From 94af3abf995b17f6a008b00152c94841242ec6c7 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Wed, 20 Nov 2013 22:15:02 +1100 Subject: powerpc: ELF2 binaries launched directly. No function descriptor, but we set r12 up and set TIF_RESTOREALL as it normally isn't restored on return from syscall. Signed-off-by: Rusty Russell Signed-off-by: Anton Blanchard Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/process.c | 50 ++++++++++++++++++++++++++++++------------- 1 file changed, 35 insertions(+), 15 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 75c2d100998..0650e18169f 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -1086,25 +1086,45 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp) regs->msr = MSR_USER; #else if (!is_32bit_task()) { - unsigned long entry, toc; + unsigned long entry; - /* start is a relocated pointer to the function descriptor for - * the elf _start routine. The first entry in the function - * descriptor is the entry address of _start and the second - * entry is the TOC value we need to use. - */ - __get_user(entry, (unsigned long __user *)start); - __get_user(toc, (unsigned long __user *)start+1); + if (is_elf2_task()) { + /* Look ma, no function descriptors! */ + entry = start; - /* Check whether the e_entry function descriptor entries - * need to be relocated before we can use them. - */ - if (load_addr != 0) { - entry += load_addr; - toc += load_addr; + /* + * Ulrich says: + * The latest iteration of the ABI requires that when + * calling a function (at its global entry point), + * the caller must ensure r12 holds the entry point + * address (so that the function can quickly + * establish addressability). + */ + regs->gpr[12] = start; + /* Make sure that's restored on entry to userspace. */ + set_thread_flag(TIF_RESTOREALL); + } else { + unsigned long toc; + + /* start is a relocated pointer to the function + * descriptor for the elf _start routine. The first + * entry in the function descriptor is the entry + * address of _start and the second entry is the TOC + * value we need to use. + */ + __get_user(entry, (unsigned long __user *)start); + __get_user(toc, (unsigned long __user *)start+1); + + /* Check whether the e_entry function descriptor entries + * need to be relocated before we can use them. + */ + if (load_addr != 0) { + entry += load_addr; + toc += load_addr; + } + regs->gpr[2] = toc; } regs->nip = entry; - regs->gpr[2] = toc; regs->msr = MSR_USER64; } else { regs->nip = start; -- cgit v1.2.3-70-g09d2 From d606b92aedb0542e60965e9058ab37efcebfaec6 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Wed, 20 Nov 2013 22:15:03 +1100 Subject: powerpc: ELF2 binaries signal handling For the ELFv2 ABI, the hander is the entry point, not a function descriptor. We also need to set up r12, and fortunately the fast_exception_return exit path restores r12 for us so nothing else is required. Signed-off-by: Rusty Russell Signed-off-by: Anton Blanchard Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/signal_64.c | 25 ++++++++++++++++--------- 1 file changed, 16 insertions(+), 9 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index b3c615764c9..e66f67b8b9e 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -701,12 +701,6 @@ badframe: int handle_rt_signal64(int signr, struct k_sigaction *ka, siginfo_t *info, sigset_t *set, struct pt_regs *regs) { - /* Handler is *really* a pointer to the function descriptor for - * the signal routine. The first entry in the function - * descriptor is the entry address of signal and the second - * entry is the TOC value we need to use. - */ - func_descr_t __user *funct_desc_ptr; struct rt_sigframe __user *frame; unsigned long newsp = 0; long err = 0; @@ -766,19 +760,32 @@ int handle_rt_signal64(int signr, struct k_sigaction *ka, siginfo_t *info, goto badframe; regs->link = (unsigned long) &frame->tramp[0]; } - funct_desc_ptr = (func_descr_t __user *) ka->sa.sa_handler; /* Allocate a dummy caller frame for the signal handler. */ newsp = ((unsigned long)frame) - __SIGNAL_FRAMESIZE; err |= put_user(regs->gpr[1], (unsigned long __user *)newsp); /* Set up "regs" so we "return" to the signal handler. */ - err |= get_user(regs->nip, &funct_desc_ptr->entry); + if (is_elf2_task()) { + regs->nip = (unsigned long) ka->sa.sa_handler; + regs->gpr[12] = regs->nip; + } else { + /* Handler is *really* a pointer to the function descriptor for + * the signal routine. The first entry in the function + * descriptor is the entry address of signal and the second + * entry is the TOC value we need to use. + */ + func_descr_t __user *funct_desc_ptr = + (func_descr_t __user *) ka->sa.sa_handler; + + err |= get_user(regs->nip, &funct_desc_ptr->entry); + err |= get_user(regs->gpr[2], &funct_desc_ptr->toc); + } + /* enter the signal handler in native-endian mode */ regs->msr &= ~MSR_LE; regs->msr |= (MSR_KERNEL & MSR_LE); regs->gpr[1] = newsp; - err |= get_user(regs->gpr[2], &funct_desc_ptr->toc); regs->gpr[3] = signr; regs->result = 0; if (ka->sa.sa_flags & SA_SIGINFO) { -- cgit v1.2.3-70-g09d2 From 280270828f108be56f0c486def58acabb070244f Mon Sep 17 00:00:00 2001 From: Ulrich Weigand Date: Thu, 21 Nov 2013 07:38:05 +1100 Subject: powerpc: Wrong DWARF CFI in the kernel vdso for little-endian / ELFv2 I've finally tracked down why my CR signal-unwind test case still fails on little-endian. The problem turned to be that the kernel installs a signal trampoline in the vDSO, and provides a DWARF CFI record for that trampoline. This CFI describes the save location for CR: rsave (70, 38*RSIZE + (RSIZE - CRSIZE)) which is correct for big-endian, but points to the wrong word on little-endian. This is wrong no matter which ABI. In addition, for the ELFv2 ABI, we should not only provide a CFI record for register 70 (cr2), but for all CR fields separately. Strictly speaking, I guess this would mean providing two separate vDSO images, one for ELFv1 processes and one for ELFv2 processes (or maybe playing some tricks with conditional DWARF expressions). However, having CFI records for the other CR fields in ELFv1 is not actually wrong, they just will be ignored. So it seems the simplest fix would be just to always provide CFI for all the fields. Signed-off-by: Ulrich Weigand Signed-off-by: Anton Blanchard Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/vdso64/sigtramp.S | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/vdso64/sigtramp.S b/arch/powerpc/kernel/vdso64/sigtramp.S index 45ea281e9a2..542c6f422e4 100644 --- a/arch/powerpc/kernel/vdso64/sigtramp.S +++ b/arch/powerpc/kernel/vdso64/sigtramp.S @@ -142,6 +142,13 @@ V_FUNCTION_END(__kernel_sigtramp_rt64) /* Size of CR reg in DWARF unwind info. */ #define CRSIZE 4 +/* Offset of CR reg within a full word. */ +#ifdef __LITTLE_ENDIAN__ +#define CROFF 0 +#else +#define CROFF (RSIZE - CRSIZE) +#endif + /* This is the offset of the VMX reg pointer. */ #define VREGS 48*RSIZE+33*8 @@ -181,7 +188,14 @@ V_FUNCTION_END(__kernel_sigtramp_rt64) rsave (31, 31*RSIZE); \ rsave (67, 32*RSIZE); /* ap, used as temp for nip */ \ rsave (65, 36*RSIZE); /* lr */ \ - rsave (70, 38*RSIZE + (RSIZE - CRSIZE)) /* cr */ + rsave (68, 38*RSIZE + CROFF); /* cr fields */ \ + rsave (69, 38*RSIZE + CROFF); \ + rsave (70, 38*RSIZE + CROFF); \ + rsave (71, 38*RSIZE + CROFF); \ + rsave (72, 38*RSIZE + CROFF); \ + rsave (73, 38*RSIZE + CROFF); \ + rsave (74, 38*RSIZE + CROFF); \ + rsave (75, 38*RSIZE + CROFF) /* Describe where the FP regs are saved. */ #define EH_FRAME_FP \ -- cgit v1.2.3-70-g09d2 From bf898ec5cbd33be11147743bee27b66b10cb2f85 Mon Sep 17 00:00:00 2001 From: Gavin Shan Date: Tue, 12 Nov 2013 14:49:21 +0800 Subject: powerpc/eeh: Enable PCI_COMMAND_MASTER for PCI bridges On PHB3, we will fail to fetch IODA tables without PCI_COMMAND_MASTER on PCI bridges. According to one experiment I had, the MSIx interrupts didn't raise from the adapter without the bit applied to all upstream PCI bridges including root port of the adapter. The patch forces to have that bit enabled accordingly. Signed-off-by: Gavin Shan CC: Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/eeh.c | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index 67130206534..4bd687d5e7a 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -686,6 +686,15 @@ void eeh_save_bars(struct eeh_dev *edev) for (i = 0; i < 16; i++) eeh_ops->read_config(dn, i * 4, 4, &edev->config_space[i]); + + /* + * For PCI bridges including root port, we need enable bus + * master explicitly. Otherwise, it can't fetch IODA table + * entries correctly. So we cache the bit in advance so that + * we can restore it after reset, either PHB range or PE range. + */ + if (edev->mode & EEH_DEV_BRIDGE) + edev->config_space[1] |= PCI_COMMAND_MASTER; } /** -- cgit v1.2.3-70-g09d2 From 0b5381a61821d1c074c76e01b27bf5f69cf2dd01 Mon Sep 17 00:00:00 2001 From: Gavin Shan Date: Tue, 12 Nov 2013 14:49:22 +0800 Subject: powerpc/eeh: More accurate log This clarifies in the log whether the error is a global PHB error or an individual PE being frozen. Signed-off-by: Gavin Shan Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/eeh_event.