diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2015-04-16 21:53:32 +0300 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2015-04-16 21:53:32 +0300 |
commit | d19d5efd8c8840aa4f38a6dfbfe500d8cc27de46 (patch) | |
tree | 2e2f4f57de790c7de2ccd6d1afbec8695b2c7a46 /arch/powerpc/platforms/pseries | |
parent | 34c9a0ffc75ad25b6a60f61e27c4a4b1189b8085 (diff) | |
parent | 2fe0753d49402aee325cc39c476b46fd51a8afec (diff) | |
download | linux-d19d5efd8c8840aa4f38a6dfbfe500d8cc27de46.tar.xz |
Merge tag 'powerpc-4.1-1' of git://git.kernel.org/pub/scm/linux/kernel/git/mpe/linux
Pull powerpc updates from Michael Ellerman:
- Numerous minor fixes, cleanups etc.
- More EEH work from Gavin to remove its dependency on device_nodes.
- Memory hotplug implemented entirely in the kernel from Nathan
Fontenot.
- Removal of redundant CONFIG_PPC_OF by Kevin Hao.
- Rewrite of VPHN parsing logic & tests from Greg Kurz.
- A fix from Nish Aravamudan to reduce memory usage by clamping
nodes_possible_map.
- Support for pstore on powernv from Hari Bathini.
- Removal of old powerpc specific byte swap routines by David Gibson.
- Fix from Vasant Hegde to prevent the flash driver telling you it was
flashing your firmware when it wasn't.
- Patch from Ben Herrenschmidt to add an OPAL heartbeat driver.
- Fix for an oops causing get/put_cpu_var() imbalance in perf by Jan
Stancek.
- Some fixes for migration from Tyrel Datwyler.
- A new syscall to switch the cpu endian by Michael Ellerman.
- Large series from Wei Yang to implement SRIOV, reviewed and acked by
Bjorn.
- A fix for the OPAL sensor driver from Cédric Le Goater.
- Fixes to get STRICT_MM_TYPECHECKS building again by Michael Ellerman.
- Large series from Daniel Axtens to make our PCI hooks per PHB rather
than per machine.
- Small patch from Sam Bobroff to explicitly abort non-suspended
transactions on syscalls, plus a test to exercise it.
- Numerous reworks and fixes for the 24x7 PMU from Sukadev Bhattiprolu.
- Small patch to enable the hard lockup detector from Anton Blanchard.
- Fix from Dave Olson for missing L2 cache information on some CPUs.
- Some fixes from Michael Ellerman to get Cell machines booting again.
- Freescale updates from Scott: Highlights include BMan device tree
nodes, an MSI erratum workaround, a couple minor performance
improvements, config updates, and misc fixes/cleanup.
* tag 'powerpc-4.1-1' of git://git.kernel.org/pub/scm/linux/kernel/git/mpe/linux: (196 commits)
powerpc/powermac: Fix build error seen with powermac smp builds
powerpc/pseries: Fix compile of memory hotplug without CONFIG_MEMORY_HOTREMOVE
powerpc: Remove PPC32 code from pseries specific find_and_init_phbs()
powerpc/cell: Fix iommu breakage caused by controller_ops change
powerpc/eeh: Fix crash in eeh_add_device_early() on Cell
powerpc/perf: Cap 64bit userspace backtraces to PERF_MAX_STACK_DEPTH
powerpc/perf/hv-24x7: Fail 24x7 initcall if create_events_from_catalog() fails
powerpc/pseries: Correct memory hotplug locking
powerpc: Fix missing L2 cache size in /sys/devices/system/cpu
powerpc: Add ppc64 hard lockup detector support
oprofile: Disable oprofile NMI timer on ppc64
powerpc/perf/hv-24x7: Add missing put_cpu_var()
powerpc/perf/hv-24x7: Break up single_24x7_request
powerpc/perf/hv-24x7: Define update_event_count()
powerpc/perf/hv-24x7: Whitespace cleanup
powerpc/perf/hv-24x7: Define add_event_to_24x7_request()
powerpc/perf/hv-24x7: Rename hv_24x7_event_update
powerpc/perf/hv-24x7: Move debug prints to separate function
powerpc/perf/hv-24x7: Drop event_24x7_request()
powerpc/perf/hv-24x7: Use pr_devel() to log message
...
Conflicts:
tools/testing/selftests/powerpc/Makefile
tools/testing/selftests/powerpc/tm/Makefile
Diffstat (limited to 'arch/powerpc/platforms/pseries')
-rw-r--r-- | arch/powerpc/platforms/pseries/Kconfig | 1 | ||||
-rw-r--r-- | arch/powerpc/platforms/pseries/dlpar.c | 118 | ||||
-rw-r--r-- | arch/powerpc/platforms/pseries/eeh_pseries.c | 98 | ||||
-rw-r--r-- | arch/powerpc/platforms/pseries/hotplug-memory.c | 489 | ||||
-rw-r--r-- | arch/powerpc/platforms/pseries/iommu.c | 9 | ||||
-rw-r--r-- | arch/powerpc/platforms/pseries/mobility.c | 26 | ||||
-rw-r--r-- | arch/powerpc/platforms/pseries/msi.c | 6 | ||||
-rw-r--r-- | arch/powerpc/platforms/pseries/nvram.c | 674 | ||||
-rw-r--r-- | arch/powerpc/platforms/pseries/pci_dlpar.c | 5 | ||||
-rw-r--r-- | arch/powerpc/platforms/pseries/pseries.h | 14 | ||||
-rw-r--r-- | arch/powerpc/platforms/pseries/setup.c | 48 | ||||
-rw-r--r-- | arch/powerpc/platforms/pseries/smp.c | 6 |
12 files changed, 743 insertions, 751 deletions
diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig index a758a9c3bbba..54c87d5d349d 100644 --- a/arch/powerpc/platforms/pseries/Kconfig +++ b/arch/powerpc/platforms/pseries/Kconfig @@ -16,7 +16,6 @@ config PPC_PSERIES select PPC_UDBG_16550 select PPC_NATIVE select PPC_PCI_CHOICE if EXPERT - select ZLIB_DEFLATE select PPC_DOORBELL select HAVE_CONTEXT_TRACKING select HOTPLUG_CPU if SMP diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c index c22bb1b4beb8..b4b11096ea8b 100644 --- a/arch/powerpc/platforms/pseries/dlpar.c +++ b/arch/powerpc/platforms/pseries/dlpar.c @@ -10,6 +10,8 @@ * 2 as published by the Free Software Foundation. */ +#define pr_fmt(fmt) "dlpar: " fmt + #include <linux/kernel.h> #include <linux/notifier.h> #include <linux/spinlock.h> @@ -535,13 +537,125 @@ static ssize_t dlpar_cpu_release(const char *buf, size_t count) return count; } +#endif /* CONFIG_ARCH_CPU_PROBE_RELEASE */ + +static int handle_dlpar_errorlog(struct pseries_hp_errorlog *hp_elog) +{ + int rc; + + /* pseries error logs are in BE format, convert to cpu type */ + switch (hp_elog->id_type) { + case PSERIES_HP_ELOG_ID_DRC_COUNT: + hp_elog->_drc_u.drc_count = + be32_to_cpu(hp_elog->_drc_u.drc_count); + break; + case PSERIES_HP_ELOG_ID_DRC_INDEX: + hp_elog->_drc_u.drc_index = + be32_to_cpu(hp_elog->_drc_u.drc_index); + } + + switch (hp_elog->resource) { + case PSERIES_HP_ELOG_RESOURCE_MEM: + rc = dlpar_memory(hp_elog); + break; + default: + pr_warn_ratelimited("Invalid resource (%d) specified\n", + hp_elog->resource); + rc = -EINVAL; + } + + return rc; +} + +static ssize_t dlpar_store(struct class *class, struct class_attribute *attr, + const char *buf, size_t count) +{ + struct pseries_hp_errorlog *hp_elog; + const char *arg; + int rc; + + hp_elog = kzalloc(sizeof(*hp_elog), GFP_KERNEL); + if (!hp_elog) { + rc = -ENOMEM; + goto dlpar_store_out; + } + + /* Parse out the request from the user, this will be in the form + * <resource> <action> <id_type> <id> + */ + arg = buf; + if (!strncmp(arg, "memory", 6)) { + hp_elog->resource = PSERIES_HP_ELOG_RESOURCE_MEM; + arg += strlen("memory "); + } else { + pr_err("Invalid resource specified: \"%s\"\n", buf); + rc = -EINVAL; + goto dlpar_store_out; + } + + if (!strncmp(arg, "add", 3)) { + hp_elog->action = PSERIES_HP_ELOG_ACTION_ADD; + arg += strlen("add "); + } else if (!strncmp(arg, "remove", 6)) { + hp_elog->action = PSERIES_HP_ELOG_ACTION_REMOVE; + arg += strlen("remove "); + } else { + pr_err("Invalid action specified: \"%s\"\n", buf); + rc = -EINVAL; + goto dlpar_store_out; + } + + if (!strncmp(arg, "index", 5)) { + u32 index; + + hp_elog->id_type = PSERIES_HP_ELOG_ID_DRC_INDEX; + arg += strlen("index "); + if (kstrtou32(arg, 0, &index)) { + rc = -EINVAL; + pr_err("Invalid drc_index specified: \"%s\"\n", buf); + goto dlpar_store_out; + } + + hp_elog->_drc_u.drc_index = cpu_to_be32(index); + } else if (!strncmp(arg, "count", 5)) { + u32 count; + + hp_elog->id_type = PSERIES_HP_ELOG_ID_DRC_COUNT; + arg += strlen("count "); + if (kstrtou32(arg, 0, &count)) { + rc = -EINVAL; + pr_err("Invalid count specified: \"%s\"\n", buf); + goto dlpar_store_out; + } + + hp_elog->_drc_u.drc_count = cpu_to_be32(count); + } else { + pr_err("Invalid id_type specified: \"%s\"\n", buf); + rc = -EINVAL; + goto dlpar_store_out; + } + + rc = handle_dlpar_errorlog(hp_elog); + +dlpar_store_out: + kfree(hp_elog); + return rc ? rc : count; +} + +static CLASS_ATTR(dlpar, S_IWUSR, NULL, dlpar_store); + static int __init pseries_dlpar_init(void) { + int rc; + +#ifdef CONFIG_ARCH_CPU_PROBE_RELEASE ppc_md.cpu_probe = dlpar_cpu_probe; ppc_md.cpu_release = dlpar_cpu_release; +#endif /* CONFIG_ARCH_CPU_PROBE_RELEASE */ - return 0; + rc = sysfs_create_file(kernel_kobj, &class_attr_dlpar.attr); + + return rc; } machine_device_initcall(pseries, pseries_dlpar_init); -#endif /* CONFIG_ARCH_CPU_PROBE_RELEASE */ diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c index a6c7e19f5eb3..2039397cc75d 100644 --- a/arch/powerpc/platforms/pseries/eeh_pseries.c +++ b/arch/powerpc/platforms/pseries/eeh_pseries.c @@ -118,9 +118,8 @@ static int pseries_eeh_init(void) return 0; } -static int pseries_eeh_cap_start(struct device_node *dn) +static int pseries_eeh_cap_start(struct pci_dn *pdn) { - struct pci_dn *pdn = PCI_DN(dn); u32 status; if (!pdn) @@ -134,10 +133,9 @@ static int pseries_eeh_cap_start(struct device_node *dn) } -static int pseries_eeh_find_cap(struct device_node *dn, int cap) +static int pseries_eeh_find_cap(struct pci_dn *pdn, int cap) { - struct pci_dn *pdn = PCI_DN(dn); - int pos = pseries_eeh_cap_start(dn); + int pos = pseries_eeh_cap_start(pdn); int cnt = 48; /* Maximal number of capabilities */ u32 id; @@ -160,10 +158,9 @@ static int pseries_eeh_find_cap(struct device_node *dn, int cap) return 0; } -static int pseries_eeh_find_ecap(struct device_node *dn, int cap) +static int pseries_eeh_find_ecap(struct pci_dn *pdn, int cap) { - struct pci_dn *pdn = PCI_DN(dn); - struct eeh_dev *edev = of_node_to_eeh_dev(dn); + struct eeh_dev *edev = pdn_to_eeh_dev(pdn); u32 header; int pos = 256; int ttl = (4096 - 256) / 8; @@ -191,53 +188,44 @@ static int pseries_eeh_find_ecap(struct device_node *dn, int cap) } /** - * pseries_eeh_of_probe - EEH probe on the given device - * @dn: OF node - * @flag: Unused + * pseries_eeh_probe - EEH probe on the given device + * @pdn: PCI device node + * @data: Unused * * When EEH module is installed during system boot, all PCI devices * are checked one by one to see if it supports EEH. The function * is introduced for the purpose. */ -static void *pseries_eeh_of_probe(struct device_node *dn, void *flag) +static void *pseries_eeh_probe(struct pci_dn *pdn, void *data) { struct eeh_dev *edev; struct eeh_pe pe; - struct pci_dn *pdn = PCI_DN(dn); - const __be32 *classp, *vendorp, *devicep; - u32 class_code; - const __be32 *regs; u32 pcie_flags; int enable = 0; int ret; /* Retrieve OF node and eeh device */ - edev = of_node_to_eeh_dev(dn); - if (edev->pe || !of_device_is_available(dn)) + edev = pdn_to_eeh_dev(pdn); + if (!edev || edev->pe) return NULL; - /* Retrieve class/vendor/device IDs */ - classp = of_get_property(dn, "class-code", NULL); - vendorp = of_get_property(dn, "vendor-id", NULL); - devicep = of_get_property(dn, "device-id", NULL); - - /* Skip for bad OF node or PCI-ISA bridge */ - if (!classp || !vendorp || !devicep) - return NULL; - if (dn->type && !strcmp(dn->type, "isa")) + /* Check class/vendor/device IDs */ + if (!pdn->vendor_id || !pdn->device_id || !pdn->class_code) return NULL; - class_code = of_read_number(classp, 1); + /* Skip for PCI-ISA bridge */ + if ((pdn->class_code >> 8) == PCI_CLASS_BRIDGE_ISA) + return NULL; /* * Update class code and mode of eeh device. We need * correctly reflects that current device is root port * or PCIe switch downstream port. */ - edev->class_code = class_code; - edev->pcix_cap = pseries_eeh_find_cap(dn, PCI_CAP_ID_PCIX); - edev->pcie_cap = pseries_eeh_find_cap(dn, PCI_CAP_ID_EXP); - edev->aer_cap = pseries_eeh_find_ecap(dn, PCI_EXT_CAP_ID_ERR); + edev->class_code = pdn->class_code; + edev->pcix_cap = pseries_eeh_find_cap(pdn, PCI_CAP_ID_PCIX); + edev->pcie_cap = pseries_eeh_find_cap(pdn, PCI_CAP_ID_EXP); + edev->aer_cap = pseries_eeh_find_ecap(pdn, PCI_EXT_CAP_ID_ERR); edev->mode &= 0xFFFFFF00; if ((edev->class_code >> 8) == PCI_CLASS_BRIDGE_PCI) { edev->mode |= EEH_DEV_BRIDGE; @@ -252,24 +240,16 @@ static void *pseries_eeh_of_probe(struct device_node *dn, void *flag) } } - /* Retrieve the device address */ - regs = of_get_property(dn, "reg", NULL); - if (!regs) { - pr_warn("%s: OF node property %s::reg not found\n", - __func__, dn->full_name); - return NULL; - } - /* Initialize the fake PE */ memset(&pe, 0, sizeof(struct eeh_pe)); pe.phb = edev->phb; - pe.config_addr = of_read_number(regs, 1); + pe.config_addr = (pdn->busno << 16) | (pdn->devfn << 8); /* Enable EEH on the device */ ret = eeh_ops->set_option(&pe, EEH_OPT_ENABLE); if (!ret) { - edev->config_addr = of_read_number(regs, 1); /* Retrieve PE address */ + edev->config_addr = (pdn->busno << 16) | (pdn->devfn << 8); edev->pe_config_addr = eeh_ops->get_pe_addr(&pe); pe.addr = edev->pe_config_addr; @@ -285,16 +265,17 @@ static void *pseries_eeh_of_probe(struct device_node *dn, void *flag) eeh_add_flag(EEH_ENABLED); eeh_add_to_parent_pe(edev); - pr_debug("%s: EEH enabled on %s PHB#%d-PE#%x, config addr#%x\n", - __func__, dn->full_name, pe.phb->global_number, - pe.addr, pe.config_addr); - } else if (dn->parent && of_node_to_eeh_dev(dn->parent) && - (of_node_to_eeh_dev(dn->parent))->pe) { + pr_debug("%s: EEH enabled on %02x:%02x.