aboutsummaryrefslogtreecommitdiff
path: root/arch/ppc/kernel/dma-mapping.c
diff options
context:
space:
mode:
Diffstat (limited to 'arch/ppc/kernel/dma-mapping.c')
-rw-r--r--arch/ppc/kernel/dma-mapping.c442
1 files changed, 0 insertions, 442 deletions
diff --git a/arch/ppc/kernel/dma-mapping.c b/arch/ppc/kernel/dma-mapping.c
deleted file mode 100644
index 10fec736396..00000000000
--- a/arch/ppc/kernel/dma-mapping.c
+++ /dev/null
@@ -1,442 +0,0 @@
-/*
- * PowerPC version derived from arch/arm/mm/consistent.c
- * Copyright (C) 2001 Dan Malek (dmalek@jlc.net)
- *
- * Copyright (C) 2000 Russell King
- *
- * Consistent memory allocators. Used for DMA devices that want to
- * share uncached memory with the processor core. The function return
- * is the virtual address and 'dma_handle' is the physical address.
- * Mostly stolen from the ARM port, with some changes for PowerPC.
- * -- Dan
- *
- * Reorganized to get rid of the arch-specific consistent_* functions
- * and provide non-coherent implementations for the DMA API. -Matt
- *
- * Added in_interrupt() safe dma_alloc_coherent()/dma_free_coherent()
- * implementation. This is pulled straight from ARM and barely
- * modified. -Matt
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/module.h>
-#include <linux/signal.h>
-#include <linux/sched.h>
-#include <linux/kernel.h>
-#include <linux/errno.h>
-#include <linux/string.h>
-#include <linux/types.h>
-#include <linux/ptrace.h>
-#include <linux/mman.h>
-#include <linux/mm.h>
-#include <linux/swap.h>
-#include <linux/stddef.h>
-#include <linux/vmalloc.h>
-#include <linux/init.h>
-#include <linux/delay.h>
-#include <linux/bootmem.h>
-#include <linux/highmem.h>
-#include <linux/dma-mapping.h>
-#include <linux/hardirq.h>
-
-#include <asm/pgalloc.h>
-#include <asm/prom.h>
-#include <asm/io.h>
-#include <asm/mmu_context.h>
-#include <asm/pgtable.h>
-#include <asm/mmu.h>
-#include <asm/uaccess.h>
-#include <asm/smp.h>
-#include <asm/machdep.h>
-
-int map_page(unsigned long va, phys_addr_t pa, int flags);
-
-#include <asm/tlbflush.h>
-
-/*
- * This address range defaults to a value that is safe for all
- * platforms which currently set CONFIG_NOT_COHERENT_CACHE. It
- * can be further configured for specific applications under
- * the "Advanced Setup" menu. -Matt
- */
-#define CONSISTENT_BASE (CONFIG_CONSISTENT_START)
-#define CONSISTENT_END (CONFIG_CONSISTENT_START + CONFIG_CONSISTENT_SIZE)
-#define CONSISTENT_OFFSET(x) (((unsigned long)(x) - CONSISTENT_BASE) >> PAGE_SHIFT)
-
-/*
- * This is the page table (2MB) covering uncached, DMA consistent allocations
- */
-static pte_t *consistent_pte;
-static DEFINE_SPINLOCK(consistent_lock);
-
-/*
- * VM region handling support.
- *
- * This should become something generic, handling VM region allocations for
- * vmalloc and similar (ioremap, module space, etc).
- *
- * I envisage vmalloc()'s supporting vm_struct becoming:
- *
- * struct vm_struct {
- * struct vm_region region;
- * unsigned long flags;
- * struct page **pages;
- * unsigned int nr_pages;
- * unsigned long phys_addr;
- * };
- *
- * get_vm_area() would then call vm_region_alloc with an appropriate
- * struct vm_region head (eg):
- *
- * struct vm_region vmalloc_head = {
- * .vm_list = LIST_HEAD_INIT(vmalloc_head.vm_list),
- * .vm_start = VMALLOC_START,
- * .vm_end = VMALLOC_END,
- * };
- *
- * However, vmalloc_head.vm_start is variable (typically, it is dependent on
- * the amount of RAM found at boot time.) I would imagine that get_vm_area()
- * would have to initialise this each time prior to calling vm_region_alloc().
- */
-struct vm_region {
- struct list_head vm_list;
- unsigned long vm_start;
- unsigned long vm_end;
-};
-
-static struct vm_region consistent_head = {
- .vm_list = LIST_HEAD_INIT(consistent_head.vm_list),
- .vm_start = CONSISTENT_BASE,
- .vm_end = CONSISTENT_END,
-};
-
-static struct vm_region *
-vm_region_alloc(struct vm_region *head, size_t size, gfp_t gfp)
-{
- unsigned long addr = head->vm_start, end = head->vm_end - size;
- unsigned long flags;
- struct vm_region *c, *new;
-
- new = kmalloc(sizeof(struct vm_region), gfp);
- if (!new)
- goto out;
-
- spin_lock_irqsave(&consistent_lock, flags);
-
- list_for_each_entry(c, &head->vm_list, vm_list) {
- if ((addr + size) < addr)
- goto nospc;
- if ((addr + size) <= c->vm_start)
- goto found;
- addr = c->vm_end;
- if (addr > end)
- goto nospc;
- }
-
- found:
- /*
- * Insert this entry _before_ the one we found.
- */
- list_add_tail(&new->vm_list, &c->vm_list);
- new->vm_start = addr;
- new->vm_end = addr + size;
-
- spin_unlock_irqrestore(&consistent_lock, flags);
- return new;
-
- nospc:
- spin_unlock_irqrestore(&consistent_lock, flags);
- kfree(new);
- out:
- return NULL;
-}
-
-static struct vm_region *vm_region_find(struct vm_region *head, unsigned long addr)
-{
- struct vm_region *c;
-
- list_for_each_entry(c, &head->vm_list, vm_list) {
- if (c->vm_start == addr)
- goto out;
- }
- c = NULL;
- out:
- return c;
-}
-
-/*
- * Allocate DMA-coherent memory space and return both the kernel remapped
- * virtual and bus address for that space.
- */
-void *
-__dma_alloc_coherent(size_t size, dma_addr_t *handle, gfp_t gfp)
-{
- struct page *page;
- struct vm_region *c;
- unsigned long order;
- u64 mask = 0x00ffffff, limit; /* ISA default */
-
- if (!consistent_pte) {
- printk(KERN_ERR "%s: not initialised\n", __func__);
- dump_stack();
- return NULL;
- }
-
- size = PAGE_ALIGN(size);
- limit = (mask + 1) & ~mask;
- if ((limit && size >= limit) || size >= (CONSISTENT_END - CONSISTENT_BASE)) {
- printk(KERN_WARNING "coherent allocation too big (requested %#x mask %#Lx)\n",
- size, mask);
- return NULL;
- }
-
- order = get_order(size);
-
- if (mask != 0xffffffff)
- gfp |= GFP_DMA;
-
- page = alloc_pages(gfp, order);
- if (!page)
- goto no_page;
-
- /*
- * Invalidate any data that might be lurking in the
- * kernel direct-mapped region for device DMA.
- */
- {
- unsigned long kaddr = (unsigned long)page_address(page);
- memset(page_address(page), 0, size);
- flush_dcache_range(kaddr, kaddr + size);
- }
-
- /*
- * Allocate a virtual address in the consistent mapping region.
- */
- c = vm_region_alloc(&consistent_head, size,
- gfp & ~(__GFP_DMA | __GFP_HIGHMEM));
- if (c) {
- unsigned long vaddr = c->vm_start;
- pte_t *pte = consistent_pte + CONSISTENT_OFFSET(vaddr);
- struct page *end = page + (1 << order);
-
- split_page(page, order);
-
- /*
- * Set the "dma handle"
- */
- *handle = page_to_bus(page);
-
- do {
- BUG_ON(!pte_none(*pte));
-
- SetPageReserved(page);
- set_pte_at(&init_mm, vaddr,
- pte, mk_pte(page, pgprot_noncached(PAGE_KERNEL)));
- page++;
- pte++;
- vaddr += PAGE_SIZE;
- } while (size -= PAGE_SIZE);
-
- /*
- * Free the otherwise unused pages.
- */
- while (page < end) {
- __free_page(page);
- page++;
- }
-
- return (void *)c->vm_start;
- }
-
- if (page)
- __free_pages(page, order);
- no_page:
- return NULL;
-}
-EXPORT_SYMBOL(__dma_alloc_coherent);
-
-/*
- * free a page as defined by the above mapping.
- */
-void __dma_free_coherent(size_t size, void *vaddr)
-{
- struct vm_region *c;
- unsigned long flags, addr;
- pte_t *ptep;
-
- size = PAGE_ALIGN(size);
-
- spin_lock_irqsave(&consistent_lock, flags);
-
- c = vm_region_find(&consistent_head, (unsigned long)vaddr);
- if (!c)
- goto no_area;
-
- if ((c->vm_end - c->vm_start) != size) {
- printk(KERN_ERR "%s: freeing wrong coherent size (%ld != %d)\n",
- __func__, c->vm_end - c->vm_start, size);
- dump_stack();
- size = c->vm_end - c->vm_start;
- }
-
- ptep = consistent_pte + CONSISTENT_OFFSET(c->vm_start);
- addr = c->vm_start;
- do {
- pte_t pte = ptep_get_and_clear(&init_mm, addr, ptep);
- unsigned long pfn;
-
- ptep++;
- addr += PAGE_SIZE;
-
- if (!pte_none(pte) && pte_present(pte)) {
- pfn = pte_pfn(pte);
-
- if (pfn_valid(pfn)) {
- struct page *page = pfn_to_page(pfn);
- ClearPageReserved(page);
-
- __free_page(page);
- continue;
- }
- }
-
- printk(KERN_CRIT "%s: bad page in kernel page table\n",
- __func__);
- } while (size -= PAGE_SIZE);
-
- flush_tlb_kernel_range(c->vm_start, c->vm_end);
-
- list_del(&c->vm_list);
-
- spin_unlock_irqrestore(&consistent_lock, flags);
-
- kfree(c);
- return;
-
- no_area:
- spin_unlock_irqrestore(&consistent_lock, flags);
- printk(KERN_ERR "%s: trying to free invalid coherent area: %p\n",
- __func__, vaddr);
- dump_stack();
-}
-EXPORT_SYMBOL(__dma_free_coherent);
-
-/*
- * Initialise the consistent memory allocation.
- */
-static int __init dma_alloc_init(void)
-{
- pgd_t *pgd;
- pmd_t *pmd;
- pte_t *pte;
- int ret = 0;
-
- do {
- pgd = pgd_offset(&init_mm, CONSISTENT_BASE);
- pmd = pmd_alloc(&init_mm, pgd, CONSISTENT_BASE);
- if (!pmd) {
- printk(KERN_ERR "%s: no pmd tables\n", __func__);
- ret = -ENOMEM;
- break;
- }
- WARN_ON(!pmd_none(*pmd));
-
- pte = pte_alloc_kernel(pmd, CONSISTENT_BASE);
- if (!pte) {
- printk(KERN_ERR "%s: no pte tables\n", __func__);
- ret = -ENOMEM;
- break;
- }
-
- consistent_pte = pte;
- } while (0);
-
- return ret;
-}
-
-core_initcall(dma_alloc_init);
-
-/*
- * make an area consistent.
- */
-void __dma_sync(void *vaddr, size_t size, int direction)
-{
- unsigned long start = (unsigned long)vaddr;
- unsigned long end = start + size;
-
- switch (direction) {
- case DMA_NONE:
- BUG();
- case DMA_FROM_DEVICE: /* invalidate only */
- invalidate_dcache_range(start, end);
- break;
- case DMA_TO_DEVICE: /* writeback only */
- clean_dcache_range(start, end);
- break;
- case DMA_BIDIRECTIONAL: /* writeback and invalidate */
- flush_dcache_range(start, end);
- break;
- }
-}
-EXPORT_SYMBOL(__dma_sync);
-
-#ifdef CONFIG_HIGHMEM
-/*
- * __dma_sync_page() implementation for systems using highmem.
- * In this case, each page of a buffer must be kmapped/kunmapped
- * in order to have a virtual address for __dma_sync(). This must
- * not sleep so kmap_atomic()/kunmap_atomic() are used.
- *
- * Note: yes, it is possible and correct to have a buffer extend
- * beyond the first page.
- */
-static inline void __dma_sync_page_highmem(struct page *page,
- unsigned long offset, size_t size, int direction)
-{
- size_t seg_size = min((size_t)(PAGE_SIZE - offset), size);
- size_t cur_size = seg_size;
- unsigned long flags, start, seg_offset = offset;
- int nr_segs = 1 + ((size - seg_size) + PAGE_SIZE - 1)/PAGE_SIZE;
- int seg_nr = 0;
-
- local_irq_save(flags);
-
- do {
- start = (unsigned long)kmap_atomic(page + seg_nr,
- KM_PPC_SYNC_PAGE) + seg_offset;
-
- /* Sync this buffer segment */
- __dma_sync((void *)start, seg_size, direction);
- kunmap_atomic((void *)start, KM_PPC_SYNC_PAGE);
- seg_nr++;
-
- /* Calculate next buffer segment size */
- seg_size = min((size_t)PAGE_SIZE, size - cur_size);
-
- /* Add the segment size to our running total */
- cur_size += seg_size;
- seg_offset = 0;
- } while (seg_nr < nr_segs);
-
- local_irq_restore(flags);
-}
-#endif /* CONFIG_HIGHMEM */
-
-/*
- * __dma_sync_page makes memory consistent. identical to __dma_sync, but
- * takes a struct page instead of a virtual address
- */
-void __dma_sync_page(struct page *page, unsigned long offset,
- size_t size, int direction)
-{
-#ifdef CONFIG_HIGHMEM
- __dma_sync_page_highmem(page, offset, size, direction);
-#else
- unsigned long start = (unsigned long)page_address(page) + offset;
- __dma_sync((void *)start, size, direction);
-#endif
-}
-EXPORT_SYMBOL(__dma_sync_page);
00%'> -rw-r--r--arch/powerpc/kernel/irq.c1056
-rw-r--r--arch/powerpc/kernel/isa-bridge.c15
-rw-r--r--arch/powerpc/kernel/kgdb.c40
-rw-r--r--arch/powerpc/kernel/kprobes.c38
-rw-r--r--arch/powerpc/kernel/kvm.c392
-rw-r--r--arch/powerpc/kernel/kvm_emul.S124
-rw-r--r--arch/powerpc/kernel/legacy_serial.c96
-rw-r--r--arch/powerpc/kernel/lparcfg.c813
-rw-r--r--arch/powerpc/kernel/machine_kexec.c59
-rw-r--r--arch/powerpc/kernel/machine_kexec_64.c27
-rw-r--r--arch/powerpc/kernel/mce.c352
-rw-r--r--arch/powerpc/kernel/mce_power.c313
-rw-r--r--arch/powerpc/kernel/misc.S8
-rw-r--r--arch/powerpc/kernel/misc_32.S298
-rw-r--r--arch/powerpc/kernel/misc_64.S167
-rw-r--r--arch/powerpc/kernel/module.c3
-rw-r--r--arch/powerpc/kernel/module_32.c14
-rw-r--r--arch/powerpc/kernel/module_64.c309
-rw-r--r--arch/powerpc/kernel/mpc7450-pmu.c422
-rw-r--r--arch/powerpc/kernel/nvram_64.c35
-rw-r--r--arch/powerpc/kernel/of_platform.c17
-rw-r--r--arch/powerpc/kernel/paca.c73
-rw-r--r--arch/powerpc/kernel/pci-common.c538
-rw-r--r--arch/powerpc/kernel/pci-hotplug.c109
-rw-r--r--arch/powerpc/kernel/pci_32.c12
-rw-r--r--arch/powerpc/kernel/pci_64.c43
-rw-r--r--arch/powerpc/kernel/pci_dn.c32
-rw-r--r--arch/powerpc/kernel/pci_of_scan.c117
-rw-r--r--arch/powerpc/kernel/perf_callchain.c492
-rw-r--r--arch/powerpc/kernel/perf_event.c1432
-rw-r--r--arch/powerpc/kernel/perf_event_fsl_emb.c688
-rw-r--r--arch/powerpc/kernel/pmc.c1
-rw-r--r--arch/powerpc/kernel/power4-pmu.c621
-rw-r--r--arch/powerpc/kernel/power5+-pmu.c690
-rw-r--r--arch/powerpc/kernel/power5-pmu.c629
-rw-r--r--arch/powerpc/kernel/power6-pmu.c552
-rw-r--r--arch/powerpc/kernel/power7-pmu.c379
-rw-r--r--arch/powerpc/kernel/ppc32.h77
-rw-r--r--arch/powerpc/kernel/ppc970-pmu.c502
-rw-r--r--arch/powerpc/kernel/ppc_ksyms.c29
-rw-r--r--arch/powerpc/kernel/proc_powerpc.c37
-rw-r--r--arch/powerpc/kernel/process.c838
-rw-r--r--arch/powerpc/kernel/prom.c471
-rw-r--r--arch/powerpc/kernel/prom_init.c1205
-rw-r--r--arch/powerpc/kernel/prom_init_check.sh3
-rw-r--r--arch/powerpc/kernel/prom_parse.c17
-rw-r--r--arch/powerpc/kernel/ptrace.c452
-rw-r--r--arch/powerpc/kernel/ptrace32.c70
-rw-r--r--arch/powerpc/kernel/reloc_32.S3
-rw-r--r--arch/powerpc/kernel/reloc_64.S5
-rw-r--r--arch/powerpc/kernel/rtas.c251
-rw-r--r--arch/powerpc/kernel/rtas_flash.c522
-rw-r--r--arch/powerpc/kernel/rtas_pci.c88
-rw-r--r--arch/powerpc/kernel/rtasd.c57
-rw-r--r--arch/powerpc/kernel/setup-common.c73
-rw-r--r--arch/powerpc/kernel/setup.h9
-rw-r--r--arch/powerpc/kernel/setup_32.c38
-rw-r--r--arch/powerpc/kernel/setup_64.c179
-rw-r--r--arch/powerpc/kernel/signal.c108
-rw-r--r--arch/powerpc/kernel/signal.h15
-rw-r--r--arch/powerpc/kernel/signal_32.c852
-rw-r--r--arch/powerpc/kernel/signal_64.c426
-rw-r--r--arch/powerpc/kernel/smp-tbsync.c9
-rw-r--r--arch/powerpc/kernel/smp.c365
-rw-r--r--arch/powerpc/kernel/softemu8xx.c200
-rw-r--r--arch/powerpc/kernel/swsusp.c2
-rw-r--r--arch/powerpc/kernel/swsusp_64.c1
-rw-r--r--arch/powerpc/kernel/swsusp_asm64.S49
-rw-r--r--arch/powerpc/kernel/swsusp_booke.S40
-rw-r--r--arch/powerpc/kernel/sys_ppc32.c499
-rw-r--r--arch/powerpc/kernel/syscalls.c9
-rw-r--r--arch/powerpc/kernel/sysfs.c467
-rw-r--r--arch/powerpc/kernel/systbl.S18
-rw-r--r--arch/powerpc/kernel/time.c320
-rw-r--r--arch/powerpc/kernel/tm.S481
-rw-r--r--arch/powerpc/kernel/traps.c536
-rw-r--r--arch/powerpc/kernel/udbg.c39
-rw-r--r--arch/powerpc/kernel/udbg_16550.c365
-rw-r--r--arch/powerpc/kernel/uprobes.c207
-rw-r--r--arch/powerpc/kernel/vdso.c48
-rw-r--r--arch/powerpc/kernel/vdso32/Makefile4
-rw-r--r--arch/powerpc/kernel/vdso32/getcpu.S45
-rw-r--r--arch/powerpc/kernel/vdso32/gettimeofday.S32
-rw-r--r--arch/powerpc/kernel/vdso32/vdso32.lds.S8
-rw-r--r--arch/powerpc/kernel/vdso32/vdso32_wrapper.S3
-rw-r--r--arch/powerpc/kernel/vdso64/Makefile2
-rw-r--r--arch/powerpc/kernel/vdso64/getcpu.S45
-rw-r--r--arch/powerpc/kernel/vdso64/gettimeofday.S26
-rw-r--r--arch/powerpc/kernel/vdso64/sigtramp.S16
-rw-r--r--arch/powerpc/kernel/vdso64/vdso64.lds.S6
-rw-r--r--arch/powerpc/kernel/vdso64/vdso64_wrapper.S3
-rw-r--r--arch/powerpc/kernel/vecemu.c6
-rw-r--r--arch/powerpc/kernel/vector.S101
-rw-r--r--arch/powerpc/kernel/vio.c486
-rw-r--r--arch/powerpc/kernel/vmlinux.lds.S13
149 files changed, 18911 insertions, 15519 deletions
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index ee728e433aa..670c312d914 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -2,12 +2,13 @@
# Makefile for the linux kernel.
#
+CFLAGS_prom.o = -I$(src)/../../../scripts/dtc/libfdt
CFLAGS_ptrace.o += -DUTS_MACHINE='"$(UTS_MACHINE)"'
subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror
ifeq ($(CONFIG_PPC64),y)
-CFLAGS_prom_init.o += -mno-minimal-toc
+CFLAGS_prom_init.o += $(NO_MINIMAL_TOC)
endif
ifeq ($(CONFIG_PPC32),y)
CFLAGS_prom_init.o += -fPIC
@@ -28,7 +29,7 @@ endif
obj-y := cputable.o ptrace.o syscalls.o \
irq.o align.o signal_32.o pmc.o vdso.o \
- init_task.o process.o systbl.o idle.o \
+ process.o systbl.o idle.o \
signal.o sysfs.o cacheinfo.o time.o \
prom.o traps.o setup-common.o \
udbg.o misc.o io.o dma.o \
@@ -38,16 +39,15 @@ obj-$(CONFIG_PPC64) += setup_64.o sys_ppc32.o \
paca.o nvram_64.o firmware.o
obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o
obj-$(CONFIG_PPC_BOOK3S_64) += cpu_setup_ppc970.o cpu_setup_pa6t.o
-obj-$(CONFIG_PPC_BOOK3S_64) += cpu_setup_power7.o
+obj-$(CONFIG_PPC_BOOK3S_64) += cpu_setup_power.o
+obj-$(CONFIG_PPC_BOOK3S_64) += mce.o mce_power.o
obj64-$(CONFIG_RELOCATABLE) += reloc_64.o
obj-$(CONFIG_PPC_BOOK3E_64) += exceptions-64e.o idle_book3e.o
-obj-$(CONFIG_PPC_A2) += cpu_setup_a2.o
obj-$(CONFIG_PPC64) += vdso64/
obj-$(CONFIG_ALTIVEC) += vecemu.o
obj-$(CONFIG_PPC_970_NAP) += idle_power4.o
obj-$(CONFIG_PPC_P7_NAP) += idle_power7.o
obj-$(CONFIG_PPC_OF) += of_platform.o prom_parse.o
-obj-$(CONFIG_PPC_CLOCK) += clock.o
procfs-y := proc_powerpc.o
obj-$(CONFIG_PROC_FS) += $(procfs-y)
rtaspci-$(CONFIG_PPC64)-$(CONFIG_PCI) := rtas_pci.o
@@ -55,11 +55,13 @@ obj-$(CONFIG_PPC_RTAS) += rtas.o rtas-rtc.o $(rtaspci-y-y)
obj-$(CONFIG_PPC_RTAS_DAEMON) += rtasd.o
obj-$(CONFIG_RTAS_FLASH) += rtas_flash.o
obj-$(CONFIG_RTAS_PROC) += rtas-proc.o
-obj-$(CONFIG_LPARCFG) += lparcfg.o
obj-$(CONFIG_IBMVIO) += vio.o
obj-$(CONFIG_IBMEBUS) += ibmebus.o
+obj-$(CONFIG_EEH) += eeh.o eeh_pe.o eeh_dev.o eeh_cache.o \
+ eeh_driver.o eeh_event.o eeh_sysfs.o
obj-$(CONFIG_GENERIC_TBSYNC) += smp-tbsync.o
obj-$(CONFIG_CRASH_DUMP) += crash_dump.o
+obj-$(CONFIG_FA_DUMP) += fadump.o
ifeq ($(CONFIG_PPC32),y)
obj-$(CONFIG_E500) += idle_e500.o
endif
@@ -74,8 +76,8 @@ endif
obj64-$(CONFIG_HIBERNATION) += swsusp_asm64.o
obj-$(CONFIG_MODULES) += module.o module_$(CONFIG_WORD_SIZE).o
obj-$(CONFIG_44x) += cpu_setup_44x.o
-obj-$(CONFIG_PPC_FSL_BOOK3E) += cpu_setup_fsl_booke.o dbell.o
-obj-$(CONFIG_PPC_BOOK3E_64) += dbell.o
+obj-$(CONFIG_PPC_FSL_BOOK3E) += cpu_setup_fsl_booke.o
+obj-$(CONFIG_PPC_DOORBELL) += dbell.o
obj-$(CONFIG_JUMP_LABEL) += jump_label.o
extra-y := head_$(CONFIG_WORD_SIZE).o
@@ -90,16 +92,16 @@ obj-$(CONFIG_RELOCATABLE_PPC32) += reloc_32.o
obj-$(CONFIG_PPC32) += entry_32.o setup_32.o
obj-$(CONFIG_PPC64) += dma-iommu.o iommu.o
obj-$(CONFIG_KGDB) += kgdb.o
-obj-$(CONFIG_PPC_OF_BOOT_TRAMPOLINE) += prom_init.o
obj-$(CONFIG_MODULES) += ppc_ksyms.o
obj-$(CONFIG_BOOTX_TEXT) += btext.o
obj-$(CONFIG_SMP) += smp.o
obj-$(CONFIG_KPROBES) += kprobes.o
+obj-$(CONFIG_UPROBES) += uprobes.o
obj-$(CONFIG_PPC_UDBG_16550) += legacy_serial.o udbg_16550.o
obj-$(CONFIG_STACKTRACE) += stacktrace.o
obj-$(CONFIG_SWIOTLB) += dma-swiotlb.o
-pci64-$(CONFIG_PPC64) += pci_dn.o isa-bridge.o
+pci64-$(CONFIG_PPC64) += pci_dn.o pci-hotplug.o isa-bridge.o
obj-$(CONFIG_PCI) += pci_$(CONFIG_WORD_SIZE).o $(pci64-y) \
pci-common.o pci_of_scan.o
obj-$(CONFIG_PCI_MSI) += msi.o
@@ -113,22 +115,13 @@ obj-$(CONFIG_PPC_IO_WORKAROUNDS) += io-workarounds.o
obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o
obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o
obj-$(CONFIG_FTRACE_SYSCALLS) += ftrace.o
-obj-$(CONFIG_PERF_EVENTS) += perf_callchain.o
-obj-$(CONFIG_PPC_PERF_CTRS) += perf_event.o
-obj64-$(CONFIG_PPC_PERF_CTRS) += power4-pmu.o ppc970-pmu.o power5-pmu.o \
- power5+-pmu.o power6-pmu.o power7-pmu.o
-obj32-$(CONFIG_PPC_PERF_CTRS) += mpc7450-pmu.o
-
-obj-$(CONFIG_FSL_EMB_PERF_EVENT) += perf_event_fsl_emb.o
-obj-$(CONFIG_FSL_EMB_PERF_EVENT_E500) += e500-pmu.o
-
-obj-$(CONFIG_8XX_MINIMAL_FPEMU) += softemu8xx.o
-
-ifneq ($(CONFIG_PPC_INDIRECT_IO),y)
+ifneq ($(CONFIG_PPC_INDIRECT_PIO),y)
obj-y += iomap.o
endif
+obj64-$(CONFIG_PPC_TRANSACTIONAL_MEM) += tm.o
+
obj-$(CONFIG_PPC64) += $(obj64-y)
obj-$(CONFIG_PPC32) += $(obj32-y)
@@ -136,6 +129,7 @@ ifneq ($(CONFIG_XMON)$(CONFIG_KEXEC),)
obj-y += ppc_save_regs.o
endif
+obj-$(CONFIG_EPAPR_PARAVIRT) += epapr_paravirt.o epapr_hcalls.o
obj-$(CONFIG_KVM_GUEST) += kvm.o kvm_emul.o
# Disable GCOV in odd or sensitive code
@@ -148,6 +142,7 @@ GCOV_PROFILE_kprobes.o := n
extra-$(CONFIG_PPC_FPU) += fpu.o
extra-$(CONFIG_ALTIVEC) += vector.o
extra-$(CONFIG_PPC64) += entry_64.o
+extra-$(CONFIG_PPC_OF_BOOT_TRAMPOLINE) += prom_init.o
extra-y += systbl_chk.i
$(obj)/systbl.o: systbl_chk
diff --git a/arch/powerpc/kernel/align.c b/arch/powerpc/kernel/align.c
index 8184ee97e48..34f55524d45 100644
--- a/arch/powerpc/kernel/align.c
+++ b/arch/powerpc/kernel/align.c
@@ -21,18 +21,17 @@
#include <linux/mm.h>
#include <asm/processor.h>
#include <asm/uaccess.h>
-#include <asm/system.h>
#include <asm/cache.h>
#include <asm/cputable.h>
#include <asm/emulated_ops.h>
+#include <asm/switch_to.h>
+#include <asm/disassemble.h>
struct aligninfo {
unsigned char len;
unsigned char flags;
};
-#define IS_XFORM(inst) (((inst) >> 26) == 31)
-#define IS_DSFORM(inst) (((inst) >> 26) >= 56)
#define INVALID { 0, 0 }
@@ -54,8 +53,6 @@ struct aligninfo {
/* DSISR bits reported for a DCBZ instruction: */
#define DCBZ 0x5f /* 8xx/82xx dcbz faults when cache not enabled */
-#define SWAP(a, b) (t = (a), (a) = (b), (b) = t)
-
/*
* The PowerPC stores certain bits of the instruction that caused the
* alignment exception in the DSISR register. This array maps those
@@ -75,7 +72,7 @@ static struct aligninfo aligninfo[128] = {
{ 8, LD+F }, /* 00 0 1001: lfd */
{ 4, ST+F+S }, /* 00 0 1010: stfs */
{ 8, ST+F }, /* 00 0 1011: stfd */
- INVALID, /* 00 0 1100 */
+ { 16, LD }, /* 00 0 1100: lq */
{ 8, LD }, /* 00 0 1101: ld/ldu/lwa */
INVALID, /* 00 0 1110 */
{ 8, ST }, /* 00 0 1111: std/stdu */
@@ -142,7 +139,7 @@ static struct aligninfo aligninfo[128] = {
{ 2, LD+SW }, /* 10 0 1100: lhbrx */
{ 4, LD+SE }, /* 10 0 1101 lwa */
{ 2, ST+SW }, /* 10 0 1110: sthbrx */
- INVALID, /* 10 0 1111 */
+ { 16, ST }, /* 10 0 1111: stq */
INVALID, /* 10 1 0000 */
INVALID, /* 10 1 0001 */
INVALID, /* 10 1 0010 */
@@ -194,37 +191,6 @@ static struct aligninfo aligninfo[128] = {
};
/*
- * Create a DSISR value from the instruction
- */
-static inline unsigned make_dsisr(unsigned instr)
-{
- unsigned dsisr;
-
-
- /* bits 6:15 --> 22:31 */
- dsisr = (instr & 0x03ff0000) >> 16;
-
- if (IS_XFORM(instr)) {
- /* bits 29:30 --> 15:16 */
- dsisr |= (instr & 0x00000006) << 14;
- /* bit 25 --> 17 */
- dsisr |= (instr & 0x00000040) << 8;
- /* bits 21:24 --> 18:21 */
- dsisr |= (instr & 0x00000780) << 3;
- } else {
- /* bit 5 --> 17 */
- dsisr |= (instr & 0x04000000) >> 12;
- /* bits 1: 4 --> 18:21 */
- dsisr |= (instr & 0x78000000) >> 17;
- /* bits 30:31 --> 12:13 */
- if (IS_DSFORM(instr))
- dsisr |= (instr & 0x00000003) << 18;
- }
-
- return dsisr;
-}
-
-/*
* The dcbz (data cache block zero) instruction
* gives an alignment fault if used on non-cacheable
* memory. We handle the fault mainly for the
@@ -256,11 +222,17 @@ static int emulate_dcbz(struct pt_regs *regs, unsigned char __user *addr)
* bottom 4 bytes of each register, and the loads clear the
* top 4 bytes of the affected register.
*/
+#ifdef __BIG_ENDIAN__
#ifdef CONFIG_PPC64
#define REG_BYTE(rp, i) *((u8 *)((rp) + ((i) >> 2)) + ((i) & 3) + 4)
#else
#define REG_BYTE(rp, i) *((u8 *)(rp) + (i))
#endif
+#endif
+
+#ifdef __LITTLE_ENDIAN__
+#define REG_BYTE(rp, i) (*(((u8 *)((rp) + ((i)>>2)) + ((i)&3))))
+#endif
#define SWIZ_PTR(p) ((unsigned char __user *)((p) ^ swiz))
@@ -305,6 +277,15 @@ static int emulate_multiple(struct pt_regs *regs, unsigned char __user *addr,
nb0 = nb + reg * 4 - 128;
nb = 128 - reg * 4;
}
+#ifdef __LITTLE_ENDIAN__
+ /*
+ * String instructions are endian neutral but the code
+ * below is not. Force byte swapping on so that the
+ * effects of swizzling are undone in the load/store
+ * loops below.
+ */
+ flags ^= SW;
+#endif
} else {
/* lwm, stmw */
nb = (32 - reg) * 4;
@@ -372,8 +353,6 @@ static int emulate_fp_pair(unsigned char __user *addr, unsigned int reg,
char *ptr1 = (char *) &current->thread.TS_FPR(reg+1);
int i, ret, sw = 0;
- if (!(flags & F))
- return 0;
if (reg & 1)
return 0; /* invalid form: FRS/FRT must be even */
if (flags & SW)
@@ -393,6 +372,34 @@ static int emulate_fp_pair(unsigned char __user *addr, unsigned int reg,
return 1; /* exception handled and fixed up */
}
+#ifdef CONFIG_PPC64
+static int emulate_lq_stq(struct pt_regs *regs, unsigned char __user *addr,
+ unsigned int reg, unsigned int flags)
+{
+ char *ptr0 = (char *)&regs->gpr[reg];
+ char *ptr1 = (char *)&regs->gpr[reg+1];
+ int i, ret, sw = 0;
+
+ if (reg & 1)
+ return 0; /* invalid form: GPR must be even */
+ if (flags & SW)
+ sw = 7;
+ ret = 0;
+ for (i = 0; i < 8; ++i) {
+ if (!(flags & ST)) {
+ ret |= __get_user(ptr0[i^sw], addr + i);
+ ret |= __get_user(ptr1[i^sw], addr + i + 8);
+ } else {
+ ret |= __put_user(ptr0[i^sw], addr + i);
+ ret |= __put_user(ptr1[i^sw], addr + i + 8);
+ }
+ }
+ if (ret)
+ return -EFAULT;
+ return 1; /* exception handled and fixed up */
+}
+#endif /* CONFIG_PPC64 */
+
#ifdef CONFIG_SPE
static struct aligninfo spe_aligninfo[32] = {
@@ -458,7 +465,7 @@ static struct aligninfo spe_aligninfo[32] = {
static int emulate_spe(struct pt_regs *regs, unsigned int reg,
unsigned int instr)
{
- int t, ret;
+ int ret;
union {
u64 ll;
u32 w[2];
@@ -581,24 +588,18 @@ static int emulate_spe(struct pt_regs *regs, unsigned int reg,
if (flags & SW) {
switch (flags & 0xf0) {
case E8:
- SWAP(data.v[0], data.v[7]);
- SWAP(data.v[1], data.v[6]);
- SWAP(data.v[2], data.v[5]);
- SWAP(data.v[3], data.v[4]);
+ data.ll = swab64(data.ll);
break;
case E4:
-
- SWAP(data.v[0], data.v[3]);
- SWAP(data.v[1], data.v[2]);
- SWAP(data.v[4], data.v[7]);
- SWAP(data.v[5], data.v[6]);
+ data.w[0] = swab32(data.w[0]);
+ data.w[1] = swab32(data.w[1]);
break;
/* Its half word endian */
default:
- SWAP(data.v[0], data.v[1]);
- SWAP(data.v[2], data.v[3]);
- SWAP(data.v[4], data.v[5]);
- SWAP(data.v[6], data.v[7]);
+ data.h[0] = swab16(data.h[0]);
+ data.h[1] = swab16(data.h[1]);
+ data.h[2] = swab16(data.h[2]);
+ data.h[3] = swab16(data.h[3]);
break;
}
}
@@ -651,17 +652,38 @@ static int emulate_vsx(unsigned char __user *addr, unsigned int reg,
int sw = 0;
int i, j;
+ /* userland only */
+ if (unlikely(!user_mode(regs)))
+ return 0;
+
flush_vsx_to_thread(current);
if (reg < 32)
- ptr = (char *) &current->thread.TS_FPR(reg);
+ ptr = (char *) &current->thread.fp_state.fpr[reg][0];
else
- ptr = (char *) &current->thread.vr[reg - 32];
+ ptr = (char *) &current->thread.vr_state.vr[reg - 32];
lptr = (unsigned long *) ptr;
+#ifdef __LITTLE_ENDIAN__
+ if (flags & SW) {
+ elsize = length;
+ sw = length-1;
+ } else {
+ /*
+ * The elements are BE ordered, even in LE mode, so process
+ * them in reverse order.
+ */
+ addr += length - elsize;
+
+ /* 8 byte memory accesses go in the top 8 bytes of the VR */
+ if (length == 8)
+ ptr += 8;
+ }
+#else
if (flags & SW)
sw = elsize-1;
+#endif
for (j = 0; j < length; j += elsize) {
for (i = 0; i < elsize; ++i) {
@@ -671,19 +693,31 @@ static int emulate_vsx(unsigned char __user *addr, unsigned int reg,
ret |= __get_user(ptr[i^sw], addr + i);
}
ptr += elsize;
+#ifdef __LITTLE_ENDIAN__
+ addr -= elsize;
+#else
addr += elsize;
+#endif
}
+#ifdef __BIG_ENDIAN__
+#define VSX_HI 0
+#define VSX_LO 1
+#else
+#define VSX_HI 1
+#define VSX_LO 0
+#endif
+
if (!ret) {
if (flags & U)
regs->gpr[areg] = regs->dar;
/* Splat load copies the same data to top and bottom 8 bytes */
if (flags & SPLT)
- lptr[1] = lptr[0];
- /* For 8 byte loads, zero the top 8 bytes */
+ lptr[VSX_LO] = lptr[VSX_HI];
+ /* For 8 byte loads, zero the low 8 bytes */
else if (!(flags & ST) && (8 == length))
- lptr[1] = 0;
+ lptr[VSX_LO] = 0;
} else
return -EFAULT;
@@ -706,18 +740,28 @@ int fix_alignment(struct pt_regs *regs)
unsigned int dsisr;
unsigned char __user *addr;
unsigned long p, swiz;
- int ret, t;
- union {
+ int ret, i;
+ union data {
u64 ll;
double dd;
unsigned char v[8];
struct {
+#ifdef __LITTLE_ENDIAN__
+ int low32;
+ unsigned hi32;
+#else
unsigned hi32;
int low32;
+#endif
} x32;
struct {
+#ifdef __LITTLE_ENDIAN__
+ short low16;
+ unsigned char hi48[6];
+#else
unsigned char hi48[6];
short low16;
+#endif
} x16;
} data;
@@ -764,10 +808,21 @@ int fix_alignment(struct pt_regs *regs)
nb = aligninfo[instr].len;
flags = aligninfo[instr].flags;
+ /* ldbrx/stdbrx overlap lfs/stfs in the DSISR unfortunately */
+ if (IS_XFORM(instruction) && ((instruction >> 1) & 0x3ff) == 532) {
+ nb = 8;
+ flags = LD+SW;
+ } else if (IS_XFORM(instruction) &&
+ ((instruction >> 1) & 0x3ff) == 660) {
+ nb = 8;
+ flags = ST+SW;
+ }
+
/* Byteswap little endian loads and stores */
swiz = 0;
- if (regs->msr & MSR_LE) {
+ if ((regs->msr & MSR_LE) != (MSR_KERNEL & MSR_LE)) {
flags ^= SW;
+#ifdef __BIG_ENDIAN__
/*
* So-called "PowerPC little endian" mode works by
* swizzling addresses rather than by actually doing
@@ -780,6 +835,7 @@ int fix_alignment(struct pt_regs *regs)
*/
if (cpu_has_feature(CPU_FTR_PPC_LE))
swiz = 7;
+#endif
}
/* DAR has the operand effective address */
@@ -804,7 +860,7 @@ int fix_alignment(struct pt_regs *regs)
elsize = 8;
flags = 0;
- if (regs->msr & MSR_LE)
+ if ((regs->msr & MSR_LE) != (MSR_KERNEL & MSR_LE))
flags |= SW;
if (instruction & 0x100)
flags |= ST;
@@ -852,10 +908,20 @@ int fix_alignment(struct pt_regs *regs)
flush_fp_to_thread(current);
}
- /* Special case for 16-byte FP loads and stores */
- if (nb == 16) {
- PPC_WARN_ALIGNMENT(fp_pair, regs);
- return emulate_fp_pair(addr, reg, flags);
+ if ((nb == 16)) {
+ if (flags & F) {
+ /* Special case for 16-byte FP loads and stores */
+ PPC_WARN_ALIGNMENT(fp_pair, regs);
+ return emulate_fp_pair(addr, reg, flags);
+ } else {
+#ifdef CONFIG_PPC64
+ /* Special case for 16-byte loads and stores */
+ PPC_WARN_ALIGNMENT(lq_stq, regs);
+ return emulate_lq_stq(regs, addr, reg, flags);
+#else
+ return 0;
+#endif
+ }
}
PPC_WARN_ALIGNMENT(unaligned, regs);
@@ -864,32 +930,36 @@ int fix_alignment(struct pt_regs *regs)
* get it from register values
*/
if (!(flags & ST)) {
- data.ll = 0;
- ret = 0;
- p = (unsigned long) addr;
+ unsigned int start = 0;
+
switch (nb) {
- case 8:
- ret |= __get_user_inatomic(data.v[0], SWIZ_PTR(p++));
- ret |= __get_user_inatomic(data.v[1], SWIZ_PTR(p++));
- ret |= __get_user_inatomic(data.v[2], SWIZ_PTR(p++));
- ret |= __get_user_inatomic(data.v[3], SWIZ_PTR(p++));
case 4:
- ret |= __get_user_inatomic(data.v[4], SWIZ_PTR(p++));
- ret |= __get_user_inatomic(data.v[5], SWIZ_PTR(p++));
+ start = offsetof(union data, x32.low32);
+ break;
case 2:
- ret |= __get_user_inatomic(data.v[6], SWIZ_PTR(p++));
- ret |= __get_user_inatomic(data.v[7], SWIZ_PTR(p++));
- if (unlikely(ret))
- return -EFAULT;
+ start = offsetof(union data, x16.low16);
+ break;
}
+
+ data.ll = 0;
+ ret = 0;
+ p = (unsigned long)addr;
+
+ for (i = 0; i < nb; i++)
+ ret |= __get_user_inatomic(data.v[start + i],
+ SWIZ_PTR(p++));
+
+ if (unlikely(ret))
+ return -EFAULT;
+
} else if (flags & F) {
- data.dd = current->thread.TS_FPR(reg);
+ data.ll = current->thread.TS_FPR(reg);
if (flags & S) {
/* Single-precision FP store requires conversion... */
#ifdef CONFIG_PPC_FPU
preempt_disable();
enable_kernel_fp();
- cvt_df(&data.dd, (float *)&data.v[4]);
+ cvt_df(&data.dd, (float *)&data.x32.low32);
preempt_enable();
#else
return 0;
@@ -901,17 +971,13 @@ int fix_alignment(struct pt_regs *regs)
if (flags & SW) {
switch (nb) {
case 8:
- SWAP(data.v[0], data.v[7]);
- SWAP(data.v[1], data.v[6]);
- SWAP(data.v[2], data.v[5]);
- SWAP(data.v[3], data.v[4]);
+ data.ll = swab64(data.ll);
break;
case 4:
- SWAP(data.v[4], data.v[7]);
- SWAP(data.v[5], data.v[6]);
+ data.x32.low32 = swab32(data.x32.low32);
break;
case 2:
- SWAP(data.v[6], data.v[7]);
+ data.x16.low16 = swab16(data.x16.low16);
break;
}
}
@@ -933,7 +999,7 @@ int fix_alignment(struct pt_regs *regs)
#ifdef CONFIG_PPC_FPU
preempt_disable();
enable_kernel_fp();
- cvt_fd((float *)&data.v[4], &data.dd);
+ cvt_fd((float *)&data.x32.low32, &data.dd);
preempt_enable();
#else
return 0;
@@ -943,25 +1009,28 @@ int fix_alignment(struct pt_regs *regs)
/* Store result to memory or update registers */
if (flags & ST) {
- ret = 0;
- p = (unsigned long) addr;
+ unsigned int start = 0;
+
switch (nb) {
- case 8:
- ret |= __put_user_inatomic(data.v[0], SWIZ_PTR(p++));
- ret |= __put_user_inatomic(data.v[1], SWIZ_PTR(p++));
- ret |= __put_user_inatomic(data.v[2], SWIZ_PTR(p++));
- ret |= __put_user_inatomic(data.v[3], SWIZ_PTR(p++));
case 4:
- ret |= __put_user_inatomic(data.v[4], SWIZ_PTR(p++));
- ret |= __put_user_inatomic(data.v[5], SWIZ_PTR(p++));
+ start = offsetof(union data, x32.low32);
+ break;
case 2:
- ret |= __put_user_inatomic(data.v[6], SWIZ_PTR(p++));
- ret |= __put_user_inatomic(data.v[7], SWIZ_PTR(p++));
+ start = offsetof(union data, x16.low16);
+ break;
}
+
+ ret = 0;
+ p = (unsigned long)addr;
+
+ for (i = 0; i < nb; i++)
+ ret |= __put_user_inatomic(data.v[start + i],
+ SWIZ_PTR(p++));
+
if (unlikely(ret))
return -EFAULT;
} else if (flags & F)
- current->thread.TS_FPR(reg) = data.dd;
+ current->thread.TS_FPR(reg) = data.ll;
else
regs->gpr[reg] = data.ll;
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 04caee7d9bc..f5995a91221 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -46,9 +46,6 @@
#include <asm/hvcall.h>
#include <asm/xics.h>
#endif
-#ifdef CONFIG_PPC_ISERIES
-#include <asm/iseries/alpaca.h>
-#endif
#ifdef CONFIG_PPC_POWERNV
#include <asm/opal.h>
#endif
@@ -57,6 +54,7 @@
#endif
#if defined(CONFIG_KVM) && defined(CONFIG_PPC_BOOK3S)
#include <asm/kvm_book3s.h>
+#include <asm/kvm_ppc.h>
#endif
#ifdef CONFIG_PPC32
@@ -79,36 +77,37 @@ int main(void)
DEFINE(SIGSEGV, SIGSEGV);
DEFINE(NMI_MASK, NMI_MASK);
DEFINE(THREAD_DSCR, offsetof(struct thread_struct, dscr));
+ DEFINE(THREAD_DSCR_INHERIT, offsetof(struct thread_struct, dscr_inherit));
+ DEFINE(TASKTHREADPPR, offsetof(struct task_struct, thread.ppr));
#else
DEFINE(THREAD_INFO, offsetof(struct task_struct, stack));
+ DEFINE(THREAD_INFO_GAP, _ALIGN_UP(sizeof(struct thread_info), 16));
+ DEFINE(KSP_LIMIT, offsetof(struct thread_struct, ksp_limit));
#endif /* CONFIG_PPC64 */
DEFINE(KSP, offsetof(struct thread_struct, ksp));
- DEFINE(KSP_LIMIT, offsetof(struct thread_struct, ksp_limit));
DEFINE(PT_REGS, offsetof(struct thread_struct, regs));
#ifdef CONFIG_BOOKE
DEFINE(THREAD_NORMSAVES, offsetof(struct thread_struct, normsave[0]));
#endif
DEFINE(THREAD_FPEXC_MODE, offsetof(struct thread_struct, fpexc_mode));
- DEFINE(THREAD_FPR0, offsetof(struct thread_struct, fpr[0]));
- DEFINE(THREAD_FPSCR, offsetof(struct thread_struct, fpscr));
+ DEFINE(THREAD_FPSTATE, offsetof(struct thread_struct, fp_state));
+ DEFINE(THREAD_FPSAVEAREA, offsetof(struct thread_struct, fp_save_area));
+ DEFINE(FPSTATE_FPSCR, offsetof(struct thread_fp_state, fpscr));
#ifdef CONFIG_ALTIVEC
- DEFINE(THREAD_VR0, offsetof(struct thread_struct, vr[0]));
+ DEFINE(THREAD_VRSTATE, offsetof(struct thread_struct, vr_state));
+ DEFINE(THREAD_VRSAVEAREA, offsetof(struct thread_struct, vr_save_area));
DEFINE(THREAD_VRSAVE, offsetof(struct thread_struct, vrsave));
- DEFINE(THREAD_VSCR, offsetof(struct thread_struct, vscr));
DEFINE(THREAD_USED_VR, offsetof(struct thread_struct, used_vr));
+ DEFINE(VRSTATE_VSCR, offsetof(struct thread_vr_state, vscr));
#endif /* CONFIG_ALTIVEC */
#ifdef CONFIG_VSX
- DEFINE(THREAD_VSR0, offsetof(struct thread_struct, fpr));
DEFINE(THREAD_USED_VSR, offsetof(struct thread_struct, used_vsr));
#endif /* CONFIG_VSX */
#ifdef CONFIG_PPC64
DEFINE(KSP_VSID, offsetof(struct thread_struct, ksp_vsid));
#else /* CONFIG_PPC64 */
DEFINE(PGDIR, offsetof(struct thread_struct, pgdir));
-#if defined(CONFIG_4xx) || defined(CONFIG_BOOKE)
- DEFINE(THREAD_DBCR0, offsetof(struct thread_struct, dbcr0));
-#endif
#ifdef CONFIG_SPE
DEFINE(THREAD_EVR0, offsetof(struct thread_struct, evr[0]));
DEFINE(THREAD_ACC, offsetof(struct thread_struct, acc));
@@ -116,9 +115,46 @@ int main(void)
DEFINE(THREAD_USED_SPE, offsetof(struct thread_struct, used_spe));
#endif /* CONFIG_SPE */
#endif /* CONFIG_PPC64 */
+#if defined(CONFIG_4xx) || defined(CONFIG_BOOKE)
+ DEFINE(THREAD_DBCR0, offsetof(struct thread_struct, debug.dbcr0));
+#endif
#ifdef CONFIG_KVM_BOOK3S_32_HANDLER
DEFINE(THREAD_KVM_SVCPU, offsetof(struct thread_struct, kvm_shadow_vcpu));
#endif
+#if defined(CONFIG_KVM) && defined(CONFIG_BOOKE)
+ DEFINE(THREAD_KVM_VCPU, offsetof(struct thread_struct, kvm_vcpu));
+#endif
+
+#ifdef CONFIG_PPC_BOOK3S_64
+ DEFINE(THREAD_TAR, offsetof(struct thread_struct, tar));
+ DEFINE(THREAD_BESCR, offsetof(struct thread_struct, bescr));
+ DEFINE(THREAD_EBBHR, offsetof(struct thread_struct, ebbhr));
+ DEFINE(THREAD_EBBRR, offsetof(struct thread_struct, ebbrr));
+ DEFINE(THREAD_SIAR, offsetof(struct thread_struct, siar));
+ DEFINE(THREAD_SDAR, offsetof(struct thread_struct, sdar));
+ DEFINE(THREAD_SIER, offsetof(struct thread_struct, sier));
+ DEFINE(THREAD_MMCR0, offsetof(struct thread_struct, mmcr0));
+ DEFINE(THREAD_MMCR2, offsetof(struct thread_struct, mmcr2));
+#endif
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ DEFINE(PACATMSCRATCH, offsetof(struct paca_struct, tm_scratch));
+ DEFINE(THREAD_TM_TFHAR, offsetof(struct thread_struct, tm_tfhar));
+ DEFINE(THREAD_TM_TEXASR, offsetof(struct thread_struct, tm_texasr));
+ DEFINE(THREAD_TM_TFIAR, offsetof(struct thread_struct, tm_tfiar));
+ DEFINE(THREAD_TM_TAR, offsetof(struct thread_struct, tm_tar));
+ DEFINE(THREAD_TM_PPR, offsetof(struct thread_struct, tm_ppr));
+ DEFINE(THREAD_TM_DSCR, offsetof(struct thread_struct, tm_dscr));
+ DEFINE(PT_CKPT_REGS, offsetof(struct thread_struct, ckpt_regs));
+ DEFINE(THREAD_TRANSACT_VRSTATE, offsetof(struct thread_struct,
+ transact_vr));
+ DEFINE(THREAD_TRANSACT_VRSAVE, offsetof(struct thread_struct,
+ transact_vrsave));
+ DEFINE(THREAD_TRANSACT_FPSTATE, offsetof(struct thread_struct,
+ transact_fp));
+ /* Local pt_regs on stack for Transactional Memory funcs. */
+ DEFINE(TM_FRAME_SIZE, STACK_FRAME_OVERHEAD +
+ sizeof(struct pt_regs) + 16);
+#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
DEFINE(TI_FLAGS, offsetof(struct thread_info, flags));
DEFINE(TI_LOCAL_FLAGS, offsetof(struct thread_info, local_flags));
@@ -147,7 +183,7 @@ int main(void)
DEFINE(PACAKBASE, offsetof(struct paca_struct, kernelbase));
DEFINE(PACAKMSR, offsetof(struct paca_struct, kernel_msr));
DEFINE(PACASOFTIRQEN, offsetof(struct paca_struct, soft_enabled));
- DEFINE(PACAHARDIRQEN, offsetof(struct paca_struct, hard_enabled));
+ DEFINE(PACAIRQHAPPENED, offsetof(struct paca_struct, irq_happened));
DEFINE(PACACONTEXTID, offsetof(struct paca_struct, context.id));
#ifdef CONFIG_PPC_MM_SLICES
DEFINE(PACALOWSLICESPSIZE, offsetof(struct paca_struct,
@@ -168,6 +204,15 @@ int main(void)
DEFINE(PACA_MC_STACK, offsetof(struct paca_struct, mc_kstack));
DEFINE(PACA_CRIT_STACK, offsetof(struct paca_struct, crit_kstack));
DEFINE(PACA_DBG_STACK, offsetof(struct paca_struct, dbg_kstack));
+ DEFINE(PACA_TCD_PTR, offsetof(struct paca_struct, tcd_ptr));
+
+ DEFINE(TCD_ESEL_NEXT,
+ offsetof(struct tlb_core_data, esel_next));
+ DEFINE(TCD_ESEL_MAX,
+ offsetof(struct tlb_core_data, esel_max));
+ DEFINE(TCD_ESEL_FIRST,
+ offsetof(struct tlb_core_data, esel_first));
+ DEFINE(TCD_LOCK, offsetof(struct tlb_core_data, lock));
#endif /* CONFIG_PPC_BOOK3E */
#ifdef CONFIG_PPC_STD_MMU_64
@@ -191,24 +236,26 @@ int main(void)
DEFINE(SLBSHADOW_STACKESID,
offsetof(struct slb_shadow, save_area[SLB_NUM_BOLTED - 1].esid));
DEFINE(SLBSHADOW_SAVEAREA, offsetof(struct slb_shadow, save_area));
- DEFINE(LPPACASRR0, offsetof(struct lppaca, saved_srr0));
- DEFINE(LPPACASRR1, offsetof(struct lppaca, saved_srr1));
- DEFINE(LPPACAANYINT, offsetof(struct lppaca, int_dword.any_int));
- DEFINE(LPPACADECRINT, offsetof(struct lppaca, int_dword.fields.decr_int));
DEFINE(LPPACA_PMCINUSE, offsetof(struct lppaca, pmcregs_in_use));
DEFINE(LPPACA_DTLIDX, offsetof(struct lppaca, dtl_idx));
DEFINE(LPPACA_YIELDCOUNT, offsetof(struct lppaca, yield_count));
DEFINE(PACA_DTL_RIDX, offsetof(struct paca_struct, dtl_ridx));
#endif /* CONFIG_PPC_STD_MMU_64 */
DEFINE(PACAEMERGSP, offsetof(struct paca_struct, emergency_sp));
+#ifdef CONFIG_PPC_BOOK3S_64
+ DEFINE(PACAMCEMERGSP, offsetof(struct paca_struct, mc_emergency_sp));
+ DEFINE(PACA_IN_MCE, offsetof(struct paca_struct, in_mce));
+#endif
DEFINE(PACAHWCPUID, offsetof(struct paca_struct, hw_cpu_id));
DEFINE(PACAKEXECSTATE, offsetof(struct paca_struct, kexec_state));
+ DEFINE(PACA_DSCR, offsetof(struct paca_struct, dscr_default));
DEFINE(PACA_STARTTIME, offsetof(struct paca_struct, starttime));
DEFINE(PACA_STARTTIME_USER, offsetof(struct paca_struct, starttime_user));
DEFINE(PACA_USER_TIME, offsetof(struct paca_struct, user_time));
DEFINE(PACA_SYSTEM_TIME, offsetof(struct paca_struct, system_time));
DEFINE(PACA_TRAP_SAVE, offsetof(struct paca_struct, trap_save));
DEFINE(PACA_NAPSTATELOST, offsetof(struct paca_struct, nap_state_lost));
+ DEFINE(PACA_SPRG_VDSO, offsetof(struct paca_struct, sprg_vdso));
#endif /* CONFIG_PPC64 */
/* RTAS */
@@ -384,40 +431,28 @@ int main(void)
DEFINE(BUG_ENTRY_SIZE, sizeof(struct bug_entry));
#endif
-#ifdef CONFIG_PPC_ISERIES
- /* the assembler miscalculates the VSID values */
- DEFINE(PAGE_OFFSET_ESID, GET_ESID(PAGE_OFFSET));
- DEFINE(PAGE_OFFSET_VSID, KERNEL_VSID(PAGE_OFFSET));
- DEFINE(VMALLOC_START_ESID, GET_ESID(VMALLOC_START));
- DEFINE(VMALLOC_START_VSID, KERNEL_VSID(VMALLOC_START));
-
- /* alpaca */
- DEFINE(ALPACA_SIZE, sizeof(struct alpaca));
-#endif
-
DEFINE(PGD_TABLE_SIZE, PGD_TABLE_SIZE);
DEFINE(PTE_SIZE, sizeof(pte_t));
#ifdef CONFIG_KVM
DEFINE(VCPU_HOST_STACK, offsetof(struct kvm_vcpu, arch.host_stack));
DEFINE(VCPU_HOST_PID, offsetof(struct kvm_vcpu, arch.host_pid));
+ DEFINE(VCPU_GUEST_PID, offsetof(struct kvm_vcpu, arch.pid));
DEFINE(VCPU_GPRS, offsetof(struct kvm_vcpu, arch.gpr));
DEFINE(VCPU_VRSAVE, offsetof(struct kvm_vcpu, arch.vrsave));
- DEFINE(VCPU_FPRS, offsetof(struct kvm_vcpu, arch.fpr));
- DEFINE(VCPU_FPSCR, offsetof(struct kvm_vcpu, arch.fpscr));
+ DEFINE(VCPU_FPRS, offsetof(struct kvm_vcpu, arch.fp.fpr));
#ifdef CONFIG_ALTIVEC
- DEFINE(VCPU_VRS, offsetof(struct kvm_vcpu, arch.vr));
- DEFINE(VCPU_VSCR, offsetof(struct kvm_vcpu, arch.vscr));
-#endif
-#ifdef CONFIG_VSX
- DEFINE(VCPU_VSRS, offsetof(struct kvm_vcpu, arch.vsr));
+ DEFINE(VCPU_VRS, offsetof(struct kvm_vcpu, arch.vr.vr));
#endif
DEFINE(VCPU_XER, offsetof(struct kvm_vcpu, arch.xer));
DEFINE(VCPU_CTR, offsetof(struct kvm_vcpu, arch.ctr));
DEFINE(VCPU_LR, offsetof(struct kvm_vcpu, arch.lr));
+#ifdef CONFIG_PPC_BOOK3S
+ DEFINE(VCPU_TAR, offsetof(struct kvm_vcpu, arch.tar));
+#endif
DEFINE(VCPU_CR, offsetof(struct kvm_vcpu, arch.cr));
DEFINE(VCPU_PC, offsetof(struct kvm_vcpu, arch.pc));
-#ifdef CONFIG_KVM_BOOK3S_64_HV
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
DEFINE(VCPU_MSR, offsetof(struct kvm_vcpu, arch.shregs.msr));
DEFINE(VCPU_SRR0, offsetof(struct kvm_vcpu, arch.shregs.srr0));
DEFINE(VCPU_SRR1, offsetof(struct kvm_vcpu, arch.shregs.srr1));
@@ -426,71 +461,128 @@ int main(void)
DEFINE(VCPU_SPRG2, offsetof(struct kvm_vcpu, arch.shregs.sprg2));
DEFINE(VCPU_SPRG3, offsetof(struct kvm_vcpu, arch.shregs.sprg3));
#endif
- DEFINE(VCPU_SPRG4, offsetof(struct kvm_vcpu, arch.sprg4));
- DEFINE(VCPU_SPRG5, offsetof(struct kvm_vcpu, arch.sprg5));
- DEFINE(VCPU_SPRG6, offsetof(struct kvm_vcpu, arch.sprg6));
- DEFINE(VCPU_SPRG7, offsetof(struct kvm_vcpu, arch.sprg7));
+ DEFINE(VCPU_SHARED_SPRG3, offsetof(struct kvm_vcpu_arch_shared, sprg3));
+ DEFINE(VCPU_SHARED_SPRG4, offsetof(struct kvm_vcpu_arch_shared, sprg4));
+ DEFINE(VCPU_SHARED_SPRG5, offsetof(struct kvm_vcpu_arch_shared, sprg5));
+ DEFINE(VCPU_SHARED_SPRG6, offsetof(struct kvm_vcpu_arch_shared, sprg6));
+ DEFINE(VCPU_SHARED_SPRG7, offsetof(struct kvm_vcpu_arch_shared, sprg7));
DEFINE(VCPU_SHADOW_PID, offsetof(struct kvm_vcpu, arch.shadow_pid));
DEFINE(VCPU_SHADOW_PID1, offsetof(struct kvm_vcpu, arch.shadow_pid1));
DEFINE(VCPU_SHARED, offsetof(struct kvm_vcpu, arch.shared));
DEFINE(VCPU_SHARED_MSR, offsetof(struct kvm_vcpu_arch_shared, msr));
DEFINE(VCPU_SHADOW_MSR, offsetof(struct kvm_vcpu, arch.shadow_msr));
+#if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_KVM_BOOK3S_PR_POSSIBLE)
+ DEFINE(VCPU_SHAREDBE, offsetof(struct kvm_vcpu, arch.shared_big_endian));
+#endif
- /* book3s */
-#ifdef CONFIG_KVM_BOOK3S_64_HV
+ DEFINE(VCPU_SHARED_MAS0, offsetof(struct kvm_vcpu_arch_shared, mas0));
+ DEFINE(VCPU_SHARED_MAS1, offsetof(struct kvm_vcpu_arch_shared, mas1));
+ DEFINE(VCPU_SHARED_MAS2, offsetof(struct kvm_vcpu_arch_shared, mas2));
+ DEFINE(VCPU_SHARED_MAS7_3, offsetof(struct kvm_vcpu_arch_shared, mas7_3));
+ DEFINE(VCPU_SHARED_MAS4, offsetof(struct kvm_vcpu_arch_shared, mas4));
+ DEFINE(VCPU_SHARED_MAS6, offsetof(struct kvm_vcpu_arch_shared, mas6));
+
+ DEFINE(VCPU_KVM, offsetof(struct kvm_vcpu, kvm));
DEFINE(KVM_LPID, offsetof(struct kvm, arch.lpid));
+
+ /* book3s */
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
DEFINE(KVM_SDR1, offsetof(struct kvm, arch.sdr1));
DEFINE(KVM_HOST_LPID, offsetof(struct kvm, arch.host_lpid));
DEFINE(KVM_HOST_LPCR, offsetof(struct kvm, arch.host_lpcr));
DEFINE(KVM_HOST_SDR1, offsetof(struct kvm, arch.host_sdr1));
DEFINE(KVM_TLBIE_LOCK, offsetof(struct kvm, arch.tlbie_lock));
- DEFINE(KVM_ONLINE_CPUS, offsetof(struct kvm, online_vcpus.counter));
- DEFINE(KVM_LAST_VCPU, offsetof(struct kvm, arch.last_vcpu));
+ DEFINE(KVM_NEED_FLUSH, offsetof(struct kvm, arch.need_tlb_flush.bits));
DEFINE(KVM_LPCR, offsetof(struct kvm, arch.lpcr));
DEFINE(KVM_RMOR, offsetof(struct kvm, arch.rmor));
+ DEFINE(KVM_VRMA_SLB_V, offsetof(struct kvm, arch.vrma_slb_v));
DEFINE(VCPU_DSISR, offsetof(struct kvm_vcpu, arch.shregs.dsisr));
DEFINE(VCPU_DAR, offsetof(struct kvm_vcpu, arch.shregs.dar));
+ DEFINE(VCPU_VPA, offsetof(struct kvm_vcpu, arch.vpa.pinned_addr));
+ DEFINE(VCPU_VPA_DIRTY, offsetof(struct kvm_vcpu, arch.vpa.dirty));
#endif
#ifdef CONFIG_PPC_BOOK3S
- DEFINE(VCPU_KVM, offsetof(struct kvm_vcpu, kvm));
DEFINE(VCPU_VCPUID, offsetof(struct kvm_vcpu, vcpu_id));
DEFINE(VCPU_PURR, offsetof(struct kvm_vcpu, arch.purr));
DEFINE(VCPU_SPURR, offsetof(struct kvm_vcpu, arch.spurr));
+ DEFINE(VCPU_IC, offsetof(struct kvm_vcpu, arch.ic));
+ DEFINE(VCPU_VTB, offsetof(struct kvm_vcpu, arch.vtb));
DEFINE(VCPU_DSCR, offsetof(struct kvm_vcpu, arch.dscr));
DEFINE(VCPU_AMR, offsetof(struct kvm_vcpu, arch.amr));
DEFINE(VCPU_UAMOR, offsetof(struct kvm_vcpu, arch.uamor));
+ DEFINE(VCPU_IAMR, offsetof(struct kvm_vcpu, arch.iamr));
DEFINE(VCPU_CTRL, offsetof(struct kvm_vcpu, arch.ctrl));
DEFINE(VCPU_DABR, offsetof(struct kvm_vcpu, arch.dabr));
+ DEFINE(VCPU_DABRX, offsetof(struct kvm_vcpu, arch.dabrx));
+ DEFINE(VCPU_DAWR, offsetof(struct kvm_vcpu, arch.dawr));
+ DEFINE(VCPU_DAWRX, offsetof(struct kvm_vcpu, arch.dawrx));
+ DEFINE(VCPU_CIABR, offsetof(struct kvm_vcpu, arch.ciabr));
DEFINE(VCPU_HFLAGS, offsetof(struct kvm_vcpu, arch.hflags));
DEFINE(VCPU_DEC, offsetof(struct kvm_vcpu, arch.dec));
DEFINE(VCPU_DEC_EXPIRES, offsetof(struct kvm_vcpu, arch.dec_expires));
DEFINE(VCPU_PENDING_EXC, offsetof(struct kvm_vcpu, arch.pending_exceptions));
DEFINE(VCPU_CEDED, offsetof(struct kvm_vcpu, arch.ceded));
DEFINE(VCPU_PRODDED, offsetof(struct kvm_vcpu, arch.prodded));
- DEFINE(VCPU_VPA, offsetof(struct kvm_vcpu, arch.vpa));
DEFINE(VCPU_MMCR, offsetof(struct kvm_vcpu, arch.mmcr));
DEFINE(VCPU_PMC, offsetof(struct kvm_vcpu, arch.pmc));
+ DEFINE(VCPU_SPMC, offsetof(struct kvm_vcpu, arch.spmc));
+ DEFINE(VCPU_SIAR, offsetof(struct kvm_vcpu, arch.siar));
+ DEFINE(VCPU_SDAR, offsetof(struct kvm_vcpu, arch.sdar));
+ DEFINE(VCPU_SIER, offsetof(struct kvm_vcpu, arch.sier));
DEFINE(VCPU_SLB, offsetof(struct kvm_vcpu, arch.slb));
DEFINE(VCPU_SLB_MAX, offsetof(struct kvm_vcpu, arch.slb_max));
DEFINE(VCPU_SLB_NR, offsetof(struct kvm_vcpu, arch.slb_nr));
- DEFINE(VCPU_LAST_CPU, offsetof(struct kvm_vcpu, arch.last_cpu));
DEFINE(VCPU_FAULT_DSISR, offsetof(struct kvm_vcpu, arch.fault_dsisr));
DEFINE(VCPU_FAULT_DAR, offsetof(struct kvm_vcpu, arch.fault_dar));
+ DEFINE(VCPU_INTR_MSR, offsetof(struct kvm_vcpu, arch.intr_msr));
DEFINE(VCPU_LAST_INST, offsetof(struct kvm_vcpu, arch.last_inst));
DEFINE(VCPU_TRAP, offsetof(struct kvm_vcpu, arch.trap));
- DEFINE(VCPU_PTID, offsetof(struct kvm_vcpu, arch.ptid));
+ DEFINE(VCPU_CFAR, offsetof(struct kvm_vcpu, arch.cfar));
+ DEFINE(VCPU_PPR, offsetof(struct kvm_vcpu, arch.ppr));
+ DEFINE(VCPU_FSCR, offsetof(struct kvm_vcpu, arch.fscr));
+ DEFINE(VCPU_SHADOW_FSCR, offsetof(struct kvm_vcpu, arch.shadow_fscr));
+ DEFINE(VCPU_PSPB, offsetof(struct kvm_vcpu, arch.pspb));
+ DEFINE(VCPU_EBBHR, offsetof(struct kvm_vcpu, arch.ebbhr));
+ DEFINE(VCPU_EBBRR, offsetof(struct kvm_vcpu, arch.ebbrr));
+ DEFINE(VCPU_BESCR, offsetof(struct kvm_vcpu, arch.bescr));
+ DEFINE(VCPU_CSIGR, offsetof(struct kvm_vcpu, arch.csigr));
+ DEFINE(VCPU_TACR, offsetof(struct kvm_vcpu, arch.tacr));
+ DEFINE(VCPU_TCSCR, offsetof(struct kvm_vcpu, arch.tcscr));
+ DEFINE(VCPU_ACOP, offsetof(struct kvm_vcpu, arch.acop));
+ DEFINE(VCPU_WORT, offsetof(struct kvm_vcpu, arch.wort));
+ DEFINE(VCPU_SHADOW_SRR1, offsetof(struct kvm_vcpu, arch.shadow_srr1));
DEFINE(VCORE_ENTRY_EXIT, offsetof(struct kvmppc_vcore, entry_exit_count));
DEFINE(VCORE_NAP_COUNT, offsetof(struct kvmppc_vcore, nap_count));
DEFINE(VCORE_IN_GUEST, offsetof(struct kvmppc_vcore, in_guest));
DEFINE(VCORE_NAPPING_THREADS, offsetof(struct kvmppc_vcore, napping_threads));
- DEFINE(VCPU_SVCPU, offsetof(struct kvmppc_vcpu_book3s, shadow_vcpu) -
- offsetof(struct kvmppc_vcpu_book3s, vcpu));
+ DEFINE(VCORE_KVM, offsetof(struct kvmppc_vcore, kvm));
+ DEFINE(VCORE_TB_OFFSET, offsetof(struct kvmppc_vcore, tb_offset));
+ DEFINE(VCORE_LPCR, offsetof(struct kvmppc_vcore, lpcr));
+ DEFINE(VCORE_PCR, offsetof(struct kvmppc_vcore, pcr));
+ DEFINE(VCORE_DPDES, offsetof(struct kvmppc_vcore, dpdes));
DEFINE(VCPU_SLB_E, offsetof(struct kvmppc_slb, orige));
DEFINE(VCPU_SLB_V, offsetof(struct kvmppc_slb, origv));
DEFINE(VCPU_SLB_SIZE, sizeof(struct kvmppc_slb));
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ DEFINE(VCPU_TFHAR, offsetof(struct kvm_vcpu, arch.tfhar));
+ DEFINE(VCPU_TFIAR, offsetof(struct kvm_vcpu, arch.tfiar));
+ DEFINE(VCPU_TEXASR, offsetof(struct kvm_vcpu, arch.texasr));
+ DEFINE(VCPU_GPR_TM, offsetof(struct kvm_vcpu, arch.gpr_tm));
+ DEFINE(VCPU_FPRS_TM, offsetof(struct kvm_vcpu, arch.fp_tm.fpr));
+ DEFINE(VCPU_VRS_TM, offsetof(struct kvm_vcpu, arch.vr_tm.vr));
+ DEFINE(VCPU_VRSAVE_TM, offsetof(struct kvm_vcpu, arch.vrsave_tm));
+ DEFINE(VCPU_CR_TM, offsetof(struct kvm_vcpu, arch.cr_tm));
+ DEFINE(VCPU_LR_TM, offsetof(struct kvm_vcpu, arch.lr_tm));
+ DEFINE(VCPU_CTR_TM, offsetof(struct kvm_vcpu, arch.ctr_tm));
+ DEFINE(VCPU_AMR_TM, offsetof(struct kvm_vcpu, arch.amr_tm));
+ DEFINE(VCPU_PPR_TM, offsetof(struct kvm_vcpu, arch.ppr_tm));
+ DEFINE(VCPU_DSCR_TM, offsetof(struct kvm_vcpu, arch.dscr_tm));
+ DEFINE(VCPU_TAR_TM, offsetof(struct kvm_vcpu, arch.tar_tm));
+#endif
#ifdef CONFIG_PPC_BOOK3S_64
-#ifdef CONFIG_KVM_BOOK3S_PR
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
+ DEFINE(PACA_SVCPU, offsetof(struct paca_struct, shadow_vcpu));
# define SVCPU_FIELD(x, f) DEFINE(x, offsetof(struct paca_struct, shadow_vcpu.f))
#else
# define SVCPU_FIELD(x, f)
@@ -530,6 +622,7 @@ int main(void)
#ifdef CONFIG_PPC64
SVCPU_FIELD(SVCPU_SLB, slb);
SVCPU_FIELD(SVCPU_SLB_MAX, slb_max);
+ SVCPU_FIELD(SVCPU_SHADOW_FSCR, shadow_fscr);
#endif
HSTATE_FIELD(HSTATE_HOST_R1, host_r1);
@@ -538,14 +631,20 @@ int main(void)
HSTATE_FIELD(HSTATE_VMHANDLER, vmhandler);
HSTATE_FIELD(HSTATE_SCRATCH0, scratch0);
HSTATE_FIELD(HSTATE_SCRATCH1, scratch1);
+ HSTATE_FIELD(HSTATE_SCRATCH2, scratch2);
HSTATE_FIELD(HSTATE_IN_GUEST, in_guest);
HSTATE_FIELD(HSTATE_RESTORE_HID5, restore_hid5);
HSTATE_FIELD(HSTATE_NAPPING, napping);
-#ifdef CONFIG_KVM_BOOK3S_64_HV
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+ HSTATE_FIELD(HSTATE_HWTHREAD_REQ, hwthread_req);
+ HSTATE_FIELD(HSTATE_HWTHREAD_STATE, hwthread_state);
HSTATE_FIELD(HSTATE_KVM_VCPU, kvm_vcpu);
HSTATE_FIELD(HSTATE_KVM_VCORE, kvm_vcore);
HSTATE_FIELD(HSTATE_XICS_PHYS, xics_phys);
+ HSTATE_FIELD(HSTATE_SAVED_XIRR, saved_xirr);
+ HSTATE_FIELD(HSTATE_HOST_IPI, host_ipi);
+ HSTATE_FIELD(HSTATE_PTID, ptid);
HSTATE_FIELD(HSTATE_MMCR, host_mmcr);
HSTATE_FIELD(HSTATE_PMC, host_pmc);
HSTATE_FIELD(HSTATE_PURR, host_purr);
@@ -554,7 +653,13 @@ int main(void)
HSTATE_FIELD(HSTATE_DABR, dabr);
HSTATE_FIELD(HSTATE_DECEXP, dec_expires);
DEFINE(IPI_PRIORITY, IPI_PRIORITY);
-#endif /* CONFIG_KVM_BOOK3S_64_HV */
+#endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */
+
+#ifdef CONFIG_PPC_BOOK3S_64
+ HSTATE_FIELD(HSTATE_CFAR, cfar);
+ HSTATE_FIELD(HSTATE_PPR, ppr);
+ HSTATE_FIELD(HSTATE_HOST_FSCR, host_fscr);
+#endif /* CONFIG_PPC_BOOK3S_64 */
#else /* CONFIG_PPC_BOOK3S */
DEFINE(VCPU_CR, offsetof(struct kvm_vcpu, arch.cr));
@@ -565,6 +670,7 @@ int main(void)
DEFINE(VCPU_LAST_INST, offsetof(struct kvm_vcpu, arch.last_inst));
DEFINE(VCPU_FAULT_DEAR, offsetof(struct kvm_vcpu, arch.fault_dear));
DEFINE(VCPU_FAULT_ESR, offsetof(struct kvm_vcpu, arch.fault_esr));
+ DEFINE(VCPU_CRIT_SAVE, offsetof(struct kvm_vcpu, arch.crit_save));
#endif /* CONFIG_PPC_BOOK3S */
#endif /* CONFIG_KVM */
@@ -603,6 +709,12 @@ int main(void)
DEFINE(VCPU_HOST_SPEFSCR, offsetof(struct kvm_vcpu, arch.host_spefscr));
#endif
+#ifdef CONFIG_KVM_BOOKE_HV
+ DEFINE(VCPU_HOST_MAS4, offsetof(struct kvm_vcpu, arch.host_mas4));
+ DEFINE(VCPU_HOST_MAS6, offsetof(struct kvm_vcpu, arch.host_mas6));
+ DEFINE(VCPU_EPLC, offsetof(struct kvm_vcpu, arch.eplc));
+#endif
+
#ifdef CONFIG_KVM_EXIT_TIMING
DEFINE(VCPU_TIMING_EXIT_TBU, offsetof(struct kvm_vcpu,
arch.timing_exit.tv32.tbu));
diff --git a/arch/powerpc/kernel/btext.c b/arch/powerpc/kernel/btext.c
index ac8f52732fd..41c011cb607 100644
--- a/arch/powerpc/kernel/btext.c
+++ b/arch/powerpc/kernel/btext.c
@@ -25,11 +25,6 @@
static void scrollscreen(void);
#endif
-static void draw_byte(unsigned char c, long locX, long locY);
-static void draw_byte_32(unsigned char *bits, unsigned int *base, int rb);
-static void draw_byte_16(unsigned char *bits, unsigned int *base, int rb);
-static void draw_byte_8(unsigned char *bits, unsigned int *base, int rb);
-
#define __force_data __attribute__((__section__(".data")))
static int g_loc_X __force_data;
@@ -52,6 +47,26 @@ static unsigned char vga_font[cmapsz];
int boot_text_mapped __force_data = 0;
int force_printk_to_btext = 0;
+extern void rmci_on(void);
+extern void rmci_off(void);
+
+static inline void rmci_maybe_on(void)
+{
+#if defined(CONFIG_PPC_EARLY_DEBUG_BOOTX) && defined(CONFIG_PPC64)
+ if (!(mfmsr() & MSR_DR))
+ rmci_on();
+#endif
+}
+
+static inline void rmci_maybe_off(void)
+{
+#if defined(CONFIG_PPC_EARLY_DEBUG_BOOTX) && defined(CONFIG_PPC64)
+ if (!(mfmsr() & MSR_DR))
+ rmci_off();
+#endif
+}
+
+
#ifdef CONFIG_PPC32
/* Calc BAT values for mapping the display and store them
* in disp_BAT. Those values are then used from head.S to map
@@ -134,7 +149,7 @@ void __init btext_unmap(void)
* changes.
