diff options
Diffstat (limited to 'arch/powerpc/kernel')
31 files changed, 1462 insertions, 2742 deletions
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index 1925341dbb9c..a3a6047fd395 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -19,6 +19,10 @@ CFLAGS_init.o += $(DISABLE_LATENT_ENTROPY_PLUGIN) CFLAGS_btext.o += $(DISABLE_LATENT_ENTROPY_PLUGIN) CFLAGS_prom.o += $(DISABLE_LATENT_ENTROPY_PLUGIN) +# -fstack-protector triggers protection checks in this code, +# but it is being used too early to link to meaningful stack_chk logic. +CFLAGS_prom_init.o += $(call cc-option, -fno-stack-protector) + ifdef CONFIG_FUNCTION_TRACER # Do not trace early boot code CFLAGS_REMOVE_cputable.o = -mno-sched-epilog $(CC_FLAGS_FTRACE) @@ -58,8 +62,6 @@ obj-$(CONFIG_PPC_RTAS) += rtas.o rtas-rtc.o $(rtaspci-y-y) obj-$(CONFIG_PPC_RTAS_DAEMON) += rtasd.o obj-$(CONFIG_RTAS_FLASH) += rtas_flash.o obj-$(CONFIG_RTAS_PROC) += rtas-proc.o -obj-$(CONFIG_IBMVIO) += vio.o -obj-$(CONFIG_IBMEBUS) += ibmebus.o obj-$(CONFIG_EEH) += eeh.o eeh_pe.o eeh_dev.o eeh_cache.o \ eeh_driver.o eeh_event.o eeh_sysfs.o obj-$(CONFIG_GENERIC_TBSYNC) += smp-tbsync.o @@ -107,8 +109,9 @@ pci64-$(CONFIG_PPC64) += pci_dn.o pci-hotplug.o isa-bridge.o obj-$(CONFIG_PCI) += pci_$(BITS).o $(pci64-y) \ pci-common.o pci_of_scan.o obj-$(CONFIG_PCI_MSI) += msi.o -obj-$(CONFIG_KEXEC) += machine_kexec.o crash.o \ +obj-$(CONFIG_KEXEC_CORE) += machine_kexec.o crash.o \ machine_kexec_$(BITS).o +obj-$(CONFIG_KEXEC_FILE) += machine_kexec_file_$(BITS).o kexec_elf_$(BITS).o obj-$(CONFIG_AUDIT) += audit.o obj64-$(CONFIG_AUDIT) += compat_audit.o @@ -128,7 +131,7 @@ obj64-$(CONFIG_PPC_TRANSACTIONAL_MEM) += tm.o obj-$(CONFIG_PPC64) += $(obj64-y) obj-$(CONFIG_PPC32) += $(obj32-y) -ifneq ($(CONFIG_XMON)$(CONFIG_KEXEC),) +ifneq ($(CONFIG_XMON)$(CONFIG_KEXEC_CORE),) obj-y += ppc_save_regs.o endif diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 195a9fc8f81c..0601e6a7297c 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -91,6 +91,9 @@ int main(void) DEFINE(TI_livepatch_sp, offsetof(struct thread_info, livepatch_sp)); #endif +#ifdef CONFIG_CC_STACKPROTECTOR + DEFINE(TSK_STACK_CANARY, offsetof(struct task_struct, stack_canary)); +#endif DEFINE(KSP, offsetof(struct thread_struct, ksp)); DEFINE(PT_REGS, offsetof(struct thread_struct, regs)); #ifdef CONFIG_BOOKE diff --git a/arch/powerpc/kernel/cpu_setup_power.S b/arch/powerpc/kernel/cpu_setup_power.S index f3e1f5d29dce..917188615bf5 100644 --- a/arch/powerpc/kernel/cpu_setup_power.S +++ b/arch/powerpc/kernel/cpu_setup_power.S @@ -96,6 +96,7 @@ _GLOBAL(__setup_cpu_power9) mtlr r11 beqlr li r0,0 + mtspr SPRN_PSSCR,r0 mtspr SPRN_LPID,r0 mfspr r3,SPRN_LPCR LOAD_REG_IMMEDIATE(r4, LPCR_PECEDH | LPCR_PECE_HVEE | LPCR_HVICE) @@ -116,6 +117,7 @@ _GLOBAL(__restore_cpu_power9) mtlr r11 beqlr li r0,0 + mtspr SPRN_PSSCR,r0 mtspr SPRN_LPID,r0 mfspr r3,SPRN_LPCR LOAD_REG_IMMEDIATE(r4, LPCR_PECEDH | LPCR_PECE_HVEE | LPCR_HVICE) diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index f25731627d7f..8180bfd7ab93 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -372,7 +372,7 @@ static int eeh_phb_check_failure(struct eeh_pe *pe) /* Find the PHB PE */ phb_pe = eeh_phb_pe_get(pe->phb); if (!phb_pe) { - pr_warn("%s Can't find PE for PHB#%d\n", + pr_warn("%s Can't find PE for PHB#%x\n", __func__, pe->phb->global_number); return -EEXIST; } @@ -664,7 +664,7 @@ int eeh_pci_enable(struct eeh_pe *pe, int function) rc = eeh_ops->set_option(pe, function); if (rc) pr_warn("%s: Unexpected state change %d on " - "PHB#%d-PE#%x, err=%d\n", + "PHB#%x-PE#%x, err=%d\n", __func__, function, pe->phb->global_number, pe->addr, rc); @@ -808,76 +808,67 @@ static void *eeh_set_dev_freset(void *data, void *flag) } /** - * eeh_reset_pe_once - Assert the pci #RST line for 1/4 second + * eeh_pe_reset_full - Complete a full reset process on the indicated PE * @pe: EEH PE * - * Assert the PCI #RST line for 1/4 second. + * This function executes a full reset procedure on a PE, including setting + * the appropriate flags, performing a fundamental or hot reset, and then + * deactivating the reset status. It is designed to be used within the EEH + * subsystem, as opposed to eeh_pe_reset which is exported to drivers and + * only performs a single operation at a time. + * + * This function will attempt to reset a PE three times before failing. */ -static void eeh_reset_pe_once(struct eeh_pe *pe) +int eeh_pe_reset_full(struct eeh_pe *pe) { + int active_flags = (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE); + int reset_state = (EEH_PE_RESET | EEH_PE_CFG_BLOCKED); + int type = EEH_RESET_HOT; unsigned int freset = 0; + int i, state, ret; - /* Determine type of EEH reset required for - * Partitionable Endpoint, a hot-reset (1) - * or a fundamental reset (3). - * A fundamental reset required by any device under - * Partitionable Endpoint trumps hot-reset. + /* + * Determine the type of reset to perform - hot or fundamental. + * Hot reset is the default operation, unless any device under the + * PE requires a fundamental reset. */ eeh_pe_dev_traverse(pe, eeh_set_dev_freset, &freset); if (freset) - eeh_ops->reset(pe, EEH_RESET_FUNDAMENTAL); - else - eeh_ops->reset(pe, EEH_RESET_HOT); - - eeh_ops->reset(pe, EEH_RESET_DEACTIVATE); -} - -/** - * eeh_reset_pe - Reset the indicated PE - * @pe: EEH PE - * - * This routine should be called to reset indicated device, including - * PE. A PE might include multiple PCI devices and sometimes PCI bridges - * might be involved as well. - */ -int eeh_reset_pe(struct eeh_pe *pe) -{ - int flags = (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE); - int i, state, ret; + type = EEH_RESET_FUNDAMENTAL; - /* Mark as reset and block config space */ - eeh_pe_state_mark(pe, EEH_PE_RESET | EEH_PE_CFG_BLOCKED); + /* Mark the PE as in reset state and block config space accesses */ + eeh_pe_state_mark(pe, reset_state); - /* Take three shots at resetting the bus */ + /* Make three attempts at resetting the bus */ for (i = 0; i < 3; i++) { - eeh_reset_pe_once(pe); + ret = eeh_pe_reset(pe, type); + if (ret) + break; - /* - * EEH_PE_ISOLATED is expected to be removed after - * BAR restore. - */ + ret = eeh_pe_reset(pe, EEH_RESET_DEACTIVATE); + if (ret) + break; + + /* Wait until the PE is in a functioning state */ state = eeh_ops->wait_state(pe, PCI_BUS_RESET_WAIT_MSEC); - if ((state & flags) == flags) { - ret = 0; - goto out; - } + if ((state & active_flags) == active_flags) + break; if (state < 0) { - pr_warn("%s: Unrecoverable slot failure on PHB#%d-PE#%x", + pr_warn("%s: Unrecoverable slot failure on PHB#%x-PE#%x", __func__, pe->phb->global_number, pe->addr); ret = -ENOTRECOVERABLE; - goto out; + break; } - /* We might run out of credits */ + /* Set error in case this is our last attempt */ ret = -EIO; pr_warn("%s: Failure %d resetting PHB#%x-PE#%x\n (%d)\n", __func__, state, pe->phb->global_number, pe->addr, (i + 1)); } -out: - eeh_pe_state_clear(pe, EEH_PE_RESET | EEH_PE_CFG_BLOCKED); + eeh_pe_state_clear(pe, reset_state); return ret; } @@ -1601,6 +1592,7 @@ static int eeh_pe_reenable_devices(struct eeh_pe *pe) return eeh_unfreeze_pe(pe, true); } + /** * eeh_pe_reset - Issue PE reset according to specified type * @pe: EEH PE diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index 5c31369435f2..d88573bdd090 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -588,7 +588,7 @@ int eeh_pe_reset_and_recover(struct eeh_pe *pe) eeh_pe_dev_traverse(pe, eeh_dev_save_state, NULL); /* Issue reset */ - ret = eeh_reset_pe(pe); + ret = eeh_pe_reset_full(pe); if (ret) { eeh_pe_state_clear(pe, EEH_PE_RECOVERING); return ret; @@ -659,7 +659,7 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus, * config accesses. So we prefer to block them. However, controlled * PCI config accesses initiated from EEH itself are allowed. */ - rc = eeh_reset_pe(pe); + rc = eeh_pe_reset_full(pe); if (rc) return rc; @@ -734,7 +734,7 @@ static void eeh_handle_normal_event(struct eeh_pe *pe) frozen_bus = eeh_pe_bus_get(pe); if (!frozen_bus) { - pr_err("%s: Cannot find PCI bus for PHB#%d-PE#%x\n", + pr_err("%s: Cannot find PCI bus for PHB#%x-PE#%x\n", __func__, pe->phb->global_number, pe->addr); return; } @@ -878,7 +878,7 @@ excess_failures: * are due to poorly seated PCI cards. Only 10% or so are * due to actual, failed cards. */ - pr_err("EEH: PHB#%d-PE#%x has failed %d times in the\n" + pr_err("EEH: PHB#%x-PE#%x has failed %d times in the\n" "last hour and has been permanently disabled.\n" "Please try reseating or replacing it.\n", pe->phb->global_number, pe->addr, @@ -886,7 +886,7 @@ excess_failures: goto perm_error; hard_fail: - pr_err("EEH: Unable to recover from failure from PHB#%d-PE#%x.\n" + pr_err("EEH: Unable to recover from failure from PHB#%x-PE#%x.\n" "Please try reseating or replacing it\n", pe->phb->global_number, pe->addr); @@ -1000,7 +1000,7 @@ static void eeh_handle_special_event(void) bus = eeh_pe_bus_get(phb_pe); if (!bus) { pr_err("%s: Cannot find PCI bus for " - "PHB#%d-PE#%x\n", + "PHB#%x-PE#%x\n", __func__, pe->phb->global_number, pe->addr); diff --git a/arch/powerpc/kernel/eeh_event.c b/arch/powerpc/kernel/eeh_event.c index 82e7327e3cd0..accbf8b5fd46 100644 --- a/arch/powerpc/kernel/eeh_event.c +++ b/arch/powerpc/kernel/eeh_event.c @@ -75,11 +75,11 @@ static int eeh_event_handler(void * dummy) if (pe) { eeh_pe_state_mark(pe, EEH_PE_RECOVERING); if (pe->type & EEH_PE_PHB) - pr_info("EEH: Detected error on PHB#%d\n", + pr_info("EEH: Detected error on PHB#%x\n", pe->phb->global_number); else pr_info("EEH: Detected PCI bus error on " - "PHB#%d-PE#%x\n", + "PHB#%x-PE#%x\n", pe->phb->global_number, pe->addr); eeh_handle_event(pe); eeh_pe_state_clear(pe, EEH_PE_RECOVERING); diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c index de7d091c4c31..cc4b206f77e4 100644 --- a/arch/powerpc/kernel/eeh_pe.c +++ b/arch/powerpc/kernel/eeh_pe.c @@ -104,7 +104,7 @@ int eeh_phb_pe_create(struct pci_controller *phb) /* Put it into the list */ list_add_tail(&pe->child, &eeh_phb_pe); - pr_debug("EEH: Add PE for PHB#%d\n", phb->global_number); + pr_debug("EEH: Add PE for PHB#%x\n", phb->global_number); return 0; } @@ -333,7 +333,7 @@ int eeh_add_to_parent_pe(struct eeh_dev *edev) /* Check if the PE number is valid */ if (!eeh_has_flag(EEH_VALID_PE_ZERO) && !edev->pe_config_addr) { - pr_err("%s: Invalid PE#0 for edev 0x%x on PHB#%d\n", + pr_err("%s: Invalid PE#0 for edev 0x%x on PHB#%x\n", __func__, edev->config_addr, edev->phb->global_number); return -EINVAL; } diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S index 3841d749a430..5742dbdbee46 100644 --- a/arch/powerpc/kernel/entry_32.S +++ b/arch/powerpc/kernel/entry_32.S @@ -674,7 +674,11 @@ BEGIN_FTR_SECTION mtspr SPRN_SPEFSCR,r0 /* restore SPEFSCR reg */ END_FTR_SECTION_IFSET(CPU_FTR_SPE) #endif /* CONFIG_SPE */ - +#if defined(CONFIG_CC_STACKPROTECTOR) && !defined(CONFIG_SMP) + lwz r0,TSK_STACK_CANARY(r2) + lis r4,__stack_chk_guard@ha + stw r0,__stack_chk_guard@l(r4) +#endif lwz r0,_CCR(r1) mtcrf 0xFF,r0 /* r3-r12 are destroyed -- Cort */ diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S index 38a1f96430e1..45b453e4d0c8 100644 --- a/arch/powerpc/kernel/exceptions-64e.S +++ b/arch/powerpc/kernel/exceptions-64e.S @@ -923,10 +923,10 @@ kernel_dbg_exc: PROLOG_ADDITION_NONE) EXCEPTION_COMMON(0x340) addi r3,r1,STACK_FRAME_OVERHEAD - bl .save_nvgprs + bl save_nvgprs INTS_RESTORE_HARD - bl .unknown_exception - b .ret_from_except + bl unknown_exception + b ret_from_except /* * An interrupt came in while soft-disabled; We mark paca->irq_happened diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 1ba82ea90230..d39d6118c6e9 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -1408,7 +1408,7 @@ USE_TEXT_SECTION() /* * Hash table stuff */ - .align 7 + .balign IFETCH_ALIGN_BYTES do_hash_page: #ifdef CONFIG_PPC_STD_MMU_64 andis. r0,r4,0xa410 /* weird error? */ diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c index a95639b8d4ac..5c9f50c1aa99 100644 --- a/arch/powerpc/kernel/ftrace.c +++ b/arch/powerpc/kernel/ftrace.c @@ -47,13 +47,11 @@ ftrace_modify_code(unsigned long ip, unsigned int old, unsigned int new) unsigned int replaced; /* - * Note: Due to modules and __init, code can - * disappear and change, we need to protect against faulting - * as well as code changing. We do this by using the - * probe_kernel_* functions. - * - * No real locking needed, this code is run through - * kstop_machine, or before SMP starts. + * Note: + * We are paranoid about modifying text, as if a bug was to happen, it + * could cause us to read or write to someplace that could cause harm. + * Carefully read and modify the code with probe_kernel_*(), and make + * sure what we read is what we expected it to be before modifying it. */ /* read the text we want to modify */ diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S index 04c546e20cc0..1dc5eae2ced3 100644 --- a/arch/powerpc/kernel/head_64.S +++ b/arch/powerpc/kernel/head_64.S @@ -107,12 +107,19 @@ __secondary_hold_acknowledge: * crash_kernel region. The loader is responsible for * observing the alignment requirement. */ + +#ifdef CONFIG_RELOCATABLE_TEST +#define RUN_AT_LOAD_DEFAULT 1 /* Test relocation, do not copy to 0 */ +#else +#define RUN_AT_LOAD_DEFAULT 0x72756e30 /* "run0" -- relocate to 0 by default */ +#endif + /* Do not move this variable as kexec-tools knows about it. */ . = 0x5c .globl __run_at_load __run_at_load: DEFINE_FIXED_SYMBOL(__run_at_load) - .long 0x72756e30 /* "run0" -- relocate to 0 by default */ + .long RUN_AT_LOAD_DEFAULT #endif . = 0x60 @@ -153,7 +160,7 @@ __secondary_hold: cmpdi 0,r12,0 beq 100b -#if defined(CONFIG_SMP) || defined(CONFIG_KEXEC) +#if defined(CONFIG_SMP) || defined(CONFIG_KEXEC_CORE) #ifdef CONFIG_PPC_BOOK3E tovirt(r12,r12) #endif @@ -214,9 +221,9 @@ booting_thread_hwid: */ _GLOBAL(book3e_start_thread) LOAD_REG_IMMEDIATE(r5, MSR_KERNEL) - cmpi 0, r3, 0 + cmpwi r3, 0 beq 10f - cmpi 0, r3, 1 + cmpwi r3, 1 beq 11f /* If the thread id is invalid, just exit. */ b 13f @@ -241,9 +248,9 @@ _GLOBAL(book3e_start_thread) * r3 = the thread physical id */ _GLOBAL(book3e_stop_thread) - cmpi 0, r3, 0 + cmpwi r3, 0 beq 10f - cmpi 0, r3, 1 + cmpwi r3, 1 beq 10f /* If the thread id is invalid, just exit. */ b 13f diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S index fb133a163263..1a9c99d3e5d8 100644 --- a/arch/powerpc/kernel/head_8xx.S +++ b/arch/powerpc/kernel/head_8xx.S @@ -73,6 +73,9 @@ #define RPN_PATTERN 0x00f0 #endif +#define PAGE_SHIFT_512K 19 +#define PAGE_SHIFT_8M 23 + __HEAD _ENTRY(_stext); _ENTRY(_start); @@ -322,7 +325,7 @@ SystemCall: #endif InstructionTLBMiss: -#if defined(CONFIG_8xx_CPU6) || defined(CONFIG_MODULES) || defined (CONFIG_DEBUG_PAGEALLOC) +#if defined(CONFIG_8xx_CPU6) || defined(CONFIG_MODULES) || defined (CONFIG_DEBUG_PAGEALLOC) || defined (CONFIG_HUGETLB_PAGE) mtspr SPRN_SPRG_SCRATCH2, r3 #endif EXCEPTION_PROLOG_0 @@ -332,10 +335,12 @@ InstructionTLBMiss: */ mfspr r10, SPRN_SRR0 /* Get effective address of fault */ INVALIDATE_ADJACENT_PAGES_CPU15(r11, r10) -#if defined(CONFIG_MODULES) || defined (CONFIG_DEBUG_PAGEALLOC) /* Only modules will cause ITLB Misses as we always * pin the first 8MB of kernel memory */ +#if defined(CONFIG_MODULES) || defined (CONFIG_DEBUG_PAGEALLOC) || defined (CONFIG_HUGETLB_PAGE) mfcr r3 +#endif +#if defined(CONFIG_MODULES) || defined (CONFIG_DEBUG_PAGEALLOC) IS_KERNEL(r11, r10) #endif mfspr r11, SPRN_M_TW /* Get level 1 table */ @@ -343,7 +348,6 @@ InstructionTLBMiss: BRANCH_UNLESS_KERNEL(3f) lis r11, (swapper_pg_dir-PAGE_OFFSET)@ha 3: - mtcr r3 #endif /* Insert level 1 index */ rlwimi r11, r10, 32 - ((PAGE_SHIFT - 2) << 1), (PAGE_SHIFT - 2) << 1, 29 @@ -351,14 +355,25 @@ InstructionTLBMiss: /* Extract level 2 index */ rlwinm r10, r10, 32 - (PAGE_SHIFT - 2), 32 - PAGE_SHIFT, 29 +#ifdef CONFIG_HUGETLB_PAGE + mtcr r11 + bt- 28, 10f /* bit 28 = Large page (8M) */ + bt- 29, 20f /* bit 29 = Large page (8M or 512k) */ +#endif rlwimi r10, r11, 0, 0, 32 - PAGE_SHIFT - 1 /* Add level 2 base */ lwz r10, 0(r10) /* Get the pte */ - +4: +#if defined(CONFIG_MODULES) || defined (CONFIG_DEBUG_PAGEALLOC) || defined (CONFIG_HUGETLB_PAGE) + mtcr r3 +#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 @@ -371,16 +386,45 @@ InstructionTLBMiss: * 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 */ /* Restore registers */ -#if defined(CONFIG_8xx_CPU6) || defined(CONFIG_MODULES) || defined (CONFIG_DEBUG_PAGEALLOC) +#if defined(CONFIG_8xx_CPU6) || defined(CONFIG_MODULES) || defined (CONFIG_DEBUG_PAGEALLOC) || defined (CONFIG_HUGETLB_PAGE) mfspr r3, SPRN_SPRG_SCRATCH2 #endif EXCEPTION_EPILOG_0 rfi +#ifdef CONFIG_HUGETLB_PAGE +10: /* 8M pages */ +#ifdef CONFIG_PPC_16K_PAGES + /* Extract level 2 index */ + rlwinm r10, r10, 32 - (PAGE_SHIFT_8M - PAGE_SHIFT), 32 + PAGE_SHIFT_8M - (PAGE_SHIFT << 1), 29 + /* Add level 2 base */ + rlwimi r10, r11, 0, 0, 32 + PAGE_SHIFT_8M - (PAGE_SHIFT << 1) - 1 +#else + /* Level 2 base */ + 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 */ + /* Extract level 2 index */ + rlwinm r10, r10, 32 - (PAGE_SHIFT_512K - PAGE_SHIFT), 32 + PAGE_SHIFT_512K - (PAGE_SHIFT << 1), 29 + /* 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 @@ -407,7 +451,6 @@ _ENTRY(DTLBMiss_jmp) #endif blt cr7, DTLBMissLinear 3: - mtcr r3 mfspr r10, SPRN_MD_EPN /* Insert level 1 index */ @@ -418,8 +461,15 @@ _ENTRY(DTLBMiss_jmp) */ /* Extract level 2 index */ rlwinm r10, r10, 32 - (PAGE_SHIFT - 2), 32 - PAGE_SHIFT, 29 +#ifdef CONFIG_HUGETLB_PAGE + mtcr r11 + bt- 28, 10f /* bit 28 = Large page (8M) */ + bt- 29, 20f /* bit 29 = Large page (8M or 512k) */ +#endif rlwimi r10, r11, 0, 0, 32 - PAGE_SHIFT - 1 /* Add level 2 base */ lwz r10, 0(r10) /* Get the pte */ +4: + mtcr r3 /* 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 @@ -434,6 +484,11 @@ _ENTRY(DTLBMiss_jmp) 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 @@ -455,7 +510,11 @@ _ENTRY(DTLBMiss_jmp) * 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 */ @@ -465,6 +524,30 @@ _ENTRY(DTLBMiss_jmp) EXCEPTION_EPILOG_0 rfi +#ifdef CONFIG_HUGETLB_PAGE +10: /* 8M pages */ + /* Extract level 2 index */ +#ifdef CONFIG_PPC_16K_PAGES + rlwinm r10, r10, 32 - (PAGE_SHIFT_8M - PAGE_SHIFT), 32 + PAGE_SHIFT_8M - (PAGE_SHIFT << 1), 29 + /* Add level 2 base */ + rlwimi r10, r11, 0, 0, 32 + PAGE_SHIFT_8M - (PAGE_SHIFT << 1) - 1 +#else + /* Level 2 base */ + 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 */ + /* Extract level 2 index */ + rlwinm r10, r10, 32 - (PAGE_SHIFT_512K - PAGE_SHIFT), 32 + PAGE_SHIFT_512K - (PAGE_SHIFT << 1), 29 + /* 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 /* This is an instruction TLB error on the MPC8xx. This could be due * to many reasons, such as executing guarded memory or illegal instruction @@ -586,6 +669,9 @@ _ENTRY(FixupDAR_cmp) /* Insert level 1 index */ 3: rlwimi r11, r10, 32 - ((PAGE_SHIFT - 2) << 1), (PAGE_SHIFT - 2) << 1, 29 lwz r11, (swapper_pg_dir-PAGE_OFFSET)@l(r11) /* Get the level 1 entry */ + mtcr r11 + bt 28,200f /* bit 28 = Large page (8M) */ + bt 29,202f /* bit 29 = Large page (8M or 512K) */ rlwinm r11, r11,0,0,19 /* Extract page descriptor page address */ /* Insert level 2 index */ rlwimi r11, r10, 32 - (PAGE_SHIFT - 2), 32 - PAGE_SHIFT, 29 @@ -611,6 +697,27 @@ _ENTRY(FixupDAR_cmp) 141: mfspr r10,SPRN_SPRG_SCRATCH2 b DARFixed /* Nope, go back to normal TLB processing */ + /* concat physical page address(r11) and page offset(r10) */ +200: +#ifdef CONFIG_PPC_16K_PAGES + rlwinm r11, r11, 0, 0, 32 + PAGE_SHIFT_8M - (PAGE_SHIFT << 1) - 1 + rlwimi r11, r10, 32 - (PAGE_SHIFT_8M - 2), 32 + PAGE_SHIFT_8M - (PAGE_SHIFT << 1), 29 +#else + rlwinm r11, r10, 0, ~HUGEPD_SHIFT_MASK +#endif + lwz r11, 0(r11) /* Get the pte */ + /* concat physical page address(r11) and page offset(r10) */ + rlwimi r11, r10, 0, 32 - PAGE_SHIFT_8M, 31 + b 201b + +202: + rlwinm r11, r11, 0, 0, 32 + PAGE_SHIFT_512K - (PAGE_SHIFT << 1) - 1 + rlwimi r11, r10, 32 - (PAGE_SHIFT_512K - 2), 32 + PAGE_SHIFT_512K - (PAGE_SHIFT << 1), 29 + lwz r11, 0(r11) /* Get the pte */ + /* concat physical page address(r11) and page offset(r10) */ + rlwimi r11, r10, 0, 32 - PAGE_SHIFT_512K, 31 + b 201b + 144: mfspr r10, SPRN_DSISR rlwinm r10, r10,0,7,5 /* Clear store bit for buggy dcbst insn */ mtspr SPRN_DSISR, r10 diff --git a/arch/powerpc/kernel/ibmebus.c b/arch/powerpc/kernel/ibmebus.c deleted file mode 100644 index 6ca9a2ffaac7..000000000000 --- a/arch/powerpc/kernel/ibmebus.c +++ /dev/null @@ -1,759 +0,0 @@ -/* - * IBM PowerPC IBM eBus Infrastructure Support. - * - * Copyright (c) 2005 IBM Corporation - * Joachim Fenkes <fenkes@de.ibm.com> - * Heiko J Schick <schickhj@de.ibm.com> - * - * All rights reserved. - * - * This source code is distributed under a dual license of GPL v2.0 and OpenIB - * BSD. - * - * OpenIB BSD License - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions are met: - * - * Redistributions of source code must retain the above copyright notice, this - * list of conditions and the following disclaimer. - * - * Redistributions in binary form must reproduce the above copyright notice, - * this list of conditions and the following disclaimer in the documentation - * and/or other materials - * provided with the distribution. - * - * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" - * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE - * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE - * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE - * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR - * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF - * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR - * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER - * IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) - * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE - * POSSIBILITY OF SUCH DAMAGE. - */ - -#include <linux/init.h> -#include <linux/export.h> -#include <linux/console.h> -#include <linux/kobject.h> -#include <linux/dma-mapping.h> -#include <linux/interrupt.h> -#include <linux/of.h> -#include <linux/slab.h> -#include <linux/stat.h> -#include <linux/of_platform.h> -#include <asm/ibmebus.h> - -static struct device ibmebus_bus_device = { /* fake "parent" device */ - .init_name = "ibmebus", -}; - -struct bus_type ibmebus_bus_type; - -/* These devices will automatically be added to the bus during init */ -static const struct of_device_id ibmebus_matches[] __initconst = { - { .compatible = "IBM,lhca" }, - { .compatible = "IBM,lhea" }, - {}, -}; - -static void *ibmebus_alloc_coherent(struct device *dev, - size_t size, - dma_addr_t *dma_handle, - gfp_t flag, - unsigned long attrs) -{ - void *mem; - - mem = kmalloc(size, flag); - *dma_handle = (dma_addr_t)mem; - - return mem; -} - -static void ibmebus_free_coherent(struct device *dev, - size_t size, void *vaddr, - dma_addr_t dma_handle, - unsigned long attrs) -{ - kfree(vaddr); -} - -static dma_addr_t ibmebus_map_page(struct device *dev, - struct page *page, - unsigned long offset, - size_t size, - enum dma_data_direction direction, - unsigned long attrs) -{ - return (dma_addr_t)(page_address(page) + offset); -} - -static void ibmebus_unmap_page(struct device *dev, - dma_addr_t dma_addr, - size_t size, - enum dma_data_direction direction, - unsigned long attrs) -{ - return; -} - -static int ibmebus_map_sg(struct device *dev, - struct scatterlist *sgl, - int nents, enum dma_data_direction direction, - unsigned long attrs) -{ - struct scatterlist *sg; - int i; - - for_each_sg(sgl, sg, nents, i) { - sg->dma_address = (dma_addr_t) sg_virt(sg); - sg->dma_length = sg->length; - } - - return nents; -} - -static void ibmebus_unmap_sg(struct device *dev, - struct scatterlist *sg, - int nents, enum dma_data_direction direction, - unsigned long attrs) -{ - return; -} - -static int ibmebus_dma_supported(struct device *dev, u64 mask) -{ - return mask == DMA_BIT_MASK(64); -} - -static u64 ibmebus_dma_get_required_mask(struct device *dev) -{ - return DMA_BIT_MASK(64); -} - -static struct dma_map_ops ibmebus_dma_ops = { - .alloc = ibmebus_alloc_coherent, - .free = ibmebus_free_coherent, - .map_sg = ibmebus_map_sg, - .unmap_sg = ibmebus_unmap_sg, - .dma_supported = ibmebus_dma_supported, - .get_required_mask = ibmebus_dma_get_required_mask, - .map_page = ibmebus_map_page, - .unmap_page = ibmebus_unmap_page, -}; - -static int ibmebus_match_path(struct device *dev, void *data) -{ - struct device_node *dn = to_platform_device(dev)->dev.of_node; - return (dn->full_name && - (strcasecmp((char *)data, dn->full_name) == 0)); -} - -static int ibmebus_match_node(struct device *dev, void *data) -{ - return to_platform_device(dev)->dev.of_node == data; -} - -static int ibmebus_create_device(struct device_node *dn) -{ - struct platform_device *dev; - int ret; - - dev = of_device_alloc(dn, NULL, &ibmebus_bus_device); - if (!dev) - return -ENOMEM; - - dev->dev.bus = &ibmebus_bus_type; - dev->dev.archdata.dma_ops = &ibmebus_dma_ops; - - ret = of_device_add(dev); - if (ret) - platform_device_put(dev); - return ret; -} - -static int ibmebus_create_devices(const struct of_device_id *matches) -{ - struct device_node *root, *child; - int ret = 0; - - root = of_find_node_by_path("/"); - - for_each_child_of_node(root, child) { - if (!of_match_node(matches, child)) - continue; - - if (bus_find_device(&ibmebus_bus_type, NULL, child, - ibmebus_match_node)) - continue; - - ret = ibmebus_create_device(child); - if (ret) { - printk(KERN_ERR "%s: failed to create device (%i)", - __func__, ret); - of_node_put(child); - break; - } - } - - of_node_put(root); - return ret; -} - -int ibmebus_register_driver(struct platform_driver *drv) -{ - /* If the driver uses devices that ibmebus doesn't know, add them */ - ibmebus_create_devices(drv->driver.of_match_table); - - drv->driver.bus = &ibmebus_bus_type; - return driver_register(&drv->driver); -} -EXPORT_SYMBOL(ibmebus_register_driver); - -void ibmebus_unregister_driver(struct platform_driver *drv) -{ - driver_unregister(&drv->driver); -} -EXPORT_SYMBOL(ibmebus_unregister_driver); - -int ibmebus_request_irq(u32 ist, irq_handler_t handler, - unsigned long irq_flags, const char *devname, - void *dev_id) -{ - unsigned int irq = irq_create_mapping(NULL, ist); - - if (!irq) - return -EINVAL; - - return request_irq(irq, handler, irq_flags, devname, dev_id); -} -EXPORT_SYMBOL(ibmebus_request_irq); - -void ibmebus_free_irq(u32 ist, void *dev_id) -{ - unsigned int irq = irq_find_mapping(NULL, ist); - - free_irq(irq, dev_id); - irq_dispose_mapping(irq); -} -EXPORT_SYMBOL(ibmebus_free_irq); - -static char *ibmebus_chomp(const char *in, size_t count) -{ - char *out = kmalloc(count + 1, GFP_KERNEL); - - if (!out) - return NULL; - - memcpy(out, in, count); - out[count] = '\0'; - if (out[count - 1] == '\n') - out[count - 1] = '\0'; - - return out; -} - -static ssize_t ibmebus_store_probe(struct bus_type *bus, - const char *buf, size_t count) -{ - struct device_node *dn = NULL; - char *path; - ssize_t rc = 0; - - path = ibmebus_chomp(buf, count); - if (!path) - return -ENOMEM; - - if (bus_find_device(&ibmebus_bus_type, NULL, path, - ibmebus_match_path)) { - printk(KERN_WARNING "%s: %s has already been probed\n", - __func__, path); - rc = -EEXIST; - goto out; - } - - if ((dn = of_find_node_by_path(path))) { - rc = ibmebus_create_device(dn); - of_node_put(dn); - } else { - printk(KERN_WARNING "%s: no such device node: %s\n", - __func__, path); - rc = -ENODEV; - } - -out: - kfree(path); - if (rc) - return rc; - return count; -} -static BUS_ATTR(probe, S_IWUSR, NULL, ibmebus_store_probe); - -static ssize_t ibmebus_store_remove(struct bus_type *bus, - const char *buf, size_t count) -{ - struct device *dev; - char *path; - - path = ibmebus_chomp(buf, count); - if (!path) - return -ENOMEM; - - if ((dev = bus_find_device(&ibmebus_bus_type, NULL, path, - ibmebus_match_path))) { - of_device_unregister(to_platform_device(dev)); - - kfree(path); - return count; - } else { - printk(KERN_WARNING "%s: %s not on the bus\n", - __func__, path); - - kfree(path); - return -ENODEV; - } -} -static BUS_ATTR(remove, S_IWUSR, NULL, ibmebus_store_remove); - -static struct attribute *ibmbus_bus_attrs[] = { - &bus_attr_probe.attr, - &bus_attr_remove.attr, - NULL, -}; -ATTRIBUTE_GROUPS(ibmbus_bus); - -static int ibmebus_bus_bus_match(struct device *dev, struct device_driver *drv) -{ - const struct of_device_id *matches = drv->of_match_table; - - if (!matches) - return 0; - - return of_match_device(matches, dev) != NULL; -} - -static int ibmebus_bus_device_probe(struct device *dev) -{ - int error = -ENODEV; - struct platform_driver *drv; - struct platform_device *of_dev; - - drv = to_platform_driver(dev->driver); - of_dev = to_platform_device(dev); - - if (!drv->probe) - return error; - - of_dev_get(of_dev); - - if (of_driver_match_device(dev, dev->driver)) - error = drv->probe(of_dev); - if (error) - of_dev_put(of_dev); - - return error; -} - -static int ibmebus_bus_device_remove(struct device *dev) -{ - struct platform_device *of_dev = to_platform_device(dev); - struct platform_driver *drv = to_platform_driver(dev->driver); - - if (dev->driver && drv->remove) - drv->remove(of_dev); - return 0; -} - -static void ibmebus_bus_device_shutdown(struct device *dev) -{ - struct platform_device *of_dev = to_platform_device(dev); - struct platform_driver *drv = to_platform_driver(dev->driver); - - if (dev->driver && drv->shutdown) - drv->shutdown(of_dev); -} - -/* - * ibmebus_bus_device_attrs - */ -static ssize_t devspec_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - struct platform_device *ofdev; - - ofdev = to_platform_device(dev); - return sprintf(buf, "%s\n", ofdev->dev.of_node->full_name); -} - -static ssize_t name_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - struct platform_device *ofdev; - - ofdev = to_platform_device(dev); - return sprintf(buf, "%s\n", ofdev->dev.of_node->name); -} - -static ssize_t modalias_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - ssize_t len = of_device_get_modalias(dev, buf, PAGE_SIZE - 2); - buf[len] = '\n'; - buf[len+1] = 0; - return len+1; -} - -static struct device_attribute ibmebus_bus_device_attrs[] = { - __ATTR_RO(devspec), - __ATTR_RO(name), - __ATTR_RO(modalias), - __ATTR_NULL -}; - -#ifdef CONFIG_PM_SLEEP -static int ibmebus_bus_legacy_suspend(struct device *dev, pm_message_t mesg) -{ - struct platform_device *of_dev = to_platform_device(dev); - struct platform_driver *drv = to_platform_driver(dev->driver); - int ret = 0; - - if (dev->driver && drv->suspend) - ret = drv->suspend(of_dev, mesg); - return ret; -} - -static int ibmebus_bus_legacy_resume(struct device *dev) -{ - struct platform_device *of_dev = to_platform_device(dev); - struct platform_driver *drv = to_platform_driver(dev->driver); - int ret = 0; - - if (dev->driver && drv->resume) - ret = drv->resume(of_dev); - return ret; -} - -static int ibmebus_bus_pm_prepare(struct device *dev) -{ - struct device_driver *drv = dev->driver; - int ret = 0; - - if (drv && drv->pm && drv->pm->prepare) - ret = drv->pm->prepare(dev); - - return ret; -} - -static void ibmebus_bus_pm_complete(struct device *dev) -{ - struct device_driver *drv = dev->driver; - - if (drv && drv->pm && drv->pm->complete) - drv->pm->complete(dev); -} - -#ifdef CONFIG_SUSPEND - -static int ibmebus_bus_pm_suspend(struct device *dev) -{ - struct device_driver *drv = dev->driver; - int ret = 0; - - if (!drv) - return 0; - - if (drv->pm) { - if (drv->pm->suspend) - ret = drv->pm->suspend(dev); - } else { - ret = ibmebus_bus_legacy_suspend(dev, PMSG_SUSPEND); - } - - return ret; -} - -static int ibmebus_bus_pm_suspend_noirq(struct device *dev) -{ - struct device_driver *drv = dev->driver; - int ret = 0; - - if (!drv) - return 0; - - if (drv->pm) { - if (drv->pm->suspend_noirq) - ret = drv->pm->suspend_noirq(dev); - } - - return ret; -} - -static int ibmebus_bus_pm_resume(struct device *dev) -{ - struct device_driver *drv = dev->driver; - int ret = 0; - - if (!drv) - return 0; - - if (drv->pm) { - if (drv->pm->resume) - ret = drv->pm->resume(dev); - } else { - ret = ibmebus_bus_legacy_resume(dev); - } - - return ret; -} - -static int ibmebus_bus_pm_resume_noirq(struct device *dev) -{ - struct device_driver *drv = dev->driver; - int ret = 0; - - if (!drv) - return 0; - - if (drv->pm) { - if (drv->pm->resume_noirq) - ret = drv->pm->resume_noirq(dev); - } - - return ret; -} - -#else /* !CONFIG_SUSPEND */ - -#define ibmebus_bus_pm_suspend NULL -#define ibmebus_bus_pm_resume NULL -#define ibmebus_bus_pm_suspend_noirq NULL -#define ibmebus_bus_pm_resume_noirq NULL - -#endif /* !CONFIG_SUSPEND */ - -#ifdef CONFIG_HIBERNATE_CALLBACKS - -static int ibmebus_bus_pm_freeze(struct device *dev) -{ - struct device_driver *drv = dev->driver; - int ret = 0; - - if (!drv) - return 0; - - if (drv->pm) { - if (drv->pm->freeze) - ret = drv->pm->freeze(dev); - } else { - ret = ibmebus_bus_legacy_suspend(dev, PMSG_FREEZE); - } - - return ret; -} - -static int ibmebus_bus_pm_freeze_noirq(struct device *dev) -{ - struct device_driver *drv = dev->driver; - int ret = 0; - - if (!drv) - return 0; - - if (drv->pm) { - if (drv->pm->freeze_noirq) - ret = drv->pm->freeze_noirq(dev); - } - - return ret; -} - -static int ibmebus_bus_pm_thaw(struct device *dev) -{ - struct device_driver *drv = dev->driver; - int ret = 0; - - if (!drv) - return 0; - - if (drv->pm) { - if (drv->pm->thaw) - ret = drv->pm->thaw(dev); - } else { - ret = ibmebus_bus_legacy_resume(dev); - } - - return ret; -} - -static int ibmebus_bus_pm_thaw_noirq(struct device *dev) -{ - struct device_driver *drv = dev->driver; - int ret = 0; - - if (!drv) - return 0; - - if (drv->pm) { - if (drv->pm->thaw_noirq) - ret = drv->pm->thaw_noirq(dev); - } - - return ret; -} - -static int ibmebus_bus_pm_poweroff(struct device *dev) -{ - struct device_driver *drv = dev->driver; - int ret = 0; - - if (!drv) - return 0; - - if (drv->pm) { - if (drv->pm->poweroff) - ret = drv->pm->poweroff(dev); - } else { - ret = ibmebus_bus_legacy_suspend(dev, PMSG_HIBERNATE); - } - - return ret; -} - -static int ibmebus_bus_pm_poweroff_noirq(struct device *dev) -{ - struct device_driver *drv = dev->driver; - int ret = 0; - - if (!drv) - return 0; - - if (drv->pm) { - if (drv->pm->poweroff_noirq) - ret = drv->pm->poweroff_noirq(dev); - } - - return ret; -} - -static int ibmebus_bus_pm_restore(struct device *dev) -{ - struct device_driver *drv = dev->driver; - int ret = 0; - - if (!drv) - return 0; - - if (drv->pm) { - if (drv->pm->restore) - ret = drv->pm->restore(dev); - } else { - ret = ibmebus_bus_legacy_resume(dev); - } - - return ret; -} - -static int ibmebus_bus_pm_restore_noirq(struct device *dev) -{ - struct device_driver *drv = dev->driver; - int ret = 0; - - if (!drv) - return 0; - - if (drv->pm) { - if (drv->pm->restore_noirq) - ret = drv->pm->restore_noirq(dev); - } - - return ret; -} - -#else /* !CONFIG_HIBERNATE_CALLBACKS */ - -#define ibmebus_bus_pm_freeze NULL -#define ibmebus_bus_pm_thaw NULL -#define ibmebus_bus_pm_poweroff NULL -#define ibmebus_bus_pm_restore NULL -#define ibmebus_bus_pm_freeze_noirq NULL -#define ibmebus_bus_pm_thaw_noirq NULL -#define ibmebus_bus_pm_poweroff_noirq NULL -#define ibmebus_bus_pm_restore_noirq NULL - -#endif /* !CONFIG_HIBERNATE_CALLBACKS */ - -static struct dev_pm_ops ibmebus_bus_dev_pm_ops = { - .prepare = ibmebus_bus_pm_prepare, - .complete = ibmebus_bus_pm_complete, - .suspend = ibmebus_bus_pm_suspend, - .resume = ibmebus_bus_pm_resume, - .freeze = ibmebus_bus_pm_freeze, - .thaw = ibmebus_bus_pm_thaw, - .poweroff = ibmebus_bus_pm_poweroff, - .restore = ibmebus_bus_pm_restore, - .suspend_noirq = ibmebus_bus_pm_suspend_noirq, - .resume_noirq = ibmebus_bus_pm_resume_noirq, - .freeze_noirq = ibmebus_bus_pm_freeze_noirq, - .thaw_noirq = ibmebus_bus_pm_thaw_noirq, - .poweroff_noirq = ibmebus_bus_pm_poweroff_noirq, - .restore_noirq = ibmebus_bus_pm_restore_noirq, -}; - -#define IBMEBUS_BUS_PM_OPS_PTR (&ibmebus_bus_dev_pm_ops) - -#else /* !CONFIG_PM_SLEEP */ - -#define IBMEBUS_BUS_PM_OPS_PTR NULL - -#endif /* !CONFIG_PM_SLEEP */ - -struct bus_type ibmebus_bus_type = { - .name = "ibmebus", - .uevent = of_device_uevent_modalias, - .bus_groups = ibmbus_bus_groups, - .match = ibmebus_bus_bus_match, - .probe = ibmebus_bus_device_probe, - .remove = ibmebus_bus_device_remove, - .shutdown = ibmebus_bus_device_shutdown, - .dev_attrs = ibmebus_bus_device_attrs, - .pm = IBMEBUS_BUS_PM_OPS_PTR, -}; -EXPORT_SYMBOL(ibmebus_bus_type); - -static int __init ibmebus_bus_init(void) -{ - int err; - - printk(KERN_INFO "IBM eBus Device Driver\n"); - - err = bus_register(&ibmebus_bus_type); - if (err) { - printk(KERN_ERR "%s: failed to register IBM eBus.