem_struct)); + addr = addr & PAGE_MASK; + + fdm.header.dump_format_version = cpu_to_be32(0x00000001); + fdm.header.dump_num_sections = cpu_to_be16(3); + fdm.header.dump_status_flag = 0; + fdm.header.offset_first_dump_section = + cpu_to_be32((u32)offsetof(struct rtas_fadump_mem_struct, + cpu_state_data)); + + /* + * Fields for disk dump option. + * We are not using disk dump option, hence set these fields to 0. + */ + fdm.header.dd_block_size = 0; + fdm.header.dd_block_offset = 0; + fdm.header.dd_num_blocks = 0; + fdm.header.dd_offset_disk_path = 0; + + /* set 0 to disable an automatic dump-reboot. */ + fdm.header.max_time_auto = 0; + + /* Kernel dump sections */ + /* cpu state data section. */ + fdm.cpu_state_data.request_flag = + cpu_to_be32(RTAS_FADUMP_REQUEST_FLAG); + fdm.cpu_state_data.source_data_type = + cpu_to_be16(RTAS_FADUMP_CPU_STATE_DATA); + fdm.cpu_state_data.source_address = 0; + fdm.cpu_state_data.source_len = + cpu_to_be64(fadump_conf->cpu_state_data_size); + fdm.cpu_state_data.destination_address = cpu_to_be64(addr); + addr += fadump_conf->cpu_state_data_size; + + /* hpte region section */ + fdm.hpte_region.request_flag = cpu_to_be32(RTAS_FADUMP_REQUEST_FLAG); + fdm.hpte_region.source_data_type = + cpu_to_be16(RTAS_FADUMP_HPTE_REGION); + fdm.hpte_region.source_address = 0; + fdm.hpte_region.source_len = + cpu_to_be64(fadump_conf->hpte_region_size); + fdm.hpte_region.destination_address = cpu_to_be64(addr); + addr += fadump_conf->hpte_region_size; + + /* RMA region section */ + fdm.rmr_region.request_flag = cpu_to_be32(RTAS_FADUMP_REQUEST_FLAG); + fdm.rmr_region.source_data_type = + cpu_to_be16(RTAS_FADUMP_REAL_MODE_REGION); + fdm.rmr_region.source_address = cpu_to_be64(0); + fdm.rmr_region.source_len = cpu_to_be64(fadump_conf->boot_memory_size); + fdm.rmr_region.destination_address = cpu_to_be64(addr); + addr += fadump_conf->boot_memory_size; + + rtas_fadump_update_config(fadump_conf, &fdm); + + return addr; +} + +static u64 rtas_fadump_get_bootmem_min(void) +{ + return RTAS_FADUMP_MIN_BOOT_MEM; +} + +static int rtas_fadump_register(struct fw_dump *fadump_conf) +{ + unsigned int wait_time; + int rc, err = -EIO; + + /* TODO: Add upper time limit for the delay */ + do { + rc = rtas_call(fadump_conf->ibm_configure_kernel_dump, 3, 1, + NULL, FADUMP_REGISTER, &fdm, + sizeof(struct rtas_fadump_mem_struct)); + + wait_time = rtas_busy_delay_time(rc); + if (wait_time) + mdelay(wait_time); + + } while (wait_time); + + switch (rc) { + case 0: + pr_info("Registration is successful!\n"); + fadump_conf->dump_registered = 1; + err = 0; + break; + case -1: + pr_err("Failed to register. Hardware Error(%d).\n", rc); + break; + case -3: + if (!is_fadump_boot_mem_contiguous()) + pr_err("Can't have holes in boot memory area.\n"); + else if (!is_fadump_reserved_mem_contiguous()) + pr_err("Can't have holes in reserved memory area.\n"); + + pr_err("Failed to register. Parameter Error(%d).\n", rc); + err = -EINVAL; + break; + case -9: + pr_err("Already registered!\n"); + fadump_conf->dump_registered = 1; + err = -EEXIST; + break; + default: + pr_err("Failed to register. Unknown Error(%d).\n", rc); + break; + } + + return err; +} + +static int rtas_fadump_unregister(struct fw_dump *fadump_conf) +{ + unsigned int wait_time; + int rc; + + /* TODO: Add upper time limit for the delay */ + do { + rc = rtas_call(fadump_conf->ibm_configure_kernel_dump, 3, 1, + NULL, FADUMP_UNREGISTER, &fdm, + sizeof(struct rtas_fadump_mem_struct)); + + wait_time = rtas_busy_delay_time(rc); + if (wait_time) + mdelay(wait_time); + } while (wait_time); + + if (rc) { + pr_err("Failed to un-register - unexpected error(%d).\n", rc); + return -EIO; + } + + fadump_conf->dump_registered = 0; + return 0; +} + +static int rtas_fadump_invalidate(struct fw_dump *fadump_conf) +{ + unsigned int wait_time; + int rc; + + /* TODO: Add upper time limit for the delay */ + do { + rc = rtas_call(fadump_conf->ibm_configure_kernel_dump, 3, 1, + NULL, FADUMP_INVALIDATE, fdm_active, + sizeof(struct rtas_fadump_mem_struct)); + + wait_time = rtas_busy_delay_time(rc); + if (wait_time) + mdelay(wait_time); + } while (wait_time); + + if (rc) { + pr_err("Failed to invalidate - unexpected error (%d).\n", rc); + return -EIO; + } + + fadump_conf->dump_active = 0; + fdm_active = NULL; + return 0; +} + +#define RTAS_FADUMP_GPR_MASK 0xffffff0000000000 +static inline int rtas_fadump_gpr_index(u64 id) +{ + char str[3]; + int i = -1; + + if ((id & RTAS_FADUMP_GPR_MASK) == fadump_str_to_u64("GPR")) { + /* get the digits at the end */ + id &= ~RTAS_FADUMP_GPR_MASK; + id >>= 24; + str[2] = '\0'; + str[1] = id & 0xff; + str[0] = (id >> 8) & 0xff; + if (kstrtoint(str, 10, &i)) + i = -EINVAL; + if (i > 31) + i = -1; + } + return i; +} + +void rtas_fadump_set_regval(struct pt_regs *regs, u64 reg_id, u64 reg_val) +{ + int i; + + i = rtas_fadump_gpr_index(reg_id); + if (i >= 0) + regs->gpr[i] = (unsigned long)reg_val; + else if (reg_id == fadump_str_to_u64("NIA")) + regs->nip = (unsigned long)reg_val; + else if (reg_id == fadump_str_to_u64("MSR")) + regs->msr = (unsigned long)reg_val; + else if (reg_id == fadump_str_to_u64("CTR")) + regs->ctr = (unsigned long)reg_val; + else if (reg_id == fadump_str_to_u64("LR")) + regs->link = (unsigned long)reg_val; + else if (reg_id == fadump_str_to_u64("XER")) + regs->xer = (unsigned long)reg_val; + else if (reg_id == fadump_str_to_u64("CR")) + regs->ccr = (unsigned long)reg_val; + else if (reg_id == fadump_str_to_u64("DAR")) + regs->dar = (unsigned long)reg_val; + else if (reg_id == fadump_str_to_u64("DSISR")) + regs->dsisr = (unsigned long)reg_val; +} + +static struct rtas_fadump_reg_entry* +rtas_fadump_read_regs(struct rtas_fadump_reg_entry *reg_entry, + struct pt_regs *regs) +{ + memset(regs, 0, sizeof(struct pt_regs)); + + while (be64_to_cpu(reg_entry->reg_id) != fadump_str_to_u64("CPUEND")) { + rtas_fadump_set_regval(regs, be64_to_cpu(reg_entry->reg_id), + be64_to_cpu(reg_entry->reg_value)); + reg_entry++; + } + reg_entry++; + return reg_entry; +} + +/* + * Read CPU state dump data and convert it into ELF notes. + * The CPU dump starts with magic number "REGSAVE". NumCpusOffset should be + * used to access the data to allow for additional fields to be added without + * affecting compatibility. Each list of registers for a CPU starts with + * "CPUSTRT" and ends with "CPUEND". Each register entry is of 16 bytes, + * 8 Byte ASCII identifier and 8 Byte register value. The register entry + * with identifier "CPUSTRT" and "CPUEND" contains 4 byte cpu id as part + * of register value. For more details refer to PAPR document. + * + * Only for the crashing cpu we ignore the CPU dump data and get exact + * state from fadump crash info structure populated by first kernel at the + * time of crash. + */ +static int __init rtas_fadump_build_cpu_notes(struct fw_dump *fadump_conf) +{ + struct rtas_fadump_reg_save_area_header *reg_header; + struct fadump_crash_info_header *fdh = NULL; + struct rtas_fadump_reg_entry *reg_entry; + u32 num_cpus, *note_buf; + int i, rc = 0, cpu = 0; + struct pt_regs regs; + unsigned long addr; + void *vaddr; + + addr = be64_to_cpu(fdm_active->cpu_state_data.destination_address); + vaddr = __va(addr); + + reg_header = vaddr; + if (be64_to_cpu(reg_header->magic_number) != + fadump_str_to_u64("REGSAVE")) { + pr_err("Unable to read register save area.\n"); + return -ENOENT; + } + + pr_debug("--------CPU State Data------------\n"); + pr_debug("Magic Number: %llx\n", be64_to_cpu(reg_header->magic_number)); + pr_debug("NumCpuOffset: %x\n", be32_to_cpu(reg_header->num_cpu_offset)); + + vaddr += be32_to_cpu(reg_header->num_cpu_offset); + num_cpus = be32_to_cpu(*((__be32 *)(vaddr))); + pr_debug("NumCpus : %u\n", num_cpus); + vaddr += sizeof(u32); + reg_entry = (struct rtas_fadump_reg_entry *)vaddr; + + rc = fadump_setup_cpu_notes_buf(num_cpus); + if (rc != 0) + return rc; + + note_buf = (u32 *)fadump_conf->cpu_notes_buf_vaddr; + + if (fadump_conf->fadumphdr_addr) + fdh = __va(fadump_conf->fadumphdr_addr); + + for (i = 0; i < num_cpus; i++) { + if (be64_to_cpu(reg_entry->reg_id) != + fadump_str_to_u64("CPUSTRT")) { + pr_err("Unable to read CPU state data\n"); + rc = -ENOENT; + goto error_out; + } + /* Lower 4 bytes of reg_value contains logical cpu id */ + cpu = (be64_to_cpu(reg_entry->reg_value) & + RTAS_FADUMP_CPU_ID_MASK); + if (fdh && !cpumask_test_cpu(cpu, &fdh->online_mask)) { + RTAS_FADUMP_SKIP_TO_NEXT_CPU(reg_entry); + continue; + } + pr_debug("Reading register data for cpu %d...\n", cpu); + if (fdh && fdh->crashing_cpu == cpu) { + regs = fdh->regs; + note_buf = fadump_regs_to_elf_notes(note_buf, ®s); + RTAS_FADUMP_SKIP_TO_NEXT_CPU(reg_entry); + } else { + reg_entry++; + reg_entry = rtas_fadump_read_regs(reg_entry, ®s); + note_buf = fadump_regs_to_elf_notes(note_buf, ®s); + } + } + final_note(note_buf); + + if (fdh) { + pr_debug("Updating elfcore header (%llx) with cpu notes\n", + fdh->elfcorehdr_addr); + fadump_update_elfcore_header(__va(fdh->elfcorehdr_addr)); + } + return 0; + +error_out: + fadump_free_cpu_notes_buf(); + return rc; + +} + +/* + * Validate and process the dump data stored by firmware before exporting + * it through '/proc/vmcore'. + */ +static int __init rtas_fadump_process(struct fw_dump *fadump_conf) +{ + struct fadump_crash_info_header *fdh; + int rc = 0; + + if (!fdm_active || !fadump_conf->fadumphdr_addr) + return -EINVAL; + + /* Check if the dump data is valid. */ + if ((be16_to_cpu(fdm_active->header.dump_status_flag) == + RTAS_FADUMP_ERROR_FLAG) || + (fdm_active->cpu_state_data.error_flags != 0) || + (fdm_active->rmr_region.error_flags != 0)) { + pr_err("Dump taken by platform is not valid\n"); + return -EINVAL; + } + if ((fdm_active->rmr_region.bytes_dumped != + fdm_active->rmr_region.source_len) || + !fdm_active->cpu_state_data.bytes_dumped) { + pr_err("Dump taken by platform is incomplete\n"); + return -EINVAL; + } + + /* Validate the fadump crash info header */ + fdh = __va(fadump_conf->fadumphdr_addr); + if (fdh->magic_number != FADUMP_CRASH_INFO_MAGIC) { + pr_err("Crash info header is not valid.\n"); + return -EINVAL; + } + + rc = rtas_fadump_build_cpu_notes(fadump_conf); + if (rc) + return rc; + + /* + * We are done validating dump info and elfcore header is now ready + * to be exported. set elfcorehdr_addr so that vmcore module will + * export the elfcore header through '/proc/vmcore'. + */ + elfcorehdr_addr = fdh->elfcorehdr_addr; + + return 0; +} + +static void rtas_fadump_region_show(struct fw_dump *fadump_conf, + struct seq_file *m) +{ + const struct rtas_fadump_section *cpu_data_section; + const struct rtas_fadump_mem_struct *fdm_ptr; + + if (fdm_active) + fdm_ptr = fdm_active; + else + fdm_ptr = &fdm; + + cpu_data_section = &(fdm_ptr->cpu_state_data); + seq_printf(m, "CPU :[%#016llx-%#016llx] %#llx bytes, Dumped: %#llx\n", + be64_to_cpu(cpu_data_section->destination_address), + be64_to_cpu(cpu_data_section->destination_address) + + be64_to_cpu(cpu_data_section->source_len) - 1, + be64_to_cpu(cpu_data_section->source_len), + be64_to_cpu(cpu_data_section->bytes_dumped)); + + seq_printf(m, "HPTE:[%#016llx-%#016llx] %#llx bytes, Dumped: %#llx\n", + be64_to_cpu(fdm_ptr->hpte_region.destination_address), + be64_to_cpu(fdm_ptr->hpte_region.destination_address) + + be64_to_cpu(fdm_ptr->hpte_region.source_len) - 1, + be64_to_cpu(fdm_ptr->hpte_region.source_len), + be64_to_cpu(fdm_ptr->hpte_region.bytes_dumped)); + + seq_printf(m, "DUMP: Src: %#016llx, Dest: %#016llx, ", + be64_to_cpu(fdm_ptr->rmr_region.source_address), + be64_to_cpu(fdm_ptr->rmr_region.destination_address)); + seq_printf(m, "Size: %#llx, Dumped: %#llx bytes\n", + be64_to_cpu(fdm_ptr->rmr_region.source_len), + be64_to_cpu(fdm_ptr->rmr_region.bytes_dumped)); + + /* Dump is active. Show reserved area start address. */ + if (fdm_active) { + seq_printf(m, "\nMemory above %#016lx is reserved for saving crash dump\n", + fadump_conf->reserve_dump_area_start); + } +} + +static void rtas_fadump_trigger(struct fadump_crash_info_header *fdh, + const char *msg) +{ + /* Call ibm,os-term rtas call to trigger firmware assisted dump */ + rtas_os_term((char *)msg); +} + +static struct fadump_ops rtas_fadump_ops = { + .fadump_init_mem_struct = rtas_fadump_init_mem_struct, + .fadump_get_bootmem_min = rtas_fadump_get_bootmem_min, + .fadump_register = rtas_fadump_register, + .fadump_unregister = rtas_fadump_unregister, + .fadump_invalidate = rtas_fadump_invalidate, + .fadump_process = rtas_fadump_process, + .fadump_region_show = rtas_fadump_region_show, + .fadump_trigger = rtas_fadump_trigger, +}; + +void __init rtas_fadump_dt_scan(struct fw_dump *fadump_conf, u64 node) +{ + int i, size, num_sections; + const __be32 *sections; + const __be32 *token; + + /* + * Check if Firmware Assisted dump is supported. if yes, check + * if dump has been initiated on last reboot. + */ + token = of_get_flat_dt_prop(node, "ibm,configure-kernel-dump", NULL); + if (!token) + return; + + fadump_conf->ibm_configure_kernel_dump = be32_to_cpu(*token); + fadump_conf->ops = &rtas_fadump_ops; + fadump_conf->fadump_supported = 1; + + /* Firmware supports 64-bit value for size, align it to pagesize. */ + fadump_conf->max_copy_size = _ALIGN_DOWN(U64_MAX, PAGE_SIZE); + + /* + * The 'ibm,kernel-dump' rtas node is present only if there is + * dump data waiting for us. + */ + fdm_active = of_get_flat_dt_prop(node, "ibm,kernel-dump", NULL); + if (fdm_active) { + pr_info("Firmware-assisted dump is active.\n"); + fadump_conf->dump_active = 1; + rtas_fadump_get_config(fadump_conf, (void *)__pa(fdm_active)); + } + + /* Get the sizes required to store dump data for the firmware provided + * dump sections. + * For each dump section type supported, a 32bit cell which defines + * the ID of a supported section followed by two 32 bit cells which + * gives the size of the section in bytes. + */ + sections = of_get_flat_dt_prop(node, "ibm,configure-kernel-dump-sizes", + &size); + + if (!sections) + return; + + num_sections = size / (3 * sizeof(u32)); + + for (i = 0; i < num_sections; i++, sections += 3) { + u32 type = (u32)of_read_number(sections, 1); + + switch (type) { + case RTAS_FADUMP_CPU_STATE_DATA: + fadump_conf->cpu_state_data_size = + of_read_ulong(§ions[1], 2); + break; + case RTAS_FADUMP_HPTE_REGION: + fadump_conf->hpte_region_size = + of_read_ulong(§ions[1], 2); + break; + } + } +} diff --git a/arch/powerpc/platforms/pseries/rtas-fadump.h b/arch/powerpc/platforms/pseries/rtas-fadump.h new file mode 100644 index 000000000000..fd59bd7ca9c3 --- /dev/null +++ b/arch/powerpc/platforms/pseries/rtas-fadump.h @@ -0,0 +1,114 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Firmware-Assisted Dump support on POWERVM platform. + * + * Copyright 2011, Mahesh Salgaonkar, IBM Corporation. + * Copyright 2019, Hari Bathini, IBM Corporation. + */ + +#ifndef _PSERIES_RTAS_FADUMP_H +#define _PSERIES_RTAS_FADUMP_H + +/* + * On some Power systems where RMO is 128MB, it still requires minimum of + * 256MB for kernel to boot successfully. When kdump infrastructure is + * configured to save vmcore over network, we run into OOM issue while + * loading modules related to network setup. Hence we need additional 64M + * of memory to avoid OOM issue. + */ +#define RTAS_FADUMP_MIN_BOOT_MEM ((0x1UL << 28) + (0x1UL << 26)) + +/* Firmware provided dump sections */ +#define RTAS_FADUMP_CPU_STATE_DATA 0x0001 +#define RTAS_FADUMP_HPTE_REGION 0x0002 +#define RTAS_FADUMP_REAL_MODE_REGION 0x0011 + +/* Dump request flag */ +#define RTAS_FADUMP_REQUEST_FLAG 0x00000001 + +/* Dump status flag */ +#define RTAS_FADUMP_ERROR_FLAG 0x2000 + +/* Kernel Dump section info */ +struct rtas_fadump_section { + __be32 request_flag; + __be16 source_data_type; + __be16 error_flags; + __be64 source_address; + __be64 source_len; + __be64 bytes_dumped; + __be64 destination_address; +}; + +/* ibm,configure-kernel-dump header. */ +struct rtas_fadump_section_header { + __be32 dump_format_version; + __be16 dump_num_sections; + __be16 dump_status_flag; + __be32 offset_first_dump_section; + + /* Fields for disk dump option. */ + __be32 dd_block_size; + __be64 dd_block_offset; + __be64 dd_num_blocks; + __be32 dd_offset_disk_path; + + /* Maximum time allowed to prevent an automatic dump-reboot. */ + __be32 max_time_auto; +}; + +/* + * Firmware Assisted dump memory structure. This structure is required for + * registering future kernel dump with power firmware through rtas call. + * + * No disk dump option. Hence disk dump path string section is not included. + */ +struct rtas_fadump_mem_struct { + struct rtas_fadump_section_header header; + + /* Kernel dump sections */ + struct rtas_fadump_section cpu_state_data; + struct rtas_fadump_section hpte_region; + + /* + * TODO: Extend multiple boot memory regions support in the kernel + * for this platform. + */ + struct rtas_fadump_section rmr_region; +}; + +/* + * The firmware-assisted dump format. + * + * The register save area is an area in the partition's memory used to preserve + * the register contents (CPU state data) for the active CPUs during a firmware + * assisted dump. The dump format