*/
-static void map_boot_text(void)
+void btext_map(void)
{
unsigned long base, offset, size;
unsigned char *vbase;
@@ -209,7 +224,7 @@ int btext_initialize(struct device_node *np)
dispDeviceRect[2] = width;
dispDeviceRect[3] = height;
- map_boot_text();
+ btext_map();
return 0;
}
@@ -283,7 +298,7 @@ void btext_update_display(unsigned long phys, int width, int height,
iounmap(logicalDisplayBase);
boot_text_mapped = 0;
}
- map_boot_text();
+ btext_map();
g_loc_X = 0;
g_loc_Y = 0;
g_max_loc_X = width / 8;
@@ -298,6 +313,7 @@ void btext_clearscreen(void)
(dispDeviceDepth >> 3)) >> 2;
int i,j;
+ rmci_maybe_on();
for (i=0; i<(dispDeviceRect[3] - dispDeviceRect[1]); i++)
{
unsigned int *ptr = base;
@@ -305,6 +321,7 @@ void btext_clearscreen(void)
*(ptr++) = 0;
base += (dispDeviceRowBytes >> 2);
}
+ rmci_maybe_off();
}
void btext_flushscreen(void)
@@ -355,6 +372,8 @@ static void scrollscreen(void)
(dispDeviceDepth >> 3)) >> 2;
int i,j;
+ rmci_maybe_on();
+
for (i=0; i<(dispDeviceRect[3] - dispDeviceRect[1] - 16); i++)
{
unsigned int *src_ptr = src;
@@ -371,9 +390,116 @@ static void scrollscreen(void)
*(dst_ptr++) = 0;
dst += (dispDeviceRowBytes >> 2);
}
+
+ rmci_maybe_off();
}
#endif /* ndef NO_SCROLL */
+static unsigned int expand_bits_8[16] = {
+ 0x00000000,
+ 0x000000ff,
+ 0x0000ff00,
+ 0x0000ffff,
+ 0x00ff0000,
+ 0x00ff00ff,
+ 0x00ffff00,
+ 0x00ffffff,
+ 0xff000000,
+ 0xff0000ff,
+ 0xff00ff00,
+ 0xff00ffff,
+ 0xffff0000,
+ 0xffff00ff,
+ 0xffffff00,
+ 0xffffffff
+};
+
+static unsigned int expand_bits_16[4] = {
+ 0x00000000,
+ 0x0000ffff,
+ 0xffff0000,
+ 0xffffffff
+};
+
+
+static void draw_byte_32(unsigned char *font, unsigned int *base, int rb)
+{
+ int l, bits;
+ int fg = 0xFFFFFFFFUL;
+ int bg = 0x00000000UL;
+
+ for (l = 0; l < 16; ++l)
+ {
+ bits = *font++;
+ base[0] = (-(bits >> 7) & fg) ^ bg;
+ base[1] = (-((bits >> 6) & 1) & fg) ^ bg;
+ base[2] = (-((bits >> 5) & 1) & fg) ^ bg;
+ base[3] = (-((bits >> 4) & 1) & fg) ^ bg;
+ base[4] = (-((bits >> 3) & 1) & fg) ^ bg;
+ base[5] = (-((bits >> 2) & 1) & fg) ^ bg;
+ base[6] = (-((bits >> 1) & 1) & fg) ^ bg;
+ base[7] = (-(bits & 1) & fg) ^ bg;
+ base = (unsigned int *) ((char *)base + rb);
+ }
+}
+
+static inline void draw_byte_16(unsigned char *font, unsigned int *base, int rb)
+{
+ int l, bits;
+ int fg = 0xFFFFFFFFUL;
+ int bg = 0x00000000UL;
+ unsigned int *eb = (int *)expand_bits_16;
+
+ for (l = 0; l < 16; ++l)
+ {
+ bits = *font++;
+ base[0] = (eb[bits >> 6] & fg) ^ bg;
+ base[1] = (eb[(bits >> 4) & 3] & fg) ^ bg;
+ base[2] = (eb[(bits >> 2) & 3] & fg) ^ bg;
+ base[3] = (eb[bits & 3] & fg) ^ bg;
+ base = (unsigned int *) ((char *)base + rb);
+ }
+}
+
+static inline void draw_byte_8(unsigned char *font, unsigned int *base, int rb)
+{
+ int l, bits;
+ int fg = 0x0F0F0F0FUL;
+ int bg = 0x00000000UL;
+ unsigned int *eb = (int *)expand_bits_8;
+
+ for (l = 0; l < 16; ++l)
+ {
+ bits = *font++;
+ base[0] = (eb[bits >> 4] & fg) ^ bg;
+ base[1] = (eb[bits & 0xf] & fg) ^ bg;
+ base = (unsigned int *) ((char *)base + rb);
+ }
+}
+
+static noinline void draw_byte(unsigned char c, long locX, long locY)
+{
+ unsigned char *base = calc_base(locX << 3, locY << 4);
+ unsigned char *font = &vga_font[((unsigned int)c) * 16];
+ int rb = dispDeviceRowBytes;
+
+ rmci_maybe_on();
+ switch(dispDeviceDepth) {
+ case 24:
+ case 32:
+ draw_byte_32(font, (unsigned int *)base, rb);
+ break;
+ case 15:
+ case 16:
+ draw_byte_16(font, (unsigned int *)base, rb);
+ break;
+ case 8:
+ draw_byte_8(font, (unsigned int *)base, rb);
+ break;
+ }
+ rmci_maybe_off();
+}
+
void btext_drawchar(char c)
{
int cline = 0;
@@ -465,107 +591,12 @@ void btext_drawhex(unsigned long v)
btext_drawchar(' ');
}
-static void draw_byte(unsigned char c, long locX, long locY)
-{
- unsigned char *base = calc_base(locX << 3, locY << 4);
- unsigned char *font = &vga_font[((unsigned int)c) * 16];
- int rb = dispDeviceRowBytes;
-
- switch(dispDeviceDepth) {
- case 24:
- case 32:
- draw_byte_32(font, (unsigned int *)base, rb);
- break;
- case 15:
- case 16:
- draw_byte_16(font, (unsigned int *)base, rb);
- break;
- case 8:
- draw_byte_8(font, (unsigned int *)base, rb);
- break;
- }
-}
-
-static unsigned int expand_bits_8[16] = {
- 0x00000000,
- 0x000000ff,
- 0x0000ff00,
- 0x0000ffff,
- 0x00ff0000,
- 0x00ff00ff,
- 0x00ffff00,
- 0x00ffffff,
- 0xff000000,
- 0xff0000ff,
- 0xff00ff00,
- 0xff00ffff,
- 0xffff0000,
- 0xffff00ff,
- 0xffffff00,
- 0xffffffff
-};
-
-static unsigned int expand_bits_16[4] = {
- 0x00000000,
- 0x0000ffff,
- 0xffff0000,
- 0xffffffff
-};
-
-
-static void draw_byte_32(unsigned char *font, unsigned int *base, int rb)
-{
- int l, bits;
- int fg = 0xFFFFFFFFUL;
- int bg = 0x00000000UL;
-
- for (l = 0; l < 16; ++l)
- {
- bits = *font++;
- base[0] = (-(bits >> 7) & fg) ^ bg;
- base[1] = (-((bits >> 6) & 1) & fg) ^ bg;
- base[2] = (-((bits >> 5) & 1) & fg) ^ bg;
- base[3] = (-((bits >> 4) & 1) & fg) ^ bg;
- base[4] = (-((bits >> 3) & 1) & fg) ^ bg;
- base[5] = (-((bits >> 2) & 1) & fg) ^ bg;
- base[6] = (-((bits >> 1) & 1) & fg) ^ bg;
- base[7] = (-(bits & 1) & fg) ^ bg;
- base = (unsigned int *) ((char *)base + rb);
- }
-}
-
-static void draw_byte_16(unsigned char *font, unsigned int *base, int rb)
-{
- int l, bits;
- int fg = 0xFFFFFFFFUL;
- int bg = 0x00000000UL;
- unsigned int *eb = (int *)expand_bits_16;
-
- for (l = 0; l < 16; ++l)
- {
- bits = *font++;
- base[0] = (eb[bits >> 6] & fg) ^ bg;
- base[1] = (eb[(bits >> 4) & 3] & fg) ^ bg;
- base[2] = (eb[(bits >> 2) & 3] & fg) ^ bg;
- base[3] = (eb[bits & 3] & fg) ^ bg;
- base = (unsigned int *) ((char *)base + rb);
- }
-}
-
-static void draw_byte_8(unsigned char *font, unsigned int *base, int rb)
+void __init udbg_init_btext(void)
{
- int l, bits;
- int fg = 0x0F0F0F0FUL;
- int bg = 0x00000000UL;
- unsigned int *eb = (int *)expand_bits_8;
-
- for (l = 0; l < 16; ++l)
- {
- bits = *font++;
- base[0] = (eb[bits >> 4] & fg) ^ bg;
- base[1] = (eb[bits & 0xf] & fg) ^ bg;
- base = (unsigned int *) ((char *)base + rb);
- }
+ /* If btext is enabled, we might have a BAT setup for early display,
+ * thus we do enable some very basic udbg output
+ */
+ udbg_putc = btext_drawchar;
}
static unsigned char vga_font[cmapsz] = {
@@ -913,10 +944,3 @@ static unsigned char vga_font[cmapsz] = {
0x00, 0x00, 0x00, 0x00,
};
-void __init udbg_init_btext(void)
-{
- /* If btext is enabled, we might have a BAT setup for early display,
- * thus we do enable some very basic udbg output
- */
- udbg_putc = btext_drawchar;
-}
diff --git a/arch/powerpc/kernel/cacheinfo.c b/arch/powerpc/kernel/cacheinfo.c
index 92c6b008dd2..40198d50b4c 100644
--- a/arch/powerpc/kernel/cacheinfo.c
+++ b/arch/powerpc/kernel/cacheinfo.c
@@ -12,7 +12,6 @@
#include <linux/cpu.h>
#include <linux/cpumask.h>
-#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/kobject.h>
#include <linux/list.h>
@@ -131,7 +130,8 @@ static const char *cache_type_string(const struct cache *cache)
return cache_type_info[cache->type].name;
}
-static void __cpuinit cache_init(struct cache *cache, int type, int level, struct device_node *ofnode)
+static void cache_init(struct cache *cache, int type, int level,
+ struct device_node *ofnode)
{
cache->type = type;
cache->level = level;
@@ -140,7 +140,7 @@ static void __cpuinit cache_init(struct cache *cache, int type, int level, struc
list_add(&cache->list, &cache_list);
}
-static struct cache *__cpuinit new_cache(int type, int level, struct device_node *ofnode)
+static struct cache *new_cache(int type, int level, struct device_node *ofnode)
{
struct cache *cache;
@@ -195,7 +195,7 @@ static void cache_cpu_set(struct cache *cache, int cpu)
static int cache_size(const struct cache *cache, unsigned int *ret)
{
const char *propname;
- const u32 *cache_size;
+ const __be32 *cache_size;
propname = cache_type_info[cache->type].size_prop;
@@ -203,7 +203,7 @@ static int cache_size(const struct cache *cache, unsigned int *ret)
if (!cache_size)
return -ENODEV;
- *ret = *cache_size;
+ *ret = of_read_number(cache_size, 1);
return 0;
}
@@ -221,7 +221,7 @@ static int cache_size_kb(const struct cache *cache, unsigned int *ret)
/* not cache_line_size() because that's a macro in include/linux/cache.h */
static int cache_get_line_size(const struct cache *cache, unsigned int *ret)
{
- const u32 *line_size;
+ const __be32 *line_size;
int i, lim;
lim = ARRAY_SIZE(cache_type_info[cache->type].line_size_props);
@@ -238,14 +238,14 @@ static int cache_get_line_size(const struct cache *cache, unsigned int *ret)
if (!line_size)
return -ENODEV;
- *ret = *line_size;
+ *ret = of_read_number(line_size, 1);
return 0;
}
static int cache_nr_sets(const struct cache *cache, unsigned int *ret)
{
const char *propname;
- const u32 *nr_sets;
+ const __be32 *nr_sets;
propname = cache_type_info[cache->type].nr_sets_prop;
@@ -253,7 +253,7 @@ static int cache_nr_sets(const struct cache *cache, unsigned int *ret)
if (!nr_sets)
return -ENODEV;
- *ret = *nr_sets;
+ *ret = of_read_number(nr_sets, 1);
return 0;
}
@@ -324,7 +324,8 @@ static bool cache_node_is_unified(const struct device_node *np)
return of_get_property(np, "cache-unified", NULL);
}
-static struct cache *__cpuinit cache_do_one_devnode_unified(struct device_node *node, int level)
+static struct cache *cache_do_one_devnode_unified(struct device_node *node,
+ int level)
{
struct cache *cache;
@@ -335,7 +336,8 @@ static struct cache *__cpuinit cache_do_one_devnode_unified(struct device_node *
return cache;
}
-static struct cache *__cpuinit cache_do_one_devnode_split(struct device_node *node, int level)
+static struct cache *cache_do_one_devnode_split(struct device_node *node,
+ int level)
{
struct cache *dcache, *icache;
@@ -357,7 +359,7 @@ err:
return NULL;
}
-static struct cache *__cpuinit cache_do_one_devnode(struct device_node *node, int level)
+static struct cache *cache_do_one_devnode(struct device_node *node, int level)
{
struct cache *cache;
@@ -369,7 +371,8 @@ static struct cache *__cpuinit cache_do_one_devnode(struct device_node *node, in
return cache;
}
-static struct cache *__cpuinit cache_lookup_or_instantiate(struct device_node *node, int level)
+static struct cache *cache_lookup_or_instantiate(struct device_node *node,
+ int level)
{
struct cache *cache;
@@ -385,7 +388,7 @@ static struct cache *__cpuinit cache_lookup_or_instantiate(struct device_node *n
return cache;
}
-static void __cpuinit link_cache_lists(struct cache *smaller, struct cache *bigger)
+static void link_cache_lists(struct cache *smaller, struct cache *bigger)
{
while (smaller->next_local) {
if (smaller->next_local == bigger)
@@ -396,13 +399,13 @@ static void __cpuinit link_cache_lists(struct cache *smaller, struct cache *bigg
smaller->next_local = bigger;
}
-static void __cpuinit do_subsidiary_caches_debugcheck(struct cache *cache)
+static void do_subsidiary_caches_debugcheck(struct cache *cache)
{
WARN_ON_ONCE(cache->level != 1);
WARN_ON_ONCE(strcmp(cache->ofnode->type, "cpu"));
}
-static void __cpuinit do_subsidiary_caches(struct cache *cache)
+static void do_subsidiary_caches(struct cache *cache)
{
struct device_node *subcache_node;
int level = cache->level;
@@ -423,7 +426,7 @@ static void __cpuinit do_subsidiary_caches(struct cache *cache)
}
}
-static struct cache *__cpuinit cache_chain_instantiate(unsigned int cpu_id)
+static struct cache *cache_chain_instantiate(unsigned int cpu_id)
{
struct device_node *cpu_node;
struct cache *cpu_cache = NULL;
@@ -448,7 +451,7 @@ out:
return cpu_cache;
}
-static struct cache_dir *__cpuinit cacheinfo_create_cache_dir(unsigned int cpu_id)
+static struct cache_dir *cacheinfo_create_cache_dir(unsigned int cpu_id)
{
struct cache_dir *cache_dir;
struct device *dev;
@@ -653,7 +656,7 @@ static struct kobj_type cache_index_type = {
.default_attrs = cache_index_default_attrs,
};
-static void __cpuinit cacheinfo_create_index_opt_attrs(struct cache_index_dir *dir)
+static void cacheinfo_create_index_opt_attrs(struct cache_index_dir *dir)
{
const char *cache_name;
const char *cache_type;
@@ -696,7 +699,8 @@ static void __cpuinit cacheinfo_create_index_opt_attrs(struct cache_index_dir *d
kfree(buf);
}
-static void __cpuinit cacheinfo_create_index_dir(struct cache *cache, int index, struct cache_dir *cache_dir)
+static void cacheinfo_create_index_dir(struct cache *cache, int index,
+ struct cache_dir *cache_dir)
{
struct cache_index_dir *index_dir;
int rc;
@@ -722,7 +726,8 @@ err:
kfree(index_dir);
}
-static void __cpuinit cacheinfo_sysfs_populate(unsigned int cpu_id, struct cache *cache_list)
+static void cacheinfo_sysfs_populate(unsigned int cpu_id,
+ struct cache *cache_list)
{
struct cache_dir *cache_dir;
struct cache *cache;
@@ -740,7 +745,7 @@ static void __cpuinit cacheinfo_sysfs_populate(unsigned int cpu_id, struct cache
}
}
-void __cpuinit cacheinfo_cpu_online(unsigned int cpu_id)
+void cacheinfo_cpu_online(unsigned int cpu_id)
{
struct cache *cache;
@@ -751,7 +756,10 @@ void __cpuinit cacheinfo_cpu_online(unsigned int cpu_id)
cacheinfo_sysfs_populate(cpu_id, cache);
}
-#ifdef CONFIG_HOTPLUG_CPU /* functions needed for cpu offline */
+/* functions needed to remove cache entry for cpu offline or suspend/resume */
+
+#if (defined(CONFIG_PPC_PSERIES) && defined(CONFIG_SUSPEND)) || \
+ defined(CONFIG_HOTPLUG_CPU)
static struct cache *cache_lookup_by_cpu(unsigned int cpu_id)
{
@@ -788,6 +796,9 @@ static void remove_cache_dir(struct cache_dir *cache_dir)
{
remove_index_dirs(cache_dir);
+ /* Remove cache dir from sysfs */
+ kobject_del(cache_dir->kobj);
+
kobject_put(cache_dir->kobj);
kfree(cache_dir);
@@ -835,4 +846,4 @@ void cacheinfo_cpu_offline(unsigned int cpu_id)
if (cache)
cache_cpu_clear(cache, cpu_id);
}
-#endif /* CONFIG_HOTPLUG_CPU */
+#endif /* (CONFIG_PPC_PSERIES && CONFIG_SUSPEND) || CONFIG_HOTPLUG_CPU */
diff --git a/arch/powerpc/kernel/clock.c b/arch/powerpc/kernel/clock.c
deleted file mode 100644
index a764b47791e..00000000000
--- a/arch/powerpc/kernel/clock.c
+++ /dev/null
@@ -1,82 +0,0 @@
-/*
- * Dummy clk implementations for powerpc.
- * These need to be overridden in platform code.
- */
-
-#include <linux/clk.h>
-#include <linux/err.h>
-#include <linux/errno.h>
-#include <linux/export.h>
-#include <asm/clk_interface.h>
-
-struct clk_interface clk_functions;
-
-struct clk *clk_get(struct device *dev, const char *id)
-{
- if (clk_functions.clk_get)
- return clk_functions.clk_get(dev, id);
- return ERR_PTR(-ENOSYS);
-}
-EXPORT_SYMBOL(clk_get);
-
-void clk_put(struct clk *clk)
-{
- if (clk_functions.clk_put)
- clk_functions.clk_put(clk);
-}
-EXPORT_SYMBOL(clk_put);
-
-int clk_enable(struct clk *clk)
-{
- if (clk_functions.clk_enable)
- return clk_functions.clk_enable(clk);
- return -ENOSYS;
-}
-EXPORT_SYMBOL(clk_enable);
-
-void clk_disable(struct clk *clk)
-{
- if (clk_functions.clk_disable)
- clk_functions.clk_disable(clk);
-}
-EXPORT_SYMBOL(clk_disable);
-
-unsigned long clk_get_rate(struct clk *clk)
-{
- if (clk_functions.clk_get_rate)
- return clk_functions.clk_get_rate(clk);
- return 0;
-}
-EXPORT_SYMBOL(clk_get_rate);
-
-long clk_round_rate(struct clk *clk, unsigned long rate)
-{
- if (clk_functions.clk_round_rate)
- return clk_functions.clk_round_rate(clk, rate);
- return -ENOSYS;
-}
-EXPORT_SYMBOL(clk_round_rate);
-
-int clk_set_rate(struct clk *clk, unsigned long rate)
-{
- if (clk_functions.clk_set_rate)
- return clk_functions.clk_set_rate(clk, rate);
- return -ENOSYS;
-}
-EXPORT_SYMBOL(clk_set_rate);
-
-struct clk *clk_get_parent(struct clk *clk)
-{
- if (clk_functions.clk_get_parent)
- return clk_functions.clk_get_parent(clk);
- return ERR_PTR(-ENOSYS);
-}
-EXPORT_SYMBOL(clk_get_parent);
-
-int clk_set_parent(struct clk *clk, struct clk *parent)
-{
- if (clk_functions.clk_set_parent)
- return clk_functions.clk_set_parent(clk, parent);
- return -ENOSYS;
-}
-EXPORT_SYMBOL(clk_set_parent);
diff --git a/arch/powerpc/kernel/cpu_setup_a2.S b/arch/powerpc/kernel/cpu_setup_a2.S
deleted file mode 100644
index ebc62f42a23..00000000000
--- a/arch/powerpc/kernel/cpu_setup_a2.S
+++ /dev/null
@@ -1,120 +0,0 @@
-/*
- * A2 specific assembly support code
- *
- * Copyright 2009 Ben Herrenschmidt, IBM Corp.
- *
- * 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.
- */
-
-#include <asm/asm-offsets.h>
-#include <asm/ppc_asm.h>
-#include <asm/ppc-opcode.h>
-#include <asm/processor.h>
-#include <asm/reg_a2.h>
-#include <asm/reg.h>
-#include <asm/thread_info.h>
-
-/*
- * Disable thdid and class fields in ERATs to bump PID to full 14 bits capacity.
- * This also prevents external LPID accesses but that isn't a problem when not a
- * guest. Under PV, this setting will be ignored and MMUCR will return the right
- * number of PID bits we can use.
- */
-#define MMUCR1_EXTEND_PID \
- (MMUCR1_ICTID | MMUCR1_ITTID | MMUCR1_DCTID | \
- MMUCR1_DTTID | MMUCR1_DCCD)
-
-/*
- * Use extended PIDs if enabled.
- * Don't clear the ERATs on context sync events and enable I & D LRU.
- * Enable ERAT back invalidate when tlbwe overwrites an entry.
- */
-#define INITIAL_MMUCR1 \
- (MMUCR1_EXTEND_PID | MMUCR1_CSINV_NEVER | MMUCR1_IRRE | \
- MMUCR1_DRRE | MMUCR1_TLBWE_BINV)
-
-_GLOBAL(__setup_cpu_a2)
- /* Some of these are actually thread local and some are
- * core local but doing it always won't hurt
- */
-
-#ifdef CONFIG_PPC_ICSWX
- /* Make sure ACOP starts out as zero */
- li r3,0
- mtspr SPRN_ACOP,r3
-
- /* Skip the following if we are in Guest mode */
- mfmsr r3
- andis. r0,r3,MSR_GS@h
- bne _icswx_skip_guest
-
- /* Enable icswx instruction */
- mfspr r3,SPRN_A2_CCR2
- ori r3,r3,A2_CCR2_ENABLE_ICSWX
- mtspr SPRN_A2_CCR2,r3
-
- /* Unmask all CTs in HACOP */
- li r3,-1
- mtspr SPRN_HACOP,r3
-_icswx_skip_guest:
-#endif /* CONFIG_PPC_ICSWX */
-
- /* Enable doorbell */
- mfspr r3,SPRN_A2_CCR2
- oris r3,r3,A2_CCR2_ENABLE_PC@h
- mtspr SPRN_A2_CCR2,r3
- isync
-
- /* Setup CCR0 to disable power saving for now as it's busted
- * in the current implementations. Setup CCR1 to wake on
- * interrupts normally (we write the default value but who
- * knows what FW may have clobbered...)
- */
- li r3,0
- mtspr SPRN_A2_CCR0, r3
- LOAD_REG_IMMEDIATE(r3,0x0f0f0f0f)
- mtspr SPRN_A2_CCR1, r3
-
- /* Initialise MMUCR1 */
- lis r3,INITIAL_MMUCR1@h
- ori r3,r3,INITIAL_MMUCR1@l
- mtspr SPRN_MMUCR1,r3
-
- /* Set MMUCR2 to enable 4K, 64K, 1M, 16M and 1G pages */
- LOAD_REG_IMMEDIATE(r3, 0x000a7531)
- mtspr SPRN_MMUCR2,r3
-
- /* Set MMUCR3 to write all thids bit to the TLB */
- LOAD_REG_IMMEDIATE(r3, 0x0000000f)
- mtspr SPRN_MMUCR3,r3
-
- /* Don't do ERAT stuff if running guest mode */
- mfmsr r3
- andis. r0,r3,MSR_GS@h
- bne 1f
-
- /* Now set the I-ERAT watermark to 15 */
- lis r4,(MMUCR0_TLBSEL_I|MMUCR0_ECL)@h
- mtspr SPRN_MMUCR0, r4
- li r4,A2_IERAT_SIZE-1
- PPC_ERATWE(r4,r4,3)
-
- /* Now set the D-ERAT watermark to 31 */
- lis r4,(MMUCR0_TLBSEL_D|MMUCR0_ECL)@h
- mtspr SPRN_MMUCR0, r4
- li r4,A2_DERAT_SIZE-1
- PPC_ERATWE(r4,r4,3)
-
- /* And invalidate the beast just in case. That won't get rid of
- * a bolted entry though it will be in LRU and so will go away eventually
- * but let's not bother for now
- */
- PPC_ERATILX(0,0,0)
-1:
- blr
-
-_GLOBAL(__restore_cpu_a2)
- b __setup_cpu_a2
diff --git a/arch/powerpc/kernel/cpu_setup_fsl_booke.S b/arch/powerpc/kernel/cpu_setup_fsl_booke.S
index 8053db02b85..4f1393d2007 100644
--- a/arch/powerpc/kernel/cpu_setup_fsl_booke.S
+++ b/arch/powerpc/kernel/cpu_setup_fsl_booke.S
@@ -16,6 +16,8 @@
#include <asm/processor.h>
#include <asm/cputable.h>
#include <asm/ppc_asm.h>
+#include <asm/mmu-book3e.h>
+#include <asm/asm-offsets.h>
_GLOBAL(__e500_icache_setup)
mfspr r0, SPRN_L1CSR1
@@ -51,6 +53,61 @@ _GLOBAL(__e500_dcache_setup)
isync
blr
+/*
+ * FIXME - we haven't yet done testing to determine a reasonable default
+ * value for PW20_WAIT_IDLE_BIT.
+ */
+#define PW20_WAIT_IDLE_BIT 50 /* 1ms, TB frequency is 41.66MHZ */
+_GLOBAL(setup_pw20_idle)
+ mfspr r3, SPRN_PWRMGTCR0
+
+ /* Set PW20_WAIT bit, enable pw20 state*/
+ ori r3, r3, PWRMGTCR0_PW20_WAIT
+ li r11, PW20_WAIT_IDLE_BIT
+
+ /* Set Automatic PW20 Core Idle Count */
+ rlwimi r3, r11, PWRMGTCR0_PW20_ENT_SHIFT, PWRMGTCR0_PW20_ENT
+
+ mtspr SPRN_PWRMGTCR0, r3
+
+ blr
+
+/*
+ * FIXME - we haven't yet done testing to determine a reasonable default
+ * value for AV_WAIT_IDLE_BIT.
+ */
+#define AV_WAIT_IDLE_BIT 50 /* 1ms, TB frequency is 41.66MHZ */
+_GLOBAL(setup_altivec_idle)
+ mfspr r3, SPRN_PWRMGTCR0
+
+ /* Enable Altivec Idle */
+ oris r3, r3, PWRMGTCR0_AV_IDLE_PD_EN@h
+ li r11, AV_WAIT_IDLE_BIT
+
+ /* Set Automatic AltiVec Idle Count */
+ rlwimi r3, r11, PWRMGTCR0_AV_IDLE_CNT_SHIFT, PWRMGTCR0_AV_IDLE_CNT
+
+ mtspr SPRN_PWRMGTCR0, r3
+
+ blr
+
+_GLOBAL(__setup_cpu_e6500)
+ mflr r6
+#ifdef CONFIG_PPC64
+ bl setup_altivec_ivors
+ /* Touch IVOR42 only if the CPU supports E.HV category */
+ mfspr r10,SPRN_MMUCFG
+ rlwinm. r10,r10,0,MMUCFG_LPIDSIZE
+ beq 1f
+ bl setup_lrat_ivor
+1:
+#endif
+ bl setup_pw20_idle
+ bl setup_altivec_idle
+ bl __setup_cpu_e5500
+ mtlr r6
+ blr
+
#ifdef CONFIG_PPC32
_GLOBAL(__setup_cpu_e200)
/* enable dedicated debug exception handling resources (Debug APU) */
@@ -64,7 +121,7 @@ _GLOBAL(__setup_cpu_e500v2)
bl __e500_icache_setup
bl __e500_dcache_setup
bl __setup_e500_ivors
-#ifdef CONFIG_FSL_RIO
+#if defined(CONFIG_FSL_RIO) || defined(CONFIG_FSL_PCI)
/* Ensure that RFXE is set */
mfspr r3,SPRN_HID1
oris r3,r3,HID1_RFXE@h
@@ -73,26 +130,96 @@ _GLOBAL(__setup_cpu_e500v2)
mtlr r4
blr
_GLOBAL(__setup_cpu_e500mc)
- mflr r4
+_GLOBAL(__setup_cpu_e5500)
+ mflr r5
bl __e500_icache_setup
bl __e500_dcache_setup
bl __setup_e500mc_ivors
- mtlr r4
+ /*
+ * We only want to touch IVOR38-41 if we're running on hardware
+ * that supports category E.HV. The architectural way to determine
+ * this is MMUCFG[LPIDSIZE].
+ */
+ mfspr r3, SPRN_MMUCFG
+ rlwinm. r3, r3, 0, MMUCFG_LPIDSIZE
+ beq 1f
+ bl __setup_ehv_ivors
+ b 2f
+1:
+ lwz r3, CPU_SPEC_FEATURES(r4)
+ /* We need this check as cpu_setup is also called for
+ * the secondary cores. So, if we have already cleared
+ * the feature on the primary core, avoid doing it on the
+ * secondary core.
+ */
+ andis. r6, r3, CPU_FTR_EMB_HV@h
+ beq 2f
+ rlwinm r3, r3, 0, ~CPU_FTR_EMB_HV
+ stw r3, CPU_SPEC_FEATURES(r4)
+2:
+ mtlr r5
blr
#endif
-/* Right now, restore and setup are the same thing */
+
+#ifdef CONFIG_PPC_BOOK3E_64
+_GLOBAL(__restore_cpu_e6500)
+ mflr r5
+ bl setup_altivec_ivors
+ /* Touch IVOR42 only if the CPU supports E.HV category */
+ mfspr r10,SPRN_MMUCFG
+ rlwinm. r10,r10,0,MMUCFG_LPIDSIZE
+ beq 1f
+ bl setup_lrat_ivor
+1:
+ bl setup_pw20_idle
+ bl setup_altivec_idle
+ bl __restore_cpu_e5500
+ mtlr r5
+ blr
+
_GLOBAL(__restore_cpu_e5500)
-_GLOBAL(__setup_cpu_e5500)
mflr r4
bl __e500_icache_setup
bl __e500_dcache_setup
-#ifdef CONFIG_PPC_BOOK3E_64
- bl .__setup_base_ivors
- bl .setup_perfmon_ivor
- bl .setup_doorbell_ivors
- bl .setup_ehv_ivors
-#else
- bl __setup_e500mc_ivors
-#endif
+ bl __setup_base_ivors
+ bl setup_perfmon_ivor
+ bl setup_doorbell_ivors
+ /*
+ * We only want to touch IVOR38-41 if we're running on hardware
+ * that supports category E.HV. The architectural way to determine
+ * this is MMUCFG[LPIDSIZE].
+ */
+ mfspr r10,SPRN_MMUCFG
+ rlwinm. r10,r10,0,MMUCFG_LPIDSIZE
+ beq 1f
+ bl setup_ehv_ivors
+1:
mtlr r4
blr
+
+_GLOBAL(__setup_cpu_e5500)
+ mflr r5
+ bl __e500_icache_setup
+ bl __e500_dcache_setup
+ bl __setup_base_ivors
+ bl setup_perfmon_ivor
+ bl setup_doorbell_ivors
+ /*
+ * We only want to touch IVOR38-41 if we're running on hardware
+ * that supports category E.HV. The architectural way to determine
+ * this is MMUCFG[LPIDSIZE].
+ */
+ mfspr r10,SPRN_MMUCFG
+ rlwinm. r10,r10,0,MMUCFG_LPIDSIZE
+ beq 1f
+ bl setup_ehv_ivors
+ b 2f
+1:
+ ld r10,CPU_SPEC_FEATURES(r4)
+ LOAD_REG_IMMEDIATE(r9,CPU_FTR_EMB_HV)
+ andc r10,r10,r9
+ std r10,CPU_SPEC_FEATURES(r4)
+2:
+ mtlr r5
+ blr
+#endif
diff --git a/arch/powerpc/kernel/cpu_setup_power7.S b/arch/powerpc/kernel/cpu_setup_power.S
index 76797c5105d..46733535cc0 100644
--- a/arch/powerpc/kernel/cpu_setup_power7.S
+++ b/arch/powerpc/kernel/cpu_setup_power.S
@@ -27,8 +27,9 @@ _GLOBAL(__setup_cpu_power7)
beqlr
li r0,0
mtspr SPRN_LPID,r0
+ mfspr r3,SPRN_LPCR
bl __init_LPCR
- bl __init_TLB
+ bl __init_tlb_power7
mtlr r11
blr
@@ -39,8 +40,46 @@ _GLOBAL(__restore_cpu_power7)
beqlr
li r0,0
mtspr SPRN_LPID,r0
+ mfspr r3,SPRN_LPCR
+ bl __init_LPCR
+ bl __init_tlb_power7
+ mtlr r11
+ blr
+
+_GLOBAL(__setup_cpu_power8)
+ mflr r11
+ bl __init_FSCR
+ bl __init_PMU
+ bl __init_hvmode_206
+ mtlr r11
+ beqlr
+ li r0,0
+ mtspr SPRN_LPID,r0
+ mfspr r3,SPRN_LPCR
+ ori r3, r3, LPCR_PECEDH
+ bl __init_LPCR
+ bl __init_HFSCR
+ bl __init_tlb_power8
+ bl __init_PMU_HV
+ mtlr r11
+ blr
+
+_GLOBAL(__restore_cpu_power8)
+ mflr r11
+ bl __init_FSCR
+ bl __init_PMU
+ mfmsr r3
+ rldicl. r0,r3,4,63
+ mtlr r11
+ beqlr
+ li r0,0
+ mtspr SPRN_LPID,r0
+ mfspr r3,SPRN_LPCR
+ ori r3, r3, LPCR_PECEDH
bl __init_LPCR
- bl __init_TLB
+ bl __init_HFSCR
+ bl __init_tlb_power8
+ bl __init_PMU_HV
mtlr r11
blr
@@ -57,6 +96,7 @@ __init_hvmode_206:
__init_LPCR:
/* Setup a sane LPCR:
+ * Called with initial LPCR in R3
*
* LPES = 0b01 (HSRR0/1 used for 0x500)
* PECE = 0b111
@@ -67,7 +107,6 @@ __init_LPCR:
*
* Other bits untouched for now
*/
- mfspr r3,SPRN_LPCR
li r5,1
rldimi r3,r5, LPCR_LPES_SH, 64-LPCR_LPES_SH-2
ori r3,r3,(LPCR_PECE0|LPCR_PECE1|LPCR_PECE2)
@@ -82,14 +121,62 @@ __init_LPCR:
isync
blr
-__init_TLB:
- /* Clear the TLB */
+__init_FSCR:
+ mfspr r3,SPRN_FSCR
+ ori r3,r3,FSCR_TAR|FSCR_DSCR|FSCR_EBB
+ mtspr SPRN_FSCR,r3
+ blr
+
+__init_HFSCR:
+ mfspr r3,SPRN_HFSCR
+ ori r3,r3,HFSCR_TAR|HFSCR_TM|HFSCR_BHRB|HFSCR_PM|\
+ HFSCR_DSCR|HFSCR_VECVSX|HFSCR_FP|HFSCR_EBB
+ mtspr SPRN_HFSCR,r3
+ blr
+
+/*
+ * Clear the TLB using the specified IS form of tlbiel instruction
+ * (invalidate by congruence class). P7 has 128 CCs., P8 has 512.
+ *
+ * r3 = IS field
+ */
+__init_tlb_power7:
+ li r3,0xc00 /* IS field = 0b11 */
+_GLOBAL(__flush_tlb_power7)
li r6,128
mtctr r6
- li r7,0xc00 /* IS field = 0b11 */
+ mr r7,r3 /* IS field */
+ ptesync
+2: tlbiel r7
+ addi r7,r7,0x1000
+ bdnz 2b
+ ptesync
+1: blr
+
+__init_tlb_power8:
+ li r3,0xc00 /* IS field = 0b11 */
+_GLOBAL(__flush_tlb_power8)
+ li r6,512
+ mtctr r6
+ mr r7,r3 /* IS field */
ptesync
2: tlbiel r7
addi r7,r7,0x1000
bdnz 2b
ptesync
1: blr
+
+__init_PMU_HV:
+ li r5,0
+ mtspr SPRN_MMCRC,r5
+ mtspr SPRN_MMCRH,r5
+ blr
+
+__init_PMU:
+ li r5,0
+ mtspr SPRN_MMCRS,r5
+ mtspr SPRN_MMCRA,r5
+ mtspr SPRN_MMCR0,r5
+ mtspr SPRN_MMCR1,r5
+ mtspr SPRN_MMCR2,r5
+ blr
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index 81db9e2a8a2..0c157642c2a 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -20,6 +20,7 @@
#include <asm/cputable.h>
#include <asm/prom.h> /* for PTRRELOC on ARCH=ppc */
#include <asm/mmu.h>
+#include <asm/setup.h>
struct cpu_spec* cur_cpu_spec = NULL;
EXPORT_SYMBOL(cur_cpu_spec);
@@ -67,11 +68,19 @@ extern void __restore_cpu_pa6t(void);
extern void __restore_cpu_ppc970(void);
extern void __setup_cpu_power7(unsigned long offset, struct cpu_spec* spec);
extern void __restore_cpu_power7(void);
+extern void __setup_cpu_power8(unsigned long offset, struct cpu_spec* spec);
+extern void __restore_cpu_power8(void);
extern void __restore_cpu_a2(void);
+extern void __flush_tlb_power7(unsigned long inval_selector);
+extern void __flush_tlb_power8(unsigned long inval_selector);
+extern long __machine_check_early_realmode_p7(struct pt_regs *regs);
+extern long __machine_check_early_realmode_p8(struct pt_regs *regs);
#endif /* CONFIG_PPC64 */
#if defined(CONFIG_E500)
extern void __setup_cpu_e5500(unsigned long offset, struct cpu_spec* spec);
+extern void __setup_cpu_e6500(unsigned long offset, struct cpu_spec* spec);
extern void __restore_cpu_e5500(void);
+extern void __restore_cpu_e6500(void);
#endif /* CONFIG_E500 */
/* This table only contains "desktop" CPUs, it need to be filled with embedded
@@ -93,6 +102,15 @@ extern void __restore_cpu_e5500(void);
PPC_FEATURE_SMT | PPC_FEATURE_ICACHE_SNOOP | \
PPC_FEATURE_TRUE_LE | \
PPC_FEATURE_PSERIES_PERFMON_COMPAT)
+#define COMMON_USER2_POWER7 (PPC_FEATURE2_DSCR)
+#define COMMON_USER_POWER8 (COMMON_USER_PPC64 | PPC_FEATURE_ARCH_2_06 |\
+ PPC_FEATURE_SMT | PPC_FEATURE_ICACHE_SNOOP | \
+ PPC_FEATURE_TRUE_LE | \
+ PPC_FEATURE_PSERIES_PERFMON_COMPAT)
+#define COMMON_USER2_POWER8 (PPC_FEATURE2_ARCH_2_07 | \
+ PPC_FEATURE2_HTM_COMP | PPC_FEATURE2_DSCR | \
+ PPC_FEATURE2_ISEL | PPC_FEATURE2_TAR | \
+ PPC_FEATURE2_VEC_CRYPTO)
#define COMMON_USER_PA6T (COMMON_USER_PPC64 | PPC_FEATURE_PA6T |\
PPC_FEATURE_TRUE_LE | \
PPC_FEATURE_HAS_ALTIVEC_COMP)
@@ -268,7 +286,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
.cpu_features = CPU_FTRS_PPC970,
.cpu_user_features = COMMON_USER_POWER4 |
PPC_FEATURE_HAS_ALTIVEC_COMP,
- .mmu_features = MMU_FTR_HPTE_TABLE,
+ .mmu_features = MMU_FTRS_PPC970,
.icache_bsize = 128,
.dcache_bsize = 128,
.num_pmcs = 8,
@@ -419,6 +437,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
.cpu_name = "POWER7 (architected)",
.cpu_features = CPU_FTRS_POWER7,
.cpu_user_features = COMMON_USER_POWER7,
+ .cpu_user_features2 = COMMON_USER2_POWER7,
.mmu_features = MMU_FTRS_POWER7,
.icache_bsize = 128,
.dcache_bsize = 128,
@@ -426,14 +445,35 @@ static struct cpu_spec __initdata cpu_specs[] = {
.oprofile_cpu_type = "ppc64/ibm-compat-v1",
.cpu_setup = __setup_cpu_power7,
.cpu_restore = __restore_cpu_power7,
+ .flush_tlb = __flush_tlb_power7,
+ .machine_check_early = __machine_check_early_realmode_p7,
.platform = "power7",
},
+ { /* 2.07-compliant processor, i.e. Power8 "architected" mode */
+ .pvr_mask = 0xffffffff,
+ .pvr_value = 0x0f000004,
+ .cpu_name = "POWER8 (architected)",
+ .cpu_features = CPU_FTRS_POWER8,
+ .cpu_user_features = COMMON_USER_POWER8,
+ .cpu_user_features2 = COMMON_USER2_POWER8,
+ .mmu_features = MMU_FTRS_POWER8,
+ .icache_bsize = 128,
+ .dcache_bsize = 128,
+ .oprofile_type = PPC_OPROFILE_INVALID,
+ .oprofile_cpu_type = "ppc64/ibm-compat-v1",
+ .cpu_setup = __setup_cpu_power8,
+ .cpu_restore = __restore_cpu_power8,
+ .flush_tlb = __flush_tlb_power8,
+ .machine_check_early = __machine_check_early_realmode_p8,
+ .platform = "power8",
+ },
{ /* Power7 */
.pvr_mask = 0xffff0000,
.pvr_value = 0x003f0000,
.cpu_name = "POWER7 (raw)",
.cpu_features = CPU_FTRS_POWER7,
.cpu_user_features = COMMON_USER_POWER7,
+ .cpu_user_features2 = COMMON_USER2_POWER7,
.mmu_features = MMU_FTRS_POWER7,
.icache_bsize = 128,
.dcache_bsize = 128,
@@ -443,6 +483,8 @@ static struct cpu_spec __initdata cpu_specs[] = {
.oprofile_type = PPC_OPROFILE_POWER4,
.cpu_setup = __setup_cpu_power7,
.cpu_restore = __restore_cpu_power7,
+ .flush_tlb = __flush_tlb_power7,
+ .machine_check_early = __machine_check_early_realmode_p7,
.platform = "power7",
},
{ /* Power7+ */
@@ -451,6 +493,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
.cpu_name = "POWER7+ (raw)",
.cpu_features = CPU_FTRS_POWER7,
.cpu_user_features = COMMON_USER_POWER7,
+ .cpu_user_features2 = COMMON_USER2_POWER7,
.mmu_features = MMU_FTRS_POWER7,
.icache_bsize = 128,
.dcache_bsize = 128,
@@ -460,8 +503,70 @@ static struct cpu_spec __initdata cpu_specs[] = {
.oprofile_type = PPC_OPROFILE_POWER4,
.cpu_setup = __setup_cpu_power7,
.cpu_restore = __restore_cpu_power7,
+ .flush_tlb = __flush_tlb_power7,
+ .machine_check_early = __machine_check_early_realmode_p7,
.platform = "power7+",
},
+ { /* Power8E */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x004b0000,
+ .cpu_name = "POWER8E (raw)",
+ .cpu_features = CPU_FTRS_POWER8E,
+ .cpu_user_features = COMMON_USER_POWER8,
+ .cpu_user_features2 = COMMON_USER2_POWER8,
+ .mmu_features = MMU_FTRS_POWER8,
+ .icache_bsize = 128,
+ .dcache_bsize = 128,
+ .num_pmcs = 6,
+ .pmc_type = PPC_PMC_IBM,
+ .oprofile_cpu_type = "ppc64/power8",
+ .oprofile_type = PPC_OPROFILE_INVALID,
+ .cpu_setup = __setup_cpu_power8,
+ .cpu_restore = __restore_cpu_power8,
+ .flush_tlb = __flush_tlb_power8,
+ .machine_check_early = __machine_check_early_realmode_p8,
+ .platform = "power8",
+ },
+ { /* Power8 DD1: Does not support doorbell IPIs */
+ .pvr_mask = 0xffffff00,
+ .pvr_value = 0x004d0100,
+ .cpu_name = "POWER8 (raw)",
+ .cpu_features = CPU_FTRS_POWER8_DD1,
+ .cpu_user_features = COMMON_USER_POWER8,
+ .cpu_user_features2 = COMMON_USER2_POWER8,
+ .mmu_features = MMU_FTRS_POWER8,
+ .icache_bsize = 128,
+ .dcache_bsize = 128,
+ .num_pmcs = 6,
+ .pmc_type = PPC_PMC_IBM,
+ .oprofile_cpu_type = "ppc64/power8",
+ .oprofile_type = PPC_OPROFILE_INVALID,
+ .cpu_setup = __setup_cpu_power8,
+ .cpu_restore = __restore_cpu_power8,
+ .flush_tlb = __flush_tlb_power8,
+ .machine_check_early = __machine_check_early_realmode_p8,
+ .platform = "power8",
+ },
+ { /* Power8 */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x004d0000,
+ .cpu_name = "POWER8 (raw)",
+ .cpu_features = CPU_FTRS_POWER8,
+ .cpu_user_features = COMMON_USER_POWER8,
+ .cpu_user_features2 = COMMON_USER2_POWER8,
+ .mmu_features = MMU_FTRS_POWER8,
+ .icache_bsize = 128,
+ .dcache_bsize = 128,
+ .num_pmcs = 6,
+ .pmc_type = PPC_PMC_IBM,
+ .oprofile_cpu_type = "ppc64/power8",
+ .oprofile_type = PPC_OPROFILE_INVALID,
+ .cpu_setup = __setup_cpu_power8,
+ .cpu_restore = __restore_cpu_power8,
+ .flush_tlb = __flush_tlb_power8,
+ .machine_check_early = __machine_check_early_realmode_p8,
+ .platform = "power8",
+ },
{ /* Cell Broadband Engine */
.pvr_mask = 0xffff0000,
.pvr_value = 0x00700000,
@@ -1816,7 +1921,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
.platform = "ppc440",
},
{ /* 464 in APM821xx */
- .pvr_mask = 0xffffff00,
+ .pvr_mask = 0xfffffff0,
.pvr_value = 0x12C41C80,
.cpu_name = "APM821XX",
.cpu_features = CPU_FTRS_44X,
@@ -1954,6 +2059,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
.cpu_user_features = COMMON_USER_BOOKE |
PPC_FEATURE_HAS_SPE_COMP |
PPC_FEATURE_HAS_EFP_SINGLE_COMP,
+ .cpu_user_features2 = PPC_FEATURE2_ISEL,
.mmu_features = MMU_FTR_TYPE_FSL_E,
.icache_bsize = 32,
.dcache_bsize = 32,
@@ -1973,6 +2079,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
PPC_FEATURE_HAS_SPE_COMP |
PPC_FEATURE_HAS_EFP_SINGLE_COMP |
PPC_FEATURE_HAS_EFP_DOUBLE_COMP,
+ .cpu_user_features2 = PPC_FEATURE2_ISEL,
.mmu_features = MMU_FTR_TYPE_FSL_E | MMU_FTR_BIG_PHYS,
.icache_bsize = 32,
.dcache_bsize = 32,
@@ -1989,6 +2096,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
.cpu_name = "e500mc",
.cpu_features = CPU_FTRS_E500MC,
.cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU,
+ .cpu_user_features2 = PPC_FEATURE2_ISEL,
.mmu_features = MMU_FTR_TYPE_FSL_E | MMU_FTR_BIG_PHYS |
MMU_FTR_USE_TLBILX,
.icache_bsize = 64,
@@ -2007,6 +2115,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
.cpu_name = "e5500",
.cpu_features = CPU_FTRS_E5500,
.cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU,
+ .cpu_user_features2 = PPC_FEATURE2_ISEL,
.mmu_features = MMU_FTR_TYPE_FSL_E | MMU_FTR_BIG_PHYS |
MMU_FTR_USE_TLBILX,
.icache_bsize = 64,
@@ -2015,10 +2124,34 @@ static struct cpu_spec __initdata cpu_specs[] = {
.oprofile_cpu_type = "ppc/e500mc",
.oprofile_type = PPC_OPROFILE_FSL_EMB,
.cpu_setup = __setup_cpu_e5500,
+#ifndef CONFIG_PPC32
.cpu_restore = __restore_cpu_e5500,
+#endif
.machine_check = machine_check_e500mc,
.platform = "ppce5500",
},
+ { /* e6500 */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x80400000,
+ .cpu_name = "e6500",
+ .cpu_features = CPU_FTRS_E6500,
+ .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU |
+ PPC_FEATURE_HAS_ALTIVEC_COMP,
+ .cpu_user_features2 = PPC_FEATURE2_ISEL,
+ .mmu_features = MMU_FTR_TYPE_FSL_E | MMU_FTR_BIG_PHYS |
+ MMU_FTR_USE_TLBILX,
+ .icache_bsize = 64,
+ .dcache_bsize = 64,
+ .num_pmcs = 6,
+ .oprofile_cpu_type = "ppc/e6500",
+ .oprofile_type = PPC_OPROFILE_FSL_EMB,
+ .cpu_setup = __setup_cpu_e6500,
+#ifndef CONFIG_PPC32
+ .cpu_restore = __restore_cpu_e6500,
+#endif
+ .machine_check = machine_check_e500mc,
+ .platform = "ppce6500",
+ },
#ifdef CONFIG_PPC32
{ /* default match */
.pvr_mask = 0x00000000,
@@ -2036,44 +2169,6 @@ static struct cpu_spec __initdata cpu_specs[] = {
}
#endif /* CONFIG_PPC32 */
#endif /* CONFIG_E500 */
-
-#ifdef CONFIG_PPC_A2
- { /* Standard A2 (>= DD2) + FPU core */
- .pvr_mask = 0xffff0000,
- .pvr_value = 0x00480000,
- .cpu_name = "A2 (>= DD2)",
- .cpu_features = CPU_FTRS_A2,
- .cpu_user_features = COMMON_USER_PPC64,
- .mmu_features = MMU_FTRS_A2,
- .icache_bsize = 64,
- .dcache_bsize = 64,
- .num_pmcs = 0,
- .cpu_setup = __setup_cpu_a2,
- .cpu_restore = __restore_cpu_a2,
- .machine_check = machine_check_generic,
- .platform = "ppca2",
- },
- { /* This is a default entry to get going, to be replaced by
- * a real one at some stage
- */
-#define CPU_FTRS_BASE_BOOK3E (CPU_FTR_USE_TB | \
- CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_SMT | \
- CPU_FTR_NODSISRALIGN | CPU_FTR_NOEXECUTE)
- .pvr_mask = 0x00000000,
- .pvr_value = 0x00000000,
- .cpu_name = "Book3E",
- .cpu_features = CPU_FTRS_BASE_BOOK3E,
- .cpu_user_features = COMMON_USER_PPC64,
- .mmu_features = MMU_FTR_TYPE_3E | MMU_FTR_USE_TLBILX |
- MMU_FTR_USE_TLBIVAX_BCAST |
- MMU_FTR_LOCK_BCAST_INVAL,
- .icache_bsize = 64,
- .dcache_bsize = 64,
- .num_pmcs = 0,
- .machine_check = machine_check_generic,
- .platform = "power6",
- },
-#endif /* CONFIG_PPC_A2 */
};
static struct cpu_spec the_cpu_spec;
diff --git a/arch/powerpc/kernel/crash.c b/arch/powerpc/kernel/crash.c
index abef75176c0..51dbace3269 100644
--- a/arch/powerpc/kernel/crash.c
+++ b/arch/powerpc/kernel/crash.c
@@ -17,7 +17,6 @@
#include <linux/export.h>
#include <linux/crash_dump.h>
#include <linux/delay.h>
-#include <linux/init.h>
#include <linux/irq.h>
#include <linux/types.h>
@@ -27,8 +26,8 @@
#include <asm/kdump.h>
#include <asm/prom.h>
#include <asm/smp.h>
-#include <asm/system.h>
#include <asm/setjmp.h>
+#include <asm/debug.h>
/*
* The primary CPU waits a while for all secondary CPUs to enter. This is to
@@ -82,7 +81,7 @@ void crash_ipi_callback(struct pt_regs *regs)
}
atomic_inc(&cpus_in_crash);
- smp_mb__after_atomic_inc();
+ smp_mb__after_atomic();
/*
* Starting the kdump boot.
diff --git a/arch/powerpc/kernel/crash_dump.c b/arch/powerpc/kernel/crash_dump.c
index b3ba5163eae..7a13f378ca2 100644
--- a/arch/powerpc/kernel/crash_dump.c
+++ b/arch/powerpc/kernel/crash_dump.c
@@ -69,16 +69,6 @@ void __init setup_kdump_trampoline(void)
}
#endif /* CONFIG_NONSTATIC_KERNEL */
-static int __init parse_savemaxmem(char *p)
-{
- if (p)
- saved_max_pfn = (memparse(p, &p) >> PAGE_SHIFT) - 1;
-
- return 1;
-}
-__setup("savemaxmem=", parse_savemaxmem);
-
-
static size_t copy_oldmem_vaddr(void *vaddr, char *buf, size_t csize,
unsigned long offset, int userbuf)
{
@@ -108,17 +98,19 @@ ssize_t copy_oldmem_page(unsigned long pfn, char *buf,
size_t csize, unsigned long offset, int userbuf)
{
void *vaddr;
+ phys_addr_t paddr;
if (!csize)
return 0;
csize = min_t(size_t, csize, PAGE_SIZE);
+ paddr = pfn << PAGE_SHIFT;
- if ((min_low_pfn < pfn) && (pfn < max_pfn)) {
- vaddr = __va(pfn << PAGE_SHIFT);
+ if (memblock_is_region_memory(paddr, csize)) {
+ vaddr = __va(paddr);
csize = copy_oldmem_vaddr(vaddr, buf, csize, offset, userbuf);
} else {
- vaddr = __ioremap(pfn << PAGE_SHIFT, PAGE_SIZE, 0);
+ vaddr = __ioremap(paddr, PAGE_SIZE, 0);
csize = copy_oldmem_vaddr(vaddr, buf, csize, offset, userbuf);
iounmap(vaddr);
}
@@ -134,15 +126,15 @@ ssize_t copy_oldmem_page(unsigned long pfn, char *buf,
void crash_free_reserved_phys_range(unsigned long begin, unsigned long end)
{
unsigned long addr;
- const u32 *basep, *sizep;
+ const __be32 *basep, *sizep;
unsigned int rtas_start = 0, rtas_end = 0;
basep = of_get_property(rtas.dev, "linux,rtas-base", NULL);
sizep = of_get_property(rtas.dev, "rtas-size", NULL);
if (basep && sizep) {
- rtas_start = *basep;
- rtas_end = *basep + *sizep;
+ rtas_start = be32_to_cpup(basep);
+ rtas_end = rtas_start + be32_to_cpup(sizep);
}
for (addr = begin; addr < end; addr += PAGE_SIZE) {
@@ -150,10 +142,7 @@ void crash_free_reserved_phys_range(unsigned long begin, unsigned long end)
if (addr <= rtas_end && ((addr + PAGE_SIZE) > rtas_start))
continue;
- ClearPageReserved(pfn_to_page(addr >> PAGE_SHIFT));
- init_page_count(pfn_to_page(addr >> PAGE_SHIFT));
- free_page((unsigned long)__va(addr));
- totalram_pages++;
+ free_reserved_page(pfn_to_page(addr >> PAGE_SHIFT));
}
}
#endif
diff --git a/arch/powerpc/kernel/dbell.c b/arch/powerpc/kernel/dbell.c
index 2cc451aaaca..d55c76c571f 100644
--- a/arch/powerpc/kernel/dbell.c
+++ b/arch/powerpc/kernel/dbell.c
@@ -21,14 +21,16 @@
#ifdef CONFIG_SMP
void doorbell_setup_this_cpu(void)
{
- unsigned long tag = mfspr(SPRN_PIR) & 0x3fff;
+ unsigned long tag = mfspr(SPRN_DOORBELL_CPUTAG) & PPC_DBELL_TAG_MASK;
smp_muxed_ipi_set_data(smp_processor_id(), tag);
}
void doorbell_cause_ipi(int cpu, unsigned long data)
{
- ppc_msgsnd(PPC_DBELL, 0, data);
+ /* Order previous accesses vs. msgsnd, which is treated as a store */
+ mb();
+ ppc_msgsnd(PPC_DBELL_MSGTYPE, 0, data);
}
void doorbell_exception(struct pt_regs *regs)
@@ -37,6 +39,10 @@ void doorbell_exception(struct pt_regs *regs)
irq_enter();
+ may_hard_irq_enable();
+
+ __get_cpu_var(irq_stat).doorbell_irqs++;
+
smp_ipi_demux();
irq_exit();
diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c
index 3f6464b4d97..54d0116256f 100644
--- a/arch/powerpc/kernel/dma-iommu.c
+++ b/arch/powerpc/kernel/dma-iommu.c
@@ -17,7 +17,8 @@
* to the dma address (mapping) of the first page.
