diff options
Diffstat (limited to 'arch/powerpc/kernel')
72 files changed, 814 insertions, 1402 deletions
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index f43c1198768c..7bf6b16b2d93 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -70,7 +70,7 @@ obj-y := cputable.o syscalls.o switch.o \ signal.o sysfs.o cacheinfo.o time.o \ prom.o traps.o setup-common.o \ udbg.o misc.o io.o misc_$(BITS).o \ - of_platform.o prom_parse.o firmware.o \ + prom_parse.o firmware.o \ hw_breakpoint_constraints.o interrupt.o \ kdebugfs.o stacktrace.o syscall.o obj-y += ptrace/ @@ -126,7 +126,7 @@ obj-$(CONFIG_PPC_BOOK3S_32) += head_book3s_32.o obj-$(CONFIG_44x) += head_44x.o obj-$(CONFIG_PPC_8xx) += head_8xx.o obj-$(CONFIG_PPC_85xx) += head_85xx.o -extra-y += vmlinux.lds +always-$(KBUILD_BUILTIN) += vmlinux.lds obj-$(CONFIG_RELOCATABLE) += reloc_$(BITS).o @@ -149,11 +149,6 @@ obj-$(CONFIG_PCI) += pci_$(BITS).o $(pci64-y) \ pci-common.o pci_of_scan.o obj-$(CONFIG_PCI_MSI) += msi.o -obj-$(CONFIG_AUDIT) += audit.o -obj64-$(CONFIG_AUDIT) += compat_audit.o - -obj-$(CONFIG_PPC_IO_WORKAROUNDS) += io-workarounds.o - obj-y += trace/ ifneq ($(CONFIG_PPC_INDIRECT_PIO),y) @@ -162,9 +157,7 @@ endif obj64-$(CONFIG_PPC_TRANSACTIONAL_MEM) += tm.o -ifneq ($(CONFIG_XMON)$(CONFIG_KEXEC_CORE)(CONFIG_PPC_BOOK3S),) obj-y += ppc_save_regs.o -endif obj-$(CONFIG_EPAPR_PARAVIRT) += epapr_paravirt.o epapr_hcalls.o obj-$(CONFIG_KVM_GUEST) += kvm.o kvm_emul.o @@ -203,7 +196,9 @@ obj-$(CONFIG_ALTIVEC) += vector.o obj-$(CONFIG_PPC_OF_BOOT_TRAMPOLINE) += prom_init.o obj64-$(CONFIG_PPC_OF_BOOT_TRAMPOLINE) += prom_entry_64.o -extra-$(CONFIG_PPC_OF_BOOT_TRAMPOLINE) += prom_init_check +ifdef KBUILD_BUILTIN +always-$(CONFIG_PPC_OF_BOOT_TRAMPOLINE) += prom_init_check +endif obj-$(CONFIG_PPC64) += $(obj64-y) obj-$(CONFIG_PPC32) += $(obj32-y) diff --git a/arch/powerpc/kernel/align.c b/arch/powerpc/kernel/align.c index 3e37ece06739..61409431138f 100644 --- a/arch/powerpc/kernel/align.c +++ b/arch/powerpc/kernel/align.c @@ -165,25 +165,23 @@ static int emulate_spe(struct pt_regs *regs, unsigned int reg, temp.ll = data.ll = 0; p = addr; - if (!user_read_access_begin(addr, nb)) - return -EFAULT; - - switch (nb) { - case 8: - unsafe_get_user(temp.v[0], p++, Efault_read); - unsafe_get_user(temp.v[1], p++, Efault_read); - unsafe_get_user(temp.v[2], p++, Efault_read); - unsafe_get_user(temp.v[3], p++, Efault_read); - fallthrough; - case 4: - unsafe_get_user(temp.v[4], p++, Efault_read); - unsafe_get_user(temp.v[5], p++, Efault_read); - fallthrough; - case 2: - unsafe_get_user(temp.v[6], p++, Efault_read); - unsafe_get_user(temp.v[7], p++, Efault_read); + scoped_user_read_access_size(addr, nb, efault) { + switch (nb) { + case 8: + unsafe_get_user(temp.v[0], p++, efault); + unsafe_get_user(temp.v[1], p++, efault); + unsafe_get_user(temp.v[2], p++, efault); + unsafe_get_user(temp.v[3], p++, efault); + fallthrough; + case 4: + unsafe_get_user(temp.v[4], p++, efault); + unsafe_get_user(temp.v[5], p++, efault); + fallthrough; + case 2: + unsafe_get_user(temp.v[6], p++, efault); + unsafe_get_user(temp.v[7], p++, efault); + } } - user_read_access_end(); switch (instr) { case EVLDD: @@ -252,25 +250,23 @@ static int emulate_spe(struct pt_regs *regs, unsigned int reg, if (flags & ST) { p = addr; - if (!user_write_access_begin(addr, nb)) - return -EFAULT; - - switch (nb) { - case 8: - unsafe_put_user(data.v[0], p++, Efault_write); - unsafe_put_user(data.v[1], p++, Efault_write); - unsafe_put_user(data.v[2], p++, Efault_write); - unsafe_put_user(data.v[3], p++, Efault_write); - fallthrough; - case 4: - unsafe_put_user(data.v[4], p++, Efault_write); - unsafe_put_user(data.v[5], p++, Efault_write); - fallthrough; - case 2: - unsafe_put_user(data.v[6], p++, Efault_write); - unsafe_put_user(data.v[7], p++, Efault_write); + scoped_user_write_access_size(addr, nb, efault) { + switch (nb) { + case 8: + unsafe_put_user(data.v[0], p++, efault); + unsafe_put_user(data.v[1], p++, efault); + unsafe_put_user(data.v[2], p++, efault); + unsafe_put_user(data.v[3], p++, efault); + fallthrough; + case 4: + unsafe_put_user(data.v[4], p++, efault); + unsafe_put_user(data.v[5], p++, efault); + fallthrough; + case 2: + unsafe_put_user(data.v[6], p++, efault); + unsafe_put_user(data.v[7], p++, efault); + } } - user_write_access_end(); } else { *evr = data.w[0]; regs->gpr[reg] = data.w[1]; @@ -278,12 +274,7 @@ static int emulate_spe(struct pt_regs *regs, unsigned int reg, return 1; -Efault_read: - user_read_access_end(); - return -EFAULT; - -Efault_write: - user_write_access_end(); +efault: return -EFAULT; } #endif /* CONFIG_SPE */ diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 7a390bd4f4af..46149f326fd4 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -8,6 +8,7 @@ * compile this file to assembler, and then extract the * #defines from the assembly-language output. */ +#define COMPILE_OFFSETS #include <linux/compat.h> #include <linux/signal.h> @@ -330,11 +331,10 @@ int main(void) #ifndef CONFIG_PPC64 DEFINE(TASK_SIZE, TASK_SIZE); - DEFINE(NUM_USER_SEGMENTS, TASK_SIZE>>28); + DEFINE(NUM_USER_SEGMENTS, ALIGN(TASK_SIZE, SZ_256M) >> 28); #endif /* ! CONFIG_PPC64 */ /* datapage offsets for use by vdso */ - OFFSET(VDSO_DATA_OFFSET, vdso_arch_data, data); OFFSET(CFG_TB_TICKS_PER_SEC, vdso_arch_data, tb_ticks_per_sec); #ifdef CONFIG_PPC64 OFFSET(CFG_ICACHE_BLOCKSZ, vdso_arch_data, icache_block_size); diff --git a/arch/powerpc/kernel/audit.c b/arch/powerpc/kernel/audit.c deleted file mode 100644 index 92298d6a3a37..000000000000 --- a/arch/powerpc/kernel/audit.c +++ /dev/null @@ -1,87 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <linux/init.h> -#include <linux/types.h> -#include <linux/audit.h> -#include <asm/unistd.h> - -#include "audit_32.h" - -static unsigned dir_class[] = { -#include <asm-generic/audit_dir_write.h> -~0U -}; - -static unsigned read_class[] = { -#include <asm-generic/audit_read.h> -~0U -}; - -static unsigned write_class[] = { -#include <asm-generic/audit_write.h> -~0U -}; - -static unsigned chattr_class[] = { -#include <asm-generic/audit_change_attr.h> -~0U -}; - -static unsigned signal_class[] = { -#include <asm-generic/audit_signal.h> -~0U -}; - -int audit_classify_arch(int arch) -{ -#ifdef CONFIG_PPC64 - if (arch == AUDIT_ARCH_PPC) - return 1; -#endif - return 0; -} - -int audit_classify_syscall(int abi, unsigned syscall) -{ -#ifdef CONFIG_PPC64 - if (abi == AUDIT_ARCH_PPC) - return ppc32_classify_syscall(syscall); -#endif - switch(syscall) { - case __NR_open: - return AUDITSC_OPEN; - case __NR_openat: - return AUDITSC_OPENAT; - case __NR_socketcall: - return AUDITSC_SOCKETCALL; - case __NR_execve: - return AUDITSC_EXECVE; - case __NR_openat2: - return AUDITSC_OPENAT2; - default: - return AUDITSC_NATIVE; - } -} - -static int __init audit_classes_init(void) -{ -#ifdef CONFIG_PPC64 - extern __u32 ppc32_dir_class[]; - extern __u32 ppc32_write_class[]; - extern __u32 ppc32_read_class[]; - extern __u32 ppc32_chattr_class[]; - extern __u32 ppc32_signal_class[]; - audit_register_class(AUDIT_CLASS_WRITE_32, ppc32_write_class); - audit_register_class(AUDIT_CLASS_READ_32, ppc32_read_class); - audit_register_class(AUDIT_CLASS_DIR_WRITE_32, ppc32_dir_class); - audit_register_class(AUDIT_CLASS_CHATTR_32, ppc32_chattr_class); - audit_register_class(AUDIT_CLASS_SIGNAL_32, ppc32_signal_class); -#endif - audit_register_class(AUDIT_CLASS_WRITE, write_class); - audit_register_class(AUDIT_CLASS_READ, read_class); - audit_register_class(AUDIT_CLASS_DIR_WRITE, dir_class); - audit_register_class(AUDIT_CLASS_CHATTR, chattr_class); - audit_register_class(AUDIT_CLASS_SIGNAL, signal_class); - return 0; -} - -__initcall(audit_classes_init); diff --git a/arch/powerpc/kernel/btext.c b/arch/powerpc/kernel/btext.c index 7f63f1cdc6c3..b23dddfce26d 100644 --- a/arch/powerpc/kernel/btext.c +++ b/arch/powerpc/kernel/btext.c @@ -6,6 +6,7 @@ */ #include <linux/kernel.h> #include <linux/string.h> +#include <linux/hex.h> #include <linux/init.h> #include <linux/export.h> #include <linux/font.h> @@ -20,6 +21,7 @@ #include <asm/io.h> #include <asm/processor.h> #include <asm/udbg.h> +#include <asm/setup.h> #define NO_SCROLL @@ -463,7 +465,7 @@ static noinline void draw_byte(unsigned char c, long locX, long locY) { unsigned char *base = calc_base(locX << 3, locY << 4); unsigned int font_index = c * 16; - const unsigned char *font = font_sun_8x16.data + font_index; + const unsigned char *font = PTRRELOC(font_sun_8x16.data) + font_index; int rb = dispDeviceRowBytes; rmci_maybe_on(); diff --git a/arch/powerpc/kernel/cacheinfo.c b/arch/powerpc/kernel/cacheinfo.c index 0fcc463b02e2..90d51d9b3ed2 100644 --- a/arch/powerpc/kernel/cacheinfo.c +++ b/arch/powerpc/kernel/cacheinfo.c @@ -157,7 +157,7 @@ static struct cache *new_cache(int type, int level, { struct cache *cache; - cache = kzalloc(sizeof(*cache), GFP_KERNEL); + cache = kzalloc_obj(*cache); if (cache) cache_init(cache, type, level, ofnode, group_id); @@ -540,7 +540,7 @@ static struct cache_dir *cacheinfo_create_cache_dir(unsigned int cpu_id) if (!kobj) goto err; - cache_dir = kzalloc(sizeof(*cache_dir), GFP_KERNEL); + cache_dir = kzalloc_obj(*cache_dir); if (!cache_dir) goto err; @@ -788,7 +788,7 @@ static void cacheinfo_create_index_dir(struct cache *cache, int index, struct cache_index_dir *index_dir; int rc; - index_dir = kzalloc(sizeof(*index_dir), GFP_KERNEL); + index_dir = kzalloc_obj(*index_dir); if (!index_dir) return; diff --git a/arch/powerpc/kernel/compat_audit.c b/arch/powerpc/kernel/compat_audit.c deleted file mode 100644 index 57b38c592b9f..000000000000 --- a/arch/powerpc/kernel/compat_audit.c +++ /dev/null @@ -1,49 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#undef __powerpc64__ -#include <linux/audit_arch.h> -#include <asm/unistd.h> - -#include "audit_32.h" - -unsigned ppc32_dir_class[] = { -#include <asm-generic/audit_dir_write.h> -~0U -}; - -unsigned ppc32_chattr_class[] = { -#include <asm-generic/audit_change_attr.h> -~0U -}; - -unsigned ppc32_write_class[] = { -#include <asm-generic/audit_write.h> -~0U -}; - -unsigned ppc32_read_class[] = { -#include <asm-generic/audit_read.h> -~0U -}; - -unsigned ppc32_signal_class[] = { -#include <asm-generic/audit_signal.h> -~0U -}; - -int ppc32_classify_syscall(unsigned syscall) -{ - switch(syscall) { - case __NR_open: - return AUDITSC_OPEN; - case __NR_openat: - return AUDITSC_OPENAT; - case __NR_socketcall: - return AUDITSC_SOCKETCALL; - case __NR_execve: - return AUDITSC_EXECVE; - case __NR_openat2: - return AUDITSC_OPENAT2; - default: - return AUDITSC_COMPAT; - } -} diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c index f0ae39e77e37..8b4de508d2eb 100644 --- a/arch/powerpc/kernel/dma-iommu.c +++ b/arch/powerpc/kernel/dma-iommu.c @@ -14,7 +14,7 @@ #define can_map_direct(dev, addr) \ ((dev)->bus_dma_limit >= phys_to_dma((dev), (addr))) -bool arch_dma_map_page_direct(struct device *dev, phys_addr_t addr) +bool arch_dma_map_phys_direct(struct device *dev, phys_addr_t addr) { if (likely(!dev->bus_dma_limit)) return false; @@ -24,7 +24,7 @@ bool arch_dma_map_page_direct(struct device *dev, phys_addr_t addr) #define is_direct_handle(dev, h) ((h) >= (dev)->archdata.dma_offset) -bool arch_dma_unmap_page_direct(struct device *dev, dma_addr_t dma_handle) +bool arch_dma_unmap_phys_direct(struct device *dev, dma_addr_t dma_handle) { if (likely(!dev->bus_dma_limit)) return false; @@ -65,6 +65,21 @@ bool arch_dma_unmap_sg_direct(struct device *dev, struct scatterlist *sg, return true; } +bool arch_dma_alloc_direct(struct device *dev) +{ + if (dev->dma_ops_bypass && dev->bus_dma_limit) + return true; + + return false; +} + +bool arch_dma_free_direct(struct device *dev, dma_addr_t dma_handle) +{ + if (!dev->dma_ops_bypass || !dev->bus_dma_limit) + return false; + + return is_direct_handle(dev, dma_handle); +} #endif /* CONFIG_ARCH_HAS_DMA_MAP_DIRECT */ /* @@ -93,28 +108,26 @@ static void dma_iommu_free_coherent(struct device *dev, size_t size, /* Creates TCEs for a user provided buffer. The user buffer must be * contiguous real kernel storage (not vmalloc). The address passed here - * comprises a page address and offset into that page. The dma_addr_t - * returned will point to the same byte within the page as was passed in. + * is a physical address to that page. The dma_addr_t returned will point + * to the same byte within the page as was passed in. */ -static dma_addr_t dma_iommu_map_page(struct device *dev, struct page *page, - unsigned long offset, size_t size, +static dma_addr_t dma_iommu_map_phys(struct device *dev, phys_addr_t phys, + size_t size, enum dma_data_direction direction, unsigned long attrs) { - return iommu_map_page(dev, get_iommu_table_base(dev), page, offset, - size, dma_get_mask(dev), direction, attrs); + return iommu_map_phys(dev, get_iommu_table_base(dev), phys, size, + dma_get_mask(dev), direction, attrs); } - -static void dma_iommu_unmap_page(struct device *dev, dma_addr_t dma_handle, +static void dma_iommu_unmap_phys(struct device *dev, dma_addr_t dma_handle, size_t size, enum dma_data_direction direction, unsigned long attrs) { - iommu_unmap_page(get_iommu_table_base(dev), dma_handle, size, direction, + iommu_unmap_phys(get_iommu_table_base(dev), dma_handle, size, direction, attrs); } - static int dma_iommu_map_sg(struct device *dev, struct scatterlist *sglist, int nelems, enum dma_data_direction direction, unsigned long attrs) @@ -136,7 +149,7 @@ static bool dma_iommu_bypass_supported(struct device *dev, u64 mask) struct pci_dev *pdev = to_pci_dev(dev); struct pci_controller *phb = pci_bus_to_host(pdev->bus); - if (iommu_fixed_is_weak || !phb->controller_ops.iommu_bypass_supported) + if (!phb->controller_ops.iommu_bypass_supported) return false; return phb->controller_ops.iommu_bypass_supported(pdev, mask); } @@ -148,17 +161,12 @@ int dma_iommu_dma_supported(struct device *dev, u64 mask) if (dev_is_pci(dev) && dma_iommu_bypass_supported(dev, mask)) { /* - * dma_iommu_bypass_supported() sets dma_max when there is - * 1:1 mapping but it is somehow limited. - * ibm,pmemory is one example. + * fixed ops will be used for RAM. This is limited by + * bus_dma_limit which is set when RAM is pre-mapped. */ - dev->dma_ops_bypass = dev->bus_dma_limit == 0; - if (!dev->dma_ops_bypass) - dev_warn(dev, - "iommu: 64-bit OK but direct DMA is limited by %llx\n", - dev->bus_dma_limit); - else - dev_dbg(dev, "iommu: 64-bit OK, using fixed ops\n"); + dev->dma_ops_bypass = true; + dev_info(dev, "iommu: 64-bit OK but direct DMA is limited by %llx\n", + dev->bus_dma_limit); return 1; } @@ -211,8 +219,8 @@ const struct dma_map_ops dma_iommu_ops = { .map_sg = dma_iommu_map_sg, .unmap_sg = dma_iommu_unmap_sg, .dma_supported = dma_iommu_dma_supported, - .map_page = dma_iommu_map_page, - .unmap_page = dma_iommu_unmap_page, + .map_phys = dma_iommu_map_phys, + .unmap_phys = dma_iommu_unmap_phys, .get_required_mask = dma_iommu_get_required_mask, .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 83fe99861eb1..bb836f02101c 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -1139,6 +1139,7 @@ int eeh_unfreeze_pe(struct eeh_pe *pe) return ret; } +EXPORT_SYMBOL_GPL(eeh_unfreeze_pe); static struct pci_device_id eeh_reset_ids[] = { @@ -1208,16 +1209,16 @@ int eeh_dev_open(struct pci_dev *pdev) struct eeh_dev *edev; int ret = -ENODEV; - mutex_lock(&eeh_dev_mutex); + guard(mutex)(&eeh_dev_mutex); /* No PCI device ? */ if (!pdev) - goto out; + return ret; /* No EEH device or PE ? */ edev = pci_dev_to_eeh_dev(pdev); if (!edev || !edev->pe) - goto out; + return ret; /* * The PE might have been put into frozen state, but we @@ -1227,16 +1228,12 @@ int eeh_dev_open(struct pci_dev *pdev) */ ret = eeh_pe_change_owner(edev->pe); if (ret) - goto out; + return ret; /* Increase PE's pass through count */ atomic_inc(&edev->pe->pass_dev_cnt); - mutex_unlock(&eeh_dev_mutex); return 0; -out: - mutex_unlock(&eeh_dev_mutex); - return ret; } EXPORT_SYMBOL_GPL(eeh_dev_open); @@ -1252,22 +1249,20 @@ void eeh_dev_release(struct pci_dev *pdev) { struct eeh_dev *edev; - mutex_lock(&eeh_dev_mutex); + guard(mutex)(&eeh_dev_mutex); /* No PCI device ? */ if (!pdev) - goto out; + return; /* No EEH device ? */ edev = pci_dev_to_eeh_dev(pdev); if (!edev || !edev->pe || !eeh_pe_passed(edev->pe)) - goto out; + return; /* Decrease PE's pass through count */ WARN_ON(atomic_dec_if_positive(&edev->pe->pass_dev_cnt) < 0); eeh_pe_change_owner(edev->pe); -out: - mutex_unlock(&eeh_dev_mutex); } EXPORT_SYMBOL(eeh_dev_release); @@ -1509,6 +1504,8 @@ int eeh_pe_configure(struct eeh_pe *pe) /* Invalid PE ? */ if (!pe) return -ENODEV; + else + ret = eeh_ops->configure_bridge(pe); return ret; } diff --git a/arch/powerpc/kernel/eeh_cache.c b/arch/powerpc/kernel/eeh_cache.c index 2f9dbf8ad2ee..57e5382f790a 100644 --- a/arch/powerpc/kernel/eeh_cache.c +++ b/arch/powerpc/kernel/eeh_cache.c @@ -138,7 +138,7 @@ eeh_addr_cache_insert(struct pci_dev *dev, resource_size_t alo, return piar; } } - piar = kzalloc(sizeof(struct pci_io_addr_range), GFP_ATOMIC); + piar = kzalloc_obj(struct pci_io_addr_range, GFP_ATOMIC); if (!piar) return NULL; diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index 7efe04c68f0f..028f69158532 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -257,13 +257,12 @@ static void eeh_pe_report_edev(struct eeh_dev *edev, eeh_report_fn fn, struct pci_driver *driver; enum pci_ers_result new_result; - 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"); + *result = PCI_ERS_RESULT_DISCONNECT; return; } device_lock(&pdev->dev); @@ -304,8 +303,9 @@ static void eeh_pe_report(const char *name, struct eeh_pe *root, struct eeh_dev *edev, *tmp; pr_info("EEH: Beginning: '%s'\n", name); - eeh_for_each_pe(root, pe) eeh_pe_for_each_dev(pe, edev, tmp) - eeh_pe_report_edev(edev, fn, result); + eeh_for_each_pe(root, pe) + eeh_pe_for_each_dev(pe, edev, tmp) + eeh_pe_report_edev(edev, fn, result); if (result) pr_info("EEH: Finished:'%s' with aggregate recovery state:'%s'\n", name, pci_ers_result_name(*result)); @@ -334,7 +334,7 @@ static enum pci_ers_result eeh_report_error(struct eeh_dev *edev, rc = driver->err_handler->error_detected(pdev, pci_channel_io_frozen); edev->in_error = true; - pci_uevent_ers(pdev, PCI_ERS_RESULT_NONE); + pci_uevent_ers(pdev, rc); return rc; } @@ -383,6 +383,8 @@ static void eeh_dev_restore_state(struct eeh_dev *edev, void *userdata) if (!edev) return; + pci_lock_rescan_remove(); + /* * The content in the config space isn't saved because * the blocked config space on some adapters. We have @@ -393,14 +395,19 @@ 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); + pci_unlock_rescan_remove(); return; } pdev = eeh_dev_to_pci_dev(edev); - if (!pdev) + if (!pdev) { + pci_unlock_rescan_remove(); return; + } pci_restore_state(pdev); + + pci_unlock_rescan_remove(); } /** @@ -647,9 +654,7 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus, if (any_passed || driver_eeh_aware || (pe->type & EEH_PE_VF)) { eeh_pe_dev_traverse(pe, eeh_rmv_device, rmv_data); } else { - pci_lock_rescan_remove(); pci_hp_remove_devices(bus); - pci_unlock_rescan_remove(); } /* @@ -665,8 +670,6 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus, if (rc) return rc; - pci_lock_rescan_remove(); - /* Restore PE */ eeh_ops->configure_bridge(pe); eeh_pe_restore_bars(pe); @@ -674,7 +677,6 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus, /* Clear frozen state */ rc = eeh_clear_pe_frozen_state(pe, false); if (rc) { - pci_unlock_rescan_remove(); return rc; } @@ -709,7 +711,6 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus, pe->tstamp = tstamp; pe->freeze_count = cnt; - pci_unlock_rescan_remove(); return 0; } @@ -843,10 +844,13 @@ void eeh_handle_normal_event(struct eeh_pe *pe) {LIST_HEAD_INIT(rmv_data.removed_vf_list), 0}; int devices = 0; - bus = eeh_pe_bus_get(pe); + pci_lock_rescan_remove(); + + bus = eeh_pe_bus_get_nolock(pe); if (!bus) { pr_err("%s: Cannot find PCI bus for PHB#%x-PE#%x\n", __func__, pe->phb->global_number, pe->addr); + pci_unlock_rescan_remove(); return; } @@ -882,14 +886,15 @@ void eeh_handle_normal_event(struct eeh_pe *pe) /* Log the event */ if (pe->type & EEH_PE_PHB) { pr_err("EEH: Recovering PHB#%x, location: %s\n", - pe->phb->global_number, eeh_pe_loc_get(pe)); + pe->phb->global_number, eeh_pe_loc_get_bus(bus)); } else { struct eeh_pe *phb_pe = eeh_phb_pe_get(pe->phb); pr_err("EEH: Recovering PHB#%x-PE#%x\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)); + eeh_pe_loc_get_bus(bus), + eeh_pe_loc_get_bus(eeh_pe_bus_get_nolock(phb_pe))); } #ifdef CONFIG_STACKTRACE @@ -907,7 +912,7 @@ void eeh_handle_normal_event(struct eeh_pe *pe) /* 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]); + pr_err("EEH: [%p] %pS\n", ptrs[i], ptrs[i]); pe->trace_entries = 0; } @@ -1094,10 +1099,15 @@ recover_failed: eeh_pe_state_clear(pe, EEH_PE_PRI_BUS, true); eeh_pe_dev_mode_mark(pe, EEH_DEV_REMOVED); - pci_lock_rescan_remove(); - pci_hp_remove_devices(bus); - pci_unlock_rescan_remove(); + bus = eeh_pe_bus_get_nolock(pe); + if (bus) + pci_hp_remove_devices(bus); + else + pr_err("%s: PCI bus for PHB#%x-PE#%x disappeared\n", + __func__, pe->phb->global_number, pe->addr); + /* The passed PE should no longer be used */ + pci_unlock_rescan_remove(); return; } @@ -1114,6 +1124,8 @@ out: eeh_clear_slot_attention(edev->pdev); eeh_pe_state_clear(pe, EEH_PE_RECOVERING, true); + + pci_unlock_rescan_remove(); } /** @@ -1132,6 +1144,7 @@ void eeh_handle_special_event(void) unsigned long flags; int rc; + pci_lock_rescan_remove(); do { rc = eeh_ops->next_error(&pe); @@ -1171,10 +1184,12 @@ void eeh_handle_special_event(void) break; case EEH_NEXT_ERR_NONE: + pci_unlock_rescan_remove(); return; default: pr_warn("%s: Invalid value %d from next_error()\n", __func__, rc); + pci_unlock_rescan_remove(); return; } @@ -1186,7 +1201,9 @@ 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); + pci_unlock_rescan_remove(); eeh_handle_normal_event(pe); + pci_lock_rescan_remove(); } else { eeh_for_each_pe(pe, tmp_pe) eeh_pe_for_each_dev(tmp_pe, edev, tmp_edev) @@ -1199,7 +1216,6 @@ void eeh_handle_special_event(void) eeh_report_failure, NULL); eeh_set_channel_state(pe, pci_channel_io_perm_failure); - pci_lock_rescan_remove(); list_for_each_entry(hose, &hose_list, list_node) { phb_pe = eeh_phb_pe_get(hose); if (!phb_pe || @@ -1207,7 +1223,7 @@ void eeh_handle_special_event(void) (phb_pe->state & EEH_PE_RECOVERING)) continue; - bus = eeh_pe_bus_get(phb_pe); + bus = eeh_pe_bus_get_nolock(phb_pe); if (!bus) { pr_err("%s: Cannot find PCI bus for " "PHB#%x-PE#%x\n", @@ -1218,7 +1234,6 @@ void eeh_handle_special_event(void) } pci_hp_remove_devices(bus); } - pci_unlock_rescan_remove(); } /* @@ -1228,4 +1243,6 @@ void eeh_handle_special_event(void) if (rc == EEH_NEXT_ERR_DEAD_IOC) break; } while (rc != EEH_NEXT_ERR_NONE); + + pci_unlock_rescan_remove(); } diff --git a/arch/powerpc/kernel/eeh_event.c b/arch/powerpc/kernel/eeh_event.c index c23a454af08a..279c1ceccd6d 100644 --- a/arch/powerpc/kernel/eeh_event.c +++ b/arch/powerpc/kernel/eeh_event.c @@ -104,7 +104,7 @@ int __eeh_send_failure_event(struct eeh_pe *pe) unsigned long flags; struct eeh_event *event; - event = kzalloc(sizeof(*event), GFP_ATOMIC); + event = kzalloc_obj(*event, GFP_ATOMIC); if (!event) { pr_err("EEH: out of memory, event not handled\n"); return -ENOMEM; diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c index d283d281d28e..040e8f69a4aa 100644 --- a/arch/powerpc/kernel/eeh_pe.c +++ b/arch/powerpc/kernel/eeh_pe.c @@ -671,10 +671,12 @@ static void eeh_bridge_check_link(struct eeh_dev *edev) eeh_ops->write_config(edev, cap + PCI_EXP_LNKCTL, 2, val); /* Check link */ - if (!edev->pdev->link_active_reporting) { - eeh_edev_dbg(edev, "No link reporting capability\n"); - msleep(1000); - return; + if (edev->pdev) { + if (!edev->pdev->link_active_reporting) { + eeh_edev_dbg(edev, "No link reporting capability\n"); + msleep(1000); + return; + } } /* Wait the link is up until timeout (5s) */ @@ -810,6 +812,24 @@ void eeh_pe_restore_bars(struct eeh_pe *pe) const char *eeh_pe_loc_get(struct eeh_pe *pe) { struct pci_bus *bus = eeh_pe_bus_get(pe); + return eeh_pe_loc_get_bus(bus); +} + +/** + * eeh_pe_loc_get_bus - Retrieve location code binding to the given PCI bus + * @bus: PCI bus + * + * Retrieve the location code associated with the given PCI bus. If the bus + * is a root bus, the location code is fetched from the PHB device tree node + * or root port. Otherwise, the location code is obtained from the device + * tree node of the upstream bridge of the bus. The function walks up the + * bus hierarchy if necessary, checking each node for the appropriate + * location code property ("ibm,io-base-loc-code" for root buses, + * "ibm,slot-location-code" for others). If no location code is found, + * returns "N/A". + */ +const char *eeh_pe_loc_get_bus(struct pci_bus *bus) +{ struct device_node *dn; const char *loc = NULL; @@ -836,8 +856,9 @@ const char *eeh_pe_loc_get(struct eeh_pe *pe) } /** - * eeh_pe_bus_get - Retrieve PCI bus according to the given PE + * _eeh_pe_bus_get - Retrieve PCI bus according to the given PE * @pe: EEH PE + * @do_lock: Is the caller already held the pci_lock_rescan_remove? * * Retrieve the PCI bus according to the given PE. Basically, * there're 3 types of PEs: PHB/Bus/Device. For PHB PE, the @@ -845,7 +866,7 @@ const char *eeh_pe_loc_get(struct eeh_pe *pe) * returned for BUS PE. However, we don't have associated PCI * bus for DEVICE PE. */ -struct pci_bus *eeh_pe_bus_get(struct eeh_pe *pe) +static struct pci_bus *_eeh_pe_bus_get(struct eeh_pe *pe, bool do_lock) { struct eeh_dev *edev; struct pci_dev *pdev; @@ -860,11 +881,58 @@ struct pci_bus *eeh_pe_bus_get(struct eeh_pe *pe) /* Retrieve the parent PCI bus of first (top) PCI device */ edev = list_first_entry_or_null(&pe->edevs, struct eeh_dev, entry); - pci_lock_rescan_remove(); + if (do_lock) + pci_lock_rescan_remove(); pdev = eeh_dev_to_pci_dev(edev); if (pdev) bus = pdev->bus; - pci_unlock_rescan_remove(); + if (do_lock) + pci_unlock_rescan_remove(); return bus; } + +/** + * eeh_pe_bus_get - Retrieve PCI bus associated with the given EEH PE, locking + * if needed + * @pe: Pointer to the EEH PE + * + * This function is a wrapper around _eeh_pe_bus_get(), which retrieves the PCI + * bus associated with the provided EEH PE structure. It acquires the PCI + * rescans lock to ensure safe access to shared data during the retrieval + * process. This function should be used when the caller requires the PCI bus + * while holding the rescan/remove lock, typically during operations that modify + * or inspect PCIe device state in a safe manner. + * + * RETURNS: + * A pointer to the PCI bus associated with the EEH PE, or NULL if none found. + */ + +struct pci_bus *eeh_pe_bus_get(struct eeh_pe *pe) +{ + return _eeh_pe_bus_get(pe, true); +} + +/** + * eeh_pe_bus_get_nolock - Retrieve PCI bus associated with the given EEH PE + * without locking + * @pe: Pointer to the EEH PE + * + * This function is a variant of _eeh_pe_bus_get() that retrieves the PCI bus + * associated with the specified EEH PE without acquiring the + * pci_lock_rescan_remove lock. It should only be used when the caller can + * guarantee safe access to PE structures without the need for that lock, + * typically in contexts where the lock is already held locking is otherwise + * managed. + * + * RETURNS: + * pointer to the PCI bus associated with the EEH PE, or NULL if none is found. + * + * NOTE: + * Use this function carefully to avoid race conditions and data corruption. + */ + +struct pci_bus *eeh_pe_bus_get_nolock(struct eeh_pe *pe) +{ + return _eeh_pe_bus_get(pe, false); +} diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S index f4a8c9877249..d8426251b1cd 100644 --- a/arch/powerpc/kernel/entry_32.S +++ b/arch/powerpc/kernel/entry_32.S @@ -168,6 +168,7 @@ syscall_exit_finish: REST_GPR(0, r1) REST_GPRS(3, 12, r1) b 1b +_ASM_NOKPROBE_SYMBOL(syscall_exit_finish) #ifdef CONFIG_44x .L44x_icache_flush: @@ -216,7 +217,7 @@ fast_exception_return: beq 3f /* if not, we've got problems */ #endif -2: lwz r10,_CCR(r11) + lwz r10,_CCR(r11) REST_GPRS(1, 6, r11) mtcr r10 lwz r10,_LINK(r11) @@ -224,13 +225,10 @@ fast_exception_return: /* Clear the exception marker on the stack to avoid confusing stacktrace */ li r10, 0 stw r10, 8(r11) - REST_GPR(10, r11) -#if defined(CONFIG_PPC_8xx) && defined(CONFIG_PERF_EVENTS) - mtspr SPRN_NRI, r0 -#endif mtspr SPRN_SRR1,r9 mtspr SPRN_SRR0,r12 REST_GPR(9, r11) + REST_GPR(10, r11) REST_GPR(12, r11) REST_GPR(11, r11) rfi @@ -263,10 +261,9 @@ interrupt_return: mtspr SPRN_SRR1,r12 BEGIN_FTR_SECTION + lwarx r0,0,r1 +END_FTR_SECTION_IFSET(CPU_FTR_NEED_PAIRED_STWCX) stwcx. r0,0,r1 /* to clear the reservation */ -FTR_SECTION_ELSE - lwarx r0,0,r1 -ALT_FTR_SECTION_END_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS) lwz r3,_CCR(r1) lwz r4,_LINK(r1) @@ -306,10 +303,9 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS) mtspr SPRN_SRR1,r12 BEGIN_FTR_SECTION + lwarx r0,0,r1 +END_FTR_SECTION_IFSET(CPU_FTR_NEED_PAIRED_STWCX) stwcx. r0,0,r1 /* to clear the reservation */ -FTR_SECTION_ELSE - lwarx r0,0,r1 -ALT_FTR_SECTION_END_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS) lwz r3,_LINK(r1) lwz r4,_CTR(r1) diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 195b075d116c..b7229430ca94 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -2537,27 +2537,8 @@ EXC_REAL_NONE(0x1000, 0x100) EXC_VIRT_NONE(0x5000, 0x100) EXC_REAL_NONE(0x1100, 0x100) EXC_VIRT_NONE(0x5100, 0x100) - -#ifdef CONFIG_CBE_RAS -INT_DEFINE_BEGIN(cbe_system_error) - IVEC=0x1200 - IHSRR=1 -INT_DEFINE_END(cbe_system_error) - -EXC_REAL_BEGIN(cbe_system_error, 0x1200, 0x100) - GEN_INT_ENTRY cbe_system_error, virt=0 -EXC_REAL_END(cbe_system_error, 0x1200, 0x100) -EXC_VIRT_NONE(0x5200, 0x100) -EXC_COMMON_BEGIN(cbe_system_error_common) - GEN_COMMON cbe_system_error - addi r3,r1,STACK_INT_FRAME_REGS - bl CFUNC(cbe_system_error_exception) - b interrupt_return_hsrr - -#else /* CONFIG_CBE_RAS */ EXC_REAL_NONE(0x1200, 0x100) EXC_VIRT_NONE(0x5200, 0x100) -#endif /** * Interrupt 0x1300 - Instruction Address Breakpoint Interrupt. @@ -2708,26 +2689,8 @@ EXC_COMMON_BEGIN(denorm_exception_common) b interrupt_return_hsrr -#ifdef CONFIG_CBE_RAS -INT_DEFINE_BEGIN(cbe_maintenance) - IVEC=0x1600 - IHSRR=1 -INT_DEFINE_END(cbe_maintenance) - -EXC_REAL_BEGIN(cbe_maintenance, 0x1600, 0x100) - GEN_INT_ENTRY cbe_maintenance, virt=0 -EXC_REAL_END(cbe_maintenance, 0x1600, 0x100) -EXC_VIRT_NONE(0x5600, 0x100) -EXC_COMMON_BEGIN(cbe_maintenance_common) - GEN_COMMON cbe_maintenance - addi r3,r1,STACK_INT_FRAME_REGS - bl CFUNC(cbe_maintenance_exception) - b interrupt_return_hsrr - -#else /* CONFIG_CBE_RAS */ EXC_REAL_NONE(0x1600, 0x100) EXC_VIRT_NONE(0x5600, 0x100) -#endif INT_DEFINE_BEGIN(altivec_assist) @@ -2755,26 +2718,8 @@ EXC_COMMON_BEGIN(altivec_assist_common) b interrupt_return_srr -#ifdef CONFIG_CBE_RAS -INT_DEFINE_BEGIN(cbe_thermal) - IVEC=0x1800 - IHSRR=1 -INT_DEFINE_END(cbe_thermal) - -EXC_REAL_BEGIN(cbe_thermal, 0x1800, 0x100) - GEN_INT_ENTRY cbe_thermal, virt=0 -EXC_REAL_END(cbe_thermal, 0x1800, 0x100) -EXC_VIRT_NONE(0x5800, 0x100) -EXC_COMMON_BEGIN(cbe_thermal_common) - GEN_COMMON cbe_thermal - addi r3,r1,STACK_INT_FRAME_REGS - bl CFUNC(cbe_thermal_exception) - b interrupt_return_hsrr - -#else /* CONFIG_CBE_RAS */ EXC_REAL_NONE(0x1800, 0x100) EXC_VIRT_NONE(0x5800, 0x100) -#endif #ifdef CONFIG_PPC_WATCHDOG diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c index 4b371c738213..501d43bf18f3 100644 --- a/arch/powerpc/kernel/fadump.c +++ b/arch/powerpc/kernel/fadump.c @@ -33,6 +33,7 @@ #include <asm/fadump-internal.h> #include <asm/setup.h> #include <asm/interrupt.h> +#include <asm/prom.h> /* * The CPU who acquired the lock to trigger the fadump crash should @@ -289,10 +290,8 @@ static void __init fadump_show_config(void) if (!fw_dump.fadump_supported) return; - pr_debug("Fadump enabled : %s\n", - (fw_dump.fadump_enabled ? "yes" : "no")); - pr_debug("Dump Active : %s\n", - (fw_dump.dump_active ? "yes" : "no")); + pr_debug("Fadump enabled : %s\n", str_yes_no(fw_dump.fadump_enabled)); + pr_debug("Dump Active : %s\n", str_yes_no(fw_dump.dump_active)); 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); @@ -334,7 +333,7 @@ static __init u64 fadump_calculate_reserve_size(void) * memory at a predefined offset. */ ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(), - &size, &base, NULL, NULL); + &size, &base, NULL, NULL, NULL); if (ret == 0 && size > 0) { unsigned long max_size; @@ -751,7 +750,7 @@ u32 *__init fadump_regs_to_elf_notes(u32 *buf, struct pt_regs *regs) * prstatus.pr_pid = ???? */ elf_core_copy_regs(&prstatus.pr_reg, regs); - buf = append_elf_note(buf, CRASH_CORE_NOTE_NAME, NT_PRSTATUS, + buf = append_elf_note(buf, NN_PRSTATUS, NT_PRSTATUS, &prstatus, sizeof(prstatus)); return buf; } @@ -776,24 +775,12 @@ void __init fadump_update_elfcore_header(char *bufp) static void *__init fadump_alloc_buffer(unsigned long size) { - unsigned long count, i; - struct page *page; - void *vaddr; - - vaddr = alloc_pages_exact(size, GFP_KERNEL | __GFP_ZERO); - if (!vaddr) - return NULL; - - count = PAGE_ALIGN(size) / PAGE_SIZE; - page = virt_to_page(vaddr); - for (i = 0; i < count; i++) - mark_page_reserved(page + i); - return vaddr; + return alloc_pages_exact(size, GFP_KERNEL | __GFP_ZERO); } static void fadump_free_buffer(unsigned long vaddr, unsigned long size) { - free_reserved_area((void *)vaddr, (void *)(vaddr + size), -1, NULL); + free_pages_exact((void *)vaddr, size); } s32 __init fadump_setup_cpu_notes_buf(u32 num_cpus) @@ -1374,15 +1361,12 @@ static void fadump_free_elfcorehdr_buf(void) static void fadump_invalidate_release_mem(void) { - mutex_lock(&fadump_mutex); - if (!fw_dump.dump_active) { - mutex_unlock(&fadump_mutex); - return; + scoped_guard(mutex, &fadump_mutex) { + if (!fw_dump.dump_active) + return; + fadump_cleanup(); } - fadump_cleanup(); - mutex_unlock(&fadump_mutex); - fadump_free_elfcorehdr_buf(); fadump_release_memory(fw_dump.boot_mem_top, memblock_end_of_DRAM()); fadump_free_cpu_notes_buf(); @@ -1751,6 +1735,9 @@ void __init fadump_setup_param_area(void) { phys_addr_t range_start, range_end; + if (!fw_dump.fadump_enabled) + return; + if (!fw_dump.param_area_supported || fw_dump.dump_active) return; @@ -1764,19 +1751,19 @@ void __init fadump_setup_param_area(void) range_end = memblock_end_of_DRAM(); } else { /* - * Passing additional parameters is supported for hash MMU only - * if the first memory block size is 768MB or higher. + * Memory range for passing additional parameters for HASH MMU + * must meet the following conditions: + * 1. The first memory block size must be higher than the + * minimum RMA (MIN_RMA) size. Bootloader can use memory + * upto RMA size. So it should be avoided. + * 2. The range should be between MIN_RMA and RMA size (ppc64_rma_size) + * 3. It must not overlap with the fadump reserved area. */ - if (ppc64_rma_size < 0x30000000) + if (ppc64_rma_size < MIN_RMA*1024*1024) return; - /* - * 640 MB to 768 MB is not used by PFW/bootloader. So, try reserving - * memory for passing additional parameters in this range to avoid - * being stomped on by PFW/bootloader. - */ - range_start = 0x2A000000; - range_end = range_start + 0x4000000; + range_start = MIN_RMA * 1024 * 1024; + range_end = min(ppc64_rma_size, fw_dump.boot_mem_top); } fw_dump.param_area = memblock_phys_alloc_range(COMMAND_LINE_SIZE, diff --git a/arch/powerpc/kernel/head_85xx.S b/arch/powerpc/kernel/head_85xx.S index f9a73fae6464..8867596d35ad 100644 --- a/arch/powerpc/kernel/head_85xx.S +++ b/arch/powerpc/kernel/head_85xx.S @@ -305,7 +305,6 @@ set_ivor: * r12 is pointer to the pte * r10 is the pshift from the PGD, if we're a hugepage */ -#ifdef CONFIG_PTE_64BIT #ifdef CONFIG_HUGETLB_PAGE #define FIND_PTE \ rlwinm r12, r13, 14, 18, 28; /* Compute pgdir/pmd offset */ \ @@ -329,15 +328,6 @@ set_ivor: rlwimi r12, r13, 23, 20, 28; /* Compute pte address */ \ lwz r11, 4(r12); /* Get pte entry */ #endif /* HUGEPAGE */ -#else /* !PTE_64BIT */ -#define FIND_PTE \ - rlwimi r11, r13, 12, 20, 29; /* Create L1 (pgdir/pmd) address */ \ - lwz r11, 0(r11); /* Get L1 entry */ \ - rlwinm. r12, r11, 0, 0, 19; /* Extract L2 (pte) base address */ \ - beq 2f; /* Bail if no table */ \ - rlwimi r12, r13, 22, 20, 29; /* Compute PTE address */ \ - lwz r11, 0(r12); /* Get Linux PTE */ -#endif /* * Interrupt vector entry code @@ -473,22 +463,16 @@ END_BTB_FLUSH_SECTION 4: FIND_PTE -#ifdef CONFIG_PTE_64BIT li r13,_PAGE_PRESENT|_PAGE_BAP_SR oris r13,r13,_PAGE_ACCESSED@h -#else - li r13,_PAGE_PRESENT|_PAGE_READ|_PAGE_ACCESSED -#endif andc. r13,r13,r11 /* Check permission */ -#ifdef CONFIG_PTE_64BIT #ifdef CONFIG_SMP subf r13,r11,r12 /* create false data dep */ lwzx r13,r11,r13 /* Get upper pte bits */ #else lwz r13,0(r12) /* Get upper pte bits */ #endif -#endif bne 2f /* Bail if permission/valid mismatch */ @@ -552,12 +536,8 @@ END_BTB_FLUSH_SECTION FIND_PTE /* Make up the required permissions for kernel code */ -#ifdef CONFIG_PTE_64BIT li r13,_PAGE_PRESENT | _PAGE_BAP_SX oris r13,r13,_PAGE_ACCESSED@h -#else - li r13,_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_EXEC -#endif b 4f /* Get the PGD for the current thread */ @@ -573,24 +553,18 @@ END_BTB_FLUSH_SECTION FIND_PTE /* Make up the required permissions for user code */ -#ifdef CONFIG_PTE_64BIT li r13,_PAGE_PRESENT | _PAGE_BAP_UX oris r13,r13,_PAGE_ACCESSED@h -#else - li r13,_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_EXEC -#endif 4: andc. r13,r13,r11 /* Check permission */ -#ifdef CONFIG_PTE_64BIT #ifdef CONFIG_SMP subf r13,r11,r12 /* create false data dep */ lwzx r13,r11,r13 /* Get upper pte bits */ #else lwz r13,0(r12) /* Get upper pte bits */ #endif -#endif bne 2f /* Bail if permission mismatch */ @@ -683,7 +657,7 @@ interrupt_end: * r10 - tsize encoding (if HUGETLB_PAGE) or available to use * r11 - TLB (info from Linux PTE) * r12 - available to use - * r13 - upper bits of PTE (if PTE_64BIT) or available to use + * r13 - upper bits of PTE * CR5 - results of addr >= PAGE_OFFSET * MAS0, MAS1 - loaded with proper value when we get here * MAS2, MAS3 - will need additional info from Linux PTE @@ -751,7 +725,6 @@ finish_tlb_load: * here we (properly should) assume have the appropriate value. */ finish_tlb_load_cont: -#ifdef CONFIG_PTE_64BIT rlwinm r12, r11, 32-2, 26, 31 /* Move in perm bits */ andi. r10, r11, _PAGE_DIRTY bne 1f @@ -764,26 +737,9 @@ BEGIN_MMU_FTR_SECTION srwi r10, r13, 12 /* grab RPN[12:31] */ mtspr SPRN_MAS7, r10 END_MMU_FTR_SECTION_IFSET(MMU_FTR_BIG_PHYS) -#else - li r10, (_PAGE_EXEC | _PAGE_READ) - mr r13, r11 - rlwimi r10, r11, 31, 29, 29 /* extract _PAGE_DIRTY into SW */ - and r12, r11, r10 - mcrf cr0, cr5 /* Test for user page */ - slwi r10, r12, 1 - or r10, r10, r12 - rlwinm r10, r10, 0, ~_PAGE_EXEC /* Clear SX on user pages */ - isellt r12, r10, r12 - rlwimi r13, r12, 0, 20, 31 /* Get RPN from PTE, merge w/ perms */ - mtspr SPRN_MAS3, r13 -#endif mfspr r12, SPRN_MAS2 -#ifdef CONFIG_PTE_64BIT rlwimi r12, r11, 32-19, 27, 31 /* extract WIMGE from pte */ -#else - rlwimi r12, r11, 26, 27, 31 /* extract WIMGE from pte */ -#endif #ifdef CONFIG_HUGETLB_PAGE beq 6, 3f /* don't mask if page isn't huge */ li r13, 1 diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S index 56c5ebe21b99..393e19ee1322 100644 --- a/arch/powerpc/kernel/head_8xx.S +++ b/arch/powerpc/kernel/head_8xx.S @@ -162,7 +162,7 @@ instruction_counter: * For the MPC8xx, this is a software tablewalk to load the instruction * TLB. The task switch loads the M_TWB register with the pointer to the first * level table. - * If we discover there is no second level table (value is zero) or if there + * If there is no second level table (value is zero) or if there * is an invalid pte, we load that into the TLB, which causes another fault * into the TLB Error interrupt where we can handle such problems. * We have to use the MD_xxx registers for the tablewalk because the @@ -183,14 +183,11 @@ instruction_counter: mtspr SPRN_SPRG_SCRATCH2, r10 mtspr SPRN_M_TW, r11 - /* If we are faulting a kernel address, we have to use the - * kernel page tables. - */ mfspr r10, SPRN_SRR0 /* Get effective address of fault */ INVALIDATE_ADJACENT_PAGES_CPU15(r10, r11) mtspr SPRN_MD_EPN, r10 mfspr r10, SPRN_M_TWB /* Get level 1 table */ - lwz r11, (swapper_pg_dir-PAGE_OFFSET)@l(r10) /* Get level 1 entry */ + lwz r11, 0(r10) /* Get level 1 entry */ mtspr SPRN_MD_TWC, r11 mfspr r10, SPRN_MD_TWC lwz r10, 0(r10) /* Get the pte */ @@ -228,12 +225,8 @@ instruction_counter: mtspr SPRN_SPRG_SCRATCH2, r10 mtspr SPRN_M_TW, r11 - /* If we are faulting a kernel address, we have to use the - * kernel page tables. - */ - mfspr r10, SPRN_MD_EPN mfspr r10, SPRN_M_TWB /* Get level 1 table */ - lwz r11, (swapper_pg_dir-PAGE_OFFSET)@l(r10) /* Get level 1 entry */ + lwz r11, 0(r10) /* Get level 1 entry */ mtspr SPRN_MD_TWC, r11 mfspr r10, SPRN_MD_TWC @@ -375,7 +368,7 @@ FixupPGD: mfspr r10, SPRN_DAR mtspr SPRN_MD_EPN, r10 mfspr r11, SPRN_M_TWB /* Get level 1 table */ - lwz r10, (swapper_pg_dir - PAGE_OFFSET)@l(r11) /* Get the level 1 entry */ + lwz r10, 0(r11) /* Get the level 1 entry */ cmpwi cr1, r10, 0 bne cr1, 1f @@ -384,7 +377,7 @@ FixupPGD: lwz r10, (swapper_pg_dir - PAGE_OFFSET)@l(r10) /* Get the level 1 entry */ cmpwi cr1, r10, 0 beq cr1, 1f - stw r10, (swapper_pg_dir - PAGE_OFFSET)@l(r11) /* Set the level 1 entry */ + stw r10, 0(r11) /* Set the level 1 entry */ mfspr r10, SPRN_M_TW mtcr r10 mfspr r10, SPRN_SPRG_SCRATCH0 @@ -412,9 +405,10 @@ FixupDAR:/* Entry point for dcbx workaround. */ tophys(r11, r10) mfspr r11, SPRN_M_TWB /* Get level 1 table */ rlwinm r11, r11, 0, 20, 31 - oris r11, r11, (swapper_pg_dir - PAGE_OFFSET)@ha + oris r11, r11, (swapper_pg_dir - PAGE_OFFSET)@h + ori r11, r11, (swapper_pg_dir - PAGE_OFFSET)@l 3: - lwz r11, (swapper_pg_dir-PAGE_OFFSET)@l(r11) /* Get the level 1 entry */ + lwz r11, 0(r11) /* Get the level 1 entry */ rlwinm r11, r11, 0, ~_PMD_PAGE_8M mtspr SPRN_MD_TWC, r11 mfspr r11, SPRN_MD_TWC @@ -535,7 +529,8 @@ start_here: li r0,0 stwu r0,THREAD_SIZE-STACK_FRAME_MIN_SIZE(r1) - lis r6, swapper_pg_dir@ha + lis r6, swapper_pg_dir@h + ori r6, r6, swapper_pg_dir@l tophys(r6,r6) mtspr SPRN_M_TWB, r6 diff --git a/arch/powerpc/kernel/head_book3s_32.S b/arch/powerpc/kernel/head_book3s_32.S index cb2bca76be53..c1779455ea32 100644 --- a/arch/powerpc/kernel/head_book3s_32.S +++ b/arch/powerpc/kernel/head_book3s_32.S @@ -420,7 +420,7 @@ InstructionTLBMiss: lwz r2,0(r2) /* get pmd entry */ #ifdef CONFIG_EXECMEM rlwinm r3, r0, 4, 0xf - subi r3, r3, (TASK_SIZE >> 28) & 0xf + subi r3, r3, NUM_USER_SEGMENTS #endif rlwinm. r2,r2,0,0,19 /* extract address of pte page */ beq- InstructionAddressInvalid /* return if no mapping */ @@ -475,7 +475,7 @@ DataLoadTLBMiss: lwz r2,0(r1) /* get pmd entry */ rlwinm r3, r0, 4, 0xf rlwinm. r2,r2,0,0,19 /* extract address of pte page */ - subi r3, r3, (TASK_SIZE >> 28) & 0xf + subi r3, r3, NUM_USER_SEGMENTS beq- 2f /* bail if no mapping */ 1: rlwimi r2,r0,22,20,29 /* insert next 10 bits of address */ lwz r2,0(r2) /* get linux-style pte */ @@ -554,7 +554,7 @@ DataStoreTLBMiss: lwz r2,0(r1) /* get pmd entry */ rlwinm r3, r0, 4, 0xf rlwinm. r2,r2,0,0,19 /* extract address of pte page */ - subi r3, r3, (TASK_SIZE >> 28) & 0xf + subi r3, r3, NUM_USER_SEGMENTS beq- 2f /* bail if no mapping */ 1: rlwimi r2,r0,22,20,29 /* insert next 10 bits of address */ diff --git a/arch/powerpc/kernel/head_booke.h b/arch/powerpc/kernel/head_booke.h index 0b5c1993809e..75471fb6fb10 100644 --- a/arch/powerpc/kernel/head_booke.h +++ b/arch/powerpc/kernel/head_booke.h @@ -7,7 +7,7 @@ #include <asm/kvm_booke_hv_asm.h> #include <asm/thread_info.h> /* for THREAD_SHIFT */ -#ifdef __ASSEMBLY__ +#ifdef __ASSEMBLER__ /* * Macros used for common Book-e exception handling @@ -522,5 +522,5 @@ label: bl kernel_fp_unavailable_exception; \ b interrupt_return -#endif /* __ASSEMBLY__ */ +#endif /* __ASSEMBLER__ */ #endif /* __HEAD_BOOKE_H__ */ diff --git a/arch/powerpc/kernel/ima_arch.c b/arch/powerpc/kernel/ima_arch.c index b7029beed847..17f9304855e9 100644 --- a/arch/powerpc/kernel/ima_arch.c +++ b/arch/powerpc/kernel/ima_arch.c @@ -7,11 +7,6 @@ #include <linux/ima.h> #include <asm/secure_boot.h> -bool arch_ima_get_secureboot(void) -{ - return is_ppc_secureboot_enabled(); -} - /* * The "secure_rules" are enabled only on "secureboot" enabled systems. * These rules verify the file signatures against known good values. @@ -63,8 +58,7 @@ static const char *const secure_and_trusted_rules[] = { const char *const *arch_get_ima_policy(void) { if (is_ppc_secureboot_enabled()) { - if (IS_ENABLED(CONFIG_MODULE_SIG)) - set_module_sig_enforced(); + set_module_sig_enforced(); if (is_ppc_trustedboot_enabled()) return secure_and_trusted_rules; diff --git a/arch/powerpc/kernel/interrupt.c b/arch/powerpc/kernel/interrupt.c index 8f4acc55407b..e63bfde13e03 100644 --- a/arch/powerpc/kernel/interrupt.c +++ b/arch/powerpc/kernel/interrupt.c @@ -25,6 +25,10 @@ unsigned long global_dbcr0[NR_CPUS]; #endif +#if defined(CONFIG_PREEMPT_DYNAMIC) +DEFINE_STATIC_KEY_TRUE(sk_dynamic_irqentry_exit_cond_resched); +#endif + #ifdef CONFIG_PPC_BOOK3S_64 DEFINE_STATIC_KEY_FALSE(interrupt_exit_not_reentrant); static inline bool exit_must_hard_disable(void) @@ -396,7 +400,7 @@ notrace unsigned long interrupt_exit_kernel_prepare(struct pt_regs *regs) /* Returning to a kernel context with local irqs enabled. */ WARN_ON_ONCE(!(regs->msr & MSR_EE)); again: - if (IS_ENABLED(CONFIG_PREEMPTION)) { + if (need_irq_preemption()) { /* Return to preemptible kernel context */ if (unlikely(read_thread_flags() & _TIF_NEED_RESCHED)) { if (preempt_count() == 0) @@ -439,6 +443,9 @@ again: if (unlikely(stack_store)) __hard_EE_RI_disable(); +#else + } else { + __hard_EE_RI_disable(); #endif /* CONFIG_PPC64 */ } diff --git a/arch/powerpc/kernel/io-workarounds.c b/arch/powerpc/kernel/io-workarounds.c deleted file mode 100644 index c877f074d174..000000000000 --- a/arch/powerpc/kernel/io-workarounds.c +++ /dev/null @@ -1,197 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Support PCI IO workaround - * - * Copyright (C) 2006 Benjamin Herrenschmidt <benh@kernel.crashing.org> - * IBM, Corp. - * (C) Copyright 2007-2008 TOSHIBA CORPORATION - */ -#undef DEBUG - -#include <linux/kernel.h> -#include <linux/sched/mm.h> /* for init_mm */ -#include <linux/pgtable.h> - -#include <asm/io.h> -#include <asm/machdep.h> -#include <asm/ppc-pci.h> -#include <asm/io-workarounds.h> -#include <asm/pte-walk.h> - - -#define IOWA_MAX_BUS 8 - -static struct iowa_bus iowa_busses[IOWA_MAX_BUS]; -static unsigned int iowa_bus_count; - -static struct iowa_bus *iowa_pci_find(unsigned long vaddr, unsigned long paddr) -{ - int i, j; - struct resource *res; - unsigned long vstart, vend; - - for (i = 0; i < iowa_bus_count; i++) { - struct iowa_bus *bus = &iowa_busses[i]; - struct pci_controller *phb = bus->phb; - - if (vaddr) { - vstart = (unsigned long)phb->io_base_virt; - vend = vstart + phb->pci_io_size - 1; - if ((vaddr >= vstart) && (vaddr <= vend)) - return bus; - } - - if (paddr) - for (j = 0; j < 3; j++) { - res = &phb->mem_resources[j]; - if (paddr >= res->start && paddr <= res->end) - return bus; - } - } - - return NULL; -} - -#ifdef CONFIG_PPC_INDIRECT_MMIO -struct iowa_bus *iowa_mem_find_bus(const PCI_IO_ADDR addr) -{ - struct iowa_bus *bus; - int token; - - token = PCI_GET_ADDR_TOKEN(addr); - - if (token && token <= iowa_bus_count) - bus = &iowa_busses[token - 1]; - else { - unsigned long vaddr, paddr; - - vaddr = (unsigned long)PCI_FIX_ADDR(addr); - if (vaddr < PHB_IO_BASE || vaddr >= PHB_IO_END) - return NULL; - - paddr = ppc_find_vmap_phys(vaddr); - - bus = iowa_pci_find(vaddr, paddr); - - if (bus == NULL) - return NULL; - } - - return bus; -} -#else /* CONFIG_PPC_INDIRECT_MMIO */ -struct iowa_bus *iowa_mem_find_bus(const PCI_IO_ADDR addr) -{ - return NULL; -} -#endif /* !CONFIG_PPC_INDIRECT_MMIO */ - -#ifdef CONFIG_PPC_INDIRECT_PIO -struct iowa_bus *iowa_pio_find_bus(unsigned long port) -{ - unsigned long vaddr = (unsigned long)pci_io_base + port; - return iowa_pci_find(vaddr, 0); -} -#else -struct iowa_bus *iowa_pio_find_bus(unsigned long port) -{ - return NULL; -} -#endif - -#define DEF_PCI_AC_RET(name, ret, at, al, space, aa) \ -static ret iowa_##name at \ -{ \ - struct iowa_bus *bus; \ - bus = iowa_##space##_find_bus(aa); \ - if (bus && bus->ops && bus->ops->name) \ - return bus->ops->name al; \ - return __do_##name al; \ -} - -#define DEF_PCI_AC_NORET(name, at, al, space, aa) \ -static void iowa_##name at \ -{ \ - struct iowa_bus *bus; \ - bus = iowa_##space##_find_bus(aa); \ - if (bus && bus->ops && bus->ops->name) { \ - bus->ops->name al; \ - return; \ - } \ - __do_##name al; \ -} - -#include <asm/io-defs.h> - -#undef DEF_PCI_AC_RET -#undef DEF_PCI_AC_NORET - -static const struct ppc_pci_io iowa_pci_io = { - -#define DEF_PCI_AC_RET(name, ret, at, al, space, aa) .name = iowa_##name, -#define DEF_PCI_AC_NORET(name, at, al, space, aa) .name = iowa_##name, - -#include <asm/io-defs.h> - -#undef DEF_PCI_AC_RET -#undef DEF_PCI_AC_NORET - -}; - -#ifdef CONFIG_PPC_INDIRECT_MMIO -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); - int busno; - - bus = iowa_pci_find(0, (unsigned long)addr); - if (bus != NULL) { - busno = bus - iowa_busses; - PCI_SET_ADDR_TOKEN(res, busno + 1); - } - return res; -} -#endif /* !CONFIG_PPC_INDIRECT_MMIO */ - -bool io_workaround_inited; - -/* Enable IO workaround */ -static void io_workaround_init(void) -{ - if (io_workaround_inited) - return; - ppc_pci_io = iowa_pci_io; - io_workaround_inited = true; -} - -/* Register new bus to support workaround */ -void iowa_register_bus(struct pci_controller *phb, struct ppc_pci_io *ops, - int (*initfunc)(struct iowa_bus *, void *), void *data) -{ - struct iowa_bus *bus; - struct device_node *np = phb->dn; - - io_workaround_init(); - - if (iowa_bus_count >= IOWA_MAX_BUS) { - pr_err("IOWA:Too many pci bridges, " - "workarounds disabled for %pOF\n", np); - return; - } - - bus = &iowa_busses[iowa_bus_count]; - bus->phb = phb; - bus->ops = ops; - bus->private = data; - - if (initfunc) - if ((*initfunc)(bus, data)) - return; - - iowa_bus_count++; - - pr_debug("IOWA:[%d]Add bus, %pOF.\n", iowa_bus_count-1, np); -} - diff --git a/arch/powerpc/kernel/io.c b/arch/powerpc/kernel/io.c index 6af535905984..bcc201c01514 100644 --- a/arch/powerpc/kernel/io.c +++ b/arch/powerpc/kernel/io.c @@ -31,13 +31,14 @@ void _insb(const volatile u8 __iomem *port, void *buf, long count) if (unlikely(count <= 0)) return; - asm volatile("sync"); + + mb(); do { tmp = *(const volatile u8 __force *)port; eieio(); *tbuf++ = tmp; } while (--count != 0); - asm volatile("twi 0,%0,0; isync" : : "r" (tmp)); + data_barrier(tmp); } EXPORT_SYMBOL(_insb); @@ -47,75 +48,80 @@ void _outsb(volatile u8 __iomem *port, const void *buf, long count) if (unlikely(count <= 0)) return; - asm volatile("sync"); + + mb(); do { *(volatile u8 __force *)port = *tbuf++; } while (--count != 0); - asm volatile("sync"); + mb(); } EXPORT_SYMBOL(_outsb); -void _insw_ns(const volatile u16 __iomem *port, void *buf, long count) +void _insw(const volatile u16 __iomem *port, void *buf, long count) { u16 *tbuf = buf; u16 tmp; if (unlikely(count <= 0)) return; - asm volatile("sync"); + + mb(); do { tmp = *(const volatile u16 __force *)port; eieio(); *tbuf++ = tmp; } while (--count != 0); - asm volatile("twi 0,%0,0; isync" : : "r" (tmp)); + data_barrier(tmp); } -EXPORT_SYMBOL(_insw_ns); +EXPORT_SYMBOL(_insw); -void _outsw_ns(volatile u16 __iomem *port, const void *buf, long count) +void _outsw(volatile u16 __iomem *port, const void *buf, long count) { const u16 *tbuf = buf; if (unlikely(count <= 0)) return; - asm volatile("sync"); + + mb(); do { *(volatile u16 __force *)port = *tbuf++; } while (--count != 0); - asm volatile("sync"); + mb(); } -EXPORT_SYMBOL(_outsw_ns); +EXPORT_SYMBOL(_outsw); -void _insl_ns(const volatile u32 __iomem *port, void *buf, long count) +void _insl(const volatile u32 __iomem *port, void *buf, long count) { u32 *tbuf = buf; u32 tmp; if (unlikely(count <= 0)) return; - asm volatile("sync"); + + mb(); do { tmp = *(const volatile u32 __force *)port; eieio(); *tbuf++ = tmp; } while (--count != 0); - asm volatile("twi 0,%0,0; isync" : : "r" (tmp)); + data_barrier(tmp); } -EXPORT_SYMBOL(_insl_ns); +EXPORT_SYMBOL(_insl); -void _outsl_ns(volatile u32 __iomem *port, const void *buf, long count) +void _outsl(volatile u32 __iomem *port, const void *buf, long count) { const u32 *tbuf = buf; if (unlikely(count <= 0)) return; - asm volatile("sync"); + + mb(); do { *(volatile u32 __force *)port = *tbuf++; } while (--count != 0); - asm volatile("sync"); + mb(); } -EXPORT_SYMBOL(_outsl_ns); +EXPORT_SYMBOL(_outsl); #define IO_CHECK_ALIGN(v,a) ((((unsigned long)(v)) & ((a) - 1)) == 0) @@ -127,7 +133,7 @@ _memset_io(volatile void __iomem *addr, int c, unsigned long n) lc |= lc << 8; lc |= lc << 16; - __asm__ __volatile__ ("sync" : : : "memory"); + mb(); while(n && !IO_CHECK_ALIGN(p, 4)) { *((volatile u8 *)p) = c; p++; @@ -143,7 +149,7 @@ _memset_io(volatile void __iomem *addr, int c, unsigned long n) p++; n--; } - __asm__ __volatile__ ("sync" : : : "memory"); + mb(); } EXPORT_SYMBOL(_memset_io); @@ -152,7 +158,7 @@ void _memcpy_fromio(void *dest, const volatile void __iomem *src, { void *vsrc = (void __force *) src; - __asm__ __volatile__ ("sync" : : : "memory"); + mb(); while(n && (!IO_CHECK_ALIGN(vsrc, 4) || !IO_CHECK_ALIGN(dest, 4))) { *((u8 *)dest) = *((volatile u8 *)vsrc); eieio(); @@ -174,7 +180,7 @@ void _memcpy_fromio(void *dest, const volatile void __iomem *src, dest++; n--; } - __asm__ __volatile__ ("sync" : : : "memory"); + mb(); } EXPORT_SYMBOL(_memcpy_fromio); @@ -182,7 +188,7 @@ void _memcpy_toio(volatile void __iomem *dest, const void *src, unsigned long n) { void *vdest = (void __force *) dest; - __asm__ __volatile__ ("sync" : : : "memory"); + mb(); while(n && (!IO_CHECK_ALIGN(vdest, 4) || !IO_CHECK_ALIGN(src, 4))) { *((volatile u8 *)vdest) = *((u8 *)src); src++; @@ -201,6 +207,6 @@ void _memcpy_toio(volatile void __iomem *dest, const void *src, unsigned long n) vdest++; n--; } - __asm__ __volatile__ ("sync" : : : "memory"); + mb(); } EXPORT_SYMBOL(_memcpy_toio); diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index 0ebae6e4c19d..d122e8447831 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -16,6 +16,7 @@ #include <linux/mm.h> #include <linux/spinlock.h> #include <linux/string.h> +#include <linux/string_choices.h> #include <linux/dma-mapping.h> #include <linux/bitmap.h> #include <linux/iommu-helper.h> @@ -769,8 +770,8 @@ struct iommu_table *iommu_init_table(struct iommu_table *tbl, int nid, iommu_table_clear(tbl); if (!welcomed) { - printk(KERN_INFO "IOMMU table initialized, virtual merging %s\n", - novmerge ? "disabled" : "enabled"); + pr_info("IOMMU table initialized, virtual merging %s\n", + str_disabled_enabled(novmerge)); welcomed = 1; } @@ -847,12 +848,12 @@ EXPORT_SYMBOL_GPL(iommu_tce_table_put); /* Creates TCEs for a user provided buffer. The user buffer must be * contiguous real kernel storage (not vmalloc). The address passed here - * comprises a page address and offset into that page. The dma_addr_t - * returned will point to the same byte within the page as was passed in. + * is physical address into that page. The dma_addr_t returned will point + * to the same byte within the page as was passed in. */ -dma_addr_t iommu_map_page(struct device *dev, struct iommu_table *tbl, - struct page *page, unsigned long offset, size_t size, - unsigned long mask, enum dma_data_direction direction, +dma_addr_t iommu_map_phys(struct device *dev, struct iommu_table *tbl, + phys_addr_t phys, size_t size, unsigned long mask, + enum dma_data_direction direction, unsigned long attrs) { dma_addr_t dma_handle = DMA_MAPPING_ERROR; @@ -862,7 +863,7 @@ dma_addr_t iommu_map_page(struct device *dev, struct iommu_table *tbl, BUG_ON(direction == DMA_NONE); - vaddr = page_address(page) + offset; + vaddr = phys_to_virt(phys); uaddr = (unsigned long)vaddr; if (tbl) { @@ -889,7 +890,7 @@ dma_addr_t iommu_map_page(struct device *dev, struct iommu_table *tbl, return dma_handle; } -void iommu_unmap_page(struct iommu_table *tbl, dma_addr_t dma_handle, +void iommu_unmap_phys(struct iommu_table *tbl, dma_addr_t dma_handle, size_t size, enum dma_data_direction direction, unsigned long attrs) { @@ -1155,9 +1156,10 @@ EXPORT_SYMBOL_GPL(iommu_add_device); */ static int spapr_tce_platform_iommu_attach_dev(struct iommu_domain *platform_domain, - struct device *dev) + struct device *dev, + struct iommu_domain *old) { - struct iommu_domain *domain = iommu_get_domain_for_dev(dev); + struct iommu_domain *domain = iommu_driver_get_domain_for_dev(dev); struct iommu_table_group *table_group; struct iommu_group *grp; @@ -1188,7 +1190,7 @@ static struct iommu_domain spapr_tce_platform_domain = { static int spapr_tce_blocked_iommu_attach_dev(struct iommu_domain *platform_domain, - struct device *dev) + struct device *dev, struct iommu_domain *old) { struct iommu_group *grp = iommu_group_get(dev); struct iommu_table_group *table_group; diff --git a/arch/powerpc/kernel/kgdb.c b/arch/powerpc/kernel/kgdb.c index 5081334b7bd2..861db2334db8 100644 --- a/arch/powerpc/kernel/kgdb.c +++ b/arch/powerpc/kernel/kgdb.c @@ -101,7 +101,6 @@ static int computeSignal(unsigned int tt) } /** - * * kgdb_skipexception - Bail out of KGDB when we've been triggered. * @exception: Exception vector number * @regs: Current &struct pt_regs. @@ -109,6 +108,8 @@ static int computeSignal(unsigned int tt) * On some architectures we need to skip a breakpoint exception when * it occurs after a breakpoint has been removed. * + * Return: return %1 if the breakpoint for this address has been removed, + * otherwise return %0 */ int kgdb_skipexception(int exception, struct pt_regs *regs) { diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c index 5b3c093611ba..7209d00a9c25 100644 --- a/arch/powerpc/kernel/kvm.c +++ b/arch/powerpc/kernel/kvm.c @@ -632,19 +632,19 @@ static void __init kvm_check_ins(u32 *inst, u32 features) #endif } - switch (inst_no_rt & ~KVM_MASK_RB) { #ifdef CONFIG_PPC_BOOK3S_32 + switch (inst_no_rt & ~KVM_MASK_RB) { case KVM_INST_MTSRIN: if (features & KVM_MAGIC_FEAT_SR) { u32 inst_rb = _inst & KVM_MASK_RB; kvm_patch_ins_mtsrin(inst, inst_rt, inst_rb); } break; -#endif } +#endif - switch (_inst) { #ifdef CONFIG_BOOKE + switch (_inst) { case KVM_INST_WRTEEI_0: kvm_patch_ins_wrteei_0(inst); break; @@ -652,8 +652,8 @@ static void __init kvm_check_ins(u32 *inst, u32 features) case KVM_INST_WRTEEI_1: kvm_patch_ins_wrtee(inst, 0, 1); break; -#endif } +#endif } extern u32 kvm_template_start[]; diff --git a/arch/powerpc/kernel/legacy_serial.c b/arch/powerpc/kernel/legacy_serial.c index 1da2f6e7d2a1..ae1906bfe8a5 100644 --- a/arch/powerpc/kernel/legacy_serial.c +++ b/arch/powerpc/kernel/legacy_serial.c @@ -54,9 +54,10 @@ static int legacy_serial_console = -1; static const upf_t legacy_port_flags = UPF_BOOT_AUTOCONF | UPF_SKIP_TEST | UPF_SHARE_IRQ | UPF_FIXED_PORT; -static unsigned int tsi_serial_in(struct uart_port *p, int offset) +static u32 tsi_serial_in(struct uart_port *p, unsigned int offset) { - unsigned int tmp; + u32 tmp; + offset = offset << p->regshift; if (offset == UART_IIR) { tmp = readl(p->membase + (UART_IIR & ~3)); @@ -65,7 +66,7 @@ static unsigned int tsi_serial_in(struct uart_port *p, int offset) return readb(p->membase + offset); } -static void tsi_serial_out(struct uart_port *p, int offset, int value) +static void tsi_serial_out(struct uart_port *p, unsigned int offset, u32 value) { offset = offset << p->regshift; if (!((offset == UART_IER) && (value & UART_IER_UUE))) @@ -77,6 +78,8 @@ static int __init add_legacy_port(struct device_node *np, int want_index, phys_addr_t taddr, unsigned long irq, upf_t flags, int irq_check_parent) { + struct plat_serial8250_port *legacy_port; + struct legacy_serial_info *legacy_info; const __be32 *clk, *spd, *rs; u32 clock = BASE_BAUD * 16; u32 shift = 0; @@ -110,16 +113,17 @@ static int __init add_legacy_port(struct device_node *np, int want_index, if (index >= legacy_serial_count) legacy_serial_count = index + 1; + legacy_port = &legacy_serial_ports[index]; + legacy_info = &legacy_serial_infos[index]; + /* Check if there is a port who already claimed our slot */ - if (legacy_serial_infos[index].np != NULL) { + if (legacy_info->np != NULL) { /* if we still have some room, move it, else override */ if (legacy_serial_count < MAX_LEGACY_SERIAL_PORTS) { printk(KERN_DEBUG "Moved legacy port %d -> %d\n", index, legacy_serial_count); - legacy_serial_ports[legacy_serial_count] = - legacy_serial_ports[index]; - legacy_serial_infos[legacy_serial_count] = - legacy_serial_infos[index]; + legacy_serial_ports[legacy_serial_count] = *legacy_port; + legacy_serial_infos[legacy_serial_count] = *legacy_info; legacy_serial_count++; } else { printk(KERN_DEBUG "Replacing legacy port %d\n", index); @@ -127,36 +131,32 @@ static int __init add_legacy_port(struct device_node *np, int want_index, } /* Now fill the entry */ - memset(&legacy_serial_ports[index], 0, - sizeof(struct plat_serial8250_port)); + memset(legacy_port, 0, sizeof(*legacy_port)); if (iotype == UPIO_PORT) - legacy_serial_ports[index].iobase = base; + legacy_port->iobase = base; else - legacy_serial_ports[index].mapbase = base; - - legacy_serial_ports[index].iotype = iotype; - legacy_serial_ports[index].uartclk = clock; - legacy_serial_ports[index].irq = irq; - legacy_serial_ports[index].flags = flags; - legacy_serial_ports[index].regshift = shift; - legacy_serial_infos[index].taddr = taddr; - legacy_serial_infos[index].np = of_node_get(np); - legacy_serial_infos[index].clock = clock; - legacy_serial_infos[index].speed = spd ? be32_to_cpup(spd) : 0; - legacy_serial_infos[index].irq_check_parent = irq_check_parent; + legacy_port->mapbase = base; + + legacy_port->iotype = iotype; + legacy_port->uartclk = clock; + legacy_port->irq = irq; + legacy_port->flags = flags; + legacy_port->regshift = shift; + legacy_info->taddr = taddr; + legacy_info->np = of_node_get(np); + legacy_info->clock = clock; + legacy_info->speed = spd ? be32_to_cpup(spd) : 0; + legacy_info->irq_check_parent = irq_check_parent; if (iotype == UPIO_TSI) { - legacy_serial_ports[index].serial_in = tsi_serial_in; - legacy_serial_ports[index].serial_out = tsi_serial_out; + legacy_port->serial_in = tsi_serial_in; + legacy_port->serial_out = tsi_serial_out; } - printk(KERN_DEBUG "Found legacy serial port %d for %pOF\n", - index, np); - printk(KERN_DEBUG " %s=%llx, taddr=%llx, irq=%lx, clk=%d, speed=%d\n", + printk(KERN_DEBUG "Found legacy serial port %d for %pOF\n", index, np); + printk(KERN_DEBUG " %s=%pa, taddr=%pa, irq=%lx, clk=%d, speed=%d\n", (iotype == UPIO_PORT) ? "port" : "mem", - (unsigned long long)base, (unsigned long long)taddr, irq, - legacy_serial_ports[index].uartclk, - legacy_serial_infos[index].speed); + &base, &taddr, irq, legacy_port->uartclk, legacy_info->speed); return index; } diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c index 34a5aec4908f..2a44bc8e2439 100644 --- a/arch/powerpc/kernel/module_64.c +++ b/arch/powerpc/kernel/module_64.c @@ -209,8 +209,7 @@ static unsigned long get_stubs_size(const Elf64_Ehdr *hdr, char *secstrings, struct module *me) { - /* One extra reloc so it's always 0-addr terminated */ - unsigned long relocs = 1; + unsigned long relocs = 0; unsigned i; /* Every relocated section... */ @@ -258,10 +257,6 @@ static unsigned long get_stubs_size(const Elf64_Ehdr *hdr, break; } } - if (i == hdr->e_shnum) { - pr_err("%s: doesn't contain __patchable_function_entries.\n", me->name); - return -ENOEXEC; - } #endif pr_debug("Looks like a total of %lu stubs, max\n", relocs); @@ -709,7 +704,7 @@ static unsigned long stub_for_addr(const Elf64_Shdr *sechdrs, /* Find this stub, or if that fails, the next avail. entry */ stubs = (void *)sechdrs[me->arch.stubs_section].sh_addr; - for (i = 0; stub_func_addr(stubs[i].funcdata); i++) { + for (i = 0; i < me->arch.stub_count; i++) { if (WARN_ON(i >= num_stubs)) return 0; @@ -720,6 +715,7 @@ static unsigned long stub_for_addr(const Elf64_Shdr *sechdrs, if (!create_stub(sechdrs, &stubs[i], addr, me, name)) return 0; + me->arch.stub_count++; return (unsigned long)&stubs[i]; } @@ -1122,29 +1118,19 @@ int module_trampoline_target(struct module *mod, unsigned long addr, static int setup_ftrace_ool_stubs(const Elf64_Shdr *sechdrs, unsigned long addr, struct module *me) { #ifdef CONFIG_PPC_FTRACE_OUT_OF_LINE - unsigned int i, total_stubs, num_stubs; + unsigned int total_stubs, num_stubs; struct ppc64_stub_entry *stub; total_stubs = sechdrs[me->arch.stubs_section].sh_size / sizeof(*stub); num_stubs = roundup(me->arch.ool_stub_count * sizeof(struct ftrace_ool_stub), sizeof(struct ppc64_stub_entry)) / sizeof(struct ppc64_stub_entry); - /* Find the next available entry */ - stub = (void *)sechdrs[me->arch.stubs_section].sh_addr; - for (i = 0; stub_func_addr(stub[i].funcdata); i++) - if (WARN_ON(i >= total_stubs)) - return -1; - - if (WARN_ON(i + num_stubs > total_stubs)) + if (WARN_ON(me->arch.stub_count + num_stubs > total_stubs)) return -1; - stub += i; - me->arch.ool_stubs = (struct ftrace_ool_stub *)stub; - - /* reserve stubs */ - for (i = 0; i < num_stubs; i++) - if (patch_u32((void *)&stub->funcdata, PPC_RAW_NOP())) - return -1; + stub = (void *)sechdrs[me->arch.stubs_section].sh_addr; + me->arch.ool_stubs = (struct ftrace_ool_stub *)(stub + me->arch.stub_count); + me->arch.stub_count += num_stubs; #endif return 0; diff --git a/arch/powerpc/kernel/nvram_64.c b/arch/powerpc/kernel/nvram_64.c index f9c6568a9137..42b29324287c 100644 --- a/arch/powerpc/kernel/nvram_64.c +++ b/arch/powerpc/kernel/nvram_64.c @@ -890,7 +890,7 @@ loff_t __init nvram_create_partition(const char *name, int sig, return -ENOSPC; /* Create our OS partition */ - new_part = kzalloc(sizeof(*new_part), GFP_KERNEL); + new_part = kzalloc_obj(*new_part); if (!new_part) { pr_err("%s: kmalloc failed\n", __func__); return -ENOMEM; @@ -1030,7 +1030,7 @@ int __init nvram_scan_partitions(void) "detected: 0-length partition\n"); goto out; } - tmp_part = kmalloc(sizeof(*tmp_part), GFP_KERNEL); + tmp_part = kmalloc_obj(*tmp_part); err = -ENOMEM; if (!tmp_part) { printk(KERN_ERR "nvram_scan_partitions: kmalloc failed\n"); diff --git a/arch/powerpc/kernel/of_platform.c b/arch/powerpc/kernel/of_platform.c deleted file mode 100644 index adc76fa58d1e..000000000000 --- a/arch/powerpc/kernel/of_platform.c +++ /dev/null @@ -1,102 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * Copyright (C) 2006 Benjamin Herrenschmidt, IBM Corp. - * <benh@kernel.crashing.org> - * and Arnd Bergmann, IBM Corp. - */ - -#undef DEBUG - -#include <linux/string.h> -#include <linux/kernel.h> -#include <linux/init.h> -#include <linux/export.h> -#include <linux/mod_devicetable.h> -#include <linux/pci.h> -#include <linux/platform_device.h> -#include <linux/atomic.h> - -#include <asm/errno.h> -#include <asm/topology.h> -#include <asm/pci-bridge.h> -#include <asm/ppc-pci.h> -#include <asm/eeh.h> - -#ifdef CONFIG_PPC_OF_PLATFORM_PCI - -/* The probing of PCI controllers from of_platform is currently - * 64 bits only, mostly due to gratuitous differences between - * the 32 and 64 bits PCI code on PowerPC and the 32 bits one - * lacking some bits needed here. - */ - -static int of_pci_phb_probe(struct platform_device *dev) -{ - struct pci_controller *phb; - - /* Check if we can do that ... */ - if (ppc_md.pci_setup_phb == NULL) - return -ENODEV; - - pr_info("Setting up PCI bus %pOF\n", dev->dev.of_node); - - /* Alloc and setup PHB data structure */ - phb = pcibios_alloc_controller(dev->dev.of_node); - if (!phb) - return -ENODEV; - - /* Setup parent in sysfs */ - phb->parent = &dev->dev; - - /* Setup the PHB using arch provided callback */ - if (ppc_md.pci_setup_phb(phb)) { - pcibios_free_controller(phb); - return -ENODEV; - } - - /* Process "ranges" property */ - pci_process_bridge_OF_ranges(phb, dev->dev.of_node, 0); - - /* Init pci_dn data structures */ - pci_devs_phb_init_dynamic(phb); - - /* Create EEH PE for the PHB */ - eeh_phb_pe_create(phb); - - /* Scan the bus */ - pcibios_scan_phb(phb); - if (phb->bus == NULL) - return -ENXIO; - - /* Claim resources. This might need some rework as well depending - * whether we are doing probe-only or not, like assigning unassigned - * resources etc... - */ - pcibios_claim_one_bus(phb->bus); - - /* Add probed PCI devices to the device model */ - pci_bus_add_devices(phb->bus); - - return 0; -} - -static const struct of_device_id of_pci_phb_ids[] = { - { .type = "pci", }, - { .type = "pcix", }, - { .type = "pcie", }, - { .type = "pciex", }, - { .type = "ht", }, - {} -}; - -static struct platform_driver of_pci_phb_driver = { - .probe = of_pci_phb_probe, - .driver = { - .name = "of-pci", - .of_match_table = of_pci_phb_ids, - }, -}; - -builtin_platform_driver(of_pci_phb_driver); - -#endif /* CONFIG_PPC_OF_PLATFORM_PCI */ diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index eac84d687b53..8efe95a0c4ff 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -125,7 +125,7 @@ struct pci_controller *pcibios_alloc_controller(struct device_node *dev) { struct pci_controller *phb; - phb = kzalloc(sizeof(struct pci_controller), GFP_KERNEL); + phb = kzalloc_obj(struct pci_controller); if (phb == NULL) return NULL; @@ -432,7 +432,7 @@ static int pci_read_irq_line(struct pci_dev *pci_dev) struct pci_intx_virq *vi, *vitmp; /* Preallocate vi as rewind is complex if this fails after mapping */ - vi = kzalloc(sizeof(struct pci_intx_virq), GFP_KERNEL); + vi = kzalloc_obj(struct pci_intx_virq); if (!vi) return -1; @@ -1132,7 +1132,9 @@ static int skip_isa_ioresource_align(struct pci_dev *dev) * which might have be mirrored at 0x0100-0x03ff.. */ resource_size_t pcibios_align_resource(void *data, const struct resource *res, - resource_size_t size, resource_size_t align) + const struct resource *empty_res, + resource_size_t size, + resource_size_t align) { struct pci_dev *dev = data; resource_size_t start = res->start; @@ -1142,6 +1144,8 @@ resource_size_t pcibios_align_resource(void *data, const struct resource *res, return start; if (start & 0x300) start = (start + 0x3ff) & ~0x3ff; + } else if (res->flags & IORESOURCE_MEM) { + start = pci_align_resource(dev, res, empty_res, size, align); } return start; @@ -1368,7 +1372,7 @@ static void __init pcibios_reserve_legacy_regions(struct pci_bus *bus) if (!