\n", - __func__); - return err; - } - - err = device_register(&ibmebus_bus_device); - if (err) { - printk(KERN_WARNING "%s: device_register returned %i\n", - __func__, err); - bus_unregister(&ibmebus_bus_type); - - return err; - } - - err = ibmebus_create_devices(ibmebus_matches); - if (err) { - device_unregister(&ibmebus_bus_device); - bus_unregister(&ibmebus_bus_type); - return err; - } - - return 0; -} -postcore_initcall(ibmebus_bus_init); diff --git a/arch/powerpc/kernel/kexec_elf_64.c b/arch/powerpc/kernel/kexec_elf_64.c new file mode 100644 index 000000000000..6acffd34a70f --- /dev/null +++ b/arch/powerpc/kernel/kexec_elf_64.c @@ -0,0 +1,663 @@ +/* + * Load ELF vmlinux file for the kexec_file_load syscall. + * + * Copyright (C) 2004 Adam Litke (agl@us.ibm.com) + * Copyright (C) 2004 IBM Corp. + * Copyright (C) 2005 R Sharada (sharada@in.ibm.com) + * Copyright (C) 2006 Mohan Kumar M (mohan@in.ibm.com) + * Copyright (C) 2016 IBM Corporation + * + * Based on kexec-tools' kexec-elf-exec.c and kexec-elf-ppc64.c. + * Heavily modified for the kernel by + * Thiago Jung Bauermann <bauerman@linux.vnet.ibm.com>. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation (version 2 of the License). + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#define pr_fmt(fmt) "kexec_elf: " fmt + +#include <linux/elf.h> +#include <linux/kexec.h> +#include <linux/libfdt.h> +#include <linux/module.h> +#include <linux/of_fdt.h> +#include <linux/slab.h> +#include <linux/types.h> + +#define PURGATORY_STACK_SIZE (16 * 1024) + +#define elf_addr_to_cpu elf64_to_cpu + +#ifndef Elf_Rel +#define Elf_Rel Elf64_Rel +#endif /* Elf_Rel */ + +struct elf_info { + /* + * Where the ELF binary contents are kept. + * Memory managed by the user of the struct. + */ + const char *buffer; + + const struct elfhdr *ehdr; + const struct elf_phdr *proghdrs; + struct elf_shdr *sechdrs; +}; + +static inline bool elf_is_elf_file(const struct elfhdr *ehdr) +{ + return memcmp(ehdr->e_ident, ELFMAG, SELFMAG) == 0; +} + +static uint64_t elf64_to_cpu(const struct elfhdr *ehdr, uint64_t value) +{ + if (ehdr->e_ident[EI_DATA] == ELFDATA2LSB) + value = le64_to_cpu(value); + else if (ehdr->e_ident[EI_DATA] == ELFDATA2MSB) + value = be64_to_cpu(value); + + return value; +} + +static uint16_t elf16_to_cpu(const struct elfhdr *ehdr, uint16_t value) +{ + if (ehdr->e_ident[EI_DATA] == ELFDATA2LSB) + value = le16_to_cpu(value); + else if (ehdr->e_ident[EI_DATA] == ELFDATA2MSB) + value = be16_to_cpu(value); + + return value; +} + +static uint32_t elf32_to_cpu(const struct elfhdr *ehdr, uint32_t value) +{ + if (ehdr->e_ident[EI_DATA] == ELFDATA2LSB) + value = le32_to_cpu(value); + else if (ehdr->e_ident[EI_DATA] == ELFDATA2MSB) + value = be32_to_cpu(value); + + return value; +} + +/** + * elf_is_ehdr_sane - check that it is safe to use the ELF header + * @buf_len: size of the buffer in which the ELF file is loaded. + */ +static bool elf_is_ehdr_sane(const struct elfhdr *ehdr, size_t buf_len) +{ + if (ehdr->e_phnum > 0 && ehdr->e_phentsize != sizeof(struct elf_phdr)) { + pr_debug("Bad program header size.\n"); + return false; + } else if (ehdr->e_shnum > 0 && + ehdr->e_shentsize != sizeof(struct elf_shdr)) { + pr_debug("Bad section header size.\n"); + return false; + } else if (ehdr->e_ident[EI_VERSION] != EV_CURRENT || + ehdr->e_version != EV_CURRENT) { + pr_debug("Unknown ELF version.\n"); + return false; + } + + if (ehdr->e_phoff > 0 && ehdr->e_phnum > 0) { + size_t phdr_size; + + /* + * e_phnum is at most 65535 so calculating the size of the + * program header cannot overflow. + */ + phdr_size = sizeof(struct elf_phdr) * ehdr->e_phnum; + + /* Sanity check the program header table location. */ + if (ehdr->e_phoff + phdr_size < ehdr->e_phoff) { + pr_debug("Program headers at invalid location.\n"); + return false; + } else if (ehdr->e_phoff + phdr_size > buf_len) { + pr_debug("Program headers truncated.\n"); + return false; + } + } + + if (ehdr->e_shoff > 0 && ehdr->e_shnum > 0) { + size_t shdr_size; + + /* + * e_shnum is at most 65536 so calculating + * the size of the section header cannot overflow. + */ + shdr_size = sizeof(struct elf_shdr) * ehdr->e_shnum; + + /* Sanity check the section header table location. */ + if (ehdr->e_shoff + shdr_size < ehdr->e_shoff) { + pr_debug("Section headers at invalid location.\n"); + return false; + } else if (ehdr->e_shoff + shdr_size > buf_len) { + pr_debug("Section headers truncated.\n"); + return false; + } + } + + return true; +} + +static int elf_read_ehdr(const char *buf, size_t len, struct elfhdr *ehdr) +{ + struct elfhdr *buf_ehdr; + + if (len < sizeof(*buf_ehdr)) { + pr_debug("Buffer is too small to hold ELF header.\n"); + return -ENOEXEC; + } + + memset(ehdr, 0, sizeof(*ehdr)); + memcpy(ehdr->e_ident, buf, sizeof(ehdr->e_ident)); + if (!elf_is_elf_file(ehdr)) { + pr_debug("No ELF header magic.\n"); + return -ENOEXEC; + } + + if (ehdr->e_ident[EI_CLASS] != ELF_CLASS) { + pr_debug("Not a supported ELF class.\n"); + return -ENOEXEC; + } else if (ehdr->e_ident[EI_DATA] != ELFDATA2LSB && + ehdr->e_ident[EI_DATA] != ELFDATA2MSB) { + pr_debug("Not a supported ELF data format.\n"); + return -ENOEXEC; + } + + buf_ehdr = (struct elfhdr *) buf; + if (elf16_to_cpu(ehdr, buf_ehdr->e_ehsize) != sizeof(*buf_ehdr)) { + pr_debug("Bad ELF header size.\n"); + return -ENOEXEC; + } + + ehdr->e_type = elf16_to_cpu(ehdr, buf_ehdr->e_type); + ehdr->e_machine = elf16_to_cpu(ehdr, buf_ehdr->e_machine); + ehdr->e_version = elf32_to_cpu(ehdr, buf_ehdr->e_version); + ehdr->e_entry = elf_addr_to_cpu(ehdr, buf_ehdr->e_entry); + ehdr->e_phoff = elf_addr_to_cpu(ehdr, buf_ehdr->e_phoff); + ehdr->e_shoff = elf_addr_to_cpu(ehdr, buf_ehdr->e_shoff); + ehdr->e_flags = elf32_to_cpu(ehdr, buf_ehdr->e_flags); + ehdr->e_phentsize = elf16_to_cpu(ehdr, buf_ehdr->e_phentsize); + ehdr->e_phnum = elf16_to_cpu(ehdr, buf_ehdr->e_phnum); + ehdr->e_shentsize = elf16_to_cpu(ehdr, buf_ehdr->e_shentsize); + ehdr->e_shnum = elf16_to_cpu(ehdr, buf_ehdr->e_shnum); + ehdr->e_shstrndx = elf16_to_cpu(ehdr, buf_ehdr->e_shstrndx); + + return elf_is_ehdr_sane(ehdr, len) ? 0 : -ENOEXEC; +} + +/** + * elf_is_phdr_sane - check that it is safe to use the program header + * @buf_len: size of the buffer in which the ELF file is loaded. + */ +static bool elf_is_phdr_sane(const struct elf_phdr *phdr, size_t buf_len) +{ + + if (phdr->p_offset + phdr->p_filesz < phdr->p_offset) { + pr_debug("ELF segment location wraps around.\n"); + return false; + } else if (phdr->p_offset + phdr->p_filesz > buf_len) { + pr_debug("ELF segment not in file.\n"); + return false; + } else if (phdr->p_paddr + phdr->p_memsz < phdr->p_paddr) { + pr_debug("ELF segment address wraps around.\n"); + return false; + } + + return true; +} + +static int elf_read_phdr(const char *buf, size_t len, struct elf_info *elf_info, + int idx) +{ + /* Override the const in proghdrs, we are the ones doing the loading. */ + struct elf_phdr *phdr = (struct elf_phdr *) &elf_info->proghdrs[idx]; + const char *pbuf; + struct elf_phdr *buf_phdr; + + pbuf = buf + elf_info->ehdr->e_phoff + (idx * sizeof(*buf_phdr)); + buf_phdr = (struct elf_phdr *) pbuf; + + phdr->p_type = elf32_to_cpu(elf_info->ehdr, buf_phdr->p_type); + phdr->p_offset = elf_addr_to_cpu(elf_info->ehdr, buf_phdr->p_offset); + phdr->p_paddr = elf_addr_to_cpu(elf_info->ehdr, buf_phdr->p_paddr); + phdr->p_vaddr = elf_addr_to_cpu(elf_info->ehdr, buf_phdr->p_vaddr); + phdr->p_flags = elf32_to_cpu(elf_info->ehdr, buf_phdr->p_flags); + + /* + * The following fields have a type equivalent to Elf_Addr + * both in 32 bit and 64 bit ELF. + */ + phdr->p_filesz = elf_addr_to_cpu(elf_info->ehdr, buf_phdr->p_filesz); + phdr->p_memsz = elf_addr_to_cpu(elf_info->ehdr, buf_phdr->p_memsz); + phdr->p_align = elf_addr_to_cpu(elf_info->ehdr, buf_phdr->p_align); + + return elf_is_phdr_sane(phdr, len) ? 0 : -ENOEXEC; +} + +/** + * elf_read_phdrs - read the program headers from the buffer + * + * This function assumes that the program header table was checked for sanity. + * Use elf_is_ehdr_sane() if it wasn't. + */ +static int elf_read_phdrs(const char *buf, size_t len, + struct elf_info *elf_info) +{ + size_t phdr_size, i; + const struct elfhdr *ehdr = elf_info->ehdr; + + /* + * e_phnum is at most 65535 so calculating the size of the + * program header cannot overflow. + */ + phdr_size = sizeof(struct elf_phdr) * ehdr->e_phnum; + + elf_info->proghdrs = kzalloc(phdr_size, GFP_KERNEL); + if (!elf_info->proghdrs) + return -ENOMEM; + + for (i = 0; i < ehdr->e_phnum; i++) { + int ret; + + ret = elf_read_phdr(buf, len, elf_info, i); + if (ret) { + kfree(elf_info->proghdrs); + elf_info->proghdrs = NULL; + return ret; + } + } + + return 0; +} + +/** + * elf_is_shdr_sane - check that it is safe to use the section header + * @buf_len: size of the buffer in which the ELF file is loaded. + */ +static bool elf_is_shdr_sane(const struct elf_shdr *shdr, size_t buf_len) +{ + bool size_ok; + + /* SHT_NULL headers have undefined values, so we can't check them. */ + if (shdr->sh_type == SHT_NULL) + return true; + + /* Now verify sh_entsize */ + switch (shdr->sh_type) { + case SHT_SYMTAB: + size_ok = shdr->sh_entsize == sizeof(Elf_Sym); + break; + case SHT_RELA: + size_ok = shdr->sh_entsize == sizeof(Elf_Rela); + break; + case SHT_DYNAMIC: + size_ok = shdr->sh_entsize == sizeof(Elf_Dyn); + break; + case SHT_REL: + size_ok = shdr->sh_entsize == sizeof(Elf_Rel); + break; + case SHT_NOTE: + case SHT_PROGBITS: + case SHT_HASH: + case SHT_NOBITS: + default: + /* + * This is a section whose entsize requirements + * I don't care about. If I don't know about + * the section I can't care about it's entsize + * requirements. + */ + size_ok = true; + break; + } + + if (!size_ok) { + pr_debug("ELF section with wrong entry size.\n"); + return false; + } else if (shdr->sh_addr + shdr->sh_size < shdr->sh_addr) { + pr_debug("ELF section address wraps around.\n"); + return false; + } + + if (shdr->sh_type != SHT_NOBITS) { + if (shdr->sh_offset + shdr->sh_size < shdr->sh_offset) { + pr_debug("ELF section location wraps around.\n"); + return false; + } else if (shdr->sh_offset + shdr->sh_size > buf_len) { + pr_debug("ELF section not in file.\n"); + return false; + } + } + + return true; +} + +static int elf_read_shdr(const char *buf, size_t len, struct elf_info *elf_info, + int idx) +{ + struct elf_shdr *shdr = &elf_info->sechdrs[idx]; + const struct elfhdr *ehdr = elf_info->ehdr; + const char *sbuf; + struct elf_shdr *buf_shdr; + + sbuf = buf + ehdr->e_shoff + idx * sizeof(*buf_shdr); + buf_shdr = (struct elf_shdr *) sbuf; + + shdr->sh_name = elf32_to_cpu(ehdr, buf_shdr->sh_name); + shdr->sh_type = elf32_to_cpu(ehdr, buf_shdr->sh_type); + shdr->sh_addr = elf_addr_to_cpu(ehdr, buf_shdr->sh_addr); + shdr->sh_offset = elf_addr_to_cpu(ehdr, buf_shdr->sh_offset); + shdr->sh_link = elf32_to_cpu(ehdr, buf_shdr->sh_link); + shdr->sh_info = elf32_to_cpu(ehdr, buf_shdr->sh_info); + + /* + * The following fields have a type equivalent to Elf_Addr + * both in 32 bit and 64 bit ELF. + */ + shdr->sh_flags = elf_addr_to_cpu(ehdr, buf_shdr->sh_flags); + shdr->sh_size = elf_addr_to_cpu(ehdr, buf_shdr->sh_size); + shdr->sh_addralign = elf_addr_to_cpu(ehdr, buf_shdr->sh_addralign); + shdr->sh_entsize = elf_addr_to_cpu(ehdr, buf_shdr->sh_entsize); + + return elf_is_shdr_sane(shdr, len) ? 0 : -ENOEXEC; +} + +/** + * elf_read_shdrs - read the section headers from the buffer + * + * This function assumes that the section header table was checked for sanity. + * Use elf_is_ehdr_sane() if it wasn't. + */ +static int elf_read_shdrs(const char *buf, size_t len, + struct elf_info *elf_info) +{ + size_t shdr_size, i; + + /* + * e_shnum is at most 65536 so calculating + * the size of the section header cannot overflow. + */ + shdr_size = sizeof(struct elf_shdr) * elf_info->ehdr->e_shnum; + + elf_info->sechdrs = kzalloc(shdr_size, GFP_KERNEL); + if (!elf_info->sechdrs) + return -ENOMEM; + + for (i = 0; i < elf_info->ehdr->e_shnum; i++) { + int ret; + + ret = elf_read_shdr(buf, len, elf_info, i); + if (ret) { + kfree(elf_info->sechdrs); + elf_info->sechdrs = NULL; + return ret; + } + } + + return 0; +} + +/** + * elf_read_from_buffer - read ELF file and sets up ELF header and ELF info + * @buf: Buffer to read ELF file from. + * @len: Size of @buf. + * @ehdr: Pointer to existing struct which will be populated. + * @elf_info: Pointer to existing struct which will be populated. + * + * This function allows reading ELF files with different byte order than + * the kernel, byte-swapping the fields as needed. + * + * Return: + * On success returns 0, and the caller should call elf_free_info(elf_info) to + * free the memory allocated for the section and program headers. + */ +int elf_read_from_buffer(const char *buf, size_t len, struct elfhdr *ehdr, + struct elf_info *elf_info) +{ + int ret; + + ret = elf_read_ehdr(buf, len, ehdr); + if (ret) + return ret; + + elf_info->buffer = buf; + elf_info->ehdr = ehdr; + if (ehdr->e_phoff > 0 && ehdr->e_phnum > 0) { + ret = elf_read_phdrs(buf, len, elf_info); + if (ret) + return ret; + } + if (ehdr->e_shoff > 0 && ehdr->e_shnum > 0) { + ret = elf_read_shdrs(buf, len, elf_info); + if (ret) { + kfree(elf_info->proghdrs); + return ret; + } + } + + return 0; +} + +/** + * elf_free_info - free memory allocated by elf_read_from_buffer + */ +void elf_free_info(struct elf_info *elf_info) +{ + kfree(elf_info->proghdrs); + kfree(elf_info->sechdrs); + memset(elf_info, 0, sizeof(*elf_info)); +} +/** + * build_elf_exec_info - read ELF executable and check that we can use it + */ +static int build_elf_exec_info(const char *buf, size_t len, struct elfhdr *ehdr, + struct elf_info *elf_info) +{ + int i; + int ret; + + ret = elf_read_from_buffer(buf, len, ehdr, elf_info); + if (ret) + return ret; + + /* Big endian vmlinux has type ET_DYN. */ + if (ehdr->e_type != ET_EXEC && ehdr->e_type != ET_DYN) { + pr_err("Not an ELF executable.\n"); + goto error; + } else if (!elf_info->proghdrs) { + pr_err("No ELF program header.\n"); + goto error; + } + + for (i = 0; i < ehdr->e_phnum; i++) { + /* + * Kexec does not support loading interpreters. + * In addition this check keeps us from attempting + * to kexec ordinay executables. + */ + if (elf_info->proghdrs[i].p_type == PT_INTERP) { + pr_err("Requires an ELF interpreter.\n"); + goto error; + } + } + + return 0; +error: + elf_free_info(elf_info); + return -ENOEXEC; +} + +static int elf64_probe(const char *buf, unsigned long len) +{ + struct elfhdr ehdr; + struct elf_info elf_info; + int ret; + + ret = build_elf_exec_info(buf, len, &ehdr, &elf_info); + if (ret) + return ret; + + elf_free_info(&elf_info); + + return elf_check_arch(&ehdr) ? 