%01x PHB#%d-PE#%x\n", + __func__, pdn->busno, PCI_SLOT(pdn->devfn), + PCI_FUNC(pdn->devfn), pe.phb->global_number, + pe.addr); + } else if (pdn->parent && pdn_to_eeh_dev(pdn->parent) && + (pdn_to_eeh_dev(pdn->parent))->pe) { /* This device doesn't support EEH, but it may have an * EEH parent, in which case we mark it as supported. */ - edev->config_addr = of_node_to_eeh_dev(dn->parent)->config_addr; - edev->pe_config_addr = of_node_to_eeh_dev(dn->parent)->pe_config_addr; + edev->config_addr = pdn_to_eeh_dev(pdn->parent)->config_addr; + edev->pe_config_addr = pdn_to_eeh_dev(pdn->parent)->pe_config_addr; eeh_add_to_parent_pe(edev); } } @@ -670,45 +651,36 @@ static int pseries_eeh_configure_bridge(struct eeh_pe *pe) /** * pseries_eeh_read_config - Read PCI config space - * @dn: device node + * @pdn: PCI device node * @where: PCI address * @size: size to read * @val: return value * * Read config space from the speicifed device */ -static int pseries_eeh_read_config(struct device_node *dn, int where, int size, u32 *val) +static int pseries_eeh_read_config(struct pci_dn *pdn, int where, int size, u32 *val) { - struct pci_dn *pdn; - - pdn = PCI_DN(dn); - return rtas_read_config(pdn, where, size, val); } /** * pseries_eeh_write_config - Write PCI config space - * @dn: device node + * @pdn: PCI device node * @where: PCI address * @size: size to write * @val: value to be written * * Write config space to the specified device */ -static int pseries_eeh_write_config(struct device_node *dn, int where, int size, u32 val) +static int pseries_eeh_write_config(struct pci_dn *pdn, int where, int size, u32 val) { - struct pci_dn *pdn; - - pdn = PCI_DN(dn); - return rtas_write_config(pdn, where, size, val); } static struct eeh_ops pseries_eeh_ops = { .name = "pseries", .init = pseries_eeh_init, - .of_probe = pseries_eeh_of_probe, - .dev_probe = NULL, + .probe = pseries_eeh_probe, .set_option = pseries_eeh_set_option, .get_pe_addr = pseries_eeh_get_pe_addr, .get_state = pseries_eeh_get_state, diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c index fa41f0da5b6f..0ced387e1463 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -9,11 +9,14 @@ * 2 of the License, or (at your option) any later version. */ +#define pr_fmt(fmt) "pseries-hotplug-mem: " fmt + #include <linux/of.h> #include <linux/of_address.h> #include <linux/memblock.h> #include <linux/memory.h> #include <linux/memory_hotplug.h> +#include <linux/slab.h> #include <asm/firmware.h> #include <asm/machdep.h> @@ -21,6 +24,8 @@ #include <asm/sparsemem.h> #include "pseries.h" +static bool rtas_hp_event; + unsigned long pseries_memory_block_size(void) { struct device_node *np; @@ -64,6 +69,67 @@ unsigned long pseries_memory_block_size(void) return memblock_size; } +static void dlpar_free_drconf_property(struct property *prop) +{ + kfree(prop->name); + kfree(prop->value); + kfree(prop); +} + +static struct property *dlpar_clone_drconf_property(struct device_node *dn) +{ + struct property *prop, *new_prop; + struct of_drconf_cell *lmbs; + u32 num_lmbs, *p; + int i; + + prop = of_find_property(dn, "ibm,dynamic-memory", NULL); + if (!prop) + return NULL; + + new_prop = kzalloc(sizeof(*new_prop), GFP_KERNEL); + if (!new_prop) + return NULL; + + new_prop->name = kstrdup(prop->name, GFP_KERNEL); + new_prop->value = kmalloc(prop->length, GFP_KERNEL); + if (!new_prop->name || !new_prop->value) { + dlpar_free_drconf_property(new_prop); + return NULL; + } + + memcpy(new_prop->value, prop->value, prop->length); + new_prop->length = prop->length; + + /* Convert the property to cpu endian-ness */ + p = new_prop->value; + *p = be32_to_cpu(*p); + + num_lmbs = *p++; + lmbs = (struct of_drconf_cell *)p; + + 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].flags = be32_to_cpu(lmbs[i].flags); + } + + return new_prop; +} + +static struct memory_block *lmb_to_memblock(struct of_drconf_cell *lmb) +{ + unsigned long section_nr; + struct mem_section *mem_sect; + struct memory_block *mem_block; + + section_nr = pfn_to_section_nr(PFN_DOWN(lmb->base_addr)); + mem_sect = __nr_to_section(section_nr); + + mem_block = find_memory_block(mem_sect); + return mem_block; +} + #ifdef CONFIG_MEMORY_HOTREMOVE static int pseries_remove_memblock(unsigned long base, unsigned int memblock_size) { @@ -122,6 +188,173 @@ static int pseries_remove_mem_node(struct device_node *np) pseries_remove_memblock(base, lmb_size); return 0; } + +static bool lmb_is_removable(struct of_drconf_cell *lmb) +{ + int i, scns_per_block; + int rc = 1; + unsigned long pfn, block_sz; + u64 phys_addr; + + if (!(lmb->flags & DRCONF_MEM_ASSIGNED)) + return false; + + block_sz = memory_block_size_bytes(); + scns_per_block = block_sz / MIN_MEMORY_BLOCK_SIZE; + phys_addr = lmb->base_addr; + + for (i = 0; i < scns_per_block; i++) { + pfn = PFN_DOWN(phys_addr); + if (!pfn_present(pfn)) + continue; + + rc &= is_mem_section_removable(pfn, PAGES_PER_SECTION); + phys_addr += MIN_MEMORY_BLOCK_SIZE; + } + + return rc ? true : false; +} + +static int dlpar_add_lmb(struct of_drconf_cell *); + +static int dlpar_remove_lmb(struct of_drconf_cell *lmb) +{ + struct memory_block *mem_block; + unsigned long block_sz; + int nid, rc; + + if (!lmb_is_removable(lmb)) + return -EINVAL; + + mem_block = lmb_to_memblock(lmb); + if (!mem_block) + return -EINVAL; + + rc = device_offline(&mem_block->dev); + put_device(&mem_block->dev); + if (rc) + return rc; + + block_sz = pseries_memory_block_size(); + nid = memory_add_physaddr_to_nid(lmb->base_addr); + + remove_memory(nid, lmb->base_addr, block_sz); + + /* Update memory regions for memory remove */ + memblock_remove(lmb->base_addr, block_sz); + + dlpar_release_drc(lmb->drc_index); + + lmb->flags &= ~DRCONF_MEM_ASSIGNED; + return 0; +} + +static int dlpar_memory_remove_by_count(u32 lmbs_to_remove, + struct property *prop) +{ + struct of_drconf_cell *lmbs; + int lmbs_removed = 0; + int lmbs_available = 0; + u32 num_lmbs, *p; + int i, rc; + + pr_info("Attempting to hot-remove %d LMB(s)\n", lmbs_to_remove); + + if (lmbs_to_remove == 0) + return -EINVAL; + + p = prop->value; + num_lmbs = *p++; + lmbs = (struct of_drconf_cell *)p; + + /* Validate that there are enough LMBs to satisfy the request */ + for (i = 0; i < num_lmbs; i++) { + if (lmbs[i].flags & DRCONF_MEM_ASSIGNED) + lmbs_available++; + } + + if (lmbs_available < lmbs_to_remove) + return -EINVAL; + + for (i = 0; i < num_lmbs && lmbs_removed < lmbs_to_remove; i++) { + rc = dlpar_remove_lmb(&lmbs[i]); + if (rc) + continue; + + lmbs_removed++; + + /* Mark this lmb so we can add it later if all of the + * requested LMBs cannot be removed. + */ + lmbs[i].reserved = 1; + } + + if (lmbs_removed != lmbs_to_remove) { + pr_err("Memory hot-remove failed, adding LMB's back\n"); + + for (i = 0; i < num_lmbs; i++) { + if (!lmbs[i].reserved) + continue; + + rc = dlpar_add_lmb(&lmbs[i]); + if (rc) + pr_err("Failed to add LMB back, drc index %x\n", + lmbs[i].drc_index); + + lmbs[i].reserved = 0; + } + + rc = -EINVAL; + } else { + for (i = 0; i < num_lmbs; i++) { + if (!lmbs[i].reserved) + continue; + + pr_info("Memory at %llx was hot-removed\n", + lmbs[i].base_addr); + + lmbs[i].reserved = 0; + } + rc = 0; + } + + return rc; +} + +static int dlpar_memory_remove_by_index(u32 drc_index, struct property *prop) +{ + struct of_drconf_cell *lmbs; + u32 num_lmbs, *p; + int lmb_found; + int i, rc; + + pr_info("Attempting to hot-remove LMB, drc index %x\n", drc_index); + + p = prop->value; + num_lmbs = *p++; + lmbs = (struct of_drconf_cell *)p; + + lmb_found = 0; + for (i = 0; i < num_lmbs; i++) { + if (lmbs[i].drc_index == drc_index) { + lmb_found = 1; + rc = dlpar_remove_lmb(&lmbs[i]); + break; + } + } + + if (!lmb_found) + rc = -EINVAL; + + if (rc) + pr_info("Failed to hot-remove memory at %llx\n", + lmbs[i].base_addr); + else + pr_info("Memory at %llx was hot-removed\n", lmbs[i].base_addr); + + return rc; +} + #else static inline int pseries_remove_memblock(unsigned long base, unsigned