(hose->io_resource.flags & IORESOURCE_IO)) goto no_io; offset = (unsigned long)hose->io_base_virt - _IO_BASE; - res = kzalloc(sizeof(struct resource), GFP_KERNEL); + res = kzalloc_obj(struct resource); BUG_ON(res == NULL); res->name = "Legacy IO"; res->flags = IORESOURCE_IO; @@ -1396,7 +1400,7 @@ static void __init pcibios_reserve_legacy_regions(struct pci_bus *bus) } if (i >= 3) return; - res = kzalloc(sizeof(struct resource), GFP_KERNEL); + res = kzalloc_obj(struct resource); BUG_ON(res == NULL); res->name = "Legacy VGA memory"; res->flags = IORESOURCE_MEM; diff --git a/arch/powerpc/kernel/pci-hotplug.c b/arch/powerpc/kernel/pci-hotplug.c index 9ea74973d78d..6f444d0822d8 100644 --- a/arch/powerpc/kernel/pci-hotplug.c +++ b/arch/powerpc/kernel/pci-hotplug.c @@ -141,6 +141,9 @@ void pci_hp_add_devices(struct pci_bus *bus) struct pci_controller *phb; struct device_node *dn = pci_bus_to_OF_node(bus); + if (!dn) + return; + phb = pci_bus_to_host(bus); mode = PCI_PROBE_NORMAL; diff --git a/arch/powerpc/kernel/pci_dn.c b/arch/powerpc/kernel/pci_dn.c index 38561d6a2079..a7b664befed2 100644 --- a/arch/powerpc/kernel/pci_dn.c +++ b/arch/powerpc/kernel/pci_dn.c @@ -130,7 +130,7 @@ static struct eeh_dev *eeh_dev_init(struct pci_dn *pdn) struct eeh_dev *edev; /* Allocate EEH device */ - edev = kzalloc(sizeof(*edev), GFP_KERNEL); + edev = kzalloc_obj(*edev); if (!edev) return NULL; @@ -154,7 +154,7 @@ static struct pci_dn *add_one_sriov_vf_pdn(struct pci_dn *parent, if (!parent) return NULL; - pdn = kzalloc(sizeof(*pdn), GFP_KERNEL); + pdn = kzalloc_obj(*pdn); if (!pdn) return NULL; @@ -290,7 +290,7 @@ struct pci_dn *pci_add_device_node_info(struct pci_controller *hose, struct eeh_dev *edev; #endif - pdn = kzalloc(sizeof(*pdn), GFP_KERNEL); + pdn = kzalloc_obj(*pdn); if (pdn == NULL) return NULL; dn->data = pdn; diff --git a/arch/powerpc/kernel/pci_of_scan.c b/arch/powerpc/kernel/pci_of_scan.c index 756043dd06e9..fb9fbf0d1796 100644 --- a/arch/powerpc/kernel/pci_of_scan.c +++ b/arch/powerpc/kernel/pci_of_scan.c @@ -212,6 +212,13 @@ struct pci_dev *of_create_pci_dev(struct device_node *node, dev->error_state = pci_channel_io_normal; dev->dma_mask = 0xffffffff; + /* + * Assume 64-bit addresses for MSI initially. Will be changed to 32-bit + * if MSI (rather than MSI-X) capability does not have + * PCI_MSI_FLAGS_64BIT. Can also be overridden by driver. + */ + dev->msi_addr_mask = DMA_BIT_MASK(64); + /* Early fixups, before probing the BARs */ pci_fixup_device(pci_fixup_early, dev); diff --git a/arch/powerpc/kernel/proc_powerpc.c b/arch/powerpc/kernel/proc_powerpc.c index 3816a2bf2b84..d083b4517065 100644 --- a/arch/powerpc/kernel/proc_powerpc.c +++ b/arch/powerpc/kernel/proc_powerpc.c @@ -9,6 +9,7 @@ #include <linux/proc_fs.h> #include <linux/kernel.h> #include <linux/of.h> +#include <linux/string.h> #include <asm/machdep.h> #include <asm/vdso_datapage.h> @@ -56,7 +57,7 @@ static int __init proc_ppc64_init(void) { struct proc_dir_entry *pde; - strcpy((char *)systemcfg->eye_catcher, "SYSTEMCFG:PPC64"); + strscpy(systemcfg->eye_catcher, "SYSTEMCFG:PPC64"); systemcfg->version.major = SYSTEMCFG_MAJOR; systemcfg->version.minor = SYSTEMCFG_MINOR; systemcfg->processor = mfspr(SPRN_PVR); diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index ef91f71e07c4..a15d0b619b1f 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -1000,7 +1000,7 @@ static inline void tm_reclaim_task(struct task_struct *tsk) WARN_ON(tm_suspend_disabled); - TM_DEBUG("--- tm_reclaim on pid %d (NIP=%lx, " + TM_DEBUG("---- tm_reclaim on pid %d (NIP=%lx, " "ccr=%lx, msr=%lx, trap=%lx)\n", tsk->pid, thr->regs->nip, thr->regs->ccr, thr->regs->msr, @@ -1008,7 +1008,7 @@ static inline void tm_reclaim_task(struct task_struct *tsk) tm_reclaim_thread(thr, TM_CAUSE_RESCHED); - TM_DEBUG("--- tm_reclaim on pid %d complete\n", + TM_DEBUG("---- tm_reclaim on pid %d complete\n", tsk->pid); out_and_saveregs: @@ -1281,9 +1281,6 @@ struct task_struct *__switch_to(struct task_struct *prev, { struct thread_struct *new_thread, *old_thread; struct task_struct *last; -#ifdef CONFIG_PPC_64S_HASH_MMU - struct ppc64_tlb_batch *batch; -#endif new_thread = &new->thread; old_thread = ¤t->thread; @@ -1291,14 +1288,6 @@ struct task_struct *__switch_to(struct task_struct *prev, WARN_ON(!irqs_disabled()); #ifdef CONFIG_PPC_64S_HASH_MMU - batch = this_cpu_ptr(&ppc64_tlb_batch); - if (batch->active) { - current_thread_info()->local_flags |= _TLF_LAZY_MMU; - if (batch->index) - __flush_tlb_pending(batch); - batch->active = 0; - } - /* * On POWER9 the copy-paste buffer can only paste into * foreign real addresses, so unprivileged processes can not @@ -1369,20 +1358,6 @@ struct task_struct *__switch_to(struct task_struct *prev, */ #ifdef CONFIG_PPC_BOOK3S_64 -#ifdef CONFIG_PPC_64S_HASH_MMU - /* - * This applies to a process that was context switched while inside - * arch_enter_lazy_mmu_mode(), to re-activate the batch that was - * deactivated above, before _switch(). This will never be the case - * for new tasks. - */ - if (current_thread_info()->local_flags & _TLF_LAZY_MMU) { - current_thread_info()->local_flags &= ~_TLF_LAZY_MMU; - batch = this_cpu_ptr(&ppc64_tlb_batch); - batch->active = 1; - } -#endif - /* * Math facilities are masked out of the child MSR in copy_thread. * A new task does not need to restore_math because it will @@ -1805,7 +1780,7 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) f = ret_from_kernel_user_thread; } else { struct pt_regs *regs = current_pt_regs(); - unsigned long clone_flags = args->flags; + u64 clone_flags = args->flags; unsigned long usp = args->stack; /* Copy registers */ @@ -1897,8 +1872,6 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) return 0; } -void preload_new_slb_context(unsigned long start, unsigned long sp); - /* * Set up a thread for executing a new program */ @@ -1906,9 +1879,6 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp) { #ifdef CONFIG_PPC64 unsigned long load_addr = regs->gpr[2]; /* saved by ELF_PLAT_INIT */ - - if (IS_ENABLED(CONFIG_PPC_BOOK3S_64) && !radix_enabled()) - preload_new_slb_context(start, sp); #endif #ifdef CONFIG_PPC_TRANSACTIONAL_MEM @@ -2367,14 +2337,14 @@ void __no_sanitize_address show_stack(struct task_struct *tsk, (sp + STACK_INT_FRAME_REGS); lr = regs->link; - printk("%s--- interrupt: %lx at %pS\n", + printk("%s---- interrupt: %lx at %pS\n", loglvl, regs->trap, (void *)regs->nip); // Detect the case of an empty pt_regs at the very base // of the stack and suppress showing it in full. if (!empty_user_regs(regs, tsk)) { __show_regs(regs); - printk("%s--- interrupt: %lx\n", loglvl, regs->trap); + printk("%s---- interrupt: %lx\n", loglvl, regs->trap); } firstframe = 1; diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index e0059842a1c6..9ed9dde7d231 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -860,7 +860,7 @@ void __init early_init_devtree(void *params) */ if (fadump_reserve_mem() == 0) #endif - reserve_crashkernel(); + arch_reserve_crashkernel(); early_reserve_mem(); if (memory_limit > memblock_phys_mem_size()) diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index 57082fac4668..f26e80cbc615 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -1061,7 +1061,7 @@ static const struct ibm_arch_vec ibm_architecture_vec_template __initconst = { .virt_base = cpu_to_be32(0xffffffff), .virt_size = cpu_to_be32(0xffffffff), .load_base = cpu_to_be32(0xffffffff), - .min_rma = cpu_to_be32(512), /* 512MB min RMA */ + .min_rma = cpu_to_be32(MIN_RMA), .min_load = cpu_to_be32(0xffffffff), /* full client load */ .min_rma_percent = 0, /* min RMA percentage of total RAM */ .max_pft_size = 48, /* max log_2(hash table size) */ @@ -2889,11 +2889,12 @@ static void __init fixup_device_tree_pmac(void) char type[8]; phandle node; - // Some pmacs are missing #size-cells on escc nodes + // Some pmacs are missing #size-cells on escc or i2s nodes for (node = 0; prom_next_node(&node); ) { type[0] = '\0'; prom_getprop(node, "device_type", type, sizeof(type)); - if (prom_strcmp(type, "escc")) + if (prom_strcmp(type, "escc") && prom_strcmp(type, "i2s") && + prom_strcmp(type, "media-bay")) continue; if (prom_getproplen(node, "#size-cells") != PROM_ERROR) diff --git a/arch/powerpc/kernel/prom_init_check.sh b/arch/powerpc/kernel/prom_init_check.sh index 69623b9045d5..3090b97258ae 100644 --- a/arch/powerpc/kernel/prom_init_check.sh +++ b/arch/powerpc/kernel/prom_init_check.sh @@ -15,8 +15,8 @@ has_renamed_memintrinsics() { - grep -q "^CONFIG_KASAN=y$" ${KCONFIG_CONFIG} && \ - ! grep -q "^CONFIG_CC_HAS_KASAN_MEMINTRINSIC_PREFIX=y" ${KCONFIG_CONFIG} + grep -q "^CONFIG_KASAN=y$" "${KCONFIG_CONFIG}" && \ + ! grep -q "^CONFIG_CC_HAS_KASAN_MEMINTRINSIC_PREFIX=y" "${KCONFIG_CONFIG}" } if has_renamed_memintrinsics @@ -42,15 +42,15 @@ check_section() { file=$1 section=$2 - size=$(objdump -h -j $section $file 2>/dev/null | awk "\$2 == \"$section\" {print \$3}") + size=$(objdump -h -j "$section" "$file" 2>/dev/null | awk "\$2 == \"$section\" {print \$3}") size=${size:-0} - if [ $size -ne 0 ]; then + if [ "$size" -ne 0 ]; then ERROR=1 echo "Error: Section $section not empty in prom_init.c" >&2 fi } -for UNDEF in $($NM -u $OBJ | awk '{print $2}') +for UNDEF in $($NM -u "$OBJ" | awk '{print $2}') do # On 64-bit nm gives us the function descriptors, which have # a leading . on the name, so strip it off here. @@ -87,8 +87,8 @@ do fi done -check_section $OBJ .data -check_section $OBJ .bss -check_section $OBJ .init.data +check_section "$OBJ" .data +check_section "$OBJ" .bss +check_section "$OBJ" .init.data exit $ERROR diff --git a/arch/powerpc/kernel/ptrace/ptrace-view.c b/arch/powerpc/kernel/ptrace/ptrace-view.c index c1819e0a6684..eb5f2091bb59 100644 --- a/arch/powerpc/kernel/ptrace/ptrace-view.c +++ b/arch/powerpc/kernel/ptrace/ptrace-view.c @@ -568,114 +568,114 @@ static int pkey_set(struct task_struct *target, const struct user_regset *regset static const struct user_regset native_regsets[] = { [REGSET_GPR] = { - .core_note_type = NT_PRSTATUS, .n = ELF_NGREG, + USER_REGSET_NOTE_TYPE(PRSTATUS), .n = ELF_NGREG, .size = sizeof(long), .align = sizeof(long), .regset_get = gpr_get, .set = gpr_set }, [REGSET_FPR] = { - .core_note_type = NT_PRFPREG, .n = ELF_NFPREG, + USER_REGSET_NOTE_TYPE(PRFPREG), .n = ELF_NFPREG, .size = sizeof(double), .align = sizeof(double), .regset_get = fpr_get, .set = fpr_set }, #ifdef CONFIG_ALTIVEC [REGSET_VMX] = { - .core_note_type = NT_PPC_VMX, .n = 34, + USER_REGSET_NOTE_TYPE(PPC_VMX), .n = 34, .size = sizeof(vector128), .align = sizeof(vector128), .active = vr_active, .regset_get = vr_get, .set = vr_set }, #endif #ifdef CONFIG_VSX [REGSET_VSX] = { - .core_note_type = NT_PPC_VSX, .n = 32, + USER_REGSET_NOTE_TYPE(PPC_VSX), .n = 32, .size = sizeof(double), .align = sizeof(double), .active = vsr_active, .regset_get = vsr_get, .set = vsr_set }, #endif #ifdef CONFIG_SPE [REGSET_SPE] = { - .core_note_type = NT_PPC_SPE, .n = 35, + USER_REGSET_NOTE_TYPE(PPC_SPE), .n = 35, .size = sizeof(u32), .align = sizeof(u32), .active = evr_active, .regset_get = evr_get, .set = evr_set }, #endif #ifdef CONFIG_PPC_TRANSACTIONAL_MEM [REGSET_TM_CGPR] = { - .core_note_type = NT_PPC_TM_CGPR, .n = ELF_NGREG, + USER_REGSET_NOTE_TYPE(PPC_TM_CGPR), .n = ELF_NGREG, .size = sizeof(long), .align = sizeof(long), .active = tm_cgpr_active, .regset_get = tm_cgpr_get, .set = tm_cgpr_set }, [REGSET_TM_CFPR] = { - .core_note_type = NT_PPC_TM_CFPR, .n = ELF_NFPREG, + USER_REGSET_NOTE_TYPE(PPC_TM_CFPR), .n = ELF_NFPREG, .size = sizeof(double), .align = sizeof(double), .active = tm_cfpr_active, .regset_get = tm_cfpr_get, .set = tm_cfpr_set }, [REGSET_TM_CVMX] = { - .core_note_type = NT_PPC_TM_CVMX, .n = ELF_NVMX, + USER_REGSET_NOTE_TYPE(PPC_TM_CVMX), .n = ELF_NVMX, .size = sizeof(vector128), .align = sizeof(vector128), .active = tm_cvmx_active, .regset_get = tm_cvmx_get, .set = tm_cvmx_set }, [REGSET_TM_CVSX] = { - .core_note_type = NT_PPC_TM_CVSX, .n = ELF_NVSX, + USER_REGSET_NOTE_TYPE(PPC_TM_CVSX), .n = ELF_NVSX, .size = sizeof(double), .align = sizeof(double), .active = tm_cvsx_active, .regset_get = tm_cvsx_get, .set = tm_cvsx_set }, [REGSET_TM_SPR] = { - .core_note_type = NT_PPC_TM_SPR, .n = ELF_NTMSPRREG, + USER_REGSET_NOTE_TYPE(PPC_TM_SPR), .n = ELF_NTMSPRREG, .size = sizeof(u64), .align = sizeof(u64), .active = tm_spr_active, .regset_get = tm_spr_get, .set = tm_spr_set }, [REGSET_TM_CTAR] = { - .core_note_type = NT_PPC_TM_CTAR, .n = 1, + USER_REGSET_NOTE_TYPE(PPC_TM_CTAR), .n = 1, .size = sizeof(u64), .align = sizeof(u64), .active = tm_tar_active, .regset_get = tm_tar_get, .set = tm_tar_set }, [REGSET_TM_CPPR] = { - .core_note_type = NT_PPC_TM_CPPR, .n = 1, + USER_REGSET_NOTE_TYPE(PPC_TM_CPPR), .n = 1, .size = sizeof(u64), .align = sizeof(u64), .active = tm_ppr_active, .regset_get = tm_ppr_get, .set = tm_ppr_set }, [REGSET_TM_CDSCR] = { - .core_note_type = NT_PPC_TM_CDSCR, .n = 1, + USER_REGSET_NOTE_TYPE(PPC_TM_CDSCR), .n = 1, .size = sizeof(u64), .align = sizeof(u64), .active = tm_dscr_active, .regset_get = tm_dscr_get, .set = tm_dscr_set }, #endif #ifdef CONFIG_PPC64 [REGSET_PPR] = { - .core_note_type = NT_PPC_PPR, .n = 1, + USER_REGSET_NOTE_TYPE(PPC_PPR), .n = 1, .size = sizeof(u64), .align = sizeof(u64), .regset_get = ppr_get, .set = ppr_set }, [REGSET_DSCR] = { - .core_note_type = NT_PPC_DSCR, .n = 1, + USER_REGSET_NOTE_TYPE(PPC_DSCR), .n = 1, .size = sizeof(u64), .align = sizeof(u64), .regset_get = dscr_get, .set = dscr_set }, #endif #ifdef CONFIG_PPC_BOOK3S_64 [REGSET_TAR] = { - .core_note_type = NT_PPC_TAR, .n = 1, + USER_REGSET_NOTE_TYPE(PPC_TAR), .n = 1, .size = sizeof(u64), .align = sizeof(u64), .regset_get = tar_get, .set = tar_set }, [REGSET_EBB] = { - .core_note_type = NT_PPC_EBB, .n = ELF_NEBB, + USER_REGSET_NOTE_TYPE(PPC_EBB), .n = ELF_NEBB, .size = sizeof(u64), .align = sizeof(u64), .active = ebb_active, .regset_get = ebb_get, .set = ebb_set }, [REGSET_PMR] = { - .core_note_type = NT_PPC_PMU, .n = ELF_NPMU, + USER_REGSET_NOTE_TYPE(PPC_PMU), .n = ELF_NPMU, .size = sizeof(u64), .align = sizeof(u64), .active = pmu_active, .regset_get = pmu_get, .set = pmu_set }, [REGSET_DEXCR] = { - .core_note_type = NT_PPC_DEXCR, .n = ELF_NDEXCR, + USER_REGSET_NOTE_TYPE(PPC_DEXCR), .n = ELF_NDEXCR, .size = sizeof(u64), .align = sizeof(u64), .active = dexcr_active, .regset_get = dexcr_get }, #ifdef CONFIG_CHECKPOINT_RESTORE [REGSET_HASHKEYR] = { - .core_note_type = NT_PPC_HASHKEYR, .n = ELF_NHASHKEYR, + USER_REGSET_NOTE_TYPE(PPC_HASHKEYR), .n = ELF_NHASHKEYR, .size = sizeof(u64), .align = sizeof(u64), .active = hashkeyr_active, .regset_get = hashkeyr_get, .set = hashkeyr_set }, @@ -683,7 +683,7 @@ static const struct user_regset native_regsets[] = { #endif #ifdef CONFIG_PPC_MEM_KEYS [REGSET_PKEY] = { - .core_note_type = NT_PPC_PKEY, .n = ELF_NPKEY, + USER_REGSET_NOTE_TYPE(PPC_PKEY), .n = ELF_NPKEY, .size = sizeof(u64), .align = sizeof(u64), .active = pkey_active, .regset_get = pkey_get, .set = pkey_set }, @@ -758,38 +758,37 @@ static int gpr32_set_common_user(struct task_struct *target, const void *kbuf = NULL; compat_ulong_t reg; - if (!user_read_access_begin(u, count)) - return -EFAULT; - - pos /= sizeof(reg); - count /= sizeof(reg); - - for (; count > 0 && pos < PT_MSR; --count) { - unsafe_get_user(reg, u++, Efault); - regs[pos++] = reg; - } - - if (count > 0 && pos == PT_MSR) { - unsafe_get_user(reg, u++, Efault); - set_user_msr(target, reg); - ++pos; - --count; - } - - for (; count > 0 && pos <= PT_MAX_PUT_REG; --count) { - unsafe_get_user(reg, u++, Efault); - regs[pos++] = reg; - } - for (; count > 0 && pos < PT_TRAP; --count, ++pos) - unsafe_get_user(reg, u++, Efault); - - if (count > 0 && pos == PT_TRAP) { - unsafe_get_user(reg, u++, Efault); - set_user_trap(target, reg); - ++pos; - --count; + scoped_user_read_access_size(ubuf, count, efault) { + u = ubuf; + pos /= sizeof(reg); + count /= sizeof(reg); + + for (; count > 0 && pos < PT_MSR; --count) { + unsafe_get_user(reg, u++, efault); + regs[pos++] = reg; + } + + if (count > 0 && pos == PT_MSR) { + unsafe_get_user(reg, u++, efault); + set_user_msr(target, reg); + ++pos; + --count; + } + + for (; count > 0 && pos <= PT_MAX_PUT_REG; --count) { + unsafe_get_user(reg, u++, efault); + regs[pos++] = reg; + } + for (; count > 0 && pos < PT_TRAP; --count, ++pos) + unsafe_get_user(reg, u++, efault); + + if (count > 0 && pos == PT_TRAP) { + unsafe_get_user(reg, u++, efault); + set_user_trap(target, reg); + ++pos; + --count; + } } - user_read_access_end(); ubuf = u; pos *= sizeof(reg); @@ -798,8 +797,7 @@ static int gpr32_set_common_user(struct task_struct *target, (PT_TRAP + 1) * sizeof(reg), -1); return 0; -Efault: - user_read_access_end(); +efault: return -EFAULT; } @@ -843,92 +841,92 @@ static int gpr32_set(struct task_struct *target, */ static const struct user_regset compat_regsets[] = { [REGSET_GPR] = { - .core_note_type = NT_PRSTATUS, .n = ELF_NGREG, + USER_REGSET_NOTE_TYPE(PRSTATUS), .n = ELF_NGREG, .size = sizeof(compat_long_t), .align = sizeof(compat_long_t), .regset_get = gpr32_get, .set = gpr32_set }, [REGSET_FPR] = { - .core_note_type = NT_PRFPREG, .n = ELF_NFPREG, + USER_REGSET_NOTE_TYPE(PRFPREG), .n = ELF_NFPREG, .size = sizeof(double), .align = sizeof(double), .regset_get = fpr_get, .set = fpr_set }, #ifdef CONFIG_ALTIVEC [REGSET_VMX] = { - .core_note_type = NT_PPC_VMX, .n = 34, + USER_REGSET_NOTE_TYPE(PPC_VMX), .n = 34, .size = sizeof(vector128), .align = sizeof(vector128), .active = vr_active, .regset_get = vr_get, .set = vr_set }, #endif #ifdef CONFIG_SPE [REGSET_SPE] = { - .core_note_type = NT_PPC_SPE, .n = 35, + USER_REGSET_NOTE_TYPE(PPC_SPE), .n = 35, .size = sizeof(u32), .align = sizeof(u32), .active = evr_active, .regset_get = evr_get, .set = evr_set }, #endif #ifdef CONFIG_PPC_TRANSACTIONAL_MEM [REGSET_TM_CGPR] = { - .core_note_type = NT_PPC_TM_CGPR, .n = ELF_NGREG, + USER_REGSET_NOTE_TYPE(PPC_TM_CGPR), .n = ELF_NGREG, .size = sizeof(long), .align = sizeof(long), .active = tm_cgpr_active, .regset_get = tm_cgpr32_get, .set = tm_cgpr32_set }, [REGSET_TM_CFPR] = { - .core_note_type = NT_PPC_TM_CFPR, .n = ELF_NFPREG, + USER_REGSET_NOTE_TYPE(PPC_TM_CFPR), .n = ELF_NFPREG, .size = sizeof(double), .align = sizeof(double), .active = tm_cfpr_active, .regset_get = tm_cfpr_get, .set = tm_cfpr_set }, [REGSET_TM_CVMX] = { - .core_note_type = NT_PPC_TM_CVMX, .n = ELF_NVMX, + USER_REGSET_NOTE_TYPE(PPC_TM_CVMX), .n = ELF_NVMX, .size = sizeof(vector128), .align = sizeof(vector128), .active = tm_cvmx_active, .regset_get = tm_cvmx_get, .set = tm_cvmx_set }, [REGSET_TM_CVSX] = { - .core_note_type = NT_PPC_TM_CVSX, .n = ELF_NVSX, + USER_REGSET_NOTE_TYPE(PPC_TM_CVSX), .n = ELF_NVSX, .size = sizeof(double), .align = sizeof(double), .active = tm_cvsx_active, .regset_get = tm_cvsx_get, .set = tm_cvsx_set }, [REGSET_TM_SPR] = { - .core_note_type = NT_PPC_TM_SPR, .n = ELF_NTMSPRREG, + USER_REGSET_NOTE_TYPE(PPC_TM_SPR), .n = ELF_NTMSPRREG, .size = sizeof(u64), .align = sizeof(u64), .active = tm_spr_active, .regset_get = tm_spr_get, .set = tm_spr_set }, [REGSET_TM_CTAR] = { - .core_note_type = NT_PPC_TM_CTAR, .n = 1, + USER_REGSET_NOTE_TYPE(PPC_TM_CTAR), .n = 1, .size = sizeof(u64), .align = sizeof(u64), .active = tm_tar_active, .regset_get = tm_tar_get, .set = tm_tar_set }, [REGSET_TM_CPPR] = { - .core_note_type = NT_PPC_TM_CPPR, .n = 1, + USER_REGSET_NOTE_TYPE(PPC_TM_CPPR), .n = 1, .size = sizeof(u64), .align = sizeof(u64), .active = tm_ppr_active, .regset_get = tm_ppr_get, .set = tm_ppr_set }, [REGSET_TM_CDSCR] = { - .core_note_type = NT_PPC_TM_CDSCR, .n = 1, + USER_REGSET_NOTE_TYPE(PPC_TM_CDSCR), .n = 1, .size = sizeof(u64), .align = sizeof(u64), .active = tm_dscr_active, .regset_get = tm_dscr_get, .set = tm_dscr_set }, #endif #ifdef CONFIG_PPC64 [REGSET_PPR] = { - .core_note_type = NT_PPC_PPR, .n = 1, + USER_REGSET_NOTE_TYPE(PPC_PPR), .n = 1, .size = sizeof(u64), .align = sizeof(u64), .regset_get = ppr_get, .set = ppr_set }, [REGSET_DSCR] = { - .core_note_type = NT_PPC_DSCR, .n = 1, + USER_REGSET_NOTE_TYPE(PPC_DSCR), .n = 1, .size = sizeof(u64), .align = sizeof(u64), .regset_get = dscr_get, .set = dscr_set }, #endif #ifdef CONFIG_PPC_BOOK3S_64 [REGSET_TAR] = { - .core_note_type = NT_PPC_TAR, .n = 1, + USER_REGSET_NOTE_TYPE(PPC_TAR), .n = 1, .size = sizeof(u64), .align = sizeof(u64), .regset_get = tar_get, .set = tar_set }, [REGSET_EBB] = { - .core_note_type = NT_PPC_EBB, .n = ELF_NEBB, + USER_REGSET_NOTE_TYPE(PPC_EBB), .n = ELF_NEBB, .size = sizeof(u64), .align = sizeof(u64), .active = ebb_active, .regset_get = ebb_get, .set = ebb_set }, diff --git a/arch/powerpc/kernel/ptrace/ptrace.c b/arch/powerpc/kernel/ptrace/ptrace.c index 727ed4a14545..c6997df63287 100644 --- a/arch/powerpc/kernel/ptrace/ptrace.c +++ b/arch/powerpc/kernel/ptrace/ptrace.c @@ -215,7 +215,7 @@ static int do_seccomp(struct pt_regs *regs) * have already loaded -ENOSYS into r3, or seccomp has put * something else in r3 (via SECCOMP_RET_ERRNO/TRACE). */ - if (__secure_computing(NULL)) + if (__secure_computing()) return -1; /* diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c index d31c9799cab2..8d81c1e7a8db 100644 --- a/arch/powerpc/kernel/rtas.c +++ b/arch/powerpc/kernel/rtas.c @@ -92,12 +92,14 @@ struct rtas_function { * Per-function locks for sequence-based RTAS functions. */ static DEFINE_MUTEX(rtas_ibm_activate_firmware_lock); -static DEFINE_MUTEX(rtas_ibm_get_dynamic_sensor_state_lock); -static DEFINE_MUTEX(rtas_ibm_get_indices_lock); static DEFINE_MUTEX(rtas_ibm_lpar_perftools_lock); -static DEFINE_MUTEX(rtas_ibm_physical_attestation_lock); -static DEFINE_MUTEX(rtas_ibm_set_dynamic_indicator_lock); +DEFINE_MUTEX(rtas_ibm_physical_attestation_lock); DEFINE_MUTEX(rtas_ibm_get_vpd_lock); +DEFINE_MUTEX(rtas_ibm_get_indices_lock); +DEFINE_MUTEX(rtas_ibm_set_dynamic_indicator_lock); +DEFINE_MUTEX(rtas_ibm_get_dynamic_sensor_state_lock); +DEFINE_MUTEX(rtas_ibm_receive_hvpipe_msg_lock); +DEFINE_MUTEX(rtas_ibm_send_hvpipe_msg_lock); static struct rtas_function rtas_function_table[] __ro_after_init = { [RTAS_FNIDX__CHECK_EXCEPTION] = { @@ -373,6 +375,17 @@ static struct rtas_function rtas_function_table[] __ro_after_init = { [RTAS_FNIDX__IBM_READ_SLOT_RESET_STATE2] = { .name = "ibm,read-slot-reset-state2", }, + [RTAS_FNIDX__IBM_RECEIVE_HVPIPE_MSG] { + .name = "ibm,receive-hvpipe-msg", + .filter = &(const struct rtas_filter) { + .buf_idx1 = 0, .size_idx1 = 1, + .buf_idx2 = -1, .size_idx2 = -1, + }, + /* + * PAPR+ v2.13 R1–7.3.32.1 + */ + .lock = &rtas_ibm_receive_hvpipe_msg_lock, + }, [RTAS_FNIDX__IBM_REMOVE_PE_DMA_WINDOW] = { .name = "ibm,remove-pe-dma-window", }, @@ -391,6 +404,17 @@ static struct rtas_function rtas_function_table[] __ro_after_init = { .buf_idx2 = -1, .size_idx2 = -1, }, }, + [RTAS_FNIDX__IBM_SEND_HVPIPE_MSG] { + .name = "ibm,send-hvpipe-msg", + .filter = &(const struct rtas_filter) { + .buf_idx1 = 1, .size_idx1 = -1, + .buf_idx2 = -1, .size_idx2 = -1, + }, + /* + * PAPR+ v2.13 R1–7.3.32.2 + */ + .lock = &rtas_ibm_send_hvpipe_msg_lock, + }, [RTAS_FNIDX__IBM_SET_DYNAMIC_INDICATOR] = { .name = "ibm,set-dynamic-indicator", .filter = &(const struct rtas_filter) { @@ -798,66 +822,6 @@ void __init udbg_init_rtas_panel(void) udbg_putc = call_rtas_display_status_delay; } -#ifdef CONFIG_UDBG_RTAS_CONSOLE - -/* If you think you're dying before early_init_dt_scan_rtas() does its - * work, you can hard code the token values for your firmware here and - * hardcode rtas.base/entry etc. - */ -static unsigned int rtas_putchar_token = RTAS_UNKNOWN_SERVICE; -static unsigned int rtas_getchar_token = RTAS_UNKNOWN_SERVICE; - -static void udbg_rtascon_putc(char c) -{ - int tries; - - if (!rtas.base) - return; - - /* Add CRs before LFs */ - if (c == '\n') - udbg_rtascon_putc('\r'); - - /* if there is more than one character to be displayed, wait a bit */ - for (tries = 0; tries < 16; tries++) { - if (rtas_call(rtas_putchar_token, 1, 1, NULL, c) == 0) - break; - udelay(1000); - } -} - -static int udbg_rtascon_getc_poll(void) -{ - int c; - - if (!rtas.base) - return -1; - - if (rtas_call(rtas_getchar_token, 0, 2, &c)) - return -1; - - return c; -} - -static int udbg_rtascon_getc(void) -{ - int c; - - while ((c = udbg_rtascon_getc_poll()) == -1) - ; - - return c; -} - - -void __init udbg_init_rtas_console(void) -{ - udbg_putc = udbg_rtascon_putc; - udbg_getc = udbg_rtascon_getc; - udbg_getc_poll = udbg_rtascon_getc_poll; -} -#endif /* CONFIG_UDBG_RTAS_CONSOLE */ - void rtas_progress(char *s, unsigned short hex) { struct device_node *root; @@ -2135,21 +2099,6 @@ int __init early_init_dt_scan_rtas(unsigned long node, rtas.size = *sizep; } -#ifdef CONFIG_UDBG_RTAS_CONSOLE - basep = of_get_flat_dt_prop(node, "put-term-char", NULL); - if (basep) - rtas_putchar_token = *basep; - - basep = of_get_flat_dt_prop(node, "get-term-char", NULL); - if (basep) - rtas_getchar_token = *basep; - - if (rtas_putchar_token != RTAS_UNKNOWN_SERVICE && - rtas_getchar_token != RTAS_UNKNOWN_SERVICE) - udbg_init_rtas_console(); - -#endif - /* break now */ return 1; } diff --git a/arch/powerpc/kernel/rtas_flash.c b/arch/powerpc/kernel/rtas_flash.c index 5407024881e5..583dc16e9d3c 100644 --- a/arch/powerpc/kernel/rtas_flash.c +++ b/arch/powerpc/kernel/rtas_flash.c @@ -312,13 +312,13 @@ static ssize_t rtas_flash_write(struct file *file, const char __user *buffer, { struct rtas_update_flash_t *const uf = &rtas_update_flash_data; char *p; - int next_free, rc; + int next_free; struct flash_block_list *fl; - mutex_lock(&rtas_update_flash_mutex); + guard(mutex)(&rtas_update_flash_mutex); if (uf->status == FLASH_AUTH || count == 0) - goto out; /* discard data */ + return count; /* discard data */ /* In the case that the image is not ready for flashing, the memory * allocated for the block list will be freed upon the release of the @@ -327,7 +327,7 @@ static ssize_t rtas_flash_write(struct file *file, const char __user *buffer, if (uf->flist == NULL) { uf->flist = kmem_cache_zalloc(flash_block_cache, GFP_KERNEL); if (!uf->flist) - goto nomem; + return -ENOMEM; } fl = uf->flist; @@ -338,7 +338,7 @@ static ssize_t rtas_flash_write(struct file *file, const char __user *buffer, /* Need to allocate another block_list */ fl->next = kmem_cache_zalloc(flash_block_cache, GFP_KERNEL); if (!fl->next) - goto nomem; + return -ENOMEM; fl = fl->next; next_free = 0; } @@ -347,25 +347,17 @@ static ssize_t rtas_flash_write(struct file *file, const char __user *buffer, count = RTAS_BLK_SIZE; p = kmem_cache_zalloc(flash_block_cache, GFP_KERNEL); if (!p) - goto nomem; + return -ENOMEM; if(copy_from_user(p, buffer, count)) { kmem_cache_free(flash_block_cache, p); - rc = -EFAULT; - goto error; + return -EFAULT; } fl->blocks[next_free].data = p; fl->blocks[next_free].length = count; fl->num_blocks++; -out: - mutex_unlock(&rtas_update_flash_mutex); - return count; -nomem: - rc = -ENOMEM; -error: - mutex_unlock(&rtas_update_flash_mutex); - return rc; + return count; } /* @@ -405,19 +397,18 @@ static ssize_t manage_flash_write(struct file *file, const char __user *buf, static const char reject_str[] = "0"; static const char commit_str[] = "1"; char stkbuf[10]; - int op, rc; + int op; - mutex_lock(&rtas_manage_flash_mutex); + guard(mutex)(&rtas_manage_flash_mutex); if ((args_buf->status == MANAGE_AUTH) || (count == 0)) - goto out; + return count; op = -1; if (buf) { if (count > 9) count = 9; - rc = -EFAULT; if (copy_from_user (stkbuf, buf, count)) - goto error; + return -EFAULT; if (strncmp(stkbuf, reject_str, strlen(reject_str)) == 0) op = RTAS_REJECT_TMP_IMG; else if (strncmp(stkbuf, commit_str, strlen(commit_str)) == 0) @@ -425,18 +416,11 @@ static ssize_t manage_flash_write(struct file *file, const char __user *buf, } if (op == -1) { /* buf is empty, or contains invalid string */ - rc = -EINVAL; - goto error; + return -EINVAL; } manage_flash(args_buf, op); -out: - mutex_unlock(&rtas_manage_flash_mutex); return count; - -error: - mutex_unlock(&rtas_manage_flash_mutex); - return rc; } /* @@ -499,16 +483,14 @@ static ssize_t validate_flash_write(struct file *file, const char __user *buf, { struct rtas_validate_flash_t *const args_buf = &rtas_validate_flash_data; - int rc; - mutex_lock(&rtas_validate_flash_mutex); + guard(mutex)(&rtas_validate_flash_mutex); /* We are only interested in the first 4K of the * candidate image */ if ((*off >= VALIDATE_BUF_SIZE) || (args_buf->status == VALIDATE_AUTH)) { *off += count; - mutex_unlock(&rtas_validate_flash_mutex); return count; } @@ -519,20 +501,14 @@ static ssize_t validate_flash_write(struct file *file, const char __user *buf, args_buf->status = VALIDATE_INCOMPLETE; } - if (!access_ok(buf, count)) { - rc = -EFAULT; - goto done; - } - if (copy_from_user(args_buf->buf + *off, buf, count)) { - rc = -EFAULT; - goto done; - } + if (!access_ok(buf, count)) + return -EFAULT; + + if (copy_from_user(args_buf->buf + *off, buf, count)) + return -EFAULT; *off += count; - rc = count; -done: - mutex_unlock(&rtas_validate_flash_mutex); - return rc; + return count; } static int validate_flash_release(struct inode *inode, struct file *file) diff --git a/arch/powerpc/kernel/rtasd.c b/arch/powerpc/kernel/rtasd.c index 9bba469239fc..6336ec9aedd0 100644 --- a/arch/powerpc/kernel/rtasd.c +++ b/arch/powerpc/kernel/rtasd.c @@ -89,6 +89,8 @@ static char *rtas_event_type(int type) return "Platform Resource Reassignment Event"; case RTAS_TYPE_HOTPLUG: return "Hotplug Event"; + case RTAS_TYPE_HVPIPE: + return "Hypervisor Pipe Notification event"; } return rtas_type[0]; diff --git a/arch/powerpc/kernel/secure_boot.c b/arch/powerpc/kernel/secure_boot.c index 3a28795b4ed8..28436c1599e0 100644 --- a/arch/powerpc/kernel/secure_boot.c +++ b/arch/powerpc/kernel/secure_boot.c @@ -5,6 +5,7 @@ */ #include <linux/types.h> #include <linux/of.h> +#include <linux/secure_boot.h> #include <linux/string_choices.h> #include <asm/secure_boot.h> @@ -44,6 +45,11 @@ out: return enabled; } +bool arch_get_secureboot(void) +{ + return is_ppc_secureboot_enabled(); +} + bool is_ppc_trustedboot_enabled(void) { struct device_node *node; diff --git a/arch/powerpc/kernel/secvar-sysfs.c b/arch/powerpc/kernel/secvar-sysfs.c index fbeb1cbac01b..395399bbab2c 100644 --- a/arch/powerpc/kernel/secvar-sysfs.c +++ b/arch/powerpc/kernel/secvar-sysfs.c @@ -12,6 +12,7 @@ #include <linux/string.h> #include <linux/of.h> #include <asm/secvar.h> +#include <asm/plpks.h> #define NAME_MAX_SIZE 1024 @@ -52,7 +53,7 @@ static ssize_t size_show(struct kobject *kobj, struct kobj_attribute *attr, } static ssize_t data_read(struct file *filep, struct kobject *kobj, - struct bin_attribute *attr, char *buf, loff_t off, + const struct bin_attribute *attr, char *buf, loff_t off, size_t count) { char *data; @@ -85,7 +86,7 @@ data_fail: } static ssize_t update_write(struct file *filep, struct kobject *kobj, - struct bin_attribute *attr, char *buf, loff_t off, + const struct bin_attribute *attr, char *buf, loff_t off, size_t count) { int rc; @@ -104,11 +105,11 @@ static struct kobj_attribute format_attr = __ATTR_RO(format); static struct kobj_attribute size_attr = __ATTR_RO(size); -static struct bin_attribute data_attr = __BIN_ATTR_RO(data, 0); +static struct bin_attribute data_attr __ro_after_init = __BIN_ATTR_RO(data, 0); -static struct bin_attribute update_attr = __BIN_ATTR_WO(update, 0); +static struct bin_attribute update_attr __ro_after_init = __BIN_ATTR_WO(update, 0); -static struct bin_attribute *secvar_bin_attrs[] = { +static const struct bin_attribute *const secvar_bin_attrs[] = { &data_attr, &update_attr, NULL, @@ -130,7 +131,7 @@ static const struct kobj_type secvar_ktype = { .default_groups = secvar_attr_groups, }; -static int update_kobj_size(void) +static __init int update_kobj_size(void) { u64 varsize; @@ -145,25 +146,12 @@ static int update_kobj_size(void) return 0; } -static int secvar_sysfs_config(struct kobject *kobj) -{ - struct attribute_group config_group = { - .name = "config", - .attrs = (struct attribute **)secvar_ops->config_attrs, - }; - - if (secvar_ops->config_attrs) - return sysfs_create_group(kobj, &config_group); - - return 0; -} - -static int add_var(const char *name) +static __init int add_var(const char *name) { struct kobject *kobj; int rc; - kobj = kzalloc(sizeof(*kobj), GFP_KERNEL); + kobj = kzalloc_obj(*kobj); if (!kobj) return -ENOMEM; @@ -181,7 +169,7 @@ static int add_var(const char *name) return 0; } -static int secvar_sysfs_load(void) +static __init int secvar_sysfs_load(void) { u64 namesize = 0; char *name; @@ -209,7 +197,7 @@ static int secvar_sysfs_load(void) return rc; } -static int secvar_sysfs_load_static(void) +static __init int secvar_sysfs_load_static(void) { const char * const *name_ptr = secvar_ops->var_names; int rc; @@ -224,7 +212,7 @@ static int secvar_sysfs_load_static(void) return 0; } -static int secvar_sysfs_init(void) +static __init int secvar_sysfs_init(void) { u64 max_size; int rc; @@ -260,12 +248,15 @@ static int secvar_sysfs_init(void) goto err; } - rc = secvar_sysfs_config(secvar_kobj); + rc = plpks_config_create_softlink(secvar_kobj); if (rc) { - pr_err("Failed to create config directory\n"); + pr_err("Failed to create softlink to PLPKS config directory"); goto err; } + pr_info("/sys/firmware/secvar/config is now deprecated.\n"); + pr_info("Will be removed in future versions.