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/eeh_event.c b/arch/powerpc/kernel/eeh_event.c index d27c5afc90a..72d748b56c8 100644 --- a/arch/powerpc/kernel/eeh_event.c +++ b/arch/powerpc/kernel/eeh_event.c @@ -74,8 +74,13 @@ static int eeh_event_handler(void * dummy) pe = event->pe; if (pe) { eeh_pe_state_mark(pe, EEH_PE_RECOVERING); - pr_info("EEH: Detected PCI bus error on PHB#%d-PE#%x\n", - pe->phb->global_number, pe->addr); + if (pe->type & EEH_PE_PHB) + pr_info("EEH: Detected error on PHB#%d\n", + pe->phb->global_number); + else + pr_info("EEH: Detected PCI bus error on " + "PHB#%d-PE#%x\n", + pe->phb->global_number, pe->addr); eeh_handle_event(pe); eeh_pe_state_clear(pe, EEH_PE_RECOVERING); } else { -- cgit v1.2.3-70-g09d2 From c54006491dde7d1b8050c5542716b751be92ed80 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Fri, 15 Nov 2013 15:41:19 +1100 Subject: powerpc: Print DAR and DSISR on machine check oopses Machine check exceptions set DAR and DSISR, so print them in our oops output. Signed-off-by: Anton Blanchard Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/process.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 75c2d100998..37c4103a8cf 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -864,7 +864,7 @@ void show_regs(struct pt_regs * regs) trap = TRAP(regs); if ((regs->trap != 0xc00) && cpu_has_feature(CPU_FTR_CFAR)) printk("CFAR: "REG"\n", regs->orig_gpr3); - if (trap == 0x300 || trap == 0x600) + if (trap == 0x200 || trap == 0x300 || trap == 0x600) #if defined(CONFIG_4xx) || defined(CONFIG_BOOKE) printk("DEAR: "REG", ESR: "REG"\n", regs->dar, regs->dsisr); #else -- cgit v1.2.3-70-g09d2 From 9db8bcfd73d4a18c0b3428c30557ccce1171d0af Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Fri, 15 Nov 2013 15:48:38 +1100 Subject: powerpc: Remove a few lines of oops output We waste quite a few lines in our oops output: ... MSR: 8000000000009032 CR: 28044024 XER: 00000000 SOFTE: 0 CFAR: 0000000000009088 DAR: 000000000000001c, DSISR: 40000000 GPR00: c0000000000c74f0 c00000037cc1b010 c000000000d2bb30 0000000000000000 ... We can do a better job here and remove 3 lines: MSR: 8000000000009032 CR: 28044024 XER: 00000000 CFAR: 0000000000009088 DAR: 0000000000000010, DSISR: 40000000 SOFTE: 1 GPR00: c0000000000e3d10 c00000037cc2fda0 c000000000d2c3a8 0000000000000001 Also move PACATMSCRATCH up, it doesn't really belong in the stack trace section. Signed-off-by: Anton Blanchard Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/process.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 37c4103a8cf..373980ae52a 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -858,17 +858,20 @@ void show_regs(struct pt_regs * regs) printk("MSR: "REG" ", regs->msr); printbits(regs->msr, msr_bits); printk(" CR: %08lx XER: %08lx\n", regs->ccr, regs->xer); -#ifdef CONFIG_PPC64 - printk("SOFTE: %ld\n", regs->softe); -#endif trap = TRAP(regs); if ((regs->trap != 0xc00) && cpu_has_feature(CPU_FTR_CFAR)) - printk("CFAR: "REG"\n", regs->orig_gpr3); + printk("CFAR: "REG" ", regs->orig_gpr3); if (trap == 0x200 || trap == 0x300 || trap == 0x600) #if defined(CONFIG_4xx) || defined(CONFIG_BOOKE) - printk("DEAR: "REG", ESR: "REG"\n", regs->dar, regs->dsisr); + printk("DEAR: "REG" ESR: "REG" ", regs->dar, regs->dsisr); #else - printk("DAR: "REG", DSISR: %08lx\n", regs->dar, regs->dsisr); + printk("DAR: "REG" DSISR: %08lx ", regs->dar, regs->dsisr); +#endif +#ifdef CONFIG_PPC64 + printk("SOFTE: %ld ", regs->softe); +#endif +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + printk("\nPACATMSCRATCH: %016llx ", get_paca()->tm_scratch); #endif for (i = 0; i < 32; i++) { @@ -886,9 +889,6 @@ void show_regs(struct pt_regs * regs) */ printk("NIP ["REG"] %pS\n", regs->nip, (void *)regs->nip); printk("LR ["REG"] %pS\n", regs->link, (void *)regs->link); -#endif -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM - printk("PACATMSCRATCH [%llx]\n", get_paca()->tm_scratch); #endif show_stack(current, (unsigned long *) regs->gpr[1]); if (!user_mode(regs)) -- cgit v1.2.3-70-g09d2 From 84b073868b9d9e754ae48b828337633d1b386482 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Sun, 17 Nov 2013 11:39:05 +1100 Subject: powerpc/pseries: Duplicate dtl entries sometimes sent to userspace When