*/
static void *dma_iommu_alloc_coherent(struct device *dev, size_t size,
- dma_addr_t *dma_handle, gfp_t flag)
+ dma_addr_t *dma_handle, gfp_t flag,
+ struct dma_attrs *attrs)
{
return iommu_alloc_coherent(dev, get_iommu_table_base(dev), size,
dma_handle, dev->coherent_dma_mask, flag,
@@ -25,7 +26,8 @@ static void *dma_iommu_alloc_coherent(struct device *dev, size_t size,
}
static void dma_iommu_free_coherent(struct device *dev, size_t size,
- void *vaddr, dma_addr_t dma_handle)
+ void *vaddr, dma_addr_t dma_handle,
+ struct dma_attrs *attrs)
{
iommu_free_coherent(get_iommu_table_base(dev), size, vaddr, dma_handle);
}
@@ -81,11 +83,10 @@ static int dma_iommu_dma_supported(struct device *dev, u64 mask)
return 0;
}
- if ((tbl->it_offset + tbl->it_size) > (mask >> IOMMU_PAGE_SHIFT)) {
- dev_info(dev, "Warning: IOMMU window too big for device mask\n");
- dev_info(dev, "mask: 0x%08llx, table end: 0x%08lx\n",
- mask, (tbl->it_offset + tbl->it_size) <<
- IOMMU_PAGE_SHIFT);
+ if (tbl->it_offset > (mask >> tbl->it_page_shift)) {
+ dev_info(dev, "Warning: IOMMU offset too big for device mask\n");
+ dev_info(dev, "mask: 0x%08llx, table offset: 0x%08lx\n",
+ mask, tbl->it_offset << tbl->it_page_shift);
return 0;
} else
return 1;
@@ -105,8 +106,9 @@ static u64 dma_iommu_get_required_mask(struct device *dev)
}
struct dma_map_ops dma_iommu_ops = {
- .alloc_coherent = dma_iommu_alloc_coherent,
- .free_coherent = dma_iommu_free_coherent,
+ .alloc = dma_iommu_alloc_coherent,
+ .free = dma_iommu_free_coherent,
+ .mmap = dma_direct_mmap_coherent,
.map_sg = dma_iommu_map_sg,
.unmap_sg = dma_iommu_unmap_sg,
.dma_supported = dma_iommu_dma_supported,
diff --git a/arch/powerpc/kernel/dma-swiotlb.c b/arch/powerpc/kernel/dma-swiotlb.c
index 1ebc9189aad..bd1a2aba599 100644
--- a/arch/powerpc/kernel/dma-swiotlb.c
+++ b/arch/powerpc/kernel/dma-swiotlb.c
@@ -12,6 +12,7 @@
*/
#include <linux/dma-mapping.h>
+#include <linux/memblock.h>
#include <linux/pfn.h>
#include <linux/of_platform.h>
#include <linux/platform_device.h>
@@ -20,7 +21,6 @@
#include <asm/machdep.h>
#include <asm/swiotlb.h>
#include <asm/dma.h>
-#include <asm/abs_addr.h>
unsigned int ppc_swiotlb_enable;
@@ -47,8 +47,9 @@ static u64 swiotlb_powerpc_get_required(struct device *dev)
* for everything else.
*/
struct dma_map_ops swiotlb_dma_ops = {
- .alloc_coherent = dma_direct_alloc_coherent,
- .free_coherent = dma_direct_free_coherent,
+ .alloc = dma_direct_alloc_coherent,
+ .free = dma_direct_free_coherent,
+ .mmap = dma_direct_mmap_coherent,
.map_sg = swiotlb_map_sg_attrs,
.unmap_sg = swiotlb_unmap_sg_attrs,
.dma_supported = swiotlb_dma_supported,
@@ -104,3 +105,23 @@ int __init swiotlb_setup_bus_notifier(void)
&ppc_swiotlb_plat_bus_notifier);
return 0;
}
+
+void swiotlb_detect_4g(void)
+{
+ if ((memblock_end_of_DRAM() - 1) > 0xffffffff)
+ ppc_swiotlb_enable = 1;
+}
+
+static int __init swiotlb_late_init(void)
+{
+ if (ppc_swiotlb_enable) {
+ swiotlb_print_info();
+ set_pci_dma_ops(&swiotlb_dma_ops);
+ ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_swiotlb;
+ } else {
+ swiotlb_free();
+ }
+
+ return 0;
+}
+subsys_initcall(swiotlb_late_init);
diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c
index 7d0233c12ee..ee78f6e49d6 100644
--- a/arch/powerpc/kernel/dma.c
+++ b/arch/powerpc/kernel/dma.c
@@ -11,8 +11,9 @@
#include <linux/gfp.h>
#include <linux/memblock.h>
#include <linux/export.h>
+#include <linux/pci.h>
+#include <asm/vio.h>
#include <asm/bug.h>
-#include <asm/abs_addr.h>
#include <asm/machdep.h>
/*
@@ -26,7 +27,8 @@
void *dma_direct_alloc_coherent(struct device *dev, size_t size,
- dma_addr_t *dma_handle, gfp_t flag)
+ dma_addr_t *dma_handle, gfp_t flag,
+ struct dma_attrs *attrs)
{
void *ret;
#ifdef CONFIG_NOT_COHERENT_CACHE
@@ -47,14 +49,15 @@ void *dma_direct_alloc_coherent(struct device *dev, size_t size,
return NULL;
ret = page_address(page);
memset(ret, 0, size);
- *dma_handle = virt_to_abs(ret) + get_dma_offset(dev);
+ *dma_handle = __pa(ret) + get_dma_offset(dev);
return ret;
#endif
}
void dma_direct_free_coherent(struct device *dev, size_t size,
- void *vaddr, dma_addr_t dma_handle)
+ void *vaddr, dma_addr_t dma_handle,
+ struct dma_attrs *attrs)
{
#ifdef CONFIG_NOT_COHERENT_CACHE
__dma_free_coherent(size, vaddr);
@@ -63,6 +66,24 @@ void dma_direct_free_coherent(struct device *dev, size_t size,
#endif
}
+int dma_direct_mmap_coherent(struct device *dev, struct vm_area_struct *vma,
+ void *cpu_addr, dma_addr_t handle, size_t size,
+ struct dma_attrs *attrs)
+{
+ unsigned long pfn;
+
+#ifdef CONFIG_NOT_COHERENT_CACHE
+ vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
+ pfn = __dma_get_coherent_pfn((unsigned long)cpu_addr);
+#else
+ pfn = page_to_pfn(virt_to_page(cpu_addr));
+#endif
+ return remap_pfn_range(vma, vma->vm_start,
+ pfn + vma->vm_pgoff,
+ vma->vm_end - vma->vm_start,
+ vma->vm_page_prot);
+}
+
static int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl,
int nents, enum dma_data_direction direction,
struct dma_attrs *attrs)
@@ -150,8 +171,9 @@ static inline void dma_direct_sync_single(struct device *dev,
#endif
struct dma_map_ops dma_direct_ops = {
- .alloc_coherent = dma_direct_alloc_coherent,
- .free_coherent = dma_direct_free_coherent,
+ .alloc = dma_direct_alloc_coherent,
+ .free = dma_direct_free_coherent,
+ .mmap = dma_direct_mmap_coherent,
.map_sg = dma_direct_map_sg,
.unmap_sg = dma_direct_unmap_sg,
.dma_supported = dma_direct_dma_supported,
@@ -169,12 +191,10 @@ EXPORT_SYMBOL(dma_direct_ops);
#define PREALLOC_DMA_DEBUG_ENTRIES (1 << 16)
-int dma_set_mask(struct device *dev, u64 dma_mask)
+int __dma_set_mask(struct device *dev, u64 dma_mask)
{
struct dma_map_ops *dma_ops = get_dma_ops(dev);
- if (ppc_md.dma_set_mask)
- return ppc_md.dma_set_mask(dev, dma_mask);
if ((dma_ops != NULL) && (dma_ops->set_dma_mask != NULL))
return dma_ops->set_dma_mask(dev, dma_mask);
if (!dev->dma_mask || !dma_supported(dev, dma_mask))
@@ -182,6 +202,12 @@ int dma_set_mask(struct device *dev, u64 dma_mask)
*dev->dma_mask = dma_mask;
return 0;
}
+int dma_set_mask(struct device *dev, u64 dma_mask)
+{
+ if (ppc_md.dma_set_mask)
+ return ppc_md.dma_set_mask(dev, dma_mask);
+ return __dma_set_mask(dev, dma_mask);
+}
EXPORT_SYMBOL(dma_set_mask);
u64 dma_get_required_mask(struct device *dev)
@@ -203,26 +229,15 @@ EXPORT_SYMBOL_GPL(dma_get_required_mask);
static int __init dma_init(void)
{
- dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES);
+ dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES);
+#ifdef CONFIG_PCI
+ dma_debug_add_bus(&pci_bus_type);
+#endif
+#ifdef CONFIG_IBMVIO
+ dma_debug_add_bus(&vio_bus_type);
+#endif
return 0;
}
fs_initcall(dma_init);
-int dma_mmap_coherent(struct device *dev, struct vm_area_struct *vma,
- void *cpu_addr, dma_addr_t handle, size_t size)
-{
- unsigned long pfn;
-
-#ifdef CONFIG_NOT_COHERENT_CACHE
- vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
- pfn = __dma_get_coherent_pfn((unsigned long)cpu_addr);
-#else
- pfn = page_to_pfn(virt_to_page(cpu_addr));
-#endif
- return remap_pfn_range(vma, vma->vm_start,
- pfn + vma->vm_pgoff,
- vma->vm_end - vma->vm_start,
- vma->vm_page_prot);
-}
-EXPORT_SYMBOL_GPL(dma_mmap_coherent);
diff --git a/arch/powerpc/kernel/e500-pmu.c b/arch/powerpc/kernel/e500-pmu.c
deleted file mode 100644
index cb2e2949c8d..00000000000
--- a/arch/powerpc/kernel/e500-pmu.c
+++ /dev/null
@@ -1,134 +0,0 @@
-/*
- * Performance counter support for e500 family processors.
- *
- * Copyright 2008-2009 Paul Mackerras, IBM Corporation.
- * Copyright 2010 Freescale Semiconductor, Inc.
- *
- * 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.
- */
-#include <linux/string.h>
-#include <linux/perf_event.h>
-#include <asm/reg.h>
-#include <asm/cputable.h>
-
-/*
- * Map of generic hardware event types to hardware events
- * Zero if unsupported
- */
-static int e500_generic_events[] = {
- [PERF_COUNT_HW_CPU_CYCLES] = 1,
- [PERF_COUNT_HW_INSTRUCTIONS] = 2,
- [PERF_COUNT_HW_CACHE_MISSES] = 41, /* Data L1 cache reloads */
- [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 12,
- [PERF_COUNT_HW_BRANCH_MISSES] = 15,
-};
-
-#define C(x) PERF_COUNT_HW_CACHE_##x
-
-/*
- * Table of generalized cache-related events.
- * 0 means not supported, -1 means nonsensical, other values
- * are event codes.
- */
-static int e500_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
- /*
- * D-cache misses are not split into read/write/prefetch;
- * use raw event 41.
- */
- [C(L1D)] = { /* RESULT_ACCESS RESULT_MISS */
- [C(OP_READ)] = { 27, 0 },
- [C(OP_WRITE)] = { 28, 0 },
- [C(OP_PREFETCH)] = { 29, 0 },
- },
- [C(L1I)] = { /* RESULT_ACCESS RESULT_MISS */
- [C(OP_READ)] = { 2, 60 },
- [C(OP_WRITE)] = { -1, -1 },
- [C(OP_PREFETCH)] = { 0, 0 },
- },
- /*
- * Assuming LL means L2, it's not a good match for this model.
- * It allocates only on L1 castout or explicit prefetch, and
- * does not have separate read/write events (but it does have
- * separate instruction/data events).
- */
- [C(LL)] = { /* RESULT_ACCESS RESULT_MISS */
- [C(OP_READ)] = { 0, 0 },
- [C(OP_WRITE)] = { 0, 0 },
- [C(OP_PREFETCH)] = { 0, 0 },
- },
- /*
- * There are data/instruction MMU misses, but that's a miss on
- * the chip's internal level-one TLB which is probably not
- * what the user wants. Instead, unified level-two TLB misses
- * are reported here.
- */
- [C(DTLB)] = { /* RESULT_ACCESS RESULT_MISS */
- [C(OP_READ)] = { 26, 66 },
- [C(OP_WRITE)] = { -1, -1 },
- [C(OP_PREFETCH)] = { -1, -1 },
- },
- [C(BPU)] = { /* RESULT_ACCESS RESULT_MISS */
- [C(OP_READ)] = { 12, 15 },
- [C(OP_WRITE)] = { -1, -1 },
- [C(OP_PREFETCH)] = { -1, -1 },
- },
- [C(NODE)] = { /* RESULT_ACCESS RESULT_MISS */
- [C(OP_READ)] = { -1, -1 },
- [C(OP_WRITE)] = { -1, -1 },
- [C(OP_PREFETCH)] = { -1, -1 },
- },
-};
-
-static int num_events = 128;
-
-/* Upper half of event id is PMLCb, for threshold events */
-static u64 e500_xlate_event(u64 event_id)
-{
- u32 event_low = (u32)event_id;
- u64 ret;
-
- if (event_low >= num_events)
- return 0;
-
- ret = FSL_EMB_EVENT_VALID;
-
- if (event_low >= 76 && event_low <= 81) {
- ret |= FSL_EMB_EVENT_RESTRICTED;
- ret |= event_id &
- (FSL_EMB_EVENT_THRESHMUL | FSL_EMB_EVENT_THRESH);
- } else if (event_id &
- (FSL_EMB_EVENT_THRESHMUL | FSL_EMB_EVENT_THRESH)) {
- /* Threshold requested on non-threshold event */
- return 0;
- }
-
- return ret;
-}
-
-static struct fsl_emb_pmu e500_pmu = {
- .name = "e500 family",
- .n_counter = 4,
- .n_restricted = 2,
- .xlate_event = e500_xlate_event,
- .n_generic = ARRAY_SIZE(e500_generic_events),
- .generic_events = e500_generic_events,
- .cache_events = &e500_cache_events,
-};
-
-static int init_e500_pmu(void)
-{
- if (!cur_cpu_spec->oprofile_cpu_type)
- return -ENODEV;
-
- if (!strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc/e500mc"))
- num_events = 256;
- else if (strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc/e500"))
- return -ENODEV;
-
- return register_fsl_emb_pmu(&e500_pmu);
-}
-
-early_initcall(init_e500_pmu);
diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
new file mode 100644
index 00000000000..86e25702aac
--- /dev/null
+++ b/arch/powerpc/kernel/eeh.c
@@ -0,0 +1,1183 @@
+/*
+ * Copyright IBM Corporation 2001, 2005, 2006
+ * Copyright Dave Engebretsen & Todd Inglett 2001
+ * Copyright Linas Vepstas 2005, 2006
+ * Copyright 2001-2012 IBM Corporation.
+ *
+ * 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
+ *
+ * Please address comments and feedback to Linas Vepstas <linas@austin.ibm.com>
+ */
+
+#include <linux/delay.h>
+#include <linux/debugfs.h>
+#include <linux/sched.h>
+#include <linux/init.h>
+#include <linux/list.h>
+#include <linux/pci.h>
+#include <linux/proc_fs.h>
+#include <linux/rbtree.h>
+#include <linux/reboot.h>
+#include <linux/seq_file.h>
+#include <linux/spinlock.h>
+#include <linux/export.h>
+#include <linux/of.h>
+
+#include <linux/atomic.h>
+#include <asm/debug.h>
+#include <asm/eeh.h>
+#include <asm/eeh_event.h>
+#include <asm/io.h>
+#include <asm/machdep.h>
+#include <asm/ppc-pci.h>
+#include <asm/rtas.h>
+
+
+/** Overview:
+ * EEH, or "Extended Error Handling" is a PCI bridge technology for
+ * dealing with PCI bus errors that can't be dealt with within the
+ * usual PCI framework, except by check-stopping the CPU. Systems
+ * that are designed for high-availability/reliability cannot afford
+ * to crash due to a "mere" PCI error, thus the need for EEH.
+ * An EEH-capable bridge operates by converting a detected error
+ * into a "slot freeze", taking the PCI adapter off-line, making
+ * the slot behave, from the OS'es point of view, as if the slot
+ * were "empty": all reads return 0xff's and all writes are silently
+ * ignored. EEH slot isolation events can be triggered by parity
+ * errors on the address or data busses (e.g. during posted writes),
+ * which in turn might be caused by low voltage on the bus, dust,
+ * vibration, humidity, radioactivity or plain-old failed hardware.
+ *
+ * Note, however, that one of the leading causes of EEH slot
+ * freeze events are buggy device drivers, buggy device microcode,
+ * or buggy device hardware. This is because any attempt by the
+ * device to bus-master data to a memory address that is not
+ * assigned to the device will trigger a slot freeze. (The idea
+ * is to prevent devices-gone-wild from corrupting system memory).
+ * Buggy hardware/drivers will have a miserable time co-existing
+ * with EEH.
+ *
+ * Ideally, a PCI device driver, when suspecting that an isolation
+ * event has occurred (e.g. by reading 0xff's), will then ask EEH
+ * whether this is the case, and then take appropriate steps to
+ * reset the PCI slot, the PCI device, and then resume operations.
+ * However, until that day, the checking is done here, with the
+ * eeh_check_failure() routine embedded in the MMIO macros. If
+ * the slot is found to be isolated, an "EEH Event" is synthesized
+ * and sent out for processing.
+ */
+
+/* If a device driver keeps reading an MMIO register in an interrupt
+ * handler after a slot isolation event, it might be broken.
+ * This sets the threshold for how many read attempts we allow
+ * before printing an error message.
+ */
+#define EEH_MAX_FAILS 2100000
+
+/* Time to wait for a PCI slot to report status, in milliseconds */
+#define PCI_BUS_RESET_WAIT_MSEC (5*60*1000)
+
+/*
+ * EEH probe mode support, which is part of the flags,
+ * is to support multiple platforms for EEH. Some platforms
+ * like pSeries do PCI emunation based on device tree.
+ * However, other platforms like powernv probe PCI devices
+ * from hardware. The flag is used to distinguish that.
+ * In addition, struct eeh_ops::probe would be invoked for
+ * particular OF node or PCI device so that the corresponding
+ * PE would be created there.
+ */
+int eeh_subsystem_flags;
+EXPORT_SYMBOL(eeh_subsystem_flags);
+
+/* Platform dependent EEH operations */
+struct eeh_ops *eeh_ops = NULL;
+
+/* Lock to avoid races due to multiple reports of an error */
+DEFINE_RAW_SPINLOCK(confirm_error_lock);
+
+/* Buffer for reporting pci register dumps. Its here in BSS, and
+ * not dynamically alloced, so that it ends up in RMO where RTAS
+ * can access it.
+ */
+#define EEH_PCI_REGS_LOG_LEN 4096
+static unsigned char pci_regs_buf[EEH_PCI_REGS_LOG_LEN];
+
+/*
+ * The struct is used to maintain the EEH global statistic
+ * information. Besides, the EEH global statistics will be
+ * exported to user space through procfs
+ */
+struct eeh_stats {
+ u64 no_device; /* PCI device not found */
+ u64 no_dn; /* OF node not found */
+ u64 no_cfg_addr; /* Config address not found */
+ u64 ignored_check; /* EEH check skipped */
+ u64 total_mmio_ffs; /* Total EEH checks */
+ u64 false_positives; /* Unnecessary EEH checks */
+ u64 slot_resets; /* PE reset */
+};
+
+static struct eeh_stats eeh_stats;
+
+#define IS_BRIDGE(class_code) (((class_code)<<16) == PCI_BASE_CLASS_BRIDGE)
+
+static int __init eeh_setup(char *str)
+{
+ if (!strcmp(str, "off"))
+ eeh_subsystem_flags |= EEH_FORCE_DISABLED;
+
+ return 1;
+}
+__setup("eeh=", eeh_setup);
+
+/**
+ * eeh_gather_pci_data - Copy assorted PCI config space registers to buff
+ * @edev: device to report data for
+ * @buf: point to buffer in which to log
+ * @len: amount of room in buffer
+ *
+ * This routine captures assorted PCI configuration space data,
+ * and puts them into a buffer for RTAS error logging.
+ */
+static size_t eeh_gather_pci_data(struct eeh_dev *edev, char * buf, size_t len)
+{
+ struct device_node *dn = eeh_dev_to_of_node(edev);
+ u32 cfg;
+ int cap, i;
+ int n = 0;
+
+ n += scnprintf(buf+n, len-n, "%s\n", dn->full_name);
+ pr_warn("EEH: of node=%s\n", dn->full_name);
+
+ eeh_ops->read_config(dn, PCI_VENDOR_ID, 4, &cfg);
+ n += scnprintf(buf+n, len-n, "dev/vend:%08x\n", cfg);
+ pr_warn("EEH: PCI device/vendor: %08x\n", cfg);
+
+ eeh_ops->read_config(dn, PCI_COMMAND, 4, &cfg);
+ n += scnprintf(buf+n, len-n, "cmd/stat:%x\n", cfg);
+ pr_warn("EEH: PCI cmd/status register: %08x\n", cfg);
+
+ /* Gather bridge-specific registers */
+ if (edev->mode & EEH_DEV_BRIDGE) {
+ eeh_ops->read_config(dn, PCI_SEC_STATUS, 2, &cfg);
+ n += scnprintf(buf+n, len-n, "sec stat:%x\n", cfg);
+ pr_warn("EEH: Bridge secondary status: %04x\n", cfg);
+
+ eeh_ops->read_config(dn, PCI_BRIDGE_CONTROL, 2, &cfg);
+ n += scnprintf(buf+n, len-n, "brdg ctl:%x\n", cfg);
+ pr_warn("EEH: Bridge control: %04x\n", cfg);
+ }
+
+ /* Dump out the PCI-X command and status regs */
+ cap = edev->pcix_cap;
+ if (cap) {
+ eeh_ops->read_config(dn, cap, 4, &cfg);
+ n += scnprintf(buf+n, len-n, "pcix-cmd:%x\n", cfg);
+ pr_warn("EEH: PCI-X cmd: %08x\n", cfg);
+
+ eeh_ops->read_config(dn, cap+4, 4, &cfg);
+ n += scnprintf(buf+n, len-n, "pcix-stat:%x\n", cfg);
+ pr_warn("EEH: PCI-X status: %08x\n", cfg);
+ }
+
+ /* If PCI-E capable, dump PCI-E cap 10 */
+ cap = edev->pcie_cap;
+ if (cap) {
+ n += scnprintf(buf+n, len-n, "pci-e cap10:\n");
+ pr_warn("EEH: PCI-E capabilities and status follow:\n");
+
+ for (i=0; i<=8; i++) {
+ eeh_ops->read_config(dn, cap+4*i, 4, &cfg);
+ n += scnprintf(buf+n, len-n, "%02x:%x\n", 4*i, cfg);
+ pr_warn("EEH: PCI-E %02x: %08x\n", i, cfg);
+ }
+ }
+
+ /* If AER capable, dump it */
+ cap = edev->aer_cap;
+ if (cap) {
+ n += scnprintf(buf+n, len-n, "pci-e AER:\n");
+ pr_warn("EEH: PCI-E AER capability register set follows:\n");
+
+ for (i=0; i<14; i++) {
+ eeh_ops->read_config(dn, cap+4*i, 4, &cfg);
+ n += scnprintf(buf+n, len-n, "%02x:%x\n", 4*i, cfg);
+ pr_warn("EEH: PCI-E AER %02x: %08x\n", i, cfg);
+ }
+ }
+
+ return n;
+}
+
+/**
+ * eeh_slot_error_detail - Generate combined log including driver log and error log
+ * @pe: EEH PE
+ * @severity: temporary or permanent error log
+ *
+ * This routine should be called to generate the combined log, which
+ * is comprised of driver log and error log. The driver log is figured
+ * out from the config space of the corresponding PCI device, while
+ * the error log is fetched through platform dependent function call.
+ */
+void eeh_slot_error_detail(struct eeh_pe *pe, int severity)
+{
+ size_t loglen = 0;
+ struct eeh_dev *edev, *tmp;
+
+ /*
+ * When the PHB is fenced or dead, it's pointless to collect
+ * the data from PCI config space because it should return
+ * 0xFF's. For ER, we still retrieve the data from the PCI
+ * config space.
+ *
+ * For pHyp, we have to enable IO for log retrieval. Otherwise,
+ * 0xFF's is always returned from PCI config space.
+ */
+ if (!(pe->type & EEH_PE_PHB)) {
+ if (eeh_probe_mode_devtree())
+ eeh_pci_enable(pe, EEH_OPT_THAW_MMIO);
+ eeh_ops->configure_bridge(pe);
+ eeh_pe_restore_bars(pe);
+
+ pci_regs_buf[0] = 0;
+ eeh_pe_for_each_dev(pe, edev, tmp) {
+ loglen += eeh_gather_pci_data(edev, pci_regs_buf + loglen,
+ EEH_PCI_REGS_LOG_LEN - loglen);
+ }
+ }
+
+ eeh_ops->get_log(pe, severity, pci_regs_buf, loglen);
+}
+
+/**
+ * eeh_token_to_phys - Convert EEH address token to phys address
+ * @token: I/O token, should be address in the form 0xA....
+ *
+ * This routine should be called to convert virtual I/O address
+ * to physical one.
+ */
+static inline unsigned long eeh_token_to_phys(unsigned long token)
+{
+ pte_t *ptep;
+ unsigned long pa;
+ int hugepage_shift;
+
+ /*
+ * We won't find hugepages here, iomem
+ */
+ ptep = find_linux_pte_or_hugepte(init_mm.pgd, token, &hugepage_shift);
+ if (!ptep)
+ return token;
+ WARN_ON(hugepage_shift);
+ pa = pte_pfn(*ptep) << PAGE_SHIFT;
+
+ return pa | (token & (PAGE_SIZE-1));
+}
+
+/*
+ * On PowerNV platform, we might already have fenced PHB there.
+ * For that case, it's meaningless to recover frozen PE. Intead,
+ * We have to handle fenced PHB firstly.
+ */
+static int eeh_phb_check_failure(struct eeh_pe *pe)
+{
+ struct eeh_pe *phb_pe;
+ unsigned long flags;
+ int ret;
+
+ if (!eeh_probe_mode_dev())
+ return -EPERM;
+
+ /* Find the PHB PE */
+ phb_pe = eeh_phb_pe_get(pe->phb);
+ if (!phb_pe) {
+ pr_warning("%s Can't find PE for PHB#%d\n",
+ __func__, pe->phb->global_number);
+ return -EEXIST;
+ }
+
+ /* If the PHB has been in problematic state */
+ eeh_serialize_lock(&flags);
+ if (phb_pe->state & EEH_PE_ISOLATED) {
+ ret = 0;
+ goto out;
+ }
+
+ /* Check PHB state */
+ ret = eeh_ops->get_state(phb_pe, NULL);
+ if ((ret < 0) ||
+ (ret == EEH_STATE_NOT_SUPPORT) ||
+ (ret & (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE)) ==
+ (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE)) {
+ ret = 0;
+ goto out;
+ }
+
+ /* Isolate the PHB and send event */
+ eeh_pe_state_mark(phb_pe, EEH_PE_ISOLATED);
+ eeh_serialize_unlock(flags);
+
+ pr_err("EEH: PHB#%x failure detected, location: %s\n",
+ phb_pe->phb->global_number, eeh_pe_loc_get(phb_pe));
+ dump_stack();
+ eeh_send_failure_event(phb_pe);
+
+ return 1;
+out:
+ eeh_serialize_unlock(flags);
+ return ret;
+}
+
+/**
+ * eeh_dev_check_failure - Check if all 1's data is due to EEH slot freeze
+ * @edev: eeh device
+ *
+ * Check for an EEH failure for the given device node. Call this
+ * routine if the result of a read was all 0xff's and you want to
+ * find out if this is due to an EEH slot freeze. This routine
+ * will query firmware for the EEH status.
+ *
+ * Returns 0 if there has not been an EEH error; otherwise returns
+ * a non-zero value and queues up a slot isolation event notification.
+ *
+ * It is safe to call this routine in an interrupt context.
+ */
+int eeh_dev_check_failure(struct eeh_dev *edev)
+{
+ int ret;
+ int active_flags = (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE);
+ unsigned long flags;
+ struct device_node *dn;
+ struct pci_dev *dev;
+ struct eeh_pe *pe, *parent_pe, *phb_pe;
+ int rc = 0;
+ const char *location;
+
+ eeh_stats.total_mmio_ffs++;
+
+ if (!eeh_enabled())
+ return 0;
+
+ if (!edev) {
+ eeh_stats.no_dn++;
+ return 0;
+ }
+ dn = eeh_dev_to_of_node(edev);
+ dev = eeh_dev_to_pci_dev(edev);
+ pe = edev->pe;
+
+ /* Access to IO BARs might get this far and still not want checking. */
+ if (!pe) {
+ eeh_stats.ignored_check++;
+ pr_debug("EEH: Ignored check for %s %s\n",
+ eeh_pci_name(dev), dn->full_name);
+ return 0;
+ }
+
+ if (!pe->addr && !pe->config_addr) {
+ eeh_stats.no_cfg_addr++;
+ return 0;
+ }
+
+ /*
+ * On PowerNV platform, we might already have fenced PHB
+ * there and we need take care of that firstly.
+ */
+ ret = eeh_phb_check_failure(pe);
+ if (ret > 0)
+ return ret;
+
+ /* If we already have a pending isolation event for this
+ * slot, we know it's bad already, we don't need to check.
+ * Do this checking under a lock; as multiple PCI devices
+ * in one slot might report errors simultaneously, and we
+ * only want one error recovery routine running.
+ */
+ eeh_serialize_lock(&flags);
+ rc = 1;
+ if (pe->state & EEH_PE_ISOLATED) {
+ pe->check_count++;
+ if (pe->check_count % EEH_MAX_FAILS == 0) {
+ location = of_get_property(dn, "ibm,loc-code", NULL);
+ printk(KERN_ERR "EEH: %d reads ignored for recovering device at "
+ "location=%s driver=%s pci addr=%s\n",
+ pe->check_count, location,
+ eeh_driver_name(dev), eeh_pci_name(dev));
+ printk(KERN_ERR "EEH: Might be infinite loop in %s driver\n",
+ eeh_driver_name(dev));
+ dump_stack();
+ }
+ goto dn_unlock;
+ }
+
+ /*
+ * Now test for an EEH failure. This is VERY expensive.
+ * Note that the eeh_config_addr may be a parent device
+ * in the case of a device behind a bridge, or it may be
+ * function zero of a multi-function device.
+ * In any case they must share a common PHB.
+ */
+ ret = eeh_ops->get_state(pe, NULL);
+
+ /* Note that config-io to empty slots may fail;
+ * they are empty when they don't have children.
+ * We will punt with the following conditions: Failure to get
+ * PE's state, EEH not support and Permanently unavailable
+ * state, PE is in good state.
+ */
+ if ((ret < 0) ||
+ (ret == EEH_STATE_NOT_SUPPORT) ||
+ ((ret & active_flags) == active_flags)) {
+ eeh_stats.false_positives++;
+ pe->false_positives++;
+ rc = 0;
+ goto dn_unlock;
+ }
+
+ /*
+ * It should be corner case that the parent PE has been
+ * put into frozen state as well. We should take care
+ * that at first.
+ */
+ parent_pe = pe->parent;
+ while (parent_pe) {
+ /* Hit the ceiling ? */
+ if (parent_pe->type & EEH_PE_PHB)
+ break;
+
+ /* Frozen parent PE ? */
+ ret = eeh_ops->get_state(parent_pe, NULL);
+ if (ret > 0 &&
+ (ret & active_flags) != active_flags)
+ pe = parent_pe;
+
+ /* Next parent level */
+ parent_pe = parent_pe->parent;
+ }
+
+ eeh_stats.slot_resets++;
+
+ /* Avoid repeated reports of this failure, including problems
+ * with other functions on this device, and functions under
+ * bridges.
+ */
+ eeh_pe_state_mark(pe, EEH_PE_ISOLATED);
+ eeh_serialize_unlock(flags);
+
+ /* Most EEH events are due to device driver bugs. Having
+ * a stack trace will help the device-driver authors figure
+ * out what happened. So print that out.
+ */
+ phb_pe = eeh_phb_pe_get(pe->phb);
+ pr_err("EEH: Frozen PHB#%x-PE#%x detected\n",
+ pe->phb->global_number, pe->addr);
+ pr_err("EEH: PE location: %s, PHB location: %s\n",
+ eeh_pe_loc_get(pe), eeh_pe_loc_get(phb_pe));
+ dump_stack();
+
+ eeh_send_failure_event(pe);
+
+ return 1;
+
+dn_unlock:
+ eeh_serialize_unlock(flags);
+ return rc;
+}
+
+EXPORT_SYMBOL_GPL(eeh_dev_check_failure);
+
+/**
+ * eeh_check_failure - Check if all 1's data is due to EEH slot freeze
+ * @token: I/O token, should be address in the form 0xA....
+ * @val: value, should be all 1's (XXX why do we need this arg??)
+ *
+ * Check for an EEH failure at the given token address. Call this
+ * routine if the result of a read was all 0xff's and you want to
+ * find out if this is due to an EEH slot freeze event. This routine
+ * will query firmware for the EEH status.
+ *
+ * Note this routine is safe to call in an interrupt context.
+ */
+unsigned long eeh_check_failure(const volatile void __iomem *token, unsigned long val)
+{
+ unsigned long addr;
+ struct eeh_dev *edev;
+
+ /* Finding the phys addr + pci device; this is pretty quick. */
+ addr = eeh_token_to_phys((unsigned long __force) token);
+ edev = eeh_addr_cache_get_dev(addr);
+ if (!edev) {
+ eeh_stats.no_device++;
+ return val;
+ }
+
+ eeh_dev_check_failure(edev);
+ return val;
+}
+
+EXPORT_SYMBOL(eeh_check_failure);
+
+
+/**
+ * eeh_pci_enable - Enable MMIO or DMA transfers for this slot
+ * @pe: EEH PE
+ *
+ * This routine should be called to reenable frozen MMIO or DMA
+ * so that it would work correctly again. It's useful while doing
+ * recovery or log collection on the indicated device.
+ */
+int eeh_pci_enable(struct eeh_pe *pe, int function)
+{
+ int rc, flags = (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE);
+
+ /*
+ * pHyp doesn't allow to enable IO or DMA on unfrozen PE.
+ * Also, it's pointless to enable them on unfrozen PE. So
+ * we have the check here.
+ */
+ if (function == EEH_OPT_THAW_MMIO ||
+ function == EEH_OPT_THAW_DMA) {
+ rc = eeh_ops->get_state(pe, NULL);
+ if (rc < 0)
+ return rc;
+
+ /* Needn't to enable or already enabled */
+ if ((rc == EEH_STATE_NOT_SUPPORT) ||
+ ((rc & flags) == flags))
+ return 0;
+ }
+
+ rc = eeh_ops->set_option(pe, function);
+ if (rc)
+ pr_warn("%s: Unexpected state change %d on "
+ "PHB#%d-PE#%x, err=%d\n",
+ __func__, function, pe->phb->global_number,
+ pe->addr, rc);
+
+ rc = eeh_ops->wait_state(pe, PCI_BUS_RESET_WAIT_MSEC);
+ if (rc <= 0)
+ return rc;
+
+ if ((function == EEH_OPT_THAW_MMIO) &&
+ (rc & EEH_STATE_MMIO_ENABLED))
+ return 0;
+
+ if ((function == EEH_OPT_THAW_DMA) &&
+ (rc & EEH_STATE_DMA_ENABLED))
+ return 0;
+
+ return rc;
+}
+
+/**
+ * pcibios_set_pcie_slot_reset - Set PCI-E reset state
+ * @dev: pci device struct
+ * @state: reset state to enter
+ *
+ * Return value:
+ * 0 if success
+ */
+int pcibios_set_pcie_reset_state(struct pci_dev *dev, enum pcie_reset_state state)
+{
+ struct eeh_dev *edev = pci_dev_to_eeh_dev(dev);
+ struct eeh_pe *pe = edev->pe;
+
+ if (!pe) {
+ pr_err("%s: No PE found on PCI device %s\n",
+ __func__, pci_name(dev));
+ return -EINVAL;
+ }
+
+ switch (state) {
+ case pcie_deassert_reset:
+ eeh_ops->reset(pe, EEH_RESET_DEACTIVATE);
+ break;
+ case pcie_hot_reset:
+ eeh_ops->reset(pe, EEH_RESET_HOT);
+ break;
+ case pcie_warm_reset:
+ eeh_ops->reset(pe, EEH_RESET_FUNDAMENTAL);
+ break;
+ default:
+ return -EINVAL;
+ };
+
+ return 0;
+}
+
+/**
+ * eeh_set_pe_freset - Check the required reset for the indicated device
+ * @data: EEH device
+ * @flag: return value
+ *
+ * Each device might have its preferred reset type: fundamental or
+ * hot reset. The routine is used to collected the information for
+ * the indicated device and its children so that the bunch of the
+ * devices could be reset properly.
+ */
+static void *eeh_set_dev_freset(void *data, void *flag)
+{
+ struct pci_dev *dev;
+ unsigned int *freset = (unsigned int *)flag;
+ struct eeh_dev *edev = (struct eeh_dev *)data;
+
+ dev = eeh_dev_to_pci_dev(edev);
+ if (dev)
+ *freset |= dev->needs_freset;
+
+ return NULL;
+}
+
+/**
+ * eeh_reset_pe_once - Assert the pci #RST line for 1/4 second
+ * @pe: EEH PE
+ *
+ * Assert the PCI #RST line for 1/4 second.
+ */
+static void eeh_reset_pe_once(struct eeh_pe *pe)
+{
+ unsigned int freset = 0;
+
+ /* Determine type of EEH reset required for
+ * Partitionable Endpoint, a hot-reset (1)
+ * or a fundamental reset (3).
+ * A fundamental reset required by any device under
+ * Partitionable Endpoint trumps hot-reset.
+ */
+ eeh_pe_dev_traverse(pe, eeh_set_dev_freset, &freset);
+
+ if (freset)
+ eeh_ops->reset(pe, EEH_RESET_FUNDAMENTAL);
+ else
+ eeh_ops->reset(pe, EEH_RESET_HOT);
+
+ eeh_ops->reset(pe, EEH_RESET_DEACTIVATE);
+}
+
+/**
+ * eeh_reset_pe - Reset the indicated PE
+ * @pe: EEH PE
+ *
+ * This routine should be called to reset indicated device, including
+ * PE. A PE might include multiple PCI devices and sometimes PCI bridges
+ * might be involved as well.
+ */
+int eeh_reset_pe(struct eeh_pe *pe)
+{
+ int flags = (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE);
+ int i, rc;
+
+ /* Take three shots at resetting the bus */
+ for (i=0; i<3; i++) {
+ eeh_reset_pe_once(pe);
+
+ /*
+ * EEH_PE_ISOLATED is expected to be removed after
+ * BAR restore.
+ */
+ rc = eeh_ops->wait_state(pe, PCI_BUS_RESET_WAIT_MSEC);
+ if ((rc & flags) == flags)
+ return 0;
+
+ if (rc < 0) {
+ pr_err("%s: Unrecoverable slot failure on PHB#%d-PE#%x",
+ __func__, pe->phb->global_number, pe->addr);
+ return -1;
+ }
+ pr_err("EEH: bus reset %d failed on PHB#%d-PE#%x, rc=%d\n",
+ i+1, pe->phb->global_number, pe->addr, rc);
+ }
+
+ return -1;
+}
+
+/**
+ * eeh_save_bars - Save device bars
+ * @edev: PCI device associated EEH device
+ *
+ * Save the values of the device bars. Unlike the restore
+ * routine, this routine is *not* recursive. This is because
+ * PCI devices are added individually; but, for the restore,
+ * an entire slot is reset at a time.
+ */
+void eeh_save_bars(struct eeh_dev *edev)
+{
+ int i;
+ struct device_node *dn;
+
+ if (!edev)
+ return;
+ dn = eeh_dev_to_of_node(edev);
+
+ for (i = 0; i < 16; i++)
+ eeh_ops->read_config(dn, i * 4, 4, &edev->config_space[i]);
+
+ /*
+ * For PCI bridges including root port, we need enable bus
+ * master explicitly. Otherwise, it can't fetch IODA table
+ * entries correctly. So we cache the bit in advance so that
+ * we can restore it after reset, either PHB range or PE range.
+ */
+ if (edev->mode & EEH_DEV_BRIDGE)
+ edev->config_space[1] |= PCI_COMMAND_MASTER;
+}
+
+/**
+ * eeh_ops_register - Register platform dependent EEH operations
+ * @ops: platform dependent EEH operations
+ *
+ * Register the platform dependent EEH operation callback
+ * functions. The platform should call this function before
+ * any other EEH operations.
+ */
+int __init eeh_ops_register(struct eeh_ops *ops)
+{
+ if (!ops->name) {
+ pr_warning("%s: Invalid EEH ops name for %p\n",
+ __func__, ops);
+ return -EINVAL;
+ }
+
+ if (eeh_ops && eeh_ops != ops) {
+ pr_warning("%s: EEH ops of platform %s already existing (%s)\n",
+ __func__, eeh_ops->name, ops->name);
+ return -EEXIST;
+ }
+
+ eeh_ops = ops;
+
+ return 0;
+}
+
+/**
+ * eeh_ops_unregister - Unreigster platform dependent EEH operations
+ * @name: name of EEH platform operations
+ *
+ * Unregister the platform dependent EEH operation callback
+ * functions.
+ */
+int __exit eeh_ops_unregister(const char *name)
+{
+ if (!name || !strlen(name)) {
+ pr_warning("%s: Invalid EEH ops name\n",
+ __func__);
+ return -EINVAL;
+ }
+
+ if (eeh_ops && !strcmp(eeh_ops->name, name)) {
+ eeh_ops = NULL;
+ return 0;
+ }
+
+ return -EEXIST;
+}
+
+static int eeh_reboot_notifier(struct notifier_block *nb,
+ unsigned long action, void *unused)
+{
+ eeh_set_enable(false);
+ return NOTIFY_DONE;
+}
+
+static struct notifier_block eeh_reboot_nb = {
+ .notifier_call = eeh_reboot_notifier,
+};
+
+/**
+ * eeh_init - EEH initialization
+ *
+ * Initialize EEH by trying to enable it for all of the adapters in the system.
+ * As a side effect we can determine here if eeh is supported at all.
+ * Note that we leave EEH on so failed config cycles won't cause a machine
+ * check. If a user turns off EEH for a particular adapter they are really
+ * telling Linux to ignore errors. Some hardware (e.g. POWER5) won't
+ * grant access to a slot if EEH isn't enabled, and so we always enable
+ * EEH for all slots/all devices.
+ *
+ * The eeh-force-off option disables EEH checking globally, for all slots.
+ * Even if force-off is set, the EEH hardware is still enabled, so that
+ * newer systems can boot.
+ */
+int eeh_init(void)
+{
+ struct pci_controller *hose, *tmp;
+ struct device_node *phb;
+ static int cnt = 0;
+ int ret = 0;
+
+ /*
+ * We have to delay the initialization on PowerNV after
+ * the PCI hierarchy tree has been built because the PEs
+ * are figured out based on PCI devices instead of device
+ * tree nodes
+ */
+ if (machine_is(powernv) && cnt++ <= 0)
+ return ret;
+
+ /* Register reboot notifier */
+ ret = register_reboot_notifier(&eeh_reboot_nb);
+ if (ret) {
+ pr_warn("%s: Failed to register notifier (%d)\n",
+ __func__, ret);
+ return ret;
+ }
+
+ /* call platform initialization function */
+ if (!eeh_ops) {
+ pr_warning("%s: Platform EEH operation not found\n",
+ __func__);
+ return -EEXIST;
+ } else if ((ret = eeh_ops->init())) {
+ pr_warning("%s: Failed to call platform init function (%d)\n",
+ __func__, ret);
+ return ret;
+ }
+
+ /* Initialize EEH event */
+ ret = eeh_event_init();
+ if (ret)
+ return ret;
+
+ /* Enable EEH for all adapters */
+ if (eeh_probe_mode_devtree()) {
+ list_for_each_entry_safe(hose, tmp,
+ &hose_list, list_node) {
+ phb = hose->dn;
+ traverse_pci_devices(phb, eeh_ops->of_probe, NULL);
+ }
+ } else if (eeh_probe_mode_dev()) {
+ list_for_each_entry_safe(hose, tmp,
+ &hose_list, list_node)
+ pci_walk_bus(hose->bus, eeh_ops->dev_probe, NULL);
+ } else {
+ pr_warn("%s: Invalid probe mode %x",
+ __func__, eeh_subsystem_flags);
+ return -EINVAL;
+ }
+
+ /*
+ * Call platform post-initialization. Actually, It's good chance
+ * to inform platform that EEH is ready to supply service if the
+ * I/O cache stuff has been built up.
+ */
+ if (eeh_ops->post_init) {
+ ret = eeh_ops->post_init();
+ if (ret)
+ return ret;
+ }
+
+ if (eeh_enabled())
+ pr_info("EEH: PCI Enhanced I/O Error Handling Enabled\n");
+ else
+ pr_warning("EEH: No capable adapters found\n");
+
+ return ret;
+}
+
+core_initcall_sync(eeh_init);
+
+/**
+ * eeh_add_device_early - Enable EEH for the indicated device_node
+ * @dn: device node for which to set up EEH
+ *
+ * This routine must be used to perform EEH initialization for PCI
+ * devices that were added after system boot (e.g. hotplug, dlpar).
+ * This routine must be called before any i/o is performed to the
+ * adapter (inluding any config-space i/o).
+ * Whether this actually enables EEH or not for this device depends
+ * on the CEC architecture, type of the device, on earlier boot
+ * command-line arguments & etc.
+ */
+void eeh_add_device_early(struct device_node *dn)
+{
+ struct pci_controller *phb;
+
+ /*
+ * If we're doing EEH probe based on PCI device, we
+ * would delay the probe until late stage because
+ * the PCI device isn't available this moment.
+ */
+ if (!eeh_probe_mode_devtree())
+ return;
+
+ if (!of_node_to_eeh_dev(dn))
+ return;
+ phb = of_node_to_eeh_dev(dn)->phb;
+
+ /* USB Bus children of PCI devices will not have BUID's */
+ if (NULL == phb || 0 == phb->buid)
+ return;
+
+ eeh_ops->of_probe(dn, NULL);
+}
+
+/**
+ * eeh_add_device_tree_early - Enable EEH for the indicated device
+ * @dn: device node
+ *
+ * This routine must be used to perform EEH initialization for the
+ * indicated PCI device that was added after system boot (e.g.
+ * hotplug, dlpar).
+ */
+void eeh_add_device_tree_early(struct device_node *dn)
+{
+ struct device_node *sib;
+
+ for_each_child_of_node(dn, sib)
+ eeh_add_device_tree_early(sib);
+ eeh_add_device_early(dn);
+}
+EXPORT_SYMBOL_GPL(eeh_add_device_tree_early);
+
+/**
+ * eeh_add_device_late - Perform EEH initialization for the indicated pci device
+ * @dev: pci device for which to set up EEH
+ *
+ * This routine must be used to complete EEH initialization for PCI
+ * devices that were added after system boot (e.g. hotplug, dlpar).
+ */
+void eeh_add_device_late(struct pci_dev *dev)
+{
+ struct device_node *dn;
+ struct eeh_dev *edev;
+
+ if (!dev || !eeh_enabled())
+ return;
+
+ pr_debug("EEH: Adding device %s\n", pci_name(dev));
+
+ dn = pci_device_to_OF_node(dev);
+ edev = of_node_to_eeh_dev(dn);
+ if (edev->pdev == dev) {
+ pr_debug("EEH: Already referenced !\n");
+ return;
+ }
+
+ /*
+ * The EEH cache might not be removed correctly because of
+ * unbalanced kref to the device during unplug time, which
+ * relies on pcibios_release_device(). So we have to remove
+ * that here explicitly.
+ */
+ if (edev->pdev) {
+ eeh_rmv_from_parent_pe(edev);
+ eeh_addr_cache_rmv_dev(edev->pdev);
+ eeh_sysfs_remove_device(edev->pdev);
+ edev->mode &= ~EEH_DEV_SYSFS;
+
+ /*
+ * We definitely should have the PCI device removed
+ * though it wasn't correctly. So we needn't call
+ * into error handler afterwards.
+ */
+ edev->mode |= EEH_DEV_NO_HANDLER;
+
+ edev->pdev = NULL;
+ dev->dev.archdata.edev = NULL;
+ }
+
+ edev->pdev = dev;
+ dev->dev.archdata.edev = edev;
+
+ /*
+ * We have to do the EEH probe here because the PCI device
+ * hasn't been created yet in the early stage.
+ */
+ if (eeh_probe_mode_dev())
+ eeh_ops->dev_probe(dev, NULL);
+
+ eeh_addr_cache_insert_dev(dev);
+}
+
+/**
+ * eeh_add_device_tree_late - Perform EEH initialization for the indicated PCI bus
+ * @bus: PCI bus
+ *
+ * This routine must be used to perform EEH initialization for PCI
+ * devices which are attached to the indicated PCI bus. The PCI bus
+ * is added after system boot through hotplug or dlpar.
+ */
+void eeh_add_device_tree_late(struct pci_bus *bus)
+{
+ struct pci_dev *dev;
+
+ list_for_each_entry(dev, &bus->devices, bus_list) {
+ eeh_add_device_late(dev);
+ if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE) {
+ struct pci_bus *subbus = dev->subordinate;
+ if (subbus)
+ eeh_add_device_tree_late(subbus);
+ }
+ }
+}
+EXPORT_SYMBOL_GPL(eeh_add_device_tree_late);
+
+/**
+ * eeh_add_sysfs_files - Add EEH sysfs files for the indicated PCI bus
+ * @bus: PCI bus
+ *
+ * This routine must be used to add EEH sysfs files for PCI
+ * devices which are attached to the indicated PCI bus. The PCI bus
+ * is added after system boot through hotplug or dlpar.
+ */
+void eeh_add_sysfs_files(struct pci_bus *bus)
+{
+ struct pci_dev *dev;
+
+ list_for_each_entry(dev, &bus->devices, bus_list) {
+ eeh_sysfs_add_device(dev);
+ if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE) {
+ struct pci_bus *subbus = dev->subordinate;
+ if (subbus)
+ eeh_add_sysfs_files(subbus);
+ }
+ }
+}
+EXPORT_SYMBOL_GPL(eeh_add_sysfs_files);
+
+/**
+ * eeh_remove_device - Undo EEH setup for the indicated pci device
+ * @dev: pci device to be removed
+ *
+ * This routine should be called when a device is removed from
+ * a running system (e.g. by hotplug or dlpar). It unregisters
+ * the PCI device from the EEH subsystem. I/O errors affecting
+ * this device will no longer be detected after this call; thus,
+ * i/o errors affecting this slot may leave this device unusable.
+ */
+void eeh_remove_device(struct pci_dev *dev)
+{
+ struct eeh_dev *edev;
+
+ if (!dev || !eeh_enabled())
+ return;
+ edev = pci_dev_to_eeh_dev(dev);
+
+ /* Unregister the device with the EEH/PCI address search system */
+ pr_debug("EEH: Removing device %s\n", pci_name(dev));
+
+ if (!edev || !edev->pdev || !edev->pe) {
+ pr_debug("EEH: Not referenced !\n");
+ return;
+ }
+
+ /*
+ * During the hotplug for EEH error recovery, we need the EEH
+ * device attached to the parent PE in order for BAR restore
+ * a bit later. So we keep it for BAR restore and remove it
+ * from the parent PE during the BAR resotre.
+ */
+ edev->pdev = NULL;
+ dev->dev.archdata.edev = NULL;
+ if (!(edev->pe->state & EEH_PE_KEEP))
+ eeh_rmv_from_parent_pe(edev);
+ else
+ edev->mode |= EEH_DEV_DISCONNECTED;
+
+ /*
+ * We're removing from the PCI subsystem, that means
+ * the PCI device driver can't support EEH or not
+ * well. So we rely on hotplug completely to do recovery
+ * for the specific PCI device.
+ */
+ edev->mode |= EEH_DEV_NO_HANDLER;
+
+ eeh_addr_cache_rmv_dev(dev);
+ eeh_sysfs_remove_device(dev);
+ edev->mode &= ~EEH_DEV_SYSFS;
+}
+
+static int proc_eeh_show(struct seq_file *m, void *v)
+{
+ if (!eeh_enabled()) {
+ seq_printf(m, "EEH Subsystem is globally disabled\n");
+ seq_printf(m, "eeh_total_mmio_ffs=%llu\n", eeh_stats.total_mmio_ffs);
+ } else {
+ seq_printf(m, "EEH Subsystem is enabled\n");
+ seq_printf(m,
+ "no device=%llu\n"
+ "no device node=%llu\n"
+ "no config address=%llu\n"
+ "check not wanted=%llu\n"
+ "eeh_total_mmio_ffs=%llu\n"
+ "eeh_false_positives=%llu\n"
+ "eeh_slot_resets=%llu\n",
+ eeh_stats.no_device,
+ eeh_stats.no_dn,
+ eeh_stats.no_cfg_addr,
+ eeh_stats.ignored_check,
+ eeh_stats.total_mmio_ffs,
+ eeh_stats.false_positives,
+ eeh_stats.slot_resets);
+ }
+
+ return 0;
+}
+
+static int proc_eeh_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, proc_eeh_show, NULL);
+}
+
+static const struct file_operations proc_eeh_operations = {
+ .open = proc_eeh_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+
+#ifdef CONFIG_DEBUG_FS
+static int eeh_enable_dbgfs_set(void *data, u64 val)
+{
+ if (val)
+ eeh_subsystem_flags &= ~EEH_FORCE_DISABLED;
+ else
+ eeh_subsystem_flags |= EEH_FORCE_DISABLED;
+
+ /* Notify the backend */
+ if (eeh_ops->post_init)
+ eeh_ops->post_init();
+
+ return 0;
+}
+
+static int eeh_enable_dbgfs_get(void *data, u64 *val)
+{
+ if (eeh_enabled())
+ *val = 0x1ul;
+ else
+ *val = 0x0ul;
+ return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(eeh_enable_dbgfs_ops, eeh_enable_dbgfs_get,
+ eeh_enable_dbgfs_set, "0x%llx\n");
+#endif
+
+static int __init eeh_init_proc(void)
+{
+ if (machine_is(pseries) || machine_is(powernv)) {
+ proc_create("powerpc/eeh", 0, NULL, &proc_eeh_operations);
+#ifdef CONFIG_DEBUG_FS
+ debugfs_create_file("eeh_enable", 0600,
+ powerpc_debugfs_root, NULL,
+ &eeh_enable_dbgfs_ops);
+#endif
+ }
+
+ return 0;
+}
+__initcall(eeh_init_proc);
diff --git a/arch/powerpc/kernel/eeh_cache.c b/arch/powerpc/kernel/eeh_cache.c
new file mode 100644
index 00000000000..e8c9fd546a5
--- /dev/null
+++ b/arch/powerpc/kernel/eeh_cache.c
@@ -0,0 +1,310 @@
+/*
+ * PCI address cache; allows the lookup of PCI devices based on I/O address
+ *
+ * Copyright IBM Corporation 2004
+ * Copyright Linas Vepstas <linas@austin.ibm.com> 2004
+ *
+ * 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/list.h>
+#include <linux/pci.h>
+#include <linux/rbtree.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/atomic.h>
+#include <asm/pci-bridge.h>
+#include <asm/ppc-pci.h>
+
+
+/**
+ * The pci address cache subsystem. This subsystem places
+ * PCI device address resources into a red-black tree, sorted
+ * according to the address range, so that given only an i/o
+ * address, the corresponding PCI device can be **quickly**
+ * found. It is safe to perform an address lookup in an interrupt
+ * context; this ability is an important feature.
+ *
+ * Currently, the only customer of this code is the EEH subsystem;
+ * thus, this code has been somewhat tailored to suit EEH better.
+ * In particular, the cache does *not* hold the addresses of devices
+ * for which EEH is not enabled.
+ *
+ * (Implementation Note: The RB tree seems to be better/faster
+ * than any hash algo I could think of for this problem, even
+ * with the penalty of slow pointer chases for d-cache misses).
+ */
+struct pci_io_addr_range {
+ struct rb_node rb_node;
+ unsigned long addr_lo;
+ unsigned long addr_hi;
+ struct eeh_dev *edev;
+ struct pci_dev *pcidev;
+ unsigned int flags;
+};
+
+static struct pci_io_addr_cache {
+ struct rb_root rb_root;
+ spinlock_t piar_lock;
+} pci_io_addr_cache_root;
+
+static inline struct eeh_dev *__eeh_addr_cache_get_device(unsigned long addr)
+{
+ struct rb_node *n = pci_io_addr_cache_root.rb_root.rb_node;
+
+ while (n) {
+ struct pci_io_addr_range *piar;
+ piar = rb_entry(n, struct pci_io_addr_range, rb_node);
+
+ if (addr < piar->addr_lo)
+ n = n->rb_left;
+ else if (addr > piar->addr_hi)
+ n = n->rb_right;
+ else
+ return piar->edev;
+ }
+
+ return NULL;
+}
+
+/**
+ * eeh_addr_cache_get_dev - Get device, given only address
+ * @addr: mmio (PIO) phys address or i/o port number
+ *
+ * Given an mmio phys address, or a port number, find a pci device
+ * that implements this address. Be sure to pci_dev_put the device
+ * when finished. I/O port numbers are assumed to be offset
+ * from zero (that is, they do *not* have pci_io_addr added in).
+ * It is safe to call this function within an interrupt.
+ */
+struct eeh_dev *eeh_addr_cache_get_dev(unsigned long addr)
+{
+ struct eeh_dev *edev;
+ unsigned long flags;
+
+ spin_lock_irqsave(&pci_io_addr_cache_root.piar_lock, flags);
+ edev = __eeh_addr_cache_get_device(addr);
+ spin_unlock_irqrestore(&pci_io_addr_cache_root.piar_lock, flags);
+ return edev;
+}
+
+#ifdef DEBUG
+/*
+ * Handy-dandy debug print routine, does nothing more
+ * than print out the contents of our addr cache.
+ */
+static void eeh_addr_cache_print(struct pci_io_addr_cache *cache)
+{
+ struct rb_node *n;
+ int cnt = 0;
+
+ n = rb_first(&cache->rb_root);
+ while (n) {
+ struct pci_io_addr_range *piar;
+ piar = rb_entry(n, struct pci_io_addr_range, rb_node);
+ pr_debug("PCI: %s addr range %d [%lx-%lx]: %s\n",
+ (piar->flags & IORESOURCE_IO) ? "i/o" : "mem", cnt,
+ piar->addr_lo, piar->addr_hi, pci_name(piar->pcidev));
+ cnt++;
+ n = rb_next(n);
+ }
+}
+#endif
+
+/* Insert address range into the rb tree. */
+static struct pci_io_addr_range *
+eeh_addr_cache_insert(struct pci_dev *dev, unsigned long alo,
+ unsigned long ahi, unsigned int flags)
+{
+ struct rb_node **p = &pci_io_addr_cache_root.rb_root.rb_node;
+ struct rb_node *parent = NULL;
+ struct pci_io_addr_range *piar;
+
+ /* Walk tree, find a place to insert into tree */
+ while (*p) {
+ parent = *p;
+ piar = rb_entry(parent, struct pci_io_addr_range, rb_node);
+ if (ahi < piar->addr_lo) {
+ p = &parent->rb_left;
+ } else if (alo > piar->addr_hi) {
+ p = &parent->rb_right;
+ } else {
+ if (dev != piar->pcidev ||
+ alo != piar->addr_lo || ahi != piar->addr_hi) {
+ pr_warning("PIAR: overlapping address range\n");
+ }
+ return piar;
+ }
+ }
+ piar = kzalloc(sizeof(struct pci_io_addr_range), GFP_ATOMIC);
+ if (!piar)
+ return NULL;
+
+ piar->addr_lo = alo;
+ piar->addr_hi = ahi;
+ piar->edev = pci_dev_to_eeh_dev(dev);
+ piar->pcidev = dev;
+ piar->flags = flags;
+
+#ifdef DEBUG
+ pr_debug("PIAR: insert range=[%lx:%lx] dev=%s\n",
+ alo, ahi, pci_name(dev));
+#endif
+
+ rb_link_node(&piar->rb_node, parent, p);
+ rb_insert_color(&piar->rb_node, &pci_io_addr_cache_root.rb_root);
+
+ return piar;
+}
+
+static void __eeh_addr_cache_insert_dev(struct pci_dev *dev)
+{
+ struct device_node *dn;
+ struct eeh_dev *edev;
+ int i;
+
+ dn = pci_device_to_OF_node(dev);
+ if (!dn) {
+ pr_warning("PCI: no pci dn found for dev=%s\n", pci_name(dev));
+ return;
+ }
+
+ edev = of_node_to_eeh_dev(dn);
+ if (!edev) {
+ pr_warning("PCI: no EEH dev found for dn=%s\n",
+ dn->full_name);
+ return;
+ }
+
+ /* Skip any devices for which EEH is not enabled. */
+ if (!eeh_probe_mode_dev() && !edev->pe) {
+#ifdef DEBUG
+ pr_info("PCI: skip building address cache for=%s - %s\n",
+ pci_name(dev), dn->full_name);
+#endif
+ return;
+ }
+
+ /* Walk resources on this device, poke them into the tree */
+ for (i = 0; i < DEVICE_COUNT_RESOURCE; i++) {
+ unsigned long start = pci_resource_start(dev,i);
+ unsigned long end = pci_resource_end(dev,i);
+ unsigned int flags = pci_resource_flags(dev,i);
+
+ /* We are interested only bus addresses, not dma or other stuff */
+ if (0 == (flags & (IORESOURCE_IO | IORESOURCE_MEM)))
+ continue;
+ if (start == 0 || ~start == 0 || end == 0 || ~end == 0)
+ continue;
+ eeh_addr_cache_insert(dev, start, end, flags);
+ }
+}
+
+/**
+ * eeh_addr_cache_insert_dev - Add a device to the address cache
+ * @dev: PCI device whose I/O addresses we are interested in.
+ *
+ * In order to support the fast lookup of devices based on addresses,
+ * we maintain a cache of devices that can be quickly searched.
+ * This routine adds a device to that cache.
+ */
+void eeh_addr_cache_insert_dev(struct pci_dev *dev)
+{
+ unsigned long flags;
+
+ /* Ignore PCI bridges */
+ if ((dev->class >> 16) == PCI_BASE_CLASS_BRIDGE)
+ return;
+
+ spin_lock_irqsave(&pci_io_addr_cache_root.piar_lock, flags);
+ __eeh_addr_cache_insert_dev(dev);
+ spin_unlock_irqrestore(&pci_io_addr_cache_root.piar_lock, flags);
+}
+
+static inline void __eeh_addr_cache_rmv_dev(struct pci_dev *dev)
+{
+ struct rb_node *n;
+
+restart:
+ n = rb_first(&pci_io_addr_cache_root.rb_root);
+ while (n) {
+ struct pci_io_addr_range *piar;
+ piar = rb_entry(n, struct pci_io_addr_range, rb_node);
+
+ if (piar->pcidev == dev) {
+ rb_erase(n, &pci_io_addr_cache_root.rb_root);
+ kfree(piar);
+ goto restart;
+ }
+ n = rb_next(n);
+ }
+}
+
+/**
+ * eeh_addr_cache_rmv_dev - remove pci device from addr cache
+ * @dev: device to remove
+ *
+ * Remove a device from the addr-cache tree.
+ * This is potentially expensive, since it will walk
+ * the tree multiple times (once per resource).
+ * But so what; device removal doesn't need to be that fast.