int memblock_size) @@ -132,8 +365,261 @@ static inline int pseries_remove_mem_node(struct device_node *np) { return 0; } +static inline int dlpar_memory_remove(struct pseries_hp_errorlog *hp_elog) +{ + return -EOPNOTSUPP; +} +static int dlpar_remove_lmb(struct of_drconf_cell *lmb) +{ + return -EOPNOTSUPP; +} +static int dlpar_memory_remove_by_count(u32 lmbs_to_remove, + struct property *prop) +{ + return -EOPNOTSUPP; +} +static int dlpar_memory_remove_by_index(u32 drc_index, struct property *prop) +{ + return -EOPNOTSUPP; +} + #endif /* CONFIG_MEMORY_HOTREMOVE */ +static int dlpar_add_lmb(struct of_drconf_cell *lmb) +{ + struct memory_block *mem_block; + unsigned long block_sz; + int nid, rc; + + if (lmb->flags & DRCONF_MEM_ASSIGNED) + return -EINVAL; + + block_sz = memory_block_size_bytes(); + + rc = dlpar_acquire_drc(lmb->drc_index); + if (rc) + return rc; + + /* Find the node id for this address */ + nid = memory_add_physaddr_to_nid(lmb->base_addr); + + /* Add the memory */ + rc = add_memory(nid, lmb->base_addr, block_sz); + if (rc) { + dlpar_release_drc(lmb->drc_index); + return rc; + } + + /* Register this block of memory */ + rc = memblock_add(lmb->base_addr, block_sz); + if (rc) { + remove_memory(nid, lmb->base_addr, block_sz); + dlpar_release_drc(lmb->drc_index); + return rc; + } + + mem_block = lmb_to_memblock(lmb); + if (!mem_block) { + remove_memory(nid, lmb->base_addr, block_sz); + dlpar_release_drc(lmb->drc_index); + return -EINVAL; + } + + rc = device_online(&mem_block->dev); + put_device(&mem_block->dev); + if (rc) { + remove_memory(nid, lmb->base_addr, block_sz); + dlpar_release_drc(lmb->drc_index); + return rc; + } + + lmb->flags |= DRCONF_MEM_ASSIGNED; + return 0; +} + +static int dlpar_memory_add_by_count(u32 lmbs_to_add, struct property *prop) +{ + struct of_drconf_cell *lmbs; + u32 num_lmbs, *p; + int lmbs_available = 0; + int lmbs_added = 0; + int i, rc; + + pr_info("Attempting to hot-add %d LMB(s)\n", lmbs_to_add); + + if (lmbs_to_add == 0) + return -EINVAL; + + p = prop->value; + num_lmbs = *p++; + lmbs = (struct of_drconf_cell *)p; + + /* Validate that there are enough LMBs to satisfy the request */ + for (i = 0; i < num_lmbs; i++) { + if (!(lmbs[i].flags & DRCONF_MEM_ASSIGNED)) + lmbs_available++; + } + + if (lmbs_available < lmbs_to_add) + return -EINVAL; + + for (i = 0; i < num_lmbs && lmbs_to_add != lmbs_added; i++) { + rc = dlpar_add_lmb(&lmbs[i]); + if (rc) + continue; + + lmbs_added++; + + /* Mark this lmb so we can remove it later if all of the + * requested LMBs cannot be added. + */ + lmbs[i].reserved = 1; + } + + if (lmbs_added != lmbs_to_add) { + pr_err("Memory hot-add failed, removing any added LMBs\n"); + + for (i = 0; i < num_lmbs; i++) { + if (!lmbs[i].reserved) + continue; + + rc = dlpar_remove_lmb(&lmbs[i]); + if (rc) + pr_err("Failed to remove LMB, drc index %x\n", + be32_to_cpu(lmbs[i].drc_index)); + } + rc = -EINVAL; + } else { + for (i = 0; i < num_lmbs; i++) { + if (!lmbs[i].reserved) + continue; + + pr_info("Memory at %llx (drc index %x) was hot-added\n", + lmbs[i].base_addr, lmbs[i].drc_index); + lmbs[i].reserved = 0; + } + } + + return rc; +} + +static int dlpar_memory_add_by_index(u32 drc_index, struct property *prop) +{ + struct of_drconf_cell *lmbs; + u32 num_lmbs, *p; + int i, lmb_found; + int rc; + + pr_info("Attempting to hot-add LMB, drc index %x\n", drc_index); + + p = prop->value; + num_lmbs = *p++; + lmbs = (struct of_drconf_cell *)p; + + lmb_found = 0; + for (i = 0; i < num_lmbs; i++) { + if (lmbs[i].drc_index == drc_index) { + lmb_found = 1; + rc = dlpar_add_lmb(&lmbs[i]); + break; + } + } + + if (!lmb_found) + rc = -EINVAL; + + if (rc) + pr_info("Failed to hot-add memory, drc index %x\n", drc_index); + else + pr_info("Memory at %llx (drc index %x) was hot-added\n", + lmbs[i].base_addr, drc_index); + + return rc; +} + +static void dlpar_update_drconf_property(struct device_node *dn, + struct property *prop) +{ + struct of_drconf_cell *lmbs; + u32 num_lmbs, *p; + int i; + + /* Convert the property back to BE */ + p = prop->value; + num_lmbs = *p; + *p = cpu_to_be32(*p); + p++; + + lmbs = (struct of_drconf_cell *)p; + 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].flags = cpu_to_be32(lmbs[i].flags); + } + + rtas_hp_event = true; + of_update_property(dn, prop); + rtas_hp_event = false; +} + +int dlpar_memory(struct pseries_hp_errorlog *hp_elog) +{ + struct device_node *dn; + struct property *prop; + u32 count, drc_index; + int rc; + + count = hp_elog->_drc_u.drc_count; + drc_index = hp_elog->_drc_u.drc_index; + + lock_device_hotplug(); + + dn = of_find_node_by_path("/ibm,dynamic-reconfiguration-memory"); + if (!dn) { + rc = -EINVAL; + goto dlpar_memory_out; + } + + prop = dlpar_clone_drconf_property(dn); + if (!prop) { + rc = -EINVAL; + goto dlpar_memory_out; + } + + switch (hp_elog->action) { + case PSERIES_HP_ELOG_ACTION_ADD: + if (hp_elog->id_type == PSERIES_HP_ELOG_ID_DRC_COUNT) + rc = dlpar_memory_add_by_count(count, prop); + else if (hp_elog->id_type == PSERIES_HP_ELOG_ID_DRC_INDEX) + rc = dlpar_memory_add_by_index(drc_index, prop); + else + rc = -EINVAL; + break; + case PSERIES_HP_ELOG_ACTION_REMOVE: + if (hp_elog->id_type == PSERIES_HP_ELOG_ID_DRC_COUNT) + rc = dlpar_memory_remove_by_count(count, prop); + else if (hp_elog->id_type == PSERIES_HP_ELOG_ID_DRC_INDEX) + rc = dlpar_memory_remove_by_index(drc_index, prop); + else + rc = -EINVAL; + break; + default: + pr_err("Invalid action (%d) specified\n", hp_elog->action); + rc = -EINVAL; + break; + } + + if (rc) + dlpar_free_drconf_property(prop); + else + dlpar_update_drconf_property(dn, prop); + +dlpar_memory_out: + of_node_put(dn); + unlock_device_hotplug(); + return rc; +} + static int pseries_add_mem_node(struct device_node *np) { const char *type; @@ -174,6 +660,9 @@ static int pseries_update_drconf_memory(struct of_reconfig_data *pr) __be32 *p; int i, rc = -EINVAL; + if (rtas_hp_event) + return 0; + memblock_size = pseries_memory_block_size(); if (!memblock_size) return -EINVAL; diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index 7803a19adb31..61d5a17f45c0 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -49,6 +49,7 @@ #include <asm/mmzone.h> #include <asm/plpar_wrappers.h> +#include "pseries.h" static void tce_invalidate_pSeries_sw(struct iommu_table *tbl, __be64 *startp, __be64 *endp) @@ -1307,16 +1308,16 @@ void iommu_init_early_pSeries(void) ppc_md.tce_free = tce_free_pSeriesLP; } ppc_md.tce_get = tce_get_pSeriesLP; - ppc_md.pci_dma_bus_setup = pci_dma_bus_setup_pSeriesLP; - ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_pSeriesLP; + pseries_pci_controller_ops.dma_bus_setup = pci_dma_bus_setup_pSeriesLP; + pseries_pci_controller_ops.dma_dev_setup = pci_dma_dev_setup_pSeriesLP; ppc_md.dma_set_mask = dma_set_mask_pSeriesLP; ppc_md.dma_get_required_mask = dma_get_required_mask_pSeriesLP; } else { ppc_md.tce_build = tce_build_pSeries; ppc_md.tce_free = tce_free_pSeries; ppc_md.tce_get = tce_get_pseries; - ppc_md.pci_dma_bus_setup = pci_dma_bus_setup_pSeries; - ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_pSeries; + pseries_pci_controller_ops.dma_bus_setup = pci_dma_bus_setup_pSeries; + pseries_pci_controller_ops.dma_dev_setup = pci_dma_dev_setup_pSeries; } diff --git a/arch/powerpc/platforms/pseries/mobility.c b/arch/powerpc/platforms/pseries/mobility.c index 8f35d525cede..ceb18d349459 100644 --- a/arch/powerpc/platforms/pseries/mobility.c +++ b/arch/powerpc/platforms/pseries/mobility.c @@ -320,28 +320,34 @@ static ssize_t migrate_store(struct class *class, struct class_attribute *attr, { u64 streamid; int rc; - int vasi_rc = 0; rc = kstrtou64(buf, 0, &streamid); if (rc) return rc; do { - rc = rtas_ibm_suspend_me(streamid, &vasi_rc); - if (!rc && vasi_rc == RTAS_NOT_SUSPENDABLE) + rc = rtas_ibm_suspend_me(streamid); + if (rc == -EAGAIN) ssleep(1); - } while (!rc && vasi_rc == RTAS_NOT_SUSPENDABLE); + } while (rc == -EAGAIN); if (rc) return rc; - if (vasi_rc) - return vasi_rc; post_mobility_fixup(); return count; } +/* + * Used by drmgr to determine the kernel behavior of the migration interface. + * + * Version 1: Performs all PAPR requirements for migration including + * firmware activation and device tree update. + */ +#define MIGRATION_API_VERSION 1 + static CLASS_ATTR(migration, S_IWUSR, NULL, migrate_store); +static CLASS_ATTR_STRING(api_version, S_IRUGO, __stringify(MIGRATION_API_VERSION)); static int __init mobility_sysfs_init(void) { @@ -352,7 +358,13 @@ static int __init mobility_sysfs_init(void) return -ENOMEM; rc = sysfs_create_file(mobility_kobj, &class_attr_migration.attr); + if (rc) + pr_err("mobility: unable to create migration sysfs file (%d)\n", rc); - return rc; + rc = sysfs_create_file(mobility_kobj, &class_attr_api_version.attr.attr); + if (rc) + pr_err("mobility: unable to create api_version sysfs file (%d)\n", rc); + + return 0; } machine_device_initcall(pseries, mobility_sysfs_init); diff --git a/arch/powerpc/platforms/pseries/msi.c b/arch/powerpc/platforms/pseries/msi.c index 691a154c286d..c8d24f9a6948 100644 --- a/arch/powerpc/platforms/pseries/msi.c +++ b/arch/powerpc/platforms/pseries/msi.c @@ -195,6 +195,7 @@ static struct device_node *find_pe_total_msi(struct pci_dev *dev, int *total) static struct device_node *find_pe_dn(struct pci_dev *dev, int *total) { struct device_node *dn; + struct pci_dn *pdn; struct eeh_dev *edev; /* Found our PE and assume 8 at that point. */ @@ -204,10 +205,11 @@ static struct device_node *find_pe_dn(struct pci_dev *dev, int *total) return NULL; /* Get the top level device in the PE */ - edev = of_node_to_eeh_dev(dn); + edev = pdn_to_eeh_dev(PCI_DN(dn)); if (edev->pe) edev = list_first_entry(&edev->pe->edevs, struct eeh_dev, list); - dn = eeh_dev_to_of_node(edev); + pdn = eeh_dev_to_pdn(edev); + dn = pdn ? pdn->node : NULL; if (!dn) return NULL; diff --git a/arch/powerpc/platforms/pseries/nvram.c b/arch/powerpc/platforms/pseries/nvram.c index 054a0ed5c7ee..9f8184175c86 100644 --- a/arch/powerpc/platforms/pseries/nvram.c +++ b/arch/powerpc/platforms/pseries/nvram.c @@ -20,7 +20,6 @@ #include <linux/kmsg_dump.h> #include <linux/pstore.h> #include <linux/ctype.h> -#include <linux/zlib.h> #include <asm/uaccess.h> #include <asm/nvram.h> #include <asm/rtas.h> @@ -30,129 +29,17 @@ /* Max bytes to read/write in one go */ #define NVRW_CNT 0x20 -/* - * Set oops header version to distinguish between old and new format header. - * lnx,oops-log partition max size is 4000, header version > 4000 will - * help in identifying new header. - */ -#define OOPS_HDR_VERSION 5000 - static unsigned int nvram_size; static int nvram_fetch, nvram_store; static char nvram_buf[NVRW_CNT]; /* assume this is in the first 4GB */ static DEFINE_SPINLOCK(nvram_lock); -struct err_log_info { - __be32 error_type; - __be32 seq_num; -}; - -struct nvram_os_partition { - const char *name; - int req_size; /* desired size, in bytes */ - int min_size; /* minimum acceptable size (0 means req_size) */ - long size; /* size of data portion (excluding err_log_info) */ - long index; /* offset of data portion of partition */ - bool os_partition; /* partition initialized by OS, not FW */ -}; - -static struct nvram_os_partition rtas_log_partition = { - .name = "ibm,rtas-log", - .req_size = 2079, - .min_size = 1055, - .index = -1, - .os_partition = true -}; - -static struct nvram_os_partition oops_log_partition = { - .name = "lnx,oops-log", - .req_size = 4000, - .min_size = 2000, - .index = -1, - .os_partition = true -}; - -static const char *pseries_nvram_os_partitions[] = { - "ibm,rtas-log", - "lnx,oops-log", - NULL -}; - -struct oops_log_info { - __be16 version; - __be16 report_length; - __be64 timestamp; -} __attribute__((packed)); - -static void oops_to_nvram(struct kmsg_dumper *dumper, - enum kmsg_dump_reason reason); - -static struct kmsg_dumper nvram_kmsg_dumper = { - .dump = oops_to_nvram -}; - /* See clobbering_unread_rtas_event() */ #define NVRAM_RTAS_READ_TIMEOUT 5 /* seconds */ -static unsigned long last_unread_rtas_event; /* timestamp */ - -/* - * For capturing and compressing an oops or panic report... - - * big_oops_buf[] holds the uncompressed text we're capturing. - * - * oops_buf[] holds the compressed text, preceded by a oops header. - * oops header has u16 holding the version of oops header (to differentiate - * between old and new format header) followed by u16 holding the length of - * the compressed* text (*Or uncompressed, if compression fails.) and u64 - * holding the timestamp. oops_buf[] gets written to NVRAM. - * - * oops_log_info points to the header. oops_data points to the compressed text. - * - * +- oops_buf - * | +- oops_data - * v v - * +-----------+-----------+-----------+------------------------+ - * | version | length | timestamp | text | - * | (2 bytes) | (2 bytes) | (8 bytes) | (oops_data_sz bytes) | - * +-----------+-----------+-----------+------------------------+ - * ^ - * +- oops_log_info - * - * We preallocate these buffers during init to avoid kmalloc during oops/panic. - */ -static size_t big_oops_buf_sz; -static char *big_oops_buf, *oops_buf; -static char *oops_data; -static size_t oops_data_sz; - -/* Compression parameters */ -#define COMPR_LEVEL 6 -#define WINDOW_BITS 12 -#define MEM_LEVEL 4 -static struct z_stream_s stream; +static time64_t last_unread_rtas_event; /* timestamp */ #ifdef CONFIG_PSTORE -static struct nvram_os_partition of_config_partition = { - .name = "of-config", - .index = -1, - .os_partition = false -}; - -static struct nvram_os_partition common_partition = { - .name = "common", - .index = -1, - .os_partition = false -}; - -static enum pstore_type_id nvram_type_ids[] = { - PSTORE_TYPE_DMESG, - PSTORE_TYPE_PPC_RTAS, - PSTORE_TYPE_PPC_OF, - PSTORE_TYPE_PPC_COMMON, - -1 -}; -static int read_type; -static unsigned long last_rtas_event; +time64_t last_rtas_event; #endif static ssize_t pSeries_nvram_read(char *buf, size_t count, loff_t *index) @@ -246,132 +133,26 @@ static ssize_t pSeries_nvram_get_size(void) return nvram_size ? nvram_size : -ENODEV; } - -/* nvram_write_os_partition, nvram_write_error_log +/* nvram_write_error_log * * We need to buffer the error logs into nvram to ensure that we have - * the failure information to decode. If we have a severe error there - * is no way to guarantee that the OS or the machine is in a state to - * get back to user land and write the error to disk. For example if - * the SCSI device driver causes a Machine Check by writing to a bad - * IO address, there is no way of guaranteeing that the device driver - * is in any state that is would also be able to write the error data - * captured to disk, thus we buffer it in NVRAM for analysis on the - * next boot. - * - * In NVRAM the partition containing the error log buffer will looks like: - * Header (in bytes): - * +-----------+----------+--------+------------+------------------+ - * | signature | checksum | length | name | data | - * |0 |1 |2 3|4 15|16 length-1| - * +-----------+----------+--------+------------+------------------+ - * - * The 'data' section would look like (in bytes): - * +--------------+------------+-----------------------------------+ - * | event_logged | sequence # | error log | - * |0 3|4 7|8 error_log_size-1| - * +--------------+------------+-----------------------------------+ - * - * event_logged: 0 if event has not been logged to syslog, 1 if it has - * sequence #: The unique sequence # for each event. (until it wraps) - * error log: The error log from event_scan + * the failure information to decode. */ -static int nvram_write_os_partition(struct nvram_os_partition *part, - char *buff, int length, - unsigned int err_type, - unsigned int error_log_cnt) -{ - int rc; - loff_t tmp_index; - struct err_log_info info; - - if (part->index == -1) { - return -ESPIPE; - } - - if (length > part->size) { - length = part->size; - } - - info.error_type = cpu_to_be32(err_type); - info.seq_num = cpu_to_be32(error_log_cnt); - - tmp_index = part->index; - - rc = ppc_md.nvram_write((char *)&info, sizeof(struct err_log_info), &tmp_index); - if (rc <= 0) { - pr_err("%s: Failed nvram_write (%d)\n", __func__, rc); - return rc; - } - - rc = ppc_md.nvram_write(buff, length, &tmp_index); - if (rc <= 0) { - pr_err("%s: Failed nvram_write (%d)\n", __func__, rc); - return rc; - } - - return 0; -} - int nvram_write_error_log(char * buff, int length, unsigned int err_type, unsigned int error_log_cnt) { int rc = nvram_write_os_partition(&rtas_log_partition, buff, length, err_type, error_log_cnt); if (!rc) { - last_unread_rtas_event = get_seconds(); + last_unread_rtas_event = ktime_get_real_seconds(); #ifdef CONFIG_PSTORE - last_rtas_event = get_seconds(); + last_rtas_event = ktime_get_real_seconds(); #endif } return rc; } -/* nvram_read_partition - * - * Reads nvram partition for at most 'length' - */ -static int nvram_read_partition(struct nvram_os_partition *part, char *buff, - int length, unsigned int *err_type, - unsigned int *error_log_cnt) -{ - int rc; - loff_t tmp_index; - struct err_log_info info; - - if (part->index == -1) - return -1; - - if (length > part->size) - length = part->size; - - tmp_index = part->index; - - if (part->os_partition) { - rc = ppc_md.nvram_read((char *)&info, - sizeof(struct err_log_info), - &tmp_index); - if (rc <= 0) { - pr_err("%s: Failed nvram_read (%d)\n", __func__, rc); - return rc; - } - } - - rc = ppc_md.nvram_read(buff, length, &tmp_index); - if (rc <= 0) { - pr_err("%s: Failed nvram_read (%d)\n", __func__, rc); - return rc; - } - - if (part->os_partition) { - *error_log_cnt = be32_to_cpu(info.seq_num); - *err_type = be32_to_cpu(info.error_type); - } - - return 0; -} - /* nvram_read_error_log * * Reads nvram for error log for at most 'length' @@ -407,67 +188,6 @@ int nvram_clear_error_log(void) return 0; } -/* pseries_nvram_init_os_partition - * - * This sets up a partition with an "OS" signature. - * - * The general strategy is the following: - * 1.) If a partition with the indicated name already exists... - * - If it's large enough, use it. - * - Otherwise, recycle it and keep going. - * 2.) Search for a free partition that is large enough. - * 3.) If there's not a free partition large enough, recycle any obsolete - * OS partitions and try again. - * 4.) Will first try getting a chunk that will satisfy the requested size. - * 5.) If a chunk of the requested size cannot be allocated, then try finding - * a chunk that will satisfy the minum needed. - * - * Returns 0 on success, else -1. - */ -static int __init pseries_nvram_init_os_partition(struct nvram_os_partition - *part) -{ - loff_t p; - int size; - - /* Look for ours */ - p = nvram_find_partition(part->name, NVRAM_SIG_OS, &size); - - /* Found one but too small, remove it */ - if (p && size < part->min_size) { - pr_info("nvram: Found too small %s partition," - " removing it...\n", part->name); - nvram_remove_partition(part->name, NVRAM_SIG_OS, NULL); - p = 0; - } - - /* Create one if we didn't find */ - if (!p) { - p = nvram_create_partition(part->name, NVRAM_SIG_OS, - part->req_size, part->min_size); - if (p == -ENOSPC) { - pr_info("nvram: No room to create %s partition, " - "deleting any obsolete OS partitions...\n", - part->name); - nvram_remove_partition(NULL, NVRAM_SIG_OS, - pseries_nvram_os_partitions); - p = nvram_create_partition(part->name, NVRAM_SIG_OS, - part->req_size, part->min_size); - } - } - - if (p <= 0) { - pr_err("nvram: Failed to find or create %s" - " partition, err %d\n", part->name, (int)p); - return -1; - } - - part->index = p; - part->size = nvram_get_partition_size(p) - sizeof(struct err_log_info); - - return 0; -} - /* * Are we using the ibm,rtas-log for oops/panic reports? And if so, * would logging this oops/panic overwrite an RTAS event that rtas_errd @@ -476,321 +196,14 @@ static int __init pseries_nvram_init_os_partition(struct nvram_os_partition * We assume that if rtas_errd hasn't read the RTAS event in * NVRAM_RTAS_READ_TIMEOUT seconds, it's probably not going to. */ -static int clobbering_unread_rtas_event(void) +int clobbering_unread_rtas_event(void) { return (oops_log_partition.index == rtas_log_partition.index && last_unread_rtas_event - && get_seconds() - last_unread_rtas_event <= + && ktime_get_real_seconds() - last_unread_rtas_event <= NVRAM_RTAS_READ_TIMEOUT); } -/* Derived from logfs_compress() */ -static int nvram_compress(const void *in, void *out, size_t inlen, - size_t outlen) -{ - int err, ret; - - ret = -EIO; - err = zlib_deflateInit2(&stream, COMPR_LEVEL, Z_DEFLATED, WINDOW_BITS, - MEM_LEVEL, Z_DEFAULT_STRATEGY); - if (err != Z_OK) - goto error; - - stream.next_in = in; - stream.avail_in = inlen; - stream.total_in = 0; - stream.next_out = out; - stream.avail_out = outlen; - stream.total_out = 0; - - err = zlib_deflate(&stream, Z_FINISH); - if (err != Z_STREAM_END) - goto error; - - err = zlib_deflateEnd(&stream); - if (err != Z_OK) - goto error; - - if (stream.total_out >= stream.total_in) - goto error; - - ret = stream.total_out; -error: - return ret; -} - -/* Compress the text from big_oops_buf into oops_buf. */ -static int zip_oops(size_t text_len) -{ - struct oops_log_info *oops_hdr = (struct oops_log_info *)oops_buf; - int zipped_len = nvram_compress(big_oops_buf, oops_data, text_len, - oops_data_sz); - if (zipped_len < 0) { - pr_err("nvram: compression failed; returned %d\n", zipped_len); - pr_err("nvram: logging uncompressed oops/panic report\n"); - return -1; - } - oops_hdr->version = cpu_to_be16(OOPS_HDR_VERSION); - oops_hdr->report_length = cpu_to_be16(zipped_len); - oops_hdr->timestamp = cpu_to_be64(get_seconds()); - return 0; -} - -#ifdef CONFIG_PSTORE -static int nvram_pstore_open(struct pstore_info *psi) -{ - /* Reset the iterator to start reading partitions again */ - read_type = -1; - return 0; -} - -/** - * nvram_pstore_write - pstore write callback for nvram - * @type: Type of message logged - * @reason: reason behind dump (oops/panic) - * @id: identifier to indicate the write performed - * @part: pstore writes data to registered buffer in parts, - * part number will indicate the same. - * @count: Indicates oops count - * @compressed: Flag to indicate the log is compressed - * @size: number of bytes written to the registered buffer - * @psi: registered pstore_info structure - * - * Called by pstore_dump() when an oops or panic report is logged in the - * printk buffer. - * Returns 0 on successful write. - */ -static int nvram_pstore_write(enum pstore_type_id type, - enum kmsg_dump_reason reason, - u64 *id, unsigned int part, int count, - bool compressed, size_t size, - struct pstore_info *psi) -{ - int rc; - unsigned int err_type = ERR_TYPE_KERNEL_PANIC; - struct oops_log_info *oops_hdr = (struct oops_log_info *) oops_buf; - - /* part 1 has the recent messages from printk buffer */ - if (part > 1 || type != PSTORE_TYPE_DMESG || - clobbering_unread_rtas_event()) - return -1; - - oops_hdr->version = cpu_to_be16(OOPS_HDR_VERSION); - oops_hdr->report_length = cpu_to_be16(size); - oops_hdr->timestamp = cpu_to_be64(get_seconds()); - - if (compressed) - err_type = ERR_TYPE_KERNEL_PANIC_GZ; - - rc = nvram_write_os_partition(&oops_log_partition, oops_buf, - (int) (sizeof(*oops_hdr) + size), err_type, count); - - if (rc != 0) - return rc; - - *id = part; - return 0; -} - -/* - * Reads the oops/panic report, rtas, of-config and common partition. - * Returns the length of the data we read from each partition. - * Returns 0 if we've been called before. - */ -static ssize_t nvram_pstore_read(u64 *id, enum pstore_type_id *type, - int *count, struct timespec *time, char **buf, - bool *compressed, struct pstore_info *psi) -{ - struct oops_log_info *oops_hdr; - unsigned int err_type, id_no, size = 0; - struct nvram_os_partition *part = NULL; - char *buff = NULL; - int sig = 0; - loff_t p; - - read_type++; - - switch (nvram_type_ids[read_type]) { - case PSTORE_TYPE_DMESG: - part = &oops_log_partition; - *type = PSTORE_TYPE_DMESG; - break; - case PSTORE_TYPE_PPC_RTAS: - part = &rtas_log_partition; - *type = PSTORE_TYPE_PPC_RTAS; - time->tv_sec = last_rtas_event; - time->tv_nsec = 0; - break; - case PSTORE_TYPE_PPC_OF: - sig = NVRAM_SIG_OF; - part = &of_config_partition; - *type = PSTORE_TYPE_PPC_OF; - *id = PSTORE_TYPE_PPC_OF; - time->tv_sec = 0; - time->tv_nsec = 0; - break; - case PSTORE_TYPE_PPC_COMMON: - sig = NVRAM_SIG_SYS; - part = &common_partition; - *type = PSTORE_TYPE_PPC_COMMON; - *id = PSTORE_TYPE_PPC_COMMON; - time->tv_sec = 0; - time->tv_nsec = 0; - break; - default: - return 0; - } - - if (!part->os_partition) { - p = nvram_find_partition(part->name, sig, &size); - if (p <= 0) { - pr_err("nvram: Failed to find partition %s, " - "err %d\n", part->name, (int)p); - return 0; - } - part->index = p; - part->size = size; - } - - buff = kmalloc(part->size, GFP_KERNEL); - - if (!buff) - return -ENOMEM; - - if (nvram_read_partition(part, buff, part->size, &err_type, &id_no)) { - kfree(buff); - return 0; - } - - *count = 0; - - if (part->os_partition) - *id = id_no; - - if (nvram_type_ids[read_type] == PSTORE_TYPE_DMESG) { - size_t length, hdr_size; - - oops_hdr = (struct oops_log_info *)buff; - if (be16_to_cpu(oops_hdr->version) < OOPS_HDR_VERSION) { - /* Old format oops header had 2-byte record size */ - hdr_size = sizeof(u16); - length = be16_to_cpu(oops_hdr->version); - time->tv_sec = 0; - time->tv_nsec = 0; - } else { - hdr_size = sizeof(*oops_hdr); - length = be16_to_cpu(oops_hdr->report_length); - time->tv_sec = be64_to_cpu(oops_hdr->timestamp); - time->tv_nsec = 0; - } - *buf = kmalloc(length, GFP_KERNEL); - if (*buf == NULL) - return -ENOMEM; - memcpy(*buf, buff + hdr_size, length); - kfree(buff); - - if (err_type == ERR_TYPE_KERNEL_PANIC_GZ) - *compressed = true; - else - *compressed = false; - return length; - } - - *buf = buff; - return part->size; -} - -static struct pstore_info nvram_pstore_info = { - .owner = THIS_MODULE, - .name = "nvram", - .open = nvram_pstore_open, - .read = nvram_pstore_read, - .write = nvram_pstore_write, -}; - -static int nvram_pstore_init(void) -{ - int rc = 0; - - nvram_pstore_info.buf = oops_data; - nvram_pstore_info.bufsize = oops_data_sz; - - spin_lock_init(&nvram_pstore_info.buf_lock); - - rc = pstore_register(&nvram_pstore_info); - if (rc != 0) - pr_err("nvram: pstore_register() failed, defaults to " - "kmsg_dump; returned %d\n", rc); - - return rc; -} -#else -static int nvram_pstore_init(void) -{ - return -1; -} -#endif - -static void __init nvram_init_oops_partition(int rtas_partition_exists) -{ - int rc; - - rc = pseries_nvram_init_os_partition(&oops_log_partition); - if (rc != 0) { - if (!rtas_partition_exists) - return; - pr_notice("nvram: Using %s partition to log both" - " RTAS errors and oops/panic reports\n", - rtas_log_partition.name); - memcpy(&oops_log_partition, &rtas_log_partition, - sizeof(rtas_log_partition)); - } - oops_buf = kmalloc(oops_log_partition.size, GFP_KERNEL); - if (!oops_buf) { - pr_err("nvram: No memory for %s partition\n", - oops_log_partition.name); - return; - } - oops_data = oops_buf + sizeof(struct oops_log_info); - oops_data_sz = oops_log_partition.size - sizeof(struct oops_log_info); - - rc = nvram_pstore_init(); - - if (!rc) - return; - - /* - * Figure compression (preceded by elimination of each line's <n> - * severity prefix) will reduce the oops/panic report to at most - * 45% of its original size. - */ - big_oops_buf_sz = (oops_data_sz * 100) / 45; - big_oops_buf = kmalloc(big_oops_buf_sz, GFP_KERNEL); - if (big_oops_buf) { - stream.workspace = kmalloc(zlib_deflate_workspacesize( - WINDOW_BITS, MEM_LEVEL), GFP_KERNEL); - if (!stream.workspace) { - pr_err("nvram: No memory for compression workspace; " - "skipping compression of %s partition data\n", - oops_log_partition.name); - kfree(big_oops_buf); - big_oops_buf = NULL; - } - } else { - pr_err("No memory for uncompressed %s data; " - "skipping compression\n", oops_log_partition.name); - stream.workspace = NULL; - } - - rc = kmsg_dump_register(&nvram_kmsg_dumper); - if (rc != 0) { - pr_err("nvram: kmsg_dump_register() failed; returned %d\n", rc); - kfree(oops_buf); - kfree(big_oops_buf); - kfree(stream.workspace); - } -} - static int __init pseries_nvram_init_log_partitions(void) { int rc; @@ -798,7 +211,7 @@ static int __init pseries_nvram_init_log_partitions(void) /* Scan nvram for partitions */ nvram_scan_partitions(); - rc = pseries_nvram_init_os_partition(&rtas_log_partition); + rc = nvram_init_os_partition(&rtas_log_partition); nvram_init_oops_partition(rc == 0); return 0; } @@ -834,72 +247,3 @@ int __init pSeries_nvram_init(void) return 0; } - -/* - * This is our kmsg_dump callback, called after an oops or panic report - * has been written to the printk buffer. We want to capture as much - * of the printk buffer as possible. First, capture as much as we can - * that we think will compress sufficiently to fit in the lnx,oops-log - * partition. If that's too much, go back and capture uncompressed text. - */ -static void oops_to_nvram(struct kmsg_dumper *dumper, - enum kmsg_dump_reason reason) -{ - struct oops_log_info *oops_hdr = (struct oops_log_info *)oops_buf; - static unsigned int oops_count = 0; - static bool panicking = false; - static DEFINE_SPINLOCK(lock); - unsigned long flags; - size_t text_len; - unsigned int err_type = ERR_TYPE_KERNEL_PANIC_GZ; - int rc = -1; - - switch (reason) { - case KMSG_DUMP_RESTART: - case KMSG_DUMP_HALT: - case KMSG_DUMP_POWEROFF: - /* These are almost always orderly shutdowns. */ - return; - case KMSG_DUMP_OOPS: - break; - case KMSG_DUMP_PANIC: - panicking = true; - break; - case KMSG_DUMP_EMERG: - if (panicking) - /* Panic report already captured. */ - return; - break; - default: - pr_err("%s: ignoring unrecognized KMSG_DUMP_* reason %d\n", - __func__, (int) reason); - return; - } - - if (clobbering_unread_rtas_event()) - return; - - if (!spin_trylock_irqsave(&lock, flags)) - return; - - if (big_oops_buf) { - kmsg_dump_get_buffer(dumper, false, - big_oops_buf, big_oops_buf_sz, &text_len); - rc = zip_oops(text_len); - } - if (rc != 0) { - kmsg_dump_rewind(dumper); - kmsg_dump_get_buffer(dumper, false, - oops_data, oops_data_sz, &text_len); - err_type = ERR_TYPE_KERNEL_PANIC; - oops_hdr->version = cpu_to_be16(OOPS_HDR_VERSION); - oops_hdr->report_length = cpu_to_be16(text_len); - oops_hdr->timestamp = cpu_to_be64(get_seconds()); - } - - (void) nvram_write_os_partition(&oops_log_partition, oops_buf, - (int) (sizeof(*oops_hdr) + text_len), err_type, - ++oops_count); - - spin_unlock_irqrestore(&lock, flags); -} diff --git a/arch/powerpc/platforms/pseries/pci_dlpar.c b/arch/powerpc/platforms/pseries/pci_dlpar.c index 89e23811199c..5d4a3df59d0c 100644 --- a/arch/powerpc/platforms/pseries/pci_dlpar.c +++ b/arch/powerpc/platforms/pseries/pci_dlpar.c @@ -32,6 +32,8 @@ #include <asm/firmware.h> #include <asm/eeh.h> +#include "pseries.h" + static struct pci_bus * find_bus_among_children(struct pci_bus *bus, struct device_node *dn) @@ -75,6 +77,7 @@ struct pci_controller *init_phb_dynamic(struct device_node *dn) return NULL; rtas_setup_phb(phb); pci_process_bridge_OF_ranges(phb, dn, 0); + phb->controller_ops = pseries_pci_controller_ops; pci_devs_phb_init_dynamic(phb); @@ -82,7 +85,7 @@ struct pci_controller *init_phb_dynamic(struct device_node *dn) eeh_dev_phb_init_dynamic(phb); if (dn->child) - eeh_add_device_tree_early(dn); + eeh_add_device_tree_early(PCI_DN(dn)); pcibios_scan_phb(phb); pcibios_finish_adding_to_bus(phb->bus); diff --git a/arch/powerpc/platforms/pseries/pseries.h b/arch/powerpc/platforms/pseries/pseries.h index 1796c5438cc6..8411c27293e4 100644 --- a/arch/powerpc/platforms/pseries/pseries.h +++ b/arch/powerpc/platforms/pseries/pseries.h @@ -11,6 +11,7 @@ #define _PSERIES_PSERIES_H #include <linux/interrupt.h> +#include <asm/rtas.h> struct device_node; @@ -60,11 +61,24 @@ extern struct device_node *dlpar_configure_connector(__be32, struct device_node *); extern int dlpar_attach_node(struct device_node *); extern int dlpar_detach_node(struct device_node *); +extern int dlpar_acquire_drc(u32 drc_index); +extern int dlpar_release_drc(u32 drc_index); + +#ifdef CONFIG_MEMORY_HOTPLUG +int dlpar_memory(struct pseries_hp_errorlog *hp_elog); +#else +static inline int dlpar_memory(struct pseries_hp_errorlog *hp_elog) +{ + return -EOPNOTSUPP; +} +#endif /* PCI root bridge prepare function override for pseries */ struct pci_host_bridge; int pseries_root_bridge_prepare(struct pci_host_bridge *bridge); +extern struct pci_controller_ops pseries_pci_controller_ops; + unsigned long pseries_memory_block_size(void); #endif /* _PSERIES_PSERIES_H */ diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index e445b6701f50..df6a7041922b 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -265,7 +265,7 @@ static int pci_dn_reconfig_notifier(struct notifier_block *nb, unsigned long act update_dn_pci_info(np, pci->phb); /* Create EEH device for the OF node */ - eeh_dev_init(np, pci->phb); + eeh_dev_init(PCI_DN(np), pci->phb); } break; default: @@ -461,6 +461,47 @@ static long pseries_little_endian_exceptions(void) } #endif +static void __init find_and_init_phbs(void) +{ + struct device_node *node; + struct pci_controller *phb; + struct device_node *root = of_find_node_by_path("/"); + + for_each_child_of_node(root, node) { + if (node->type == NULL || (strcmp(node->type, "pci") != 0 && + strcmp(node->type, "pciex") != 0)) + continue; + + phb = pcibios_alloc_controller(node); + if (!phb) + continue; + rtas_setup_phb(phb); + pci_process_bridge_OF_ranges(phb, node, 0); + isa_bridge_find_early(phb); + phb->controller_ops = pseries_pci_controller_ops; + } + + of_node_put(root); + pci_devs_phb_init(); + + /* + * PCI_PROBE_ONLY and PCI_REASSIGN_ALL_BUS can be set via properties + * in chosen. + */ + if (of_chosen) { + const int *prop; + + prop = of_get_property(of_chosen, + "linux,pci-probe-only", NULL); + if (prop) { + if (*prop) + pci_add_flags(PCI_PROBE_ONLY); + else + pci_clear_flags(PCI_PROBE_ONLY); + } + } +} + static void __init pSeries_setup_arch(void) { set_arch_panic_timeout(10, ARCH_PANIC_TIMEOUT); @@ -793,6 +834,10 @@ static int pSeries_pci_probe_mode(struct pci_bus *bus) void pSeries_final_fixup(void) { } #endif +struct pci_controller_ops pseries_pci_controller_ops = { + .probe_mode = pSeries_pci_probe_mode, +}; + define_machine(pseries) { .name = "pSeries", .probe = pSeries_probe, @@ -801,7 +846,6 @@ define_machine(pseries) { .show_cpuinfo = pSeries_show_cpuinfo, .log_error = pSeries_log_error, .pcibios_fixup = pSeries_final_fixup, - .pci_probe_mode = pSeries_pci_probe_mode, .restart = rtas_restart, .halt = rtas_halt, .panic = rtas_os_term, diff --git a/arch/powerpc/platforms/pseries/smp.c b/arch/powerpc/platforms/pseries/smp.c index a3555b10c1a5..6932ea803e33 100644 --- a/arch/powerpc/platforms/pseries/smp.c +++ b/arch/powerpc/platforms/pseries/smp.c @@ -197,16 +197,14 @@ static void pSeries_cause_ipi_mux(int cpu, unsigned long data) xics_cause_ipi(cpu, data); } -static __init int pSeries_smp_probe(void) +static __init void pSeries_smp_probe(void) { - int ret = xics_smp_probe(); + xics_smp_probe(); if (cpu_has_feature(CPU_FTR_DBELL)) { xics_cause_ipi = smp_ops->cause_ipi; smp_ops->cause_ipi = pSeries_cause_ipi_mux; } - - return ret; } static struct smp_ops_t pSeries_mpic_smp_ops = { |