reading from the dispatch trace log (dtl) userspace interface, I sometimes see duplicate entries. One example: # hexdump -C dtl.out 00000000 07 04 00 0c 00 00 48 44 00 00 00 00 00 00 00 00 00000010 00 0c a0 b4 16 83 6d 68 00 00 00 00 00 00 00 00 00000020 00 00 00 00 10 00 13 50 80 00 00 00 00 00 d0 32 00000030 07 04 00 0c 00 00 48 44 00 00 00 00 00 00 00 00 00000040 00 0c a0 b4 16 83 6d 68 00 00 00 00 00 00 00 00 00000050 00 00 00 00 10 00 13 50 80 00 00 00 00 00 d0 32 The problem is in scan_dispatch_log() where we call dtl_consumer() but bail out before incrementing the index. To fix this I moved dtl_consumer() after the timebase comparison. Signed-off-by: Anton Blanchard Cc: stable@vger.kernel.org Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/time.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index 192b051df97..b3b144121cc 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -213,8 +213,6 @@ static u64 scan_dispatch_log(u64 stop_tb) if (i == be64_to_cpu(vpa->dtl_idx)) return 0; while (i < be64_to_cpu(vpa->dtl_idx)) { - if (dtl_consumer) - dtl_consumer(dtl, i); dtb = be64_to_cpu(dtl->timebase); tb_delta = be32_to_cpu(dtl->enqueue_to_dispatch_time) + be32_to_cpu(dtl->ready_to_enqueue_time); @@ -227,6 +225,8 @@ static u64 scan_dispatch_log(u64 stop_tb) } if (dtb > stop_tb) break; + if (dtl_consumer) + dtl_consumer(dtl, i); stolen += tb_delta; ++i; ++dtl; -- cgit v1.2.3-70-g09d2 From 6d888d1ab0000dff8ea2901bcdf5d213f2a54e8b Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Mon, 18 Nov 2013 13:19:17 +1100 Subject: powerpc: Only print PACATMSCRATCH in oops when TM is active If TM is not active there is no need to print PACATMSCRATCH so we can save ourselves a line. Signed-off-by: Anton Blanchard Acked-by: Michael Neuling Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/process.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 373980ae52a..6cd50ac1221 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -871,7 +871,8 @@ void show_regs(struct pt_regs * regs) printk("SOFTE: %ld ", regs->softe); #endif #ifdef CONFIG_PPC_TRANSACTIONAL_MEM - printk("\nPACATMSCRATCH: %016llx ", get_paca()->tm_scratch); + if (MSR_TM_ACTIVE(regs->msr)) + printk("\nPACATMSCRATCH: %016llx ", get_paca()->tm_scratch); #endif for (i = 0; i < 32; i++) { -- cgit v1.2.3-70-g09d2 From c6102609289de268bcc6093e606483ea8bb35c84 Mon Sep 17 00:00:00 2001 From: Li Zhong Date: Tue, 19 Nov 2013 16:11:37 +0800 Subject: powerpc/vio: Fix a dma_mask issue of vio I encountered following issue: [ 0.283035] ibmvscsi 30000015: couldn't initialize event pool [ 5.688822] ibmvscsi: probe of 30000015 failed with error -1 which prevents the storage from being recognized, and the machine from booting. After some digging, it seems that it is caused by commit 4886c399da as dma_mask pointer in viodev->dev is not set, so in dma_set_mask_and_coherent(), dma_set_coherent_mask() is not called because dma_set_mask(), which is dma_set_mask_pSeriesLP() returned EIO. While before the commit, dma_set_coherent_mask() is always called. I tried to replace dma_set_mask_and_coherent() with dma_coerce_mask_and_coherent(), and the machine could boot again. Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/vio.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/vio.c b/arch/powerpc/kernel/vio.c index e7d0c88f621..76a64821f4a 100644 --- a/arch/powerpc/kernel/vio.c +++ b/arch/powerpc/kernel/vio.c @@ -1419,7 +1419,7 @@ struct vio_dev *vio_register_device_node(struct device_node *of_node) /* needed to ensure proper operation of coherent allocations * later, in case driver doesn't set it explicitly */ - dma_set_mask_and_coherent(&viodev->dev, DMA_BIT_MASK(64)); + dma_coerce_mask_and_coherent(&viodev->dev, DMA_BIT_MASK(64)); } /* register with generic device framework */ -- cgit v1.2.3-70-g09d2 From 3eb906c6b6c123513718e7742a96a4189f900382 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Wed, 20 Nov 2013 11:05:01 +1100 Subject: powerpc: Make cpu_to_chip_id() available when SMP=n Up until now we have only used cpu_to_chip_id() in the topology code, which is only used on SMP builds. However my recent commit a4da0d5 "Implement arch_get_random_long/int() for powernv" added a usage when SMP=n, breaking the build. Move cpu_to_chip_id() into prom.c so it is available for SMP=n builds. We would move the extern to prom.h, but that breaks the include in topology.h. Instead we leave it in smp.h, but move it out of the CONFIG_SMP #ifdef. We