diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2018-02-02 21:01:04 +0300 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2018-02-02 21:01:04 +0300 |
| commit | 03f51d4efa2287cc628bb20b0c032036d2a9e66a (patch) | |
| tree | ec7fb3b6624d53092e2768578f3ef887c8d77f22 /arch/powerpc/kernel | |
| parent | 367b0df173b0ebea5d18b6971c244e260b5feb17 (diff) | |
| parent | 015eb1b89e959c9349f0a01803fb8ed1ced36f09 (diff) | |
| download | linux-03f51d4efa2287cc628bb20b0c032036d2a9e66a.tar.xz | |
Merge tag 'powerpc-4.16-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux
Pull powerpc updates from Michael Ellerman:
"Highlights:
- Enable support for memory protection keys aka "pkeys" on Power7/8/9
when using the hash table MMU.
- Extend our interrupt soft masking to support masking PMU interrupts
as well as "normal" interrupts, and then use that to implement
local_t for a ~4x speedup vs the current atomics-based
implementation.
- A new driver "ocxl" for "Open Coherent Accelerator Processor
Interface (OpenCAPI)" devices.
- Support for new device tree properties on PowerVM to describe
hotpluggable memory and devices.
- Add support for CLOCK_{REALTIME/MONOTONIC}_COARSE to the 64-bit
VDSO.
- Freescale updates from Scott: fixes for CPM GPIO and an FSL PCI
erratum workaround, plus a minor cleanup patch.
As well as quite a lot of other changes all over the place, and small
fixes and cleanups as always.
Thanks to: Alan Modra, Alastair D'Silva, Alexey Kardashevskiy,
Alistair Popple, Andreas Schwab, Andrew Donnellan, Aneesh Kumar K.V,
Anju T Sudhakar, Anshuman Khandual, Anton Blanchard, Arnd Bergmann,
Balbir Singh, Benjamin Herrenschmidt, Bhaktipriya Shridhar, Bryant G.
Ly, Cédric Le Goater, Christophe Leroy, Christophe Lombard, Cyril Bur,
David Gibson, Desnes A. Nunes do Rosario, Dmitry Torokhov, Frederic
Barrat, Geert Uytterhoeven, Guilherme G. Piccoli, Gustavo A. R. Silva,
Gustavo Romero, Ivan Mikhaylov, Joakim Tjernlund, Joe Perches, Josh
Poimboeuf, Juan J. Alvarez, Julia Cartwright, Kamalesh Babulal,
Madhavan Srinivasan, Mahesh Salgaonkar, Mathieu Malaterre, Michael
Bringmann, Michael Hanselmann, Michael Neuling, Nathan Fontenot,
Naveen N. Rao, Nicholas Piggin, Paul Mackerras, Philippe Bergheaud,
Ram Pai, Russell Currey, Santosh Sivaraj, Scott Wood, Seth Forshee,
Simon Guo, Stewart Smith, Sukadev Bhattiprolu, Thiago Jung Bauermann,
Vaibhav Jain, Vasyl Gomonovych"
* tag 'powerpc-4.16-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (199 commits)
powerpc/mm/radix: Fix build error when RADIX_MMU=n
macintosh/ams-input: Use true and false for boolean values
macintosh: change some data types from int to bool
powerpc/watchdog: Print the NIP in soft_nmi_interrupt()
powerpc/watchdog: regs can't be null in soft_nmi_interrupt()
powerpc/watchdog: Tweak watchdog printks
powerpc/cell: Remove axonram driver
rtc-opal: Fix handling of firmware error codes, prevent busy loops
powerpc/mpc52xx_gpt: make use of raw_spinlock variants
macintosh/adb: Properly mark continued kernel messages
powerpc/pseries: Fix cpu hotplug crash with memoryless nodes
powerpc/numa: Ensure nodes initialized for hotplug
powerpc/numa: Use ibm,max-associativity-domains to discover possible nodes
powerpc/kernel: Block interrupts when updating TIDR
powerpc/powernv/idoa: Remove unnecessary pcidev from pci_dn
powerpc/mm/nohash: do not flush the entire mm when range is a single page
powerpc/pseries: Add Initialization of VF Bars
powerpc/pseries/pci: Associate PEs to VFs in configure SR-IOV
powerpc/eeh: Add EEH notify resume sysfs
powerpc/eeh: Add EEH operations to notify resume
...
Diffstat (limited to 'arch/powerpc/kernel')
46 files changed, 980 insertions, 747 deletions
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index f390d57cf2e1..88b84ac76b53 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -178,7 +178,7 @@ int main(void) OFFSET(PACATOC, paca_struct, kernel_toc); OFFSET(PACAKBASE, paca_struct, kernelbase); OFFSET(PACAKMSR, paca_struct, kernel_msr); - OFFSET(PACASOFTIRQEN, paca_struct, soft_enabled); + OFFSET(PACAIRQSOFTMASK, paca_struct, irq_soft_mask); OFFSET(PACAIRQHAPPENED, paca_struct, irq_happened); #ifdef CONFIG_PPC_BOOK3S OFFSET(PACACONTEXTID, paca_struct, mm_ctx_id); @@ -239,8 +239,7 @@ int main(void) OFFSET(PACA_IN_NMI, paca_struct, in_nmi); OFFSET(PACA_RFI_FLUSH_FALLBACK_AREA, paca_struct, rfi_flush_fallback_area); OFFSET(PACA_EXRFI, paca_struct, exrfi); - OFFSET(PACA_L1D_FLUSH_CONGRUENCE, paca_struct, l1d_flush_congruence); - OFFSET(PACA_L1D_FLUSH_SETS, paca_struct, l1d_flush_sets); + OFFSET(PACA_L1D_FLUSH_SIZE, paca_struct, l1d_flush_size); #endif OFFSET(PACAHWCPUID, paca_struct, hw_cpu_id); @@ -401,6 +400,8 @@ int main(void) /* Other bits used by the vdso */ DEFINE(CLOCK_REALTIME, CLOCK_REALTIME); DEFINE(CLOCK_MONOTONIC, CLOCK_MONOTONIC); + DEFINE(CLOCK_REALTIME_COARSE, CLOCK_REALTIME_COARSE); + DEFINE(CLOCK_MONOTONIC_COARSE, CLOCK_MONOTONIC_COARSE); DEFINE(NSEC_PER_SEC, NSEC_PER_SEC); DEFINE(CLOCK_REALTIME_RES, MONOTONIC_RES_NSEC); diff --git a/arch/powerpc/kernel/cpu_setup_power.S b/arch/powerpc/kernel/cpu_setup_power.S index 679bbe714e85..3f30c994e931 100644 --- a/arch/powerpc/kernel/cpu_setup_power.S +++ b/arch/powerpc/kernel/cpu_setup_power.S @@ -31,7 +31,6 @@ _GLOBAL(__setup_cpu_power7) mfspr r3,SPRN_LPCR li r4,(LPCR_LPES1 >> LPCR_LPES_SH) bl __init_LPCR_ISA206 - bl __init_tlb_power7 mtlr r11 blr @@ -45,7 +44,6 @@ _GLOBAL(__restore_cpu_power7) mfspr r3,SPRN_LPCR li r4,(LPCR_LPES1 >> LPCR_LPES_SH) bl __init_LPCR_ISA206 - bl __init_tlb_power7 mtlr r11 blr @@ -64,7 +62,6 @@ _GLOBAL(__setup_cpu_power8) li r4,0 /* LPES = 0 */ bl __init_LPCR_ISA206 bl __init_HFSCR - bl __init_tlb_power8 bl __init_PMU_HV bl __init_PMU_HV_ISA207 mtlr r11 @@ -86,7 +83,6 @@ _GLOBAL(__restore_cpu_power8) li r4,0 /* LPES = 0 */ bl __init_LPCR_ISA206 bl __init_HFSCR - bl __init_tlb_power8 bl __init_PMU_HV bl __init_PMU_HV_ISA207 mtlr r11 @@ -111,7 +107,6 @@ _GLOBAL(__setup_cpu_power9) li r4,0 /* LPES = 0 */ bl __init_LPCR_ISA300 bl __init_HFSCR - bl __init_tlb_power9 bl __init_PMU_HV mtlr r11 blr @@ -136,7 +131,6 @@ _GLOBAL(__restore_cpu_power9) li r4,0 /* LPES = 0 */ bl __init_LPCR_ISA300 bl __init_HFSCR - bl __init_tlb_power9 bl __init_PMU_HV mtlr r11 blr @@ -194,50 +188,6 @@ __init_HFSCR: mtspr SPRN_HFSCR,r3 blr -/* - * Clear the TLB using the specified IS form of tlbiel instruction - * (invalidate by congruence class). P7 has 128 CCs., P8 has 512. - */ -__init_tlb_power7: - li r6,POWER7_TLB_SETS - mtctr r6 - li r7,0xc00 /* IS field = 0b11 */ - ptesync -2: tlbiel r7 - addi r7,r7,0x1000 - bdnz 2b - ptesync -1: blr - -__init_tlb_power8: - li r6,POWER8_TLB_SETS - mtctr r6 - li r7,0xc00 /* IS field = 0b11 */ - ptesync -2: tlbiel r7 - addi r7,r7,0x1000 - bdnz 2b - ptesync -1: blr - -/* - * Flush the TLB in hash mode. Hash must flush with RIC=2 once for process - * and one for partition scope to clear process and partition table entries. - */ -__init_tlb_power9: - li r6,POWER9_TLB_SETS_HASH - 1 - mtctr r6 - li r7,0xc00 /* IS field = 0b11 */ - li r8,0 - ptesync - PPC_TLBIEL(7, 8, 2, 1, 0) - PPC_TLBIEL(7, 8, 2, 0, 0) -2: addi r7,r7,0x1000 - PPC_TLBIEL(7, 8, 0, 0, 0) - bdnz 2b - ptesync -1: blr - __init_PMU_HV: li r5,0 mtspr SPRN_MMCRC,r5 diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index 1350f49d81a8..c40a9fc1e5d1 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -74,9 +74,6 @@ extern void __setup_cpu_power8(unsigned long offset, struct cpu_spec* spec); extern void __restore_cpu_power8(void); extern void __setup_cpu_power9(unsigned long offset, struct cpu_spec* spec); extern void __restore_cpu_power9(void); -extern void __flush_tlb_power7(unsigned int action); -extern void __flush_tlb_power8(unsigned int action); -extern void __flush_tlb_power9(unsigned int action); extern long __machine_check_early_realmode_p7(struct pt_regs *regs); extern long __machine_check_early_realmode_p8(struct pt_regs *regs); extern long __machine_check_early_realmode_p9(struct pt_regs *regs); @@ -368,7 +365,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .oprofile_cpu_type = "ppc64/ibm-compat-v1", .cpu_setup = __setup_cpu_power7, .cpu_restore = __restore_cpu_power7, - .flush_tlb = __flush_tlb_power7, .machine_check_early = __machine_check_early_realmode_p7, .platform = "power7", }, @@ -386,7 +382,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .oprofile_cpu_type = "ppc64/ibm-compat-v1", .cpu_setup = __setup_cpu_power8, .cpu_restore = __restore_cpu_power8, - .flush_tlb = __flush_tlb_power8, .machine_check_early = __machine_check_early_realmode_p8, .platform = "power8", }, @@ -404,7 +399,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .oprofile_cpu_type = "ppc64/ibm-compat-v1", .cpu_setup = __setup_cpu_power9, .cpu_restore = __restore_cpu_power9, - .flush_tlb = __flush_tlb_power9, .platform = "power9", }, { /* Power7 */ @@ -423,7 +417,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .oprofile_type = PPC_OPROFILE_POWER4, .cpu_setup = __setup_cpu_power7, .cpu_restore = __restore_cpu_power7, - .flush_tlb = __flush_tlb_power7, .machine_check_early = __machine_check_early_realmode_p7, .platform = "power7", }, @@ -443,7 +436,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .oprofile_type = PPC_OPROFILE_POWER4, .cpu_setup = __setup_cpu_power7, .cpu_restore = __restore_cpu_power7, - .flush_tlb = __flush_tlb_power7, .machine_check_early = __machine_check_early_realmode_p7, .platform = "power7+", }, @@ -463,7 +455,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .oprofile_type = PPC_OPROFILE_INVALID, .cpu_setup = __setup_cpu_power8, .cpu_restore = __restore_cpu_power8, - .flush_tlb = __flush_tlb_power8, .machine_check_early = __machine_check_early_realmode_p8, .platform = "power8", }, @@ -483,7 +474,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .oprofile_type = PPC_OPROFILE_INVALID, .cpu_setup = __setup_cpu_power8, .cpu_restore = __restore_cpu_power8, - .flush_tlb = __flush_tlb_power8, .machine_check_early = __machine_check_early_realmode_p8, .platform = "power8", }, @@ -503,7 +493,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .oprofile_type = PPC_OPROFILE_INVALID, .cpu_setup = __setup_cpu_power8, .cpu_restore = __restore_cpu_power8, - .flush_tlb = __flush_tlb_power8, .machine_check_early = __machine_check_early_realmode_p8, .platform = "power8", }, @@ -523,7 +512,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .oprofile_type = PPC_OPROFILE_INVALID, .cpu_setup = __setup_cpu_power8, .cpu_restore = __restore_cpu_power8, - .flush_tlb = __flush_tlb_power8, .machine_check_early = __machine_check_early_realmode_p8, .platform = "power8", }, @@ -543,7 +531,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .oprofile_type = PPC_OPROFILE_INVALID, .cpu_setup = __setup_cpu_power9, .cpu_restore = __restore_cpu_power9, - .flush_tlb = __flush_tlb_power9, .machine_check_early = __machine_check_early_realmode_p9, .platform = "power9", }, @@ -563,7 +550,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .oprofile_type = PPC_OPROFILE_INVALID, .cpu_setup = __setup_cpu_power9, .cpu_restore = __restore_cpu_power9, - .flush_tlb = __flush_tlb_power9, .machine_check_early = __machine_check_early_realmode_p9, .platform = "power9", }, @@ -583,7 +569,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .oprofile_type = PPC_OPROFILE_INVALID, .cpu_setup = __setup_cpu_power9, .cpu_restore = __restore_cpu_power9, - .flush_tlb = __flush_tlb_power9, .machine_check_early = __machine_check_early_realmode_p9, .platform = "power9", }, diff --git a/arch/powerpc/kernel/crash.c b/arch/powerpc/kernel/crash.c index cbabb5adccd9..00b215125d3e 100644 --- a/arch/powerpc/kernel/crash.c +++ b/arch/powerpc/kernel/crash.c @@ -44,6 +44,14 @@ #define REAL_MODE_TIMEOUT 10000 static int time_to_dump; +/* + * crash_wake_offline should be set to 1 by platforms that intend to wake + * up offline cpus prior to jumping to a kdump kernel. Currently powernv + * sets it to 1, since we want to avoid things from happening when an + * offline CPU wakes up due to something like an HMI (malfunction error), + * which propagates to all threads. + */ +int crash_wake_offline; #define CRASH_HANDLER_MAX 3 /* List of shutdown handles */ @@ -63,15 +71,12 @@ static int handle_fault(struct pt_regs *regs) #ifdef CONFIG_SMP static atomic_t cpus_in_crash; -static void crash_ipi_callback(struct pt_regs *regs) +void crash_ipi_callback(struct pt_regs *regs) { static cpumask_t cpus_state_saved = CPU_MASK_NONE; int cpu = smp_processor_id(); - if (!cpu_online(cpu)) - return; - hard_irq_disable(); if (!cpumask_test_cpu(cpu, &cpus_state_saved)) { crash_save_cpu(regs, cpu); @@ -109,6 +114,9 @@ static void crash_kexec_prepare_cpus(int cpu) printk(KERN_EMERG "Sending IPI to other CPUs\n"); + if (crash_wake_offline) + ncpus = num_present_cpus() - 1; + crash_send_ipi(crash_ipi_callback); smp_wmb(); diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c index 8bdc2f96c5d6..945e2c29ad2d 100644 --- a/arch/powerpc/kernel/dt_cpu_ftrs.c +++ b/arch/powerpc/kernel/dt_cpu_ftrs.c @@ -77,8 +77,6 @@ struct dt_cpu_feature { * Set up the base CPU */ -extern void __flush_tlb_power8(unsigned int action); -extern void __flush_tlb_power9(unsigned int action); extern long __machine_check_early_realmode_p8(struct pt_regs *regs); extern long __machine_check_early_realmode_p9(struct