diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2018-06-07 10:23:33 -0700 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2018-06-07 10:23:33 -0700 |
| commit | c90fca951e90ba470a3dc6087667edffcf8db21b (patch) | |
| tree | b131279a9290826e78884ee706cc0a4f1d82be4e /arch/powerpc/kernel | |
| parent | c0ab85267e25e34ce8b7e4429f0ef01fa0795b80 (diff) | |
| parent | ff5bc793e47b537bf3e904fada585e102c54dd8b (diff) | |
| download | linux-c90fca951e90ba470a3dc6087667edffcf8db21b.tar.bz2 | |
Merge tag 'powerpc-4.18-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux
Pull powerpc updates from Michael Ellerman:
"Notable changes:
- Support for split PMD page table lock on 64-bit Book3S (Power8/9).
- Add support for HAVE_RELIABLE_STACKTRACE, so we properly support
live patching again.
- Add support for patching barrier_nospec in copy_from_user() and
syscall entry.
- A couple of fixes for our data breakpoints on Book3S.
- A series from Nick optimising TLB/mm handling with the Radix MMU.
- Numerous small cleanups to squash sparse/gcc warnings from Mathieu
Malaterre.
- Several series optimising various parts of the 32-bit code from
Christophe Leroy.
- Removal of support for two old machines, "SBC834xE" and "C2K"
("GEFanuc,C2K"), which is why the diffstat has so many deletions.
And many other small improvements & fixes.
There's a few out-of-area changes. Some minor ftrace changes OK'ed by
Steve, and a fix to our powernv cpuidle driver. Then there's a series
touching mm, x86 and fs/proc/task_mmu.c, which cleans up some details
around pkey support. It was ack'ed/reviewed by Ingo & Dave and has
been in next for several weeks.
Thanks to: Akshay Adiga, Alastair D'Silva, Alexey Kardashevskiy, Al
Viro, Andrew Donnellan, Aneesh Kumar K.V, Anju T Sudhakar, Arnd
Bergmann, Balbir Singh, Cédric Le Goater, Christophe Leroy, Christophe
Lombard, Colin Ian King, Dave Hansen, Fabio Estevam, Finn Thain,
Frederic Barrat, Gautham R. Shenoy, Haren Myneni, Hari Bathini, Ingo
Molnar, Jonathan Neuschäfer, Josh Poimboeuf, Kamalesh Babulal,
Madhavan Srinivasan, Mahesh Salgaonkar, Mark Greer, Mathieu Malaterre,
Matthew Wilcox, Michael Neuling, Michal Suchanek, Naveen N. Rao,
Nicholas Piggin, Nicolai Stange, Olof Johansson, Paul Gortmaker, Paul
Mackerras, Peter Rosin, Pridhiviraj Paidipeddi, Ram Pai, Rashmica
Gupta, Ravi Bangoria, Russell Currey, Sam Bobroff, Samuel
Mendoza-Jonas, Segher Boessenkool, Shilpasri G Bhat, Simon Guo,
Souptick Joarder, Stewart Smith, Thiago Jung Bauermann, Torsten Duwe,
Vaibhav Jain, Wei Yongjun, Wolfram Sang, Yisheng Xie, YueHaibing"
* tag 'powerpc-4.18-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (251 commits)
powerpc/64s/radix: Fix missing ptesync in flush_cache_vmap
cpuidle: powernv: Fix promotion from snooze if next state disabled
powerpc: fix build failure by disabling attribute-alias warning in pci_32
ocxl: Fix missing unlock on error in afu_ioctl_enable_p9_wait()
powerpc-opal: fix spelling mistake "Uniterrupted" -> "Uninterrupted"
powerpc: fix spelling mistake: "Usupported" -> "Unsupported"
powerpc/pkeys: Detach execute_only key on !PROT_EXEC
powerpc/powernv: copy/paste - Mask SO bit in CR
powerpc: Remove core support for Marvell mv64x60 hostbridges
powerpc/boot: Remove core support for Marvell mv64x60 hostbridges
powerpc/boot: Remove support for Marvell mv64x60 i2c controller
powerpc/boot: Remove support for Marvell MPSC serial controller
powerpc/embedded6xx: Remove C2K board support
powerpc/lib: optimise PPC32 memcmp
powerpc/lib: optimise 32 bits __clear_user()
powerpc/time: inline arch_vtime_task_switch()
powerpc/Makefile: set -mcpu=860 flag for the 8xx
powerpc: Implement csum_ipv6_magic in assembly
powerpc/32: Optimise __csum_partial()
powerpc/lib: Adjust .balign inside string functions for PPC32
...
Diffstat (limited to 'arch/powerpc/kernel')
59 files changed, 1370 insertions, 893 deletions
diff --git a/arch/powerpc/kernel/align.c b/arch/powerpc/kernel/align.c index 3e6c0744c174..11550a3d1ac2 100644 --- a/arch/powerpc/kernel/align.c +++ b/arch/powerpc/kernel/align.c @@ -339,7 +339,7 @@ int fix_alignment(struct pt_regs *regs) if (r < 0) return -EINVAL; - type = op.type & INSTR_TYPE_MASK; + type = GETTYPE(op.type); if (!OP_IS_LOAD_STORE(type)) { if (op.type != CACHEOP + DCBZ) return -EINVAL; diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 8817c5a6bcc2..9fc9e0977009 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -180,6 +180,7 @@ int main(void) OFFSET(PACAKMSR, paca_struct, kernel_msr); OFFSET(PACAIRQSOFTMASK, paca_struct, irq_soft_mask); OFFSET(PACAIRQHAPPENED, paca_struct, irq_happened); + OFFSET(PACA_FTRACE_ENABLED, paca_struct, ftrace_enabled); #ifdef CONFIG_PPC_BOOK3S OFFSET(PACACONTEXTID, paca_struct, mm_ctx_id); #ifdef CONFIG_PPC_MM_SLICES diff --git a/arch/powerpc/kernel/btext.c b/arch/powerpc/kernel/btext.c index 6537cba1a758..b2072d5bbf2b 100644 --- a/arch/powerpc/kernel/btext.c +++ b/arch/powerpc/kernel/btext.c @@ -157,20 +157,20 @@ void btext_map(void) /* By default, we are no longer mapped */ boot_text_mapped = 0; - if (dispDeviceBase == 0) + if (!dispDeviceBase) return; base = ((unsigned long) dispDeviceBase) & 0xFFFFF000UL; offset = ((unsigned long) dispDeviceBase) - base; size = dispDeviceRowBytes * dispDeviceRect[3] + offset + dispDeviceRect[0]; vbase = __ioremap(base, size, pgprot_val(pgprot_noncached_wc(__pgprot(0)))); - if (vbase == 0) + if (!vbase) return; logicalDisplayBase = vbase + offset; boot_text_mapped = 1; } -int btext_initialize(struct device_node *np) +static int btext_initialize(struct device_node *np) { unsigned int width, height, depth, pitch; unsigned long address = 0; @@ -270,7 +270,7 @@ static unsigned char * calc_base(int x, int y) unsigned char *base; base = logicalDisplayBase; - if (base == 0) + if (!base) base = dispDeviceBase; base += (x + dispDeviceRect[0]) * (dispDeviceDepth >> 3); base += (y + dispDeviceRect[1]) * dispDeviceRowBytes; @@ -281,7 +281,7 @@ static unsigned char * calc_base(int x, int y) void btext_update_display(unsigned long phys, int width, int height, int depth, int pitch) { - if (dispDeviceBase == 0) + if (!dispDeviceBase) return; /* check it's the same frame buffer (within 256MB) */ diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c index 138157deeadf..155170d70324 100644 --- a/arch/powerpc/kernel/dma.c +++ b/arch/powerpc/kernel/dma.c @@ -235,8 +235,6 @@ static inline dma_addr_t dma_nommu_map_page(struct device *dev, enum dma_data_direction dir, unsigned long attrs) { - BUG_ON(dir == DMA_NONE); - if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) __dma_sync_page(page, offset, size, dir); diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c index c904477abaf3..4be1c0de9406 100644 --- a/arch/powerpc/kernel/dt_cpu_ftrs.c +++ b/arch/powerpc/kernel/dt_cpu_ftrs.c @@ -717,6 +717,7 @@ static __init void cpufeatures_cpu_quirks(void) if ((version & 0xffff0000) == 0x004e0000) { cur_cpu_spec->cpu_features &= ~(CPU_FTR_DAWR); cur_cpu_spec->cpu_features |= CPU_FTR_P9_TLBIE_BUG; + cur_cpu_spec->cpu_features |= CPU_FTR_P9_TIDR; } /* diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index 90bb39b1a23c..5746809cfaad 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -263,9 +263,8 @@ static size_t eeh_dump_dev_log(struct eeh_dev *edev, char *buf, size_t len) return n; } -static void *eeh_dump_pe_log(void *data, void *flag) +static void *eeh_dump_pe_log(struct eeh_pe *pe, void *flag) { - struct eeh_pe *pe = data; struct eeh_dev *edev, *tmp; size_t *plen = flag; @@ -542,8 +541,12 @@ int eeh_dev_check_failure(struct eeh_dev *edev) /* Frozen parent PE ? */ ret = eeh_ops->get_state(parent_pe, NULL); - if (ret > 0 && !eeh_state_active(ret)) + if (ret > 0 && !eeh_state_active(ret)) { pe = parent_pe; + pr_err("EEH: Failure of PHB#%x-PE#%x will be handled at parent PHB#%x-PE#%x.\n", + pe->phb->global_number, pe->addr, + pe->phb->global_number, parent_pe->addr); + } /* Next parent level */ parent_pe = parent_pe->parent; @@ -686,9 +689,9 @@ int eeh_pci_enable(struct eeh_pe *pe, int function) return rc; } -static void *eeh_disable_and_save_dev_state(void *data, void *userdata) +static void *eeh_disable_and_save_dev_state(struct eeh_dev *edev, + void *userdata) { - struct eeh_dev *edev = data; struct pci_dev *pdev = eeh_dev_to_pci_dev(edev); struct pci_dev *dev = userdata; @@ -714,9 +717,8 @@ static void *eeh_disable_and_save_dev_state(void *data, void *userdata) return NULL; } -static void *eeh_restore_dev_state(void *data, void *userdata) +static void *eeh_restore_dev_state(struct eeh_dev *edev, void *userdata) { - struct eeh_dev *edev = data; struct pci_dn *pdn = eeh_dev_to_pdn(edev); struct pci_dev *pdev = eeh_dev_to_pci_dev(edev); struct pci_dev *dev = userdata; @@ -856,11 +858,10 @@ int pcibios_set_pcie_reset_state(struct pci_dev *dev, enum pcie_reset_state stat * the indicated device and its children so that the bunch of the * devices could be reset properly. */ -static void *eeh_set_dev_freset(void *data, void *flag) +static void *eeh_set_dev_freset(struct eeh_dev *edev, void *flag) { struct pci_dev *dev; unsigned int *freset = (unsigned int *)flag; - struct eeh_dev *edev = (struct eeh_dev *)data; dev = eeh_dev_to_pci_dev(edev); if (dev) diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index b8a329f04814..67619b4b3f96 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -39,18 +39,82 @@ struct eeh_rmv_data { int removed; }; -/** - * eeh_pcid_name - Retrieve name of PCI device driver - * @pdev: PCI device - * - * This routine is used to retrieve the name of PCI device driver - * if that's valid. - */ -static inline const char *eeh_pcid_name(struct pci_dev *pdev) +static int eeh_result_priority(enum pci_ers_result result) +{ + switch (result) { + case PCI_ERS_RESULT_NONE: + return 1; + case PCI_ERS_RESULT_NO_AER_DRIVER: + return 2; + case PCI_ERS_RESULT_RECOVERED: + return 3; + case PCI_ERS_RESULT_CAN_RECOVER: + return 4; + case PCI_ERS_RESULT_DISCONNECT: + return 5; + case PCI_ERS_RESULT_NEED_RESET: + return 6; + default: + WARN_ONCE(1, "Unknown pci_ers_result value: %d\n", (int)result); + return 0; + } +}; + +const char *pci_ers_result_name(enum pci_ers_result result) +{ + switch (result) { + case PCI_ERS_RESULT_NONE: + return "none"; + case PCI_ERS_RESULT_CAN_RECOVER: + return "can recover"; + case PCI_ERS_RESULT_NEED_RESET: + return "need reset"; + case PCI_ERS_RESULT_DISCONNECT: + return "disconnect"; + case PCI_ERS_RESULT_RECOVERED: + return "recovered"; + case PCI_ERS_RESULT_NO_AER_DRIVER: + return "no AER driver"; + default: + WARN_ONCE(1, "Unknown result type: %d\n", (int)result); + return "unknown"; + } +}; + +static __printf(2, 3) void eeh_edev_info(const struct eeh_dev *edev, + const char *fmt, ...) +{ + struct va_format vaf; + va_list args; + + va_start(args, fmt); + + vaf.fmt = fmt; + vaf.va = &args; + + printk(KERN_INFO "EEH: PE#%x (PCI %s): %pV\n", edev->pe_config_addr, + edev->pdev ? dev_name(&edev->pdev->dev) : "none", &vaf); + + va_end(args); +} + +static enum pci_ers_result pci_ers_merge_result(enum pci_ers_result old, + enum pci_ers_result new) +{ + if (eeh_result_priority(new) > eeh_result_priority(old)) + return new; + return old; +} + +static bool eeh_dev_removed(struct eeh_dev *edev) { - if (pdev && pdev->dev.driver) - return pdev->dev.driver->name; - return ""; + return !edev || (edev->mode & EEH_DEV_REMOVED); +} + +static bool eeh_edev_actionable(struct eeh_dev *edev) +{ + return (edev->pdev && !eeh_dev_removed(edev) && + !eeh_pe_passed(edev->pe)); } /** @@ -98,22 +162,20 @@ static inline void eeh_pcid_put(struct pci_dev *pdev) * do real work because EEH should freeze DMA transfers for those PCI * devices encountering EEH errors, which includes MSI or MSI-X. */ -static void eeh_disable_irq(struct pci_dev *dev) +static void eeh_disable_irq(struct eeh_dev *edev) { - struct eeh_dev *edev = pci_dev_to_eeh_dev(dev); - /* Don't disable MSI and MSI-X interrupts. They are * effectively disabled by the DMA Stopped state * when an EEH error occurs. */ - if (dev->msi_enabled || dev->msix_enabled) + if (edev->pdev->msi_enabled || edev->pdev->msix_enabled) return; - if (!irq_has_action(dev->irq)) + if (!irq_has_action(edev->pdev->irq)) return; edev->mode |= EEH_DEV_IRQ_DISABLED; - disable_irq_nosync(dev->irq); + disable_irq_nosync(edev->pdev->irq); } /** @@ -123,10 +185,8 @@ static void eeh_disable_irq(struct pci_dev *dev) * This routine must be called to enable interrupt while failed * device could be resumed. */ -static void eeh_enable_irq(struct pci_dev *dev) +static void eeh_enable_irq(struct eeh_dev *edev) { - struct eeh_dev *edev = pci_dev_to_eeh_dev(dev); - if ((edev->mode) & EEH_DEV_IRQ_DISABLED) { edev->mode &= ~EEH_DEV_IRQ_DISABLED; /* @@ -149,23 +209,13 @@ static void eeh_enable_irq(struct pci_dev *dev) * * tglx */ - if (irqd_irq_disabled(irq_get_irq_data(dev->irq))) - enable_irq(dev->irq); + if (irqd_irq_disabled(irq_get_irq_data(edev->pdev->irq))) + enable_irq(edev->pdev->irq); } } -static bool eeh_dev_removed(struct eeh_dev *edev) -{ - /* EEH device removed ? */ - if (!edev || (edev->mode & EEH_DEV_REMOVED)) - return true; - - return false; -} - -static void *eeh_dev_save_state(void *data, void *userdata) +static void *eeh_dev_save_state(struct eeh_dev *edev, void *userdata) { - struct eeh_dev *edev = data; struct pci_dev *pdev; if (!edev) @@ -189,144 +239,155 @@ static void *eeh_dev_save_state(void *data, void *userdata) return NULL; } -/** - * eeh_report_error - Report pci error to each device driver - * @data: eeh device - * @userdata: return value - * - * Report an EEH error to each device driver, collect up and - * merge the device driver responses. Cumulative response - * passed back in "userdata". - */ -static void *eeh_report_error(void *data, void *userdata) +static void eeh_set_channel_state(struct eeh_pe *root, enum pci_channel_state s) { - struct eeh_dev *edev = (struct eeh_dev *)data; - struct pci_dev *dev = eeh_dev_to_pci_dev(edev); - enum pci_ers_result rc, *res = userdata; - struct pci_driver *driver; + struct eeh_pe *pe; + struct eeh_dev *edev, *tmp; - if (!dev || eeh_dev_removed(edev) || eeh_pe_passed(edev->pe)) - return NULL; + eeh_for_each_pe(root, pe) + eeh_pe_for_each_dev(pe, edev, tmp) + if (eeh_edev_actionable(edev)) + edev->pdev->error_state = s; +} - device_lock(&dev->dev); - dev->error_state = pci_channel_io_frozen; +static void eeh_set_irq_state(struct eeh_pe *root, bool enable) +{ + struct eeh_pe *pe; + struct eeh_dev *edev, *tmp; - driver = eeh_pcid_get(dev); - if (!driver) goto out_no_dev; + eeh_for_each_pe(root, pe) { + eeh_pe_for_each_dev(pe, edev, tmp) { + if (!eeh_edev_actionable(edev)) + continue; - eeh_disable_irq(dev); + if (!eeh_pcid_get(edev->pdev)) + continue; - if (!driver->err_handler || - !driver->err_handler->error_detected) - goto out; + if (enable) + eeh_enable_irq(edev); + else + eeh_disable_irq(edev); - rc = driver->err_handler->error_detected(dev, pci_channel_io_frozen); + eeh_pcid_put(edev->pdev); + } + } +} - /* A driver that needs a reset trumps all others */ - if (rc == PCI_ERS_RESULT_NEED_RESET) *res = rc; - if (*res == PCI_ERS_RESULT_NONE) *res = rc; +typedef enum pci_ers_result (*eeh_report_fn)(struct eeh_dev *, + struct pci_driver *); +static void eeh_pe_report_edev(struct eeh_dev *edev, eeh_report_fn fn, + enum pci_ers_result *result) +{ + struct pci_driver *driver; + enum pci_ers_result new_result; + + device_lock(&edev->pdev->dev); + if (eeh_edev_actionable(edev)) { + driver = eeh_pcid_get(edev->pdev); + + if (!driver) + eeh_edev_info(edev, "no driver"); + else if (!driver->err_handler) + eeh_edev_info(edev, "driver not EEH aware"); + else if (edev->mode & EEH_DEV_NO_HANDLER) + eeh_edev_info(edev, "driver bound too late"); + else { + new_result = fn(edev, driver); + eeh_edev_info(edev, "%s driver reports: '%s'", + driver->name, + pci_ers_result_name(new_result)); + if (result) + *result = pci_ers_merge_result(*result, + new_result); + } + if (driver) + eeh_pcid_put(edev->pdev); + } else { + eeh_edev_info(edev, "not actionable (%d,%d,%d)", !!edev->pdev, + !eeh_dev_removed(edev), !eeh_pe_passed(edev->pe)); + } + device_unlock(&edev->pdev->dev); +} - edev->in_error = true; - pci_uevent_ers(dev, PCI_ERS_RESULT_NONE); +static void eeh_pe_report(const char *name, struct eeh_pe *root, + eeh_report_fn fn, enum pci_ers_result *result) +{ + struct eeh_pe *pe; + struct eeh_dev *edev, *tmp; -out: - eeh_pcid_put(dev); -out_no_dev: - device_unlock(&dev->dev); - return NULL; + 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); + if (result) + pr_info("EEH: Finished:'%s' with aggregate recovery state:'%s'\n", + name, pci_ers_result_name(*result)); + else + pr_info("EEH: Finished:'%s'", name); } /** - * eeh_report_mmio_enabled - Tell drivers that MMIO has been enabled - * @data: eeh device - * @userdata: return value + * eeh_report_error - Report pci error to each device driver + * @edev: eeh device + * @driver: device's PCI driver * - * Tells each device driver that IO ports, MMIO and config space I/O - * are now enabled. Collects up and merges the device driver responses. - * Cumulative response passed back in "userdata". + * Report an EEH error to each device driver. */ -static void *eeh_report_mmio_enabled(void *data, void *userdata) +static enum pci_ers_result eeh_report_error(struct eeh_dev *edev, + struct pci_driver *driver) { - struct eeh_dev *edev = (struct eeh_dev *)data; - struct pci_dev *dev = eeh_dev_to_pci_dev(edev); - enum pci_ers_result rc, *res = userdata; - struct pci_driver *driver; - - if (!dev || eeh_dev_removed(edev) || eeh_pe_passed(edev->pe)) - return NULL; - - device_lock(&dev->dev); - driver = eeh_pcid_get(dev); - if (!driver) goto out_no_dev; + enum pci_ers_result rc; + struct pci_dev *dev = edev->pdev; - if (!driver->err_handler || - !driver->err_handler->mmio_enabled || - (edev->mode & EEH_DEV_NO_HANDLER)) - goto out; + if (!driver->err_handler->error_detected) + return PCI_ERS_RESULT_NONE; - rc = driver->err_handler->mmio_enabled(dev); + eeh_edev_info(edev, "Invoking %s->error_detected(IO frozen)", + driver->name); + rc = driver->err_handler->error_detected(dev, pci_channel_io_frozen); - /* A driver that needs a reset trumps all others */ - if (rc == PCI_ERS_RESULT_NEED_RESET) *res = rc; - if (*res == PCI_ERS_RESULT_NONE) *res = rc; + edev->in_error = true; + pci_uevent_ers(dev, PCI_ERS_RESULT_NONE); + return rc; +} -out: - eeh_pcid_put(dev); -out_no_dev: - device_unlock(&dev->dev); - return NULL; +/** + * eeh_report_mmio_enabled - Tell drivers that MMIO has been enabled + * @edev: eeh device + * @driver: device's PCI driver + * + * Tells each device driver that IO ports, MMIO and config space I/O + * are now enabled. + */ +static enum pci_ers_result eeh_report_mmio_enabled(struct eeh_dev *edev, + struct pci_driver *driver) +{ + if (!driver->err_handler->mmio_enabled) + return PCI_ERS_RESULT_NONE; + eeh_edev_info(edev, "Invoking %s->mmio_enabled()", driver->name); + return driver->err_handler->mmio_enabled(edev->pdev); } /** * eeh_report_reset - Tell device that slot has been reset - * @data: eeh device - * @userdata: return value + * @edev: eeh device + * @driver: device's PCI driver * * This routine must be called while EEH tries to reset particular * PCI device so that the associated PCI device driver could take * some actions, usually to save data the driver needs so that the * driver can work again while the device is recovered. */ -static void *eeh_report_reset(void *data, void *userdata) +static enum pci_ers_result eeh_report_reset(struct eeh_dev *edev, + struct pci_driver *driver) { - struct eeh_dev *edev = (struct eeh_dev *)data; - struct pci_dev *dev = eeh_dev_to_pci_dev(edev); - enum pci_ers_result rc, *res = userdata; - struct pci_driver *driver; - - if (!dev || eeh_dev_removed(edev) || eeh_pe_passed(edev->pe)) - return NULL; - - device_lock(&dev->dev); - dev->error_state = pci_channel_io_normal; - - driver = eeh_pcid_get(dev); - if (!driver) goto out_no_dev; - - eeh_enable_irq(dev); - - if (!driver->err_handler || - !driver->err_handler->slot_reset || - (edev->mode & EEH_DEV_NO_HANDLER) || - (!edev->in_error)) - goto out; - - rc = driver->err_handler->slot_reset(dev); - if ((*res == PCI_ERS_RESULT_NONE) || - (*res == PCI_ERS_RESULT_RECOVERED)) *res = rc; - if (*res == PCI_ERS_RESULT_DISCONNECT && - rc == PCI_ERS_RESULT_NEED_RESET) *res = rc; - -out: - eeh_pcid_put(dev); -out_no_dev: - device_unlock(&dev->dev); - return NULL; + if (!driver->err_handler->slot_reset || !edev->in_error) + return PCI_ERS_RESULT_NONE; + eeh_edev_info(edev, "Invoking %s->slot_reset()", driver->name); + return driver->err_handler->slot_reset(edev->pdev); } -static void *eeh_dev_restore_state(void *data, void *userdata) +static void *eeh_dev_restore_state(struct eeh_dev *edev, void *userdata) { - struct eeh_dev *edev = data; struct pci_dev *pdev; if (!edev) @@ -355,91 +416,53 @@ static void *eeh_dev_restore_state(void *data, void *userdata) /** * eeh_report_resume - Tell device to resume normal operations - * @data: eeh device - * @userdata: return value + * @edev: eeh device + * @driver: device's PCI driver * * This routine must be called to notify the device driver that it * could resume so that the device driver can do some initialization * to make the recovered device work again. */ -static void *eeh_report_resume(void *data, void *userdata) +static enum pci_ers_result eeh_report_resume(struct eeh_dev *edev, + struct pci_driver *driver) { - struct eeh_dev *edev = (struct eeh_dev *)data; - struct pci_dev *dev = eeh_dev_to_pci_dev(edev); - bool was_in_error; - struct pci_driver *driver; + if (!driver->err_handler->resume || !edev->in_error) + return PCI_ERS_RESULT_NONE; - if (!dev || eeh_dev_removed(edev) || eeh_pe_passed(edev->pe)) - return NULL; - - device_lock(&dev->dev); - dev->error_state = pci_channel_io_normal; - - driver = eeh_pcid_get(dev); - if (!driver) goto out_no_dev; - - was_in_error = edev->in_error; - edev->in_error = false; - eeh_enable_irq(dev); - - if (!driver->err_handler || - !driver->err_handler->resume || - (edev->mode & EEH_DEV_NO_HANDLER) || !was_in_error) { - edev->mode &= ~EEH_DEV_NO_HANDLER; - goto out; - } - - driver->err_handler->resume(dev); + eeh_edev_info(edev, "Invoking %s->resume()", driver->name); + driver->err_handler->resume(edev->pdev); - pci_uevent_ers(dev, PCI_ERS_RESULT_RECOVERED); -out: - eeh_pcid_put(dev); + pci_uevent_ers(edev->pdev, PCI_ERS_RESULT_RECOVERED); #ifdef CONFIG_PCI_IOV if (eeh_ops->notify_resume && eeh_dev_to_pdn(edev)) eeh_ops->notify_resume(eeh_dev_to_pdn(edev)); #endif -out_no_dev: - device_unlock(&dev->dev); - return NULL; + return PCI_ERS_RESULT_NONE; } /** * eeh_report_failure - Tell device driver that device is dead. - * @data: eeh device - * @userdata: return value + * @edev: eeh device + * @driver: device's PCI driver * * This informs the device driver that the device is permanently * dead, and that no further recovery attempts will be made on it. */ -static void *eeh_report_failure(void *data, void *userdata) +static enum pci_ers_result eeh_report_failure(struct eeh_dev *edev, + struct pci_driver *driver) { - struct eeh_dev *edev = (struct eeh_dev *)data; - struct pci_dev *dev = eeh_dev_to_pci_dev(edev); - struct pci_driver *driver; + enum pci_ers_result rc; - if (!dev || eeh_dev_removed(edev) || eeh_pe_passed(edev->pe)) - return NULL; - - device_lock(&dev->dev); - dev->error_state = pci_channel_io_perm_failure; - - driver = eeh_pcid_get(dev); - if (!driver) goto out_no_dev; + if (!driver->err_handler->error_detected) + return PCI_ERS_RESULT_NONE; - eeh_disable_irq(dev); + eeh_edev_info(edev, "Invoking %s->error_detected(permanent failure)", + driver->name); + rc = driver->err_handler->error_detected(edev->pdev, + pci_channel_io_perm_failure); - if (!driver->err_handler || - !driver->err_handler->error_detected) - goto out; - - driver->err_handler->error_detected(dev, pci_channel_io_perm_failure); - - pci_uevent_ers(dev, PCI_ERS_RESULT_DISCONNECT); -out: - eeh_pcid_put(dev); -out_no_dev: - device_unlock(&dev->dev); - return NULL; + pci_uevent_ers(edev->pdev, PCI_ERS_RESULT_DISCONNECT); + return rc; } static void *eeh_add_virt_device(void *data, void *userdata) @@ -458,9 +481,11 @@ static void *eeh_add_virt_device(void *data, void *userdata) driver = eeh_pcid_get(dev); if (driver) { - eeh_pcid_put(dev); - if (driver->err_handler) + if (driver->err_handler) { + eeh_pcid_put(dev); return NULL; + } + eeh_pcid_put(dev); } #ifdef CONFIG_PCI_IOV @@ -469,10 +494,9 @@ static void *eeh_add_virt_device(void *data, void *userdata) return NULL; } -static void *eeh_rmv_device(void *data, void *userdata) +static void *eeh_rmv_device(struct eeh_dev *edev, void *userdata) { struct pci_driver *driver; - struct eeh_dev *edev = (struct eeh_dev *)data; struct pci_dev *dev = eeh_dev_to_pci_dev(edev); struct eeh_rmv_data *rmv_data = (struct eeh_rmv_data *)userdata; int *removed = rmv_data ? &rmv_data->removed : NULL; @@ -497,17 +521,19 @@ static void *eeh_rmv_device(void *data, void *userdata) if (eeh_dev_removed(edev)) return NULL; - driver = eeh_pcid_get(dev); - if (driver) { - eeh_pcid_put(dev); - if (removed && - eeh_pe_passed(edev->pe)) - return NULL; - if (removed && - driver->err_handler && - driver->err_handler->error_detected && - driver->err_handler->slot_reset) + if (removed) { + if (eeh_pe_passed(edev->pe)) return NULL; + driver = eeh_pcid_get(dev); + if (driver) { + if (driver->err_handler && + driver->err_handler->error_detected && + driver->err_handler->slot_reset) { + eeh_pcid_put(dev); + return NULL; + } + eeh_pcid_put(dev); + } } /* Remove it from PCI subsystem */ @@ -542,9 +568,8 @@ static void *eeh_rmv_device(void *data, void *userdata) return NULL; } -static void *eeh_pe_detach_dev(void *data, void *userdata) +static void *eeh_pe_detach_dev(struct eeh_pe *pe, void *userdata) { - struct eeh_pe *pe = (struct eeh_pe *)data; struct eeh_dev *edev, *tmp; eeh_pe_for_each_dev(pe, edev, tmp) { @@ -565,9 +590,8 @@ static void *eeh_pe_detach_dev(void *data, void *userdata) * PE reset (for 3 times), we try to clear the frozen state * for 3 times as well. */ -static void *__eeh_clear_pe_frozen_state(void *data, void *flag) +static void *__eeh_clear_pe_frozen_state(struct eeh_pe *pe, void *flag) { - struct eeh_pe *pe = (struct eeh_pe *)data; bool clear_sw_state = *(bool *)flag; int i, rc = 1; @@ -762,6 +786,7 @@ void eeh_handle_normal_event(struct eeh_pe *pe) { struct pci_bus *bus; struct eeh_dev *edev, *tmp; + struct eeh_pe *tmp_pe; int rc = 0; enum pci_ers_result result = PCI_ERS_RESULT_NONE; struct eeh_rmv_data rmv_data = {LIST_HEAD_INIT(rmv_data.edev_list), 0}; @@ -778,14 +803,13 @@ void eeh_handle_normal_event(struct eeh_pe *pe) eeh_pe_update_time_stamp(pe); pe->freeze_count++; if (pe->freeze_count > eeh_max_freezes) { - pr_err("EEH: PHB#%x-PE#%x has failed %d times in the\n" - "last hour and has been permanently disabled.\n", + pr_err("EEH: PHB#%x-PE#%x has failed %d times in the last hour and has been permanently disabled.\n", pe->phb->global_number, pe->addr, pe->freeze_count); goto hard_fail; } - pr_warn("EEH: This PCI device has failed %d times in the last hour\n", - pe->freeze_count); + pr_warn("EEH: This PCI device has failed %d times in the last hour and will be permanently disabled after %d failures.\n", + pe->freeze_count, eeh_max_freezes); /* Walk the various device drivers attached to this slot through * a reset sequence, giving each an opportunity to do what it needs @@ -798,7 +822,10 @@ void eeh_handle_normal_event(struct eeh_pe *pe) * hotplug for this case. */ pr_info("EEH: Notify device drivers to shutdown\n"); - eeh_pe_dev_traverse(pe, eeh_report_error, &result); + eeh_set_channel_state(pe, pci_channel_io_frozen); + eeh_set_irq_state(pe, false); + eeh_pe_report("error_detected(IO frozen)", pe, eeh_report_error, + &result); if ((pe->type & EEH_PE_PHB) && result != PCI_ERS_RESULT_NONE && result != PCI_ERS_RESULT_NEED_RESET) @@ -845,7 +872,8 @@ void eeh_handle_normal_event(struct eeh_pe *pe) result = PCI_ERS_RESULT_NEED_RESET; } else { pr_info("EEH: Notify device drivers to resume I/O\n"); - eeh_pe_dev_traverse(pe, eeh_report_mmio_enabled, &result); + eeh_pe_report("mmio_enabled", pe, + eeh_report_mmio_enabled, &result); } } @@ -888,7 +916,9 @@ void eeh_handle_normal_event(struct eeh_pe *pe) pr_info("EEH: Notify device drivers " "the completion of reset\n"); result = PCI_ERS_RESULT_NONE; - eeh_pe_dev_traverse(pe, eeh_report_reset, &result); + eeh_set_channel_state(pe, pci_channel_io_normal); + eeh_set_irq_state(pe, true); + eeh_pe_report("slot_reset", pe, eeh_report_reset, &result); } /* All devices should claim they have recovered by now. */ @@ -909,8 +939,17 @@ void eeh_handle_normal_event(struct eeh_pe *pe) /* Tell all device drivers that they can resume operations */ pr_info("EEH: Notify device driver to resume\n"); - eeh_pe_dev_traverse(pe, eeh_report_resume, NULL); + eeh_set_channel_state(pe, pci_channel_io_normal); + eeh_set_irq_state(pe, true); + eeh_pe_report("resume", pe, eeh_report_resume, NULL); + eeh_for_each_pe(pe, tmp_pe) { + eeh_pe_for_each_dev(tmp_pe, edev, tmp) { + edev->mode &= ~EEH_DEV_NO_HANDLER; + edev->in_error = false; + } + } + pr_info("EEH: Recovery successful.\n"); goto final; hard_fail: @@ -926,7 +965,10 @@ hard_fail: eeh_slot_error_detail(pe, EEH_LOG_PERM); /* Notify all devices that they're about to go down. */ - eeh_pe_dev_traverse(pe, eeh_report_failure, NULL); + eeh_set_channel_state(pe, pci_channel_io_perm_failure); + eeh_set_irq_state(pe, false); + eeh_pe_report("error_detected(permanent failure)", pe, + eeh_report_failure, NULL); /* Mark the PE to be removed permanently */ eeh_pe_state_mark(pe, EEH_PE_REMOVED); @@ -1035,7 +1077,9 @@ void eeh_handle_special_event(void) /* Notify all devices to be down */ eeh_pe_state_clear(pe, EEH_PE_PRI_BUS); - eeh_pe_dev_traverse(pe, + eeh_set_channel_state(pe, pci_channel_io_perm_failure); + eeh_pe_report( + "error_detected(permanent failure)", pe, eeh_report_failure, NULL); bus = eeh_pe_bus_get(phb_pe); if (!bus) { diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c index ee5a67d57aab..1b238ecc553e 100644 --- a/arch/powerpc/kernel/eeh_pe.c +++ b/arch/powerpc/kernel/eeh_pe.c @@ -142,8 +142,7 @@ struct eeh_pe *eeh_phb_pe_get(struct pci_controller *phb) * The function is used to retrieve the next PE in the * hierarchy PE tree. */ -static struct eeh_pe *eeh_pe_next(struct eeh_pe *pe, - struct eeh_pe *root) +struct eeh_pe *eeh_pe_next(struct eeh_pe *pe, struct eeh_pe *root) { struct list_head *next = pe->child_list.next; @@ -173,12 +172,12 @@ static struct eeh_pe *eeh_pe_next(struct eeh_pe *pe, * to be traversed. */ void *eeh_pe_traverse(struct eeh_pe *root, - eeh_traverse_func fn, void *flag) + eeh_pe_traverse_func fn, void *flag) { struct eeh_pe *pe; void *ret; - for (pe = root; pe; pe = eeh_pe_next(pe, root)) { + eeh_for_each_pe(root, pe) { ret = fn(pe, flag); if (ret) return ret; } @@ -196,7 +195,7 @@ void *eeh_pe_traverse(struct eeh_pe *root, * PE and its child PEs. */ void *eeh_pe_dev_traverse(struct eeh_pe *root, - eeh_traverse_func fn, void *flag) + eeh_edev_traverse_func fn, void *flag) { struct eeh_pe *pe; struct eeh_dev *edev, *tmp; @@ -209,7 +208,7 @@ void *eeh_pe_dev_traverse(struct eeh_pe *root, } /* Traverse root PE */ - for (pe = root; pe; pe = eeh_pe_next(pe, root)) { + eeh_for_each_pe(root, pe) { eeh_pe_for_each_dev(pe, edev, tmp) { ret = fn(edev, flag); if (ret) @@ -235,9 +234,8 @@ struct eeh_pe_get_flag { int config_addr; }; -static void *__eeh_pe_get(void *data, void *flag) +static void *__eeh_pe_get(struct eeh_pe *pe, void *flag) { - struct eeh_pe *pe = (struct eeh_pe *)data; struct eeh_pe_get_flag *tmp = (struct eeh_pe_get_flag *) flag; /* Unexpected PHB PE */ @@ -551,9 +549,8 @@ void eeh_pe_update_time_stamp(struct eeh_pe *pe) * PE. Also, the associated PCI devices will be put into IO frozen * state as well. */ -static void *__eeh_pe_state_mark(void *data, void *flag) +static void *__eeh_pe_state_mark(struct eeh_pe *pe, void *flag) { - struct eeh_pe *pe = (struct eeh_pe *)data; int state = *((int *)flag); struct eeh_dev *edev, *tmp; struct pci_dev *pdev; @@ -595,9 +592,8 @@ void eeh_pe_state_mark(struct eeh_pe *pe, int state) } EXPORT_SYMBOL_GPL(eeh_pe_state_mark); -static void *__eeh_pe_dev_mode_mark(void *data, void *flag) +static void *__eeh_pe_dev_mode_mark(struct eeh_dev *edev, void *flag) { - struct eeh_dev *edev = data; int mode = *((int *)flag); edev->mode |= mode; @@ -625,9 +621,8 @@ void eeh_pe_dev_mode_mark(struct eeh_pe *pe, int mode) * given PE. Besides, we also clear the check count of the PE * as well. */ -static void *__eeh_pe_state_clear(void *data, void *flag) +static void *__eeh_pe_state_clear(struct eeh_pe *pe, void *flag) { - struct eeh_pe *pe = (struct eeh_pe *)data; int state = *((int *)flag); struct eeh_dev *edev, *tmp; struct pci_dev *pdev; @@ -858,9 +853,8 @@ static void eeh_restore_device_bars(struct eeh_dev *edev) * the expansion ROM base address, the latency timer, and etc. * from the saved values in the device node. */ -static void *eeh_restore_one_device_bars(void *data, void *flag) +static void *eeh_restore_one_device_bars(struct eeh_dev *edev, void *flag) { - struct eeh_dev *edev = (struct eeh_dev *)data; struct pci_dn *pdn = eeh_dev_to_pdn(edev); /* Do special restore for bridges */ diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index 51695608c68b..b10e01021214 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -36,6 +36,7 @@ #include <asm/context_tracking.h> #include <asm/tm.h> #include <asm/ppc-opcode.h> +#include <asm/barrier.h> #include <asm/export.h> #ifdef CONFIG_PPC_BOOK3S #include <asm/exception-64s.h> @@ -178,6 +179,15 @@ system_call: /* label this so stack traces look sane */ clrldi r8,r8,32 15: slwi r0,r0,4 + + barrier_nospec_asm + /* + * Prevent the load of the handler below (based on the user-passed + * system call number) being speculatively executed until the test + * against NR_syscalls and branch to .Lsyscall_enosys above has + * committed. + */ + ldx r12,r11,r0 /* Fetch system call handler [ptr] */ mtctr r12 bctrl /* Call handler */ @@ -596,6 +606,7 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT) * actually hit this code path. */ + isync slbie r6 slbie r6 /* Workaround POWER5 < DD2.1 issue */ slbmte r7,r0 diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index f283958129f2..285c6465324a 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -1501,6 +1501,7 @@ masked_##_H##interrupt: \ xori r10,r10,MSR_EE; /* clear MSR_EE */ \ mtspr SPRN_##_H##SRR1,r10; \ 2: mtcrf 0x80,r9; \ + std r1,PACAR1(r13); \ ld r9,PACA_EXGEN+EX_R9(r13); \ ld r10,PACA_EXGEN+EX_R10(r13); \ ld r11,PACA_EXGEN+EX_R11(r13); \ diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c index 3c2c2688918f..07e8396d472b 100644 --- a/arch/powerpc/kernel/fadump.c +++ b/arch/powerpc/kernel/fadump.c @@ -335,6 +335,26 @@ static unsigned long get_fadump_area_size(void) return size; } +static void __init fadump_reserve_crash_area(unsigned long base, + unsigned long size) +{ + struct memblock_region *reg; + unsigned long mstart, mend, msize; + + for_each_memblock(memory, reg) { + mstart = max_t(unsigned long, base, reg->base); + mend = reg->base + reg->size; + mend = min(base + size, mend); + + if (mstart < mend) { + msize = mend - mstart; + memblock_reserve(mstart, msize); + pr_info("Reserved %ldMB of memory at %#016lx for saving crash dump\n", + (msize >> 20), mstart); + } + } +} + int __init fadump_reserve_mem(void) { unsigned long base, size, memory_boundary; @@ -380,7 +400,16 @@ int __init fadump_reserve_mem(void) memory_boundary = memblock_end_of_DRAM(); if (fw_dump.dump_active) { - printk(KERN_INFO "Firmware-assisted dump is active.\n"); + pr_info("Firmware-assisted dump is active.\n"); + +#ifdef CONFIG_HUGETLB_PAGE + /* + * FADump capture kernel doesn't care much about hugepages. + * In fact, handling hugepages in capture kernel is asking for + * trouble. So, disable HugeTLB support when fadump is active. + */ + hugetlb_disabled = true; +#endif /* * If last boot has crashed then reserve all the memory * above boot_memory_size so that we don't touch it until @@ -389,11 +418,7 @@ int __init fadump_reserve_mem(void) */ base = fw_dump.boot_memory_size; size = memory_boundary - base; - memblock_reserve(base, size); - printk(KERN_INFO "Reserved %ldMB of memory at %ldMB " - "for saving crash dump\n", - (unsigned long)(size >> 20), - (unsigned long)(base >> 20)); + fadump_reserve_crash_area(base, size); fw_dump.fadumphdr_addr = be64_to_cpu(fdm_active->rmr_region.destination_address) + @@ -1155,6 +1180,9 @@ void fadump_cleanup(void) init_fadump_mem_struct(&fdm, be64_to_cpu(fdm_active->cpu_state_data.destination_address)); fadump_invalidate_dump(&fdm); + } else if (fw_dump.dump_registered) { + /* Un-register Firmware-assisted dump if it was registered. */ + fadump_unregister_dump(&fdm); } } diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S index d8670a37d70c..6cab07e76732 100644 --- a/arch/powerpc/kernel/head_8xx.S +++ b/arch/powerpc/kernel/head_8xx.S @@ -913,7 +913,7 @@ start_here: tovirt(r6,r6) lis r5, abatron_pteptrs@h ori r5, r5, abatron_pteptrs@l - stw r5, 0xf0(r0) /* Must match your Abatron config file */ + stw r5, 0xf0(0) /* Must match your Abatron config file */ tophys(r5,r5) stw r6, 0(r5) diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c index 4c1012b80d3b..80547dad37da 100644 --- a/arch/powerpc/kernel/hw_breakpoint.c +++ b/arch/powerpc/kernel/hw_breakpoint.c @@ -178,8 +178,8 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp) if (cpu_has_feature(CPU_FTR_DAWR)) { length_max = 512 ; /* 64 doublewords */ /* DAWR region can't cross 512 boundary */ - if ((bp->attr.bp_addr >> 10) != - ((bp->attr.bp_addr + bp->attr.bp_len - 1) >> 10)) + if ((bp->attr.bp_addr >> 9) != + ((bp->attr.bp_addr + bp->attr.bp_len - 1) >> 9)) return -EINVAL; } if (info->len > diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index 061aa0f47bb1..0682fef1f385 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -89,7 +89,7 @@ atomic_t ppc_n_lost_interrupts; #ifdef CONFIG_TAU_INT extern int tau_initialized; -extern int tau_interrupts(int); +u32 tau_interrupts(unsigned long cpu); #endif #endif /* CONFIG_PPC32 */ @@ -508,6 +508,11 @@ int arch_show_interrupts(struct seq_file *p, int prec) seq_printf(p, "%10u ", per_cpu(irq_stat, j).timer_irqs_event); seq_printf(p, " Local timer interrupts for timer event device\n"); + seq_printf(p, "%*s: ", prec, "BCT"); + for_each_online_cpu(j) + seq_printf(p, "%10u ", per_cpu(irq_stat, j).broadcast_irqs_event); + seq_printf(p, " Broadcast timer interrupts for timer event device\n"); + seq_printf(p, "%*s: ", prec, "LOC"); for_each_online_cpu(j) seq_printf(p, "%10u ", per_cpu(irq_stat, j).timer_irqs_others); @@ -567,6 +572,7 @@ u64 arch_irq_stat_cpu(unsigned int cpu) { u64 sum = per_cpu(irq_stat, cpu).timer_irqs_event; + sum += per_cpu(irq_stat, cpu).broadcast_irqs_event; sum += per_cpu(irq_stat, cpu).pmu_irqs; sum += per_cpu(irq_stat, cpu).mce_exceptions; sum += per_cpu(irq_stat, cpu).spurious_irqs; diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c index 9ad37f827a97..683b5b3805bd 100644 --- a/arch/powerpc/kernel/kvm.c +++ b/arch/powerpc/kernel/kvm.c @@ -25,6 +25,7 @@ #include <linux/kvm_para.h> #include <linux/slab.h> #include <linux/of.h> +#include <linux/pagemap.h> #include <asm/reg.h> #include <asm/sections.h> @@ -672,14 +673,13 @@ static void kvm_use_magic_page(void) { u32 *p; u32 *start, *end; - u32 tmp; u32 features; /* Tell the host to map the magic page to -4096 on all CPUs */ on_each_cpu(kvm_map_magic_page, &features, 1); /* Quick self-test to see if the mapping works */ - if (__get_user(tmp, (u32*)KVM_MAGIC_PAGE)) { + if (!fault_in_pages_readable((const char *)KVM_MAGIC_PAGE, sizeof(u32))) { kvm_patching_worked = false; return; } diff --git a/arch/powerpc/kernel/machine_kexec.c b/arch/powerpc/kernel/machine_kexec.c index 2694d078741d..936c7e2d421e 100644 --- a/arch/powerpc/kernel/machine_kexec.c +++ b/arch/powerpc/kernel/machine_kexec.c @@ -98,12 +98,14 @@ void machine_kexec(struct kimage *image) int save_ftrace_enabled; save_ftrace_enabled = __ftrace_enabled_save(); + this_cpu_disable_ftrace(); if (ppc_md.machine_kexec) ppc_md.machine_kexec(image); else default_machine_kexec(image); + this_cpu_enable_ftrace(); __ftrace_enabled_restore(save_ftrace_enabled); /* Fall back to normal restart if we're still alive. */ diff --git a/arch/powerpc/kernel/machine_kexec_64.c b/arch/powerpc/kernel/machine_kexec_64.c index 1044bf15d5ed..a0f6f45005bd 100644 --- a/arch/powerpc/kernel/machine_kexec_64.c +++ b/arch/powerpc/kernel/machine_kexec_64.c @@ -231,16 +231,16 @@ static void kexec_prepare_cpus(void) /* we are sure every CPU has IRQs off at this point */ kexec_all_irq_disabled = 1; - /* after we tell the others to go down */ - if (ppc_md.kexec_cpu_down) - ppc_md.kexec_cpu_down(0, 0); - /* * Before removing MMU mappings make sure all CPUs have entered real * mode: */ kexec_prepare_cpus_wait(KEXEC_STATE_REAL_MODE); + /* after we tell the others to go down */ + if (ppc_md.kexec_cpu_down) + ppc_md.kexec_cpu_down(0, 0); + put_cpu(); } diff --git a/arch/powerpc/kernel/misc.S b/arch/powerpc/kernel/misc.S index 384357cb8bc0..0b196cdcd15d 100644 --- a/arch/powerpc/kernel/misc.S +++ b/arch/powerpc/kernel/misc.S @@ -25,23 +25,12 @@ /* * Returns (address we are running at) - (address we were linked at) * for use before the text and data are mapped to KERNELBASE. - */ - -_GLOBAL(reloc_offset) - mflr r0 - bl 1f -1: mflr r3 - PPC_LL r4,(2f-1b)(r3) - subf r3,r4,r3 - mtlr r0 - blr - .align 3 -2: PPC_LONG 1b - -/* * add_reloc_offset(x) returns x + reloc_offset(). */ + +_GLOBAL(reloc_offset) + li r3, 0 _GLOBAL(add_reloc_offset) mflr r0 bl 1f @@ -60,6 +49,10 @@ _GLOBAL(setjmp) PPC_STL r0,0(r3) PPC_STL r1,SZL(r3) PPC_STL r2,2*SZL(r3) +#ifdef CONFIG_PPC32 + mfcr r12 + stmw r12, 3*SZL(r3) +#else mfcr r0 PPC_STL r0,3*SZL(r3) PPC_STL r13,4*SZL(r3) @@ -81,14 +74,16 @@ _GLOBAL(setjmp) PPC_STL r29,20*SZL(r3) PPC_STL r30,21*SZL(r3) PPC_STL r31,22*SZL(r3) +#endif li r3,0 blr _GLOBAL(longjmp) - PPC_LCMPI r4,0 - bne 1f - li r4,1 -1: PPC_LL r13,4*SZL(r3) +#ifdef CONFIG_PPC32 + lmw r12, 3*SZL(r3) + mtcrf 0x38, r12 +#else + PPC_LL r13,4*SZL(r3) PPC_LL r14,5*SZL(r3) PPC_LL r15,6*SZL(r3) PPC_LL r16,7*SZL(r3) @@ -109,11 +104,14 @@ _GLOBAL(longjmp) PPC_LL r31,22*SZL(r3) PPC_LL r0,3*SZL(r3) mtcrf 0x38,r0 +#endif PPC_LL r0,0(r3) PPC_LL r1,SZL(r3) PPC_LL r2,2*SZL(r3) mtlr r0 - mr r3,r4 + mr. r3, r4 + bnelr + li r3, 1 blr _GLOBAL(current_stack_pointer) diff --git a/arch/powerpc/kernel/module.c b/arch/powerpc/kernel/module.c index 3f7ba0f5bf29..1b3c6835e730 100644 --- a/arch/powerpc/kernel/module.c +++ b/arch/powerpc/kernel/module.c @@ -72,6 +72,12 @@ int module_finalize(const Elf_Ehdr *hdr, do_feature_fixups(powerpc_firmware_features, (void *)sect->sh_addr, (void *)sect->sh_addr + sect->sh_size); + + sect = find_section(hdr, sechdrs, "__spec_barrier_fixup"); + if (sect != NULL) + do_barrier_nospec_fixups_range(barrier_nospec_enabled, + (void *)sect->sh_addr, + (void *)sect->sh_addr + sect->sh_size); #endif sect = find_section(hdr, sechdrs, "__lwsync_fixup"); diff --git a/arch/powerpc/kernel/module_32.c b/arch/powerpc/kernel/module_32.c index 5a7a78f12562..88d83771f462 100644 --- a/arch/powerpc/kernel/module_32.c +++ b/arch/powerpc/kernel/module_32.c @@ -109,12 +109,12 @@ static unsigned long get_plt_size(const Elf32_Ehdr *hdr, for (i = 1; i < hdr->e_shnum; i++) { /* If it's called *.init*, and we're not init, we're not interested */ - if ((strstr(secstrings + sechdrs[i].sh_name, ".init") != 0) + if ((strstr(secstrings + sechdrs[i].sh_name, ".init") != NULL) != is_init) continue; /* We don't want to look at debug sections. */ - if (strstr(secstrings + sechdrs[i].sh_name, ".debug") != 0) + if (strstr(secstrings + sechdrs[i].sh_name, ".debug")) continue; if (sechdrs[i].sh_type == SHT_RELA) { diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c index a2636c250b7b..1b7419579820 100644 --- a/arch/powerpc/kernel/module_64.c +++ b/arch/powerpc/kernel/module_64.c @@ -280,6 +280,10 @@ static unsigned long get_stubs_size(const Elf64_Ehdr *hdr, #ifdef CONFIG_DYNAMIC_FTRACE /* make the trampoline to the ftrace_caller */ relocs++; +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS + /* an additional one for ftrace_regs_caller */ + relocs++; +#endif #endif pr_debug("Looks like a total of %lu stubs, max\n", relocs); @@ -463,8 +467,11 @@ static unsigned long stub_for_addr(const Elf64_Shdr *sechdrs, } #ifdef CC_USING_MPROFILE_KERNEL -static bool is_early_mcount_callsite(u32 *instruction) +static bool is_mprofile_mcount_callsite(const char *name, u32 *instruction) { + if (strcmp("_mcount", name)) + return false; + /* * Check if this is one of the -mprofile-kernel sequences. */ @@ -496,8 +503,7 @@ static void squash_toc_save_inst(const char *name, unsigned long addr) #else static void squash_toc_save_inst(const char *name, unsigned long addr) { } -/* without -mprofile-kernel, mcount calls are never early */ -static bool is_early_mcount_callsite(u32 *instruction) +static bool is_mprofile_mcount_callsite(const char *name, u32 *instruction) { return false; } @@ -505,11 +511,11 @@ static bool is_early_mcount_callsite(u32 *instruction) /* We expect a noop next: if it is, replace it with instruction to restore r2. */ -static int restore_r2(u32 *instruction, struct module *me) +static int restore_r2(const char *name, u32 *instruction, struct module *me) { u32 *prev_insn = instruction - 1; - if (is_early_mcount_callsite(prev_insn)) + if (is_mprofile_mcount_callsite(name, prev_insn)) return 1; /* @@ -650,7 +656,8 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, value = stub_for_addr(sechdrs, value, me); if (!value) return -ENOENT; - if (!restore_r2((u32 *)location + 1, me)) + if (!restore_r2(strtab + sym->st_name, + (u32 *)location + 1, me)) return -ENOEXEC; squash_toc_save_inst(strtab + sym->st_name, value); @@ -762,7 +769,8 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, * via the paca (in r13). The target (ftrace_caller()) is responsible for * saving and restoring the toc before returning. */ -static unsigned long create_ftrace_stub(const Elf64_Shdr *sechdrs, struct module *me) +static unsigned long create_ftrace_stub(const Elf64_Shdr *sechdrs, + struct module *me, unsigned long addr) { struct ppc64_stub_entry *entry; unsigned int i, num_stubs; @@ -789,9 +797,10 @@ static unsigned long create_ftrace_stub(const Elf64_Shdr *sechdrs, struct module memcpy(entry->jump, stub_insns, sizeof(stub_insns)); /* Stub uses address relative to kernel toc (from the paca) */ - reladdr = (unsigned long)ftrace_caller - kernel_toc_addr(); + reladdr = addr - kernel_toc_addr(); if (reladdr > 0x7FFFFFFF || reladdr < -(0x80000000L)) { - pr_err("%s: Address of ftrace_caller out of range of kernel_toc.\n", me->name); + pr_err("%s: Address of %ps out of range of kernel_toc.\n", + me->name, (void *)addr); return 0; } @@ -799,22 +808,29 @@ static unsigned long create_ftrace_stub(const Elf64_Shdr *sechdrs, struct module entry->jump[2] |= PPC_LO(reladdr); /* Eventhough we don't use funcdata in the stub, it's needed elsewhere. */ - entry->funcdata = func_desc((unsigned long)ftrace_caller); + entry->funcdata = func_desc(addr); entry->magic = STUB_MAGIC; return (unsigned long)entry; } #else -static unsigned long create_ftrace_stub(const Elf64_Shdr *sechdrs, struct module *me) +static unsigned long create_ftrace_stub(const Elf64_Shdr *sechdrs, + struct module *me, unsigned long addr) { - return stub_for_addr(sechdrs, (unsigned long)ftrace_caller, me); + return stub_for_addr(sechdrs, addr, me); } #endif int module_finalize_ftrace(struct module *mod, const Elf_Shdr *sechdrs) { - mod->arch.toc = my_r2(sechdrs, mod); - mod->arch.tramp = create_ftrace_stub(sechdrs, mod); + mod->arch.tramp = create_ftrace_stub(sechdrs, mod, + (unsigned long)ftrace_caller); +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS + mod->arch.tramp_regs = create_ftrace_stub(sechdrs, mod, + (unsigned long)ftrace_regs_caller); + if (!mod->arch.tramp_regs) + return -ENOENT; +#endif if (!mod->arch.tramp) return -ENOENT; diff --git a/arch/powerpc/kernel/nvram_64.c b/arch/powerpc/kernel/nvram_64.c index ba681dac7b46..22e9d281324d 100644 --- a/arch/powerpc/kernel/nvram_64.c +++ b/arch/powerpc/kernel/nvram_64.c @@ -1030,7 +1030,7 @@ loff_t __init nvram_create_partition(const char *name, int sig, return -ENOSPC; /* Create our OS partition */ - new_part = kmalloc(sizeof(*new_part), GFP_KERNEL); + new_part = kzalloc(sizeof(*new_part), GFP_KERNEL); if (!new_part) { pr_err("%s: kmalloc failed\n", __func__); return -ENOMEM; @@ -1039,7 +1039,7 @@ loff_t __init nvram_create_partition(const char *name, int sig, new_part->index = free_part->index; new_part->header.signature = sig; new_part->header.length = size; - strncpy(new_part->header.name, name, 12); + memcpy(new_part->header.name, name, strnlen(name, sizeof(new_part->header.name))); new_part->header.checksum = nvram_checksum(&new_part->header); rc = nvram_write_header(new_part); diff --git a/arch/powerpc/kernel/pci_32.c b/arch/powerpc/kernel/pci_32.c index 85ad2f78b889..4f861055a852 100644 --- a/arch/powerpc/kernel/pci_32.c +++ b/arch/powerpc/kernel/pci_32.c @@ -11,11 +11,13 @@ #include <linux/sched.h> #include <linux/errno.h> #include <linux/bootmem.h> +#include <linux/syscalls.h> #include <linux/irq.h> #include <linux/list.h> #include <linux/of.h> #include <linux/slab.h> #include <linux/export.h> +#include <linux/syscalls.h> #include <asm/processor.h> #include <asm/io.h> @@ -283,7 +285,11 @@ pci_bus_to_hose(int bus) * Note that the returned IO or memory