+ */
+void eeh_addr_cache_rmv_dev(struct pci_dev *dev)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&pci_io_addr_cache_root.piar_lock, flags);
+ __eeh_addr_cache_rmv_dev(dev);
+ spin_unlock_irqrestore(&pci_io_addr_cache_root.piar_lock, flags);
+}
+
+/**
+ * eeh_addr_cache_build - Build a cache of I/O addresses
+ *
+ * Build a cache of pci i/o addresses. This cache will be used to
+ * find the pci device that corresponds to a given address.
+ * This routine scans all pci busses to build the cache.
+ * Must be run late in boot process, after the pci controllers
+ * have been scanned for devices (after all device resources are known).
+ */
+void eeh_addr_cache_build(void)
+{
+ struct device_node *dn;
+ struct eeh_dev *edev;
+ struct pci_dev *dev = NULL;
+
+ spin_lock_init(&pci_io_addr_cache_root.piar_lock);
+
+ for_each_pci_dev(dev) {
+ dn = pci_device_to_OF_node(dev);
+ if (!dn)
+ continue;
+
+ edev = of_node_to_eeh_dev(dn);
+ if (!edev)
+ continue;
+
+ dev->dev.archdata.edev = edev;
+ edev->pdev = dev;
+
+ eeh_addr_cache_insert_dev(dev);
+ eeh_sysfs_add_device(dev);
+ }
+
+#ifdef DEBUG
+ /* Verify tree built up above, echo back the list of addrs. */
+ eeh_addr_cache_print(&pci_io_addr_cache_root);
+#endif
+}
diff --git a/arch/powerpc/kernel/eeh_dev.c b/arch/powerpc/kernel/eeh_dev.c
new file mode 100644
index 00000000000..1efa28f5fc5
--- /dev/null
+++ b/arch/powerpc/kernel/eeh_dev.c
@@ -0,0 +1,112 @@
+/*
+ * The file intends to implement dynamic creation of EEH device, which will
+ * be bound with OF node and PCI device simutaneously. The EEH devices would
+ * be foundamental information for EEH core components to work proerly. Besides,
+ * We have to support multiple situations where dynamic creation of EEH device
+ * is required:
+ *
+ * 1) Before PCI emunation starts, we need create EEH devices according to the
+ * PCI sensitive OF nodes.
+ * 2) When PCI emunation is done, we need do the binding between PCI device and
+ * the associated EEH device.
+ * 3) DR (Dynamic Reconfiguration) would create PCI sensitive OF node. EEH device
+ * will be created while PCI sensitive OF node is detected from DR.
+ * 4) PCI hotplug needs redoing the binding between PCI device and EEH device. If
+ * PHB is newly inserted, we also need create EEH devices accordingly.
+ *
+ * Copyright Benjamin Herrenschmidt & Gavin Shan, IBM Corporation 2012.
+ *
+ * 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/export.h>
+#include <linux/gfp.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/pci.h>
+#include <linux/string.h>
+
+#include <asm/pci-bridge.h>
+#include <asm/ppc-pci.h>
+
+/**
+ * eeh_dev_init - Create EEH device according to OF node
+ * @dn: device node
+ * @data: PHB
+ *
+ * It will create EEH device according to the given OF node. The function
+ * might be called by PCI emunation, DR, PHB hotplug.
+ */
+void *eeh_dev_init(struct device_node *dn, void *data)
+{
+ struct pci_controller *phb = data;
+ struct eeh_dev *edev;
+
+ /* Allocate EEH device */
+ edev = kzalloc(sizeof(*edev), GFP_KERNEL);
+ if (!edev) {
+ pr_warning("%s: out of memory\n", __func__);
+ return NULL;
+ }
+
+ /* Associate EEH device with OF node */
+ PCI_DN(dn)->edev = edev;
+ edev->dn = dn;
+ edev->phb = phb;
+ INIT_LIST_HEAD(&edev->list);
+
+ return NULL;
+}
+
+/**
+ * eeh_dev_phb_init_dynamic - Create EEH devices for devices included in PHB
+ * @phb: PHB
+ *
+ * Scan the PHB OF node and its child association, then create the
+ * EEH devices accordingly
+ */
+void eeh_dev_phb_init_dynamic(struct pci_controller *phb)
+{
+ struct device_node *dn = phb->dn;
+
+ /* EEH PE for PHB */
+ eeh_phb_pe_create(phb);
+
+ /* EEH device for PHB */
+ eeh_dev_init(dn, phb);
+
+ /* EEH devices for children OF nodes */
+ traverse_pci_devices(dn, eeh_dev_init, phb);
+}
+
+/**
+ * eeh_dev_phb_init - Create EEH devices for devices included in existing PHBs
+ *
+ * Scan all the existing PHBs and create EEH devices for their OF
+ * nodes and their children OF nodes
+ */
+static int __init eeh_dev_phb_init(void)
+{
+ struct pci_controller *phb, *tmp;
+
+ list_for_each_entry_safe(phb, tmp, &hose_list, list_node)
+ eeh_dev_phb_init_dynamic(phb);
+
+ pr_info("EEH: devices created\n");
+
+ return 0;
+}
+
+core_initcall(eeh_dev_phb_init);
diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c
new file mode 100644
index 00000000000..420da61d4ce
--- /dev/null
+++ b/arch/powerpc/kernel/eeh_driver.c
@@ -0,0 +1,870 @@
+/*
+ * PCI Error Recovery Driver for RPA-compliant PPC64 platform.
+ * Copyright IBM Corp. 2004 2005
+ * Copyright Linas Vepstas <linas@linas.org> 2004, 2005
+ *
+ * All rights reserved.
+ *
+ * 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, GOOD TITLE or
+ * NON INFRINGEMENT. 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., 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ * Send comments and feedback to Linas Vepstas <linas@austin.ibm.com>
+ */
+#include <linux/delay.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <asm/eeh.h>
+#include <asm/eeh_event.h>
+#include <asm/ppc-pci.h>
+#include <asm/pci-bridge.h>
+#include <asm/prom.h>
+#include <asm/rtas.h>
+
+/**
+ * eeh_pcid_name - Retrieve name of PCI device driver
+ * @pdev: PCI device
+ *
+ * This routine is used to retrieve the name of PCI device driver
+ * if that's valid.
+ */
+static inline const char *eeh_pcid_name(struct pci_dev *pdev)
+{
+ if (pdev && pdev->dev.driver)
+ return pdev->dev.driver->name;
+ return "";
+}
+
+/**
+ * eeh_pcid_get - Get the PCI device driver
+ * @pdev: PCI device
+ *
+ * The function is used to retrieve the PCI device driver for
+ * the indicated PCI device. Besides, we will increase the reference
+ * of the PCI device driver to prevent that being unloaded on
+ * the fly. Otherwise, kernel crash would be seen.
+ */
+static inline struct pci_driver *eeh_pcid_get(struct pci_dev *pdev)
+{
+ if (!pdev || !pdev->driver)
+ return NULL;
+
+ if (!try_module_get(pdev->driver->driver.owner))
+ return NULL;
+
+ return pdev->driver;
+}
+
+/**
+ * eeh_pcid_put - Dereference on the PCI device driver
+ * @pdev: PCI device
+ *
+ * The function is called to do dereference on the PCI device
+ * driver of the indicated PCI device.
+ */
+static inline void eeh_pcid_put(struct pci_dev *pdev)
+{
+ if (!pdev || !pdev->driver)
+ return;
+
+ module_put(pdev->driver->driver.owner);
+}
+
+#if 0
+static void print_device_node_tree(struct pci_dn *pdn, int dent)
+{
+ int i;
+ struct device_node *pc;
+
+ if (!pdn)
+ return;
+ for (i = 0; i < dent; i++)
+ printk(" ");
+ printk("dn=%s mode=%x \tcfg_addr=%x pe_addr=%x \tfull=%s\n",
+ pdn->node->name, pdn->eeh_mode, pdn->eeh_config_addr,
+ pdn->eeh_pe_config_addr, pdn->node->full_name);
+ dent += 3;
+ pc = pdn->node->child;
+ while (pc) {
+ print_device_node_tree(PCI_DN(pc), dent);
+ pc = pc->sibling;
+ }
+}
+#endif
+
+/**
+ * eeh_disable_irq - Disable interrupt for the recovering device
+ * @dev: PCI device
+ *
+ * This routine must be called when reporting temporary or permanent
+ * error to the particular PCI device to disable interrupt of that
+ * device. If the device has enabled MSI or MSI-X interrupt, we needn't
+ * do real work because EEH should freeze DMA transfers for those PCI
+ * devices encountering EEH errors, which includes MSI or MSI-X.
+ */
+static void eeh_disable_irq(struct pci_dev *dev)
+{
+ struct eeh_dev *edev = pci_dev_to_eeh_dev(dev);
+
+ /* Don't disable MSI and MSI-X interrupts. They are
+ * effectively disabled by the DMA Stopped state
+ * when an EEH error occurs.
+ */
+ if (dev->msi_enabled || dev->msix_enabled)
+ return;
+
+ if (!irq_has_action(dev->irq))
+ return;
+
+ edev->mode |= EEH_DEV_IRQ_DISABLED;
+ disable_irq_nosync(dev->irq);
+}
+
+/**
+ * eeh_enable_irq - Enable interrupt for the recovering device
+ * @dev: PCI device
+ *
+ * This routine must be called to enable interrupt while failed
+ * device could be resumed.
+ */
+static void eeh_enable_irq(struct pci_dev *dev)
+{
+ struct eeh_dev *edev = pci_dev_to_eeh_dev(dev);
+
+ if ((edev->mode) & EEH_DEV_IRQ_DISABLED) {
+ edev->mode &= ~EEH_DEV_IRQ_DISABLED;
+ /*
+ * FIXME !!!!!
+ *
+ * This is just ass backwards. This maze has
+ * unbalanced irq_enable/disable calls. So instead of
+ * finding the root cause it works around the warning
+ * in the irq_enable code by conditionally calling
+ * into it.
+ *
+ * That's just wrong.The warning in the core code is
+ * there to tell people to fix their assymetries in
+ * their own code, not by abusing the core information
+ * to avoid it.
+ *
+ * I so wish that the assymetry would be the other way
+ * round and a few more irq_disable calls render that
+ * shit unusable forever.
+ *
+ * tglx
+ */
+ if (irqd_irq_disabled(irq_get_irq_data(dev->irq)))
+ enable_irq(dev->irq);
+ }
+}
+
+static bool eeh_dev_removed(struct eeh_dev *edev)
+{
+ /* EEH device removed ? */
+ if (!edev || (edev->mode & EEH_DEV_REMOVED))
+ return true;
+
+ return false;
+}
+
+/**
+ * eeh_report_error - Report pci error to each device driver
+ * @data: eeh device
+ * @userdata: return value
+ *
+ * Report an EEH error to each device driver, collect up and
+ * merge the device driver responses. Cumulative response
+ * passed back in "userdata".
+ */
+static void *eeh_report_error(void *data, void *userdata)
+{
+ struct eeh_dev *edev = (struct eeh_dev *)data;
+ struct pci_dev *dev = eeh_dev_to_pci_dev(edev);
+ enum pci_ers_result rc, *res = userdata;
+ struct pci_driver *driver;
+
+ if (!dev || eeh_dev_removed(edev))
+ return NULL;
+ dev->error_state = pci_channel_io_frozen;
+
+ driver = eeh_pcid_get(dev);
+ if (!driver) return NULL;
+
+ eeh_disable_irq(dev);
+
+ if (!driver->err_handler ||
+ !driver->err_handler->error_detected) {
+ eeh_pcid_put(dev);
+ return NULL;
+ }
+
+ rc = driver->err_handler->error_detected(dev, pci_channel_io_frozen);
+
+ /* A driver that needs a reset trumps all others */
+ if (rc == PCI_ERS_RESULT_NEED_RESET) *res = rc;
+ if (*res == PCI_ERS_RESULT_NONE) *res = rc;
+
+ eeh_pcid_put(dev);
+ return NULL;
+}
+
+/**
+ * eeh_report_mmio_enabled - Tell drivers that MMIO has been enabled
+ * @data: eeh device
+ * @userdata: return value
+ *
+ * Tells each device driver that IO ports, MMIO and config space I/O
+ * are now enabled. Collects up and merges the device driver responses.
+ * Cumulative response passed back in "userdata".
+ */
+static void *eeh_report_mmio_enabled(void *data, void *userdata)
+{
+ struct eeh_dev *edev = (struct eeh_dev *)data;
+ struct pci_dev *dev = eeh_dev_to_pci_dev(edev);
+ enum pci_ers_result rc, *res = userdata;
+ struct pci_driver *driver;
+
+ if (!dev || eeh_dev_removed(edev))
+ return NULL;
+
+ driver = eeh_pcid_get(dev);
+ if (!driver) return NULL;
+
+ if (!driver->err_handler ||
+ !driver->err_handler->mmio_enabled ||
+ (edev->mode & EEH_DEV_NO_HANDLER)) {
+ eeh_pcid_put(dev);
+ return NULL;
+ }
+
+ rc = driver->err_handler->mmio_enabled(dev);
+
+ /* A driver that needs a reset trumps all others */
+ if (rc == PCI_ERS_RESULT_NEED_RESET) *res = rc;
+ if (*res == PCI_ERS_RESULT_NONE) *res = rc;
+
+ eeh_pcid_put(dev);
+ return NULL;
+}
+
+/**
+ * eeh_report_reset - Tell device that slot has been reset
+ * @data: eeh device
+ * @userdata: return value
+ *
+ * This routine must be called while EEH tries to reset particular
+ * PCI device so that the associated PCI device driver could take
+ * some actions, usually to save data the driver needs so that the
+ * driver can work again while the device is recovered.
+ */
+static void *eeh_report_reset(void *data, void *userdata)
+{
+ struct eeh_dev *edev = (struct eeh_dev *)data;
+ struct pci_dev *dev = eeh_dev_to_pci_dev(edev);
+ enum pci_ers_result rc, *res = userdata;
+ struct pci_driver *driver;
+
+ if (!dev || eeh_dev_removed(edev))
+ return NULL;
+ dev->error_state = pci_channel_io_normal;
+
+ driver = eeh_pcid_get(dev);
+ if (!driver) return NULL;
+
+ eeh_enable_irq(dev);
+
+ if (!driver->err_handler ||
+ !driver->err_handler->slot_reset ||
+ (edev->mode & EEH_DEV_NO_HANDLER)) {
+ eeh_pcid_put(dev);
+ return NULL;
+ }
+
+ rc = driver->err_handler->slot_reset(dev);
+ if ((*res == PCI_ERS_RESULT_NONE) ||
+ (*res == PCI_ERS_RESULT_RECOVERED)) *res = rc;
+ if (*res == PCI_ERS_RESULT_DISCONNECT &&
+ rc == PCI_ERS_RESULT_NEED_RESET) *res = rc;
+
+ eeh_pcid_put(dev);
+ return NULL;
+}
+
+/**
+ * eeh_report_resume - Tell device to resume normal operations
+ * @data: eeh device
+ * @userdata: return value
+ *
+ * This routine must be called to notify the device driver that it
+ * could resume so that the device driver can do some initialization
+ * to make the recovered device work again.
+ */
+static void *eeh_report_resume(void *data, void *userdata)
+{
+ struct eeh_dev *edev = (struct eeh_dev *)data;
+ struct pci_dev *dev = eeh_dev_to_pci_dev(edev);
+ struct pci_driver *driver;
+
+ if (!dev || eeh_dev_removed(edev))
+ return NULL;
+ dev->error_state = pci_channel_io_normal;
+
+ driver = eeh_pcid_get(dev);
+ if (!driver) return NULL;
+
+ eeh_enable_irq(dev);
+
+ if (!driver->err_handler ||
+ !driver->err_handler->resume ||
+ (edev->mode & EEH_DEV_NO_HANDLER)) {
+ edev->mode &= ~EEH_DEV_NO_HANDLER;
+ eeh_pcid_put(dev);
+ return NULL;
+ }
+
+ driver->err_handler->resume(dev);
+
+ eeh_pcid_put(dev);
+ return NULL;
+}
+
+/**
+ * eeh_report_failure - Tell device driver that device is dead.
+ * @data: eeh device
+ * @userdata: return value
+ *
+ * This informs the device driver that the device is permanently
+ * dead, and that no further recovery attempts will be made on it.
+ */
+static void *eeh_report_failure(void *data, void *userdata)
+{
+ struct eeh_dev *edev = (struct eeh_dev *)data;
+ struct pci_dev *dev = eeh_dev_to_pci_dev(edev);
+ struct pci_driver *driver;
+
+ if (!dev || eeh_dev_removed(edev))
+ return NULL;
+ dev->error_state = pci_channel_io_perm_failure;
+
+ driver = eeh_pcid_get(dev);
+ if (!driver) return NULL;
+
+ eeh_disable_irq(dev);
+
+ if (!driver->err_handler ||
+ !driver->err_handler->error_detected) {
+ eeh_pcid_put(dev);
+ return NULL;
+ }
+
+ driver->err_handler->error_detected(dev, pci_channel_io_perm_failure);
+
+ eeh_pcid_put(dev);
+ return NULL;
+}
+
+static void *eeh_rmv_device(void *data, void *userdata)
+{
+ struct pci_driver *driver;
+ struct eeh_dev *edev = (struct eeh_dev *)data;
+ struct pci_dev *dev = eeh_dev_to_pci_dev(edev);
+ int *removed = (int *)userdata;
+
+ /*
+ * Actually, we should remove the PCI bridges as well.
+ * However, that's lots of complexity to do that,
+ * particularly some of devices under the bridge might
+ * support EEH. So we just care about PCI devices for
+ * simplicity here.
+ */
+ if (!dev || (dev->hdr_type & PCI_HEADER_TYPE_BRIDGE))
+ return NULL;
+
+ /*
+ * We rely on count-based pcibios_release_device() to
+ * detach permanently offlined PEs. Unfortunately, that's
+ * not reliable enough. We might have the permanently
+ * offlined PEs attached, but we needn't take care of
+ * them and their child devices.
+ */
+ if (eeh_dev_removed(edev))
+ return NULL;
+
+ driver = eeh_pcid_get(dev);
+ if (driver) {
+ eeh_pcid_put(dev);
+ if (driver->err_handler)
+ return NULL;
+ }
+
+ /* Remove it from PCI subsystem */
+ pr_debug("EEH: Removing %s without EEH sensitive driver\n",
+ pci_name(dev));
+ edev->bus = dev->bus;
+ edev->mode |= EEH_DEV_DISCONNECTED;
+ (*removed)++;
+
+ pci_lock_rescan_remove();
+ pci_stop_and_remove_bus_device(dev);
+ pci_unlock_rescan_remove();
+
+ return NULL;
+}
+
+static void *eeh_pe_detach_dev(void *data, void *userdata)
+{
+ struct eeh_pe *pe = (struct eeh_pe *)data;
+ struct eeh_dev *edev, *tmp;
+
+ eeh_pe_for_each_dev(pe, edev, tmp) {
+ if (!(edev->mode & EEH_DEV_DISCONNECTED))
+ continue;
+
+ edev->mode &= ~(EEH_DEV_DISCONNECTED | EEH_DEV_IRQ_DISABLED);
+ eeh_rmv_from_parent_pe(edev);
+ }
+
+ return NULL;
+}
+
+/*
+ * Explicitly clear PE's frozen state for PowerNV where
+ * we have frozen PE until BAR restore is completed. It's
+ * harmless to clear it for pSeries. To be consistent with
+ * PE reset (for 3 times), we try to clear the frozen state
+ * for 3 times as well.
+ */
+static void *__eeh_clear_pe_frozen_state(void *data, void *flag)
+{
+ struct eeh_pe *pe = (struct eeh_pe *)data;
+ int i, rc;
+
+ for (i = 0; i < 3; i++) {
+ rc = eeh_pci_enable(pe, EEH_OPT_THAW_MMIO);
+ if (rc)
+ continue;
+ rc = eeh_pci_enable(pe, EEH_OPT_THAW_DMA);
+ if (!rc)
+ break;
+ }
+
+ /* The PE has been isolated, clear it */
+ if (rc) {
+ pr_warn("%s: Can't clear frozen PHB#%x-PE#%x (%d)\n",
+ __func__, pe->phb->global_number, pe->addr, rc);
+ return (void *)pe;
+ }
+
+ return NULL;
+}
+
+static int eeh_clear_pe_frozen_state(struct eeh_pe *pe)
+{
+ void *rc;
+
+ rc = eeh_pe_traverse(pe, __eeh_clear_pe_frozen_state, NULL);
+ if (!rc)
+ eeh_pe_state_clear(pe, EEH_PE_ISOLATED);
+
+ return rc ? -EIO : 0;
+}
+
+/**
+ * eeh_reset_device - Perform actual reset of a pci slot
+ * @pe: EEH PE
+ * @bus: PCI bus corresponding to the isolcated slot
+ *
+ * This routine must be called to do reset on the indicated PE.
+ * During the reset, udev might be invoked because those affected
+ * PCI devices will be removed and then added.
+ */
+static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus)
+{
+ struct pci_bus *frozen_bus = eeh_pe_bus_get(pe);
+ struct timeval tstamp;
+ int cnt, rc, removed = 0;
+
+ /* pcibios will clear the counter; save the value */
+ cnt = pe->freeze_count;
+ tstamp = pe->tstamp;
+
+ /*
+ * We don't remove the corresponding PE instances because
+ * we need the information afterwords. The attached EEH
+ * devices are expected to be attached soon when calling
+ * into pcibios_add_pci_devices().
+ */
+ eeh_pe_state_mark(pe, EEH_PE_KEEP);
+ if (bus) {
+ pci_lock_rescan_remove();
+ pcibios_remove_pci_devices(bus);
+ pci_unlock_rescan_remove();
+ } else if (frozen_bus) {
+ eeh_pe_dev_traverse(pe, eeh_rmv_device, &removed);
+ }
+
+ /*
+ * Reset the pci controller. (Asserts RST#; resets config space).
+ * Reconfigure bridges and devices. Don't try to bring the system
+ * up if the reset failed for some reason.
+ *
+ * During the reset, it's very dangerous to have uncontrolled PCI
+ * config accesses. So we prefer to block them. However, controlled
+ * PCI config accesses initiated from EEH itself are allowed.
+ */
+ eeh_pe_state_mark(pe, EEH_PE_RESET);
+ rc = eeh_reset_pe(pe);
+ if (rc) {
+ eeh_pe_state_clear(pe, EEH_PE_RESET);
+ return rc;
+ }
+
+ pci_lock_rescan_remove();
+
+ /* Restore PE */
+ eeh_ops->configure_bridge(pe);
+ eeh_pe_restore_bars(pe);
+ eeh_pe_state_clear(pe, EEH_PE_RESET);
+
+ /* Clear frozen state */
+ rc = eeh_clear_pe_frozen_state(pe);
+ if (rc)
+ return rc;
+
+ /* Give the system 5 seconds to finish running the user-space
+ * hotplug shutdown scripts, e.g. ifdown for ethernet. Yes,
+ * this is a hack, but if we don't do this, and try to bring
+ * the device up before the scripts have taken it down,
+ * potentially weird things happen.
+ */
+ if (bus) {
+ pr_info("EEH: Sleep 5s ahead of complete hotplug\n");
+ ssleep(5);
+
+ /*
+ * The EEH device is still connected with its parent
+ * PE. We should disconnect it so the binding can be
+ * rebuilt when adding PCI devices.
+ */
+ eeh_pe_traverse(pe, eeh_pe_detach_dev, NULL);
+ pcibios_add_pci_devices(bus);
+ } else if (frozen_bus && removed) {
+ pr_info("EEH: Sleep 5s ahead of partial hotplug\n");
+ ssleep(5);
+
+ eeh_pe_traverse(pe, eeh_pe_detach_dev, NULL);
+ pcibios_add_pci_devices(frozen_bus);
+ }
+ eeh_pe_state_clear(pe, EEH_PE_KEEP);
+
+ pe->tstamp = tstamp;
+ pe->freeze_count = cnt;
+
+ pci_unlock_rescan_remove();
+ return 0;
+}
+
+/* The longest amount of time to wait for a pci device
+ * to come back on line, in seconds.
+ */
+#define MAX_WAIT_FOR_RECOVERY 300
+
+static void eeh_handle_normal_event(struct eeh_pe *pe)
+{
+ struct pci_bus *frozen_bus;
+ int rc = 0;
+ enum pci_ers_result result = PCI_ERS_RESULT_NONE;
+
+ frozen_bus = eeh_pe_bus_get(pe);
+ if (!frozen_bus) {
+ pr_err("%s: Cannot find PCI bus for PHB#%d-PE#%x\n",
+ __func__, pe->phb->global_number, pe->addr);
+ return;
+ }
+
+ eeh_pe_update_time_stamp(pe);
+ pe->freeze_count++;
+ if (pe->freeze_count > EEH_MAX_ALLOWED_FREEZES)
+ goto excess_failures;
+ pr_warning("EEH: This PCI device has failed %d times in the last hour\n",
+ pe->freeze_count);
+
+ /* Walk the various device drivers attached to this slot through
+ * a reset sequence, giving each an opportunity to do what it needs
+ * to accomplish the reset. Each child gets a report of the
+ * status ... if any child can't handle the reset, then the entire
+ * slot is dlpar removed and added.
+ */
+ pr_info("EEH: Notify device drivers to shutdown\n");
+ eeh_pe_dev_traverse(pe, eeh_report_error, &result);
+
+ /* Get the current PCI slot state. This can take a long time,
+ * sometimes over 3 seconds for certain systems.
+ */
+ rc = eeh_ops->wait_state(pe, MAX_WAIT_FOR_RECOVERY*1000);
+ if (rc < 0 || rc == EEH_STATE_NOT_SUPPORT) {
+ pr_warning("EEH: Permanent failure\n");
+ goto hard_fail;
+ }
+
+ /* Since rtas may enable MMIO when posting the error log,
+ * don't post the error log until after all dev drivers
+ * have been informed.
+ */
+ pr_info("EEH: Collect temporary log\n");
+ eeh_slot_error_detail(pe, EEH_LOG_TEMP);
+
+ /* If all device drivers were EEH-unaware, then shut
+ * down all of the device drivers, and hope they
+ * go down willingly, without panicing the system.
+ */
+ if (result == PCI_ERS_RESULT_NONE) {
+ pr_info("EEH: Reset with hotplug activity\n");
+ rc = eeh_reset_device(pe, frozen_bus);
+ if (rc) {
+ pr_warning("%s: Unable to reset, err=%d\n",
+ __func__, rc);
+ goto hard_fail;
+ }
+ }
+
+ /* If all devices reported they can proceed, then re-enable MMIO */
+ if (result == PCI_ERS_RESULT_CAN_RECOVER) {
+ pr_info("EEH: Enable I/O for affected devices\n");
+ rc = eeh_pci_enable(pe, EEH_OPT_THAW_MMIO);
+
+ if (rc < 0)
+ goto hard_fail;
+ if (rc) {
+ result = PCI_ERS_RESULT_NEED_RESET;
+ } else {
+ pr_info("EEH: Notify device drivers to resume I/O\n");
+ eeh_pe_dev_traverse(pe, eeh_report_mmio_enabled, &result);
+ }
+ }
+
+ /* If all devices reported they can proceed, then re-enable DMA */
+ if (result == PCI_ERS_RESULT_CAN_RECOVER) {
+ pr_info("EEH: Enabled DMA for affected devices\n");
+ rc = eeh_pci_enable(pe, EEH_OPT_THAW_DMA);
+
+ if (rc < 0)
+ goto hard_fail;
+ if (rc) {
+ result = PCI_ERS_RESULT_NEED_RESET;
+ } else {
+ /*
+ * We didn't do PE reset for the case. The PE
+ * is still in frozen state. Clear it before
+ * resuming the PE.
+ */
+ eeh_pe_state_clear(pe, EEH_PE_ISOLATED);
+ result = PCI_ERS_RESULT_RECOVERED;
+ }
+ }
+
+ /* If any device has a hard failure, then shut off everything. */
+ if (result == PCI_ERS_RESULT_DISCONNECT) {
+ pr_warning("EEH: Device driver gave up\n");
+ goto hard_fail;
+ }
+
+ /* If any device called out for a reset, then reset the slot */
+ if (result == PCI_ERS_RESULT_NEED_RESET) {
+ pr_info("EEH: Reset without hotplug activity\n");
+ rc = eeh_reset_device(pe, NULL);
+ if (rc) {
+ pr_warning("%s: Cannot reset, err=%d\n",
+ __func__, rc);
+ goto hard_fail;
+ }
+
+ pr_info("EEH: Notify device drivers "
+ "the completion of reset\n");
+ result = PCI_ERS_RESULT_NONE;
+ eeh_pe_dev_traverse(pe, eeh_report_reset, &result);
+ }
+
+ /* All devices should claim they have recovered by now. */
+ if ((result != PCI_ERS_RESULT_RECOVERED) &&
+ (result != PCI_ERS_RESULT_NONE)) {
+ pr_warning("EEH: Not recovered\n");
+ goto hard_fail;
+ }
+
+ /* Tell all device drivers that they can resume operations */
+ pr_info("EEH: Notify device driver to resume\n");
+ eeh_pe_dev_traverse(pe, eeh_report_resume, NULL);
+
+ return;
+
+excess_failures:
+ /*
+ * About 90% of all real-life EEH failures in the field
+ * are due to poorly seated PCI cards. Only 10% or so are
+ * due to actual, failed cards.
+ */
+ pr_err("EEH: PHB#%d-PE#%x has failed %d times in the\n"
+ "last hour and has been permanently disabled.\n"
+ "Please try reseating or replacing it.\n",
+ pe->phb->global_number, pe->addr,
+ pe->freeze_count);
+ goto perm_error;
+
+hard_fail:
+ pr_err("EEH: Unable to recover from failure from PHB#%d-PE#%x.\n"
+ "Please try reseating or replacing it\n",
+ pe->phb->global_number, pe->addr);
+
+perm_error:
+ eeh_slot_error_detail(pe, EEH_LOG_PERM);
+
+ /* Notify all devices that they're about to go down. */
+ eeh_pe_dev_traverse(pe, eeh_report_failure, NULL);
+
+ /* Mark the PE to be removed permanently */
+ pe->freeze_count = EEH_MAX_ALLOWED_FREEZES + 1;
+
+ /*
+ * Shut down the device drivers for good. We mark
+ * all removed devices correctly to avoid access
+ * the their PCI config any more.
+ */
+ if (frozen_bus) {
+ eeh_pe_dev_mode_mark(pe, EEH_DEV_REMOVED);
+
+ pci_lock_rescan_remove();
+ pcibios_remove_pci_devices(frozen_bus);
+ pci_unlock_rescan_remove();
+ }
+}
+
+static void eeh_handle_special_event(void)
+{
+ struct eeh_pe *pe, *phb_pe;
+ struct pci_bus *bus;
+ struct pci_controller *hose;
+ unsigned long flags;
+ int rc;
+
+
+ do {
+ rc = eeh_ops->next_error(&pe);
+
+ switch (rc) {
+ case EEH_NEXT_ERR_DEAD_IOC:
+ /* Mark all PHBs in dead state */
+ eeh_serialize_lock(&flags);
+
+ /* Purge all events */
+ eeh_remove_event(NULL, true);
+
+ list_for_each_entry(hose, &hose_list, list_node) {
+ phb_pe = eeh_phb_pe_get(hose);
+ if (!phb_pe) continue;
+
+ eeh_pe_state_mark(phb_pe, EEH_PE_ISOLATED);
+ }
+
+ eeh_serialize_unlock(flags);
+
+ break;
+ case EEH_NEXT_ERR_FROZEN_PE:
+ case EEH_NEXT_ERR_FENCED_PHB:
+ case EEH_NEXT_ERR_DEAD_PHB:
+ /* Mark the PE in fenced state */
+ eeh_serialize_lock(&flags);
+
+ /* Purge all events of the PHB */
+ eeh_remove_event(pe, true);
+
+ if (rc == EEH_NEXT_ERR_DEAD_PHB)
+ eeh_pe_state_mark(pe, EEH_PE_ISOLATED);
+ else
+ eeh_pe_state_mark(pe,
+ EEH_PE_ISOLATED | EEH_PE_RECOVERING);
+
+ eeh_serialize_unlock(flags);
+
+ break;
+ case EEH_NEXT_ERR_NONE:
+ return;
+ default:
+ pr_warn("%s: Invalid value %d from next_error()\n",
+ __func__, rc);
+ return;
+ }
+
+ /*
+ * For fenced PHB and frozen PE, it's handled as normal
+ * event. We have to remove the affected PHBs for dead
+ * PHB and IOC
+ */
+ if (rc == EEH_NEXT_ERR_FROZEN_PE ||
+ rc == EEH_NEXT_ERR_FENCED_PHB) {
+ eeh_handle_normal_event(pe);
+ eeh_pe_state_clear(pe, EEH_PE_RECOVERING);
+ } else {
+ pci_lock_rescan_remove();
+ list_for_each_entry(hose, &hose_list, list_node) {
+ phb_pe = eeh_phb_pe_get(hose);
+ if (!phb_pe ||
+ !(phb_pe->state & EEH_PE_ISOLATED) ||
+ (phb_pe->state & EEH_PE_RECOVERING))
+ continue;
+
+ /* Notify all devices to be down */
+ bus = eeh_pe_bus_get(phb_pe);
+ eeh_pe_dev_traverse(pe,
+ eeh_report_failure, NULL);
+ pcibios_remove_pci_devices(bus);
+ }
+ pci_unlock_rescan_remove();
+ }
+
+ /*
+ * If we have detected dead IOC, we needn't proceed
+ * any more since all PHBs would have been removed
+ */
+ if (rc == EEH_NEXT_ERR_DEAD_IOC)
+ break;
+ } while (rc != EEH_NEXT_ERR_NONE);
+}
+
+/**
+ * eeh_handle_event - Reset a PCI device after hard lockup.
+ * @pe: EEH PE
+ *
+ * While PHB detects address or data parity errors on particular PCI
+ * slot, the associated PE will be frozen. Besides, DMA's occurring
+ * to wild addresses (which usually happen due to bugs in device
+ * drivers or in PCI adapter firmware) can cause EEH error. #SERR,
+ * #PERR or other misc PCI-related errors also can trigger EEH errors.
+ *
+ * Recovery process consists of unplugging the device driver (which
+ * generated hotplug events to userspace), then issuing a PCI #RST to
+ * the device, then reconfiguring the PCI config space for all bridges
+ * & devices under this slot, and then finally restarting the device
+ * drivers (which cause a second set of hotplug events to go out to
+ * userspace).
+ */
+void eeh_handle_event(struct eeh_pe *pe)
+{
+ if (pe)
+ eeh_handle_normal_event(pe);
+ else
+ eeh_handle_special_event();
+}
diff --git a/arch/powerpc/kernel/eeh_event.c b/arch/powerpc/kernel/eeh_event.c
new file mode 100644
index 00000000000..4eefb6e34db
--- /dev/null
+++ b/arch/powerpc/kernel/eeh_event.c
@@ -0,0 +1,196 @@
+/*
+ * 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
+ *
+ * Copyright (c) 2005 Linas Vepstas <linas@linas.org>
+ */
+
+#include <linux/delay.h>
+#include <linux/list.h>
+#include <linux/sched.h>
+#include <linux/semaphore.h>
+#include <linux/pci.h>
+#include <linux/slab.h>
+#include <linux/kthread.h>
+#include <asm/eeh_event.h>
+#include <asm/ppc-pci.h>
+
+/** Overview:
+ * EEH error states may be detected within exception handlers;
+ * however, the recovery processing needs to occur asynchronously
+ * in a normal kernel context and not an interrupt context.
+ * This pair of routines creates an event and queues it onto a
+ * work-queue, where a worker thread can drive recovery.
+ */
+
+static DEFINE_SPINLOCK(eeh_eventlist_lock);
+static struct semaphore eeh_eventlist_sem;
+LIST_HEAD(eeh_eventlist);
+
+/**
+ * eeh_event_handler - Dispatch EEH events.
+ * @dummy - unused
+ *
+ * The detection of a frozen slot can occur inside an interrupt,
+ * where it can be hard to do anything about it. The goal of this
+ * routine is to pull these detection events out of the context
+ * of the interrupt handler, and re-dispatch them for processing
+ * at a later time in a normal context.
+ */
+static int eeh_event_handler(void * dummy)
+{
+ unsigned long flags;
+ struct eeh_event *event;
+ struct eeh_pe *pe;
+
+ while (!kthread_should_stop()) {
+ if (down_interruptible(&eeh_eventlist_sem))
+ break;
+
+ /* Fetch EEH event from the queue */
+ spin_lock_irqsave(&eeh_eventlist_lock, flags);
+ event = NULL;
+ if (!list_empty(&eeh_eventlist)) {
+ event = list_entry(eeh_eventlist.next,
+ struct eeh_event, list);
+ list_del(&event->list);
+ }
+ spin_unlock_irqrestore(&eeh_eventlist_lock, flags);
+ if (!event)
+ continue;
+
+ /* We might have event without binding PE */
+ pe = event->pe;
+ if (pe) {
+ eeh_pe_state_mark(pe, EEH_PE_RECOVERING);
+ if (pe->type & EEH_PE_PHB)
+ pr_info("EEH: Detected error on PHB#%d\n",
+ pe->phb->global_number);
+ else
+ pr_info("EEH: Detected PCI bus error on "
+ "PHB#%d-PE#%x\n",
+ pe->phb->global_number, pe->addr);
+ eeh_handle_event(pe);
+ eeh_pe_state_clear(pe, EEH_PE_RECOVERING);
+ } else {
+ eeh_handle_event(NULL);
+ }
+
+ kfree(event);
+ }
+
+ return 0;
+}
+
+/**
+ * eeh_event_init - Start kernel thread to handle EEH events
+ *
+ * This routine is called to start the kernel thread for processing
+ * EEH event.
+ */
+int eeh_event_init(void)
+{
+ struct task_struct *t;
+ int ret = 0;
+
+ /* Initialize semaphore */
+ sema_init(&eeh_eventlist_sem, 0);
+
+ t = kthread_run(eeh_event_handler, NULL, "eehd");
+ if (IS_ERR(t)) {
+ ret = PTR_ERR(t);
+ pr_err("%s: Failed to start EEH daemon (%d)\n",
+ __func__, ret);
+ return ret;
+ }
+
+ return 0;
+}
+
+/**
+ * eeh_send_failure_event - Generate a PCI error event
+ * @pe: EEH PE
+ *
+ * This routine can be called within an interrupt context;
+ * the actual event will be delivered in a normal context
+ * (from a workqueue).
+ */
+int eeh_send_failure_event(struct eeh_pe *pe)
+{
+ unsigned long flags;
+ struct eeh_event *event;
+
+ event = kzalloc(sizeof(*event), GFP_ATOMIC);
+ if (!event) {
+ pr_err("EEH: out of memory, event not handled\n");
+ return -ENOMEM;
+ }
+ event->pe = pe;
+
+ /* We may or may not be called in an interrupt context */
+ spin_lock_irqsave(&eeh_eventlist_lock, flags);
+ list_add(&event->list, &eeh_eventlist);
+ spin_unlock_irqrestore(&eeh_eventlist_lock, flags);
+
+ /* For EEH deamon to knick in */
+ up(&eeh_eventlist_sem);
+
+ return 0;
+}
+
+/**
+ * eeh_remove_event - Remove EEH event from the queue
+ * @pe: Event binding to the PE
+ * @force: Event will be removed unconditionally
+ *
+ * On PowerNV platform, we might have subsequent coming events
+ * is part of the former one. For that case, those subsequent
+ * coming events are totally duplicated and unnecessary, thus
+ * they should be removed.
+ */
+void eeh_remove_event(struct eeh_pe *pe, bool force)
+{
+ unsigned long flags;
+ struct eeh_event *event, *tmp;
+
+ /*
+ * If we have NULL PE passed in, we have dead IOC
+ * or we're sure we can report all existing errors
+ * by the caller.
+ *
+ * With "force", the event with associated PE that
+ * have been isolated, the event won't be removed
+ * to avoid event lost.
+ */
+ spin_lock_irqsave(&eeh_eventlist_lock, flags);
+ list_for_each_entry_safe(event, tmp, &eeh_eventlist, list) {
+ if (!force && event->pe &&
+ (event->pe->state & EEH_PE_ISOLATED))
+ continue;
+
+ if (!pe) {
+ list_del(&event->list);
+ kfree(event);
+ } else if (pe->type & EEH_PE_PHB) {
+ if (event->pe && event->pe->phb == pe->phb) {
+ list_del(&event->list);
+ kfree(event);
+ }
+ } else if (event->pe == pe) {
+ list_del(&event->list);
+ kfree(event);
+ }
+ }
+ spin_unlock_irqrestore(&eeh_eventlist_lock, flags);
+}
diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c
new file mode 100644
index 00000000000..fbd01eba447
--- /dev/null
+++ b/arch/powerpc/kernel/eeh_pe.c
@@ -0,0 +1,887 @@
+/*
+ * The file intends to implement PE based on the information from
+ * platforms. Basically, there have 3 types of PEs: PHB/Bus/Device.
+ * All the PEs should be organized as hierarchy tree. The first level
+ * of the tree will be associated to existing PHBs since the particular
+ * PE is only meaningful in one PHB domain.
+ *
+ * Copyright Benjamin Herrenschmidt & Gavin Shan, IBM Corporation 2012.
+ *
+ * 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/delay.h>
+#include <linux/export.h>
+#include <linux/gfp.h>
+#include <linux/kernel.h>
+#include <linux/pci.h>
+#include <linux/string.h>
+
+#include <asm/pci-bridge.h>
+#include <asm/ppc-pci.h>
+
+static LIST_HEAD(eeh_phb_pe);
+
+/**
+ * eeh_pe_alloc - Allocate PE
+ * @phb: PCI controller
+ * @type: PE type
+ *
+ * Allocate PE instance dynamically.
+ */
+static struct eeh_pe *eeh_pe_alloc(struct pci_controller *phb, int type)
+{
+ struct eeh_pe *pe;
+
+ /* Allocate PHB PE */
+ pe = kzalloc(sizeof(struct eeh_pe), GFP_KERNEL);
+ if (!pe) return NULL;
+
+ /* Initialize PHB PE */
+ pe->type = type;
+ pe->phb = phb;
+ INIT_LIST_HEAD(&pe->child_list);
+ INIT_LIST_HEAD(&pe->child);
+ INIT_LIST_HEAD(&pe->edevs);
+
+ return pe;
+}
+
+/**
+ * eeh_phb_pe_create - Create PHB PE
+ * @phb: PCI controller
+ *
+ * The function should be called while the PHB is detected during
+ * system boot or PCI hotplug in order to create PHB PE.
+ */
+int eeh_phb_pe_create(struct pci_controller *phb)
+{
+ struct eeh_pe *pe;
+
+ /* Allocate PHB PE */
+ pe = eeh_pe_alloc(phb, EEH_PE_PHB);
+ if (!pe) {
+ pr_err("%s: out of memory!\n", __func__);
+ return -ENOMEM;
+ }
+
+ /* Put it into the list */
+ list_add_tail(&pe->child, &eeh_phb_pe);
+
+ pr_debug("EEH: Add PE for PHB#%d\n", phb->global_number);
+
+ return 0;
+}
+
+/**
+ * eeh_phb_pe_get - Retrieve PHB PE based on the given PHB
+ * @phb: PCI controller
+ *
+ * The overall PEs form hierarchy tree. The first layer of the
+ * hierarchy tree is composed of PHB PEs. The function is used
+ * to retrieve the corresponding PHB PE according to the given PHB.
+ */
+struct eeh_pe *eeh_phb_pe_get(struct pci_controller *phb)
+{
+ struct eeh_pe *pe;
+
+ list_for_each_entry(pe, &eeh_phb_pe, child) {
+ /*
+ * Actually, we needn't check the type since
+ * the PE for PHB has been determined when that
+ * was created.
+ */
+ if ((pe->type & EEH_PE_PHB) && pe->phb == phb)
+ return pe;
+ }
+
+ return NULL;
+}
+
+/**
+ * eeh_pe_next - Retrieve the next PE in the tree
+ * @pe: current PE
+ * @root: root PE
+ *
+ * The function is used to retrieve the next PE in the
+ * hierarchy PE tree.
+ */
+static struct eeh_pe *eeh_pe_next(struct eeh_pe *pe,
+ struct eeh_pe *root)
+{
+ struct list_head *next = pe->child_list.next;
+
+ if (next == &pe->child_list) {
+ while (1) {
+ if (pe == root)
+ return NULL;
+ next = pe->child.next;
+ if (next != &pe->parent->child_list)
+ break;
+ pe = pe->parent;
+ }
+ }
+
+ return list_entry(next, struct eeh_pe, child);
+}
+
+/**
+ * eeh_pe_traverse - Traverse PEs in the specified PHB
+ * @root: root PE
+ * @fn: callback
+ * @flag: extra parameter to callback
+ *
+ * The function is used to traverse the specified PE and its
+ * child PEs. The traversing is to be terminated once the
+ * callback returns something other than NULL, or no more PEs
+ * to be traversed.
+ */
+void *eeh_pe_traverse(struct eeh_pe *root,
+ eeh_traverse_func fn, void *flag)
+{
+ struct eeh_pe *pe;
+ void *ret;
+
+ for (pe = root; pe; pe = eeh_pe_next(pe, root)) {
+ ret = fn(pe, flag);
+ if (ret) return ret;
+ }
+
+ return NULL;
+}
+
+/**
+ * eeh_pe_dev_traverse - Traverse the devices from the PE
+ * @root: EEH PE
+ * @fn: function callback
+ * @flag: extra parameter to callback
+ *
+ * The function is used to traverse the devices of the specified
+ * PE and its child PEs.
+ */
+void *eeh_pe_dev_traverse(struct eeh_pe *root,
+ eeh_traverse_func fn, void *flag)
+{
+ struct eeh_pe *pe;
+ struct eeh_dev *edev, *tmp;
+ void *ret;
+
+ if (!root) {
+ pr_warning("%s: Invalid PE %p\n", __func__, root);
+ return NULL;
+ }
+
+ /* Traverse root PE */
+ for (pe = root; pe; pe = eeh_pe_next(pe, root)) {
+ eeh_pe_for_each_dev(pe, edev, tmp) {
+ ret = fn(edev, flag);
+ if (ret)
+ return ret;
+ }
+ }
+
+ return NULL;
+}
+
+/**
+ * __eeh_pe_get - Check the PE address
+ * @data: EEH PE
+ * @flag: EEH device
+ *
+ * For one particular PE, it can be identified by PE address
+ * or tranditional BDF address. BDF address is composed of
+ * Bus/Device/Function number. The extra data referred by flag
+ * indicates which type of address should be used.
+ */
+static void *__eeh_pe_get(void *data, void *flag)
+{
+ struct eeh_pe *pe = (struct eeh_pe *)data;
+ struct eeh_dev *edev = (struct eeh_dev *)flag;
+
+ /* Unexpected PHB PE */
+ if (pe->type & EEH_PE_PHB)
+ return NULL;
+
+ /* We prefer PE address */
+ if (edev->pe_config_addr &&
+ (edev->pe_config_addr == pe->addr))
+ return pe;
+
+ /* Try BDF address */
+ if (edev->config_addr &&
+ (edev->config_addr == pe->config_addr))
+ return pe;
+
+ return NULL;
+}
+
+/**
+ * eeh_pe_get - Search PE based on the given address
+ * @edev: EEH device
+ *
+ * Search the corresponding PE based on the specified address which
+ * is included in the eeh device. The function is used to check if
+ * the associated PE has been created against the PE address. It's
+ * notable that the PE address has 2 format: traditional PE address
+ * which is composed of PCI bus/device/function number, or unified
+ * PE address.
+ */
+struct eeh_pe *eeh_pe_get(struct eeh_dev *edev)
+{
+ struct eeh_pe *root = eeh_phb_pe_get(edev->phb);
+ struct eeh_pe *pe;
+
+ pe = eeh_pe_traverse(root, __eeh_pe_get, edev);
+
+ return pe;
+}
+
+/**
+ * eeh_pe_get_parent - Retrieve the parent PE
+ * @edev: EEH device
+ *
+ * The whole PEs existing in the system are organized as hierarchy
+ * tree. The function is used to retrieve the parent PE according
+ * to the parent EEH device.
+ */
+static struct eeh_pe *eeh_pe_get_parent(struct eeh_dev *edev)
+{
+ struct device_node *dn;
+ struct eeh_dev *parent;
+
+ /*
+ * It might have the case for the indirect parent
+ * EEH device already having associated PE, but
+ * the direct parent EEH device doesn't have yet.
+ */
+ dn = edev->dn->parent;
+ while (dn) {
+ /* We're poking out of PCI territory */
+ if (!PCI_DN(dn)) return NULL;
+
+ parent = of_node_to_eeh_dev(dn);
+ /* We're poking out of PCI territory */
+ if (!parent) return NULL;
+
+ if (parent->pe)
+ return parent->pe;
+
+ dn = dn->parent;
+ }
+
+ return NULL;
+}
+
+/**
+ * eeh_add_to_parent_pe - Add EEH device to parent PE
+ * @edev: EEH device
+ *
+ * Add EEH device to the parent PE. If the parent PE already
+ * exists, the PE type will be changed to EEH_PE_BUS. Otherwise,
+ * we have to create new PE to hold the EEH device and the new
+ * PE will be linked to its parent PE as well.
+ */
+int eeh_add_to_parent_pe(struct eeh_dev *edev)
+{
+ struct eeh_pe *pe, *parent;
+
+ /*
+ * Search the PE has been existing or not according
+ * to the PE address. If that has been existing, the
+ * PE should be composed of PCI bus and its subordinate
+ * components.
+ */
+ pe = eeh_pe_get(edev);
+ if (pe && !(pe->type & EEH_PE_INVALID)) {
+ if (!edev->pe_config_addr) {
+ pr_err("%s: PE with addr 0x%x already exists\n",
+ __func__, edev->config_addr);
+ return -EEXIST;
+ }
+
+ /* Mark the PE as type of PCI bus */
+ pe->type = EEH_PE_BUS;
+ edev->pe = pe;
+
+ /* Put the edev to PE */
+ list_add_tail(&edev->list, &pe->edevs);
+ pr_debug("EEH: Add %s to Bus PE#%x\n",
+ edev->dn->full_name, pe->addr);
+
+ return 0;
+ } else if (pe && (pe->type & EEH_PE_INVALID)) {
+ list_add_tail(&edev->list, &pe->edevs);
+ edev->pe = pe;
+ /*
+ * We're running to here because of PCI hotplug caused by
+ * EEH recovery. We need clear EEH_PE_INVALID until the top.
+ */
+ parent = pe;
+ while (parent) {
+ if (!(parent->type & EEH_PE_INVALID))
+ break;
+ parent->type &= ~(EEH_PE_INVALID | EEH_PE_KEEP);
+ parent = parent->parent;
+ }
+ pr_debug("EEH: Add %s to Device PE#%x, Parent PE#%x\n",
+ edev->dn->full_name, pe->addr, pe->parent->addr);
+
+ return 0;
+ }
+
+ /* Create a new EEH PE */
+ pe = eeh_pe_alloc(edev->phb, EEH_PE_DEVICE);
+ if (!pe) {
+ pr_err("%s: out of memory!\n", __func__);
+ return -ENOMEM;
+ }
+ pe->addr = edev->pe_config_addr;
+ pe->config_addr = edev->config_addr;
+
+ /*
+ * While doing PE reset, we probably hot-reset the
+ * upstream bridge. However, the PCI devices including
+ * the associated EEH devices might be removed when EEH
+ * core is doing recovery. So that won't safe to retrieve
+ * the bridge through downstream EEH device. We have to
+ * trace the parent PCI bus, then the upstream bridge.
+ */
+ if (eeh_probe_mode_dev())
+ pe->bus = eeh_dev_to_pci_dev(edev)->bus;
+
+ /*
+ * Put the new EEH PE into hierarchy tree. If the parent
+ * can't be found, the newly created PE will be attached
+ * to PHB directly. Otherwise, we have to associate the
+ * PE with its parent.
+ */
+ parent = eeh_pe_get_parent(edev);
+ if (!parent) {
+ parent = eeh_phb_pe_get(edev->phb);
+ if (!parent) {
+ pr_err("%s: No PHB PE is found (PHB Domain=%d)\n",
+ __func__, edev->phb->global_number);
+ edev->pe = NULL;
+ kfree(pe);
+ return -EEXIST;
+ }
+ }
+ pe->parent = parent;
+
+ /*
+ * Put the newly created PE into the child list and
+ * link the EEH device accordingly.
+ */
+ list_add_tail(&pe->child, &parent->child_list);
+ list_add_tail(&edev->list, &pe->edevs);
+ edev->pe = pe;
+ pr_debug("EEH: Add %s to Device PE#%x, Parent PE#%x\n",
+ edev->dn->full_name, pe->addr, pe->parent->addr);
+
+ return 0;
+}
+
+/**
+ * eeh_rmv_from_parent_pe - Remove one EEH device from the associated PE
+ * @edev: EEH device
+ *
+ * The PE hierarchy tree might be changed when doing PCI hotplug.
+ * Also, the PCI devices or buses could be removed from the system
+ * during EEH recovery. So we have to call the function remove the
+ * corresponding PE accordingly if necessary.
+ */
+int eeh_rmv_from_parent_pe(struct eeh_dev *edev)
+{
+ struct eeh_pe *pe, *parent, *child;
+ int cnt;
+
+ if (!edev->pe) {
+ pr_debug("%s: No PE found for EEH device %s\n",
+ __func__, edev->dn->full_name);
+ return -EEXIST;
+ }
+
+ /* Remove the EEH device */
+ pe = edev->pe;
+ edev->pe = NULL;
+ list_del(&edev->list);
+
+ /*
+ * Check if the parent PE includes any EEH devices.
+ * If not, we should delete that. Also, we should
+ * delete the parent PE if it doesn't have associated
+ * child PEs and EEH devices.
+ */
+ while (1) {
+ parent = pe->parent;
+ if (pe->type & EEH_PE_PHB)
+ break;
+
+ if (!(pe->state & EEH_PE_KEEP)) {
+ if (list_empty(&pe->edevs) &&
+ list_empty(&pe->child_list)) {
+ list_del(&pe->child);
+ kfree(pe);
+ } else {
+ break;
+ }
+ } else {
+ if (list_empty(&pe->edevs)) {
+ cnt = 0;
+ list_for_each_entry(child, &pe->child_list, child) {
+ if (!(child->type & EEH_PE_INVALID)) {
+ cnt++;
+ break;
+ }
+ }
+
+ if (!cnt)
+ pe->type |= EEH_PE_INVALID;
+ else
+ break;
+ }
+ }
+
+ pe = parent;
+ }
+
+ return 0;
+}
+
+/**
+ * eeh_pe_update_time_stamp - Update PE's frozen time stamp
+ * @pe: EEH PE
+ *
+ * We have time stamp for each PE to trace its time of getting
+ * frozen in last hour. The function should be called to update
+ * the time stamp on first error of the specific PE. On the other
+ * handle, we needn't account for errors happened in last hour.
+ */
+void eeh_pe_update_time_stamp(struct eeh_pe *pe)
+{
+ struct timeval tstamp;
+
+ if (!pe) return;
+
+ if (pe->freeze_count <= 0) {
+ pe->freeze_count = 0;
+ do_gettimeofday(&pe->tstamp);
+ } else {
+ do_gettimeofday(&tstamp);
+ if (tstamp.tv_sec - pe->tstamp.tv_sec > 3600) {
+ pe->tstamp = tstamp;
+ pe->freeze_count = 0;
+ }
+ }
+}
+
+/**
+ * __eeh_pe_state_mark - Mark the state for the PE
+ * @data: EEH PE
+ * @flag: state
+ *
+ * The function is used to mark the indicated state for the given
+ * PE. Also, the associated PCI devices will be put into IO frozen
+ * state as well.
+ */
+static void *__eeh_pe_state_mark(void *data, void *flag)
+{
+ struct eeh_pe *pe = (struct eeh_pe *)data;
+ int state = *((int *)flag);
+ struct eeh_dev *edev, *tmp;
+ struct pci_dev *pdev;
+
+ /* Keep the state of permanently removed PE intact */
+ if ((pe->freeze_count > EEH_MAX_ALLOWED_FREEZES) &&
+ (state & (EEH_PE_ISOLATED | EEH_PE_RECOVERING)))
+ return NULL;
+
+ pe->state |= state;
+
+ /* Offline PCI devices if applicable */
+ if (state != EEH_PE_ISOLATED)
+ return NULL;
+
+ eeh_pe_for_each_dev(pe, edev, tmp) {
+ pdev = eeh_dev_to_pci_dev(edev);
+ if (pdev)
+ pdev->error_state = pci_channel_io_frozen;
+ }
+
+ return NULL;
+}
+
+/**
+ * eeh_pe_state_mark - Mark specified state for PE and its associated device
+ * @pe: EEH PE
+ *
+ * EEH error affects the current PE and its child PEs. The function
+ * is used to mark appropriate state for the affected PEs and the
+ * associated devices.
+ */
+void eeh_pe_state_mark(struct eeh_pe *pe, int state)
+{
+ eeh_pe_traverse(pe, __eeh_pe_state_mark, &state);
+}
+
+static void *__eeh_pe_dev_mode_mark(void *data, void *flag)
+{
+ struct eeh_dev *edev = data;
+ int mode = *((int *)flag);
+
+ edev->mode |= mode;
+
+ return NULL;
+}
+
+/**
+ * eeh_pe_dev_state_mark - Mark state for all device under the PE
+ * @pe: EEH PE
+ *
+ * Mark specific state for all child devices of the PE.
+ */
+void eeh_pe_dev_mode_mark(struct eeh_pe *pe, int mode)
+{
+ eeh_pe_dev_traverse(pe, __eeh_pe_dev_mode_mark, &mode);
+}
+
+/**
+ * __eeh_pe_state_clear - Clear state for the PE
+ * @data: EEH PE
+ * @flag: state
+ *
+ * The function is used to clear the indicated state from the
+ * given PE. Besides, we also clear the check count of the PE
+ * as well.
+ */
+static void *__eeh_pe_state_clear(void *data, void *flag)
+{
+ struct eeh_pe *pe = (struct eeh_pe *)data;
+ int state = *((int *)flag);
+
+ /* Keep the state of permanently removed PE intact */
+ if ((pe->freeze_count > EEH_MAX_ALLOWED_FREEZES) &&
+ (state & EEH_PE_ISOLATED))
+ return NULL;
+
+ pe->state &= ~state;
+
+ /* Clear check count since last isolation */
+ if (state & EEH_PE_ISOLATED)
+ pe->check_count = 0;
+
+ return NULL;
+}
+
+/**
+ * eeh_pe_state_clear - Clear state for the PE and its children
+ * @pe: PE
+ * @state: state to be cleared
+ *
+ * When the PE and its children has been recovered from error,
+ * we need clear the error state for that. The function is used
+ * for the purpose.
+ */
+void eeh_pe_state_clear(struct eeh_pe *pe, int state)
+{
+ eeh_pe_traverse(pe, __eeh_pe_state_clear, &state);
+}
+
+/*
+ * Some PCI bridges (e.g. PLX bridges) have primary/secondary
+ * buses assigned explicitly by firmware, and we probably have
+ * lost that after reset. So we have to delay the check until
+ * the PCI-CFG registers have been restored for the parent
+ * bridge.
+ *
+ * Don't use normal PCI-CFG accessors, which probably has been
+ * blocked on normal path during the stage. So we need utilize
+ * eeh operations, which is always permitted.
+ */
+static void eeh_bridge_check_link(struct eeh_dev *edev,
+ struct device_node *dn)
+{
+ int cap;
+ uint32_t val;
+ int timeout = 0;
+
+ /*
+ * We only check root port and downstream ports of
+ * PCIe switches
+ */
+ if (!(edev->mode & (EEH_DEV_ROOT_PORT | EEH_DEV_DS_PORT)))
+ return;
+
+ pr_debug("%s: Check PCIe link for %04x:%02x:%02x.%01x ...\n",
+ __func__, edev->phb->global_number,
+ edev->config_addr >> 8,
+ PCI_SLOT(edev->config_addr & 0xFF),
+ PCI_FUNC(edev->config_addr & 0xFF));
+
+ /* Check slot status */
+ cap = edev->pcie_cap;
+ eeh_ops->read_config(dn, cap + PCI_EXP_SLTSTA, 2, &val);
+ if (!(val & PCI_EXP_SLTSTA_PDS)) {
+ pr_debug(" No card in the slot (0x%04x) !\n", val);
+ return;
+ }
+
+ /* Check power status if we have the capability */
+ eeh_ops->read_config(dn, cap + PCI_EXP_SLTCAP, 2, &val);
+ if (val & PCI_EXP_SLTCAP_PCP) {
+ eeh_ops->read_config(dn, cap + PCI_EXP_SLTCTL, 2, &val);
+ if (val & PCI_EXP_SLTCTL_PCC) {
+ pr_debug(" In power-off state, power it on ...\n");
+ val &= ~(PCI_EXP_SLTCTL_PCC | PCI_EXP_SLTCTL_PIC);
+ val |= (0x0100 & PCI_EXP_SLTCTL_PIC);
+ eeh_ops->write_config(dn, cap + PCI_EXP_SLTCTL, 2, val);
+ msleep(2 * 1000);
+ }
+ }
+
+ /* Enable link */
+ eeh_ops->read_config(dn, cap + PCI_EXP_LNKCTL, 2, &val);
+ val &= ~PCI_EXP_LNKCTL_LD;
+ eeh_ops->write_config(dn, cap + PCI_EXP_LNKCTL, 2, val);
+
+ /* Check link */
+ eeh_ops->read_config(dn, cap + PCI_EXP_LNKCAP, 4, &val);
+ if (!(val & PCI_EXP_LNKCAP_DLLLARC)) {
+ pr_debug(" No link reporting capability (0x%08x) \n", val);
+ msleep(1000);
+ return;
+ }
+
+ /* Wait the link is up until timeout (5s) */
+ timeout = 0;
+ while (timeout < 5000) {
+ msleep(20);
+ timeout += 20;
+
+ eeh_ops->read_config(dn, cap + PCI_EXP_LNKSTA, 2, &val);
+ if (val & PCI_EXP_LNKSTA_DLLLA)
+ break;
+ }
+
+ if (val & PCI_EXP_LNKSTA_DLLLA)
+ pr_debug(" Link up (%s)\n",
+ (val & PCI_EXP_LNKSTA_CLS_2_5GB) ? "2.5GB" : "5GB");
+ else
+ pr_debug(" Link not ready (0x%04x)\n", val);
+}
+
+#define BYTE_SWAP(OFF) (8*((OFF)/4)+3-(OFF))
+#define SAVED_BYTE(OFF) (((u8 *)(edev->config_space))[BYTE_SWAP(OFF)])
+
+static void eeh_restore_bridge_bars(struct eeh_dev *edev,
+ struct device_node *dn)
+{
+ int i;
+
+ /*
+ * Device BARs: 0x10 - 0x18
+ * Bus numbers and windows: 0x18 - 0x30
+ */
+ for (i = 4; i < 13; i++)
+ eeh_ops->write_config(dn, i*4, 4, edev->config_space[i]);
+ /* Rom: 0x38 */
+ eeh_ops->write_config(dn, 14*4, 4, edev->config_space[14]);
+
+ /* Cache line & Latency timer: 0xC 0xD */
+ eeh_ops->write_config(dn, PCI_CACHE_LINE_SIZE, 1,
+ SAVED_BYTE(PCI_CACHE_LINE_SIZE));
+ eeh_ops->write_config(dn, PCI_LATENCY_TIMER, 1,
+ SAVED_BYTE(PCI_LATENCY_TIMER));
+ /* Max latency, min grant, interrupt ping and line: 0x3C */
+ eeh_ops->write_config(dn, 15*4, 4, edev->config_space[15]);
+
+ /* PCI Command: 0x4 */
+ eeh_ops->write_config(dn, PCI_COMMAND, 4, edev->config_space[1]);
+
+ /* Check the PCIe link is ready */
+ eeh_bridge_check_link(edev, dn);
+}
+
+static void eeh_restore_device_bars(struct eeh_dev *edev,
+ struct device_node *dn)
+{
+ int i;
+ u32 cmd;
+
+ for (i = 4; i < 10; i++)
+ eeh_ops->write_config(dn, i*4, 4, edev->config_space[i]);
+ /* 12 == Expansion ROM Address */
+ eeh_ops->write_config(dn, 12*4, 4, edev->config_space[12]);
+
+ eeh_ops->write_config(dn, PCI_CACHE_LINE_SIZE, 1,
+ SAVED_BYTE(PCI_CACHE_LINE_SIZE));
+ eeh_ops->write_config(dn, PCI_LATENCY_TIMER, 1,
+ SAVED_BYTE(PCI_LATENCY_TIMER));
+
+ /* max latency, min grant, interrupt pin and line */
+ eeh_ops->write_config(dn, 15*4, 4, edev->config_space[15]);
+
+ /*
+ * Restore PERR & SERR bits, some devices require it,
+ * don't touch the other command bits
+ */
+ eeh_ops->read_config(dn, PCI_COMMAND, 4, &cmd);
+ if (edev->config_space[1] & PCI_COMMAND_PARITY)
+ cmd |= PCI_COMMAND_PARITY;
+ else
+ cmd &= ~PCI_COMMAND_PARITY;
+ if (edev->config_space[1] & PCI_COMMAND_SERR)
+ cmd |= PCI_COMMAND_SERR;
+ else
+ cmd &= ~PCI_COMMAND_SERR;
+ eeh_ops->write_config(dn, PCI_COMMAND, 4, cmd);
+}
+
+/**
+ * eeh_restore_one_device_bars - Restore the Base Address Registers for one device
+ * @data: EEH device
+ * @flag: Unused
+ *
+ * Loads the PCI configuration space base address registers,
+ * the expansion ROM base address, the latency timer, and etc.
+ * from the saved values in the device node.
+ */
+static void *eeh_restore_one_device_bars(void *data, void *flag)
+{
+ struct eeh_dev *edev = (struct eeh_dev *)data;
+ struct device_node *dn = eeh_dev_to_of_node(edev);
+
+ /* Do special restore for bridges */
+ if (edev->mode & EEH_DEV_BRIDGE)
+ eeh_restore_bridge_bars(edev, dn);
+ else
+ eeh_restore_device_bars(edev, dn);
+
+ if (eeh_ops->restore_config)
+ eeh_ops->restore_config(dn);
+
+ return NULL;
+}
+
+/**
+ * eeh_pe_restore_bars - Restore the PCI config space info
+ * @pe: EEH PE
+ *
+ * This routine performs a recursive walk to the children
+ * of this device as well.
+ */
+void eeh_pe_restore_bars(struct eeh_pe *pe)
+{
+ /*
+ * We needn't take the EEH lock since eeh_pe_dev_traverse()
+ * will take that.
+ */
+ eeh_pe_dev_traverse(pe, eeh_restore_one_device_bars, NULL);
+}
+
+/**
+ * eeh_pe_loc_get - Retrieve location code binding to the given PE
+ * @pe: EEH PE
+ *
+ * Retrieve the location code of the given PE. If the primary PE bus
+ * is root bus, we will grab location code from PHB device tree node
+ * or root port. Otherwise, the upstream bridge's device tree node
+ * of the primary PE bus will be checked for the location code.
