diff options
Diffstat (limited to 'arch/powerpc/kernel')
31 files changed, 828 insertions, 378 deletions
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index 1784b6a6ca1d..f43c1198768c 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -139,6 +139,7 @@ obj-$(CONFIG_KPROBES) += kprobes.o obj-$(CONFIG_OPTPROBES) += optprobes.o optprobes_head.o obj-$(CONFIG_KPROBES_ON_FTRACE) += kprobes-ftrace.o obj-$(CONFIG_UPROBES) += uprobes.o +obj-$(CONFIG_RETHOOK) += rethook.o obj-$(CONFIG_PPC_UDBG_16550) += legacy_serial.o udbg_16550.o obj-$(CONFIG_SWIOTLB) += dma-swiotlb.o obj-$(CONFIG_ARCH_HAS_DMA_SET_MASK) += dma-mask.o diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 23733282de4d..131a8cc10dbe 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -335,6 +335,7 @@ int main(void) /* datapage offsets for use by vdso */ OFFSET(VDSO_DATA_OFFSET, vdso_arch_data, data); + OFFSET(VDSO_RNG_DATA_OFFSET, vdso_arch_data, rng_data); OFFSET(CFG_TB_TICKS_PER_SEC, vdso_arch_data, tb_ticks_per_sec); #ifdef CONFIG_PPC64 OFFSET(CFG_ICACHE_BLOCKSZ, vdso_arch_data, icache_block_size); @@ -346,6 +347,8 @@ int main(void) #else OFFSET(CFG_SYSCALL_MAP32, vdso_arch_data, syscall_map); #endif + OFFSET(VDSO_CLOCKMODE_OFFSET, vdso_arch_data, data[0].clock_mode); + DEFINE(VDSO_CLOCKMODE_TIMENS, VDSO_CLOCKMODE_TIMENS); #ifdef CONFIG_BUG DEFINE(BUG_ENTRY_SIZE, sizeof(struct bug_entry)); diff --git a/arch/powerpc/kernel/cacheinfo.c b/arch/powerpc/kernel/cacheinfo.c index f502337dd37d..0fcc463b02e2 100644 --- a/arch/powerpc/kernel/cacheinfo.c +++ b/arch/powerpc/kernel/cacheinfo.c @@ -735,7 +735,7 @@ static const struct sysfs_ops cache_index_ops = { .show = cache_index_show, }; -static struct kobj_type cache_index_type = { +static const struct kobj_type cache_index_type = { .release = cache_index_release, .sysfs_ops = &cache_index_ops, .default_groups = cache_index_default_groups, diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index d03f17987fca..83fe99861eb1 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -1537,10 +1537,6 @@ int eeh_pe_inject_err(struct eeh_pe *pe, int type, int func, if (!eeh_ops || !eeh_ops->err_inject) return -ENOENT; - /* Check on PCI error type */ - if (type != EEH_ERR_TYPE_32 && type != EEH_ERR_TYPE_64) - return -EINVAL; - /* Check on PCI error function */ if (func < EEH_ERR_FUNC_MIN || func > EEH_ERR_FUNC_MAX) return -EINVAL; @@ -1578,6 +1574,104 @@ static int proc_eeh_show(struct seq_file *m, void *v) } #endif /* CONFIG_PROC_FS */ +static int eeh_break_device(struct pci_dev *pdev) +{ + struct resource *bar = NULL; + void __iomem *mapped; + u16 old, bit; + int i, pos; + + /* Do we have an MMIO BAR to disable? */ + for (i = 0; i <= PCI_STD_RESOURCE_END; i++) { + struct resource *r = &pdev->resource[i]; + + if (!r->flags || !r->start) + continue; + if (r->flags & IORESOURCE_IO) + continue; + if (r->flags & IORESOURCE_UNSET) + continue; + + bar = r; + break; + } + + if (!bar) { + pci_err(pdev, "Unable to find Memory BAR to cause EEH with\n"); + return -ENXIO; + } + + pci_err(pdev, "Going to break: %pR\n", bar); + + if (pdev->is_virtfn) { +#ifndef CONFIG_PCI_IOV + return -ENXIO; +#else + /* + * VFs don't have a per-function COMMAND register, so the best + * we can do is clear the Memory Space Enable bit in the PF's + * SRIOV control reg. + * + * Unfortunately, this requires that we have a PF (i.e doesn't + * work for a passed-through VF) and it has the potential side + * effect of also causing an EEH on every other VF under the + * PF. Oh well. + */ + pdev = pdev->physfn; + if (!pdev) + return -ENXIO; /* passed through VFs have no PF */ + + pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_SRIOV); + pos += PCI_SRIOV_CTRL; + bit = PCI_SRIOV_CTRL_MSE; +#endif /* !CONFIG_PCI_IOV */ + } else { + bit = PCI_COMMAND_MEMORY; + pos = PCI_COMMAND; + } + + /* + * Process here is: + * + * 1. Disable Memory space. + * + * 2. Perform an MMIO to the device. This should result in an error + * (CA / UR) being raised by the device which results in an EEH + * PE freeze. Using the in_8() accessor skips the eeh detection hook + * so the freeze hook so the EEH Detection machinery won't be + * triggered here. This is to match the usual behaviour of EEH + * where the HW will asynchronously freeze a PE and it's up to + * the kernel to notice and deal with it. + * + * 3. Turn Memory space back on. This is more important for VFs + * since recovery will probably fail if we don't. For normal + * the COMMAND register is reset as a part of re-initialising + * the device. + * + * Breaking stuff is the point so who cares if it's racy ;) + */ + pci_read_config_word(pdev, pos, &old); + + mapped = ioremap(bar->start, PAGE_SIZE); + if (!mapped) { + pci_err(pdev, "Unable to map MMIO BAR %pR\n", bar); + return -ENXIO; + } + + pci_write_config_word(pdev, pos, old & ~bit); + in_8(mapped); + pci_write_config_word(pdev, pos, old); + + iounmap(mapped); + + return 0; +} + +int eeh_pe_inject_mmio_error(struct pci_dev *pdev) +{ + return eeh_break_device(pdev); +} + #ifdef CONFIG_DEBUG_FS @@ -1682,7 +1776,6 @@ static ssize_t eeh_force_recover_write(struct file *filp, static const struct file_operations eeh_force_recover_fops = { .open = simple_open, - .llseek = no_llseek, .write = eeh_force_recover_write, }; @@ -1726,104 +1819,10 @@ static ssize_t eeh_dev_check_write(struct file *filp, static const struct file_operations eeh_dev_check_fops = { .open = simple_open, - .llseek = no_llseek, .write = eeh_dev_check_write, .read = eeh_debugfs_dev_usage, }; -static int eeh_debugfs_break_device(struct pci_dev *pdev) -{ - struct resource *bar = NULL; - void __iomem *mapped; - u16 old, bit; - int i, pos; - - /* Do we have an MMIO BAR to disable? */ - for (i = 0; i <= PCI_STD_RESOURCE_END; i++) { - struct resource *r = &pdev->resource[i]; - - if (!r->flags || !r->start) - continue; - if (r->flags & IORESOURCE_IO) - continue; - if (r->flags & IORESOURCE_UNSET) - continue; - - bar = r; - break; - } - - if (!bar) { - pci_err(pdev, "Unable to find Memory BAR to cause EEH with\n"); - return -ENXIO; - } - - pci_err(pdev, "Going to break: %pR\n", bar); - - if (pdev->is_virtfn) { -#ifndef CONFIG_PCI_IOV - return -ENXIO; -#else - /* - * VFs don't have a per-function COMMAND register, so the best - * we can do is clear the Memory Space Enable bit in the PF's - * SRIOV control reg. - * - * Unfortunately, this requires that we have a PF (i.e doesn't - * work for a passed-through VF) and it has the potential side - * effect of also causing an EEH on every other VF under the - * PF. Oh well. - */ - pdev = pdev->physfn; - if (!pdev) - return -ENXIO; /* passed through VFs have no PF */ - - pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_SRIOV); - pos += PCI_SRIOV_CTRL; - bit = PCI_SRIOV_CTRL_MSE; -#endif /* !CONFIG_PCI_IOV */ - } else { - bit = PCI_COMMAND_MEMORY; - pos = PCI_COMMAND; - } - - /* - * Process here is: - * - * 1. Disable Memory space. - * - * 2. Perform an MMIO to the device. This should result in an error - * (CA / UR) being raised by the device which results in an EEH - * PE freeze. Using the in_8() accessor skips the eeh detection hook - * so the freeze hook so the EEH Detection machinery won't be - * triggered here. This is to match the usual behaviour of EEH - * where the HW will asynchronously freeze a PE and it's up to - * the kernel