contains register save area header followed + * by register entries. Each list of registers for a CPU starts with "CPUSTRT" + * and ends with "CPUEND". + */ + +/* Register save area header. */ +struct rtas_fadump_reg_save_area_header { + __be64 magic_number; + __be32 version; + __be32 num_cpu_offset; +}; + +/* Register entry. */ +struct rtas_fadump_reg_entry { + __be64 reg_id; + __be64 reg_value; +}; + +/* Utility macros */ +#define RTAS_FADUMP_SKIP_TO_NEXT_CPU(reg_entry) \ +({ \ + while (be64_to_cpu(reg_entry->reg_id) != \ + fadump_str_to_u64("CPUEND")) \ + reg_entry++; \ + reg_entry++; \ +}) + +#define RTAS_FADUMP_CPU_ID_MASK ((1UL << 32) - 1) + +#endif /* _PSERIES_RTAS_FADUMP_H */ diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index f5940cc71c37..f8adcd0e4589 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -69,6 +69,7 @@ #include <asm/security_features.h> #include <asm/asm-const.h> #include <asm/swiotlb.h> +#include <asm/svm.h> #include "pseries.h" #include "../../../../drivers/pci/pci.h" @@ -141,17 +142,19 @@ static void __init fwnmi_init(void) } #ifdef CONFIG_PPC_BOOK3S_64 - /* Allocate per cpu slb area to save old slb contents during MCE */ - size = sizeof(struct slb_entry) * mmu_slb_size * nr_cpus; - slb_ptr = memblock_alloc_try_nid_raw(size, sizeof(struct slb_entry), - MEMBLOCK_LOW_LIMIT, ppc64_rma_size, - NUMA_NO_NODE); - if (!slb_ptr) - panic("Failed to allocate %zu bytes below %pa for slb area\n", - size, &ppc64_rma_size); - - for_each_possible_cpu(i) - paca_ptrs[i]->mce_faulty_slbs = slb_ptr + (mmu_slb_size * i); + if (!radix_enabled()) { + /* Allocate per cpu area to save old slb contents during MCE */ + size = sizeof(struct slb_entry) * mmu_slb_size * nr_cpus; + slb_ptr = memblock_alloc_try_nid_raw(size, + sizeof(struct slb_entry), MEMBLOCK_LOW_LIMIT, + ppc64_rma_size, NUMA_NO_NODE); + if (!slb_ptr) + panic("Failed to allocate %zu bytes below %pa for slb area\n", + size, &ppc64_rma_size); + + for_each_possible_cpu(i) + paca_ptrs[i]->mce_faulty_slbs = slb_ptr + (mmu_slb_size * i); + } #endif } @@ -297,8 +300,10 @@ static inline int alloc_dispatch_logs(void) static int alloc_dispatch_log_kmem_cache(void) { + void (*ctor)(void *) = get_dtl_cache_ctor(); + dtl_cache = kmem_cache_create("dtl", DISPATCH_LOG_BYTES, - DISPATCH_LOG_BYTES, 0, NULL); + DISPATCH_LOG_BYTES, 0, ctor); if (!dtl_cache) { pr_warn("Failed to create dispatch trace log buffer cache\n"); pr_warn("Stolen time statistics will be unreliable\n"); @@ -316,6 +321,9 @@ static void pseries_lpar_idle(void) * low power mode by ceding processor to hypervisor */ + if (!prep_irq_for_idle()) + return; + /* Indicate to hypervisor that we are idle. */ get_lppaca()->idle = 1; diff --git a/arch/powerpc/platforms/pseries/smp.c b/arch/powerpc/platforms/pseries/smp.c index 4b3ef8d9c63f..ad61e90032da 100644 --- a/arch/powerpc/platforms/pseries/smp.c +++ b/arch/powerpc/platforms/pseries/smp.c @@ -41,6 +41,7 @@ #include <asm/dbell.h> #include <asm/plpar_wrappers.h> #include <asm/code-patching.h> +#include <asm/svm.h> #include "pseries.h" #include "offline_states.h" @@ -221,7 +222,7 @@ static __init void pSeries_smp_probe_xics(void) { xics_smp_probe(); - if (cpu_has_feature(CPU_FTR_DBELL)) + if (cpu_has_feature(CPU_FTR_DBELL) && !is_secure_guest()) smp_ops->cause_ipi = smp_pseries_cause_ipi; else smp_ops->cause_ipi = icp_ops->cause_ipi; diff --git a/arch/powerpc/platforms/pseries/svm.c b/arch/powerpc/platforms/pseries/svm.c new file mode 100644 index 000000000000..40c0637203d5 --- /dev/null +++ b/arch/powerpc/platforms/pseries/svm.c @@ -0,0 +1,85 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Secure VM platform + * + * Copyright 2018 IBM Corporation + * Author: Anshuman Khandual <khandual@linux.vnet.ibm.com> + */ + +#include <linux/mm.h> +#include <asm/machdep.h> +#include <asm/svm.h> +#include <asm/swiotlb.h> +#include <asm/ultravisor.h> + +static int __init init_svm(void) +{ + if (!is_secure_guest()) + return 0; + + /* Don't release the SWIOTLB buffer. */ + ppc_swiotlb_enable = 1; + + /* + * Since the guest memory is inaccessible to the host, devices always + * need to use the SWIOTLB buffer for DMA even if dma_capable() says + * otherwise. + */ + swiotlb_force = SWIOTLB_FORCE; + + /* Share the SWIOTLB buffer with the host. */ + swiotlb_update_mem_attributes(); + + return 0; +} +machine_early_initcall(pseries, init_svm); + +int set_memory_encrypted(unsigned long addr, int numpages) +{ + if (!PAGE_ALIGNED(addr)) + return -EINVAL; + + uv_unshare_page(PHYS_PFN(__pa(addr)), numpages); + + return 0; +} + +int set_memory_decrypted(unsigned long addr, int numpages) +{ + if (!PAGE_ALIGNED(addr)) + return -EINVAL; + + uv_share_page(PHYS_PFN(__pa(addr)), numpages); + + return 0; +} + +/* There's one dispatch log per CPU. */ +#define NR_DTL_PAGE (DISPATCH_LOG_BYTES * CONFIG_NR_CPUS / PAGE_SIZE) + +static struct page *dtl_page_store[NR_DTL_PAGE]; +static long dtl_nr_pages; + +static bool is_dtl_page_shared(struct page *page) +{ + long i; + + for (i = 0; i < dtl_nr_pages; i++) + if (dtl_page_store[i] == page) + return true; + + return false; +} + +void dtl_cache_ctor(void *addr) +{ + unsigned long pfn = PHYS_PFN(__pa(addr)); + struct page *page = pfn_to_page(pfn); + + if (!is_dtl_page_shared(page)) { + dtl_page_store[dtl_nr_pages] = page; + dtl_nr_pages++; + WARN_ON(dtl_nr_pages >= NR_DTL_PAGE); + uv_share_page(pfn, 1); + } +} diff --git a/arch/powerpc/platforms/pseries/vio.c b/arch/powerpc/platforms/pseries/vio.c index 6601b9d404dc..79e2287991db 100644 --- a/arch/powerpc/platforms/pseries/vio.c +++ b/arch/powerpc/platforms/pseries/vio.c @@ -605,6 +605,8 @@ static const struct dma_map_ops vio_dma_mapping_ops = { .unmap_page = vio_dma_iommu_unmap_page, .dma_supported = dma_iommu_dma_supported, .get_required_mask = dma_iommu_get_required_mask, + .mmap = dma_common_mmap, + .get_sgtable = dma_common_get_sgtable, }; /** @@ -1191,7 +1193,7 @@ static struct iommu_table *vio_build_iommu_table(struct vio_dev *dev) else tbl->it_ops = &iommu_table_pseries_ops; - return iommu_init_table(tbl, -1); + return iommu_init_table(tbl, -1, 0, 0); } /** diff --git a/arch/powerpc/sysdev/Kconfig b/arch/powerpc/sysdev/Kconfig index d23288c4abf6..9ebcc1337560 100644 --- a/arch/powerpc/sysdev/Kconfig +++ b/arch/powerpc/sysdev/Kconfig @@ -28,13 +28,6 @@ config PPC_MSI_BITMAP source "arch/powerpc/sysdev/xics/Kconfig" source "arch/powerpc/sysdev/xive/Kconfig" -config PPC_SCOM - bool - -config SCOM_DEBUGFS - bool "Expose SCOM controllers via debugfs" - depends on PPC_SCOM && DEBUG_FS - config GE_FPGA bool diff --git a/arch/powerpc/sysdev/Makefile b/arch/powerpc/sysdev/Makefile index 9d73dfddf060..603b3c656d19 100644 --- a/arch/powerpc/sysdev/Makefile +++ b/arch/powerpc/sysdev/Makefile @@ -49,8 +49,6 @@ ifdef CONFIG_SUSPEND obj-$(CONFIG_PPC_BOOK3S_32) += 6xx-suspend.o endif -obj-$(CONFIG_PPC_SCOM) += scom.o - obj-$(CONFIG_PPC_EARLY_DEBUG_MEMCONS) += udbg_memcons.o obj-$(CONFIG_PPC_XICS) += xics/ diff --git a/arch/powerpc/sysdev/dart_iommu.c b/arch/powerpc/sysdev/dart_iommu.c index 21a1fae0714e..6b4a34b36d98 100644 --- a/arch/powerpc/sysdev/dart_iommu.c +++ b/arch/powerpc/sysdev/dart_iommu.c @@ -344,7 +344,7 @@ static void iommu_table_dart_setup(void) iommu_table_dart.it_index = 0; iommu_table_dart.it_blocksize = 1; iommu_table_dart.it_ops = &iommu_dart_ops; - iommu_init_table(&iommu_table_dart, -1); + iommu_init_table(&iommu_table_dart, -1, 0, 0); /* Reserve the last page of the DART to avoid possible prefetch * past the DART mapped area diff --git a/arch/powerpc/sysdev/scom.c b/arch/powerpc/sysdev/scom.c deleted file mode 100644 index 94e885bf3aee..000000000000 --- a/arch/powerpc/sysdev/scom.c +++ /dev/null @@ -1,223 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * Copyright 2010 Benjamin Herrenschmidt, IBM Corp - * <benh@kernel.crashing.org> - * and David Gibson, IBM Corporation. - */ - -#include <linux/kernel.h> -#include <linux/slab.h> -#include <linux/export.h> -#include <asm/debugfs.h> -#include <asm/prom.h> -#include <asm/scom.h> -#include <linux/uaccess.h> - -const struct scom_controller *scom_controller; -EXPORT_SYMBOL_GPL(scom_controller); - -struct device_node *scom_find_parent(struct device_node *node) -{ - struct device_node *par, *tmp; - const u32 *p; - - for (par = of_node_get(node); par;) { - if (of_get_property(par, "scom-controller", NULL)) - break; - p = of_get_property(par, "scom-parent", NULL); - tmp = par; - if (p == NULL) - par = of_get_parent(par); - else - par = of_find_node_by_phandle(*p); - of_node_put(tmp); - } - return par; -} -EXPORT_SYMBOL_GPL(scom_find_parent); - -scom_map_t scom_map_device(struct device_node *dev, int index) -{ - struct device_node *parent; - unsigned int cells, size; - const __be32 *prop, *sprop; - u64 reg, cnt; - scom_map_t ret; - - parent = scom_find_parent(dev); - - if (parent == NULL) - return NULL; - - /* - * We support "scom-reg" properties for adding scom registers - * to a random device-tree node with an explicit scom-parent - * - * We also support the simple "reg" property if the device is - * a direct child of a scom controller. - * - * In case both exist, "scom-reg" takes precedence. - */ - prop = of_get_property(dev, "scom-reg", &size); - sprop = of_get_property(parent, "#scom-cells", NULL); - if (!prop && parent == dev->parent) { - prop = of_get_property(dev, "reg", &size); - sprop = of_get_property(parent, "#address-cells", NULL); - } - if (!prop) - return NULL; - cells = sprop ? be32_to_cpup(sprop) : 1; - size >>= 2; - - if (index >= (size / (2*cells))) - return NULL; - - reg = of_read_number(&prop[index * cells * 2], cells); - cnt = of_read_number(&prop[index * cells * 2 + cells], cells); - - ret = scom_map(parent, reg, cnt); - of_node_put(parent); - - return ret; -} -EXPORT_SYMBOL_GPL(scom_map_device); - -#ifdef CONFIG_SCOM_DEBUGFS -struct scom_debug_entry { - struct device_node *dn; - struct debugfs_blob_wrapper path; - char name[16]; -}; - -static ssize_t scom_debug_read(struct file *filp, char __user *ubuf, - size_t count, loff_t *ppos) -{ - struct scom_debug_entry *ent = filp->private_data; - u64 __user *ubuf64 = (u64 __user *)ubuf; - loff_t off = *ppos; - ssize_t done = 0; - u64 reg, reg_cnt, val; - scom_map_t map; - int rc; - - if (off < 0 || (off & 7) || (count & 7)) - return -EINVAL; - reg = off >> 3; - reg_cnt = count >> 3; - - map = scom_map(ent->dn, reg, reg_cnt); - if (!scom_map_ok(map)) - return -ENXIO; - - for (reg = 0; reg < reg_cnt; reg++) { - rc = scom_read(map, reg, &val); - if (!rc) - rc = put_user(val, ubuf64); - if (rc) { - if (!done) - done = rc; - break; - } - ubuf64++; - *ppos += 8; - done += 8; - } - scom_unmap(map); - return done; -} - -static ssize_t scom_debug_write(struct file* filp, const char __user *ubuf, - size_t count, loff_t *ppos) -{ - struct scom_debug_entry *ent = filp->private_data; - u64 __user *ubuf64 = (u64 __user *)ubuf; - loff_t off = *ppos; - ssize_t done = 0; - u64 reg, reg_cnt, val; - scom_map_t map; - int rc; - - if (off < 0 || (off & 7) || (count & 7)) - return -EINVAL; - reg = off >> 3; - reg_cnt = count >> 3; - - map = scom_map(ent->dn, reg, reg_cnt); - if (!scom_map_ok(map)) - return -ENXIO; - - for (reg = 0; reg < reg_cnt; reg++) { - rc = get_user(val, ubuf64); - if (!rc) - rc = scom_write(map, reg, val); - if (rc) { - if (!done) - done = rc; - break; - } - ubuf64++; - done += 8; - } - scom_unmap(map); - return done; -} - -static const struct