+ */
+const char *eeh_pe_loc_get(struct eeh_pe *pe)
+{
+ struct pci_controller *hose;
+ struct pci_bus *bus = eeh_pe_bus_get(pe);
+ struct pci_dev *pdev;
+ struct device_node *dn;
+ const char *loc;
+
+ if (!bus)
+ return "N/A";
+
+ /* PHB PE or root PE ? */
+ if (pci_is_root_bus(bus)) {
+ hose = pci_bus_to_host(bus);
+ loc = of_get_property(hose->dn,
+ "ibm,loc-code", NULL);
+ if (loc)
+ return loc;
+ loc = of_get_property(hose->dn,
+ "ibm,io-base-loc-code", NULL);
+ if (loc)
+ return loc;
+
+ pdev = pci_get_slot(bus, 0x0);
+ } else {
+ pdev = bus->self;
+ }
+
+ if (!pdev) {
+ loc = "N/A";
+ goto out;
+ }
+
+ dn = pci_device_to_OF_node(pdev);
+ if (!dn) {
+ loc = "N/A";
+ goto out;
+ }
+
+ loc = of_get_property(dn, "ibm,loc-code", NULL);
+ if (!loc)
+ loc = of_get_property(dn, "ibm,slot-location-code", NULL);
+ if (!loc)
+ loc = "N/A";
+
+out:
+ if (pci_is_root_bus(bus) && pdev)
+ pci_dev_put(pdev);
+ return loc;
+}
+
+/**
+ * eeh_pe_bus_get - Retrieve PCI bus according to the given PE
+ * @pe: EEH PE
+ *
+ * Retrieve the PCI bus according to the given PE. Basically,
+ * there're 3 types of PEs: PHB/Bus/Device. For PHB PE, the
+ * primary PCI bus will be retrieved. The parent bus will be
+ * returned for BUS PE. However, we don't have associated PCI
+ * bus for DEVICE PE.
+ */
+struct pci_bus *eeh_pe_bus_get(struct eeh_pe *pe)
+{
+ struct pci_bus *bus = NULL;
+ struct eeh_dev *edev;
+ struct pci_dev *pdev;
+
+ if (pe->type & EEH_PE_PHB) {
+ bus = pe->phb->bus;
+ } else if (pe->type & EEH_PE_BUS ||
+ pe->type & EEH_PE_DEVICE) {
+ if (pe->bus) {
+ bus = pe->bus;
+ goto out;
+ }
+
+ edev = list_first_entry(&pe->edevs, struct eeh_dev, list);
+ pdev = eeh_dev_to_pci_dev(edev);
+ if (pdev)
+ bus = pdev->bus;
+ }
+
+out:
+ return bus;
+}
diff --git a/arch/powerpc/kernel/eeh_sysfs.c b/arch/powerpc/kernel/eeh_sysfs.c
new file mode 100644
index 00000000000..e2595ba4b72
--- /dev/null
+++ b/arch/powerpc/kernel/eeh_sysfs.c
@@ -0,0 +1,98 @@
+/*
+ * Sysfs entries for PCI Error Recovery for PAPR-compliant platform.
+ * Copyright IBM Corporation 2007
+ * Copyright Linas Vepstas <linas@austin.ibm.com> 2007
+ *
+ * All rights reserved.
+ *
+ * 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, GOOD TITLE or
+ * NON INFRINGEMENT. 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., 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ * Send comments and feedback to Linas Vepstas <linas@austin.ibm.com>
+ */
+#include <linux/pci.h>
+#include <linux/stat.h>
+#include <asm/ppc-pci.h>
+#include <asm/pci-bridge.h>
+
+/**
+ * EEH_SHOW_ATTR -- Create sysfs entry for eeh statistic
+ * @_name: name of file in sysfs directory
+ * @_memb: name of member in struct pci_dn to access
+ * @_format: printf format for display
+ *
+ * All of the attributes look very similar, so just
+ * auto-gen a cut-n-paste routine to display them.
+ */
+#define EEH_SHOW_ATTR(_name,_memb,_format) \
+static ssize_t eeh_show_##_name(struct device *dev, \
+ struct device_attribute *attr, char *buf) \
+{ \
+ struct pci_dev *pdev = to_pci_dev(dev); \
+ struct eeh_dev *edev = pci_dev_to_eeh_dev(pdev); \
+ \
+ if (!edev) \
+ return 0; \
+ \
+ return sprintf(buf, _format "\n", edev->_memb); \
+} \
+static DEVICE_ATTR(_name, S_IRUGO, eeh_show_##_name, NULL);
+
+EEH_SHOW_ATTR(eeh_mode, mode, "0x%x");
+EEH_SHOW_ATTR(eeh_config_addr, config_addr, "0x%x");
+EEH_SHOW_ATTR(eeh_pe_config_addr, pe_config_addr, "0x%x");
+
+void eeh_sysfs_add_device(struct pci_dev *pdev)
+{
+ struct eeh_dev *edev = pci_dev_to_eeh_dev(pdev);
+ int rc=0;
+
+ if (!eeh_enabled())
+ return;
+
+ if (edev && (edev->mode & EEH_DEV_SYSFS))
+ return;
+
+ rc += device_create_file(&pdev->dev, &dev_attr_eeh_mode);
+ rc += device_create_file(&pdev->dev, &dev_attr_eeh_config_addr);
+ rc += device_create_file(&pdev->dev, &dev_attr_eeh_pe_config_addr);
+
+ if (rc)
+ printk(KERN_WARNING "EEH: Unable to create sysfs entries\n");
+ else if (edev)
+ edev->mode |= EEH_DEV_SYSFS;
+}
+
+void eeh_sysfs_remove_device(struct pci_dev *pdev)
+{
+ struct eeh_dev *edev = pci_dev_to_eeh_dev(pdev);
+
+ /*
+ * The parent directory might have been removed. We needn't
+ * continue for that case.
+ */
+ if (!pdev->dev.kobj.sd) {
+ if (edev)
+ edev->mode &= ~EEH_DEV_SYSFS;
+ return;
+ }
+
+ device_remove_file(&pdev->dev, &dev_attr_eeh_mode);
+ device_remove_file(&pdev->dev, &dev_attr_eeh_config_addr);
+ device_remove_file(&pdev->dev, &dev_attr_eeh_pe_config_addr);
+
+ if (edev)
+ edev->mode &= ~EEH_DEV_SYSFS;
+}
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index 4f80cf1ce77..22b45a4955c 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -89,6 +89,10 @@ crit_transfer_to_handler:
mfspr r0,SPRN_SRR1
stw r0,_SRR1(r11)
+ /* set the stack limit to the current stack
+ * and set the limit to protect the thread_info
+ * struct
+ */
mfspr r8,SPRN_SPRG_THREAD
lwz r0,KSP_LIMIT(r8)
stw r0,SAVED_KSP_LIMIT(r11)
@@ -109,6 +113,10 @@ crit_transfer_to_handler:
mfspr r0,SPRN_SRR1
stw r0,crit_srr1@l(0)
+ /* set the stack limit to the current stack
+ * and set the limit to protect the thread_info
+ * struct
+ */
mfspr r8,SPRN_SPRG_THREAD
lwz r0,KSP_LIMIT(r8)
stw r0,saved_ksp_limit@l(0)
@@ -158,7 +166,7 @@ transfer_to_handler:
tophys(r11,r11)
addi r11,r11,global_dbcr0@l
#ifdef CONFIG_SMP
- rlwinm r9,r1,0,0,(31-THREAD_SHIFT)
+ CURRENT_THREAD_INFO(r9, r1)
lwz r9,TI_CPU(r9)
slwi r9,r9,3
add r11,r11,r9
@@ -179,7 +187,7 @@ transfer_to_handler:
ble- stack_ovf /* then the kernel stack overflowed */
5:
#if defined(CONFIG_6xx) || defined(CONFIG_E500)
- rlwinm r9,r1,0,0,31-THREAD_SHIFT
+ CURRENT_THREAD_INFO(r9, r1)
tophys(r9,r9) /* check local flags */
lwz r12,TI_LOCAL_FLAGS(r9)
mtcrf 0x01,r12
@@ -206,40 +214,37 @@ reenable_mmu: /* re-enable mmu so we can */
andi. r10,r10,MSR_EE /* Did EE change? */
beq 1f
- /* Save handler and return address into the 2 unused words
- * of the STACK_FRAME_OVERHEAD (sneak sneak sneak). Everything
- * else can be recovered from the pt_regs except r3 which for
- * normal interrupts has been set to pt_regs and for syscalls
- * is an argument, so we temporarily use ORIG_GPR3 to save it
- */
- stw r9,8(r1)
- stw r11,12(r1)
- stw r3,ORIG_GPR3(r1)
/*
* The trace_hardirqs_off will use CALLER_ADDR0 and CALLER_ADDR1.
* If from user mode there is only one stack frame on the stack, and
* accessing CALLER_ADDR1 will cause oops. So we need create a dummy
* stack frame to make trace_hardirqs_off happy.
+ *
+ * This is handy because we also need to save a bunch of GPRs,
+ * r3 can be different from GPR3(r1) at this point, r9 and r11
+ * contains the old MSR and handler address respectively,
+ * r4 & r5 can contain page fault arguments that need to be passed
+ * along as well. r12, CCR, CTR, XER etc... are left clobbered as
+ * they aren't useful past this point (aren't syscall arguments),
+ * the rest is restored from the exception frame.
*/
- andi. r12,r12,MSR_PR
- beq 11f
- stwu r1,-16(r1)
- bl trace_hardirqs_off
- addi r1,r1,16
- b 12f
-
-11:
+ stwu r1,-32(r1)
+ stw r9,8(r1)
+ stw r11,12(r1)
+ stw r3,16(r1)
+ stw r4,20(r1)
+ stw r5,24(r1)
bl trace_hardirqs_off
-12:
+ lwz r5,24(r1)
+ lwz r4,20(r1)
+ lwz r3,16(r1)
+ lwz r11,12(r1)
+ lwz r9,8(r1)
+ addi r1,r1,32
lwz r0,GPR0(r1)
- lwz r3,ORIG_GPR3(r1)
- lwz r4,GPR4(r1)
- lwz r5,GPR5(r1)
lwz r6,GPR6(r1)
lwz r7,GPR7(r1)
lwz r8,GPR8(r1)
- lwz r9,8(r1)
- lwz r11,12(r1)
1: mtctr r11
mtlr r9
bctr /* jump to handler */
@@ -330,7 +335,7 @@ _GLOBAL(DoSyscall)
mtmsr r11
1:
#endif /* CONFIG_TRACE_IRQFLAGS */
- rlwinm r10,r1,0,0,(31-THREAD_SHIFT) /* current_thread_info() */
+ CURRENT_THREAD_INFO(r10, r1)
lwz r11,TI_FLAGS(r10)
andi. r11,r11,_TIF_SYSCALL_T_OR_A
bne- syscall_dotrace
@@ -351,7 +356,7 @@ ret_from_syscall:
bl do_show_syscall_exit
#endif
mr r6,r3
- rlwinm r12,r1,0,0,(31-THREAD_SHIFT) /* current_thread_info() */
+ CURRENT_THREAD_INFO(r12, r1)
/* disable interrupts so current_thread_info()->flags can't change */
LOAD_MSR_KERNEL(r10,MSR_KERNEL) /* doesn't include MSR_EE */
/* Note: We don't bother telling lockdep about it */
@@ -430,6 +435,17 @@ ret_from_fork:
li r3,0
b ret_from_syscall
+ .globl ret_from_kernel_thread
+ret_from_kernel_thread:
+ REST_NVGPRS(r1)
+ bl schedule_tail
+ mtlr r14
+ mr r3,r15
+ PPC440EP_ERR42
+ blrl
+ li r3,0
+ b ret_from_syscall
+
/* Traced system call support */
syscall_dotrace:
SAVE_NVGPRS(r1)
@@ -812,7 +828,7 @@ ret_from_except:
user_exc_return: /* r10 contains MSR_KERNEL here */
/* Check current_thread_info()->flags */
- rlwinm r9,r1,0,0,(31-THREAD_SHIFT)
+ CURRENT_THREAD_INFO(r9, r1)
lwz r9,TI_FLAGS(r9)
andi. r0,r9,_TIF_USER_WORK_MASK
bne do_work
@@ -826,19 +842,56 @@ restore_user:
bnel- load_dbcr0
#endif
-#ifdef CONFIG_PREEMPT
b restore
/* N.B. the only way to get here is from the beq following ret_from_except. */
resume_kernel:
+ /* check current_thread_info, _TIF_EMULATE_STACK_STORE */
+ CURRENT_THREAD_INFO(r9, r1)
+ lwz r8,TI_FLAGS(r9)
+ andis. r0,r8,_TIF_EMULATE_STACK_STORE@h
+ beq+ 1f
+
+ addi r8,r1,INT_FRAME_SIZE /* Get the kprobed function entry */
+
+ lwz r3,GPR1(r1)
+ subi r3,r3,INT_FRAME_SIZE /* dst: Allocate a trampoline exception frame */
+ mr r4,r1 /* src: current exception frame */
+ mr r1,r3 /* Reroute the trampoline frame to r1 */
+
+ /* Copy from the original to the trampoline. */
+ li r5,INT_FRAME_SIZE/4 /* size: INT_FRAME_SIZE */
+ li r6,0 /* start offset: 0 */
+ mtctr r5
+2: lwzx r0,r6,r4
+ stwx r0,r6,r3
+ addi r6,r6,4
+ bdnz 2b
+
+ /* Do real store operation to complete stwu */
+ lwz r5,GPR1(r1)
+ stw r8,0(r5)
+
+ /* Clear _TIF_EMULATE_STACK_STORE flag */
+ lis r11,_TIF_EMULATE_STACK_STORE@h
+ addi r5,r9,TI_FLAGS
+0: lwarx r8,0,r5
+ andc r8,r8,r11
+#ifdef CONFIG_IBM405_ERR77
+ dcbt 0,r5
+#endif
+ stwcx. r8,0,r5
+ bne- 0b
+1:
+
+#ifdef CONFIG_PREEMPT
/* check current_thread_info->preempt_count */
- rlwinm r9,r1,0,0,(31-THREAD_SHIFT)
lwz r0,TI_PREEMPT(r9)
cmpwi 0,r0,0 /* if non-zero, just restore regs and return */
bne restore
- lwz r0,TI_FLAGS(r9)
- andi. r0,r0,_TIF_NEED_RESCHED
+ andi. r8,r8,_TIF_NEED_RESCHED
beq+ restore
+ lwz r3,_MSR(r1)
andi. r0,r3,MSR_EE /* interrupts off? */
beq restore /* don't schedule if so */
#ifdef CONFIG_TRACE_IRQFLAGS
@@ -849,7 +902,7 @@ resume_kernel:
bl trace_hardirqs_off
#endif
1: bl preempt_schedule_irq
- rlwinm r9,r1,0,0,(31-THREAD_SHIFT)
+ CURRENT_THREAD_INFO(r9, r1)
lwz r3,TI_FLAGS(r9)
andi. r0,r3,_TIF_NEED_RESCHED
bne- 1b
@@ -859,8 +912,6 @@ resume_kernel:
*/
bl trace_hardirqs_on
#endif
-#else
-resume_kernel:
#endif /* CONFIG_PREEMPT */
/* interrupts are hard-disabled at this point */
@@ -1119,7 +1170,7 @@ ret_from_debug_exc:
lwz r10,SAVED_KSP_LIMIT(r1)
stw r10,KSP_LIMIT(r9)
lwz r9,THREAD_INFO-THREAD(r9)
- rlwinm r10,r1,0,0,(31-THREAD_SHIFT)
+ CURRENT_THREAD_INFO(r10, r1)
lwz r10,TI_PREEMPT(r10)
stw r10,TI_PREEMPT(r9)
RESTORE_xSRR(SRR0,SRR1);
@@ -1153,7 +1204,7 @@ load_dbcr0:
lis r11,global_dbcr0@ha
addi r11,r11,global_dbcr0@l
#ifdef CONFIG_SMP
- rlwinm r9,r1,0,0,(31-THREAD_SHIFT)
+ CURRENT_THREAD_INFO(r9, r1)
lwz r9,TI_CPU(r9)
slwi r9,r9,3
add r11,r11,r9
@@ -1194,7 +1245,7 @@ recheck:
LOAD_MSR_KERNEL(r10,MSR_KERNEL)
SYNC
MTMSRD(r10) /* disable interrupts */
- rlwinm r9,r1,0,0,(31-THREAD_SHIFT)
+ CURRENT_THREAD_INFO(r9, r1)
lwz r9,TI_FLAGS(r9)
andi. r0,r9,_TIF_NEED_RESCHED
bne- do_resched
@@ -1213,7 +1264,7 @@ do_user_signal: /* r10 contains MSR_KERNEL here */
stw r3,_TRAP(r1)
2: addi r3,r1,STACK_FRAME_OVERHEAD
mr r4,r9
- bl do_signal
+ bl do_notify_resume
REST_NVGPRS(r1)
b recheck
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index d834425186a..6528c5e2cc4 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -32,13 +32,15 @@
#include <asm/ptrace.h>
#include <asm/irqflags.h>
#include <asm/ftrace.h>
+#include <asm/hw_irq.h>
+#include <asm/context_tracking.h>
/*
* System calls.
*/
.section ".toc","aw"
-.SYS_CALL_TABLE:
- .tc .sys_call_table[TC],.sys_call_table
+SYS_CALL_TABLE:
+ .tc sys_call_table[TC],sys_call_table
/* This value is used to mark exception frames on the stack. */
exception_marker:
@@ -61,16 +63,11 @@ system_call_common:
std r12,_MSR(r1)
std r0,GPR0(r1)
std r10,GPR1(r1)
+ beq 2f /* if from kernel mode */
ACCOUNT_CPU_USER_ENTRY(r10, r11)
- /*
- * This "crclr so" clears CR0.SO, which is the error indication on
- * return from this system call. There must be no cmp instruction
- * between it and the "mfcr r9" below, otherwise if XER.SO is set,
- * CR0.SO will get set, causing all system calls to appear to fail.
- */
- crclr so
- std r2,GPR2(r1)
+2: std r2,GPR2(r1)
std r3,GPR3(r1)
+ mfcr r2
std r4,GPR4(r1)
std r5,GPR5(r1)
std r6,GPR6(r1)
@@ -81,85 +78,82 @@ system_call_common:
std r11,GPR10(r1)
std r11,GPR11(r1)
std r11,GPR12(r1)
+ std r11,_XER(r1)
+ std r11,_CTR(r1)
std r9,GPR13(r1)
- mfcr r9
mflr r10
+ /*
+ * This clears CR0.SO (bit 28), which is the error indication on
+ * return from this system call.
+ */
+ rldimi r2,r11,28,(63-28)
li r11,0xc01
- std r9,_CCR(r1)
std r10,_LINK(r1)
std r11,_TRAP(r1)
- mfxer r9
- mfctr r10
- std r9,_XER(r1)
- std r10,_CTR(r1)
std r3,ORIG_GPR3(r1)
+ std r2,_CCR(r1)
ld r2,PACATOC(r13)
addi r9,r1,STACK_FRAME_OVERHEAD
ld r11,exception_marker@toc(r2)
std r11,-16(r9) /* "regshere" marker */
-#if defined(CONFIG_VIRT_CPU_ACCOUNTING) && defined(CONFIG_PPC_SPLPAR)
+#if defined(CONFIG_VIRT_CPU_ACCOUNTING_NATIVE) && defined(CONFIG_PPC_SPLPAR)
BEGIN_FW_FTR_SECTION
beq 33f
/* if from user, see if there are any DTL entries to process */
ld r10,PACALPPACAPTR(r13) /* get ptr to VPA */
ld r11,PACA_DTL_RIDX(r13) /* get log read index */
- ld r10,LPPACA_DTLIDX(r10) /* get log write index */
+ addi r10,r10,LPPACA_DTLIDX
+ LDX_BE r10,0,r10 /* get log write index */
cmpd cr1,r11,r10
beq+ cr1,33f
- bl .accumulate_stolen_time
+ bl accumulate_stolen_time
REST_GPR(0,r1)
REST_4GPRS(3,r1)
REST_2GPRS(7,r1)
addi r9,r1,STACK_FRAME_OVERHEAD
33:
END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLPAR)
-#endif /* CONFIG_VIRT_CPU_ACCOUNTING && CONFIG_PPC_SPLPAR */
+#endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE && CONFIG_PPC_SPLPAR */
-#ifdef CONFIG_TRACE_IRQFLAGS
- bl .trace_hardirqs_on
- REST_GPR(0,r1)
- REST_4GPRS(3,r1)
- REST_2GPRS(7,r1)
- addi r9,r1,STACK_FRAME_OVERHEAD
- ld r12,_MSR(r1)
-#endif /* CONFIG_TRACE_IRQFLAGS */
- li r10,1
- stb r10,PACASOFTIRQEN(r13)
- stb r10,PACAHARDIRQEN(r13)
- std r10,SOFTE(r1)
-#ifdef CONFIG_PPC_ISERIES
-BEGIN_FW_FTR_SECTION
- /* Hack for handling interrupts when soft-enabling on iSeries */
- cmpdi cr1,r0,0x5555 /* syscall 0x5555 */
- andi. r10,r12,MSR_PR /* from kernel */
- crand 4*cr0+eq,4*cr1+eq,4*cr0+eq
- bne 2f
- b hardware_interrupt_entry
-2:
-END_FW_FTR_SECTION_IFSET(FW_FEATURE_ISERIES)
-#endif /* CONFIG_PPC_ISERIES */
+ /*
+ * A syscall should always be called with interrupts enabled
+ * so we just unconditionally hard-enable here. When some kind
+ * of irq tracing is used, we additionally check that condition
+ * is correct
+ */
+#if defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_BUG)
+ lbz r10,PACASOFTIRQEN(r13)
+ xori r10,r10,1
+1: tdnei r10,0
+ EMIT_BUG_ENTRY 1b,__FILE__,__LINE__,BUGFLAG_WARNING
+#endif
- /* Hard enable interrupts */
#ifdef CONFIG_PPC_BOOK3E
wrteei 1
#else
- mfmsr r11
+ ld r11,PACAKMSR(r13)
ori r11,r11,MSR_EE
mtmsrd r11,1
#endif /* CONFIG_PPC_BOOK3E */
+ /* We do need to set SOFTE in the stack frame or the return
+ * from interrupt will be painful
+ */
+ li r10,1
+ std r10,SOFTE(r1)
+
#ifdef SHOW_SYSCALLS
- bl .do_show_syscall
+ bl do_show_syscall
REST_GPR(0,r1)
REST_4GPRS(3,r1)
REST_2GPRS(7,r1)
addi r9,r1,STACK_FRAME_OVERHEAD
#endif
- clrrdi r11,r1,THREAD_SHIFT
+ CURRENT_THREAD_INFO(r11, r1)
ld r10,TI_FLAGS(r11)
andi. r11,r10,_TIF_SYSCALL_T_OR_A
- bne- syscall_dotrace
-syscall_dotrace_cont:
+ bne syscall_dotrace
+.Lsyscall_dotrace_cont:
cmpldi 0,r0,NR_syscalls
bge- syscall_enosys
@@ -168,7 +162,7 @@ system_call: /* label this so stack traces look sane */
* Need to vector to 32 Bit or default sys_call_table here,
* based on caller's run-mode / personality.
*/
- ld r11,.SYS_CALL_TABLE@toc(2)
+ ld r11,SYS_CALL_TABLE@toc(2)
andi. r10,r10,_TIF_32BIT
beq 15f
addi r11,r11,8 /* use 32-bit syscall entries */
@@ -180,17 +174,17 @@ system_call: /* label this so stack traces look sane */
clrldi r8,r8,32
15:
slwi r0,r0,4
- ldx r10,r11,r0 /* Fetch system call handler [ptr] */
- mtctr r10
+ ldx r12,r11,r0 /* Fetch system call handler [ptr] */
+ mtctr r12
bctrl /* Call handler */
syscall_exit:
std r3,RESULT(r1)
#ifdef SHOW_SYSCALLS
- bl .do_show_syscall_exit
+ bl do_show_syscall_exit
ld r3,RESULT(r1)
#endif
- clrrdi r12,r1,THREAD_SHIFT
+ CURRENT_THREAD_INFO(r12, r1)
ld r8,_MSR(r1)
#ifdef CONFIG_PPC_BOOK3S
@@ -198,17 +192,24 @@ syscall_exit:
andi. r10,r8,MSR_RI
beq- unrecov_restore
#endif
-
- /* Disable interrupts so current_thread_info()->flags can't change,
+ /*
+ * Disable interrupts so current_thread_info()->flags can't change,
* and so that we don't get interrupted after loading SRR0/1.
*/
#ifdef CONFIG_PPC_BOOK3E
wrteei 0
#else
- mfmsr r10
- rldicl r10,r10,48,1
- rotldi r10,r10,16
- mtmsrd r10,1
+ ld r10,PACAKMSR(r13)
+ /*
+ * For performance reasons we clear RI the same time that we
+ * clear EE. We only need to clear RI just before we restore r13
+ * below, but batching it with EE saves us one expensive mtmsrd call.
+ * We have to be careful to restore RI if we branch anywhere from
+ * here (eg syscall_exit_work).
+ */
+ li r9,MSR_RI
+ andc r11,r10,r9
+ mtmsrd r11,1
#endif /* CONFIG_PPC_BOOK3E */
ld r9,TI_FLAGS(r12)
@@ -218,27 +219,17 @@ syscall_exit:
cmpld r3,r11
ld r5,_CCR(r1)
bge- syscall_error
-syscall_error_cont:
+.Lsyscall_error_cont:
ld r7,_NIP(r1)
BEGIN_FTR_SECTION
stdcx. r0,0,r1 /* to clear the reservation */
END_FTR_SECTION_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS)
andi. r6,r8,MSR_PR
ld r4,_LINK(r1)
- /*
- * Clear RI before restoring r13. If we are returning to
- * userspace and we take an exception after restoring r13,
- * we end up corrupting the userspace r13 value.
- */
-#ifdef CONFIG_PPC_BOOK3S
- /* No MSR:RI on BookE */
- li r12,MSR_RI
- andc r11,r10,r12
- mtmsrd r11,1 /* clear MSR.RI */
-#endif /* CONFIG_PPC_BOOK3S */
beq- 1f
ACCOUNT_CPU_USER_EXIT(r11, r12)
+ HMT_MEDIUM_LOW_HAS_PPR
ld r13,GPR13(r1) /* only restore r13 if returning to usermode */
1: ld r2,GPR2(r1)
ld r1,GPR1(r1)
@@ -253,13 +244,13 @@ syscall_error:
oris r5,r5,0x1000 /* Set SO bit in CR */
neg r3,r3
std r5,_CCR(r1)
- b syscall_error_cont
+ b .Lsyscall_error_cont
/* Traced system call support */
syscall_dotrace:
- bl .save_nvgprs
+ bl save_nvgprs
addi r3,r1,STACK_FRAME_OVERHEAD
- bl .do_syscall_trace_enter
+ bl do_syscall_trace_enter
/*
* Restore argument registers possibly just changed.
* We use the return value of do_syscall_trace_enter
@@ -273,15 +264,18 @@ syscall_dotrace:
ld r7,GPR7(r1)
ld r8,GPR8(r1)
addi r9,r1,STACK_FRAME_OVERHEAD
- clrrdi r10,r1,THREAD_SHIFT
+ CURRENT_THREAD_INFO(r10, r1)
ld r10,TI_FLAGS(r10)
- b syscall_dotrace_cont
+ b .Lsyscall_dotrace_cont
syscall_enosys:
li r3,-ENOSYS
b syscall_exit
syscall_exit_work:
+#ifdef CONFIG_PPC_BOOK3S
+ mtmsrd r10,1 /* Restore RI */
+#endif
/* If TIF_RESTOREALL is set, don't scribble on either r3 or ccr.
If TIF_NOERROR is set, just save r3 as it is. */
@@ -312,22 +306,23 @@ syscall_exit_work:
subi r12,r12,TI_FLAGS
4: /* Anything else left to do? */
+ SET_DEFAULT_THREAD_PPR(r3, r10) /* Set thread.ppr = 3 */
andi. r0,r9,(_TIF_SYSCALL_T_OR_A|_TIF_SINGLESTEP)
- beq .ret_from_except_lite
+ beq ret_from_except_lite
/* Re-enable interrupts */
#ifdef CONFIG_PPC_BOOK3E
wrteei 1
#else
- mfmsr r10
+ ld r10,PACAKMSR(r13)
ori r10,r10,MSR_EE
mtmsrd r10,1
#endif /* CONFIG_PPC_BOOK3E */
- bl .save_nvgprs
+ bl save_nvgprs
addi r3,r1,STACK_FRAME_OVERHEAD
- bl .do_syscall_trace_leave
- b .ret_from_except
+ bl do_syscall_trace_leave
+ b ret_from_except
/* Save non-volatile GPRs, if not already saved. */
_GLOBAL(save_nvgprs)
@@ -350,36 +345,48 @@ _GLOBAL(save_nvgprs)
*/
_GLOBAL(ppc_fork)
- bl .save_nvgprs
- bl .sys_fork
+ bl save_nvgprs
+ bl sys_fork
b syscall_exit
_GLOBAL(ppc_vfork)
- bl .save_nvgprs
- bl .sys_vfork
+ bl save_nvgprs
+ bl sys_vfork
b syscall_exit
_GLOBAL(ppc_clone)
- bl .save_nvgprs
- bl .sys_clone
+ bl save_nvgprs
+ bl sys_clone
b syscall_exit
_GLOBAL(ppc32_swapcontext)
- bl .save_nvgprs
- bl .compat_sys_swapcontext
+ bl save_nvgprs
+ bl compat_sys_swapcontext
b syscall_exit
_GLOBAL(ppc64_swapcontext)
- bl .save_nvgprs
- bl .sys_swapcontext
+ bl save_nvgprs
+ bl sys_swapcontext
b syscall_exit
_GLOBAL(ret_from_fork)
- bl .schedule_tail
+ bl schedule_tail
REST_NVGPRS(r1)
li r3,0
b syscall_exit
+_GLOBAL(ret_from_kernel_thread)
+ bl schedule_tail
+ REST_NVGPRS(r1)
+ mtlr r14
+ mr r3,r15
+#if defined(_CALL_ELF) && _CALL_ELF == 2
+ mr r12,r14
+#endif
+ blrl
+ li r3,0
+ b syscall_exit
+
/*
* This routine switches between two different tasks. The process
* state of one is saved on its kernel stack. Then the state
@@ -421,12 +428,6 @@ BEGIN_FTR_SECTION
std r24,THREAD_VRSAVE(r3)
END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
#endif /* CONFIG_ALTIVEC */
-#ifdef CONFIG_PPC64
-BEGIN_FTR_SECTION
- mfspr r25,SPRN_DSCR
- std r25,THREAD_DSCR(r3)
-END_FTR_SECTION_IFSET(CPU_FTR_DSCR)
-#endif
and. r0,r0,r22
beq+ 1f
andc r22,r22,r0
@@ -437,6 +438,18 @@ END_FTR_SECTION_IFSET(CPU_FTR_DSCR)
std r23,_CCR(r1)
std r1,KSP(r3) /* Set old stack pointer */
+#ifdef CONFIG_PPC_BOOK3S_64
+BEGIN_FTR_SECTION
+ /* Event based branch registers */
+ mfspr r0, SPRN_BESCR
+ std r0, THREAD_BESCR(r3)
+ mfspr r0, SPRN_EBBHR
+ std r0, THREAD_EBBHR(r3)
+ mfspr r0, SPRN_EBBRR
+ std r0, THREAD_EBBRR(r3)
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
+#endif
+
#ifdef CONFIG_SMP
/* We need a sync somewhere here to make sure that if the
* previous task gets rescheduled on another CPU, it sees all
@@ -456,6 +469,13 @@ BEGIN_FTR_SECTION
ldarx r6,0,r1
END_FTR_SECTION_IFSET(CPU_FTR_STCX_CHECKS_ADDRESS)
+#ifdef CONFIG_PPC_BOOK3S
+/* Cancel all explict user streams as they will have no use after context
+ * switch and will stop the HW from creating streams itself
+ */
+ DCBT_STOP_ALL_STREAM_IDS(r6)
+#endif
+
addi r6,r4,-THREAD /* Convert THREAD to 'current' */
std r6,PACACURRENT(r13) /* Set new 'current' */
@@ -493,9 +513,11 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)
*/
ld r9,PACA_SLBSHADOWPTR(r13)
li r12,0
- std r12,SLBSHADOW_STACKESID(r9) /* Clear ESID */
- std r7,SLBSHADOW_STACKVSID(r9) /* Save VSID */
- std r0,SLBSHADOW_STACKESID(r9) /* Save ESID */
+ std r12,SLBSHADOW_STACKESID(r9) /* Clear ESID */
+ li r12,SLBSHADOW_STACKVSID
+ STDX_BE r7,r12,r9 /* Save VSID */
+ li r12,SLBSHADOW_STACKESID
+ STDX_BE r0,r12,r9 /* Save ESID */
/* No need to check for MMU_FTR_NO_SLBIE_B here, since when
* we have 1TB segments, the only CPUs known to have the errata
@@ -510,7 +532,7 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)
2:
#endif /* !CONFIG_PPC_BOOK3S */
- clrrdi r7,r8,THREAD_SHIFT /* base of new stack */
+ CURRENT_THREAD_INFO(r7, r8) /* base of new stack */
/* Note: this uses SWITCH_FRAME_SIZE rather than INT_FRAME_SIZE
because we don't need to leave the 288-byte ABI gap at the
top of the kernel stack. */
@@ -519,8 +541,20 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)
mr r1,r8 /* start using new stack pointer */
std r7,PACAKSAVE(r13)
- ld r6,_CCR(r1)
- mtcrf 0xFF,r6
+#ifdef CONFIG_PPC_BOOK3S_64
+BEGIN_FTR_SECTION
+ /* Event based branch registers */
+ ld r0, THREAD_BESCR(r4)
+ mtspr SPRN_BESCR, r0
+ ld r0, THREAD_EBBHR(r4)
+ mtspr SPRN_EBBHR, r0
+ ld r0, THREAD_EBBRR(r4)
+ mtspr SPRN_EBBRR, r0
+
+ ld r0,THREAD_TAR(r4)
+ mtspr SPRN_TAR,r0
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
+#endif
#ifdef CONFIG_ALTIVEC
BEGIN_FTR_SECTION
@@ -530,14 +564,27 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
#endif /* CONFIG_ALTIVEC */
#ifdef CONFIG_PPC64
BEGIN_FTR_SECTION
+ lwz r6,THREAD_DSCR_INHERIT(r4)
ld r0,THREAD_DSCR(r4)
+ cmpwi r6,0
+ bne 1f
+ ld r0,PACA_DSCR(r13)
+1:
+BEGIN_FTR_SECTION_NESTED(70)
+ mfspr r8, SPRN_FSCR
+ rldimi r8, r6, FSCR_DSCR_LG, (63 - FSCR_DSCR_LG)
+ mtspr SPRN_FSCR, r8
+END_FTR_SECTION_NESTED(CPU_FTR_ARCH_207S, CPU_FTR_ARCH_207S, 70)
cmpd r0,r25
- beq 1f
+ beq 2f
mtspr SPRN_DSCR,r0
-1:
+2:
END_FTR_SECTION_IFSET(CPU_FTR_DSCR)
#endif
+ ld r6,_CCR(r1)
+ mtcrf 0xFF,r6
+
/* r3-r13 are destroyed -- Cort */
REST_8GPRS(14, r1)
REST_10GPRS(22, r1)
@@ -553,7 +600,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_DSCR)
_GLOBAL(ret_from_except)
ld r11,_TRAP(r1)
andi. r0,r11,1
- bne .ret_from_except_lite
+ bne ret_from_except_lite
REST_NVGPRS(r1)
_GLOBAL(ret_from_except_lite)
@@ -565,51 +612,197 @@ _GLOBAL(ret_from_except_lite)
#ifdef CONFIG_PPC_BOOK3E
wrteei 0
#else
- mfmsr r10 /* Get current interrupt state */
- rldicl r9,r10,48,1 /* clear MSR_EE */
- rotldi r9,r9,16
- mtmsrd r9,1 /* Update machine state */
+ ld r10,PACAKMSR(r13) /* Get kernel MSR without EE */
+ mtmsrd r10,1 /* Update machine state */
#endif /* CONFIG_PPC_BOOK3E */
-#ifdef CONFIG_PREEMPT
- clrrdi r9,r1,THREAD_SHIFT /* current_thread_info() */
- li r0,_TIF_NEED_RESCHED /* bits to check */
+ CURRENT_THREAD_INFO(r9, r1)
ld r3,_MSR(r1)
+#ifdef CONFIG_PPC_BOOK3E
+ ld r10,PACACURRENT(r13)
+#endif /* CONFIG_PPC_BOOK3E */
ld r4,TI_FLAGS(r9)
- /* Move MSR_PR bit in r3 to _TIF_SIGPENDING position in r0 */
- rlwimi r0,r3,32+TIF_SIGPENDING-MSR_PR_LG,_TIF_SIGPENDING
- and. r0,r4,r0 /* check NEED_RESCHED and maybe SIGPENDING */
- bne do_work
-
-#else /* !CONFIG_PREEMPT */
- ld r3,_MSR(r1) /* Returning to user mode? */
andi. r3,r3,MSR_PR
- beq restore /* if not, just restore regs and return */
+ beq resume_kernel
+#ifdef CONFIG_PPC_BOOK3E
+ lwz r3,(THREAD+THREAD_DBCR0)(r10)
+#endif /* CONFIG_PPC_BOOK3E */
/* Check current_thread_info()->flags */
- clrrdi r9,r1,THREAD_SHIFT
- ld r4,TI_FLAGS(r9)
andi. r0,r4,_TIF_USER_WORK_MASK
- bne do_work
+#ifdef CONFIG_PPC_BOOK3E
+ bne 1f
+ /*
+ * Check to see if the dbcr0 register is set up to debug.
+ * Use the internal debug mode bit to do this.
+ */
+ andis. r0,r3,DBCR0_IDM@h
+ beq restore
+ mfmsr r0
+ rlwinm r0,r0,0,~MSR_DE /* Clear MSR.DE */
+ mtmsr r0
+ mtspr SPRN_DBCR0,r3
+ li r10, -1
+ mtspr SPRN_DBSR,r10
+ b restore
+#else
+ beq restore
#endif
+1: andi. r0,r4,_TIF_NEED_RESCHED
+ beq 2f
+ bl restore_interrupts
+ SCHEDULE_USER
+ b ret_from_except_lite
+2:
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ andi. r0,r4,_TIF_USER_WORK_MASK & ~_TIF_RESTORE_TM
+ bne 3f /* only restore TM if nothing else to do */
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ bl restore_tm_state
+ b restore
+3:
+#endif
+ bl save_nvgprs
+ bl restore_interrupts
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ bl do_notify_resume
+ b ret_from_except
+
+resume_kernel:
+ /* check current_thread_info, _TIF_EMULATE_STACK_STORE */
+ andis. r8,r4,_TIF_EMULATE_STACK_STORE@h
+ beq+ 1f
+
+ addi r8,r1,INT_FRAME_SIZE /* Get the kprobed function entry */
+
+ lwz r3,GPR1(r1)
+ subi r3,r3,INT_FRAME_SIZE /* dst: Allocate a trampoline exception frame */
+ mr r4,r1 /* src: current exception frame */
+ mr r1,r3 /* Reroute the trampoline frame to r1 */
+
+ /* Copy from the original to the trampoline. */
+ li r5,INT_FRAME_SIZE/8 /* size: INT_FRAME_SIZE */
+ li r6,0 /* start offset: 0 */
+ mtctr r5
+2: ldx r0,r6,r4
+ stdx r0,r6,r3
+ addi r6,r6,8
+ bdnz 2b
+
+ /* Do real store operation to complete stwu */
+ lwz r5,GPR1(r1)
+ std r8,0(r5)
+
+ /* Clear _TIF_EMULATE_STACK_STORE flag */
+ lis r11,_TIF_EMULATE_STACK_STORE@h
+ addi r5,r9,TI_FLAGS
+0: ldarx r4,0,r5
+ andc r4,r4,r11
+ stdcx. r4,0,r5
+ bne- 0b
+1:
+
+#ifdef CONFIG_PREEMPT
+ /* Check if we need to preempt */
+ andi. r0,r4,_TIF_NEED_RESCHED
+ beq+ restore
+ /* Check that preempt_count() == 0 and interrupts are enabled */
+ lwz r8,TI_PREEMPT(r9)
+ cmpwi cr1,r8,0
+ ld r0,SOFTE(r1)
+ cmpdi r0,0
+ crandc eq,cr1*4+eq,eq
+ bne restore
+
+ /*
+ * Here we are preempting the current task. We want to make
+ * sure we are soft-disabled first and reconcile irq state.
+ */
+ RECONCILE_IRQ_STATE(r3,r4)
+1: bl preempt_schedule_irq
+
+ /* Re-test flags and eventually loop */
+ CURRENT_THREAD_INFO(r9, r1)
+ ld r4,TI_FLAGS(r9)
+ andi. r0,r4,_TIF_NEED_RESCHED
+ bne 1b
+
+ /*
+ * arch_local_irq_restore() from preempt_schedule_irq above may
+ * enable hard interrupt but we really should disable interrupts
+ * when we return from the interrupt, and so that we don't get
+ * interrupted after loading SRR0/1.
+ */
+#ifdef CONFIG_PPC_BOOK3E
+ wrteei 0
+#else
+ ld r10,PACAKMSR(r13) /* Get kernel MSR without EE */
+ mtmsrd r10,1 /* Update machine state */
+#endif /* CONFIG_PPC_BOOK3E */
+#endif /* CONFIG_PREEMPT */
+ .globl fast_exc_return_irq
+fast_exc_return_irq:
restore:
-BEGIN_FW_FTR_SECTION
+ /*
+ * This is the main kernel exit path. First we check if we
+ * are about to re-enable interrupts
+ */
ld r5,SOFTE(r1)
-FW_FTR_SECTION_ELSE
- b .Liseries_check_pending_irqs
-ALT_FW_FTR_SECTION_END_IFCLR(FW_FEATURE_ISERIES)
-2:
- TRACE_AND_RESTORE_IRQ(r5);
+ lbz r6,PACASOFTIRQEN(r13)
+ cmpwi cr0,r5,0
+ beq restore_irq_off
- /* extract EE bit and use it to restore paca->hard_enabled */
- ld r3,_MSR(r1)
- rldicl r4,r3,49,63 /* r0 = (r3 >> 15) & 1 */
- stb r4,PACAHARDIRQEN(r13)
+ /* We are enabling, were we already enabled ? Yes, just return */
+ cmpwi cr0,r6,1
+ beq cr0,do_restore
+ /*
+ * We are about to soft-enable interrupts (we are hard disabled
+ * at this point). We check if there's anything that needs to
+ * be replayed first.
+ */
+ lbz r0,PACAIRQHAPPENED(r13)
+ cmpwi cr0,r0,0
+ bne- restore_check_irq_replay
+
+ /*
+ * Get here when nothing happened while soft-disabled, just
+ * soft-enable and move-on. We will hard-enable as a side
+ * effect of rfi
+ */
+restore_no_replay:
+ TRACE_ENABLE_INTS
+ li r0,1
+ stb r0,PACASOFTIRQEN(r13);
+
+ /*
+ * Final return path. BookE is handled in a different file
+ */
+do_restore:
#ifdef CONFIG_PPC_BOOK3E
- b .exception_return_book3e
+ b exception_return_book3e
#else
+ /*
+ * Clear the reservation. If we know the CPU tracks the address of
+ * the reservation then we can potentially save some cycles and use
+ * a larx. On POWER6 and POWER7 this is significantly faster.
+ */
+BEGIN_FTR_SECTION
+ stdcx. r0,0,r1 /* to clear the reservation */
+FTR_SECTION_ELSE
+ ldarx r4,0,r1
+ALT_FTR_SECTION_END_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS)
+
+ /*
+ * Some code path such as load_up_fpu or altivec return directly
+ * here. They run entirely hard disabled and do not alter the
+ * interrupt state. They also don't use lwarx/stwcx. and thus
+ * are known not to leave dangling reservations.
+ */
+ .globl fast_exception_return
+fast_exception_return:
+ ld r3,_MSR(r1)
ld r4,_CTR(r1)
ld r0,_LINK(r1)
mtctr r4
@@ -622,32 +815,35 @@ ALT_FW_FTR_SECTION_END_IFCLR(FW_FEATURE_ISERIES)
andi. r0,r3,MSR_RI
beq- unrecov_restore
- /*
- * Clear the reservation. If we know the CPU tracks the address of
- * the reservation then we can potentially save some cycles and use
- * a larx. On POWER6 and POWER7 this is significantly faster.
- */
+ /* Load PPR from thread struct before we clear MSR:RI */
BEGIN_FTR_SECTION
- stdcx. r0,0,r1 /* to clear the reservation */
-FTR_SECTION_ELSE
- ldarx r4,0,r1
-ALT_FTR_SECTION_END_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS)
+ ld r2,PACACURRENT(r13)
+ ld r2,TASKTHREADPPR(r2)
+END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
/*
* Clear RI before restoring r13. If we are returning to
* userspace and we take an exception after restoring r13,
* we end up corrupting the userspace r13 value.
*/
- mfmsr r4
- andc r4,r4,r0 /* r0 contains MSR_RI here */
+ ld r4,PACAKMSR(r13) /* Get kernel MSR without EE */
+ andc r4,r4,r0 /* r0 contains MSR_RI here */
mtmsrd r4,1
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ /* TM debug */
+ std r3, PACATMSCRATCH(r13) /* Stash returned-to MSR */
+#endif
/*
* r13 is our per cpu area, only restore it if we are returning to
- * userspace
+ * userspace the value stored in the stack frame may belong to
+ * another CPU.
*/
andi. r0,r3,MSR_PR
beq 1f
+BEGIN_FTR_SECTION
+ mtspr SPRN_PPR,r2 /* Restore PPR */
+END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
ACCOUNT_CPU_USER_EXIT(r2, r4)
REST_GPR(13, r1)
1:
@@ -669,99 +865,86 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS)
#endif /* CONFIG_PPC_BOOK3E */
-.Liseries_check_pending_irqs:
-#ifdef CONFIG_PPC_ISERIES
- ld r5,SOFTE(r1)
- cmpdi 0,r5,0
- beq 2b
- /* Check for pending interrupts (iSeries) */
- ld r3,PACALPPACAPTR(r13)
- ld r3,LPPACAANYINT(r3)
- cmpdi r3,0
- beq+ 2b /* skip do_IRQ if no interrupts */
-
- li r3,0
- stb r3,PACASOFTIRQEN(r13) /* ensure we are soft-disabled */
-#ifdef CONFIG_TRACE_IRQFLAGS
- bl .trace_hardirqs_off
- mfmsr r10
-#endif
- ori r10,r10,MSR_EE
- mtmsrd r10 /* hard-enable again */
- addi r3,r1,STACK_FRAME_OVERHEAD
- bl .do_IRQ
- b .ret_from_except_lite /* loop back and handle more */
-#endif
-
-do_work:
-#ifdef CONFIG_PREEMPT
- andi. r0,r3,MSR_PR /* Returning to user mode? */
- bne user_work
- /* Check that preempt_count() == 0 and interrupts are enabled */
- lwz r8,TI_PREEMPT(r9)
- cmpwi cr1,r8,0
- ld r0,SOFTE(r1)
- cmpdi r0,0
- crandc eq,cr1*4+eq,eq
- bne restore
-
- /* Here we are preempting the current task.
+ /*
+ * We are returning to a context with interrupts soft disabled.
*
- * Ensure interrupts are soft-disabled. We also properly mark
- * the PACA to reflect the fact that they are hard-disabled
- * and trace the change
+ * However, we may also about to hard enable, so we need to
+ * make sure that in this case, we also clear PACA_IRQ_HARD_DIS
+ * or that bit can get out of sync and bad things will happen
*/
- li r0,0
- stb r0,PACASOFTIRQEN(r13)
- stb r0,PACAHARDIRQEN(r13)
+restore_irq_off:
+ ld r3,_MSR(r1)
+ lbz r7,PACAIRQHAPPENED(r13)
+ andi. r0,r3,MSR_EE
+ beq 1f
+ rlwinm r7,r7,0,~PACA_IRQ_HARD_DIS
+ stb r7,PACAIRQHAPPENED(r13)
+1: li r0,0
+ stb r0,PACASOFTIRQEN(r13);
TRACE_DISABLE_INTS
+ b do_restore
- /* Call the scheduler with soft IRQs off */
-1: bl .preempt_schedule_irq
-
- /* Hard-disable interrupts again (and update PACA) */
-#ifdef CONFIG_PPC_BOOK3E
- wrteei 0
-#else
- mfmsr r10
- rldicl r10,r10,48,1
- rotldi r10,r10,16
- mtmsrd r10,1
-#endif /* CONFIG_PPC_BOOK3E */
- li r0,0
- stb r0,PACAHARDIRQEN(r13)
-
- /* Re-test flags and eventually loop */
- clrrdi r9,r1,THREAD_SHIFT
- ld r4,TI_FLAGS(r9)
- andi. r0,r4,_TIF_NEED_RESCHED
- bne 1b
- b restore
-
-user_work:
-#endif /* CONFIG_PREEMPT */
+ /*
+ * Something did happen, check if a re-emit is needed
+ * (this also clears paca->irq_happened)
+ */
+restore_check_irq_replay:
+ /* XXX: We could implement a fast path here where we check
+ * for irq_happened being just 0x01, in which case we can
+ * clear it and return. That means that we would potentially
+ * miss a decrementer having wrapped all the way around.
+ *
+ * Still, this might be useful for things like hash_page
+ */
+ bl __check_irq_replay
+ cmpwi cr0,r3,0
+ beq restore_no_replay
+
+ /*
+ * We need to re-emit an interrupt. We do so by re-using our
+ * existing exception frame. We first change the trap value,
+ * but we need to ensure we preserve the low nibble of it
+ */
+ ld r4,_TRAP(r1)
+ clrldi r4,r4,60
+ or r4,r4,r3
+ std r4,_TRAP(r1)
- /* Enable interrupts */
+ /*
+ * Then find the right handler and call it. Interrupts are
+ * still soft-disabled and we keep them that way.
+ */
+ cmpwi cr0,r3,0x500
+ bne 1f
+ addi r3,r1,STACK_FRAME_OVERHEAD;
+ bl do_IRQ
+ b ret_from_except
+1: cmpwi cr0,r3,0x900
+ bne 1f
+ addi r3,r1,STACK_FRAME_OVERHEAD;
+ bl timer_interrupt
+ b ret_from_except
+#ifdef CONFIG_PPC_DOORBELL
+1:
#ifdef CONFIG_PPC_BOOK3E
- wrteei 1
+ cmpwi cr0,r3,0x280
#else
- ori r10,r10,MSR_EE
- mtmsrd r10,1
+ BEGIN_FTR_SECTION
+ cmpwi cr0,r3,0xe80
+ FTR_SECTION_ELSE
+ cmpwi cr0,r3,0xa00
+ ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE)
#endif /* CONFIG_PPC_BOOK3E */
-
- andi. r0,r4,_TIF_NEED_RESCHED
- beq 1f
- bl .schedule
- b .ret_from_except_lite
-
-1: bl .save_nvgprs
- addi r3,r1,STACK_FRAME_OVERHEAD
- bl .do_signal
- b .ret_from_except
-
+ bne 1f
+ addi r3,r1,STACK_FRAME_OVERHEAD;
+ bl doorbell_exception
+ b ret_from_except
+#endif /* CONFIG_PPC_DOORBELL */
+1: b ret_from_except /* What else to do here ? */
+
unrecov_restore:
addi r3,r1,STACK_FRAME_OVERHEAD
- bl .unrecoverable_exception
+ bl unrecoverable_exception
b unrecov_restore
#ifdef CONFIG_PPC_RTAS
@@ -827,7 +1010,7 @@ _GLOBAL(enter_rtas)
std r6,PACASAVEDMSR(r13)
/* Setup our real return addr */
- LOAD_REG_ADDR(r4,.rtas_return_loc)
+ LOAD_REG_ADDR(r4,rtas_return_loc)
clrldi r4,r4,2 /* convert to realmode address */
mtlr r4
@@ -837,7 +1020,7 @@ _GLOBAL(enter_rtas)
li r9,1
rldicr r9,r9,MSR_SF_LG,(63-MSR_SF_LG)
- ori r9,r9,MSR_IR|MSR_DR|MSR_FE0|MSR_FE1|MSR_FP|MSR_RI
+ ori r9,r9,MSR_IR|MSR_DR|MSR_FE0|MSR_FE1|MSR_FP|MSR_RI|MSR_LE
andc r6,r0,r9
sync /* disable interrupts so SRR0/1 */
mtmsrd r0 /* don't get trashed */
@@ -851,14 +1034,16 @@ _GLOBAL(enter_rtas)
rfid
b . /* prevent speculative execution */
-_STATIC(rtas_return_loc)
+rtas_return_loc:
+ FIXUP_ENDIAN
+
/* relocation is off at this point */
GET_PACA(r4)
clrldi r4,r4,2 /* convert to realmode address */
bcl 20,31,$+4
0: mflr r3
- ld r3,(1f-0b)(r3) /* get &.rtas_restore_regs */
+ ld r3,(1f-0b)(r3) /* get &rtas_restore_regs */
mfmsr r6
li r0,MSR_RI
@@ -875,9 +1060,9 @@ _STATIC(rtas_return_loc)
b . /* prevent speculative execution */
.align 3
-1: .llong .rtas_restore_regs
+1: .llong rtas_restore_regs
-_STATIC(rtas_restore_regs)
+rtas_restore_regs:
/* relocation is on at this point */
REST_GPR(2, r1) /* Restore the TOC */
REST_GPR(13, r1) /* Restore paca */
@@ -923,28 +1108,30 @@ _GLOBAL(enter_prom)
std r10,_CCR(r1)
std r11,_MSR(r1)
- /* Get the PROM entrypoint */
- mtlr r4
+ /* Put PROM address in SRR0 */
+ mtsrr0 r4
- /* Switch MSR to 32 bits mode
+ /* Setup our trampoline return addr in LR */
+ bcl 20,31,$+4
+0: mflr r4
+ addi r4,r4,(1f - 0b)
+ mtlr r4
+
+ /* Prepare a 32-bit mode big endian MSR
*/
#ifdef CONFIG_PPC_BOOK3E
rlwinm r11,r11,0,1,31
- mtmsr r11
+ mtsrr1 r11
+ rfi
#else /* CONFIG_PPC_BOOK3E */
- mfmsr r11
- li r12,1
- rldicr r12,r12,MSR_SF_LG,(63-MSR_SF_LG)
- andc r11,r11,r12
- li r12,1
- rldicr r12,r12,MSR_ISF_LG,(63-MSR_ISF_LG)
- andc r11,r11,r12
- mtmsrd r11
+ LOAD_REG_IMMEDIATE(r12, MSR_SF | MSR_ISF | MSR_LE)
+ andc r11,r11,r12
+ mtsrr1 r11
+ rfid
#endif /* CONFIG_PPC_BOOK3E */
- isync
- /* Enter PROM here... */
- blrl
+1: /* Return from OF */
+ FIXUP_ENDIAN
/* Just make sure that r1 top 32 bits didn't get
* corrupt by OF
@@ -975,7 +1162,7 @@ _GLOBAL(mcount)
_GLOBAL(_mcount)
blr
-_GLOBAL(ftrace_caller)
+_GLOBAL_TOC(ftrace_caller)
/* Taken from output of objdump from lib64/glibc */
mflr r3
ld r11, 0(r1)
@@ -999,10 +1186,7 @@ _GLOBAL(ftrace_graph_stub)
_GLOBAL(ftrace_stub)
blr
#else
-_GLOBAL(mcount)
- blr
-
-_GLOBAL(_mcount)
+_GLOBAL_TOC(_mcount)
/* Taken from output of objdump from lib64/glibc */
mflr r3
ld r11, 0(r1)
@@ -1040,7 +1224,7 @@ _GLOBAL(ftrace_graph_caller)
ld r11, 112(r1)
addi r3, r11, 16
- bl .prepare_ftrace_return
+ bl prepare_ftrace_return
nop
ld r0, 128(r1)
@@ -1056,7 +1240,7 @@ _GLOBAL(return_to_handler)
mr r31, r1
stdu r1, -112(r1)
- bl .ftrace_return_to_handler
+ bl ftrace_return_to_handler
nop
/* return value has real return address */
@@ -1086,7 +1270,7 @@ _GLOBAL(mod_return_to_handler)
*/
ld r2, PACATOC(r13)
- bl .ftrace_return_to_handler
+ bl ftrace_return_to_handler
nop
/* return value has real return address */
diff --git a/arch/powerpc/kernel/epapr_hcalls.S b/arch/powerpc/kernel/epapr_hcalls.S
new file mode 100644
index 00000000000..9f1ebf7338f
--- /dev/null
+++ b/arch/powerpc/kernel/epapr_hcalls.S
@@ -0,0 +1,55 @@
+/*
+ * Copyright (C) 2012 Freescale Semiconductor, Inc.
+ *
+ * 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.
+ */
+
+#include <linux/threads.h>
+#include <asm/epapr_hcalls.h>
+#include <asm/reg.h>
+#include <asm/page.h>
+#include <asm/cputable.h>
+#include <asm/thread_info.h>
+#include <asm/ppc_asm.h>
+#include <asm/asm-compat.h>
+#include <asm/asm-offsets.h>
+
+#ifndef CONFIG_PPC64
+/* epapr_ev_idle() was derived from e500_idle() */
+_GLOBAL(epapr_ev_idle)
+ CURRENT_THREAD_INFO(r3, r1)
+ PPC_LL r4, TI_LOCAL_FLAGS(r3) /* set napping bit */
+ ori r4, r4,_TLF_NAPPING /* so when we take an exception */
+ PPC_STL r4, TI_LOCAL_FLAGS(r3) /* it will return to our caller */
+
+ wrteei 1
+
+idle_loop:
+ LOAD_REG_IMMEDIATE(r11, EV_HCALL_TOKEN(EV_IDLE))
+
+.global epapr_ev_idle_start
+epapr_ev_idle_start:
+ li r3, -1
+ nop
+ nop
+ nop
+
+ /*
+ * Guard against spurious wakeups from a hypervisor --
+ * only interrupt will cause us to return to LR due to
+ * _TLF_NAPPING.
+ */
+ b idle_loop
+#endif
+
+/* Hypercall entry point. Will be patched with device tree instructions. */
+.global epapr_hypercall_start
+epapr_hypercall_start:
+ li r3, -1
+ nop
+ nop
+ nop
+ blr
diff --git a/arch/powerpc/kernel/epapr_paravirt.c b/arch/powerpc/kernel/epapr_paravirt.c
new file mode 100644
index 00000000000..59e4ba74975
--- /dev/null
+++ b/arch/powerpc/kernel/epapr_paravirt.c
@@ -0,0 +1,85 @@
+/*
+ * ePAPR para-virtualization support.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * 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, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
+ *
+ * Copyright (C) 2012 Freescale Semiconductor, Inc.
+ */
+
+#include <linux/of.h>
+#include <linux/of_fdt.h>
+#include <asm/epapr_hcalls.h>
+#include <asm/cacheflush.h>
+#include <asm/code-patching.h>
+#include <asm/machdep.h>
+
+#if !defined(CONFIG_64BIT) || defined(CONFIG_PPC_BOOK3E_64)
+extern void epapr_ev_idle(void);
+extern u32 epapr_ev_idle_start[];
+#endif
+
+bool epapr_paravirt_enabled;
+static bool __maybe_unused epapr_has_idle;
+
+static int __init early_init_dt_scan_epapr(unsigned long node,
+ const char *uname,
+ int depth, void *data)
+{
+ const u32 *insts;
+ int len;
+ int i;
+
+ insts = of_get_flat_dt_prop(node, "hcall-instructions", &len);
+ if (!insts)
+ return 0;
+
+ if (len % 4 || len > (4 * 4))
+ return -1;
+
+ for (i = 0; i < (len / 4); i++) {
+ u32 inst = be32_to_cpu(insts[i]);
+ patch_instruction(epapr_hypercall_start + i, inst);
+#if !defined(CONFIG_64BIT) || defined(CONFIG_PPC_BOOK3E_64)
+ patch_instruction(epapr_ev_idle_start + i, inst);
+#endif
+ }
+
+#if !defined(CONFIG_64BIT) || defined(CONFIG_PPC_BOOK3E_64)
+ if (of_get_flat_dt_prop(node, "has-idle", NULL))
+ epapr_has_idle = true;
+#endif
+
+ epapr_paravirt_enabled = true;
+
+ return 1;
+}
+
+int __init epapr_paravirt_early_init(void)
+{
+ of_scan_flat_dt(early_init_dt_scan_epapr, NULL);
+
+ return 0;
+}
+
+static int __init epapr_idle_init(void)
+{
+#if !defined(CONFIG_64BIT) || defined(CONFIG_PPC_BOOK3E_64)
+ if (epapr_has_idle)
+ ppc_md.power_save = epapr_ev_idle;
+#endif
+
+ return 0;
+}
+
+postcore_initcall(epapr_idle_init);
diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S
index 429983c06f9..bb9cac6c805 100644
--- a/arch/powerpc/kernel/exceptions-64e.S
+++ b/arch/powerpc/kernel/exceptions-64e.S
@@ -24,6 +24,9 @@
#include <asm/ptrace.h>
#include <asm/ppc-opcode.h>
#include <asm/mmu.h>
+#include <asm/hw_irq.h>
+#include <asm/kvm_asm.h>
+#include <asm/kvm_booke_hv_asm.h>
/* XXX This will ultimately add space for a special exception save
* structure used to save things like SRR0/SRR1, SPRGs, MAS, etc...
@@ -31,19 +34,263 @@
* special interrupts from within a non-standard level will probably
* blow you up
*/
-#define SPECIAL_EXC_FRAME_SIZE INT_FRAME_SIZE
+#define SPECIAL_EXC_SRR0 0
+#define SPECIAL_EXC_SRR1 1
+#define SPECIAL_EXC_SPRG_GEN 2
+#define SPECIAL_EXC_SPRG_TLB 3
+#define SPECIAL_EXC_MAS0 4
+#define SPECIAL_EXC_MAS1 5
+#define SPECIAL_EXC_MAS2 6
+#define SPECIAL_EXC_MAS3 7
+#define SPECIAL_EXC_MAS6 8
+#define SPECIAL_EXC_MAS7 9
+#define SPECIAL_EXC_MAS5 10 /* E.HV only */
+#define SPECIAL_EXC_MAS8 11 /* E.HV only */
+#define SPECIAL_EXC_IRQHAPPENED 12
+#define SPECIAL_EXC_DEAR 13
+#define SPECIAL_EXC_ESR 14
+#define SPECIAL_EXC_SOFTE 15
+#define SPECIAL_EXC_CSRR0 16
+#define SPECIAL_EXC_CSRR1 17
+/* must be even to keep 16-byte stack alignment */
+#define SPECIAL_EXC_END 18
+
+#define SPECIAL_EXC_FRAME_SIZE (INT_FRAME_SIZE + SPECIAL_EXC_END * 8)
+#define SPECIAL_EXC_FRAME_OFFS (INT_FRAME_SIZE - 288)
+
+#define SPECIAL_EXC_STORE(reg, name) \
+ std reg, (SPECIAL_EXC_##name * 8 + SPECIAL_EXC_FRAME_OFFS)(r1)
+
+#define SPECIAL_EXC_LOAD(reg, name) \
+ ld reg, (SPECIAL_EXC_##name * 8 + SPECIAL_EXC_FRAME_OFFS)(r1)
+
+special_reg_save:
+ lbz r9,PACAIRQHAPPENED(r13)
+ RECONCILE_IRQ_STATE(r3,r4)
+
+ /*
+ * We only need (or have stack space) to save this stuff if
+ * we interrupted the kernel.
+ */
+ ld r3,_MSR(r1)
+ andi. r3,r3,MSR_PR
+ bnelr
+
+ /* Copy info into temporary exception thread info */
+ ld r11,PACAKSAVE(r13)
+ CURRENT_THREAD_INFO(r11, r11)
+ CURRENT_THREAD_INFO(r12, r1)
+ ld r10,TI_FLAGS(r11)
+ std r10,TI_FLAGS(r12)
+ ld r10,TI_PREEMPT(r11)
+ std r10,TI_PREEMPT(r12)
+ ld r10,TI_TASK(r11)
+ std r10,TI_TASK(r12)
+
+ /*
+ * Advance to the next TLB exception frame for handler
+ * types that don't do it automatically.
+ */
+ LOAD_REG_ADDR(r11,extlb_level_exc)
+ lwz r12,0(r11)
+ mfspr r10,SPRN_SPRG_TLB_EXFRAME
+ add r10,r10,r12
+ mtspr SPRN_SPRG_TLB_EXFRAME,r10
+
+ /*
+ * Save registers needed to allow nesting of certain exceptions
+ * (such as TLB misses) inside special exception levels
+ */
+ mfspr r10,SPRN_SRR0
+ SPECIAL_EXC_STORE(r10,SRR0)
+ mfspr r10,SPRN_SRR1
+ SPECIAL_EXC_STORE(r10,SRR1)
+ mfspr r10,SPRN_SPRG_GEN_SCRATCH
+ SPECIAL_EXC_STORE(r10,SPRG_GEN)
+ mfspr r10,SPRN_SPRG_TLB_SCRATCH
+ SPECIAL_EXC_STORE(r10,SPRG_TLB)
+ mfspr r10,SPRN_MAS0
+ SPECIAL_EXC_STORE(r10,MAS0)
+ mfspr r10,SPRN_MAS1
+ SPECIAL_EXC_STORE(r10,MAS1)
+ mfspr r10,SPRN_MAS2
+ SPECIAL_EXC_STORE(r10,MAS2)
+ mfspr r10,SPRN_MAS3
+ SPECIAL_EXC_STORE(r10,MAS3)
+ mfspr r10,SPRN_MAS6
+ SPECIAL_EXC_STORE(r10,MAS6)
+ mfspr r10,SPRN_MAS7
+ SPECIAL_EXC_STORE(r10,MAS7)
+BEGIN_FTR_SECTION
+ mfspr r10,SPRN_MAS5
+ SPECIAL_EXC_STORE(r10,MAS5)
+ mfspr r10,SPRN_MAS8
+ SPECIAL_EXC_STORE(r10,MAS8)
+
+ /* MAS5/8 could have inappropriate values if we interrupted KVM code */
+ li r10,0
+ mtspr SPRN_MAS5,r10
+ mtspr SPRN_MAS8,r10
+END_FTR_SECTION_IFSET(CPU_FTR_EMB_HV)
+ SPECIAL_EXC_STORE(r9,IRQHAPPENED)
+
+ mfspr r10,SPRN_DEAR
+ SPECIAL_EXC_STORE(r10,DEAR)
+ mfspr r10,SPRN_ESR
+ SPECIAL_EXC_STORE(r10,ESR)
+
+ lbz r10,PACASOFTIRQEN(r13)
+ SPECIAL_EXC_STORE(r10,SOFTE)
+ ld r10,_NIP(r1)
+ SPECIAL_EXC_STORE(r10,CSRR0)
+ ld r10,_MSR(r1)
+ SPECIAL_EXC_STORE(r10,CSRR1)
+
+ blr
+
+ret_from_level_except:
+ ld r3,_MSR(r1)
+ andi. r3,r3,MSR_PR
+ beq 1f
+ b ret_from_except
+1:
+
+ LOAD_REG_ADDR(r11,extlb_level_exc)
+ lwz r12,0(r11)
+ mfspr r10,SPRN_SPRG_TLB_EXFRAME
+ sub r10,r10,r12
+ mtspr SPRN_SPRG_TLB_EXFRAME,r10
+
+ /*
+ * It's possible that the special level exception interrupted a
+ * TLB miss handler, and inserted the same entry that the
+ * interrupted handler was about to insert. On CPUs without TLB
+ * write conditional, this can result in a duplicate TLB entry.