also need to include asm/smp.h in rng.c, because the linux version skips asm/smp.h on UP. What a mess. Signed-off-by: Michael Ellerman Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/smp.h | 2 +- arch/powerpc/kernel/prom.c | 20 ++++++++++++++++++++ arch/powerpc/kernel/smp.c | 16 ---------------- arch/powerpc/platforms/powernv/rng.c | 1 + 4 files changed, 22 insertions(+), 17 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h index 98da78e0c2c..084e0807db9 100644 --- a/arch/powerpc/include/asm/smp.h +++ b/arch/powerpc/include/asm/smp.h @@ -33,6 +33,7 @@ extern int boot_cpuid; extern int spinning_secondaries; extern void cpu_die(void); +extern int cpu_to_chip_id(int cpu); #ifdef CONFIG_SMP @@ -112,7 +113,6 @@ static inline struct cpumask *cpu_core_mask(int cpu) } extern int cpu_to_core_id(int cpu); -extern int cpu_to_chip_id(int cpu); /* Since OpenPIC has only 4 IPIs, we use slightly different message numbers. * diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index f3a47098fb8..fa0ad8aafbc 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -777,6 +777,26 @@ int of_get_ibm_chip_id(struct device_node *np) return -1; } +/** + * cpu_to_chip_id - Return the cpus chip-id + * @cpu: The logical cpu number. + * + * Return the value of the ibm,chip-id property corresponding to the given + * logical cpu number. If the chip-id can not be found, returns -1. + */ +int cpu_to_chip_id(int cpu) +{ + struct device_node *np; + + np = of_get_cpu_node(cpu, NULL); + if (!np) + return -1; + + of_node_put(np); + return of_get_ibm_chip_id(np); +} +EXPORT_SYMBOL(cpu_to_chip_id); + #ifdef CONFIG_PPC_PSERIES /* * Fix up the uninitialized fields in a new device node: diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 930cd8af350..a3b64f3bf9a 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -597,22 +597,6 @@ out: return id; } -/* Return the value of the chip-id property corresponding - * to the given logical cpu. - */ -int cpu_to_chip_id(int cpu) -{ - struct device_node *np; - - np = of_get_cpu_node(cpu, NULL); - if (!np) - return -1; - - of_node_put(np); - return of_get_ibm_chip_id(np); -} -EXPORT_SYMBOL(cpu_to_chip_id); - /* Helper routines for cpu to core mapping */ int cpu_core_index_of_thread(int cpu) { diff --git a/arch/powerpc/platforms/powernv/rng.c b/arch/powerpc/platforms/powernv/rng.c index 8844628915d..1cb160dc160 100644 --- a/arch/powerpc/platforms/powernv/rng.c +++ b/arch/powerpc/platforms/powernv/rng.c @@ -19,6 +19,7 @@ #include #include #include +#include struct powernv_rng { -- cgit v1.2.3-70-g09d2 From c13f20ac48328b05cd3b8c19e31ed6c132b44b42 Mon Sep 17 00:00:00 2001 From: Michael Neuling Date: Wed, 20 Nov 2013 16:18:54 +1100 Subject: powerpc/signals: Mark VSX not saved with small contexts The VSX MSR bit in the user context indicates if the context contains VSX state. Currently we set this when the process has touched VSX at any stage. Unfortunately, if the user has not provided enough space to save the VSX state, we can't save it but we currently still set the MSR VSX bit. This patch changes this to clear the MSR VSX bit when the user doesn't provide enough space. This indicates that there is no valid VSX state in the user context. This is needed to support get/set/make/swapcontext for applications that use VSX but only provide a small context. For example, getcontext in glibc provides a smaller context since the VSX registers don't need to be saved over the glibc function call. But since the program calling getcontext may have used VSX, the kernel currently says the VSX state is valid when it's not. If the returned context is then used in setcontext (ie. a small context without VSX but with MSR VSX set), the kernel will refuse the context. This situation has been reported by the glibc community. Based on patch from Carlos O'Donell. Tested-by: Haren Myneni Signed-off-by: Michael Neuling Cc: stable@vger.kernel.org Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/signal_32.