diff options
Diffstat (limited to 'arch/powerpc/platforms')
46 files changed, 992 insertions, 273 deletions
diff --git a/arch/powerpc/platforms/44x/warp-nand.c b/arch/powerpc/platforms/44x/warp-nand.c index e55746b824b4..89ecd76127d8 100644 --- a/arch/powerpc/platforms/44x/warp-nand.c +++ b/arch/powerpc/platforms/44x/warp-nand.c @@ -24,7 +24,7 @@ static struct resource warp_ndfc = { .start = WARP_NAND_FLASH_REG_ADDR, - .end = WARP_NAND_FLASH_REG_ADDR + WARP_NAND_FLASH_REG_SIZE, + .end = WARP_NAND_FLASH_REG_ADDR + WARP_NAND_FLASH_REG_SIZE - 1, .flags = IORESOURCE_MEM, }; diff --git a/arch/powerpc/platforms/44x/warp.c b/arch/powerpc/platforms/44x/warp.c index 9565995cba7f..960edf89be51 100644 --- a/arch/powerpc/platforms/44x/warp.c +++ b/arch/powerpc/platforms/44x/warp.c @@ -30,18 +30,6 @@ static __initdata struct of_device_id warp_of_bus[] = { {}, }; -static __initdata struct i2c_board_info warp_i2c_info[] = { - { I2C_BOARD_INFO("ad7414", 0x4a) } -}; - -static int __init warp_arch_init(void) -{ - /* This should go away once support is moved to the dts. */ - i2c_register_board_info(0, warp_i2c_info, ARRAY_SIZE(warp_i2c_info)); - return 0; -} -machine_arch_initcall(warp, warp_arch_init); - static int __init warp_device_probe(void) { of_platform_bus_probe(NULL, warp_of_bus, NULL); @@ -223,7 +211,7 @@ static void pika_setup_critical_temp(struct i2c_client *client) /* These registers are in 1 degree increments. */ i2c_smbus_write_byte_data(client, 2, 65); /* Thigh */ - i2c_smbus_write_byte_data(client, 3, 55); /* Tlow */ + i2c_smbus_write_byte_data(client, 3, 0); /* Tlow */ np = of_find_compatible_node(NULL, NULL, "adi,ad7414"); if (np == NULL) { @@ -289,8 +277,15 @@ found_it: printk(KERN_INFO "PIKA DTM thread running.\n"); while (!kthread_should_stop()) { - u16 temp = swab16(i2c_smbus_read_word_data(client, 0)); - out_be32(fpga + 0x20, temp); + int val; + + val = i2c_smbus_read_word_data(client, 0); + if (val < 0) + dev_dbg(&client->dev, "DTM read temp failed.\n"); + else { + s16 temp = swab16(val); + out_be32(fpga + 0x20, temp); + } pika_dtm_check_fan(fpga); diff --git a/arch/powerpc/platforms/52xx/Kconfig b/arch/powerpc/platforms/52xx/Kconfig index d664b1bce381..696a5ee4962d 100644 --- a/arch/powerpc/platforms/52xx/Kconfig +++ b/arch/powerpc/platforms/52xx/Kconfig @@ -1,7 +1,6 @@ config PPC_MPC52xx bool "52xx-based boards" depends on PPC_MULTIPLATFORM && PPC32 - select FSL_SOC select PPC_CLOCK select PPC_PCI_CHOICE @@ -48,6 +47,7 @@ config PPC_MPC5200_BUGFIX config PPC_MPC5200_GPIO bool "MPC5200 GPIO support" depends on PPC_MPC52xx - select HAVE_GPIO_LIB + select ARCH_REQUIRE_GPIOLIB + select GENERIC_GPIO help Enable gpiolib support for mpc5200 based boards diff --git a/arch/powerpc/platforms/52xx/Makefile b/arch/powerpc/platforms/52xx/Makefile index daf0e1568d6d..b8a52062738a 100644 --- a/arch/powerpc/platforms/52xx/Makefile +++ b/arch/powerpc/platforms/52xx/Makefile @@ -1,10 +1,8 @@ # # Makefile for 52xx based boards # -ifeq ($(CONFIG_PPC_MERGE),y) obj-y += mpc52xx_pic.o mpc52xx_common.o obj-$(CONFIG_PCI) += mpc52xx_pci.o -endif obj-$(CONFIG_PPC_MPC5200_SIMPLE) += mpc5200_simple.o obj-$(CONFIG_PPC_EFIKA) += efika.o @@ -15,4 +13,4 @@ ifeq ($(CONFIG_PPC_LITE5200),y) obj-$(CONFIG_PM) += lite5200_sleep.o lite5200_pm.o endif -obj-$(CONFIG_PPC_MPC5200_GPIO) += mpc52xx_gpio.o
\ No newline at end of file +obj-$(CONFIG_PPC_MPC5200_GPIO) += mpc52xx_gpio.o diff --git a/arch/powerpc/platforms/83xx/mpc832x_mds.c b/arch/powerpc/platforms/83xx/mpc832x_mds.c index dd4be4aee314..ec43477caa63 100644 --- a/arch/powerpc/platforms/83xx/mpc832x_mds.c +++ b/arch/powerpc/platforms/83xx/mpc832x_mds.c @@ -105,6 +105,7 @@ static void __init mpc832x_sys_setup_arch(void) static struct of_device_id mpc832x_ids[] = { { .type = "soc", }, { .compatible = "soc", }, + { .compatible = "simple-bus", }, { .type = "qe", }, { .compatible = "fsl,qe", }, {}, diff --git a/arch/powerpc/platforms/83xx/mpc832x_rdb.c b/arch/powerpc/platforms/83xx/mpc832x_rdb.c index f049d692d4c8..0300268ce5b8 100644 --- a/arch/powerpc/platforms/83xx/mpc832x_rdb.c +++ b/arch/powerpc/platforms/83xx/mpc832x_rdb.c @@ -115,6 +115,7 @@ static void __init mpc832x_rdb_setup_arch(void) static struct of_device_id mpc832x_ids[] = { { .type = "soc", }, { .compatible = "soc", }, + { .compatible = "simple-bus", }, { .type = "qe", }, { .compatible = "fsl,qe", }, {}, diff --git a/arch/powerpc/platforms/83xx/mpc834x_itx.c b/arch/powerpc/platforms/83xx/mpc834x_itx.c index 7301d77a08ee..76092d37c7d9 100644 --- a/arch/powerpc/platforms/83xx/mpc834x_itx.c +++ b/arch/powerpc/platforms/83xx/mpc834x_itx.c @@ -41,6 +41,7 @@ static struct of_device_id __initdata mpc834x_itx_ids[] = { { .compatible = "fsl,pq2pro-localbus", }, + { .compatible = "simple-bus", }, {}, }; diff --git a/arch/powerpc/platforms/83xx/mpc834x_mds.c b/arch/powerpc/platforms/83xx/mpc834x_mds.c index 30d509aa9f08..fc3f2ed1f3e9 100644 --- a/arch/powerpc/platforms/83xx/mpc834x_mds.c +++ b/arch/powerpc/platforms/83xx/mpc834x_mds.c @@ -111,6 +111,7 @@ static void __init mpc834x_mds_init_IRQ(void) static struct of_device_id mpc834x_ids[] = { { .type = "soc", }, { .compatible = "soc", }, + { .compatible = "simple-bus", }, {}, }; diff --git a/arch/powerpc/platforms/83xx/mpc836x_mds.c b/arch/powerpc/platforms/83xx/mpc836x_mds.c index 75b80e836576..9d46e5bdd101 100644 --- a/arch/powerpc/platforms/83xx/mpc836x_mds.c +++ b/arch/powerpc/platforms/83xx/mpc836x_mds.c @@ -136,6 +136,7 @@ static void __init mpc836x_mds_setup_arch(void) static struct of_device_id mpc836x_ids[] = { { .type = "soc", }, { .compatible = "soc", }, + { .compatible = "simple-bus", }, { .type = "qe", }, { .compatible = "fsl,qe", }, {}, diff --git a/arch/powerpc/platforms/83xx/sbc834x.c b/arch/powerpc/platforms/83xx/sbc834x.c index fc21f5c15bab..156c4e218009 100644 --- a/arch/powerpc/platforms/83xx/sbc834x.c +++ b/arch/powerpc/platforms/83xx/sbc834x.c @@ -83,6 +83,7 @@ static void __init sbc834x_init_IRQ(void) static struct __initdata of_device_id sbc834x_ids[] = { { .type = "soc", }, { .compatible = "soc", }, + { .compatible = "simple-bus", }, {}, }; diff --git a/arch/powerpc/platforms/85xx/ksi8560.c b/arch/powerpc/platforms/85xx/ksi8560.c index 2145adeb220c..8a3b117b6ce2 100644 --- a/arch/powerpc/platforms/85xx/ksi8560.c +++ b/arch/powerpc/platforms/85xx/ksi8560.c @@ -222,6 +222,7 @@ static void ksi8560_show_cpuinfo(struct seq_file *m) static struct of_device_id __initdata of_bus_ids[] = { { .type = "soc", }, + { .type = "simple-bus", }, { .name = "cpm", }, { .name = "localbus", }, {}, diff --git a/arch/powerpc/platforms/85xx/mpc8536_ds.c b/arch/powerpc/platforms/85xx/mpc8536_ds.c index 6b846aa1ced9..1bf5aefdfeb1 100644 --- a/arch/powerpc/platforms/85xx/mpc8536_ds.c +++ b/arch/powerpc/platforms/85xx/mpc8536_ds.c @@ -91,6 +91,7 @@ static void __init mpc8536_ds_setup_arch(void) static struct of_device_id __initdata mpc8536_ds_ids[] = { { .type = "soc", }, { .compatible = "soc", }, + { .compatible = "simple-bus", }, {}, }; diff --git a/arch/powerpc/platforms/85xx/mpc85xx_ads.c b/arch/powerpc/platforms/85xx/mpc85xx_ads.c index ba498d6f2d02..d17807a6b89a 100644 --- a/arch/powerpc/platforms/85xx/mpc85xx_ads.c +++ b/arch/powerpc/platforms/85xx/mpc85xx_ads.c @@ -230,6 +230,7 @@ static struct of_device_id __initdata of_bus_ids[] = { { .type = "soc", }, { .name = "cpm", }, { .name = "localbus", }, + { .compatible = "simple-bus", }, {}, }; diff --git a/arch/powerpc/platforms/85xx/mpc85xx_ds.c b/arch/powerpc/platforms/85xx/mpc85xx_ds.c index 00c535806647..483b65cbabae 100644 --- a/arch/powerpc/platforms/85xx/mpc85xx_ds.c +++ b/arch/powerpc/platforms/85xx/mpc85xx_ds.c @@ -186,6 +186,7 @@ static int __init mpc8544_ds_probe(void) static struct of_device_id __initdata mpc85xxds_ids[] = { { .type = "soc", }, { .compatible = "soc", }, + { .compatible = "simple-bus", }, {}, }; diff --git a/arch/powerpc/platforms/85xx/mpc85xx_mds.c b/arch/powerpc/platforms/85xx/mpc85xx_mds.c index 