+ * Wipe all non-bolted entries to be safe.
+ *
+ * Note that this doesn't protect against any TLB misses
+ * we may take accessing the stack from here to the end of
+ * the special level exception. It's not clear how we can
+ * reasonably protect against that, but only CPUs with
+ * neither TLB write conditional nor bolted kernel memory
+ * are affected. Do any such CPUs even exist?
+ */
+ PPC_TLBILX_ALL(0,R0)
+
+ REST_NVGPRS(r1)
+
+ SPECIAL_EXC_LOAD(r10,SRR0)
+ mtspr SPRN_SRR0,r10
+ SPECIAL_EXC_LOAD(r10,SRR1)
+ mtspr SPRN_SRR1,r10
+ SPECIAL_EXC_LOAD(r10,SPRG_GEN)
+ mtspr SPRN_SPRG_GEN_SCRATCH,r10
+ SPECIAL_EXC_LOAD(r10,SPRG_TLB)
+ mtspr SPRN_SPRG_TLB_SCRATCH,r10
+ SPECIAL_EXC_LOAD(r10,MAS0)
+ mtspr SPRN_MAS0,r10
+ SPECIAL_EXC_LOAD(r10,MAS1)
+ mtspr SPRN_MAS1,r10
+ SPECIAL_EXC_LOAD(r10,MAS2)
+ mtspr SPRN_MAS2,r10
+ SPECIAL_EXC_LOAD(r10,MAS3)
+ mtspr SPRN_MAS3,r10
+ SPECIAL_EXC_LOAD(r10,MAS6)
+ mtspr SPRN_MAS6,r10
+ SPECIAL_EXC_LOAD(r10,MAS7)
+ mtspr SPRN_MAS7,r10
+BEGIN_FTR_SECTION
+ SPECIAL_EXC_LOAD(r10,MAS5)
+ mtspr SPRN_MAS5,r10
+ SPECIAL_EXC_LOAD(r10,MAS8)
+ mtspr SPRN_MAS8,r10
+END_FTR_SECTION_IFSET(CPU_FTR_EMB_HV)
+
+ lbz r6,PACASOFTIRQEN(r13)
+ ld r5,SOFTE(r1)
+
+ /* Interrupts had better not already be enabled... */
+ twnei r6,0
+
+ cmpwi cr0,r5,0
+ beq 1f
+
+ TRACE_ENABLE_INTS
+ stb r5,PACASOFTIRQEN(r13)
+1:
+ /*
+ * Restore PACAIRQHAPPENED rather than setting it based on
+ * the return MSR[EE], since we could have interrupted
+ * __check_irq_replay() or other inconsistent transitory
+ * states that must remain that way.
+ */
+ SPECIAL_EXC_LOAD(r10,IRQHAPPENED)
+ stb r10,PACAIRQHAPPENED(r13)
+
+ SPECIAL_EXC_LOAD(r10,DEAR)
+ mtspr SPRN_DEAR,r10
+ SPECIAL_EXC_LOAD(r10,ESR)
+ mtspr SPRN_ESR,r10
+
+ stdcx. r0,0,r1 /* to clear the reservation */
+
+ REST_4GPRS(2, r1)
+ REST_4GPRS(6, r1)
+
+ ld r10,_CTR(r1)
+ ld r11,_XER(r1)
+ mtctr r10
+ mtxer r11
+
+ blr
+
+.macro ret_from_level srr0 srr1 paca_ex scratch
+ bl ret_from_level_except
+
+ ld r10,_LINK(r1)
+ ld r11,_CCR(r1)
+ ld r0,GPR13(r1)
+ mtlr r10
+ mtcr r11
+
+ ld r10,GPR10(r1)
+ ld r11,GPR11(r1)
+ ld r12,GPR12(r1)
+ mtspr \scratch,r0
+
+ std r10,\paca_ex+EX_R10(r13);
+ std r11,\paca_ex+EX_R11(r13);
+ ld r10,_NIP(r1)
+ ld r11,_MSR(r1)
+ ld r0,GPR0(r1)
+ ld r1,GPR1(r1)
+ mtspr \srr0,r10
+ mtspr \srr1,r11
+ ld r10,\paca_ex+EX_R10(r13)
+ ld r11,\paca_ex+EX_R11(r13)
+ mfspr r13,\scratch
+.endm
+
+ret_from_crit_except:
+ ret_from_level SPRN_CSRR0 SPRN_CSRR1 PACA_EXCRIT SPRN_SPRG_CRIT_SCRATCH
+ rfci
+
+ret_from_mc_except:
+ ret_from_level SPRN_MCSRR0 SPRN_MCSRR1 PACA_EXMC SPRN_SPRG_MC_SCRATCH
+ rfmci
/* Exception prolog code for all exceptions */
-#define EXCEPTION_PROLOG(n, type, addition) \
+#define EXCEPTION_PROLOG(n, intnum, type, addition) \
mtspr SPRN_SPRG_##type##_SCRATCH,r13; /* get spare registers */ \
mfspr r13,SPRN_SPRG_PACA; /* get PACA */ \
std r10,PACA_EX##type+EX_R10(r13); \
std r11,PACA_EX##type+EX_R11(r13); \
mfcr r10; /* save CR */ \
+ mfspr r11,SPRN_##type##_SRR1;/* what are we coming from */ \
+ DO_KVM intnum,SPRN_##type##_SRR1; /* KVM hook */ \
+ stw r10,PACA_EX##type+EX_CR(r13); /* save old CR in the PACA */ \
addition; /* additional code for that exc. */ \
std r1,PACA_EX##type+EX_R1(r13); /* save old r1 in the PACA */ \
- stw r10,PACA_EX##type+EX_CR(r13); /* save old CR in the PACA */ \
- mfspr r11,SPRN_##type##_SRR1;/* what are we coming from */ \
type##_SET_KSTACK; /* get special stack if necessary */\
andi. r10,r11,MSR_PR; /* save stack pointer */ \
beq 1f; /* branch around if supervisor */ \
@@ -58,78 +305,79 @@
#define SPRN_GEN_SRR0 SPRN_SRR0
#define SPRN_GEN_SRR1 SPRN_SRR1
+#define GDBELL_SET_KSTACK GEN_SET_KSTACK
+#define SPRN_GDBELL_SRR0 SPRN_GSRR0
+#define SPRN_GDBELL_SRR1 SPRN_GSRR1
+
#define CRIT_SET_KSTACK \
ld r1,PACA_CRIT_STACK(r13); \
- subi r1,r1,SPECIAL_EXC_FRAME_SIZE;
+ subi r1,r1,SPECIAL_EXC_FRAME_SIZE
#define SPRN_CRIT_SRR0 SPRN_CSRR0
#define SPRN_CRIT_SRR1 SPRN_CSRR1
#define DBG_SET_KSTACK \
ld r1,PACA_DBG_STACK(r13); \
- subi r1,r1,SPECIAL_EXC_FRAME_SIZE;
+ subi r1,r1,SPECIAL_EXC_FRAME_SIZE
#define SPRN_DBG_SRR0 SPRN_DSRR0
#define SPRN_DBG_SRR1 SPRN_DSRR1
#define MC_SET_KSTACK \
ld r1,PACA_MC_STACK(r13); \
- subi r1,r1,SPECIAL_EXC_FRAME_SIZE;
+ subi r1,r1,SPECIAL_EXC_FRAME_SIZE
#define SPRN_MC_SRR0 SPRN_MCSRR0
#define SPRN_MC_SRR1 SPRN_MCSRR1
-#define NORMAL_EXCEPTION_PROLOG(n, addition) \
- EXCEPTION_PROLOG(n, GEN, addition##_GEN)
+#define NORMAL_EXCEPTION_PROLOG(n, intnum, addition) \
+ EXCEPTION_PROLOG(n, intnum, GEN, addition##_GEN(n))
-#define CRIT_EXCEPTION_PROLOG(n, addition) \
- EXCEPTION_PROLOG(n, CRIT, addition##_CRIT)
+#define CRIT_EXCEPTION_PROLOG(n, intnum, addition) \
+ EXCEPTION_PROLOG(n, intnum, CRIT, addition##_CRIT(n))
-#define DBG_EXCEPTION_PROLOG(n, addition) \
- EXCEPTION_PROLOG(n, DBG, addition##_DBG)
+#define DBG_EXCEPTION_PROLOG(n, intnum, addition) \
+ EXCEPTION_PROLOG(n, intnum, DBG, addition##_DBG(n))
-#define MC_EXCEPTION_PROLOG(n, addition) \
- EXCEPTION_PROLOG(n, MC, addition##_MC)
+#define MC_EXCEPTION_PROLOG(n, intnum, addition) \
+ EXCEPTION_PROLOG(n, intnum, MC, addition##_MC(n))
+#define GDBELL_EXCEPTION_PROLOG(n, intnum, addition) \
+ EXCEPTION_PROLOG(n, intnum, GDBELL, addition##_GDBELL(n))
/* Variants of the "addition" argument for the prolog
*/
-#define PROLOG_ADDITION_NONE_GEN
-#define PROLOG_ADDITION_NONE_CRIT
-#define PROLOG_ADDITION_NONE_DBG
-#define PROLOG_ADDITION_NONE_MC
-
-#define PROLOG_ADDITION_MASKABLE_GEN \
- lbz r11,PACASOFTIRQEN(r13); /* are irqs soft-disabled ? */ \
- cmpwi cr0,r11,0; /* yes -> go out of line */ \
- beq masked_interrupt_book3e;
-
-#define PROLOG_ADDITION_2REGS_GEN \
+#define PROLOG_ADDITION_NONE_GEN(n)
+#define PROLOG_ADDITION_NONE_GDBELL(n)
+#define PROLOG_ADDITION_NONE_CRIT(n)
+#define PROLOG_ADDITION_NONE_DBG(n)
+#define PROLOG_ADDITION_NONE_MC(n)
+
+#define PROLOG_ADDITION_MASKABLE_GEN(n) \
+ lbz r10,PACASOFTIRQEN(r13); /* are irqs soft-disabled ? */ \
+ cmpwi cr0,r10,0; /* yes -> go out of line */ \
+ beq masked_interrupt_book3e_##n
+
+#define PROLOG_ADDITION_2REGS_GEN(n) \
std r14,PACA_EXGEN+EX_R14(r13); \
std r15,PACA_EXGEN+EX_R15(r13)
-#define PROLOG_ADDITION_1REG_GEN \
+#define PROLOG_ADDITION_1REG_GEN(n) \
std r14,PACA_EXGEN+EX_R14(r13);
-#define PROLOG_ADDITION_2REGS_CRIT \
+#define PROLOG_ADDITION_2REGS_CRIT(n) \
std r14,PACA_EXCRIT+EX_R14(r13); \
std r15,PACA_EXCRIT+EX_R15(r13)
-#define PROLOG_ADDITION_2REGS_DBG \
+#define PROLOG_ADDITION_2REGS_DBG(n) \
std r14,PACA_EXDBG+EX_R14(r13); \
std r15,PACA_EXDBG+EX_R15(r13)
-#define PROLOG_ADDITION_2REGS_MC \
+#define PROLOG_ADDITION_2REGS_MC(n) \
std r14,PACA_EXMC+EX_R14(r13); \
std r15,PACA_EXMC+EX_R15(r13)
-#define PROLOG_ADDITION_DOORBELL_GEN \
- lbz r11,PACASOFTIRQEN(r13); /* are irqs soft-disabled ? */ \
- cmpwi cr0,r11,0; /* yes -> go out of line */ \
- beq masked_doorbell_book3e
-
-/* Core exception code for all exceptions except TLB misses.
- * XXX: Needs to make SPRN_SPRG_GEN depend on exception type
- */
-#define EXCEPTION_COMMON(n, excf, ints) \
+/* Core exception code for all exceptions except TLB misses. */
+#define EXCEPTION_COMMON_LVL(n, scratch, excf) \
+exc_##n##_common: \
std r0,GPR0(r1); /* save r0 in stackframe */ \
std r2,GPR2(r1); /* save r2 in stackframe */ \
SAVE_4GPRS(3, r1); /* save r3 - r6 in stackframe */ \
@@ -137,10 +385,11 @@
std r9,GPR9(r1); /* save r9 in stackframe */ \
std r10,_NIP(r1); /* save SRR0 to stackframe */ \
std r11,_MSR(r1); /* save SRR1 to stackframe */ \
+ beq 2f; /* if from kernel mode */ \
ACCOUNT_CPU_USER_ENTRY(r10,r11);/* accounting (uses cr0+eq) */ \
- ld r3,excf+EX_R10(r13); /* get back r10 */ \
+2: ld r3,excf+EX_R10(r13); /* get back r10 */ \
ld r4,excf+EX_R11(r13); /* get back r11 */ \
- mfspr r5,SPRN_SPRG_GEN_SCRATCH;/* get back r13 */ \
+ mfspr r5,scratch; /* get back r13 */ \
std r12,GPR12(r1); /* save r12 in stackframe */ \
ld r2,PACATOC(r13); /* get kernel TOC into r2 */ \
mflr r6; /* save LR in stackframe */ \
@@ -164,23 +413,29 @@
std r11,SOFTE(r1); /* and save it to stackframe */ \
std r12,STACK_FRAME_OVERHEAD-16(r1); /* mark the frame */ \
std r3,_TRAP(r1); /* set trap number */ \
- std r0,RESULT(r1); /* clear regs->result */ \
- ints;
-
-/* Variants for the "ints" argument */
-#define INTS_KEEP
-#define INTS_DISABLE_SOFT \
- stb r0,PACASOFTIRQEN(r13); /* mark interrupts soft-disabled */ \
- TRACE_DISABLE_INTS;
-#define INTS_DISABLE_HARD \
- stb r0,PACAHARDIRQEN(r13); /* and hard disabled */
-#define INTS_DISABLE_ALL \
- INTS_DISABLE_SOFT \
- INTS_DISABLE_HARD
-
-/* This is called by exceptions that used INTS_KEEP (that is did not clear
- * neither soft nor hard IRQ indicators in the PACA. This will restore MSR:EE
- * to it's previous value
+ std r0,RESULT(r1); /* clear regs->result */
+
+#define EXCEPTION_COMMON(n) \
+ EXCEPTION_COMMON_LVL(n, SPRN_SPRG_GEN_SCRATCH, PACA_EXGEN)
+#define EXCEPTION_COMMON_CRIT(n) \
+ EXCEPTION_COMMON_LVL(n, SPRN_SPRG_CRIT_SCRATCH, PACA_EXCRIT)
+#define EXCEPTION_COMMON_MC(n) \
+ EXCEPTION_COMMON_LVL(n, SPRN_SPRG_MC_SCRATCH, PACA_EXMC)
+#define EXCEPTION_COMMON_DBG(n) \
+ EXCEPTION_COMMON_LVL(n, SPRN_SPRG_DBG_SCRATCH, PACA_EXDBG)
+
+/*
+ * This is meant for exceptions that don't immediately hard-enable. We
+ * set a bit in paca->irq_happened to ensure that a subsequent call to
+ * arch_local_irq_restore() will properly hard-enable and avoid the
+ * fast-path, and then reconcile irq state.
+ */
+#define INTS_DISABLE RECONCILE_IRQ_STATE(r3,r4)
+
+/*
+ * This is called by exceptions that don't use INTS_DISABLE (that did not
+ * touch irq indicators in the PACA). This will restore MSR:EE to it's
+ * previous value
*
* XXX In the long run, we may want to open-code it in order to separate the
* load from the wrtee, thus limiting the latency caused by the dependency
@@ -224,7 +479,7 @@ exc_##n##_bad_stack: \
* interrupts happen before the wait instruction.
*/
#define CHECK_NAPPING() \
- clrrdi r11,r1,THREAD_SHIFT; \
+ CURRENT_THREAD_INFO(r11, r1); \
ld r10,TI_LOCAL_FLAGS(r11); \
andi. r9,r10,_TLF_NAPPING; \
beq+ 1f; \
@@ -235,15 +490,16 @@ exc_##n##_bad_stack: \
1:
-#define MASKABLE_EXCEPTION(trapnum, label, hdlr, ack) \
+#define MASKABLE_EXCEPTION(trapnum, intnum, label, hdlr, ack) \
START_EXCEPTION(label); \
- NORMAL_EXCEPTION_PROLOG(trapnum, PROLOG_ADDITION_MASKABLE) \
- EXCEPTION_COMMON(trapnum, PACA_EXGEN, INTS_DISABLE_ALL) \
+ NORMAL_EXCEPTION_PROLOG(trapnum, intnum, PROLOG_ADDITION_MASKABLE)\
+ EXCEPTION_COMMON(trapnum) \
+ INTS_DISABLE; \
ack(r8); \
CHECK_NAPPING(); \
addi r3,r1,STACK_FRAME_OVERHEAD; \
bl hdlr; \
- b .ret_from_except_lite;
+ b ret_from_except_lite;
/* This value is used to mark exception frames on the stack. */
.section ".toc","aw"
@@ -259,8 +515,8 @@ exception_marker:
.balign 0x1000
.globl interrupt_base_book3e
interrupt_base_book3e: /* fake trap */
- EXCEPTION_STUB(0x000, machine_check) /* 0x0200 */
- EXCEPTION_STUB(0x020, critical_input) /* 0x0580 */
+ EXCEPTION_STUB(0x000, machine_check)
+ EXCEPTION_STUB(0x020, critical_input) /* 0x0100 */
EXCEPTION_STUB(0x040, debug_crit) /* 0x0d00 */
EXCEPTION_STUB(0x060, data_storage) /* 0x0300 */
EXCEPTION_STUB(0x080, instruction_storage) /* 0x0400 */
@@ -275,6 +531,8 @@ interrupt_base_book3e: /* fake trap */
EXCEPTION_STUB(0x1a0, watchdog) /* 0x09f0 */
EXCEPTION_STUB(0x1c0, data_tlb_miss)
EXCEPTION_STUB(0x1e0, instruction_tlb_miss)
+ EXCEPTION_STUB(0x200, altivec_unavailable)
+ EXCEPTION_STUB(0x220, altivec_assist)
EXCEPTION_STUB(0x260, perfmon)
EXCEPTION_STUB(0x280, doorbell)
EXCEPTION_STUB(0x2a0, doorbell_crit)
@@ -282,103 +540,163 @@ interrupt_base_book3e: /* fake trap */
EXCEPTION_STUB(0x2e0, guest_doorbell_crit)
EXCEPTION_STUB(0x300, hypercall)
EXCEPTION_STUB(0x320, ehpriv)
+ EXCEPTION_STUB(0x340, lrat_error)
.globl interrupt_end_book3e
interrupt_end_book3e:
/* Critical Input Interrupt */
START_EXCEPTION(critical_input);
- CRIT_EXCEPTION_PROLOG(0x100, PROLOG_ADDITION_NONE)
-// EXCEPTION_COMMON(0x100, PACA_EXCRIT, INTS_DISABLE_ALL)
-// bl special_reg_save_crit
-// CHECK_NAPPING();
-// addi r3,r1,STACK_FRAME_OVERHEAD
-// bl .critical_exception
-// b ret_from_crit_except
- b .
+ CRIT_EXCEPTION_PROLOG(0x100, BOOKE_INTERRUPT_CRITICAL,
+ PROLOG_ADDITION_NONE)
+ EXCEPTION_COMMON_CRIT(0x100)
+ bl save_nvgprs
+ bl special_reg_save
+ CHECK_NAPPING();
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ bl unknown_exception
+ b ret_from_crit_except
/* Machine Check Interrupt */
START_EXCEPTION(machine_check);
- CRIT_EXCEPTION_PROLOG(0x200, PROLOG_ADDITION_NONE)
-// EXCEPTION_COMMON(0x200, PACA_EXMC, INTS_DISABLE_ALL)
-// bl special_reg_save_mc
-// addi r3,r1,STACK_FRAME_OVERHEAD
-// CHECK_NAPPING();
-// bl .machine_check_exception
-// b ret_from_mc_except
- b .
+ MC_EXCEPTION_PROLOG(0x000, BOOKE_INTERRUPT_MACHINE_CHECK,
+ PROLOG_ADDITION_NONE)
+ EXCEPTION_COMMON_MC(0x000)
+ bl save_nvgprs
+ bl special_reg_save
+ CHECK_NAPPING();
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ bl machine_check_exception
+ b ret_from_mc_except
/* Data Storage Interrupt */
START_EXCEPTION(data_storage)
- NORMAL_EXCEPTION_PROLOG(0x300, PROLOG_ADDITION_2REGS)
+ NORMAL_EXCEPTION_PROLOG(0x300, BOOKE_INTERRUPT_DATA_STORAGE,
+ PROLOG_ADDITION_2REGS)
mfspr r14,SPRN_DEAR
mfspr r15,SPRN_ESR
- EXCEPTION_COMMON(0x300, PACA_EXGEN, INTS_KEEP)
+ EXCEPTION_COMMON(0x300)
+ INTS_DISABLE
b storage_fault_common
/* Instruction Storage Interrupt */
START_EXCEPTION(instruction_storage);
- NORMAL_EXCEPTION_PROLOG(0x400, PROLOG_ADDITION_2REGS)
+ NORMAL_EXCEPTION_PROLOG(0x400, BOOKE_INTERRUPT_INST_STORAGE,
+ PROLOG_ADDITION_2REGS)
li r15,0
mr r14,r10
- EXCEPTION_COMMON(0x400, PACA_EXGEN, INTS_KEEP)
+ EXCEPTION_COMMON(0x400)
+ INTS_DISABLE
b storage_fault_common
/* External Input Interrupt */
- MASKABLE_EXCEPTION(0x500, external_input, .do_IRQ, ACK_NONE)
+ MASKABLE_EXCEPTION(0x500, BOOKE_INTERRUPT_EXTERNAL,
+ external_input, do_IRQ, ACK_NONE)
/* Alignment */
START_EXCEPTION(alignment);
- NORMAL_EXCEPTION_PROLOG(0x600, PROLOG_ADDITION_2REGS)
+ NORMAL_EXCEPTION_PROLOG(0x600, BOOKE_INTERRUPT_ALIGNMENT,
+ PROLOG_ADDITION_2REGS)
mfspr r14,SPRN_DEAR
mfspr r15,SPRN_ESR
- EXCEPTION_COMMON(0x600, PACA_EXGEN, INTS_KEEP)
+ EXCEPTION_COMMON(0x600)
b alignment_more /* no room, go out of line */
/* Program Interrupt */
START_EXCEPTION(program);
- NORMAL_EXCEPTION_PROLOG(0x700, PROLOG_ADDITION_1REG)
+ NORMAL_EXCEPTION_PROLOG(0x700, BOOKE_INTERRUPT_PROGRAM,
+ PROLOG_ADDITION_1REG)
mfspr r14,SPRN_ESR
- EXCEPTION_COMMON(0x700, PACA_EXGEN, INTS_DISABLE_SOFT)
+ EXCEPTION_COMMON(0x700)
+ INTS_DISABLE
std r14,_DSISR(r1)
addi r3,r1,STACK_FRAME_OVERHEAD
ld r14,PACA_EXGEN+EX_R14(r13)
- bl .save_nvgprs
- INTS_RESTORE_HARD
- bl .program_check_exception
- b .ret_from_except
+ bl save_nvgprs
+ bl program_check_exception
+ b ret_from_except
/* Floating Point Unavailable Interrupt */
START_EXCEPTION(fp_unavailable);
- NORMAL_EXCEPTION_PROLOG(0x800, PROLOG_ADDITION_NONE)
+ NORMAL_EXCEPTION_PROLOG(0x800, BOOKE_INTERRUPT_FP_UNAVAIL,
+ PROLOG_ADDITION_NONE)
/* we can probably do a shorter exception entry for that one... */
- EXCEPTION_COMMON(0x800, PACA_EXGEN, INTS_KEEP)
- bne 1f /* if from user, just load it up */
- bl .save_nvgprs
+ EXCEPTION_COMMON(0x800)
+ ld r12,_MSR(r1)
+ andi. r0,r12,MSR_PR;
+ beq- 1f
+ bl load_up_fpu
+ b fast_exception_return
+1: INTS_DISABLE
+ bl save_nvgprs
addi r3,r1,STACK_FRAME_OVERHEAD
- INTS_RESTORE_HARD
- bl .kernel_fp_unavailable_exception
- BUG_OPCODE
-1: ld r12,_MSR(r1)
- bl .load_up_fpu
+ bl kernel_fp_unavailable_exception
+ b ret_from_except
+
+/* Altivec Unavailable Interrupt */
+ START_EXCEPTION(altivec_unavailable);
+ NORMAL_EXCEPTION_PROLOG(0x200, BOOKE_INTERRUPT_SPE_ALTIVEC_UNAVAIL,
+ PROLOG_ADDITION_NONE)
+ /* we can probably do a shorter exception entry for that one... */
+ EXCEPTION_COMMON(0x200)
+#ifdef CONFIG_ALTIVEC
+BEGIN_FTR_SECTION
+ ld r12,_MSR(r1)
+ andi. r0,r12,MSR_PR;
+ beq- 1f
+ bl load_up_altivec
b fast_exception_return
+1:
+END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
+#endif
+ INTS_DISABLE
+ bl save_nvgprs
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ bl altivec_unavailable_exception
+ b ret_from_except
+
+/* AltiVec Assist */
+ START_EXCEPTION(altivec_assist);
+ NORMAL_EXCEPTION_PROLOG(0x220,
+ BOOKE_INTERRUPT_SPE_FP_DATA_ALTIVEC_ASSIST,
+ PROLOG_ADDITION_NONE)
+ EXCEPTION_COMMON(0x220)
+ INTS_DISABLE
+ bl save_nvgprs
+ addi r3,r1,STACK_FRAME_OVERHEAD
+#ifdef CONFIG_ALTIVEC
+BEGIN_FTR_SECTION
+ bl altivec_assist_exception
+END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
+#else
+ bl unknown_exception
+#endif
+ b ret_from_except
+
/* Decrementer Interrupt */
- MASKABLE_EXCEPTION(0x900, decrementer, .timer_interrupt, ACK_DEC)
+ MASKABLE_EXCEPTION(0x900, BOOKE_INTERRUPT_DECREMENTER,
+ decrementer, timer_interrupt, ACK_DEC)
/* Fixed Interval Timer Interrupt */
- MASKABLE_EXCEPTION(0x980, fixed_interval, .unknown_exception, ACK_FIT)
+ MASKABLE_EXCEPTION(0x980, BOOKE_INTERRUPT_FIT,
+ fixed_interval, unknown_exception, ACK_FIT)
/* Watchdog Timer Interrupt */
START_EXCEPTION(watchdog);
- CRIT_EXCEPTION_PROLOG(0x9f0, PROLOG_ADDITION_NONE)
-// EXCEPTION_COMMON(0x9f0, PACA_EXCRIT, INTS_DISABLE_ALL)
-// bl special_reg_save_crit
-// CHECK_NAPPING();
-// addi r3,r1,STACK_FRAME_OVERHEAD
-// bl .unknown_exception
-// b ret_from_crit_except
- b .
+ CRIT_EXCEPTION_PROLOG(0x9f0, BOOKE_INTERRUPT_WATCHDOG,
+ PROLOG_ADDITION_NONE)
+ EXCEPTION_COMMON_CRIT(0x9f0)
+ bl save_nvgprs
+ bl special_reg_save
+ CHECK_NAPPING();
+ addi r3,r1,STACK_FRAME_OVERHEAD
+#ifdef CONFIG_BOOKE_WDT
+ bl WatchdogException
+#else
+ bl unknown_exception
+#endif
+ b ret_from_crit_except
/* System Call Interrupt */
START_EXCEPTION(system_call)
@@ -390,17 +708,19 @@ interrupt_end_book3e:
/* Auxiliary Processor Unavailable Interrupt */
START_EXCEPTION(ap_unavailable);
- NORMAL_EXCEPTION_PROLOG(0xf20, PROLOG_ADDITION_NONE)
- EXCEPTION_COMMON(0xf20, PACA_EXGEN, INTS_KEEP)
+ NORMAL_EXCEPTION_PROLOG(0xf20, BOOKE_INTERRUPT_AP_UNAVAIL,
+ PROLOG_ADDITION_NONE)
+ EXCEPTION_COMMON(0xf20)
+ INTS_DISABLE
+ bl save_nvgprs
addi r3,r1,STACK_FRAME_OVERHEAD
- bl .save_nvgprs
- INTS_RESTORE_HARD
- bl .unknown_exception
- b .ret_from_except
+ bl unknown_exception
+ b ret_from_except
/* Debug exception as a critical interrupt*/
START_EXCEPTION(debug_crit);
- CRIT_EXCEPTION_PROLOG(0xd00, PROLOG_ADDITION_2REGS)
+ CRIT_EXCEPTION_PROLOG(0xd00, BOOKE_INTERRUPT_DEBUG,
+ PROLOG_ADDITION_2REGS)
/*
* If there is a single step or branch-taken exception in an
@@ -412,7 +732,7 @@ interrupt_end_book3e:
*/
mfspr r14,SPRN_DBSR /* check single-step/branch taken */
- andis. r15,r14,DBSR_IC@h
+ andis. r15,r14,(DBSR_IC|DBSR_BT)@h
beq+ 1f
LOAD_REG_IMMEDIATE(r14,interrupt_base_book3e)
@@ -423,7 +743,7 @@ interrupt_end_book3e:
bge+ cr1,1f
/* here it looks like we got an inappropriate debug exception. */
- lis r14,DBSR_IC@h /* clear the IC event */
+ lis r14,(DBSR_IC|DBSR_BT)@h /* clear the event */
rlwinm r11,r11,0,~MSR_DE /* clear DE in the CSRR1 value */
mtspr SPRN_DBSR,r14
mtspr SPRN_CSRR1,r11
@@ -447,25 +767,24 @@ interrupt_end_book3e:
/* Now we mash up things to make it look like we are coming on a
* normal exception
*/
- mfspr r15,SPRN_SPRG_CRIT_SCRATCH
- mtspr SPRN_SPRG_GEN_SCRATCH,r15
mfspr r14,SPRN_DBSR
- EXCEPTION_COMMON(0xd00, PACA_EXCRIT, INTS_DISABLE_ALL)
+ EXCEPTION_COMMON_CRIT(0xd00)
std r14,_DSISR(r1)
addi r3,r1,STACK_FRAME_OVERHEAD
mr r4,r14
ld r14,PACA_EXCRIT+EX_R14(r13)
ld r15,PACA_EXCRIT+EX_R15(r13)
- bl .save_nvgprs
- bl .DebugException
- b .ret_from_except
+ bl save_nvgprs
+ bl DebugException
+ b ret_from_except
kernel_dbg_exc:
b . /* NYI */
/* Debug exception as a debug interrupt*/
START_EXCEPTION(debug_debug);
- DBG_EXCEPTION_PROLOG(0xd00, PROLOG_ADDITION_2REGS)
+ DBG_EXCEPTION_PROLOG(0xd00, BOOKE_INTERRUPT_DEBUG,
+ PROLOG_ADDITION_2REGS)
/*
* If there is a single step or branch-taken exception in an
@@ -477,7 +796,7 @@ kernel_dbg_exc:
*/
mfspr r14,SPRN_DBSR /* check single-step/branch taken */
- andis. r15,r14,DBSR_IC@h
+ andis. r15,r14,(DBSR_IC|DBSR_BT)@h
beq+ 1f
LOAD_REG_IMMEDIATE(r14,interrupt_base_book3e)
@@ -488,7 +807,7 @@ kernel_dbg_exc:
bge+ cr1,1f
/* here it looks like we got an inappropriate debug exception. */
- lis r14,DBSR_IC@h /* clear the IC event */
+ lis r14,(DBSR_IC|DBSR_BT)@h /* clear the event */
rlwinm r11,r11,0,~MSR_DE /* clear DE in the DSRR1 value */
mtspr SPRN_DBSR,r14
mtspr SPRN_DSRR1,r11
@@ -512,71 +831,175 @@ kernel_dbg_exc:
/* Now we mash up things to make it look like we are coming on a
* normal exception
*/
- mfspr r15,SPRN_SPRG_DBG_SCRATCH
- mtspr SPRN_SPRG_GEN_SCRATCH,r15
mfspr r14,SPRN_DBSR
- EXCEPTION_COMMON(0xd00, PACA_EXDBG, INTS_DISABLE_ALL)
+ EXCEPTION_COMMON_DBG(0xd08)
+ INTS_DISABLE
std r14,_DSISR(r1)
addi r3,r1,STACK_FRAME_OVERHEAD
mr r4,r14
ld r14,PACA_EXDBG+EX_R14(r13)
ld r15,PACA_EXDBG+EX_R15(r13)
- bl .save_nvgprs
- bl .DebugException
- b .ret_from_except
-
- MASKABLE_EXCEPTION(0x260, perfmon, .performance_monitor_exception, ACK_NONE)
-
-/* Doorbell interrupt */
- START_EXCEPTION(doorbell)
- NORMAL_EXCEPTION_PROLOG(0x2070, PROLOG_ADDITION_DOORBELL)
- EXCEPTION_COMMON(0x2070, PACA_EXGEN, INTS_DISABLE_ALL)
+ bl save_nvgprs
+ bl DebugException
+ b ret_from_except
+
+ START_EXCEPTION(perfmon);
+ NORMAL_EXCEPTION_PROLOG(0x260, BOOKE_INTERRUPT_PERFORMANCE_MONITOR,
+ PROLOG_ADDITION_NONE)
+ EXCEPTION_COMMON(0x260)
+ INTS_DISABLE
CHECK_NAPPING()
addi r3,r1,STACK_FRAME_OVERHEAD
- bl .doorbell_exception
- b .ret_from_except_lite
+ bl performance_monitor_exception
+ b ret_from_except_lite
+
+/* Doorbell interrupt */
+ MASKABLE_EXCEPTION(0x280, BOOKE_INTERRUPT_DOORBELL,
+ doorbell, doorbell_exception, ACK_NONE)
/* Doorbell critical Interrupt */
START_EXCEPTION(doorbell_crit);
- CRIT_EXCEPTION_PROLOG(0x2080, PROLOG_ADDITION_NONE)
-// EXCEPTION_COMMON(0x2080, PACA_EXCRIT, INTS_DISABLE_ALL)
-// bl special_reg_save_crit
-// CHECK_NAPPING();
-// addi r3,r1,STACK_FRAME_OVERHEAD
-// bl .doorbell_critical_exception
-// b ret_from_crit_except
- b .
-
- MASKABLE_EXCEPTION(0x2c0, guest_doorbell, .unknown_exception, ACK_NONE)
- MASKABLE_EXCEPTION(0x2e0, guest_doorbell_crit, .unknown_exception, ACK_NONE)
- MASKABLE_EXCEPTION(0x310, hypercall, .unknown_exception, ACK_NONE)
- MASKABLE_EXCEPTION(0x320, ehpriv, .unknown_exception, ACK_NONE)
+ CRIT_EXCEPTION_PROLOG(0x2a0, BOOKE_INTERRUPT_DOORBELL_CRITICAL,
+ PROLOG_ADDITION_NONE)
+ EXCEPTION_COMMON_CRIT(0x2a0)
+ bl save_nvgprs
+ bl special_reg_save
+ CHECK_NAPPING();
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ bl unknown_exception
+ b ret_from_crit_except
+/*
+ * Guest doorbell interrupt
+ * This general exception use GSRRx save/restore registers
+ */
+ START_EXCEPTION(guest_doorbell);
+ GDBELL_EXCEPTION_PROLOG(0x2c0, BOOKE_INTERRUPT_GUEST_DBELL,
+ PROLOG_ADDITION_NONE)
+ EXCEPTION_COMMON(0x2c0)
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ bl save_nvgprs
+ INTS_RESTORE_HARD
+ bl unknown_exception
+ b ret_from_except
+
+/* Guest Doorbell critical Interrupt */
+ START_EXCEPTION(guest_doorbell_crit);
+ CRIT_EXCEPTION_PROLOG(0x2e0, BOOKE_INTERRUPT_GUEST_DBELL_CRIT,
+ PROLOG_ADDITION_NONE)
+ EXCEPTION_COMMON_CRIT(0x2e0)
+ bl save_nvgprs
+ bl special_reg_save
+ CHECK_NAPPING();
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ bl unknown_exception
+ b ret_from_crit_except
+
+/* Hypervisor call */
+ START_EXCEPTION(hypercall);
+ NORMAL_EXCEPTION_PROLOG(0x310, BOOKE_INTERRUPT_HV_SYSCALL,
+ PROLOG_ADDITION_NONE)
+ EXCEPTION_COMMON(0x310)
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ bl save_nvgprs
+ INTS_RESTORE_HARD
+ bl unknown_exception
+ b ret_from_except
+
+/* Embedded Hypervisor priviledged */
+ START_EXCEPTION(ehpriv);
+ NORMAL_EXCEPTION_PROLOG(0x320, BOOKE_INTERRUPT_HV_PRIV,
+ PROLOG_ADDITION_NONE)
+ EXCEPTION_COMMON(0x320)
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ bl save_nvgprs
+ INTS_RESTORE_HARD
+ bl unknown_exception
+ b ret_from_except
+
+/* LRAT Error interrupt */
+ START_EXCEPTION(lrat_error);
+ NORMAL_EXCEPTION_PROLOG(0x340, BOOKE_INTERRUPT_LRAT_ERROR,
+ PROLOG_ADDITION_NONE)
+ EXCEPTION_COMMON(0x340)
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ bl .save_nvgprs
+ INTS_RESTORE_HARD
+ bl .unknown_exception
+ b .ret_from_except
/*
- * An interrupt came in while soft-disabled; clear EE in SRR1,
- * clear paca->hard_enabled and return.
+ * An interrupt came in while soft-disabled; We mark paca->irq_happened
+ * accordingly and if the interrupt is level sensitive, we hard disable
*/
-masked_doorbell_book3e:
- mtcr r10
- /* Resend the doorbell to fire again when ints enabled */
- mfspr r10,SPRN_PIR
- PPC_MSGSND(r10)
- b masked_interrupt_book3e_common
-masked_interrupt_book3e:
- mtcr r10
-masked_interrupt_book3e_common:
- stb r11,PACAHARDIRQEN(r13)
- mfspr r10,SPRN_SRR1
- rldicl r11,r10,48,1 /* clear MSR_EE */
- rotldi r10,r11,16
- mtspr SPRN_SRR1,r10
- ld r10,PACA_EXGEN+EX_R10(r13); /* restore registers */
- ld r11,PACA_EXGEN+EX_R11(r13);
- mfspr r13,SPRN_SPRG_GEN_SCRATCH;
+.macro masked_interrupt_book3e paca_irq full_mask
+ lbz r10,PACAIRQHAPPENED(r13)
+ ori r10,r10,\paca_irq
+ stb r10,PACAIRQHAPPENED(r13)
+
+ .if \full_mask == 1
+ rldicl r10,r11,48,1 /* clear MSR_EE */
+ rotldi r11,r10,16
+ mtspr SPRN_SRR1,r11
+ .endif
+
+ lwz r11,PACA_EXGEN+EX_CR(r13)
+ mtcr r11
+ ld r10,PACA_EXGEN+EX_R10(r13)
+ ld r11,PACA_EXGEN+EX_R11(r13)
+ mfspr r13,SPRN_SPRG_GEN_SCRATCH
rfi
b .
+.endm
+
+masked_interrupt_book3e_0x500:
+ // XXX When adding support for EPR, use PACA_IRQ_EE_EDGE
+ masked_interrupt_book3e PACA_IRQ_EE 1
+
+masked_interrupt_book3e_0x900:
+ ACK_DEC(r10);
+ masked_interrupt_book3e PACA_IRQ_DEC 0
+
+masked_interrupt_book3e_0x980:
+ ACK_FIT(r10);
+ masked_interrupt_book3e PACA_IRQ_DEC 0
+
+masked_interrupt_book3e_0x280:
+masked_interrupt_book3e_0x2c0:
+ masked_interrupt_book3e PACA_IRQ_DBELL 0
+
+/*
+ * Called from arch_local_irq_enable when an interrupt needs
+ * to be resent. r3 contains either 0x500,0x900,0x260 or 0x280
+ * to indicate the kind of interrupt. MSR:EE is already off.
+ * We generate a stackframe like if a real interrupt had happened.
+ *
+ * Note: While MSR:EE is off, we need to make sure that _MSR
+ * in the generated frame has EE set to 1 or the exception
+ * handler will not properly re-enable them.
+ */
+_GLOBAL(__replay_interrupt)
+ /* We are going to jump to the exception common code which
+ * will retrieve various register values from the PACA which
+ * we don't give a damn about.
+ */
+ mflr r10
+ mfmsr r11
+ mfcr r4
+ mtspr SPRN_SPRG_GEN_SCRATCH,r13;
+ std r1,PACA_EXGEN+EX_R1(r13);
+ stw r4,PACA_EXGEN+EX_CR(r13);
+ ori r11,r11,MSR_EE
+ subi r1,r1,INT_FRAME_SIZE;
+ cmpwi cr0,r3,0x500
+ beq exc_0x500_common
+ cmpwi cr0,r3,0x900
+ beq exc_0x900_common
+ cmpwi cr0,r3,0x280
+ beq exc_0x280_common
+ blr
+
/*
* This is called from 0x300 and 0x400 handlers after the prologs with
@@ -591,17 +1014,16 @@ storage_fault_common:
mr r5,r15
ld r14,PACA_EXGEN+EX_R14(r13)
ld r15,PACA_EXGEN+EX_R15(r13)
- INTS_RESTORE_HARD
- bl .do_page_fault
+ bl do_page_fault
cmpdi r3,0
bne- 1f
- b .ret_from_except_lite
-1: bl .save_nvgprs
+ b ret_from_except_lite
+1: bl save_nvgprs
mr r5,r3
addi r3,r1,STACK_FRAME_OVERHEAD
ld r4,_DAR(r1)
- bl .bad_page_fault
- b .ret_from_except
+ bl bad_page_fault
+ b ret_from_except
/*
* Alignment exception doesn't fit entirely in the 0x100 bytes so it
@@ -613,10 +1035,10 @@ alignment_more:
addi r3,r1,STACK_FRAME_OVERHEAD
ld r14,PACA_EXGEN+EX_R14(r13)
ld r15,PACA_EXGEN+EX_R15(r13)
- bl .save_nvgprs
+ bl save_nvgprs
INTS_RESTORE_HARD
- bl .alignment_exception
- b .ret_from_except
+ bl alignment_exception
+ b ret_from_except
/*
* We branch here from entry_64.S for the last stage of the exception
@@ -679,12 +1101,16 @@ fast_exception_return:
BAD_STACK_TRAMPOLINE(0x000)
BAD_STACK_TRAMPOLINE(0x100)
BAD_STACK_TRAMPOLINE(0x200)
+BAD_STACK_TRAMPOLINE(0x220)
BAD_STACK_TRAMPOLINE(0x260)
+BAD_STACK_TRAMPOLINE(0x280)
+BAD_STACK_TRAMPOLINE(0x2a0)
BAD_STACK_TRAMPOLINE(0x2c0)
BAD_STACK_TRAMPOLINE(0x2e0)
BAD_STACK_TRAMPOLINE(0x300)
BAD_STACK_TRAMPOLINE(0x310)
BAD_STACK_TRAMPOLINE(0x320)
+BAD_STACK_TRAMPOLINE(0x340)
BAD_STACK_TRAMPOLINE(0x400)
BAD_STACK_TRAMPOLINE(0x500)
BAD_STACK_TRAMPOLINE(0x600)
@@ -697,11 +1123,10 @@ BAD_STACK_TRAMPOLINE(0xa00)
BAD_STACK_TRAMPOLINE(0xb00)
BAD_STACK_TRAMPOLINE(0xc00)
BAD_STACK_TRAMPOLINE(0xd00)
+BAD_STACK_TRAMPOLINE(0xd08)
BAD_STACK_TRAMPOLINE(0xe00)
BAD_STACK_TRAMPOLINE(0xf00)
BAD_STACK_TRAMPOLINE(0xf20)
-BAD_STACK_TRAMPOLINE(0x2070)
-BAD_STACK_TRAMPOLINE(0x2080)
.globl bad_stack_book3e
bad_stack_book3e:
@@ -747,7 +1172,7 @@ bad_stack_book3e:
std r12,0(r11)
ld r2,PACATOC(r13)
1: addi r3,r1,STACK_FRAME_OVERHEAD
- bl .kernel_bad_stack
+ bl kernel_bad_stack
b 1b
/*
@@ -829,7 +1254,7 @@ skpinv: addi r6,r6,1 /* Increment */
bne 1b /* If not, repeat */
/* Invalidate all TLBs */
- PPC_TLBILX_ALL(0,0)
+ PPC_TLBILX_ALL(0,R0)
sync
isync
@@ -882,12 +1307,9 @@ skpinv: addi r6,r6,1 /* Increment */
mtspr SPRN_MAS0,r3
tlbre
mfspr r6,SPRN_MAS1
- rlwinm r6,r6,0,2,0 /* clear IPROT */
+ rlwinm r6,r6,0,2,31 /* clear IPROT and VALID */
mtspr SPRN_MAS1,r6
tlbwe
-
- /* Invalidate TLB1 */
- PPC_TLBILX_ALL(0,0)
sync
isync
@@ -941,12 +1363,9 @@ skpinv: addi r6,r6,1 /* Increment */
mtspr SPRN_MAS0,r4
tlbre
mfspr r5,SPRN_MAS1
- rlwinm r5,r5,0,2,0 /* clear IPROT */
+ rlwinm r5,r5,0,2,31 /* clear IPROT and VALID */
mtspr SPRN_MAS1,r5
tlbwe
-
- /* Invalidate TLB1 */
- PPC_TLBILX_ALL(0,0)
sync
isync
@@ -1048,23 +1467,7 @@ a2_tlbinit_after_linear_map:
.globl a2_tlbinit_after_iprot_flush
a2_tlbinit_after_iprot_flush:
-#ifdef CONFIG_PPC_EARLY_DEBUG_WSP
- /* Now establish early debug mappings if applicable */
- /* Restore the MAS0 we used for linear mapping load */
- mtspr SPRN_MAS0,r11
-
- lis r3,(MAS1_VALID | MAS1_IPROT)@h
- ori r3,r3,(BOOK3E_PAGESZ_4K << MAS1_TSIZE_SHIFT)
- mtspr SPRN_MAS1,r3
- LOAD_REG_IMMEDIATE(r3, WSP_UART_VIRT | MAS2_I | MAS2_G)
- mtspr SPRN_MAS2,r3
- LOAD_REG_IMMEDIATE(r3, WSP_UART_PHYS | MAS3_SR | MAS3_SW)
- mtspr SPRN_MAS7_MAS3,r3
- /* re-use the MAS8 value from the linear mapping */
- tlbwe
-#endif /* CONFIG_PPC_EARLY_DEBUG_WSP */
-
- PPC_TLBILX(0,0,0)
+ PPC_TLBILX(0,0,R0)
sync
isync
@@ -1102,13 +1505,13 @@ _GLOBAL(start_initialization_book3e)
* and always use AS 0, so we just set it up to match our link
* address and never use 0 based addresses.
*/
- bl .initial_tlb_book3e
+ bl initial_tlb_book3e
/* Init global core bits */
- bl .init_core_book3e
+ bl init_core_book3e
/* Init per-thread bits */
- bl .init_thread_book3e
+ bl init_thread_book3e
/* Return to common init code */
tovirt(r28,r28)
@@ -1129,7 +1532,7 @@ _GLOBAL(start_initialization_book3e)
*/
_GLOBAL(book3e_secondary_core_init_tlb_set)
li r4,1
- b .generic_secondary_smp_init
+ b generic_secondary_smp_init
_GLOBAL(book3e_secondary_core_init)
mflr r28
@@ -1139,18 +1542,18 @@ _GLOBAL(book3e_secondary_core_init)
bne 2f
/* Setup TLB for this core */
- bl .initial_tlb_book3e
+ bl initial_tlb_book3e
/* We can return from the above running at a different
* address, so recalculate r2 (TOC)
*/
- bl .relative_toc
+ bl relative_toc
/* Init global core bits */
-2: bl .init_core_book3e
+2: bl init_core_book3e
/* Init per-thread bits */
-3: bl .init_thread_book3e
+3: bl init_thread_book3e
/* Return to common init code at proper virtual address.
*
@@ -1177,14 +1580,14 @@ _GLOBAL(book3e_secondary_thread_init)
mflr r28
b 3b
-_STATIC(init_core_book3e)
+init_core_book3e:
/* Establish the interrupt vector base */
LOAD_REG_IMMEDIATE(r3, interrupt_base_book3e)
mtspr SPRN_IVPR,r3
sync
blr
-_STATIC(init_thread_book3e)
+init_thread_book3e:
lis r3,(SPRN_EPCR_ICM | SPRN_EPCR_GICM)@h
mtspr SPRN_EPCR,r3
@@ -1221,6 +1624,11 @@ _GLOBAL(__setup_base_ivors)
blr
+_GLOBAL(setup_altivec_ivors)
+ SET_IVOR(32, 0x200) /* AltiVec Unavailable */
+ SET_IVOR(33, 0x220) /* AltiVec Assist */
+ blr
+
_GLOBAL(setup_perfmon_ivor)
SET_IVOR(35, 0x260) /* Performance Monitor */
blr
@@ -1228,25 +1636,15 @@ _GLOBAL(setup_perfmon_ivor)
_GLOBAL(setup_doorbell_ivors)
SET_IVOR(36, 0x280) /* Processor Doorbell */
SET_IVOR(37, 0x2a0) /* Processor Doorbell Crit */
-
- /* Check MMUCFG[LPIDSIZE] to determine if we have category E.HV */
- mfspr r10,SPRN_MMUCFG
- rlwinm. r10,r10,0,MMUCFG_LPIDSIZE
- beqlr
-
- SET_IVOR(38, 0x2c0) /* Guest Processor Doorbell */
- SET_IVOR(39, 0x2e0) /* Guest Processor Doorbell Crit/MC */
blr
_GLOBAL(setup_ehv_ivors)
- /*
- * We may be running as a guest and lack E.HV even on a chip
- * that normally has it.
- */
- mfspr r10,SPRN_MMUCFG
- rlwinm. r10,r10,0,MMUCFG_LPIDSIZE
- beqlr
-
SET_IVOR(40, 0x300) /* Embedded Hypervisor System Call */
SET_IVOR(41, 0x320) /* Embedded Hypervisor Privilege */
+ SET_IVOR(38, 0x2c0) /* Guest Processor Doorbell */
+ SET_IVOR(39, 0x2e0) /* Guest Processor Doorbell Crit/MC */
+ blr
+
+_GLOBAL(setup_lrat_ivor)
+ SET_IVOR(42, 0x340) /* LRAT Error */
blr
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index d4be7bb3dbd..a7d36b19221 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -12,18 +12,75 @@
*
*/
+#include <asm/hw_irq.h>
#include <asm/exception-64s.h>
#include <asm/ptrace.h>
/*
* We layout physical memory as follows:
* 0x0000 - 0x00ff : Secondary processor spin code
- * 0x0100 - 0x2fff : pSeries Interrupt prologs
- * 0x3000 - 0x5fff : interrupt support, iSeries and common interrupt prologs
- * 0x6000 - 0x6fff : Initial (CPU0) segment table
+ * 0x0100 - 0x17ff : pSeries Interrupt prologs
+ * 0x1800 - 0x4000 : interrupt support common interrupt prologs
+ * 0x4000 - 0x5fff : pSeries interrupts with IR=1,DR=1
+ * 0x6000 - 0x6fff : more interrupt support including for IR=1,DR=1
* 0x7000 - 0x7fff : FWNMI data area
- * 0x8000 - : Early init and support code
+ * 0x8000 - 0x8fff : Initial (CPU0) segment table
+ * 0x9000 - : Early init and support code
*/
+ /* Syscall routine is used twice, in reloc-off and reloc-on paths */
+#define SYSCALL_PSERIES_1 \
+BEGIN_FTR_SECTION \
+ cmpdi r0,0x1ebe ; \
+ beq- 1f ; \
+END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE) \
+ mr r9,r13 ; \
+ GET_PACA(r13) ; \
+ mfspr r11,SPRN_SRR0 ; \
+0:
+
+#define SYSCALL_PSERIES_2_RFID \
+ mfspr r12,SPRN_SRR1 ; \
+ ld r10,PACAKBASE(r13) ; \
+ LOAD_HANDLER(r10, system_call_entry) ; \
+ mtspr SPRN_SRR0,r10 ; \
+ ld r10,PACAKMSR(r13) ; \
+ mtspr SPRN_SRR1,r10 ; \
+ rfid ; \
+ b . ; /* prevent speculative execution */
+
+#define SYSCALL_PSERIES_3 \
+ /* Fast LE/BE switch system call */ \
+1: mfspr r12,SPRN_SRR1 ; \
+ xori r12,r12,MSR_LE ; \
+ mtspr SPRN_SRR1,r12 ; \
+ rfid ; /* return to userspace */ \
+ b . ; /* prevent speculative execution */
+
+#if defined(CONFIG_RELOCATABLE)
+ /*
+ * We can't branch directly; in the direct case we use LR
+ * and system_call_entry restores LR. (We thus need to move
+ * LR to r10 in the RFID case too.)
+ */
+#define SYSCALL_PSERIES_2_DIRECT \
+ mflr r10 ; \
+ ld r12,PACAKBASE(r13) ; \
+ LOAD_HANDLER(r12, system_call_entry_direct) ; \
+ mtctr r12 ; \
+ mfspr r12,SPRN_SRR1 ; \
+ /* Re-use of r13... No spare regs to do this */ \
+ li r13,MSR_RI ; \
+ mtmsrd r13,1 ; \
+ GET_PACA(r13) ; /* get r13 back */ \
+ bctr ;
+#else
+ /* We can branch directly */
+#define SYSCALL_PSERIES_2_DIRECT \
+ mfspr r12,SPRN_SRR1 ; \
+ li r10,MSR_RI ; \
+ mtmsrd r10,1 ; /* Set RI (EE=0) */ \
+ b system_call_entry_direct ;
+#endif
/*
* This is the start of the interrupt handlers for pSeries
@@ -39,7 +96,7 @@ __start_interrupts:
.globl system_reset_pSeries;
system_reset_pSeries:
- HMT_MEDIUM;
+ HMT_MEDIUM_PPR_DISCARD
SET_SCRATCH0(r13)
#ifdef CONFIG_PPC_P7_NAP
BEGIN_FTR_SECTION
@@ -56,24 +113,32 @@ BEGIN_FTR_SECTION
cmpwi cr1,r13,2
/* Total loss of HV state is fatal, we could try to use the
* PIR to locate a PACA, then use an emergency stack etc...
- * but for now, let's just stay stuck here
+ * OPAL v3 based powernv platforms have new idle states
+ * which fall in this catagory.
*/
- bgt cr1,.
+ bgt cr1,8f
GET_PACA(r13)
-#ifdef CONFIG_KVM_BOOK3S_64_HV
- lbz r0,PACAPROCSTART(r13)
- cmpwi r0,0x80
- bne 1f
- li r0,1
- stb r0,PACAPROCSTART(r13)
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+ li r0,KVM_HWTHREAD_IN_KERNEL
+ stb r0,HSTATE_HWTHREAD_STATE(r13)
+ /* Order setting hwthread_state vs. testing hwthread_req */
+ sync
+ lbz r0,HSTATE_HWTHREAD_REQ(r13)
+ cmpwi r0,0
+ beq 1f
b kvm_start_guest
1:
#endif
beq cr1,2f
- b .power7_wakeup_noloss
-2: b .power7_wakeup_loss
+ b power7_wakeup_noloss
+2: b power7_wakeup_loss
+
+ /* Fast Sleep wakeup on PowerNV */
+8: GET_PACA(r13)
+ b power7_wakeup_tb_loss
+
9:
END_FTR_SECTION_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
#endif /* CONFIG_PPC_P7_NAP */
@@ -86,28 +151,57 @@ machine_check_pSeries_1:
* some code path might still want to branch into the original
* vector
*/
- b machine_check_pSeries
+ HMT_MEDIUM_PPR_DISCARD
+ SET_SCRATCH0(r13) /* save r13 */
+#ifdef CONFIG_PPC_P7_NAP
+BEGIN_FTR_SECTION
+ /* Running native on arch 2.06 or later, check if we are
+ * waking up from nap. We only handle no state loss and
+ * supervisor state loss. We do -not- handle hypervisor
+ * state loss at this time.
+ */
+ mfspr r13,SPRN_SRR1
+ rlwinm. r13,r13,47-31,30,31
+ OPT_GET_SPR(r13, SPRN_CFAR, CPU_FTR_CFAR)
+ beq 9f
+
+ mfspr r13,SPRN_SRR1
+ rlwinm. r13,r13,47-31,30,31
+ /* waking up from powersave (nap) state */
+ cmpwi cr1,r13,2
+ /* Total loss of HV state is fatal. let's just stay stuck here */
+ OPT_GET_SPR(r13, SPRN_CFAR, CPU_FTR_CFAR)
+ bgt cr1,.
+9:
+ OPT_SET_SPR(r13, SPRN_CFAR, CPU_FTR_CFAR)
+END_FTR_SECTION_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
+#endif /* CONFIG_PPC_P7_NAP */
+ EXCEPTION_PROLOG_0(PACA_EXMC)
+BEGIN_FTR_SECTION
+ b machine_check_pSeries_early
+FTR_SECTION_ELSE
+ b machine_check_pSeries_0
+ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE)
. = 0x300
.globl data_access_pSeries
data_access_pSeries:
- HMT_MEDIUM
+ HMT_MEDIUM_PPR_DISCARD
SET_SCRATCH0(r13)
-#ifndef CONFIG_POWER4_ONLY
BEGIN_FTR_SECTION
b data_access_check_stab
data_access_not_stab:
END_MMU_FTR_SECTION_IFCLR(MMU_FTR_SLB)
-#endif
EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, data_access_common, EXC_STD,
- KVMTEST_PR, 0x300)
+ KVMTEST, 0x300)
. = 0x380
.globl data_access_slb_pSeries
data_access_slb_pSeries:
- HMT_MEDIUM
+ HMT_MEDIUM_PPR_DISCARD
SET_SCRATCH0(r13)
- EXCEPTION_PROLOG_1(PACA_EXSLB, KVMTEST_PR, 0x380)
+ EXCEPTION_PROLOG_0(PACA_EXSLB)
+ EXCEPTION_PROLOG_1(PACA_EXSLB, KVMTEST, 0x380)
std r3,PACA_EXSLB+EX_R3(r13)
mfspr r3,SPRN_DAR
#ifdef __DISABLED__
@@ -117,16 +211,16 @@ data_access_slb_pSeries:
#endif /* __DISABLED__ */
mfspr r12,SPRN_SRR1
#ifndef CONFIG_RELOCATABLE
- b .slb_miss_realmode
+ b slb_miss_realmode
#else
/*
- * We can't just use a direct branch to .slb_miss_realmode
+ * We can't just use a direct branch to slb_miss_realmode
* because the distance from here to there depends on where
* the kernel ends up being put.
*/
mfctr r11
ld r10,PACAKBASE(r13)
- LOAD_HANDLER(r10, .slb_miss_realmode)
+ LOAD_HANDLER(r10, slb_miss_realmode)
mtctr r10
bctr
#endif
@@ -136,8 +230,9 @@ data_access_slb_pSeries:
. = 0x480
.globl instruction_access_slb_pSeries
instruction_access_slb_pSeries:
- HMT_MEDIUM
+ HMT_MEDIUM_PPR_DISCARD
SET_SCRATCH0(r13)
+ EXCEPTION_PROLOG_0(PACA_EXSLB)
EXCEPTION_PROLOG_1(PACA_EXSLB, KVMTEST_PR, 0x480)
std r3,PACA_EXSLB+EX_R3(r13)
mfspr r3,SPRN_SRR0 /* SRR0 is faulting address */
@@ -148,11 +243,11 @@ instruction_access_slb_pSeries:
#endif /* __DISABLED__ */
mfspr r12,SPRN_SRR1
#ifndef CONFIG_RELOCATABLE
- b .slb_miss_realmode
+ b slb_miss_realmode
#else
mfctr r11
ld r10,PACAKBASE(r13)
- LOAD_HANDLER(r10, .slb_miss_realmode)
+ LOAD_HANDLER(r10, slb_miss_realmode)
mtctr r10
bctr
#endif
@@ -165,6 +260,7 @@ instruction_access_slb_pSeries:
.globl hardware_interrupt_hv;
hardware_interrupt_pSeries:
hardware_interrupt_hv:
+ HMT_MEDIUM_PPR_DISCARD
BEGIN_FTR_SECTION
_MASKABLE_EXCEPTION_PSERIES(0x502, hardware_interrupt,
EXC_HV, SOFTEN_TEST_HV)
@@ -184,10 +280,14 @@ hardware_interrupt_hv:
STD_EXCEPTION_PSERIES(0x800, 0x800, fp_unavailable)
KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0x800)
- MASKABLE_EXCEPTION_PSERIES(0x900, 0x900, decrementer)
- MASKABLE_EXCEPTION_HV(0x980, 0x982, decrementer)
+ . = 0x900
+ .globl decrementer_pSeries
+decrementer_pSeries:
+ _MASKABLE_EXCEPTION_PSERIES(0x900, decrementer, EXC_STD, SOFTEN_TEST_PR)
+
+ STD_EXCEPTION_HV(0x980, 0x982, hdecrementer)
- STD_EXCEPTION_PSERIES(0xa00, 0xa00, trap_0a)
+ MASKABLE_EXCEPTION_PSERIES(0xa00, 0xa00, doorbell_super)
KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xa00)
STD_EXCEPTION_PSERIES(0xb00, 0xb00, trap_0b)
@@ -206,31 +306,11 @@ system_call_pSeries:
KVMTEST(0xc00)
GET_SCRATCH0(r13)
#endif
-BEGIN_FTR_SECTION
- cmpdi r0,0x1ebe
- beq- 1f
-END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE)
- mr r9,r13
- GET_PACA(r13)
- mfspr r11,SPRN_SRR0
- mfspr r12,SPRN_SRR1
- ld r10,PACAKBASE(r13)
- LOAD_HANDLER(r10, system_call_entry)
- mtspr SPRN_SRR0,r10
- ld r10,PACAKMSR(r13)
- mtspr SPRN_SRR1,r10
- rfid
- b . /* prevent speculative execution */
-
+ SYSCALL_PSERIES_1
+ SYSCALL_PSERIES_2_RFID
+ SYSCALL_PSERIES_3
KVM_HANDLER(PACA_EXGEN, EXC_STD, 0xc00)
-/* Fast LE/BE switch system call */
-1: mfspr r12,SPRN_SRR1
- xori r12,r12,MSR_LE
- mtspr SPRN_SRR1,r12
- rfid /* return to userspace */
- b .
-
STD_EXCEPTION_PSERIES(0xd00, 0xd00, single_step)
KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xd00)
@@ -238,33 +318,70 @@ END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE)
* out of line to handle them
*/
. = 0xe00
+hv_data_storage_trampoline:
+ SET_SCRATCH0(r13)
+ EXCEPTION_PROLOG_0(PACA_EXGEN)
b h_data_storage_hv
+
. = 0xe20
+hv_instr_storage_trampoline:
+ SET_SCRATCH0(r13)
+ EXCEPTION_PROLOG_0(PACA_EXGEN)
b h_instr_storage_hv
+
. = 0xe40
+emulation_assist_trampoline:
+ SET_SCRATCH0(r13)
+ EXCEPTION_PROLOG_0(PACA_EXGEN)
b emulation_assist_hv
- . = 0xe50
- b hmi_exception_hv
+
. = 0xe60
+hv_exception_trampoline:
+ SET_SCRATCH0(r13)
+ EXCEPTION_PROLOG_0(PACA_EXGEN)
b hmi_exception_hv
+ . = 0xe80
+hv_doorbell_trampoline:
+ SET_SCRATCH0(r13)
+ EXCEPTION_PROLOG_0(PACA_EXGEN)
+ b h_doorbell_hv
+
/* We need to deal with the Altivec unavailable exception
* here which is at 0xf20, thus in the middle of the
* prolog code of the PerformanceMonitor one. A little
* trickery is thus necessary
*/
-performance_monitor_pSeries_1:
. = 0xf00
+performance_monitor_pseries_trampoline:
+ SET_SCRATCH0(r13)
+ EXCEPTION_PROLOG_0(PACA_EXGEN)
b performance_monitor_pSeries
-altivec_unavailable_pSeries_1:
. = 0xf20
+altivec_unavailable_pseries_trampoline:
+ SET_SCRATCH0(r13)
+ EXCEPTION_PROLOG_0(PACA_EXGEN)
b altivec_unavailable_pSeries
-vsx_unavailable_pSeries_1:
. = 0xf40
+vsx_unavailable_pseries_trampoline:
+ SET_SCRATCH0(r13)
+ EXCEPTION_PROLOG_0(PACA_EXGEN)
b vsx_unavailable_pSeries
+ . = 0xf60
+facility_unavailable_trampoline:
+ SET_SCRATCH0(r13)
+ EXCEPTION_PROLOG_0(PACA_EXGEN)
+ b facility_unavailable_pSeries
+
+ . = 0xf80
+hv_facility_unavailable_trampoline:
+ SET_SCRATCH0(r13)
+ EXCEPTION_PROLOG_0(PACA_EXGEN)
+ b facility_unavailable_hv
+
#ifdef CONFIG_CBE_RAS
STD_EXCEPTION_HV(0x1200, 0x1202, cbe_system_error)
KVM_HANDLER_SKIP(PACA_EXGEN, EXC_HV, 0x1202)
@@ -273,6 +390,26 @@ vsx_unavailable_pSeries_1:
STD_EXCEPTION_PSERIES(0x1300, 0x1300, instruction_breakpoint)
KVM_HANDLER_PR_SKIP(PACA_EXGEN, EXC_STD, 0x1300)
+ . = 0x1500
+ .global denorm_exception_hv
+denorm_exception_hv:
+ HMT_MEDIUM_PPR_DISCARD
+ mtspr SPRN_SPRG_HSCRATCH0,r13
+ EXCEPTION_PROLOG_0(PACA_EXGEN)
+ EXCEPTION_PROLOG_1(PACA_EXGEN, NOTEST, 0x1500)
+
+#ifdef CONFIG_PPC_DENORMALISATION
+ mfspr r10,SPRN_HSRR1
+ mfspr r11,SPRN_HSRR0 /* save HSRR0 */
+ andis. r10,r10,(HSRR1_DENORM)@h /* denorm? */
+ addi r11,r11,-4 /* HSRR0 is next instruction */
+ bne+ denorm_assist
+#endif
+
+ KVMTEST(0x1500)
+ EXCEPTION_PROLOG_PSERIES_1(denorm_common, EXC_HV)
+ KVM_HANDLER_SKIP(PACA_EXGEN, EXC_STD, 0x1500)
+
#ifdef CONFIG_CBE_RAS
STD_EXCEPTION_HV(0x1600, 0x1602, cbe_maintenance)
KVM_HANDLER_SKIP(PACA_EXGEN, EXC_HV, 0x1602)
@@ -284,23 +421,100 @@ vsx_unavailable_pSeries_1:
#ifdef CONFIG_CBE_RAS
STD_EXCEPTION_HV(0x1800, 0x1802, cbe_thermal)
KVM_HANDLER_SKIP(PACA_EXGEN, EXC_HV, 0x1802)
+#else
+ . = 0x1800
#endif /* CONFIG_CBE_RAS */
- . = 0x3000
/*** Out of line interrupts support ***/
+ .align 7
/* moved from 0x200 */
+machine_check_pSeries_early:
+BEGIN_FTR_SECTION
+ EXCEPTION_PROLOG_1(PACA_EXMC, NOTEST, 0x200)
+ /*
+ * Register contents:
+ * R13 = PACA
+ * R9 = CR
+ * Original R9 to R13 is saved on PACA_EXMC
+ *
+ * Switch to mc_emergency stack and handle re-entrancy (we limit
+ * the nested MCE upto level 4 to avoid stack overflow).