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index 749778e0a69..1844298f5ea 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -457,7 +457,15 @@ static int save_user_regs(struct pt_regs *regs, struct mcontext __user *frame, if (copy_vsx_to_user(&frame->mc_vsregs, current)) return 1; msr |= MSR_VSX; - } + } else if (!ctx_has_vsx_region) + /* + * With a small context structure we can't hold the VSX + * registers, hence clear the MSR value to indicate the state + * was not saved. + */ + msr &= ~MSR_VSX; + + #endif /* CONFIG_VSX */ #ifdef CONFIG_SPE /* save spe registers */ -- cgit v1.2.3-70-g09d2 From ae2163be10ac6090e7aeed72591e2d7fabb1cdda Mon Sep 17 00:00:00 2001 From: LEROY Christophe Date: Fri, 22 Nov 2013 17:57:31 +0100 Subject: powerpc/8xx: mfspr SPRN_TBRx in lieu of mftb/mftbu is not supported Commit beb2dc0a7a84be003ce54e98b95d65cc66e6e536 breaks the MPC8xx which seems to not support using mfspr SPRN_TBRx instead of mftb/mftbu despite what is written in the reference manual. This patch reverts to the use of mftb/mftbu when CONFIG_8xx is selected. Signed-off-by: Christophe Leroy Signed-off-by: Scott Wood --- arch/powerpc/boot/util.S | 14 ++++++++++++++ arch/powerpc/include/asm/ppc_asm.h | 2 ++ arch/powerpc/include/asm/reg.h | 7 +++++++ arch/powerpc/include/asm/timex.h | 8 ++++++++ arch/powerpc/kernel/vdso32/gettimeofday.S | 6 ++++++ 5 files changed, 37 insertions(+) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/boot/util.S b/arch/powerpc/boot/util.S index 5143228e3e5..6636b1d7821 100644 --- a/arch/powerpc/boot/util.S +++ b/arch/powerpc/boot/util.S @@ -71,18 +71,32 @@ udelay: add r4,r4,r5 addi r4,r4,-1 divw r4,r4,r5 /* BUS ticks */ +#ifdef CONFIG_8xx +1: mftbu r5 + mftb r6 + mftbu r7 +#else 1: mfspr r5, SPRN_TBRU mfspr r6, SPRN_TBRL mfspr r7, SPRN_TBRU +#endif cmpw 0,r5,r7 bne 1b /* Get [synced] base time */ addc r9,r6,r4 /* Compute end time */ addze r8,r5 +#ifdef CONFIG_8xx +2: mftbu r5 +#else 2: mfspr r5, SPRN_TBRU +#endif cmpw 0,r5,r8 blt 2b bgt 3f +#ifdef CONFIG_8xx + mftb r6 +#else mfspr r6, SPRN_TBRL +#endif cmpw 0,r6,r9 blt 2b 3: blr diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h index 3c1acc31a09..f595b98079e 100644 --- a/arch/powerpc/include/asm/ppc_asm.h +++ b/arch/powerpc/include/asm/ppc_asm.h @@ -366,6 +366,8 @@ BEGIN_FTR_SECTION_NESTED(96); \ cmpwi dest,0; \ beq- 90b; \ END_FTR_SECTION_NESTED(CPU_FTR_CELL_TB_BUG, CPU_FTR_CELL_TB_BUG, 96) +#elif defined(CONFIG_8xx) +#define MFTB(dest) mftb dest #else #define MFTB(dest) mfspr dest, SPRN_TBRL #endif diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index 5c45787d551..fa8388ed94c 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -1174,12 +1174,19 @@ #else /* __powerpc64__ */ +#if defined(CONFIG_8xx) +#define mftbl() ({unsigned long rval; \ + asm volatile("mftbl %0" : "=r" (rval)); rval;}) +#define mftbu() ({unsigned long rval; \ + asm volatile("mftbu %0" : "=r" (rval)); rval;}) +#else #define mftbl() ({unsigned long rval; \ asm volatile("mfspr %0, %1" : "=r" (rval) : \ "i" (SPRN_TBRL)); rval;}) #define mftbu() ({unsigned long rval; \ asm volatile("mfspr %0, %1" : "=r" (rval) : \ "i" (SPRN_TBRU)); rval;}) +#endif #endif /* !__powerpc64__ */ #define mttbl(v) asm volatile("mttbl %0":: "r"(v)) diff --git a/arch/powerpc/include/asm/timex.h b/arch/powerpc/include/asm/timex.h index 18908caa1f3..2cf846edb3f 100644 --- a/arch/powerpc/include/asm/timex.h +++ b/arch/powerpc/include/asm/timex.h @@ -29,7 +29,11 @@ static inline cycles_t get_cycles(void) ret = 0; __asm__ __volatile__( +#ifdef CONFIG_8xx + "97: mftb %0\n" +#else "97: mfspr %0, %2\n" +#endif "99:\n" ".section __ftr_fixup,\"a\"\n" ".align 2\n" @@ -41,7 +45,11 @@ static inline cycles_t get_cycles(void) " .long 0\n" " .long 0\n" ".previous" +#ifdef CONFIG_8xx + : "=r" (ret) : "i" (CPU_FTR_601)); +#else : "=r" (ret) : "i" (CPU_FTR_601), "i" (SPRN_TBRL)); +#endif return ret; #endif } diff --git a/arch/powerpc/kernel/vdso32/gettimeofday.S b/arch/powerpc/kernel/vdso32/gettimeofday.S index 6b1f2a6d551..6b2b69616e7 100644 --- a/arch/powerpc/kernel/vdso32/gettimeofday.S +++ b/arch/powerpc/kernel/vdso32/gettimeofday.S @@ -232,9 +232,15 @@ __do_get_tspec: lwz r6,(CFG_TB_ORIG_STAMP+4)(r9) /* Get a stable TB value */ +#ifdef CONFIG_8xx +2: mftbu r3 + mftbl r4 + mftbu r0 +#else 2: mfspr r3, SPRN_TBRU mfspr r4, SPRN_TBRL mfspr r0, SPRN_TBRU +#endif cmplw cr0,r3,r0 bne- 2b -- cgit v1.2.3-70-g09d2 From 8ff812719ac73ef9428b788e210221c8d87b2a8c Mon Sep 17 00:00:00 2001 From: Hari Bathini Date: Fri, 15 Nov 2013 23:01:32 +0530 Subject: powerpc/kdump: Adding symbols in vmcoreinfo to facilitate dump filtering When CONFIG_SPARSEMEM_VMEMMAP option is used in kernel, makedumpfile fails to filter vmcore dump as it fails to do vmemmap translations. So far dump filtering on ppc64 never had to deal with vmemmap addresses seperately as vmemmap regions where mapped in zone normal. But with the inclusion of CONFIG_SPARSEMEM_VMEMMAP