file_operations scom_debug_fops = { - .read = scom_debug_read, - .write = scom_debug_write, - .open = simple_open, - .llseek = default_llseek, -}; - -static int scom_debug_init_one(struct dentry *root, struct device_node *dn, - int i) -{ - struct scom_debug_entry *ent; - struct dentry *dir; - - ent = kzalloc(sizeof(*ent), GFP_KERNEL); - if (!ent) - return -ENOMEM; - - ent->dn = of_node_get(dn); - snprintf(ent->name, 16, "%08x", i); - ent->path.data = (void*)kasprintf(GFP_KERNEL, "%pOF", dn); - ent->path.size = strlen((char *)ent->path.data); - - dir = debugfs_create_dir(ent->name, root); - if (!dir) { - of_node_put(dn); - kfree(ent->path.data); - kfree(ent); - return -1; - } - - debugfs_create_blob("devspec", 0400, dir, &ent->path); - debugfs_create_file("access", 0600, dir, ent, &scom_debug_fops); - - return 0; -} - -static int scom_debug_init(void) -{ - struct device_node *dn; - struct dentry *root; - int i, rc; - - root = debugfs_create_dir("scom", powerpc_debugfs_root); - if (!root) - return -1; - - i = rc = 0; - for_each_node_with_property(dn, "scom-controller") { - int id = of_get_ibm_chip_id(dn); - if (id == -1) - id = i; - rc |= scom_debug_init_one(root, dn, id); - i++; - } - - return rc; -} -device_initcall(scom_debug_init); -#endif /* CONFIG_SCOM_DEBUGFS */ diff --git a/arch/powerpc/sysdev/xive/common.c b/arch/powerpc/sysdev/xive/common.c index 1cdb39575eae..df832b09e3e9 100644 --- a/arch/powerpc/sysdev/xive/common.c +++ b/arch/powerpc/sysdev/xive/common.c @@ -135,7 +135,7 @@ static u32 xive_read_eq(struct xive_q *q, bool just_peek) static u32 xive_scan_interrupts(struct xive_cpu *xc, bool just_peek) { u32 irq = 0; - u8 prio; + u8 prio = 0; /* Find highest pending priority */ while (xc->pending_prio != 0) { @@ -148,8 +148,19 @@ static u32 xive_scan_interrupts(struct xive_cpu *xc, bool just_peek) irq = xive_read_eq(&xc->queue[prio], just_peek); /* Found something ? That's it */ - if (irq) - break; + if (irq) { + if (just_peek || irq_to_desc(irq)) + break; + /* + * We should never get here; if we do then we must + * have failed to synchronize the interrupt properly + * when shutting it down. + */ + pr_crit("xive: got interrupt %d without descriptor, dropping\n", + irq); + WARN_ON(1); + continue; + } /* Clear pending bits */ xc->pending_prio &= ~(1 << prio); @@ -185,7 +196,7 @@ static u32 xive_scan_interrupts(struct xive_cpu *xc, bool just_peek) /* * This is used to perform the magic loads from an ESB - * described in xive.h + * described in xive-regs.h */ static notrace u8 xive_esb_read(struct xive_irq_data *xd, u32 offset) { @@ -226,26 +237,61 @@ static notrace void xive_dump_eq(const char *name, struct xive_q *q) i0 = be32_to_cpup(q->qpage + idx); idx = (idx + 1) & q->msk; i1 = be32_to_cpup(q->qpage + idx); - xmon_printf(" %s Q T=%d %08x %08x ...\n", name, - q->toggle, i0, i1); + xmon_printf("%s idx=%d T=%d %08x %08x ...", name, + q->idx, q->toggle, i0, i1); } notrace void xmon_xive_do_dump(int cpu) { struct xive_cpu *xc = per_cpu(xive_cpu, cpu); - xmon_printf("XIVE state for CPU %d:\n", cpu); - xmon_printf(" pp=%02x cppr=%02x\n", xc->pending_prio, xc->cppr); - xive_dump_eq("IRQ", &xc->queue[xive_irq_priority]); + xmon_printf("CPU %d:", cpu); + if (xc) { + xmon_printf("pp=%02x CPPR=%02x ", xc->pending_prio, xc->cppr); + #ifdef CONFIG_SMP - { - u64 val = xive_esb_read(&xc->ipi_data, XIVE_ESB_GET); - xmon_printf(" IPI state: %x:%c%c\n", xc->hw_ipi, - val & XIVE_ESB_VAL_P ? 'P' : 'p', - val & XIVE_ESB_VAL_Q ? 'Q' : 'q'); - } + { + u64 val = xive_esb_read(&xc->ipi_data, XIVE_ESB_GET); + + xmon_printf("IPI=0x%08x PQ=%c%c ", xc->hw_ipi, + val & XIVE_ESB_VAL_P ? 'P' : '-', + val & XIVE_ESB_VAL_Q ? 'Q' : '-'); + } #endif + xive_dump_eq("EQ", &xc->queue[xive_irq_priority]); + } + xmon_printf("\n"); +} + +int xmon_xive_get_irq_config(u32 hw_irq, struct irq_data *d) +{ + int rc; + u32 target; + u8 prio; + u32 lirq; + + rc = xive_ops->get_irq_config(hw_irq, &target, &prio, &lirq); + if (rc) { + xmon_printf("IRQ 0x%08x : no config rc=%d\n", hw_irq, rc); + return rc; + } + + xmon_printf("IRQ 0x%08x : target=0x%x prio=%02x lirq=0x%x ", + hw_irq, target, prio, lirq); + + if (d) { + struct xive_irq_data *xd = irq_data_get_irq_handler_data(d); + u64 val = xive_esb_read(xd, XIVE_ESB_GET); + + xmon_printf("PQ=%c%c", + val & XIVE_ESB_VAL_P ? 'P' : '-', + val & XIVE_ESB_VAL_Q ? 'Q' : '-'); + } + + xmon_printf("\n"); + return 0; } + #endif /* CONFIG_XMON */ static unsigned int xive_get_irq(void) @@ -307,6 +353,7 @@ static void xive_do_queue_eoi(struct xive_cpu *xc) */ static void xive_do_source_eoi(u32 hw_irq, struct xive_irq_data *xd) { + xd->stale_p = false; /* If the XIVE supports the new "store EOI facility, use it */ if (xd->flags & XIVE_IRQ_FLAG_STORE_EOI) xive_esb_write(xd, XIVE_ESB_STORE_EOI, 0); @@ -350,7 +397,7 @@ static void xive_do_source_eoi(u32 hw_irq, struct xive_irq_data *xd) } } -/* irq_chip eoi callback */ +/* irq_chip eoi callback, called with irq descriptor lock held */ static void xive_irq_eoi(struct irq_data *d) { struct xive_irq_data *xd = irq_data_get_irq_handler_data(d); @@ -366,6 +413,8 @@ static void xive_irq_eoi(struct irq_data *d) if (!irqd_irq_disabled(d) && !irqd_is_forwarded_to_vcpu(d) && !(xd->flags & XIVE_IRQ_NO_EOI)) xive_do_source_eoi(irqd_to_hwirq(d), xd); + else + xd->stale_p = true; /* * Clear saved_p to indicate that it's no longer occupying @@ -397,11 +446,16 @@ static void xive_do_source_set_mask(struct xive_irq_data *xd, */ if (mask) { val = xive_esb_read(xd, XIVE_ESB_SET_PQ_01); - xd->saved_p = !!(val & XIVE_ESB_VAL_P); - } else if (xd->saved_p) + if (!xd->stale_p && !!