From a2b05b7aa60e1e9b60faf01dfb1cca35638d1ab1 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Thu, 11 May 2017 21:24:41 +1000 Subject: [PATCH 01/13] powerpc/64s: Add dt_cpu_ftrs boot time setup option Provide a dt_cpu_ftrs= cmdline option to disable the dt_cpu_ftrs CPU feature discovery, and fall back to the "cputable" based version. Also allow control of advertising unknown features to userspace and with this parameter, and remove the clunky CONFIG option. Signed-off-by: Nicholas Piggin [mpe: Add explicit early check of bootargs in dt_cpu_ftrs_init()] Signed-off-by: Michael Ellerman --- .../admin-guide/kernel-parameters.txt | 9 +++ arch/powerpc/Kconfig | 5 -- arch/powerpc/kernel/dt_cpu_ftrs.c | 57 ++++++++++++++++--- 3 files changed, 57 insertions(+), 14 deletions(-) diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 15f79c27748d..0f5c3b4347c6 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -866,6 +866,15 @@ dscc4.setup= [NET] + dt_cpu_ftrs= [PPC] + Format: {"off" | "known"} + Control how the dt_cpu_ftrs device-tree binding is + used for CPU feature discovery and setup (if it + exists). + off: Do not use it, fall back to legacy cpu table. + known: Do not pass through unknown features to guests + or userspace, only those that the kernel is aware of. + dump_apple_properties [X86] Dump name and content of EFI device properties on x86 Macs. Useful for driver authors to determine diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index f7c8f9972f61..4a4a05afcaf7 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -391,11 +391,6 @@ config PPC_DT_CPU_FTRS firmware provides this binding. If you're not sure say Y. -config PPC_CPUFEATURES_ENABLE_UNKNOWN - bool "cpufeatures pass through unknown features to guest/userspace" - depends on PPC_DT_CPU_FTRS - default y - config HIGHMEM bool "High memory support" depends on PPC32 diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c index fcc7588a96d6..76eebba13a1d 100644 --- a/arch/powerpc/kernel/dt_cpu_ftrs.c +++ b/arch/powerpc/kernel/dt_cpu_ftrs.c @@ -8,6 +8,7 @@ #include #include #include +#include #include #include #include @@ -671,12 +672,24 @@ static struct dt_cpu_feature_match __initdata {"wait-v3", feat_enable, 0}, }; -/* XXX: how to configure this? Default + boot time? */ -#ifdef CONFIG_PPC_CPUFEATURES_ENABLE_UNKNOWN -#define CPU_FEATURE_ENABLE_UNKNOWN 1 -#else -#define CPU_FEATURE_ENABLE_UNKNOWN 0 -#endif +static bool __initdata using_dt_cpu_ftrs; +static bool __initdata enable_unknown = true; + +static int __init dt_cpu_ftrs_parse(char *str) +{ + if (!str) + return 0; + + if (!strcmp(str, "off")) + using_dt_cpu_ftrs = false; + else if (!strcmp(str, "known")) + enable_unknown = false; + else + return 1; + + return 0; +} +early_param("dt_cpu_ftrs", dt_cpu_ftrs_parse); static void __init cpufeatures_setup_start(u32 isa) { @@ -707,7 +720,7 @@ static bool __init cpufeatures_process_feature(struct dt_cpu_feature *f) } } - if (!known && CPU_FEATURE_ENABLE_UNKNOWN) { + if (!known && enable_unknown) { if (!feat_try_enable_unknown(f)) { pr_info("not enabling: %s (unknown and unsupported by kernel)\n", f->name); @@ -756,6 +769,26 @@ static void __init cpufeatures_setup_finished(void) cur_cpu_spec->cpu_features, cur_cpu_spec->mmu_features); } +static int __init disabled_on_cmdline(void) +{ + unsigned long root, chosen; + const char *p; + + root = of_get_flat_dt_root(); + chosen = of_get_flat_dt_subnode_by_name(root, "chosen"); + if (chosen == -FDT_ERR_NOTFOUND) + return false; + + p = of_get_flat_dt_prop(chosen, "bootargs", NULL); + if (!p) + return false; + + if (strstr(p, "dt_cpu_ftrs=off")) + return true; + + return false; +} + static int __init fdt_find_cpu_features(unsigned long node, const char *uname, int depth, void *data) { @@ -766,8 +799,6 @@ static int __init fdt_find_cpu_features(unsigned long node, const char *uname, return 0; } -static bool __initdata using_dt_cpu_ftrs = false; - bool __init dt_cpu_ftrs_in_use(void) { return using_dt_cpu_ftrs; @@ -775,6 +806,8 @@ bool __init dt_cpu_ftrs_in_use(void) bool __init dt_cpu_ftrs_init(void *fdt) { + using_dt_cpu_ftrs = false; + /* Setup and verify the FDT, if it fails we just bail */ if (!early_init_dt_verify(fdt)) return false; @@ -782,6 +815,9 @@ bool __init dt_cpu_ftrs_init(void *fdt) if (!of_scan_flat_dt(fdt_find_cpu_features, NULL)) return false; + if (disabled_on_cmdline()) + return false; + cpufeatures_setup_cpu(); using_dt_cpu_ftrs = true; @@ -1027,5 +1063,8 @@ static int __init dt_cpu_ftrs_scan_callback(unsigned long node, const char void __init dt_cpu_ftrs_scan(void) { + if (!using_dt_cpu_ftrs) + return; + of_scan_flat_dt(dt_cpu_ftrs_scan_callback, NULL); } From 99acc9bede06bbb2662aafff51f5b9e529fa845e Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Mon, 29 May 2017 20:26:07 +1000 Subject: [PATCH 02/13] powerpc/spufs: Fix coredump of SPU contexts If a process dumps core while it has SPU contexts active then we have code to also dump information about the SPU contexts. Unfortunately it's been broken for 3 1/2 years, and we didn't notice. In commit 7b1f4020d0d1 ("spufs: get rid of dump_emit() wrappers") the nread variable was removed and rc used instead. That means when the loop exits successfully, rc has the number of bytes read, but it's then used as the return value for the function, which should return 0 on success. So fix it by setting rc = 0 before returning in the success case. Fixes: 7b1f4020d0d1 ("spufs: get rid of dump_emit() wrappers") Signed-off-by: Michael Ellerman Acked-by: Jeremy Kerr Signed-off-by: Michael Ellerman --- arch/powerpc/platforms/cell/spufs/coredump.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/powerpc/platforms/cell/spufs/coredump.c b/arch/powerpc/platforms/cell/spufs/coredump.c index e5a891ae80ee..84b7ac926ce6 100644 --- a/arch/powerpc/platforms/cell/spufs/coredump.c +++ b/arch/powerpc/platforms/cell/spufs/coredump.c @@ -175,6 +175,8 @@ static int spufs_arch_write_note(struct spu_context *ctx, int i, skip = roundup(cprm->pos - total + sz, 4) - cprm->pos; if (!dump_skip(cprm, skip)) goto Eio; + + rc = 0; out: free_page((unsigned long)buf); return rc; From 6f553912eedafae13ff20b322a65e471fe7f5236 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Wed, 24 May 2017 10:01:55 +0200 Subject: [PATCH 03/13] powerpc/sysdev/simple_gpio: Fix oops in gpio save_regs function of_mm_gpiochip_add_data() generates an oops for NULL pointer dereference. of_mm_gpiochip_add_data() calls mm_gc->save_regs() before setting the data, therefore ->save_regs() cannot use gpiochip_get_data() Fixes: 937daafca774 ("powerpc: simple-gpio: use gpiochip data pointer") Cc: stable@vger.kernel.org # v4.7+ Signed-off-by: Christophe Leroy Reviewed-by: Linus Walleij Signed-off-by: Michael Ellerman --- arch/powerpc/sysdev/simple_gpio.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/powerpc/sysdev/simple_gpio.c b/arch/powerpc/sysdev/simple_gpio.c index ef470b470b04..6afddae2fb47 100644 --- a/arch/powerpc/sysdev/simple_gpio.c +++ b/arch/powerpc/sysdev/simple_gpio.c @@ -75,7 +75,8 @@ static int u8_gpio_dir_out(struct gpio_chip *gc, unsigned int gpio, int val) static void u8_gpio_save_regs(struct of_mm_gpio_chip *mm_gc) { - struct u8_gpio_chip *u8_gc = gpiochip_get_data(&mm_gc->gc); + struct u8_gpio_chip *u8_gc = + container_of(mm_gc, struct u8_gpio_chip, mm_gc); u8_gc->data = in_8(mm_gc->regs); } From dc421b200f91930c9c6a9586810ff8c232cf10fc Mon Sep 17 00:00:00 2001 From: Michael Bringmann Date: Mon, 22 May 2017 15:44:37 -0500 Subject: [PATCH 04/13] powerpc/hotplug-mem: Fix missing endian conversion of aa_index When adding or removing memory, the aa_index (affinity value) for the memblock must also be converted to match the endianness of the rest of the 'ibm,dynamic-memory' property. Otherwise, subsequent retrieval of the attribute will likely lead to non-existent nodes, followed by using the default node in the code inappropriately. Fixes: 5f97b2a0d176 ("powerpc/pseries: Implement memory hotplug add in the kernel") Cc: stable@vger.kernel.org # v4.1+ Signed-off-by: Michael Bringmann Signed-off-by: Michael Ellerman --- arch/powerpc/platforms/pseries/hotplug-memory.