base is a physical address */ -long sys_pciconfig_iobase(long which, unsigned long bus, unsigned long devfn) +#pragma GCC diagnostic push +#pragma GCC diagnostic ignored "-Wpragmas" +#pragma GCC diagnostic ignored "-Wattribute-alias" +SYSCALL_DEFINE3(pciconfig_iobase, long, which, + unsigned long, bus, unsigned long, devfn) { struct pci_controller* hose; long result = -EOPNOTSUPP; @@ -307,5 +313,4 @@ long sys_pciconfig_iobase(long which, unsigned long bus, unsigned long devfn) return result; } - - +#pragma GCC diagnostic pop diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c index 15ce0306b092..812171c09f42 100644 --- a/arch/powerpc/kernel/pci_64.c +++ b/arch/powerpc/kernel/pci_64.c @@ -203,8 +203,11 @@ void pcibios_setup_phb_io_space(struct pci_controller *hose) #define IOBASE_ISA_IO 3 #define IOBASE_ISA_MEM 4 -long sys_pciconfig_iobase(long which, unsigned long in_bus, - unsigned long in_devfn) +#pragma GCC diagnostic push +#pragma GCC diagnostic ignored "-Wpragmas" +#pragma GCC diagnostic ignored "-Wattribute-alias" +SYSCALL_DEFINE3(pciconfig_iobase, long, which, unsigned long, in_bus, + unsigned long, in_devfn) { struct pci_controller* hose; struct pci_bus *tmp_bus, *bus = NULL; @@ -256,6 +259,7 @@ long sys_pciconfig_iobase(long which, unsigned long in_bus, return -EOPNOTSUPP; } +#pragma GCC diagnostic pop #ifdef CONFIG_NUMA int pcibus_to_node(struct pci_bus *bus) diff --git a/arch/powerpc/kernel/ppc_save_regs.S b/arch/powerpc/kernel/ppc_save_regs.S index 1b1787d52896..8afbe213d729 100644 --- a/arch/powerpc/kernel/ppc_save_regs.S +++ b/arch/powerpc/kernel/ppc_save_regs.S @@ -25,6 +25,9 @@ */ _GLOBAL(ppc_save_regs) PPC_STL r0,0*SZL(r3) +#ifdef CONFIG_PPC32 + stmw r2, 2*SZL(r3) +#else PPC_STL r2,2*SZL(r3) PPC_STL r3,3*SZL(r3) PPC_STL r4,4*SZL(r3) @@ -55,6 +58,7 @@ _GLOBAL(ppc_save_regs) PPC_STL r29,29*SZL(r3) PPC_STL r30,30*SZL(r3) PPC_STL r31,31*SZL(r3) +#endif /* go up one stack frame for SP */ PPC_LL r4,0(r1) PPC_STL r4,1*SZL(r3) diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 26ea9793d290..9ef4aea9fffe 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -154,6 +154,7 @@ unsigned long msr_check_and_set(unsigned long bits) return newmsr; } +EXPORT_SYMBOL_GPL(msr_check_and_set); void __msr_check_and_clear(unsigned long bits) { @@ -846,10 +847,6 @@ bool ppc_breakpoint_available(void) } EXPORT_SYMBOL_GPL(ppc_breakpoint_available); -#ifdef CONFIG_PPC64 -DEFINE_PER_CPU(struct cpu_usage, cpu_usage_array); -#endif - static inline bool hw_brk_match(struct arch_hw_breakpoint *a, struct arch_hw_breakpoint *b) { @@ -1155,7 +1152,7 @@ static inline void restore_sprs(struct thread_struct *old_thread, mtspr(SPRN_TAR, new_thread->tar); } - if (cpu_has_feature(CPU_FTR_ARCH_300) && + if (cpu_has_feature(CPU_FTR_P9_TIDR) && old_thread->tidr != new_thread->tidr) mtspr(SPRN_TIDR, new_thread->tidr); #endif @@ -1182,20 +1179,6 @@ struct task_struct *__switch_to(struct task_struct *prev, WARN_ON(!irqs_disabled()); -#ifdef CONFIG_PPC64 - /* - * Collect processor utilization data per process - */ - if (firmware_has_feature(FW_FEATURE_SPLPAR)) { - struct cpu_usage *cu = this_cpu_ptr(&cpu_usage_array); - long unsigned start_tb, current_tb; - start_tb = old_thread->start_tb; - cu->current_tb = current_tb = mfspr(SPRN_PURR); - old_thread->accum_tb += (current_tb - start_tb); - new_thread->start_tb = current_tb; - } -#endif /* CONFIG_PPC64 */ - #ifdef CONFIG_PPC_BOOK3S_64 batch = this_cpu_ptr(&ppc64_tlb_batch); if (batch->active) { @@ -1438,7 +1421,7 @@ void show_regs(struct pt_regs * regs) pr_cont("DAR: "REG" DSISR: %08lx ", regs->dar, regs->dsisr); #endif #ifdef CONFIG_PPC64 - pr_cont("SOFTE: %ld ", regs->softe); + pr_cont("IRQMASK: %lx ", regs->softe); #endif #ifdef CONFIG_PPC_TRANSACTIONAL_MEM if (MSR_TM_ACTIVE(regs->msr)) @@ -1497,104 +1480,42 @@ int set_thread_uses_vas(void) } #ifdef CONFIG_PPC64 -static DEFINE_SPINLOCK(vas_thread_id_lock); -static DEFINE_IDA(vas_thread_ida); - -/* - * We need to assign a unique thread id to each thread in a process. +/** + * Assign a TIDR (thread ID) for task @t and set it in the thread + * structure. For now, we only support setting TIDR for 'current' task. * - * This thread id, referred to as TIDR, and separate from the Linux's tgid, - * is intended to be used to direct an ASB_Notify from the hardware to the - * thread, when a suitable event occurs in the system. + * Since the TID value is a truncated form of it PID, it is possible + * (but unlikely) for 2 threads to have the same TID. In the unlikely event + * that 2 threads share the same TID and are waiting, one of the following + * cases will happen: * - * One such event is a "paste" instruction in the context of Fast Thread - * Wakeup (aka Core-to-core wake up in the Virtual Accelerator Switchboard - * (VAS) in POWER9. + * 1. The correct thread is running, the wrong thread is not + * In this situation, the correct thread is woken and proceeds to pass it's + * condition check. * - * To get a unique TIDR per process we could simply reuse task_pid_nr() but - * the problem is that task_pid_nr() is not yet available copy_thread() is - * called. Fixing that would require changing more intrusive arch-neutral - * code in code path in copy_process()?. + * 2. Neither threads are running + * In this situation, neither thread will be woken. When scheduled, the waiting + * threads will execute either a wait, which will return immediately, followed + * by a condition check, which will pass for the correct thread and fail + * for the wrong thread, or they will execute the condition check immediately. * - * Further, to assign unique TIDRs within each process, we need an atomic - * field (or an IDR) in task_struct, which again intrudes into the arch- - * neutral code. So try to assign globally unique TIDRs for now. + * 3. The wrong thread is running, the correct thread is not + * The wrong thread will be woken, but will fail it's condition check and + * re-execute wait. The correct thread, when scheduled, will execute either + * it's condition check (which will pass), or wait, which returns immediately + * when called the first time after the thread is scheduled, followed by it's + * condition check (which will pass). * - * NOTE: TIDR 0 indicates that the thread does not need a TIDR value. - * For now, only threads that expect to be notified by the VAS - * hardware need a TIDR value and we assign values > 0 for those. - */ -#define MAX_THREAD_CONTEXT ((1 << 16) - 1) -static int assign_thread_tidr(void) -{ - int index; - int err; - unsigned long flags; - -again: - if (!ida_pre_get(&vas_thread_ida, GFP_KERNEL)) - return -ENOMEM; - - spin_lock_irqsave(&vas_thread_id_lock, flags); - err = ida_get_new_above(&vas_thread_ida, 1, &index); - spin_unlock_irqrestore(&vas_thread_id_lock, flags); - - if (err == -EAGAIN) - goto again; - else if (err) - return err; - - if (index > MAX_THREAD_CONTEXT) { - spin_lock_irqsave(&vas_thread_id_lock, flags); - ida_remove(&vas_thread_ida, index); - spin_unlock_irqrestore(&vas_thread_id_lock, flags); - return -ENOMEM; - } - - return index; -} - -static void free_thread_tidr(int id) -{ - unsigned long flags; - - spin_lock_irqsave(&vas_thread_id_lock, flags); - ida_remove(&vas_thread_ida, id); - spin_unlock_irqrestore(&vas_thread_id_lock, flags); -} - -/* - * Clear any TIDR value assigned to this thread. - */ -void clear_thread_tidr(struct task_struct *t) -{ - if (!t->thread.tidr) - return; - - if (!cpu_has_feature(CPU_FTR_ARCH_300)) { - WARN_ON_ONCE(1); - return; - } - - mtspr(SPRN_TIDR, 0); - free_thread_tidr(t->thread.tidr); - t->thread.tidr = 0; -} - -void arch_release_task_struct(struct task_struct *t) -{ - clear_thread_tidr(t); -} - -/* - * Assign a unique TIDR (thread id) for task @t and set it in the thread - * structure. For now, we only support setting TIDR for 'current' task. + * 4. Both threads are running + * Both threads will be woken. The wrong thread will fail it's condition check + * and execute another wait, while the correct thread will pass it's condition + * check. + * + * @t: the task to set the thread ID for */ int set_thread_tidr(struct task_struct *t) { - int rc; - - if (!cpu_has_feature(CPU_FTR_ARCH_300)) + if (!cpu_has_feature(CPU_FTR_P9_TIDR)) return -EINVAL; if (t != current) @@ -1603,11 +1524,7 @@ int set_thread_tidr(struct task_struct *t) if (t->thread.tidr) return 0; - rc = assign_thread_tidr(); - if (rc < 0) - return rc; - - t->thread.tidr = rc; + t->thread.tidr = (u16)task_pid_nr(t); mtspr(SPRN_TIDR, t->thread.tidr); return 0; diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index 9dbed488aba1..05e7fb47a7a4 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -332,25 +332,10 @@ static int __init early_init_dt_scan_cpus(unsigned long node, * NOTE: This must match the parsing done in smp_setup_cpu_maps. */ for (i = 0; i < nthreads; i++) { - /* - * version 2 of the kexec param format adds the phys cpuid of - * booted proc. - */ - if (fdt_version(initial_boot_params) >= 2) { - if (be32_to_cpu(intserv[i]) == - fdt_boot_cpuid_phys(initial_boot_params)) { - found = boot_cpu_count; - found_thread = i; - } - } else { - /* - * Check if it's the boot-cpu, set it's hw index now, - * unfortunately this format did not support booting - * off secondary threads. - */ - if (of_get_flat_dt_prop(node, - "linux,boot-cpu", NULL) != NULL) - found = boot_cpu_count; + if (be32_to_cpu(intserv[i]) == + fdt_boot_cpuid_phys(initial_boot_params)) { + found = boot_cpu_count; + found_thread = i; } #ifdef CONFIG_SMP /* logical cpu id is always 0 on UP kernels */ diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index f9d6befb55a6..5425dd3d6a9f 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -103,7 +103,7 @@ int of_workarounds; #ifdef DEBUG_PROM #define prom_debug(x...) prom_printf(x) #else -#define prom_debug(x...) +#define prom_debug(x...) do { } while (0) #endif @@ -301,6 +301,10 @@ static void __init prom_print(const char *msg) } +/* + * Both prom_print_hex & prom_print_dec takes an unsigned long as input so that + * we do not need __udivdi3 or __umoddi3 on 32bits. + */ static void __init prom_print_hex(unsigned long val) { int i, nibbles = sizeof(val)*2; @@ -334,12 +338,14 @@ static void __init prom_print_dec(unsigned long val) call_prom("write", 3, 1, prom.stdout, buf+i, size); } +__printf(1, 2) static void __init prom_printf(const char *format, ...) { const char *p, *q, *s; va_list args; unsigned long v; long vs; + int n = 0; va_start(args, format); for (p = format; *p != 0; p = q) { @@ -358,6 +364,10 @@ static void __init prom_printf(const char *format, ...) ++q; if (*q == 0) break; + while (*q == 'l') { + ++q; + ++n; + } switch (*q) { case 's': ++q; @@ -366,39 +376,55 @@ static void __init prom_printf(const char *format, ...) break; case 'x': ++q; - v = va_arg(args, unsigned long); + switch (n) { + case 0: + v = va_arg(args, unsigned int); + break; + case 1: + v = va_arg(args, unsigned long); + break; + case 2: + default: + v = va_arg(args, unsigned long long); + break; + } prom_print_hex(v); break; - case 'd': + case 'u': ++q; - vs = va_arg(args, int); - if (vs < 0) { - prom_print("-"); - vs = -vs; + switch (n) { + case 0: + v = va_arg(args, unsigned int); + break; + case 1: + v = va_arg(args, unsigned long); + break; + case 2: + default: + v = va_arg(args, unsigned long long); + break; } - prom_print_dec(vs); + prom_print_dec(v); break; - case 'l': + case 'd': ++q; - if (*q == 0) + switch (n) { + case 0: + vs = va_arg(args, int); break; - else if (*q == 'x') { - ++q; - v = va_arg(args, unsigned long); - prom_print_hex(v); - } else if (*q == 'u') { /* '%lu' */ - ++q; - v = va_arg(args, unsigned long); - prom_print_dec(v); - } else if (*q == 'd') { /* %ld */ - ++q; + case 1: vs = va_arg(args, long); - if (vs < 0) { - prom_print("-"); - vs = -vs; - } - prom_print_dec(vs); + break; + case 2: + default: + vs = va_arg(args, long long); + break; } + if (vs < 0) { + prom_print("-"); + vs = -vs; + } + prom_print_dec(vs); break; } } @@ -1160,7 +1186,7 @@ static void __init prom_send_capabilities(void) */ cores = DIV_ROUND_UP(NR_CPUS, prom_count_smt_threads()); - prom_printf("Max number of cores passed to firmware: %lu (NR_CPUS = %lu)\n", + prom_printf("Max number of cores passed to firmware: %u (NR_CPUS = %d)\n", cores, NR_CPUS); ibm_architecture_vec.vec5.max_cpus = cpu_to_be32(cores); @@ -1242,7 +1268,7 @@ static unsigned long __init alloc_up(unsigned long size, unsigned long align) if (align) base = _ALIGN_UP(base, align); - prom_debug("alloc_up(%x, %x)\n", size, align); + prom_debug("%s(%lx, %lx)\n", __func__, size, align); if (ram_top == 0) prom_panic("alloc_up() called with mem not initialized\n"); @@ -1253,7 +1279,7 @@ static unsigned long __init alloc_up(unsigned long size, unsigned long align) for(; (base + size) <= alloc_top; base = _ALIGN_UP(base + 0x100000, align)) { - prom_debug(" trying: 0x%x\n\r", base); + prom_debug(" trying: 0x%lx\n\r", base); addr = (unsigned long)prom_claim(base, size, 0); if (addr != PROM_ERROR && addr != 0) break; @@ -1265,12 +1291,12 @@ static unsigned long __init alloc_up(unsigned long size, unsigned long align) return 0; alloc_bottom = addr + size; - prom_debug(" -> %x\n", addr); - prom_debug(" alloc_bottom : %x\n", alloc_bottom); - prom_debug(" alloc_top : %x\n", alloc_top); - prom_debug(" alloc_top_hi : %x\n", alloc_top_high); - prom_debug(" rmo_top : %x\n", rmo_top); - prom_debug(" ram_top : %x\n", ram_top); + prom_debug(" -> %lx\n", addr); + prom_debug(" alloc_bottom : %lx\n", alloc_bottom); + prom_debug(" alloc_top : %lx\n", alloc_top); + prom_debug(" alloc_top_hi : %lx\n", alloc_top_high); + prom_debug(" rmo_top : %lx\n", rmo_top); + prom_debug(" ram_top : %lx\n", ram_top); return addr; } @@ -1285,7 +1311,7 @@ static unsigned long __init alloc_down(unsigned long size, unsigned long align, { unsigned long base, addr = 0; - prom_debug("alloc_down(%x, %x, %s)\n", size, align, + prom_debug("%s(%lx, %lx, %s)\n", __func__, size, align, highmem ? "(high)" : "(low)"); if (ram_top == 0) prom_panic("alloc_down() called with mem not initialized\n"); @@ -1313,7 +1339,7 @@ static unsigned long __init alloc_down(unsigned long size, unsigned long align, base = _ALIGN_DOWN(alloc_top - size, align); for (; base > alloc_bottom; base = _ALIGN_DOWN(base - 0x100000, align)) { - prom_debug(" trying: 0x%x\n\r", base); + prom_debug(" trying: 0x%lx\n\r", base); addr = (unsigned long)prom_claim(base, size, 0); if (addr != PROM_ERROR && addr != 0) break; @@ -1324,12 +1350,12 @@ static unsigned long __init alloc_down(unsigned long size, unsigned long align, alloc_top = addr; bail: - prom_debug(" -> %x\n", addr); - prom_debug(" alloc_bottom : %x\n", alloc_bottom); - prom_debug(" alloc_top : %x\n", alloc_top); - prom_debug(" alloc_top_hi : %x\n", alloc_top_high); - prom_debug(" rmo_top : %x\n", rmo_top); - prom_debug(" ram_top : %x\n", ram_top); + prom_debug(" -> %lx\n", addr); + prom_debug(" alloc_bottom : %lx\n", alloc_bottom); + prom_debug(" alloc_top : %lx\n", alloc_top); + prom_debug(" alloc_top_hi : %lx\n", alloc_top_high); + prom_debug(" rmo_top : %lx\n", rmo_top); + prom_debug(" ram_top : %lx\n", ram_top); return addr; } @@ -1455,7 +1481,7 @@ static void __init prom_init_mem(void) if (size == 0) continue; - prom_debug(" %x %x\n", base, size); + prom_debug(" %lx %lx\n", base, size); if (base == 0 && (of_platform & PLATFORM_LPAR)) rmo_top = size; if ((base + size) > ram_top) @@ -1475,12 +1501,12 @@ static void __init prom_init_mem(void) if (prom_memory_limit) { if (prom_memory_limit <= alloc_bottom) { - prom_printf("Ignoring mem=%x <= alloc_bottom.\n", - prom_memory_limit); + prom_printf("Ignoring mem=%lx <= alloc_bottom.\n", + prom_memory_limit); prom_memory_limit = 0; } else if (prom_memory_limit >= ram_top) { - prom_printf("Ignoring mem=%x >= ram_top.\n", - prom_memory_limit); + prom_printf("Ignoring mem=%lx >= ram_top.