\n"); + if (secvar_ops->get_next) rc = secvar_sysfs_load(); else diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index a08b0ede4e64..8a86b0efcb1c 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -865,6 +865,10 @@ static __init void print_system_info(void) cur_cpu_spec->cpu_user_features, cur_cpu_spec->cpu_user_features2); pr_info("mmu_features = 0x%08x\n", cur_cpu_spec->mmu_features); + pr_info(" possible = 0x%016lx\n", + (unsigned long)MMU_FTRS_POSSIBLE); + pr_info(" always = 0x%016lx\n", + (unsigned long)MMU_FTRS_ALWAYS); #ifdef CONFIG_PPC64 pr_info("firmware_features = 0x%016lx\n", powerpc_firmware_features); #ifdef CONFIG_PPC_BOOK3S @@ -957,8 +961,6 @@ void __init setup_arch(char **cmdline_p) /* Parse memory topology */ mem_topology_setup(); - /* Set max_mapnr before paging_init() */ - set_max_mapnr(max_pfn); high_memory = (void *)__va(max_low_pfn * PAGE_SIZE); /* @@ -996,15 +998,6 @@ void __init setup_arch(char **cmdline_p) initmem_init(); - /* - * Reserve large chunks of memory for use by CMA for fadump, KVM and - * hugetlb. These must be called after initmem_init(), so that - * pageblock_order is initialised. - */ - fadump_cma_init(); - kvm_cma_reserve(); - gigantic_hugetlb_cma_reserve(); - early_memtest(min_low_pfn << PAGE_SHIFT, max_low_pfn << PAGE_SHIFT); if (ppc_md.setup_arch) diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index e67f3048611f..8fd7cbf3bd04 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -141,10 +141,7 @@ void __init check_smt_enabled(void) smt_enabled_at_boot = 0; else { int smt; - int rc; - - rc = kstrtoint(smt_enabled_cmdline, 10, &smt); - if (!rc) + if (!kstrtoint(smt_enabled_cmdline, 10, &smt)) smt_enabled_at_boot = min(threads_per_core, smt); } @@ -892,7 +889,7 @@ unsigned long memory_block_size_bytes(void) } #endif -#if defined(CONFIG_PPC_INDIRECT_PIO) || defined(CONFIG_PPC_INDIRECT_MMIO) +#ifdef CONFIG_PPC_INDIRECT_PIO struct ppc_pci_io ppc_pci_io; EXPORT_SYMBOL(ppc_pci_io); #endif diff --git a/arch/powerpc/kernel/smp-tbsync.c b/arch/powerpc/kernel/smp-tbsync.c index 21c39355b25e..e6377ff08be9 100644 --- a/arch/powerpc/kernel/smp-tbsync.c +++ b/arch/powerpc/kernel/smp-tbsync.c @@ -117,7 +117,7 @@ void smp_generic_give_timebase(void) pr_debug("Software timebase sync\n"); /* if this fails then this kernel won't work anyway... */ - tbsync = kzalloc( sizeof(*tbsync), GFP_KERNEL ); + tbsync = kzalloc_obj(*tbsync); mb(); running = 1; diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 5ac7084eebc0..3467f86fd78f 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -822,6 +822,8 @@ static int parse_thread_groups(struct device_node *dn, count = of_property_count_u32_elems(dn, "ibm,thread-groups"); thread_group_array = kcalloc(count, sizeof(u32), GFP_KERNEL); + if (!thread_group_array) + return -ENOMEM; ret = of_property_read_u32_array(dn, "ibm,thread-groups", thread_group_array, count); if (ret) @@ -1028,19 +1030,19 @@ static int powerpc_shared_proc_flags(void) * We can't just pass cpu_l2_cache_mask() directly because * returns a non-const pointer and the compiler barfs on that. */ -static const struct cpumask *shared_cache_mask(int cpu) +static const struct cpumask *tl_cache_mask(struct sched_domain_topology_level *tl, int cpu) { return per_cpu(cpu_l2_cache_map, cpu); } #ifdef CONFIG_SCHED_SMT -static const struct cpumask *smallcore_smt_mask(int cpu) +static const struct cpumask *tl_smallcore_smt_mask(struct sched_domain_topology_level *tl, int cpu) { return cpu_smallcore_mask(cpu); } #endif -static struct cpumask *cpu_coregroup_mask(int cpu) +struct cpumask *cpu_coregroup_mask(int cpu) { return per_cpu(cpu_coregroup_map, cpu); } @@ -1054,11 +1056,6 @@ static bool has_coregroup_support(void) return coregroup_enabled; } -static const struct cpumask *cpu_mc_mask(int cpu) -{ - return cpu_coregroup_mask(cpu); -} - static int __init init_big_cores(void) { int cpu; @@ -1090,6 +1087,29 @@ static int __init init_big_cores(void) return 0; } +/* + * die_mask and die_id are only available on systems which support + * multiple coregroups within a same package. On all other systems, die_mask + * would be same as package mask and die_id would be set to -1. + */ +const struct cpumask *cpu_die_mask(int cpu) +{ + if (has_coregroup_support()) + return per_cpu(cpu_coregroup_map, cpu); + else + return cpu_node_mask(cpu); +} +EXPORT_SYMBOL_GPL(cpu_die_mask); + +int cpu_die_id(int cpu) +{ + if (has_coregroup_support()) + return cpu_to_coregroup_id(cpu); + else + return -1; +} +EXPORT_SYMBOL_GPL(cpu_die_id); + void __init smp_prepare_cpus(unsigned int max_cpus) { unsigned int cpu, num_threads; @@ -1152,7 +1172,7 @@ void __init smp_prepare_cpus(unsigned int max_cpus) * Assumption: if boot_cpuid doesn't have a chip-id, then no * other CPUs, will also not have chip-id. */ - chip_id_lookup_table = kcalloc(idx, sizeof(int), GFP_KERNEL); + chip_id_lookup_table = kzalloc_objs(int, idx); if (chip_id_lookup_table) memset(chip_id_lookup_table, -1, sizeof(int) * idx); } @@ -1448,7 +1468,7 @@ static bool update_mask_by_l2(int cpu, cpumask_var_t *mask) return false; } - cpumask_and(*mask, cpu_online_mask, cpu_cpu_mask(cpu)); + cpumask_and(*mask, cpu_online_mask, cpu_node_mask(cpu)); /* Update l2-cache mask with all the CPUs that are part of submask */ or_cpumasks_related(cpu, cpu, submask_fn, cpu_l2_cache_mask); @@ -1538,7 +1558,7 @@ static void update_coregroup_mask(int cpu, cpumask_var_t *mask) return; } - cpumask_and(*mask, cpu_online_mask, cpu_cpu_mask(cpu)); + cpumask_and(*mask, cpu_online_mask, cpu_node_mask(cpu)); /* Update coregroup mask with all the CPUs that are part of submask */ or_cpumasks_related(cpu, cpu, submask_fn, cpu_coregroup_mask); @@ -1601,7 +1621,7 @@ static void add_cpu_to_masks(int cpu) /* If chip_id is -1; limit the cpu_core_mask to within PKG */ if (chip_id == -1) - cpumask_and(mask, mask, cpu_cpu_mask(cpu)); + cpumask_and(mask, mask, cpu_node_mask(cpu)); for_each_cpu(i, mask) { if (chip_id == cpu_to_chip_id(i)) { @@ -1700,28 +1720,23 @@ static void __init build_sched_topology(void) #ifdef CONFIG_SCHED_SMT if (has_big_cores) { pr_info("Big cores detected but using small core scheduling\n"); - powerpc_topology[i++] = (struct sched_domain_topology_level){ - smallcore_smt_mask, powerpc_smt_flags, SD_INIT_NAME(SMT) - }; + powerpc_topology[i++] = + SDTL_INIT(tl_smallcore_smt_mask, powerpc_smt_flags, SMT); } else { - powerpc_topology[i++] = (struct sched_domain_topology_level){ - cpu_smt_mask, powerpc_smt_flags, SD_INIT_NAME(SMT) - }; + powerpc_topology[i++] = SDTL_INIT(tl_smt_mask, powerpc_smt_flags, SMT); } #endif if (shared_caches) { - powerpc_topology[i++] = (struct sched_domain_topology_level){ - shared_cache_mask, powerpc_shared_cache_flags, SD_INIT_NAME(CACHE) - }; + powerpc_topology[i++] = + SDTL_INIT(tl_cache_mask, powerpc_shared_cache_flags, CACHE); } + if (has_coregroup_support()) { - powerpc_topology[i++] = (struct sched_domain_topology_level){ - cpu_mc_mask, powerpc_shared_proc_flags, SD_INIT_NAME(MC) - }; + powerpc_topology[i++] = + SDTL_INIT(tl_mc_mask, powerpc_shared_proc_flags, MC); } - powerpc_topology[i++] = (struct sched_domain_topology_level){ - cpu_cpu_mask, powerpc_shared_proc_flags, SD_INIT_NAME(PKG) - }; + + powerpc_topology[i++] = SDTL_INIT(tl_pkg_mask, powerpc_shared_proc_flags, PKG); /* There must be one trailing NULL entry left. */ BUG_ON(i >= ARRAY_SIZE(powerpc_topology) - 1); diff --git a/arch/powerpc/kernel/static_call.c b/arch/powerpc/kernel/static_call.c index 7cfd0710e757..ec3101f95e53 100644 --- a/arch/powerpc/kernel/static_call.c +++ b/arch/powerpc/kernel/static_call.c @@ -8,26 +8,54 @@ void arch_static_call_transform(void *site, void *tramp, void *func, bool tail) { int err; bool is_ret0 = (func == __static_call_return0); - unsigned long target = (unsigned long)(is_ret0 ? tramp + PPC_SCT_RET0 : func); - bool is_short = is_offset_in_branch_range((long)target - (long)tramp); - - if (!tramp) - return; + unsigned long _tramp = (unsigned long)tramp; + unsigned long _func = (unsigned long)func; + unsigned long _ret0 = _tramp + PPC_SCT_RET0; + bool is_short = is_offset_in_branch_range((long)func - (long)(site ? : tramp)); mutex_lock(&text_mutex); - if (func && !is_short) { - err = patch_ulong(tramp + PPC_SCT_DATA, target); - if (err) - goto out; + if (site && tail) { + if (!func) + err = patch_instruction(site, ppc_inst(PPC_RAW_BLR())); + else if (is_ret0) + err = patch_branch(site, _ret0, 0); + else if (is_short) + err = patch_branch(site, _func, 0); + else if (tramp) + err = patch_branch(site, _tramp, 0); + else + err = 0; + } else if (site) { + if (!func) + err = patch_instruction(site, ppc_inst(PPC_RAW_NOP())); + else if (is_ret0) + err = patch_instruction(site, ppc_inst(PPC_RAW_LI(_R3, 0))); + else if (is_short) + err = patch_branch(site, _func, BRANCH_SET_LINK); + else if (tramp) + err = patch_branch(site, _tramp, BRANCH_SET_LINK); + else + err = 0; + } else if (tramp) { + if (func && !is_short) { + err = patch_ulong(tramp + PPC_SCT_DATA, _func); + if (err) + goto out; + } + + if (!func) + err = patch_instruction(tramp, ppc_inst(PPC_RAW_BLR())); + else if (is_ret0) + err = patch_branch(tramp, _ret0, 0); + else if (is_short) + err = patch_branch(tramp, _func, 0); + else + err = patch_instruction(tramp, ppc_inst(PPC_RAW_NOP())); + } else { + err = 0; } - if (!func) - err = patch_instruction(tramp, ppc_inst(PPC_RAW_BLR())); - else if (is_short) - err = patch_branch(tramp, target, 0); - else - err = patch_instruction(tramp, ppc_inst(PPC_RAW_NOP())); out: mutex_unlock(&text_mutex); diff --git a/arch/powerpc/kernel/switch.S b/arch/powerpc/kernel/switch.S index 608c0ce7cec6..59e3ee99db0e 100644 --- a/arch/powerpc/kernel/switch.S +++ b/arch/powerpc/kernel/switch.S @@ -39,7 +39,6 @@ flush_branch_caches: // Flush the link stack .rept 64 - ANNOTATE_INTRA_FUNCTION_CALL bl .+4 .endr b 1f diff --git a/arch/powerpc/kernel/sys_ppc32.c b/arch/powerpc/kernel/sys_ppc32.c index d451a8229223..03fa487f2614 100644 --- a/arch/powerpc/kernel/sys_ppc32.c +++ b/arch/powerpc/kernel/sys_ppc32.c @@ -101,7 +101,7 @@ PPC32_SYSCALL_DEFINE4(ppc_ftruncate64, unsigned int, fd, u32, reg4, unsigned long, len1, unsigned long, len2) { - return ksys_ftruncate(fd, merge_64(len1, len2)); + return ksys_ftruncate(fd, merge_64(len1, len2), FTRUNCATE_LFS); } PPC32_SYSCALL_DEFINE6(ppc32_fadvise64, diff --git a/arch/powerpc/kernel/syscall.c b/arch/powerpc/kernel/syscall.c index be159ad4b77b..b762677f8737 100644 --- a/arch/powerpc/kernel/syscall.c +++ b/arch/powerpc/kernel/syscall.c @@ -20,8 +20,6 @@ notrace long system_call_exception(struct pt_regs *regs, unsigned long r0) kuap_lock(); - add_random_kstack_offset(); - if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) BUG_ON(irq_soft_mask_return() != IRQS_ALL_DISABLED); @@ -30,6 +28,8 @@ notrace long system_call_exception(struct pt_regs *regs, unsigned long r0) CT_WARN_ON(ct_state() == CT_STATE_KERNEL); user_exit_irqoff(); + add_random_kstack_offset(); + BUG_ON(regs_is_unrecoverable(regs)); BUG_ON(!user_mode(regs)); BUG_ON(arch_irq_disabled_regs(regs)); @@ -173,17 +173,5 @@ notrace long system_call_exception(struct pt_regs *regs, unsigned long r0) } #endif - /* - * Ultimately, this value will get limited by KSTACK_OFFSET_MAX(), - * so the maximum stack offset is 1k bytes (10 bits). - * - * The actual entropy will be further reduced by the compiler when - * applying stack alignment constraints: the powerpc architecture - * may have two kinds of stack alignment (16-bytes and 8-bytes). - * - * So the resulting 6 or 7 bits of entropy is seen in SP[9:4] or SP[9:3]. - */ - choose_random_kstack_offset(mftb()); - return ret; } diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl index d8b4ab78bef0..4fcc7c58a105 100644 --- a/arch/powerpc/kernel/syscalls/syscall.tbl +++ b/arch/powerpc/kernel/syscalls/syscall.tbl @@ -557,3 +557,8 @@ 464 common getxattrat sys_getxattrat 465 common listxattrat sys_listxattrat 466 common removexattrat sys_removexattrat +467 common open_tree_attr sys_open_tree_attr +468 common file_getattr sys_file_getattr +469 common file_setattr sys_file_setattr +470 common listns sys_listns +471 nospu rseq_slice_yield sys_rseq_slice_yield diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index 0727332ad86f..b4472288e0d4 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -137,7 +137,7 @@ EXPORT_SYMBOL_GPL(rtc_lock); static u64 tb_to_ns_scale __read_mostly; static unsigned tb_to_ns_shift __read_mostly; -static u64 boot_tb __read_mostly; +static u64 boot_tb __ro_after_init; extern struct timezone sys_tz; static long timezone_offset; @@ -458,6 +458,10 @@ DEFINE_PER_CPU(u8, irq_work_pending); #endif /* 32 vs 64 bit */ +/* + * Must be called with preemption disabled since it updates + * per-CPU irq_work state and programs the local CPU decrementer. + */ void arch_irq_work_raise(void) { /* @@ -471,10 +475,8 @@ void arch_irq_work_raise(void) * which could get tangled up if we're messing with the same state * here. */ - preempt_disable(); set_irq_work_pending_flag(); set_dec(1); - preempt_enable(); } static void set_dec_or_work(u64 val) @@ -639,6 +641,12 @@ notrace unsigned long long sched_clock(void) return mulhdu(get_tb() - boot_tb, tb_to_ns_scale) << tb_to_ns_shift; } +#ifdef CONFIG_PPC_SPLPAR +u64 get_boot_tb(void) +{ + return boot_tb; +} +#endif #ifdef CONFIG_PPC_PSERIES @@ -901,6 +909,38 @@ void secondary_cpu_time_init(void) register_decrementer_clockevent(smp_processor_id()); } +/* + * Divide a 128-bit dividend by a 32-bit divisor, leaving a 128 bit + * result. + */ +static __init void div128_by_32(u64 dividend_high, u64 dividend_low, + unsigned int divisor, struct div_result *dr) +{ + unsigned long a, b, c, d; + unsigned long w, x, y, z; + u64 ra, rb, rc; + + a = dividend_high >> 32; + b = dividend_high & 0xffffffff; + c = dividend_low >> 32; + d = dividend_low & 0xffffffff; + + w = a / divisor; + ra = ((u64)(a - (w * divisor)) << 32) + b; + + rb = ((u64)do_div(ra, divisor) << 32) + c; + x = ra; + + rc = ((u64)do_div(rb, divisor) << 32) + d; + y = rb; + + do_div(rc, divisor); + z = rc; + + dr->result_high = ((u64)w << 32) + x; + dr->result_low = ((u64)y << 32) + z; +} + /* This function is only called on the boot processor */ void __init time_init(void) { @@ -950,7 +990,7 @@ void __init time_init(void) sys_tz.tz_dsttime = 0; } - vdso_data->tb_ticks_per_sec = tb_ticks_per_sec; + vdso_k_arch_data->tb_ticks_per_sec = tb_ticks_per_sec; #ifdef CONFIG_PPC64_PROC_SYSTEMCFG systemcfg->tb_ticks_per_sec = tb_ticks_per_sec; #endif @@ -974,39 +1014,6 @@ void __init time_init(void) enable_sched_clock_irqtime(); } -/* - * Divide a 128-bit dividend by a 32-bit divisor, leaving a 128 bit - * result. - */ -void div128_by_32(u64 dividend_high, u64 dividend_low, - unsigned divisor, struct div_result *dr) -{ - unsigned long a, b, c, d; - unsigned long w, x, y, z; - u64 ra, rb, rc; - - a = dividend_high >> 32; - b = dividend_high & 0xffffffff; - c = dividend_low >> 32; - d = dividend_low & 0xffffffff; - - w = a / divisor; - ra = ((u64)(a - (w * divisor)) << 32) + b; - - rb = ((u64) do_div(ra, divisor) << 32) + c; - x = ra; - - rc = ((u64) do_div(rb, divisor) << 32) + d; - y = rb; - - do_div(rc, divisor); - z = rc; - - dr->result_high = ((u64)w << 32) + x; - dr->result_low = ((u64)y << 32) + z; - -} - /* We don't need to calibrate delay, we use the CPU timebase for that */ void calibrate_delay(void) { diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c index 2f776f137a89..1b2f293e7dcb 100644 --- a/arch/powerpc/kernel/trace/ftrace.c +++ b/arch/powerpc/kernel/trace/ftrace.c @@ -37,11 +37,29 @@ unsigned long ftrace_call_adjust(unsigned long addr) if (addr >= (unsigned long)__exittext_begin && addr < (unsigned long)__exittext_end) return 0; - if (IS_ENABLED(CONFIG_ARCH_USING_PATCHABLE_FUNCTION_ENTRY) && - !IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE)) { - addr += MCOUNT_INSN_SIZE; - if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS)) + if (IS_ENABLED(CONFIG_ARCH_USING_PATCHABLE_FUNCTION_ENTRY)) { + if (!IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE)) { addr += MCOUNT_INSN_SIZE; + if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS)) + addr += MCOUNT_INSN_SIZE; + } else if (IS_ENABLED(CONFIG_CC_IS_CLANG) && IS_ENABLED(CONFIG_PPC64)) { + /* + * addr points to global entry point though the NOP was emitted at local + * entry point due to https://github.com/llvm/llvm-project/issues/163706 + * Handle that here with ppc_function_entry() for kernel symbols while + * adjusting module addresses in the else case, by looking for the below + * module global entry point sequence: + * ld r2, -8(r12) + * add r2, r2, r12 + */ + if (is_kernel_text(addr) || is_kernel_inittext(addr)) + addr = ppc_function_entry((void *)addr); + else if ((ppc_inst_val(ppc_inst_read((u32 *)addr)) == + PPC_RAW_LD(_R2, _R12, -8)) && + (ppc_inst_val(ppc_inst_read((u32 *)(addr+4))) == + PPC_RAW_ADD(_R2, _R2, _R12))) + addr += 8; + } } return addr; @@ -115,10 +133,8 @@ static unsigned long ftrace_lookup_module_stub(unsigned long ip, unsigned long a { struct module *mod = NULL; - preempt_disable(); - mod = __module_text_address(ip); - preempt_enable(); - + scoped_guard(rcu) + mod = __module_text_address(ip); if (!mod) pr_err("No module loaded at addr=%lx\n", ip); @@ -490,8 +506,10 @@ int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec) return ret; /* Set up out-of-line stub */ - if (IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE)) - return ftrace_init_ool_stub(mod, rec); + if (IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE)) { + ret = ftrace_init_ool_stub(mod, rec); + goto out; + } /* Nop-out the ftrace location */ new = ppc_inst(PPC_RAW_NOP()); @@ -522,6 +540,10 @@ int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec) return -EINVAL; } +out: + if (!ret) + ret = ftrace_rec_set_nop_ops(rec); + return ret; } diff --git a/arch/powerpc/kernel/trace/ftrace_64_pg.c b/arch/powerpc/kernel/trace/ftrace_64_pg.c index ac35015f04c6..5c6e545d1708 100644 --- a/arch/powerpc/kernel/trace/ftrace_64_pg.c +++ b/arch/powerpc/kernel/trace/ftrace_64_pg.c @@ -120,10 +120,8 @@ static struct module *ftrace_lookup_module(struct dyn_ftrace *rec) { struct module *mod; - preempt_disable(); - mod = __module_text_address(rec->ip); - preempt_enable(); - + scoped_guard(rcu) + mod = __module_text_address(rec->ip); if (!mod) pr_err("No module loaded at addr=%lx\n", rec->ip); diff --git a/arch/powerpc/kernel/trace/ftrace_entry.S b/arch/powerpc/kernel/trace/ftrace_entry.S index 2c1b24100eca..6599fe3c6234 100644 --- a/arch/powerpc/kernel/trace/ftrace_entry.S +++ b/arch/powerpc/kernel/trace/ftrace_entry.S @@ -212,10 +212,10 @@ bne- 1f mr r3, r15 +1: mtlr r3 .if \allregs == 0 REST_GPR(15, r1) .endif -1: mtlr r3 #endif /* Restore gprs */ @@ -409,23 +409,31 @@ EXPORT_SYMBOL(_mcount) _GLOBAL(return_to_handler) /* need to save return values */ #ifdef CONFIG_PPC64 - std r4, -32(r1) - std r3, -24(r1) + stdu r1, -SWITCH_FRAME_SIZE(r1) + std r4, GPR4(r1) + std r3, GPR3(r1) + /* Save previous stack pointer (r1) */ + addi r3, r1, SWITCH_FRAME_SIZE + std r3, GPR1(r1) /* save TOC */ - std r2, -16(r1) - std r31, -8(r1) + std r2, 24(r1) + std r31, 32(r1) mr r31, r1 - stdu r1, -112(r1) - + /* pass ftrace_regs/pt_regs to ftrace_return_to_handler */ + addi r3, r1, STACK_INT_FRAME_REGS /* * We might be called from a module. * Switch to our TOC to run inside the core kernel. */ LOAD_PACA_TOC() #else - stwu r1, -16(r1) - stw r3, 8(r1) - stw r4, 12(r1) + stwu r1, -SWITCH_FRAME_SIZE(r1) + stw r4, GPR4(r1) + stw r3, GPR3(r1) + addi r3, r1, SWITCH_FRAME_SIZE + stw r3, GPR1(r1) + /* pass ftrace_regs/pt_regs to ftrace_return_to_handler */ + addi r3, r1, STACK_INT_FRAME_REGS #endif bl ftrace_return_to_handler @@ -435,15 +443,15 @@ _GLOBAL(return_to_handler) mtlr r3 #ifdef CONFIG_PPC64 - ld r1, 0(r1) - ld r4, -32(r1) - ld r3, -24(r1) - ld r2, -16(r1) - ld r31, -8(r1) + ld r4, GPR4(r1) + ld r3, GPR3(r1) + ld r2, 24(r1) + ld r31, 32(r1) + ld r1, 0(r1) #else - lwz r3, 8(r1) - lwz r4, 12(r1) - addi r1, r1, 16 + lwz r3, GPR3(r1) + lwz r4, GPR4(r1) + addi r1, r1, SWITCH_FRAME_SIZE #endif /* Jump back to real return