to notice and deal with it. - * - * 3. Turn Memory space back on. This is more important for VFs - * since recovery will probably fail if we don't. For normal - * the COMMAND register is reset as a part of re-initialising - * the device. - * - * Breaking stuff is the point so who cares if it's racy ;) - */ - pci_read_config_word(pdev, pos, &old); - - mapped = ioremap(bar->start, PAGE_SIZE); - if (!mapped) { - pci_err(pdev, "Unable to map MMIO BAR %pR\n", bar); - return -ENXIO; - } - - pci_write_config_word(pdev, pos, old & ~bit); - in_8(mapped); - pci_write_config_word(pdev, pos, old); - - iounmap(mapped); - - return 0; -} - static ssize_t eeh_dev_break_write(struct file *filp, const char __user *user_buf, size_t count, loff_t *ppos) @@ -1835,7 +1834,7 @@ static ssize_t eeh_dev_break_write(struct file *filp, if (IS_ERR(pdev)) return PTR_ERR(pdev); - ret = eeh_debugfs_break_device(pdev); + ret = eeh_break_device(pdev); pci_dev_put(pdev); if (ret < 0) @@ -1846,7 +1845,6 @@ static ssize_t eeh_dev_break_write(struct file *filp, static const struct file_operations eeh_dev_break_fops = { .open = simple_open, - .llseek = no_llseek, .write = eeh_dev_break_write, .read = eeh_debugfs_dev_usage, }; @@ -1893,7 +1891,6 @@ static ssize_t eeh_dev_can_recover(struct file *filp, static const struct file_operations eeh_dev_can_recover_fops = { .open = simple_open, - .llseek = no_llseek, .write = eeh_dev_can_recover, .read = eeh_debugfs_dev_usage, }; diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index eaf2f167c342..195b075d116c 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -1989,13 +1989,6 @@ INT_DEFINE_END(system_call) INTERRUPT_TO_KERNEL #endif -#ifdef CONFIG_PPC_FAST_ENDIAN_SWITCH -BEGIN_FTR_SECTION - cmpdi r0,0x1ebe - beq- 1f -END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE) -#endif - /* We reach here with PACA in r13, r13 in r9. */ mfspr r11,SPRN_SRR0 mfspr r12,SPRN_SRR1 @@ -2015,16 +2008,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE) b system_call_common #endif .endif - -#ifdef CONFIG_PPC_FAST_ENDIAN_SWITCH - /* Fast LE/BE switch system call */ -1: mfspr r12,SPRN_SRR1 - xori r12,r12,MSR_LE - mtspr SPRN_SRR1,r12 - mr r13,r9 - RFI_TO_USER /* return to userspace */ - b . /* prevent speculative execution */ -#endif .endm EXC_REAL_BEGIN(system_call, 0xc00, 0x100) diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S index ac74321b1192..811a7130505c 100644 --- a/arch/powerpc/kernel/head_8xx.S +++ b/arch/powerpc/kernel/head_8xx.S @@ -40,16 +40,6 @@ #include "head_32.h" -.macro compare_to_kernel_boundary scratch, addr -#if CONFIG_TASK_SIZE <= 0x80000000 && CONFIG_PAGE_OFFSET >= 0x80000000 -/* By simply checking Address >= 0x80000000, we know if its a kernel address */ - not. \scratch, \addr -#else - rlwinm \scratch, \addr, 16, 0xfff8 - cmpli cr0, \scratch, PAGE_OFFSET@h -#endif -.endm - #define PAGE_SHIFT_512K 19 #define PAGE_SHIFT_8M 23 @@ -199,18 +189,7 @@ instruction_counter: mfspr r10, SPRN_SRR0 /* Get effective address of fault */ INVALIDATE_ADJACENT_PAGES_CPU15(r10, r11) mtspr SPRN_MD_EPN, r10 -#ifdef CONFIG_EXECMEM - mfcr r11 - compare_to_kernel_boundary r10, r10 -#endif mfspr r10, SPRN_M_TWB /* Get level 1 table */ -#ifdef CONFIG_EXECMEM - blt+ 3f - rlwinm r10, r10, 0, 20, 31 - oris r10, r10, (swapper_pg_dir - PAGE_OFFSET)@ha -3: - mtcr r11 -#endif lwz r11, (swapper_pg_dir-PAGE_OFFSET)@l(r10) /* Get level 1 entry */ mtspr SPRN_MD_TWC, r11 mfspr r10, SPRN_MD_TWC @@ -248,19 +227,12 @@ instruction_counter: START_EXCEPTION(INTERRUPT_DATA_TLB_MISS_8xx, DataStoreTLBMiss) mtspr SPRN_SPRG_SCRATCH2, r10 mtspr SPRN_M_TW, r11 - mfcr r11 /* If we are faulting a kernel address, we have to use the * kernel page tables. */ mfspr r10, SPRN_MD_EPN - compare_to_kernel_boundary r10, r10 mfspr r10, SPRN_M_TWB /* Get level 1 table */ - blt+ 3f - rlwinm r10, r10, 0, 20, 31 - oris r10, r10, (swapper_pg_dir - PAGE_OFFSET)@ha -3: - mtcr r11 lwz r11, (swapper_pg_dir-PAGE_OFFSET)@l(r10) /* Get level 1 entry */ mtspr SPRN_MD_TWC, r11 @@ -332,15 +304,19 @@ instruction_counter: cmpwi cr1, r11, RPN_PATTERN beq- cr1, FixupDAR /* must be a buggy dcbX, icbi insn. */ DARFixed:/* Return from dcbx instruction bug workaround */ + mfspr r11, SPRN_DSISR + rlwinm r11, r11, 0, DSISR_NOHPTE + cmpwi cr1, r11, 0 + beq+ cr1, .Ldtlbie + mfspr r11, SPRN_DAR + tlbie r11 + rlwinm r11, r11, 16, 0xffff + cmplwi cr1, r11, TASK_SIZE@h + bge- cr1, FixupPGD +.Ldtlbie: EXCEPTION_PROLOG_1 /* 0x300 is DataAccess exception, needed by bad_page_fault() */ EXCEPTION_PROLOG_2 INTERRUPT_DATA_STORAGE DataTLBError handle_dar_dsisr=1 - lwz r4, _DAR(r11) - lwz r5, _DSISR(r11) - andis. r10,r5,DSISR_NOHPTE@h - beq+ .Ldtlbie - tlbie r4 -.Ldtlbie: prepare_transfer_to_handler bl do_page_fault b interrupt_return @@ -394,6 +370,30 @@ DARFixed:/* Return from dcbx instruction bug workaround */ __HEAD . = 0x2000 +FixupPGD: + mtspr SPRN_M_TW, r10 + mfspr r10, SPRN_DAR + mtspr SPRN_MD_EPN, r10 + mfspr r11, SPRN_M_TWB /* Get level 1 table */ + lwz r10, (swapper_pg_dir - PAGE_OFFSET)@l(r11) /* Get the level 1 entry */ + cmpwi cr1, r10, 0 + bne cr1, 1f + + rlwinm r10, r11, 0, 20, 31 + oris r10, r10, (swapper_pg_dir - PAGE_OFFSET)@ha + lwz r10, (swapper_pg_dir - PAGE_OFFSET)@l(r10) /* Get the level 1 entry */ + cmpwi cr1, r10, 0 + beq cr1, 1f + stw r10, (swapper_pg_dir - PAGE_OFFSET)@l(r11) /* Set the level 1 entry */ + mfspr r10, SPRN_M_TW + mtcr r10 + mfspr r10, SPRN_SPRG_SCRATCH0 + mfspr r11, SPRN_SPRG_SCRATCH1 + rfi +1: + mfspr r10, SPRN_M_TW + b .Ldtlbie + /* This is the procedure to calculate the data EA for buggy dcbx,dcbi instructions * by decoding the registers used by the dcbx instruction and adding them. * DAR is set to the calculated address. @@ -404,7 +404,7 @@ FixupDAR:/* Entry point for dcbx workaround. */ mfspr r10, SPRN_SRR0 mtspr SPRN_MD_EPN, r10 rlwinm r11, r10, 16, 0xfff8 - cmpli cr1, r11, PAGE_OFFSET@h + cmpli cr1, r11, TASK_SIZE@h mfspr r11, SPRN_M_TWB /* Get level 1 table */ blt+ cr1, 3f @@ -587,6 +587,10 @@ start_here: lis r0, (MD_TWAM | MD_RSV4I)@h mtspr SPRN_MD_CTR, r0 #endif +#ifndef CONFIG_PIN_TLB_TEXT + li r0, 0 + mtspr SPRN_MI_CTR, r0 +#endif #if !defined(CONFIG_PIN_TLB_DATA) && !defined(CONFIG_PIN_TLB_IMMR) lis r0, MD_TWAM@h mtspr SPRN_MD_CTR, r0 @@ -683,6 +687,7 @@ SYM_FUNC_START_LOCAL(initial_mmu) blr SYM_FUNC_END(initial_mmu) +#ifdef CONFIG_PIN_TLB _GLOBAL(mmu_pin_tlb) lis r9, (1f - PAGE_OFFSET)@h ori r9, r9, (1f - PAGE_OFFSET)@l @@ -704,6 +709,7 @@ _GLOBAL(mmu_pin_tlb) mtspr SPRN_MD_CTR, r6 tlbia +#ifdef CONFIG_PIN_TLB_TEXT LOAD_REG_IMMEDIATE(r5, 28 << 8) LOAD_REG_IMMEDIATE(r6, PAGE_OFFSET) LOAD_REG_IMMEDIATE(r7, MI_SVALID | MI_PS8MEG | _PMD_ACCESSED) @@ -724,6 +730,7 @@ _GLOBAL(mmu_pin_tlb) bdnzt lt, 2b lis r0, MI_RSV4I@h mtspr SPRN_MI_CTR, r0 +#endif LOAD_REG_IMMEDIATE(r5, 28 << 8 | MD_TWAM) #ifdef CONFIG_PIN_TLB_DATA @@ -783,3 +790,4 @@ _GLOBAL(mmu_pin_tlb) mtspr SPRN_SRR1, r10 mtspr SPRN_SRR0, r11 rfi +#endif diff --git a/arch/powerpc/kernel/head_book3s_32.S b/arch/powerpc/kernel/head_book3s_32.S index 57196883a00e..cb2bca76be53 100644 --- a/arch/powerpc/kernel/head_book3s_32.S +++ b/arch/powerpc/kernel/head_book3s_32.S @@ -411,39 +411,26 @@ END_FTR_SECTION_IFSET(CPU_FTR_FPU_UNAVAILABLE) */ . = INTERRUPT_INST_TLB_MISS_603 InstructionTLBMiss: -/* - * r0: userspace flag (later scratch) - * r1: linux style pte ( later