0 : -ENOEXEC; +} + +/** + * elf_exec_load - load ELF executable image + * @lowest_load_addr: On return, will be the address where the first PT_LOAD + * section will be loaded in memory. + * + * Return: + * 0 on success, negative value on failure. + */ +static int elf_exec_load(struct kimage *image, struct elfhdr *ehdr, + struct elf_info *elf_info, + unsigned long *lowest_load_addr) +{ + unsigned long base = 0, lowest_addr = UINT_MAX; + int ret; + size_t i; + struct kexec_buf kbuf = { .image = image, .buf_max = ppc64_rma_size, + .top_down = false }; + + /* Read in the PT_LOAD segments. */ + for (i = 0; i < ehdr->e_phnum; i++) { + unsigned long load_addr; + size_t size; + const struct elf_phdr *phdr; + + phdr = &elf_info->proghdrs[i]; + if (phdr->p_type != PT_LOAD) + continue; + + size = phdr->p_filesz; + if (size > phdr->p_memsz) + size = phdr->p_memsz; + + kbuf.buffer = (void *) elf_info->buffer + phdr->p_offset; + kbuf.bufsz = size; + kbuf.memsz = phdr->p_memsz; + kbuf.buf_align = phdr->p_align; + kbuf.buf_min = phdr->p_paddr + base; + ret = kexec_add_buffer(&kbuf); + if (ret) + goto out; + load_addr = kbuf.mem; + + if (load_addr < lowest_addr) + lowest_addr = load_addr; + } + + /* Update entry point to reflect new load address. */ + ehdr->e_entry += base; + + *lowest_load_addr = lowest_addr; + ret = 0; + out: + return ret; +} + +static void *elf64_load(struct kimage *image, char *kernel_buf, + unsigned long kernel_len, char *initrd, + unsigned long initrd_len, char *cmdline, + unsigned long cmdline_len) +{ + int ret; + unsigned int fdt_size; + unsigned long kernel_load_addr, purgatory_load_addr; + unsigned long initrd_load_addr = 0, fdt_load_addr; + void *fdt; + const void *slave_code; + struct elfhdr ehdr; + struct elf_info elf_info; + struct kexec_buf kbuf = { .image = image, .buf_min = 0, + .buf_max = ppc64_rma_size }; + + ret = build_elf_exec_info(kernel_buf, kernel_len, &ehdr, &elf_info); + if (ret) + goto out; + + ret = elf_exec_load(image, &ehdr, &elf_info, &kernel_load_addr); + if (ret) + goto out; + + pr_debug("Loaded the kernel at 0x%lx\n", kernel_load_addr); + + ret = kexec_load_purgatory(image, 0, ppc64_rma_size, true, + &purgatory_load_addr); + if (ret) { + pr_err("Loading purgatory failed.\n"); + goto out; + } + + pr_debug("Loaded purgatory at 0x%lx\n", purgatory_load_addr); + + if (initrd != NULL) { + kbuf.buffer = initrd; + kbuf.bufsz = kbuf.memsz = initrd_len; + kbuf.buf_align = PAGE_SIZE; + kbuf.top_down = false; + ret = kexec_add_buffer(&kbuf); + if (ret) + goto out; + initrd_load_addr = kbuf.mem; + + pr_debug("Loaded initrd at 0x%lx\n", initrd_load_addr); + } + + fdt_size = fdt_totalsize(initial_boot_params) * 2; + fdt = kmalloc(fdt_size, GFP_KERNEL); + if (!fdt) { + pr_err("Not enough memory for the device tree.\n"); + ret = -ENOMEM; + goto out; + } + ret = fdt_open_into(initial_boot_params, fdt, fdt_size); + if (ret < 0) { + pr_err("Error setting up the new device tree.\n"); + ret = -EINVAL; + goto out; + } + + ret = setup_new_fdt(fdt, initrd_load_addr, initrd_len, cmdline); + if (ret) + goto out; + + fdt_pack(fdt); + + kbuf.buffer = fdt; + kbuf.bufsz = kbuf.memsz = fdt_size; + kbuf.buf_align = PAGE_SIZE; + kbuf.top_down = true; + ret = kexec_add_buffer(&kbuf); + if (ret) + goto out; + fdt_load_addr = kbuf.mem; + + pr_debug("Loaded device tree at 0x%lx\n", fdt_load_addr); + + slave_code = elf_info.buffer + elf_info.proghdrs[0].p_offset; + ret = setup_purgatory(image, slave_code, fdt, kernel_load_addr, + fdt_load_addr); + if (ret) + pr_err("Error setting up the purgatory.\n"); + +out: + elf_free_info(&elf_info); + + /* Make kimage_file_post_load_cleanup free the fdt buffer for us. */ + return ret ? ERR_PTR(ret) : fdt; +} + +struct kexec_file_ops kexec_elf64_ops = { + .probe = elf64_probe, + .load = elf64_load, +}; diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c index e785cc9e1ecd..ad108b842669 100644 --- a/arch/powerpc/kernel/kprobes.c +++ b/arch/powerpc/kernel/kprobes.c @@ -140,13 +140,16 @@ void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri, regs->link = (unsigned long)kretprobe_trampoline; } -static int __kprobes kprobe_handler(struct pt_regs *regs) +int __kprobes kprobe_handler(struct pt_regs *regs) { struct kprobe *p; int ret = 0; unsigned int *addr = (unsigned int *)regs->nip; struct kprobe_ctlblk *kcb; + if (user_mode(regs)) + return 0; + /* * We don't want to be preempted for the entire * duration of kprobe processing @@ -359,12 +362,12 @@ static int __kprobes trampoline_probe_handler(struct kprobe *p, * single-stepped a copy of the instruction. The address of this * copy is p->ainsn.insn. */ -static int __kprobes post_kprobe_handler(struct pt_regs *regs) +int __kprobes kprobe_post_handler(struct pt_regs *regs) { struct kprobe *cur = kprobe_running(); struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - if (!cur) + if (!cur || user_mode(regs)) return 0; /* make sure we got here for instruction we have a kprobe on */ @@ -449,7 +452,7 @@ int __kprobes kprobe_fault_handler(struct pt_regs *regs, int trapnr) * zero, try to fix up. */ if ((entry = search_exception_tables(regs->nip)) != NULL) { - regs->nip = entry->fixup; + regs->nip = extable_fixup(entry); return 1; } @@ -470,25 +473,7 @@ int __kprobes kprobe_fault_handler(struct pt_regs *regs, int trapnr) int __kprobes kprobe_exceptions_notify(struct notifier_block *self, unsigned long val, void *data) { - struct die_args *args = (struct die_args *)data; - int ret = NOTIFY_DONE; - - if (args->regs && user_mode(args->regs)) - return ret; - - switch (val) { - case DIE_BPT: - if (kprobe_handler(args->regs)) - ret = NOTIFY_STOP; - break; - case DIE_SSTEP: - if (post_kprobe_handler(args->regs)) - ret = NOTIFY_STOP; - break; - default: - break; - } - return ret; + return NOTIFY_DONE; } unsigned long arch_deref_entry_point(void *entry) diff --git a/arch/powerpc/kernel/machine_kexec_64.c b/arch/powerpc/kernel/machine_kexec_64.c index a205fa3d9bf3..5c12e21d0d1a 100644 --- a/arch/powerpc/kernel/machine_kexec_64.c +++ b/arch/powerpc/kernel/machine_kexec_64.c @@ -310,7 +310,7 @@ void default_machine_kexec(struct kimage *image) if (!kdump_in_progress()) kexec_prepare_cpus(); - pr_debug("kexec: Starting switchover sequence.\n"); + printk("kexec: Starting switchover sequence.\n"); /* switch to a staticly allocated stack. Based on irq stack code. * We setup preempt_count to avoid using VMX in memcpy. diff --git a/arch/powerpc/kernel/machine_kexec_file_64.c b/arch/powerpc/kernel/machine_kexec_file_64.c new file mode 100644 index 000000000000..7abc8a75ee48 --- /dev/null +++ b/arch/powerpc/kernel/machine_kexec_file_64.c @@ -0,0 +1,338 @@ +/* + * ppc64 code to implement the kexec_file_load syscall + * + * Copyright (C) 2004 Adam Litke (agl@us.ibm.com) + * Copyright (C) 2004 IBM Corp. + * Copyright (C) 2004,2005 Milton D Miller II, IBM Corporation + * Copyright (C) 2005 R Sharada (sharada@in.ibm.com) + * Copyright (C) 2006 Mohan Kumar M (mohan@in.ibm.com) + * Copyright (C) 2016 IBM Corporation + * + * Based on kexec-tools' kexec-elf-ppc64.c, fs2dt.c. + * Heavily modified for the kernel by + * Thiago Jung Bauermann <bauerman@linux.vnet.ibm.com>. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation (version 2 of the License). + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include <linux/slab.h> +#include <linux/kexec.h> +#include <linux/memblock.h> +#include <linux/of_fdt.h> +#include <linux/libfdt.h> + +#define SLAVE_CODE_SIZE 256 + +static struct kexec_file_ops *kexec_file_loaders[] = { + &kexec_elf64_ops, +}; + +int arch_kexec_kernel_image_probe(struct kimage *image, void *buf, + unsigned long buf_len) +{ + int i, ret = -ENOEXEC; + struct kexec_file_ops *fops; + + /* We don't support crash kernels yet. */ + if (image->type == KEXEC_TYPE_CRASH) + return -ENOTSUPP; + + for (i = 0; i < ARRAY_SIZE(kexec_file_loaders); i++) { + fops = kexec_file_loaders[i]; + if (!fops || !fops->probe) + continue; + + ret = fops->probe(buf, buf_len); + if (!ret) { + image->fops = fops; + return ret; + } + } + + return ret; +} + +void *arch_kexec_kernel_image_load(struct kimage *image) +{ + if (!image->fops || !image->fops->load) + return ERR_PTR(-ENOEXEC); + + return image->fops->load(image, image->kernel_buf, + image->kernel_buf_len, image->initrd_buf, + image->initrd_buf_len, image->cmdline_buf, + image->cmdline_buf_len); +} + +int arch_kimage_file_post_load_cleanup(struct kimage *image) +{ + if (!image->fops || !image->fops->cleanup) + return 0; + + return image->fops->cleanup(image->image_loader_data); +} + +/** + * arch_kexec_walk_mem - call func(data) for each unreserved memory block + * @kbuf: Context info for the search. Also passed to @func. + * @func: Function to call for each memory block. + * + * This function is used by kexec_add_buffer and kexec_locate_mem_hole + * to find unreserved memory to load kexec segments into. + * + * Return: The memory walk will stop when func returns a non-zero value + * and that value will be returned. If all free regions are visited without + * func returning non-zero, then zero will be returned. + */ +int arch_kexec_walk_mem(struct kexec_buf *kbuf, int (*func)(u64, u64, void *)) +{ + int ret = 0; + u64 i; + phys_addr_t mstart, mend; + + if (kbuf->top_down) { + for_each_free_mem_range_reverse(i, NUMA_NO_NODE, 0, + &mstart, &mend, NULL) { + /* + * In memblock, end points to the first byte after the + * range while in kexec, end points to the last byte + * in the range. + */ + ret = func(mstart, mend - 1, kbuf); + if (ret) + break; + } + } else { + for_each_free_mem_range(i, NUMA_NO_NODE, 0, &mstart, &mend, + NULL) { + /* + * In memblock, end points to the first byte after the + * range while in kexec, end points to the last byte + * in the range. + */ + ret = func(mstart, mend - 1, kbuf); + if (ret) + break; + } + } + + return ret; +} + +/** + * setup_purgatory - initialize the purgatory's global variables + * @image: kexec image. + * @slave_code: Slave code for the purgatory. + * @fdt: Flattened device tree for the next kernel. + * @kernel_load_addr: Address where the kernel is loaded. + * @fdt_load_addr: Address where the flattened device tree is loaded. + * + * Return: 0 on success, or negative errno on error. + */ +int setup_purgatory(struct kimage *image, const void *slave_code, + const void *fdt, unsigned long kernel_load_addr, + unsigned long fdt_load_addr) +{ + unsigned int *slave_code_buf, master_entry; + int ret; + + slave_code_buf = kmalloc(SLAVE_CODE_SIZE, GFP_KERNEL); + if (!slave_code_buf) + return -ENOMEM; + + /* Get the slave code from the new kernel and put it in purgatory. */ + ret = kexec_purgatory_get_set_symbol(image, "purgatory_start", + slave_code_buf, SLAVE_CODE_SIZE, + true); + if (ret) { + kfree(slave_code_buf); + return ret; + } + + master_entry = slave_code_buf[0]; + memcpy(slave_code_buf, slave_code, SLAVE_CODE_SIZE); + slave_code_buf[0] = master_entry; + ret = kexec_purgatory_get_set_symbol(image, "purgatory_start", + slave_code_buf, SLAVE_CODE_SIZE, + false); + kfree(slave_code_buf); + + ret = kexec_purgatory_get_set_symbol(image, "kernel", &kernel_load_addr, + sizeof(kernel_load_addr), false); + if (ret) + return ret; + ret = kexec_purgatory_get_set_symbol(image, "dt_offset", &fdt_load_addr, + sizeof(fdt_load_addr), false); + if (ret) + return ret; + + return 0; +} + +/** + * delete_fdt_mem_rsv - delete memory reservation with given address and size + * + * Return: 0 on success, or negative errno on error. + */ +static int delete_fdt_mem_rsv(void *fdt, unsigned long start, unsigned long size) +{ + int i, ret, num_rsvs = fdt_num_mem_rsv(fdt); + + for (i = 0; i < num_rsvs; i++) { + uint64_t rsv_start, rsv_size; + + ret = fdt_get_mem_rsv(fdt, i, &rsv_start, &rsv_size); + if (ret) { + pr_err("Malformed device tree.\n"); + return -EINVAL; + } + + if (rsv_start == start && rsv_size == size) { + ret = fdt_del_mem_rsv(fdt, i); + if (ret) { + pr_err("Error deleting device tree reservation.\n"); + return -EINVAL; + } + + return 0; + } + } + + return -ENOENT; +} + +/* + * setup_new_fdt - modify /chosen and memory reservation for the next kernel + * @fdt: Flattened device tree for the next kernel. + * @initrd_load_addr: Address where the next initrd will be loaded. + * @initrd_len: Size of the next initrd, or 0 if there will be none. + * @cmdline: Command line for the next kernel, or NULL if there will + * be none. + * + * Return: 0 on success, or negative errno on error. + */ +int setup_new_fdt(void *fdt, unsigned long initrd_load_addr, + unsigned long initrd_len, const char *cmdline) +{ + int ret, chosen_node; + const void *prop; + + /* Remove memory reservation for the current device tree. */ + ret = delete_fdt_mem_rsv(fdt, __pa(initial_boot_params), + fdt_totalsize(initial_boot_params)); + if (ret == 0) + pr_debug("Removed old device tree reservation.\n"); + else if (ret != -ENOENT) + return ret; + + chosen_node = fdt_path_offset(fdt, "/chosen"); + if (chosen_node == -FDT_ERR_NOTFOUND) { + chosen_node = fdt_add_subnode(fdt, fdt_path_offset(fdt, "/"), + "chosen"); + if (chosen_node < 0) { + pr_err("Error creating /chosen.\n"); + return -EINVAL; + } + } else if (chosen_node < 0) { + pr_err("Malformed device tree: error reading /chosen.\n"); + return -EINVAL; + } + + /* Did we boot using an initrd? */ + prop = fdt_getprop(fdt, chosen_node, "linux,initrd-start", NULL); + if (prop) { + uint64_t tmp_start, tmp_end, tmp_size; + + tmp_start = fdt64_to_cpu(*((const fdt64_t *) prop)); + + prop = fdt_getprop(fdt, chosen_node, "linux,initrd-end", NULL); + if (!prop) { + pr_err("Malformed device tree.\n"); + return -EINVAL; + } + tmp_end = fdt64_to_cpu(*((const fdt64_t *) prop)); + + /* + * kexec reserves exact initrd size, while firmware may + * reserve a multiple of PAGE_SIZE, so check for both. + */ + tmp_size = tmp_end - tmp_start; + ret = delete_fdt_mem_rsv(fdt, tmp_start, tmp_size); + if (ret == -ENOENT) + ret = delete_fdt_mem_rsv(fdt, tmp_start, + round_up(tmp_size, PAGE_SIZE)); + if (ret == 0) + pr_debug("Removed old initrd reservation.\n"); + else if (ret != -ENOENT) + return ret; + + /* If there's no new initrd, delete the old initrd's info. */ + if (initrd_len == 0) { + ret = fdt_delprop(fdt, chosen_node, + "linux,initrd-start"); + if (ret) { + pr_err("Error deleting linux,initrd-start.\n"); + return -EINVAL; + } + + ret = fdt_delprop(fdt, chosen_node, "linux,initrd-end"); + if (ret) { + pr_err("Error deleting linux,initrd-end.\n"); + return -EINVAL; + } + } + } + + if (initrd_len) { + ret = fdt_setprop_u64(fdt, chosen_node, + "linux,initrd-start", + initrd_load_addr); + if (ret < 0) { + pr_err("Error setting up the new device tree.\n"); + return -EINVAL; + } + + /* initrd-end is the first address after the initrd image. */ + ret = fdt_setprop_u64(fdt, chosen_node, "linux,initrd-end", + initrd_load_addr + initrd_len); + if (ret < 0) { + pr_err("Error setting up the new device tree.\n"); + return -EINVAL; + } + + ret = fdt_add_mem_rsv(fdt, initrd_load_addr, initrd_len); + if (ret) { + pr_err("Error reserving initrd memory: %s\n", + fdt_strerror(ret)); + return -EINVAL; + } + } + + if (cmdline != NULL) { + ret = fdt_setprop_string(fdt, chosen_node, "bootargs", cmdline); + if (ret < 0) { + pr_err("Error setting up the new device tree.\n"); + return -EINVAL; + } + } else { + ret = fdt_delprop(fdt, chosen_node, "bootargs"); + if (ret && ret != -FDT_ERR_NOTFOUND) { + pr_err("Error deleting bootargs.\n"); + return -EINVAL; + } + } + + ret = fdt_setprop(fdt, chosen_node, "linux,booted-from-kexec", NULL, 0); + if (ret) { + pr_err("Error setting up the new device tree.