diff options
Diffstat (limited to 'arch/powerpc/kernel')
72 files changed, 3591 insertions, 2883 deletions
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 0ea6c4aa3a20..a7ca8fe62368 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -52,10 +52,11 @@ 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 +obj-$(CONFIG_PPC_DAWR) += dawr.o obj-$(CONFIG_PPC_BOOK3S_64) += cpu_setup_ppc970.o cpu_setup_pa6t.o obj-$(CONFIG_PPC_BOOK3S_64) += cpu_setup_power.o obj-$(CONFIG_PPC_BOOK3S_64) += mce.o mce_power.o @@ -77,7 +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-$(CONFIG_E500) += idle_e500.o endif @@ -154,6 +157,9 @@ endif obj-$(CONFIG_EPAPR_PARAVIRT) += epapr_paravirt.o epapr_hcalls.o obj-$(CONFIG_KVM_GUEST) += kvm.o kvm_emul.o +ifneq ($(CONFIG_PPC_POWERNV)$(CONFIG_PPC_SVM),) +obj-y += ucall.o +endif # Disable GCOV, KCOV & sanitizers in odd or sensitive code GCOV_PROFILE_prom_init.o := n @@ -183,15 +189,13 @@ extra-$(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/align.c b/arch/powerpc/kernel/align.c index 7107ad86de65..92045ed64976 100644 --- a/arch/powerpc/kernel/align.c +++ b/arch/powerpc/kernel/align.c @@ -176,9 +176,11 @@ static int emulate_spe(struct pt_regs *regs, unsigned int reg, ret |= __get_user_inatomic(temp.v[1], p++); ret |= __get_user_inatomic(temp.v[2], p++); ret |= __get_user_inatomic(temp.v[3], p++); + /* fall through */ case 4: ret |= __get_user_inatomic(temp.v[4], p++); ret |= __get_user_inatomic(temp.v[5], p++); + /* fall through */ case 2: ret |= __get_user_inatomic(temp.v[6], p++); ret |= __get_user_inatomic(temp.v[7], p++); @@ -259,9 +261,11 @@ static int emulate_spe(struct pt_regs *regs, unsigned int reg, ret |= __put_user_inatomic(data.v[1], p++); ret |= __put_user_inatomic(data.v[2], p++); ret |= __put_user_inatomic(data.v[3], p++); + /* fall through */ case 4: ret |= __put_user_inatomic(data.v[4], p++); ret |= __put_user_inatomic(data.v[5], p++); + /* fall through */ case 2: ret |= __put_user_inatomic(data.v[6], p++); ret |= __put_user_inatomic(data.v[7], p++); diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 31dc7e64cbfc..484f54dab247 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -266,7 +266,9 @@ int main(void) OFFSET(ACCOUNT_STARTTIME_USER, paca_struct, accounting.starttime_user); OFFSET(ACCOUNT_USER_TIME, paca_struct, accounting.utime); OFFSET(ACCOUNT_SYSTEM_TIME, paca_struct, accounting.stime); +#ifdef CONFIG_PPC_BOOK3E OFFSET(PACA_TRAP_SAVE, paca_struct, trap_save); +#endif OFFSET(PACA_SPRG_VDSO, paca_struct, sprg_vdso); #else /* CONFIG_PPC64 */ #ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE @@ -504,6 +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/cacheinfo.c b/arch/powerpc/kernel/cacheinfo.c index 9fbb9d12e0c0..470336277c67 100644 --- a/arch/powerpc/kernel/cacheinfo.c +++ b/arch/powerpc/kernel/cacheinfo.c @@ -891,4 +891,25 @@ void cacheinfo_cpu_offline(unsigned int cpu_id) if (cache) cache_cpu_clear(cache, cpu_id); } + +void cacheinfo_teardown(void) +{ + unsigned int cpu; + + lockdep_assert_cpus_held(); + + for_each_online_cpu(cpu) + cacheinfo_cpu_offline(cpu); +} + +void cacheinfo_rebuild(void) +{ + unsigned int cpu; + + lockdep_assert_cpus_held(); + + for_each_online_cpu(cpu) + cacheinfo_cpu_online(cpu); +} + #endif /* (CONFIG_PPC_PSERIES && CONFIG_SUSPEND) || CONFIG_HOTPLUG_CPU */ diff --git a/arch/powerpc/kernel/cacheinfo.h b/arch/powerpc/kernel/cacheinfo.h index 955f5e999f1b..52bd3fc6642d 100644 --- a/arch/powerpc/kernel/cacheinfo.h +++ b/arch/powerpc/kernel/cacheinfo.h @@ -6,4 +6,8 @@ extern void cacheinfo_cpu_online(unsigned int cpu_id); extern void cacheinfo_cpu_offline(unsigned int cpu_id); +/* Allow migration/suspend to tear down and rebuild the hierarchy. */ +extern void cacheinfo_teardown(void); +extern void cacheinfo_rebuild(void); + #endif /* _PPC_CACHEINFO_H */ diff --git a/arch/powerpc/kernel/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/dawr.c b/arch/powerpc/kernel/dawr.c new file mode 100644 index 000000000000..5f66b95b6858 --- /dev/null +++ b/arch/powerpc/kernel/dawr.c @@ -0,0 +1,101 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * DAWR infrastructure + * + * Copyright 2019, Michael Neuling, IBM Corporation. + */ + +#include <linux/types.h> +#include <linux/export.h> +#include <linux/fs.h> +#include <linux/debugfs.h> +#include <asm/debugfs.h> +#include <asm/machdep.h> +#include <asm/hvcall.h> + +bool dawr_force_enable; +EXPORT_SYMBOL_GPL(dawr_force_enable); + +int set_dawr(struct arch_hw_breakpoint *brk) +{ + unsigned long dawr, dawrx, mrd; + + dawr = brk->address; + + dawrx = (brk->type & (HW_BRK_TYPE_READ | HW_BRK_TYPE_WRITE)) + << (63 - 58); + dawrx |= ((brk->type & (HW_BRK_TYPE_TRANSLATE)) >> 2) << (63 - 59); + dawrx |= (brk->type & (HW_BRK_TYPE_PRIV_ALL)) >> 3; + /* + * DAWR length is stored in field MDR bits 48:53. Matches range in + * doublewords (64 bits) baised by -1 eg. 0b000000=1DW and + * 0b111111=64DW. + * brk->len is in bytes. + * This aligns up to double word size, shifts and does the bias. + */ + mrd = ((brk->len + 7) >> 3) - 1; + dawrx |= (mrd & 0x3f) << (63 - 53); + + if (ppc_md.set_dawr) + return ppc_md.set_dawr(dawr, dawrx); + + mtspr(SPRN_DAWR, dawr); + mtspr(SPRN_DAWRX, dawrx); + + return 0; +} + +static void set_dawr_cb(void *info) +{ + set_dawr(info); +} + +static ssize_t dawr_write_file_bool(struct file *file, + const char __user *user_buf, + size_t count, loff_t *ppos) +{ + struct arch_hw_breakpoint null_brk = {0, 0, 0}; + size_t rc; + + /* Send error to user if they hypervisor won't allow us to write DAWR */ + if (!dawr_force_enable && + firmware_has_feature(FW_FEATURE_LPAR) && + set_dawr(&null_brk) != H_SUCCESS) + return -ENODEV; + + rc = debugfs_write_file_bool(file, user_buf, count, ppos); + if (rc) + return rc; + + /* If we are clearing, make sure all CPUs have the DAWR cleared */ + if (!dawr_force_enable) + smp_call_function(set_dawr_cb, &null_brk, 0); + + return rc; +} + +static const struct file_operations dawr_enable_fops = { + .read = debugfs_read_file_bool, + .write = dawr_write_file_bool, + .open = simple_open, + .llseek = default_llseek, +}; + +static int __init dawr_force_setup(void) +{ + if (cpu_has_feature(CPU_FTR_DAWR)) { + /* Don't setup sysfs file for user control on P8 */ + dawr_force_enable = true; + return 0; + } + + if (PVR_VER(mfspr(SPRN_PVR)) == PVR_POWER9) { + /* Turn DAWR off by default, but allow admin to turn it on */ + debugfs_create_file_unsafe("dawr_enable_dangerous", 0600, + powerpc_debugfs_root, + &dawr_force_enable, + &dawr_enable_fops); + } + return 0; +} +arch_initcall(dawr_force_setup); diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c index 09231ef06d01..e486d1d78de2 100644 --- a/arch/powerpc/kernel/dma-iommu.c +++ b/arch/powerpc/kernel/dma-iommu.c @@ -71,7 +71,7 @@ static dma_addr_t dma_iommu_map_page(struct device *dev, struct page *page, return dma_direct_map_page(dev, page, offset, size, direction, attrs); return iommu_map_page(dev, get_iommu_table_base(dev), page, offset, - size, device_to_mask(dev), direction, attrs); + size, dma_get_mask(dev), direction, attrs); } @@ -82,6 +82,8 @@ static void dma_iommu_unmap_page(struct device *dev, dma_addr_t dma_handle, if (!dma_iommu_map_bypass(dev, attrs)) iommu_unmap_page(get_iommu_table_base(dev), dma_handle, size, direction, attrs); + else + dma_direct_unmap_page(dev, dma_handle, size, direction, attrs); } @@ -92,7 +94,7 @@ static int dma_iommu_map_sg(struct device *dev, struct scatterlist *sglist, if (dma_iommu_map_bypass(dev, attrs)) return dma_direct_map_sg(dev, sglist, nelems, direction, attrs); return ppc_iommu_map_sg(dev, get_iommu_table_base(dev), sglist, nelems, - device_to_mask(dev), direction, attrs); + dma_get_mask(dev), direction, attrs); } static void dma_iommu_unmap_sg(struct device *dev, struct scatterlist *sglist, @@ -102,6 +104,8 @@ static void dma_iommu_unmap_sg(struct device *dev, struct scatterlist *sglist, if (!dma_iommu_map_bypass(dev, attrs)) ppc_iommu_unmap_sg(get_iommu_table_base(dev), sglist, nelems, direction, attrs); + else + dma_direct_unmap_sg(dev, sglist, nelems, direction, attrs); } static bool dma_iommu_bypass_supported(struct device *dev, u64 mask) @@ -118,18 +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", @@ -163,6 +166,34 @@ u64 dma_iommu_get_required_mask(struct device *dev) return mask; } +static void dma_iommu_sync_for_cpu(struct device *dev, dma_addr_t addr, + size_t size, enum dma_data_direction dir) +{ + if (dma_iommu_alloc_bypass(dev)) + dma_direct_sync_single_for_cpu(dev, addr, size, dir); +} + +static void dma_iommu_sync_for_device(struct device *dev, dma_addr_t addr, + size_t sz, enum dma_data_direction dir) +{ + if (dma_iommu_alloc_bypass(dev)) + dma_direct_sync_single_for_device(dev, addr, sz, dir); +} + +extern void dma_iommu_sync_sg_for_cpu(struct device *dev, + struct scatterlist *sgl, int nents, enum dma_data_direction dir) +{ + if (dma_iommu_alloc_bypass(dev)) + dma_direct_sync_sg_for_cpu(dev, sgl, nents, dir); +} + +extern void dma_iommu_sync_sg_for_device(struct device *dev, + struct scatterlist *sgl, int nents, enum dma_data_direction dir) +{ + if (dma_iommu_alloc_bypass(dev)) + dma_direct_sync_sg_for_device(dev, sgl, nents, dir); +} + const struct dma_map_ops dma_iommu_ops = { .alloc = dma_iommu_alloc_coherent, .free = dma_iommu_free_coherent, @@ -172,4 +203,10 @@ const struct dma_map_ops dma_iommu_ops = { .map_page = dma_iommu_map_page, .unmap_page = dma_iommu_unmap_page, .get_required_mask = dma_iommu_get_required_mask, + .sync_single_for_cpu = dma_iommu_sync_for_cpu, + .sync_single_for_device = dma_iommu_sync_for_device, + .sync_sg_for_cpu = dma_iommu_sync_sg_for_cpu, + .sync_sg_for_device = dma_iommu_sync_sg_for_device, + .