pt_regs *regs); @@ -92,27 +90,6 @@ static struct { static void (*init_pmu_registers)(void); -static void cpufeatures_flush_tlb(void) -{ - /* - * This is a temporary measure to keep equivalent TLB flush as the - * cputable based setup code. - */ - switch (PVR_VER(mfspr(SPRN_PVR))) { - case PVR_POWER8: - case PVR_POWER8E: - case PVR_POWER8NVL: - __flush_tlb_power8(TLB_INVAL_SCOPE_GLOBAL); - break; - case PVR_POWER9: - __flush_tlb_power9(TLB_INVAL_SCOPE_GLOBAL); - break; - default: - pr_err("unknown CPU version for boot TLB flush\n"); - break; - } -} - static void __restore_cpu_cpufeatures(void) { /* @@ -137,8 +114,6 @@ static void __restore_cpu_cpufeatures(void) if (init_pmu_registers) init_pmu_registers(); - - cpufeatures_flush_tlb(); } static char dt_cpu_name[64]; @@ -157,7 +132,6 @@ static struct cpu_spec __initdata base_cpu_spec = { .oprofile_type = PPC_OPROFILE_INVALID, .cpu_setup = NULL, .cpu_restore = __restore_cpu_cpufeatures, - .flush_tlb = NULL, .machine_check_early = NULL, .platform = NULL, }; @@ -412,7 +386,6 @@ static void init_pmu_power8(void) static int __init feat_enable_mce_power8(struct dt_cpu_feature *f) { cur_cpu_spec->platform = "power8"; - cur_cpu_spec->flush_tlb = __flush_tlb_power8; cur_cpu_spec->machine_check_early = __machine_check_early_realmode_p8; return 1; @@ -451,7 +424,6 @@ static void init_pmu_power9(void) static int __init feat_enable_mce_power9(struct dt_cpu_feature *f) { cur_cpu_spec->platform = "power9"; - cur_cpu_spec->flush_tlb = __flush_tlb_power9; cur_cpu_spec->machine_check_early = __machine_check_early_realmode_p9; return 1; @@ -752,8 +724,6 @@ static void __init cpufeatures_setup_finished(void) system_registers.hfscr = mfspr(SPRN_HFSCR); system_registers.fscr = mfspr(SPRN_FSCR); - cpufeatures_flush_tlb(); - pr_info("final cpu/mmu features = 0x%016lx 0x%08x\n", cur_cpu_spec->cpu_features, cur_cpu_spec->mmu_features); } diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index cbca0a667682..cc649809885e 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -740,6 +740,65 @@ static void *eeh_restore_dev_state(void *data, void *userdata) return NULL; } +int eeh_restore_vf_config(struct pci_dn *pdn) +{ + struct eeh_dev *edev = pdn_to_eeh_dev(pdn); + u32 devctl, cmd, cap2, aer_capctl; + int old_mps; + + if (edev->pcie_cap) { + /* Restore MPS */ + old_mps = (ffs(pdn->mps) - 8) << 5; + eeh_ops->read_config(pdn, edev->pcie_cap + PCI_EXP_DEVCTL, + 2, &devctl); + devctl &= ~PCI_EXP_DEVCTL_PAYLOAD; + devctl |= old_mps; + eeh_ops->write_config(pdn, edev->pcie_cap + PCI_EXP_DEVCTL, + 2, devctl); + + /* Disable Completion Timeout */ + eeh_ops->read_config(pdn, edev->pcie_cap + PCI_EXP_DEVCAP2, + 4, &cap2); + if (cap2 & 0x10) { + eeh_ops->read_config(pdn, + edev->pcie_cap + PCI_EXP_DEVCTL2, + 4, &cap2); + cap2 |= 0x10; + eeh_ops->write_config(pdn, + edev->pcie_cap + PCI_EXP_DEVCTL2, + 4, cap2); + } + } + + /* Enable SERR and parity checking */ + eeh_ops->read_config(pdn, PCI_COMMAND, 2, &cmd); + cmd |= (PCI_COMMAND_PARITY | PCI_COMMAND_SERR); + eeh_ops->write_config(pdn, PCI_COMMAND, 2, cmd); + + /* Enable report various errors */ + if (edev->pcie_cap) { + eeh_ops->read_config(pdn, edev->pcie_cap + PCI_EXP_DEVCTL, + 2, &devctl); + devctl &= ~PCI_EXP_DEVCTL_CERE; + devctl |= (PCI_EXP_DEVCTL_NFERE | + PCI_EXP_DEVCTL_FERE | + PCI_EXP_DEVCTL_URRE); + eeh_ops->write_config(pdn, edev->pcie_cap + PCI_EXP_DEVCTL, + 2, devctl); + } + + /* Enable ECRC generation and check */ + if (edev->pcie_cap && edev->aer_cap) { + eeh_ops->read_config(pdn, edev->aer_cap + PCI_ERR_CAP, + 4, &aer_capctl); + aer_capctl |= (PCI_ERR_CAP_ECRC_GENE | PCI_ERR_CAP_ECRC_CHKE); + eeh_ops->write_config(pdn, edev->aer_cap + PCI_ERR_CAP, + 4, aer_capctl); + } + + return 0; +} + /** * pcibios_set_pcie_reset_state - Set PCI-E reset state * @dev: pci device struct diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index 4f71e4c9beb7..beea2182d754 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -228,6 +228,7 @@ static void *eeh_report_error(void *data, void *userdata) edev->in_error = true; eeh_pcid_put(dev); + pci_uevent_ers(dev, PCI_ERS_RESULT_NONE); return NULL; } @@ -381,6 +382,10 @@ static void *eeh_report_resume(void *data, void *userdata) driver->err_handler->resume(dev); eeh_pcid_put(dev); + pci_uevent_ers(dev, PCI_ERS_RESULT_RECOVERED); +#ifdef CONFIG_PCI_IOV + eeh_ops->notify_resume(eeh_dev_to_pdn(edev)); +#endif return NULL; } @@ -416,6 +421,7 @@ static void *eeh_report_failure(void *data, void *userdata) driver->err_handler->error_detected(dev, pci_channel_io_perm_failure); eeh_pcid_put(dev); + pci_uevent_ers(dev, PCI_ERS_RESULT_DISCONNECT); return NULL; } @@ -440,7 +446,7 @@ static void *eeh_add_virt_device(void *data, void *userdata) return NULL; } -#ifdef CONFIG_PPC_POWERNV +#ifdef CONFIG_PCI_IOV pci_iov_add_virtfn(edev->physfn, pdn->vf_index); #endif return NULL; @@ -496,7 +502,7 @@ static void *eeh_rmv_device(void *data, void *userdata) (*removed)++; if (edev->physfn) { -#ifdef CONFIG_PPC_POWERNV +#ifdef CONFIG_PCI_IOV struct pci_dn *pdn = eeh_dev_to_pdn(edev); pci_iov_remove_virtfn(edev->physfn, pdn->vf_index); diff --git a/arch/powerpc/kernel/eeh_sysfs.c b/arch/powerpc/kernel/eeh_sysfs.c index 797549289798..deed906dd8f1 100644 --- a/arch/powerpc/kernel/eeh_sysfs.c +++ b/arch/powerpc/kernel/eeh_sysfs.c @@ -48,7 +48,7 @@ static ssize_t eeh_show_##_name(struct device *dev, \ \ return sprintf(buf, _format "\n", edev->_memb); \ } \ -static DEVICE_ATTR(_name, S_IRUGO, eeh_show_##_name, NULL); +static DEVICE_ATTR(_name, 0444, eeh_show_##_name, NULL); EEH_SHOW_ATTR(eeh_mode, mode, "0x%x"); EEH_SHOW_ATTR(eeh_pe_config_addr, pe_config_addr, "0x%x"); @@ -90,6 +90,65 @@ static ssize_t eeh_pe_state_store(struct device *dev, static DEVICE_ATTR_RW(eeh_pe_state); +#ifdef CONFIG_PCI_IOV +static ssize_t eeh_notify_resume_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct pci_dev *pdev = to_pci_dev(dev); + struct eeh_dev *edev = pci_dev_to_eeh_dev(pdev); + struct pci_dn *pdn = pci_get_pdn(pdev); + + if (!edev || !edev->pe) + return -ENODEV; + + pdn = pci_get_pdn(pdev); + return sprintf(buf, "%d\n", pdn->last_allow_rc); +} + +static ssize_t eeh_notify_resume_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct pci_dev *pdev = to_pci_dev(dev); + struct eeh_dev *edev = pci_dev_to_eeh_dev(pdev); + + if (!edev || !edev->pe || !eeh_ops->notify_resume) + return -ENODEV; + + if (eeh_ops->notify_resume(pci_get_pdn(pdev))) + return -EIO; + + return count; +} +static DEVICE_ATTR_RW(eeh_notify_resume); + +static int eeh_notify_resume_add(struct pci_dev *pdev) +{ + struct device_node *np; + int rc = 0; + + np = pci_device_to_OF_node(pdev->is_physfn ? pdev : pdev->physfn); + + if (of_property_read_bool(np, "ibm,is-open-sriov-pf")) + rc = device_create_file(&pdev->dev, &dev_attr_eeh_notify_resume); + + return rc; +} + +static void eeh_notify_resume_remove(struct pci_dev *pdev) +{ + struct device_node *np; + + np = pci_device_to_OF_node(pdev->is_physfn ? pdev : pdev->physfn); + + if (of_property_read_bool(np, "ibm,is-open-sriov-pf")) + device_remove_file(&pdev->dev, &dev_attr_eeh_notify_resume); +} +#else +static inline int eeh_notify_resume_add(struct pci_dev *pdev) { return 0; } +static inline void eeh_notify_resume_remove(struct pci_dev *pdev) { } +#endif /* CONFIG_PCI_IOV */ + void eeh_sysfs_add_device(struct pci_dev *pdev) { struct eeh_dev *edev = pci_dev_to_eeh_dev(pdev); @@ -104,6 +163,7 @@ void eeh_sysfs_add_device(struct pci_dev *pdev) rc += device_create_file(&pdev->dev, &dev_attr_eeh_mode); rc += device_create_file(&pdev->dev, &dev_attr_eeh_pe_config_addr); rc += device_create_file(&pdev->dev, &dev_attr_eeh_pe_state); + rc += eeh_notify_resume_add(pdev); if (rc) pr_warn("EEH: Unable to create sysfs entries\n"); @@ -129,6 +189,8 @@ void eeh_sysfs_remove_device(struct pci_dev *pdev) device_remove_file(&pdev->dev, &dev_attr_eeh_pe_config_addr); device_remove_file(&pdev->dev, &dev_attr_eeh_pe_state); + eeh_notify_resume_remove(pdev); + if (edev) edev->mode &= ~EEH_DEV_SYSFS; } diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S index e780e1fbf6c2..eb8d01bae8c6 100644 --- a/arch/powerpc/kernel/entry_32.S +++ b/arch/powerpc/kernel/entry_32.S @@ -211,7 +211,7 @@ transfer_to_handler_cont: mflr r9 lwz r11,0(r9) /* virtual address of handler */ lwz r9,4(r9) /* where to go when done */ -#ifdef CONFIG_PPC_8xx_PERF_EVENT +#if defined(CONFIG_PPC_8xx) && defined(CONFIG_PERF_EVENTS) mtspr SPRN_NRI, r0 #endif #ifdef CONFIG_TRACE_IRQFLAGS @@ -301,7 +301,7 @@ stack_ovf: lis r9,StackOverflow@ha addi r9,r9,StackOverflow@l LOAD_MSR_KERNEL(r10,MSR_KERNEL) -#ifdef CONFIG_PPC_8xx_PERF_EVENT +#if defined(CONFIG_PPC_8xx) && defined(CONFIG_PERF_EVENTS) mtspr SPRN_NRI, r0 #endif mtspr SPRN_SRR0,r9 @@ -430,7 +430,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_NEED_PAIRED_STWCX) lwz r7,_NIP(r1) lwz r2,GPR2(r1) lwz r1,GPR1(r1) -#ifdef CONFIG_PPC_8xx_PERF_EVENT +#if defined(CONFIG_PPC_8xx) && defined(CONFIG_PERF_EVENTS) mtspr SPRN_NRI, r0 #endif mtspr SPRN_SRR0,r7 @@ -727,7 +727,7 @@ fast_exception_return: lwz r10,_LINK(r11) mtlr r10 REST_GPR(10, r11) -#ifdef CONFIG_PPC_8xx_PERF_EVENT +#if defined(CONFIG_PPC_8xx) && defined(CONFIG_PERF_EVENTS) mtspr SPRN_NRI, r0 #endif mtspr SPRN_SRR1,r9 @@ -978,7 +978,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_NEED_PAIRED_STWCX) .globl exc_exit_restart exc_exit_restart: lwz r12,_NIP(r1) -#ifdef CONFIG_PPC_8xx_PERF_EVENT +#if defined(CONFIG_PPC_8xx) && defined(CONFIG_PERF_EVENTS) mtspr SPRN_NRI, r0 #endif mtspr SPRN_SRR0,r12 diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index 2748584b767d..2cb5109a7ea3 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -133,10 +133,9 @@ END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLPAR) * of irq tracing is used, we additionally check that condition * is correct */ -#if defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_BUG) - lbz r10,PACASOFTIRQEN(r13) - xori r10,r10,1 -1: tdnei r10,0 +#if defined(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG) && defined(CONFIG_BUG) + lbz r10,PACAIRQSOFTMASK(r13) +1: tdnei r10,IRQS_ENABLED EMIT_BUG_ENTRY 1b,__FILE__,__LINE__,BUGFLAG_WARNING #endif @@ -152,7 +151,7 @@ system_call: /* label this so stack traces look sane */ /* We do need to set SOFTE in the stack frame or the return * from interrupt will be painful */ - li r10,1 + li r10,IRQS_ENABLED std r10,SOFTE(r1) CURRENT_THREAD_INFO(r11, r1) @@ -755,10 +754,10 @@ resume_kernel: beq+ restore /* Check that preempt_count() == 0 and interrupts are enabled */ lwz r8,TI_PREEMPT(r9) - cmpwi cr1,r8,0 + cmpwi cr0,r8,0 + bne restore ld r0,SOFTE(r1) - cmpdi r0,0 - crandc eq,cr1*4+eq,eq + andi. r0,r0,IRQS_DISABLED bne restore /* @@ -796,12 +795,12 @@ restore: * are about to re-enable interrupts */ ld r5,SOFTE(r1) - lbz r6,PACASOFTIRQEN(r13) - cmpwi cr0,r5,0 - beq .Lrestore_irq_off + lbz r6,PACAIRQSOFTMASK(r13) + andi. r5,r5,IRQS_DISABLED + bne .Lrestore_irq_off /* We are enabling, were we already enabled ? Yes, just return */ - cmpwi cr0,r6,1 + andi. r6,r6,IRQS_DISABLED beq cr0,.Ldo_restore /* @@ -820,8 +819,8 @@ restore: */ .Lrestore_no_replay: TRACE_ENABLE_INTS - li r0,1 - stb r0,PACASOFTIRQEN(r13); + li r0,IRQS_ENABLED + stb r0,PACAIRQSOFTMASK(r13); /* * Final return path. BookE is handled in a different file @@ -939,9 +938,13 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) beq 1f rlwinm r7,r7,0,~PACA_IRQ_HARD_DIS stb r7,PACAIRQHAPPENED(r13) -1: li r0,0 - stb r0,PACASOFTIRQEN(r13); - TRACE_DISABLE_INTS +1: +#if defined(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG) && defined(CONFIG_BUG) + /* The interrupt should not have soft enabled. */ + lbz r7,PACAIRQSOFTMASK(r13) +1: tdeqi r7,IRQS_ENABLED + EMIT_BUG_ENTRY 1b,__FILE__,__LINE__,BUGFLAG_WARNING +#endif b .Ldo_restore /* @@ -979,6 +982,11 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) addi r3,r1,STACK_FRAME_OVERHEAD; bl do_IRQ b ret_from_except +1: cmpwi cr0,r3,0xf00 + bne 1f + addi r3,r1,STACK_FRAME_OVERHEAD; + bl performance_monitor_exception + b ret_from_except 1: cmpwi cr0,r3,0xe60 bne 1f addi r3,r1,STACK_FRAME_OVERHEAD; @@ -1055,15 +1063,15 @@ _GLOBAL(enter_rtas) li r0,0 mtcr r0 -#ifdef CONFIG_BUG +#ifdef CONFIG_BUG /* There is no way it is acceptable to get here with interrupts enabled, * check it with the asm equivalent of WARN_ON */ - lbz r0,PACASOFTIRQEN(r13) -1: tdnei r0,0 + lbz r0,PACAIRQSOFTMASK(r13) +1: tdeqi r0,IRQS_ENABLED EMIT_BUG_ENTRY 1b,__FILE__,__LINE__,BUGFLAG_WARNING #endif - + /* Hard-disable interrupts */ mfmsr r6 rldicl r7,r6,48,1 @@ -1107,6 +1115,17 @@ __enter_rtas: rtas_return_loc: FIXUP_ENDIAN + /* + * Clear RI and set SF before anything. + */ + mfmsr r6 + li r0,MSR_RI + andc r6,r6,r0 + sldi r0,r0,(MSR_SF_LG - MSR_RI_LG) + or r6,r6,r0 + sync + mtmsrd r6 + /* relocation is off at this point */ GET_PACA(r4) clrldi r4,r4,2 /* convert to realmode address */ @@ -1115,12 +1134,6 @@ rtas_return_loc: 0: mflr r3 ld r3,(1f-0b)(r3) /* get &rtas_restore_regs */ - mfmsr r6 - li r0,MSR_RI - andc r6,r6,r0 - sync - mtmsrd r6 - ld r1,PACAR1(r4) /* Restore our SP */ ld r4,PACASAVEDMSR(r4) /* Restore our MSR */ diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S index acd8ca76233e..ee832d344a5a 100644 --- a/arch/powerpc/kernel/exceptions-64e.S +++ b/arch/powerpc/kernel/exceptions-64e.S @@ -139,7 +139,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_EMB_HV) mfspr r10,SPRN_ESR SPECIAL_EXC_STORE(r10,ESR) - lbz r10,PACASOFTIRQEN(r13) + lbz r10,PACAIRQSOFTMASK(r13) SPECIAL_EXC_STORE(r10,SOFTE) ld r10,_NIP(r1) SPECIAL_EXC_STORE(r10,CSRR0) @@ -206,17 +206,17 @@ BEGIN_FTR_SECTION mtspr SPRN_MAS8,r10 END_FTR_SECTION_IFSET(CPU_FTR_EMB_HV) - lbz r6,PACASOFTIRQEN(r13) + lbz r6,PACAIRQSOFTMASK(r13) ld r5,SOFTE(r1) /* Interrupts had better not already be enabled... */ - twnei r6,0 + tweqi r6,IRQS_ENABLED - cmpwi cr0,r5,0 - beq 1f + andi. r6,r5,IRQS_DISABLED + bne 1f TRACE_ENABLE_INTS - stb r5,PACASOFTIRQEN(r13) + stb r5,PACAIRQSOFTMASK(r13) 1: /* * Restore PACAIRQHAPPENED rather than setting it based on @@ -351,9 +351,9 @@ ret_from_mc_except: #define PROLOG_ADDITION_NONE_MC(n) #define PROLOG_ADDITION_MASKABLE_GEN(n) \ - lbz r10,PACASOFTIRQEN(r13); /* are irqs soft-disabled ? */ \ - cmpwi cr0,r10,0; /* yes -> go out of line */ \ - beq masked_interrupt_book3e_##n + lbz r10,PACAIRQSOFTMASK(r13); /* are irqs soft-masked? */ \ + andi. r10,r10,IRQS_DISABLED; /* yes -> go out of line */ \ + bne masked_interrupt_book3e_##n #define PROLOG_ADDITION_2REGS_GEN(n) \ std r14,PACA_EXGEN+EX_R14(r13); \ @@ -397,7 +397,7 @@ exc_##n##_common: \ mfspr r8,SPRN_XER; /* save XER in stackframe */ \ ld r9,excf+EX_R1(r13); /* load orig r1 back from PACA */ \ lwz r10,excf+EX_CR(r13); /* load orig CR back from PACA */ \ - lbz r11,PACASOFTIRQEN(r13); /* get current IRQ softe */ \ + lbz r11,PACAIRQSOFTMASK(r13); /* get current IRQ softe */ \ ld r12,exception_marker@toc(r2); \ li r0,0; \ std r3,GPR10(r1); /* save r10 to stackframe */ \ diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 2dc10bf646b8..243d072a225a 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -718,10 +718,12 @@ EXC_REAL_BEGIN(hardware_interrupt, 0x500, 0x100) hardware_interrupt_hv: BEGIN_FTR_SECTION _MASKABLE_EXCEPTION_PSERIES(0x500, hardware_interrupt_common, - EXC_HV, SOFTEN_TEST_HV) + EXC_HV, SOFTEN_TEST_HV, + IRQS_DISABLED) FTR_SECTION_ELSE _MASKABLE_EXCEPTION_PSERIES(0x500, hardware_interrupt_common, - EXC_STD, SOFTEN_TEST_PR) + EXC_STD, SOFTEN_TEST_PR, + IRQS_DISABLED) ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206) EXC_REAL_END(hardware_interrupt, 0x500, 0x100) @@ -729,9 +731,13 @@ EXC_VIRT_BEGIN(hardware_interrupt, 0x4500, 0x100) .globl hardware_interrupt_relon_hv; hardware_interrupt_relon_hv: BEGIN_FTR_SECTION - _MASKABLE_RELON_EXCEPTION_PSERIES(0x500, hardware_interrupt_common, EXC_HV, SOFTEN_TEST_HV) + _MASKABLE_RELON_EXCEPTION_PSERIES(0x500, hardware_interrupt_common, + EXC_HV, SOFTEN_TEST_HV, + IRQS_DISABLED) FTR_SECTION_ELSE - _MASKABLE_RELON_EXCEPTION_PSERIES(0x500, hardware_interrupt_common, EXC_STD, SOFTEN_TEST_PR) + _MASKABLE_RELON_EXCEPTION_PSERIES(0x500, hardware_interrupt_common, + EXC_STD, SOFTEN_TEST_PR, + IRQS_DISABLED) ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE) EXC_VIRT_END(hardware_interrupt, 0x4500, 0x100) @@ -827,8 +833,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_TM) #endif -EXC_REAL_MASKABLE(decrementer, 0x900, 0x80) -EXC_VIRT_MASKABLE(decrementer, 0x4900, 0x80, 0x900) +EXC_REAL_MASKABLE(decrementer, 0x900, 0x80, IRQS_DISABLED) +EXC_VIRT_MASKABLE(decrementer, 0x4900, 0x80, 0x900, IRQS_DISABLED) TRAMP_KVM(PACA_EXGEN, 0x900) EXC_COMMON_ASYNC(decrementer_common, 0x900, timer_interrupt) @@ -839,8 +845,8 @@ TRAMP_KVM_HV(PACA_EXGEN, 0x980) EXC_COMMON(hdecrementer_common, 0x980, hdec_interrupt) -EXC_REAL_MASKABLE(doorbell_super, 0xa00, 0x100) -EXC_VIRT_MASKABLE(doorbell_super, 0x4a00, 0x100, 0xa00) +EXC_REAL_MASKABLE(doorbell_super, 0xa00, 0x100, IRQS_DISABLED) +EXC_VIRT_MASKABLE(doorbell_super, 0x4a00, 0x100, 0xa00, IRQS_DISABLED) TRAMP_KVM(PACA_EXGEN, 0xa00) #ifdef CONFIG_PPC_DOORBELL EXC_COMMON_ASYNC(doorbell_super_common, 0xa00, doorbell_exception) @@ -1052,7 +1058,7 @@ EXC_COMMON(emulation_assist_common, 0xe40, emulation_assist_interrupt) * mode. */ __EXC_REAL_OOL_HV_DIRECT(hmi_exception, 0xe60, 0x20, hmi_exception_early) -__TRAMP_REAL_OOL_MASKABLE_HV(hmi_exception, 0xe60) +__TRAMP_REAL_OOL_MASKABLE_HV(hmi_exception, 0xe60, IRQS_DISABLED) EXC_VIRT_NONE(0x4e60, 0x20) TRAMP_KVM_HV(PACA_EXGEN, 0xe60) TRAMP_REAL_BEGIN(hmi_exception_early) @@ -1110,8 +1116,8 @@ EXC_COMMON_BEGIN(hmi_exception_common) EXCEPTION_COMMON(PACA_EXGEN, 0xe60, hmi_exception_common, handle_hmi_exception, ret_from_except, FINISH_NAP;ADD_NVGPRS;ADD_RECONCILE;RUNLATCH_ON) -EXC_REAL_OOL_MASKABLE_HV(h_doorbell, 0xe80, 0x20) -EXC_VIRT_OOL_MASKABLE_HV(h_doorbell, 0x4e80, 0x20, 0xe80) +EXC_REAL_OOL_MASKABLE_HV(h_doorbell, 0xe80, 0x20, IRQS_DISABLED) +EXC_VIRT_OOL_MASKABLE_HV(h_doorbell, 0x4e80, 0x20, 0xe80, IRQS_DISABLED) TRAMP_KVM_HV(PACA_EXGEN, 0xe80) #ifdef CONFIG_PPC_DOORBELL EXC_COMMON_ASYNC(h_doorbell_common, 0xe80, doorbell_exception) @@ -1120,8 +1126,8 @@ EXC_COMMON_ASYNC(h_doorbell_common, 0xe80, unknown_exception) #endif -EXC_REAL_OOL_MASKABLE_HV(h_virt_irq, 0xea0, 0x20) -EXC_VIRT_OOL_MASKABLE_HV(h_virt_irq, 0x4ea0, 0x20, 0xea0) +EXC_REAL_OOL_MASKABLE_HV(h_virt_irq, 0xea0, 0x20, IRQS_DISABLED) +EXC_VIRT_OOL_MASKABLE_HV(h_virt_irq, 0x4ea0, 0x20, 0xea0, IRQS_DISABLED) TRAMP_KVM_HV(PACA_EXGEN, 0xea0) EXC_COMMON_ASYNC(h_virt_irq_common, 0xea0, do_IRQ) @@ -1132,8 +1138,8 @@ EXC_REAL_NONE(0xee0, 0x20) EXC_VIRT_NONE(0x4ee0, 0x20) -EXC_REAL_OOL(performance_monitor, 0xf00, 0x20) -EXC_VIRT_OOL(performance_monitor, 0x4f00, 0x20, 0xf00) +EXC_REAL_OOL_MASKABLE(performance_monitor, 0xf00, 0x20, IRQS_PMI_DISABLED) +EXC_VIRT_OOL_MASKABLE(performance_monitor, 0x4f00, 0x20, 0xf00, IRQS_PMI_DISABLED) TRAMP_KVM(PACA_EXGEN, 0xf00) EXC_COMMON_ASYNC(performance_monitor_common, 0xf00, performance_monitor_exception) @@ -1345,7 +1351,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR) b . #endif -EXC_COMMON_HV(denorm_common, 0x1500, unknown_exception) +EXC_COMMON(denorm_common, 0x1500, unknown_exception) #ifdef CONFIG_CBE_RAS @@ -1455,39 +1461,37 @@ TRAMP_REAL_BEGIN(rfi_flush_fallback) std r9,PACA_EXRFI+EX_R9(r13) std r10,PACA_EXRFI+EX_R10(r13) std r11,PACA_EXRFI+EX_R11(r13) - std r12,PACA_EXRFI+EX_R12(r13) - std r8,PACA_EXRFI+EX_R13(r13) mfctr r9 ld r10,PACA_RFI_FLUSH_FALLBACK_AREA(r13) - ld r11,PACA_L1D_FLUSH_SETS(r13) - ld r12,PACA_L1D_FLUSH_CONGRUENCE(r13) - /* - * The load adresses are at staggered offsets within cachelines, - * which suits some pipelines better (on others it should not - * hurt). - */ - addi r12,r12,8 + ld r11,PACA_L1D_FLUSH_SIZE(r13) + srdi r11,r11,(7 + 3) /* 128 byte lines, unrolled 8x */ mtctr r11 DCBT_STOP_ALL_STREAM_IDS(r11) /* Stop prefetch streams */ /* order ld/st prior to dcbt stop all streams with flushing */ sync -1: li r8,0 - .rept 8 /* 8-way set associative */ - ldx r11,r10,r8 - add r8,r8,r12 - xor r11,r11,r11 // Ensure r11 is 0 even if fallback area is not - add r8,r8,r11 // Add 0, this creates a dependency on the ldx - .endr - addi r10,r10,128 /* 128 byte cache line */ + + /* + * The load adresses are at staggered offsets within cachelines, + * which suits some pipelines better (on others it should not + * hurt). + */ +1: + ld r11,(0x80 + 8)*0(r10) + ld r11,(0x80 + 8)*1(r10) + ld r11,(0x80 + 8)*2(r10) + ld r11,(0x80 + 8)*3(r10) + ld r11,(0x80 + 8)*4(r10) + ld r11,(0x80 + 8)*5(r10) + ld r11,(0x80 + 8)*6(r10) + ld r11,(0x80 + 8)*7(r10) + addi r10,r10,0x80*8 bdnz 1b mtctr r9 ld r9,PACA_EXRFI+EX_R9(r13) ld r10,PACA_EXRFI+EX_R10(r13) ld r11,PACA_EXRFI+EX_R11(r13) - ld r12,PACA_EXRFI+EX_R12(r13) - ld r8,PACA_EXRFI+EX_R13(r13) GET_SCRATCH0(r13); rfid @@ -1497,39 +1501,37 @@ TRAMP_REAL_BEGIN(hrfi_flush_fallback) std r9,PACA_EXRFI+EX_R9(r13) std r10,PACA_EXRFI+EX_R10(r13) std r11,PACA_EXRFI+EX_R11(r13) - std r12,PACA_EXRFI+EX_R12(r13) - std r8,PACA_EXRFI+EX_R13(r13) mfctr r9 ld r10,PACA_RFI_FLUSH_FALLBACK_AREA(r13) - ld r11,PACA_L1D_FLUSH_SETS(r13) - ld r12,PACA_L1D_FLUSH_CONGRUENCE(r13) - /* - * The load adresses are at staggered offsets within cachelines, - * which suits some pipelines better (on others it should not - * hurt). - */ - addi r12,r12,8 + ld r11,PACA_L1D_FLUSH_SIZE(r13) + srdi r11,r11,(7 + 3) /* 128 byte lines, unrolled 8x */ mtctr r11 DCBT_STOP_ALL_STREAM_IDS(r11) /* Stop prefetch streams */ /* order ld/st prior to dcbt stop all streams with flushing */ sync -1: li r8,0 - .rept 8 /* 8-way set associative */ - ldx r11,r10,r8 - add r8,r8,r12 - xor r11,r11,r11 // Ensure r11 is 0 even if fallback area is not - add r8,r8,r11 // Add 0, this creates a dependency on the ldx - .endr - addi r10,r10,128 /* 128 byte cache line */ + + /* + * The load adresses are at staggered offsets within cachelines, + * which suits some pipelines better (on others it should not + * hurt). + */ +1: + ld r11,(0x80 + 8)*0(r10) + ld r11,(0x80 + 8)*1(r10) + ld r11,(0x80 + 8)*2(r10) + ld r11,(0x80 + 8)*3(r10) + ld r11,(0x80 + 8)*4(r10) + ld r11,(0x80 + 8)*5(r10) + ld r11,(0x80 + 8)*6(r10) + ld r11,(0x80 + 8)*7(r10) + addi r10,r10,0x80*8 bdnz 1b mtctr r9 ld r9,PACA_EXRFI+EX_R9(r13) ld r10,PACA_EXRFI+EX_R10(r13) ld r11,PACA_EXRFI+EX_R11(r13) - ld r12,PACA_EXRFI+EX_R12(r13) - ld r8,PACA_EXRFI+EX_R13(r13) GET_SCRATCH0(r13); hrfid @@ -1632,7 +1634,7 @@ USE_TEXT_SECTION() .balign IFETCH_ALIGN_BYTES do_hash_page: #ifdef CONFIG_PPC_BOOK3S_64 - lis r0,(DSISR_BAD_FAULT_64S|DSISR_DABRMATCH)@h + lis r0,(DSISR_BAD_FAULT_64S | DSISR_DABRMATCH | DSISR_KEYFAULT)@h ori r0,r0,DSISR_BAD_FAULT_64S@l and. r0,r4,r0 /* weird error? */ bne- handle_page_fault /* if not, try to insert a HPTE */ @@ -1828,6 +1830,8 @@ BEGIN_FTR_SECTION FTR_SECTION_ELSE beq hardware_interrupt_common ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_300) + cmpwi r3,0xf00 + beq performance_monitor_common BEGIN_FTR_SECTION cmpwi r3,0xa00 beq h_doorbell_common_msgclr diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S index aa71a90f5222..a61151a6ea5e 100644 --- a/arch/powerpc/kernel/head_64.S +++ b/arch/powerpc/kernel/head_64.S @@ -765,8 +765,8 @@ _GLOBAL(pmac_secondary_start) /* Mark interrupts soft and hard disabled (they might be enabled * in the PACA when doing hotplug) */ - li r0,0 - stb r0,PACASOFTIRQEN(r13) + li r0,IRQS_DISABLED + stb r0,PACAIRQSOFTMASK(r13) li r0,PACA_IRQ_HARD_DIS stb r0,PACAIRQHAPPENED(r13) @@ -822,7 +822,8 @@ __secondary_start: /* Mark interrupts soft and hard disabled (they might be enabled * in the PACA when doing hotplug) */ - stb r7,PACASOFTIRQEN(r13) + li r7,IRQS_DISABLED + stb r7,PACAIRQSOFTMASK(r13) li r0,PACA_IRQ_HARD_DIS stb r0,PACAIRQHAPPENED(r13) @@ -988,8 +989,8 @@ start_here_common: /* Mark interrupts soft and hard disabled (they might be enabled * in the PACA when doing hotplug) */ - li r0,0 - stb r0,PACASOFTIRQEN(r13) + li r0,IRQS_DISABLED + stb r0,PACAIRQSOFTMASK(r13) li r0,PACA_IRQ_HARD_DIS stb r0,PACAIRQHAPPENED(r13) diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S index 4fee00d414e8..d8670a37d70c 100644 --- a/arch/powerpc/kernel/head_8xx.S +++ b/arch/powerpc/kernel/head_8xx.S @@ -33,23 +33,6 @@ #include <asm/fixmap.h> #include <asm/export.h> -/* Macro to make the code more readable. */ -#ifdef CONFIG_8xx_CPU6 -#define SPRN_MI_TWC_ADDR 0x2b80 -#define SPRN_MI_RPN_ADDR 0x2d80 -#define SPRN_MD_TWC_ADDR 0x3b80 -#define SPRN_MD_RPN_ADDR 0x3d80 - -#define MTSPR_CPU6(spr, reg, treg) \ - li treg, spr##_ADDR; \ - stw treg, 12(r0); \ - lwz treg, 12(r0); \ - mtspr spr, reg -#else -#define MTSPR_CPU6(spr, reg, treg) \ - mtspr spr, reg -#endif - #if CONFIG_TASK_SIZE <= 0x80000000 && CONFIG_PAGE_OFFSET >= 0x80000000 /* By simply checking Address >= 0x80000000, we know if its a kernel address */ #define SIMPLE_KERNEL_ADDRESS 1 @@ -69,11 +52,7 @@ * Value for the bits that have fixed value in RPN entries. * Also used for tagging DAR for DTLBerror. */ -#ifdef CONFIG_PPC_16K_PAGES -#define RPN_PATTERN (0x00f0 | MD_SPS16K) -#else #define RPN_PATTERN 0x00f0 -#endif #define PAGE_SHIFT_512K 19 #define PAGE_SHIFT_8M 23 @@ -134,15 +113,12 @@ turn_on_mmu: * task's thread_struct. */ #define EXCEPTION_PROLOG \ - EXCEPTION_PROLOG_0; \ + mtspr SPRN_SPRG_SCRATCH0, r10; \ + mtspr SPRN_SPRG_SCRATCH1, r11; \ mfcr r10; \ EXCEPTION_PROLOG_1; \ EXCEPTION_PROLOG_2 -#define EXCEPTION_PROLOG_0 \ - mtspr SPRN_SPRG_SCRATCH0,r10; \ - mtspr SPRN_SPRG_SCRATCH1,r11 - #define EXCEPTION_PROLOG_1 \ mfspr r11,SPRN_SRR1; /* check whether user or kernel */ \ andi. r11,r11,MSR_PR; \ @@ -177,13 +153,6 @@ turn_on_mmu: SAVE_2GPRS(7, r11) /* - * Exception exit code. - */ -#define EXCEPTION_EPILOG_0 \ - mfspr r10,SPRN_SPRG_SCRATCH0; \ - mfspr r11,SPRN_SPRG_SCRATCH1 - -/* * Note: code which follows this uses cr0.eq (set if from kernel), * r11, r12 (SRR0), and r9 (SRR1). * @@ -326,15 +295,10 @@ SystemCall: #endif InstructionTLBMiss: -#if defined(CONFIG_8xx_CPU6) || defined(ITLB_MISS_KERNEL) || defined(CONFIG_HUGETLB_PAGE) - mtspr SPRN_SPRG_SCRATCH2, r3 -#endif - EXCEPTION_PROLOG_0 -#ifdef CONFIG_PPC_8xx_PERF_EVENT - lis r10, (itlb_miss_counter - PAGE_OFFSET)@ha - lwz r11, (itlb_miss_counter - PAGE_OFFSET)@l(r10) - addi r11, r11, 1 - stw r11, (itlb_miss_counter - PAGE_OFFSET)@l(r10) + mtspr SPRN_SPRG_SCRATCH0, r10 + mtspr SPRN_SPRG_SCRATCH1, r11 +#if defined(ITLB_MISS_KERNEL) || defined(CONFIG_HUGETLB_PAGE) + mtspr SPRN_SPRG_SCRATCH2, r12 #endif /* If we are faulting a kernel address, we have to use the @@ -345,7 +309,7 @@ InstructionTLBMiss: /* Only modules will cause ITLB Misses as we always * pin the