\n"); + return -EINVAL; + } + + return 0; +} diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c index 5e7ece0fda9f..c6923ff45131 100644 --- a/arch/powerpc/kernel/mce.c +++ b/arch/powerpc/kernel/mce.c @@ -72,7 +72,6 @@ void save_mce_event(struct pt_regs *regs, long handled, struct mce_error_info *mce_err, uint64_t nip, uint64_t addr) { - uint64_t srr1; int index = __this_cpu_inc_return(mce_nest_count) - 1; struct machine_check_event *mce = this_cpu_ptr(&mce_event[index]); @@ -99,8 +98,6 @@ void save_mce_event(struct pt_regs *regs, long handled, mce->disposition = MCE_DISPOSITION_NOT_RECOVERED; mce->severity = MCE_SEV_ERROR_SYNC; - srr1 = regs->msr; - /* * Populate the mce error_type and type-specific error_type. */ diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S index 93cf7a5846a6..1863324c6a3c 100644 --- a/arch/powerpc/kernel/misc_32.S +++ b/arch/powerpc/kernel/misc_32.S @@ -614,7 +614,7 @@ _GLOBAL(start_secondary_resume) _GLOBAL(__main) blr -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE /* * Must be relocatable PIC code callable as a C function. */ diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S index 4f178671f230..32be2a844947 100644 --- a/arch/powerpc/kernel/misc_64.S +++ b/arch/powerpc/kernel/misc_64.S @@ -478,7 +478,7 @@ _GLOBAL(kexec_wait) addi r5,r5,kexec_flag-1b 99: HMT_LOW -#ifdef CONFIG_KEXEC /* use no memory without kexec */ +#ifdef CONFIG_KEXEC_CORE /* use no memory without kexec */ lwz r4,0(r5) cmpwi 0,r4,0 beq 99b @@ -503,7 +503,7 @@ kexec_flag: .long 0 -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE #ifdef CONFIG_PPC_BOOK3E /* * BOOK3E has no real MMU mode, so we have to setup the initial TLB @@ -716,4 +716,4 @@ _GLOBAL(kexec_sequence) mtlr 4 li r5,0 blr /* image->start(physid, image->start, 0); */ -#endif /* CONFIG_KEXEC */ +#endif /* CONFIG_KEXEC_CORE */ diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c index 183368e008cf..bb1807184bad 100644 --- a/arch/powerpc/kernel/module_64.c +++ b/arch/powerpc/kernel/module_64.c @@ -652,6 +652,11 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, *location = value - (unsigned long)location; break; + case R_PPC64_REL32: + /* 32 bits relative (used by relative exception tables) */ + *(u32 *)location = value - (unsigned long)location; + break; + case R_PPC64_TOCSAVE: /* * Marker reloc indicates we don't have to save r2. diff --git a/arch/powerpc/kernel/of_platform.c b/arch/powerpc/kernel/of_platform.c index b60a67d92ebd..34aeac54f120 100644 --- a/arch/powerpc/kernel/of_platform.c +++ b/arch/powerpc/kernel/of_platform.c @@ -114,11 +114,6 @@ static struct platform_driver of_pci_phb_driver = { }, }; -static __init int of_pci_phb_init(void) -{ - return platform_driver_register(&of_pci_phb_driver); -} - -device_initcall(of_pci_phb_init); +builtin_platform_driver(of_pci_phb_driver); #endif /* CONFIG_PPC_OF_PLATFORM_PCI */ diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 49a680d5ae37..04885cec24df 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -64,6 +64,12 @@ #include <linux/kprobes.h> #include <linux/kdebug.h> +#ifdef CONFIG_CC_STACKPROTECTOR +#include <linux/stackprotector.h> +unsigned long __stack_chk_guard __read_mostly; +EXPORT_SYMBOL(__stack_chk_guard); +#endif + /* Transactional Memory debug */ #ifdef TM_DEBUG_SW #define TM_DEBUG(x...) printk(KERN_INFO x) @@ -1051,14 +1057,6 @@ static inline void save_sprs(struct thread_struct *t) */ t->tar = mfspr(SPRN_TAR); } - - if (cpu_has_feature(CPU_FTR_ARCH_300)) { - /* Conditionally save Load Monitor registers, if enabled */ - if (t->fscr & FSCR_LM) { - t->lmrr = mfspr(SPRN_LMRR); - t->lmser = mfspr(SPRN_LMSER); - } - } #endif } @@ -1094,16 +1092,6 @@ static inline void restore_sprs(struct thread_struct *old_thread, if (old_thread->tar != new_thread->tar) mtspr(SPRN_TAR, new_thread->tar); } - - if (cpu_has_feature(CPU_FTR_ARCH_300)) { - /* Conditionally restore Load Monitor registers, if enabled */ - if (new_thread->fscr & FSCR_LM) { - if (old_thread->lmrr != new_thread->lmrr) - mtspr(SPRN_LMRR, new_thread->lmrr); - if (old_thread->lmser != new_thread->lmser) - mtspr(SPRN_LMSER, new_thread->lmser); - } - } #endif } diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index b0245bed6f54..f5d399e46193 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -156,21 +156,22 @@ static struct ibm_pa_feature { unsigned char pabit; /* bit number (big-endian) */ unsigned char invert; /* if 1, pa bit set => clear feature */ } ibm_pa_features[] __initdata = { - {0, 0, PPC_FEATURE_HAS_MMU, 0, 0, 0, 0}, - {0, 0, PPC_FEATURE_HAS_FPU, 0, 0, 1, 0}, - {CPU_FTR_CTRL, 0, 0, 0, 0, 3, 0}, - {CPU_FTR_NOEXECUTE, 0, 0, 0, 0, 6, 0}, - {CPU_FTR_NODSISRALIGN, 0, 0, 0, 1, 1, 1}, - {0, MMU_FTR_CI_LARGE_PAGE, 0, 0, 1, 2, 0}, - {CPU_FTR_REAL_LE, 0, PPC_FEATURE_TRUE_LE, 0, 5, 0, 0}, + { .pabyte = 0, .pabit = 0, .cpu_user_ftrs = PPC_FEATURE_HAS_MMU }, + { .pabyte = 0, .pabit = 1, .cpu_user_ftrs = PPC_FEATURE_HAS_FPU }, + { .pabyte = 0, .pabit = 3, .cpu_features = CPU_FTR_CTRL }, + { .pabyte = 0, .pabit = 6, .cpu_features = CPU_FTR_NOEXECUTE }, + { .pabyte = 1, .pabit = 2, .mmu_features = MMU_FTR_CI_LARGE_PAGE }, + { .pabyte = 40, .pabit = 0, .mmu_features = MMU_FTR_TYPE_RADIX }, + { .pabyte = 1, .pabit = 1, .invert = 1, .cpu_features = CPU_FTR_NODSISRALIGN }, + { .pabyte = 5, .pabit = 0, .cpu_features = CPU_FTR_REAL_LE, + .cpu_user_ftrs = PPC_FEATURE_TRUE_LE }, /* * If the kernel doesn't support TM (ie CONFIG_PPC_TRANSACTIONAL_MEM=n), * we don't want to turn on TM here, so we use the *_COMP versions * which are 0 if the kernel doesn't support TM. */ - {CPU_FTR_TM_COMP, 0, 0, - PPC_FEATURE2_HTM_COMP|PPC_FEATURE2_HTM_NOSC_COMP, 22, 0, 0}, - {0, MMU_FTR_TYPE_RADIX, 0, 0, 40, 0, 0}, + { .pabyte = 22, .pabit = 0, .cpu_features = CPU_FTR_TM_COMP, + .cpu_user_ftrs2 = PPC_FEATURE2_HTM_COMP | PPC_FEATURE2_HTM_NOSC_COMP }, }; static void __init scan_features(unsigned long node, const unsigned char *ftrs, @@ -427,7 +428,7 @@ static int __init early_init_dt_scan_chosen_ppc(unsigned long node, tce_alloc_end = *lprop; #endif -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE lprop = of_get_flat_dt_prop(node, "linux,crashkernel-base", NULL); if (lprop) crashk_res.start = *lprop; diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index 88ac964f4858..ec47a939cbdd 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -461,14 +461,14 @@ static int __init prom_next_node(phandle *nodep) } } -static int inline prom_getprop(phandle node, const char *pname, +static inline int prom_getprop(phandle node, const char *pname, void *value, size_t valuelen) { return call_prom("getprop", 4, 1, node, ADDR(pname), (u32)(unsigned long) value, (u32) valuelen); } -static int inline prom_getproplen(phandle node, const char *pname) +static inline int prom_getproplen(phandle node, const char *pname) { return call_prom("getproplen", 2, 1, node, ADDR(pname)); } @@ -635,13 +635,7 @@ static void __init early_cmdline_parse(void) * * See prom.h for the definition of the bits specified in the * architecture vector. - * - * Because the description vector contains a mix of byte and word - * values, we declare it as an unsigned char array, and use this - * macro to put word values in. */ -#define W(x) ((x) >> 24) & 0xff, ((x) >> 16) & 0xff, \ - ((x) >> 8) & 0xff, (x) & 0xff /* Firmware expects the value to be n - 1, where n is the # of vectors */ #define NUM_VECTORS(n) ((n) - 1) @@ -652,92 +646,205 @@ static void __init early_cmdline_parse(void) */ #define VECTOR_LENGTH(n) (1 + (n) - 2) -unsigned char ibm_architecture_vec[] = { - W(0xfffe0000), W(0x003a0000), /* POWER5/POWER5+ */ - W(0xffff0000), W(0x003e0000), /* POWER6 */ - W(0xffff0000), W(0x003f0000), /* POWER7 */ - W(0xffff0000), W(0x004b0000), /* POWER8E */ - W(0xffff0000), W(0x004c0000), /* POWER8NVL */ - W(0xffff0000), W(0x004d0000), /* POWER8 */ - W(0xffffffff), W(0x0f000004), /* all 2.07-compliant */ - W(0xffffffff), W(0x0f000003), /* all 2.06-compliant */ - W(0xffffffff), W(0x0f000002), /* all 2.05-compliant */ - W(0xfffffffe), W(0x0f000001), /* all 2.04-compliant and earlier */ - NUM_VECTORS(6), /* 6 option vectors */ - - /* option vector 1: processor architectures supported */ - VECTOR_LENGTH(2), /* length */ - 0, /* don't ignore, don't halt */ - OV1_PPC_2_00 | OV1_PPC_2_01 | OV1_PPC_2_02 | OV1_PPC_2_03 | - OV1_PPC_2_04 | OV1_PPC_2_05 | OV1_PPC_2_06 | OV1_PPC_2_07, +struct option_vector1 { + u8 byte1; + u8 arch_versions; +} __packed; + +struct option_vector2 { + u8 byte1; + __be16 reserved; + __be32 real_base; + __be32 real_size; + __be32 virt_base; + __be32 virt_size; + __be32 load_base; + __be32 min_rma; + __be32 min_load; + u8 min_rma_percent; + u8 max_pft_size; +} __packed; + +struct option_vector3 { + u8 byte1; + u8 byte2; +} __packed; + +struct option_vector4 { + u8 byte1; + u8 min_vp_cap; +} __packed; + +struct option_vector5 { + u8 byte1; + u8 byte2; + u8 byte3; + u8 cmo; + u8 associativity; + u8 bin_opts; + u8 micro_checkpoint; + u8 reserved0; + __be32 max_cpus; + __be16 papr_level; + __be16 reserved1; + u8 platform_facilities; + u8 reserved2; + __be16 reserved3; + u8 subprocessors; +} __packed; + +struct option_vector6 { + u8 reserved; + u8 secondary_pteg; + u8 os_name; +} __packed; + +struct ibm_arch_vec { + struct { u32 mask, val; } pvrs[10]; + + u8 num_vectors; + + u8 vec1_len; + struct option_vector1 vec1; + + u8 vec2_len; + struct option_vector2 vec2; + + u8 vec3_len; + struct option_vector3 vec3; + + u8 vec4_len; + struct option_vector4 vec4; + + u8 vec5_len; + struct option_vector5 vec5; + + u8 vec6_len; + struct option_vector6 vec6; +} __packed; + +struct ibm_arch_vec __cacheline_aligned ibm_architecture_vec = { + .pvrs = { + { + .mask = cpu_to_be32(0xfffe0000), /* POWER5/POWER5+ */ + .val = cpu_to_be32(0x003a0000), + }, + { + .mask = cpu_to_be32(0xffff0000), /* POWER6 */ + .val = cpu_to_be32(0x003e0000), + }, + { + .mask = cpu_to_be32(0xffff0000), /* POWER7 */ + .val = cpu_to_be32(0x003f0000), + }, + { + .mask = cpu_to_be32(0xffff0000), /* POWER8E */ + .val = cpu_to_be32(0x004b0000), + }, + { + .mask = cpu_to_be32(0xffff0000), /* POWER8NVL */ + .val = cpu_to_be32(0x004c0000), + }, + { + .mask = cpu_to_be32(0xffff0000), /* POWER8 */ + .val = cpu_to_be32(0x004d0000), + }, + { + .mask = cpu_to_be32(0xffffffff), /* all 2.07-compliant */ + .val = cpu_to_be32(0x0f000004), + }, + { + .mask = cpu_to_be32(0xffffffff), /* all 2.06-compliant */ + .val = cpu_to_be32(0x0f000003), + }, + { + .mask = cpu_to_be32(0xffffffff), /* all 2.05-compliant */ + .val = cpu_to_be32(0x0f000002), + }, + { + .mask = cpu_to_be32(0xfffffffe), /* all 2.04-compliant and earlier */ + .val = cpu_to_be32(0x0f000001), + }, + }, + + .num_vectors = NUM_VECTORS(6), + .vec1_len = VECTOR_LENGTH(sizeof(struct option_vector1)), + .vec1 = { + .byte1 = 0, + .arch_versions = OV1_PPC_2_00 | OV1_PPC_2_01 | OV1_PPC_2_02 | OV1_PPC_2_03 | + OV1_PPC_2_04 | OV1_PPC_2_05 | OV1_PPC_2_06 | OV1_PPC_2_07, + }, + + .vec2_len = VECTOR_LENGTH(sizeof(struct option_vector2)), /* option vector 2: Open Firmware options supported */ - VECTOR_LENGTH(33), /* length */ - OV2_REAL_MODE, - 0, 0, - W(0xffffffff), /* real_base */ - W(0xffffffff), /* real_size */ - W(0xffffffff), /* virt_base */ - W(0xffffffff), /* virt_size */ - W(0xffffffff), /* load_base */ - W(256), /* 256MB min RMA */ - W(0xffffffff), /* full client load */ - 0, /* min RMA percentage of total RAM */ - 48, /* max log_2(hash table size) */ + .vec2 = { + .byte1 = OV2_REAL_MODE, + .reserved = 0, + .real_base = cpu_to_be32(0xffffffff), + .real_size = cpu_to_be32(0xffffffff), + .virt_base = cpu_to_be32(0xffffffff), + .virt_size = cpu_to_be32(0xffffffff), + .load_base = cpu_to_be32(0xffffffff), + .min_rma = cpu_to_be32(256), /* 256MB min RMA */ + .min_load = cpu_to_be32(0xffffffff), /* full client load */ + .min_rma_percent = 0, /* min RMA percentage of total RAM */ + .max_pft_size = 48, /* max log_2(hash table size) */ + }, + .vec3_len = VECTOR_LENGTH(sizeof(struct option_vector3)), /* option vector 3: processor options supported */ - VECTOR_LENGTH(2), /* length */ - 0, /* don't ignore, don't halt */ - OV3_FP | OV3_VMX | OV3_DFP, + .vec3 = { + .byte1 = 0, /* don't ignore, don't halt */ + .byte2 = OV3_FP | OV3_VMX | OV3_DFP, + }, + .vec4_len = VECTOR_LENGTH(sizeof(struct option_vector4)), /* option vector 4: IBM PAPR implementation */ - VECTOR_LENGTH(2), /* length */ - 0, /* don't halt */ - OV4_MIN_ENT_CAP, /* minimum VP entitled capacity */ + .vec4 = { + .byte1 = 0, /* don't halt */ + .min_vp_cap = OV4_MIN_ENT_CAP, /* minimum VP entitled capacity */ + }, + .vec5_len = VECTOR_LENGTH(sizeof(struct option_vector5)), /* option vector 5: PAPR/OF options */ - VECTOR_LENGTH(21), /* length */ - 0, /* don't ignore, don't halt */ - OV5_FEAT(OV5_LPAR) | OV5_FEAT(OV5_SPLPAR) | OV5_FEAT(OV5_LARGE_PAGES) | - OV5_FEAT(OV5_DRCONF_MEMORY) | OV5_FEAT(OV5_DONATE_DEDICATE_CPU) | + .vec5 = { + .byte1 = 0, /* don't ignore, don't halt */ + .byte2 = OV5_FEAT(OV5_LPAR) | OV5_FEAT(OV5_SPLPAR) | OV5_FEAT(OV5_LARGE_PAGES) | + OV5_FEAT(OV5_DRCONF_MEMORY) | OV5_FEAT(OV5_DONATE_DEDICATE_CPU) | #ifdef CONFIG_PCI_MSI - /* PCIe/MSI support. Without MSI full PCIe is not supported */ - OV5_FEAT(OV5_MSI), + /* PCIe/MSI support. Without MSI full PCIe is not supported */ + OV5_FEAT(OV5_MSI), #else - 0, + 0, #endif - 0, + .byte3 = 0, + .cmo = #ifdef CONFIG_PPC_SMLPAR - OV5_FEAT(OV5_CMO) | OV5_FEAT(OV5_XCMO), + OV5_FEAT(OV5_CMO) | OV5_FEAT(OV5_XCMO), #else - 0, + 0, #endif - OV5_FEAT(OV5_TYPE1_AFFINITY) | OV5_FEAT(OV5_PRRN), - 0, - 0, - 0, - /* WARNING: The offset of the "number of cores" field below - * must match by the macro below. Update the definition if - * the structure layout changes. - */ -#define IBM_ARCH_VEC_NRCORES_OFFSET 133 - W(NR_CPUS), /* number of cores supported */ - 0, - 0, - 0, - 0, - OV5_FEAT(OV5_PFO_HW_RNG) | OV5_FEAT(OV5_PFO_HW_ENCR) | - OV5_FEAT(OV5_PFO_HW_842), /* Byte 17 */ - 0, /* Byte 18 */ - 0, /* Byte 19 */ - 0, /* Byte 20 */ - OV5_FEAT(OV5_SUB_PROCESSORS), /* Byte 21 */ + .associativity = OV5_FEAT(OV5_TYPE1_AFFINITY) | OV5_FEAT(OV5_PRRN), + .bin_opts = 0, + .micro_checkpoint = 0, + .reserved0 = 0, + .max_cpus = cpu_to_be32(NR_CPUS), /* number of cores supported */ + .papr_level = 0, + .reserved1 = 0, + .platform_facilities = OV5_FEAT(OV5_PFO_HW_RNG) | OV5_FEAT(OV5_PFO_HW_ENCR) | OV5_FEAT(OV5_PFO_HW_842), + .reserved2 = 0, + .reserved3 = 0, + .subprocessors = 1, + }, /* option vector 6: IBM PAPR hints */ - VECTOR_LENGTH(3), /* length */ - 0, - 0, - OV6_LINUX, + .vec6_len = VECTOR_LENGTH(sizeof(struct option_vector6)), + .vec6 = { + .reserved = 0, + .secondary_pteg = 0, + .os_name = OV6_LINUX, + }, }; /* Old method - ELF header with PT_NOTE sections only works on BE */ @@ -873,7 +980,6 @@ static void __init prom_send_capabilities(void) ihandle root; prom_arg_t ret; u32 cores; - unsigned char *ptcores; root = call_prom("open", 1, 1, ADDR("/")); if (root != 0) { @@ -884,37 +990,18 @@ static void __init prom_send_capabilities(void) * divide NR_CPUS. */ - /* The core value may start at an odd address. If such a word - * access is made at a cache line boundary, this leads to an - * exception which may not be handled at this time. - * Forcing a per byte access to avoid exception. - */ - ptcores = &ibm_architecture_vec[IBM_ARCH_VEC_NRCORES_OFFSET]; - cores = 0; - cores |= ptcores[0] << 24; - cores |= ptcores[1] << 16; - cores |= ptcores[2] << 8; - cores |= ptcores[3]; - if (cores != NR_CPUS) { - prom_printf("WARNING ! " - "ibm_architecture_vec structure inconsistent: %lu!\n", - cores); - } else { - cores = DIV_ROUND_UP(NR_CPUS, prom_count_smt_threads()); - prom_printf("Max number of cores passed to firmware: %lu (NR_CPUS = %lu)\n", - cores, NR_CPUS); - ptcores[0] = (cores >> 24) & 0xff; - ptcores[1] = (cores >> 16) & 0xff; - ptcores[2] = (cores >> 8) & 0xff; - ptcores[3] = cores & 0xff; - } + cores = DIV_ROUND_UP(NR_CPUS, prom_count_smt_threads()); + prom_printf("Max number of cores passed to firmware: %lu (NR_CPUS = %lu)\n", + cores, NR_CPUS); + + ibm_architecture_vec.vec5.max_cpus = cpu_to_be32(cores); /* try calling the ibm,client-architecture-support method */ prom_printf("Calling ibm,client-architecture-support..."); if (call_prom_ret("call-method", 3, 2, &ret, ADDR("ibm,client-architecture-support"), root, - ADDR(ibm_architecture_vec)) == 0) { + ADDR(&ibm_architecture_vec)) == 0) { /* the call exists... */ if (ret) prom_printf("\nWARNING: ibm,client-architecture" diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index 270ee30abdcf..f516ac508ae3 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -915,7 +915,7 @@ void __init setup_arch(char **cmdline_p) init_mm.context.pte_frag = NULL; #endif #ifdef CONFIG_SPAPR_TCE_IOMMU - mm_iommu_init(&init_mm.context); + mm_iommu_init(&init_mm); #endif irqstack_early_init(); exc_lvl_early_init(); diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 8d586cff8a41..6824157e4d2e 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -354,7 +354,7 @@ void early_setup_secondary(void) #endif /* CONFIG_SMP */ -#if defined(CONFIG_SMP) || defined(CONFIG_KEXEC) +#if defined(CONFIG_SMP) || defined(CONFIG_KEXEC_CORE) static bool use_spinloop(void) { if (!IS_ENABLED(CONFIG_PPC_BOOK3E)) @@ -399,7 +399,7 @@ void smp_release_cpus(void) DBG(" <- smp_release_cpus()\n"); } -#endif /* CONFIG_SMP || CONFIG_KEXEC */ +#endif /* CONFIG_SMP || CONFIG_KEXEC_CORE */ /* * Initialize some remaining members of the ppc64_caches and systemcfg diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 9c6f3fd58059..893bd7f79be6 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -193,7 +193,7 @@ int smp_request_message_ipi(int virq, int msg) if (msg < 0 || msg > PPC_MSG_DEBUGGER_BREAK) { return -EINVAL; } -#if !defined(CONFIG_DEBUGGER) && !defined(CONFIG_KEXEC) +#if !defined(CONFIG_DEBUGGER) && !defined(CONFIG_KEXEC_CORE) if (msg == PPC_MSG_DEBUGGER_BREAK) { return 1; } @@ -325,7 +325,7 @@ void tick_broadcast(const struct cpumask *mask) } #endif -#if defined(CONFIG_DEBUGGER) || defined(CONFIG_KEXEC) +#if defined(CONFIG_DEBUGGER) || defined(CONFIG_KEXEC_CORE) void smp_send_debugger_break(void) { int cpu; @@ -340,7 +340,7 @@ void smp_send_debugger_break(void) } #endif -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE void crash_send_ipi(void (*crash_ipi_callback)(struct pt_regs *)) { crash_ipi_function_ptr = crash_ipi_callback; diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index 023a462725b5..4239aaf74886 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -64,8 +64,9 @@ #include <asm/asm-prototypes.h> #include <asm/hmi.h> #include <sysdev/fsl_pci.h> +#include <asm/kprobes.h> -#if defined(CONFIG_DEBUGGER) || defined(CONFIG_KEXEC) +#if defined(CONFIG_DEBUGGER) || defined(CONFIG_KEXEC_CORE) int (*__debugger)(struct pt_regs *regs) __read_mostly; int (*__debugger_ipi)(struct pt_regs *regs) __read_mostly; int (*__debugger_bpt)(struct pt_regs *regs) __read_mostly; @@ -122,9 +123,6 @@ static unsigned long oops_begin(struct pt_regs *regs) int cpu; unsigned long flags; - if (debugger(regs)) - return 1; - oops_enter(); /* racy, but better