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 f192d57db47d..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 @@ -354,10 +364,19 @@ static inline unsigned long eeh_token_to_phys(unsigned long token) ptep = find_init_mm_pte(token, &hugepage_shift); if (!ptep) return token; - WARN_ON(hugepage_shift); - pa = pte_pfn(*ptep) << PAGE_SHIFT; - return pa | (token & (PAGE_SIZE-1)); + pa = pte_pfn(*ptep); + + /* On radix we can do hugepage mappings for io, so handle that */ + if (hugepage_shift) { + pa <<= hugepage_shift; + pa |= token & ((1ul << hugepage_shift) - 1); + } else { + pa <<= PAGE_SHIFT; + pa |= token & (PAGE_SIZE - 1); + } + + return pa; } /* @@ -401,11 +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); @@ -432,7 +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; @@ -451,8 +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; } @@ -492,12 +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(); } @@ -564,13 +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; @@ -688,7 +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); @@ -699,7 +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); @@ -712,18 +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) @@ -732,8 +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) @@ -859,7 +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; @@ -867,8 +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) @@ -1054,23 +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 * @@ -1111,6 +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(); } @@ -1181,15 +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; } @@ -1237,6 +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) { @@ -1290,10 +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; } @@ -1881,6 +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) @@ -1896,6 +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 320472373122..cf11277ebd02 100644 --- a/arch/powerpc/kernel/eeh_cache.c +++ b/arch/powerpc/kernel/eeh_cache.c @@ -18,6 +18,8 @@ /** + * DOC: Overview + * * The pci address cache subsystem. This subsystem places * PCI device address resources into a red-black tree, sorted * according to the address range, so that given only an i/o @@ -34,6 +36,7 @@ * than any hash algo I could think of for this problem, even * with the penalty of slow pointer chases for d-cache misses). */ + struct pci_io_addr_range { struct rb_node rb_node; resource_size_t addr_lo; @@ -145,8 +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); @@ -226,8 +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; @@ -255,37 +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 85fdb6d879f1..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) @@ -597,6 +597,14 @@ ppc_clone: stw r0,_TRAP(r1) /* register set saved */ b sys_clone + .globl ppc_clone3 +ppc_clone3: + SAVE_NVGPRS(r1) + lwz r0,_TRAP(r1) + rlwinm r0,r0,0,0,30 /* clear LSB to indicate full */ + stw r0,_TRAP(r1) /* register set saved */ + b sys_clone3 + .globl ppc_swapcontext ppc_swapcontext: SAVE_NVGPRS(r1) @@ -769,11 +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) @@ -792,9 +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 @@ -816,7 +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 */ @@ -983,7 +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 @@ -1058,7 +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); \ @@ -1228,7 +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) @@ -1262,11 +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 @@ -1275,9 +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 @@ -1321,7 +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 d9105fcf4021..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 @@ -487,6 +478,11 @@ _GLOBAL(ppc_clone) bl sys_clone b .Lsyscall_exit +_GLOBAL(ppc_clone3) + bl save_nvgprs + bl sys_clone3 + b .Lsyscall_exit + _GLOBAL(ppc32_swapcontext) bl save_nvgprs bl compat_sys_swapcontext 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 73ba246ca11d..d0018dd17e0a 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -21,6 +21,677 @@ #include <asm/feature-fixups.h> #include <asm/kup.h> +/* PACA save area offsets (exgen, exmc, etc) */ +#define EX_R9 0 +#define EX_R10 8 +#define EX_R11 16 +#define EX_R12 24 +#define EX_R13 32 +#define EX_DAR 40 +#define EX_DSISR 48 +#define EX_CCR 52 +#define EX_CFAR 56 +#define EX_PPR 64 +#if defined(CONFIG_RELOCATABLE) +#define EX_CTR 72 +.if EX_SIZE != 10 + .error "EX_SIZE is wrong" +.endif +#else +.if EX_SIZE != 9 + .error "EX_SIZE is wrong" +.endif +#endif + +/* + * 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 + * part of label. This requires that the label be within 64KB of kernelbase, and + * that kernelbase be 64K aligned. + */ +#define LOAD_HANDLER(reg, label) \ + ld reg,PACAKBASE(r13); /* get high part of &label */ \ + ori reg,reg,FIXED_SYMBOL_ABS_ADDR(label) + +#define __LOAD_HANDLER(reg, label) \ + ld reg,PACAKBASE(r13); \ + ori reg,reg,(ABS_ADDR(label))@l + +/* + * Branches from unrelocated code (e.g., interrupts) to labels outside + * head-y require >64K offsets. + */ +#define __LOAD_FAR_HANDLER(reg, label) \ + ld reg,PACAKBASE(r13); \ + ori reg,reg,(ABS_ADDR(label))@l; \ + addis reg,reg,(ABS_ADDR(label))@h + +/* Exception register prefixes */ +#define EXC_HV_OR_STD 2 /* depends on HVMODE */ +#define EXC_HV 1 +#define EXC_STD 0 + +#if defined(CONFIG_RELOCATABLE) +/* + * If we support interrupts with relocation on AND we're a relocatable kernel, + * we need to use CTR to get to the 2nd level handler. So, save/restore it + * when required. + */ +#define SAVE_CTR(reg, area) mfctr reg ; std reg,area+EX_CTR(r13) +#define GET_CTR(reg, area) ld reg,area+EX_CTR(r13) +#define RESTORE_CTR(reg, area) ld reg,area+EX_CTR(r13) ; mtctr reg +#else +/* ...else CTR is unused and in register. */ +#define SAVE_CTR(reg, area) +#define GET_CTR(reg, area) mfctr reg +#define RESTORE_CTR(reg, area) +#endif + +/* + * PPR save/restore macros used in exceptions-64s.S + * Used for P7 or later processors + */ +#define SAVE_PPR(area, ra) \ +BEGIN_FTR_SECTION_NESTED(940) \ + ld ra,area+EX_PPR(r13); /* Read PPR from paca */ \ + std ra,_PPR(r1); \ +END_FTR_SECTION_NESTED(CPU_FTR_HAS_PPR,CPU_FTR_HAS_PPR,940) + +#define RESTORE_PPR_PACA(area, ra) \ +BEGIN_FTR_SECTION_NESTED(941) \ + ld ra,area+EX_PPR(r13); \ + mtspr SPRN_PPR,ra; \ +END_FTR_SECTION_NESTED(CPU_FTR_HAS_PPR,CPU_FTR_HAS_PPR,941) + +/* + * Get an SPR into a register if the CPU has the given feature + */ +#define OPT_GET_SPR(ra, spr, ftr) \ +BEGIN_FTR_SECTION_NESTED(943) \ + mfspr ra,spr; \ +END_FTR_SECTION_NESTED(ftr,ftr,943) + +/* + * Set an SPR from a register if the CPU has the given feature + */ +#define OPT_SET_SPR(ra, spr, ftr) \ +BEGIN_FTR_SECTION_NESTED(943) \ + mtspr spr,ra; \ +END_FTR_SECTION_NESTED(ftr,ftr,943) + +/* + * Save a register to the PACA if the CPU has the given feature + */ +#define OPT_SAVE_REG_TO_PACA(offset, ra, ftr) \ +BEGIN_FTR_SECTION_NESTED(943) \ + std ra,offset(r13); \ +END_FTR_SECTION_NESTED(ftr,ftr,943) + +/* + * Branch to label using its 0xC000 address. This results in instruction + * address suitable for MSR[IR]=0 or 1, which allows relocation to be turned + * on using mtmsr rather than rfid. + * + * This could set the 0xc bits for !RELOCATABLE as an immediate, rather than + * load KBASE for a slight optimisation. + */ +#define BRANCH_TO_C000(reg, label) \ + __LOAD_FAR_HANDLER(reg, label); \ + mtctr reg; \ + bctr + +.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 +/* + * If hv is possible, interrupts come into to the hv version + * of the kvmppc_interrupt code, which then jumps to the PR handler, + * kvmppc_interrupt_pr, if the guest is a PR guest. + */ +#define kvmppc_interrupt kvmppc_interrupt_hv +#else +#define kvmppc_interrupt kvmppc_interrupt_pr +#endif + +.macro KVMTEST name, hsrr, n + lbz r10,HSTATE_IN_GUEST(r13) + cmpwi r10,0 + bne \name\()_kvm +.endm + +.macro KVM_HANDLER vec, hsrr, area, skip + .if \skip + cmpwi r10,KVM_GUEST_MODE_SKIP + beq 89f + .else +BEGIN_FTR_SECTION_NESTED(947) + ld r10,\area+EX_CFAR(r13) + std r10,HSTATE_CFAR(r13) +END_FTR_SECTION_NESTED(CPU_FTR_CFAR,CPU_FTR_CFAR,947) + .endif + +BEGIN_FTR_SECTION_NESTED(948) + ld r10,\area+EX_PPR(r13) + std r10,HSTATE_PPR(r13) +END_FTR_SECTION_NESTED(CPU_FTR_HAS_PPR,CPU_FTR_HAS_PPR,948) + ld r10,\area+EX_R10(r13) + std r12,HSTATE_SCRATCH0(r13) + sldi r12,r9,32 + /* HSRR variants have the 0x2 bit added to their trap number */ + .if \hsrr == 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,(\vec) + .endif + +#ifdef CONFIG_RELOCATABLE + /* + * KVM requires __LOAD_FAR_HANDLER beause kvmppc_interrupt lives + * outside the head section. CONFIG_RELOCATABLE KVM expects CTR + * to be saved in HSTATE_SCRATCH1. + */ + mfctr r9 + std r9,HSTATE_SCRATCH1(r13) + __LOAD_FAR_HANDLER(r9, kvmppc_interrupt) + mtctr r9 + ld r9,\area+EX_R9(r13) + bctr +#else + ld r9,\area+EX_R9(r13) + b kvmppc_interrupt +#endif + + + .if \skip +89: mtocrf 0x80,r9 + ld r9,\area+EX_R9(r13) + ld r10,\area+EX_R10(r13) + .if \hsrr == 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 + .endif + .endif +.endm + +#else +.macro KVMTEST name, hsrr, n +.endm +.macro KVM_HANDLER name, vec, hsrr, area, skip +.endm +#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 + +/* + * 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?) + */ +.