first 8MB of kernel memory */ #if defined(ITLB_MISS_KERNEL) || defined(CONFIG_HUGETLB_PAGE) - mfcr r3 + mfcr r12 #endif #ifdef ITLB_MISS_KERNEL #if defined(SIMPLE_KERNEL_ADDRESS) && defined(CONFIG_PIN_TLB_TEXT) @@ -388,40 +352,46 @@ _ENTRY(ITLBMiss_cmp) lwz r10, 0(r10) /* Get the pte */ 4: #if defined(ITLB_MISS_KERNEL) || defined(CONFIG_HUGETLB_PAGE) - mtcr r3 + mtcr r12 #endif - /* Insert the APG into the TWC from the Linux PTE. */ - rlwimi r11, r10, 0, 25, 26 - /* Load the MI_TWC with the attributes for this "segment." */ - MTSPR_CPU6(SPRN_MI_TWC, r11, r3) /* Set segment attributes */ -#if defined (CONFIG_HUGETLB_PAGE) && defined (CONFIG_PPC_4K_PAGES) - rlwimi r10, r11, 1, MI_SPS16K -#endif #ifdef CONFIG_SWAP - rlwinm r11, r10, 32-5, _PAGE_PRESENT - and r11, r11, r10 - rlwimi r10, r11, 0, _PAGE_PRESENT + rlwinm r11, r10, 31, _PAGE_ACCESSED >> 1 #endif - li r11, RPN_PATTERN + /* Load the MI_TWC with the attributes for this "segment." */ + mtspr SPRN_MI_TWC, r11 /* Set segment attributes */ + + li r11, RPN_PATTERN | 0x200 /* The Linux PTE won't go exactly into the MMU TLB. - * Software indicator bits 20-23 and 28 must be clear. - * Software indicator bits 24, 25, 26, and 27 must be + * Software indicator bits 20 and 23 must be clear. + * Software indicator bits 22, 24, 25, 26, and 27 must be * set. All other Linux PTE bits control the behavior * of the MMU. */ -#if defined (CONFIG_HUGETLB_PAGE) && defined (CONFIG_PPC_4K_PAGES) - rlwimi r10, r11, 0, 0x0ff0 /* Set 24-27, clear 20-23 */ -#else - rlwimi r10, r11, 0, 0x0ff8 /* Set 24-27, clear 20-23,28 */ -#endif - MTSPR_CPU6(SPRN_MI_RPN, r10, r3) /* Update TLB entry */ + rlwimi r11, r10, 4, 0x0400 /* Copy _PAGE_EXEC into bit 21 */ + rlwimi r10, r11, 0, 0x0ff0 /* Set 22, 24-27, clear 20,23 */ + mtspr SPRN_MI_RPN, r10 /* Update TLB entry */ /* Restore registers */ -#if defined(CONFIG_8xx_CPU6) || defined(ITLB_MISS_KERNEL) || defined(CONFIG_HUGETLB_PAGE) - mfspr r3, SPRN_SPRG_SCRATCH2 +_ENTRY(itlb_miss_exit_1) + mfspr r10, SPRN_SPRG_SCRATCH0 + mfspr r11, SPRN_SPRG_SCRATCH1 +#if defined(ITLB_MISS_KERNEL) || defined(CONFIG_HUGETLB_PAGE) + mfspr r12, SPRN_SPRG_SCRATCH2 +#endif + rfi +#ifdef CONFIG_PERF_EVENTS +_ENTRY(itlb_miss_perf) + lis r10, (itlb_miss_counter - PAGE_OFFSET)@ha + lwz r11, (itlb_miss_counter - PAGE_OFFSET)@l(r10) + addi r11, r11, 1 + stw r11, (itlb_miss_counter - PAGE_OFFSET)@l(r10) +#endif + mfspr r10, SPRN_SPRG_SCRATCH0 + mfspr r11, SPRN_SPRG_SCRATCH1 +#if defined(ITLB_MISS_KERNEL) || defined(CONFIG_HUGETLB_PAGE) + mfspr r12, SPRN_SPRG_SCRATCH2 #endif - EXCEPTION_EPILOG_0 rfi #ifdef CONFIG_HUGETLB_PAGE @@ -436,7 +406,6 @@ _ENTRY(ITLBMiss_cmp) rlwinm r10, r11, 0, ~HUGEPD_SHIFT_MASK #endif lwz r10, 0(r10) /* Get the pte */ - rlwinm r11, r11, 0, 0xf b 4b 20: /* 512k pages */ @@ -445,21 +414,15 @@ _ENTRY(ITLBMiss_cmp) /* Add level 2 base */ rlwimi r10, r11, 0, 0, 32 + PAGE_SHIFT_512K - (PAGE_SHIFT << 1) - 1 lwz r10, 0(r10) /* Get the pte */ - rlwinm r11, r11, 0, 0xf b 4b #endif . = 0x1200 DataStoreTLBMiss: - mtspr SPRN_SPRG_SCRATCH2, r3 - EXCEPTION_PROLOG_0 -#ifdef CONFIG_PPC_8xx_PERF_EVENT - lis r10, (dtlb_miss_counter - PAGE_OFFSET)@ha - lwz r11, (dtlb_miss_counter - PAGE_OFFSET)@l(r10) - addi r11, r11, 1 - stw r11, (dtlb_miss_counter - PAGE_OFFSET)@l(r10) -#endif - mfcr r3 + mtspr SPRN_SPRG_SCRATCH0, r10 + mtspr SPRN_SPRG_SCRATCH1, r11 + mtspr SPRN_SPRG_SCRATCH2, r12 + mfcr r12 /* If we are faulting a kernel address, we have to use the * kernel page tables. @@ -499,59 +462,49 @@ _ENTRY(DTLBMiss_jmp) rlwimi r10, r11, 0, 0, 32 - PAGE_SHIFT - 1 /* Add level 2 base */ lwz r10, 0(r10) /* Get the pte */ 4: - mtcr r3 + mtcr r12 - /* Insert the Guarded flag and APG into the TWC from the Linux PTE. - * It is bit 26-27 of both the Linux PTE and the TWC (at least + /* Insert the Guarded flag into the TWC from the Linux PTE. + * It is bit 27 of both the Linux PTE and the TWC (at least * I got that right :-). It will be better when we can put * this into the Linux pgd/pmd and load it in the operation * above. */ - rlwimi r11, r10, 0, 26, 27 - /* Insert the WriteThru flag into the TWC from the Linux PTE. - * It is bit 25 in the Linux PTE and bit 30 in the TWC - */ - rlwimi r11, r10, 32-5, 30, 30 - MTSPR_CPU6(SPRN_MD_TWC, r11, r3) - - /* In 4k pages mode, SPS (bit 28) in RPN must match PS[1] (bit 29) - * In 16k pages mode, SPS is always 1 */ -#if defined (CONFIG_HUGETLB_PAGE) && defined (CONFIG_PPC_4K_PAGES) - rlwimi r10, r11, 1, MD_SPS16K -#endif - /* Both _PAGE_ACCESSED and _PAGE_PRESENT has to be set. - * We also need to know if the insn is a load/store, so: - * Clear _PAGE_PRESENT and load that which will - * trap into DTLB Error with store bit set accordinly. - */ - /* PRESENT=0x1, ACCESSED=0x20 - * r11 = ((r10 & PRESENT) & ((r10 & ACCESSED) >> 5)); - * r10 = (r10 & ~PRESENT) | r11; - */ + rlwimi r11, r10, 0, _PAGE_GUARDED #ifdef CONFIG_SWAP - rlwinm r11, r10, 32-5, _PAGE_PRESENT - and r11, r11, r10 - rlwimi r10, r11, 0, _PAGE_PRESENT + /* _PAGE_ACCESSED has to be set. We use second APG bit for that, 0 + * on that bit will represent a Non Access group + */ + rlwinm r11, r10, 31, _PAGE_ACCESSED >> 1 #endif + mtspr SPRN_MD_TWC, r11 + /* The Linux PTE won't go exactly into the MMU TLB. - * Software indicator bits 22 and 28 must be clear. * Software indicator bits 24, 25, 26, and 27 must be * set. All other Linux PTE bits control the behavior * of the MMU. */ li r11, RPN_PATTERN -#if defined (CONFIG_HUGETLB_PAGE) && defined (CONFIG_PPC_4K_PAGES) rlwimi r10, r11, 0, 24, 27 /* Set 24-27 */ -#else - rlwimi r10, r11, 0, 24, 28 /* Set 24-27, clear 28 */ -#endif - rlwimi r10, r11, 0, 20, 20 /* clear 20 */ - MTSPR_CPU6(SPRN_MD_RPN, r10, r3) /* Update TLB entry */ + mtspr SPRN_MD_RPN, r10 /* Update TLB entry */ /* Restore registers */ - mfspr r3, SPRN_SPRG_SCRATCH2 mtspr SPRN_DAR, r11 /* Tag DAR */ - EXCEPTION_EPILOG_0 +_ENTRY(dtlb_miss_exit_1) + mfspr r10, SPRN_SPRG_SCRATCH0 + mfspr r11, SPRN_SPRG_SCRATCH1 + mfspr r12, SPRN_SPRG_SCRATCH2 + rfi +#ifdef CONFIG_PERF_EVENTS +_ENTRY(dtlb_miss_perf) + lis r10, (dtlb_miss_counter - PAGE_OFFSET)@ha + lwz r11, (dtlb_miss_counter - PAGE_OFFSET)@l(r10) + addi r11, r11, 1 + stw r11, (dtlb_miss_counter - PAGE_OFFSET)@l(r10) +#endif + mfspr r10, SPRN_SPRG_SCRATCH0 + mfspr r11, SPRN_SPRG_SCRATCH1 + mfspr r12, SPRN_SPRG_SCRATCH2 rfi #ifdef CONFIG_HUGETLB_PAGE @@ -566,7 +519,6 @@ _ENTRY(DTLBMiss_jmp) rlwinm r10, r11, 0, ~HUGEPD_SHIFT_MASK #endif lwz r10, 0(r10) /* Get the pte */ - rlwinm r11, r11, 0, 0xf b 4b 20: /* 512k pages */ @@ -575,7 +527,6 @@ _ENTRY(DTLBMiss_jmp) /* Add level 2 base */ rlwimi r10, r11, 0, 0, 32 + PAGE_SHIFT_512K - (PAGE_SHIFT << 1) - 1 lwz r10, 0(r10) /* Get the pte */ - rlwinm r11, r11, 0, 0xf b 4b #endif @@ -601,7 +552,8 @@ itlbie: */ . = 0x1400 DataTLBError: - EXCEPTION_PROLOG_0 + mtspr SPRN_SPRG_SCRATCH0, r10 + mtspr SPRN_SPRG_SCRATCH1, r11 mfcr r10 mfspr r11, SPRN_DAR @@ -636,7 +588,8 @@ dtlbie: */ . = 0x1c00 DataBreakpoint: - EXCEPTION_PROLOG_0 + mtspr SPRN_SPRG_SCRATCH0, r10 + mtspr SPRN_SPRG_SCRATCH1, r11 mfcr r10 mfspr r11, SPRN_SRR0 cmplwi cr0, r11, (dtlbie - PAGE_OFFSET)@l @@ -652,13 +605,15 @@ DataBreakpoint: EXC_XFER_EE(0x1c00, do_break) 11: mtcr r10 - EXCEPTION_EPILOG_0 + mfspr r10, SPRN_SPRG_SCRATCH0 + mfspr r11, SPRN_SPRG_SCRATCH1 rfi -#ifdef CONFIG_PPC_8xx_PERF_EVENT +#ifdef CONFIG_PERF_EVENTS . = 0x1d00 InstructionBreakpoint: - EXCEPTION_PROLOG_0 + mtspr SPRN_SPRG_SCRATCH0, r10 + mtspr SPRN_SPRG_SCRATCH1, r11 lis r10, (instruction_counter - PAGE_OFFSET)@ha lwz r11, (instruction_counter - PAGE_OFFSET)@l(r10) addi r11, r11, -1 @@ -666,7 +621,8 @@ InstructionBreakpoint: lis r10, 0xffff ori r10, r10, 0x01 mtspr SPRN_COUNTA, r10 - EXCEPTION_EPILOG_0 + mfspr r10, SPRN_SPRG_SCRATCH0 + mfspr r11, SPRN_SPRG_SCRATCH1 rfi #else EXCEPTION(0x1d00, Trap_1d, unknown_exception, EXC_XFER_EE) @@ -681,51 +637,57 @@ InstructionBreakpoint: * not enough space in the DataStoreTLBMiss area. */ DTLBMissIMMR: - mtcr r3 - /* Set 512k byte guarded page and mark it valid */ - li r10, MD_PS512K | MD_GUARDED | MD_SVALID - MTSPR_CPU6(SPRN_MD_TWC, r10, r11) + mtcr r12 + /* Set 512k byte guarded page and mark it valid and accessed */ + li r10, MD_PS512K | MD_GUARDED | MD_SVALID | M_APG2 + mtspr SPRN_MD_TWC, r10 mfspr r10, SPRN_IMMR /* Get current IMMR */ rlwinm r10, r10, 0, 0xfff80000 /* Get 512 kbytes boundary */ - ori r10, r10, 0xf0 | MD_SPS16K | _PAGE_SHARED | _PAGE_DIRTY | \ + ori r10, r10, 0xf0 | MD_SPS16K | _PAGE_PRIVILEGED | _PAGE_DIRTY | \ _PAGE_PRESENT | _PAGE_NO_CACHE - MTSPR_CPU6(SPRN_MD_RPN, r10, r11) /* Update TLB entry */ + mtspr SPRN_MD_RPN, r10 /* Update TLB entry */ li r11, RPN_PATTERN mtspr SPRN_DAR, r11 /* Tag DAR */ - mfspr r3, SPRN_SPRG_SCRATCH2 - EXCEPTION_EPILOG_0 +_ENTRY(dtlb_miss_exit_2) + mfspr r10, SPRN_SPRG_SCRATCH0 + mfspr r11, SPRN_SPRG_SCRATCH1 + mfspr r12, SPRN_SPRG_SCRATCH2 rfi DTLBMissLinear: - mtcr r3 - /* Set 8M byte page and mark it valid */ - li r11, MD_PS8MEG | MD_SVALID - MTSPR_CPU6(SPRN_MD_TWC, r11, r3) + mtcr r12 + /* Set 8M byte page and mark it valid and accessed */ + li r11, MD_PS8MEG | MD_SVALID | M_APG2 + mtspr SPRN_MD_TWC, r11 rlwinm r10, r10, 0, 0x0f800000 /* 8xx supports max 256Mb RAM */ - ori r10, r10, 0xf0 | MD_SPS16K | _PAGE_SHARED | _PAGE_DIRTY | \ + ori r10, r10, 0xf0 | MD_SPS16K | _PAGE_PRIVILEGED | _PAGE_DIRTY | \ _PAGE_PRESENT - MTSPR_CPU6(SPRN_MD_RPN, r10, r11) /* Update TLB entry */ + mtspr SPRN_MD_RPN, r10 /* Update TLB entry */ li r11, RPN_PATTERN mtspr SPRN_DAR, r11 /* Tag DAR */ - mfspr r3, SPRN_SPRG_SCRATCH2 - EXCEPTION_EPILOG_0 +_ENTRY(dtlb_miss_exit_3) + mfspr r10, SPRN_SPRG_SCRATCH0 + mfspr r11, SPRN_SPRG_SCRATCH1 + mfspr r12, SPRN_SPRG_SCRATCH2 rfi #ifndef CONFIG_PIN_TLB_TEXT ITLBMissLinear: - mtcr r3 - /* Set 8M byte page and mark it valid */ - li r11, MI_PS8MEG | MI_SVALID | _PAGE_EXEC - MTSPR_CPU6(SPRN_MI_TWC, r11, r3) + mtcr r12 + /* Set 8M byte page and mark it valid,accessed */ + li r11, MI_PS8MEG | MI_SVALID | M_APG2 + mtspr SPRN_MI_TWC, r11 rlwinm r10, r10, 0, 0x0f800000 /* 8xx supports max 256Mb RAM */ - ori r10, r10, 0xf0 | MI_SPS16K | _PAGE_SHARED | _PAGE_DIRTY | \ + ori r10, r10, 0xf0 | MI_SPS16K | _PAGE_PRIVILEGED | _PAGE_DIRTY | \ _PAGE_PRESENT - MTSPR_CPU6(SPRN_MI_RPN, r10, r11) /* Update TLB entry */ + mtspr SPRN_MI_RPN, r10 /* Update TLB entry */ - mfspr r3, SPRN_SPRG_SCRATCH2 - EXCEPTION_EPILOG_0 +_ENTRY(itlb_miss_exit_2) + mfspr r10, SPRN_SPRG_SCRATCH0 + mfspr r11, SPRN_SPRG_SCRATCH1 + mfspr r12, SPRN_SPRG_SCRATCH2 rfi #endif @@ -933,13 +895,6 @@ start_here: */ lis r6, swapper_pg_dir@ha tophys(r6,r6) -#ifdef CONFIG_8xx_CPU6 - lis r4, cpu6_errata_word@h - ori r4, r4, cpu6_errata_word@l - li r3, 0x3f80 - stw r3, 12(r4) - lwz r3, 12(r4) -#endif mtspr SPRN_M_TW, r6 lis r4,2f@h ori r4,r4,2f@l @@ -1004,8 +959,8 @@ initial_mmu: lis r8, KERNELBASE@h /* Create vaddr for TLB */ ori r8, r8, MI_EVALID /* Mark it valid */ mtspr SPRN_MI_EPN, r8 - li r8, MI_PS8MEG | (2 << 5) /* Set 8M byte page, APG 2 */ - ori r8, r8, MI_SVALID /* Make it valid */ + li r8, MI_PS8MEG /* Set 8M byte page */ + ori r8, r8, MI_SVALID | M_APG2 /* Make it valid, APG 2 */ mtspr SPRN_MI_TWC, r8 li r8, MI_BOOTINIT /* Create RPN for address 0 */ mtspr SPRN_MI_RPN, r8 /* Store TLB entry */ @@ -1032,7 +987,7 @@ initial_mmu: ori r8, r8, MD_EVALID /* Mark it valid */ mtspr SPRN_MD_EPN, r8 li r8, MD_PS512K | MD_GUARDED /* Set 512k byte page */ - ori r8, r8, MD_SVALID /* Make it valid */ + ori r8, r8, MD_SVALID | M_APG2 /* Make it valid and accessed */ mtspr SPRN_MD_TWC, r8 mr r8, r9 /* Create paddr for TLB */ ori r8, r8, MI_BOOTINIT|0x2 /* Inhibit cache -- Cort */ @@ -1061,7 +1016,7 @@ initial_mmu: #endif /* Disable debug mode entry on breakpoints */ mfspr r8, SPRN_DER -#ifdef CONFIG_PPC_8xx_PERF_EVENT +#ifdef CONFIG_PERF_EVENTS rlwinm r8, r8, 0, ~0xc #else rlwinm r8, r8, 0, ~0x8 @@ -1094,13 +1049,7 @@ swapper_pg_dir: abatron_pteptrs: .space 8 -#ifdef CONFIG_8xx_CPU6 - .globl cpu6_errata_word -cpu6_errata_word: - .space 16 -#endif - -#ifdef CONFIG_PPC_8xx_PERF_EVENT +#ifdef CONFIG_PERF_EVENTS .globl itlb_miss_counter itlb_miss_counter: .space 4 diff --git a/arch/powerpc/kernel/idle_book3e.S b/arch/powerpc/kernel/idle_book3e.S index 48c21acef915..2b269315d377 100644 --- a/arch/powerpc/kernel/idle_book3e.S +++ b/arch/powerpc/kernel/idle_book3e.S @@ -17,6 +17,7 @@ #include <asm/processor.h> #include <asm/thread_info.h> #include <asm/epapr_hcalls.h> +#include <asm/hw_irq.h> /* 64-bit version only for now */ #ifdef CONFIG_PPC64 @@ -46,8 +47,8 @@ _GLOBAL(\name) bl trace_hardirqs_on addi r1,r1,128 #endif - li r0,1 - stb r0,PACASOFTIRQEN(r13) + li r0,IRQS_ENABLED + stb r0,PACAIRQSOFTMASK(r13) /* Interrupts will make use return to LR, so get something we want * in there diff --git a/arch/powerpc/kernel/idle_power4.S b/arch/powerpc/kernel/idle_power4.S index f57a19348bdd..08faa93755f9 100644 --- a/arch/powerpc/kernel/idle_power4.S +++ b/arch/powerpc/kernel/idle_power4.S @@ -15,6 +15,7 @@ #include <asm/ppc_asm.h> #include <asm/asm-offsets.h> #include <asm/irqflags.h> +#include <asm/hw_irq.h> #undef DEBUG @@ -53,8 +54,8 @@ END_FTR_SECTION_IFCLR(CPU_FTR_CAN_NAP) mfmsr r7 #endif /* CONFIG_TRACE_IRQFLAGS */ - li r0,1 - stb r0,PACASOFTIRQEN(r13) /* we'll hard-enable shortly */ + li r0,IRQS_ENABLED + stb r0,PACAIRQSOFTMASK(r13) /* we'll