43a459f63e31..2494c5155919 100644 --- a/arch/powerpc/platforms/85xx/mpc85xx_mds.c +++ b/arch/powerpc/platforms/85xx/mpc85xx_mds.c @@ -260,6 +260,7 @@ machine_arch_initcall(mpc85xx_mds, board_fixups); static struct of_device_id mpc85xx_ids[] = { { .type = "soc", }, { .compatible = "soc", }, + { .compatible = "simple-bus", }, { .type = "qe", }, { .compatible = "fsl,qe", }, {}, diff --git a/arch/powerpc/platforms/85xx/sbc8560.c b/arch/powerpc/platforms/85xx/sbc8560.c index 2c580cd24e4f..6509ade71668 100644 --- a/arch/powerpc/platforms/85xx/sbc8560.c +++ b/arch/powerpc/platforms/85xx/sbc8560.c @@ -217,6 +217,7 @@ static struct of_device_id __initdata of_bus_ids[] = { { .type = "soc", }, { .name = "cpm", }, { .name = "localbus", }, + { .compatible = "simple-bus", }, {}, }; diff --git a/arch/powerpc/platforms/86xx/mpc86xx_smp.c b/arch/powerpc/platforms/86xx/mpc86xx_smp.c index 835f2dc24dc9..014e26cda08d 100644 --- a/arch/powerpc/platforms/86xx/mpc86xx_smp.c +++ b/arch/powerpc/platforms/86xx/mpc86xx_smp.c @@ -19,7 +19,7 @@ #include <asm/page.h> #include <asm/pgtable.h> #include <asm/pci-bridge.h> -#include <asm-powerpc/mpic.h> +#include <asm/mpic.h> #include <asm/mpc86xx.h> #include <asm/cacheflush.h> diff --git a/arch/powerpc/platforms/8xx/Kconfig b/arch/powerpc/platforms/8xx/Kconfig index 6fc849e51e48..71d7562e190b 100644 --- a/arch/powerpc/platforms/8xx/Kconfig +++ b/arch/powerpc/platforms/8xx/Kconfig @@ -105,6 +105,16 @@ config 8xx_COPYBACK If in doubt, say Y here. +config 8xx_GPIO + bool "GPIO API Support" + select GENERIC_GPIO + select ARCH_REQUIRE_GPIOLIB + help + Saying Y here will cause the ports on an MPC8xx processor to be used + with the GPIO API. If you say N here, the kernel needs less memory. + + If in doubt, say Y here. + config 8xx_CPU6 bool "CPU6 Silicon Errata (860 Pre Rev. C)" help diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig index 1d0968775c0a..4c900efa164e 100644 --- a/arch/powerpc/platforms/Kconfig +++ b/arch/powerpc/platforms/Kconfig @@ -254,6 +254,8 @@ config CPM2 select CPM select PPC_LIB_RHEAP select PPC_PCI_CHOICE + select ARCH_REQUIRE_GPIOLIB + select GENERIC_GPIO help The CPM2 (Communications Processor Module) is a coprocessor on embedded CPUs made by Freescale. Selecting this option means that @@ -281,6 +283,7 @@ config FSL_ULI1575 config CPM bool + select PPC_CLOCK config OF_RTC bool diff --git a/arch/powerpc/platforms/Makefile b/arch/powerpc/platforms/Makefile index 423a0234dc31..8079e0b4fd69 100644 --- a/arch/powerpc/platforms/Makefile +++ b/arch/powerpc/platforms/Makefile @@ -1,13 +1,7 @@ obj-$(CONFIG_FSL_ULI1575) += fsl_uli1575.o -ifeq ($(CONFIG_PPC_MERGE),y) obj-$(CONFIG_PPC_PMAC) += powermac/ -else -ifeq ($(CONFIG_PPC64),y) -obj-$(CONFIG_PPC_PMAC) += powermac/ -endif -endif obj-$(CONFIG_PPC_CHRP) += chrp/ obj-$(CONFIG_40x) += 40x/ obj-$(CONFIG_44x) += 44x/ diff --git a/arch/powerpc/platforms/cell/cbe_cpufreq_pmi.c b/arch/powerpc/platforms/cell/cbe_cpufreq_pmi.c index 69288f653144..3233fe84d158 100644 --- a/arch/powerpc/platforms/cell/cbe_cpufreq_pmi.c +++ b/arch/powerpc/platforms/cell/cbe_cpufreq_pmi.c @@ -96,6 +96,12 @@ static int pmi_notifier(struct notifier_block *nb, struct cpufreq_frequency_table *cbe_freqs; u8 node; + /* Should this really be called for CPUFREQ_ADJUST, CPUFREQ_INCOMPATIBLE + * and CPUFREQ_NOTIFY policy events?) + */ + if (event == CPUFREQ_START) + return 0; + cbe_freqs = cpufreq_frequency_get_table(policy->cpu); node = cbe_cpu_to_node(policy->cpu); diff --git a/arch/powerpc/platforms/cell/celleb_scc_pciex.c b/arch/powerpc/platforms/cell/celleb_scc_pciex.c index 0e04f8fb152a..3e7e0f1568ef 100644 --- a/arch/powerpc/platforms/cell/celleb_scc_pciex.c +++ b/arch/powerpc/platforms/cell/celleb_scc_pciex.c @@ -281,7 +281,7 @@ static int __init scc_pciex_iowa_init(struct iowa_bus *bus, void *data) dummy_page_da = dma_map_single(bus->phb->parent, dummy_page_va, PAGE_SIZE, DMA_FROM_DEVICE); - if (dma_mapping_error(dummy_page_da)) { + if (dma_mapping_error(bus->phb->parent, dummy_page_da)) { pr_err("PCIEX:Map dummy page failed.\n"); kfree(dummy_page_va); return -1; diff --git a/arch/powerpc/platforms/cell/iommu.c b/arch/powerpc/platforms/cell/iommu.c index 208005ca262c..e06420af5fe9 100644 --- a/arch/powerpc/platforms/cell/iommu.c +++ b/arch/powerpc/platforms/cell/iommu.c @@ -172,7 +172,7 @@ static void invalidate_tce_cache(struct cbe_iommu *iommu, unsigned long *pte, } } -static void tce_build_cell(struct iommu_table *tbl, long index, long npages, +static int tce_build_cell(struct iommu_table *tbl, long index, long npages, unsigned long uaddr, enum dma_data_direction direction, struct dma_attrs *attrs) { @@ -213,6 +213,7 @@ static void tce_build_cell(struct iommu_table *tbl, long index, long npages, pr_debug("tce_build_cell(index=%lx,n=%lx,dir=%d,base_pte=%lx)\n", index, npages, direction, base_pte); + return 0; } static void tce_free_cell(struct iommu_table *tbl, long index, long npages) @@ -1150,12 +1151,23 @@ static int iommu_fixed_disabled; static int __init setup_iommu_fixed(char *str) { + struct device_node *pciep; + if (strcmp(str, "off") == 0) iommu_fixed_disabled = 1; - else if (strcmp(str, "weak") == 0) + /* If we can find a pcie-endpoint in the device tree assume that + * we're on a triblade or a CAB so by default the fixed mapping + * should be set to be weakly ordered; but only if the boot + * option WASN'T set for strong ordering + */ + pciep = of_find_node_by_type(NULL, "pcie-endpoint"); + + if (strcmp(str, "weak") == 0 || (pciep && strcmp(str, "strong") != 0)) iommu_fixed_is_weak = 1; + of_node_put(pciep); + return 1; } __setup("iommu_fixed=", setup_iommu_fixed); diff --git a/arch/powerpc/platforms/cell/spider-pci.c b/arch/powerpc/platforms/cell/spider-pci.c index 418b605ac35a..5122ec145271 100644 --- a/arch/powerpc/platforms/cell/spider-pci.c +++ b/arch/powerpc/platforms/cell/spider-pci.c @@ -111,7 +111,7 @@ static int __init spiderpci_pci_setup_chip(struct pci_controller *phb, dummy_page_da = dma_map_single(phb->parent, dummy_page_va, PAGE_SIZE, DMA_FROM_DEVICE); - if (dma_mapping_error(dummy_page_da)) { + if (dma_mapping_error(phb->parent, dummy_page_da)) { pr_err("SPIDER-IOWA:Map dummy page filed.\n"); kfree(dummy_page_va); return -1; diff --git a/arch/powerpc/platforms/cell/spufs/file.c b/arch/powerpc/platforms/cell/spufs/file.c index 99c73066b82f..010a51f59796 100644 --- a/arch/powerpc/platforms/cell/spufs/file.c +++ b/arch/powerpc/platforms/cell/spufs/file.c @@ -288,9 +288,32 @@ spufs_mem_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf) return VM_FAULT_NOPAGE; } +static int spufs_mem_mmap_access(struct vm_area_struct *vma, + unsigned long address, + void *buf, int len, int write) +{ + struct spu_context *ctx = vma->vm_file->private_data; + unsigned long offset = address - vma->vm_start; + char *local_store; + + if (write && !