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 + + .if \reconcile + RECONCILE_IRQ_STATE(r10, r11) + .endif +.endm + +/* + * Restore all registers including H/SRR0/1 saved in a stack frame of a + * standard exception. + */ +.macro EXCEPTION_RESTORE_REGS hsrr + /* Move original SRR0 and SRR1 into the respective regs */ + ld r9,_MSR(r1) + .if \hsrr == EXC_HV_OR_STD + .error "EXC_HV_OR_STD Not implemented for EXCEPTION_RESTORE_REGS" + .endif + .if \hsrr + mtspr SPRN_HSRR1,r9 + .else + mtspr SPRN_SRR1,r9 + .endif + ld r9,_NIP(r1) + .if \hsrr + mtspr SPRN_HSRR0,r9 + .else + mtspr SPRN_SRR0,r9 + .endif + ld r9,_CTR(r1) + mtctr r9 + ld r9,_XER(r1) + mtxer r9 + ld r9,_LINK(r1) + mtlr r9 + ld r9,_CCR(r1) + mtcr r9 + REST_8GPRS(2, r1) + REST_4GPRS(10, r1) + REST_GPR(0, r1) + /* restore original r1. */ + ld r1,GPR1(r1) +.endm + +#define RUNLATCH_ON \ +BEGIN_FTR_SECTION \ + ld r3, PACA_THREAD_INFO(r13); \ + ld r4,TI_LOCAL_FLAGS(r3); \ + andi. r0,r4,_TLF_RUNLATCH; \ + beql ppc64_runlatch_on_trampoline; \ +END_FTR_SECTION_IFSET(CPU_FTR_CTRL) + +/* + * When the idle code in power4_idle puts the CPU into NAP mode, + * it has to do so in a loop, and relies on the external interrupt + * and decrementer interrupt entry code to get it out of the loop. + * It sets the _TLF_NAPPING bit in current_thread_info()->local_flags + * to signal that it is in the loop and needs help to get out. + */ +#ifdef CONFIG_PPC_970_NAP +#define FINISH_NAP \ +BEGIN_FTR_SECTION \ + ld r11, PACA_THREAD_INFO(r13); \ + ld r9,TI_LOCAL_FLAGS(r11); \ + andi. r10,r9,_TLF_NAPPING; \ + bnel power4_fixup_nap; \ +END_FTR_SECTION_IFSET(CPU_FTR_CAN_NAP) +#else +#define FINISH_NAP +#endif + +#define EXC_COMMON(name, realvec, hdlr) \ + EXC_COMMON_BEGIN(name); \ + INT_COMMON realvec, PACA_EXGEN, 1, 1, 1, 0, 0 ; \ + bl save_nvgprs; \ + addi r3,r1,STACK_FRAME_OVERHEAD; \ + bl hdlr; \ + b ret_from_except + +/* + * Like EXC_COMMON, but for exceptions that can occur in the idle task and + * therefore need the special idle handling (finish nap and runlatch) + */ +#define EXC_COMMON_ASYNC(name, realvec, hdlr) \ + EXC_COMMON_BEGIN(name); \ + INT_COMMON realvec, PACA_EXGEN, 1, 1, 1, 0, 0 ; \ + FINISH_NAP; \ + RUNLATCH_ON; \ + addi r3,r1,STACK_FRAME_OVERHEAD; \ + bl hdlr; \ + b ret_from_except_lite + + /* * There are a few constraints to be concerned with. * - Real mode exceptions code/data must be located at their physical location. @@ -107,6 +778,7 @@ __start_interrupts: EXC_VIRT_NONE(0x4000, 0x100) +EXC_REAL_BEGIN(system_reset, 0x100, 0x100) #ifdef CONFIG_PPC_P7_NAP /* * If running native on arch 2.06 or later, check if we are waking up @@ -114,60 +786,67 @@ EXC_VIRT_NONE(0x4000, 0x100) * bits 46:47. A non-0 value indicates that we are coming from a power * saving state. The idle wakeup handler initially runs in real mode, * but we branch to the 0xc000... address so we can turn on relocation - * with mtmsr. + * with mtmsrd later, after SPRs are restored. + * + * Careful to minimise cost for the fast path (idle wakeup) while + * also avoiding clobbering CFAR for the debug path (non-idle). + * + * For the idle wake case volatile registers can be clobbered, which + * is why we use those initially. If it turns out to not be an idle + * wake, carefully put everything back the way it was, so we can use + * common exception macros to handle it. */ -#define IDLETEST(n) \ - BEGIN_FTR_SECTION ; \ - mfspr r10,SPRN_SRR1 ; \ - rlwinm. r10,r10,47-31,30,31 ; \ - beq- 1f ; \ - cmpwi cr1,r10,2 ; \ - mfspr r3,SPRN_SRR1 ; \ - bltlr cr1 ; /* no state loss, return to idle caller */ \ - BRANCH_TO_C000(r10, system_reset_idle_common) ; \ -1: \ - KVMTEST_PR(n) ; \ - END_FTR_SECTION_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206) -#else -#define IDLETEST NOTEST +BEGIN_FTR_SECTION + SET_SCRATCH0(r13) + GET_PACA(r13) + std r3,PACA_EXNMI+0*8(r13) + std r4,PACA_EXNMI+1*8(r13) + std r5,PACA_EXNMI+2*8(r13) + mfspr r3,SPRN_SRR1 + mfocrf r4,0x80 + rlwinm. r5,r3,47-31,30,31 + bne+ system_reset_idle_wake + /* Not powersave wakeup. Restore regs for regular interrupt handler. */ + mtocrf 0x80,r4 + ld r3,PACA_EXNMI+0*8(r13) + ld r4,PACA_EXNMI+1*8(r13) + ld r5,PACA_EXNMI+2*8(r13) + GET_SCRATCH0(r13) +END_FTR_SECTION_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206) #endif -EXC_REAL_BEGIN(system_reset, 0x100, 0x100) - SET_SCRATCH0(r13) + 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. + * + * In theory, we should not enable relocation here if it was disabled + * in SRR1, because the MMU may not be configured to support it (e.g., + * SLB may have been cleared). In practice, there should only be a few + * small windows where that's the case, and sreset is considered to + * be dangerous anyway. */ - EXCEPTION_PROLOG_NORI(PACA_EXNMI, system_reset_common, EXC_STD, - IDLETEST, 0x100) - EXC_REAL_END(system_reset, 0x100, 0x100) EXC_VIRT_NONE(0x4100, 0x100) -TRAMP_KVM(PACA_EXNMI, 0x100) +INT_KVM_HANDLER system_reset 0x100, EXC_STD, PACA_EXNMI, 0 #ifdef CONFIG_PPC_P7_NAP -EXC_COMMON_BEGIN(system_reset_idle_common) - /* - * This must be a direct branch (without linker branch stub) because - * we can not use TOC at this point as r2 may not be restored yet. - */ - b idle_return_gpr_loss +TRAMP_REAL_BEGIN(system_reset_idle_wake) + /* We are waking up from idle, so may clobber any volatile register */ + cmpwi cr1,r5,2 + bltlr cr1 /* no state loss, return to idle caller with r3=SRR1 */ + BRANCH_TO_C000(r12, DOTSYM(idle_return_gpr_loss)) #endif +#ifdef CONFIG_PPC_PSERIES /* - * Set IRQS_ALL_DISABLED unconditionally so arch_irqs_disabled does - * the right thing. We do not want to reconcile because that goes - * through irq tracing which we don't want in NMI. - * - * Save PACAIRQHAPPENED because some code will do a hard disable - * (e.g., xmon). So we want to restore this back to where it was - * when we return. DAR is unused in the stack, so save it there. + * Vectors for the FWNMI option. Share common code. */ -#define ADD_RECONCILE_NMI \ - li r10,IRQS_ALL_DISABLED; \ - stb r10,PACAIRQSOFTMASK(r13); \ - lbz r10,PACAIRQHAPPENED(r13); \ - std r10,_DAR(r1) +TRAMP_REAL_BEGIN(system_reset_fwnmi) + /* See comment at system_reset exception, don't turn on RI */ + INT_HANDLER system_reset, 0x100, area=PACA_EXNMI, ri=0 + +#endif /* CONFIG_PPC_PSERIES */ EXC_COMMON_BEGIN(system_reset_common) /* @@ -185,15 +864,27 @@ EXC_COMMON_BEGIN(system_reset_common) mr r10,r1 ld r1,PACA_NMI_EMERG_SP(r13) subi r1,r1,INT_FRAME_SIZE - EXCEPTION_COMMON_NORET_STACK(PACA_EXNMI, 0x100, - system_reset, system_reset_exception, - ADD_NVGPRS;ADD_RECONCILE_NMI) + INT_COMMON 0x100, PACA_EXNMI, 0, 1, 0, 0, 0 + bl save_nvgprs + /* + * Set IRQS_ALL_DISABLED unconditionally so arch_irqs_disabled does + * the right thing. We do not want to reconcile because that goes + * through irq tracing which we don't want in NMI. + * + * Save PACAIRQHAPPENED because some code will do a hard disable + * (e.g., xmon). So we want to restore this back to where it was + * when we return. DAR is unused in the stack, so save it there. + */ + li r10,IRQS_ALL_DISABLED + stb r10,PACAIRQSOFTMASK(r13) + lbz r10,PACAIRQHAPPENED(r13) + std r10,_DAR(r1) + + addi r3,r1,STACK_FRAME_OVERHEAD + bl system_reset_exception - /* This (and MCE) can be simplified with mtmsrd L=1 */ /* Clear MSR_RI before setting SRR0 and SRR1. */ - li r0,MSR_RI - mfmsr r9 - andc r9,r9,r0 + li r9,0 mtmsrd r9,1 /* @@ -211,67 +902,44 @@ EXC_COMMON_BEGIN(system_reset_common) ld r10,SOFTE(r1) stb r10,PACAIRQSOFTMASK(r13) - /* - * Keep below code in synch with MACHINE_CHECK_HANDLER_WINDUP. - * Should share common bits... - */ - - /* Move original SRR0 and SRR1 into the respective regs */ - ld r9,_MSR(r1) - mtspr SPRN_SRR1,r9 - ld r3,_NIP(r1) - mtspr SPRN_SRR0,r3 - ld r9,_CTR(r1) - mtctr r9 - ld r9,_XER(r1) - mtxer r9 - ld r9,_LINK(r1) - mtlr r9 - REST_GPR(0, r1) - REST_8GPRS(2, r1) - REST_GPR(10, r1) - ld r11,_CCR(r1) - mtcr r11 - REST_GPR(11, r1) - REST_2GPRS(12, r1) - /* restore original r1. */ - ld r1,GPR1(r1) + EXCEPTION_RESTORE_REGS EXC_STD RFI_TO_USER_OR_KERNEL -#ifdef CONFIG_PPC_PSERIES -/* - * Vectors for the FWNMI option. Share common code. - */ -TRAMP_REAL_BEGIN(system_reset_fwnmi) - SET_SCRATCH0(r13) /* save r13 */ - /* See comment at system_reset exception */ - EXCEPTION_PROLOG_NORI(PACA_EXNMI, system_reset_common, EXC_STD, - NOTEST, 0x100) -#endif /* CONFIG_PPC_PSERIES */ - EXC_REAL_BEGIN(machine_check, 0x200, 0x100) - /* This is moved out of line as it can be patched by FW, but - * some code path might still want to branch into the original - * vector + 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. */ - SET_SCRATCH0(r13) /* save r13 */ - 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(PACA_EXMC, NOTEST, 0x200) + +#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 @@ -292,129 +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 -TRAMP_REAL_BEGIN(machine_check_pSeries) - .globl machine_check_fwnmi -machine_check_fwnmi: - SET_SCRATCH0(r13) /* save r13 */ - EXCEPTION_PROLOG_0(PACA_EXMC) + bl save_nvgprs + addi r3,r1,STACK_FRAME_OVERHEAD + bl machine_check_early + std r3,RESULT(r1) /* Save result */ + ld r12,_MSR(r1) + +#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(PACA_EXMC, KVMTEST_PR, 0x200) + 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. + */ + lbz r11,HSTATE_IN_GUEST(r13) + cmpwi r11,0 /* Check if coming from guest */ + bne mce_deliver /* continue if we are. */ +#endif + + /* + * 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. */ - EXCEPTION_PROLOG_2_NORI(machine_check_common, EXC_STD) + andi. r11,r12,MSR_RI + beq unrecoverable_mce -TRAMP_KVM_SKIP(PACA_EXMC, 0x200) + /* + * 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. */ - mfspr r10,SPRN_DAR - std r10,PACA_EXMC+EX_DAR(r13) - mfspr r10,SPRN_DSISR - stw r10,PACA_EXMC+EX_DSISR(r13) - EXCEPTION_PROLOG_COMMON(0x200, PACA_EXMC) + 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 r0,MSR_RI; \ - mfmsr r9; /* get MSR value */ \ - andc r9,r9,r0; \ - mtmsrd r9,1; /* Clear MSR_RI */ \ - /* Move original SRR0 and SRR1 into the respective regs */ \ - ld r9,_MSR(r1); \ - mtspr SPRN_SRR1,r9; \ - ld r3,_NIP(r1); \ - mtspr SPRN_SRR0,r3; \ - ld r9,_CTR(r1); \ - mtctr r9; \ - ld r9,_XER(r1); \ - mtxer r9; \ - ld r9,_LINK(r1); \ - mtlr r9; \ - REST_GPR(0, r1); \ - REST_8GPRS(2, r1); \ - REST_GPR(10, r1); \ - ld r11,_CCR(r1); \ - mtcr r11; \ - /* Decrement paca->in_mce. */ \ - lhz r12,PACA_IN_MCE(r13); \ - subi r12,r12,1; \ - sth r12,PACA_IN_MCE(r13); \ - REST_GPR(11, r1); \ - REST_2GPRS(12, r1); \ - /* restore original r1. */ \ - ld r1,GPR1(r1) - #ifdef CONFIG_PPC_P7_NAP /* * This is an idle wakeup. Low level machine check has already been @@ -446,72 +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 @@ -519,100 +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 - SET_SCRATCH0(r13) /* save r13 */ - 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) -SET_SCRATCH0(r13) /* save r13 */ -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(PACA_EXGEN, KVMTEST_PR, 0x300) - /* - * DAR/DSISR must be read before setting MSR[RI], because - * a d-side MCE will clobber those registers so is not - * recoverable if they are live. - */ - mfspr r10,SPRN_DAR - mfspr r11,SPRN_DSISR - std r10,PACA_EXGEN+EX_DAR(r13) - stw r11,PACA_EXGEN+EX_DSISR(r13) -EXCEPTION_PROLOG_2(data_access_common, EXC_STD) - EXC_VIRT_BEGIN(data_access, 0x4300, 0x80) -SET_SCRATCH0(r13) /* save r13 */ -EXCEPTION_PROLOG_0(PACA_EXGEN) -EXCEPTION_PROLOG_1(PACA_EXGEN, NOTEST, 0x300) - mfspr r10,SPRN_DAR - mfspr r11,SPRN_DSISR - std r10,PACA_EXGEN+EX_DAR(r13) - stw r11,PACA_EXGEN+EX_DSISR(r13) -EXCEPTION_PROLOG_2_RELON(data_access_common, EXC_STD) + 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, @@ -620,15 +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_PROLOG_COMMON(0x300, PACA_EXGEN) - 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 @@ -636,32 +1171,15 @@ ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX) EXC_REAL_BEGIN(data_access_slb, 0x380, 0x80) -SET_SCRATCH0(r13) /* save r13 */ -EXCEPTION_PROLOG_0(PACA_EXSLB) - 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(PACA_EXSLB, KVMTEST_PR, 0x380) - mfspr r10,SPRN_DAR - std r10,PACA_EXSLB+EX_DAR(r13) -EXCEPTION_PROLOG_2(data_access_slb_common, EXC_STD) - EXC_VIRT_BEGIN(data_access_slb, 0x4380, 0x80) -SET_SCRATCH0(r13) /* save r13 */ -EXCEPTION_PROLOG_0(PACA_EXSLB) -EXCEPTION_PROLOG_1(PACA_EXSLB, NOTEST, 0x380) - mfspr r10,SPRN_DAR - std r10,PACA_EXSLB+EX_DAR(r13) -EXCEPTION_PROLOG_2_RELON(data_access_slb_common, EXC_STD) + 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_PROLOG_COMMON(0x380, PACA_EXSLB) - 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 */ @@ -684,20 +1202,20 @@ 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_PROLOG_COMMON(0x400, PACA_EXGEN) - 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 @@ -705,18 +1223,15 @@ ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX) EXC_REAL_BEGIN(instruction_access_slb, 0x480, 0x80) -EXCEPTION_PROLOG(PACA_EXSLB, instruction_access_slb_common, EXC_STD, KVMTEST_PR, 0x480); + 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) -EXCEPTION_RELON_PROLOG(PACA_EXSLB, instruction_access_slb_common, EXC_STD, NOTEST, 0x480); + INT_HANDLER instruction_access_slb, 0x480, virt=1, area=PACA_EXSLB EXC_VIRT_END(instruction_access_slb, 0x4480, 0x80) - -TRAMP_KVM(PACA_EXSLB, 0x480) - +INT_KVM_HANDLER instruction_access_slb, 0x480, EXC_STD, PACA_EXSLB, 0 EXC_COMMON_BEGIN(instruction_access_slb_common) - EXCEPTION_PROLOG_COMMON(0x480, PACA_EXSLB) - 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 */ @@ -732,79 +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) - .globl hardware_interrupt_hv; -hardware_interrupt_hv: - BEGIN_FTR_SECTION - MASKABLE_EXCEPTION_HV(0x500, hardware_interrupt_common, IRQS_DISABLED) - FTR_SECTION_ELSE - MASKABLE_EXCEPTION(0x500, hardware_interrupt_common, IRQS_DISABLED) - ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206) + 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) - .globl hardware_interrupt_relon_hv; -hardware_interrupt_relon_hv: - BEGIN_FTR_SECTION - MASKABLE_RELON_EXCEPTION_HV(0x500, hardware_interrupt_common, - IRQS_DISABLED) - FTR_SECTION_ELSE - __MASKABLE_RELON_EXCEPTION(0x500, hardware_interrupt_common, - EXC_STD, SOFTEN_TEST_PR, IRQS_DISABLED) - ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE) + 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) -SET_SCRATCH0(r13) /* save r13 */ -EXCEPTION_PROLOG_0(PACA_EXGEN) -EXCEPTION_PROLOG_1(PACA_EXGEN, KVMTEST_PR, 0x600) - mfspr r10,SPRN_DAR - mfspr r11,SPRN_DSISR - std r10,PACA_EXGEN+EX_DAR(r13) - stw r11,PACA_EXGEN+EX_DSISR(r13) -EXCEPTION_PROLOG_2(alignment_common, EXC_STD) + INT_HANDLER alignment, 0x600, dar=1, dsisr=1, kvm=1 EXC_REAL_END(alignment, 0x600, 0x100) - EXC_VIRT_BEGIN(alignment, 0x4600, 0x100) -SET_SCRATCH0(r13) /* save r13 */ -EXCEPTION_PROLOG_0(PACA_EXGEN) -EXCEPTION_PROLOG_1(PACA_EXGEN, NOTEST, 0x600) - mfspr r10,SPRN_DAR - mfspr r11,SPRN_DSISR - std r10,PACA_EXGEN+EX_DAR(r13) - stw r11,PACA_EXGEN+EX_DSISR(r13) -EXCEPTION_PROLOG_2_RELON(alignment_common, EXC_STD) + 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_PROLOG_COMMON(0x600, PACA_EXGEN) - 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 @@ -814,39 +1294,49 @@ EXC_COMMON_BEGIN(program_check_common) * we switch to the emergency stack if we're taking a TM Bad Thing from * the kernel. */ - li r10,MSR_PR /* Build a mask of MSR_PR .. */ - oris r10,r10,0x200000@h /* .. and SRR1_PROGTM */ - and r10,r10,r12 /* Mask SRR1 with that. */ - srdi r10,r10,8 /* Shift it so we can compare */ - cmpldi r10,(0x200000 >> 8) /* .. with an immediate. */ - bne 1f /* If != go to normal path. */ - - /* SRR1 had PR=0 and SRR1_PROGTM=1, so use the emergency stack */ - andi. r10,r12,MSR_PR; /* Set CR0 correctly for label */ + + andi. r10,r12,MSR_PR + bne 2f /* If userspace, go normal path */ + + andis. r10,r12,(SRR1_PROGTM)@h + bne 1f /* If TM, emergency */ + + cmpdi r1,-INT_FRAME_SIZE /* check if r1 is in userspace */ + blt 2f /* normal path if not */ + + /* Use the emergency stack */ +1: andi. r10,r12,MSR_PR /* Set CR0 correctly for label */ /* 3 in EXCEPTION_PROLOG_COMMON */ mr r10,r1 /* Save r1 */ ld r1,PACAEMERGSP(r13) /* Use emergency stack */ subi r1,r1,INT_FRAME_SIZE /* alloc stack frame */ - b 3f /* Jump into the macro !! */ -1: EXCEPTION_PROLOG_COMMON(0x700, PACA_EXGEN) + INT_COMMON 0x700, PACA_EXGEN, 0, 1, 1, 0, 0 + b 3f +2: + 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_PROLOG_COMMON(0x800, PACA_EXGEN) + 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 @@ -869,21 +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 @@ -891,17 +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. * @@ -910,7 +1408,7 @@ EXC_COMMON(trap_0b_common, 0xb00, unknown_exception) * * Call convention: * - * syscall register convention is in Documentation/powerpc/syscall64-abi.txt + * syscall register convention is in Documentation/powerpc/syscall64-abi.rst * * For hypercalls, the register convention is as follows: * r0 volatile @@ -932,6 +1430,7 @@ EXC_COMMON(trap_0b_common, 0xb00, unknown_exception) * without saving, though xer is not a good idea to use, as hardware may * interpret some bits so it may be costly to change them. */ +.macro SYSTEM_CALL virt #ifdef CONFIG_KVM_BOOK3S_64_HANDLER /* * There is a little bit of juggling to get syscall and hcall @@ -941,95 +1440,66 @@ EXC_COMMON(trap_0b_common, 0xb00, unknown_exception) * Userspace syscalls have already saved the PPR, hcalls must save * it before setting HMT_MEDIUM. */ -#define SYSCALL_KVMTEST \ - mtctr r13; \ - GET_PACA(r13); \ - std r10,PACA_EXGEN+EX_R10(r13); \ - INTERRUPT_TO_KERNEL; \ - KVMTEST_PR(0xc00); /* uses r10, branch to do_kvm_0xc00_system_call */ \ - HMT_MEDIUM; \ - mfctr r9; - + mtctr r13 + GET_PACA(r13) + std r10,PACA_EXGEN+EX_R10(r13) + INTERRUPT_TO_KERNEL + KVMTEST system_call EXC_STD 0xc00 /* uses r10, branch to system_call_kvm */ + mfctr r9 #else -#define SYSCALL_KVMTEST \ - HMT_MEDIUM; \ - mr r9,r13; \ - GET_PACA(r13); \ - INTERRUPT_TO_KERNEL; + mr r9,r13 + GET_PACA(r13) + INTERRUPT_TO_KERNEL #endif - -#define LOAD_SYSCALL_HANDLER(reg) \ - __LOAD_HANDLER(reg, system_call_common) - -/* - * After SYSCALL_KVMTEST, we reach here with PACA in r13, r13 in r9, - * and HMT_MEDIUM. - */ -#define SYSCALL_REAL \ - mfspr r11,SPRN_SRR0 ; \ - mfspr r12,SPRN_SRR1 ; \ - LOAD_SYSCALL_HANDLER(r10) ; \ - mtspr SPRN_SRR0,r10 ; \ - ld r10,PACAKMSR(r13) ; \ - mtspr SPRN_SRR1,r10 ; \ - RFI_TO_KERNEL ; \ - b . ; /* prevent speculative execution */ #ifdef CONFIG_PPC_FAST_ENDIAN_SWITCH -#define SYSCALL_FASTENDIAN_TEST \ -BEGIN_FTR_SECTION \ - cmpdi r0,0x1ebe ; \ - beq- 1f ; \ -END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE) \ - -#define SYSCALL_FASTENDIAN \ - /* Fast LE/BE switch system call */ \ -1: mfspr r12,SPRN_SRR1 ; \ - xori r12,r12,MSR_LE ; \ - mtspr SPRN_SRR1,r12 ; \ - mr r13,r9 ; \ - RFI_TO_USER ; /* return to userspace */ \ - b . ; /* prevent speculative execution */ -#else -#define SYSCALL_FASTENDIAN_TEST -#define SYSCALL_FASTENDIAN -#endif /* CONFIG_PPC_FAST_ENDIAN_SWITCH */ +BEGIN_FTR_SECTION + cmpdi r0,0x1ebe + beq- 1f +END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE) +#endif -#if defined(CONFIG_RELOCATABLE) - /* - * We can't branch directly so we do it via the CTR which - * is volatile across system calls. - */ -#define SYSCALL_VIRT \ - LOAD_SYSCALL_HANDLER(r10) ; \ - mtctr r10 ; \ - mfspr r11,SPRN_SRR0 ; \ - mfspr r12,SPRN_SRR1 ; \ - li r10,MSR_RI ; \ - mtmsrd r10,1 ; \ - bctr ; + /* We reach here with PACA in r13, r13 in r9. */ + mfspr r11,SPRN_SRR0 + mfspr r12,SPRN_SRR1 + + HMT_MEDIUM + + .if ! \virt + __LOAD_HANDLER(r10, system_call_common) + mtspr SPRN_SRR0,r10 + ld r10,PACAKMSR(r13) + mtspr SPRN_SRR1,r10 + RFI_TO_KERNEL + b . /* prevent speculative execution */ + .else + li r10,MSR_RI + mtmsrd r10,1 /* Set RI (EE=0) */ +#ifdef CONFIG_RELOCATABLE + __LOAD_HANDLER(r10, system_call_common) + mtctr r10 + bctr #else - /* We can branch directly */ -#define SYSCALL_VIRT \ - mfspr r11,SPRN_SRR0 ; \ - mfspr r12,SPRN_SRR1 ; \ - li r10,MSR_RI ; \ - mtmsrd r10,1 ; /* Set RI (EE=0) */ \ - b system_call_common ; + b system_call_common #endif + .endif + +#ifdef CONFIG_PPC_FAST_ENDIAN_SWITCH + /* Fast LE/BE switch system call */ +1: mfspr r12,SPRN_SRR1 + xori r12,r12,MSR_LE + mtspr SPRN_SRR1,r12 + mr r13,r9 + RFI_TO_USER /* return to userspace */ + b . /* prevent speculative execution */ +#endif +.endm EXC_REAL_BEGIN(system_call, 0xc00, 0x100) - SYSCALL_KVMTEST /* loads PACA into r13, and saves r13 to r9 */ - SYSCALL_FASTENDIAN_TEST - SYSCALL_REAL - SYSCALL_FASTENDIAN + SYSTEM_CALL 0 EXC_REAL_END(system_call, 0xc00, 0x100) - EXC_VIRT_BEGIN(system_call, 0x4c00, 0x100) - SYSCALL_KVMTEST /* loads PACA into r13, and saves r13 to r9 */ - SYSCALL_FASTENDIAN_TEST - SYSCALL_VIRT - SYSCALL_FASTENDIAN + SYSTEM_CALL 1 EXC_VIRT_END(system_call, 0x4c00, 0x100) #ifdef CONFIG_KVM_BOOK3S_64_HANDLER @@ -1040,7 +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 @@ -1053,32 +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) + 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_PROLOG_COMMON(0xe00, PACA_EXGEN) + 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 @@ -1087,15 +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) @@ -1104,69 +1583,55 @@ EXC_COMMON(emulation_assist_common, 0xe40, emulation_assist_interrupt) * first, and then eventaully from there to the trampoline to get into virtual * mode. */ -__EXC_REAL_OOL_HV_DIRECT(hmi_exception, 0xe60, 0x20, hmi_exception_early) -__TRAMP_REAL_OOL_MASKABLE_HV(hmi_exception, 0xe60, IRQS_DISABLED) +EXC_REAL_BEGIN(hmi_exception, 0xe60, 0x20) + 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(PACA_EXGEN, KVMTEST_HV, 0xe60) +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 */ + mfspr r12,SPRN_HSRR1 /* Save HSRR1 */ mr r10,r1 /* Save r1 */ ld r1,PACAEMERGSP(r13) /* Use emergency stack for realmode */ subi r1,r1,INT_FRAME_SIZE /* alloc stack frame */ - mfspr r11,SPRN_HSRR0 /* Save HSRR0 */ - mfspr r12,SPRN_HSRR1 /* Save HSRR1 */ - EXCEPTION_PROLOG_COMMON_1() + /* We don't touch AMR here, we never go to virtual mode */ - EXCEPTION_PROLOG_COMMON_2(PACA_EXGEN) - EXCEPTION_PROLOG_COMMON_3(0xe60) + INT_COMMON 0xe60, PACA_EXGEN, 0, 0, 0, 0, 0 + addi r3,r1,STACK_FRAME_OVERHEAD - BRANCH_LINK_TO_FAR(DOTSYM(hmi_exception_realmode)) /* Function call ABI */ + bl hmi_exception_realmode cmpdi cr0,r3,0 - - /* Windup the stack. */ - /* Move original HSRR0 and HSRR1 into the respective regs */ - ld r9,_MSR(r1) - mtspr SPRN_HSRR1,r9 - ld r3,_NIP(r1) - mtspr SPRN_HSRR0,r3 - ld r9,_CTR(r1) - mtctr r9 - ld r9,_XER(r1) - mtxer r9 - ld r9,_LINK(r1) - mtlr r9 - REST_GPR(0, r1) - REST_8GPRS(2, r1) - REST_GPR(10, r1) - ld r11,_CCR(r1) - REST_2GPRS(12, r1) bne 1f - mtcr r11 - REST_GPR(11, r1) - ld r1,GPR1(r1) - HRFI_TO_USER_OR_KERNEL -1: mtcr r11 - REST_GPR(11, r1) - ld r1,GPR1(r1) + EXCEPTION_RESTORE_REGS EXC_HV + HRFI_TO_USER_OR_KERNEL +1: /* * Go to virtual mode and pull the HMI event information from * firmware. */ - .globl hmi_exception_after_realmode -hmi_exception_after_realmode: - SET_SCRATCH0(r13) - EXCEPTION_PROLOG_0(PACA_EXGEN) - b tramp_real_hmi_exception + EXCEPTION_RESTORE_REGS EXC_HV + INT_HANDLER hmi_exception, 0xe60, hsrr=EXC_HV, bitmask=IRQS_DISABLED, kvm=1 EXC_COMMON_BEGIN(hmi_exception_common) -EXCEPTION_COMMON(PACA_EXGEN, 0xe60, hmi_exception_common, handle_hmi_exception, - ret_from_except, FINISH_NAP;ADD_NVGPRS;ADD_RECONCILE;RUNLATCH_ON) + INT_COMMON 0xe60, PACA_EXGEN, 1, 1, 1, 0, 0 + FINISH_NAP + 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 @@ -1174,9 +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) @@ -1186,17 +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_PROLOG_COMMON(0xf20, PACA_EXGEN) + INT_COMMON 0xf20, PACA_EXGEN, 1, 1, 0, 0, 0 #ifdef CONFIG_ALTIVEC BEGIN_FTR_SECTION beq 1f @@ -1229,11 +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_PROLOG_COMMON(0xf40, PACA_EXGEN) + INT_COMMON 0xf40, PACA_EXGEN, 1, 1, 0, 0, 0 #ifdef CONFIG_VSX BEGIN_FTR_SECTION beq 1f @@ -1265,15 +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) @@ -1290,9 +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) @@ -1300,38 +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) - mtspr SPRN_SPRG_HSCRATCH0,r13 - EXCEPTION_PROLOG_0(PACA_EXGEN) - EXCEPTION_PROLOG_1(PACA_EXGEN, NOTEST, 0x1500) - + 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_HV(0x1500) - EXCEPTION_PROLOG_2(denorm_common, EXC_HV) + 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) @@ -1346,12 +1842,11 @@ BEGIN_FTR_SECTION mtmsrd r10 sync -#define FMR2(n) fmr (n), (n) ; fmr n+1, n+1 -#define FMR4(n) FMR2(n) ; FMR2(n+2) -#define FMR8(n) FMR4(n) ; FMR4(n+4) -#define FMR16(n) FMR8(n) ; FMR8(n+8) -#define FMR32(n) FMR16(n) ; FMR16(n+16) - FMR32(0) + .Lreg=0 + .rept 32 + fmr .Lreg,.Lreg + .Lreg=.Lreg+1 + .endr FTR_SECTION_ELSE /* @@ -1363,12 +1858,11 @@ FTR_SECTION_ELSE mtmsrd r10 sync -#define XVCPSGNDP2(n) XVCPSGNDP(n,n,n) ; XVCPSGNDP(n+1,n+1,n+1) -#define XVCPSGNDP4(n) XVCPSGNDP2(n) ; XVCPSGNDP2(n+2) -#define XVCPSGNDP8(n) XVCPSGNDP4(n) ; XVCPSGNDP4(n+4) -#define XVCPSGNDP16(n) XVCPSGNDP8(n) ; XVCPSGNDP8(n+8) -#define XVCPSGNDP32(n) XVCPSGNDP16(n) ; XVCPSGNDP16(n+16) - XVCPSGNDP32(0) + .Lreg=0 + .rept 32 + XVCPSGNDP(.Lreg,.Lreg,.Lreg) + .Lreg=.Lreg+1 + .endr ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_206) @@ -1379,7 +1873,12 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S) * To denormalise we need to move a copy of the register to itself. * For POWER8 we need to do that for all 64 VSX registers */ - XVCPSGNDP32(32) + .Lreg=32 + .rept 32 + XVCPSGNDP(.Lreg,.Lreg,.Lreg) + .Lreg=.Lreg+1 + .endr + denorm_done: mfspr r11,SPRN_HSRR0 subi r11,r11,4 @@ -1403,9 +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) @@ -1413,9 +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 @@ -1424,15 +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 @@ -1442,7 +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(soft_nmi_common, _H) + INT_SAVE_SRR_AND_JUMP soft_nmi_common, _H, 1 /* * Branch to soft_nmi_interrupt using the emergency stack. The emergency @@ -1457,9 +1965,10 @@ EXC_COMMON_BEGIN(soft_nmi_common) mr r10,r1 ld r1,PACAEMERGSP(r13) subi r1,r1,INT_FRAME_SIZE - EXCEPTION_COMMON_NORET_STACK(PACA_EXGEN, 0x900, - system_reset, soft_nmi_interrupt, - ADD_NVGPRS;ADD_RECONCILE) + INT_COMMON 0x900, PACA_EXGEN, 0, 1, 1, 0, 0 + bl save_nvgprs + addi r3,r1,STACK_FRAME_OVERHEAD + bl soft_nmi_interrupt b ret_from_except #else /* CONFIG_PPC_WATCHDOG */ @@ -1477,35 +1986,50 @@ EXC_COMMON_BEGIN(soft_nmi_common) * - Else it is one of PACA_IRQ_MUST_HARD_MASK, so hard disable and return. * This is called with r10 containing the value to OR to the paca field. */ -#define MASKED_INTERRUPT(_H) \ -masked_##_H##interrupt: \ - std r11,PACA_EXGEN+EX_R11(r13); \ - lbz r11,PACAIRQHAPPENED(r13); \ - or r11,r11,r10; \ - stb r11,PACAIRQHAPPENED(r13); \ - cmpwi r10,PACA_IRQ_DEC; \ - bne 1f; \ - lis r10,0x7fff; \ - ori r10,r10,0xffff; \ - mtspr SPRN_DEC,r10; \ - b MASKED_DEC_HANDLER_LABEL; \ -1: andi. r10,r10,PACA_IRQ_MUST_HARD_MASK; \ - beq 2f; \ - mfspr r10,SPRN_##_H##SRR1; \ - xori r10,r10,MSR_EE; /* clear MSR_EE */ \ - mtspr SPRN_##_H##SRR1,r10; \ - ori r11,r11,PACA_IRQ_HARD_DIS; \ - stb r11,PACAIRQHAPPENED(r13); \ -2: /* done */ \ - mtcrf 0x80,r9; \ - std r1,PACAR1(r13); \ - ld r9,PACA_EXGEN+EX_R9(r13); \ - ld r10,PACA_EXGEN+EX_R10(r13); \ - ld r11,PACA_EXGEN+EX_R11(r13); \ - /* returns to kernel where r13 must be set up, so don't restore it */ \ - ##_H##RFI_TO_KERNEL; \ - b .; \ - MASKED_DEC_HANDLER(_H) +.macro MASKED_INTERRUPT hsrr + .if \hsrr +masked_Hinterrupt: + .else +masked_interrupt: + .endif + std r11,PACA_EXGEN+EX_R11(r13) + lbz r11,PACAIRQHAPPENED(r13) + or r11,r11,r10 + stb r11,PACAIRQHAPPENED(r13) + cmpwi r10,PACA_IRQ_DEC + bne 1f + lis r10,0x7fff + ori r10,r10,0xffff + mtspr SPRN_DEC,r10 + b MASKED_DEC_HANDLER_LABEL +1: andi. r10,r10,PACA_IRQ_MUST_HARD_MASK + beq 2f + .if \hsrr + mfspr r10,SPRN_HSRR1 + xori r10,r10,MSR_EE /* clear MSR_EE */ + mtspr SPRN_HSRR1,r10 + .else + mfspr r10,SPRN_SRR1 + xori r10,r10,MSR_EE /* clear MSR_EE */ + mtspr SPRN_SRR1,r10 + .endif + ori r11,r11,PACA_IRQ_HARD_DIS + stb r11,PACAIRQHAPPENED(r13) +2: /* done */ + mtcrf 0x80,r9 + std r1,PACAR1(r13) + ld r9,PACA_EXGEN+EX_R9(r13) + ld r10,PACA_EXGEN+EX_R10(r13) + ld r11,PACA_EXGEN+EX_R11(r13) + /* returns to kernel where r13 must be set up, so don't restore it */ + .if \hsrr + HRFI_TO_KERNEL + .else + RFI_TO_KERNEL + .endif + b . + MASKED_DEC_HANDLER(\hsrr\()) +.endm TRAMP_REAL_BEGIN(stf_barrier_fallback) std r9,PACA_EXRFI+EX_R9(r13) @@ -1612,8 +2136,8 @@ TRAMP_REAL_BEGIN(hrfi_flush_fallback) * cannot reach these if they are put there. */ USE_FIXED_SECTION(virt_trampolines) - MASKED_INTERRUPT() - MASKED_INTERRUPT(H) + MASKED_INTERRUPT EXC_STD + MASKED_INTERRUPT EXC_HV #ifdef CONFIG_KVM_BOOK3S_64_HANDLER TRAMP_REAL_BEGIN(kvmppc_skip_interrupt) @@ -1699,6 +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 */ @@ -1707,7 +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" */ @@ -1715,15 +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 */ @@ -1733,24 +2284,23 @@ 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 - beq+ 12f + beq+ ret_from_except_lite 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 @@ -1761,7 +2311,12 @@ handle_dabr_fault: ld r5,_DSISR(r1) addi r3,r1,STACK_FRAME_OVERHEAD bl do_break -12: b ret_from_except_lite + /* + * do_break() may have changed the NV GPRS while handling a breakpoint. + * If so, we need to restore them with their updated values. Don't use + * ret_from_except_lite here. + */ + b ret_from_except #ifdef CONFIG_PPC_BOOK3S_64 @@ -1784,74 +2339,12 @@ 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 b ret_from_except /* - * Here we have detected that the kernel stack pointer is bad. - * R9 contains the saved CR, r13 points to the paca, - * r10 contains the (bad) kernel stack pointer, - * r11 and r12 contain the saved SRR0 and SRR1. - * We switch to using an emergency stack, save the registers there, - * and call kernel_bad_stack(), which panics. - */ -bad_stack: - ld r1,PACAEMERGSP(r13) - subi r1,r1,64+INT_FRAME_SIZE - std r9,_CCR(r1) - std r10,GPR1(r1) - std r11,_NIP(r1) - std r12,_MSR(r1) - mfspr r11,SPRN_DAR - mfspr r12,SPRN_DSISR - std r11,_DAR(r1) - std r12,_DSISR(r1) - mflr r10 - mfctr r11 - mfxer r12 - std r10,_LINK(r1) - std r11,_CTR(r1) - std r12,_XER(r1) - SAVE_GPR(0,r1) - SAVE_GPR(2,r1) - ld r10,EX_R3(r3) - std r10,GPR3(r1) - SAVE_GPR(4,r1) - SAVE_4GPRS(5,r1) - ld r9,EX_R9(r3) - ld r10,EX_R10(r3) - SAVE_2GPRS(9,r1) - ld r9,EX_R11(r3) - ld r10,EX_R12(r3) - ld r11,EX_R13(r3) - std r9,GPR11(r1) - std r10,GPR12(r1) - std r11,GPR13(r1) -BEGIN_FTR_SECTION - ld r10,EX_CFAR(r3) - std r10,ORIG_GPR3(r1) -END_FTR_SECTION_IFSET(CPU_FTR_CFAR) - SAVE_8GPRS(14,r1) - SAVE_10GPRS(22,r1) - lhz r12,PACA_TRAP_SAVE(r13) - std r12,_TRAP(r1) - addi r11,r1,INT_FRAME_SIZE - std r11,0(r1) - li r12,0 - std r12,0(r11) - ld r2,PACATOC(r13) - ld r11,exception_marker@toc(r2) - std r12,RESULT(r1) - std r11,STACK_FRAME_OVERHEAD-16(r1) -1: addi r3,r1,STACK_FRAME_OVERHEAD - bl kernel_bad_stack - b 1b -_ASM_NOKPROBE_SYMBOL(bad_stack); - -/* * When doorbell is triggered from system reset wakeup, the message is * not cleared, so it would fire again when EE is enabled. * diff --git a/arch/powerpc/kernel/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 b5a5c6896019..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: @@ -900,6 +901,7 @@ p_toc: .8byte __toc_start + 0x8000 - 0b /* * This is where the main kernel code starts. */ +__REF start_here_multiplatform: /* set up the TOC */ bl relative_toc @@ -975,6 +977,7 @@ start_here_multiplatform: RFI b . /* prevent speculative execution */ + .previous /* This is where all platforms converge execution */ start_here_common: @@ -996,7 +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 a293a53b4365..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; @@ -251,31 +296,9 @@ 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 @@ -366,59 +389,3 @@ void hw_breakpoint_pmu_read(struct perf_event *bp) { /* TODO */ } - -bool dawr_force_enable; -EXPORT_SYMBOL_GPL(dawr_force_enable); - -static ssize_t dawr_write_file_bool(struct file *file, - const char __user *user_buf, - size_t count, loff_t *ppos) -{ - struct arch_hw_breakpoint null_brk = {0, 0, 0}; - size_t rc; - - /* Send error to user if they hypervisor won't allow us to write DAWR */ - if ((!dawr_force_enable) && - (firmware_has_feature(FW_FEATURE_LPAR)) && - (set_dawr(&null_brk) != H_SUCCESS)) - return -1; - - rc = debugfs_write_file_bool(file, user_buf, count, ppos); - if (rc) - return rc; - - /* If we are clearing, make sure all CPUs have the DAWR cleared */ - if (!dawr_force_enable) - smp_call_function((smp_call_func_t)set_dawr, &null_brk, 0); - - return rc; -} - -static const struct file_operations dawr_enable_fops = { - .read = debugfs_read_file_bool, - .write = dawr_write_file_bool, - .open = simple_open, - .llseek = default_llseek, -}; - -static int __init dawr_force_setup(void) -{ - dawr_force_enable = false; - - if (cpu_has_feature(CPU_FTR_DAWR)) { - /* Don't setup sysfs file for user control on P8 */ - dawr_force_enable = true; - return 0; - } - - if (PVR_VER(mfspr(SPRN_PVR)) == PVR_POWER9) { - /* Turn DAWR off by default, but allow admin to turn it on */ - dawr_force_enable = false; - debugfs_create_file_unsafe("dawr_enable_dangerous", 0600, - powerpc_debugfs_root, - &dawr_force_enable, - &dawr_enable_fops); - } - return 0; -} -arch_initcall(dawr_force_setup); diff --git a/arch/powerpc/kernel/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/irq.c b/arch/powerpc/kernel/irq.c index bc68c53af67c..5645bc9cbc09 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -255,7 +255,7 @@ notrace void arch_local_irq_restore(unsigned long mask) irq_happened = get_irq_happened(); if (!irq_happened) { #ifdef CONFIG_PPC_IRQ_SOFT_MASK_DEBUG - WARN_ON(!(mfmsr() & MSR_EE)); + WARN_ON_ONCE(!(mfmsr() & MSR_EE)); #endif return; } @@ -268,7 +268,7 @@ notrace void arch_local_irq_restore(unsigned long mask) */ if (!(irq_happened & PACA_IRQ_HARD_DIS)) { #ifdef CONFIG_PPC_IRQ_SOFT_MASK_DEBUG - WARN_ON(!(mfmsr() & MSR_EE)); + WARN_ON_ONCE(!(mfmsr() & MSR_EE)); #endif __hard_irq_disable(); #ifdef CONFIG_PPC_IRQ_SOFT_MASK_DEBUG @@ -279,7 +279,7 @@ notrace void arch_local_irq_restore(unsigned long mask) * warn if we are wrong. Only do that when IRQ tracing * is enabled as mfmsr() can be costly. */ - if (WARN_ON(mfmsr() & MSR_EE)) + if (WARN_ON_ONCE(mfmsr() & MSR_EE)) __hard_irq_disable(); #endif } diff --git a/arch/powerpc/kernel/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 e39536aad30d..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 */ @@ -82,8 +94,7 @@ static void flush_erat(void) return; } #endif - /* PPC_INVALIDATE_ERAT can only be used on ISA v3 and newer */ - asm volatile(PPC_INVALIDATE_ERAT : : :"memory"); + asm volatile(PPC_ISA_3_0_INVALIDATE_ERAT : : :"memory"); } #define MCE_FLUSH_SLB 1 @@ -345,7 +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) { /* @@ -398,6 +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: @@ -483,6 +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; @@ -542,7 +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; } @@ -559,9 +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 @@ -594,7 +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/misc_64.S b/arch/powerpc/kernel/misc_64.S index 1ad4089dd110..b55a7b4cb543 100644 --- a/arch/powerpc/kernel/misc_64.S +++ b/arch/powerpc/kernel/misc_64.S @@ -110,58 +110,6 @@ _ASM_NOKPROBE_SYMBOL(flush_icache_range) EXPORT_SYMBOL(flush_icache_range) /* - * Like above, but only do the D-cache. - * - * flush_dcache_range(unsigned long start, unsigned long stop) - * - * flush all bytes from start to stop-1 inclusive - */ -_GLOBAL_TOC(flush_dcache_range) - -/* - * Flush the data cache to memory - * - * Different systems have different cache line sizes - */ - ld r10,PPC64_CACHES@toc(r2) - lwz r7,DCACHEL1BLOCKSIZE(r10) /* Get dcache block size */ - addi r5,r7,-1 - andc r6,r3,r5 /* round low to line bdy */ - subf r8,r6,r4 /* compute length */ - add r8,r8,r5 /* ensure we get enough */ - lwz r9,DCACHEL1LOGBLOCKSIZE(r10) /* Get log-2 of dcache block size */ - srw. r8,r8,r9 /* compute line count */ - beqlr /* nothing to do? */ - mtctr r8 -0: dcbst 0,r6 - add r6,r6,r7 - bdnz 0b - sync - blr -EXPORT_SYMBOL(flush_dcache_range) - -_GLOBAL(flush_inval_dcache_range) - ld r10,PPC64_CACHES@toc(r2) - lwz r7,DCACHEL1BLOCKSIZE(r10) /* Get dcache block size */ - addi r5,r7,-1 - andc r6,r3,r5 /* round low to line bdy */ - subf r8,r6,r4 /* compute length */ - add r8,r8,r5 /* ensure we get enough */ - lwz r9,DCACHEL1LOGBLOCKSIZE(r10)/* Get log-2 of dcache block size */ - srw. r8,r8,r9 /* compute line count */ - beqlr /* nothing to do? */ - sync - isync - mtctr r8 -0: dcbf 0,r6 - add r6,r6,r7 - bdnz 0b - sync - isync - blr - - -/* * Flush a particular page from the data cache to RAM. * Note: this is necessary because the instruction cache does *not* * snoop from the data cache. diff --git a/arch/powerpc/kernel/module_32.c b/arch/powerpc/kernel/module_32.c index 991d396fb50d..d7134c614c16 100644 --- a/arch/powerpc/kernel/module_32.c +++ b/arch/powerpc/kernel/module_32.c @@ -160,10 +160,12 @@ int module_frob_arch_sections(Elf32_Ehdr *hdr, static inline int entry_matches(struct ppc_plt_entry *entry, Elf32_Addr val) { - if (entry->jump[0] == 0x3d800000 + ((val + 0x8000) >> 16) - && entry->jump[1] == 0x398c0000 + (val & 0xffff)) - return 1; - return 0; + if (entry->jump[0] != (PPC_INST_ADDIS | __PPC_RT(R12) | PPC_HA(val))) + return 0; + if (entry->jump[1] != (PPC_INST_ADDI | __PPC_RT(R12) | __PPC_RA(R12) | + PPC_LO(val))) + return 0; + return 1; } /* Set up a trampoline in the PLT to bounce us to the distant function */ @@ -188,10 +190,16 @@ static uint32_t do_plt_call(void *location, entry++; } - entry->jump[0] = 0x3d800000+((val+0x8000)>>16); /* lis r12,sym@ha */ - entry->jump[1] = 0x398c0000 + (val&0xffff); /* addi r12,r12,sym@l*/ - entry->jump[2] = 0x7d8903a6; /* mtctr r12 */ - entry->jump[3] = 0x4e800420; /* bctr */ + /* + * lis r12, sym@ha + * addi r12, r12, sym@l + * mtctr r12 + * bctr + */ + entry->jump[0] = PPC_INST_ADDIS | __PPC_RT(R12) | PPC_HA(val); + entry->jump[1] = PPC_INST_ADDI | __PPC_RT(R12) | __PPC_RA(R12) | PPC_LO(val); + entry->jump[2] = PPC_INST_MTCTR | __PPC_RS(R12); + entry->jump[3] = PPC_INST_BCTR; pr_debug("Initialized plt for 0x%x at %p\n", val, entry); return (uint32_t)entry; diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c index a93b10c48000..007606a48fd9 100644 --- a/arch/powerpc/kernel/module_64.c +++ b/arch/powerpc/kernel/module_64.c @@ -121,20 +121,27 @@ struct ppc64_stub_entry * the stub, but it's significantly shorter to put these values at the * end of the stub code, and patch the stub address (32-bits relative * to the TOC ptr, r2) into the stub. + * + * addis r11,r2, <high> + * addi r11,r11, <low> + * std r2,R2_STACK_OFFSET(r1) + * ld r12,32(r11) + * ld r2,40(r11) + * mtctr r12 + * bctr */ - static u32 ppc64_stub_insns[] = { - 0x3d620000, /* addis r11,r2, <high> */ - 0x396b0000, /* addi r11,r11, <low> */ + PPC_INST_ADDIS | __PPC_RT(R11) | __PPC_RA(R2), + PPC_INST_ADDI | __PPC_RT(R11) | __PPC_RA(R11), /* Save current r2 value in magic place on the stack. */ - 0xf8410000|R2_STACK_OFFSET, /* std r2,R2_STACK_OFFSET(r1) */ - 0xe98b0020, /* ld r12,32(r11) */ + PPC_INST_STD | __PPC_RS(R2) | __PPC_RA(R1) | R2_STACK_OFFSET, + PPC_INST_LD | __PPC_RT(R12) | __PPC_RA(R11) | 32, #ifdef PPC64_ELF_ABI_v1 /* Set up new r2 from function descriptor */ - 0xe84b0028, /* ld r2,40(r11) */ + PPC_INST_LD | __PPC_RT(R2) | __PPC_RA(R11) | 40, #endif - 0x7d8903a6, /* mtctr r12 */ - 0x4e800420 /* bctr */ + PPC_INST_MTCTR | __PPC_RS(R12), + PPC_INST_BCTR, }; #ifdef CONFIG_DYNAMIC_FTRACE @@ -388,13 +395,6 @@ static inline unsigned long my_r2(const Elf64_Shdr *sechdrs, struct module *me) return (sechdrs[me->arch.toc_section].sh_addr & ~0xfful) + 0x8000; } -/* Both low and high 16 bits are added as SIGNED additions, so if low - 16 bits has high bit set, high 16 bits must be adjusted. These - macros do that (stolen from binutils). */ -#define PPC_LO(v) ((v) & 0xffff) -#define PPC_HI(v) (((v) >> 16) & 0xffff) -#define PPC_HA(v) PPC_HI ((v) + 0x8000) - /* Patch stub to reference function and correct r2 value. */ static inline int create_stub(const Elf64_Shdr *sechdrs, struct ppc64_stub_entry *entry, @@ -699,18 +699,21 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, * ld r2, ...(r12) * add r2, r2, r12 */ - if ((((uint32_t *)location)[0] & ~0xfffc) - != 0xe84c0000) + if ((((uint32_t *)location)[0] & ~0xfffc) != + (PPC_INST_LD | __PPC_RT(R2) | __PPC_RA(R12))) break; - if (((uint32_t *)location)[1] != 0x7c426214) + if (((uint32_t *)location)[1] != + (PPC_INST_ADD | __PPC_RT(R2) | __PPC_RA(R2) | __PPC_RB(R12))) break; /* * If found, replace it with: * addis r2, r12, (.TOC.-func)@ha - * addi r2, r12, (.TOC.-func)@l + * addi r2, r2, (.TOC.-func)@l */ - ((uint32_t *)location)[0] = 0x3c4c0000 + PPC_HA(value); - ((uint32_t *)location)[1] = 0x38420000 + PPC_LO(value); + ((uint32_t *)location)[0] = PPC_INST_ADDIS | __PPC_RT(R2) | + __PPC_RA(R12) | PPC_HA(value); + ((uint32_t *)location)[1] = PPC_INST_ADDI | __PPC_RT(R2) | + __PPC_RA(R2) | PPC_LO(value); break; case R_PPC64_REL16_HA: @@ -764,12 +767,19 @@ static unsigned long create_ftrace_stub(const Elf64_Shdr *sechdrs, { struct ppc64_stub_entry *entry; unsigned int i, num_stubs; + /* + * ld r12,PACATOC(r13) + * addis r12,r12,<high> + * addi r12,r12,<low> + * mtctr r12 + * bctr + */ static u32 stub_insns[] = { - 0xe98d0000 | PACATOC, /* ld r12,PACATOC(r13) */ - 0x3d8c0000, /* addis r12,r12,<high> */ - 0x398c0000, /* addi r12,r12,<low> */ - 0x7d8903a6, /* mtctr r12 */ - 0x4e800420, /* bctr */ + PPC_INST_LD | __PPC_RT(R12) | __PPC_RA(R13) | PACATOC, + PPC_INST_ADDIS | __PPC_RT(R12) | __PPC_RA(R12), + PPC_INST_ADDI | __PPC_RT(R12) | __PPC_RA(R12), + PPC_INST_MTCTR | __PPC_RS(R12), + PPC_INST_BCTR, }; long reladdr; diff --git a/arch/powerpc/kernel/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 24522aa37665..f91d7e94872e 100644 --- a/arch/powerpc/kernel/pci_of_scan.c +++ b/arch/powerpc/kernel/pci_of_scan.c @@ -34,29 +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; - 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; } @@ -77,10 +123,16 @@ static void of_pci_parse_addrs(struct device_node *node, struct pci_dev *dev) const __be32 *addrs; u32 i; int proplen; + bool mark_unset = false; addrs = of_get_property(node, "assigned-addresses", &proplen); - if (!addrs) - return; + if (!addrs || !proplen) { + addrs = of_get_property(node, "reg", &proplen); + if (!addrs || !proplen) + return; + mark_unset = true; + } + pr_debug(" parse addresses (%d bytes) @ %p\n", proplen, addrs); for (; proplen >= 20; proplen -= 20, addrs += 5) { flags = pci_parse_of_flags(of_read_number(addrs, 1), 0); @@ -105,6 +157,8 @@ static void of_pci_parse_addrs(struct device_node *node, struct pci_dev *dev) continue; } res->flags = flags; + if (mark_unset) + res->flags |= IORESOURCE_UNSET; res->name = pci_name(dev); region.start = base; region.end = base + size - 1; diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index f0fbbf6a6a1f..639ceae7da9d 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -101,21 +101,8 @@ static void check_if_tm_restore_required(struct task_struct *tsk) } } -static bool tm_active_with_fp(struct task_struct *tsk) -{ - return MSR_TM_ACTIVE(tsk->thread.regs->msr) && - (tsk->thread.ckpt_regs.msr & MSR_FP); -} - -static bool tm_active_with_altivec(struct task_struct *tsk) -{ - return MSR_TM_ACTIVE(tsk->thread.regs->msr) && - (tsk->thread.ckpt_regs.msr & MSR_VEC); -} #else static inline void check_if_tm_restore_required(struct task_struct *tsk) { } -static inline bool tm_active_with_fp(struct task_struct *tsk) { return false; } -static inline bool tm_active_with_altivec(struct task_struct *tsk) { return false; } #endif /* CONFIG_PPC_TRANSACTIONAL_MEM */ bool strict_msr_control; @@ -252,7 +239,7 @@ EXPORT_SYMBOL(enable_kernel_fp); static int restore_fp(struct task_struct *tsk) { - if (tsk->thread.load_fp || tm_active_with_fp(tsk)) { + if (tsk->thread.load_fp) { load_fp_state(¤t->thread.fp_state); current->thread.load_fp++; return 1; @@ -334,8 +321,7 @@ EXPORT_SYMBOL_GPL(flush_altivec_to_thread); static int restore_altivec(struct task_struct *tsk) { - if (cpu_has_feature(CPU_FTR_ALTIVEC) && - (tsk->thread.load_vec || tm_active_with_altivec(tsk))) { + if (cpu_has_feature(CPU_FTR_ALTIVEC) && (tsk->thread.load_vec)) { load_vr_state(&tsk->thread.vr_state); tsk->thread.used_vr = 1; tsk->thread.load_vec++; @@ -497,13 +483,14 @@ void giveup_all(struct task_struct *tsk) if (!tsk->thread.regs) return; + check_if_tm_restore_required(tsk); + usermsr = tsk->thread.regs->msr; if ((usermsr & msr_all_available) == 0) return; msr_check_and_set(msr_all_available); - check_if_tm_restore_required(tsk); WARN_ON((usermsr & MSR_VSX) && !((usermsr & MSR_FP) && (usermsr & MSR_VEC))); @@ -639,7 +626,7 @@ void do_break (struct pt_regs *regs, unsigned long address, hw_breakpoint_disable(); /* Deliver the signal to userspace */ - force_sig_fault(SIGTRAP, TRAP_HWBKPT, (void __user *)address, current); + force_sig_fault(SIGTRAP, TRAP_HWBKPT, (void __user *)address); } #endif /* CONFIG_PPC_ADV_DEBUG_REGS */ @@ -793,34 +780,6 @@ static inline int set_dabr(struct arch_hw_breakpoint *brk) return __set_dabr(dabr, dabrx); } -int set_dawr(struct arch_hw_breakpoint *brk) -{ - unsigned long dawr, dawrx, mrd; - - dawr = brk->address; - - dawrx = (brk->type & (HW_BRK_TYPE_READ | HW_BRK_TYPE_WRITE)) \ - << (63 - 58); //* read/write bits */ - dawrx |= ((brk->type & (HW_BRK_TYPE_TRANSLATE)) >> 2) \ - << (63 - 59); //* translate */ - dawrx |= (brk->type & (HW_BRK_TYPE_PRIV_ALL)) \ - >> 3; //* PRIM bits */ - /* dawr length is stored in field MDR bits 48:53. Matches range in - doublewords (64 bits) baised by -1 eg. 0b000000=1DW and - 0b111111=64DW. - brk->len is in bytes. - This aligns up to double word size, shifts and does the bias. - */ - mrd = ((brk->len + 7) >> 3) - 1; - dawrx |= (mrd & 0x3f) << (63 - 53); - - if (ppc_md.set_dawr) - return ppc_md.set_dawr(dawr, dawrx); - mtspr(SPRN_DAWR, dawr); - mtspr(SPRN_DAWRX, dawrx); - return 0; -} - void __set_breakpoint(struct arch_hw_breakpoint *brk) { memcpy(this_cpu_ptr(¤t_brk), brk, sizeof(*brk)); @@ -1628,8 +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); @@ -1670,10 +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; @@ -2074,10 +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) @@ -2106,15 +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 ed446b7ea164..