+ * Save MCE registers srr1, srr0, dar and dsisr and then set ME=1
+ *
+ * We use paca->in_mce to check whether this is the first entry or
+ * nested machine check. We increment paca->in_mce to track nested
+ * machine checks.
+ *
+ * If this is the first entry then set stack pointer to
+ * paca->mc_emergency_sp, otherwise r1 is already pointing to
+ * stack frame on mc_emergency stack.
+ *
+ * NOTE: We are here with MSR_ME=0 (off), which means we risk a
+ * checkstop if we get another machine check exception before we do
+ * rfid with MSR_ME=1.
+ */
+ mr r11,r1 /* Save r1 */
+ lhz r10,PACA_IN_MCE(r13)
+ cmpwi r10,0 /* Are we in nested machine check */
+ bne 0f /* Yes, we are. */
+ /* First machine check entry */
+ ld r1,PACAMCEMERGSP(r13) /* Use MC emergency stack */
+0: subi r1,r1,INT_FRAME_SIZE /* alloc stack frame */
+ addi r10,r10,1 /* increment paca->in_mce */
+ sth r10,PACA_IN_MCE(r13)
+ /* Limit nested MCE to level 4 to avoid stack overflow */
+ cmpwi r10,4
+ bgt 2f /* Check if we hit limit of 4 */
+ std r11,GPR1(r1) /* Save r1 on the stack. */
+ std r11,0(r1) /* make stack chain pointer */
+ mfspr r11,SPRN_SRR0 /* Save SRR0 */
+ std r11,_NIP(r1)
+ mfspr r11,SPRN_SRR1 /* Save SRR1 */
+ std r11,_MSR(r1)
+ mfspr r11,SPRN_DAR /* Save DAR */
+ std r11,_DAR(r1)
+ mfspr r11,SPRN_DSISR /* Save DSISR */
+ std r11,_DSISR(r1)
+ std r9,_CCR(r1) /* Save CR in stackframe */
+ /* Save r9 through r13 from EXMC save area to stack frame. */
+ EXCEPTION_PROLOG_COMMON_2(PACA_EXMC)
+ mfmsr r11 /* get MSR value */
+ ori r11,r11,MSR_ME /* turn on ME bit */
+ ori r11,r11,MSR_RI /* turn on RI bit */
+ ld r12,PACAKBASE(r13) /* get high part of &label */
+ LOAD_HANDLER(r12, machine_check_handle_early)
+1: mtspr SPRN_SRR0,r12
+ mtspr SPRN_SRR1,r11
+ rfid
+ b . /* prevent speculative execution */
+2:
+ /* Stack overflow. Stay on emergency stack and panic.
+ * Keep the ME bit off while panic-ing, so that if we hit
+ * another machine check we checkstop.
+ */
+ addi r1,r1,INT_FRAME_SIZE /* go back to previous stack frame */
+ ld r11,PACAKMSR(r13)
+ ld r12,PACAKBASE(r13)
+ LOAD_HANDLER(r12, unrecover_mce)
+ li r10,MSR_ME
+ andc r11,r11,r10 /* Turn off MSR_ME */
+ b 1b
+ b . /* prevent speculative execution */
+END_FTR_SECTION_IFSET(CPU_FTR_HVMODE)
+
machine_check_pSeries:
.globl machine_check_fwnmi
machine_check_fwnmi:
- HMT_MEDIUM
+ HMT_MEDIUM_PPR_DISCARD
SET_SCRATCH0(r13) /* save r13 */
- EXCEPTION_PROLOG_PSERIES(PACA_EXMC, machine_check_common,
- EXC_STD, KVMTEST, 0x200)
+ EXCEPTION_PROLOG_0(PACA_EXMC)
+machine_check_pSeries_0:
+ EXCEPTION_PROLOG_1(PACA_EXMC, KVMTEST, 0x200)
+ EXCEPTION_PROLOG_PSERIES_1(machine_check_common, EXC_STD)
KVM_HANDLER_SKIP(PACA_EXMC, EXC_STD, 0x200)
-#ifndef CONFIG_POWER4_ONLY
/* moved from 0x300 */
data_access_check_stab:
GET_PACA(r13)
@@ -310,7 +524,7 @@ data_access_check_stab:
mfspr r9,SPRN_DSISR
srdi r10,r10,60
rlwimi r10,r9,16,0x20
-#ifdef CONFIG_KVM_BOOK3S_PR
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
lbz r9,HSTATE_IN_GUEST(r13)
rlwimi r10,r9,8,0x300
#endif
@@ -326,64 +540,172 @@ do_stab_bolted_pSeries:
std r12,PACA_EXSLB+EX_R12(r13)
GET_SCRATCH0(r10)
std r10,PACA_EXSLB+EX_R13(r13)
- EXCEPTION_PROLOG_PSERIES_1(.do_stab_bolted, EXC_STD)
-#endif /* CONFIG_POWER4_ONLY */
+ EXCEPTION_PROLOG_PSERIES_1(do_stab_bolted, EXC_STD)
- KVM_HANDLER_PR_SKIP(PACA_EXGEN, EXC_STD, 0x300)
- KVM_HANDLER_PR_SKIP(PACA_EXSLB, EXC_STD, 0x380)
+ KVM_HANDLER_SKIP(PACA_EXGEN, EXC_STD, 0x300)
+ KVM_HANDLER_SKIP(PACA_EXSLB, EXC_STD, 0x380)
KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0x400)
KVM_HANDLER_PR(PACA_EXSLB, EXC_STD, 0x480)
KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0x900)
KVM_HANDLER(PACA_EXGEN, EXC_HV, 0x982)
+#ifdef CONFIG_PPC_DENORMALISATION
+denorm_assist:
+BEGIN_FTR_SECTION
+/*
+ * To denormalise we need to move a copy of the register to itself.
+ * For POWER6 do that here for all FP regs.
+ */
+ mfmsr r10
+ ori r10,r10,(MSR_FP|MSR_FE0|MSR_FE1)
+ xori r10,r10,(MSR_FE0|MSR_FE1)
+ mtmsrd r10
+ sync
+
+#define FMR2(n) fmr (n), (n) ; fmr n+1, n+1
+#define FMR4(n) FMR2(n) ; FMR2(n+2)
+#define FMR8(n) FMR4(n) ; FMR4(n+4)
+#define FMR16(n) FMR8(n) ; FMR8(n+8)
+#define FMR32(n) FMR16(n) ; FMR16(n+16)
+ FMR32(0)
+
+FTR_SECTION_ELSE
+/*
+ * To denormalise we need to move a copy of the register to itself.
+ * For POWER7 do that here for the first 32 VSX registers only.
+ */
+ mfmsr r10
+ oris r10,r10,MSR_VSX@h
+ mtmsrd r10
+ sync
+
+#define XVCPSGNDP2(n) XVCPSGNDP(n,n,n) ; XVCPSGNDP(n+1,n+1,n+1)
+#define XVCPSGNDP4(n) XVCPSGNDP2(n) ; XVCPSGNDP2(n+2)
+#define XVCPSGNDP8(n) XVCPSGNDP4(n) ; XVCPSGNDP4(n+4)
+#define XVCPSGNDP16(n) XVCPSGNDP8(n) ; XVCPSGNDP8(n+8)
+#define XVCPSGNDP32(n) XVCPSGNDP16(n) ; XVCPSGNDP16(n+16)
+ XVCPSGNDP32(0)
+
+ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_206)
+
+BEGIN_FTR_SECTION
+ b denorm_done
+END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
+/*
+ * To denormalise we need to move a copy of the register to itself.
+ * For POWER8 we need to do that for all 64 VSX registers
+ */
+ XVCPSGNDP32(32)
+denorm_done:
+ mtspr SPRN_HSRR0,r11
+ mtcrf 0x80,r9
+ ld r9,PACA_EXGEN+EX_R9(r13)
+ RESTORE_PPR_PACA(PACA_EXGEN, r10)
+BEGIN_FTR_SECTION
+ ld r10,PACA_EXGEN+EX_CFAR(r13)
+ mtspr SPRN_CFAR,r10
+END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
+ ld r10,PACA_EXGEN+EX_R10(r13)
+ ld r11,PACA_EXGEN+EX_R11(r13)
+ ld r12,PACA_EXGEN+EX_R12(r13)
+ ld r13,PACA_EXGEN+EX_R13(r13)
+ HRFID
+ b .
+#endif
+
.align 7
/* moved from 0xe00 */
- STD_EXCEPTION_HV(., 0xe02, h_data_storage)
+ STD_EXCEPTION_HV_OOL(0xe02, h_data_storage)
KVM_HANDLER_SKIP(PACA_EXGEN, EXC_HV, 0xe02)
- STD_EXCEPTION_HV(., 0xe22, h_instr_storage)
+ STD_EXCEPTION_HV_OOL(0xe22, h_instr_storage)
KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xe22)
- STD_EXCEPTION_HV(., 0xe42, emulation_assist)
+ STD_EXCEPTION_HV_OOL(0xe42, emulation_assist)
KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xe42)
- STD_EXCEPTION_HV(., 0xe62, hmi_exception) /* need to flush cache ? */
+ STD_EXCEPTION_HV_OOL(0xe62, hmi_exception) /* need to flush cache ? */
KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xe62)
+ MASKABLE_EXCEPTION_HV_OOL(0xe82, h_doorbell)
+ KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xe82)
/* moved from 0xf00 */
- STD_EXCEPTION_PSERIES(., 0xf00, performance_monitor)
+ STD_EXCEPTION_PSERIES_OOL(0xf00, performance_monitor)
KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xf00)
- STD_EXCEPTION_PSERIES(., 0xf20, altivec_unavailable)
+ STD_EXCEPTION_PSERIES_OOL(0xf20, altivec_unavailable)
KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xf20)
- STD_EXCEPTION_PSERIES(., 0xf40, vsx_unavailable)
+ STD_EXCEPTION_PSERIES_OOL(0xf40, vsx_unavailable)
KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xf40)
+ STD_EXCEPTION_PSERIES_OOL(0xf60, facility_unavailable)
+ KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xf60)
+ STD_EXCEPTION_HV_OOL(0xf82, facility_unavailable)
+ KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xf82)
/*
- * An interrupt came in while soft-disabled; clear EE in SRR1,
- * clear paca->hard_enabled and return.
+ * An interrupt came in while soft-disabled. We set paca->irq_happened, then:
+ * - If it was a decrementer interrupt, we bump the dec to max and and return.
+ * - If it was a doorbell we return immediately since doorbells are edge
+ * triggered and won't automatically refire.
+ * - else we hard disable and return.
+ * This is called with r10 containing the value to OR to the paca field.
*/
-masked_interrupt:
- stb r10,PACAHARDIRQEN(r13)
- mtcrf 0x80,r9
- ld r9,PACA_EXGEN+EX_R9(r13)
- mfspr r10,SPRN_SRR1
- rldicl r10,r10,48,1 /* clear MSR_EE */
- rotldi r10,r10,16
- mtspr SPRN_SRR1,r10
- ld r10,PACA_EXGEN+EX_R10(r13)
- GET_SCRATCH0(r13)
- rfid
+#define MASKED_INTERRUPT(_H) \
+masked_##_H##interrupt: \
+ std r11,PACA_EXGEN+EX_R11(r13); \
+ lbz r11,PACAIRQHAPPENED(r13); \
+ or r11,r11,r10; \
+ stb r11,PACAIRQHAPPENED(r13); \
+ cmpwi r10,PACA_IRQ_DEC; \
+ bne 1f; \
+ lis r10,0x7fff; \
+ ori r10,r10,0xffff; \
+ mtspr SPRN_DEC,r10; \
+ b 2f; \
+1: cmpwi r10,PACA_IRQ_DBELL; \
+ beq 2f; \
+ mfspr r10,SPRN_##_H##SRR1; \
+ rldicl r10,r10,48,1; /* clear MSR_EE */ \
+ rotldi r10,r10,16; \
+ mtspr SPRN_##_H##SRR1,r10; \
+2: mtcrf 0x80,r9; \
+ ld r9,PACA_EXGEN+EX_R9(r13); \
+ ld r10,PACA_EXGEN+EX_R10(r13); \
+ ld r11,PACA_EXGEN+EX_R11(r13); \
+ GET_SCRATCH0(r13); \
+ ##_H##rfid; \
b .
+
+ MASKED_INTERRUPT()
+ MASKED_INTERRUPT(H)
-masked_Hinterrupt:
- stb r10,PACAHARDIRQEN(r13)
- mtcrf 0x80,r9
- ld r9,PACA_EXGEN+EX_R9(r13)
- mfspr r10,SPRN_HSRR1
- rldicl r10,r10,48,1 /* clear MSR_EE */
- rotldi r10,r10,16
- mtspr SPRN_HSRR1,r10
- ld r10,PACA_EXGEN+EX_R10(r13)
- GET_SCRATCH0(r13)
- hrfid
- b .
+/*
+ * Called from arch_local_irq_enable when an interrupt needs
+ * to be resent. r3 contains 0x500, 0x900, 0xa00 or 0xe80 to indicate
+ * which kind of interrupt. MSR:EE is already off. We generate a
+ * stackframe like if a real interrupt had happened.
+ *
+ * Note: While MSR:EE is off, we need to make sure that _MSR
+ * in the generated frame has EE set to 1 or the exception
+ * handler will not properly re-enable them.
+ */
+_GLOBAL(__replay_interrupt)
+ /* We are going to jump to the exception common code which
+ * will retrieve various register values from the PACA which
+ * we don't give a damn about, so we don't bother storing them.
+ */
+ mfmsr r12
+ mflr r11
+ mfcr r9
+ ori r12,r12,MSR_EE
+ cmpwi r3,0x900
+ beq decrementer_common
+ cmpwi r3,0x500
+ beq hardware_interrupt_common
+BEGIN_FTR_SECTION
+ cmpwi r3,0xe80
+ beq h_doorbell_common
+FTR_SECTION_ELSE
+ cmpwi r3,0xa00
+ beq doorbell_super_common
+ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE)
+ blr
#ifdef CONFIG_PPC_PSERIES
/*
@@ -392,7 +714,7 @@ masked_Hinterrupt:
.globl system_reset_fwnmi
.align 7
system_reset_fwnmi:
- HMT_MEDIUM
+ HMT_MEDIUM_PPR_DISCARD
SET_SCRATCH0(r13) /* save r13 */
EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, system_reset_common, EXC_STD,
NOTEST, 0x100)
@@ -427,61 +749,241 @@ slb_miss_user_pseries:
b . /* prevent spec. execution */
#endif /* __DISABLED__ */
- .align 7
- .globl __end_interrupts
-__end_interrupts:
+#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
+kvmppc_skip_interrupt:
+ /*
+ * Here all GPRs are unchanged from when the interrupt happened
+ * except for r13, which is saved in SPRG_SCRATCH0.
+ */
+ mfspr r13, SPRN_SRR0
+ addi r13, r13, 4
+ mtspr SPRN_SRR0, r13
+ GET_SCRATCH0(r13)
+ rfid
+ b .
+
+kvmppc_skip_Hinterrupt:
+ /*
+ * Here all GPRs are unchanged from when the interrupt happened
+ * except for r13, which is saved in SPRG_SCRATCH0.
+ */
+ mfspr r13, SPRN_HSRR0
+ addi r13, r13, 4
+ mtspr SPRN_HSRR0, r13
+ GET_SCRATCH0(r13)
+ hrfid
+ b .
+#endif
/*
* Code from here down to __end_handlers is invoked from the
* exception prologs above. Because the prologs assemble the
* addresses of these handlers using the LOAD_HANDLER macro,
- * which uses an addi instruction, these handlers must be in
- * the first 32k of the kernel image.
+ * which uses an ori instruction, these handlers must be in
+ * the first 64k of the kernel image.
*/
/*** Common interrupt handlers ***/
- STD_EXCEPTION_COMMON(0x100, system_reset, .system_reset_exception)
+ STD_EXCEPTION_COMMON(0x100, system_reset, system_reset_exception)
- /*
- * Machine check is different because we use a different
- * save area: PACA_EXMC instead of PACA_EXGEN.
- */
- .align 7
- .globl machine_check_common
-machine_check_common:
- EXCEPTION_PROLOG_COMMON(0x200, PACA_EXMC)
- FINISH_NAP
- DISABLE_INTS
- bl .save_nvgprs
- addi r3,r1,STACK_FRAME_OVERHEAD
- bl .machine_check_exception
- b .ret_from_except
-
- STD_EXCEPTION_COMMON_LITE(0x900, decrementer, .timer_interrupt)
- STD_EXCEPTION_COMMON(0xa00, trap_0a, .unknown_exception)
- STD_EXCEPTION_COMMON(0xb00, trap_0b, .unknown_exception)
- STD_EXCEPTION_COMMON(0xd00, single_step, .single_step_exception)
- STD_EXCEPTION_COMMON(0xe00, trap_0e, .unknown_exception)
- STD_EXCEPTION_COMMON(0xe40, emulation_assist, .program_check_exception)
- STD_EXCEPTION_COMMON(0xe60, hmi_exception, .unknown_exception)
- STD_EXCEPTION_COMMON_IDLE(0xf00, performance_monitor, .performance_monitor_exception)
- STD_EXCEPTION_COMMON(0x1300, instruction_breakpoint, .instruction_breakpoint_exception)
+ STD_EXCEPTION_COMMON_ASYNC(0x500, hardware_interrupt, do_IRQ)
+ STD_EXCEPTION_COMMON_ASYNC(0x900, decrementer, timer_interrupt)
+ STD_EXCEPTION_COMMON(0x980, hdecrementer, hdec_interrupt)
+#ifdef CONFIG_PPC_DOORBELL
+ STD_EXCEPTION_COMMON_ASYNC(0xa00, doorbell_super, doorbell_exception)
+#else
+ STD_EXCEPTION_COMMON_ASYNC(0xa00, doorbell_super, unknown_exception)
+#endif
+ STD_EXCEPTION_COMMON(0xb00, trap_0b, unknown_exception)
+ STD_EXCEPTION_COMMON(0xd00, single_step, single_step_exception)
+ STD_EXCEPTION_COMMON(0xe00, trap_0e, unknown_exception)
+ STD_EXCEPTION_COMMON(0xe40, emulation_assist, emulation_assist_interrupt)
+ STD_EXCEPTION_COMMON(0xe60, hmi_exception, unknown_exception)
+#ifdef CONFIG_PPC_DOORBELL
+ STD_EXCEPTION_COMMON_ASYNC(0xe80, h_doorbell, doorbell_exception)
+#else
+ STD_EXCEPTION_COMMON_ASYNC(0xe80, h_doorbell, unknown_exception)
+#endif
+ STD_EXCEPTION_COMMON_ASYNC(0xf00, performance_monitor, performance_monitor_exception)
+ STD_EXCEPTION_COMMON(0x1300, instruction_breakpoint, instruction_breakpoint_exception)
+ STD_EXCEPTION_COMMON(0x1502, denorm, unknown_exception)
#ifdef CONFIG_ALTIVEC
- STD_EXCEPTION_COMMON(0x1700, altivec_assist, .altivec_assist_exception)
+ STD_EXCEPTION_COMMON(0x1700, altivec_assist, altivec_assist_exception)
#else
- STD_EXCEPTION_COMMON(0x1700, altivec_assist, .unknown_exception)
+ STD_EXCEPTION_COMMON(0x1700, altivec_assist, unknown_exception)
#endif
#ifdef CONFIG_CBE_RAS
- STD_EXCEPTION_COMMON(0x1200, cbe_system_error, .cbe_system_error_exception)
- STD_EXCEPTION_COMMON(0x1600, cbe_maintenance, .cbe_maintenance_exception)
- STD_EXCEPTION_COMMON(0x1800, cbe_thermal, .cbe_thermal_exception)
+ STD_EXCEPTION_COMMON(0x1200, cbe_system_error, cbe_system_error_exception)
+ STD_EXCEPTION_COMMON(0x1600, cbe_maintenance, cbe_maintenance_exception)
+ STD_EXCEPTION_COMMON(0x1800, cbe_thermal, cbe_thermal_exception)
#endif /* CONFIG_CBE_RAS */
+ /*
+ * Relocation-on interrupts: A subset of the interrupts can be delivered
+ * with IR=1/DR=1, if AIL==2 and MSR.HV won't be changed by delivering
+ * it. Addresses are the same as the original interrupt addresses, but
+ * offset by 0xc000000000004000.
+ * It's impossible to receive interrupts below 0x300 via this mechanism.
+ * KVM: None of these traps are from the guest ; anything that escalated
+ * to HV=1 from HV=0 is delivered via real mode handlers.
+ */
+
+ /*
+ * This uses the standard macro, since the original 0x300 vector
+ * only has extra guff for STAB-based processors -- which never
+ * come here.
+ */
+ STD_RELON_EXCEPTION_PSERIES(0x4300, 0x300, data_access)
+ . = 0x4380
+ .globl data_access_slb_relon_pSeries
+data_access_slb_relon_pSeries:
+ SET_SCRATCH0(r13)
+ EXCEPTION_PROLOG_0(PACA_EXSLB)
+ EXCEPTION_PROLOG_1(PACA_EXSLB, NOTEST, 0x380)
+ std r3,PACA_EXSLB+EX_R3(r13)
+ mfspr r3,SPRN_DAR
+ mfspr r12,SPRN_SRR1
+#ifndef CONFIG_RELOCATABLE
+ b slb_miss_realmode
+#else
+ /*
+ * We can't just use a direct branch to slb_miss_realmode
+ * because the distance from here to there depends on where
+ * the kernel ends up being put.
+ */
+ mfctr r11
+ ld r10,PACAKBASE(r13)
+ LOAD_HANDLER(r10, slb_miss_realmode)
+ mtctr r10
+ bctr
+#endif
+
+ STD_RELON_EXCEPTION_PSERIES(0x4400, 0x400, instruction_access)
+ . = 0x4480
+ .globl instruction_access_slb_relon_pSeries
+instruction_access_slb_relon_pSeries:
+ SET_SCRATCH0(r13)
+ EXCEPTION_PROLOG_0(PACA_EXSLB)
+ EXCEPTION_PROLOG_1(PACA_EXSLB, NOTEST, 0x480)
+ std r3,PACA_EXSLB+EX_R3(r13)
+ mfspr r3,SPRN_SRR0 /* SRR0 is faulting address */
+ mfspr r12,SPRN_SRR1
+#ifndef CONFIG_RELOCATABLE
+ b slb_miss_realmode
+#else
+ mfctr r11
+ ld r10,PACAKBASE(r13)
+ LOAD_HANDLER(r10, slb_miss_realmode)
+ mtctr r10
+ bctr
+#endif
+
+ . = 0x4500
+ .globl hardware_interrupt_relon_pSeries;
+ .globl hardware_interrupt_relon_hv;
+hardware_interrupt_relon_pSeries:
+hardware_interrupt_relon_hv:
+ BEGIN_FTR_SECTION
+ _MASKABLE_RELON_EXCEPTION_PSERIES(0x502, hardware_interrupt, EXC_HV, SOFTEN_TEST_HV)
+ FTR_SECTION_ELSE
+ _MASKABLE_RELON_EXCEPTION_PSERIES(0x500, hardware_interrupt, EXC_STD, SOFTEN_TEST_PR)
+ ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE)
+ STD_RELON_EXCEPTION_PSERIES(0x4600, 0x600, alignment)
+ STD_RELON_EXCEPTION_PSERIES(0x4700, 0x700, program_check)
+ STD_RELON_EXCEPTION_PSERIES(0x4800, 0x800, fp_unavailable)
+ MASKABLE_RELON_EXCEPTION_PSERIES(0x4900, 0x900, decrementer)
+ STD_RELON_EXCEPTION_HV(0x4980, 0x982, hdecrementer)
+ MASKABLE_RELON_EXCEPTION_PSERIES(0x4a00, 0xa00, doorbell_super)
+ STD_RELON_EXCEPTION_PSERIES(0x4b00, 0xb00, trap_0b)
+
+ . = 0x4c00
+ .globl system_call_relon_pSeries
+system_call_relon_pSeries:
+ HMT_MEDIUM
+ SYSCALL_PSERIES_1
+ SYSCALL_PSERIES_2_DIRECT
+ SYSCALL_PSERIES_3
+
+ STD_RELON_EXCEPTION_PSERIES(0x4d00, 0xd00, single_step)
+
+ . = 0x4e00
+ b . /* Can't happen, see v2.07 Book III-S section 6.5 */
+
+ . = 0x4e20
+ b . /* Can't happen, see v2.07 Book III-S section 6.5 */
+
+ . = 0x4e40
+emulation_assist_relon_trampoline:
+ SET_SCRATCH0(r13)
+ EXCEPTION_PROLOG_0(PACA_EXGEN)
+ b emulation_assist_relon_hv
+
+ . = 0x4e60
+ b . /* Can't happen, see v2.07 Book III-S section 6.5 */
+
+ . = 0x4e80
+h_doorbell_relon_trampoline:
+ SET_SCRATCH0(r13)
+ EXCEPTION_PROLOG_0(PACA_EXGEN)
+ b h_doorbell_relon_hv
+
+ . = 0x4f00
+performance_monitor_relon_pseries_trampoline:
+ SET_SCRATCH0(r13)
+ EXCEPTION_PROLOG_0(PACA_EXGEN)
+ b performance_monitor_relon_pSeries
+
+ . = 0x4f20
+altivec_unavailable_relon_pseries_trampoline:
+ SET_SCRATCH0(r13)
+ EXCEPTION_PROLOG_0(PACA_EXGEN)
+ b altivec_unavailable_relon_pSeries
+
+ . = 0x4f40
+vsx_unavailable_relon_pseries_trampoline:
+ SET_SCRATCH0(r13)
+ EXCEPTION_PROLOG_0(PACA_EXGEN)
+ b vsx_unavailable_relon_pSeries
+
+ . = 0x4f60
+facility_unavailable_relon_trampoline:
+ SET_SCRATCH0(r13)
+ EXCEPTION_PROLOG_0(PACA_EXGEN)
+ b facility_unavailable_relon_pSeries
+
+ . = 0x4f80
+hv_facility_unavailable_relon_trampoline:
+ SET_SCRATCH0(r13)
+ EXCEPTION_PROLOG_0(PACA_EXGEN)
+ b hv_facility_unavailable_relon_hv
+
+ STD_RELON_EXCEPTION_PSERIES(0x5300, 0x1300, instruction_breakpoint)
+#ifdef CONFIG_PPC_DENORMALISATION
+ . = 0x5500
+ b denorm_exception_hv
+#endif
+ STD_RELON_EXCEPTION_PSERIES(0x5700, 0x1700, altivec_assist)
+
+ /* Other future vectors */
+ .align 7
+ .globl __end_interrupts
+__end_interrupts:
+
.align 7
+system_call_entry_direct:
+#if defined(CONFIG_RELOCATABLE)
+ /* The first level prologue may have used LR to get here, saving
+ * orig in r10. To save hacking/ifdeffing common code, restore here.
+ */
+ mtlr r10
+#endif
system_call_entry:
b system_call_common
+ppc64_runlatch_on_trampoline:
+ b __ppc64_runlatch_on
+
/*
* Here we have detected that the kernel stack pointer is bad.
* R9 contains the saved CR, r13 points to the paca,
@@ -539,7 +1041,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
std r12,RESULT(r1)
std r11,STACK_FRAME_OVERHEAD-16(r1)
1: addi r3,r1,STACK_FRAME_OVERHEAD
- bl .kernel_bad_stack
+ bl kernel_bad_stack
b 1b
/*
@@ -555,34 +1057,39 @@ data_access_common:
mfspr r10,SPRN_DSISR
stw r10,PACA_EXGEN+EX_DSISR(r13)
EXCEPTION_PROLOG_COMMON(0x300, PACA_EXGEN)
+ DISABLE_INTS
+ ld r12,_MSR(r1)
ld r3,PACA_EXGEN+EX_DAR(r13)
lwz r4,PACA_EXGEN+EX_DSISR(r13)
li r5,0x300
- b .do_hash_page /* Try to handle as hpte fault */
+ b do_hash_page /* Try to handle as hpte fault */
.align 7
- .globl h_data_storage_common
+ .globl h_data_storage_common
h_data_storage_common:
- mfspr r10,SPRN_HDAR
- std r10,PACA_EXGEN+EX_DAR(r13)
- mfspr r10,SPRN_HDSISR
- stw r10,PACA_EXGEN+EX_DSISR(r13)
- EXCEPTION_PROLOG_COMMON(0xe00, PACA_EXGEN)
- bl .save_nvgprs
- addi r3,r1,STACK_FRAME_OVERHEAD
- bl .unknown_exception
- b .ret_from_except
+ mfspr r10,SPRN_HDAR
+ std r10,PACA_EXGEN+EX_DAR(r13)
+ mfspr r10,SPRN_HDSISR
+ stw r10,PACA_EXGEN+EX_DSISR(r13)
+ EXCEPTION_PROLOG_COMMON(0xe00, PACA_EXGEN)
+ bl save_nvgprs
+ DISABLE_INTS
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ bl unknown_exception
+ b ret_from_except
.align 7
.globl instruction_access_common
instruction_access_common:
EXCEPTION_PROLOG_COMMON(0x400, PACA_EXGEN)
+ DISABLE_INTS
+ ld r12,_MSR(r1)
ld r3,_NIP(r1)
andis. r4,r12,0x5820
li r5,0x400
- b .do_hash_page /* Try to handle as hpte fault */
+ b do_hash_page /* Try to handle as hpte fault */
- STD_EXCEPTION_COMMON(0xe20, h_instr_storage, .unknown_exception)
+ STD_EXCEPTION_COMMON(0xe20, h_instr_storage, unknown_exception)
/*
* Here is the common SLB miss user that is used when going to virtual
@@ -597,7 +1104,7 @@ slb_miss_user_common:
stw r9,PACA_EXGEN+EX_CCR(r13)
std r10,PACA_EXGEN+EX_LR(r13)
std r11,PACA_EXGEN+EX_SRR0(r13)
- bl .slb_allocate_user
+ bl slb_allocate_user
ld r10,PACA_EXGEN+EX_LR(r13)
ld r3,PACA_EXGEN+EX_R3(r13)
@@ -640,116 +1147,37 @@ slb_miss_fault:
unrecov_user_slb:
EXCEPTION_PROLOG_COMMON(0x4200, PACA_EXGEN)
DISABLE_INTS
- bl .save_nvgprs
+ bl save_nvgprs
1: addi r3,r1,STACK_FRAME_OVERHEAD
- bl .unrecoverable_exception
+ bl unrecoverable_exception
b 1b
#endif /* __DISABLED__ */
-/*
- * r13 points to the PACA, r9 contains the saved CR,
- * r12 contain the saved SRR1, SRR0 is still ready for return
- * r3 has the faulting address
- * r9 - r13 are saved in paca->exslb.
- * r3 is saved in paca->slb_r3
- * We assume we aren't going to take any exceptions during this procedure.
- */
-_GLOBAL(slb_miss_realmode)
- mflr r10
-#ifdef CONFIG_RELOCATABLE
- mtctr r11
-#endif
-
- stw r9,PACA_EXSLB+EX_CCR(r13) /* save CR in exc. frame */
- std r10,PACA_EXSLB+EX_LR(r13) /* save LR */
-
- bl .slb_allocate_realmode
-
- /* All done -- return from exception. */
-
- ld r10,PACA_EXSLB+EX_LR(r13)
- ld r3,PACA_EXSLB+EX_R3(r13)
- lwz r9,PACA_EXSLB+EX_CCR(r13) /* get saved CR */
-#ifdef CONFIG_PPC_ISERIES
-BEGIN_FW_FTR_SECTION
- ld r11,PACALPPACAPTR(r13)
- ld r11,LPPACASRR0(r11) /* get SRR0 value */
-END_FW_FTR_SECTION_IFSET(FW_FEATURE_ISERIES)
-#endif /* CONFIG_PPC_ISERIES */
-
- mtlr r10
-
- andi. r10,r12,MSR_RI /* check for unrecoverable exception */
- beq- 2f
-
-.machine push
-.machine "power4"
- mtcrf 0x80,r9
- mtcrf 0x01,r9 /* slb_allocate uses cr0 and cr7 */
-.machine pop
-
-#ifdef CONFIG_PPC_ISERIES
-BEGIN_FW_FTR_SECTION
- mtspr SPRN_SRR0,r11
- mtspr SPRN_SRR1,r12
-END_FW_FTR_SECTION_IFSET(FW_FEATURE_ISERIES)
-#endif /* CONFIG_PPC_ISERIES */
- ld r9,PACA_EXSLB+EX_R9(r13)
- ld r10,PACA_EXSLB+EX_R10(r13)
- ld r11,PACA_EXSLB+EX_R11(r13)
- ld r12,PACA_EXSLB+EX_R12(r13)
- ld r13,PACA_EXSLB+EX_R13(r13)
- rfid
- b . /* prevent speculative execution */
-
-2:
-#ifdef CONFIG_PPC_ISERIES
-BEGIN_FW_FTR_SECTION
- b unrecov_slb
-END_FW_FTR_SECTION_IFSET(FW_FEATURE_ISERIES)
-#endif /* CONFIG_PPC_ISERIES */
- mfspr r11,SPRN_SRR0
- ld r10,PACAKBASE(r13)
- LOAD_HANDLER(r10,unrecov_slb)
- mtspr SPRN_SRR0,r10
- ld r10,PACAKMSR(r13)
- mtspr SPRN_SRR1,r10
- rfid
- b .
-
-unrecov_slb:
- EXCEPTION_PROLOG_COMMON(0x4100, PACA_EXSLB)
- DISABLE_INTS
- bl .save_nvgprs
-1: addi r3,r1,STACK_FRAME_OVERHEAD
- bl .unrecoverable_exception
- b 1b
-
+ /*
+ * Machine check is different because we use a different
+ * save area: PACA_EXMC instead of PACA_EXGEN.
+ */
.align 7
- .globl hardware_interrupt_common
- .globl hardware_interrupt_entry
-hardware_interrupt_common:
- EXCEPTION_PROLOG_COMMON(0x500, PACA_EXGEN)
+ .globl machine_check_common
+machine_check_common:
+
+ mfspr r10,SPRN_DAR
+ std r10,PACA_EXGEN+EX_DAR(r13)
+ mfspr r10,SPRN_DSISR
+ stw r10,PACA_EXGEN+EX_DSISR(r13)
+ EXCEPTION_PROLOG_COMMON(0x200, PACA_EXMC)
FINISH_NAP
-hardware_interrupt_entry:
DISABLE_INTS
-BEGIN_FTR_SECTION
- bl .ppc64_runlatch_on
-END_FTR_SECTION_IFSET(CPU_FTR_CTRL)
+ ld r3,PACA_EXGEN+EX_DAR(r13)
+ lwz r4,PACA_EXGEN+EX_DSISR(r13)
+ std r3,_DAR(r1)
+ std r4,_DSISR(r1)
+ bl save_nvgprs
addi r3,r1,STACK_FRAME_OVERHEAD
- bl .do_IRQ
- b .ret_from_except_lite
-
-#ifdef CONFIG_PPC_970_NAP
-power4_fixup_nap:
- andc r9,r9,r10
- std r9,TI_LOCAL_FLAGS(r11)
- ld r10,_LINK(r1) /* make idle task do the */
- std r10,_NIP(r1) /* equivalent of a blr */
- blr
-#endif
+ bl machine_check_exception
+ b ret_from_except
.align 7
.globl alignment_common
@@ -763,35 +1191,52 @@ alignment_common:
lwz r4,PACA_EXGEN+EX_DSISR(r13)
std r3,_DAR(r1)
std r4,_DSISR(r1)
- bl .save_nvgprs
+ bl save_nvgprs
+ DISABLE_INTS
addi r3,r1,STACK_FRAME_OVERHEAD
- ENABLE_INTS
- bl .alignment_exception
- b .ret_from_except
+ bl alignment_exception
+ b ret_from_except
.align 7
.globl program_check_common
program_check_common:
EXCEPTION_PROLOG_COMMON(0x700, PACA_EXGEN)
- bl .save_nvgprs
+ bl save_nvgprs
+ DISABLE_INTS
addi r3,r1,STACK_FRAME_OVERHEAD
- ENABLE_INTS
- bl .program_check_exception
- b .ret_from_except
+ bl program_check_exception
+ b ret_from_except
.align 7
.globl fp_unavailable_common
fp_unavailable_common:
EXCEPTION_PROLOG_COMMON(0x800, PACA_EXGEN)
bne 1f /* if from user, just load it up */
- bl .save_nvgprs
+ bl save_nvgprs
+ DISABLE_INTS
addi r3,r1,STACK_FRAME_OVERHEAD
- ENABLE_INTS
- bl .kernel_fp_unavailable_exception
+ bl kernel_fp_unavailable_exception
BUG_OPCODE
-1: bl .load_up_fpu
+1:
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+BEGIN_FTR_SECTION
+ /* Test if 2 TM state bits are zero. If non-zero (ie. userspace was in
+ * transaction), go do TM stuff
+ */
+ rldicl. r0, r12, (64-MSR_TS_LG), (64-2)
+ bne- 2f
+END_FTR_SECTION_IFSET(CPU_FTR_TM)
+#endif
+ bl load_up_fpu
b fast_exception_return
-
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+2: /* User process was in a transaction */
+ bl save_nvgprs
+ DISABLE_INTS
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ bl fp_unavailable_tm
+ b ret_from_except
+#endif
.align 7
.globl altivec_unavailable_common
altivec_unavailable_common:
@@ -799,16 +1244,33 @@ altivec_unavailable_common:
#ifdef CONFIG_ALTIVEC
BEGIN_FTR_SECTION
beq 1f
- bl .load_up_altivec
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ BEGIN_FTR_SECTION_NESTED(69)
+ /* Test if 2 TM state bits are zero. If non-zero (ie. userspace was in
+ * transaction), go do TM stuff
+ */
+ rldicl. r0, r12, (64-MSR_TS_LG), (64-2)
+ bne- 2f
+ END_FTR_SECTION_NESTED(CPU_FTR_TM, CPU_FTR_TM, 69)
+#endif
+ bl load_up_altivec
b fast_exception_return
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+2: /* User process was in a transaction */
+ bl save_nvgprs
+ DISABLE_INTS
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ bl altivec_unavailable_tm
+ b ret_from_except
+#endif
1:
END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
#endif
- bl .save_nvgprs
+ bl save_nvgprs
+ DISABLE_INTS
addi r3,r1,STACK_FRAME_OVERHEAD
- ENABLE_INTS
- bl .altivec_unavailable_exception
- b .ret_from_except
+ bl altivec_unavailable_exception
+ b ret_from_except
.align 7
.globl vsx_unavailable_common
@@ -816,85 +1278,315 @@ vsx_unavailable_common:
EXCEPTION_PROLOG_COMMON(0xf40, PACA_EXGEN)
#ifdef CONFIG_VSX
BEGIN_FTR_SECTION
- bne .load_up_vsx
+ beq 1f
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ BEGIN_FTR_SECTION_NESTED(69)
+ /* Test if 2 TM state bits are zero. If non-zero (ie. userspace was in
+ * transaction), go do TM stuff
+ */
+ rldicl. r0, r12, (64-MSR_TS_LG), (64-2)
+ bne- 2f
+ END_FTR_SECTION_NESTED(CPU_FTR_TM, CPU_FTR_TM, 69)
+#endif
+ b load_up_vsx
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+2: /* User process was in a transaction */
+ bl save_nvgprs
+ DISABLE_INTS
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ bl vsx_unavailable_tm
+ b ret_from_except
+#endif
1:
END_FTR_SECTION_IFSET(CPU_FTR_VSX)
#endif
- bl .save_nvgprs
+ bl save_nvgprs
+ DISABLE_INTS
addi r3,r1,STACK_FRAME_OVERHEAD
- ENABLE_INTS
- bl .vsx_unavailable_exception
- b .ret_from_except
+ bl vsx_unavailable_exception
+ b ret_from_except
+
+ STD_EXCEPTION_COMMON(0xf60, facility_unavailable, facility_unavailable_exception)
+ STD_EXCEPTION_COMMON(0xf80, hv_facility_unavailable, facility_unavailable_exception)
.align 7
.globl __end_handlers
__end_handlers:
+ /* Equivalents to the above handlers for relocation-on interrupt vectors */
+ STD_RELON_EXCEPTION_HV_OOL(0xe40, emulation_assist)
+ MASKABLE_RELON_EXCEPTION_HV_OOL(0xe80, h_doorbell)
+
+ STD_RELON_EXCEPTION_PSERIES_OOL(0xf00, performance_monitor)
+ STD_RELON_EXCEPTION_PSERIES_OOL(0xf20, altivec_unavailable)
+ STD_RELON_EXCEPTION_PSERIES_OOL(0xf40, vsx_unavailable)
+ STD_RELON_EXCEPTION_PSERIES_OOL(0xf60, facility_unavailable)
+ STD_RELON_EXCEPTION_HV_OOL(0xf80, hv_facility_unavailable)
+
+#if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV)
/*
- * Return from an exception with minimal checks.
- * The caller is assumed to have done EXCEPTION_PROLOG_COMMON.
- * If interrupts have been enabled, or anything has been
- * done that might have changed the scheduling status of
- * any task or sent any task a signal, you should use
- * ret_from_except or ret_from_except_lite instead of this.
+ * Data area reserved for FWNMI option.
+ * This address (0x7000) is fixed by the RPA.
*/
-fast_exc_return_irq: /* restores irq state too */
- ld r3,SOFTE(r1)
- TRACE_AND_RESTORE_IRQ(r3);
- ld r12,_MSR(r1)
- rldicl r4,r12,49,63 /* get MSR_EE to LSB */
- stb r4,PACAHARDIRQEN(r13) /* restore paca->hard_enabled */
- b 1f
+ .= 0x7000
+ .globl fwnmi_data_area
+fwnmi_data_area:
+
+ /* pseries and powernv need to keep the whole page from
+ * 0x7000 to 0x8000 free for use by the firmware
+ */
+ . = 0x8000
+#endif /* defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV) */
+
+/* Space for CPU0's segment table */
+ .balign 4096
+ .globl initial_stab
+initial_stab:
+ .space 4096
+
+#ifdef CONFIG_PPC_POWERNV
+_GLOBAL(opal_mc_secondary_handler)
+ HMT_MEDIUM_PPR_DISCARD
+ SET_SCRATCH0(r13)
+ GET_PACA(r13)
+ clrldi r3,r3,2
+ tovirt(r3,r3)
+ std r3,PACA_OPAL_MC_EVT(r13)
+ ld r13,OPAL_MC_SRR0(r3)
+ mtspr SPRN_SRR0,r13
+ ld r13,OPAL_MC_SRR1(r3)
+ mtspr SPRN_SRR1,r13
+ ld r3,OPAL_MC_GPR3(r3)
+ GET_SCRATCH0(r13)
+ b machine_check_pSeries
+#endif /* CONFIG_PPC_POWERNV */
- .globl fast_exception_return
-fast_exception_return:
+
+#define MACHINE_CHECK_HANDLER_WINDUP \
+ /* Clear MSR_RI before setting SRR0 and SRR1. */\
+ li r0,MSR_RI; \
+ mfmsr r9; /* get MSR value */ \
+ andc r9,r9,r0; \
+ mtmsrd r9,1; /* Clear MSR_RI */ \
+ /* Move original SRR0 and SRR1 into the respective regs */ \
+ ld r9,_MSR(r1); \
+ mtspr SPRN_SRR1,r9; \
+ ld r3,_NIP(r1); \
+ mtspr SPRN_SRR0,r3; \
+ ld r9,_CTR(r1); \
+ mtctr r9; \
+ ld r9,_XER(r1); \
+ mtxer r9; \
+ ld r9,_LINK(r1); \
+ mtlr r9; \
+ REST_GPR(0, r1); \
+ REST_8GPRS(2, r1); \
+ REST_GPR(10, r1); \
+ ld r11,_CCR(r1); \
+ mtcr r11; \
+ /* Decrement paca->in_mce. */ \
+ lhz r12,PACA_IN_MCE(r13); \
+ subi r12,r12,1; \
+ sth r12,PACA_IN_MCE(r13); \
+ REST_GPR(11, r1); \
+ REST_2GPRS(12, r1); \
+ /* restore original r1. */ \
+ ld r1,GPR1(r1)
+
+ /*
+ * Handle machine check early in real mode. We come here with
+ * ME=1, MMU (IR=0 and DR=0) off and using MC emergency stack.
+ */
+ .align 7
+ .globl machine_check_handle_early
+machine_check_handle_early:
+ std r0,GPR0(r1) /* Save r0 */
+ EXCEPTION_PROLOG_COMMON_3(0x200)
+ bl save_nvgprs
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ bl machine_check_early
+ std r3,RESULT(r1) /* Save result */
ld r12,_MSR(r1)
-1: ld r11,_NIP(r1)
- andi. r3,r12,MSR_RI /* check if RI is set */
- beq- unrecov_fer
+#ifdef CONFIG_PPC_P7_NAP
+ /*
+ * Check if thread was in power saving mode. We come here when any
+ * of the following is true:
+ * a. thread wasn't in power saving mode
+ * b. thread was in power saving mode with no state loss or
+ * supervisor state loss
+ *
+ * Go back to nap again if (b) is true.
+ */
+ rlwinm. r11,r12,47-31,30,31 /* Was it in power saving mode? */
+ beq 4f /* No, it wasn;t */
+ /* Thread was in power saving mode. Go back to nap again. */
+ cmpwi r11,2
+ bne 3f
+ /* Supervisor state loss */
+ li r0,1
+ stb r0,PACA_NAPSTATELOST(r13)
+3: bl machine_check_queue_event
+ MACHINE_CHECK_HANDLER_WINDUP
+ GET_PACA(r13)
+ ld r1,PACAR1(r13)
+ b power7_enter_nap_mode
+4:
+#endif
+ /*
+ * Check if we are coming from hypervisor userspace. If yes then we
+ * continue in host kernel in V mode to deliver the MC event.
+ */
+ rldicl. r11,r12,4,63 /* See if MC hit while in HV mode. */
+ beq 5f
+ andi. r11,r12,MSR_PR /* See if coming from user. */
+ bne 9f /* continue in V mode if we are. */
-#ifdef CONFIG_VIRT_CPU_ACCOUNTING
- andi. r3,r12,MSR_PR
- beq 2f
- ACCOUNT_CPU_USER_EXIT(r3, r4)
+5:
+#ifdef CONFIG_KVM_BOOK3S_64_HV
+ /*
+ * We are coming from kernel context. Check if we are coming from
+ * guest. if yes, then we can continue. We will fall through
+ * do_kvm_200->kvmppc_interrupt to deliver the MC event to guest.
+ */
+ lbz r11,HSTATE_IN_GUEST(r13)
+ cmpwi r11,0 /* Check if coming from guest */
+ bne 9f /* continue if we are. */
+#endif
+ /*
+ * At this point we are not sure about what context we come from.
+ * Queue up the MCE event and return from the interrupt.
+ * But before that, check if this is an un-recoverable exception.
+ * If yes, then stay on emergency stack and panic.
+ */
+ andi. r11,r12,MSR_RI
+ bne 2f
+1: mfspr r11,SPRN_SRR0
+ ld r10,PACAKBASE(r13)
+ LOAD_HANDLER(r10,unrecover_mce)
+ mtspr SPRN_SRR0,r10
+ ld r10,PACAKMSR(r13)
+ /*
+ * We are going down. But there are chances that we might get hit by
+ * another MCE during panic path and we may run into unstable state
+ * with no way out. Hence, turn ME bit off while going down, so that
+ * when another MCE is hit during panic path, system will checkstop
+ * and hypervisor will get restarted cleanly by SP.
+ */
+ li r3,MSR_ME
+ andc r10,r10,r3 /* Turn off MSR_ME */
+ mtspr SPRN_SRR1,r10
+ rfid
+ b .
2:
+ /*
+ * Check if we have successfully handled/recovered from error, if not
+ * then stay on emergency stack and panic.
+ */
+ ld r3,RESULT(r1) /* Load result */
+ cmpdi r3,0 /* see if we handled MCE successfully */
+
+ beq 1b /* if !handled then panic */
+ /*
+ * Return from MC interrupt.
+ * Queue up the MCE event so that we can log it later, while
+ * returning from kernel or opal call.
+ */
+ bl machine_check_queue_event
+ MACHINE_CHECK_HANDLER_WINDUP
+ rfid
+9:
+ /* Deliver the machine check to host kernel in V mode. */
+ MACHINE_CHECK_HANDLER_WINDUP
+ b machine_check_pSeries
+
+unrecover_mce:
+ /* Invoke machine_check_exception to print MCE event and panic. */
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ bl machine_check_exception
+ /*
+ * We will not reach here. Even if we did, there is no way out. Call
+ * unrecoverable_exception and die.
+ */
+1: addi r3,r1,STACK_FRAME_OVERHEAD
+ bl unrecoverable_exception
+ b 1b
+/*
+ * r13 points to the PACA, r9 contains the saved CR,
+ * r12 contain the saved SRR1, SRR0 is still ready for return
+ * r3 has the faulting address
+ * r9 - r13 are saved in paca->exslb.
+ * r3 is saved in paca->slb_r3
+ * We assume we aren't going to take any exceptions during this procedure.
+ */
+slb_miss_realmode:
+ mflr r10
+#ifdef CONFIG_RELOCATABLE
+ mtctr r11
#endif
- ld r3,_CCR(r1)
- ld r4,_LINK(r1)
- ld r5,_CTR(r1)
- ld r6,_XER(r1)
- mtcr r3
- mtlr r4
- mtctr r5
- mtxer r6
- REST_GPR(0, r1)
- REST_8GPRS(2, r1)
+ stw r9,PACA_EXSLB+EX_CCR(r13) /* save CR in exc. frame */
+ std r10,PACA_EXSLB+EX_LR(r13) /* save LR */
+
+ bl slb_allocate_realmode
- mfmsr r10
- rldicl r10,r10,48,1 /* clear EE */
- rldicr r10,r10,16,61 /* clear RI (LE is 0 already) */
- mtmsrd r10,1
+ /* All done -- return from exception. */
- mtspr SPRN_SRR1,r12
- mtspr SPRN_SRR0,r11
- REST_4GPRS(10, r1)
- ld r1,GPR1(r1)
+ ld r10,PACA_EXSLB+EX_LR(r13)
+ ld r3,PACA_EXSLB+EX_R3(r13)
+ lwz r9,PACA_EXSLB+EX_CCR(r13) /* get saved CR */
+
+ mtlr r10
+
+ andi. r10,r12,MSR_RI /* check for unrecoverable exception */
+ beq- 2f
+
+.machine push
+.machine "power4"
+ mtcrf 0x80,r9
+ mtcrf 0x01,r9 /* slb_allocate uses cr0 and cr7 */
+.machine pop
+
+ RESTORE_PPR_PACA(PACA_EXSLB, r9)
+ ld r9,PACA_EXSLB+EX_R9(r13)
+ ld r10,PACA_EXSLB+EX_R10(r13)
+ ld r11,PACA_EXSLB+EX_R11(r13)
+ ld r12,PACA_EXSLB+EX_R12(r13)
+ ld r13,PACA_EXSLB+EX_R13(r13)
rfid
b . /* prevent speculative execution */
-unrecov_fer:
- bl .save_nvgprs
+2: mfspr r11,SPRN_SRR0
+ ld r10,PACAKBASE(r13)
+ LOAD_HANDLER(r10,unrecov_slb)
+ mtspr SPRN_SRR0,r10
+ ld r10,PACAKMSR(r13)
+ mtspr SPRN_SRR1,r10
+ rfid
+ b .
+
+unrecov_slb:
+ EXCEPTION_PROLOG_COMMON(0x4100, PACA_EXSLB)
+ DISABLE_INTS
+ bl save_nvgprs
1: addi r3,r1,STACK_FRAME_OVERHEAD
- bl .unrecoverable_exception
+ bl unrecoverable_exception
b 1b
+#ifdef CONFIG_PPC_970_NAP
+power4_fixup_nap:
+ andc r9,r9,r10
+ std r9,TI_LOCAL_FLAGS(r11)
+ ld r10,_LINK(r1) /* make idle task do the */
+ std r10,_NIP(r1) /* equivalent of a blr */
+ blr
+#endif
+
/*
* Hash table stuff
*/
.align 7
-_STATIC(do_hash_page)
+do_hash_page:
std r3,_DAR(r1)
std r4,_DSISR(r1)
@@ -908,32 +1600,10 @@ BEGIN_FTR_SECTION
bne- do_ste_alloc /* If so handle it */
END_MMU_FTR_SECTION_IFCLR(MMU_FTR_SLB)
- clrrdi r11,r1,THREAD_SHIFT
+ CURRENT_THREAD_INFO(r11, r1)
lwz r0,TI_PREEMPT(r11) /* If we're in an "NMI" */
andis. r0,r0,NMI_MASK@h /* (i.e. an irq when soft-disabled) */
bne 77f /* then don't call hash_page now */
-
- /*
- * On iSeries, we soft-disable interrupts here, then
- * hard-enable interrupts so that the hash_page code can spin on
- * the hash_table_lock without problems on a shared processor.
- */
- DISABLE_INTS
-
- /*
- * Currently, trace_hardirqs_off() will be called by DISABLE_INTS
- * and will clobber volatile registers when irq tracing is enabled
- * so we need to reload them. It may be possible to be smarter here
- * and move the irq tracing elsewhere but let's keep it simple for
- * now
- */
-#ifdef CONFIG_TRACE_IRQFLAGS
- ld r3,_DAR(r1)
- ld r4,_DSISR(r1)
- ld r5,_TRAP(r1)
- ld r12,_MSR(r1)
- clrrdi r5,r5,4
-#endif /* CONFIG_TRACE_IRQFLAGS */
/*
* We need to set the _PAGE_USER bit if MSR_PR is set or if we are
* accessing a userspace segment (even from the kernel). We assume
@@ -951,80 +1621,51 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_SLB)
* r4 contains the required access permissions
* r5 contains the trap number
*
- * at return r3 = 0 for success
+ * at return r3 = 0 for success, 1 for page fault, negative for error
*/
- bl .hash_page /* build HPTE if possible */
+ bl hash_page /* build HPTE if possible */
cmpdi r3,0 /* see if hash_page succeeded */
-BEGIN_FW_FTR_SECTION
- /*
- * If we had interrupts soft-enabled at the point where the
- * DSI/ISI occurred, and an interrupt came in during hash_page,
- * handle it now.
- * We jump to ret_from_except_lite rather than fast_exception_return
- * because ret_from_except_lite will check for and handle pending
- * interrupts if necessary.
- */
- beq 13f
-END_FW_FTR_SECTION_IFSET(FW_FEATURE_ISERIES)
-
-BEGIN_FW_FTR_SECTION
- /*
- * Here we have interrupts hard-disabled, so it is sufficient
- * to restore paca->{soft,hard}_enable and get out.
- */
+ /* Success */
beq fast_exc_return_irq /* Return from exception on success */
-END_FW_FTR_SECTION_IFCLR(FW_FEATURE_ISERIES)
-
- /* For a hash failure, we don't bother re-enabling interrupts */
- ble- 12f
-
- /*
- * hash_page couldn't handle it, set soft interrupt enable back
- * to what it was before the trap. Note that .arch_local_irq_restore
- * handles any interrupts pending at this point.
- */
- ld r3,SOFTE(r1)
- TRACE_AND_RESTORE_IRQ_PARTIAL(r3, 11f)
- bl .arch_local_irq_restore
- b 11f
-/* We have a data breakpoint exception - handle it */
-handle_dabr_fault:
- bl .save_nvgprs
- ld r4,_DAR(r1)
- ld r5,_DSISR(r1)
- addi r3,r1,STACK_FRAME_OVERHEAD
- bl .do_dabr
- b .ret_from_except_lite
+ /* Error */
+ blt- 13f
/* Here we have a page fault that hash_page can't handle. */
handle_page_fault:
- ENABLE_INTS
11: ld r4,_DAR(r1)
ld r5,_DSISR(r1)
addi r3,r1,STACK_FRAME_OVERHEAD
- bl .do_page_fault
+ bl do_page_fault
cmpdi r3,0
- beq+ 13f
- bl .save_nvgprs
+ beq+ 12f
+ bl save_nvgprs
mr r5,r3
addi r3,r1,STACK_FRAME_OVERHEAD
lwz r4,_DAR(r1)
- bl .bad_page_fault
- b .ret_from_except
+ bl bad_page_fault
+ b ret_from_except
+
+/* We have a data breakpoint exception - handle it */
+handle_dabr_fault:
+ bl save_nvgprs
+ ld r4,_DAR(r1)
+ ld r5,_DSISR(r1)
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ bl do_break
+12: b ret_from_except_lite
-13: b .ret_from_except_lite
/* We have a page fault that hash_page could handle but HV refused
* the PTE insertion
*/
-12: bl .save_nvgprs
+13: bl save_nvgprs
mr r5,r3
addi r3,r1,STACK_FRAME_OVERHEAD
ld r4,_DAR(r1)
- bl .low_hash_fault
- b .ret_from_except
+ bl low_hash_fault
+ b ret_from_except
/*
* We come here as a result of a DSI at a point where we don't want
@@ -1033,16 +1674,16 @@ handle_page_fault:
* were soft-disabled. We want to invoke the exception handler for
* the access, or panic if there isn't a handler.
*/
-77: bl .save_nvgprs
+77: bl save_nvgprs
mr r4,r3
addi r3,r1,STACK_FRAME_OVERHEAD
li r5,SIGSEGV
- bl .bad_page_fault
- b .ret_from_except
+ bl bad_page_fault
+ b ret_from_except
/* here we have a segment miss */
do_ste_alloc:
- bl .ste_allocate /* try to insert stab entry */
+ bl ste_allocate /* try to insert stab entry */
cmpdi r3,0
bne- handle_page_fault
b fast_exception_return
@@ -1055,21 +1696,39 @@ do_ste_alloc:
* We assume (DAR >> 60) == 0xc.
*/
.align 7
-_GLOBAL(do_stab_bolted)
+do_stab_bolted:
stw r9,PACA_EXSLB+EX_CCR(r13) /* save CR in exc. frame */
std r11,PACA_EXSLB+EX_SRR0(r13) /* save SRR0 in exc. frame */
+ mfspr r11,SPRN_DAR /* ea */
+
+ /*
+ * check for bad kernel/user address
+ * (ea & ~REGION_MASK) >= PGTABLE_RANGE
+ */
+ rldicr. r9,r11,4,(63 - 46 - 4)
+ li r9,0 /* VSID = 0 for bad address */
+ bne- 0f
+
+ /*
+ * Calculate VSID:
+ * This is the kernel vsid, we take the top for context from
+ * the range. context = (MAX_USER_CONTEXT) + ((ea >> 60) - 0xc) + 1
+ * Here we know that (ea >> 60) == 0xc
+ */
+ lis r9,(MAX_USER_CONTEXT + 1)@ha
+ addi r9,r9,(MAX_USER_CONTEXT + 1)@l
+
+ srdi r10,r11,SID_SHIFT
+ rldimi r10,r9,ESID_BITS,0 /* proto vsid */
+ ASM_VSID_SCRAMBLE(r10, r9, 256M)
+ rldic r9,r10,12,16 /* r9 = vsid << 12 */
+0:
/* Hash to the primary group */
ld r10,PACASTABVIRT(r13)
- mfspr r11,SPRN_DAR
- srdi r11,r11,28
+ srdi r11,r11,SID_SHIFT
rldimi r10,r11,7,52 /* r10 = first ste of the group */
- /* Calculate VSID */
- /* This is a kernel address, so protovsid = ESID */
- ASM_VSID_SCRAMBLE(r11, r9, 256M)
- rldic r9,r11,12,16 /* r9 = vsid << 12 */
-
/* Search the primary group for a free entry */
1: ld r11,0(r10) /* Test valid bit of the current ste */
andi. r11,r11,0x80
@@ -1132,73 +1791,3 @@ _GLOBAL(do_stab_bolted)
ld r13,PACA_EXSLB+EX_R13(r13)
rfid
b . /* prevent speculative execution */
-
-#if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV)
-/*
- * Data area reserved for FWNMI option.
- * This address (0x7000) is fixed by the RPA.
- */
- .= 0x7000
- .globl fwnmi_data_area
-fwnmi_data_area:
-#endif /* defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV) */
-
- /* iSeries does not use the FWNMI stuff, so it is safe to put
- * this here, even if we later allow kernels that will boot on
- * both pSeries and iSeries */
-#ifdef CONFIG_PPC_ISERIES
- . = LPARMAP_PHYS
- .globl xLparMap
-xLparMap:
- .quad HvEsidsToMap /* xNumberEsids */
- .quad HvRangesToMap /* xNumberRanges */
- .quad STAB0_PAGE /* xSegmentTableOffs */
- .zero 40 /* xRsvd */
- /* xEsids (HvEsidsToMap entries of 2 quads) */
- .quad PAGE_OFFSET_ESID /* xKernelEsid */
- .quad PAGE_OFFSET_VSID /* xKernelVsid */
- .quad VMALLOC_START_ESID /* xKernelEsid */
- .quad VMALLOC_START_VSID /* xKernelVsid */
- /* xRanges (HvRangesToMap entries of 3 quads) */
- .quad HvPagesToMap /* xPages */
- .quad 0 /* xOffset */
- .quad PAGE_OFFSET_VSID << (SID_SHIFT - HW_PAGE_SHIFT) /* xVPN */
-
-#endif /* CONFIG_PPC_ISERIES */
-
-#if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV)
- /* pseries and powernv need to keep the whole page from
- * 0x7000 to 0x8000 free for use by the firmware
- */
- . = 0x8000
-#endif /* defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV) */
-
-/*
- * Space for CPU0's segment table.
- *
- * On iSeries, the hypervisor must fill in at least one entry before
- * we get control (with relocate on). The address is given to the hv
- * as a page number (see xLparMap above), so this must be at a
- * fixed address (the linker can't compute (u64)&initial_stab >>
- * PAGE_SHIFT).
- */
- . = STAB0_OFFSET /* 0x8000 */
- .globl initial_stab
-initial_stab:
- .space 4096
-#ifdef CONFIG_PPC_POWERNV
-_GLOBAL(opal_mc_secondary_handler)
- HMT_MEDIUM
- SET_SCRATCH0(r13)
- GET_PACA(r13)
- clrldi r3,r3,2
- tovirt(r3,r3)
- std r3,PACA_OPAL_MC_EVT(r13)
- ld r13,OPAL_MC_SRR0(r3)
- mtspr SPRN_SRR0,r13
- ld r13,OPAL_MC_SRR1(r3)
- mtspr SPRN_SRR1,r13
- ld r3,OPAL_MC_GPR3(r3)
- GET_SCRATCH0(r13)
- b machine_check_pSeries
-#endif /* CONFIG_PPC_POWERNV */
diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c
new file mode 100644
index 00000000000..742694c1d85
--- /dev/null
+++ b/arch/powerpc/kernel/fadump.c
@@ -0,0 +1,1316 @@
+/*
+ * Firmware Assisted dump: A robust mechanism to get reliable kernel crash
+ * dump with assistance from firmware. This approach does not use kexec,
+ * instead firmware assists in booting the kdump kernel while preserving
+ * memory contents. The most of the code implementation has been adapted
+ * from phyp assisted dump implementation written by Linas Vepstas and
+ * Manish Ahuja
+ *
+ * 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.
+ *
+ * Copyright 2011 IBM Corporation
+ * Author: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
+ */
+
+#undef DEBUG
+#define pr_fmt(fmt) "fadump: " fmt
+
+#include <linux/string.h>
+#include <linux/memblock.h>
+#include <linux/delay.h>
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+#include <linux/crash_dump.h>
+#include <linux/kobject.h>
+#include <linux/sysfs.h>
+
+#include <asm/page.h>
+#include <asm/prom.h>
+#include <asm/rtas.h>
+#include <asm/fadump.h>
+#include <asm/debug.h>
+#include <asm/setup.h>
+
+static struct fw_dump fw_dump;
+static struct fadump_mem_struct fdm;
+static const struct fadump_mem_struct *fdm_active;
+
+static DEFINE_MUTEX(fadump_mutex);
+struct fad_crash_memory_ranges crash_memory_ranges[INIT_CRASHMEM_RANGES];
+int crash_mem_ranges;
+
+/* Scan the Firmware Assisted dump configuration details. */
+int __init early_init_dt_scan_fw_dump(unsigned long node,
+ const char *uname, int depth, void *data)
+{
+ const __be32 *sections;
+ int i, num_sections;
+ int size;
+ const int *token;
+
+ if (depth != 1 || strcmp(uname, "rtas") != 0)
+ return 0;
+
+ /*
+ * Check if Firmware Assisted dump is supported. if yes, check
+ * if dump has been initiated on last reboot.
+ */
+ token = of_get_flat_dt_prop(node, "ibm,configure-kernel-dump", NULL);
+ if (!token)
+ return 1;
+
+ fw_dump.fadump_supported = 1;
+ fw_dump.ibm_configure_kernel_dump = *token;
+
+ /*
+ * The 'ibm,kernel-dump' rtas node is present only if there is
+ * dump data waiting for us.
+ */
+ fdm_active = of_get_flat_dt_prop(node, "ibm,kernel-dump", NULL);
+ if (fdm_active)
+ fw_dump.dump_active = 1;
+
+ /* Get the sizes required to store dump data for the firmware provided
+ * dump sections.
+ * For each dump section type supported, a 32bit cell which defines
+ * the ID of a supported section followed by two 32 bit cells which
+ * gives teh size of the section in bytes.
+ */
+ sections = of_get_flat_dt_prop(node, "ibm,configure-kernel-dump-sizes",
+ &size);
+
+ if (!sections)
+ return 1;
+
+ num_sections = size / (3 * sizeof(u32));
+
+ for (i = 0; i < num_sections; i++, sections += 3) {
+ u32 type = (u32)of_read_number(sections, 1);
+
+ switch (type) {
+ case FADUMP_CPU_STATE_DATA:
+ fw_dump.cpu_state_data_size =
+ of_read_ulong(&sections[1], 2);
+ break;
+ case FADUMP_HPTE_REGION:
+ fw_dump.hpte_region_size =
+ of_read_ulong(&sections[1], 2);
+ break;
+ }
+ }
+
+ return 1;
+}
+
+int is_fadump_active(void)
+{
+ return fw_dump.dump_active;
+}
+
+/* Print firmware assisted dump configurations for debugging purpose. */
+static void fadump_show_config(void)
+{
+ pr_debug("Support for firmware-assisted dump (fadump): %s\n",
+ (fw_dump.fadump_supported ? "present" : "no support"));
+
+ if (!fw_dump.fadump_supported)
+ return;
+
+ pr_debug("Fadump enabled : %s\n",
+ (fw_dump.fadump_enabled ? "yes" : "no"));
+ pr_debug("Dump Active : %s\n",
+ (fw_dump.dump_active ? "yes" : "no"));
+ pr_debug("Dump section sizes:\n");
+ pr_debug(" CPU state data size: %lx\n", fw_dump.cpu_state_data_size);
+ pr_debug(" HPTE region size : %lx\n", fw_dump.hpte_region_size);
+ pr_debug("Boot memory size : %lx\n", fw_dump.boot_memory_size);
+}
+
+static unsigned long init_fadump_mem_struct(struct fadump_mem_struct *fdm,
+ unsigned long addr)
+{
+ if (!fdm)
+ return 0;
+
+ memset(fdm, 0, sizeof(struct fadump_mem_struct));
+ addr = addr & PAGE_MASK;
+
+ fdm->header.dump_format_version = 0x00000001;
+ fdm->header.dump_num_sections = 3;
+ fdm->header.dump_status_flag = 0;
+ fdm->header.offset_first_dump_section =
+ (u32)offsetof(struct fadump_mem_struct, cpu_state_data);
+
+ /*
+ * Fields for disk dump option.