(vma->vm_flags & VM_WRITE)) + return -EACCES; + if (spu_acquire(ctx)) + return -EINTR; + if ((offset + len) > vma->vm_end) + len = vma->vm_end - offset; + local_store = ctx->ops->get_ls(ctx); + if (write) + memcpy_toio(local_store + offset, buf, len); + else + memcpy_fromio(buf, local_store + offset, len); + spu_release(ctx); + return len; +} static struct vm_operations_struct spufs_mem_mmap_vmops = { .fault = spufs_mem_mmap_fault, + .access = spufs_mem_mmap_access, }; static int spufs_mem_mmap(struct file *file, struct vm_area_struct *vma) diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c index 7123472801d9..690ca7b0dcf6 100644 --- a/arch/powerpc/platforms/cell/spufs/inode.c +++ b/arch/powerpc/platforms/cell/spufs/inode.c @@ -78,7 +78,7 @@ spufs_destroy_inode(struct inode *inode) } static void -spufs_init_once(struct kmem_cache *cachep, void *p) +spufs_init_once(void *p) { struct spufs_inode_info *ei = p; diff --git a/arch/powerpc/platforms/cell/spufs/run.c b/arch/powerpc/platforms/cell/spufs/run.c index f7edba6cb795..c9bb7cfd3dca 100644 --- a/arch/powerpc/platforms/cell/spufs/run.c +++ b/arch/powerpc/platforms/cell/spufs/run.c @@ -206,11 +206,6 @@ static int spu_run_init(struct spu_context *ctx, u32 *npc) (SPU_RUNCNTL_RUNNABLE | SPU_RUNCNTL_ISOLATE); if (runcntl == 0) runcntl = SPU_RUNCNTL_RUNNABLE; - } - - if (ctx->flags & SPU_CREATE_NOSCHED) { - spuctx_switch_state(ctx, SPU_UTIL_USER); - ctx->ops->runcntl_write(ctx, runcntl); } else { unsigned long privcntl; @@ -219,9 +214,15 @@ static int spu_run_init(struct spu_context *ctx, u32 *npc) else privcntl = SPU_PRIVCNTL_MODE_NORMAL; - ctx->ops->npc_write(ctx, *npc); ctx->ops->privcntl_write(ctx, privcntl); - ctx->ops->runcntl_write(ctx, runcntl); + ctx->ops->npc_write(ctx, *npc); + } + + ctx->ops->runcntl_write(ctx, runcntl); + + if (ctx->flags & SPU_CREATE_NOSCHED) { + spuctx_switch_state(ctx, SPU_UTIL_USER); + } else { if (ctx->state == SPU_STATE_SAVED) { ret = spu_activate(ctx, 0); diff --git a/arch/powerpc/platforms/cell/spufs/sched.c b/arch/powerpc/platforms/cell/spufs/sched.c index 34654743363d..67595bc380dc 100644 --- a/arch/powerpc/platforms/cell/spufs/sched.c +++ b/arch/powerpc/platforms/cell/spufs/sched.c @@ -312,11 +312,28 @@ static struct spu *aff_ref_location(struct spu_context *ctx, int mem_aff, */ node = cpu_to_node(raw_smp_processor_id()); for (n = 0; n < MAX_NUMNODES; n++, node++) { + int available_spus; + node = (node < MAX_NUMNODES) ? node : 0; if (!node_allowed(ctx, node)) continue; + + available_spus = 0; mutex_lock(&cbe_spu_info[node].list_mutex); list_for_each_entry(spu, &cbe_spu_info[node].spus, cbe_list) { + if (spu->ctx && spu->ctx->gang + && spu->ctx->aff_offset == 0) + available_spus -= + (spu->ctx->gang->contexts - 1); + else + available_spus++; + } + if (available_spus < ctx->gang->contexts) { + mutex_unlock(&cbe_spu_info[node].list_mutex); + continue; + } + + list_for_each_entry(spu, &cbe_spu_info[node].spus, cbe_list) { if ((!mem_aff || spu->has_mem_affinity) && sched_spu(spu)) { mutex_unlock(&cbe_spu_info[node].list_mutex); @@ -389,6 +406,9 @@ static int has_affinity(struct spu_context *ctx) if (list_empty(&ctx->aff_list)) return 0; + if (atomic_read(&ctx->gang->aff_sched_count) == 0) + ctx->gang->aff_ref_spu = NULL; + if (!gang->aff_ref_spu) { if (!(gang->aff_flags & AFF_MERGED)) aff_merge_remaining_ctxs(gang); @@ -416,14 +436,8 @@ static void spu_unbind_context(struct spu *spu, struct spu_context *ctx) if (spu->ctx->flags & SPU_CREATE_NOSCHED) atomic_dec(&cbe_spu_info[spu->node].reserved_spus); - if (ctx->gang){ - mutex_lock(&ctx->gang->aff_mutex); - if (has_affinity(ctx)) { - if (atomic_dec_and_test(&ctx->gang->aff_sched_count)) - ctx->gang->aff_ref_spu = NULL; - } - mutex_unlock(&ctx->gang->aff_mutex); - } + if (ctx->gang) + atomic_dec_if_positive(&ctx->gang->aff_sched_count); spu_switch_notify(spu, NULL); spu_unmap_mappings(ctx); @@ -562,10 +576,7 @@ static struct spu *spu_get_idle(struct spu_context *ctx) goto found; mutex_unlock(&cbe_spu_info[node].list_mutex); - mutex_lock(&ctx->gang->aff_mutex); - if (atomic_dec_and_test(&ctx->gang->aff_sched_count)) - ctx->gang->aff_ref_spu = NULL; - mutex_unlock(&ctx->gang->aff_mutex); + atomic_dec(&ctx->gang->aff_sched_count); goto not_found; } mutex_unlock(&ctx->gang->aff_mutex); @@ -630,9 +641,12 @@ static struct spu *find_victim(struct spu_context *ctx) if (tmp && tmp->prio > ctx->prio && !(tmp->flags & SPU_CREATE_NOSCHED) && - (!victim || tmp->prio > victim->prio)) + (!victim || tmp->prio > victim->prio)) { victim = spu->ctx; + } } + if (victim) + get_spu_context(victim); mutex_unlock(&cbe_spu_info[node].list_mutex); if (victim) { @@ -647,6 +661,7 @@ static struct spu *find_victim(struct spu_context *ctx) * look at another context or give up after X retries. */ if (!mutex_trylock(&victim->state_mutex)) { + put_spu_context(victim); victim = NULL; goto restart; } @@ -659,6 +674,7 @@ static struct spu *find_victim(struct spu_context *ctx) * restart the search. */ mutex_unlock(&victim->state_mutex); + put_spu_context(victim); victim = NULL; goto restart; } @@ -676,6 +692,7 @@ static struct spu *find_victim(struct spu_context *ctx) spu_add_to_rq(victim); mutex_unlock(&victim->state_mutex); + put_spu_context(victim); return spu; } @@ -711,17 +728,33 @@ static void spu_schedule(struct spu *spu, struct spu_context *ctx) /* not a candidate for interruptible because it's called either from the scheduler thread or from spu_deactivate */ mutex_lock(&ctx->state_mutex); - __spu_schedule(spu, ctx); + if (ctx->state == SPU_STATE_SAVED) + __spu_schedule(spu, ctx); spu_release(ctx); } -static void spu_unschedule(struct spu *spu, struct spu_context *ctx) +/** + * spu_unschedule - remove a context from a spu, and possibly release it. + * @spu: The SPU to unschedule from + * @ctx: The context currently scheduled on the SPU + * @free_spu Whether to free the SPU for other contexts + * + * Unbinds the context @ctx from the SPU @spu. If @free_spu is non-zero, the + * SPU is made available for other contexts (ie, may be returned by + * spu_get_idle). If this is zero, the caller is expected to schedule another + * context to this spu. + * + * Should be called with ctx->state_mutex held. + */ +static void spu_unschedule(struct spu *spu, struct spu_context *ctx, + int free_spu) { int node = spu->node; mutex_lock(&cbe_spu_info[node].list_mutex); cbe_spu_info[node].nr_active--; - spu->alloc_state = SPU_FREE; + if (free_spu) + spu->alloc_state = SPU_FREE; spu_unbind_context(spu, ctx); ctx->stats.invol_ctx_switch++; spu->stats.invol_ctx_switch++; @@ -821,7 +854,7 @@ static int __spu_deactivate(struct spu_context *ctx, int force, int max_prio) if (spu) { new = grab_runnable_context(max_prio, spu->node); if (new || force) { - spu_unschedule(spu, ctx); + spu_unschedule(spu, ctx, new == NULL); if (new) { if (new->flags & SPU_CREATE_NOSCHED) wake_up(&new->stop_wq); @@ -894,7 +927,7 @@ static noinline void spusched_tick(struct spu_context *ctx) new = grab_runnable_context(ctx->prio + 1, spu->node); if (new) { - spu_unschedule(spu, ctx); + spu_unschedule(spu, ctx, 0); if (test_bit(SPU_SCHED_SPU_RUN, &ctx->sched_flags)) spu_add_to_rq(ctx); } else { @@ -974,9 +1007,11 @@ static int spusched_thread(void *unused) struct spu_context *ctx = spu->ctx; if (ctx) { + get_spu_context(ctx); mutex_unlock(mtx); spusched_tick(ctx); mutex_lock(mtx); + put_spu_context(ctx); } } mutex_unlock(mtx); @@ -1019,7 +1054,7 @@ void spuctx_switch_state(struct spu_context *ctx, node = spu->node; if (old_state == SPU_UTIL_USER) atomic_dec(&cbe_spu_info[node].busy_spus); - if (new_state == SPU_UTIL_USER); + if (new_state == SPU_UTIL_USER) atomic_inc(&cbe_spu_info[node].busy_spus); } } diff --git a/arch/powerpc/platforms/cell/spufs/sputrace.c b/arch/powerpc/platforms/cell/spufs/sputrace.c index 8c0e95766a62..92d20e993ede 100644 --- a/arch/powerpc/platforms/cell/spufs/sputrace.c +++ b/arch/powerpc/platforms/cell/spufs/sputrace.c @@ -196,8 +196,7 @@ static int __init sputrace_init(void) struct proc_dir_entry *entry; int i, error = -ENOMEM; - sputrace_log = kcalloc(sizeof(struct sputrace), - bufsize, GFP_KERNEL); + sputrace_log = kcalloc(bufsize, sizeof(struct sputrace), GFP_KERNEL); if (!sputrace_log) goto out; diff --git a/arch/powerpc/platforms/iseries/Kconfig b/arch/powerpc/platforms/iseries/Kconfig index ea3e541ac74f..45ffd8e542f4 100644 --- a/arch/powerpc/platforms/iseries/Kconfig +++ b/arch/powerpc/platforms/iseries/Kconfig @@ -7,15 +7,6 @@ config PPC_ISERIES menu "iSeries device drivers" depends on PPC_ISERIES -config VIOCONS - bool "iSeries Virtual Console Support (Obsolete)" - depends on !HVC_ISERIES - default n - help - This is the old virtual console driver for legacy iSeries. - You should use the iSeries Hypervisor Virtual Console - support instead. - config VIODASD tristate "iSeries Virtual I/O disk support" help @@ -38,5 +29,5 @@ endmenu config VIOPATH bool - depends on VIOCONS || VIODASD || VIOCD || VIOTAPE || ISERIES_VETH + depends on VIODASD || VIOCD || VIOTAPE || ISERIES_VETH default y diff --git