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c index e104c71ea44a..1fb162ba9d1c 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -124,6 +124,7 @@ static struct property *dlpar_clone_drconf_property(struct device_node *dn) for (i = 0; i < num_lmbs; i++) { lmbs[i].base_addr = be64_to_cpu(lmbs[i].base_addr); lmbs[i].drc_index = be32_to_cpu(lmbs[i].drc_index); + lmbs[i].aa_index = be32_to_cpu(lmbs[i].aa_index); lmbs[i].flags = be32_to_cpu(lmbs[i].flags); } @@ -147,6 +148,7 @@ static void dlpar_update_drconf_property(struct device_node *dn, for (i = 0; i < num_lmbs; i++) { lmbs[i].base_addr = cpu_to_be64(lmbs[i].base_addr); lmbs[i].drc_index = cpu_to_be32(lmbs[i].drc_index); + lmbs[i].aa_index = cpu_to_be32(lmbs[i].aa_index); lmbs[i].flags = cpu_to_be32(lmbs[i].flags); } From 0e5e7f5e9700661c3ddd95501743fb52fec1ab07 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Thu, 25 May 2017 16:33:52 +1000 Subject: [PATCH 05/13] powerpc/64: Reclaim CPU_FTR_SUBCORE We are running low on CPU feature bits, so we only want to use them when it's really necessary. CPU_FTR_SUBCORE is only used in one place, and only in C, so we don't need it in order to make asm patching work. It can only be set on "Power8" CPUs, which in practice means POWER8, POWER8E and POWER8NVL. There are no plans to implement it on future CPUs, but if there ever were we could retrofit it then. Although KVM uses subcores, it never looks at the CPU feature, it either looks at the ISA level or the threads_per_subcore value. So drop the CPU feature and do a PVR check instead. Drop the device tree "subcore" feature as we no longer support doing anything with it, and we will drop it from skiboot too. Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/cputable.h | 3 +-- arch/powerpc/kernel/dt_cpu_ftrs.c | 1 - arch/powerpc/platforms/powernv/subcore.c | 8 +++++++- 3 files changed, 8 insertions(+), 4 deletions(-) diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h index c2d509584a98..d02ad93bf708 100644 --- a/arch/powerpc/include/asm/cputable.h +++ b/arch/powerpc/include/asm/cputable.h @@ -214,7 +214,6 @@ enum { #define CPU_FTR_DAWR LONG_ASM_CONST(0x0400000000000000) #define CPU_FTR_DABRX LONG_ASM_CONST(0x0800000000000000) #define CPU_FTR_PMAO_BUG LONG_ASM_CONST(0x1000000000000000) -#define CPU_FTR_SUBCORE LONG_ASM_CONST(0x2000000000000000) #define CPU_FTR_POWER9_DD1 LONG_ASM_CONST(0x4000000000000000) #ifndef __ASSEMBLY__ @@ -463,7 +462,7 @@ enum { CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \ CPU_FTR_ICSWX | CPU_FTR_CFAR | CPU_FTR_HVMODE | CPU_FTR_VMX_COPY | \ CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_DAWR | \ - CPU_FTR_ARCH_207S | CPU_FTR_TM_COMP | CPU_FTR_SUBCORE) + CPU_FTR_ARCH_207S | CPU_FTR_TM_COMP) #define CPU_FTRS_POWER8E (CPU_FTRS_POWER8 | CPU_FTR_PMAO_BUG) #define CPU_FTRS_POWER8_DD1 (CPU_FTRS_POWER8 & ~CPU_FTR_DBELL) #define CPU_FTRS_POWER9 (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \ diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c index 76eebba13a1d..4c7656dc4e04 100644 --- a/arch/powerpc/kernel/dt_cpu_ftrs.c +++ b/arch/powerpc/kernel/dt_cpu_ftrs.c @@ -643,7 +643,6 @@ static struct dt_cpu_feature_match __initdata {"processor-control-facility", feat_enable_dbell, CPU_FTR_DBELL}, {"processor-control-facility-v3", feat_enable_dbell, CPU_FTR_DBELL}, {"processor-utilization-of-resources-register", feat_enable_purr, 0}, - {"subcore", feat_enable, CPU_FTR_SUBCORE}, {"no-execute", feat_enable, 0}, {"strong-access-ordering", feat_enable, CPU_FTR_SAO}, {"cache-inhibited-large-page", feat_enable_large_ci, 0}, diff --git a/arch/powerpc/platforms/powernv/subcore.c b/arch/powerpc/platforms/powernv/subcore.c index 0babef11136f..8c6119280c13 100644 --- a/arch/powerpc/platforms/powernv/subcore.c +++ b/arch/powerpc/platforms/powernv/subcore.c @@ -407,7 +407,13 @@ static DEVICE_ATTR(subcores_per_core, 0644, static int subcore_init(void) { - if (!cpu_has_feature(CPU_FTR_SUBCORE)) + unsigned pvr_ver; + + pvr_ver = PVR_VER(mfspr(SPRN_PVR)); + + if (pvr_ver != PVR_POWER8 && + pvr_ver != PVR_POWER8E && + pvr_ver != PVR_POWER8NVL) return 0; /* From 1195892c091a15cc862f4e202482a36adc924e12 Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Fri, 2 Jun 2017 18:43:30 -0300 Subject: [PATCH 06/13] powerpc/kernel: Fix FP and vector register restoration Currently tsk->thread->load_vec and load_fp are not initialized during task creation, which can lead to garbage values in these variables (non-zero values). These variables will be checked later in restore_math() to validate if the FP and vector registers are being utilized. Since these values might be non-zero, the restore_math() will continue to save the FP and vectors even if they were never utilized by the userspace application. load_fp and load_vec counters will then overflow (they wrap at 255) and the FP and Altivec will be finally disabled, but before that condition is reached (counter overflow) several context switches will have restored FP and vector registers without need, causing a performance degradation. Fixes: 70fe3d980f5f ("powerpc: Restore FPU/VEC/VSX if previously used") Cc: stable@vger.kernel.org # v4.6+ Signed-off-by: Breno Leitao Signed-off-by: Gustavo Romero Acked-by: Anton Blanchard Signed-off-by: Michael Ellerman --- arch/powerpc/kernel/process.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index baae104b16c7..a9435397eab8 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -1666,6 +1666,7 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp) #ifdef CONFIG_VSX current->thread.used_vsr = 0; #endif + current->thread.load_fp = 0; memset(¤t->thread.fp_state, 0, sizeof(current->thread.fp_state)); current->thread.fp_save_area = NULL; #ifdef CONFIG_ALTIVEC @@ -1674,6 +1675,7 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp) current->thread.vr_save_area = NULL; current->thread.vrsave = 0; current->thread.used_vr = 0; + current->thread.load_vec = 0; #endif /* CONFIG_ALTIVEC */ #ifdef CONFIG_SPE memset(current->thread.evr, 0, sizeof(current->thread.evr)); From 7f22ced4377628074e2ac25f41a88f98eb3b03f1 Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Mon, 5 Jun 2017 11:40:59 -0300 Subject: [PATCH 07/13] powerpc/kernel: Initialize load_tm on task creation Currently tsk->thread.load_tm is not initialized in the task creation and can contain garbage on a new task. This is an undesired behaviour, since it affects the timing to enable and disable the transactional memory laziness (disabling and enabling the MSR TM bit, which affects TM reclaim and recheckpoint in the scheduling process). Fixes: 5d176f751ee3 ("powerpc: tm: Enable transactional memory (TM) lazily for userspace") Cc: stable@vger.kernel.org # v4.9+ Signed-off-by: Breno Leitao Signed-off-by: Michael Ellerman --- arch/powerpc/kernel/process.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index a9435397eab8..2ad725ef4368 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -1687,6 +1687,7 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp) current->thread.tm_tfhar = 0; current->thread.tm_texasr = 0; current->thread.tm_tfiar = 0; + current->thread.load_tm = 0; #endif /* CONFIG_PPC_TRANSACTIONAL_MEM */ } EXPORT_SYMBOL(start_thread); From b3aa20ba2ba8072b73bd799605b8c98927b7056c Mon Sep 17 00:00:00 2001 From: Vaibhav Jain Date: Fri, 2 Jun 2017 22:26:48 +0530 Subject: [PATCH 08/13] cxl: Avoid double free_irq() for psl,slice interrupts During an eeh call to cxl_remove can result in double free_irq of psl,slice interrupts. This can happen if perst_reloads_same_image == 1 and call to cxl_configure_adapter() fails during slot_reset callback. In such a case we see a kernel oops with following back-trace: Oops: Kernel access of bad area, sig: 11 [#1] Call Trace: free_irq+0x88/0xd0 (unreliable) cxl_unmap_irq+0x20/0x40 [cxl] cxl_native_release_psl_irq+0x78/0xd8 [cxl] pci_deconfigure_afu+0xac/0x110 [cxl] cxl_remove+0x104/0x210 [cxl] pci_device_remove+0x6c/0x110 device_release_driver_internal+0x204/0x2e0 pci_stop_bus_device+0xa0/0xd0 pci_stop_and_remove_bus_device+0x28/0x40 pci_hp_remove_devices+0xb0/0x150 pci_hp_remove_devices+0x68/0x150 eeh_handle_normal_event+0x140/0x580 eeh_handle_event+0x174/0x360 eeh_event_handler+0x1e8/0x1f0 This patch fixes the issue of double free_irq by checking that variables that hold the virqs (err_hwirq, serr_hwirq, psl_virq) are not '0' before un-mapping and resetting these variables to '0' when they are un-mapped. Cc: stable@vger.kernel.org Signed-off-by: Vaibhav Jain Reviewed-by: Andrew Donnellan Acked-by: Frederic Barrat Signed-off-by: Michael Ellerman --- drivers/misc/cxl/native.c | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) diff --git a/drivers/misc/cxl/native.c b/drivers/misc/cxl/native.c index 871a2f09c718..8d6ea9712dbd 100644 --- a/drivers/misc/cxl/native.c +++ b/drivers/misc/cxl/native.c @@ -1302,13 +1302,16 @@ int cxl_native_register_psl_err_irq(struct cxl *adapter) void cxl_native_release_psl_err_irq(struct cxl *adapter) { - if (adapter->native->err_virq != irq_find_mapping(NULL, adapter->native->err_hwirq)) + if (adapter->native->err_virq == 0 || + adapter->native->err_virq != + irq_find_mapping(NULL, adapter->native->err_hwirq)) return; cxl_p1_write(adapter, CXL_PSL_ErrIVTE, 0x0000000000000000); cxl_unmap_irq(adapter->native->err_virq, adapter); cxl_ops->release_one_irq(adapter, adapter->native->err_hwirq); kfree(adapter->irq_name); + adapter->native->err_virq = 0; } int cxl_native_register_serr_irq(struct cxl_afu *afu) @@ -1346,13 +1349,15 @@ int cxl_native_register_serr_irq(struct cxl_afu *afu) void cxl_native_release_serr_irq(struct cxl_afu *afu) { - if (afu->serr_virq != irq_find_mapping(NULL, afu->serr_hwirq)) + if (afu->serr_virq == 0 || + afu->serr_virq != irq_find_mapping(NULL, afu->serr_hwirq)) return; cxl_p1n_write(afu, CXL_PSL_SERR_An, 0x0000000000000000); cxl_unmap_irq(afu->serr_virq, afu); cxl_ops->release_one_irq(afu->adapter, afu->serr_hwirq); kfree(afu->err_irq_name); + afu->serr_virq = 0; } int cxl_native_register_psl_irq(struct cxl_afu *afu) @@ -1375,12 +1380,15 @@ int cxl_native_register_psl_irq(struct cxl_afu *afu) void cxl_native_release_psl_irq(struct cxl_afu *afu) { - if (afu->native->psl_virq != irq_find_mapping(NULL, afu->native->psl_hwirq)) + if (afu->native->psl_virq == 0 || + afu->native->psl_virq != + irq_find_mapping(NULL, afu->native->psl_hwirq)) return; cxl_unmap_irq(afu->native->psl_virq, afu); cxl_ops->release_one_irq(afu->adapter, afu->native->psl_hwirq); kfree(afu->psl_irq_name); + afu->native->psl_virq = 0; } static void recover_psl_err(struct cxl_afu *afu, u64 errstat) From ba4a648f12f4cd0a8003dd229b6ca8a53348ee4b Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Tue, 6 Jun 2017 20:23:57 +1000 Subject: [PATCH 09/13] powerpc/numa: Fix percpu allocations to be NUMA aware In commit 8c272261194d ("powerpc/numa: Enable USE_PERCPU_NUMA_NODE_ID"), we switched to the generic implementation of cpu_to_node(), which uses a percpu variable to hold the NUMA node for each CPU. Unfortunately we neglected to notice that we use cpu_to_node() in the allocation of our percpu areas, leading to a chicken and egg problem. In practice what happens is when we are setting up the percpu areas, cpu_to_node() reports that all CPUs are on node 0, so we allocate all percpu areas on node 0. This is visible in the dmesg output, as all pcpu allocs being in group 0: pcpu-alloc: [0] 00 01 02 03 [0] 04 05 06 07 pcpu-alloc: [0] 08 09 10 11 [0] 12 13 14 15 pcpu-alloc: [0] 16 17 18 19 [0] 20 21 22 23 pcpu-alloc: [0] 24 25 26 27 [0] 28 29 30 31 pcpu-alloc: [0] 32 33 34 35 [0] 36 37 38 39 pcpu-alloc: [0] 40 41 42 43 [0] 44 45 46 47 To fix it we need an early_cpu_to_node() which can run prior to percpu being setup. We already have the numa_cpu_lookup_table we can use, so just plumb it in. With