\n", + prom_memory_limit); prom_memory_limit = 0; } else { ram_top = prom_memory_limit; @@ -1512,12 +1538,13 @@ static void __init prom_init_mem(void) alloc_bottom = PAGE_ALIGN(prom_initrd_end); prom_printf("memory layout at init:\n"); - prom_printf(" memory_limit : %x (16 MB aligned)\n", prom_memory_limit); - prom_printf(" alloc_bottom : %x\n", alloc_bottom); - prom_printf(" alloc_top : %x\n", alloc_top); - prom_printf(" alloc_top_hi : %x\n", alloc_top_high); - prom_printf(" rmo_top : %x\n", rmo_top); - prom_printf(" ram_top : %x\n", ram_top); + prom_printf(" memory_limit : %lx (16 MB aligned)\n", + prom_memory_limit); + prom_printf(" alloc_bottom : %lx\n", alloc_bottom); + prom_printf(" alloc_top : %lx\n", alloc_top); + prom_printf(" alloc_top_hi : %lx\n", alloc_top_high); + prom_printf(" rmo_top : %lx\n", rmo_top); + prom_printf(" ram_top : %lx\n", ram_top); } static void __init prom_close_stdin(void) @@ -1578,7 +1605,7 @@ static void __init prom_instantiate_opal(void) return; } - prom_printf("instantiating opal at 0x%x...", base); + prom_printf("instantiating opal at 0x%llx...", base); if (call_prom_ret("call-method", 4, 3, rets, ADDR("load-opal-runtime"), @@ -1594,10 +1621,10 @@ static void __init prom_instantiate_opal(void) reserve_mem(base, size); - prom_debug("opal base = 0x%x\n", base); - prom_debug("opal align = 0x%x\n", align); - prom_debug("opal entry = 0x%x\n", entry); - prom_debug("opal size = 0x%x\n", (long)size); + prom_debug("opal base = 0x%llx\n", base); + prom_debug("opal align = 0x%llx\n", align); + prom_debug("opal entry = 0x%llx\n", entry); + prom_debug("opal size = 0x%llx\n", size); prom_setprop(opal_node, "/ibm,opal", "opal-base-address", &base, sizeof(base)); @@ -1674,7 +1701,7 @@ static void __init prom_instantiate_rtas(void) prom_debug("rtas base = 0x%x\n", base); prom_debug("rtas entry = 0x%x\n", entry); - prom_debug("rtas size = 0x%x\n", (long)size); + prom_debug("rtas size = 0x%x\n", size); prom_debug("prom_instantiate_rtas: end...\n"); } @@ -1732,7 +1759,7 @@ static void __init prom_instantiate_sml(void) if (base == 0) prom_panic("Could not allocate memory for sml\n"); - prom_printf("instantiating sml at 0x%x...", base); + prom_printf("instantiating sml at 0x%llx...", base); memset((void *)base, 0, size); @@ -1751,8 +1778,8 @@ static void __init prom_instantiate_sml(void) prom_setprop(ibmvtpm_node, "/vdevice/vtpm", "linux,sml-size", &size, sizeof(size)); - prom_debug("sml base = 0x%x\n", base); - prom_debug("sml size = 0x%x\n", (long)size); + prom_debug("sml base = 0x%llx\n", base); + prom_debug("sml size = 0x%x\n", size); prom_debug("prom_instantiate_sml: end...\n"); } @@ -1845,7 +1872,7 @@ static void __init prom_initialize_tce_table(void) prom_debug("TCE table: %s\n", path); prom_debug("\tnode = 0x%x\n", node); - prom_debug("\tbase = 0x%x\n", base); + prom_debug("\tbase = 0x%llx\n", base); prom_debug("\tsize = 0x%x\n", minsize); /* Initialize the table to have a one-to-one mapping @@ -1932,12 +1959,12 @@ static void __init prom_hold_cpus(void) } prom_debug("prom_hold_cpus: start...\n"); - prom_debug(" 1) spinloop = 0x%x\n", (unsigned long)spinloop); - prom_debug(" 1) *spinloop = 0x%x\n", *spinloop); - prom_debug(" 1) acknowledge = 0x%x\n", + prom_debug(" 1) spinloop = 0x%lx\n", (unsigned long)spinloop); + prom_debug(" 1) *spinloop = 0x%lx\n", *spinloop); + prom_debug(" 1) acknowledge = 0x%lx\n", (unsigned long)acknowledge); - prom_debug(" 1) *acknowledge = 0x%x\n", *acknowledge); - prom_debug(" 1) secondary_hold = 0x%x\n", secondary_hold); + prom_debug(" 1) *acknowledge = 0x%lx\n", *acknowledge); + prom_debug(" 1) secondary_hold = 0x%lx\n", secondary_hold); /* Set the common spinloop variable, so all of the secondary cpus * will block when they are awakened from their OF spinloop. @@ -1965,7 +1992,7 @@ static void __init prom_hold_cpus(void) prom_getprop(node, "reg", ®, sizeof(reg)); cpu_no = be32_to_cpu(reg); - prom_debug("cpu hw idx = %lu\n", cpu_no); + prom_debug("cpu hw idx = %u\n", cpu_no); /* Init the acknowledge var which will be reset by * the secondary cpu when it awakens from its OF @@ -1975,7 +2002,7 @@ static void __init prom_hold_cpus(void) if (cpu_no != prom.cpu) { /* Primary Thread of non-boot cpu or any thread */ - prom_printf("starting cpu hw idx %lu... ", cpu_no); + prom_printf("starting cpu hw idx %u... ", cpu_no); call_prom("start-cpu", 3, 0, node, secondary_hold, cpu_no); @@ -1986,11 +2013,11 @@ static void __init prom_hold_cpus(void) if (*acknowledge == cpu_no) prom_printf("done\n"); else - prom_printf("failed: %x\n", *acknowledge); + prom_printf("failed: %lx\n", *acknowledge); } #ifdef CONFIG_SMP else - prom_printf("boot cpu hw idx %lu\n", cpu_no); + prom_printf("boot cpu hw idx %u\n", cpu_no); #endif /* CONFIG_SMP */ } @@ -2268,7 +2295,7 @@ static void __init *make_room(unsigned long *mem_start, unsigned long *mem_end, while ((*mem_start + needed) > *mem_end) { unsigned long room, chunk; - prom_debug("Chunk exhausted, claiming more at %x...\n", + prom_debug("Chunk exhausted, claiming more at %lx...\n", alloc_bottom); room = alloc_top - alloc_bottom; if (room > DEVTREE_CHUNK_SIZE) @@ -2494,7 +2521,7 @@ static void __init flatten_device_tree(void) room = alloc_top - alloc_bottom - 0x4000; if (room > DEVTREE_CHUNK_SIZE) room = DEVTREE_CHUNK_SIZE; - prom_debug("starting device tree allocs at %x\n", alloc_bottom); + prom_debug("starting device tree allocs at %lx\n", alloc_bottom); /* Now try to claim that */ mem_start = (unsigned long)alloc_up(room, PAGE_SIZE); @@ -2557,7 +2584,7 @@ static void __init flatten_device_tree(void) int i; prom_printf("reserved memory map:\n"); for (i = 0; i < mem_reserve_cnt; i++) - prom_printf(" %x - %x\n", + prom_printf(" %llx - %llx\n", be64_to_cpu(mem_reserve_map[i].base), be64_to_cpu(mem_reserve_map[i].size)); } @@ -2567,9 +2594,9 @@ static void __init flatten_device_tree(void) */ mem_reserve_cnt = MEM_RESERVE_MAP_SIZE; - prom_printf("Device tree strings 0x%x -> 0x%x\n", + prom_printf("Device tree strings 0x%lx -> 0x%lx\n", dt_string_start, dt_string_end); - prom_printf("Device tree struct 0x%x -> 0x%x\n", + prom_printf("Device tree struct 0x%lx -> 0x%lx\n", dt_struct_start, dt_struct_end); } @@ -3001,7 +3028,7 @@ static void __init prom_find_boot_cpu(void) prom_getprop(cpu_pkg, "reg", &rval, sizeof(rval)); prom.cpu = be32_to_cpu(rval); - prom_debug("Booting CPU hw index = %lu\n", prom.cpu); + prom_debug("Booting CPU hw index = %d\n", prom.cpu); } static void __init prom_check_initrd(unsigned long r3, unsigned long r4) @@ -3023,8 +3050,8 @@ static void __init prom_check_initrd(unsigned long r3, unsigned long r4) reserve_mem(prom_initrd_start, prom_initrd_end - prom_initrd_start); - prom_debug("initrd_start=0x%x\n", prom_initrd_start); - prom_debug("initrd_end=0x%x\n", prom_initrd_end); + prom_debug("initrd_start=0x%lx\n", prom_initrd_start); + prom_debug("initrd_end=0x%lx\n", prom_initrd_end); } #endif /* CONFIG_BLK_DEV_INITRD */ } @@ -3277,7 +3304,7 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4, /* Don't print anything after quiesce under OPAL, it crashes OFW */ if (of_platform != PLATFORM_OPAL) { prom_printf("Booting Linux via __start() @ 0x%lx ...\n", kbase); - prom_debug("->dt_header_start=0x%x\n", hdr); + prom_debug("->dt_header_start=0x%lx\n", hdr); } #ifdef CONFIG_PPC32 diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c index d23cf632edf0..9667666eb18e 100644 --- a/arch/powerpc/kernel/ptrace.c +++ b/arch/powerpc/kernel/ptrace.c @@ -2443,6 +2443,7 @@ static int ptrace_set_debugreg(struct task_struct *task, unsigned long addr, /* Create a new breakpoint request if one doesn't exist already */ hw_breakpoint_init(&attr); attr.bp_addr = hw_brk.address; + attr.bp_len = 8; arch_bp_generic_fields(hw_brk.type, &attr.bp_type); @@ -3081,27 +3082,19 @@ long arch_ptrace(struct task_struct *child, long request, #endif /* CONFIG_HAVE_HW_BREAKPOINT */ #endif /* CONFIG_PPC_ADV_DEBUG_REGS */ - if (!access_ok(VERIFY_WRITE, datavp, - sizeof(struct ppc_debug_info))) + if (copy_to_user(datavp, &dbginfo, + sizeof(struct ppc_debug_info))) return -EFAULT; - ret = __copy_to_user(datavp, &dbginfo, - sizeof(struct ppc_debug_info)) ? - -EFAULT : 0; - break; + return 0; } case PPC_PTRACE_SETHWDEBUG: { struct ppc_hw_breakpoint bp_info; - if (!access_ok(VERIFY_READ, datavp, - sizeof(struct ppc_hw_breakpoint))) + if (copy_from_user(&bp_info, datavp, + sizeof(struct ppc_hw_breakpoint))) return -EFAULT; - ret = __copy_from_user(&bp_info, datavp, - sizeof(struct ppc_hw_breakpoint)) ? - -EFAULT : 0; - if (!ret) - ret = ppc_set_hwdebug(child, &bp_info); - break; + return ppc_set_hwdebug(child, &bp_info); } case PPC_PTRACE_DELHWDEBUG: { diff --git a/arch/powerpc/kernel/rtas-proc.c b/arch/powerpc/kernel/rtas-proc.c index d49063d0baa4..487dcd8da4de 100644 --- a/arch/powerpc/kernel/rtas-proc.c +++ b/arch/powerpc/kernel/rtas-proc.c @@ -256,7 +256,7 @@ static int __init proc_rtas_init(void) __initcall(proc_rtas_init); -static int parse_number(const char __user *p, size_t count, unsigned long *val) +static int parse_number(const char __user *p, size_t count, u64 *val) { char buf[40]; char *end; @@ -269,7 +269,7 @@ static int parse_number(const char __user *p, size_t count, unsigned long *val) buf[count] = 0; - *val = simple_strtoul(buf, &end, 10); + *val = simple_strtoull(buf, &end, 10); if (*end && *end != '\n') return -EINVAL; @@ -283,17 +283,17 @@ static ssize_t ppc_rtas_poweron_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { struct rtc_time tm; - unsigned long nowtime; + time64_t nowtime; int error = parse_number(buf, count, &nowtime); if (error) return error; power_on_time = nowtime; /* save the time */ - to_tm(nowtime, &tm); + rtc_time64_to_tm(nowtime, &tm); error = rtas_call(rtas_token("set-time-for-power-on"), 7, 1, NULL, - tm.tm_year, tm.tm_mon, tm.tm_mday, + tm.tm_year + 1900, tm.tm_mon + 1, tm.tm_mday, tm.tm_hour, tm.tm_min, tm.tm_sec, 0 /* nano */); if (error) printk(KERN_WARNING "error: setting poweron time returned: %s\n", @@ -349,14 +349,14 @@ static ssize_t ppc_rtas_clock_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { struct rtc_time tm; - unsigned long nowtime; + time64_t nowtime; int error = parse_number(buf, count, &nowtime); if (error) return error; - to_tm(nowtime, &tm); + rtc_time64_to_tm(nowtime, &tm); error = rtas_call(rtas_token("set-time-of-day"), 7, 1, NULL, - tm.tm_year, tm.tm_mon, tm.tm_mday, + tm.tm_year + 1900, tm.tm_mon + 1, tm.tm_mday, tm.tm_hour, tm.tm_min, tm.tm_sec, 0); if (error) printk(KERN_WARNING "error: setting the clock returned: %s\n", @@ -377,8 +377,8 @@ static int ppc_rtas_clock_show(struct seq_file *m, void *v) unsigned int year, mon, day, hour, min, sec; year = ret[0]; mon = ret[1]; day = ret[2]; hour = ret[3]; min = ret[4]; sec = ret[5]; - seq_printf(m, "%lu\n", - mktime(year, mon, day, hour, min, sec)); + seq_printf(m, "%lld\n", + mktime64(year, mon, day, hour, min, sec)); } return 0; } @@ -504,7 +504,7 @@ static void ppc_rtas_process_sensor(struct seq_file *m, "EPOW power off" }; const char * battery_cyclestate[] = { "None", "In progress", "Requested" }; - const char * battery_charging[] = { "Charging", "Discharching", + const char * battery_charging[] = { "Charging", "Discharging", "No current flow" }; const char * ibm_drconnector[] = { "Empty", "Present", "Unusable", "Exchange" }; @@ -707,7 +707,7 @@ static void get_location_code(struct seq_file *m, struct individual_sensor *s, static ssize_t ppc_rtas_tone_freq_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { - unsigned long freq; + u64 freq; int error = parse_number(buf, count, &freq); if (error) return error; @@ -732,7 +732,7 @@ static int ppc_rtas_tone_freq_show(struct seq_file *m, void *v) static ssize_t ppc_rtas_tone_volume_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { - unsigned long volume; + u64 volume; int error = parse_number(buf, count, &volume); if (error) return error; diff --git a/arch/powerpc/kernel/rtas-rtc.c b/arch/powerpc/kernel/rtas-rtc.c index 49600985c7ef..a28239b8b0c0 100644 --- a/arch/powerpc/kernel/rtas-rtc.c +++ b/arch/powerpc/kernel/rtas-rtc.c @@ -13,7 +13,7 @@ #define MAX_RTC_WAIT 5000 /* 5 sec */ #define RTAS_CLOCK_BUSY (-2) -unsigned long __init rtas_get_boot_time(void) +time64_t __init rtas_get_boot_time(void) { int ret[8]; int error; @@ -38,7 +38,7 @@ unsigned long __init rtas_get_boot_time(void) return 0; } - return mktime(ret[0], ret[1], ret[2], ret[3], ret[4], ret[5]); + return mktime64(ret[0], ret[1], ret[2], ret[3], ret[4], ret[5]); } /* NOTE: get_rtc_time will get an error if executed in interrupt context diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c index 3f1c4fcbe0aa..7fb9f83dcde8 100644 --- a/arch/powerpc/kernel/rtas.c +++ b/arch/powerpc/kernel/rtas.c @@ -26,6 +26,7 @@ #include <linux/memblock.h> #include <linux/slab.h> #include <linux/reboot.h> +#include <linux/syscalls.h> #include <asm/prom.h> #include <asm/rtas.h> @@ -1050,7 +1051,10 @@ struct pseries_errorlog *get_pseries_errorlog(struct rtas_error_log *log, } /* We assume to be passed big endian arguments */ -asmlinkage int ppc_rtas(struct rtas_args __user *uargs) +#pragma GCC diagnostic push +#pragma GCC diagnostic ignored "-Wpragmas" +#pragma GCC diagnostic ignored "-Wattribute-alias" +SYSCALL_DEFINE1(rtas, struct rtas_args __user *, uargs) { struct rtas_args args; unsigned long flags; @@ -1136,6 +1140,7 @@ asmlinkage int ppc_rtas(struct rtas_args __user *uargs) return 0; } +#pragma GCC diagnostic pop /* * Call early during boot, before mem init, to retrieve the RTAS diff --git a/arch/powerpc/kernel/security.c b/arch/powerpc/kernel/security.c index b98a722da915..a8b277362931 100644 --- a/arch/powerpc/kernel/security.c +++ b/arch/powerpc/kernel/security.c @@ -10,10 +10,78 @@ #include <asm/debugfs.h> #include <asm/security_features.h> +#include <asm/setup.h> unsigned long powerpc_security_features __read_mostly = SEC_FTR_DEFAULT; +bool barrier_nospec_enabled; + +static void enable_barrier_nospec(bool enable) +{ + barrier_nospec_enabled = enable; + do_barrier_nospec_fixups(enable); +} + +void setup_barrier_nospec(void) +{ + bool enable; + + /* + * It would make sense to check SEC_FTR_SPEC_BAR_ORI31 below as well. + * But there's a good reason not to. The two flags we check below are + * both are enabled by default in the kernel, so if the hcall is not + * functional they will be enabled. + * On a system where the host firmware has been updated (so the ori + * functions as a barrier), but on which the hypervisor (KVM/Qemu) has + * not been updated, we would like to enable the barrier. Dropping the + * check for SEC_FTR_SPEC_BAR_ORI31 achieves that. The only downside is + * we potentially enable the barrier on systems where the host firmware + * is not updated, but that's harmless as it's a no-op. + */ + enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) && + security_ftr_enabled(SEC_FTR_BNDS_CHK_SPEC_BAR); + + enable_barrier_nospec(enable); +} + +#ifdef CONFIG_DEBUG_FS +static int barrier_nospec_set(void *data, u64 val) +{ + switch (val) { + case 0: + case 1: + break; + default: + return -EINVAL; + } + + if (!!val == !!barrier_nospec_enabled) + return 0; + + enable_barrier_nospec(!!val); + + return 0; +} + +static int barrier_nospec_get(void *data, u64 *val) +{ + *val = barrier_nospec_enabled ? 