a/arch/powerpc/platforms/iseries/iommu.c b/arch/powerpc/platforms/iseries/iommu.c index bc818e4e2033..bb464d1211b2 100644 --- a/arch/powerpc/platforms/iseries/iommu.c +++ b/arch/powerpc/platforms/iseries/iommu.c @@ -41,7 +41,7 @@ #include <asm/iseries/hv_call_event.h> #include <asm/iseries/iommu.h> -static void tce_build_iSeries(struct iommu_table *tbl, long index, long npages, +static int tce_build_iSeries(struct iommu_table *tbl, long index, long npages, unsigned long uaddr, enum dma_data_direction direction, struct dma_attrs *attrs) { @@ -71,6 +71,7 @@ static void tce_build_iSeries(struct iommu_table *tbl, long index, long npages, index++; uaddr += TCE_PAGE_SIZE; } + return 0; } static void tce_free_iSeries(struct iommu_table *tbl, long index, long npages) diff --git a/arch/powerpc/platforms/iseries/mf.c b/arch/powerpc/platforms/iseries/mf.c index 1dc7295746da..731d7b157749 100644 --- a/arch/powerpc/platforms/iseries/mf.c +++ b/arch/powerpc/platforms/iseries/mf.c @@ -871,7 +871,7 @@ static int proc_mf_dump_cmdline(char *page, char **start, off_t off, count = 256 - off; dma_addr = iseries_hv_map(page, off + count, DMA_FROM_DEVICE); - if (dma_mapping_error(dma_addr)) + if (dma_mapping_error(NULL, dma_addr)) return -ENOMEM; memset(page, 0, off + count); memset(&vsp_cmd, 0, sizeof(vsp_cmd)); diff --git a/arch/powerpc/platforms/iseries/setup.c b/arch/powerpc/platforms/iseries/setup.c index b72120751bbe..70b688c1aefb 100644 --- a/arch/powerpc/platforms/iseries/setup.c +++ b/arch/powerpc/platforms/iseries/setup.c @@ -561,7 +561,7 @@ static void yield_shared_processor(void) static void iseries_shared_idle(void) { while (1) { - tick_nohz_stop_sched_tick(); + tick_nohz_stop_sched_tick(1); while (!need_resched() && !hvlpevent_is_pending()) { local_irq_disable(); ppc64_runlatch_off(); @@ -591,7 +591,7 @@ static void iseries_dedicated_idle(void) set_thread_flag(TIF_POLLING_NRFLAG); while (1) { - tick_nohz_stop_sched_tick(); + tick_nohz_stop_sched_tick(1); if (!need_resched()) { while (!need_resched()) { ppc64_runlatch_off(); diff --git a/arch/powerpc/platforms/pasemi/iommu.c b/arch/powerpc/platforms/pasemi/iommu.c index 70541b7a5013..a0ff03a3d8da 100644 --- a/arch/powerpc/platforms/pasemi/iommu.c +++ b/arch/powerpc/platforms/pasemi/iommu.c @@ -83,7 +83,7 @@ static u32 *iob_l2_base; static struct iommu_table iommu_table_iobmap; static int iommu_table_iobmap_inited; -static void iobmap_build(struct iommu_table *tbl, long index, +static int iobmap_build(struct iommu_table *tbl, long index, long npages, unsigned long uaddr, enum dma_data_direction direction, struct dma_attrs *attrs) @@ -108,6 +108,7 @@ static void iobmap_build(struct iommu_table *tbl, long index, uaddr += IOBMAP_PAGE_SIZE; bus_addr += IOBMAP_PAGE_SIZE; } + return 0; } diff --git a/arch/powerpc/platforms/powermac/Makefile b/arch/powerpc/platforms/powermac/Makefile index 89774177b209..be60d64be7ad 100644 --- a/arch/powerpc/platforms/powermac/Makefile +++ b/arch/powerpc/platforms/powermac/Makefile @@ -2,12 +2,12 @@ CFLAGS_bootx_init.o += -fPIC ifdef CONFIG_FTRACE # Do not trace early boot code -CFLAGS_REMOVE_bootx_init.o = -pg +CFLAGS_REMOVE_bootx_init.o = -pg -mno-sched-epilog endif obj-y += pic.o setup.o time.o feature.o pci.o \ sleep.o low_i2c.o cache.o pfunc_core.o \ - pfunc_base.o + pfunc_base.o udbg_scc.o udbg_adb.o obj-$(CONFIG_PMAC_BACKLIGHT) += backlight.o obj-$(CONFIG_CPU_FREQ_PMAC) += cpufreq_32.o obj-$(CONFIG_CPU_FREQ_PMAC64) += cpufreq_64.o @@ -19,4 +19,3 @@ obj-$(CONFIG_NVRAM:m=y) += nvram.o obj-$(CONFIG_PPC64) += nvram.o obj-$(CONFIG_PPC32) += bootx_init.o obj-$(CONFIG_SMP) += smp.o -obj-$(CONFIG_PPC_MERGE) += udbg_scc.o udbg_adb.o diff --git a/arch/powerpc/platforms/powermac/setup.c b/arch/powerpc/platforms/powermac/setup.c index 31635446901a..88ccf3a08a9c 100644 --- a/arch/powerpc/platforms/powermac/setup.c +++ b/arch/powerpc/platforms/powermac/setup.c @@ -541,6 +541,78 @@ static int __init pmac_declare_of_platform_devices(void) } machine_device_initcall(powermac, pmac_declare_of_platform_devices); +#ifdef CONFIG_SERIAL_PMACZILOG_CONSOLE +/* + * This is called very early, as part of console_init() (typically just after + * time_init()). This function is respondible for trying to find a good + * default console on serial ports. It tries to match the open firmware + * default output with one of the available serial console drivers. + */ +static int __init check_pmac_serial_console(void) +{ + struct device_node *prom_stdout = NULL; + int offset = 0; + const char *name; +#ifdef CONFIG_SERIAL_PMACZILOG_TTYS + char *devname = "ttyS"; +#else + char *devname = "ttyPZ"; +#endif + + pr_debug(" -> check_pmac_serial_console()\n"); + + /* The user has requested a console so this is already set up. */ + if (strstr(boot_command_line, "console=")) { + pr_debug(" console was specified !\n"); + return -EBUSY; + } + + if (!of_chosen) { + pr_debug(" of_chosen is NULL !\n"); + return -ENODEV; + } + + /* We are getting a weird phandle from OF ... */ + /* ... So use the full path instead */ + name = of_get_property(of_chosen, "linux,stdout-path", NULL); + if (name == NULL) { + pr_debug(" no linux,stdout-path !\n"); + return -ENODEV; + } + prom_stdout = of_find_node_by_path(name); + if (!prom_stdout) { + pr_debug(" can't find stdout package %s !\n", name); + return -ENODEV; + } + pr_debug("stdout is %s\n", prom_stdout->full_name); + + name = of_get_property(prom_stdout, "name", NULL); + if (!name) { + pr_debug(" stdout package has no name !\n"); + goto not_found; + } + + if (strcmp(name, "ch-a") == 0) + offset = 0; + else if (strcmp(name, "ch-b") == 0) + offset = 1; + else + goto not_found; + of_node_put(prom_stdout); + + pr_debug("Found serial console at %s%d\n", devname, offset); + + return add_preferred_console(devname, offset, NULL); + + not_found: + pr_debug("No preferred console found !\n"); + of_node_put(prom_stdout); + return -ENODEV; +} +console_initcall(check_pmac_serial_console); + +#endif /* CONFIG_SERIAL_PMACZILOG_CONSOLE */ + /* * Called very early, MMU is off, device-tree isn't unflattened */ diff --git a/arch/powerpc/platforms/powermac/udbg_scc.c b/arch/powerpc/platforms/powermac/udbg_scc.c index 47de4d3fc167..572771fd8463 100644 --- a/arch/powerpc/platforms/powermac/udbg_scc.c +++ b/arch/powerpc/platforms/powermac/udbg_scc.c @@ -125,13 +125,23 @@ void udbg_scc_init(int force_scc) out_8(sccc, 0xc0); /* If SCC was the OF output port, read the BRG value, else - * Setup for 57600 8N1 + * Setup for 38400 or 57600 8N1 depending on the machine */ if (ch_def != NULL) { out_8(sccc, 13); scc_inittab[1] = in_8(sccc); out_8(sccc, 12); scc_inittab[3] = in_8(sccc); + } else if (machine_is_compatible("RackMac1,1") + || machine_is_compatible("RackMac1,2") + || machine_is_compatible("MacRISC4")) { + /* Xserves and G5s default to 57600 */ + scc_inittab[1] = 0; + scc_inittab[3] = 0; + } else { + /* Others default to 38400 */ + scc_inittab[1] = 0; + scc_inittab[3] = 1; } for (i = 0; i < sizeof(scc_inittab); ++i) diff --git a/arch/powerpc/platforms/ps3/htab.c b/arch/powerpc/platforms/ps3/htab.c index 1cf901fa9031..6eb1d4d182c9 100644 --- a/arch/powerpc/platforms/ps3/htab.c +++ b/arch/powerpc/platforms/ps3/htab.c @@ -29,138 +29,75 @@ #include "platform.h" -#if defined(DEBUG) -#define DBG udbg_printf -#else -#define DBG pr_debug -#endif - -static struct hash_pte *htab; -static unsigned long htab_addr; -static unsigned char *bolttab; -static unsigned char *inusetab; - -static DEFINE_SPINLOCK(ps3_bolttab_lock); - -#define debug_dump_hpte(_a, _b, _c, _d, _e, _f, _g) \ - _debug_dump_hpte(_a, _b, _c, _d, _e, _f, _g, __func__, __LINE__) -static void _debug_dump_hpte(unsigned long pa, unsigned long va, - unsigned long group, unsigned long bitmap, struct hash_pte lhpte, - int psize, unsigned long slot, const char* func, int line) -{ - DBG("%s:%d: pa = %lxh\n", func, line, pa); - DBG("%s:%d: lpar = %lxh\n", func, line, - ps3_mm_phys_to_lpar(pa)); - DBG("%s:%d: va = %lxh\n", func, line, va); - DBG("%s:%d: group = %lxh\n", func, line, group); - DBG("%s:%d: bitmap = %lxh\n", func, line, bitmap); - DBG("%s:%d: hpte.v = %lxh\n", func, line, lhpte.v); - DBG("%s:%d: hpte.r = %lxh\n", func, line, lhpte.r); - DBG("%s:%d: psize = %xh\n", func, line, psize); - DBG("%s:%d: slot = %lxh\n", func, line, slot); -} +/** + * enum lpar_vas_id - id of LPAR virtual address space. + * @lpar_vas_id_current: Current selected virtual address space + * + * Identify the target LPAR address space. + */ + +enum ps3_lpar_vas_id { + PS3_LPAR_VAS_ID_CURRENT = 0, +}; + + +static DEFINE_SPINLOCK(ps3_htab_lock); static long ps3_hpte_insert(unsigned long hpte_group, unsigned long va, unsigned long pa, unsigned long rflags, unsigned long vflags, int psize, int ssize) { - unsigned long slot; - struct hash_pte lhpte; - int secondary = 0; - unsigned long result; - unsigned long bitmap; + int result; + u64 hpte_v, hpte_r; + u64 inserted_index; + u64 evicted_v, evicted_r; + u64 hpte_v_array[4], hpte_rs; unsigned long flags; - unsigned long p_pteg, s_pteg, b_index, b_mask, cb, ci; - - vflags &= ~HPTE_V_SECONDARY; /* this bit is ignored */ - - lhpte.v = hpte_encode_v(va, psize, MMU_SEGSIZE_256M) | - vflags | HPTE_V_VALID; - lhpte.r = hpte_encode_r(ps3_mm_phys_to_lpar(pa), psize) | rflags; - - p_pteg = hpte_group / HPTES_PER_GROUP; - s_pteg = ~p_pteg & htab_hash_mask; - - spin_lock_irqsave(&ps3_bolttab_lock, flags); - - BUG_ON(bolttab[p_pteg] == 0xff && bolttab[s_pteg] == 0xff); + long ret = -1; - bitmap = (inusetab[p_pteg] << 8) | inusetab[s_pteg]; + /* + * lv1_insert_htab_entry() will search for victim + * entry in both primary and secondary pte group + */ + vflags &= ~HPTE_V_SECONDARY; - if (bitmap == 0xffff) { - /* - * PTEG is full. Search for victim. - */ - bitmap &= ~((bolttab[p_pteg] << 8) | bolttab[s_pteg]); - do { - ci = mftb() & 15; - cb = 0x8000UL >> ci; - } while ((cb & bitmap) == 0); - } else { - /* - * search free slot in hardware order - * [primary] 0, 2, 4, 6, 1, 3, 5, 7 - * [secondary] 0, 2, 4, 6, 1, 3, 5, 7 - */ - for (ci = 0; ci < HPTES_PER_GROUP; ci += 2) { - cb = 0x8000UL >> ci; - if ((cb & bitmap) == 0) - goto found; - } - for (ci = 1; ci < HPTES_PER_GROUP; ci += 2) { - cb = 0x8000UL >> ci; - if ((cb & bitmap) == 0) - goto found; - } - for (ci = HPTES_PER_GROUP; ci < HPTES_PER_GROUP*2; ci += 2) { - cb = 0x8000UL >> ci; - if ((cb & bitmap) == 0) - goto found; - } - for (ci = HPTES_PER_GROUP+1; ci < HPTES_PER_GROUP*2; ci += 2) { - cb = 0x8000UL >> ci; - if ((cb & bitmap) == 0) - goto found; - } - } + hpte_v = hpte_encode_v(va, psize, ssize) | vflags | HPTE_V_VALID; + hpte_r = hpte_encode_r(ps3_mm_phys_to_lpar(pa), psize) | rflags; -found: - if (ci < HPTES_PER_GROUP) { - slot = p_pteg * HPTES_PER_GROUP + ci; - } else { - slot = s_pteg * HPTES_PER_GROUP + (ci & 7); - /* lhpte.dw0.dw0.h = 1; */ - vflags |= HPTE_V_SECONDARY; - lhpte.v |= HPTE_V_SECONDARY; - } + spin_lock_irqsave(&ps3_htab_lock, flags); - result = lv1_write_htab_entry(0, slot, lhpte.v, lhpte.r); + /* talk hvc to replace entries BOLTED == 0 */ + result = lv1_insert_htab_entry(PS3_LPAR_VAS_ID_CURRENT, hpte_group, + hpte_v, hpte_r, + HPTE_V_BOLTED, 0, + &inserted_index, + &evicted_v, &evicted_r); if (result) { - debug_dump_hpte(pa, va, hpte_group, bitmap, lhpte, psize, slot); + /* all entries bolted !*/ + pr_info("%s:result=%d va=%lx pa=%lx ix=%lx v=%lx r=%lx\n", + __func__, result, va, pa, hpte_group, hpte_v, hpte_r); BUG(); } /* - * If used slot is not in primary HPTE group, - * the slot should be in secondary HPTE group. + * see if the entry is inserted into secondary pteg */ + result = lv1_read_htab_entries(PS3_LPAR_VAS_ID_CURRENT, + inserted_index & ~0x3UL, + &hpte_v_array[0], &hpte_v_array[1], + &hpte_v_array[2], &hpte_v_array[3], + &hpte_rs); + BUG_ON(result); - if ((hpte_group ^ slot) & ~(HPTES_PER_GROUP - 1)) { - secondary = 1; - b_index = s_pteg; - } else { - secondary = 0; - b_index = p_pteg; - } + if (hpte_v_array[inserted_index % 4] & HPTE_V_SECONDARY) + ret = (inserted_index & 7) | (1 << 3); + else + ret = inserted_index & 7; - b_mask = (lhpte.v & HPTE_V_BOLTED) ? 1 << 7 : 0 << 7; - bolttab[b_index] |= b_mask >> (slot & 7); - b_mask = 1 << 7; - inusetab[b_index] |= b_mask >> (slot & 7); - spin_unlock_irqrestore(&ps3_bolttab_lock, flags); + spin_unlock_irqrestore(&ps3_htab_lock, flags); - return (slot & 7) | (secondary << 3); + return ret; } static long ps3_hpte_remove(unsigned long hpte_group) @@ -172,39 +109,48 @@ static long ps3_hpte_remove(unsigned long hpte_group) static long ps3_hpte_updatepp(unsigned long slot, unsigned long newpp, unsigned long va, int psize, int ssize, int local) { + int result; + u64 hpte_v, want_v, hpte_rs; + u64 hpte_v_array[4]; unsigned long flags; - unsigned long result; - unsigned long pteg, bit; - unsigned long hpte_v, want_v; + long ret; - want_v = hpte_encode_v(va, psize, MMU_SEGSIZE_256M); + want_v = hpte_encode_v(va, psize, ssize); - spin_lock_irqsave(&ps3_bolttab_lock, flags); + spin_lock_irqsave(&ps3_htab_lock, flags); - hpte_v = htab[slot].v; - if (!HPTE_V_COMPARE(hpte_v, want_v) || !(hpte_v & HPTE_V_VALID)) { - spin_unlock_irqrestore(&ps3_bolttab_lock, flags); - - /* ps3_hpte_insert() will be used to update PTE */ - return -1; - } - - result = lv1_write_htab_entry(0, slot, 0, 0); + result = lv1_read_htab_entries(PS3_LPAR_VAS_ID_CURRENT, slot & ~0x3UL, + &hpte_v_array[0], &hpte_v_array[1], + &hpte_v_array[2], &hpte_v_array[3], + &hpte_rs); if (result) { - DBG("%s: va=%lx slot=%lx psize=%d result = %ld (0x%lx)\n", - __func__, va, slot, psize, result, result); + pr_info("%s: res=%d read va=%lx slot=%lx psize=%d\n", + __func__, result, va, slot, psize); BUG(); } - pteg = slot / HPTES_PER_GROUP; - bit = slot % HPTES_PER_GROUP; - inusetab[pteg] &= ~(0x80 >> bit); + hpte_v = hpte_v_array[slot % 4]; - spin_unlock_irqrestore(&ps3_bolttab_lock, flags); + /* + * As lv1_read_htab_entries() does not give us the RPN, we can + * not synthesize the new hpte_r value here, and therefore can + * not update the hpte with lv1_insert_htab_entry(), so we + * insted invalidate it and ask the caller to update it via + * ps3_hpte_insert() by returning a -1 value. + */ + if (!HPTE_V_COMPARE(hpte_v, want_v) || !(hpte_v & HPTE_V_VALID)) { + /* not found */ + ret = -1; + } else { + /* entry found, just invalidate it */ + result = lv1_write_htab_entry(PS3_LPAR_VAS_ID_CURRENT, + slot, 0, 0); + ret = -1; + } - /* ps3_hpte_insert() will be used to update PTE */ - return -1; + spin_unlock_irqrestore(&ps3_htab_lock, flags); + return ret; } static void ps3_hpte_updateboltedpp(unsigned long newpp, unsigned long ea, @@ -217,45 +163,35 @@ static void ps3_hpte_invalidate(unsigned long slot, unsigned long va, int psize, int ssize, int local) { unsigned long flags; - unsigned long result; - unsigned long pteg, bit; + int result; + + spin_lock_irqsave(&ps3_htab_lock, flags); - spin_lock_irqsave(&ps3_bolttab_lock, flags); - result = lv1_write_htab_entry(0, slot, 0, 0); + result = lv1_write_htab_entry(PS3_LPAR_VAS_ID_CURRENT, slot, 0, 0); if (result) { - DBG("%s: va=%lx slot=%lx psize=%d result = %ld (0x%lx)\n", - __func__, va, slot, psize, result, result); + pr_info("%s: res=%d va=%lx slot=%lx psize=%d\n", + __func__, result, va, slot, psize); BUG(); } - pteg = slot / HPTES_PER_GROUP; - bit = slot % HPTES_PER_GROUP; - inusetab[pteg] &= ~(0x80 >> bit); - spin_unlock_irqrestore(&ps3_bolttab_lock, flags); + spin_unlock_irqrestore(&ps3_htab_lock, flags); } static void ps3_hpte_clear(void) { - int result; - - DBG(" -> %s:%d\n", __func__, __LINE__); + unsigned long hpte_count = (1UL << ppc64_pft_size) >> 4; + u64 i; - result = lv1_unmap_htab(htab_addr); - BUG_ON(result); + for (i = 0; i < hpte_count; i++) + lv1_write_htab_entry(PS3_LPAR_VAS_ID_CURRENT, i, 0, 0); ps3_mm_shutdown(); ps3_mm_vas_destroy(); - - DBG(" <- %s:%d\n", __func__, __LINE__); } void __init ps3_hpte_init(unsigned long htab_size) { - long bitmap_size; - - DBG(" -> %s:%d\n", __func__, __LINE__); - ppc_md.hpte_invalidate = ps3_hpte_invalidate; ppc_md.hpte_updatepp = ps3_hpte_updatepp; ppc_md.hpte_updateboltedpp = ps3_hpte_updateboltedpp; @@ -264,28 +200,5 @@ void __init ps3_hpte_init(unsigned long htab_size) ppc_md.hpte_clear_all = ps3_hpte_clear; ppc64_pft_size = __ilog2(htab_size); - - bitmap_size = htab_size / sizeof(struct hash_pte) / 8; - - bolttab = __va(lmb_alloc(bitmap_size, 1)); - inusetab = __va(lmb_alloc(bitmap_size, 1)); - - memset(bolttab, 0, bitmap_size); - memset(inusetab, 0, bitmap_size); - - DBG(" <- %s:%d\n", __func__, __LINE__); } -void __init ps3_map_htab(void) -{ - long result; - unsigned long htab_size = (1UL << ppc64_pft_size); - - result = lv1_map_htab(0, &htab_addr); - - htab = (__force struct hash_pte *)ioremap_flags(htab_addr, htab_size, - pgprot_val(PAGE_READONLY_X)); - - DBG("%s:%d: lpar %016lxh, virt %016lxh\n", __func__, __LINE__, - htab_addr, (unsigned long)htab); -} diff --git a/arch/powerpc/platforms/ps3/setup.c b/arch/powerpc/platforms/ps3/setup.c index a413abbd4123..77bc330263c4 100644 --- a/arch/powerpc/platforms/ps3/setup.c +++ b/arch/powerpc/platforms/ps3/setup.c @@ -201,7 +201,6 @@ static void __init ps3_setup_arch(void) ps3_firmware_version.rev); ps3_spu_set_platform(); - ps3_map_htab(); #ifdef CONFIG_SMP smp_init_ps3(); diff --git a/arch/powerpc/platforms/ps3/spu.c b/arch/powerpc/platforms/ps3/spu.c index d135cef9ed6a..ccae3d446b98 100644 --- a/arch/powerpc/platforms/ps3/spu.c +++ b/arch/powerpc/platforms/ps3/spu.c @@ -186,14 +186,24 @@ static void spu_unmap(struct spu *spu) iounmap(spu_pdata(spu)->shadow); } +/** + * setup_areas - Map the spu regions into the address space. + * + * The current HV requires the spu shadow regs to be mapped with the + * PTE page protection bits set as read-only (PP=3). This implementation + * uses the low level __ioremap() to bypass the page protection settings + * inforced by ioremap_flags() to get the needed PTE bits set for the + * shadow regs. + */ + static int __init setup_areas(struct spu *spu) { struct table {char* name; unsigned long addr; unsigned long size;}; + static const unsigned long shadow_flags = _PAGE_NO_CACHE | 3; - spu_pdata(spu)->shadow = ioremap_flags(spu_pdata(spu)->shadow_addr, - sizeof(struct spe_shadow), - pgprot_val(PAGE_READONLY) | - _PAGE_NO_CACHE); + spu_pdata(spu)->shadow = __ioremap(spu_pdata(spu)->shadow_addr, + sizeof(struct spe_shadow), + shadow_flags); if (!spu_pdata(spu)->shadow) { pr_debug("%s:%d: ioremap shadow failed\n", __func__, __LINE__); goto fail_ioremap; diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig index 757c0296e0b8..97619fd51e39 100644 --- a/arch/powerpc/platforms/pseries/Kconfig +++ b/arch/powerpc/platforms/pseries/Kconfig @@ -40,3 +40,26 @@ config PPC_PSERIES_DEBUG depends on PPC_PSERIES && PPC_EARLY_DEBUG bool "Enable extra debug logging in platforms/pseries" default y + +config PPC_SMLPAR + bool "Support for shared-memory logical partitions" + depends on PPC_PSERIES + select LPARCFG + default n + help + Select this option to enable shared memory partition support. + With this option a system running in an LPAR can be given more + memory than physically available and will allow firmware to + balance memory across many LPARs. + +config CMM + tristate "Collaborative memory management" + depends on PPC_SMLPAR + default y + help + Select this option, if you want to enable the kernel interface + to reduce the memory size of the system. This is accomplished + by allocating pages of memory and put them "on hold". This only + makes sense for a system running in an LPAR where the unused pages + will be reused for other LPARs. The interface allows firmware to + balance memory across many LPARs. diff --git a/arch/powerpc/platforms/pseries/Makefile b/arch/powerpc/platforms/pseries/Makefile index 554c6e42ef2a..dfe574af2dc0 100644 --- a/arch/powerpc/platforms/pseries/Makefile +++ b/arch/powerpc/platforms/pseries/Makefile @@ -24,3 +24,4 @@ obj-$(CONFIG_HVC_CONSOLE) += hvconsole.o obj-$(CONFIG_HVCS) += hvcserver.o obj-$(CONFIG_HCALL_STATS) += hvCall_inst.o obj-$(CONFIG_PHYP_DUMP) += phyp_dump.o +obj-$(CONFIG_CMM) += cmm.o diff --git a/arch/powerpc/platforms/pseries/cmm.c b/arch/powerpc/platforms/pseries/cmm.c new file mode 100644 index 000000000000..38fe32a7cc70 --- /dev/null +++ b/arch/powerpc/platforms/pseries/cmm.c @@ -0,0 +1,472 @@ +/* + * Collaborative memory management interface. + * + * Copyright (C) 2008 IBM Corporation + * Author(s): Brian King (brking@linux.vnet.ibm.com), + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * + */ + +#include <linux/ctype.h> +#include <linux/delay.h> +#include <linux/errno.h> +#include <linux/fs.h> +#include <linux/init.h> +#include <linux/kthread.h> +#include <linux/module.h> +#include <linux/oom.h> +#include <linux/sched.h> +#include <linux/stringify.h> +#include <linux/swap.h> +#include <linux/sysdev.h> +#include <asm/firmware.h> +#include <asm/hvcall.h> +#include <asm/mmu.h> +#include <asm/pgalloc.h> +#include <asm/uaccess.h> + +#include "plpar_wrappers.h" + +#define CMM_DRIVER_VERSION "1.0.0" +#define CMM_DEFAULT_DELAY 1 +#define CMM_DEBUG 0 +#define CMM_DISABLE 0 +#define CMM_OOM_KB 1024 +#define CMM_MIN_MEM_MB 256 +#define KB2PAGES(_p) ((_p)>>(PAGE_SHIFT-10)) +#define PAGES2KB(_p) ((_p)<<(PAGE_SHIFT-10)) + +static unsigned int delay = CMM_DEFAULT_DELAY; +static unsigned int oom_kb = CMM_OOM_KB; +static unsigned int cmm_debug = CMM_DEBUG; +static unsigned int cmm_disabled = CMM_DISABLE; +static unsigned long min_mem_mb = CMM_MIN_MEM_MB; +static struct sys_device cmm_sysdev; + +MODULE_AUTHOR("Brian King <brking@linux.vnet.ibm.com>"); +MODULE_DESCRIPTION("IBM System p Collaborative Memory Manager"); +MODULE_LICENSE("GPL"); +MODULE_VERSION(CMM_DRIVER_VERSION); + +module_param_named(delay, delay, uint, S_IRUGO | S_IWUSR); +MODULE_PARM_DESC(delay, "Delay (in seconds) between polls to query hypervisor paging requests. " + "[Default=" __stringify(CMM_DEFAULT_DELAY) "]"); +module_param_named(oom_kb, oom_kb, uint, S_IRUGO | S_IWUSR); +MODULE_PARM_DESC(oom_kb, "Amount of memory in kb to free on OOM. " + "[Default=" __stringify(CMM_OOM_KB) "]"); +module_param_named(min_mem_mb, min_mem_mb, ulong, S_IRUGO | S_IWUSR); +MODULE_PARM_DESC(min_mem_mb, "Minimum amount of memory (in MB) to not balloon. " + "[Default=" __stringify(CMM_MIN_MEM_MB) "]"); +module_param_named(debug, cmm_debug, uint, S_IRUGO | S_IWUSR); +MODULE_PARM_DESC(debug, "Enable module debugging logging. Set to 1 to enable. " + "[Default=" __stringify(CMM_DEBUG) "]"); + +#define CMM_NR_PAGES ((PAGE_SIZE - sizeof(void *) - sizeof(unsigned long)) / sizeof(unsigned long)) + +#define cmm_dbg(...) if (cmm_debug) { printk(KERN_INFO "cmm: "__VA_ARGS__); } + +struct cmm_page_array { + struct cmm_page_array *next; + unsigned long index; + unsigned long page[CMM_NR_PAGES]; +}; + +static unsigned long loaned_pages; +static unsigned long loaned_pages_target; +static unsigned long oom_freed_pages; + +static struct cmm_page_array *cmm_page_list; +static DEFINE_SPINLOCK(cmm_lock); + +static struct task_struct *cmm_thread_ptr; + +/** + * cmm_alloc_pages - Allocate pages and mark them as loaned + * @nr: number of pages to allocate + * + * Return value: + * number of pages requested to be allocated which were not + **/ +static long cmm_alloc_pages(long nr) +{ + struct cmm_page_array *pa, *npa; + unsigned long addr; + long rc; + + cmm_dbg("Begin request for %ld pages\n", nr); + + while (nr) { + addr = __get_free_page(GFP_NOIO | __GFP_NOWARN | + __GFP_NORETRY | __GFP_NOMEMALLOC); + if (!addr) + break; + spin_lock(&cmm_lock); + pa = cmm_page_list; + if (!pa || pa->index >= CMM_NR_PAGES) { + /* Need a new page for the page list. */ + spin_unlock(&cmm_lock); + npa = (struct cmm_page_array *)__get_free_page(GFP_NOIO | __GFP_NOWARN | + __GFP_NORETRY | __GFP_NOMEMALLOC); + if (!npa) { + pr_info("%s: Can not allocate new page list\n", __FUNCTION__); + free_page(addr); + break; + } + spin_lock(&cmm_lock); + pa = cmm_page_list; + + if (!pa || pa->index >= CMM_NR_PAGES) { + npa->next = pa; + npa->index = 0; + pa = npa; + cmm_page_list = pa; + } else + free_page((unsigned long) npa); + } + + if ((rc = plpar_page_set_loaned(__pa(addr)))) { + pr_err("%s: Can not set page to loaned. rc=%ld\n", __FUNCTION__, rc); + spin_unlock(&cmm_lock); + free_page(addr); + break; + } + + pa->page[pa->index++] = addr; + loaned_pages++; + totalram_pages--; + spin_unlock(&cmm_lock); + nr--; + } + + cmm_dbg("End request with %ld pages unfulfilled\n", nr); + return nr; +} + +/** + * cmm_free_pages - Free pages and mark them as active + * @nr: number of pages to free + * + * Return value: + * number of pages requested to be freed which were not + **/ +static long cmm_free_pages(long nr) +{ + struct cmm_page_array *pa; + unsigned long addr; + + cmm_dbg("Begin free of %ld pages.