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 @@ -168,6 +169,11 @@ static unsigned long __prombss prom_tce_alloc_end; #ifdef CONFIG_PPC_PSERIES static bool __prombss prom_radix_disable; +static bool __prombss prom_xive_disable; +#endif + +#ifdef CONFIG_PPC_SVM +static bool __prombss prom_svm_enable; #endif struct platform_support { @@ -804,7 +810,24 @@ static void __init early_cmdline_parse(void) } if (prom_radix_disable) prom_debug("Radix disabled from cmdline\n"); + + opt = prom_strstr(prom_cmd_line, "xive=off"); + if (opt) { + prom_xive_disable = true; + prom_debug("XIVE disabled from cmdline\n"); + } #endif /* CONFIG_PPC_PSERIES */ + +#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 @@ -1212,10 +1235,17 @@ static void __init prom_parse_xive_model(u8 val, switch (val) { case OV5_FEAT(OV5_XIVE_EITHER): /* Either Available */ prom_debug("XIVE - either mode supported\n"); - support->xive = true; + support->xive = !prom_xive_disable; break; case OV5_FEAT(OV5_XIVE_EXPLOIT): /* Only Exploitation mode */ prom_debug("XIVE - exploitation mode supported\n"); + if (prom_xive_disable) { + /* + * If we __have__ to do XIVE, we're better off ignoring + * the command line rather than not booting. + */ + prom_printf("WARNING: Ignoring cmdline option xive=off\n"); + } support->xive = true; break; case OV5_FEAT(OV5_XIVE_LEGACY): /* Only Legacy mode */ @@ -1562,9 +1592,6 @@ static void __init reserve_mem(u64 base, u64 size) static void __init prom_init_mem(void) { phandle node; -#ifdef DEBUG_PROM - char *path; -#endif char type[64]; unsigned int plen; cell_t *p, *endp; @@ -1586,9 +1613,6 @@ static void __init prom_init_mem(void) prom_debug("root_size_cells: %x\n", rsc); prom_debug("scanning memory:\n"); -#ifdef DEBUG_PROM - path = prom_scratch; -#endif for (node = 0; prom_next_node(&node); ) { type[0] = 0; @@ -1613,9 +1637,10 @@ static void __init prom_init_mem(void) endp = p + (plen / sizeof(cell_t)); #ifdef DEBUG_PROM - memset(path, 0, sizeof(prom_scratch)); - call_prom("package-to-path", 3, 1, node, path, sizeof(prom_scratch) - 1); - prom_debug(" node %s :\n", path); + memset(prom_scratch, 0, sizeof(prom_scratch)); + call_prom("package-to-path", 3, 1, node, prom_scratch, + sizeof(prom_scratch) - 1); + prom_debug(" node %s :\n", prom_scratch); #endif /* DEBUG_PROM */ while ((endp - p) >= (rac + rsc)) { @@ -1703,6 +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 */ @@ -3159,6 +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. @@ -3357,6 +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/ptrace.c b/arch/powerpc/kernel/ptrace.c index 684b0b315c32..8c92febf5f44 100644 --- a/arch/powerpc/kernel/ptrace.c +++ b/arch/powerpc/kernel/ptrace.c @@ -2521,7 +2521,6 @@ void ptrace_disable(struct task_struct *child) { /* make sure the single step bit is not set. */ user_disable_single_step(child); - clear_tsk_thread_flag(child, TIF_SYSCALL_EMU); } #ifdef CONFIG_PPC_ADV_DEBUG_REGS diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c index b824f4c69622..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); @@ -980,18 +984,16 @@ int rtas_ibm_suspend_me(u64 handle) cpu_hotplug_disable(); /* Check if we raced with a CPU-Offline Operation */ - if (unlikely(!cpumask_equal(cpu_present_mask, cpu_online_mask))) { - pr_err("%s: Raced against a concurrent CPU-Offline\n", - __func__); - atomic_set(&data.error, -EBUSY); + if (!cpumask_equal(cpu_present_mask, cpu_online_mask)) { + pr_info("%s: Raced against a concurrent CPU-Offline\n", __func__); + atomic_set(&data.error, -EAGAIN); goto out_hotplug_enable; } /* Call function on all CPUs. One of us will make the * rtas call */ - if (on_each_cpu(rtas_percpu_suspend_me, &data, 0)) - atomic_set(&data.error, -EINVAL); + on_each_cpu(rtas_percpu_suspend_me, &data, 0); wait_for_completion(&done); @@ -1008,6 +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/signal_32.c b/arch/powerpc/kernel/signal_32.c index a2b74e057904..98600b276f76 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -1198,6 +1198,9 @@ SYSCALL_DEFINE0(rt_sigreturn) goto bad; if (MSR_TM_ACTIVE(msr_hi<<32)) { + /* Trying to start TM on non TM system */ + if (!cpu_has_feature(CPU_FTR_TM)) + goto bad; /* We only recheckpoint on return if we're * transaction. */ @@ -1245,7 +1248,7 @@ SYSCALL_DEFINE0(rt_sigreturn) current->comm, current->pid, rt_sf, regs->nip, regs->link); - force_sig(SIGSEGV, current); + force_sig(SIGSEGV); return 0; } @@ -1334,7 +1337,7 @@ SYSCALL_DEFINE3(debug_setcontext, struct ucontext __user *, ctx, current->comm, current->pid, ctx, regs->nip, regs->link); - force_sig(SIGSEGV, current); + force_sig(SIGSEGV); goto out; } @@ -1512,6 +1515,6 @@ badframe: current->comm, current->pid, addr, regs->nip, regs->link); - force_sig(SIGSEGV, current); + force_sig(SIGSEGV); return 0; } diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index 4292ea39baa4..117515564ec7 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -771,6 +771,11 @@ SYSCALL_DEFINE0(rt_sigreturn) if (MSR_TM_ACTIVE(msr)) { /* We recheckpoint on return. */ struct ucontext __user *uc_transact; + + /* Trying to start TM on non TM system */ + if (!cpu_has_feature(CPU_FTR_TM)) + goto badframe; + if (__get_user(uc_transact, &uc->uc_link)) goto badframe; if (restore_tm_sigcontexts(current, &uc->uc_mcontext, @@ -808,7 +813,7 @@ badframe: current->comm, current->pid, "rt_sigreturn", (long)uc, regs->nip, regs->link); - force_sig(SIGSEGV, current); + force_sig(SIGSEGV); return 0; } 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/suspend.c b/arch/powerpc/kernel/suspend.c index c612d50c9d18..b84992c10854 100644 --- a/arch/powerpc/kernel/suspend.c +++ b/arch/powerpc/kernel/suspend.c @@ -7,6 +7,7 @@ */ #include <linux/mm.h> +#include <linux/suspend.h> #include <asm/page.h> #include <asm/sections.h> diff --git a/arch/powerpc/kernel/swsusp_32.S b/arch/powerpc/kernel/swsusp_32.S index 7a919e9a3400..cbdf86228eaa 100644 --- a/arch/powerpc/kernel/swsusp_32.S +++ b/arch/powerpc/kernel/swsusp_32.S @@ -25,11 +25,19 @@ #define SL_IBAT2 0x48 #define SL_DBAT3 0x50 #define SL_IBAT3 0x58 -#define SL_TB 0x60 -#define SL_R2 0x68 -#define SL_CR 0x6c -#define SL_LR 0x70 -#define SL_R12 0x74 /* r12 to r31 */ +#define SL_DBAT4 0x60 +#define SL_IBAT4 0x68 +#define SL_DBAT5 0x70 +#define SL_IBAT5 0x78 +#define SL_DBAT6 0x80 +#define SL_IBAT6 0x88 +#define SL_DBAT7 0x90 +#define SL_IBAT7 0x98 +#define SL_TB 0xa0 +#define SL_R2 0xa8 +#define SL_CR 0xac +#define SL_LR 0xb0 +#define SL_R12 0xb4 /* r12 to r31 */ #define SL_SIZE (SL_R12 + 80) .section .data @@ -114,6 +122,41 @@ _GLOBAL(swsusp_arch_suspend) mfibatl r4,3 stw r4,SL_IBAT3+4(r11) +BEGIN_MMU_FTR_SECTION + mfspr r4,SPRN_DBAT4U + stw r4,SL_DBAT4(r11) + mfspr r4,SPRN_DBAT4L + stw r4,SL_DBAT4+4(r11) + mfspr r4,SPRN_DBAT5U + stw r4,SL_DBAT5(r11) + mfspr r4,SPRN_DBAT5L + stw r4,SL_DBAT5+4(r11) + mfspr r4,SPRN_DBAT6U + stw r4,SL_DBAT6(r11) + mfspr r4,SPRN_DBAT6L + stw r4,SL_DBAT6+4(r11) + mfspr r4,SPRN_DBAT7U + stw r4,SL_DBAT7(r11) + mfspr r4,SPRN_DBAT7L + stw r4,SL_DBAT7+4(r11) + mfspr r4,SPRN_IBAT4U + stw r4,SL_IBAT4(r11) + mfspr r4,SPRN_IBAT4L + stw r4,SL_IBAT4+4(r11) + mfspr r4,SPRN_IBAT5U + stw r4,SL_IBAT5(r11) + mfspr r4,SPRN_IBAT5L + stw r4,SL_IBAT5+4(r11) + mfspr r4,SPRN_IBAT6U + stw r4,SL_IBAT6(r11) + mfspr r4,SPRN_IBAT6L + stw r4,SL_IBAT6+4(r11) + mfspr r4,SPRN_IBAT7U + stw r4,SL_IBAT7(r11) + mfspr r4,SPRN_IBAT7L + stw r4,SL_IBAT7+4(r11) +END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS) + #if 0 /* Backup various CPU config stuffs */ bl __save_cpu_setup @@ -279,27 +322,41 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) mtibatu 3,r4 lwz r4,SL_IBAT3+4(r11) mtibatl 3,r4 -#endif - BEGIN_MMU_FTR_SECTION - li r4,0 + lwz r4,SL_DBAT4(r11) mtspr SPRN_DBAT4U,r4 + lwz r4,SL_DBAT4+4(r11) mtspr SPRN_DBAT4L,r4 + lwz r4,SL_DBAT5(r11) mtspr SPRN_DBAT5U,r4 + lwz r4,SL_DBAT5+4(r11) mtspr SPRN_DBAT5L,r4 + lwz r4,SL_DBAT6(r11) mtspr SPRN_DBAT6U,r4 + lwz r4,SL_DBAT6+4(r11) mtspr SPRN_DBAT6L,r4 + lwz r4,SL_DBAT7(r11) mtspr SPRN_DBAT7U,r4 + lwz r4,SL_DBAT7+4(r11) mtspr SPRN_DBAT7L,r4 + lwz r4,SL_IBAT4(r11) mtspr SPRN_IBAT4U,r4 + lwz r4,SL_IBAT4+4(r11) mtspr SPRN_IBAT4L,r4 + lwz r4,SL_IBAT5(r11) mtspr SPRN_IBAT5U,r4 + lwz r4,SL_IBAT5+4(r11) mtspr SPRN_IBAT5L,r4 + lwz r4,SL_IBAT6(r11) mtspr SPRN_IBAT6U,r4 + lwz r4,SL_IBAT6+4(r11) mtspr SPRN_IBAT6L,r4 + lwz r4,SL_IBAT7(r11) mtspr SPRN_IBAT7U,r4 + lwz r4,SL_IBAT7+4(r11) mtspr SPRN_IBAT7L,r4 END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS) +#endif /* Flush all TLBs */ lis r4,0x1000 diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl index 103655d84b4b..43f736ed47f2 100644 --- a/arch/powerpc/kernel/syscalls/syscall.tbl +++ b/arch/powerpc/kernel/syscalls/syscall.tbl @@ -515,3 +515,5 @@ 431 common fsconfig sys_fsconfig 432 common fsmount sys_fsmount 433 common fspick sys_fspick +434 common pidfd_open sys_pidfd_open +435 nospu clone3 ppc_clone3 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/tm.S b/arch/powerpc/kernel/tm.S index 9fabdce255cd..6ba0fdd1e7f8 100644 --- a/arch/powerpc/kernel/tm.S +++ b/arch/powerpc/kernel/tm.S @@ -148,7 +148,7 @@ _GLOBAL(tm_reclaim) /* Stash the stack pointer away for use after reclaim */ std r1, PACAR1(r13) - /* Clear MSR RI since we are about to change r1, EE is already off. */ + /* Clear MSR RI since we are about to use SCRATCH0, EE is already off */ li r5, 0 mtmsrd r5, 1 @@ -474,7 +474,7 @@ restore_gprs: REST_GPR(7, r7) - /* Clear MSR RI since we are about to change r1. EE is already off */ + /* Clear MSR RI since we are about to use SCRATCH0. EE is already off */ li r5, 0 mtmsrd r5, 1 diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c index 517662a56bdc..7ea0ca044b65 100644 --- a/arch/powerpc/kernel/trace/ftrace.c +++ b/arch/powerpc/kernel/trace/ftrace.c @@ -866,10 +866,6 @@ void arch_ftrace_update_code(int command) #ifdef CONFIG_PPC64 #define PACATOC offsetof(struct paca_struct, kernel_toc) -#define PPC_LO(v) ((v) & 0xffff) -#define PPC_HI(v) (((v) >> 16) & 0xffff) -#define PPC_HA(v) PPC_HI ((v) + 0x8000) - extern unsigned int ftrace_tramp_text[], ftrace_tramp_init[]; int __init ftrace_dyn_arch_init(void) @@ -948,7 +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; @@ -960,7 +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 47df30982de1..82f43535e686 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -297,7 +297,7 @@ NOKPROBE_SYMBOL(die); void user_single_step_report(struct pt_regs *regs) { - force_sig_fault(SIGTRAP, TRAP_TRACE, (void __user *)regs->nip, current); + force_sig_fault(SIGTRAP, TRAP_TRACE, (void __user *)regs->nip); } static void show_signal_msg(int signr, struct pt_regs *regs, int code, @@ -363,7 +363,7 @@ void _exception(int signr, struct pt_regs *regs, int code, unsigned long addr) if (!exception_common(signr, regs, code, addr)) return; - force_sig_fault(signr, code, (void __user *)addr, current); + force_sig_fault(signr, code, (void __user *)addr); } /* @@ -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: *; }; |