(val & XIVE_ESB_VAL_P)) + xd->saved_p = true; + xd->stale_p = false; + } else if (xd->saved_p) { xive_esb_read(xd, XIVE_ESB_SET_PQ_10); - else + xd->saved_p = false; + } else { xive_esb_read(xd, XIVE_ESB_SET_PQ_00); + xd->stale_p = false; + } } /* @@ -541,6 +595,8 @@ static unsigned int xive_irq_startup(struct irq_data *d) unsigned int hw_irq = (unsigned int)irqd_to_hwirq(d); int target, rc; + xd->saved_p = false; + xd->stale_p = false; pr_devel("xive_irq_startup: irq %d [0x%x] data @%p\n", d->irq, hw_irq, d); @@ -587,6 +643,7 @@ static unsigned int xive_irq_startup(struct irq_data *d) return 0; } +/* called with irq descriptor lock held */ static void xive_irq_shutdown(struct irq_data *d) { struct xive_irq_data *xd = irq_data_get_irq_handler_data(d); @@ -602,16 +659,6 @@ static void xive_irq_shutdown(struct irq_data *d) xive_do_source_set_mask(xd, true); /* - * The above may have set saved_p. We clear it otherwise it - * will prevent re-enabling later on. It is ok to forget the - * fact that the interrupt might be in a queue because we are - * accounting that already in xive_dec_target_count() and will - * be re-routing it to a new queue with proper accounting when - * it's started up again - */ - xd->saved_p = false; - - /* * Mask the interrupt in HW in the IVT/EAS and set the number * to be the "bad" IRQ number */ @@ -797,6 +844,10 @@ static int xive_irq_retrigger(struct irq_data *d) return 1; } +/* + * Caller holds the irq descriptor lock, so this won't be called + * concurrently with xive_get_irqchip_state on the same interrupt. + */ static int xive_irq_set_vcpu_affinity(struct irq_data *d, void *state) { struct xive_irq_data *xd = irq_data_get_irq_handler_data(d); @@ -820,6 +871,10 @@ static int xive_irq_set_vcpu_affinity(struct irq_data *d, void *state) /* Set it to PQ=10 state to prevent further sends */ pq = xive_esb_read(xd, XIVE_ESB_SET_PQ_10); + if (!xd->stale_p) { + xd->saved_p = !!(pq & XIVE_ESB_VAL_P); + xd->stale_p = !xd->saved_p; + } /* No target ? nothing to do */ if (xd->target == XIVE_INVALID_TARGET) { @@ -827,7 +882,7 @@ static int xive_irq_set_vcpu_affinity(struct irq_data *d, void *state) * An untargetted interrupt should have been * also masked at the source */ - WARN_ON(pq & 2); + WARN_ON(xd->saved_p); return 0; } @@ -847,9 +902,8 @@ static int xive_irq_set_vcpu_affinity(struct irq_data *d, void *state) * This saved_p is cleared by the host EOI, when we know * for sure the queue slot is no longer in use. */ - if (pq & 2) { - pq = xive_esb_read(xd, XIVE_ESB_SET_PQ_11); - xd->saved_p = true; + if (xd->saved_p) { + xive_esb_read(xd, XIVE_ESB_SET_PQ_11); /* * Sync the XIVE source HW to ensure the interrupt @@ -862,8 +916,7 @@ static int xive_irq_set_vcpu_affinity(struct irq_data *d, void *state) */ if (xive_ops->sync_source) xive_ops->sync_source(hw_irq); - } else - xd->saved_p = false; + } } else { irqd_clr_forwarded_to_vcpu(d); @@ -914,6 +967,23 @@ static int xive_irq_set_vcpu_affinity(struct irq_data *d, void *state) return 0; } +/* Called with irq descriptor lock held. */ +static int xive_get_irqchip_state(struct irq_data *data, + enum irqchip_irq_state which, bool *state) +{ + struct xive_irq_data *xd = irq_data_get_irq_handler_data(data); + + switch (which) { + case IRQCHIP_STATE_ACTIVE: + *state = !xd->stale_p && + (xd->saved_p || + !!(xive_esb_read(xd, XIVE_ESB_GET) & XIVE_ESB_VAL_P)); + return 0; + default: + return -EINVAL; + } +} + static struct irq_chip xive_irq_chip = { .name = "XIVE-IRQ", .irq_startup = xive_irq_startup, @@ -925,6 +995,7 @@ static struct irq_chip xive_irq_chip = { .irq_set_type = xive_irq_set_type, .irq_retrigger = xive_irq_retrigger, .irq_set_vcpu_affinity = xive_irq_set_vcpu_affinity, + .irq_get_irqchip_state = xive_get_irqchip_state, }; bool is_xive_irq(struct irq_chip *chip) @@ -1338,6 +1409,11 @@ static void xive_flush_cpu_queue(unsigned int cpu, struct xive_cpu *xc) xd = irq_desc_get_handler_data(desc); /* + * Clear saved_p to indicate that it's no longer pending + */ + xd->saved_p = false; + + /* * For LSIs, we EOI, this will cause a resend if it's * still asserted. Otherwise do an MSI retrigger. */ diff --git a/arch/powerpc/sysdev/xive/native.c b/arch/powerpc/sysdev/xive/native.c index 2f26b74f6cfa..0ff6b739052c 100644 --- a/arch/powerpc/sysdev/xive/native.c +++ b/arch/powerpc/sysdev/xive/native.c @@ -111,6 +111,20 @@ int xive_native_configure_irq(u32 hw_irq, u32 target, u8 prio, u32 sw_irq) } EXPORT_SYMBOL_GPL(xive_native_configure_irq); +static int xive_native_get_irq_config(u32 hw_irq, u32 *target, u8 *prio, + u32 *sw_irq) +{ + s64 rc; + __be64 vp; + __be32 lirq; + + rc = opal_xive_get_irq_config(hw_irq, &vp, prio, &lirq); + + *target = be64_to_cpu(vp); + *sw_irq = be32_to_cpu(lirq); + + return rc == 0 ? 0 : -ENXIO; +} /* This can be called multiple time to change a queue configuration */ int xive_native_configure_queue(u32 vp_id, struct xive_q *q, u8 prio, @@ -231,6 +245,17 @@ static bool xive_native_match(struct device_node *node) return of_device_is_compatible(node, "ibm,opal-xive-vc"); } +static s64 opal_xive_allocate_irq(u32 chip_id) +{ + s64 irq = opal_xive_allocate_irq_raw(chip_id); + + /* + * Old versions of skiboot can incorrectly return 0xffffffff to + * indicate no space, fix it up here. + */ + return irq == 0xffffffff ? OPAL_RESOURCE : irq; +} + #ifdef CONFIG_SMP static int xive_native_get_ipi(unsigned int cpu, struct xive_cpu *xc) { @@ -442,6 +467,7 @@ EXPORT_SYMBOL_GPL(xive_native_sync_queue); static const struct xive_ops xive_native_ops = { .populate_irq_data = xive_native_populate_irq_data, .configure_irq = xive_native_configure_irq, + .get_irq_config = xive_native_get_irq_config, .setup_queue = xive_native_setup_queue, .cleanup_queue = xive_native_cleanup_queue, .match = xive_native_match, @@ -800,6 +826,13 @@ int xive_native_set_queue_state(u32 