hard-enable shortly */ BEGIN_FTR_SECTION DSSALL sync diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index b7a84522e652..f88038847790 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -67,6 +67,7 @@ #include <asm/smp.h> #include <asm/livepatch.h> #include <asm/asm-prototypes.h> +#include <asm/hw_irq.h> #ifdef CONFIG_PPC64 #include <asm/paca.h> @@ -106,12 +107,6 @@ static inline notrace unsigned long get_irq_happened(void) return happened; } -static inline notrace void set_soft_enabled(unsigned long enable) -{ - __asm__ __volatile__("stb %0,%1(13)" - : : "r" (enable), "i" (offsetof(struct paca_struct, soft_enabled))); -} - static inline notrace int decrementer_check_overflow(void) { u64 now = get_tb_or_rtc(); @@ -191,6 +186,11 @@ notrace unsigned int __check_irq_replay(void) return 0x900; } + if (happened & PACA_IRQ_PMI) { + local_paca->irq_happened &= ~PACA_IRQ_PMI; + return 0xf00; + } + if (happened & PACA_IRQ_EE) { local_paca->irq_happened &= ~PACA_IRQ_EE; return 0x500; @@ -224,15 +224,16 @@ notrace unsigned int __check_irq_replay(void) return 0; } -notrace void arch_local_irq_restore(unsigned long en) +notrace void arch_local_irq_restore(unsigned long mask) { unsigned char irq_happened; unsigned int replay; /* Write the new soft-enabled value */ - set_soft_enabled(en); - if (!en) + irq_soft_mask_set(mask); + if (mask) return; + /* * From this point onward, we can take interrupts, preempt, * etc... unless we got hard-disabled. We check if an event @@ -263,7 +264,7 @@ notrace void arch_local_irq_restore(unsigned long en) */ if (unlikely(irq_happened != PACA_IRQ_HARD_DIS)) __hard_irq_disable(); -#ifdef CONFIG_TRACE_IRQFLAGS +#ifdef CONFIG_PPC_IRQ_SOFT_MASK_DEBUG else { /* * We should already be hard disabled here. We had bugs @@ -274,9 +275,9 @@ notrace void arch_local_irq_restore(unsigned long en) if (WARN_ON(mfmsr() & MSR_EE)) __hard_irq_disable(); } -#endif /* CONFIG_TRACE_IRQFLAGS */ +#endif - set_soft_enabled(0); + irq_soft_mask_set(IRQS_ALL_DISABLED); trace_hardirqs_off(); /* @@ -288,7 +289,7 @@ notrace void arch_local_irq_restore(unsigned long en) /* We can soft-enable now */ trace_hardirqs_on(); - set_soft_enabled(1); + irq_soft_mask_set(IRQS_ENABLED); /* * And replay if we have to. This will return with interrupts @@ -363,7 +364,7 @@ bool prep_irq_for_idle(void) * of entering the low power state. */ local_paca->irq_happened &= ~PACA_IRQ_HARD_DIS; - local_paca->soft_enabled = 1; + irq_soft_mask_set(IRQS_ENABLED); /* Tell the caller to enter the low power state */ return true; diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c index 71e8a1b8c86e..efdd16a79075 100644 --- a/arch/powerpc/kernel/mce.c +++ b/arch/powerpc/kernel/mce.c @@ -495,37 +495,123 @@ long machine_check_early(struct pt_regs *regs) return handled; } -long hmi_exception_realmode(struct pt_regs *regs) +/* Possible meanings for HMER_DEBUG_TRIG bit being set on POWER9 */ +static enum { + DTRIG_UNKNOWN, + DTRIG_VECTOR_CI, /* need to emulate vector CI load instr */ + DTRIG_SUSPEND_ESCAPE, /* need to escape from TM suspend mode */ +} hmer_debug_trig_function; + +static int init_debug_trig_function(void) { - __this_cpu_inc(irq_stat.hmi_exceptions); - -#ifdef CONFIG_PPC_BOOK3S_64 - /* Workaround for P9 vector CI loads (see p9_hmi_special_emu) */ - if (pvr_version_is(PVR_POWER9)) { - unsigned long hmer = mfspr(SPRN_HMER); - - /* Do we have the debug bit set */ - if (hmer & PPC_BIT(17)) { - hmer &= ~PPC_BIT(17); - mtspr(SPRN_HMER, hmer); - - /* - * Now to avoid problems with soft-disable we - * only do the emulation if we are coming from - * user space - */ - if (user_mode(regs)) - local_paca->hmi_p9_special_emu = 1; - - /* - * Don't bother going to OPAL if that's the - * only relevant bit. - */ - if (!(hmer & mfspr(SPRN_HMEER))) - return local_paca->hmi_p9_special_emu; + int pvr; + struct device_node *cpun; + struct property *prop = NULL; + const char *str; + + /* First look in the device tree */ + preempt_disable(); + cpun = of_get_cpu_node(smp_processor_id(), NULL); + if (cpun) { + of_property_for_each_string(cpun, "ibm,hmi-special-triggers", + prop, str) { + if (strcmp(str, "bit17-vector-ci-load") == 0) + hmer_debug_trig_function = DTRIG_VECTOR_CI; + else if (strcmp(str, "bit17-tm-suspend-escape") == 0) + hmer_debug_trig_function = DTRIG_SUSPEND_ESCAPE; } + of_node_put(cpun); + } + preempt_enable(); + + /* If we found the property, don't look at PVR */ + if (prop) + goto out; + + pvr = mfspr(SPRN_PVR); + /* Check for POWER9 Nimbus (scale-out) */ + if ((PVR_VER(pvr) == PVR_POWER9) && (pvr & 0xe000) == 0) { + /* DD2.2 and later */ + if ((pvr & 0xfff) >= 0x202) + hmer_debug_trig_function = DTRIG_SUSPEND_ESCAPE; + /* DD2.0 and DD2.1 - used for vector CI load emulation */ + else if ((pvr & 0xfff) >= 0x200) + hmer_debug_trig_function = DTRIG_VECTOR_CI; + } + + out: + switch (hmer_debug_trig_function) { + case DTRIG_VECTOR_CI: + pr_debug("HMI debug trigger used for vector CI load\n"); + break; + case DTRIG_SUSPEND_ESCAPE: + pr_debug("HMI debug trigger used for TM suspend escape\n"); + break; + default: + break; } -#endif /* CONFIG_PPC_BOOK3S_64 */ + return 0; +} +__initcall(init_debug_trig_function); + +/* + * Handle HMIs that occur as a result of a debug trigger. + * Return values: + * -1 means this is not a HMI cause that we know about + * 0 means no further handling is required + * 1 means further handling is required + */ +long hmi_handle_debugtrig(struct pt_regs *regs) +{ + unsigned long hmer = mfspr(SPRN_HMER); + long ret = 0; + + /* HMER_DEBUG_TRIG bit is used for various workarounds on P9 */ + if (!((hmer & HMER_DEBUG_TRIG) + && hmer_debug_trig_function != DTRIG_UNKNOWN)) + return -1; + + hmer &= ~HMER_DEBUG_TRIG; + /* HMER is a write-AND register */ + mtspr(SPRN_HMER, ~HMER_DEBUG_TRIG); + + switch (hmer_debug_trig_function) { + case DTRIG_VECTOR_CI: + /* + * Now to avoid problems with soft-disable we + * only do the emulation if we are coming from + * host user space + */ + if (regs && user_mode(regs)) + ret = local_paca->hmi_p9_special_emu = 1; + + break; + + default: + break; + } + + /* + * See if any other HMI causes remain to be handled + */ + if (hmer & mfspr(SPRN_HMEER)) + return -1; + + return ret; +} + +/* + * Return values: + */ +long hmi_exception_realmode(struct pt_regs *regs) +{ + int ret; + + __this_cpu_inc(irq_stat.hmi_exceptions); + + ret = hmi_handle_debugtrig(regs); + if (ret >= 0) + return ret; wait_for_subcore_guest_exit(); diff --git a/arch/powerpc/kernel/mce_power.c b/arch/powerpc/kernel/mce_power.c index 644f7040b91c..fe6fc63251fe 100644 --- a/arch/powerpc/kernel/mce_power.c +++ b/arch/powerpc/kernel/mce_power.c @@ -58,115 +58,6 @@ static unsigned long addr_to_pfn(struct pt_regs *regs, unsigned long addr) return pte_pfn(*ptep); } -static void flush_tlb_206(unsigned int num_sets, unsigned int action) -{ - unsigned long rb; - unsigned int i; - - switch (action) { - case TLB_INVAL_SCOPE_GLOBAL: - rb = TLBIEL_INVAL_SET; - break; - case TLB_INVAL_SCOPE_LPID: - rb = TLBIEL_INVAL_SET_LPID; - break; - default: - BUG(); - break; - } - - asm volatile("ptesync" : : : "memory"); - for (i = 0; i < num_sets; i++) { - asm volatile("tlbiel %0" : : "r" (rb)); - rb += 1 << TLBIEL_INVAL_SET_SHIFT; - } - asm volatile("ptesync" : : : "memory"); -} - -static void flush_tlb_300(unsigned int num_sets, unsigned int action) -{ - unsigned long rb; - unsigned int i; - unsigned int r; - - switch (action) { - case TLB_INVAL_SCOPE_GLOBAL: - rb = TLBIEL_INVAL_SET; - break; - case TLB_INVAL_SCOPE_LPID: - rb = TLBIEL_INVAL_SET_LPID; - break; - default: - BUG(); - break; - } - - asm volatile("ptesync" : : : "memory"); - - if (early_radix_enabled()) - r = 1; - else - r = 0; - - /* - * First flush table/PWC caches with set 0, then flush the - * rest of the sets, partition scope. Radix must then do it - * all again with process scope. Hash just has to flush - * process table. - */ - asm volatile(PPC_TLBIEL(%0, %1, %2, %3, %4) : : - "r"(rb), "r"(0), "i"(2), "i"(0), "r"(r)); - for (i = 1; i < num_sets; i++) { - unsigned long set = i * (1<<TLBIEL_INVAL_SET_SHIFT); - - asm volatile(PPC_TLBIEL(%0, %1, %2, %3, %4) : : - "r"(rb+set), "r"(0), "i"(2), "i"(0), "r"(r)); - } - - asm volatile(PPC_TLBIEL(%0, %1, %2, %3, %4) : : - "r"(rb), "r"(0), "i"(2), "i"(1), "r"(r)); - if (early_radix_enabled()) { - for (i = 1; i < num_sets; i++) { - unsigned long set = i * (1<<TLBIEL_INVAL_SET_SHIFT); - - asm volatile(PPC_TLBIEL(%0, %1, %2, %3, %4) : : - "r"(rb+set), "r"(0), "i"(2), "i"(1), "r"(r)); - } - } - - asm volatile("ptesync" : : : "memory"); -} - -/* - * Generic routines to flush TLB on POWER processors. These routines - * are used as flush_tlb hook in the cpu_spec. - * - * action => TLB_INVAL_SCOPE_GLOBAL: Invalidate all TLBs. - * TLB_INVAL_SCOPE_LPID: Invalidate TLB for current LPID. - */ -void __flush_tlb_power7(unsigned int action) -{ - flush_tlb_206(POWER7_TLB_SETS, action); -} - -void __flush_tlb_power8(unsigned int action) -{ - flush_tlb_206(POWER8_TLB_SETS, action); -} - -void __flush_tlb_power9(unsigned int action) -{ - unsigned int num_sets; - - if (early_radix_enabled()) - num_sets = POWER9_TLB_SETS_RADIX; - else - num_sets = POWER9_TLB_SETS_HASH; - - flush_tlb_300(num_sets, action); -} - - /* flush SLBs and reload */ #ifdef CONFIG_PPC_BOOK3S_64 static void flush_and_reload_slb(void) @@ -226,10 +117,8 @@ static int mce_flush(int what) return 1; } if (what == MCE_FLUSH_TLB) { - if (cur_cpu_spec && cur_cpu_spec->flush_tlb) { - cur_cpu_spec->flush_tlb(TLB_INVAL_SCOPE_GLOBAL); - return 1; - } + tlbiel_all(); + return 1; } return 0; diff --git a/arch/powerpc/kernel/module.lds b/arch/powerpc/kernel/module.lds new file mode 100644 index 000000000000..cea5dc124be4 --- /dev/null +++ b/arch/powerpc/kernel/module.lds @@ -0,0 +1,8 @@ +/* Force alignment of .toc section. */ +SECTIONS +{ + .toc 0 : ALIGN(256) + { + *(.got .toc) + } +} diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c index 218971ac7e04..a2636c250b7b 100644 --- a/arch/powerpc/kernel/module_64.c +++ b/arch/powerpc/kernel/module_64.c @@ -348,8 +348,11 @@ int module_frob_arch_sections(Elf64_Ehdr *hdr, char *p; if (strcmp(secstrings + sechdrs[i].sh_name, ".stubs") == 0) me->arch.stubs_section = i; - else if (strcmp(secstrings + sechdrs[i].sh_name, ".toc") == 0) + else if (strcmp(secstrings + sechdrs[i].sh_name, ".toc") == 0) { me->arch.toc_section = i; + if (sechdrs[i].sh_addralign < 8) + sechdrs[i].sh_addralign = 8; + } else if (strcmp(secstrings+sechdrs[i].sh_name,"__versions")==0) dedotify_versions((void *)hdr + sechdrs[i].sh_offset, sechdrs[i].sh_size); @@ -387,12 +390,15 @@ int module_frob_arch_sections(Elf64_Ehdr *hdr, return 0; } -/* r2 is the TOC pointer: it actually points 0x8000 into the TOC (this - gives the value maximum span in an instruction which uses a signed - offset) */ +/* + * r2 is the TOC pointer: it actually points 0x8000 into the TOC (this gives the + * value maximum span in an instruction which uses a signed offset). Round down + * to a 256 byte boundary for the odd case where we are setting up r2 without a + * .toc section. + */ static inline unsigned long my_r2(const Elf64_Shdr *sechdrs, struct module *me) { - return sechdrs[me->arch.toc_section].sh_addr + 0x8000; + return (sechdrs[me->arch.toc_section].sh_addr & ~0xfful) + 0x8000; } /* Both low and high 16 bits are added as SIGNED additions, so if low @@ -501,12 +507,22 @@ static bool is_early_mcount_callsite(u32 *instruction) restore r2. */ static int restore_r2(u32 *instruction, struct module *me) { - if (is_early_mcount_callsite(instruction - 1)) + u32 *prev_insn = instruction - 1; + + if (is_early_mcount_callsite(prev_insn)) + return 1; + + /* + * Make sure the branch isn't a sibling call. Sibling calls aren't + * "link" branches and they don't return, so they don't need the r2 + * restore afterwards. + */ + if (!instr_is_relative_link_branch(*prev_insn)) return 1; if (*instruction != PPC_INST_NOP) { - pr_err("%s: Expect noop after relocate, got %08x\n", - me->name, *instruction); + pr_err("%s: Expected nop after call, got %08x at %pS\n", + me->name, *instruction, instruction); return 0; } /* ld r2,R2_STACK_OFFSET(r1) */ @@ -628,7 +644,8 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, case R_PPC_REL24: /* FIXME: Handle weak symbols here --RR */ - if (sym->st_shndx == SHN_UNDEF) { + if (sym->st_shndx == SHN_UNDEF || + sym->st_shndx == SHN_LIVEPATCH) { /* External: go via stub */ value = stub_for_addr(sechdrs, value, me); if (!value) diff --git a/arch/powerpc/kernel/optprobes_head.S b/arch/powerpc/kernel/optprobes_head.S index 52fc864cdec4..98a3aeeb3c8c 100644 --- a/arch/powerpc/kernel/optprobes_head.S +++ b/arch/powerpc/kernel/optprobes_head.S @@ -58,7 +58,7 @@ optprobe_template_entry: std r5,_XER(r1) mfcr r5 std r5,_CCR(r1) - lbz r5,PACASOFTIRQEN(r13) + lbz r5,PACAIRQSOFTMASK(r13) std r5,SOFTE(r1) /* diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c index d6597038931d..95ffedf14885 100644 --- a/arch/powerpc/kernel/paca.c +++ b/arch/powerpc/kernel/paca.c @@ -18,6 +18,8 @@ #include <asm/pgtable.h> #include <asm/kexec.h> +#include "setup.h" + #ifdef CONFIG_PPC_BOOK3S /* @@ -208,15 +210,14 @@ void __init allocate_pacas(void) u64 limit; int cpu; - limit = ppc64_rma_size; - #ifdef CONFIG_PPC_BOOK3S_64 /* - * We can't take SLB misses on