\n", nr); + spin_lock(&cmm_lock); + pa = cmm_page_list; + while (nr) { + if (!pa || pa->index <= 0) + break; + addr = pa->page[--pa->index]; + + if (pa->index == 0) { + pa = pa->next; + free_page((unsigned long) cmm_page_list); + cmm_page_list = pa; + } + + plpar_page_set_active(__pa(addr)); + free_page(addr); + loaned_pages--; + nr--; + totalram_pages++; + } + spin_unlock(&cmm_lock); + cmm_dbg("End request with %ld pages unfulfilled\n", nr); + return nr; +} + +/** + * cmm_oom_notify - OOM notifier + * @self: notifier block struct + * @dummy: not used + * @parm: returned - number of pages freed + * + * Return value: + * NOTIFY_OK + **/ +static int cmm_oom_notify(struct notifier_block *self, + unsigned long dummy, void *parm) +{ + unsigned long *freed = parm; + long nr = KB2PAGES(oom_kb); + + cmm_dbg("OOM processing started\n"); + nr = cmm_free_pages(nr); + loaned_pages_target = loaned_pages; + *freed += KB2PAGES(oom_kb) - nr; + oom_freed_pages += KB2PAGES(oom_kb) - nr; + cmm_dbg("OOM processing complete\n"); + return NOTIFY_OK; +} + +/** + * cmm_get_mpp - Read memory performance parameters + * + * Makes hcall to query the current page loan request from the hypervisor. + * + * Return value: + * nothing + **/ +static void cmm_get_mpp(void) +{ + int rc; + struct hvcall_mpp_data mpp_data; + unsigned long active_pages_target; + signed long page_loan_request; + + rc = h_get_mpp(&mpp_data); + + if (rc != H_SUCCESS) + return; + + page_loan_request = div_s64((s64)mpp_data.loan_request, PAGE_SIZE); + loaned_pages_target = page_loan_request + loaned_pages; + if (loaned_pages_target > oom_freed_pages) + loaned_pages_target -= oom_freed_pages; + else + loaned_pages_target = 0; + + active_pages_target = totalram_pages + loaned_pages - loaned_pages_target; + + if ((min_mem_mb * 1024 * 1024) > (active_pages_target * PAGE_SIZE)) + loaned_pages_target = totalram_pages + loaned_pages - + ((min_mem_mb * 1024 * 1024) / PAGE_SIZE); + + cmm_dbg("delta = %ld, loaned = %lu, target = %lu, oom = %lu, totalram = %lu\n", + page_loan_request, loaned_pages, loaned_pages_target, + oom_freed_pages, totalram_pages); +} + +static struct notifier_block cmm_oom_nb = { + .notifier_call = cmm_oom_notify +}; + +/** + * cmm_thread - CMM task thread + * @dummy: not used + * + * Return value: + * 0 + **/ +static int cmm_thread(void *dummy) +{ + unsigned long timeleft; + + while (1) { + timeleft = msleep_interruptible(delay * 1000); + + if (kthread_should_stop() || timeleft) { + loaned_pages_target = loaned_pages; + break; + } + + cmm_get_mpp(); + + if (loaned_pages_target > loaned_pages) { + if (cmm_alloc_pages(loaned_pages_target - loaned_pages)) + loaned_pages_target = loaned_pages; + } else if (loaned_pages_target < loaned_pages) + cmm_free_pages(loaned_pages - loaned_pages_target); + } + return 0; +} + +#define CMM_SHOW(name, format, args...) \ + static ssize_t show_##name(struct sys_device *dev, \ + struct sysdev_attribute *attr, \ + char *buf) \ + { \ + return sprintf(buf, format, ##args); \ + } \ + static SYSDEV_ATTR(name, S_IRUGO, show_##name, NULL) + +CMM_SHOW(loaned_kb, "%lu\n", PAGES2KB(loaned_pages)); +CMM_SHOW(loaned_target_kb, "%lu\n", PAGES2KB(loaned_pages_target)); + +static ssize_t show_oom_pages(struct sys_device *dev, + struct sysdev_attribute *attr, char *buf) +{ + return sprintf(buf, "%lu\n", PAGES2KB(oom_freed_pages)); +} + +static ssize_t store_oom_pages(struct sys_device *dev, + struct sysdev_attribute *attr, + const char *buf, size_t count) +{ + unsigned long val = simple_strtoul (buf, NULL, 10); + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + if (val != 0) + return -EBADMSG; + + oom_freed_pages = 0; + return count; +} + +static SYSDEV_ATTR(oom_freed_kb, S_IWUSR| S_IRUGO, + show_oom_pages, store_oom_pages); + +static struct sysdev_attribute *cmm_attrs[] = { + &attr_loaned_kb, + &attr_loaned_target_kb, + &attr_oom_freed_kb, +}; + +static struct sysdev_class cmm_sysdev_class = { + .name = "cmm", +}; + +/** + * cmm_sysfs_register - Register with sysfs + * + * Return value: + * 0 on success / other on failure + **/ +static int cmm_sysfs_register(struct sys_device *sysdev) +{ + int i, rc; + + if ((rc = sysdev_class_register(&cmm_sysdev_class))) + return rc; + + sysdev->id = 0; + sysdev->cls = &cmm_sysdev_class; + + if ((rc = sysdev_register(sysdev))) + goto class_unregister; + + for (i = 0; i < ARRAY_SIZE(cmm_attrs); i++) { + if ((rc = sysdev_create_file(sysdev, cmm_attrs[i]))) + goto fail; + } + + return 0; + +fail: + while (--i >= 0) + sysdev_remove_file(sysdev, cmm_attrs[i]); + sysdev_unregister(sysdev); +class_unregister: + sysdev_class_unregister(&cmm_sysdev_class); + return rc; +} + +/** + * cmm_unregister_sysfs - Unregister from sysfs + * + **/ +static void cmm_unregister_sysfs(struct sys_device *sysdev) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(cmm_attrs); i++) + sysdev_remove_file(sysdev, cmm_attrs[i]); + sysdev_unregister(sysdev); + sysdev_class_unregister(&cmm_sysdev_class); +} + +/** + * cmm_init - Module initialization + * + * Return value: + * 0 on success / other on failure + **/ +static int cmm_init(void) +{ + int rc = -ENOMEM; + + if (!firmware_has_feature(FW_FEATURE_CMO)) + return -EOPNOTSUPP; + + if ((rc = register_oom_notifier(&cmm_oom_nb)) < 0) + return rc; + + if ((rc = cmm_sysfs_register(&cmm_sysdev))) + goto out_oom_notifier; + + if (cmm_disabled) + return rc; + + cmm_thread_ptr = kthread_run(cmm_thread, NULL, "cmmthread"); + if (IS_ERR(cmm_thread_ptr)) { + rc = PTR_ERR(cmm_thread_ptr); + goto out_unregister_sysfs; + } + + return rc; + +out_unregister_sysfs: + cmm_unregister_sysfs(&cmm_sysdev); +out_oom_notifier: + unregister_oom_notifier(&cmm_oom_nb); + return rc; +} + +/** + * cmm_exit - Module exit + * + * Return value: + * nothing + **/ +static void cmm_exit(void) +{ + if (cmm_thread_ptr) + kthread_stop(cmm_thread_ptr); + unregister_oom_notifier(&cmm_oom_nb); + cmm_free_pages(loaned_pages); + cmm_unregister_sysfs(&cmm_sysdev); +} + +/** + * cmm_set_disable - Disable/Enable CMM + * + * Return value: + * 0 on success / other on failure + **/ +static int cmm_set_disable(const char *val, struct kernel_param *kp) +{ + int disable = simple_strtoul(val, NULL, 10); + + if (disable != 0 && disable != 1) + return -EINVAL; + + if (disable && !cmm_disabled) { + if (cmm_thread_ptr) + kthread_stop(cmm_thread_ptr); + cmm_thread_ptr = NULL; + cmm_free_pages(loaned_pages); + } else if (!disable && cmm_disabled) { + cmm_thread_ptr = kthread_run(cmm_thread, NULL, "cmmthread"); + if (IS_ERR(cmm_thread_ptr)) + return PTR_ERR(cmm_thread_ptr); + } + + cmm_disabled = disable; + return 0; +} + +module_param_call(disable, cmm_set_disable, param_get_uint, + &cmm_disabled, S_IRUGO | S_IWUSR); +MODULE_PARM_DESC(disable, "Disable CMM. Set to 1 to disable. " + "[Default=" __stringify(CMM_DISABLE) "]"); + +module_init(cmm_init); +module_exit(cmm_exit); diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index 5377dd4b849a..a8c446697f9e 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -48,7 +48,7 @@ #include "plpar_wrappers.h" -static void tce_build_pSeries(struct