becomes ppc hardware pte ) - * r2: ptr to linux-style pte - * r3: fault address - */ /* Get PTE (linux-style) and check access */ - mfspr r3,SPRN_IMISS -#ifdef CONFIG_EXECMEM - lis r1, TASK_SIZE@h /* check if kernel address */ - cmplw 0,r1,r3 -#endif + mfspr r0,SPRN_IMISS mfspr r2, SPRN_SDR1 li r1,_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_EXEC rlwinm r2, r2, 28, 0xfffff000 + rlwimi r2,r0,12,20,29 /* insert top 10 bits of address */ + lwz r2,0(r2) /* get pmd entry */ #ifdef CONFIG_EXECMEM - li r0, 3 - bgt- 112f - lis r2, (swapper_pg_dir - PAGE_OFFSET)@ha /* if kernel address, use */ - li r0, 0 - addi r2, r2, (swapper_pg_dir - PAGE_OFFSET)@l /* kernel page table */ + rlwinm r3, r0, 4, 0xf + subi r3, r3, (TASK_SIZE >> 28) & 0xf #endif -112: rlwimi r2,r3,12,20,29 /* insert top 10 bits of address */ - lwz r2,0(r2) /* get pmd entry */ rlwinm. r2,r2,0,0,19 /* extract address of pte page */ beq- InstructionAddressInvalid /* return if no mapping */ - rlwimi r2,r3,22,20,29 /* insert next 10 bits of address */ + rlwimi r2,r0,22,20,29 /* insert next 10 bits of address */ lwz r2,0(r2) /* get linux-style pte */ andc. r1,r1,r2 /* check access & ~permission */ bne- InstructionAddressInvalid /* return if access not permitted */ /* Convert linux-style PTE to low word of PPC-style PTE */ #ifdef CONFIG_EXECMEM - rlwimi r2, r0, 0, 31, 31 /* userspace ? -> PP lsb */ + rlwimi r2, r3, 1, 31, 31 /* userspace ? -> PP lsb */ #endif ori r1, r1, 0xe06 /* clear out reserved bits */ andc r1, r2, r1 /* PP = user? 1 : 0 */ @@ -451,7 +438,7 @@ BEGIN_FTR_SECTION rlwinm r1,r1,0,~_PAGE_COHERENT /* clear M (coherence not required) */ END_FTR_SECTION_IFCLR(CPU_FTR_NEED_COHERENT) mtspr SPRN_RPA,r1 - tlbli r3 + tlbli r0 mfspr r3,SPRN_SRR1 /* Need to restore CR0 */ mtcrf 0x80,r3 rfi @@ -480,35 +467,24 @@ InstructionAddressInvalid: */ . = INTERRUPT_DATA_LOAD_TLB_MISS_603 DataLoadTLBMiss: -/* - * r0: userspace flag (later scratch) - * r1: linux style pte ( later becomes ppc hardware pte ) - * r2: ptr to linux-style pte - * r3: fault address - */ /* Get PTE (linux-style) and check access */ - mfspr r3,SPRN_DMISS - lis r1, TASK_SIZE@h /* check if kernel address */ - cmplw 0,r1,r3 + mfspr r0,SPRN_DMISS mfspr r2, SPRN_SDR1 - li r1, _PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_READ - rlwinm r2, r2, 28, 0xfffff000 - li r0, 3 - bgt- 112f - lis r2, (swapper_pg_dir - PAGE_OFFSET)@ha /* if kernel address, use */ - li r0, 0 - addi r2, r2, (swapper_pg_dir - PAGE_OFFSET)@l /* kernel page table */ -112: rlwimi r2,r3,12,20,29 /* insert top 10 bits of address */ - lwz r2,0(r2) /* get pmd entry */ + rlwinm r1, r2, 28, 0xfffff000 + rlwimi r1,r0,12,20,29 /* insert top 10 bits of address */ + lwz r2,0(r1) /* get pmd entry */ + rlwinm r3, r0, 4, 0xf rlwinm. r2,r2,0,0,19 /* extract address of pte page */ - beq- DataAddressInvalid /* return if no mapping */ - rlwimi r2,r3,22,20,29 /* insert next 10 bits of address */ + subi r3, r3, (TASK_SIZE >> 28) & 0xf + beq- 2f /* bail if no mapping */ +1: rlwimi r2,r0,22,20,29 /* insert next 10 bits of address */ lwz r2,0(r2) /* get linux-style pte */ + li r1, _PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_READ andc. r1,r1,r2 /* check access & ~permission */ bne- DataAddressInvalid /* return if access not permitted */ /* Convert linux-style PTE to low word of PPC-style PTE */ rlwinm r1,r2,32-9,30,30 /* _PAGE_WRITE -> PP msb */ - rlwimi r2,r0,0,30,31 /* userspace ? -> PP */ + rlwimi r2,r3,2,30,31 /* userspace ? -> PP */ rlwimi r1,r2,32-3,24,24 /* _PAGE_WRITE -> _PAGE_DIRTY */ xori r1,r1,_PAGE_DIRTY /* clear dirty when not rw */ ori r1,r1,0xe04 /* clear out reserved bits */ @@ -518,25 +494,35 @@ BEGIN_FTR_SECTION END_FTR_SECTION_IFCLR(CPU_FTR_NEED_COHERENT) mtspr SPRN_RPA,r1 BEGIN_MMU_FTR_SECTION - li r0,1 + li r3,1 mfspr r1,SPRN_SPRG_603_LRU - rlwinm r2,r3,20,27,31 /* Get Address bits 15:19 */ - slw r0,r0,r2 - xor r1,r0,r1 - srw r0,r1,r2 + rlwinm r2,r0,20,27,31 /* Get Address bits 15:19 */ + slw r3,r3,r2 + xor r1,r3,r1 + srw r3,r1,r2 mtspr SPRN_SPRG_603_LRU,r1 mfspr r2,SPRN_SRR1 - rlwimi r2,r0,31-14,14,14 + rlwimi r2,r3,31-14,14,14 mtspr SPRN_SRR1,r2 mtcrf 0x80,r2 - tlbld r3 + tlbld r0 rfi MMU_FTR_SECTION_ELSE mfspr r2,SPRN_SRR1 /* Need to restore CR0 */ mtcrf 0x80,r2 - tlbld r3 + tlbld r0 rfi ALT_MMU_FTR_SECTION_END_IFSET(MMU_FTR_NEED_DTLB_SW_LRU) + +2: lis r2, (swapper_pg_dir - PAGE_OFFSET)@ha + addi r2, r2, (swapper_pg_dir - PAGE_OFFSET)@l /* kernel page table */ + rlwimi r2,r0,12,20,29 /* insert top 10 bits of address */ + lwz r2,0(r2) /* get pmd entry */ + cmpwi cr0,r2,0 + beq- DataAddressInvalid /* return if no mapping */ + stw r2,0(r1) + rlwinm. r2,r2,0,0,19 /* extract address of pte page */ + b 1b DataAddressInvalid: mfspr r3,SPRN_SRR1 rlwinm r1,r3,9,6,6 /* Get load/store bit */ @@ -560,34 +546,24 @@ DataAddressInvalid: */ . = INTERRUPT_DATA_STORE_TLB_MISS_603 DataStoreTLBMiss: -/* - * r0: userspace flag (later scratch) - * r1: linux style pte ( later becomes ppc hardware pte ) - * r2: ptr to linux-style pte - * r3: fault address - */ /* Get PTE (linux-style) and check access */ - mfspr r3,SPRN_DMISS - lis r1, TASK_SIZE@h /* check if kernel address */ - cmplw 0,r1,r3 + mfspr r0,SPRN_DMISS mfspr r2, SPRN_SDR1 - li r1, _PAGE_RW | _PAGE_DIRTY | _PAGE_PRESENT | _PAGE_ACCESSED - rlwinm r2, r2, 28, 0xfffff000 - li r0, 3 - bgt- 112f - lis r2, (swapper_pg_dir - PAGE_OFFSET)@ha /* if kernel address, use */ - li r0, 0 - addi r2, r2, (swapper_pg_dir - PAGE_OFFSET)@l /* kernel page table */ -112: rlwimi r2,r3,12,20,29 /* insert top 10 bits of address */ - lwz r2,0(r2) /* get pmd entry */ + rlwinm r1, r2, 28, 0xfffff000 + rlwimi r1,r0,12,20,29 /* insert top 10 bits of address */ + lwz r2,0(r1) /* get pmd entry */ + rlwinm r3, r0, 4, 0xf rlwinm. r2,r2,0,0,19 /* extract address of pte page */ - beq- DataAddressInvalid /* return if no mapping */ - rlwimi r2,r3,22,20,29 /* insert next 10 bits of address */ + subi r3, r3, (TASK_SIZE >> 28) & 0xf + beq- 2f /* bail if no mapping */ +1: + rlwimi r2,r0,22,20,29 /* insert next 10 bits of address */ lwz r2,0(r2) /* get linux-style pte */ + li r1, _PAGE_RW | _PAGE_DIRTY | _PAGE_PRESENT | _PAGE_ACCESSED andc. r1,r1,r2 /* check access & ~permission */ bne- DataAddressInvalid /* return if access not permitted */ /* Convert linux-style PTE to low word of PPC-style PTE */ - rlwimi r2,r0,0,31,31 /* userspace ? -> PP lsb */ + rlwimi r2,r3,1,31,31 /* userspace ? -> PP lsb */ li r1,0xe06 /* clear out reserved bits & PP msb */ andc r1,r2,r1 /* PP = user? 1: 0 */ BEGIN_FTR_SECTION @@ -597,26 +573,36 @@ END_FTR_SECTION_IFCLR(CPU_FTR_NEED_COHERENT) mfspr r2,SPRN_SRR1 /* Need to restore CR0 */ mtcrf 0x80,r2 BEGIN_MMU_FTR_SECTION - li r0,1 + li r3,1 mfspr r1,SPRN_SPRG_603_LRU - rlwinm r2,r3,20,27,31 /* Get Address bits 15:19 */ - slw r0,r0,r2 - xor r1,r0,r1 - srw r0,r1,r2 + rlwinm r2,r0,20,27,31 /* Get Address bits 15:19 */ + slw r3,r3,r2 + xor r1,r3,r1 + srw r3,r1,r2 mtspr SPRN_SPRG_603_LRU,r1 mfspr r2,SPRN_SRR1 - rlwimi r2,r0,31-14,14,14 + rlwimi r2,r3,31-14,14,14 mtspr SPRN_SRR1,r2 mtcrf 0x80,r2 - tlbld r3 + tlbld r0 rfi MMU_FTR_SECTION_ELSE mfspr r2,SPRN_SRR1 /* Need to restore CR0 */ mtcrf 0x80,r2 - tlbld r3 + tlbld r0 rfi ALT_MMU_FTR_SECTION_END_IFSET(MMU_FTR_NEED_DTLB_SW_LRU) +2: lis r2, (swapper_pg_dir - PAGE_OFFSET)@ha + addi r2, r2, (swapper_pg_dir - PAGE_OFFSET)@l /* kernel page table */ + rlwimi r2,r0,12,20,29 /* insert top 10 bits of address */ + lwz r2,0(r2) /* get pmd entry */ + cmpwi cr0,r2,0 + beq- DataAddressInvalid /* return if no mapping */ + stw r2,0(r1) + rlwinm r2,r2,0,0,19 /* extract address of pte page */ + b 1b + #ifndef CONFIG_ALTIVEC #define altivec_assist_exception unknown_exception #endif diff --git a/arch/powerpc/kernel/interrupt.c b/arch/powerpc/kernel/interrupt.c index eca293794a1e..af62ec974b97 100644 --- a/arch/powerpc/kernel/interrupt.c +++ b/arch/powerpc/kernel/interrupt.c @@ -266,7 +266,7 @@ notrace unsigned long syscall_exit_prepare(unsigned long r3, unsigned long ret = 0; bool is_not_scv = !IS_ENABLED(CONFIG_PPC_BOOK3S_64) || !scv; - CT_WARN_ON(ct_state() == CONTEXT_USER); + CT_WARN_ON(ct_state() == CT_STATE_USER); kuap_assert_locked(); @@ -344,7 +344,7 @@ notrace unsigned long interrupt_exit_user_prepare(struct pt_regs *regs) BUG_ON(regs_is_unrecoverable(regs)); BUG_ON(arch_irq_disabled_regs(regs)); - CT_WARN_ON(ct_state() == CONTEXT_USER); + CT_WARN_ON(ct_state() == CT_STATE_USER); /* * We don't need to restore AMR on the way back to userspace for KUAP. @@ -386,7 +386,7 @@ notrace unsigned long interrupt_exit_kernel_prepare(struct pt_regs *regs) if (!IS_ENABLED(CONFIG_PPC_BOOK3E_64) && TRAP(regs) != INTERRUPT_PROGRAM && TRAP(regs) != INTERRUPT_PERFMON) - CT_WARN_ON(ct_state() == CONTEXT_USER); + CT_WARN_ON(ct_state() == CT_STATE_USER); kuap = kuap_get_and_assert_locked(); diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c index 14c5ddec3056..f8aa91bc3b17 100644 --- a/arch/powerpc/kernel/kprobes.c +++ b/arch/powerpc/kernel/kprobes.c @@ -228,16 +228,6 @@ static nokprobe_inline void set_current_kprobe(struct kprobe *p, struct pt_regs kcb->kprobe_saved_msr = regs->msr; } -void arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs) -{ - ri->ret_addr = (kprobe_opcode_t *)regs->link; - ri->fp = NULL; - - /* Replace the return addr with trampoline addr */ - regs->link = (unsigned long)__kretprobe_trampoline; -} -NOKPROBE_SYMBOL(arch_prepare_kretprobe); - static int try_to_emulate(struct kprobe *p, struct pt_regs *regs) { int ret; @@ -395,49 +385,6 @@ no_kprobe: NOKPROBE_SYMBOL(kprobe_handler); /* - * Function return probe trampoline: - * - init_kprobes() establishes a probepoint here - * - When the probed function returns, this probe - * causes the handlers to fire - */ -asm(".global __kretprobe_trampoline\n" - ".type __kretprobe_trampoline, @function\n" - "__kretprobe_trampoline:\n" - "nop\n" - "blr\n" - ".size __kretprobe_trampoline, .-__kretprobe_trampoline\n"); - -/* - * Called when the probe at kretprobe trampoline is hit - */ -static int trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) -{ - unsigned long orig_ret_address; - - orig_ret_address = __kretprobe_trampoline_handler(regs, NULL); - /* - * We get here through one of two paths: - * 1. by taking a trap -> kprobe_handler() -> here - * 2. by optprobe branch -> optimized_callback() -> opt_pre_handler() -> here - * - * When going back through (1), we need regs->nip to be setup properly - * as it is used to determine the return address from the trap. - * For (2), since nip is not honoured with optprobes, we instead setup - * the link register properly so that the subsequent 'blr' in - * __kretprobe_trampoline jumps back to the right instruction. - * - * For nip, we should set the address to the previous instruction since - * we end up emulating it in kprobe_handler(), which increments the nip - * again. - */ - regs_set_return_ip(regs, orig_ret_address - 4); - regs->link = orig_ret_address; - - return 0; -} -NOKPROBE_SYMBOL(trampoline_probe_handler); - -/* * Called after single-stepping. p->addr is the address of the * instruction whose first byte has been replaced by the "breakpoint" * instruction. To avoid the SMP problems that can occur when we @@ -539,19 +486,9 @@ int kprobe_fault_handler(struct pt_regs *regs, int trapnr) } NOKPROBE_SYMBOL(kprobe_fault_handler); -static struct kprobe trampoline_p = { - .addr = (kprobe_opcode_t *) &__kretprobe_trampoline, - .pre_handler = trampoline_probe_handler -}; - -int __init arch_init_kprobes(void) -{ - return register_kprobe(&trampoline_p); -} - int arch_trampoline_kprobe(struct kprobe *p) { - if (p->addr == (kprobe_opcode_t *)&__kretprobe_trampoline) + if (p->addr == (kprobe_opcode_t *)&arch_rethook_trampoline) return 1; return 0; diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c index 7112adc597a8..e9bab599d0c2 100644 --- a/arch/powerpc/kernel/module_64.c +++ b/arch/powerpc/kernel/module_64.c @@ -651,12 +651,11 @@ static inline int create_stub(const Elf64_Shdr *sechdrs, // func_desc_t is 8 bytes if ABIv2, else 16 bytes desc = func_desc(addr); for (i = 0; i < sizeof(func_desc_t) / sizeof(u32); i++) { - if (patch_instruction(((u32 *)&entry->funcdata) + i, - ppc_inst(((u32 *)(&desc))[i]))) + if (patch_u32(((u32 *)&entry->funcdata) + i, ((u32 *)&desc)[i])) return 0; } - if (patch_instruction(&entry->magic, ppc_inst(STUB_MAGIC))) + if (patch_u32(&entry->magic, STUB_MAGIC)) return 0; return 1; diff --git a/arch/powerpc/kernel/nvram_64.c b/arch/powerpc/kernel/nvram_64.c index e385d3164648..f9c6568a9137 100644 --- a/arch/powerpc/kernel/nvram_64.c +++ b/arch/powerpc/kernel/nvram_64.c @@ -73,7 +73,7 @@ static const char *nvram_os_partitions[] = { }; static void oops_to_nvram(struct kmsg_dumper *dumper, - enum kmsg_dump_reason reason); + struct kmsg_dump_detail *detail); static struct kmsg_dumper nvram_kmsg_dumper = { .dump = oops_to_nvram @@ -643,7 +643,7 @@ void __init nvram_init_oops_partition(int rtas_partition_exists) * partition. If that's too much, go back and capture uncompressed text. */ static void oops_to_nvram(struct kmsg_dumper *dumper, - enum kmsg_dump_reason reason) + struct kmsg_dump_detail *detail) { struct oops_log_info *oops_hdr = (struct oops_log_info *)oops_buf; static unsigned int oops_count = 0; @@ -655,7 +655,7 @@ static void oops_to_nvram(struct kmsg_dumper *dumper, unsigned int err_type = ERR_TYPE_KERNEL_PANIC_GZ; int rc = -1; - switch (reason) { + switch (detail->reason) { case KMSG_DUMP_SHUTDOWN: /* These are almost always orderly shutdowns. */ return; @@ -671,7 +671,7 @@ static void oops_to_nvram(struct kmsg_dumper *dumper, break; default: pr_err("%s: ignoring unrecognized KMSG_DUMP_* reason %d\n", - __func__, (int) reason); + __func__, (int) detail->reason); return; } diff --git a/arch/powerpc/kernel/optprobes.c b/arch/powerpc/kernel/optprobes.c index 004fae2044a3..c0b351d61058 100644 --- a/arch/powerpc/kernel/optprobes.c +++ b/arch/powerpc/kernel/optprobes.c @@ -56,7 +56,7 @@ static unsigned long can_optimize(struct kprobe *p) * has a 'nop' instruction, which can be emulated. * So further checks can be skipped. */ - if (p->addr == (kprobe_opcode_t *)&__kretprobe_trampoline) + if (p->addr == (kprobe_opcode_t *)&arch_rethook_trampoline) return addr + sizeof(kprobe_opcode_t); /* diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 3b506d4c55f3..ff61a3e7984c 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -72,8 +72,6 @@ #define TM_DEBUG(x...) do { } while(0) #endif -extern unsigned long _get_SP(void); - #ifdef CONFIG_PPC_TRANSACTIONAL_MEM /* * Are we running in "Suspend disabled" mode? If so we have to block any @@ -2177,10 +2175,10 @@ static inline int valid_irq_stack(unsigned long