1 : 0; + return 0; +} + +DEFINE_SIMPLE_ATTRIBUTE(fops_barrier_nospec, + barrier_nospec_get, barrier_nospec_set, "%llu\n"); + +static __init int barrier_nospec_debugfs_init(void) +{ + debugfs_create_file("barrier_nospec", 0600, powerpc_debugfs_root, NULL, + &fops_barrier_nospec); + return 0; +} +device_initcall(barrier_nospec_debugfs_init); +#endif /* CONFIG_DEBUG_FS */ + ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, char *buf) { bool thread_priv; @@ -52,6 +120,9 @@ ssize_t cpu_show_spectre_v1(struct device *dev, struct device_attribute *attr, c if (!security_ftr_enabled(SEC_FTR_BNDS_CHK_SPEC_BAR)) return sprintf(buf, "Not affected\n"); + if (barrier_nospec_enabled) + return sprintf(buf, "Mitigation: __user pointer sanitization\n"); + return sprintf(buf, "Vulnerable\n"); } diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index 0af5c11b9e78..62b1a40d8957 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -192,12 +192,6 @@ void machine_halt(void) machine_hang(); } - -#ifdef CONFIG_TAU -extern u32 cpu_temp(unsigned long cpu); -extern u32 cpu_temp_both(unsigned long cpu); -#endif /* CONFIG_TAU */ - #ifdef CONFIG_SMP DEFINE_PER_CPU(unsigned int, cpu_pvr); #endif diff --git a/arch/powerpc/kernel/setup.h b/arch/powerpc/kernel/setup.h index d144df54ad40..c6a592b67386 100644 --- a/arch/powerpc/kernel/setup.h +++ b/arch/powerpc/kernel/setup.h @@ -62,4 +62,10 @@ void kvm_cma_reserve(void); static inline void kvm_cma_reserve(void) { }; #endif +#ifdef CONFIG_TAU +u32 cpu_temp(unsigned long cpu); +u32 cpu_temp_both(unsigned long cpu); +u32 tau_interrupts(unsigned long cpu); +#endif /* CONFIG_TAU */ + #endif /* __ARCH_POWERPC_KERNEL_SETUP_H */ diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index b78f142a4148..7a7ce8ad455e 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -346,6 +346,13 @@ void __init early_setup(unsigned long dt_ptr) */ cpu_ready_for_interrupts(); + /* + * We enable ftrace here, but since we only support DYNAMIC_FTRACE, it + * will only actually get enabled on the boot cpu much later once + * ftrace itself has been initialized. + */ + this_cpu_enable_ftrace(); + DBG(" <- early_setup()\n"); #ifdef CONFIG_PPC_EARLY_DEBUG_BOOTX diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c index 61db86ecd318..fb932f1202c7 100644 --- a/arch/powerpc/kernel/signal.c +++ b/arch/powerpc/kernel/signal.c @@ -15,6 +15,7 @@ #include <linux/key.h> #include <linux/context_tracking.h> #include <linux/livepatch.h> +#include <linux/syscalls.h> #include <asm/hw_breakpoint.h> #include <linux/uaccess.h> #include <asm/unistd.h> @@ -150,6 +151,9 @@ void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags) { user_exit(); + /* Check valid addr_limit, TIF check is done there */ + addr_limit_user_check(); + if (thread_info_flags & _TIF_UPROBE) uprobe_notify_resume(regs); diff --git a/arch/powerpc/kernel/signal.h b/arch/powerpc/kernel/signal.h index a6467f843acf..800433685888 100644 --- a/arch/powerpc/kernel/signal.h +++ b/arch/powerpc/kernel/signal.h @@ -49,10 +49,8 @@ extern int handle_rt_signal64(struct ksignal *ksig, sigset_t *set, #else /* CONFIG_PPC64 */ -extern long sys_rt_sigreturn(int r3, int r4, int r5, int r6, int r7, int r8, - struct pt_regs *regs); -extern long sys_sigreturn(int r3, int r4, int r5, int r6, int r7, int r8, - struct pt_regs *regs); +extern long sys_rt_sigreturn(void); +extern long sys_sigreturn(void); static inline int handle_rt_signal64(struct ksignal *ksig, sigset_t *set, struct task_struct *tsk) diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index 492f03451877..5eedbb282d42 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -25,9 +25,10 @@ #include <linux/errno.h> #include <linux/elf.h> #include <linux/ptrace.h> +#include <linux/pagemap.h> #include <linux/ratelimit.h> -#ifdef CONFIG_PPC64 #include <linux/syscalls.h> +#ifdef CONFIG_PPC64 #include <linux/compat.h> #else #include <linux/wait.h> @@ -57,10 +58,6 @@ #ifdef CONFIG_PPC64 -#define sys_rt_sigreturn compat_sys_rt_sigreturn -#define sys_swapcontext compat_sys_swapcontext -#define sys_sigreturn compat_sys_sigreturn - #define old_sigaction old_sigaction32 #define sigcontext sigcontext32 #define mcontext mcontext32 @@ -1041,11 +1038,18 @@ static int do_setcontext_tm(struct ucontext __user *ucp, } #endif -long sys_swapcontext(struct ucontext __user *old_ctx, - struct ucontext __user *new_ctx, - int ctx_size, int r6, int r7, int r8, struct pt_regs *regs) +#pragma GCC diagnostic push +#pragma GCC diagnostic ignored "-Wpragmas" +#pragma GCC diagnostic ignored "-Wattribute-alias" +#ifdef CONFIG_PPC64 +COMPAT_SYSCALL_DEFINE3(swapcontext, struct ucontext __user *, old_ctx, + struct ucontext __user *, new_ctx, int, ctx_size) +#else +SYSCALL_DEFINE3(swapcontext, struct ucontext __user *, old_ctx, + struct ucontext __user *, new_ctx, long, ctx_size) +#endif { - unsigned char tmp __maybe_unused; + struct pt_regs *regs = current_pt_regs(); int ctx_has_vsx_region = 0; #ifdef CONFIG_PPC64 @@ -1109,9 +1113,8 @@ long sys_swapcontext(struct ucontext __user *old_ctx, } if (new_ctx == NULL) return 0; - if (!access_ok(VERIFY_READ, new_ctx, ctx_size) - || __get_user(tmp, (u8 __user *) new_ctx) - || __get_user(tmp, (u8 __user *) new_ctx + ctx_size - 1)) + if (!access_ok(VERIFY_READ, new_ctx, ctx_size) || + fault_in_pages_readable((u8 __user *)new_ctx, ctx_size)) return -EFAULT; /* @@ -1131,11 +1134,16 @@ long sys_swapcontext(struct ucontext __user *old_ctx, set_thread_flag(TIF_RESTOREALL); return 0; } +#pragma GCC diagnostic pop -long sys_rt_sigreturn(int r3, int r4, int r5, int r6, int r7, int r8, - struct pt_regs *regs) +#ifdef CONFIG_PPC64 +COMPAT_SYSCALL_DEFINE0(rt_sigreturn) +#else +SYSCALL_DEFINE0(rt_sigreturn) +#endif { struct rt_sigframe __user *rt_sf; + struct pt_regs *regs = current_pt_regs(); #ifdef CONFIG_PPC_TRANSACTIONAL_MEM struct ucontext __user *uc_transact; unsigned long msr_hi; @@ -1223,15 +1231,16 @@ long sys_rt_sigreturn(int r3, int r4, int r5, int r6, int r7, int r8, return 0; } +#pragma GCC diagnostic push +#pragma GCC diagnostic ignored "-Wpragmas" +#pragma GCC diagnostic ignored "-Wattribute-alias" #ifdef CONFIG_PPC32 -int sys_debug_setcontext(struct ucontext __user *ctx, - int ndbg, struct sig_dbg_op __user *dbg, - int r6, int r7, int r8, - struct pt_regs *regs) +SYSCALL_DEFINE3(debug_setcontext, struct ucontext __user *, ctx, + int, ndbg, struct sig_dbg_op __user *, dbg) { + struct pt_regs *regs = current_pt_regs(); struct sig_dbg_op op; int i; - unsigned char tmp __maybe_unused; unsigned long new_msr = regs->msr; #ifdef CONFIG_PPC_ADV_DEBUG_REGS unsigned long new_dbcr0 = current->thread.debug.dbcr0; @@ -1287,9 +1296,8 @@ int sys_debug_setcontext(struct ucontext __user *ctx, current->thread.debug.dbcr0 = new_dbcr0; #endif - if (!access_ok(VERIFY_READ, ctx, sizeof(*ctx)) - || __get_user(tmp, (u8 __user *) ctx) - || __get_user(tmp, (u8 __user *) (ctx + 1) - 1)) + if (!access_ok(VERIFY_READ, ctx, sizeof(*ctx)) || + fault_in_pages_readable((u8 __user *)ctx, sizeof(*ctx))) return -EFAULT; /* @@ -1329,6 +1337,7 @@ int sys_debug_setcontext(struct ucontext __user *ctx, return 0; } #endif +#pragma GCC diagnostic pop /* * OK, we're invoking a handler @@ -1419,9 +1428,13 @@ badframe: /* * Do a signal return; undo the signal stack. */ -long sys_sigreturn(int r3, int r4, int r5, int r6, int r7, int r8, - struct pt_regs *regs) +#ifdef CONFIG_PPC64 +COMPAT_SYSCALL_DEFINE0(sigreturn) +#else +SYSCALL_DEFINE0(sigreturn) +#endif { + struct pt_regs *regs = current_pt_regs(); struct sigframe __user *sf; struct sigcontext __user *sc; struct sigcontext sigctx; diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index 720117690822..d42b60020389 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -24,6 +24,7 @@ #include <linux/elf.h> #include <linux/ptrace.h> #include <linux/ratelimit.h> +#include <linux/syscalls.h> #include <asm/sigcontext.h> #include <asm/ucontext.h> @@ -624,17 +625,17 @@ static long setup_trampoline(unsigned int syscall, unsigned int __user *tramp) /* * Handle {get,set,swap}_context operations */ -int sys_swapcontext(struct ucontext __user *old_ctx, - struct ucontext __user *new_ctx, - long ctx_size, long r6, long r7, long r8, struct pt_regs *regs) +#pragma GCC diagnostic push +#pragma GCC diagnostic ignored "-Wpragmas" +#pragma GCC diagnostic ignored "-Wattribute-alias" +SYSCALL_DEFINE3(swapcontext, struct ucontext __user *, old_ctx, + struct ucontext __user *, new_ctx, long, ctx_size) { unsigned char tmp; sigset_t set; unsigned long new_msr = 0; int ctx_has_vsx_region = 0; - BUG_ON(regs != current->thread.regs); - if (new_ctx && get_user(new_msr, &new_ctx->uc_mcontext.gp_regs[PT_MSR])) return -EFAULT; @@ -692,24 +693,22 @@ int sys_swapcontext(struct ucontext __user *old_ctx, set_thread_flag(TIF_RESTOREALL); return 0; } +#pragma GCC diagnostic pop /* * Do a signal return; undo the signal stack. */ -int sys_rt_sigreturn(unsigned long r3, unsigned long r4, unsigned long r5, - unsigned long r6, unsigned long r7, unsigned long r8, - struct pt_regs *regs) +SYSCALL_DEFINE0(rt_sigreturn) { + struct pt_regs *regs = current_pt_regs(); struct ucontext __user *uc = (struct ucontext __user *)regs->gpr[1]; sigset_t set; #ifdef CONFIG_PPC_TRANSACTIONAL_MEM unsigned long msr; #endif - BUG_ON(current->thread.regs != regs); - /* Always make any pending restarted system calls return -EINTR */ current->restart_block.fn = do_no_restart_syscall; diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 9ca7148b5881..5eadfffabe35 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -59,6 +59,7 @@ #include <asm/kexec.h> #include <asm/asm-prototypes.h> #include <asm/cpu_has_feature.h> +#include <asm/ftrace.h> #ifdef DEBUG #include <asm/udbg.h> @@ -155,11 +156,13 @@ static irqreturn_t reschedule_action(int irq, void *data) return IRQ_HANDLED; } +#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST static irqreturn_t tick_broadcast_ipi_action(int irq, void *data) { - tick_broadcast_ipi_handler(); + timer_broadcast_interrupt(); return IRQ_HANDLED; } +#endif #ifdef CONFIG_NMI_IPI static irqreturn_t nmi_ipi_action(int irq, void *data) @@ -172,7 +175,9 @@ static irqreturn_t nmi_ipi_action(int irq, void *data) static irq_handler_t smp_ipi_action[] = { [PPC_MSG_CALL_FUNCTION] = call_function_action, [PPC_MSG_RESCHEDULE] = reschedule_action, +#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST [PPC_MSG_TICK_BROADCAST] = tick_broadcast_ipi_action, +#endif #ifdef CONFIG_NMI_IPI [PPC_MSG_NMI_IPI] = nmi_ipi_action, #endif @@ -186,8 +191,12 @@ static irq_handler_t smp_ipi_action[] = { const char *smp_ipi_name[] = { [PPC_MSG_CALL_FUNCTION] = "ipi call function", [PPC_MSG_RESCHEDULE] = "ipi reschedule", +#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST [PPC_MSG_TICK_BROADCAST] = "ipi tick-broadcast", +#endif +#ifdef CONFIG_NMI_IPI [PPC_MSG_NMI_IPI] = "nmi ipi", +#endif }; /* optional function to request ipi, for controllers with >= 4 ipis */ @@ -277,8 +286,10 @@ irqreturn_t smp_ipi_demux_relaxed(void) generic_smp_call_function_interrupt(); if (all & IPI_MESSAGE(PPC_MSG_RESCHEDULE)) scheduler_ipi(); +#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST if (all & IPI_MESSAGE(PPC_MSG_TICK_BROADCAST)) - tick_broadcast_ipi_handler(); + timer_broadcast_interrupt(); +#endif #ifdef CONFIG_NMI_IPI if (all & IPI_MESSAGE(PPC_MSG_NMI_IPI)) nmi_ipi_action(0, NULL); @@ -419,9 +430,9 @@ out: return ret; } -static void do_smp_send_nmi_ipi(int cpu) +static void do_smp_send_nmi_ipi(int cpu, bool safe) { - if (smp_ops->cause_nmi_ipi && smp_ops->cause_nmi_ipi(cpu)) + if (!safe && smp_ops->cause_nmi_ipi && smp_ops->cause_nmi_ipi(cpu)) return; if (cpu >= 0) { @@ -461,7 +472,7 @@ void smp_flush_nmi_ipi(u64 delay_us) * - delay_us > 0 is the delay before giving up waiting for targets to * enter the handler, == 0 specifies indefinite delay. */ -int smp_send_nmi_ipi(int cpu, void (*fn)(struct pt_regs *), u64 delay_us) +int __smp_send_nmi_ipi(int cpu, void (*fn)(struct pt_regs *), u64 delay_us, bool safe) { unsigned long flags; int me = raw_smp_processor_id(); @@ -494,7 +505,7 @@ int smp_send_nmi_ipi(int cpu, void (*fn)(struct pt_regs *), u64 delay_us) nmi_ipi_busy_count++; nmi_ipi_unlock(); - do_smp_send_nmi_ipi(cpu); + do_smp_send_nmi_ipi(cpu, safe); while (!cpumask_empty(&nmi_ipi_pending_mask)) { udelay(1); @@ -516,6 +527,16 @@ int smp_send_nmi_ipi(int cpu, void (*fn)(struct pt_regs *), u64 delay_us) return ret; } + +int smp_send_nmi_ipi(int cpu, void (*fn)(struct pt_regs *), u64 delay_us) +{ + return __smp_send_nmi_ipi(cpu, fn, delay_us, false); +} + +int smp_send_safe_nmi_ipi(int cpu, void (*fn)(struct pt_regs *), u64 delay_us) +{ + return __smp_send_nmi_ipi(cpu, fn, delay_us, true); +} #endif /* CONFIG_NMI_IPI */ #ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST @@ -559,7 +580,7 @@ void crash_send_ipi(void (*crash_ipi_callback)(struct pt_regs *)) * entire NMI dance and waiting for * cpus to clear pending mask, etc. */ - do_smp_send_nmi_ipi(cpu); + do_smp_send_nmi_ipi(cpu, false); } } } @@ -1066,6 +1087,9 @@ void start_secondary(void *unused) local_irq_enable(); + /* We can enable ftrace for secondary cpus now */ + this_cpu_enable_ftrace(); + cpu_startup_entry(CPUHP_AP_ONLINE_IDLE); BUG(); @@ -1162,6 +1186,8 @@ int __cpu_disable(void) if (!smp_ops->cpu_disable) return -ENOSYS; + this_cpu_disable_ftrace(); + err = smp_ops->cpu_disable(); if (err) return err; @@ -1180,6 +1206,12 @@ void __cpu_die(unsigned int cpu) void cpu_die(void) { + /* + * Disable on the down path. This will be re-enabled by + * start_secondary() via start_secondary_resume() below + */ + this_cpu_disable_ftrace(); + if (ppc_md.cpu_die) ppc_md.cpu_die(); diff --git a/arch/powerpc/kernel/stacktrace.c b/arch/powerpc/kernel/stacktrace.c index d534ed901538..07e97f289c52 100644 --- a/arch/powerpc/kernel/stacktrace.c +++ b/arch/powerpc/kernel/stacktrace.c @@ -1,21 +1,27 @@ +// SPDX-License-Identifier: GPL-2.0 + /* - * Stack trace utility + * Stack trace utility functions etc. * * Copyright 2008 Christoph Hellwig, IBM Corp. - * - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. + * Copyright 2018 SUSE Linux GmbH + * Copyright 2018 Nick Piggin, Michael Ellerman, IBM Corp. */ #include <linux/export.h> +#include <linux/kallsyms.h> +#include <linux/module.h> +#include <linux/nmi.h> #include <linux/sched.h> #include <linux/sched/debug.h> +#include <linux/sched/task_stack.h> #include <linux/stacktrace.h> #include <asm/ptrace.h> #include <asm/processor.h> +#include <linux/ftrace.h> +#include <asm/kprobes.h> + +#include <asm/paca.h> /* * Save stack-backtrace addresses into a stack_trace buffer. @@ -76,3 +82,164 @@ save_stack_trace_regs(struct pt_regs *regs, struct stack_trace *trace) save_context_stack(trace, regs->gpr[1], current, 0); } EXPORT_SYMBOL_GPL(save_stack_trace_regs); + +#ifdef CONFIG_HAVE_RELIABLE_STACKTRACE +int +save_stack_trace_tsk_reliable(struct task_struct *tsk, + struct stack_trace *trace) +{ + unsigned long sp; + unsigned long stack_page = (unsigned long)task_stack_page(tsk); + unsigned long stack_end; + int graph_idx = 0; + + /* + * The last frame (unwinding first) may not yet have saved + * its LR onto the stack. + */ + int firstframe = 1; + + if (tsk == current) + sp = current_stack_pointer(); + else + sp = tsk->thread.ksp; + + stack_end = stack_page + THREAD_SIZE; + if (!is_idle_task(tsk)) { + /* + * For user tasks, this is the SP value loaded on + * kernel entry, see "PACAKSAVE(r13)" in _switch() and + * system_call_common()/EXCEPTION_PROLOG_COMMON(). + * + * Likewise for non-swapper kernel threads, + * this also happens to be the top of the stack + * as setup by copy_thread(). + * + * Note that stack backlinks are not properly setup by + * copy_thread() and thus, a forked task() will have + * an unreliable stack trace until it's been + * _switch()'ed to for the first time. + */ + stack_end -= STACK_FRAME_OVERHEAD + sizeof(struct pt_regs); + } else { + /* + * idle tasks have a custom stack layout, + * c.f. cpu_idle_thread_init(). + */ + stack_end -= STACK_FRAME_OVERHEAD; + } + + if (sp < stack_page + sizeof(struct thread_struct) || + sp > stack_end - STACK_FRAME_MIN_SIZE) { + return 1; + } + + for (;;) { + unsigned long *stack = (unsigned long *) sp; + unsigned long newsp, ip; + + /* sanity check: ABI requires SP to be aligned 16 bytes. */ + if (sp & 0xF) + return 1; + + /* Mark stacktraces with exception frames as unreliable. */ + if (sp <= stack_end - STACK_INT_FRAME_SIZE && + stack[STACK_FRAME_MARKER] == STACK_FRAME_REGS_MARKER) { + return 1; + } + + newsp = stack[0]; + /* Stack grows downwards; unwinder may only go up. */ + if (newsp <= sp) + return 1; + + if (newsp != stack_end && + newsp > stack_end - STACK_FRAME_MIN_SIZE) { + return 1; /* invalid backlink, too far up. */ + } + + /* Examine the saved LR: it must point into kernel code. */ + ip = stack[STACK_FRAME_LR_SAVE]; + if (!firstframe && !__kernel_text_address(ip)) + return 1; + firstframe = 0; + + /* + * FIXME: IMHO these tests do not belong in + * arch-dependent code, they are generic. + */ + ip = ftrace_graph_ret_addr(tsk, &graph_idx, ip, NULL); +#ifdef CONFIG_KPROBES + /* + * Mark stacktraces with kretprobed functions on them + * as unreliable. + */ + if (ip == (unsigned long)kretprobe_trampoline) + return 1; +#endif + + if (!trace->skip) + trace->entries[trace->nr_entries++] = ip; + else + trace->skip--; + + if (newsp == stack_end) + break; + + if (trace->nr_entries >= trace->max_entries) + return -E2BIG; + + sp = newsp; + } + return 0; +} +EXPORT_SYMBOL_GPL(save_stack_trace_tsk_reliable); +#endif /* CONFIG_HAVE_RELIABLE_STACKTRACE */ + +#ifdef CONFIG_PPC_BOOK3S_64 +static void handle_backtrace_ipi(struct pt_regs *regs) +{ + nmi_cpu_backtrace(regs); +} + +static void raise_backtrace_ipi(cpumask_t *mask) +{ + unsigned int cpu; + + for_each_cpu(cpu, mask) { + if (cpu == smp_processor_id()) + handle_backtrace_ipi(NULL); + else + smp_send_safe_nmi_ipi(cpu, handle_backtrace_ipi, 5 * USEC_PER_SEC); + } + + for_each_cpu(cpu, mask) { + struct paca_struct *p = paca_ptrs[cpu]; + + cpumask_clear_cpu(cpu, mask); + + pr_warn("CPU %d didn't respond to backtrace IPI, inspecting paca.