vp_id, u32 prio, u32 qtoggle, u32 qindex) } EXPORT_SYMBOL_GPL(xive_native_set_queue_state); +bool xive_native_has_queue_state_support(void) +{ + return opal_check_token(OPAL_XIVE_GET_QUEUE_STATE) && + opal_check_token(OPAL_XIVE_SET_QUEUE_STATE); +} +EXPORT_SYMBOL_GPL(xive_native_has_queue_state_support); + int xive_native_get_vp_state(u32 vp_id, u64 *out_state) { __be64 state; diff --git a/arch/powerpc/sysdev/xive/spapr.c b/arch/powerpc/sysdev/xive/spapr.c index 8ef9cf4ebb1c..33c10749edec 100644 --- a/arch/powerpc/sysdev/xive/spapr.c +++ b/arch/powerpc/sysdev/xive/spapr.c @@ -45,7 +45,7 @@ static int xive_irq_bitmap_add(int base, int count) { struct xive_irq_bitmap *xibm; - xibm = kzalloc(sizeof(*xibm), GFP_ATOMIC); + xibm = kzalloc(sizeof(*xibm), GFP_KERNEL); if (!xibm) return -ENOMEM; @@ -53,6 +53,10 @@ static int xive_irq_bitmap_add(int base, int count) xibm->base = base; xibm->count = count; xibm->bitmap = kzalloc(xibm->count, GFP_KERNEL); + if (!xibm->bitmap) { + kfree(xibm); + return -ENOMEM; + } list_add(&xibm->list, &xive_irq_bitmaps); pr_info("Using IRQ range [%x-%x]", xibm->base, @@ -211,6 +215,38 @@ static long plpar_int_set_source_config(unsigned long flags, return 0; } +static long plpar_int_get_source_config(unsigned long flags, + unsigned long lisn, + unsigned long *target, + unsigned long *prio, + unsigned long *sw_irq) +{ + unsigned long retbuf[PLPAR_HCALL_BUFSIZE]; + long rc; + + pr_devel("H_INT_GET_SOURCE_CONFIG flags=%lx lisn=%lx\n", flags, lisn); + + do { + rc = plpar_hcall(H_INT_GET_SOURCE_CONFIG, retbuf, flags, lisn, + target, prio, sw_irq); + } while (plpar_busy_delay(rc)); + + if (rc) { + pr_err("H_INT_GET_SOURCE_CONFIG lisn=%ld failed %ld\n", + lisn, rc); + return rc; + } + + *target = retbuf[0]; + *prio = retbuf[1]; + *sw_irq = retbuf[2]; + + pr_devel("H_INT_GET_SOURCE_CONFIG target=%lx prio=%lx sw_irq=%lx\n", + retbuf[0], retbuf[1], retbuf[2]); + + return 0; +} + static long plpar_int_get_queue_info(unsigned long flags, unsigned long target, unsigned long priority, @@ -394,6 +430,24 @@ static int xive_spapr_configure_irq(u32 hw_irq, u32 target, u8 prio, u32 sw_irq) return rc == 0 ? 0 : -ENXIO; } +static int xive_spapr_get_irq_config(u32 hw_irq, u32 *target, u8 *prio, + u32 *sw_irq) +{ + long rc; + unsigned long h_target; + unsigned long h_prio; + unsigned long h_sw_irq; + + rc = plpar_int_get_source_config(0, hw_irq, &h_target, &h_prio, + &h_sw_irq); + + *target = h_target; + *prio = h_prio; + *sw_irq = h_sw_irq; + + return rc == 0 ? 0 : -ENXIO; +} + /* This can be called multiple time to change a queue configuration */ static int xive_spapr_configure_queue(u32 target, struct xive_q *q, u8 prio, __be32 *qpage, u32 order) @@ -586,6 +640,7 @@ static void xive_spapr_sync_source(u32 hw_irq) static const struct xive_ops xive_spapr_ops = { .populate_irq_data = xive_spapr_populate_irq_data, .configure_irq = xive_spapr_configure_irq, + .get_irq_config = xive_spapr_get_irq_config, .setup_queue = xive_spapr_setup_queue, .cleanup_queue = xive_spapr_cleanup_queue, .match = xive_spapr_match, diff --git a/arch/powerpc/sysdev/xive/xive-internal.h b/arch/powerpc/sysdev/xive/xive-internal.h index 211725dbf364..59cd366e7933 100644 --- a/arch/powerpc/sysdev/xive/xive-internal.h +++ b/arch/powerpc/sysdev/xive/xive-internal.h @@ -33,6 +33,8 @@ struct xive_cpu { struct xive_ops { int (*populate_irq_data)(u32 hw_irq, struct xive_irq_data *data); int (*configure_irq)(u32 hw_irq, u32 target, u8 prio, u32 sw_irq); + int (*get_irq_config)(u32 hw_irq, u32 *target, u8 *prio, + u32 *sw_irq); int (*setup_queue)(unsigned int cpu, struct xive_cpu *xc, u8 prio); void (*cleanup_queue)(unsigned int cpu, struct xive_cpu *xc, u8 prio); void (*setup_cpu)(unsigned int cpu, struct xive_cpu *xc); diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index 14e56c25879f..d83364ebc5c5 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -2534,13 +2534,16 @@ static void dump_pacas(void) static void dump_one_xive(int cpu) { unsigned int hwid = get_hard_smp_processor_id(cpu); - - opal_xive_dump(XIVE_DUMP_TM_HYP, hwid); - opal_xive_dump(XIVE_DUMP_TM_POOL, hwid); - opal_xive_dump(XIVE_DUMP_TM_OS, hwid); - opal_xive_dump(XIVE_DUMP_TM_USER, hwid); - opal_xive_dump(XIVE_DUMP_VP, hwid); - opal_xive_dump(XIVE_DUMP_EMU_STATE, hwid); + bool hv = cpu_has_feature(CPU_FTR_HVMODE); + + if (hv) { + opal_xive_dump(XIVE_DUMP_TM_HYP, hwid); + opal_xive_dump(XIVE_DUMP_TM_POOL, hwid); + opal_xive_dump(XIVE_DUMP_TM_OS, hwid); + opal_xive_dump(XIVE_DUMP_TM_USER, hwid); + opal_xive_dump(XIVE_DUMP_VP, hwid); + opal_xive_dump(XIVE_DUMP_EMU_STATE, hwid); + } if (setjmp(bus_error_jmp) != 0) { catch_memory_errors = 0; @@ -2569,16 +2572,28 @@ static void dump_all_xives(void) dump_one_xive(cpu); } -static void dump_one_xive_irq(u32 num) +static void dump_one_xive_irq(u32 num, struct irq_data *d) +{ + xmon_xive_get_irq_config(num, d); +} + +static void dump_all_xive_irq(void) { - s64 rc; - __be64 vp; - u8 prio; - __be32 lirq; - - rc = opal_xive_get_irq_config(num, &vp, &prio, &lirq); - xmon_printf("IRQ 0x%x config: vp=0x%llx prio=%d lirq=0x%x (rc=%lld)\n", - num, be64_to_cpu(vp), prio, be32_to_cpu(lirq), rc); + unsigned int i; + struct irq_desc *desc; + + for_each_irq_desc(i, desc) { + struct irq_data *d = irq_desc_get_irq_data(desc); + unsigned int hwirq; + + if (!d) + continue; + + hwirq = (unsigned int)irqd_to_hwirq(d); + /* IPIs are special (HW number 0) */ + if (hwirq) + dump_one_xive_irq(hwirq, d); + } } static void dump_xives(void) @@ -2597,7 +2612,9 @@ static void dump_xives(void) return; } else if (c == 'i') { if (scanhex(&num)) - dump_one_xive_irq(num); + dump_one_xive_irq(num, NULL); + else + dump_all_xive_irq(); return; } |