than risking deadlock. */ @@ -150,14 +148,15 @@ static void oops_end(unsigned long flags, struct pt_regs *regs, int signr) { bust_spinlocks(0); - die_owner = -1; add_taint(TAINT_DIE, LOCKDEP_NOW_UNRELIABLE); die_nest_count--; oops_exit(); printk("\n"); - if (!die_nest_count) + if (!die_nest_count) { /* Nest count reaches zero, release the lock. */ + die_owner = -1; arch_spin_unlock(&die_lock); + } raw_local_irq_restore(flags); crash_fadump(regs, "die oops"); @@ -227,8 +226,12 @@ NOKPROBE_SYMBOL(__die); void die(const char *str, struct pt_regs *regs, long err) { - unsigned long flags = oops_begin(regs); + unsigned long flags; + if (debugger(regs)) + return; + + flags = oops_begin(regs); if (__die(str, regs, err)) err = 0; oops_end(flags, regs, err); @@ -365,7 +368,7 @@ static inline int check_io_access(struct pt_regs *regs) (*nip & 0x100)? "OUT to": "IN from", regs->gpr[rb] - _IO_BASE, nip); regs->msr |= MSR_RI; - regs->nip = entry->fixup; + regs->nip = extable_fixup(entry); return 1; } } @@ -824,6 +827,9 @@ void single_step_exception(struct pt_regs *regs) clear_single_step(regs); + if (kprobe_post_handler(regs)) + return; + if (notify_die(DIE_SSTEP, "single_step", regs, 5, 5, SIGTRAP) == NOTIFY_STOP) goto bail; @@ -1177,6 +1183,9 @@ void program_check_exception(struct pt_regs *regs) if (debugger_bpt(regs)) goto bail; + if (kprobe_handler(regs)) + goto bail; + /* trap exception */ if (notify_die(DIE_BPT, "breakpoint", regs, 5, 5, SIGTRAP) == NOTIFY_STOP) @@ -1430,7 +1439,6 @@ void facility_unavailable_exception(struct pt_regs *regs) [FSCR_TM_LG] = "TM", [FSCR_EBB_LG] = "EBB", [FSCR_TAR_LG] = "TAR", - [FSCR_LM_LG] = "LM", }; char *facility = "unknown"; u64 value; @@ -1488,14 +1496,6 @@ void facility_unavailable_exception(struct pt_regs *regs) emulate_single_step(regs); } return; - } else if ((status == FSCR_LM_LG) && cpu_has_feature(CPU_FTR_ARCH_300)) { - /* - * This process has touched LM, so turn it on forever - * for this process - */ - current->thread.fscr |= FSCR_LM; - mtspr(SPRN_FSCR, current->thread.fscr); - return; } if (status == FSCR_TM_LG) { @@ -1519,7 +1519,8 @@ void facility_unavailable_exception(struct pt_regs *regs) return; } - if ((status < ARRAY_SIZE(facility_strings)) && + if ((hv || status >= 2) && + (status < ARRAY_SIZE(facility_strings)) && facility_strings[status]) facility = facility_strings[status]; @@ -1527,9 +1528,8 @@ void facility_unavailable_exception(struct pt_regs *regs) if (!arch_irq_disabled_regs(regs)) local_irq_enable(); - pr_err_ratelimited( - "%sFacility '%s' unavailable, exception at 0x%lx, MSR=%lx\n", - hv ? "Hypervisor " : "", facility, regs->nip, regs->msr); + pr_err_ratelimited("%sFacility '%s' unavailable (%d), exception at 0x%lx, MSR=%lx\n", + hv ? "Hypervisor " : "", facility, status, regs->nip, regs->msr); out: if (user_mode(regs)) { @@ -1754,6 +1754,9 @@ void DebugException(struct pt_regs *regs, unsigned long debug_status) return; } + if (kprobe_post_handler(regs)) + return; + if (notify_die(DIE_SSTEP, "block_step", regs, 5, 5, SIGTRAP) == NOTIFY_STOP) { return; @@ -1768,6 +1771,9 @@ void DebugException(struct pt_regs *regs, unsigned long debug_status) /* Clear the instruction completion event */ mtspr(SPRN_DBSR, DBSR_IC); + if (kprobe_post_handler(regs)) + return; + if (notify_die(DIE_SSTEP, "single_step", regs, 5, 5, SIGTRAP) == NOTIFY_STOP) { return; diff --git a/arch/powerpc/kernel/vio.c b/arch/powerpc/kernel/vio.c deleted file mode 100644 index b3813ddb2fb4..000000000000 --- a/arch/powerpc/kernel/vio.c +++ /dev/null @@ -1,1702 +0,0 @@ -/* - * IBM PowerPC Virtual I/O Infrastructure Support. - * - * Copyright (c) 2003,2008 IBM Corp. - * Dave Engebretsen engebret@us.ibm.com - * Santiago Leon santil@us.ibm.com - * Hollis Blanchard <hollisb@us.ibm.com> - * Stephen Rothwell - * Robert Jennings <rcjenn@us.ibm.com> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ - -#include <linux/cpu.h> -#include <linux/types.h> -#include <linux/delay.h> -#include <linux/stat.h> -#include <linux/device.h> -#include <linux/init.h> -#include <linux/slab.h> -#include <linux/console.h> -#include <linux/export.h> -#include <linux/mm.h> -#include <linux/dma-mapping.h> -#include <linux/kobject.h> - -#include <asm/iommu.h> -#include <asm/dma.h> -#include <asm/vio.h> -#include <asm/prom.h> -#include <asm/firmware.h> -#include <asm/tce.h> -#include <asm/page.h> -#include <asm/hvcall.h> - -static struct vio_dev vio_bus_device = { /* fake "parent" device */ - .name = "vio", - .type = "", - .dev.init_name = "vio", - .dev.bus = &vio_bus_type, -}; - -#ifdef CONFIG_PPC_SMLPAR -/** - * vio_cmo_pool - A pool of IO memory for CMO use - * - * @size: The size of the pool in bytes - * @free: The amount of free memory in the pool - */ -struct vio_cmo_pool { - size_t size; - size_t free; -}; - -/* How many ms to delay queued balance work */ -#define VIO_CMO_BALANCE_DELAY 100 - -/* Portion out IO memory to CMO devices by this chunk size */ -#define VIO_CMO_BALANCE_CHUNK 131072 - -/** - * vio_cmo_dev_entry - A device that is CMO-enabled and requires entitlement - * - * @vio_dev: struct vio_dev pointer - * @list: pointer to other devices on bus that are being tracked - */ -struct vio_cmo_dev_entry { - struct vio_dev *viodev; - struct list_head list; -}; - -/** - * vio_cmo - VIO bus accounting structure for CMO entitlement - * - * @lock: spinlock for entire structure - * @balance_q: work queue for balancing system entitlement - * @device_list: list of CMO-enabled devices requiring entitlement - * @entitled: total system entitlement in bytes - * @reserve: pool of memory from which devices reserve entitlement, incl. spare - * @excess: pool of excess entitlement not needed for device reserves or spare - * @spare: IO memory for device hotplug functionality - * @min: minimum necessary for system operation - * @desired: desired memory for system operation - * @curr: bytes currently allocated - * @high: high water mark for IO data usage - */ -static struct vio_cmo { - spinlock_t lock; - struct delayed_work balance_q; - struct list_head device_list; - size_t entitled; - struct vio_cmo_pool reserve; - struct vio_cmo_pool excess; - size_t spare; - size_t min; - size_t desired; - size_t curr; - size_t high; -} vio_cmo; - -/** - * vio_cmo_OF_devices - Count the number of OF devices that have DMA windows - */ -static int vio_cmo_num_OF_devs(void) -{ - struct device_node *node_vroot; - int count = 0; - - /* - * Count the number of vdevice entries with an - * ibm,my-dma-window OF property - */ - node_vroot = of_find_node_by_name(NULL, "vdevice"); - if (node_vroot) { - struct device_node *of_node; - struct property *prop; - - for_each_child_of_node(node_vroot, of_node) { - prop = of_find_property(of_node, "ibm,my-dma-window", - NULL); - if (prop) - count++; - } - } - of_node_put(node_vroot); - return count; -} - -/** - * vio_cmo_alloc - allocate IO memory for CMO-enable devices - * - * @viodev: VIO device requesting IO memory - * @size: size of allocation requested - * - * Allocations come from memory reserved for the devices and any excess - * IO memory available to all devices. The spare pool used to service - * hotplug must be equal to %VIO_CMO_MIN_ENT for the excess pool to be - * made available. - * - * Return codes: - * 0 for successful allocation and -ENOMEM for a failure - */ -static inline int vio_cmo_alloc(struct vio_dev *viodev, size_t size) -{ - unsigned long flags; - size_t reserve_free = 0; - size_t excess_free = 0; - int ret = -ENOMEM; - - spin_lock_irqsave(&vio_cmo.lock, flags); - - /* Determine the amount of free entitlement available in reserve */ - if (viodev->cmo.entitled > viodev->cmo.allocated) - reserve_free = viodev->cmo.entitled - viodev->cmo.allocated; - - /* If spare is not fulfilled, the excess pool can not be used. */ - if (vio_cmo.spare >= VIO_CMO_MIN_ENT) - excess_free = vio_cmo.excess.free; - - /* The request can be satisfied */ - if ((reserve_free + excess_free) >= size) { - vio_cmo.curr += size; - if (vio_cmo.curr > vio_cmo.high) - vio_cmo.high = vio_cmo.curr; - viodev->cmo.allocated += size; - size -= min(reserve_free, size); - vio_cmo.excess.free -= size; - ret = 0; - } - - spin_unlock_irqrestore(&vio_cmo.lock, flags); - return ret; -} - -/** - * vio_cmo_dealloc - deallocate IO memory from CMO-enable devices - * @viodev: VIO device freeing IO memory - * @size: size of deallocation - * - * IO memory is freed by the device back to the correct memory pools. - * The spare pool is replenished first from either memory pool, then - * the reserve pool is used to reduce device entitlement, the excess - * pool is used to increase the reserve pool toward the desired entitlement - * target, and then the remaining memory is returned to the pools. - * - */ -static inline void vio_cmo_dealloc(struct vio_dev *viodev, size_t size) -{ - unsigned long flags; - size_t spare_needed = 0; - size_t excess_freed = 0; - size_t reserve_freed = size; - size_t tmp; - int balance = 0; - - spin_lock_irqsave(&vio_cmo.lock, flags); - vio_cmo.curr -= size; - - /* Amount of memory freed from the excess pool */ - if (viodev->cmo.allocated > viodev->cmo.entitled) { - excess_freed = min(reserve_freed, (viodev->cmo.allocated - - viodev->cmo.entitled)); - reserve_freed -= excess_freed; - } - - /* Remove allocation from device */ - viodev->cmo.allocated -= (reserve_freed + excess_freed); - - /* Spare is a subset of the reserve pool, replenish it first. */ - spare_needed = VIO_CMO_MIN_ENT - vio_cmo.spare; - - /* - * Replenish the spare in the reserve pool from the excess pool. - * This moves entitlement into the reserve pool. - */ - if (spare_needed && excess_freed) { - tmp = min(excess_freed, spare_needed); - vio_cmo.excess.size -= tmp; - vio_cmo.reserve.size += tmp; - vio_cmo.spare += tmp; - excess_freed -= tmp; - spare_needed -= tmp; - balance = 1; - } - - /* - * Replenish the spare in the reserve pool from the reserve pool. - * This removes entitlement from the device down to VIO_CMO_MIN_ENT, - * if needed, and gives it to the spare pool. The amount of used - * memory in this pool does not change. - */ - if (spare_needed && reserve_freed) { - tmp = min3(spare_needed, reserve_freed, (viodev->cmo.entitled - VIO_CMO_MIN_ENT)); - - vio_cmo.spare += tmp; - viodev->cmo.entitled -= tmp; - reserve_freed -= tmp; - spare_needed -= tmp; - balance = 1; - } - - /* - * Increase the reserve pool until the desired allocation is met. - * Move an allocation freed from the excess pool into the reserve - * pool and schedule a balance operation. - */ - if (excess_freed && (vio_cmo.desired > vio_cmo.reserve.size)) { - tmp = min(excess_freed, (vio_cmo.desired - vio_cmo.reserve.size)); - - vio_cmo.excess.size -= tmp; - vio_cmo.reserve.size += tmp; - excess_freed -= tmp; - balance = 1; - } - - /* Return memory from the excess pool to that pool */ - if (excess_freed) - vio_cmo.excess.free += excess_freed; - - if (balance) - schedule_delayed_work(&vio_cmo.balance_q, VIO_CMO_BALANCE_DELAY); - spin_unlock_irqrestore(&vio_cmo.lock, flags); -} - -/** - * vio_cmo_entitlement_update - Manage system entitlement changes - * - * @new_entitlement: new system entitlement to attempt to accommodate - * - * Increases in entitlement will be used to fulfill the spare entitlement - * and the rest is given to the excess pool. Decreases, if they are - * possible, come from the excess pool and from unused device entitlement - * - * Returns: 0 on success, -ENOMEM when change can not be made - */ -int vio_cmo_entitlement_update(size_t new_entitlement) -{ - struct vio_dev *viodev; - struct vio_cmo_dev_entry *dev_ent; - unsigned long flags; - size_t avail, delta, tmp; - - spin_lock_irqsave(&vio_cmo.lock, flags); - - /* Entitlement increases */ - if (new_entitlement > vio_cmo.entitled) { - delta = new_entitlement - vio_cmo.entitled; - - /* Fulfill spare allocation */ - if (vio_cmo.spare < VIO_CMO_MIN_ENT) { - tmp = min(delta, (VIO_CMO_MIN_ENT - vio_cmo.spare)); - vio_cmo.spare += tmp; - vio_cmo.reserve.size += tmp; - delta -= tmp; - } - - /* Remaining new allocation goes to the excess pool */ - vio_cmo.entitled += delta; - vio_cmo.excess.size += delta; - vio_cmo.excess.free += delta; - - goto out; - } - - /* Entitlement decreases */ - delta = vio_cmo.entitled - new_entitlement; - avail = vio_cmo.excess.free; - - /* - * Need to check how much unused entitlement each device can - * sacrifice to fulfill entitlement change. - */ - list_for_each_entry(dev_ent, &vio_cmo.device_list, list) { - if (avail >= delta) - break; - - viodev = dev_ent->viodev; - if ((viodev->cmo.entitled > viodev->cmo.allocated) && - (viodev->cmo.entitled > VIO_CMO_MIN_ENT)) - avail += viodev->cmo.entitled - - max_t(size_t, viodev->cmo.allocated, - VIO_CMO_MIN_ENT); - } - - if (delta <= avail) { - vio_cmo.entitled -= delta; - - /* Take entitlement from the excess pool first */ - tmp = min(vio_cmo.excess.free, delta); - vio_cmo.excess.size -= tmp; - vio_cmo.excess.free -= tmp; - delta -= tmp; - - /* - * Remove all but VIO_CMO_MIN_ENT bytes from devices - * until entitlement change is served - */ - list_for_each_entry(dev_ent, &vio_cmo.device_list, list) { - if (!delta) - break; - - viodev = dev_ent->viodev; - tmp = 0; - if ((viodev->cmo.entitled > viodev->cmo.allocated) && - (viodev->cmo.entitled > VIO_CMO_MIN_ENT)) - tmp = viodev->cmo.entitled - - max_t(size_t, viodev->cmo.allocated, - VIO_CMO_MIN_ENT); - viodev->cmo.entitled -= min(tmp, delta); - delta -= min(tmp, delta); - } - } else { - spin_unlock_irqrestore(&vio_cmo.lock, flags); - return -ENOMEM; - } - -out: - schedule_delayed_work(&vio_cmo.balance_q, 0); - spin_unlock_irqrestore(&vio_cmo.lock, flags); - return 0; -} - -/** - * vio_cmo_balance - Balance entitlement among devices - * - * @work: work queue structure for this operation - * - * Any system entitlement above the minimum needed for devices, or - * already allocated to devices, can be distributed to the devices. - * The list of devices is iterated through to recalculate the desired - * entitlement level and to determine how much entitlement above the - * minimum entitlement is allocated to devices. - * - * Small chunks of the available entitlement are given to devices until - * their requirements are fulfilled or there is no entitlement left to give. - * Upon completion sizes of the reserve and excess pools are calculated. - * - * The system minimum entitlement level is also recalculated here. - * Entitlement will be reserved for devices even after vio_bus_remove to - * accommodate reloading the driver. The OF tree is walked to count the - * number of devices present and this will remove entitlement for devices - * that have actually left the system after having vio_bus_remove called. - */ -static void vio_cmo_balance(struct work_struct *work) -{ - struct vio_cmo *cmo; - struct vio_dev *viodev; - struct vio_cmo_dev_entry *dev_ent; - unsigned long flags; - size_t avail = 0, level, chunk, need; - int devcount = 0, fulfilled; - - cmo = container_of(work, struct vio_cmo, balance_q.work); - - spin_lock_irqsave(&vio_cmo.lock, flags); - - /* Calculate minimum entitlement and fulfill spare */ - cmo->min = vio_cmo_num_OF_devs() * VIO_CMO_MIN_ENT; - BUG_ON(cmo->min > cmo->entitled); - cmo->spare = min_t(size_t, VIO_CMO_MIN_ENT, (cmo->entitled - cmo->min)); - cmo->min += cmo->spare; - cmo->desired = cmo->min; - - /* - * Determine how much entitlement is available and reset device - * entitlements - */ - avail = cmo->entitled - cmo->spare; - list_for_each_entry(dev_ent, &vio_cmo.device_list, list) { - viodev = dev_ent->viodev; - devcount++; - viodev->cmo.entitled = VIO_CMO_MIN_ENT; - cmo->desired += (viodev->cmo.desired - VIO_CMO_MIN_ENT); - avail -= max_t(size_t, viodev->cmo.allocated, VIO_CMO_MIN_ENT); - } - - /* - * Having provided each device with the minimum entitlement, loop - * over the devices portioning out the remaining entitlement - * until there is nothing left. - */ - level = VIO_CMO_MIN_ENT; - while (avail) { - fulfilled = 0; - list_for_each_entry(dev_ent, &vio_cmo.device_list, list) { - viodev = dev_ent->viodev; - - if (viodev->cmo.desired <= level) { - fulfilled++; - continue; - } - - /* - * Give the device up to VIO_CMO_BALANCE_CHUNK - * bytes of entitlement, but do not exceed the - * desired level of entitlement for the device. - */ - chunk = min_t(size_t, avail, VIO_CMO_BALANCE_CHUNK); - chunk = min(chunk, (viodev->cmo.desired - - viodev->cmo.entitled)); - viodev->cmo.entitled += chunk; - - /* - * If the memory for this entitlement increase was - * already allocated to the device it does not come - * from the available pool being portioned out. - */ - need = max(viodev->cmo.allocated, viodev->cmo.entitled)- - max(viodev->cmo.allocated, level); - avail -= need; - - } - if (fulfilled == devcount) - break; - level += VIO_CMO_BALANCE_CHUNK; - } - - /* Calculate new reserve and excess pool sizes */ - cmo->reserve.size = cmo->min; - cmo->excess.free = 0; - cmo->excess.size = 0; - need = 0; - list_for_each_entry(dev_ent, &vio_cmo.device_list, list) { - viodev = dev_ent->viodev; - /* Calculated reserve size above the minimum entitlement */ - if (viodev->cmo.entitled) - cmo->reserve.size += (viodev->cmo.entitled - - VIO_CMO_MIN_ENT); - /* Calculated used excess entitlement */ - if (viodev->cmo.allocated > viodev->cmo.entitled) - need += viodev->cmo.allocated - viodev->cmo.entitled; - } - cmo->excess.size = cmo->entitled - cmo->reserve.size; - cmo->excess.free = cmo->excess.size - need; - - cancel_delayed_work(to_delayed_work(work)); - spin_unlock_irqrestore(&vio_cmo.lock, flags); -} - -static void *vio_dma_iommu_alloc_coherent(struct device *dev, size_t size, - dma_addr_t *dma_handle, gfp_t flag, - unsigned long attrs) -{ - struct vio_dev *viodev = to_vio_dev(dev); - void *ret; - - if (vio_cmo_alloc(viodev, roundup(size, PAGE_SIZE))) { - atomic_inc(&viodev->cmo.allocs_failed); - return NULL; - } - - ret = dma_iommu_ops.alloc(dev, size, dma_handle, flag, attrs); - if (unlikely(ret == NULL)) { - vio_cmo_dealloc(viodev, roundup(size, PAGE_SIZE)); - atomic_inc(&viodev->cmo.allocs_failed); - } - - return ret; -} - -static void vio_dma_iommu_free_coherent(struct device *dev, size_t size, - void *vaddr, dma_addr_t dma_handle, - unsigned long attrs) -{ - struct vio_dev *viodev = to_vio_dev(dev); - - dma_iommu_ops.free(dev, size, vaddr, dma_handle, attrs); - - vio_cmo_dealloc(viodev, roundup(size, PAGE_SIZE)); -} - -static dma_addr_t vio_dma_iommu_map_page(struct device *dev, struct page *page, - unsigned long offset, size_t size, - enum dma_data_direction direction, - unsigned long attrs) -{ - struct vio_dev *viodev = to_vio_dev(dev); - struct iommu_table *tbl; - dma_addr_t ret = DMA_ERROR_CODE; - - tbl = get_iommu_table_base(dev); - if (vio_cmo_alloc(viodev, roundup(size, IOMMU_PAGE_SIZE(tbl)))) { - atomic_inc(&viodev->cmo.allocs_failed); - return ret; - } - - ret = dma_iommu_ops.map_page(dev, page, offset, size, direction, attrs); - if (unlikely(dma_mapping_error(dev, ret))) { - vio_cmo_dealloc(viodev, roundup(size, IOMMU_PAGE_SIZE(tbl))); - atomic_inc(&viodev->cmo.allocs_failed); - } - - return ret; -} - -static void vio_dma_iommu_unmap_page(struct device *dev, dma_addr_t dma_handle, - size_t size, - enum dma_data_direction direction, - unsigned long attrs) -{ - struct vio_dev *viodev = to_vio_dev(dev); - struct iommu_table *tbl; - - tbl = get_iommu_table_base(dev); - dma_iommu_ops.unmap_page(dev, dma_handle, size, direction, attrs); - - vio_cmo_dealloc(viodev, roundup(size, IOMMU_PAGE_SIZE(tbl))); -} - -static int vio_dma_iommu_map_sg(struct device *dev, struct scatterlist *sglist, - int nelems, enum dma_data_direction direction, - unsigned long attrs) -{ - struct vio_dev *viodev = to_vio_dev(dev); - struct iommu_table *tbl; - struct scatterlist *sgl; - int ret, count; - size_t alloc_size = 0; - - tbl = get_iommu_table_base(dev); - for_each_sg(sglist, sgl, nelems, count) - alloc_size += roundup(sgl->length, IOMMU_PAGE_SIZE(tbl)); - - if (vio_cmo_alloc(viodev, alloc_size)) { - atomic_inc(&viodev->cmo.allocs_failed); - return 0; - } - - ret = dma_iommu_ops.map_sg(dev, sglist, nelems, direction, attrs); - - if (unlikely(!ret)) { - vio_cmo_dealloc(viodev, alloc_size); - atomic_inc(&viodev->cmo.allocs_failed); - return ret; - } - - for_each_sg(sglist, sgl, ret, count) - alloc_size -= roundup(sgl->dma_length, IOMMU_PAGE_SIZE(tbl)); - if (alloc_size) - vio_cmo_dealloc(viodev, alloc_size); - - return ret; -} - -static void vio_dma_iommu_unmap_sg(struct device *dev, - struct scatterlist *sglist, int nelems, - enum dma_data_direction direction, - unsigned long attrs) -{ - struct vio_dev *viodev = to_vio_dev(dev); - struct iommu_table *tbl; - struct scatterlist *sgl; - size_t alloc_size = 0; - int count; - - tbl = get_iommu_table_base(dev); - for_each_sg(sglist, sgl, nelems, count) - alloc_size += roundup(sgl->dma_length, IOMMU_PAGE_SIZE(tbl)); - - dma_iommu_ops.unmap_sg(dev, sglist, nelems, direction, attrs); - - vio_cmo_dealloc(viodev, alloc_size); -} - -static int vio_dma_iommu_dma_supported(struct device *dev, u64 mask) -{ - return dma_iommu_ops.dma_supported(dev, mask); -} - -static u64 vio_dma_get_required_mask(struct device *dev) -{ - return dma_iommu_ops.get_required_mask(dev); -} - -static struct dma_map_ops vio_dma_mapping_ops = { - .alloc = vio_dma_iommu_alloc_coherent, - .free = vio_dma_iommu_free_coherent, - .mmap = dma_direct_mmap_coherent, - .map_sg = vio_dma_iommu_map_sg, - .unmap_sg = vio_dma_iommu_unmap_sg, - .map_page = vio_dma_iommu_map_page, - .unmap_page = vio_dma_iommu_unmap_page, - .dma_supported = vio_dma_iommu_dma_supported, - .get_required_mask = vio_dma_get_required_mask, -}; - -/** - * vio_cmo_set_dev_desired - Set desired entitlement for a device - * - * @viodev: struct vio_dev for device to alter - * @desired: new desired entitlement level in bytes - * - * For use by devices to request a change to their entitlement at runtime or - * through sysfs. The desired entitlement level is changed and a balancing - * of system resources is scheduled to run in the future. - */ -void vio_cmo_set_dev_desired(struct vio_dev *viodev, size_t desired) -{ - unsigned long flags; - struct vio_cmo_dev_entry *dev_ent; - int found = 0; - - if (!firmware_has_feature(FW_FEATURE_CMO)) - return; - - spin_lock_irqsave(&vio_cmo.lock, flags); - if (desired < VIO_CMO_MIN_ENT) - desired = VIO_CMO_MIN_ENT; - - /* - * Changes will not be made for devices not in the device list. - * If it is not in the device list, then no driver is loaded - * for the device and it can not receive entitlement. - */ - list_for_each_entry(dev_ent, &vio_cmo.device_list, list) - if (viodev == dev_ent->viodev) { - found = 1; - break; - } - if (!found) { - spin_unlock_irqrestore(&vio_cmo.lock, flags); - return; - } - - /* Increase/decrease in desired device entitlement */ - if (desired >= viodev->cmo.desired) { - /* Just bump the bus and device values prior to a balance*/ - vio_cmo.desired += desired - viodev->cmo.desired; - viodev->cmo.desired = desired; - } else { - /* Decrease bus and device values for desired entitlement */ - vio_cmo.desired -= viodev->cmo.desired - desired; - viodev->cmo.desired = desired; - /* - * If less entitlement is desired than current entitlement, move - * any reserve memory in the change region to the excess pool. - */ - if (viodev->cmo.entitled > desired) { - vio_cmo.reserve.size -= viodev->cmo.entitled - desired; - vio_cmo.excess.size += viodev->cmo.entitled - desired; - /* - * If entitlement moving from the reserve pool to the - * excess pool is currently unused, add to the excess - * free counter. - */ - if (viodev->cmo.allocated < viodev->cmo.entitled) - vio_cmo.excess.free += viodev->cmo.entitled - - max(viodev->cmo.allocated, desired); - viodev->cmo.entitled = desired; - } - } - schedule_delayed_work(&vio_cmo.balance_q, 0); - spin_unlock_irqrestore(&vio_cmo.lock, flags); -} - -/** - * vio_cmo_bus_probe - Handle CMO specific bus probe activities - * - * @viodev - Pointer to struct vio_dev for device - * - * Determine the devices IO memory entitlement needs, attempting - * to satisfy the system minimum entitlement at first and scheduling - * a balance operation to take care of the rest at a later time. - * - * Returns: 0 on success, -EINVAL when device doesn't support CMO, and - * -ENOMEM when entitlement is not available for device or - * device entry. - * - */ -static int vio_cmo_bus_probe(struct vio_dev *viodev) -{ - struct vio_cmo_dev_entry *dev_ent; - struct device *dev = &viodev->dev; - struct iommu_table *tbl; - struct vio_driver *viodrv = to_vio_driver(dev->driver); - unsigned long flags; - size_t size; - bool dma_capable = false; - - tbl = get_iommu_table_base(dev); - - /* A device requires entitlement if it has a DMA window property */ - switch (viodev->family) { - case VDEVICE: - if (of_get_property(viodev->dev.of_node, - "ibm,my-dma-window", NULL)) - dma_capable = true; - break; - case PFO: - dma_capable = false; - break; - default: - dev_warn(dev, "unknown device family: %d\n", viodev->family); - BUG(); - break; - } - - /* Configure entitlement for the device. */ - if (dma_capable) { - /* Check that the driver is CMO enabled and get desired DMA */ - if (!viodrv->get_desired_dma) { - dev_err(dev, "%s: device driver does not support CMO\n", - __func__); - return -EINVAL; - } - - viodev->cmo.desired = - IOMMU_PAGE_ALIGN(viodrv->get_desired_dma(viodev), tbl); - if (viodev->cmo.desired < VIO_CMO_MIN_ENT) - viodev->cmo.desired = VIO_CMO_MIN_ENT; - size = VIO_CMO_MIN_ENT; - - dev_ent = kmalloc(sizeof(struct vio_cmo_dev_entry), - GFP_KERNEL); - if (!dev_ent) - return -ENOMEM; - - dev_ent->viodev = viodev; - spin_lock_irqsave(&vio_cmo.lock, flags); - list_add(&dev_ent->list, &vio_cmo.device_list); - } else { - viodev->cmo.desired = 0; - size = 0; - spin_lock_irqsave(&vio_cmo.lock, flags); - } - - /* - * If the needs for vio_cmo.min have not changed since they - * were last set, the number of devices in the OF tree has - * been constant and the IO memory for this is already in - * the reserve pool. - */ - if (vio_cmo.min == ((vio_cmo_num_OF_devs() + 1) * - VIO_CMO_MIN_ENT)) { - /* Updated desired entitlement if device requires it */ - if (size) - vio_cmo.desired += (viodev->cmo.desired - - VIO_CMO_MIN_ENT); - } else { - size_t tmp; - - tmp = vio_cmo.spare + vio_cmo.excess.free; - if (tmp < size) { - dev_err(dev, "%s: insufficient free " - "entitlement to add device. " - "Need %lu, have %lu\n", __func__, - size, (vio_cmo.spare + tmp)); - spin_unlock_irqrestore(&vio_cmo.lock, flags); - return -ENOMEM; - } - - /* Use excess pool first to fulfill request */ - tmp = min(size, vio_cmo.excess.free); - vio_cmo.excess.free -= tmp; - vio_cmo.excess.size -= tmp; - vio_cmo.reserve.size += tmp; - - /* Use spare if excess pool was insufficient */ - vio_cmo.spare -= size - tmp; - - /* Update bus accounting */ - vio_cmo.min += size; - vio_cmo.desired += viodev->cmo.desired; - } - spin_unlock_irqrestore(&vio_cmo.lock, flags); - return 0; -} - -/** - * vio_cmo_bus_remove - Handle CMO specific bus removal activities - * - * @viodev - Pointer to struct vio_dev for device - * - * Remove the device from the cmo device list. The minimum entitlement - * will be reserved for the device as long as it is in the system. The - * rest of the entitlement the device had been allocated will be returned - * to the system. - */ -static void vio_cmo_bus_remove(struct vio_dev *viodev) -{ - struct vio_cmo_dev_entry *dev_ent; - unsigned long flags; - size_t tmp; - - spin_lock_irqsave(&vio_cmo.lock, flags); - if (viodev->cmo.allocated) { - dev_err(&viodev->dev, "%s: device had %lu bytes of IO " - "allocated after remove operation.\n", - __func__, viodev->cmo.allocated); - BUG(); - } - - /* - * Remove the device from the device list being maintained for - * CMO enabled devices. - */ - list_for_each_entry(dev_ent, &vio_cmo.device_list, list) - if (viodev == dev_ent->viodev) { - list_del(&dev_ent->list); - kfree(dev_ent); - break; - } - - /* - * Devices may not require any entitlement and they do not need - * to be processed. Otherwise, return the device's entitlement - * back to the pools. - */ - if (viodev->cmo.entitled) { - /* - * This device has not yet left the OF tree, it's - * minimum entitlement remains in vio_cmo.min and - * vio_cmo.desired - */ - vio_cmo.desired -= (viodev->cmo.desired - VIO_CMO_MIN_ENT); - - /* - * Save min allocation for device in reserve as long - * as it exists in OF tree as determined by later - * balance operation - */ - viodev->cmo.entitled -= VIO_CMO_MIN_ENT; - - /* Replenish spare from freed reserve pool */ - if (viodev->cmo.entitled && (vio_cmo.spare < VIO_CMO_MIN_ENT)) { - tmp = min(viodev->cmo.entitled, (VIO_CMO_MIN_ENT - - vio_cmo.spare)); - vio_cmo.spare += tmp; - viodev->cmo.entitled -= tmp; - } - - /* Remaining reserve goes to excess pool */ - vio_cmo.excess.size += viodev->cmo.entitled; - vio_cmo.excess.free += viodev->cmo.entitled; - vio_cmo.reserve.size -= viodev->cmo.entitled; - - /* - * Until the device is removed it will keep a - * minimum entitlement; this will guarantee that - * a module unload/load will result in a success. - */ - viodev->cmo.entitled = VIO_CMO_MIN_ENT; - viodev->cmo.desired = VIO_CMO_MIN_ENT; - atomic_set(&viodev->cmo.allocs_failed, 0); - } - - spin_unlock_irqrestore(&vio_cmo.lock, flags); -} - -static void vio_cmo_set_dma_ops(struct vio_dev *viodev) -{ - set_dma_ops(&viodev->dev, &vio_dma_mapping_ops); -} - -/** - * vio_cmo_bus_init - CMO entitlement initialization at bus init time - * - * Set up the reserve and excess entitlement pools based on available - * system entitlement and the number of devices in the OF tree that - * require entitlement in the reserve pool. - */ -static void vio_cmo_bus_init(void) -{ - struct hvcall_mpp_data mpp_data; - int err; - - memset(&vio_cmo, 0, sizeof(struct vio_cmo)); - spin_lock_init(&vio_cmo.lock); - INIT_LIST_HEAD(&vio_cmo.device_list); - INIT_DELAYED_WORK(&vio_cmo.balance_q, vio_cmo_balance); - - /* Get current system entitlement */ - err = h_get_mpp(&mpp_data); - - /* - * On failure, continue with entitlement set to 0, will panic() - * later when spare is reserved. - */ - if (err != H_SUCCESS) { - printk(KERN_ERR "%s: unable to determine system IO "\ - "entitlement. (%d)\n", __func__, err); - vio_cmo.entitled = 0; - } else { - vio_cmo.entitled = mpp_data.entitled_mem; - } - - /* Set reservation and check against entitlement */ - vio_cmo.spare = VIO_CMO_MIN_ENT; - vio_cmo.reserve.size = vio_cmo.spare; - vio_cmo.reserve.size += (vio_cmo_num_OF_devs() * - VIO_CMO_MIN_ENT); - if (vio_cmo.reserve.size > vio_cmo.entitled) { - printk(KERN_ERR "%s: insufficient system entitlement\n", - __func__); - panic("%s: Insufficient system entitlement", __func__); - } - - /* Set the remaining accounting variables */ - vio_cmo.excess.size = vio_cmo.entitled - vio_cmo.reserve.size; - vio_cmo.excess.free = vio_cmo.excess.size; - vio_cmo.min = vio_cmo.reserve.size; - vio_cmo.desired = vio_cmo.reserve.size; -} - -/* sysfs device functions and data structures for CMO */ - -#define viodev_cmo_rd_attr(name) \ -static ssize_t viodev_cmo_##name##_show(struct device *dev, \ - struct device_attribute *attr, \ - char *buf) \ -{ \ - return sprintf(buf, "%lu\n", to_vio_dev(dev)->cmo.name); \ -} - -static ssize_t viodev_cmo_allocs_failed_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - struct vio_dev *viodev = to_vio_dev(dev); - return sprintf(buf, "%d\n", atomic_read(&viodev->cmo.allocs_failed)); -} - -static ssize_t viodev_cmo_allocs_failed_reset(struct device *dev, - struct device_attribute *attr, const char *buf, size_t count) -{ - struct vio_dev *viodev = to_vio_dev(dev); - atomic_set(&viodev->cmo.allocs_failed, 0); - return count; -} - -static ssize_t viodev_cmo_desired_set(struct device *dev, - struct device_attribute *attr, const char *buf, size_t count) -{ - struct vio_dev *viodev = to_vio_dev(dev); - size_t new_desired; - int ret; - - ret = kstrtoul(buf, 10, &new_desired); - if (ret) - return ret; - - vio_cmo_set_dev_desired(viodev, new_desired); - return count; -} - -viodev_cmo_rd_attr(desired); -viodev_cmo_rd_attr(entitled); -viodev_cmo_rd_attr(allocated); - -static ssize_t name_show(struct device *, struct device_attribute *, char *); -static ssize_t devspec_show(struct device *, struct device_attribute *, char *); -static ssize_t modalias_show(struct device *dev, struct device_attribute *attr, - char *buf); -static struct device_attribute vio_cmo_dev_attrs[] = { - __ATTR_RO(name), - __ATTR_RO(devspec), - __ATTR_RO(modalias), - __ATTR(cmo_desired, S_IWUSR|S_IRUSR|S_IWGRP|S_IRGRP|S_IROTH, - viodev_cmo_desired_show, viodev_cmo_desired_set), - __ATTR(cmo_entitled, S_IRUGO, viodev_cmo_entitled_show, NULL), - __ATTR(cmo_allocated, S_IRUGO, viodev_cmo_allocated_show, NULL), - __ATTR(cmo_allocs_failed, S_IWUSR|S_IRUSR|S_IWGRP|S_IRGRP|S_IROTH, - viodev_cmo_allocs_failed_show, viodev_cmo_allocs_failed_reset), - __ATTR_NULL -}; - -/* sysfs bus functions and data structures for CMO */ - -#define viobus_cmo_rd_attr(name) \ -static ssize_t cmo_##name##_show(struct bus_type *bt, char *buf) \ -{ \ - return sprintf(buf, "%lu\n", vio_cmo.name); \ -} \ -static BUS_ATTR_RO(cmo_##name) - -#define viobus_cmo_pool_rd_attr(name, var) \ -static ssize_t \ -cmo_##name##_##var##_show(struct bus_type *bt, char *buf) \ -{ \ - return sprintf(buf, "%lu\n", vio_cmo.name.var); \ -} \ -static BUS_ATTR_RO(cmo_##name##_##var) - -viobus_cmo_rd_attr(entitled); -viobus_cmo_rd_attr(spare); -viobus_cmo_rd_attr(min); -viobus_cmo_rd_attr(desired); -viobus_cmo_rd_attr(curr); -viobus_cmo_pool_rd_attr(reserve, size); -viobus_cmo_pool_rd_attr(excess, size); -viobus_cmo_pool_rd_attr(excess, free); - -static ssize_t cmo_high_show(struct bus_type *bt, char *buf) -{ - return sprintf(buf, "%lu\n", vio_cmo.high); -} - -static ssize_t cmo_high_store(struct bus_type *bt, const char *buf, - size_t count) -{ - unsigned long flags; - - spin_lock_irqsave(&vio_cmo.lock, flags); - vio_cmo.high = vio_cmo.curr; - spin_unlock_irqrestore(&vio_cmo.lock, flags); - - return count; -} -static BUS_ATTR_RW(cmo_high); - -static struct attribute *vio_bus_attrs[] = { - &bus_attr_cmo_entitled.attr, - &bus_attr_cmo_spare.attr, - &bus_attr_cmo_min.attr, - &bus_attr_cmo_desired.attr, - &bus_attr_cmo_curr.attr, - &bus_attr_cmo_high.attr, - &bus_attr_cmo_reserve_size.attr, - &bus_attr_cmo_excess_size.attr, - &bus_attr_cmo_excess_free.attr, - NULL, -}; -ATTRIBUTE_GROUPS(vio_bus); - -static void vio_cmo_sysfs_init(void) -{ - vio_bus_type.dev_attrs = vio_cmo_dev_attrs; - vio_bus_type.bus_groups = vio_bus_groups; -} -#else /* CONFIG_PPC_SMLPAR */ -int vio_cmo_entitlement_update(size_t new_entitlement) { return 0; } -void vio_cmo_set_dev_desired(struct vio_dev *viodev, size_t desired) {} -static int vio_cmo_bus_probe(struct vio_dev *viodev) { return 0; } -static void vio_cmo_bus_remove(struct vio_dev *viodev) {} -static void vio_cmo_set_dma_ops(struct vio_dev *viodev) {} -static void vio_cmo_bus_init(void) {} -static void vio_cmo_sysfs_init(void) { } -#endif /* CONFIG_PPC_SMLPAR */ -EXPORT_SYMBOL(vio_cmo_entitlement_update); -EXPORT_SYMBOL(vio_cmo_set_dev_desired); - - -/* - * Platform Facilities Option (PFO) support - */ - -/** - * vio_h_cop_sync - Perform a synchronous PFO co-processor operation - * - * @vdev - Pointer to a struct vio_dev for device - * @op - Pointer to a struct vio_pfo_op for the operation parameters - * - * Calls the hypervisor to synchronously perform the PFO operation - * described in @op. In the case of a busy response from the hypervisor, - * the operation will be re-submitted indefinitely unless a non-zero timeout - * is specified or an error occurs. The timeout places a limit on when to - * stop re-submitting a operation, the total time can be exceeded if an - * operation is in progress. - * - * If op->hcall_ret is not NULL, this will be set to the return from the - * last h_cop_op call or it will be 0 if an error not involving the h_call - * was encountered. - * - * Returns: - * 0 on success, - * -EINVAL if the h_call fails due to an invalid parameter, - * -E2BIG if the h_call can not be performed synchronously, - * -EBUSY if a timeout is specified and has elapsed, - * -EACCES if the memory area for data/status has been rescinded, or - * -EPERM if a hardware fault has been indicated - */ -int vio_h_cop_sync(struct vio_dev *vdev, struct vio_pfo_op *op) -{ - struct device *dev = &vdev->dev; - unsigned long deadline = 0; - long hret = 0; - int ret = 0; - - if (op->timeout) - deadline = jiffies + msecs_to_jiffies(op->timeout); - - while (true) { - hret = plpar_hcall_norets(H_COP, op->flags, - vdev->resource_id, - op->in, op->inlen, op->out, - op->outlen, op->csbcpb); - - if (hret == H_SUCCESS || - (hret != H_NOT_ENOUGH_RESOURCES && - hret != H_BUSY && hret != H_RESOURCE) || - (op->timeout && time_after(deadline, jiffies))) - break; - - dev_dbg(dev, "%s: hcall ret(%ld), retrying.