iommu_table *tbl, long index, +static int tce_build_pSeries(struct iommu_table *tbl, long index, long npages, unsigned long uaddr, enum dma_data_direction direction, struct dma_attrs *attrs) @@ -72,6 +72,7 @@ static void tce_build_pSeries(struct iommu_table *tbl, long index, uaddr += TCE_PAGE_SIZE; tcep++; } + return 0; } @@ -94,14 +95,19 @@ static unsigned long tce_get_pseries(struct iommu_table *tbl, long index) return *tcep; } -static void tce_build_pSeriesLP(struct iommu_table *tbl, long tcenum, +static void tce_free_pSeriesLP(struct iommu_table*, long, long); +static void tce_freemulti_pSeriesLP(struct iommu_table*, long, long); + +static int tce_build_pSeriesLP(struct iommu_table *tbl, long tcenum, long npages, unsigned long uaddr, enum dma_data_direction direction, struct dma_attrs *attrs) { - u64 rc; + u64 rc = 0; u64 proto_tce, tce; u64 rpn; + int ret = 0; + long tcenum_start = tcenum, npages_start = npages; rpn = (virt_to_abs(uaddr)) >> TCE_SHIFT; proto_tce = TCE_PCI_READ; @@ -112,6 +118,13 @@ static void tce_build_pSeriesLP(struct iommu_table *tbl, long tcenum, tce = proto_tce | (rpn & TCE_RPN_MASK) << TCE_RPN_SHIFT; rc = plpar_tce_put((u64)tbl->it_index, (u64)tcenum << 12, tce); + if (unlikely(rc == H_NOT_ENOUGH_RESOURCES)) { + ret = (int)rc; + tce_free_pSeriesLP(tbl, tcenum_start, + (npages_start - (npages + 1))); + break; + } + if (rc && printk_ratelimit()) { printk("tce_build_pSeriesLP: plpar_tce_put failed. rc=%ld\n", rc); printk("\tindex = 0x%lx\n", (u64)tbl->it_index); @@ -123,25 +136,27 @@ static void tce_build_pSeriesLP(struct iommu_table *tbl, long tcenum, tcenum++; rpn++; } + return ret; } static DEFINE_PER_CPU(u64 *, tce_page) = NULL; -static void tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum, +static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum, long npages, unsigned long uaddr, enum dma_data_direction direction, struct dma_attrs *attrs) { - u64 rc; + u64 rc = 0; u64 proto_tce; u64 *tcep; u64 rpn; long l, limit; + long tcenum_start = tcenum, npages_start = npages; + int ret = 0; if (npages == 1) { - tce_build_pSeriesLP(tbl, tcenum, npages, uaddr, - direction, attrs); - return; + return tce_build_pSeriesLP(tbl, tcenum, npages, uaddr, + direction, attrs); } tcep = __get_cpu_var(tce_page); @@ -153,9 +168,8 @@ static void tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum, tcep = (u64 *)__get_free_page(GFP_ATOMIC); /* If allocation fails, fall back to the loop implementation */ if (!tcep) { - tce_build_pSeriesLP(tbl, tcenum, npages, uaddr, + return tce_build_pSeriesLP(tbl, tcenum, npages, uaddr, direction, attrs); - return; } __get_cpu_var(tce_page) = tcep; } @@ -187,6 +201,13 @@ static void tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum, tcenum += limit; } while (npages > 0 && !rc); + if (unlikely(rc == H_NOT_ENOUGH_RESOURCES)) { + ret = (int)rc; + tce_freemulti_pSeriesLP(tbl, tcenum_start, + (npages_start - (npages + limit))); + return ret; + } + if (rc && printk_ratelimit()) { printk("tce_buildmulti_pSeriesLP: plpar_tce_put failed. rc=%ld\n", rc); printk("\tindex = 0x%lx\n", (u64)tbl->it_index); @@ -194,6 +215,7 @@ static void tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum, printk("\ttce[0] val = 0x%lx\n", tcep[0]); show_stack(current, (unsigned long *)__get_SP()); } + return ret; } static void tce_free_pSeriesLP(struct iommu_table *tbl, long tcenum, long npages) diff --git a/arch/powerpc/platforms/pseries/plpar_wrappers.h b/arch/powerpc/platforms/pseries/plpar_wrappers.h index d8680b589dc9..d967c1893ab5 100644 --- a/arch/powerpc/platforms/pseries/plpar_wrappers.h +++ b/arch/powerpc/platforms/pseries/plpar_wrappers.h @@ -2,6 +2,7 @@ #define _PSERIES_PLPAR_WRAPPERS_H #include <asm/hvcall.h> +#include <asm/page.h> static inline long poll_pending(void) { @@ -42,6 +43,38 @@ static inline long register_slb_shadow(unsigned long cpu, unsigned long vpa) return vpa_call(0x3, cpu, vpa); } +static inline long plpar_page_set_loaned(unsigned long vpa) +{ + unsigned long cmo_page_sz = cmo_get_page_size(); + long rc = 0; + int i; + + for (i = 0; !rc && i < PAGE_SIZE; i += cmo_page_sz) + rc = plpar_hcall_norets(H_PAGE_INIT, H_PAGE_SET_LOANED, vpa + i, 0); + + for (i -= cmo_page_sz; rc && i != 0; i -= cmo_page_sz) + plpar_hcall_norets(H_PAGE_INIT, H_PAGE_SET_ACTIVE, + vpa + i - cmo_page_sz, 0); + + return rc; +} + +static inline long plpar_page_set_active(unsigned long vpa) +{ + unsigned long cmo_page_sz = cmo_get_page_size(); + long rc = 0; + int i; + + for (i = 0; !rc && i < PAGE_SIZE; i += cmo_page_sz) + rc = plpar_hcall_norets(H_PAGE_INIT, H_PAGE_SET_ACTIVE, vpa + i, 0); + + for (i -= cmo_page_sz; rc && i != 0; i -= cmo_page_sz) + plpar_hcall_norets(H_PAGE_INIT, H_PAGE_SET_LOANED, + vpa + i - cmo_page_sz, 0); + + return rc; +} + extern void vpa_init(int cpu); static inline long plpar_pte_enter(unsigned long flags, diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 90beb444e1dd..7b01d67b4e48 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -68,6 +68,10 @@ #include "plpar_wrappers.h" #include "pseries.h" +int CMO_PrPSP = -1; +int CMO_SecPSP = -1; +unsigned long CMO_PageSize = (ASM_CONST(1) << IOMMU_PAGE_SHIFT); +EXPORT_SYMBOL(CMO_PageSize); int fwnmi_active; /* TRUE if an FWNMI handler is present */ @@ -314,6 +318,85 @@ static int pseries_set_xdabr(unsigned long dabr) H_DABRX_KERNEL | H_DABRX_USER); } +#define CMO_CHARACTERISTICS_TOKEN 44 +#define CMO_MAXLENGTH 1026 + +/** + * fw_cmo_feature_init - FW_FEATURE_CMO is not stored in ibm,hypertas-functions, + * handle that here. (Stolen from parse_system_parameter_string) + */ +void pSeries_cmo_feature_init(void) +{ + char *ptr, *key, *value, *end; + int call_status; + int page_order = IOMMU_PAGE_SHIFT; + + pr_debug(" -> fw_cmo_feature_init()\n"); + spin_lock(&rtas_data_buf_lock); + memset(rtas_data_buf, 0, RTAS_DATA_BUF_SIZE); + call_status = rtas_call(rtas_token("ibm,get-system-parameter"), 3, 1, + NULL, + CMO_CHARACTERISTICS_TOKEN, + __pa(rtas_data_buf), + RTAS_DATA_BUF_SIZE); + + if (call_status != 0) { + spin_unlock(&rtas_data_buf_lock); + pr_debug("CMO not available\n"); + pr_debug(" <- fw_cmo_feature_init()\n"); + return; + } + + end = rtas_data_buf + CMO_MAXLENGTH - 2; + ptr = rtas_data_buf + 2; /* step over strlen value */ + key = value = ptr; + + while (*ptr && (ptr <= end)) { + /* Separate the key and value by replacing '=' with '\0' and + * point the value at the string after the '=' + */ + if (ptr[0] == '=') { + ptr[0] = '\0'; + value = ptr + 1; + } else if (ptr[0] == '\0' || ptr[0] == ',') { + /* Terminate the string containing the key/value pair */ + ptr[0] = '\0'; + + if (key == value) { + pr_debug("Malformed key/value pair\n"); + /* Never found a '=', end processing */ + break; + } + + if (0 == strcmp(key, "CMOPageSize")) + page_order = simple_strtol(value, NULL, 10); + else if (0 == strcmp(key, "PrPSP")) + CMO_PrPSP = simple_strtol(value, NULL, 10); + else if (0 == strcmp(key, "SecPSP")) + CMO_SecPSP = simple_strtol(value, NULL, 10); + value = key = ptr + 1; + } + ptr++; + } + + /* Page size is returned as the power of 2 of the page size, + * convert to the page size in bytes before returning + */ + CMO_PageSize = 1 << page_order; + pr_debug("CMO_PageSize = %lu\n", CMO_PageSize); + + if (CMO_PrPSP != -1 || CMO_SecPSP != -1) { + pr_info("CMO enabled\n"); + pr_debug("CMO enabled, PrPSP=%d, SecPSP=%d\n", CMO_PrPSP, + CMO_SecPSP); + powerpc_firmware_features |= FW_FEATURE_CMO; + } else + pr_debug("CMO not enabled, PrPSP=%d, SecPSP=%d\n", CMO_PrPSP, + CMO_SecPSP); + spin_unlock(&rtas_data_buf_lock); + pr_debug(" <- fw_cmo_feature_init()\n"); +} + /* * Early initialization. Relocation is on but do not reference unbolted pages */ @@ -329,6 +412,7 @@ static void __init pSeries_init_early(void) else if (firmware_has_feature(FW_FEATURE_XDABR)) ppc_md.set_dabr = pseries_set_xdabr; + pSeries_cmo_feature_init(); iommu_init_early_pSeries(); pr_debug(" <- pSeries_init_early()\n"); |