config option in kernel, this vmemmap address translation support becomes necessary for dump filtering. For vmemmap adress translation, few kernel symbols are needed by dump filtering tool. This patch adds those symbols to vmcoreinfo, which a dump filtering tool can use for filtering the kernel dump. Tested this changes successfully with makedumpfile tool that supports vmemmap to physical address translation outside zone normal. [ Removed unneeded #ifdef as suggested by Michael Ellerman --BenH ] Signed-off-by: Hari Bathini Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/pgalloc-64.h | 1 + arch/powerpc/kernel/machine_kexec.c | 12 ++++++++++++ 2 files changed, 13 insertions(+) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/include/asm/pgalloc-64.h b/arch/powerpc/include/asm/pgalloc-64.h index 16cb92d215d..694012877bf 100644 --- a/arch/powerpc/include/asm/pgalloc-64.h +++ b/arch/powerpc/include/asm/pgalloc-64.h @@ -16,6 +16,7 @@ struct vmemmap_backing { unsigned long phys; unsigned long virt_addr; }; +extern struct vmemmap_backing *vmemmap_list; /* * Functions that deal with pagetables that could be at any level of diff --git a/arch/powerpc/kernel/machine_kexec.c b/arch/powerpc/kernel/machine_kexec.c index e1ec57e87b3..88a7fb458df 100644 --- a/arch/powerpc/kernel/machine_kexec.c +++ b/arch/powerpc/kernel/machine_kexec.c @@ -18,6 +18,7 @@ #include #include +#include #include #include @@ -75,6 +76,17 @@ void arch_crash_save_vmcoreinfo(void) #ifndef CONFIG_NEED_MULTIPLE_NODES VMCOREINFO_SYMBOL(contig_page_data); #endif +#if defined(CONFIG_PPC64) && defined(CONFIG_SPARSEMEM_VMEMMAP) + VMCOREINFO_SYMBOL(vmemmap_list); + VMCOREINFO_SYMBOL(mmu_vmemmap_psize); + VMCOREINFO_SYMBOL(mmu_psize_defs); + VMCOREINFO_STRUCT_SIZE(vmemmap_backing); + VMCOREINFO_OFFSET(vmemmap_backing, list); + VMCOREINFO_OFFSET(vmemmap_backing, phys); + VMCOREINFO_OFFSET(vmemmap_backing, virt_addr); + VMCOREINFO_STRUCT_SIZE(mmu_psize_def); + VMCOREINFO_OFFSET(mmu_psize_def, shift); +#endif } /* -- cgit v1.2.3-70-g09d2 From ec67ad82814bee92251fd963bf01c7a173856555 Mon Sep 17 00:00:00 2001 From: Michael Neuling Date: Mon, 25 Nov 2013 11:12:20 +1100 Subject: powerpc/signals: Improved mark VSX not saved with small contexts fix In a recent patch: commit c13f20ac48328b05cd3b8c19e31ed6c132b44b42 Author: Michael Neuling powerpc/signals: Mark VSX not saved with small contexts We fixed an issue but an improved solution was later discussed after the patch was merged. Firstly, this patch doesn't handle the 64bit signals case, which could also hit this issue (but has never been reported). Secondly, the original patch isn't clear what MSR VSX should be set to. The new approach below always clears the MSR VSX bit (to indicate no VSX is in the context) and sets it only in the specific case where VSX is available (ie. when VSX has been used and the signal context passed has space to provide the state). This reverts the original patch and replaces it with the improved solution. It also adds a 64 bit version. Signed-off-by: Michael Neuling Cc: stable@vger.kernel.org Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/signal_32.c | 16 +++++++--------- arch/powerpc/kernel/signal_64.c | 6 ++++++ 2 files changed, 13 insertions(+), 9 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index 1844298f5ea..68027bfa5f8 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -445,6 +445,12 @@ static int save_user_regs(struct pt_regs *regs, struct mcontext __user *frame, #endif /* CONFIG_ALTIVEC */ if (copy_fpr_to_user(&frame->mc_fregs, current)) return 1; + + /* + * Clear the MSR VSX bit to indicate there is no valid state attached + * to this context, except in the specific case below where we set it. + */ + msr &= ~MSR_VSX; #ifdef CONFIG_VSX /* * Copy VSR 0-31 upper half from thread_struct to local @@ -457,15 +463,7 @@ static int save_user_regs(struct pt_regs *regs, struct mcontext __user *frame, if (copy_vsx_to_user(&frame->mc_vsregs, current)) return 1; msr |= MSR_VSX; - } else if (!ctx_has_vsx_region) - /* - * With a small context structure we can't hold the VSX - * registers, hence clear the MSR value to indicate the state - * was not saved. - */ - msr &= ~MSR_VSX; - - + } #endif /* CONFIG_VSX */ #ifdef CONFIG_SPE /* save spe registers */ diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index e66f67b8b9e..42991045349 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -122,6 +122,12 @@ static long setup_sigcontext(struct