\n", __func__, hret); - } - - switch (hret) { - case H_SUCCESS: - ret = 0; - break; - case H_OP_MODE: - case H_TOO_BIG: - ret = -E2BIG; - break; - case H_RESCINDED: - ret = -EACCES; - break; - case H_HARDWARE: - ret = -EPERM; - break; - case H_NOT_ENOUGH_RESOURCES: - case H_RESOURCE: - case H_BUSY: - ret = -EBUSY; - break; - default: - ret = -EINVAL; - break; - } - - if (ret) - dev_dbg(dev, "%s: Sync h_cop_op failure (ret:%d) (hret:%ld)\n", - __func__, ret, hret); - - op->hcall_err = hret; - return ret; -} -EXPORT_SYMBOL(vio_h_cop_sync); - -static struct iommu_table *vio_build_iommu_table(struct vio_dev *dev) -{ - const __be32 *dma_window; - struct iommu_table *tbl; - unsigned long offset, size; - - dma_window = of_get_property(dev->dev.of_node, - "ibm,my-dma-window", NULL); - if (!dma_window) - return NULL; - - tbl = kzalloc(sizeof(*tbl), GFP_KERNEL); - if (tbl == NULL) - return NULL; - - of_parse_dma_window(dev->dev.of_node, dma_window, - &tbl->it_index, &offset, &size); - - /* TCE table size - measured in tce entries */ - tbl->it_page_shift = IOMMU_PAGE_SHIFT_4K; - tbl->it_size = size >> tbl->it_page_shift; - /* offset for VIO should always be 0 */ - tbl->it_offset = offset >> tbl->it_page_shift; - tbl->it_busno = 0; - tbl->it_type = TCE_VB; - tbl->it_blocksize = 16; - - if (firmware_has_feature(FW_FEATURE_LPAR)) - tbl->it_ops = &iommu_table_lpar_multi_ops; - else - tbl->it_ops = &iommu_table_pseries_ops; - - return iommu_init_table(tbl, -1); -} - -/** - * vio_match_device: - Tell if a VIO device has a matching - * VIO device id structure. - * @ids: array of VIO device id structures to search in - * @dev: the VIO device structure to match against - * - * Used by a driver to check whether a VIO device present in the - * system is in its list of supported devices. Returns the matching - * vio_device_id structure or NULL if there is no match. - */ -static const struct vio_device_id *vio_match_device( - const struct vio_device_id *ids, const struct vio_dev *dev) -{ - while (ids->type[0] != '\0') { - if ((strncmp(dev->type, ids->type, strlen(ids->type)) == 0) && - of_device_is_compatible(dev->dev.of_node, - ids->compat)) - return ids; - ids++; - } - return NULL; -} - -/* - * Convert from struct device to struct vio_dev and pass to driver. - * dev->driver has already been set by generic code because vio_bus_match - * succeeded. - */ -static int vio_bus_probe(struct device *dev) -{ - struct vio_dev *viodev = to_vio_dev(dev); - struct vio_driver *viodrv = to_vio_driver(dev->driver); - const struct vio_device_id *id; - int error = -ENODEV; - - if (!viodrv->probe) - return error; - - id = vio_match_device(viodrv->id_table, viodev); - if (id) { - memset(&viodev->cmo, 0, sizeof(viodev->cmo)); - if (firmware_has_feature(FW_FEATURE_CMO)) { - error = vio_cmo_bus_probe(viodev); - if (error) - return error; - } - error = viodrv->probe(viodev, id); - if (error && firmware_has_feature(FW_FEATURE_CMO)) - vio_cmo_bus_remove(viodev); - } - - return error; -} - -/* convert from struct device to struct vio_dev and pass to driver. */ -static int vio_bus_remove(struct device *dev) -{ - struct vio_dev *viodev = to_vio_dev(dev); - struct vio_driver *viodrv = to_vio_driver(dev->driver); - struct device *devptr; - int ret = 1; - - /* - * Hold a reference to the device after the remove function is called - * to allow for CMO accounting cleanup for the device. - */ - devptr = get_device(dev); - - if (viodrv->remove) - ret = viodrv->remove(viodev); - - if (!ret && firmware_has_feature(FW_FEATURE_CMO)) - vio_cmo_bus_remove(viodev); - - put_device(devptr); - return ret; -} - -/** - * vio_register_driver: - Register a new vio driver - * @viodrv: The vio_driver structure to be registered. - */ -int __vio_register_driver(struct vio_driver *viodrv, struct module *owner, - const char *mod_name) -{ - pr_debug("%s: driver %s registering\n", __func__, viodrv->name); - - /* fill in 'struct driver' fields */ - viodrv->driver.name = viodrv->name; - viodrv->driver.pm = viodrv->pm; - viodrv->driver.bus = &vio_bus_type; - viodrv->driver.owner = owner; - viodrv->driver.mod_name = mod_name; - - return driver_register(&viodrv->driver); -} -EXPORT_SYMBOL(__vio_register_driver); - -/** - * vio_unregister_driver - Remove registration of vio driver. - * @viodrv: The vio_driver struct to be removed form registration - */ -void vio_unregister_driver(struct vio_driver *viodrv) -{ - driver_unregister(&viodrv->driver); -} -EXPORT_SYMBOL(vio_unregister_driver); - -/* vio_dev refcount hit 0 */ -static void vio_dev_release(struct device *dev) -{ - struct iommu_table *tbl = get_iommu_table_base(dev); - - if (tbl) - iommu_free_table(tbl, of_node_full_name(dev->of_node)); - of_node_put(dev->of_node); - kfree(to_vio_dev(dev)); -} - -/** - * vio_register_device_node: - Register a new vio device. - * @of_node: The OF node for this device. - * - * Creates and initializes a vio_dev structure from the data in - * of_node and adds it to the list of virtual devices. - * Returns a pointer to the created vio_dev or NULL if node has - * NULL device_type or compatible fields. - */ -struct vio_dev *vio_register_device_node(struct device_node *of_node) -{ - struct vio_dev *viodev; - struct device_node *parent_node; - const __be32 *prop; - enum vio_dev_family family; - const char *of_node_name = of_node->name ? of_node->name : "<unknown>"; - - /* - * Determine if this node is a under the /vdevice node or under the - * /ibm,platform-facilities node. This decides the device's family. - */ - parent_node = of_get_parent(of_node); - if (parent_node) { - if (!strcmp(parent_node->full_name, "/ibm,platform-facilities")) - family = PFO; - else if (!strcmp(parent_node->full_name, "/vdevice")) - family = VDEVICE; - else { - pr_warn("%s: parent(%s) of %s not recognized.\n", - __func__, - parent_node->full_name, - of_node_name); - of_node_put(parent_node); - return NULL; - } - of_node_put(parent_node); - } else { - pr_warn("%s: could not determine the parent of node %s.\n", - __func__, of_node_name); - return NULL; - } - - if (family == PFO) { - if (of_get_property(of_node, "interrupt-controller", NULL)) { - pr_debug("%s: Skipping the interrupt controller %s.\n", - __func__, of_node_name); - return NULL; - } - } - - /* allocate a vio_dev for this node */ - viodev = kzalloc(sizeof(struct vio_dev), GFP_KERNEL); - if (viodev == NULL) { - pr_warn("%s: allocation failure for VIO device.\n", __func__); - return NULL; - } - - /* we need the 'device_type' property, in order to match with drivers */ - viodev->family = family; - if (viodev->family == VDEVICE) { - unsigned int unit_address; - - if (of_node->type != NULL) - viodev->type = of_node->type; - else { - pr_warn("%s: node %s is missing the 'device_type' " - "property.\n", __func__, of_node_name); - goto out; - } - - prop = of_get_property(of_node, "reg", NULL); - if (prop == NULL) { - pr_warn("%s: node %s missing 'reg'\n", - __func__, of_node_name); - goto out; - } - unit_address = of_read_number(prop, 1); - dev_set_name(&viodev->dev, "%x", unit_address); - viodev->irq = irq_of_parse_and_map(of_node, 0); - viodev->unit_address = unit_address; - } else { - /* PFO devices need their resource_id for submitting COP_OPs - * This is an optional field for devices, but is required when - * performing synchronous ops */ - prop = of_get_property(of_node, "ibm,resource-id", NULL); - if (prop != NULL) - viodev->resource_id = of_read_number(prop, 1); - - dev_set_name(&viodev->dev, "%s", of_node_name); - viodev->type = of_node_name; - viodev->irq = 0; - } - - viodev->name = of_node->name; - viodev->dev.of_node = of_node_get(of_node); - - set_dev_node(&viodev->dev, of_node_to_nid(of_node)); - - /* init generic 'struct device' fields: */ - viodev->dev.parent = &vio_bus_device.dev; - viodev->dev.bus = &vio_bus_type; - viodev->dev.release = vio_dev_release; - - if (of_get_property(viodev->dev.of_node, "ibm,my-dma-window", NULL)) { - if (firmware_has_feature(FW_FEATURE_CMO)) - vio_cmo_set_dma_ops(viodev); - else - set_dma_ops(&viodev->dev, &dma_iommu_ops); - - set_iommu_table_base(&viodev->dev, - vio_build_iommu_table(viodev)); - - /* needed to ensure proper operation of coherent allocations - * later, in case driver doesn't set it explicitly */ - viodev->dev.coherent_dma_mask = DMA_BIT_MASK(64); - viodev->dev.dma_mask = &viodev->dev.coherent_dma_mask; - } - - /* register with generic device framework */ - if (device_register(&viodev->dev)) { - printk(KERN_ERR "%s: failed to register device %s\n", - __func__, dev_name(&viodev->dev)); - put_device(&viodev->dev); - return NULL; - } - - return viodev; - -out: /* Use this exit point for any return prior to device_register */ - kfree(viodev); - - return NULL; -} -EXPORT_SYMBOL(vio_register_device_node); - -/* - * vio_bus_scan_for_devices - Scan OF and register each child device - * @root_name - OF node name for the root of the subtree to search. - * This must be non-NULL - * - * Starting from the root node provide, register the device node for - * each child beneath the root. - */ -static void vio_bus_scan_register_devices(char *root_name) -{ - struct device_node *node_root, *node_child; - - if (!root_name) - return; - - node_root = of_find_node_by_name(NULL, root_name); - if (node_root) { - - /* - * Create struct vio_devices for each virtual device in - * the device tree. Drivers will associate with them later. - */ - node_child = of_get_next_child(node_root, NULL); - while (node_child) { - vio_register_device_node(node_child); - node_child = of_get_next_child(node_root, node_child); - } - of_node_put(node_root); - } -} - -/** - * vio_bus_init: - Initialize the virtual IO bus - */ -static int __init vio_bus_init(void) -{ - int err; - - if (firmware_has_feature(FW_FEATURE_CMO)) - vio_cmo_sysfs_init(); - - err = bus_register(&vio_bus_type); - if (err) { - printk(KERN_ERR "failed to register VIO bus\n"); - return err; - } - - /* - * The fake parent of all vio devices, just to give us - * a nice directory - */ - err = device_register(&vio_bus_device.dev); - if (err) { - printk(KERN_WARNING "%s: device_register returned %i\n", - __func__, err); - return err; - } - - if (firmware_has_feature(FW_FEATURE_CMO)) - vio_cmo_bus_init(); - - return 0; -} -postcore_initcall(vio_bus_init); - -static int __init vio_device_init(void) -{ - vio_bus_scan_register_devices("vdevice"); - vio_bus_scan_register_devices("ibm,platform-facilities"); - - return 0; -} -device_initcall(vio_device_init); - -static ssize_t name_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - return sprintf(buf, "%s\n", to_vio_dev(dev)->name); -} - -static ssize_t devspec_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - struct device_node *of_node = dev->of_node; - - return sprintf(buf, "%s\n", of_node_full_name(of_node)); -} - -static ssize_t modalias_show(struct device *dev, struct device_attribute *attr, - char *buf) -{ - const struct vio_dev *vio_dev = to_vio_dev(dev); - struct device_node *dn; - const char *cp; - - dn = dev->of_node; - if (!dn) { - strcpy(buf, "\n"); - return strlen(buf); - } - cp = of_get_property(dn, "compatible", NULL); - if (!cp) { - strcpy(buf, "\n"); - return strlen(buf); - } - - return sprintf(buf, "vio:T%sS%s\n", vio_dev->type, cp); -} - -static struct device_attribute vio_dev_attrs[] = { - __ATTR_RO(name), - __ATTR_RO(devspec), - __ATTR_RO(modalias), - __ATTR_NULL -}; - -void vio_unregister_device(struct vio_dev *viodev) -{ - device_unregister(&viodev->dev); -} -EXPORT_SYMBOL(vio_unregister_device); - -static int vio_bus_match(struct device *dev, struct device_driver *drv) -{ - const struct vio_dev *vio_dev = to_vio_dev(dev); - struct vio_driver *vio_drv = to_vio_driver(drv); - const struct vio_device_id *ids = vio_drv->id_table; - - return (ids != NULL) && (vio_match_device(ids, vio_dev) != NULL); -} - -static int vio_hotplug(struct device *dev, struct kobj_uevent_env *env) -{ - const struct vio_dev *vio_dev = to_vio_dev(dev); - struct device_node *dn; - const char *cp; - - dn = dev->of_node; - if (!dn) - return -ENODEV; - cp = of_get_property(dn, "compatible", NULL); - if (!cp) - return -ENODEV; - - add_uevent_var(env, "MODALIAS=vio:T%sS%s", vio_dev->type, cp); - return 0; -} - -struct bus_type vio_bus_type = { - .name = "vio", - .dev_attrs = vio_dev_attrs, - .uevent = vio_hotplug, - .match = vio_bus_match, - .probe = vio_bus_probe, - .remove = vio_bus_remove, -}; - -/** - * vio_get_attribute: - get attribute for virtual device - * @vdev: The vio device to get property. - * @which: The property/attribute to be extracted. - * @length: Pointer to length of returned data size (unused if NULL). - * - * Calls prom.c's of_get_property() to return the value of the - * attribute specified by @which -*/ -const void *vio_get_attribute(struct vio_dev *vdev, char *which, int *length) -{ - return of_get_property(vdev->dev.of_node, which, length); -} -EXPORT_SYMBOL(vio_get_attribute); - -#ifdef CONFIG_PPC_PSERIES -/* vio_find_name() - internal because only vio.c knows how we formatted the - * kobject name - */ -static struct vio_dev *vio_find_name(const char *name) -{ - struct device *found; - - found = bus_find_device_by_name(&vio_bus_type, NULL, name); - if (!found) - return NULL; - - return to_vio_dev(found); -} - -/** - * vio_find_node - find an already-registered vio_dev - * @vnode: device_node of the virtual device we're looking for - */ -struct vio_dev *vio_find_node(struct device_node *vnode) -{ - char kobj_name[20]; - struct device_node *vnode_parent; - const char *dev_type; - - vnode_parent = of_get_parent(vnode); - if (!vnode_parent) - return NULL; - - dev_type = of_get_property(vnode_parent, "device_type", NULL); - of_node_put(vnode_parent); - if (!dev_type) - return NULL; - - /* construct the kobject name from the device node */ - if (!strcmp(dev_type, "vdevice")) { - const __be32 *prop; - - prop = of_get_property(vnode, "reg", NULL); - if (!prop) - return NULL; - snprintf(kobj_name, sizeof(kobj_name), "%x", - (uint32_t)of_read_number(prop, 1)); - } else if (!strcmp(dev_type, "ibm,platform-facilities")) - snprintf(kobj_name, sizeof(kobj_name), "%s", vnode->name); - else - return NULL; - - return vio_find_name(kobj_name); -} -EXPORT_SYMBOL(vio_find_node); - -int vio_enable_interrupts(struct vio_dev *dev) -{ - int rc = h_vio_signal(dev->unit_address, VIO_IRQ_ENABLE); - if (rc != H_SUCCESS) - printk(KERN_ERR "vio: Error 0x%x enabling interrupts\n", rc); - return rc; -} -EXPORT_SYMBOL(vio_enable_interrupts); - -int vio_disable_interrupts(struct vio_dev *dev) -{ - int rc = h_vio_signal(dev->unit_address, VIO_IRQ_DISABLE); - if (rc != H_SUCCESS) - printk(KERN_ERR "vio: Error 0x%x disabling interrupts\n", rc); - return rc; -} -EXPORT_SYMBOL(vio_disable_interrupts); -#endif /* CONFIG_PPC_PSERIES */ |