\n", cpu); + if (!virt_addr_valid(p)) { + pr_warn("paca pointer appears corrupt? (%px)\n", p); + continue; + } + + pr_warn("irq_soft_mask: 0x%02x in_mce: %d in_nmi: %d", + p->irq_soft_mask, p->in_mce, p->in_nmi); + + if (virt_addr_valid(p->__current)) + pr_cont(" current: %d (%s)\n", p->__current->pid, + p->__current->comm); + else + pr_cont(" current pointer corrupt? (%px)\n", p->__current); + + pr_warn("Back trace of paca->saved_r1 (0x%016llx) (possibly stale):\n", p->saved_r1); + show_stack(p->__current, (unsigned long *)p->saved_r1); + } +} + +void arch_trigger_cpumask_backtrace(const cpumask_t *mask, bool exclude_self) +{ + nmi_trigger_cpumask_backtrace(mask, exclude_self, raise_backtrace_ipi); +} +#endif /* CONFIG_PPC64 */ diff --git a/arch/powerpc/kernel/sys_ppc32.c b/arch/powerpc/kernel/sys_ppc32.c index c11c73373691..bdf58ba1a94b 100644 --- a/arch/powerpc/kernel/sys_ppc32.c +++ b/arch/powerpc/kernel/sys_ppc32.c @@ -52,15 +52,6 @@ #include <asm/syscalls.h> #include <asm/switch_to.h> - -asmlinkage long ppc32_select(u32 n, compat_ulong_t __user *inp, - compat_ulong_t __user *outp, compat_ulong_t __user *exp, - compat_uptr_t tvp_x) -{ - /* sign extend n */ - return compat_sys_select((int)n, inp, outp, exp, compat_ptr(tvp_x)); -} - unsigned long compat_sys_mmap2(unsigned long addr, size_t len, unsigned long prot, unsigned long flags, unsigned long fd, unsigned long pgoff) diff --git a/arch/powerpc/kernel/syscalls.c b/arch/powerpc/kernel/syscalls.c index 466216506eb2..083fa06962fd 100644 --- a/arch/powerpc/kernel/syscalls.c +++ b/arch/powerpc/kernel/syscalls.c @@ -62,6 +62,9 @@ out: return ret; } +#pragma GCC diagnostic push +#pragma GCC diagnostic ignored "-Wpragmas" +#pragma GCC diagnostic ignored "-Wattribute-alias" SYSCALL_DEFINE6(mmap2, unsigned long, addr, size_t, len, unsigned long, prot, unsigned long, flags, unsigned long, fd, unsigned long, pgoff) @@ -75,6 +78,7 @@ SYSCALL_DEFINE6(mmap, unsigned long, addr, size_t, len, { return do_mmap2(addr, len, prot, flags, fd, offset, PAGE_SHIFT); } +#pragma GCC diagnostic pop #ifdef CONFIG_PPC32 /* diff --git a/arch/powerpc/kernel/systbl.S b/arch/powerpc/kernel/systbl.S index 7ccb7f81f8db..919a32746ede 100644 --- a/arch/powerpc/kernel/systbl.S +++ b/arch/powerpc/kernel/systbl.S @@ -35,7 +35,7 @@ #endif #define SYSCALL_SPU(func) SYSCALL(func) #define COMPAT_SYS_SPU(func) COMPAT_SYS(func) -#define PPC_SYS_SPU(func) PPC_SYS(func) +#define COMPAT_SPU_NEW(func) COMPAT_SYS(func) #define SYSX_SPU(f, f3264, f32) SYSX(f, f3264, f32) .section .rodata,"a" diff --git a/arch/powerpc/kernel/systbl_chk.c b/arch/powerpc/kernel/systbl_chk.c index 55323a620cfe..4653258722ac 100644 --- a/arch/powerpc/kernel/systbl_chk.c +++ b/arch/powerpc/kernel/systbl_chk.c @@ -31,7 +31,7 @@ #define SYSCALL_SPU(func) SYSCALL(func) #define COMPAT_SYS_SPU(func) COMPAT_SYS(func) -#define PPC_SYS_SPU(func) PPC_SYS(func) +#define COMPAT_SPU_NEW(func) COMPAT_SYS(_new##func) #define SYSX_SPU(f, f3264, f32) SYSX(f, f3264, f32) /* Just insert a marker for ni_syscalls */ diff --git a/arch/powerpc/kernel/systbl_chk.sh b/arch/powerpc/kernel/systbl_chk.sh index 31b6e7c358ca..f2e356c2a345 100644 --- a/arch/powerpc/kernel/systbl_chk.sh +++ b/arch/powerpc/kernel/systbl_chk.sh @@ -16,7 +16,7 @@ awk 'BEGIN { num = -1; } # Ignore the beginning of the file /^START_TABLE/ { num = 0; next; } /^END_TABLE/ { if (num != $2) { - printf "NR_syscalls (%s) is not one more than the last syscall (%s)\n", + printf "Error: NR_syscalls (%s) is not one more than the last syscall (%s)\n", $2, num - 1; exit(1); } @@ -25,7 +25,7 @@ awk 'BEGIN { num = -1; } # Ignore the beginning of the file { if (num == -1) next; if (($1 != -1) && ($1 != num)) { - printf "Syscall %s out of order (expected %s)\n", + printf "Error: Syscall %s out of order (expected %s)\n", $1, num; exit(1); }; diff --git a/arch/powerpc/kernel/tau_6xx.c b/arch/powerpc/kernel/tau_6xx.c index 8cdd852aedd1..e2ab8a111b69 100644 --- a/arch/powerpc/kernel/tau_6xx.c +++ b/arch/powerpc/kernel/tau_6xx.c @@ -27,6 +27,9 @@ #include <asm/cache.h> #include <asm/8xx_immap.h> #include <asm/machdep.h> +#include <asm/asm-prototypes.h> + +#include "setup.h" static struct tau_temp { @@ -50,7 +53,7 @@ struct timer_list tau_timer; #define shrink_timer 2*HZ /* period between shrinking the window */ #define min_window 2 /* minimum window size, degrees C */ -void set_thresholds(unsigned long cpu) +static void set_thresholds(unsigned long cpu) { #ifdef CONFIG_TAU_INT /* @@ -70,7 +73,7 @@ void set_thresholds(unsigned long cpu) #endif } -void TAUupdate(int cpu) +static void TAUupdate(int cpu) { unsigned thrm; @@ -205,7 +208,7 @@ static void tau_timeout_smp(struct timer_list *unused) int tau_initialized = 0; -void __init TAU_init_smp(void * info) +static void __init TAU_init_smp(void *info) { unsigned long cpu = smp_processor_id(); @@ -217,7 +220,7 @@ void __init TAU_init_smp(void * info) set_thresholds(cpu); } -int __init TAU_init(void) +static int __init TAU_init(void) { /* We assume in SMP that if one CPU has TAU support, they * all have it --BenH @@ -259,12 +262,12 @@ u32 cpu_temp_both(unsigned long cpu) return ((tau[cpu].high << 16) | tau[cpu].low); } -int cpu_temp(unsigned long cpu) +u32 cpu_temp(unsigned long cpu) { return ((tau[cpu].high + tau[cpu].low) / 2); } -int tau_interrupts(unsigned long cpu) +u32 tau_interrupts(unsigned long cpu) { return (tau[cpu].interrupts); } diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index 360e71d455cc..70f145e02487 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -163,12 +163,6 @@ EXPORT_SYMBOL(__cputime_usec_factor); void (*dtl_consumer)(struct dtl_entry *, u64); #endif -#ifdef CONFIG_PPC64 -#define get_accounting(tsk) (&get_paca()->accounting) -#else -#define get_accounting(tsk) (&task_thread_info(tsk)->accounting) -#endif - static void calc_cputime_factors(void) { struct div_result res; @@ -421,21 +415,6 @@ void vtime_flush(struct task_struct *tsk) acct->softirq_time = 0; } -#ifdef CONFIG_PPC32 -/* - * Called from the context switch with interrupts disabled, to charge all - * accumulated times to the current process, and to prepare accounting on - * the next process. - */ -void arch_vtime_task_switch(struct task_struct *prev) -{ - struct cpu_accounting_data *acct = get_accounting(current); - - acct->starttime = get_accounting(prev)->starttime; - acct->startspurr = get_accounting(prev)->startspurr; -} -#endif /* CONFIG_PPC32 */ - #else /* ! CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ #define calc_cputime_factors() #endif @@ -513,6 +492,35 @@ static inline void clear_irq_work_pending(void) "i" (offsetof(struct paca_struct, irq_work_pending))); } +void arch_irq_work_raise(void) +{ + preempt_disable(); + set_irq_work_pending_flag(); + /* + * Non-nmi code running with interrupts disabled will replay + * irq_happened before it re-enables interrupts, so setthe + * decrementer there instead of causing a hardware exception + * which would immediately hit the masked interrupt handler + * and have the net effect of setting the decrementer in + * irq_happened. + * + * NMI interrupts can not check this when they return, so the + * decrementer hardware exception is raised, which will fire + * when interrupts are next enabled. + * + * BookE does not support this yet, it must audit all NMI + * interrupt handlers to ensure they call nmi_enter() so this + * check would be correct. + */ + if (IS_ENABLED(CONFIG_BOOKE) || !irqs_disabled() || in_nmi()) { + set_dec(1); + } else { + hard_irq_disable(); + local_paca->irq_happened |= PACA_IRQ_DEC; + } + preempt_enable(); +} + #else /* 32-bit */ DEFINE_PER_CPU(u8, irq_work_pending); @@ -521,8 +529,6 @@ DEFINE_PER_CPU(u8, irq_work_pending); #define test_irq_work_pending() __this_cpu_read(irq_work_pending) #define clear_irq_work_pending() __this_cpu_write(irq_work_pending, 0) -#endif /* 32 vs 64 bit */ - void arch_irq_work_raise(void) { preempt_disable(); @@ -531,6 +537,8 @@ void arch_irq_work_raise(void) preempt_enable(); } +#endif /* 32 vs 64 bit */ + #else /* CONFIG_IRQ_WORK */ #define test_irq_work_pending() 0 @@ -538,60 +546,16 @@ void arch_irq_work_raise(void) #endif /* CONFIG_IRQ_WORK */ -static void __timer_interrupt(void) -{ - struct pt_regs *regs = get_irq_regs(); - u64 *next_tb = this_cpu_ptr(&decrementers_next_tb); - struct clock_event_device *evt = this_cpu_ptr(&decrementers); - u64 now; - - trace_timer_interrupt_entry(regs); - - if (test_irq_work_pending()) { - clear_irq_work_pending(); - irq_work_run(); - } - - now = get_tb_or_rtc(); - if (now >= *next_tb) { - *next_tb = ~(u64)0; - if (evt->event_handler) - evt->event_handler(evt); - __this_cpu_inc(irq_stat.timer_irqs_event); - } else { - now = *next_tb - now; - if (now <= decrementer_max) - set_dec(now); - /* We may have raced with new irq work */ - if (test_irq_work_pending()) - set_dec(1); - __this_cpu_inc(irq_stat.timer_irqs_others); - } - -#ifdef CONFIG_PPC64 - /* collect purr register values often, for accurate calculations */ - if (firmware_has_feature(FW_FEATURE_SPLPAR)) { - struct cpu_usage *cu = this_cpu_ptr(&cpu_usage_array); - cu->current_tb = mfspr(SPRN_PURR); - } -#endif - - trace_timer_interrupt_exit(regs); -} - /* * timer_interrupt - gets called when the decrementer overflows, * with interrupts disabled. */ -void timer_interrupt(struct pt_regs * regs) +void timer_interrupt(struct pt_regs *regs) { - struct pt_regs *old_regs; + struct clock_event_device *evt = this_cpu_ptr(&decrementers); u64 *next_tb = this_cpu_ptr(&decrementers_next_tb); - - /* Ensure a positive value is written to the decrementer, or else - * some CPUs will continue to take decrementer exceptions. - */ - set_dec(decrementer_max); + struct pt_regs *old_regs; + u64 now; /* Some implementations of hotplug will get timer interrupts while * offline, just ignore these and we also need to set @@ -599,11 +563,23 @@ void timer_interrupt(struct pt_regs * regs) * don't replay timer interrupt when return, otherwise we'll trap * here infinitely :( */ - if (!cpu_online(smp_processor_id())) { + if (unlikely(!cpu_online(smp_processor_id()))) { *next_tb = ~(u64)0; + set_dec(decrementer_max); return; } + /* Ensure a positive value is written to the decrementer, or else + * some CPUs will continue to take decrementer exceptions. When the + * PPC_WATCHDOG (decrementer based) is configured, keep this at most + * 31 bits, which is about 4 seconds on most systems, which gives + * the watchdog a chance of catching timer interrupt hard lockups. + */ + if (IS_ENABLED(CONFIG_PPC_WATCHDOG)) + set_dec(0x7fffffff); + else + set_dec(decrementer_max); + /* Conditionally hard-enable interrupts now that the DEC has been * bumped to its maximum value */ @@ -617,13 +593,46 @@ void timer_interrupt(struct pt_regs * regs) old_regs = set_irq_regs(regs); irq_enter(); + trace_timer_interrupt_entry(regs); + + if (test_irq_work_pending()) { + clear_irq_work_pending(); + irq_work_run(); + } + + now = get_tb_or_rtc(); + if (now >= *next_tb) { + *next_tb = ~(u64)0; + if (evt->event_handler) + evt->event_handler(evt); + __this_cpu_inc(irq_stat.timer_irqs_event); + } else { + now = *next_tb - now; + if (now <= decrementer_max) + set_dec(now); + /* We may have raced with new irq work */ + if (test_irq_work_pending()) + set_dec(1); + __this_cpu_inc(irq_stat.timer_irqs_others); + } - __timer_interrupt(); + trace_timer_interrupt_exit(regs); irq_exit(); set_irq_regs(old_regs); } EXPORT_SYMBOL(timer_interrupt); +#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST +void timer_broadcast_interrupt(void) +{ + u64 *next_tb = this_cpu_ptr(&decrementers_next_tb); + + *next_tb = ~(u64)0; + tick_receive_broadcast(); + __this_cpu_inc(irq_stat.broadcast_irqs_event); +} +#endif + /* * Hypervisor decrementer interrupts shouldn't occur but are sometimes * left pending on exit from a KVM guest. We don't need to do anything @@ -781,21 +790,19 @@ void __init generic_calibrate_decr(void) } } -int update_persistent_clock(struct timespec now) +int update_persistent_clock64(struct timespec64 now) { struct rtc_time tm; if (!ppc_md.set_rtc_time) return -ENODEV; - to_tm(now.tv_sec + 1 + timezone_offset, &tm); - tm.tm_year -= 1900; - tm.tm_mon -= 1; + rtc_time64_to_tm(now.tv_sec + 1 + timezone_offset, &tm); return ppc_md.set_rtc_time(&tm); } -static void __read_persistent_clock(struct timespec *ts) +static void __read_persistent_clock(struct timespec64 *ts) { struct rtc_time tm; static int first = 1; @@ -819,11 +826,10 @@ static void __read_persistent_clock(struct timespec *ts) } ppc_md.get_rtc_time(&tm); - ts->tv_sec = mktime(tm.tm_year+1900, tm.tm_mon+1, tm.tm_mday, - tm.tm_hour, tm.tm_min, tm.tm_sec); + ts->tv_sec = rtc_tm_to_time64(&tm); } -void read_persistent_clock(struct timespec *ts) +void read_persistent_clock64(struct timespec64 *ts) { __read_persistent_clock(ts); @@ -971,15 +977,6 @@ static int decrementer_shutdown(struct clock_event_device *dev) return 0; } -/* Interrupt handler for the timer broadcast IPI */ -void tick_broadcast_ipi_handler(void) -{ - u64 *next_tb = this_cpu_ptr(&decrementers_next_tb); - - *next_tb = get_tb_or_rtc(); - __timer_interrupt(); -} - static void register_decrementer_clockevent(int cpu) { struct clock_event_device *dec = &per_cpu(decrementers, cpu); @@ -1141,56 +1138,6 @@ void __init time_init(void) #endif } - -#define FEBRUARY 2 -#define STARTOFTIME 1970 -#define SECDAY 86400L -#define SECYR (SECDAY * 365) -#define leapyear(year) ((year) % 4 == 0 && \ - ((year) % 100 != 0 || (year) % 400 == 0)) -#define days_in_year(a) (leapyear(a) ? 366 : 365) -#define days_in_month(a) (month_days[(a) - 1]) - -static int month_days[12] = { - 31, 28, 31, 30, 31, 30, 31, 31, 30, 31, 30, 31 -}; - -void to_tm(int tim, struct rtc_time * tm) -{ - register int i; - register long hms, day; - - day = tim / SECDAY; - hms = tim % SECDAY; - - /* Hours, minutes, seconds are easy */ - tm->tm_hour = hms / 3600; - tm->tm_min = (hms % 3600) / 60; - tm->tm_sec = (hms % 3600) % 60; - - /* Number of years in days */ - for (i = STARTOFTIME; day >= days_in_year(i); i++) - day -= days_in_year(i); - tm->tm_year = i; - - /* Number of months in days left */ - if (leapyear(tm->tm_year)) - days_in_month(FEBRUARY) = 29; - for (i = 1; day >= days_in_month(i); i++) - day -= days_in_month(i); - days_in_month(FEBRUARY) = 28; - tm->tm_mon = i; - - /* Days are what is left over (+1) from all that. */ - tm->tm_mday = day + 1; - - /* - * No-one uses the day of the week. - */ - tm->tm_wday = -1; -} -EXPORT_SYMBOL(to_tm); - /* * Divide a 128-bit dividend by a 32-bit divisor, leaving a 128 bit * result. diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S index b92ac8e711db..ff12f47a96b6 100644 --- a/arch/powerpc/kernel/tm.S +++ b/arch/powerpc/kernel/tm.S @@ -12,6 +12,7 @@ #include <asm/ptrace.h> #include <asm/reg.h> #include <asm/bug.h> +#include <asm/export.h> #ifdef CONFIG_VSX /* See fpu.S, this is borrowed from there */ @@ -55,6 +56,16 @@ _GLOBAL(tm_enable) or r4, r4, r3 mtmsrd r4 1: blr +EXPORT_SYMBOL_GPL(tm_enable); + +_GLOBAL(tm_disable) + mfmsr r4 + li r3, MSR_TM >> 32 + sldi r3, r3, 32 + andc r4, r4, r3 + mtmsrd r4 + blr +EXPORT_SYMBOL_GPL(tm_disable); _GLOBAL(tm_save_sprs) mfspr r0, SPRN_TFHAR @@ -78,6 +89,7 @@ _GLOBAL(tm_restore_sprs) _GLOBAL(tm_abort) TABORT(R3) blr +EXPORT_SYMBOL_GPL(tm_abort); /* void tm_reclaim(struct thread_struct *thread, * uint8_t cause) diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c index 4741fe112f05..c076a32093fd 100644 --- a/arch/powerpc/kernel/trace/ftrace.c +++ b/arch/powerpc/kernel/trace/ftrace.c @@ -357,6 +357,8 @@ __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) { unsigned int op[2]; void *ip = (void *)rec->ip; + unsigned long entry, ptr, tramp; + struct module *mod = rec->arch.mod; /* read where this goes */ if (probe_kernel_read(op, ip, sizeof(op))) @@ -368,19 +370,44 @@ __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) return -EINVAL; } - /* If we never set up a trampoline to ftrace_caller, then bail */ - if (!rec->arch.mod->arch.tramp) { + /* If we never set up ftrace trampoline(s), then bail */ +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS + if (!mod->arch.tramp || !mod->arch.tramp_regs) { +#else + if (!mod->arch.tramp) { +#endif pr_err("No ftrace trampoline\n"); return -EINVAL; } +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS + if (rec->flags & FTRACE_FL_REGS) + tramp = mod->arch.tramp_regs; + else +#endif + tramp = mod->arch.tramp; + + if (module_trampoline_target(mod, tramp, &ptr)) { + pr_err("Failed to get trampoline target\n"); + return -EFAULT; + } + + pr_devel("trampoline target %lx", ptr); + + entry = ppc_global_function_entry((void *)addr); + /* This should match what was called */ + if (ptr != entry) { + pr_err("addr %lx does not match expected %lx\n", ptr, entry); + return -EINVAL; + } + /* Ensure branch is within 24 bits */ - if (!create_branch(ip, rec->arch.mod->arch.tramp, BRANCH_SET_LINK)) { + if (!create_branch(ip, tramp, BRANCH_SET_LINK)) { pr_err("Branch out of range\n"); return -EINVAL; } - if (patch_branch(ip, rec->arch.mod->arch.tramp, BRANCH_SET_LINK)) { + if (patch_branch(ip, tramp, BRANCH_SET_LINK)) { pr_err("REL24 out of range!