sp, struct task_struct *p, return 0; } +#ifdef CONFIG_PPC64 static inline int valid_emergency_stack(unsigned long sp, struct task_struct *p, unsigned long nbytes) { -#ifdef CONFIG_PPC64 unsigned long stack_page; unsigned long cpu = task_cpu(p); @@ -2208,10 +2206,26 @@ static inline int valid_emergency_stack(unsigned long sp, struct task_struct *p, if (sp >= stack_page && sp <= stack_page + THREAD_SIZE - nbytes) return 1; # endif -#endif return 0; } +#else +static inline int valid_emergency_stack(unsigned long sp, struct task_struct *p, + unsigned long nbytes) +{ + unsigned long stack_page; + unsigned long cpu = task_cpu(p); + + if (!IS_ENABLED(CONFIG_VMAP_STACK)) + return 0; + + stack_page = (unsigned long)emergency_ctx[cpu] - THREAD_SIZE; + if (sp >= stack_page && sp <= stack_page + THREAD_SIZE - nbytes) + return 1; + + return 0; +} +#endif /* * validate the stack frame of a particular minimum size, used for when we are diff --git a/arch/powerpc/kernel/rethook.c b/arch/powerpc/kernel/rethook.c new file mode 100644 index 000000000000..5f5f47ae82cf --- /dev/null +++ b/arch/powerpc/kernel/rethook.c @@ -0,0 +1,73 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * PowerPC implementation of rethook. This depends on kprobes. + */ + +#include <linux/kprobes.h> +#include <linux/rethook.h> + +/* + * Function return trampoline: + * - init_kprobes() establishes a probepoint here + * - When the probed function returns, this probe + * causes the handlers to fire + */ +asm(".global arch_rethook_trampoline\n" + ".type arch_rethook_trampoline, @function\n" + "arch_rethook_trampoline:\n" + "nop\n" + "blr\n" + ".size arch_rethook_trampoline, .-arch_rethook_trampoline\n"); + +/* + * Called when the probe at kretprobe trampoline is hit + */ +static int trampoline_rethook_handler(struct kprobe *p, struct pt_regs *regs) +{ + return !rethook_trampoline_handler(regs, regs->gpr[1]); +} +NOKPROBE_SYMBOL(trampoline_rethook_handler); + +void arch_rethook_prepare(struct rethook_node *rh, struct pt_regs *regs, bool mcount) +{ + rh->ret_addr = regs->link; + rh->frame = regs->gpr[1]; + + /* Replace the return addr with trampoline addr */ + regs->link = (unsigned long)arch_rethook_trampoline; +} +NOKPROBE_SYMBOL(arch_rethook_prepare); + +/* This is called from rethook_trampoline_handler(). */ +void arch_rethook_fixup_return(struct pt_regs *regs, unsigned long orig_ret_address) +{ + /* + * We get here through one of two paths: + * 1. by taking a trap -> kprobe_handler() -> here + * 2. by optprobe branch -> optimized_callback() -> opt_pre_handler() -> here + * + * When going back through (1), we need regs->nip to be setup properly + * as it is used to determine the return address from the trap. + * For (2), since nip is not honoured with optprobes, we instead setup + * the link register properly so that the subsequent 'blr' in + * arch_rethook_trampoline jumps back to the right instruction. + * + * For nip, we should set the address to the previous instruction since + * we end up emulating it in kprobe_handler(), which increments the nip + * again. + */ + regs_set_return_ip(regs, orig_ret_address - 4); + regs->link = orig_ret_address; +} +NOKPROBE_SYMBOL(arch_rethook_fixup_return); + +static struct kprobe trampoline_p = { + .addr = (kprobe_opcode_t *) &arch_rethook_trampoline, + .pre_handler = trampoline_rethook_handler +}; + +/* rethook initializer */ +int __init arch_init_kprobes(void) +{ + return register_kprobe(&trampoline_p); +} diff --git a/arch/powerpc/kernel/secvar-sysfs.c b/arch/powerpc/kernel/secvar-sysfs.c index eb3c053f323f..fbeb1cbac01b 100644 --- a/arch/powerpc/kernel/secvar-sysfs.c +++ b/arch/powerpc/kernel/secvar-sysfs.c @@ -125,7 +125,7 @@ static const struct attribute_group secvar_attr_group = { }; __ATTRIBUTE_GROUPS(secvar_attr); -static struct kobj_type secvar_ktype = { +static const struct kobj_type secvar_ktype = { .sysfs_ops = &kobj_sysfs_ops, .default_groups = secvar_attr_groups, }; diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index 4bd2f87616ba..943430077375 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -959,6 +959,7 @@ void __init setup_arch(char **cmdline_p) mem_topology_setup(); /* Set max_mapnr before paging_init() */ set_max_mapnr(max_pfn); + high_memory = (void *)__va(max_low_pfn * PAGE_SIZE); /* * Release secondary cpus out of their spinloops at 0x60 now that diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 46e6d2cd7a2d..4ab9b8cee77a 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -1166,7 +1166,7 @@ void __init smp_prepare_cpus(unsigned int max_cpus) cpu_smt_set_num_threads(num_threads, threads_per_core); } -void smp_prepare_boot_cpu(void) +void __init smp_prepare_boot_cpu(void) { BUG_ON(smp_processor_id() != boot_cpuid); #ifdef CONFIG_PPC64 diff --git a/arch/powerpc/kernel/stacktrace.c b/arch/powerpc/kernel/stacktrace.c index e6a958a5da27..90882b5175cd 100644 --- a/arch/powerpc/kernel/stacktrace.c +++ b/arch/powerpc/kernel/stacktrace.c @@ -21,6 +21,7 @@ #include <asm/processor.h> #include <linux/ftrace.h> #include <asm/kprobes.h> +#include <linux/rethook.h> #include <asm/paca.h> @@ -133,12 +134,13 @@ int __no_sanitize_address arch_stack_walk_reliable(stack_trace_consume_fn consum * arch-dependent code, they are generic. */ ip = ftrace_graph_ret_addr(task, &graph_idx, ip, stack); -#ifdef CONFIG_KPROBES + /* * Mark stacktraces with kretprobed functions on them * as unreliable. */ - if (ip == (unsigned long)__kretprobe_trampoline) +#ifdef CONFIG_RETHOOK + if (ip == (unsigned long)arch_rethook_trampoline) return -EINVAL; #endif diff --git a/arch/powerpc/kernel/static_call.c b/arch/powerpc/kernel/static_call.c index 863a7aa24650..1502b7e439ca 100644 --- a/arch/powerpc/kernel/static_call.c +++ b/arch/powerpc/kernel/static_call.c @@ -17,7 +17,7 @@ void arch_static_call_transform(void *site, void *tramp, void *func, bool tail) mutex_lock(&text_mutex); if (func && !is_short) { - err = patch_instruction(tramp + PPC_SCT_DATA, ppc_inst(target)); + err = patch_ulong(tramp + PPC_SCT_DATA, target); if (err) goto out; } diff --git a/arch/powerpc/kernel/syscall.c b/arch/powerpc/kernel/syscall.c index f6f868e817e6..be159ad4b77b 100644 --- a/arch/powerpc/kernel/syscall.c +++ b/arch/powerpc/kernel/syscall.c @@ -27,7 +27,7 @@ notrace long system_call_exception(struct pt_regs *regs, unsigned long r0) trace_hardirqs_off(); /* finish reconciling */ - CT_WARN_ON(ct_state() == CONTEXT_KERNEL); + CT_WARN_ON(ct_state() == CT_STATE_KERNEL); user_exit_irqoff(); BUG_ON(regs_is_unrecoverable(regs)); diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index 28d6472c380a..edf5cabe5dfd 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -121,7 +121,7 @@ static void pmac_backlight_unblank(void) props = &pmac_backlight->props; props->brightness = props->max_brightness; - props->power = FB_BLANK_UNBLANK; + props->power = BACKLIGHT_POWER_ON; backlight_update_status(pmac_backlight); } mutex_unlock(&pmac_backlight_mutex); diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c index 7a2ff9010f17..ee4b9d676cff 100644 --- a/arch/powerpc/kernel/vdso.c +++ b/arch/powerpc/kernel/vdso.c @@ -81,6 +81,21 @@ static int vdso64_mremap(const struct vm_special_mapping *sm, struct vm_area_str return vdso_mremap(sm, new_vma, &vdso64_end - &vdso64_start); } +static void vdso_close(const struct vm_special_mapping *sm, struct