the paca, and we want to access them - * in real mode, so allocate them within the RMA and also within - * the first segment. + * We access pacas in real mode, and cannot take SLB faults + * on them when in virtual mode, so allocate them accordingly. */ - limit = min(0x10000000ULL, limit); + limit = min(ppc64_bolted_size(), ppc64_rma_size); +#else + limit = ppc64_rma_size; #endif paca_size = PAGE_ALIGN(sizeof(struct paca_struct) * nr_cpu_ids); diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index 590f4d0a6cb1..208e623b2557 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -249,8 +249,31 @@ resource_size_t pcibios_iov_resource_alignment(struct pci_dev *pdev, int resno) return pci_iov_resource_size(pdev, resno); } + +int pcibios_sriov_enable(struct pci_dev *pdev, u16 num_vfs) +{ + if (ppc_md.pcibios_sriov_enable) + return ppc_md.pcibios_sriov_enable(pdev, num_vfs); + + return 0; +} + +int pcibios_sriov_disable(struct pci_dev *pdev) +{ + if (ppc_md.pcibios_sriov_disable) + return ppc_md.pcibios_sriov_disable(pdev); + + return 0; +} + #endif /* CONFIG_PCI_IOV */ +void pcibios_bus_add_device(struct pci_dev *pdev) +{ + if (ppc_md.pcibios_bus_add_device) + ppc_md.pcibios_bus_add_device(pdev); +} + static resource_size_t pcibios_io_size(const struct pci_controller *hose) { #ifdef CONFIG_PPC64 @@ -1276,8 +1299,8 @@ static void pcibios_allocate_bus_resources(struct pci_bus *bus) i + PCI_BRIDGE_RESOURCES) == 0) continue; } - pr_warning("PCI: Cannot allocate resource region " - "%d of PCI bridge %d, will remap\n", i, bus->number); + pr_warn("PCI: Cannot allocate resource region %d of PCI bridge %d, will remap\n", + i, bus->number); clear_resource: /* The resource might be figured out when doing * reassignment based on the resources required diff --git a/arch/powerpc/kernel/pci_dn.c b/arch/powerpc/kernel/pci_dn.c index 0e395afbf0f4..ab147a1909c8 100644 --- a/arch/powerpc/kernel/pci_dn.c +++ b/arch/powerpc/kernel/pci_dn.c @@ -156,10 +156,8 @@ static struct pci_dn *add_one_dev_pci_data(struct pci_dn *parent, pdn->parent = parent; pdn->busno = busno; pdn->devfn = devfn; -#ifdef CONFIG_PPC_POWERNV pdn->vf_index = vf_index; pdn->pe_number = IODA_INVALID_PE; -#endif INIT_LIST_HEAD(&pdn->child_list); INIT_LIST_HEAD(&pdn->list); list_add_tail(&pdn->list, &parent->child_list); @@ -226,9 +224,7 @@ void remove_dev_pci_data(struct pci_dev *pdev) */ if (pdev->is_virtfn) { pdn = pci_get_pdn(pdev); -#ifdef CONFIG_PPC_POWERNV pdn->pe_number = IODA_INVALID_PE; -#endif return; } @@ -294,9 +290,7 @@ struct pci_dn *pci_add_device_node_info(struct pci_controller *hose, return NULL; dn->data = pdn; pdn->phb = hose; -#ifdef CONFIG_PPC_POWERNV pdn->pe_number = IODA_INVALID_PE; -#endif regs = of_get_property(dn, "reg", NULL); if (regs) { u32 addr = of_read_number(regs, 1); diff --git a/arch/powerpc/kernel/pci_of_scan.c b/arch/powerpc/kernel/pci_of_scan.c index 0d790f8432d2..20ceec4a5f5e 100644 --- a/arch/powerpc/kernel/pci_of_scan.c +++ b/arch/powerpc/kernel/pci_of_scan.c @@ -38,7 +38,7 @@ static u32 get_int_prop(struct device_node *np, const char *name, u32 def) * @addr0: value of 1st cell of a device tree PCI address. * @bridge: Set this flag if the address is from a bridge 'ranges' property */ -static unsigned int pci_parse_of_flags(u32 addr0, int bridge) +unsigned int pci_parse_of_flags(u32 addr0, int bridge) { unsigned int flags = 0; diff --git a/arch/powerpc/kernel/proc_powerpc.c b/arch/powerpc/kernel/proc_powerpc.c index 56548bf6231f..9bfbd800d32f 100644 --- a/arch/powerpc/kernel/proc_powerpc.c +++ b/arch/powerpc/kernel/proc_powerpc.c @@ -63,7 +63,7 @@ static int __init proc_ppc64_init(void) { struct proc_dir_entry *pde; - pde = proc_create_data("powerpc/systemcfg", S_IFREG|S_IRUGO, NULL, + pde = proc_create_data("powerpc/systemcfg", S_IFREG | 0444, NULL, &page_map_fops, vdso_data); if (!pde) return 1; diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 4208cbe2fb7f..1738c4127b32 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -42,6 +42,7 @@ #include <linux/hw_breakpoint.h> #include <linux/uaccess.h> #include <linux/elf-randomize.h> +#include <linux/pkeys.h> #include <asm/pgtable.h> #include <asm/io.h> @@ -57,6 +58,7 @@ #include <asm/debug.h> #ifdef CONFIG_PPC64 #include <asm/firmware.h> +#include <asm/hw_irq.h> #endif #include <asm/code-patching.h> #include <asm/exec.h> @@ -1097,6 +1099,8 @@ static inline void save_sprs(struct thread_struct *t) t->tar = mfspr(SPRN_TAR); } #endif + + thread_pkey_regs_save(t); } static inline void restore_sprs(struct thread_struct *old_thread, @@ -1136,6 +1140,8 @@ static inline void restore_sprs(struct thread_struct *old_thread, old_thread->tidr != new_thread->tidr) mtspr(SPRN_TIDR, new_thread->tidr); #endif + + thread_pkey_regs_restore(new_thread, old_thread); } #ifdef CONFIG_PPC_BOOK3S_64 @@ -1404,7 +1410,7 @@ void show_regs(struct pt_regs * regs) print_msr_bits(regs->msr); pr_cont(" CR: %08lx XER: %08lx\n", regs->ccr, regs->xer); trap = TRAP(regs); - if ((regs->trap != 0xc00) && cpu_has_feature(CPU_FTR_CFAR)) + if ((TRAP(regs) != 0xc00) && cpu_has_feature(CPU_FTR_CFAR)) pr_cont("CFAR: "REG" ", regs->orig_gpr3); if (trap == 0x200 || trap == 0x300 || trap == 0x600) #if defined(CONFIG_4xx) || defined(CONFIG_BOOKE) @@ -1504,14 +1510,15 @@ 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(&vas_thread_id_lock); + spin_lock_irqsave(&vas_thread_id_lock, flags); err = ida_get_new_above(&vas_thread_ida, 1, &index); - spin_unlock(&vas_thread_id_lock); + spin_unlock_irqrestore(&vas_thread_id_lock, flags); if (err == -EAGAIN) goto again; @@ -1519,9 +1526,9 @@ again: return err; if (index > MAX_THREAD_CONTEXT) { - spin_lock(&vas_thread_id_lock); + spin_lock_irqsave(&vas_thread_id_lock, flags); ida_remove(&vas_thread_ida, index); - spin_unlock(&vas_thread_id_lock); + spin_unlock_irqrestore(&vas_thread_id_lock, flags); return -ENOMEM; } @@ -1530,9 +1537,11 @@ again: static void free_thread_tidr(int id) { - spin_lock(&vas_thread_id_lock); + unsigned long flags; + + spin_lock_irqsave(&vas_thread_id_lock, flags); ida_remove(&vas_thread_ida, id); - spin_unlock(&vas_thread_id_lock); + spin_unlock_irqrestore(&vas_thread_id_lock, flags); } /* @@ -1584,6 +1593,7 @@ int set_thread_tidr(struct task_struct *t) return 0; } +EXPORT_SYMBOL_GPL(set_thread_tidr); #endif /* CONFIG_PPC64 */ @@ -1669,7 +1679,7 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, childregs->gpr[14] = ppc_function_entry((void *)usp); #ifdef CONFIG_PPC64 clear_tsk_thread_flag(p, TIF_32BIT); - childregs->softe = 1; + childregs->softe = IRQS_ENABLED; #endif childregs->gpr[15] = kthread_arg; p->thread.regs = NULL; /* no user register state */ @@ -1860,6 +1870,8 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp) current->thread.tm_tfiar = 0; current->thread.load_tm = 0; #endif /* CONFIG_PPC_TRANSACTIONAL_MEM */ + + thread_pkey_regs_init(¤t->thread); } EXPORT_SYMBOL(start_thread); diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index b15bae265c90..4dffef947b8a 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -59,6 +59,7 @@ #include <asm/epapr_hcalls.h> #include <asm/firmware.h> #include <asm/dt_cpu_ftrs.h> +#include <asm/drmem.h> #include <mm/mmu_decl.h> @@ -455,92 +456,74 @@ static int __init early_init_dt_scan_chosen_ppc(unsigned long node, #ifdef CONFIG_PPC_PSERIES /* - * Interpret the ibm,dynamic-memory property in the - * /ibm,dynamic-reconfiguration-memory node. + * Interpret the ibm dynamic reconfiguration memory LMBs. * This contains a list of memory blocks along with NUMA affinity * information. */ -static int __init early_init_dt_scan_drconf_memory(unsigned long node) +static void __init early_init_drmem_lmb(struct drmem_lmb *lmb, + const __be32 **usm) { - const __be32 *dm, *ls, *usm; - int l; - unsigned long n, flags; - u64 base, size, memblock_size; - unsigned int is_kexec_kdump = 0, rngs; - - ls = of_get_flat_dt_prop(node, "ibm,lmb-size", &l); - if (ls == NULL || l < dt_root_size_cells * sizeof(__be32)) - return 0; - memblock_size = dt_mem_next_cell(dt_root_size_cells, &ls); + u64 base, size; + int is_kexec_kdump = 0, rngs; - dm = of_get_flat_dt_prop(node, "ibm,dynamic-memory", &l); - if (dm == NULL || l < sizeof(__be32)) - return 0; + base = lmb->base_addr; + size = drmem_lmb_size(); + rngs = 1; - n = of_read_number(dm++, 1); /* number of entries */ - if (l < (n * (dt_root_addr_cells + 4) + 1) * sizeof(__be32)) - return 0; + /* + * Skip this block if the reserved bit is set in flags + * or if the block is not assigned to this partition. + */ + if ((lmb->flags & DRCONF_MEM_RESERVED) || + !(lmb->flags & DRCONF_MEM_ASSIGNED)) + return; - /* check if this is a kexec/kdump kernel. */ - usm = of_get_flat_dt_prop(node, "linux,drconf-usable-memory", - &l); - if (usm != NULL) + if (*usm) is_kexec_kdump = 1; - for (; n != 0; --n) { - base = dt_mem_next_cell(dt_root_addr_cells, &dm); - flags = of_read_number(&dm[3], 1); - /* skip DRC index, pad, assoc. list index, flags */ - dm += 4; - /* skip this block if the reserved bit is set in flags - or if the block is not assigned to this partition */ - if ((flags & DRCONF_MEM_RESERVED) || - !(flags & DRCONF_MEM_ASSIGNED)) - continue; - size = memblock_size; - rngs = 1; + if (is_kexec_kdump) { + /* + * For each memblock in ibm,dynamic-memory, a + * corresponding entry in linux,drconf-usable-memory + * property contains a counter 'p' followed by 'p' + * (base, size) duple. Now read the counter from + * linux,drconf-usable-memory property + */ + rngs = dt_mem_next_cell(dt_root_size_cells, usm); + if (!rngs) /* there are no (base, size) duple */ + return; + } + + do { if (is_kexec_kdump) { - /* - * For each memblock in ibm,dynamic-memory, a corresponding - * entry in linux,drconf-usable-memory property contains - * a counter 'p' followed by 'p' (base, size) duple. - * Now read the counter from - * linux,drconf-usable-memory property - */ - rngs = dt_mem_next_cell(dt_root_size_cells, &usm); - if (!rngs) /* there are no (base, size) duple */ + base = dt_mem_next_cell(dt_root_addr_cells, usm); + size = dt_mem_next_cell(dt_root_size_cells, usm); + } + + if (iommu_is_off) { + if (base >= 0x80000000ul) continue; + if ((base + size) > 0x80000000ul) + size = 0x80000000ul - base; } - do { - if (is_kexec_kdump) { - base = dt_mem_next_cell(dt_root_addr_cells, - &usm); - size = dt_mem_next_cell(dt_root_size_cells, - &usm); - } - if (iommu_is_off) { - if (base >= 0x80000000ul) - continue; - if ((base + size) > 0x80000000ul) - size = 0x80000000ul - base; - } - memblock_add(base, size); - } while (--rngs); - } - memblock_dump_all(); - return 0; + + DBG("Adding: %llx -> %llx\n", base, size); + memblock_add(base, size); + } while (--rngs); } -#else -#define early_init_dt_scan_drconf_memory(node) 0 #endif /* CONFIG_PPC_PSERIES */ static int __init early_init_dt_scan_memory_ppc(unsigned long node, const char *uname, int depth, void *data) { +#ifdef CONFIG_PPC_PSERIES if (depth == 1 && - strcmp(uname, "ibm,dynamic-reconfiguration-memory") == 0) - return early_init_dt_scan_drconf_memory(node); + strcmp(uname, "ibm,dynamic-reconfiguration-memory") == 0) { + walk_drmem_lmbs_early(node, early_init_drmem_lmb); + return 0; + } +#endif return early_init_dt_scan_memory(node, uname, depth, data); } diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index 02190e90c7ae..adf044daafd7 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -869,10 +869,12 @@ struct ibm_arch_vec __cacheline_aligned ibm_architecture_vec = { .reserved2 = 0, .reserved3 = 0, .subprocessors = 1, + .byte22 = OV5_FEAT(OV5_DRMEM_V2), .intarch = 0, .mmu = 0, .hash_ext = 0, .radix_ext = 0, + .byte22 = OV5_FEAT(OV5_DRC_INFO), }, /* option vector 6: IBM PAPR hints */ diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c index f52ad5bb7109..ca72d7391d40 100644 --- a/arch/powerpc/kernel/ptrace.c +++ b/arch/powerpc/kernel/ptrace.c @@ -35,6 +35,7 @@ #include <linux/context_tracking.h> #include <linux/uaccess.h> +#include <linux/pkeys.h> #include <asm/page.h> #include <asm/pgtable.h> #include <asm/switch_to.h> @@ -283,6 +284,18 @@ int ptrace_get_reg(struct task_struct *task, int regno, unsigned long *data) if (regno == PT_DSCR) return get_user_dscr(task, data); +#ifdef CONFIG_PPC64 + /* + * softe copies paca->irq_soft_mask variable state. Since irq_soft_mask is + * no more used as a flag, lets force usr to alway see the softe value as 1 + * which means interrupts are not soft disabled. + */ + if (regno == PT_SOFTE) { + *data = 1; + return 0; + } +#endif + if (regno < (sizeof(struct pt_regs) / sizeof(unsigned long))) { *data = ((unsigned long *)task->thread.regs)[regno]; return 0; @@ -1775,6 +1788,61 @@ static int pmu_set(struct task_struct *target, return ret; } #endif + +#ifdef CONFIG_PPC_MEM_KEYS +static int pkey_active(struct task_struct *target, + const struct user_regset *regset) +{ + if (!arch_pkeys_enabled()) + return -ENODEV; + + return regset->n; +} + +static int pkey_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + BUILD_BUG_ON(TSO(amr) + sizeof(unsigned long) != TSO(iamr)); + BUILD_BUG_ON(TSO(iamr) + sizeof(unsigned long) != TSO(uamor)); + + if (!arch_pkeys_enabled()) + return -ENODEV; + + return user_regset_copyout(&pos, &count, &kbuf, &ubuf, + &target->thread.amr, 0, + ELF_NPKEY * sizeof(unsigned long)); +} + +static int pkey_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + u64 new_amr; + int ret; + + if (!arch_pkeys_enabled()) + return -ENODEV; + + /* Only the AMR can be set from userspace */ + if (pos != 0 || count != sizeof(new_amr)) + return -EINVAL; + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &new_amr, 0, sizeof(new_amr)); + if (ret) + return ret; + + /* UAMOR determines which bits of the AMR can be set from userspace. */ + target->thread.amr = (new_amr & target->thread.uamor) | + (target->thread.amr & ~target->thread.uamor); + + return 0; +} +#endif /* CONFIG_PPC_MEM_KEYS */ + /* * These are our native regset flavors. */ @@ -1809,6 +1877,9 @@ enum powerpc_regset { REGSET_EBB, /* EBB registers */ REGSET_PMR, /* Performance Monitor Registers */ #endif +#ifdef CONFIG_PPC_MEM_KEYS + REGSET_PKEY, /* AMR register */ +#endif }; static const struct user_regset native_regsets[] = { @@ -1914,6 +1985,13 @@ static const struct user_regset native_regsets[] = { .active = pmu_active, .get = pmu_get, .set = pmu_set }, #endif +#ifdef CONFIG_PPC_MEM_KEYS + [REGSET_PKEY] = { + .core_note_type = NT_PPC_PKEY, .n = ELF_NPKEY, + .size = sizeof(u64), .align = sizeof(u64), + .active = pkey_active, .get = pkey_get, .set = pkey_set + }, +#endif }; static const struct user_regset_view user_ppc_native_view = { diff --git a/arch/powerpc/kernel/rtas-proc.c b/arch/powerpc/kernel/rtas-proc.c index c8c5f3a550c2..fb070d8cad07 100644 --- a/arch/powerpc/kernel/rtas-proc.c +++ b/arch/powerpc/kernel/rtas-proc.c @@ -261,19 +261,19 @@ static int __init proc_rtas_init(void) if (rtas_node == NULL) return -ENODEV; - proc_create("powerpc/rtas/progress", S_IRUGO|S_IWUSR, NULL, + proc_create("powerpc/rtas/progress", 0644, NULL, &ppc_rtas_progress_operations); - proc_create("powerpc/rtas/clock", S_IRUGO|S_IWUSR, NULL, + proc_create("powerpc/rtas/clock", 0644, NULL, &ppc_rtas_clock_operations); - proc_create("powerpc/rtas/poweron", S_IWUSR|S_IRUGO, NULL, + proc_create("powerpc/rtas/poweron", 0644, NULL, &ppc_rtas_poweron_operations); - proc_create("powerpc/rtas/sensors", S_IRUGO, NULL, + proc_create("powerpc/rtas/sensors", 0444, NULL, &ppc_rtas_sensors_operations); - proc_create("powerpc/rtas/frequency", S_IWUSR|S_IRUGO, NULL, + proc_create("powerpc/rtas/frequency", 0644, NULL, &ppc_rtas_tone_freq_operations); - proc_create("powerpc/rtas/volume", S_IWUSR|S_IRUGO, NULL, + proc_create("powerpc/rtas/volume", 0644, NULL, &ppc_rtas_tone_volume_operations); - proc_create("powerpc/rtas/rmo_buffer", S_IRUSR, NULL, + proc_create("powerpc/rtas/rmo_buffer", 0400, NULL, &ppc_rtas_rmo_buf_ops); return 0; } diff --git a/arch/powerpc/kernel/rtas_flash.c b/arch/powerpc/kernel/rtas_flash.c index f6f6a8a5103a..10fabae2574d 100644 --- a/arch/powerpc/kernel/rtas_flash.c +++ b/arch/powerpc/kernel/rtas_flash.c @@ -727,7 +727,7 @@ static int __init rtas_flash_init(void) const struct rtas_flash_file *f = &rtas_flash_files[i]; int token; - if (!proc_create(f->filename, S_IRUSR | S_IWUSR, NULL, &f->fops)) + if (!proc_create(f->filename, 0600, NULL, &f->fops)) goto enomem; /* diff --git a/arch/powerpc/kernel/rtasd.c b/arch/powerpc/kernel/rtasd.c index 1da8b7d8c6ca..fc600a8b1e77 100644 --- a/arch/powerpc/kernel/rtasd.c +++ b/arch/powerpc/kernel/rtasd.c @@ -581,7 +581,7 @@ static int __init rtas_init(void) if (!rtas_log_buf) return -ENODEV; - entry = proc_create("powerpc/rtas/error_log", S_IRUSR, NULL, + entry = proc_create("powerpc/rtas/error_log", 0400, NULL, &proc_rtas_log_operations); if (!entry) printk(KERN_ERR "Failed to create error_log proc entry\n"); diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index 3f33869c6486..d73ec518ef80 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -346,10 +346,8 @@ static int show_cpuinfo(struct seq_file *m, void *v) loops_per_jiffy / (500000/HZ), (loops_per_jiffy / (5000/HZ)) % 100); #endif - -#ifdef CONFIG_SMP seq_printf(m, "\n"); -#endif + /* If this is the last cpu, print the summary */ if (cpumask_next(cpu_id, cpu_online_mask) >= nr_cpu_ids) show_cpuinfo_summary(m); @@ -379,10 +377,10 @@ static void c_stop(struct seq_file *m, void *v) } const struct seq_operations cpuinfo_op = { - .start =c_start, - .next = c_next, - .stop = c_stop, - .show = show_cpuinfo, + .start = c_start, + .next = c_next, + .stop = c_stop, + .show = show_cpuinfo, }; void __init check_for_initrd(void) @@ -459,13 +457,13 @@ static void __init cpu_init_thread_core_maps(int tpc) */ void __init smp_setup_cpu_maps(void) { - struct device_node *dn = NULL; + struct device_node *dn; int cpu = 0; int nthreads = 1; DBG("smp_setup_cpu_maps()\n"); - while ((dn = of_find_node_by_type(dn, "cpu")) && cpu < nr_cpu_ids) { + for_each_node_by_type(dn, "cpu") { const __be32 *intserv; __be32 cpu_be; int j, len; @@ -505,6 +503,11 @@ void __init smp_setup_cpu_maps(void) set_cpu_possible(cpu, true); cpu++; } + + if (cpu >= nr_cpu_ids) { + of_node_put(dn); + break; + } } /* If no SMT supported, nthreads is forced to 1 */ diff --git a/arch/powerpc/kernel/setup.h b/arch/powerpc/kernel/setup.h index 21c18071d9d5..3fc11e30308f 100644 --- a/arch/powerpc/kernel/setup.h +++ b/arch/powerpc/kernel/setup.h @@ -51,6 +51,10 @@ void record_spr_defaults(void); static inline void record_spr_defaults(void) { }; #endif +#ifdef CONFIG_PPC64 +u64 ppc64_bolted_size(void); +#endif + /* * Having this in kvm_ppc.h makes include dependencies too * tricky to solve for setup-common.c so have it here. diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index e67413f4a8f0..c388cc3357fa 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -10,8 +10,6 @@ * 2 of the License, or (at your option) any later version. */ -#define DEBUG - #include <linux/export.h> #include <linux/string.h> #include <linux/sched.h> @@ -69,6 +67,7 @@ #include <asm/livepatch.h> #include <asm/opal.h> #include <asm/cputhreads.h> +#include <asm/hw_irq.h> #include "setup.h" @@ -190,6 +189,8 @@ static void __init fixup_boot_paca(void) get_paca()->cpu_start = 1; /* Allow percpu accesses to work until we setup percpu data */ get_paca()->data_offset = 0; + /* Mark interrupts disabled in PACA */ + irq_soft_mask_set(IRQS_DISABLED); } static void __init configure_exceptions(void) @@ -352,7 +353,7 @@ void __init early_setup(unsigned long dt_ptr) void early_setup_secondary(void) { /* Mark interrupts disabled in PACA */ - get_paca()->soft_enabled = 0; + irq_soft_mask_set(IRQS_DISABLED); /* Initialize the hash table or TLB handling */ early_init_mmu_secondary(); @@ -568,25 +569,31 @@ void __init initialize_cache_info(void) DBG(" <- initialize_cache_info()\n"); } -/* This returns the limit below which memory accesses to the linear - * mapping are guarnateed not to cause a TLB or SLB miss. This is - * used to allocate interrupt or emergency stacks for which our - * exception entry path doesn't deal with being interrupted. +/* + * This returns the limit below which memory accesses to the linear + * mapping are guarnateed not to cause an architectural exception (e.g., + * TLB or SLB miss fault). + * + * This is used to allocate PACAs and various interrupt stacks that + * that are accessed early in interrupt handlers that must not cause + * re-entrant interrupts. */ -static __init u64 safe_stack_limit(void) +__init u64 ppc64_bolted_size(void) { #ifdef CONFIG_PPC_BOOK3E /* Freescale BookE bolts the entire linear mapping */ - if (mmu_has_feature(MMU_FTR_TYPE_FSL_E)) + /* XXX: BookE ppc64_rma_limit setup seems to disagree? */ + if (early_mmu_has_feature(MMU_FTR_TYPE_FSL_E)) return linear_map_top; /* Other BookE, we assume the first GB is bolted */ return 1ul << 30; #else + /* BookS radix, does not take faults on linear mapping */ if (early_radix_enabled()) return ULONG_MAX; - /* BookS, the first segment is bolted */ - if (mmu_has_feature(MMU_FTR_1T_SEGMENT)) + /* BookS hash, the first segment is bolted */ + if (early_mmu_has_feature(MMU_FTR_1T_SEGMENT)) return 1UL << SID_SHIFT_1T; return 1UL << SID_SHIFT; #endif @@ -594,7 +601,7 @@ static __init u64 safe_stack_limit(void) void __init irqstack_early_init(void) { - u64 limit = safe_stack_limit(); + u64 limit = ppc64_bolted_size(); unsigned int i; /* @@ -679,7 +686,7 @@ void __init emergency_stack_init(void) * initialized in kernel/irq.c. These are initialized here in order * to have emergency stacks available as early as possible. */ - limit = min(safe_stack_limit(), ppc64_rma_size); + limit = min(ppc64_bolted_size(), ppc64_rma_size); for_each_possible_cpu(i) { struct thread_info *ti; @@ -857,7 +864,7 @@ static void init_fallback_flush(void) int cpu; l1d_size = ppc64_caches.l1d.size; - limit = min(safe_stack_limit(), ppc64_rma_size); + limit = min(ppc64_bolted_size(), ppc64_rma_size); /* * Align to L1d size, and size it at 2x L1d size, to catch possible @@ -868,19 +875,8 @@ static void init_fallback_flush(void) memset(l1d_flush_fallback_area, 0, l1d_size * 2); for_each_possible_cpu(cpu) { - /* - * The fallback flush is currently coded for 8-way - * associativity. Different associativity is possible, but it - * will be treated as 8-way and may not evict the lines as - * effectively. - * - * 128 byte lines are mandatory. - */ - u64 c = l1d_size / 8; - paca[cpu].rfi_flush_fallback_area = l1d_flush_fallback_area; - paca[cpu].l1d_flush_congruence = c; - paca[cpu].l1d_flush_sets = c / 128; + paca[cpu].l1d_flush_size = l1d_size; } } diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index aded81169648..a46de0035214 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -111,12 +111,20 @@ static inline int save_general_regs(struct pt_regs *regs, { elf_greg_t64 *gregs = (elf_greg_t64 *)regs; int i; + /* Force usr to alway see softe as 1 (interrupts enabled) */ + elf_greg_t64 softe = 0x1; WARN_ON(!FULL_REGS(regs)); for (i = 0; i <= PT_RESULT; i ++) { if (i == 14 && !FULL_REGS(regs)) i = 32; + if ( i == PT_SOFTE) { + if(__put_user((unsigned int)softe, &frame->mc_gregs[i])) + return -EFAULT; + else + continue; + } if (__put_user((unsigned int)gregs[i], &frame->mc_gregs[i])) return -EFAULT; } diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index 4b9ca3570344..720117690822 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -110,6 +110,8 @@ static long setup_sigcontext(struct sigcontext __user *sc, struct pt_regs *regs = tsk->thread.regs; unsigned long msr = regs->msr; long err = 0; + /* Force usr to alway see softe as 1 (interrupts enabled) */ + unsigned long softe = 0x1; BUG_ON(tsk != current); @@ -169,6 +171,7 @@ static long setup_sigcontext(struct sigcontext __user *sc, WARN_ON(!FULL_REGS(regs)); err |= __copy_to_user(&sc->gp_regs, regs, GP_REGS_SIZE); err |= __put_user(msr, &sc->gp_regs[PT_MSR]); + err |= __put_user(softe, &sc->gp_regs[PT_SOFTE]); err |= __put_user(signr, &sc->signal); err |= __put_user(handler, &sc->handler); if (set != NULL) @@ -207,7 +210,7 @@ static long setup_tm_sigcontexts(struct sigcontext __user *sc, elf_vrreg_t __user *tm_v_regs = sigcontext_vmx_regs(tm_sc); #endif struct pt_regs *regs = tsk->thread.regs; - unsigned long msr = tsk->thread.ckpt_regs.msr; + unsigned long msr = tsk->thread.regs->msr; long err = 0; BUG_ON(tsk != current); @@ -216,6 +219,12 @@ static long setup_tm_sigcontexts(struct sigcontext __user *sc, WARN_ON(tm_suspend_disabled); + /* Restore checkpointed FP, VEC, and VSX bits from ckpt_regs as + * it contains the correct FP, VEC, VSX state after we treclaimed + * the transaction and giveup_all() was called on reclaiming. + */ + msr |= tsk->thread.ckpt_regs.msr & (MSR_FP | MSR_VEC | MSR_VSX); + /* Remove TM bits from thread's MSR. The MSR in the sigcontext * just indicates to userland that we were doing a transaction, but we * don't want to return in transactional state. This also ensures diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index e0a4c1f82e25..bbe7634b3a43 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -543,7 +543,25 @@ void smp_send_debugger_break(void) #ifdef CONFIG_KEXEC_CORE void crash_send_ipi(void (*crash_ipi_callback)(struct pt_regs *)) { + int cpu; + smp_send_nmi_ipi(NMI_IPI_ALL_OTHERS, crash_ipi_callback, 1000000); + if (kdump_in_progress() && crash_wake_offline) { + for_each_present_cpu(cpu) { + if (cpu_online(cpu)) + continue; + /* + * crash_ipi_callback will wait for + * all cpus, including offline CPUs. + * We don't care about nmi_ipi_function. + * Offline cpus will jump straight into + * crash_ipi_callback, we can skip the + * entire NMI dance and waiting for + * cpus to clear pending mask, etc. + */ + do_smp_send_nmi_ipi(cpu); + } + } } #endif diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c index b8d4a1dac39f..5a8bfee6e187 100644 --- a/arch/powerpc/kernel/sysfs.c +++ b/arch/powerpc/kernel/sysfs.c @@ -485,6 +485,7 @@ SYSFS_PMCSETUP(mmcra, SPRN_MMCRA); SYSFS_SPRSETUP(purr, SPRN_PURR); SYSFS_SPRSETUP(spurr, SPRN_SPURR); SYSFS_SPRSETUP(pir, SPRN_PIR); +SYSFS_SPRSETUP(tscr, SPRN_TSCR); /* Lets only enable read for phyp resources and @@ -495,6 +496,7 @@ static DEVICE_ATTR(mmcra, 0600, show_mmcra, store_mmcra); static DEVICE_ATTR(spurr, 0400, show_spurr, NULL); static DEVICE_ATTR(purr, 0400, show_purr, store_purr); static DEVICE_ATTR(pir, 0400, show_pir, NULL); +static DEVICE_ATTR(tscr, 0600, show_tscr, store_tscr); /* * This is the system wide DSCR register default value. Any @@ -785,6 +787,9 @@ static int register_cpu_online(unsigned int cpu) if (cpu_has_feature(CPU_FTR_PPCAS_ARCH_V2)) device_create_file(s, &dev_attr_pir); + + if (cpu_has_feature(CPU_FTR_ARCH_206)) + device_create_file(s, &dev_attr_tscr); #endif /* CONFIG_PPC64 */ #ifdef CONFIG_PPC_FSL_BOOK3E @@ -867,6 +872,9 @@ static int unregister_cpu_online(unsigned int cpu) if (cpu_has_feature(CPU_FTR_PPCAS_ARCH_V2)) device_remove_file(s, &dev_attr_pir); + + if (cpu_has_feature(CPU_FTR_ARCH_206)) + device_remove_file(s, &dev_attr_tscr); #endif /* CONFIG_PPC64 */ #ifdef CONFIG_PPC_FSL_BOOK3E diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index fe6f3a285455..a32823dcd9a4 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -244,7 +244,7 @@ static u64 scan_dispatch_log(u64 stop_tb) void accumulate_stolen_time(void) { u64 sst, ust; - u8 save_soft_enabled = local_paca->soft_enabled; + unsigned long save_irq_soft_mask = irq_soft_mask_return(); struct cpu_accounting_data *acct = &local_paca->accounting; /* We are called early in the exception entry, before @@ -253,7 +253,7 @@ void accumulate_stolen_time(void) * needs to reflect that so various debug stuff doesn't * complain */ - local_paca->soft_enabled = 0; + irq_soft_mask_set(IRQS_DISABLED); sst = scan_dispatch_log(acct->starttime_user); ust = scan_dispatch_log(acct->starttime); @@ -261,7 +261,7 @@ void accumulate_stolen_time(void) acct->utime -= ust; acct->steal_time += ust + sst; - local_paca->soft_enabled = save_soft_enabled; + irq_soft_mask_set(save_irq_soft_mask); } static inline u64 calculate_stolen_time(u64 stop_tb) diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index c93f1e6a9fff..1e48d157196a 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -20,6 +20,7 @@ #include <linux/sched/debug.h> #include <linux/kernel.h> #include <linux/mm.h> +#include <linux/pkeys.h> #include <linux/stddef.h> #include <linux/unistd.h> #include <linux/ptrace.h> @@ -38,6 +39,8 @@ #include <linux/ratelimit.h> #include <linux/context_tracking.h> #include <linux/smp.h> +#include <linux/console.h> +#include <linux/kmsg_dump.h> #include <asm/emulated_ops.h> #include <asm/pgtable.h> @@ -142,6 +145,28 @@ static int die_owner = -1; static unsigned int die_nest_count; static int die_counter; +extern void panic_flush_kmsg_start(void) +{ + /* + * These are mostly taken from kernel/panic.c, but tries to do + * relatively minimal work. Don't use delay functions (TB may + * be broken), don't crash dump (need to set a firmware log), + * don't run notifiers. We do want to get some information to + * Linux console. + */ + console_verbose(); + bust_spinlocks(1); +} + +extern void panic_flush_kmsg_end(void) +{ + printk_safe_flush_on_panic(); + kmsg_dump(KMSG_DUMP_PANIC); + bust_spinlocks(0); + debug_locks_off(); + console_flush_on_panic(); +} + static unsigned long oops_begin(struct pt_regs *regs) { int cpu; @@ -266,7 +291,9 @@ void user_single_step_siginfo(struct task_struct *tsk, info->si_addr = (void __user *)regs->nip; } -void _exception(int signr, struct pt_regs *regs, int code, unsigned long addr) + +void _exception_pkey(int signr, struct pt_regs *regs, int code, + unsigned long addr, int key) { siginfo_t info; const char fmt32[] = KERN_INFO "%s[%d]: unhandled signal %d " \ @@ -289,13 +316,27 @@ void _exception(int signr, struct pt_regs *regs, int code, unsigned long addr) local_irq_enable(); current->thread.trap_nr = code; + + /* + * Save all the pkey registers AMR/IAMR/UAMOR. Eg: Core dumps need + * to capture the content, if the task gets killed. + */ + thread_pkey_regs_save(¤t->thread); + memset(&info, 0, sizeof(info)); info.si_signo = signr; info.si_code = code; info.si_addr = (void __user *) addr; + info.si_pkey = key; + force_sig_info(signr, &info, current); } +void _exception(int signr, struct pt_regs *regs, int code, unsigned long addr) +{ + _exception_pkey(signr, regs, code, addr, 0); +} + void system_reset_exception(struct pt_regs *regs) { /* @@ -337,7 +378,7 @@ void system_reset_exception(struct pt_regs *regs) * No debugger or crash dump registered, print logs then * panic. */ - __die("System Reset", regs, SIGABRT); + die("System Reset", regs, SIGABRT); mdelay(2*MSEC_PER_SEC); /* Wait a little while for others to print */ add_taint(TAINT_DIE, LOCKDEP_NOW_UNRELIABLE); @@ -1564,7 +1605,7 @@ void facility_unavailable_exception(struct pt_regs *regs) u8 status; bool hv; - hv = (regs->trap == 0xf80); + hv = (TRAP(regs) == 0xf80); if (hv) value = mfspr(SPRN_HFSCR); else @@ -2113,13 +2154,13 @@ static int __init ppc_warn_emulated_init(void) if (!dir) return -ENOMEM; - d = debugfs_create_u32("do_warn", S_IRUGO | S_IWUSR, dir, + d = debugfs_create_u32("do_warn", 0644, dir, &ppc_warn_emulated); if (!d) goto fail; for (i = 0; i < sizeof(ppc_emulated)/sizeof(*entries); i++) { - d = debugfs_create_u32(entries[i].name, S_IRUGO | S_IWUSR, dir, + d = debugfs_create_u32(entries[i].name, 0644, dir, (u32 *)&entries[i].val.counter); if (!d) goto fail; diff --git a/arch/powerpc/kernel/vdso64/gettimeofday.S b/arch/powerpc/kernel/vdso64/gettimeofday.S index 382021324883..c002adcc694c 100644 --- a/arch/powerpc/kernel/vdso64/gettimeofday.S +++ b/arch/powerpc/kernel/vdso64/gettimeofday.S @@ -64,6 +64,12 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime) cmpwi cr0,r3,CLOCK_REALTIME cmpwi cr1,r3,CLOCK_MONOTONIC cror cr0*4+eq,cr0*4+eq,cr1*4+eq + + cmpwi cr5,r3,CLOCK_REALTIME_COARSE + cmpwi cr6,r3,CLOCK_MONOTONIC_COARSE + cror cr5*4+eq,cr5*4+eq,cr6*4+eq + + cror cr0*4+eq,cr0*4+eq,cr5*4+eq bne cr0,99f mflr r12 /* r12 saves lr */ @@ -72,6 +78,7 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime) bl V_LOCAL_FUNC(__get_datapage) /* get data page */ lis r7,NSEC_PER_SEC@h /* want nanoseconds */ ori r7,r7,NSEC_PER_SEC@l + beq cr5,70f 50: bl V_LOCAL_FUNC(__do_get_tspec) /* get time from tb & kernel */ bne cr1,80f /* if not monotonic, all done */ @@ -97,19 +104,57 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime) ld r0,CFG_TB_UPDATE_COUNT(r3) cmpld cr0,r0,r8 /* check if updated */ bne- 50b + b 78f - /* Add wall->monotonic offset and check for overflow or underflow. + /* + * For coarse clocks we get data directly from the vdso data page, so + * we don't need to call __do_get_tspec, but we still need to do the + * counter trick. */ - add r4,r4,r6 - add r5,r5,r9 - cmpd cr0,r5,r7 - cmpdi cr1,r5,0 - blt 1f - subf r5,r7,r5 - addi r4,r4,1 -1: bge cr1,80f - addi r4,r4,-1 - add r5,r5,r7 +70: ld r8,CFG_TB_UPDATE_COUNT(r3) + andi. r0,r8,1 /* pending update ? loop */ + bne- 70b + add r3,r3,r0 /* r0 is already 0 */ + + /* + * CLOCK_REALTIME_COARSE, below values are needed for MONOTONIC_COARSE + * too + */ + ld r4,STAMP_XTIME+TSPC64_TV_SEC(r3) + ld r5,STAMP_XTIME+TSPC64_TV_NSEC(r3) + bne cr6,75f + + /* CLOCK_MONOTONIC_COARSE */ + lwa r6,WTOM_CLOCK_SEC(r3) + lwa r9,WTOM_CLOCK_NSEC(r3) + + /* check if counter has updated */ + or r0,r6,r9 +75: or r0,r0,r4 + or r0,r0,r5 + xor r0,r0,r0 + add r3,r3,r0 + ld r0,CFG_TB_UPDATE_COUNT(r3) + cmpld cr0,r0,r8 /* check if updated */ + bne- 70b + + /* Counter has not updated, so continue calculating proper values for + * sec and nsec if monotonic coarse, or just return with the proper + * values for realtime. + */ + bne cr6,80f + + /* Add wall->monotonic offset and check for overflow or underflow */ +78: add r4,r4,r6 + add r5,r5,r9 + cmpd cr0,r5,r7 + cmpdi cr1,r5,0 + blt 79f + subf r5,r7,r5 + addi r4,r4,1 +79: bge cr1,80f + addi r4,r4,-1 + add r5,r5,r7 80: std r4,TSPC64_TV_SEC(r11) std r5,TSPC64_TV_NSEC(r11) diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index 74901a87bf7a..c8af90ff49f0 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -273,6 +273,7 @@ SECTIONS #ifdef CONFIG_PPC32 .data : AT(ADDR(.data) - LOAD_OFFSET) { DATA_DATA + *(.data.rel*) *(.sdata) *(.sdata2) *(.got.plt) *(.got) diff --git a/arch/powerpc/kernel/watchdog.c b/arch/powerpc/kernel/watchdog.c index 87da80ccced1..6256dc3b0087 100644 --- a/arch/powerpc/kernel/watchdog.c +++ b/arch/powerpc/kernel/watchdog.c @@ -6,6 +6,9 @@ * * This uses code from arch/sparc/kernel/nmi.c and kernel/watchdog.c */ + +#define pr_fmt(fmt) "watchdog: " fmt + #include <linux/kernel.h> #include <linux/param.h> #include <linux/init.h> @@ -26,15 +29,45 @@ #include <asm/paca.h> /* - * The watchdog has a simple timer that runs on each CPU, once per timer - * period. This is the heartbeat. + * The powerpc watchdog ensures that each CPU is able to service timers. + * The watchdog sets up a simple timer on each CPU to run once per timer + * period, and updates a per-cpu timestamp and a "pending" cpumask. This is + * the heartbeat. + * + * Then there are two systems to check that the heartbeat is still running. + * The local soft-NMI, and the SMP checker. + * + * The soft-NMI checker can detect lockups on the local CPU. When interrupts + * are disabled with local_irq_disable(), platforms that use soft-masking + * can leave hardware interrupts enabled and handle them with a masked + * interrupt handler. The masked handler can send the timer interrupt to the + * watchdog's soft_nmi_interrupt(), which appears to Linux as an NMI + * interrupt, and can be used to detect CPUs stuck with IRQs disabled. + * + * The soft-NMI checker will compare the heartbeat timestamp for this CPU + * with the current time, and take action if the difference exceeds the + * watchdog threshold. + * + * The limitation of the soft-NMI watchdog is that it does not work when + * interrupts are hard disabled or otherwise not being serviced. This is + * solved by also having a SMP watchdog where all CPUs check all other + * CPUs heartbeat. * - * Then there are checks to see if the heartbeat has not triggered on a CPU - * for the panic timeout period. Currently the watchdog only supports an - * SMP check, so the heartbeat only turns on when we have 2 or more CPUs. + * The SMP checker can detect lockups on other CPUs. A gobal "pending" + * cpumask is kept, containing all CPUs which enable the watchdog. Each + * CPU clears their pending bit in their heartbeat timer. When the bitmask + * becomes empty, the last CPU to clear its pending bit updates a global + * timestamp and refills the pending bitmask. * - * This is not an NMI watchdog, but Linux uses that name for a generic - * watchdog in some cases, so NMI gets used in some places. + * In the heartbeat timer, if any CPU notices that the global timestamp has + * not been updated for a period exceeding the watchdog threshold, then it + * 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 + * 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. */ static cpumask_t wd_cpus_enabled __read_mostly; @@ -47,19 +80,7 @@ static u64 wd_timer_period_ms __read_mostly; /* interval between heartbeat */ static DEFINE_PER_CPU(struct timer_list, wd_timer); static DEFINE_PER_CPU(u64, wd_timer_tb); -/* - * These are for the SMP checker. CPUs clear their pending bit in their - * heartbeat. If the bitmask becomes empty, the time is noted and the - * bitmask is refilled. - * - * All CPUs clear their bit in the pending mask every timer period. - * Once all have cleared, the time is noted and the bits are reset. - * If the time since all clear was greater than the panic timeout, - * we can panic with the list of stuck CPUs. - * - * This will work best with NMI IPIs for crash code so the stuck CPUs - * can be pulled out to get their backtraces. - */ +/* SMP checker bits */ static unsigned long __wd_smp_lock; static cpumask_t wd_smp_cpus_pending; static cpumask_t wd_smp_cpus_stuck; @@ -90,7 +111,7 @@ static inline void wd_smp_unlock(unsigned long *flags) static void wd_lockup_ipi(struct pt_regs *regs) { - pr_emerg("Watchdog CPU:%d Hard LOCKUP\n", raw_smp_processor_id()); + pr_emerg("CPU %d Hard LOCKUP\n", raw_smp_processor_id()); print_modules(); print_irqtrace_events(current); if (regs) @@ -131,8 +152,8 @@ static void watchdog_smp_panic(int cpu, u64 tb) if (cpumask_weight(&wd_smp_cpus_pending) == 0) goto out; - pr_emerg("Watchdog CPU:%d detected Hard LOCKUP other CPUS:%*pbl\n", - cpu, cpumask_pr_args(&wd_smp_cpus_pending)); + pr_emerg("CPU %d detected hard LOCKUP on other CPUs %*pbl\n", + cpu, cpumask_pr_args(&wd_smp_cpus_pending)); if (!sysctl_hardlockup_all_cpu_backtrace) { /* @@ -175,7 +196,7 @@ static void wd_smp_clear_cpu_pending(int cpu, u64 tb) if (unlikely(cpumask_test_cpu(cpu, &wd_smp_cpus_stuck))) { unsigned long flags; - pr_emerg("Watchdog CPU:%d became unstuck\n", cpu); + pr_emerg("CPU %d became unstuck\n", cpu); wd_smp_lock(&flags); cpumask_clear_cpu(cpu, &wd_smp_cpus_stuck); wd_smp_unlock(&flags); @@ -233,13 +254,10 @@ void soft_nmi_interrupt(struct pt_regs *regs) } set_cpu_stuck(cpu, tb); - pr_emerg("Watchdog CPU:%d Hard LOCKUP\n", cpu); + pr_emerg("CPU %d self-detected hard LOCKUP @ %pS\n", cpu, (void *)regs->nip); print_modules(); print_irqtrace_events(current); - if (regs) - show_regs(regs); - else - dump_stack(); + show_regs(regs); wd_smp_unlock(&flags); @@ -388,30 +406,8 @@ int __init watchdog_nmi_probe(void) "powerpc/watchdog:online", start_wd_on_cpu, stop_wd_on_cpu); if (err < 0) { - pr_warn("Watchdog could not be initialized"); + pr_warn("could not be initialized"); return err; } return 0; } - -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_nmi_ipi(cpu, handle_backtrace_ipi, 1000000); - } -} - -void arch_trigger_cpumask_backtrace(const cpumask_t *mask, bool exclude_self) -{ - nmi_trigger_cpumask_backtrace(mask, exclude_self, raise_backtrace_ipi); -} |