\n"); return -EINVAL; } @@ -388,14 +415,6 @@ __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) return 0; } -#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS -int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, - unsigned long addr) -{ - return ftrace_make_call(rec, addr); -} -#endif - #else /* !CONFIG_PPC64: */ static int __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) @@ -472,53 +491,158 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) #endif /* CONFIG_MODULES */ } -int ftrace_update_ftrace_func(ftrace_func_t func) +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS +#ifdef CONFIG_MODULES +static int +__ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, + unsigned long addr) { - unsigned long ip = (unsigned long)(&ftrace_call); - unsigned int old, new; - int ret; + unsigned int op; + unsigned long ip = rec->ip; + unsigned long entry, ptr, tramp; + struct module *mod = rec->arch.mod; - old = *(unsigned int *)&ftrace_call; - new = ftrace_call_replace(ip, (unsigned long)func, 1); - ret = ftrace_modify_code(ip, old, new); + /* If we never set up ftrace trampolines, then bail */ + if (!mod->arch.tramp || !mod->arch.tramp_regs) { + pr_err("No ftrace trampoline\n"); + return -EINVAL; + } - return ret; -} + /* read where this goes */ + if (probe_kernel_read(&op, (void *)ip, sizeof(int))) { + pr_err("Fetching opcode failed.\n"); + return -EFAULT; + } -static int __ftrace_replace_code(struct dyn_ftrace *rec, int enable) -{ - unsigned long ftrace_addr = (unsigned long)FTRACE_ADDR; - int ret; + /* Make sure that that this is still a 24bit jump */ + if (!is_bl_op(op)) { + pr_err("Not expected bl: opcode is %x\n", op); + return -EINVAL; + } + + /* lets find where the pointer goes */ + tramp = find_bl_target(ip, op); + entry = ppc_global_function_entry((void *)old_addr); + + pr_devel("ip:%lx jumps to %lx", ip, tramp); - ret = ftrace_update_record(rec, enable); + if (tramp != entry) { + /* old_addr is not within range, so we must have used a trampoline */ + if (module_trampoline_target(mod, tramp, &ptr)) { + pr_err("Failed to get trampoline target\n"); + return -EFAULT; + } + + pr_devel("trampoline target %lx", ptr); + + /* This should match what was called */ + if (ptr != entry) { + pr_err("addr %lx does not match expected %lx\n", ptr, entry); + return -EINVAL; + } + } + + /* The new target may be within range */ + if (test_24bit_addr(ip, addr)) { + /* within range */ + if (patch_branch((unsigned int *)ip, addr, BRANCH_SET_LINK)) { + pr_err("REL24 out of range!\n"); + return -EINVAL; + } - switch (ret) { - case FTRACE_UPDATE_IGNORE: return 0; - case FTRACE_UPDATE_MAKE_CALL: - return ftrace_make_call(rec, ftrace_addr); - case FTRACE_UPDATE_MAKE_NOP: - return ftrace_make_nop(NULL, rec, ftrace_addr); + } + + if (rec->flags & FTRACE_FL_REGS) + tramp = mod->arch.tramp_regs; + else + tramp = mod->arch.tramp; + + if (module_trampoline_target(mod, tramp, &ptr)) { + pr_err("Failed to get trampoline target\n"); + return -EFAULT; + } + + pr_devel("trampoline target %lx", ptr); + + entry = ppc_global_function_entry((void *)addr); + /* This should match what was called */ + if (ptr != entry) { + pr_err("addr %lx does not match expected %lx\n", ptr, entry); + return -EINVAL; + } + + /* Ensure branch is within 24 bits */ + if (!create_branch((unsigned int *)ip, tramp, BRANCH_SET_LINK)) { + pr_err("Branch out of range\n"); + return -EINVAL; + } + + if (patch_branch((unsigned int *)ip, tramp, BRANCH_SET_LINK)) { + pr_err("REL24 out of range!\n"); + return -EINVAL; } return 0; } +#endif -void ftrace_replace_code(int enable) +int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, + unsigned long addr) { - struct ftrace_rec_iter *iter; - struct dyn_ftrace *rec; + unsigned long ip = rec->ip; + unsigned int old, new; + + /* + * If the calling address is more that 24 bits away, + * then we had to use a trampoline to make the call. + * Otherwise just update the call site. + */ + if (test_24bit_addr(ip, addr) && test_24bit_addr(ip, old_addr)) { + /* within range */ + old = ftrace_call_replace(ip, old_addr, 1); + new = ftrace_call_replace(ip, addr, 1); + return ftrace_modify_code(ip, old, new); + } + +#ifdef CONFIG_MODULES + /* + * Out of range jumps are called from modules. + */ + if (!rec->arch.mod) { + pr_err("No module loaded\n"); + return -EINVAL; + } + + return __ftrace_modify_call(rec, old_addr, addr); +#else + /* We should not get here without modules */ + return -EINVAL; +#endif /* CONFIG_MODULES */ +} +#endif + +int ftrace_update_ftrace_func(ftrace_func_t func) +{ + unsigned long ip = (unsigned long)(&ftrace_call); + unsigned int old, new; int ret; - for (iter = ftrace_rec_iter_start(); iter; - iter = ftrace_rec_iter_next(iter)) { - rec = ftrace_rec_iter_record(iter); - ret = __ftrace_replace_code(rec, enable); - if (ret) { - ftrace_bug(ret, rec); - return; - } + old = *(unsigned int *)&ftrace_call; + new = ftrace_call_replace(ip, (unsigned long)func, 1); + ret = ftrace_modify_code(ip, old, new); + +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS + /* Also update the regs callback function */ + if (!ret) { + ip = (unsigned long)(&ftrace_regs_call); + old = *(unsigned int *)&ftrace_regs_call; + new = ftrace_call_replace(ip, (unsigned long)func, 1); + ret = ftrace_modify_code(ip, old, new); } +#endif + + return ret; } /* @@ -538,7 +662,6 @@ int __init ftrace_dyn_arch_init(void) #ifdef CONFIG_FUNCTION_GRAPH_TRACER -#ifdef CONFIG_DYNAMIC_FTRACE extern void ftrace_graph_call(void); extern void ftrace_graph_stub(void); @@ -567,7 +690,6 @@ int ftrace_disable_ftrace_graph_caller(void) return ftrace_modify_code(ip, old, new); } -#endif /* CONFIG_DYNAMIC_FTRACE */ /* * Hook the return address and push it in the stack of return addrs diff --git a/arch/powerpc/kernel/trace/ftrace_32.S b/arch/powerpc/kernel/trace/ftrace_32.S index afef2c076282..2c29098f630f 100644 --- a/arch/powerpc/kernel/trace/ftrace_32.S +++ b/arch/powerpc/kernel/trace/ftrace_32.S @@ -14,7 +14,6 @@ #include <asm/ftrace.h> #include <asm/export.h> -#ifdef CONFIG_DYNAMIC_FTRACE _GLOBAL(mcount) _GLOBAL(_mcount) /* @@ -47,26 +46,7 @@ _GLOBAL(ftrace_graph_stub) MCOUNT_RESTORE_FRAME /* old link register ends up in ctr reg */ bctr -#else -_GLOBAL(mcount) -_GLOBAL(_mcount) - - MCOUNT_SAVE_FRAME - subi r3, r3, MCOUNT_INSN_SIZE - LOAD_REG_ADDR(r5, ftrace_trace_function) - lwz r5,0(r5) - - mtctr r5 - bctrl - nop - -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - b ftrace_graph_caller -#endif - MCOUNT_RESTORE_FRAME - bctr -#endif EXPORT_SYMBOL(_mcount) _GLOBAL(ftrace_stub) diff --git a/arch/powerpc/kernel/trace/ftrace_64.S b/arch/powerpc/kernel/trace/ftrace_64.S index e5ccea19821e..e25f77c10a72 100644 --- a/arch/powerpc/kernel/trace/ftrace_64.S +++ b/arch/powerpc/kernel/trace/ftrace_64.S @@ -14,7 +14,6 @@ #include <asm/ppc-opcode.h> #include <asm/export.h> -#ifdef CONFIG_DYNAMIC_FTRACE _GLOBAL(mcount) _GLOBAL(_mcount) EXPORT_SYMBOL(_mcount) @@ -23,34 +22,6 @@ EXPORT_SYMBOL(_mcount) mtlr r0 bctr -#else /* CONFIG_DYNAMIC_FTRACE */ -_GLOBAL_TOC(_mcount) -EXPORT_SYMBOL(_mcount) - /* Taken from output of objdump from lib64/glibc */ - mflr r3 - ld r11, 0(r1) - stdu r1, -112(r1) - std r3, 128(r1) - ld r4, 16(r11) - - subi r3, r3, MCOUNT_INSN_SIZE - LOAD_REG_ADDR(r5,ftrace_trace_function) - ld r5,0(r5) - ld r5,0(r5) - mtctr r5 - bctrl - nop - -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - b ftrace_graph_caller -#endif - ld r0, 128(r1) - mtlr r0 - addi r1, r1, 112 -_GLOBAL(ftrace_stub) - blr -#endif /* CONFIG_DYNAMIC_FTRACE */ - #ifdef CONFIG_FUNCTION_GRAPH_TRACER _GLOBAL(return_to_handler) /* need to save return values */ diff --git a/arch/powerpc/kernel/trace/ftrace_64_mprofile.S b/arch/powerpc/kernel/trace/ftrace_64_mprofile.S index 3f3e81852422..9a5b5a513604 100644 --- a/arch/powerpc/kernel/trace/ftrace_64_mprofile.S +++ b/arch/powerpc/kernel/trace/ftrace_64_mprofile.S @@ -17,11 +17,10 @@ #include <asm/bug.h> #include <asm/ptrace.h> -#ifdef CONFIG_DYNAMIC_FTRACE /* * - * ftrace_caller() is the function that replaces _mcount() when ftrace is - * active. + * ftrace_caller()/ftrace_regs_caller() is the function that replaces _mcount() + * when ftrace is active. * * We arrive here after a function A calls function B, and we are the trace * function for B. When we enter r1 points to A's stack frame, B has not yet @@ -37,7 +36,7 @@ * Our job is to save the register state into a struct pt_regs (on the stack) * and then arrange for the ftrace function to be called. */ -_GLOBAL(ftrace_caller) +_GLOBAL(ftrace_regs_caller) /* Save the original return address in A's stack frame */ std r0,LRSAVE(r1) @@ -47,6 +46,12 @@ _GLOBAL(ftrace_caller) /* Save all gprs to pt_regs */ SAVE_GPR(0, r1) SAVE_10GPRS(2, r1) + + /* Ok to continue? */ + lbz r3, PACA_FTRACE_ENABLED(r13) + cmpdi r3, 0 + beq ftrace_no_trace + SAVE_10GPRS(12, r1) SAVE_10GPRS(22, r1) @@ -94,8 +99,8 @@ _GLOBAL(ftrace_caller) addi r6, r1 ,STACK_FRAME_OVERHEAD /* ftrace_call(r3, r4, r5, r6) */ -.globl ftrace_call -ftrace_call: +.globl ftrace_regs_call +ftrace_regs_call: bl ftrace_stub nop @@ -156,6 +161,7 @@ ftrace_call: bne- livepatch_handler #endif +ftrace_caller_common: #ifdef CONFIG_FUNCTION_GRAPH_TRACER .globl ftrace_graph_call ftrace_graph_call: @@ -168,6 +174,74 @@ _GLOBAL(ftrace_graph_stub) _GLOBAL(ftrace_stub) blr +ftrace_no_trace: + mflr r3 + mtctr r3 + REST_GPR(3, r1) + addi r1, r1, SWITCH_FRAME_SIZE + mtlr r0 + bctr + +_GLOBAL(ftrace_caller) + /* Save the original return address in A's stack frame */ + std r0, LRSAVE(r1) + + /* Create our stack frame + pt_regs */ + stdu r1, -SWITCH_FRAME_SIZE(r1) + + /* Save all gprs to pt_regs */ + SAVE_8GPRS(3, r1) + + lbz r3, PACA_FTRACE_ENABLED(r13) + cmpdi r3, 0 + beq ftrace_no_trace + + /* Get the _mcount() call site out of LR */ + mflr r7 + std r7, _NIP(r1) + + /* Save callee's TOC in the ABI compliant location */ + std r2, 24(r1) + ld r2, PACATOC(r13) /* get kernel TOC in r2 */ + + addis r3, r2, function_trace_op@toc@ha + addi r3, r3, function_trace_op@toc@l + ld r5, 0(r3) + + /* Calculate ip from nip-4 into r3 for call below */ + subi r3, r7, MCOUNT_INSN_SIZE + + /* Put the original return address in r4 as parent_ip */ + mr r4, r0 + + /* Set pt_regs to NULL */ + li r6, 0 + + /* ftrace_call(r3, r4, r5, r6) */ +.globl ftrace_call +ftrace_call: + bl ftrace_stub + nop + + ld r3, _NIP(r1) + mtctr r3 + + /* Restore gprs */ + REST_8GPRS(3,r1) + + /* Restore callee's TOC */ + ld r2, 24(r1) + + /* Pop our stack frame */ + addi r1, r1, SWITCH_FRAME_SIZE + + /* Reload original LR */ + ld r0, LRSAVE(r1) + mtlr r0 + + /* Handle function_graph or go back */ + b ftrace_caller_common + #ifdef CONFIG_LIVEPATCH /* * This function runs in the mcount context, between two functions. As @@ -236,8 +310,6 @@ livepatch_handler: blr #endif /* CONFIG_LIVEPATCH */ -#endif /* CONFIG_DYNAMIC_FTRACE */ - #ifdef CONFIG_FUNCTION_GRAPH_TRACER _GLOBAL(ftrace_graph_caller) stdu r1, -112(r1) diff --git a/arch/powerpc/kernel/trace/ftrace_64_pg.S b/arch/powerpc/kernel/trace/ftrace_64_pg.S index f095358da96e..4c515c4023de 100644 --- a/arch/powerpc/kernel/trace/ftrace_64_pg.S +++ b/arch/powerpc/kernel/trace/ftrace_64_pg.S @@ -14,8 +14,11 @@ #include <asm/ppc-opcode.h> #include <asm/export.h> -#ifdef CONFIG_DYNAMIC_FTRACE _GLOBAL_TOC(ftrace_caller) + lbz r3, PACA_FTRACE_ENABLED(r13) + cmpdi r3, 0 + beqlr + /* Taken from output of objdump from lib64/glibc */ mflr r3 ld r11, 0(r1) @@ -39,7 +42,6 @@ _GLOBAL(ftrace_graph_stub) _GLOBAL(ftrace_stub) blr -#endif /* CONFIG_DYNAMIC_FTRACE */ #ifdef CONFIG_FUNCTION_GRAPH_TRACER _GLOBAL(ftrace_graph_caller) diff --git a/arch/powerpc/kernel/vdso32/Makefile b/arch/powerpc/kernel/vdso32/Makefile index b8c434d1d459..50112d4473bb 100644 --- a/arch/powerpc/kernel/vdso32/Makefile +++ b/arch/powerpc/kernel/vdso32/Makefile @@ -8,8 +8,15 @@ obj-vdso32 = sigtramp.o gettimeofday.o datapage.o cacheflush.o note.o \ # Build rules -ifeq ($(CONFIG_PPC32),y) -CROSS32CC := $(CC) +ifdef CROSS32_COMPILE + VDSOCC := $(CROSS32_COMPILE)gcc +else + VDSOCC := $(CC) +endif + +CC32FLAGS := +ifdef CONFIG_PPC64 +CC32FLAGS += -m32 endif targets := $(obj-vdso32) vdso32.so vdso32.so.dbg @@ -45,9 +52,9 @@ $(obj-vdso32): %.o: %.S FORCE # actual build commands quiet_cmd_vdso32ld = VDSO32L $@ - cmd_vdso32ld = $(CROSS32CC) $(c_flags) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^) + cmd_vdso32ld = $(VDSOCC) $(c_flags) $(CC32FLAGS) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^) quiet_cmd_vdso32as = VDSO32A $@ - cmd_vdso32as = $(CROSS32CC) $(a_flags) -c -o $@ $< + cmd_vdso32as = $(VDSOCC) $(a_flags) $(CC32FLAGS) -c -o $@ $< # install commands for the unstripped file quiet_cmd_vdso_install = INSTALL $@ diff --git a/arch/powerpc/kernel/vecemu.c b/arch/powerpc/kernel/vecemu.c index 8812085883fd..4acd3fb2b38e 100644 --- a/arch/powerpc/kernel/vecemu.c +++ b/arch/powerpc/kernel/vecemu.c @@ -8,6 +8,7 @@ #include <linux/sched.h> #include <asm/ptrace.h> #include <asm/processor.h> +#include <asm/switch_to.h> #include <linux/uaccess.h> /* Functions in vector.S */ diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index dd10e6f1d1b7..5baac79df97e 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -153,6 +153,13 @@ SECTIONS *(__rfi_flush_fixup) __stop___rfi_flush_fixup = .; } + + . = ALIGN(8); + __spec_barrier_fixup : AT(ADDR(__spec_barrier_fixup) - LOAD_OFFSET) { + __start___barrier_nospec_fixup = .; + *(__barrier_nospec_fixup) + __stop___barrier_nospec_fixup = .; + } #endif EXCEPTION_TABLE(0) diff --git a/arch/powerpc/kernel/watchdog.c b/arch/powerpc/kernel/watchdog.c index 6256dc3b0087..1d82274f7e9f 100644 --- a/arch/powerpc/kernel/watchdog.c +++ b/arch/powerpc/kernel/watchdog.c @@ -64,7 +64,7 @@ * means the CPU(s) with their bit still set in the pending mask have had * their heartbeat stop, and action is taken. * - * Some platforms implement true NMI IPIs, which can by used by the SMP + * Some platforms implement true NMI IPIs, which can be used by the SMP * watchdog to detect an unresponsive CPU and pull it out of its stuck * state with the NMI IPI, to get crash/debug data from it. This way the * SMP watchdog can detect hardware interrupts off lockups. @@ -111,7 +111,13 @@ static inline void wd_smp_unlock(unsigned long *flags) static void wd_lockup_ipi(struct pt_regs *regs) { - pr_emerg("CPU %d Hard LOCKUP\n", raw_smp_processor_id()); + int cpu = raw_smp_processor_id(); + u64 tb = get_tb(); + + pr_emerg("CPU %d Hard LOCKUP\n", cpu); + pr_emerg("CPU %d TB:%lld, last heartbeat TB:%lld (%lldms ago)\n", + cpu, tb, per_cpu(wd_timer_tb, cpu), + tb_to_ns(tb - per_cpu(wd_timer_tb, cpu)) / 1000000); print_modules(); print_irqtrace_events(current); if (regs) @@ -154,6 +160,9 @@ static void watchdog_smp_panic(int cpu, u64 tb) pr_emerg("CPU %d detected hard LOCKUP on other CPUs %*pbl\n", cpu, cpumask_pr_args(&wd_smp_cpus_pending)); + pr_emerg("CPU %d TB:%lld, last SMP heartbeat TB:%lld (%lldms ago)\n", + cpu, tb, wd_smp_last_reset_tb, + tb_to_ns(tb - wd_smp_last_reset_tb) / 1000000); if (!sysctl_hardlockup_all_cpu_backtrace) { /* @@ -194,10 +203,19 @@ static void wd_smp_clear_cpu_pending(int cpu, u64 tb) { if (!cpumask_test_cpu(cpu, &wd_smp_cpus_pending)) { if (unlikely(cpumask_test_cpu(cpu, &wd_smp_cpus_stuck))) { + struct pt_regs *regs = get_irq_regs(); unsigned long flags; - pr_emerg("CPU %d became unstuck\n", cpu); wd_smp_lock(&flags); + + pr_emerg("CPU %d became unstuck TB:%lld\n", + cpu, tb); + print_irqtrace_events(current); + if (regs) + show_regs(regs); + else + dump_stack(); + cpumask_clear_cpu(cpu, &wd_smp_cpus_stuck); wd_smp_unlock(&flags); } @@ -245,8 +263,6 @@ void soft_nmi_interrupt(struct pt_regs *regs) tb = get_tb(); if (tb - per_cpu(wd_timer_tb, cpu) >= wd_panic_timeout_tb) { - per_cpu(wd_timer_tb, cpu) = tb; - wd_smp_lock(&flags); if (cpumask_test_cpu(cpu, &wd_smp_cpus_stuck)) { wd_smp_unlock(&flags); @@ -254,7 +270,11 @@ void soft_nmi_interrupt(struct pt_regs *regs) } set_cpu_stuck(cpu, tb); - pr_emerg("CPU %d self-detected hard LOCKUP @ %pS\n", cpu, (void *)regs->nip); + pr_emerg("CPU %d self-detected hard LOCKUP @ %pS\n", + cpu, (void *)regs->nip); + pr_emerg("CPU %d TB:%lld, last heartbeat TB:%lld (%lldms ago)\n", + cpu, tb, per_cpu(wd_timer_tb, cpu), + tb_to_ns(tb - per_cpu(wd_timer_tb, cpu)) / 1000000); print_modules(); print_irqtrace_events(current); show_regs(regs); |