vm_area_struct *vma) +{ + struct mm_struct *mm = vma->vm_mm; + + /* + * close() is called for munmap() but also for mremap(). In the mremap() + * case the vdso pointer has already been updated by the mremap() hook + * above, so it must not be set to NULL here. + */ + if (vma->vm_start != (unsigned long)mm->context.vdso) + return; + + mm->context.vdso = NULL; +} + static vm_fault_t vvar_fault(const struct vm_special_mapping *sm, struct vm_area_struct *vma, struct vm_fault *vmf); @@ -92,11 +107,13 @@ static struct vm_special_mapping vvar_spec __ro_after_init = { static struct vm_special_mapping vdso32_spec __ro_after_init = { .name = "[vdso]", .mremap = vdso32_mremap, + .close = vdso_close, }; static struct vm_special_mapping vdso64_spec __ro_after_init = { .name = "[vdso]", .mremap = vdso64_mremap, + .close = vdso_close, }; #ifdef CONFIG_TIME_NS @@ -197,13 +214,6 @@ static int __arch_setup_additional_pages(struct linux_binprm *bprm, int uses_int /* Add required alignment. */ vdso_base = ALIGN(vdso_base, VDSO_ALIGNMENT); - /* - * Put vDSO base into mm struct. We need to do this before calling - * install_special_mapping or the perf counter mmap tracking code - * will fail to recognise it as a vDSO. - */ - mm->context.vdso = (void __user *)vdso_base + vvar_size; - vma = _install_special_mapping(mm, vdso_base, vvar_size, VM_READ | VM_MAYREAD | VM_IO | VM_DONTDUMP | VM_PFNMAP, &vvar_spec); @@ -223,10 +233,15 @@ static int __arch_setup_additional_pages(struct linux_binprm *bprm, int uses_int vma = _install_special_mapping(mm, vdso_base + vvar_size, vdso_size, VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC, vdso_spec); - if (IS_ERR(vma)) + if (IS_ERR(vma)) { do_munmap(mm, vdso_base, vvar_size, NULL); + return PTR_ERR(vma); + } + + // Now that the mappings are in place, set the mm VDSO pointer + mm->context.vdso = (void __user *)vdso_base + vvar_size; - return PTR_ERR_OR_ZERO(vma); + return 0; } int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) @@ -240,8 +255,6 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) return -EINTR; rc = __arch_setup_additional_pages(bprm, uses_interp); - if (rc) - mm->context.vdso = NULL; mmap_write_unlock(mm); return rc; diff --git a/arch/powerpc/kernel/vdso/Makefile b/arch/powerpc/kernel/vdso/Makefile index 1425b6edc66b..56fb1633529a 100644 --- a/arch/powerpc/kernel/vdso/Makefile +++ b/arch/powerpc/kernel/vdso/Makefile @@ -8,30 +8,21 @@ include $(srctree)/lib/vdso/Makefile obj-vdso32 = sigtramp32-32.o gettimeofday-32.o datapage-32.o cacheflush-32.o note-32.o getcpu-32.o obj-vdso64 = sigtramp64-64.o gettimeofday-64.o datapage-64.o cacheflush-64.o note-64.o getcpu-64.o +obj-vdso32 += getrandom-32.o vgetrandom-chacha-32.o +obj-vdso64 += getrandom-64.o vgetrandom-chacha-64.o + ifneq ($(c-gettimeofday-y),) CFLAGS_vgettimeofday-32.o += -include $(c-gettimeofday-y) - CFLAGS_vgettimeofday-32.o += $(DISABLE_LATENT_ENTROPY_PLUGIN) - CFLAGS_vgettimeofday-32.o += $(call cc-option, -fno-stack-protector) - CFLAGS_vgettimeofday-32.o += -DDISABLE_BRANCH_PROFILING - CFLAGS_vgettimeofday-32.o += -ffreestanding -fasynchronous-unwind-tables - CFLAGS_REMOVE_vgettimeofday-32.o = $(CC_FLAGS_FTRACE) - CFLAGS_REMOVE_vgettimeofday-32.o += -mcmodel=medium -mabi=elfv1 -mabi=elfv2 -mcall-aixdesc - # This flag is supported by clang for 64-bit but not 32-bit so it will cause - # an unused command line flag warning for this file. - ifdef CONFIG_CC_IS_CLANG - CFLAGS_REMOVE_vgettimeofday-32.o += -fno-stack-clash-protection - endif - CFLAGS_vgettimeofday-64.o += -include $(c-gettimeofday-y) - CFLAGS_vgettimeofday-64.o += $(DISABLE_LATENT_ENTROPY_PLUGIN) - CFLAGS_vgettimeofday-64.o += $(call cc-option, -fno-stack-protector) - CFLAGS_vgettimeofday-64.o += -DDISABLE_BRANCH_PROFILING - CFLAGS_vgettimeofday-64.o += -ffreestanding -fasynchronous-unwind-tables - CFLAGS_REMOVE_vgettimeofday-64.o = $(CC_FLAGS_FTRACE) # Go prior to 1.16.x assumes r30 is not clobbered by any VDSO code. That used to be true # by accident when the VDSO was hand-written asm code, but may not be now that the VDSO is # compiler generated. To avoid breaking Go tell GCC not to use r30. Impact on code # generation is minimal, it will just use r29 instead. - CFLAGS_vgettimeofday-64.o += $(call cc-option, -ffixed-r30) + CFLAGS_vgettimeofday-64.o += -include $(c-gettimeofday-y) $(call cc-option, -ffixed-r30) +endif + +ifneq ($(c-getrandom-y),) + CFLAGS_vgetrandom-32.o += -include $(c-getrandom-y) + CFLAGS_vgetrandom-64.o += -include $(c-getrandom-y) $(call cc-option, -ffixed-r30) endif # Build rules @@ -42,12 +33,18 @@ else VDSOCC := $(CC) endif -targets := $(obj-vdso32) vdso32.so.dbg vgettimeofday-32.o +targets := $(obj-vdso32) vdso32.so.dbg vgettimeofday-32.o vgetrandom-32.o +targets += crtsavres-32.o obj-vdso32 := $(addprefix $(obj)/, $(obj-vdso32)) -targets += $(obj-vdso64) vdso64.so.dbg vgettimeofday-64.o +targets += $(obj-vdso64) vdso64.so.dbg vgettimeofday-64.o vgetrandom-64.o obj-vdso64 := $(addprefix $(obj)/, $(obj-vdso64)) -ccflags-y := -fno-common -fno-builtin +ccflags-y := -fno-common -fno-builtin -DBUILD_VDSO +ccflags-y += $(DISABLE_LATENT_ENTROPY_PLUGIN) +ccflags-y += $(call cc-option, -fno-stack-protector) +ccflags-y += -DDISABLE_BRANCH_PROFILING +ccflags-y += -ffreestanding -fasynchronous-unwind-tables +ccflags-remove-y := $(CC_FLAGS_FTRACE) ldflags-y := -Wl,--hash-style=both -nostdlib -shared -z noexecstack $(CLANG_FLAGS) ldflags-$(CONFIG_LD_IS_LLD) += $(call cc-option,--ld-path=$(LD),-fuse-ld=lld) ldflags-$(CONFIG_LD_ORPHAN_WARN) += -Wl,--orphan-handling=$(CONFIG_LD_ORPHAN_WARN_LEVEL) @@ -56,6 +53,12 @@ ldflags-$(CONFIG_LD_ORPHAN_WARN) += -Wl,--orphan-handling=$(CONFIG_LD_ORPHAN_WAR ldflags-y += $(filter-out $(CC_AUTO_VAR_INIT_ZERO_ENABLER) $(CC_FLAGS_FTRACE) -Wa$(comma)%, $(KBUILD_CFLAGS)) CC32FLAGS := -m32 +CC32FLAGSREMOVE := -mcmodel=medium -mabi=elfv1 -mabi=elfv2 -mcall-aixdesc + # This flag is supported by clang for 64-bit but not 32-bit so it will cause + # an unused command line flag warning for this file. +ifdef CONFIG_CC_IS_CLANG +CC32FLAGSREMOVE += -fno-stack-clash-protection +endif LD32FLAGS := -Wl,-soname=linux-vdso32.so.1 AS32FLAGS := -D__VDSO32__ @@ -68,20 +71,26 @@ targets += vdso64.lds CPPFLAGS_vdso64.lds += -P -C # link rule for the .so file, .lds has to be first -$(obj)/vdso32.so.dbg: $(obj)/vdso32.lds $(obj-vdso32) $(obj)/vgettimeofday-32.o FORCE +$(obj)/vdso32.so.dbg: $(obj)/vdso32.lds $(obj-vdso32) $(obj)/vgettimeofday-32.o $(obj)/vgetrandom-32.o $(obj)/crtsavres-32.o FORCE $(call if_changed,vdso32ld_and_check) -$(obj)/vdso64.so.dbg: $(obj)/vdso64.lds $(obj-vdso64) $(obj)/vgettimeofday-64.o FORCE +$(obj)/vdso64.so.dbg: $(obj)/vdso64.lds $(obj-vdso64) $(obj)/vgettimeofday-64.o $(obj)/vgetrandom-64.o FORCE $(call if_changed,vdso64ld_and_check) # assembly rules for the .S files $(obj-vdso32): %-32.o: %.S FORCE $(call if_changed_dep,vdso32as) +$(obj)/crtsavres-32.o: %-32.o: $(srctree)/arch/powerpc/lib/crtsavres.S FORCE + $(call if_changed_dep,vdso32as) $(obj)/vgettimeofday-32.o: %-32.o: %.c FORCE $(call if_changed_dep,vdso32cc) +$(obj)/vgetrandom-32.o: %-32.o: %.c FORCE + $(call if_changed_dep,vdso32cc) $(obj-vdso64): %-64.o: %.S FORCE $(call if_changed_dep,vdso64as) $(obj)/vgettimeofday-64.o: %-64.o: %.c FORCE $(call if_changed_dep,cc_o_c) +$(obj)/vgetrandom-64.o: %-64.o: %.c FORCE + $(call if_changed_dep,cc_o_c) # Generate VDSO offsets using helper script gen-vdso32sym := $(src)/gen_vdso32_offsets.sh @@ -102,7 +111,7 @@ quiet_cmd_vdso32ld_and_check = VDSO32L $@ quiet_cmd_vdso32as = VDSO32A $@ cmd_vdso32as = $(VDSOCC) $(a_flags) $(CC32FLAGS) $(AS32FLAGS) -c -o $@ $< quiet_cmd_vdso32cc = VDSO32C $@ - cmd_vdso32cc = $(VDSOCC) $(c_flags) $(CC32FLAGS) -c -o $@ $< + cmd_vdso32cc = $(VDSOCC) $(filter-out $(CC32FLAGSREMOVE), $(c_flags)) $(CC32FLAGS) -c -o $@ $< quiet_cmd_vdso64ld_and_check = VDSO64L $@ cmd_vdso64ld_and_check = $(VDSOCC) $(ldflags-y) $(LD64FLAGS) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^); $(cmd_vdso_check) diff --git a/arch/powerpc/kernel/vdso/cacheflush.S b/arch/powerpc/kernel/vdso/cacheflush.S index 0085ae464dac..3b2479bd2f9a 100644 --- a/arch/powerpc/kernel/vdso/cacheflush.S +++ b/arch/powerpc/kernel/vdso/cacheflush.S @@ -30,7 +30,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE) #ifdef CONFIG_PPC64 mflr r12 .cfi_register lr,r12 - get_datapage r10 + get_realdatapage r10, r11 mtlr r12 .cfi_restore lr #endif diff --git a/arch/powerpc/kernel/vdso/datapage.S b/arch/powerpc/kernel/vdso/datapage.S index db8e167f0166..2b19b6201a33 100644 --- a/arch/powerpc/kernel/vdso/datapage.S +++ b/arch/powerpc/kernel/vdso/datapage.S @@ -28,7 +28,7 @@ V_FUNCTION_BEGIN(__kernel_get_syscall_map) mflr r12 .cfi_register lr,r12 mr. r4,r3 - get_datapage r3 + get_realdatapage r3, r11 mtlr r12 #ifdef __powerpc64__ addi r3,r3,CFG_SYSCALL_MAP64 @@ -52,7 +52,7 @@ V_FUNCTION_BEGIN(__kernel_get_tbfreq) .cfi_startproc mflr r12 .cfi_register lr,r12 - get_datapage r3 + get_realdatapage r3, r11 #ifndef __powerpc64__ lwz r4,(CFG_TB_TICKS_PER_SEC + 4)(r3) #endif diff --git a/arch/powerpc/kernel/vdso/getrandom.S b/arch/powerpc/kernel/vdso/getrandom.S new file mode 100644 index 000000000000..f3bbf931931c --- /dev/null +++ b/arch/powerpc/kernel/vdso/getrandom.S @@ -0,0 +1,58 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Userland implementation of getrandom() for processes + * for use in the vDSO + * + * Copyright (C) 2024 Christophe Leroy <[email protected]>, CS GROUP France + */ +#include <asm/processor.h> +#include <asm/ppc_asm.h> +#include <asm/vdso.h> +#include <asm/vdso_datapage.h> +#include <asm/asm-offsets.h> +#include <asm/unistd.h> + +/* + * The macro sets two stack frames, one for the caller and one for the callee + * because there are no requirement for the caller to set a stack frame when + * calling VDSO so it may have omitted to set one, especially on PPC64 + */ + +.macro cvdso_call funct + .cfi_startproc + PPC_STLU r1, -PPC_MIN_STKFRM(r1) + .cfi_adjust_cfa_offset PPC_MIN_STKFRM + mflr r0 + PPC_STLU r1, -PPC_MIN_STKFRM(r1) + .cfi_adjust_cfa_offset PPC_MIN_STKFRM + PPC_STL r0, PPC_MIN_STKFRM + PPC_LR_STKOFF(r1) + .cfi_rel_offset lr, PPC_MIN_STKFRM + PPC_LR_STKOFF +#ifdef __powerpc64__ + PPC_STL r2, PPC_MIN_STKFRM + STK_GOT(r1) + .cfi_rel_offset r2, PPC_MIN_STKFRM + STK_GOT +#endif + get_realdatapage r8, r11 + addi r8, r8, VDSO_RNG_DATA_OFFSET + bl CFUNC(DOTSYM(\funct)) + PPC_LL r0, PPC_MIN_STKFRM + PPC_LR_STKOFF(r1) +#ifdef __powerpc64__ + PPC_LL r2, PPC_MIN_STKFRM + STK_GOT(r1) + .cfi_restore r2 +#endif + cmpwi r3, 0 + mtlr r0 + addi r1, r1, 2 * PPC_MIN_STKFRM + .cfi_restore lr + .cfi_def_cfa_offset 0 + crclr so + bgelr+ + crset so + neg r3, r3 + blr + .cfi_endproc +.endm + + .text +V_FUNCTION_BEGIN(__kernel_getrandom) + cvdso_call __c_kernel_getrandom +V_FUNCTION_END(__kernel_getrandom) diff --git a/arch/powerpc/kernel/vdso/gettimeofday.S b/arch/powerpc/kernel/vdso/gettimeofday.S index 48fc6658053a..5540d7021fa2 100644 --- a/arch/powerpc/kernel/vdso/gettimeofday.S +++ b/arch/powerpc/kernel/vdso/gettimeofday.S @@ -38,11 +38,7 @@ .else addi r4, r5, VDSO_DATA_OFFSET .endif -#ifdef __powerpc64__ bl CFUNC(DOTSYM(\funct)) -#else - bl \funct -#endif PPC_LL r0, PPC_MIN_STKFRM + PPC_LR_STKOFF(r1) #ifdef __powerpc64__ PPC_LL r2, PPC_MIN_STKFRM + STK_GOT(r1) @@ -118,16 +114,3 @@ V_FUNCTION_END(__kernel_clock_getres) V_FUNCTION_BEGIN(__kernel_time) cvdso_call __c_kernel_time call_time=1 V_FUNCTION_END(__kernel_time) - -/* Routines for restoring integer registers, called by the compiler. */ -/* Called with r11 pointing to the stack header word of the caller of the */ -/* function, just beyond the end of the integer restore area. */ -#ifndef __powerpc64__ -_GLOBAL(_restgpr_31_x) -_GLOBAL(_rest32gpr_31_x) - lwz r0,4(r11) - lwz r31,-4(r11) - mtlr r0 - mr r1,r11 - blr -#endif diff --git a/arch/powerpc/kernel/vdso/vdso32.lds.S b/arch/powerpc/kernel/vdso/vdso32.lds.S index 426e1ccc6971..7b41d5d256e8 100644 --- a/arch/powerpc/kernel/vdso/vdso32.lds.S +++ b/arch/powerpc/kernel/vdso/vdso32.lds.S @@ -74,6 +74,8 @@ SECTIONS .got : { *(.got) } :text .plt : { *(.plt) } + .rela.dyn : { *(.rela .rela*) } + _end = .; __end = .; PROVIDE(end = .); @@ -87,7 +89,7 @@ SECTIONS *(.branch_lt) *(.data .data.* .gnu.linkonce.d.* .sdata*) *(.bss .sbss .dynbss .dynsbss) - *(.got1 .glink .iplt .rela*) + *(.got1 .glink .iplt) } } @@ -128,6 +130,7 @@ VERSION #if defined(CONFIG_PPC64) || !defined(CONFIG_SMP) __kernel_getcpu; #endif + __kernel_getrandom; local: *; }; diff --git a/arch/powerpc/kernel/vdso/vdso64.lds.S b/arch/powerpc/kernel/vdso/vdso64.lds.S index bda6c8cdd459..9481e4b892ed 100644 --- a/arch/powerpc/kernel/vdso/vdso64.lds.S +++ b/arch/powerpc/kernel/vdso/vdso64.lds.S @@ -69,7 +69,7 @@ SECTIONS .eh_frame_hdr : { *(.eh_frame_hdr) } :text :eh_frame_hdr .eh_frame : { KEEP (*(.eh_frame)) } :text .gcc_except_table : { *(.gcc_except_table) } - .rela.dyn ALIGN(8) : { *(.rela.dyn) } + .rela.dyn ALIGN(8) : { *(.rela .rela*) } .got ALIGN(8) : { *(.got .toc) } @@ -86,7 +86,7 @@ SECTIONS *(.data .data.* .gnu.linkonce.d.* .sdata*) *(.bss .sbss .dynbss .dynsbss) *(.opd) - *(.glink .iplt .plt .rela*) + *(.glink .iplt .plt) } } @@ -123,6 +123,7 @@ VERSION __kernel_sigtramp_rt64; __kernel_getcpu; __kernel_time; + __kernel_getrandom; local: *; }; diff --git a/arch/powerpc/kernel/vdso/vgetrandom-chacha.S b/arch/powerpc/kernel/vdso/vgetrandom-chacha.S new file mode 100644 index 000000000000..7f9061a9e8b4 --- /dev/null +++ b/arch/powerpc/kernel/vdso/vgetrandom-chacha.S @@ -0,0 +1,365 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2024 Christophe Leroy <[email protected]>, CS GROUP France + */ + +#include <linux/linkage.h> + +#include <asm/ppc_asm.h> + +#define dst_bytes r3 +#define key r4 +#define counter r5 +#define nblocks r6 + +#define idx_r0 r0 +#define val4 r4 + +#define const0 0x61707865 +#define const1 0x3320646e +#define const2 0x79622d32 +#define const3 0x6b206574 + +#define key0 r5 +#define key1 r6 +#define key2 r7 +#define key3 r8 +#define key4 r9 +#define key5 r10 +#define key6 r11 +#define key7 r12 + +#define counter0 r14 +#define counter1 r15 + +#define state0 r16 +#define state1 r17 +#define state2 r18 +#define state3 r19 +#define state4 r20 +#define state5 r21 +#define state6 r22 +#define state7 r23 +#define state8 r24 +#define state9 r25 +#define state10 r26 +#define state11 r27 +#define state12 r28 +#define state13 r29 +#define state14 r30 +#define state15 r31 + +.macro quarterround4 a1 b1 c1 d1 a2 b2 c2 d2 a3 b3 c3 d3 a4 b4 c4 d4 + add \a1, \a1, \b1 + add \a2, \a2, \b2 + add \a3, \a3, \b3 + add \a4, \a4, \b4 + xor \d1, \d1, \a1 + xor \d2, \d2, \a2 + xor \d3, \d3, \a3 + xor \d4, \d4, \a4 + rotlwi \d1, \d1, 16 + rotlwi \d2, \d2, 16 + rotlwi \d3, \d3, 16 + rotlwi \d4, \d4, 16 + add \c1, \c1, \d1 + add \c2, \c2, \d2 + add \c3, \c3, \d3 + add \c4, \c4, \d4 + xor \b1, \b1, \c1 + xor \b2, \b2, \c2 + xor \b3, \b3, \c3 + xor \b4, \b4, \c4 + rotlwi \b1, \b1, 12 + rotlwi \b2, \b2, 12 + rotlwi \b3, \b3, 12 + rotlwi \b4, \b4, 12 + add \a1, \a1, \b1 + add \a2, \a2, \b2 + add \a3, \a3, \b3 + add \a4, \a4, \b4 + xor \d1, \d1, \a1 + xor \d2, \d2, \a2 + xor \d3, \d3, \a3 + xor \d4, \d4, \a4 + rotlwi \d1, \d1, 8 + rotlwi \d2, \d2, 8 + rotlwi \d3, \d3, 8 + rotlwi \d4, \d4, 8 + add \c1, \c1, \d1 + add \c2, \c2, \d2 + add \c3, \c3, \d3 + add \c4, \c4, \d4 + xor \b1, \b1, \c1 + xor \b2, \b2, \c2 + xor \b3, \b3, \c3 + xor \b4, \b4, \c4 + rotlwi \b1, \b1, 7 + rotlwi \b2, \b2, 7 + rotlwi \b3, \b3, 7 + rotlwi \b4, \b4, 7 +.endm + +#define QUARTERROUND4(a1,b1,c1,d1,a2,b2,c2,d2,a3,b3,c3,d3,a4,b4,c4,d4) \ + quarterround4 state##a1 state##b1 state##c1 state##d1 \ + state##a2 state##b2 state##c2 state##d2 \ + state##a3 state##b3 state##c3 state##d3 \ + state##a4 state##b4 state##c4 state##d4 + +/* + * Very basic 32 bits implementation of ChaCha20. Produces a given positive number + * of blocks of output with a nonce of 0, taking an input key and 8-byte + * counter. Importantly does not spill to the stack. Its arguments are: + * + * r3: output bytes + * r4: 32-byte key input + * r5: 8-byte counter input/output (saved on stack) + * r6: number of 64-byte blocks to write to output + * + * r0: counter of blocks (initialised with r6) + * r4: Value '4' after key has been read. + * r5-r12: key + * r14-r15: counter + * r16-r31: state + */ +SYM_FUNC_START(__arch_chacha20_blocks_nostack) +#ifdef __powerpc64__ + std counter, -216(r1) + + std r14, -144(r1) + std r15, -136(r1) + std r16, -128(r1) + std r17, -120(r1) + std r18, -112(r1) + std r19, -104(r1) + std r20, -96(r1) + std r21, -88(r1) + std r22, -80(r1) + std r23, -72(r1) + std r24, -64(r1) + std r25, -56(r1) + std r26, -48(r1) + std r27, -40(r1) + std r28, -32(r1) + std r29, -24(r1) + std r30, -16(r1) + std r31, -8(r1) +#else + stwu r1, -96(r1) + stw counter, 20(r1) +#ifdef __BIG_ENDIAN__ + stmw r14, 24(r1) +#else + stw r14, 24(r1) + stw r15, 28(r1) + stw r16, 32(r1) + stw r17, 36(r1) + stw r18, 40(r1) + stw r19, 44(r1) + stw r20, 48(r1) + stw r21, 52(r1) + stw r22, 56(r1) + stw r23, 60(r1) + stw r24, 64(r1) + stw r25, 68(r1) + stw r26, 72(r1) + stw r27, 76(r1) + stw r28, 80(r1) + stw r29, 84(r1) + stw r30, 88(r1) + stw r31, 92(r1) +#endif +#endif /* __powerpc64__ */ + + lwz counter0, 0(counter) + lwz counter1, 4(counter) +#ifdef __powerpc64__ + rldimi counter0, counter1, 32, 0 +#endif + mr idx_r0, nblocks + subi dst_bytes, dst_bytes, 4 + + lwz key0, 0(key) + lwz key1, 4(key) + lwz key2, 8(key) + lwz key3, 12(key) + lwz key4, 16(key) + lwz key5, 20(key) + lwz key6, 24(key) + lwz key7, 28(key) + + li val4, 4 +.Lblock: + li r31, 10 + + lis state0, const0@ha + lis state1, const1@ha + lis state2, const2@ha + lis state3, const3@ha + addi state0, state0, const0@l + addi state1, state1, const1@l + addi state2, state2, const2@l + addi state3, state3, const3@l + + mtctr r31 + + mr state4, key0 + mr state5, key1 + mr state6, key2 + mr state7, key3 + mr state8, key4 + mr state9, key5 + mr state10, key6 + mr state11, key7 + + mr state12, counter0 + mr state13, counter1 + + li state14, 0 + li state15, 0 + +.Lpermute: + QUARTERROUND4( 0, 4, 8,12, 1, 5, 9,13, 2, 6,10,14, 3, 7,11,15) + QUARTERROUND4( 0, 5,10,15, 1, 6,11,12, 2, 7, 8,13, 3, 4, 9,14) + + bdnz .Lpermute + + addis state0, state0, const0@ha + addis state1, state1, const1@ha + addis state2, state2, const2@ha + addis state3, state3, const3@ha + addi state0, state0, const0@l + addi state1, state1, const1@l + addi state2, state2, const2@l + addi state3, state3, const3@l + + add state4, state4, key0 + add state5, state5, key1 + add state6, state6, key2 + add state7, state7, key3 + add state8, state8, key4 + add state9, state9, key5 + add state10, state10, key6 + add state11, state11, key7 + + add state12, state12, counter0 + add state13, state13, counter1 + +#ifdef __BIG_ENDIAN__ + stwbrx state0, val4, dst_bytes + addi dst_bytes, dst_bytes, 8 + stwbrx state1, 0, dst_bytes + stwbrx state2, val4, dst_bytes + addi dst_bytes, dst_bytes, 8 + stwbrx state3, 0, dst_bytes + stwbrx state4, val4, dst_bytes + addi dst_bytes, dst_bytes, 8 + stwbrx state5, 0, dst_bytes + stwbrx state6, val4, dst_bytes + addi dst_bytes, dst_bytes, 8 + stwbrx state7, 0, dst_bytes + stwbrx state8, val4, dst_bytes + addi dst_bytes, dst_bytes, 8 + stwbrx state9, 0, dst_bytes + stwbrx state10, val4, dst_bytes + addi dst_bytes, dst_bytes, 8 + stwbrx state11, 0, dst_bytes + stwbrx state12, val4, dst_bytes + addi dst_bytes, dst_bytes, 8 + stwbrx state13, 0, dst_bytes + stwbrx state14, val4, dst_bytes + addi dst_bytes, dst_bytes, 8 + stwbrx state15, 0, dst_bytes +#else + stw state0, 4(dst_bytes) + stw state1, 8(dst_bytes) + stw state2, 12(dst_bytes) + stw state3, 16(dst_bytes) + stw state4, 20(dst_bytes) + stw state5, 24(dst_bytes) + stw state6, 28(dst_bytes) + stw state7, 32(dst_bytes) + stw state8, 36(dst_bytes) + stw state9, 40(dst_bytes) + stw state10, 44(dst_bytes) + stw state11, 48(dst_bytes) + stw state12, 52(dst_bytes) + stw state13, 56(dst_bytes) + stw state14, 60(dst_bytes) + stwu state15, 64(dst_bytes) +#endif + + subic. idx_r0, idx_r0, 1 /* subi. can't use r0 as source */ + +#ifdef __powerpc64__ + addi counter0, counter0, 1 + srdi counter1, counter0, 32 +#else + addic counter0, counter0, 1 + addze counter1, counter1 +#endif + + bne .Lblock + +#ifdef __powerpc64__ + ld counter, -216(r1) +#else + lwz counter, 20(r1) +#endif + stw counter0, 0(counter) + stw counter1, 4(counter) + + li r6, 0 + li r7, 0 + li r8, 0 + li r9, 0 + li r10, 0 + li r11, 0 + li r12, 0 + +#ifdef __powerpc64__ + ld r14, -144(r1) + ld r15, -136(r1) + ld r16, -128(r1) + ld r17, -120(r1) + ld r18, -112(r1) + ld r19, -104(r1) + ld r20, -96(r1) + ld r21, -88(r1) + ld r22, -80(r1) + ld r23, -72(r1) + ld r24, -64(r1) + ld r25, -56(r1) + ld r26, -48(r1) + ld r27, -40(r1) + ld r28, -32(r1) + ld r29, -24(r1) + ld r30, -16(r1) + ld r31, -8(r1) +#else +#ifdef __BIG_ENDIAN__ + lmw r14, 24(r1) +#else + lwz r14, 24(r1) + lwz r15, 28(r1) + lwz r16, 32(r1) + lwz r17, 36(r1) + lwz r18, 40(r1) + lwz r19, 44(r1) + lwz r20, 48(r1) + lwz r21, 52(r1) + lwz r22, 56(r1) + lwz r23, 60(r1) + lwz r24, 64(r1) + lwz r25, 68(r1) + lwz r26, 72(r1) + lwz r27, 76(r1) + lwz r28, 80(r1) + lwz r29, 84(r1) + lwz r30, 88(r1) + lwz r31, 92(r1) +#endif + addi r1, r1, 96 +#endif /* __powerpc64__ */ + blr +SYM_FUNC_END(__arch_chacha20_blocks_nostack) diff --git a/arch/powerpc/kernel/vdso/vgetrandom.c b/arch/powerpc/kernel/vdso/vgetrandom.c new file mode 100644 index 000000000000..5f855d45fb7b --- /dev/null +++ b/arch/powerpc/kernel/vdso/vgetrandom.c @@ -0,0 +1,14 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Powerpc userspace implementation of getrandom() + * + * Copyright (C) 2024 Christophe Leroy <[email protected]>, CS GROUP France + */ +#include <linux/time.h> +#include <linux/types.h> + +ssize_t __c_kernel_getrandom(void *buffer, size_t len, unsigned int flags, void *opaque_state, + size_t opaque_len, const struct vdso_rng_data *vd) +{ + return __cvdso_getrandom_data(vd, buffer, len, flags, opaque_state, opaque_len); +} |