sigcontext __user *sc, struct pt_regs *regs, flush_fp_to_thread(current); /* copy fpr regs and fpscr */ err |= copy_fpr_to_user(&sc->fp_regs, current); + + /* + * Clear the MSR VSX bit to indicate there is no valid state attached + * to this context, except in the specific case below where we set it. + */ + msr &= ~MSR_VSX; #ifdef CONFIG_VSX /* * Copy VSX low doubleword to local buffer for formatting, -- cgit v1.2.3-70-g09d2 From e0513d9ea8dd2a7b21b699ada8d59d8afbb8b5b7 Mon Sep 17 00:00:00 2001 From: Chen Gang Date: Thu, 24 Jan 2013 12:14:52 +0800 Subject: arch/powerpc/kernel: Use %12.12s instead of %12s to avoid memory overflow for tmp_part->header.name: it is "Terminating null required only for names < 12 chars". so need to limit the %.12s for it in printk additional info: %12s limit the width, not for the original string output length if name length is more than 12, it still can be fully displayed. if name length is less than 12, the ' ' will be filled before name. %.12s truly limit the original string output length (precision) Signed-off-by: Chen Gang Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/nvram_64.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/nvram_64.c b/arch/powerpc/kernel/nvram_64.c index fd82c289ab1..28b898e6818 100644 --- a/arch/powerpc/kernel/nvram_64.c +++ b/arch/powerpc/kernel/nvram_64.c @@ -210,7 +210,7 @@ static void __init nvram_print_partitions(char * label) printk(KERN_WARNING "--------%s---------\n", label); printk(KERN_WARNING "indx\t\tsig\tchks\tlen\tname\n"); list_for_each_entry(tmp_part, &nvram_partitions, partition) { - printk(KERN_WARNING "%4d \t%02x\t%02x\t%d\t%12s\n", + printk(KERN_WARNING "%4d \t%02x\t%02x\t%d\t%12.12s\n", tmp_part->index, tmp_part->header.signature, tmp_part->header.checksum, tmp_part->header.length, tmp_part->header.name); -- cgit v1.2.3-70-g09d2 From 2d6f0c3ae609a73ce6753395daaab3204cd33918 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Fri, 29 Nov 2013 14:55:22 +1100 Subject: powerpc: Fix build break with PPC_EARLY_DEBUG_BOOTX=y A kernel configured with PPC_EARLY_DEBUG_BOOTX=y but PPC_PMAC=n and PPC_MAPLE=n will fail to link: btext.c:(.text+0x2d0fc): undefined reference to `.rmci_off' btext.c:(.text+0x2d214): undefined reference to `.rmci_on' Fix it by making the build of rmci_on/off() depend on PPC_EARLY_DEBUG_BOOTX, which also enable the only code that uses them. Signed-off-by: Michael Ellerman Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/misc_64.S | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S index e59caf874d0..64bf8db12b1 100644 --- a/arch/powerpc/kernel/misc_64.S +++ b/arch/powerpc/kernel/misc_64.S @@ -246,8 +246,8 @@ _GLOBAL(__bswapdi2) or r3,r7,r9 blr -#if defined(CONFIG_PPC_PMAC) || defined(CONFIG_PPC_MAPLE) +#ifdef CONFIG_PPC_EARLY_DEBUG_BOOTX _GLOBAL(rmci_on) sync isync @@ -277,6 +277,9 @@ _GLOBAL(rmci_off) isync sync blr +#endif /* CONFIG_PPC_EARLY_DEBUG_BOOTX */ + +#if defined(CONFIG_PPC_PMAC) || defined(CONFIG_PPC_MAPLE) /* * Do an IO access in real mode -- cgit v1.2.3-70-g09d2 From e641eb03ab2b0f065fa5e64b4202fb5b0441b427 Mon Sep 17 00:00:00 2001 From: Mahesh Salgaonkar Date: Mon, 9 Dec 2013 15:33:39 +0530 Subject: powerpc: Fix up the kdump base cap to 128M The current logic sets the kdump base to min of 2G or ppc64_rma_size/2. On PowerNV kernel the first memory block 'memory@0' can be very large, equal to the DIMM size with ppc64_rma_size value capped to 1G. Hence on PowerNV, kdump base is set to 512M resulting kdump to fail while allocating paca array. This is because, paca need its memory from RMA region capped at 256M (see allocate_pacas()). This patch lowers the kdump base cap to 128M so that kdump kernel can successfully get memory below 256M for paca allocation. Signed-off-by: Mahesh Salgaonkar Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/machine_kexec.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/machine_kexec.c b/arch/powerpc/kernel/machine_kexec.c index 88a7fb458df..75d4f7340da 100644 --- a/arch/powerpc/kernel/machine_kexec.c +++ b/arch/powerpc/kernel/machine_kexec.c @@ -148,7 +148,7 @@ void __init reserve_crashkernel(void) * a small SLB (128MB) since the crash kernel needs to place * itself and some stacks to be in the first segment. */ - crashk_res.start = min(0x80000000ULL, (ppc64_rma_size / 2)); + crashk_res.start = min(0x8000000ULL, (ppc64_rma_size / 2)); #else crashk_res.start = KDUMP_KERNELBASE; #endif -- cgit v1.2.3-70-g09d2