the patch dmesg output shows two groups, 0 and 1: pcpu-alloc: [0] 00 01 02 03 [0] 04 05 06 07 pcpu-alloc: [0] 08 09 10 11 [0] 12 13 14 15 pcpu-alloc: [0] 16 17 18 19 [0] 20 21 22 23 pcpu-alloc: [1] 24 25 26 27 [1] 28 29 30 31 pcpu-alloc: [1] 32 33 34 35 [1] 36 37 38 39 pcpu-alloc: [1] 40 41 42 43 [1] 44 45 46 47 We can also check the data_offset in the paca of various CPUs, with the fix we see: CPU 0: data_offset = 0x0ffe8b0000 CPU 24: data_offset = 0x1ffe5b0000 And we can see from dmesg that CPU 24 has an allocation on node 1: node 0: [mem 0x0000000000000000-0x0000000fffffffff] node 1: [mem 0x0000001000000000-0x0000001fffffffff] Cc: stable@vger.kernel.org # v3.16+ Fixes: 8c272261194d ("powerpc/numa: Enable USE_PERCPU_NUMA_NODE_ID") Signed-off-by: Michael Ellerman Reviewed-by: Nicholas Piggin Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/topology.h | 14 ++++++++++++++ arch/powerpc/kernel/setup_64.c | 4 ++-- 2 files changed, 16 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h index 8b3b46b7b0f2..329771559cbb 100644 --- a/arch/powerpc/include/asm/topology.h +++ b/arch/powerpc/include/asm/topology.h @@ -44,8 +44,22 @@ extern void __init dump_numa_cpu_topology(void); extern int sysfs_add_device_to_node(struct device *dev, int nid); extern void sysfs_remove_device_from_node(struct device *dev, int nid); +static inline int early_cpu_to_node(int cpu) +{ + int nid; + + nid = numa_cpu_lookup_table[cpu]; + + /* + * Fall back to node 0 if nid is unset (it should be, except bugs). + * This allows callers to safely do NODE_DATA(early_cpu_to_node(cpu)). + */ + return (nid < 0) ? 0 : nid; +} #else +static inline int early_cpu_to_node(int cpu) { return 0; } + static inline void dump_numa_cpu_topology(void) {} static inline int sysfs_add_device_to_node(struct device *dev, int nid) diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index f35ff9dea4fb..a8c1f99e9607 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -661,7 +661,7 @@ void __init emergency_stack_init(void) static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, size_t align) { - return __alloc_bootmem_node(NODE_DATA(cpu_to_node(cpu)), size, align, + return __alloc_bootmem_node(NODE_DATA(early_cpu_to_node(cpu)), size, align, __pa(MAX_DMA_ADDRESS)); } @@ -672,7 +672,7 @@ static void __init pcpu_fc_free(void *ptr, size_t size) static int pcpu_cpu_distance(unsigned int from, unsigned int to) { - if (cpu_to_node(from) == cpu_to_node(to)) + if (early_cpu_to_node(from) == early_cpu_to_node(to)) return LOCAL_DISTANCE; else return REMOTE_DISTANCE; From 8c218578fcbbbdb10416c8614658bf32e3bf1655 Mon Sep 17 00:00:00 2001 From: Madhavan Srinivasan Date: Fri, 26 May 2017 13:38:27 +0530 Subject: [PATCH 10/13] powerpc/perf: Fix Power9 test_adder fields Commit 8d911904f3ce4 ('powerpc/perf: Add restrictions to PMC5 in power9 DD1') was added to restrict the use of PMC5 in Power9 DD1. Intention was to disable the use of PMC5 using raw event code. But instead of updating the power9_isa207_pmu structure (used on DD1), the commit incorrectly updated the power9_pmu structure. Fix it. Fixes: 8d911904f3ce ("powerpc/perf: Add restrictions to PMC5 in power9 DD1") Reported-by: Shriya Signed-off-by: Madhavan Srinivasan Tested-by: Shriya Signed-off-by: Michael Ellerman --- arch/powerpc/perf/power9-pmu.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/perf/power9-pmu.c b/arch/powerpc/perf/power9-pmu.c index 018f8e90ac35..bb28e1a41257 100644 --- a/arch/powerpc/perf/power9-pmu.c +++ b/arch/powerpc/perf/power9-pmu.c @@ -402,7 +402,7 @@ static struct power_pmu power9_isa207_pmu = { .name = "POWER9", .n_counter = MAX_PMU_COUNTERS, .add_fields = ISA207_ADD_FIELDS, - .test_adder = ISA207_TEST_ADDER, + .test_adder = P9_DD1_TEST_ADDER, .compute_mmcr = isa207_compute_mmcr, .config_bhrb = power9_config_bhrb, .bhrb_filter_map = power9_bhrb_filter_map, @@ -421,7 +421,7 @@ static struct power_pmu power9_pmu = { .name = "POWER9", .n_counter = MAX_PMU_COUNTERS, .add_fields = ISA207_ADD_FIELDS, - .test_adder = P9_DD1_TEST_ADDER, + .test_adder = ISA207_TEST_ADDER, .compute_mmcr = isa207_compute_mmcr, .config_bhrb = power9_config_bhrb, .bhrb_filter_map = power9_bhrb_filter_map, From cec422c11caeeccae709e9942058b6b644ce434c Mon Sep 17 00:00:00 2001 From: Frederic Barrat Date: Tue, 6 Jun 2017 11:43:41 +0200 Subject: [PATCH 11/13] cxl: Fix error path on bad ioctl Fix error path if we can't copy user structure on CXL_IOCTL_START_WORK ioctl. We shouldn't unlock the context status mutex as it was not locked (yet). Fixes: 0712dc7e73e5 ("cxl: Fix issues when unmapping contexts") Cc: stable@vger.kernel.org # v3.19+ Signed-off-by: Frederic Barrat Reviewed-by: Vaibhav Jain Reviewed-by: Andrew Donnellan Signed-off-by: Michael Ellerman --- drivers/misc/cxl/file.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/drivers/misc/cxl/file.c b/drivers/misc/cxl/file.c index 17b433f1ce23..0761271d68c5 100644 --- a/drivers/misc/cxl/file.c +++ b/drivers/misc/cxl/file.c @@ -159,11 +159,8 @@ static long afu_ioctl_start_work(struct cxl_context *ctx, /* Do this outside the status_mutex to avoid a circular dependency with * the locking in cxl_mmap_fault() */ - if (copy_from_user(&work, uwork, - sizeof(struct cxl_ioctl_start_work))) { - rc = -EFAULT; - goto out; - } + if (copy_from_user(&work, uwork, sizeof(work))) + return -EFAULT; mutex_lock(&ctx->status_mutex); if (ctx->status != OPENED) { From 92d9dfda8b547cc292af27e11e11c9eff3bb574f Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Thu, 1 Jun 2017 20:05:04 +0530 Subject: [PATCH 12/13] powerpc/mm/4k: Limit 4k page size config to 64TB virtual address space Supporting 512TB requires us to do a order 3 allocation for level 1 page table (pgd). This results in page allocation failures with certain workloads. For now limit 4k linux page size config to 64TB. Fixes: f6eedbba7a26 ("powerpc/mm/hash: Increase VA range to 128TB") Reported-by: Hugh Dickins Signed-off-by: Aneesh Kumar K.V Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/book3s/64/hash-4k.h | 2 +- arch/powerpc/include/asm/processor.h | 25 ++++++++++---------- arch/powerpc/kernel/setup-common.c | 2 +- arch/powerpc/mm/mmu_context_book3s64.c | 2 +- 4 files changed, 15 insertions(+), 16 deletions(-) diff --git a/arch/powerpc/include/asm/book3s/64/hash-4k.h b/arch/powerpc/include/asm/book3s/64/hash-4k.h index b4b5e6b671ca..0c4e470571ca 100644 --- a/arch/powerpc/include/asm/book3s/64/hash-4k.h +++ b/arch/powerpc/include/asm/book3s/64/hash-4k.h @@ -8,7 +8,7 @@ #define H_PTE_INDEX_SIZE 9 #define H_PMD_INDEX_SIZE 7 #define H_PUD_INDEX_SIZE 9 -#define H_PGD_INDEX_SIZE 12 +#define H_PGD_INDEX_SIZE 9 #ifndef __ASSEMBLY__ #define H_PTE_TABLE_SIZE (sizeof(pte_t) << H_PTE_INDEX_SIZE) diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h index a2123f291ab0..bb99b651085a 100644 --- a/arch/powerpc/include/asm/processor.h +++ b/arch/powerpc/include/asm/processor.h @@ -110,13 +110,18 @@ void release_thread(struct task_struct *); #define TASK_SIZE_128TB (0x0000800000000000UL) #define TASK_SIZE_512TB (0x0002000000000000UL) -#ifdef CONFIG_PPC_BOOK3S_64 +/* + * For now 512TB is only supported with book3s and 64K linux page size. + */ +#if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_PPC_64K_PAGES) /* * Max value currently used: */ -#define TASK_SIZE_USER64 TASK_SIZE_512TB +#define TASK_SIZE_USER64 TASK_SIZE_512TB +#define DEFAULT_MAP_WINDOW_USER64 TASK_SIZE_128TB #else -#define TASK_SIZE_USER64 TASK_SIZE_64TB +#define TASK_SIZE_USER64 TASK_SIZE_64TB +#define DEFAULT_MAP_WINDOW_USER64 TASK_SIZE_64TB #endif /* @@ -132,7 +137,7 @@ void release_thread(struct task_struct *); * space during mmap's. */ #define TASK_UNMAPPED_BASE_USER32 (PAGE_ALIGN(TASK_SIZE_USER32 / 4)) -#define TASK_UNMAPPED_BASE_USER64 (PAGE_ALIGN(TASK_SIZE_128TB / 4)) +#define TASK_UNMAPPED_BASE_USER64 (PAGE_ALIGN(DEFAULT_MAP_WINDOW_USER64 / 4)) #define TASK_UNMAPPED_BASE ((is_32bit_task()) ? \ TASK_UNMAPPED_BASE_USER32 : TASK_UNMAPPED_BASE_USER64 ) @@ -143,21 +148,15 @@ void release_thread(struct task_struct *); * with 128TB and conditionally enable upto 512TB */ #ifdef CONFIG_PPC_BOOK3S_64 -#define DEFAULT_MAP_WINDOW ((is_32bit_task()) ? \ - TASK_SIZE_USER32 : TASK_SIZE_128TB) +#define DEFAULT_MAP_WINDOW ((is_32bit_task()) ? \ + TASK_SIZE_USER32 : DEFAULT_MAP_WINDOW_USER64) #else #define DEFAULT_MAP_WINDOW TASK_SIZE #endif #ifdef __powerpc64__ -#ifdef CONFIG_PPC_BOOK3S_64 -/* Limit stack to 128TB */ -#define STACK_TOP_USER64 TASK_SIZE_128TB -#else -#define STACK_TOP_USER64 TASK_SIZE_USER64 -#endif - +#define STACK_TOP_USER64 DEFAULT_MAP_WINDOW_USER64 #define STACK_TOP_USER32 TASK_SIZE_USER32 #define STACK_TOP (is_32bit_task() ? \ diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index 71dcda91755d..857129acf960 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -928,7 +928,7 @@ void __init setup_arch(char **cmdline_p) #ifdef CONFIG_PPC_MM_SLICES #ifdef CONFIG_PPC64 - init_mm.context.addr_limit = TASK_SIZE_128TB; + init_mm.context.addr_limit = DEFAULT_MAP_WINDOW_USER64; #else #error "context.addr_limit not initialized." #endif diff --git a/arch/powerpc/mm/mmu_context_book3s64.c b/arch/powerpc/mm/mmu_context_book3s64.c index c6dca2ae78ef..a3edf813d455 100644 --- a/arch/powerpc/mm/mmu_context_book3s64.c +++ b/arch/powerpc/mm/mmu_context_book3s64.c @@ -99,7 +99,7 @@ static int hash__init_new_context(struct mm_struct *mm) * mm->context.addr_limit. Default to max task size so that we copy the * default values to paca which will help us to handle slb miss early. */ - mm->context.addr_limit = TASK_SIZE_128TB; + mm->context.addr_limit = DEFAULT_MAP_WINDOW_USER64; /* * The old code would re-promote on fork, we don't do that when using From c6ee9619e2edd9912316f7e2eaf9ffa14fafe9f9 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Thu, 8 Jun 2017 16:29:59 +1000 Subject: [PATCH 13/13] powerpc/book3s64: Move PPC_DT_CPU_FTRs and enable it by default The PPC_DT_CPU_FTRs is a bit misplaced in menuconfig, it shows up with other general kernel options. It's really more at home in the "Platform Support" section, so move it there. Also enable it by default, for Book3s 64. It does mostly nothing unless the device tree properties are found, and we will want it enabled eventually in distro kernels, so turn it on to start getting more testing. Fixes: 5a61ef74f269 ("powerpc/64s: Support new device tree binding for discovering CPU features") Signed-off-by: Michael Ellerman --- arch/powerpc/Kconfig | 11 ----------- arch/powerpc/platforms/Kconfig | 11 +++++++++++ 2 files changed, 11 insertions(+), 11 deletions(-) diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 4a4a05afcaf7..964da1891ea9 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -380,17 +380,6 @@ source "arch/powerpc/platforms/Kconfig" menu "Kernel options" -config PPC_DT_CPU_FTRS - bool "Device-tree based CPU feature discovery & setup" - depends on PPC_BOOK3S_64 - default n - help - This enables code to use a new device tree binding for describing CPU - compatibility and features. Saying Y here will attempt to use the new - binding if the firmware provides it. Currently only the skiboot - firmware provides this binding. - If you're not sure say Y. - config HIGHMEM bool "High memory support" depends on PPC32 diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig index 33244e3d9375..4fd64d3f5c44 100644 --- a/arch/powerpc/platforms/Kconfig +++ b/arch/powerpc/platforms/Kconfig @@ -59,6 +59,17 @@ config PPC_OF_BOOT_TRAMPOLINE In case of doubt, say Y +config PPC_DT_CPU_FTRS + bool "Device-tree based CPU feature discovery & setup" + depends on PPC_BOOK3S_64 + default y + help + This enables code to use a new device tree binding for describing CPU + compatibility and features. Saying Y here will attempt to use the new + binding if the firmware provides it. Currently only the skiboot + firmware provides this binding. + If you're not sure say Y. + config UDBG_RTAS_CONSOLE bool "RTAS based debug console" depends on PPC_RTAS