address */ diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index edf5cabe5dfd..cb8e9357383e 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -263,10 +263,9 @@ static int __die(const char *str, struct pt_regs *regs, long err) { printk("Oops: %s, sig: %ld [#%d]\n", str, err, ++die_counter); - printk("%s PAGE_SIZE=%luK%s%s%s%s%s%s %s\n", + printk("%s PAGE_SIZE=%luK%s %s%s%s%s %s\n", IS_ENABLED(CONFIG_CPU_LITTLE_ENDIAN) ? "LE" : "BE", PAGE_SIZE / 1024, get_mmu_str(), - IS_ENABLED(CONFIG_PREEMPT) ? " PREEMPT" : "", IS_ENABLED(CONFIG_SMP) ? " SMP" : "", IS_ENABLED(CONFIG_SMP) ? (" NR_CPUS=" __stringify(NR_CPUS)) : "", debug_pagealloc_enabled() ? " DEBUG_PAGEALLOC" : "", diff --git a/arch/powerpc/kernel/udbg.c b/arch/powerpc/kernel/udbg.c index 0a72a537f879..862b22b2b616 100644 --- a/arch/powerpc/kernel/udbg.c +++ b/arch/powerpc/kernel/udbg.c @@ -36,9 +36,6 @@ void __init udbg_early_init(void) #elif defined(CONFIG_PPC_EARLY_DEBUG_RTAS_PANEL) /* RTAS panel debug */ udbg_init_rtas_panel(); -#elif defined(CONFIG_PPC_EARLY_DEBUG_RTAS_CONSOLE) - /* RTAS console debug */ - udbg_init_rtas_console(); #elif defined(CONFIG_PPC_EARLY_DEBUG_PAS_REALMODE) udbg_init_pas_realmode(); #elif defined(CONFIG_PPC_EARLY_DEBUG_BOOTX) diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c index 43379365ce1b..d3ef251048c9 100644 --- a/arch/powerpc/kernel/vdso.c +++ b/arch/powerpc/kernel/vdso.c @@ -17,10 +17,11 @@ #include <linux/elf.h> #include <linux/security.h> #include <linux/syscalls.h> -#include <linux/time_namespace.h> +#include <linux/vdso_datastore.h> #include <vdso/datapage.h> #include <asm/syscall.h> +#include <asm/syscalls.h> #include <asm/processor.h> #include <asm/mmu.h> #include <asm/mmu_context.h> @@ -32,32 +33,14 @@ #include <asm/vdso_datapage.h> #include <asm/setup.h> +static_assert(__VDSO_PAGES == VDSO_NR_PAGES); + /* The alignment of the vDSO */ #define VDSO_ALIGNMENT (1 << 16) extern char vdso32_start, vdso32_end; extern char vdso64_start, vdso64_end; -long sys_ni_syscall(void); - -/* - * The vdso data page (aka. systemcfg for old ppc64 fans) is here. - * Once the early boot kernel code no longer needs to muck around - * with it, it will become dynamically allocated - */ -static union { - struct vdso_arch_data data; - u8 page[2 * PAGE_SIZE]; -} vdso_data_store __page_aligned_data; -struct vdso_arch_data *vdso_data = &vdso_data_store.data; - -enum vvar_pages { - VVAR_BASE_PAGE_OFFSET, - VVAR_TIME_PAGE_OFFSET, - VVAR_TIMENS_PAGE_OFFSET, - VVAR_NR_PAGES, -}; - static int vdso_mremap(const struct vm_special_mapping *sm, struct vm_area_struct *new_vma, unsigned long text_size) { @@ -96,14 +79,6 @@ static void vdso_close(const struct vm_special_mapping *sm, struct vm_area_struc mm->context.vdso = NULL; } -static vm_fault_t vvar_fault(const struct vm_special_mapping *sm, - struct vm_area_struct *vma, struct vm_fault *vmf); - -static struct vm_special_mapping vvar_spec __ro_after_init = { - .name = "[vvar]", - .fault = vvar_fault, -}; - static struct vm_special_mapping vdso32_spec __ro_after_init = { .name = "[vdso]", .mremap = vdso32_mremap, @@ -116,73 +91,6 @@ static struct vm_special_mapping vdso64_spec __ro_after_init = { .close = vdso_close, }; -#ifdef CONFIG_TIME_NS -struct vdso_data *arch_get_vdso_data(void *vvar_page) -{ - return vvar_page; -} - -/* - * The vvar mapping contains data for a specific time namespace, so when a task - * changes namespace we must unmap its vvar data for the old namespace. - * Subsequent faults will map in data for the new namespace. - * - * For more details see timens_setup_vdso_data(). - */ -int vdso_join_timens(struct task_struct *task, struct time_namespace *ns) -{ - struct mm_struct *mm = task->mm; - VMA_ITERATOR(vmi, mm, 0); - struct vm_area_struct *vma; - - mmap_read_lock(mm); - for_each_vma(vmi, vma) { - if (vma_is_special_mapping(vma, &vvar_spec)) - zap_vma_pages(vma); - } - mmap_read_unlock(mm); - - return 0; -} -#endif - -static vm_fault_t vvar_fault(const struct vm_special_mapping *sm, - struct vm_area_struct *vma, struct vm_fault *vmf) -{ - struct page *timens_page = find_timens_vvar_page(vma); - unsigned long pfn; - - switch (vmf->pgoff) { - case VVAR_BASE_PAGE_OFFSET: - pfn = virt_to_pfn(vdso_data); - break; - case VVAR_TIME_PAGE_OFFSET: - if (timens_page) - pfn = page_to_pfn(timens_page); - else - pfn = virt_to_pfn(vdso_data->data); - break; -#ifdef CONFIG_TIME_NS - case VVAR_TIMENS_PAGE_OFFSET: - /* - * If a task belongs to a time namespace then a namespace - * specific VVAR is mapped with the VVAR_DATA_PAGE_OFFSET and - * the real VVAR page is mapped with the VVAR_TIMENS_PAGE_OFFSET - * offset. - * See also the comment near timens_setup_vdso_data(). - */ - if (!timens_page) - return VM_FAULT_SIGBUS; - pfn = virt_to_pfn(vdso_data->data); - break; -#endif /* CONFIG_TIME_NS */ - default: - return VM_FAULT_SIGBUS; - } - - return vmf_insert_pfn(vma, vmf->address, pfn); -} - /* * This is called from binfmt_elf, we create the special vma for the * vDSO and insert it into the mm struct tree @@ -191,7 +99,7 @@ static int __arch_setup_additional_pages(struct linux_binprm *bprm, int uses_int { unsigned long vdso_size, vdso_base, mappings_size; struct vm_special_mapping *vdso_spec; - unsigned long vvar_size = VVAR_NR_PAGES * PAGE_SIZE; + unsigned long vvar_size = VDSO_NR_PAGES * PAGE_SIZE; struct mm_struct *mm = current->mm; struct vm_area_struct *vma; @@ -217,9 +125,7 @@ static int __arch_setup_additional_pages(struct linux_binprm *bprm, int uses_int /* Add required alignment. */ vdso_base = ALIGN(vdso_base, VDSO_ALIGNMENT); - vma = _install_special_mapping(mm, vdso_base, vvar_size, - VM_READ | VM_MAYREAD | VM_IO | - VM_DONTDUMP | VM_PFNMAP, &vvar_spec); + vma = vdso_install_vvar_mapping(mm, vdso_base); if (IS_ERR(vma)) return PTR_ERR(vma); @@ -299,10 +205,10 @@ static void __init vdso_setup_syscall_map(void) for (i = 0; i < NR_syscalls; i++) { if (sys_call_table[i] != (void *)&sys_ni_syscall) - vdso_data->syscall_map[i >> 5] |= 0x80000000UL >> (i & 0x1f); + vdso_k_arch_data->syscall_map[i >> 5] |= 0x80000000UL >> (i & 0x1f); if (IS_ENABLED(CONFIG_COMPAT) && compat_sys_call_table[i] != (void *)&sys_ni_syscall) - vdso_data->compat_syscall_map[i >> 5] |= 0x80000000UL >> (i & 0x1f); + vdso_k_arch_data->compat_syscall_map[i >> 5] |= 0x80000000UL >> (i & 0x1f); } } @@ -339,7 +245,7 @@ static struct page ** __init vdso_setup_pages(void *start, void *end) struct page **pagelist; int pages = (end - start) >> PAGE_SHIFT; - pagelist = kcalloc(pages + 1, sizeof(struct page *), GFP_KERNEL); + pagelist = kzalloc_objs(struct page *, pages + 1); if (!pagelist) panic("%s: Cannot allocate page list for VDSO", __func__); @@ -352,10 +258,10 @@ static struct page ** __init vdso_setup_pages(void *start, void *end) static int __init vdso_init(void) { #ifdef CONFIG_PPC64 - vdso_data->dcache_block_size = ppc64_caches.l1d.block_size; - vdso_data->icache_block_size = ppc64_caches.l1i.block_size; - vdso_data->dcache_log_block_size = ppc64_caches.l1d.log_block_size; - vdso_data->icache_log_block_size = ppc64_caches.l1i.log_block_size; + vdso_k_arch_data->dcache_block_size = ppc64_caches.l1d.block_size; + vdso_k_arch_data->icache_block_size = ppc64_caches.l1i.block_size; + vdso_k_arch_data->dcache_log_block_size = ppc64_caches.l1d.log_block_size; + vdso_k_arch_data->icache_log_block_size = ppc64_caches.l1i.log_block_size; #endif /* CONFIG_PPC64 */ vdso_setup_syscall_map(); diff --git a/arch/powerpc/kernel/vdso/Makefile b/arch/powerpc/kernel/vdso/Makefile index 0e3ed6fb199f..368759f81708 100644 --- a/arch/powerpc/kernel/vdso/Makefile +++ b/arch/powerpc/kernel/vdso/Makefile @@ -3,7 +3,7 @@ # List of files in the vdso, has to be asm only for now # Include the generic Makefile to check the built vdso. -include $(srctree)/lib/vdso/Makefile +include $(srctree)/lib/vdso/Makefile.include obj-vdso32 = sigtramp32-32.o gettimeofday-32.o datapage-32.o cacheflush-32.o note-32.o getcpu-32.o obj-vdso64 = sigtramp64-64.o gettimeofday-64.o datapage-64.o cacheflush-64.o note-64.o getcpu-64.o @@ -53,7 +53,7 @@ ldflags-$(CONFIG_LD_ORPHAN_WARN) += -Wl,--orphan-handling=$(CONFIG_LD_ORPHAN_WAR ldflags-y += $(filter-out $(CC_AUTO_VAR_INIT_ZERO_ENABLER) $(CC_FLAGS_FTRACE) -Wa$(comma)%, $(KBUILD_CPPFLAGS) $(KBUILD_CFLAGS)) CC32FLAGS := -m32 -CC32FLAGSREMOVE := -mcmodel=medium -mabi=elfv1 -mabi=elfv2 -mcall-aixdesc +CC32FLAGSREMOVE := -mcmodel=medium -mabi=elfv1 -mabi=elfv2 -mcall-aixdesc -mpcrel ifdef CONFIG_CC_IS_CLANG # This flag is supported by clang for 64-bit but not 32-bit so it will cause # an unused command line flag warning for this file. @@ -62,6 +62,12 @@ CC32FLAGSREMOVE += -fno-stack-clash-protection # 32-bit one. clang validates the values passed to these arguments during # parsing, even when -fno-stack-protector is passed afterwards. CC32FLAGSREMOVE += -mstack-protector-guard% +# ftrace is disabled for the vdso but arch/powerpc/Makefile adds this define to +# KBUILD_CPPFLAGS, which enables use of the 'patchable_function_entry' +# attribute in the 'inline' define via 'notrace'. This attribute is not +# supported for the powerpcle target, resulting in many instances of +# -Wunknown-attributes. +CC32FLAGSREMOVE += -DCC_USING_PATCHABLE_FUNCTION_ENTRY endif LD32FLAGS := -Wl,-soname=linux-vdso32.so.1 AS32FLAGS := -D__VDSO32__ diff --git a/arch/powerpc/kernel/vdso/cacheflush.S b/arch/powerpc/kernel/vdso/cacheflush.S index 0085ae464dac..488d3ade11e6 100644 --- a/arch/powerpc/kernel/vdso/cacheflush.S +++ b/arch/powerpc/kernel/vdso/cacheflush.S @@ -30,7 +30,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE) #ifdef CONFIG_PPC64 mflr r12 .cfi_register lr,r12 - get_datapage r10 + get_datapage r10 vdso_u_arch_data mtlr r12 .cfi_restore lr #endif diff --git a/arch/powerpc/kernel/vdso/datapage.S b/arch/powerpc/kernel/vdso/datapage.S index db8e167f0166..d23b2e8e2a34 100644 --- a/arch/powerpc/kernel/vdso/datapage.S +++ b/arch/powerpc/kernel/vdso/datapage.S @@ -28,7 +28,7 @@ V_FUNCTION_BEGIN(__kernel_get_syscall_map) mflr r12 .cfi_register lr,r12 mr. r4,r3 - get_datapage r3 + get_datapage r3 vdso_u_arch_data mtlr r12 #ifdef __powerpc64__ addi r3,r3,CFG_SYSCALL_MAP64 @@ -52,7 +52,7 @@ V_FUNCTION_BEGIN(__kernel_get_tbfreq) .cfi_startproc mflr r12 .cfi_register lr,r12 - get_datapage r3 + get_datapage r3 vdso_u_arch_data #ifndef __powerpc64__ lwz r4,(CFG_TB_TICKS_PER_SEC + 4)(r3) #endif diff --git a/arch/powerpc/kernel/vdso/gettimeofday.S b/arch/powerpc/kernel/vdso/gettimeofday.S index 5333848322ca..1c8e51691bf8 100644 --- a/arch/powerpc/kernel/vdso/gettimeofday.S +++ b/arch/powerpc/kernel/vdso/gettimeofday.S @@ -33,9 +33,9 @@ .cfi_rel_offset r2, PPC_MIN_STKFRM + STK_GOT #endif .ifeq \call_time - get_datapage r5 VDSO_DATA_OFFSET + get_datapage r5 vdso_u_time_data .else - get_datapage r4 VDSO_DATA_OFFSET + get_datapage r4 vdso_u_time_data .endif bl CFUNC(DOTSYM(\funct)) PPC_LL r0, PPC_MIN_STKFRM + PPC_LR_STKOFF(r1) @@ -103,6 +103,18 @@ V_FUNCTION_BEGIN(__kernel_clock_getres) cvdso_call __c_kernel_clock_getres V_FUNCTION_END(__kernel_clock_getres) +/* + * Exact prototype of clock_getres_time64() + * + * int __kernel_clock_getres(clockid_t clock_id, struct __timespec64 *res); + * + */ +#ifndef __powerpc64__ +V_FUNCTION_BEGIN(__kernel_clock_getres_time64) + cvdso_call __c_kernel_clock_getres_time64 +V_FUNCTION_END(__kernel_clock_getres_time64) +#endif + /* * Exact prototype of time() diff --git a/arch/powerpc/kernel/vdso/vdso32.lds.S b/arch/powerpc/kernel/vdso/vdso32.lds.S index 1a1b0b6d681a..3f384a2526ae 100644 --- a/arch/powerpc/kernel/vdso/vdso32.lds.S +++ b/arch/powerpc/kernel/vdso/vdso32.lds.S @@ -6,6 +6,7 @@ #include <asm/vdso.h> #include <asm/page.h> #include <asm-generic/vmlinux.lds.h> +#include <vdso/datapage.h> #ifdef __LITTLE_ENDIAN__ OUTPUT_FORMAT("elf32-powerpcle", "elf32-powerpcle", "elf32-powerpcle") @@ -16,7 +17,8 @@ OUTPUT_ARCH(powerpc:common) SECTIONS { - PROVIDE(_vdso_datapage = . - 3 * PAGE_SIZE); + VDSO_VVAR_SYMS + . = SIZEOF_HEADERS; .hash : { *(.hash) } :text @@ -122,6 +124,7 @@ VERSION __kernel_clock_gettime; __kernel_clock_gettime64; __kernel_clock_getres; + __kernel_clock_getres_time64; __kernel_time; __kernel_get_tbfreq; __kernel_sync_dicache; diff --git a/arch/powerpc/kernel/vdso/vdso64.lds.S b/arch/powerpc/kernel/vdso/vdso64.lds.S index e21b5506cad6..32102a05eaa7 100644 --- a/arch/powerpc/kernel/vdso/vdso64.lds.S +++ b/arch/powerpc/kernel/vdso/vdso64.lds.S @@ -6,6 +6,7 @@ #include <asm/vdso.h> #include <asm/page.h> #include <asm-generic/vmlinux.lds.h> +#include <vdso/datapage.h> #ifdef __LITTLE_ENDIAN__ OUTPUT_FORMAT("elf64-powerpcle", "elf64-powerpcle", "elf64-powerpcle") @@ -16,7 +17,8 @@ OUTPUT_ARCH(powerpc:common64) SECTIONS { - PROVIDE(_vdso_datapage = . - 3 * PAGE_SIZE); + VDSO_VVAR_SYMS + . = SIZEOF_HEADERS; .hash : { *(.hash) } :text diff --git a/arch/powerpc/kernel/vdso/vgettimeofday.c b/arch/powerpc/kernel/vdso/vgettimeofday.c index 55a287c9a736..3c194e1ab562 100644 --- a/arch/powerpc/kernel/vdso/vgettimeofday.c +++ b/arch/powerpc/kernel/vdso/vgettimeofday.c @@ -7,43 +7,49 @@ #ifdef __powerpc64__ int __c_kernel_clock_gettime(clockid_t clock, struct __kernel_timespec *ts, - const struct vdso_data *vd) + const struct vdso_time_data *vd) { return __cvdso_clock_gettime_data(vd, clock, ts); } int __c_kernel_clock_getres(clockid_t clock_id, struct __kernel_timespec *res, - const struct vdso_data *vd) + const struct vdso_time_data *vd) { return __cvdso_clock_getres_data(vd, clock_id, res); } #else int __c_kernel_clock_gettime(clockid_t clock, struct old_timespec32 *ts, - const struct vdso_data *vd) + const struct vdso_time_data *vd) { return __cvdso_clock_gettime32_data(vd, clock, ts); } int __c_kernel_clock_gettime64(clockid_t clock, struct __kernel_timespec *ts, - const struct vdso_data *vd) + const struct vdso_time_data *vd) { return __cvdso_clock_gettime_data(vd, clock, ts); } int __c_kernel_clock_getres(clockid_t clock_id, struct old_timespec32 *res, - const struct vdso_data *vd) + const struct vdso_time_data *vd) { return __cvdso_clock_getres_time32_data(vd, clock_id, res); } + +int __c_kernel_clock_getres_time64(clockid_t clock_id, struct __kernel_timespec *res, + const struct vdso_time_data *vd) +{ + return __cvdso_clock_getres_data(vd, clock_id, res); +} #endif int __c_kernel_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz, - const struct vdso_data *vd) + const struct vdso_time_data *vd) { return __cvdso_gettimeofday_data(vd, tv, tz); } -__kernel_old_time_t __c_kernel_time(__kernel_old_time_t *time, const struct vdso_data *vd) +__kernel_old_time_t __c_kernel_time(__kernel_old_time_t *time, const struct vdso_time_data *vd) { return __cvdso_time_data(vd, time); } diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index b4c9decc7a75..8fc11d6565bf 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -1,10 +1,4 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#ifdef CONFIG_PPC64 -#define PROVIDE32(x) PROVIDE(__unused__##x) -#else -#define PROVIDE32(x) PROVIDE(x) -#endif - #define BSS_FIRST_SECTIONS *(.bss.prominit) #define EMITS_PT_NOTE #define RO_EXCEPTION_TABLE_ALIGN 0 @@ -127,7 +121,6 @@ SECTIONS . = ALIGN(PAGE_SIZE); _etext = .; - PROVIDE32 (etext = .); /* Read-only data */ RO_DATA(PAGE_SIZE) @@ -337,7 +330,6 @@ SECTIONS } .hash : AT(ADDR(.hash) - LOAD_OFFSET) { *(.hash) } .gnu.hash : AT(ADDR(.gnu.hash) - LOAD_OFFSET) { *(.gnu.hash) } - .interp : AT(ADDR(.interp) - LOAD_OFFSET) { *(.interp) } .rela.dyn : AT(ADDR(.rela.dyn) - LOAD_OFFSET) { __rela_dyn_start = .; @@ -394,7 +386,6 @@ SECTIONS . = ALIGN(PAGE_SIZE); _edata = .; - PROVIDE32 (edata = .); /* * And finally the bss @@ -404,9 +395,9 @@ SECTIONS . = ALIGN(PAGE_SIZE); _end = . ; - PROVIDE32 (end = .); DWARF_DEBUG + MODINFO ELF_DETAILS DISCARDS diff --git a/arch/powerpc/kernel/watchdog.c b/arch/powerpc/kernel/watchdog.c index 8c464a5d8246..764001deb060 100644 --- a/arch/powerpc/kernel/watchdog.c +++ b/arch/powerpc/kernel/watchdog.c @@ -26,6 +26,7 @@ #include <linux/delay.h> #include <linux/processor.h> #include <linux/smp.h> +#include <linux/sys_info.h> #include <asm/interrupt.h> #include <asm/paca.h> @@ -235,7 +236,11 @@ static void watchdog_smp_panic(int cpu) pr_emerg("CPU %d TB:%lld, last SMP heartbeat TB:%lld (%lldms ago)\n", cpu, tb, last_reset, tb_to_ns(tb - last_reset) / 1000000); - if (!sysctl_hardlockup_all_cpu_backtrace) { + if (sysctl_hardlockup_all_cpu_backtrace || + (hardlockup_si_mask & SYS_INFO_ALL_BT)) { + trigger_allbutcpu_cpu_backtrace(cpu); + cpumask_clear(&wd_smp_cpus_ipi); + } else { /* * Try to trigger the stuck CPUs, unless we are going to * get a backtrace on all of them anyway. @@ -244,11 +249,9 @@ static void watchdog_smp_panic(int cpu) smp_send_nmi_ipi(c, wd_lockup_ipi, 1000000); __cpumask_clear_cpu(c, &wd_smp_cpus_ipi); } - } else { - trigger_allbutcpu_cpu_backtrace(cpu); - cpumask_clear(&wd_smp_cpus_ipi); } + sys_info(hardlockup_si_mask & ~SYS_INFO_ALL_BT); if (hardlockup_panic) nmi_panic(NULL, "Hard LOCKUP"); @@ -415,9 +418,11 @@ DEFINE_INTERRUPT_HANDLER_NMI(soft_nmi_interrupt) xchg(&__wd_nmi_output, 1); // see wd_lockup_ipi - if (sysctl_hardlockup_all_cpu_backtrace) + if (sysctl_hardlockup_all_cpu_backtrace || + (hardlockup_si_mask & SYS_INFO_ALL_BT)) trigger_allbutcpu_cpu_backtrace(cpu); + sys_info(hardlockup_si_mask & ~SYS_INFO_ALL_BT); if (hardlockup_panic) nmi_panic(regs, "Hard LOCKUP"); @@ -495,8 +500,7 @@ static void start_watchdog(void *arg) *this_cpu_ptr(&wd_timer_tb) = get_tb(); - hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); - hrtimer->function = watchdog_timer_fn; + hrtimer_setup(hrtimer, watchdog_timer_fn, CLOCK_MONOTONIC, HRTIMER_MODE_REL); hrtimer_start(hrtimer, ms_to_ktime(wd_timer_period_ms), HRTIMER_MODE_REL_PINNED); } |