+ * We are not using disk dump option, hence set these fields to 0.
+ */
+ fdm->header.dd_block_size = 0;
+ fdm->header.dd_block_offset = 0;
+ fdm->header.dd_num_blocks = 0;
+ fdm->header.dd_offset_disk_path = 0;
+
+ /* set 0 to disable an automatic dump-reboot. */
+ fdm->header.max_time_auto = 0;
+
+ /* Kernel dump sections */
+ /* cpu state data section. */
+ fdm->cpu_state_data.request_flag = FADUMP_REQUEST_FLAG;
+ fdm->cpu_state_data.source_data_type = FADUMP_CPU_STATE_DATA;
+ fdm->cpu_state_data.source_address = 0;
+ fdm->cpu_state_data.source_len = fw_dump.cpu_state_data_size;
+ fdm->cpu_state_data.destination_address = addr;
+ addr += fw_dump.cpu_state_data_size;
+
+ /* hpte region section */
+ fdm->hpte_region.request_flag = FADUMP_REQUEST_FLAG;
+ fdm->hpte_region.source_data_type = FADUMP_HPTE_REGION;
+ fdm->hpte_region.source_address = 0;
+ fdm->hpte_region.source_len = fw_dump.hpte_region_size;
+ fdm->hpte_region.destination_address = addr;
+ addr += fw_dump.hpte_region_size;
+
+ /* RMA region section */
+ fdm->rmr_region.request_flag = FADUMP_REQUEST_FLAG;
+ fdm->rmr_region.source_data_type = FADUMP_REAL_MODE_REGION;
+ fdm->rmr_region.source_address = RMA_START;
+ fdm->rmr_region.source_len = fw_dump.boot_memory_size;
+ fdm->rmr_region.destination_address = addr;
+ addr += fw_dump.boot_memory_size;
+
+ return addr;
+}
+
+/**
+ * fadump_calculate_reserve_size(): reserve variable boot area 5% of System RAM
+ *
+ * Function to find the largest memory size we need to reserve during early
+ * boot process. This will be the size of the memory that is required for a
+ * kernel to boot successfully.
+ *
+ * This function has been taken from phyp-assisted dump feature implementation.
+ *
+ * returns larger of 256MB or 5% rounded down to multiples of 256MB.
+ *
+ * TODO: Come up with better approach to find out more accurate memory size
+ * that is required for a kernel to boot successfully.
+ *
+ */
+static inline unsigned long fadump_calculate_reserve_size(void)
+{
+ unsigned long size;
+
+ /*
+ * Check if the size is specified through fadump_reserve_mem= cmdline
+ * option. If yes, then use that.
+ */
+ if (fw_dump.reserve_bootvar)
+ return fw_dump.reserve_bootvar;
+
+ /* divide by 20 to get 5% of value */
+ size = memblock_end_of_DRAM() / 20;
+
+ /* round it down in multiples of 256 */
+ size = size & ~0x0FFFFFFFUL;
+
+ /* Truncate to memory_limit. We don't want to over reserve the memory.*/
+ if (memory_limit && size > memory_limit)
+ size = memory_limit;
+
+ return (size > MIN_BOOT_MEM ? size : MIN_BOOT_MEM);
+}
+
+/*
+ * Calculate the total memory size required to be reserved for
+ * firmware-assisted dump registration.
+ */
+static unsigned long get_fadump_area_size(void)
+{
+ unsigned long size = 0;
+
+ size += fw_dump.cpu_state_data_size;
+ size += fw_dump.hpte_region_size;
+ size += fw_dump.boot_memory_size;
+ size += sizeof(struct fadump_crash_info_header);
+ size += sizeof(struct elfhdr); /* ELF core header.*/
+ size += sizeof(struct elf_phdr); /* place holder for cpu notes */
+ /* Program headers for crash memory regions. */
+ size += sizeof(struct elf_phdr) * (memblock_num_regions(memory) + 2);
+
+ size = PAGE_ALIGN(size);
+ return size;
+}
+
+int __init fadump_reserve_mem(void)
+{
+ unsigned long base, size, memory_boundary;
+
+ if (!fw_dump.fadump_enabled)
+ return 0;
+
+ if (!fw_dump.fadump_supported) {
+ printk(KERN_INFO "Firmware-assisted dump is not supported on"
+ " this hardware\n");
+ fw_dump.fadump_enabled = 0;
+ return 0;
+ }
+ /*
+ * Initialize boot memory size
+ * If dump is active then we have already calculated the size during
+ * first kernel.
+ */
+ if (fdm_active)
+ fw_dump.boot_memory_size = fdm_active->rmr_region.source_len;
+ else
+ fw_dump.boot_memory_size = fadump_calculate_reserve_size();
+
+ /*
+ * Calculate the memory boundary.
+ * If memory_limit is less than actual memory boundary then reserve
+ * the memory for fadump beyond the memory_limit and adjust the
+ * memory_limit accordingly, so that the running kernel can run with
+ * specified memory_limit.
+ */
+ if (memory_limit && memory_limit < memblock_end_of_DRAM()) {
+ size = get_fadump_area_size();
+ if ((memory_limit + size) < memblock_end_of_DRAM())
+ memory_limit += size;
+ else
+ memory_limit = memblock_end_of_DRAM();
+ printk(KERN_INFO "Adjusted memory_limit for firmware-assisted"
+ " dump, now %#016llx\n", memory_limit);
+ }
+ if (memory_limit)
+ memory_boundary = memory_limit;
+ else
+ memory_boundary = memblock_end_of_DRAM();
+
+ if (fw_dump.dump_active) {
+ printk(KERN_INFO "Firmware-assisted dump is active.\n");
+ /*
+ * If last boot has crashed then reserve all the memory
+ * above boot_memory_size so that we don't touch it until
+ * dump is written to disk by userspace tool. This memory
+ * will be released for general use once the dump is saved.
+ */
+ base = fw_dump.boot_memory_size;
+ size = memory_boundary - base;
+ memblock_reserve(base, size);
+ printk(KERN_INFO "Reserved %ldMB of memory at %ldMB "
+ "for saving crash dump\n",
+ (unsigned long)(size >> 20),
+ (unsigned long)(base >> 20));
+
+ fw_dump.fadumphdr_addr =
+ fdm_active->rmr_region.destination_address +
+ fdm_active->rmr_region.source_len;
+ pr_debug("fadumphdr_addr = %p\n",
+ (void *) fw_dump.fadumphdr_addr);
+ } else {
+ /* Reserve the memory at the top of memory. */
+ size = get_fadump_area_size();
+ base = memory_boundary - size;
+ memblock_reserve(base, size);
+ printk(KERN_INFO "Reserved %ldMB of memory at %ldMB "
+ "for firmware-assisted dump\n",
+ (unsigned long)(size >> 20),
+ (unsigned long)(base >> 20));
+ }
+ fw_dump.reserve_dump_area_start = base;
+ fw_dump.reserve_dump_area_size = size;
+ return 1;
+}
+
+/* Look for fadump= cmdline option. */
+static int __init early_fadump_param(char *p)
+{
+ if (!p)
+ return 1;
+
+ if (strncmp(p, "on", 2) == 0)
+ fw_dump.fadump_enabled = 1;
+ else if (strncmp(p, "off", 3) == 0)
+ fw_dump.fadump_enabled = 0;
+
+ return 0;
+}
+early_param("fadump", early_fadump_param);
+
+/* Look for fadump_reserve_mem= cmdline option */
+static int __init early_fadump_reserve_mem(char *p)
+{
+ if (p)
+ fw_dump.reserve_bootvar = memparse(p, &p);
+ return 0;
+}
+early_param("fadump_reserve_mem", early_fadump_reserve_mem);
+
+static void register_fw_dump(struct fadump_mem_struct *fdm)
+{
+ int rc;
+ unsigned int wait_time;
+
+ pr_debug("Registering for firmware-assisted kernel dump...\n");
+
+ /* TODO: Add upper time limit for the delay */
+ do {
+ rc = rtas_call(fw_dump.ibm_configure_kernel_dump, 3, 1, NULL,
+ FADUMP_REGISTER, fdm,
+ sizeof(struct fadump_mem_struct));
+
+ wait_time = rtas_busy_delay_time(rc);
+ if (wait_time)
+ mdelay(wait_time);
+
+ } while (wait_time);
+
+ switch (rc) {
+ case -1:
+ printk(KERN_ERR "Failed to register firmware-assisted kernel"
+ " dump. Hardware Error(%d).\n", rc);
+ break;
+ case -3:
+ printk(KERN_ERR "Failed to register firmware-assisted kernel"
+ " dump. Parameter Error(%d).\n", rc);
+ break;
+ case -9:
+ printk(KERN_ERR "firmware-assisted kernel dump is already "
+ " registered.");
+ fw_dump.dump_registered = 1;
+ break;
+ case 0:
+ printk(KERN_INFO "firmware-assisted kernel dump registration"
+ " is successful\n");
+ fw_dump.dump_registered = 1;
+ break;
+ }
+}
+
+void crash_fadump(struct pt_regs *regs, const char *str)
+{
+ struct fadump_crash_info_header *fdh = NULL;
+
+ if (!fw_dump.dump_registered || !fw_dump.fadumphdr_addr)
+ return;
+
+ fdh = __va(fw_dump.fadumphdr_addr);
+ crashing_cpu = smp_processor_id();
+ fdh->crashing_cpu = crashing_cpu;
+ crash_save_vmcoreinfo();
+
+ if (regs)
+ fdh->regs = *regs;
+ else
+ ppc_save_regs(&fdh->regs);
+
+ fdh->cpu_online_mask = *cpu_online_mask;
+
+ /* Call ibm,os-term rtas call to trigger firmware assisted dump */
+ rtas_os_term((char *)str);
+}
+
+#define GPR_MASK 0xffffff0000000000
+static inline int fadump_gpr_index(u64 id)
+{
+ int i = -1;
+ char str[3];
+
+ if ((id & GPR_MASK) == REG_ID("GPR")) {
+ /* get the digits at the end */
+ id &= ~GPR_MASK;
+ id >>= 24;
+ str[2] = '\0';
+ str[1] = id & 0xff;
+ str[0] = (id >> 8) & 0xff;
+ sscanf(str, "%d", &i);
+ if (i > 31)
+ i = -1;
+ }
+ return i;
+}
+
+static inline void fadump_set_regval(struct pt_regs *regs, u64 reg_id,
+ u64 reg_val)
+{
+ int i;
+
+ i = fadump_gpr_index(reg_id);
+ if (i >= 0)
+ regs->gpr[i] = (unsigned long)reg_val;
+ else if (reg_id == REG_ID("NIA"))
+ regs->nip = (unsigned long)reg_val;
+ else if (reg_id == REG_ID("MSR"))
+ regs->msr = (unsigned long)reg_val;
+ else if (reg_id == REG_ID("CTR"))
+ regs->ctr = (unsigned long)reg_val;
+ else if (reg_id == REG_ID("LR"))
+ regs->link = (unsigned long)reg_val;
+ else if (reg_id == REG_ID("XER"))
+ regs->xer = (unsigned long)reg_val;
+ else if (reg_id == REG_ID("CR"))
+ regs->ccr = (unsigned long)reg_val;
+ else if (reg_id == REG_ID("DAR"))
+ regs->dar = (unsigned long)reg_val;
+ else if (reg_id == REG_ID("DSISR"))
+ regs->dsisr = (unsigned long)reg_val;
+}
+
+static struct fadump_reg_entry*
+fadump_read_registers(struct fadump_reg_entry *reg_entry, struct pt_regs *regs)
+{
+ memset(regs, 0, sizeof(struct pt_regs));
+
+ while (reg_entry->reg_id != REG_ID("CPUEND")) {
+ fadump_set_regval(regs, reg_entry->reg_id,
+ reg_entry->reg_value);
+ reg_entry++;
+ }
+ reg_entry++;
+ return reg_entry;
+}
+
+static u32 *fadump_append_elf_note(u32 *buf, char *name, unsigned type,
+ void *data, size_t data_len)
+{
+ struct elf_note note;
+
+ note.n_namesz = strlen(name) + 1;
+ note.n_descsz = data_len;
+ note.n_type = type;
+ memcpy(buf, &note, sizeof(note));
+ buf += (sizeof(note) + 3)/4;
+ memcpy(buf, name, note.n_namesz);
+ buf += (note.n_namesz + 3)/4;
+ memcpy(buf, data, note.n_descsz);
+ buf += (note.n_descsz + 3)/4;
+
+ return buf;
+}
+
+static void fadump_final_note(u32 *buf)
+{
+ struct elf_note note;
+
+ note.n_namesz = 0;
+ note.n_descsz = 0;
+ note.n_type = 0;
+ memcpy(buf, &note, sizeof(note));
+}
+
+static u32 *fadump_regs_to_elf_notes(u32 *buf, struct pt_regs *regs)
+{
+ struct elf_prstatus prstatus;
+
+ memset(&prstatus, 0, sizeof(prstatus));
+ /*
+ * FIXME: How do i get PID? Do I really need it?
+ * prstatus.pr_pid = ????
+ */
+ elf_core_copy_kernel_regs(&prstatus.pr_reg, regs);
+ buf = fadump_append_elf_note(buf, KEXEC_CORE_NOTE_NAME, NT_PRSTATUS,
+ &prstatus, sizeof(prstatus));
+ return buf;
+}
+
+static void fadump_update_elfcore_header(char *bufp)
+{
+ struct elfhdr *elf;
+ struct elf_phdr *phdr;
+
+ elf = (struct elfhdr *)bufp;
+ bufp += sizeof(struct elfhdr);
+
+ /* First note is a place holder for cpu notes info. */
+ phdr = (struct elf_phdr *)bufp;
+
+ if (phdr->p_type == PT_NOTE) {
+ phdr->p_paddr = fw_dump.cpu_notes_buf;
+ phdr->p_offset = phdr->p_paddr;
+ phdr->p_filesz = fw_dump.cpu_notes_buf_size;
+ phdr->p_memsz = fw_dump.cpu_notes_buf_size;
+ }
+ return;
+}
+
+static void *fadump_cpu_notes_buf_alloc(unsigned long size)
+{
+ void *vaddr;
+ struct page *page;
+ unsigned long order, count, i;
+
+ order = get_order(size);
+ vaddr = (void *)__get_free_pages(GFP_KERNEL|__GFP_ZERO, order);
+ if (!vaddr)
+ return NULL;
+
+ count = 1 << order;
+ page = virt_to_page(vaddr);
+ for (i = 0; i < count; i++)
+ SetPageReserved(page + i);
+ return vaddr;
+}
+
+static void fadump_cpu_notes_buf_free(unsigned long vaddr, unsigned long size)
+{
+ struct page *page;
+ unsigned long order, count, i;
+
+ order = get_order(size);
+ count = 1 << order;
+ page = virt_to_page(vaddr);
+ for (i = 0; i < count; i++)
+ ClearPageReserved(page + i);
+ __free_pages(page, order);
+}
+
+/*
+ * Read CPU state dump data and convert it into ELF notes.
+ * The CPU dump starts with magic number "REGSAVE". NumCpusOffset should be
+ * used to access the data to allow for additional fields to be added without
+ * affecting compatibility. Each list of registers for a CPU starts with
+ * "CPUSTRT" and ends with "CPUEND". Each register entry is of 16 bytes,
+ * 8 Byte ASCII identifier and 8 Byte register value. The register entry
+ * with identifier "CPUSTRT" and "CPUEND" contains 4 byte cpu id as part
+ * of register value. For more details refer to PAPR document.
+ *
+ * Only for the crashing cpu we ignore the CPU dump data and get exact
+ * state from fadump crash info structure populated by first kernel at the
+ * time of crash.
+ */
+static int __init fadump_build_cpu_notes(const struct fadump_mem_struct *fdm)
+{
+ struct fadump_reg_save_area_header *reg_header;
+ struct fadump_reg_entry *reg_entry;
+ struct fadump_crash_info_header *fdh = NULL;
+ void *vaddr;
+ unsigned long addr;
+ u32 num_cpus, *note_buf;
+ struct pt_regs regs;
+ int i, rc = 0, cpu = 0;
+
+ if (!fdm->cpu_state_data.bytes_dumped)
+ return -EINVAL;
+
+ addr = fdm->cpu_state_data.destination_address;
+ vaddr = __va(addr);
+
+ reg_header = vaddr;
+ if (reg_header->magic_number != REGSAVE_AREA_MAGIC) {
+ printk(KERN_ERR "Unable to read register save area.\n");
+ return -ENOENT;
+ }
+ pr_debug("--------CPU State Data------------\n");
+ pr_debug("Magic Number: %llx\n", reg_header->magic_number);
+ pr_debug("NumCpuOffset: %x\n", reg_header->num_cpu_offset);
+
+ vaddr += reg_header->num_cpu_offset;
+ num_cpus = *((u32 *)(vaddr));
+ pr_debug("NumCpus : %u\n", num_cpus);
+ vaddr += sizeof(u32);
+ reg_entry = (struct fadump_reg_entry *)vaddr;
+
+ /* Allocate buffer to hold cpu crash notes. */
+ fw_dump.cpu_notes_buf_size = num_cpus * sizeof(note_buf_t);
+ fw_dump.cpu_notes_buf_size = PAGE_ALIGN(fw_dump.cpu_notes_buf_size);
+ note_buf = fadump_cpu_notes_buf_alloc(fw_dump.cpu_notes_buf_size);
+ if (!note_buf) {
+ printk(KERN_ERR "Failed to allocate 0x%lx bytes for "
+ "cpu notes buffer\n", fw_dump.cpu_notes_buf_size);
+ return -ENOMEM;
+ }
+ fw_dump.cpu_notes_buf = __pa(note_buf);
+
+ pr_debug("Allocated buffer for cpu notes of size %ld at %p\n",
+ (num_cpus * sizeof(note_buf_t)), note_buf);
+
+ if (fw_dump.fadumphdr_addr)
+ fdh = __va(fw_dump.fadumphdr_addr);
+
+ for (i = 0; i < num_cpus; i++) {
+ if (reg_entry->reg_id != REG_ID("CPUSTRT")) {
+ printk(KERN_ERR "Unable to read CPU state data\n");
+ rc = -ENOENT;
+ goto error_out;
+ }
+ /* Lower 4 bytes of reg_value contains logical cpu id */
+ cpu = reg_entry->reg_value & FADUMP_CPU_ID_MASK;
+ if (fdh && !cpumask_test_cpu(cpu, &fdh->cpu_online_mask)) {
+ SKIP_TO_NEXT_CPU(reg_entry);
+ continue;
+ }
+ pr_debug("Reading register data for cpu %d...\n", cpu);
+ if (fdh && fdh->crashing_cpu == cpu) {
+ regs = fdh->regs;
+ note_buf = fadump_regs_to_elf_notes(note_buf, &regs);
+ SKIP_TO_NEXT_CPU(reg_entry);
+ } else {
+ reg_entry++;
+ reg_entry = fadump_read_registers(reg_entry, &regs);
+ note_buf = fadump_regs_to_elf_notes(note_buf, &regs);
+ }
+ }
+ fadump_final_note(note_buf);
+
+ if (fdh) {
+ pr_debug("Updating elfcore header (%llx) with cpu notes\n",
+ fdh->elfcorehdr_addr);
+ fadump_update_elfcore_header((char *)__va(fdh->elfcorehdr_addr));
+ }
+ return 0;
+
+error_out:
+ fadump_cpu_notes_buf_free((unsigned long)__va(fw_dump.cpu_notes_buf),
+ fw_dump.cpu_notes_buf_size);
+ fw_dump.cpu_notes_buf = 0;
+ fw_dump.cpu_notes_buf_size = 0;
+ return rc;
+
+}
+
+/*
+ * Validate and process the dump data stored by firmware before exporting
+ * it through '/proc/vmcore'.
+ */
+static int __init process_fadump(const struct fadump_mem_struct *fdm_active)
+{
+ struct fadump_crash_info_header *fdh;
+ int rc = 0;
+
+ if (!fdm_active || !fw_dump.fadumphdr_addr)
+ return -EINVAL;
+
+ /* Check if the dump data is valid. */
+ if ((fdm_active->header.dump_status_flag == FADUMP_ERROR_FLAG) ||
+ (fdm_active->cpu_state_data.error_flags != 0) ||
+ (fdm_active->rmr_region.error_flags != 0)) {
+ printk(KERN_ERR "Dump taken by platform is not valid\n");
+ return -EINVAL;
+ }
+ if ((fdm_active->rmr_region.bytes_dumped !=
+ fdm_active->rmr_region.source_len) ||
+ !fdm_active->cpu_state_data.bytes_dumped) {
+ printk(KERN_ERR "Dump taken by platform is incomplete\n");
+ return -EINVAL;
+ }
+
+ /* Validate the fadump crash info header */
+ fdh = __va(fw_dump.fadumphdr_addr);
+ if (fdh->magic_number != FADUMP_CRASH_INFO_MAGIC) {
+ printk(KERN_ERR "Crash info header is not valid.\n");
+ return -EINVAL;
+ }
+
+ rc = fadump_build_cpu_notes(fdm_active);
+ if (rc)
+ return rc;
+
+ /*
+ * We are done validating dump info and elfcore header is now ready
+ * to be exported. set elfcorehdr_addr so that vmcore module will
+ * export the elfcore header through '/proc/vmcore'.
+ */
+ elfcorehdr_addr = fdh->elfcorehdr_addr;
+
+ return 0;
+}
+
+static inline void fadump_add_crash_memory(unsigned long long base,
+ unsigned long long end)
+{
+ if (base == end)
+ return;
+
+ pr_debug("crash_memory_range[%d] [%#016llx-%#016llx], %#llx bytes\n",
+ crash_mem_ranges, base, end - 1, (end - base));
+ crash_memory_ranges[crash_mem_ranges].base = base;
+ crash_memory_ranges[crash_mem_ranges].size = end - base;
+ crash_mem_ranges++;
+}
+
+static void fadump_exclude_reserved_area(unsigned long long start,
+ unsigned long long end)
+{
+ unsigned long long ra_start, ra_end;
+
+ ra_start = fw_dump.reserve_dump_area_start;
+ ra_end = ra_start + fw_dump.reserve_dump_area_size;
+
+ if ((ra_start < end) && (ra_end > start)) {
+ if ((start < ra_start) && (end > ra_end)) {
+ fadump_add_crash_memory(start, ra_start);
+ fadump_add_crash_memory(ra_end, end);
+ } else if (start < ra_start) {
+ fadump_add_crash_memory(start, ra_start);
+ } else if (ra_end < end) {
+ fadump_add_crash_memory(ra_end, end);
+ }
+ } else
+ fadump_add_crash_memory(start, end);
+}
+
+static int fadump_init_elfcore_header(char *bufp)
+{
+ struct elfhdr *elf;
+
+ elf = (struct elfhdr *) bufp;
+ bufp += sizeof(struct elfhdr);
+ memcpy(elf->e_ident, ELFMAG, SELFMAG);
+ elf->e_ident[EI_CLASS] = ELF_CLASS;
+ elf->e_ident[EI_DATA] = ELF_DATA;
+ elf->e_ident[EI_VERSION] = EV_CURRENT;
+ elf->e_ident[EI_OSABI] = ELF_OSABI;
+ memset(elf->e_ident+EI_PAD, 0, EI_NIDENT-EI_PAD);
+ elf->e_type = ET_CORE;
+ elf->e_machine = ELF_ARCH;
+ elf->e_version = EV_CURRENT;
+ elf->e_entry = 0;
+ elf->e_phoff = sizeof(struct elfhdr);
+ elf->e_shoff = 0;
+ elf->e_flags = ELF_CORE_EFLAGS;
+ elf->e_ehsize = sizeof(struct elfhdr);
+ elf->e_phentsize = sizeof(struct elf_phdr);
+ elf->e_phnum = 0;
+ elf->e_shentsize = 0;
+ elf->e_shnum = 0;
+ elf->e_shstrndx = 0;
+
+ return 0;
+}
+
+/*
+ * Traverse through memblock structure and setup crash memory ranges. These
+ * ranges will be used create PT_LOAD program headers in elfcore header.
+ */
+static void fadump_setup_crash_memory_ranges(void)
+{
+ struct memblock_region *reg;
+ unsigned long long start, end;
+
+ pr_debug("Setup crash memory ranges.\n");
+ crash_mem_ranges = 0;
+ /*
+ * add the first memory chunk (RMA_START through boot_memory_size) as
+ * a separate memory chunk. The reason is, at the time crash firmware
+ * will move the content of this memory chunk to different location
+ * specified during fadump registration. We need to create a separate
+ * program header for this chunk with the correct offset.
+ */
+ fadump_add_crash_memory(RMA_START, fw_dump.boot_memory_size);
+
+ for_each_memblock(memory, reg) {
+ start = (unsigned long long)reg->base;
+ end = start + (unsigned long long)reg->size;
+ if (start == RMA_START && end >= fw_dump.boot_memory_size)
+ start = fw_dump.boot_memory_size;
+
+ /* add this range excluding the reserved dump area. */
+ fadump_exclude_reserved_area(start, end);
+ }
+}
+
+/*
+ * If the given physical address falls within the boot memory region then
+ * return the relocated address that points to the dump region reserved
+ * for saving initial boot memory contents.
+ */
+static inline unsigned long fadump_relocate(unsigned long paddr)
+{
+ if (paddr > RMA_START && paddr < fw_dump.boot_memory_size)
+ return fdm.rmr_region.destination_address + paddr;
+ else
+ return paddr;
+}
+
+static int fadump_create_elfcore_headers(char *bufp)
+{
+ struct elfhdr *elf;
+ struct elf_phdr *phdr;
+ int i;
+
+ fadump_init_elfcore_header(bufp);
+ elf = (struct elfhdr *)bufp;
+ bufp += sizeof(struct elfhdr);
+
+ /*
+ * setup ELF PT_NOTE, place holder for cpu notes info. The notes info
+ * will be populated during second kernel boot after crash. Hence
+ * this PT_NOTE will always be the first elf note.
+ *
+ * NOTE: Any new ELF note addition should be placed after this note.
+ */
+ phdr = (struct elf_phdr *)bufp;
+ bufp += sizeof(struct elf_phdr);
+ phdr->p_type = PT_NOTE;
+ phdr->p_flags = 0;
+ phdr->p_vaddr = 0;
+ phdr->p_align = 0;
+
+ phdr->p_offset = 0;
+ phdr->p_paddr = 0;
+ phdr->p_filesz = 0;
+ phdr->p_memsz = 0;
+
+ (elf->e_phnum)++;
+
+ /* setup ELF PT_NOTE for vmcoreinfo */
+ phdr = (struct elf_phdr *)bufp;
+ bufp += sizeof(struct elf_phdr);
+ phdr->p_type = PT_NOTE;
+ phdr->p_flags = 0;
+ phdr->p_vaddr = 0;
+ phdr->p_align = 0;
+
+ phdr->p_paddr = fadump_relocate(paddr_vmcoreinfo_note());
+ phdr->p_offset = phdr->p_paddr;
+ phdr->p_memsz = vmcoreinfo_max_size;
+ phdr->p_filesz = vmcoreinfo_max_size;
+
+ /* Increment number of program headers. */
+ (elf->e_phnum)++;
+
+ /* setup PT_LOAD sections. */
+
+ for (i = 0; i < crash_mem_ranges; i++) {
+ unsigned long long mbase, msize;
+ mbase = crash_memory_ranges[i].base;
+ msize = crash_memory_ranges[i].size;
+
+ if (!msize)
+ continue;
+
+ phdr = (struct elf_phdr *)bufp;
+ bufp += sizeof(struct elf_phdr);
+ phdr->p_type = PT_LOAD;
+ phdr->p_flags = PF_R|PF_W|PF_X;
+ phdr->p_offset = mbase;
+
+ if (mbase == RMA_START) {
+ /*
+ * The entire RMA region will be moved by firmware
+ * to the specified destination_address. Hence set
+ * the correct offset.
+ */
+ phdr->p_offset = fdm.rmr_region.destination_address;
+ }
+
+ phdr->p_paddr = mbase;
+ phdr->p_vaddr = (unsigned long)__va(mbase);
+ phdr->p_filesz = msize;
+ phdr->p_memsz = msize;
+ phdr->p_align = 0;
+
+ /* Increment number of program headers. */
+ (elf->e_phnum)++;
+ }
+ return 0;
+}
+
+static unsigned long init_fadump_header(unsigned long addr)
+{
+ struct fadump_crash_info_header *fdh;
+
+ if (!addr)
+ return 0;
+
+ fw_dump.fadumphdr_addr = addr;
+ fdh = __va(addr);
+ addr += sizeof(struct fadump_crash_info_header);
+
+ memset(fdh, 0, sizeof(struct fadump_crash_info_header));
+ fdh->magic_number = FADUMP_CRASH_INFO_MAGIC;
+ fdh->elfcorehdr_addr = addr;
+ /* We will set the crashing cpu id in crash_fadump() during crash. */
+ fdh->crashing_cpu = CPU_UNKNOWN;
+
+ return addr;
+}
+
+static void register_fadump(void)
+{
+ unsigned long addr;
+ void *vaddr;
+
+ /*
+ * If no memory is reserved then we can not register for firmware-
+ * assisted dump.
+ */
+ if (!fw_dump.reserve_dump_area_size)
+ return;
+
+ fadump_setup_crash_memory_ranges();
+
+ addr = fdm.rmr_region.destination_address + fdm.rmr_region.source_len;
+ /* Initialize fadump crash info header. */
+ addr = init_fadump_header(addr);
+ vaddr = __va(addr);
+
+ pr_debug("Creating ELF core headers at %#016lx\n", addr);
+ fadump_create_elfcore_headers(vaddr);
+
+ /* register the future kernel dump with firmware. */
+ register_fw_dump(&fdm);
+}
+
+static int fadump_unregister_dump(struct fadump_mem_struct *fdm)
+{
+ int rc = 0;
+ unsigned int wait_time;
+
+ pr_debug("Un-register firmware-assisted dump\n");
+
+ /* TODO: Add upper time limit for the delay */
+ do {
+ rc = rtas_call(fw_dump.ibm_configure_kernel_dump, 3, 1, NULL,
+ FADUMP_UNREGISTER, fdm,
+ sizeof(struct fadump_mem_struct));
+
+ wait_time = rtas_busy_delay_time(rc);
+ if (wait_time)
+ mdelay(wait_time);
+ } while (wait_time);
+
+ if (rc) {
+ printk(KERN_ERR "Failed to un-register firmware-assisted dump."
+ " unexpected error(%d).\n", rc);
+ return rc;
+ }
+ fw_dump.dump_registered = 0;
+ return 0;
+}
+
+static int fadump_invalidate_dump(struct fadump_mem_struct *fdm)
+{
+ int rc = 0;
+ unsigned int wait_time;
+
+ pr_debug("Invalidating firmware-assisted dump registration\n");
+
+ /* TODO: Add upper time limit for the delay */
+ do {
+ rc = rtas_call(fw_dump.ibm_configure_kernel_dump, 3, 1, NULL,
+ FADUMP_INVALIDATE, fdm,
+ sizeof(struct fadump_mem_struct));
+
+ wait_time = rtas_busy_delay_time(rc);
+ if (wait_time)
+ mdelay(wait_time);
+ } while (wait_time);
+
+ if (rc) {
+ printk(KERN_ERR "Failed to invalidate firmware-assisted dump "
+ "rgistration. unexpected error(%d).\n", rc);
+ return rc;
+ }
+ fw_dump.dump_active = 0;
+ fdm_active = NULL;
+ return 0;
+}
+
+void fadump_cleanup(void)
+{
+ /* Invalidate the registration only if dump is active. */
+ if (fw_dump.dump_active) {
+ init_fadump_mem_struct(&fdm,
+ fdm_active->cpu_state_data.destination_address);
+ fadump_invalidate_dump(&fdm);
+ }
+}
+
+/*
+ * Release the memory that was reserved in early boot to preserve the memory
+ * contents. The released memory will be available for general use.
+ */
+static void fadump_release_memory(unsigned long begin, unsigned long end)
+{
+ unsigned long addr;
+ unsigned long ra_start, ra_end;
+
+ ra_start = fw_dump.reserve_dump_area_start;
+ ra_end = ra_start + fw_dump.reserve_dump_area_size;
+
+ for (addr = begin; addr < end; addr += PAGE_SIZE) {
+ /*
+ * exclude the dump reserve area. Will reuse it for next
+ * fadump registration.
+ */
+ if (addr <= ra_end && ((addr + PAGE_SIZE) > ra_start))
+ continue;
+
+ free_reserved_page(pfn_to_page(addr >> PAGE_SHIFT));
+ }
+}
+
+static void fadump_invalidate_release_mem(void)
+{
+ unsigned long reserved_area_start, reserved_area_end;
+ unsigned long destination_address;
+
+ mutex_lock(&fadump_mutex);
+ if (!fw_dump.dump_active) {
+ mutex_unlock(&fadump_mutex);
+ return;
+ }
+
+ destination_address = fdm_active->cpu_state_data.destination_address;
+ fadump_cleanup();
+ mutex_unlock(&fadump_mutex);
+
+ /*
+ * Save the current reserved memory bounds we will require them
+ * later for releasing the memory for general use.
+ */
+ reserved_area_start = fw_dump.reserve_dump_area_start;
+ reserved_area_end = reserved_area_start +
+ fw_dump.reserve_dump_area_size;
+ /*
+ * Setup reserve_dump_area_start and its size so that we can
+ * reuse this reserved memory for Re-registration.
+ */
+ fw_dump.reserve_dump_area_start = destination_address;
+ fw_dump.reserve_dump_area_size = get_fadump_area_size();
+
+ fadump_release_memory(reserved_area_start, reserved_area_end);
+ if (fw_dump.cpu_notes_buf) {
+ fadump_cpu_notes_buf_free(
+ (unsigned long)__va(fw_dump.cpu_notes_buf),
+ fw_dump.cpu_notes_buf_size);
+ fw_dump.cpu_notes_buf = 0;
+ fw_dump.cpu_notes_buf_size = 0;
+ }
+ /* Initialize the kernel dump memory structure for FAD registration. */
+ init_fadump_mem_struct(&fdm, fw_dump.reserve_dump_area_start);
+}
+
+static ssize_t fadump_release_memory_store(struct kobject *kobj,
+ struct kobj_attribute *attr,
+ const char *buf, size_t count)
+{
+ if (!fw_dump.dump_active)
+ return -EPERM;
+
+ if (buf[0] == '1') {
+ /*
+ * Take away the '/proc/vmcore'. We are releasing the dump
+ * memory, hence it will not be valid anymore.
+ */
+ vmcore_cleanup();
+ fadump_invalidate_release_mem();
+
+ } else
+ return -EINVAL;
+ return count;
+}
+
+static ssize_t fadump_enabled_show(struct kobject *kobj,
+ struct kobj_attribute *attr,
+ char *buf)
+{
+ return sprintf(buf, "%d\n", fw_dump.fadump_enabled);
+}
+
+static ssize_t fadump_register_show(struct kobject *kobj,
+ struct kobj_attribute *attr,
+ char *buf)
+{
+ return sprintf(buf, "%d\n", fw_dump.dump_registered);
+}
+
+static ssize_t fadump_register_store(struct kobject *kobj,
+ struct kobj_attribute *attr,
+ const char *buf, size_t count)
+{
+ int ret = 0;
+
+ if (!fw_dump.fadump_enabled || fdm_active)
+ return -EPERM;
+
+ mutex_lock(&fadump_mutex);
+
+ switch (buf[0]) {
+ case '0':
+ if (fw_dump.dump_registered == 0) {
+ ret = -EINVAL;
+ goto unlock_out;
+ }
+ /* Un-register Firmware-assisted dump */
+ fadump_unregister_dump(&fdm);
+ break;
+ case '1':
+ if (fw_dump.dump_registered == 1) {
+ ret = -EINVAL;
+ goto unlock_out;
+ }
+ /* Register Firmware-assisted dump */
+ register_fadump();
+ break;
+ default:
+ ret = -EINVAL;
+ break;
+ }
+
+unlock_out:
+ mutex_unlock(&fadump_mutex);
+ return ret < 0 ? ret : count;
+}
+
+static int fadump_region_show(struct seq_file *m, void *private)
+{
+ const struct fadump_mem_struct *fdm_ptr;
+
+ if (!fw_dump.fadump_enabled)
+ return 0;
+
+ mutex_lock(&fadump_mutex);
+ if (fdm_active)
+ fdm_ptr = fdm_active;
+ else {
+ mutex_unlock(&fadump_mutex);
+ fdm_ptr = &fdm;
+ }
+
+ seq_printf(m,
+ "CPU : [%#016llx-%#016llx] %#llx bytes, "
+ "Dumped: %#llx\n",
+ fdm_ptr->cpu_state_data.destination_address,
+ fdm_ptr->cpu_state_data.destination_address +
+ fdm_ptr->cpu_state_data.source_len - 1,
+ fdm_ptr->cpu_state_data.source_len,
+ fdm_ptr->cpu_state_data.bytes_dumped);
+ seq_printf(m,
+ "HPTE: [%#016llx-%#016llx] %#llx bytes, "
+ "Dumped: %#llx\n",
+ fdm_ptr->hpte_region.destination_address,
+ fdm_ptr->hpte_region.destination_address +
+ fdm_ptr->hpte_region.source_len - 1,
+ fdm_ptr->hpte_region.source_len,
+ fdm_ptr->hpte_region.bytes_dumped);
+ seq_printf(m,
+ "DUMP: [%#016llx-%#016llx] %#llx bytes, "
+ "Dumped: %#llx\n",
+ fdm_ptr->rmr_region.destination_address,
+ fdm_ptr->rmr_region.destination_address +
+ fdm_ptr->rmr_region.source_len - 1,
+ fdm_ptr->rmr_region.source_len,
+ fdm_ptr->rmr_region.bytes_dumped);
+
+ if (!fdm_active ||
+ (fw_dump.reserve_dump_area_start ==
+ fdm_ptr->cpu_state_data.destination_address))
+ goto out;
+
+ /* Dump is active. Show reserved memory region. */
+ seq_printf(m,
+ " : [%#016llx-%#016llx] %#llx bytes, "
+ "Dumped: %#llx\n",
+ (unsigned long long)fw_dump.reserve_dump_area_start,
+ fdm_ptr->cpu_state_data.destination_address - 1,
+ fdm_ptr->cpu_state_data.destination_address -
+ fw_dump.reserve_dump_area_start,
+ fdm_ptr->cpu_state_data.destination_address -
+ fw_dump.reserve_dump_area_start);
+out:
+ if (fdm_active)
+ mutex_unlock(&fadump_mutex);
+ return 0;
+}
+
+static struct kobj_attribute fadump_release_attr = __ATTR(fadump_release_mem,
+ 0200, NULL,
+ fadump_release_memory_store);
+static struct kobj_attribute fadump_attr = __ATTR(fadump_enabled,
+ 0444, fadump_enabled_show,
+ NULL);
+static struct kobj_attribute fadump_register_attr = __ATTR(fadump_registered,
+ 0644, fadump_register_show,
+ fadump_register_store);
+
+static int fadump_region_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, fadump_region_show, inode->i_private);
+}
+
+static const struct file_operations fadump_region_fops = {
+ .open = fadump_region_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+
+static void fadump_init_files(void)
+{
+ struct dentry *debugfs_file;
+ int rc = 0;
+
+ rc = sysfs_create_file(kernel_kobj, &fadump_attr.attr);
+ if (rc)
+ printk(KERN_ERR "fadump: unable to create sysfs file"
+ " fadump_enabled (%d)\n", rc);
+
+ rc = sysfs_create_file(kernel_kobj, &fadump_register_attr.attr);
+ if (rc)
+ printk(KERN_ERR "fadump: unable to create sysfs file"
+ " fadump_registered (%d)\n", rc);
+
+ debugfs_file = debugfs_create_file("fadump_region", 0444,
+ powerpc_debugfs_root, NULL,
+ &fadump_region_fops);
+ if (!debugfs_file)
+ printk(KERN_ERR "fadump: unable to create debugfs file"
+ " fadump_region\n");
+
+ if (fw_dump.dump_active) {
+ rc = sysfs_create_file(kernel_kobj, &fadump_release_attr.attr);
+ if (rc)
+ printk(KERN_ERR "fadump: unable to create sysfs file"
+ " fadump_release_mem (%d)\n", rc);
+ }
+ return;
+}
+
+/*
+ * Prepare for firmware-assisted dump.
+ */
+int __init setup_fadump(void)
+{
+ if (!fw_dump.fadump_enabled)
+ return 0;
+
+ if (!fw_dump.fadump_supported) {
+ printk(KERN_ERR "Firmware-assisted dump is not supported on"
+ " this hardware\n");
+ return 0;
+ }
+
+ fadump_show_config();
+ /*
+ * If dump data is available then see if it is valid and prepare for
+ * saving it to the disk.
+ */
+ if (fw_dump.dump_active) {
+ /*
+ * if dump process fails then invalidate the registration
+ * and release memory before proceeding for re-registration.
+ */
+ if (process_fadump(fdm_active) < 0)
+ fadump_invalidate_release_mem();
+ }
+ /* Initialize the kernel dump memory structure for FAD registration. */
+ else if (fw_dump.reserve_dump_area_size)
+ init_fadump_mem_struct(&fdm, fw_dump.reserve_dump_area_start);
+ fadump_init_files();
+
+ return 1;
+}
+subsys_initcall(setup_fadump);
diff --git a/arch/powerpc/kernel/fpu.S b/arch/powerpc/kernel/fpu.S
index de369558bf0..9ad236e5d2c 100644
--- a/arch/powerpc/kernel/fpu.S
+++ b/arch/powerpc/kernel/fpu.S
@@ -26,7 +26,7 @@
#include <asm/ptrace.h>
#ifdef CONFIG_VSX
-#define REST_32FPVSRS(n,c,base) \
+#define __REST_32FPVSRS(n,c,base) \
BEGIN_FTR_SECTION \
b 2f; \
END_FTR_SECTION_IFSET(CPU_FTR_VSX); \
@@ -35,7 +35,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX); \
2: REST_32VSRS(n,c,base); \
3:
-#define SAVE_32FPVSRS(n,c,base) \
+#define __SAVE_32FPVSRS(n,c,base) \
BEGIN_FTR_SECTION \
b 2f; \
END_FTR_SECTION_IFSET(CPU_FTR_VSX); \
@@ -44,9 +44,77 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX); \
2: SAVE_32VSRS(n,c,base); \
3:
#else
-#define REST_32FPVSRS(n,b,base) REST_32FPRS(n, base)
-#define SAVE_32FPVSRS(n,b,base) SAVE_32FPRS(n, base)
+#define __REST_32FPVSRS(n,b,base) REST_32FPRS(n, base)
+#define __SAVE_32FPVSRS(n,b,base) SAVE_32FPRS(n, base)
#endif
+#define REST_32FPVSRS(n,c,base) __REST_32FPVSRS(n,__REG_##c,__REG_##base)
+#define SAVE_32FPVSRS(n,c,base) __SAVE_32FPVSRS(n,__REG_##c,__REG_##base)
+
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+/* void do_load_up_transact_fpu(struct thread_struct *thread)
+ *
+ * This is similar to load_up_fpu but for the transactional version of the FP
+ * register set. It doesn't mess with the task MSR or valid flags.
+ * Furthermore, we don't do lazy FP with TM currently.
+ */
+_GLOBAL(do_load_up_transact_fpu)
+ mfmsr r6
+ ori r5,r6,MSR_FP
+#ifdef CONFIG_VSX
+BEGIN_FTR_SECTION
+ oris r5,r5,MSR_VSX@h
+END_FTR_SECTION_IFSET(CPU_FTR_VSX)
+#endif
+ SYNC
+ MTMSRD(r5)
+
+ addi r7,r3,THREAD_TRANSACT_FPSTATE
+ lfd fr0,FPSTATE_FPSCR(r7)
+ MTFSF_L(fr0)
+ REST_32FPVSRS(0, R4, R7)
+
+ /* FP/VSX off again */
+ MTMSRD(r6)
+ SYNC
+
+ blr
+#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
+
+/*
+ * Enable use of the FPU, and VSX if possible, for the caller.
+ */
+_GLOBAL(fp_enable)
+ mfmsr r3
+ ori r3,r3,MSR_FP
+#ifdef CONFIG_VSX
+BEGIN_FTR_SECTION
+ oris r3,r3,MSR_VSX@h
+END_FTR_SECTION_IFSET(CPU_FTR_VSX)
+#endif
+ SYNC
+ MTMSRD(r3)
+ isync /* (not necessary for arch 2.02 and later) */
+ blr
+
+/*
+ * Load state from memory into FP registers including FPSCR.
+ * Assumes the caller has enabled FP in the MSR.
+ */
+_GLOBAL(load_fp_state)
+ lfd fr0,FPSTATE_FPSCR(r3)
+ MTFSF_L(fr0)
+ REST_32FPVSRS(0, R4, R3)
+ blr
+
+/*
+ * Store FP state into memory, including FPSCR
+ * Assumes the caller has enabled FP in the MSR.
+ */
+_GLOBAL(store_fp_state)
+ SAVE_32FPVSRS(0, R4, R3)
+ mffs fr0
+ stfd fr0,FPSTATE_FPSCR(r3)
+ blr
/*
* This task wants to use the FPU now.
@@ -54,6 +122,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX); \
* and save its floating-point registers in its thread_struct.
* Load up this task's FP registers from its thread_struct,
* enable the FPU for the current task and return to the task.
+ * Note that on 32-bit this can only use registers that will be
+ * restored by fast_exception_return, i.e. r3 - r6, r10 and r11.
*/
_GLOBAL(load_up_fpu)
mfmsr r5
@@ -79,9 +149,10 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX)
beq 1f
toreal(r4)
addi r4,r4,THREAD /* want last_task_used_math->thread */
- SAVE_32FPVSRS(0, r5, r4)
+ addi r10,r4,THREAD_FPSTATE
+ SAVE_32FPVSRS(0, R5, R10)
mffs fr0
- stfd fr0,THREAD_FPSCR(r4)
+ stfd fr0,FPSTATE_FPSCR(r10)
PPC_LL r5,PT_REGS(r4)
toreal(r5)
PPC_LL r4,_MSR-STACK_FRAME_OVERHEAD(r5)
@@ -92,7 +163,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX)
#endif /* CONFIG_SMP */
/* enable use of FP after return */
#ifdef CONFIG_PPC32
- mfspr r5,SPRN_SPRG_THREAD /* current task's THREAD (phys) */
+ mfspr r5,SPRN_SPRG_THREAD /* current task's THREAD (phys) */
lwz r4,THREAD_FPEXC_MODE(r5)
ori r9,r9,MSR_FP /* enable FP for current */
or r9,r9,r4
@@ -104,9 +175,10 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX)
or r12,r12,r4
std r12,_MSR(r1)
#endif
- lfd fr0,THREAD_FPSCR(r5)
+ addi r10,r5,THREAD_FPSTATE
+ lfd fr0,FPSTATE_FPSCR(r10)
MTFSF_L(fr0)
- REST_32FPVSRS(0, r4, r5)
+ REST_32FPVSRS(0, R4, R10)
#ifndef CONFIG_SMP
subi r4,r5,THREAD
fromreal(r4)
@@ -138,11 +210,15 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX)
PPC_LCMPI 0,r3,0
beqlr- /* if no previous owner, done */
addi r3,r3,THREAD /* want THREAD of task */
+ PPC_LL r6,THREAD_FPSAVEAREA(r3)
PPC_LL r5,PT_REGS(r3)
- PPC_LCMPI 0,r5,0
- SAVE_32FPVSRS(0, r4 ,r3)
+ PPC_LCMPI 0,r6,0
+ bne 2f
+ addi r6,r3,THREAD_FPSTATE
+2: PPC_LCMPI 0,r5,0
+ SAVE_32FPVSRS(0, R4, R6)
mffs fr0
- stfd fr0,THREAD_FPSCR(r3)
+ stfd fr0,FPSTATE_FPSCR(r6)
beq 1f
PPC_LL r4,_MSR-STACK_FRAME_OVERHEAD(r5)
li r3,MSR_FP|MSR_FE0|MSR_FE1
diff --git a/arch/powerpc/kernel/fsl_booke_entry_mapping.S b/arch/powerpc/kernel/fsl_booke_entry_mapping.S
index a92c79be272..f22e7e44fbf 100644
--- a/arch/powerpc/kernel/fsl_booke_entry_mapping.S
+++ b/arch/powerpc/kernel/fsl_booke_entry_mapping.S
@@ -176,6 +176,8 @@ skpinv: addi r6,r6,1 /* Increment */
/* 7. Jump to KERNELBASE mapping */
lis r6,(KERNELBASE & ~0xfff)@h
ori r6,r6,(KERNELBASE & ~0xfff)@l
+ rlwinm r7,r25,0,0x03ffffff
+ add r6,r7,r6
#elif defined(ENTRY_MAPPING_KEXEC_SETUP)
/*
diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c
index bf99cfa6bbf..d178834fe50 100644
--- a/arch/powerpc/kernel/ftrace.c
+++ b/arch/powerpc/kernel/ftrace.c
@@ -10,6 +10,8 @@
*
*/
+#define pr_fmt(fmt) "ftrace-powerpc: " fmt
+
#include <linux/spinlock.h>
#include <linux/hardirq.h>
#include <linux/uaccess.h>
@@ -63,11 +65,9 @@ ftrace_modify_code(unsigned long ip, unsigned int old, unsigned int new)
return -EINVAL;
/* replace the text with the new text */
- if (probe_kernel_write((void *)ip, &new, MCOUNT_INSN_SIZE))
+ if (patch_instruction((unsigned int *)ip, new))
return -EPERM;
- flush_icache_range(ip, ip + 8);
-
return 0;
}
@@ -76,6 +76,7 @@ ftrace_modify_code(unsigned long ip, unsigned int old, unsigned int new)
*/
static int test_24bit_addr(unsigned long ip, unsigned long addr)
{
+ addr = ppc_function_entry((void *)addr);
/* use the create_branch to verify that this offset can be branched */
return create_branch((unsigned int *)ip, addr, 0);
@@ -106,11 +107,9 @@ __ftrace_make_nop(struct module *mod,
struct dyn_ftrace *rec, unsigned long addr)
{
unsigned int op;
- unsigned int jmp[5];
- unsigned long ptr;
+ unsigned long entry, ptr;
unsigned long ip = rec->ip;
- unsigned long tramp;
- int offset;
+ void *tramp;
/* read where this goes */
if (probe_kernel_read(&op, (void *)ip, sizeof(int)))
@@ -118,106 +117,52 @@ __ftrace_make_nop(struct module *mod,
/* Make sure that that this is still a 24bit jump */
if (!is_bl_op(op)) {
- printk(KERN_ERR "Not expected bl: opcode is %x\n", op);
+ pr_err("Not expected bl: opcode is %x\n", op);
return -EINVAL;
}
/* lets find where the pointer goes */
- tramp = find_bl_target(ip, op);
+ tramp = (void *)find_bl_target(ip, op);
- /*
- * On PPC64 the trampoline looks like:
- * 0x3d, 0x82, 0x00, 0x00, addis r12,r2, <high>
- * 0x39, 0x8c, 0x00, 0x00, addi r12,r12, <low>
- * Where the bytes 2,3,6 and 7 make up the 32bit offset
- * to the TOC that holds the pointer.
- * to jump to.
- * 0xf8, 0x41, 0x00, 0x28, std r2,40(r1)
- * 0xe9, 0x6c, 0x00, 0x20, ld r11,32(r12)
- * The actually address is 32 bytes from the offset
- * into the TOC.
- * 0xe8, 0x4c, 0x00, 0x28, ld r2,40(r12)
- */
-
- pr_devel("ip:%lx jumps to %lx r2: %lx", ip, tramp, mod->arch.toc);
+ pr_devel("ip:%lx jumps to %p", ip, tramp);
- /* Find where the trampoline jumps to */
- if (probe_kernel_read(jmp, (void *)tramp, sizeof(jmp))) {
- printk(KERN_ERR "Failed to read %lx\n", tramp);
- return -EFAULT;
- }
-
- pr_devel(" %08x %08x", jmp[0], jmp[1]);
-
- /* verify that this is what we expect it to be */
- if (((jmp[0] & 0xffff0000) != 0x3d820000) ||
- ((jmp[1] & 0xffff0000) != 0x398c0000) ||
- (jmp[2] != 0xf8410028) ||
- (jmp[3] != 0xe96c0020) ||
- (jmp[4] != 0xe84c0028)) {
- printk(KERN_ERR "Not a trampoline\n");
+ if (!is_module_trampoline(tramp)) {
+ pr_err("Not a trampoline\n");
return -EINVAL;
}
- /* The bottom half is signed extended */
- offset = ((unsigned)((unsigned short)jmp[0]) << 16) +
- (int)((short)jmp[1]);
-
- pr_devel(" %x ", offset);
-
- /* get the address this jumps too */
- tramp = mod->arch.toc + offset + 32;
- pr_devel("toc: %lx", tramp);
-
- if (probe_kernel_read(jmp, (void *)tramp, 8)) {
- printk(KERN_ERR "Failed to read %lx\n", tramp);
+ if (module_trampoline_target(mod, tramp, &ptr)) {
+ pr_err("Failed to get trampoline target\n");
return -EFAULT;
}
- pr_devel(" %08x %08x\n", jmp[0], jmp[1]);
-
- ptr = ((unsigned long)jmp[0] << 32) + jmp[1];
+ pr_devel("trampoline target %lx", ptr);
+ entry = ppc_global_function_entry((void *)addr);
/* This should match what was called */
- if (ptr != ppc_function_entry((void *)addr)) {
- printk(KERN_ERR "addr does not match %lx\n", ptr);
+ if (ptr != entry) {
+ pr_err("addr %lx does not match expected %lx\n", ptr, entry);
return -EINVAL;
}
/*
- * We want to nop the line, but the next line is
- * 0xe8, 0x41, 0x00, 0x28 ld r2,40(r1)
- * This needs to be turned to a nop too.
- */
- if (probe_kernel_read(&op, (void *)(ip+4), MCOUNT_INSN_SIZE))
- return -EFAULT;
-
- if (op != 0xe8410028) {
- printk(KERN_ERR "Next line is not ld! (%08x)\n", op);
- return -EINVAL;
- }
-
- /*
- * Milton Miller pointed out that we can not blindly do nops.
- * If a task was preempted when calling a trace function,
- * the nops will remove the way to restore the TOC in r2
- * and the r2 TOC will get corrupted.
- */
-
- /*
- * Replace:
- * bl <tramp> <==== will be replaced with "b 1f"
- * ld r2,40(r1)
- * 1:
+ * Our original call site looks like:
+ *
+ * bl <tramp>
+ * ld r2,XX(r1)
+ *
+ * Milton Miller pointed out that we can not simply nop the branch.
+ * If a task was preempted when calling a trace function, the nops
+ * will remove the way to restore the TOC in r2 and the r2 TOC will
+ * get corrupted.
+ *
+ * Use a b +8 to jump over the load.
*/
op = 0x48000008; /* b +8 */
- if (probe_kernel_write((void *)ip, &op, MCOUNT_INSN_SIZE))
+ if (patch_instruction((unsigned int *)ip, op))
return -EPERM;
-
- flush_icache_range(ip, ip + 8);
-
return 0;
}
@@ -236,7 +181,7 @@ __ftrace_make_nop(struct module *mod,
/* Make sure that that this is still a 24bit jump */
if (!is_bl_op(op)) {
- printk(KERN_ERR "Not expected bl: opcode is %x\n", op);
+ pr_err("Not expected bl: opcode is %x\n", op);
return -EINVAL;
}
@@ -245,9 +190,9 @@ __ftrace_make_nop(struct module *mod,
/*
* On PPC32 the trampoline looks like:
- * 0x3d, 0x60, 0x00, 0x00 lis r11,sym@ha
- * 0x39, 0x6b, 0x00, 0x00 addi r11,r11,sym@l
- * 0x7d, 0x69, 0x03, 0xa6 mtctr r11
+ * 0x3d, 0x80, 0x00, 0x00 lis r12,sym@ha
+ * 0x39, 0x8c, 0x00, 0x00 addi r12,r12,sym@l
+ * 0x7d, 0x89, 0x03, 0xa6 mtctr r12
* 0x4e, 0x80, 0x04, 0x20 bctr
*/
@@ -255,18 +200,18 @@ __ftrace_make_nop(struct module *mod,
/* Find where the trampoline jumps to */
if (probe_kernel_read(jmp, (void *)tramp, sizeof(jmp))) {
- printk(KERN_ERR "Failed to read %lx\n", tramp);
+ pr_err("Failed to read %lx\n", tramp);
return -EFAULT;
}
pr_devel(" %08x %08x ", jmp[0], jmp[1]);
/* verify that this is what we expect it to be */
- if (((jmp[0] & 0xffff0000) != 0x3d600000) ||
- ((jmp[1] & 0xffff0000) != 0x396b0000) ||
- (jmp[2] != 0x7d6903a6) ||
+ if (((jmp[0] & 0xffff0000) != 0x3d800000) ||
+ ((jmp[1] & 0xffff0000) != 0x398c0000) ||
+ (jmp[2] != 0x7d8903a6) ||
(jmp[3] != 0x4e800420)) {
- printk(KERN_ERR "Not a trampoline\n");
+ pr_err("Not a trampoline\n");
return -EINVAL;
}
@@ -278,19 +223,16 @@ __ftrace_make_nop(struct module *mod,
pr_devel(" %lx ", tramp);
if (tramp != addr) {
- printk(KERN_ERR
- "Trampoline location %08lx does not match addr\n",
+ pr_err("Trampoline location %08lx does not match addr\n",
tramp);
return -EINVAL;
}
op = PPC_INST_NOP;
- if (probe_kernel_write((void *)ip, &op, MCOUNT_INSN_SIZE))
+ if (patch_instruction((unsigned int *)ip, op))
return -EPERM;
- flush_icache_range(ip, ip + 8);
-
return 0;
}
#endif /* PPC64 */
@@ -322,15 +264,13 @@ int ftrace_make_nop(struct module *mod,
*/
if (!rec->arch.mod) {
if (!mod) {
- printk(KERN_ERR "No module loaded addr=%lx\n",
- addr);
+ pr_err("No module loaded addr=%lx\n", addr);
return -EFAULT;
}
rec->arch.mod = mod;
} else if (mod) {
if (mod != rec->arch.mod) {
- printk(KERN_ERR
- "Record mod %p not equal to passed in mod %p\n",
+ pr_err("Record mod %p not equal to passed in mod %p\n",
rec->arch.mod, mod);
return -EINVAL;
}
@@ -351,45 +291,42 @@ static int
__ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
{
unsigned int op[2];
- unsigned long ip = rec->ip;
+ void *ip = (void *)rec->ip;
/* read where this goes */
- if (probe_kernel_read(op, (void *)ip, MCOUNT_INSN_SIZE * 2))
+ if (probe_kernel_read(op, ip, sizeof(op)))
return -EFAULT;
/*
- * It should be pointing to two nops or
- * b +8; ld r2,40(r1)
+ * We expect to see:
+ *
+ * b +8
+ * ld r2,XX(r1)
+ *
+ * The load offset is different depending on the ABI. For simplicity
+ * just mask it out when doing the compare.
*/
- if (((op[0] != 0x48000008) || (op[1] != 0xe8410028)) &&
- ((op[0] != PPC_INST_NOP) || (op[1] != PPC_INST_NOP))) {
- printk(KERN_ERR "Expected NOPs but have %x %x\n", op[0], op[1]);
+ if ((op[0] != 0x48000008) || ((op[1] & 0xffff0000) != 0xe8410000)) {
+ pr_err("Unexpected call sequence: %x %x\n", op[0], op[1]);
return -EINVAL;
}
/* If we never set up a trampoline to ftrace_caller, then bail */
if (!rec->arch.mod->arch.tramp) {
- printk(KERN_ERR "No ftrace trampoline\n");
+ pr_err("No ftrace trampoline\n");
return -EINVAL;
}
- /* create the branch to the trampoline */
- op[0] = create_branch((unsigned int *)ip,
- rec->arch.mod->arch.tramp, BRANCH_SET_LINK);
- if (!op[0]) {
- printk(KERN_ERR "REL24 out of range!\n");
+ /* Ensure branch is within 24 bits */
+ if (!create_branch(ip, rec->arch.mod->arch.tramp, BRANCH_SET_LINK)) {
+ pr_err("Branch out of range\n");
return -EINVAL;
}
- /* ld r2,40(r1) */
- op[1] = 0xe8410028;
-
- pr_devel("write to %lx\n", rec->ip);
-
- if (probe_kernel_write((void *)ip, op, MCOUNT_INSN_SIZE * 2))
- return -EPERM;
-
- flush_icache_range(ip, ip + 8);
+ if (patch_branch(ip, rec->arch.mod->arch.tramp, BRANCH_SET_LINK)) {
+ pr_err("REL24 out of range!\n");
+ return -EINVAL;
+ }
return 0;
}
@@ -406,13 +343,13 @@ __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
/* It should be pointing to a nop */
if (op != PPC_INST_NOP) {
- printk(KERN_ERR "Expected NOP but have %x\n", op);
+ pr_err("Expected NOP but have %x\n", op);
return -EINVAL;
}
/* If we never set up a trampoline to ftrace_caller, then bail */
if (!rec->arch.mod->arch.tramp) {
- printk(KERN_ERR "No ftrace trampoline\n");
+ pr_err("No ftrace trampoline\n");
return -EINVAL;
}
@@ -420,17 +357,15 @@ __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
op = create_branch((unsigned int *)ip,
rec->arch.mod->arch.tramp, BRANCH_SET_LINK);
if (!op) {
- printk(KERN_ERR "REL24 out of range!\n");
+ pr_err("REL24 out of range!\n");
return -EINVAL;
}
pr_devel("write to %lx\n", rec->ip);
- if (probe_kernel_write((void *)ip, &op, MCOUNT_INSN_SIZE))
+ if (patch_instruction((unsigned int *)ip, op))
return -EPERM;
- flush_icache_range(ip, ip + 8);
-
return 0;
}
#endif /* CONFIG_PPC64 */
@@ -460,7 +395,7 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
* already have a module defined.
*/
if (!rec->arch.mod) {
- printk(KERN_ERR "No module loaded\n");
+ pr_err("No module loaded\n");
return -EINVAL;
}
@@ -484,13 +419,60 @@ int ftrace_update_ftrace_func(ftrace_func_t func)
return ret;
}
-int __init ftrace_dyn_arch_init(void *data)
+static int __ftrace_replace_code(struct dyn_ftrace *rec, int enable)
+{
+ unsigned long ftrace_addr = (unsigned long)FTRACE_ADDR;
+ int ret;
+
+ ret = ftrace_update_record(rec, enable);
+
+ switch (ret) {
+ case FTRACE_UPDATE_IGNORE:
+ return 0;
+ case FTRACE_UPDATE_MAKE_CALL:
+ return ftrace_make_call(rec, ftrace_addr);
+ case FTRACE_UPDATE_MAKE_NOP:
+ return ftrace_make_nop(NULL, rec, ftrace_addr);
+ }
+
+ return 0;
+}
+
+void ftrace_replace_code(int enable)
{
- /* caller expects data to be zero */
- unsigned long *p = data;
+ struct ftrace_rec_iter *iter;
+ struct dyn_ftrace *rec;
+ int ret;
- *p = 0;
+ for (iter = ftrace_rec_iter_start(); iter;
+ iter = ftrace_rec_iter_next(iter)) {
+ rec = ftrace_rec_iter_record(iter);
+ ret = __ftrace_replace_code(rec, enable);
+ if (ret) {
+ ftrace_bug(ret, rec->ip);
+ return;
+ }
+ }
+}
+
+void arch_ftrace_update_code(int command)
+{
+ if (command & FTRACE_UPDATE_CALLS)
+ ftrace_replace_code(1);
+ else if (command & FTRACE_DISABLE_CALLS)
+ ftrace_replace_code(0);
+
+ if (command & FTRACE_UPDATE_TRACE_FUNC)
+ ftrace_update_ftrace_func(ftrace_trace_function);
+
+ if (command & FTRACE_START_FUNC_RET)
+ ftrace_enable_ftrace_graph_caller();
+ else if (command & FTRACE_STOP_FUNC_RET)
+ ftrace_disable_ftrace_graph_caller();
+}
+int __init ftrace_dyn_arch_init(void)
+{
return 0;
}
#endif /* CONFIG_DYNAMIC_FTRACE */
@@ -587,18 +569,17 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr)
return;
}
- if (ftrace_push_return_trace(old, self_addr, &trace.depth, 0) == -EBUSY) {
- *parent = old;
- return;
- }
-
trace.func = self_addr;
+ trace.depth = current->curr_ret_stack + 1;
/* Only trace if the calling function expects to */
if (!ftrace_graph_entry(&trace)) {
- current->curr_ret_stack--;
*parent = old;
+ return;
}
+
+ if (ftrace_push_return_trace(old, self_addr, &trace.depth, 0) == -EBUSY)
+ *parent = old;
}
#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S
index 0654dba2c1f..dc0488b6f6e 100644
--- a/arch/powerpc/kernel/head_32.S
+++ b/arch/powerpc/kernel/head_32.S
@@ -395,7 +395,7 @@ DataAccess:
bl hash_page
1: lwz r5,_DSISR(r11) /* get DSISR value */
mfspr r4,SPRN_DAR
- EXC_XFER_EE_LITE(0x300, handle_page_fault)
+ EXC_XFER_LITE(0x300, handle_page_fault)
/* Instruction access exception. */
@@ -410,7 +410,7 @@ InstructionAccess:
bl hash_page
1: mr r4,r12
mr r5,r9
- EXC_XFER_EE_LITE(0x400, handle_page_fault)
+ EXC_XFER_LITE(0x400, handle_page_fault)
/* External interrupt */
EXCEPTION(0x500, HardwareInterrupt, do_IRQ, EXC_XFER_LITE)
diff --git a/arch/powerpc/kernel/head_40x.S b/arch/powerpc/kernel/head_40x.S
index 872a6af83ba..7d7d8635227 100644
--- a/arch/powerpc/kernel/head_40x.S
+++ b/arch/powerpc/kernel/head_40x.S
@@ -394,7 +394,7 @@ label:
NORMAL_EXCEPTION_PROLOG
mr r4,r12 /* Pass SRR0 as arg2 */
li r5,0 /* Pass zero as arg3 */
- EXC_XFER_EE_LITE(0x400, handle_page_fault)
+ EXC_XFER_LITE(0x400, handle_page_fault)
/* 0x0500 - External Interrupt Exception */
EXCEPTION(0x0500, HardwareInterrupt, do_IRQ, EXC_XFER_LITE)
@@ -430,30 +430,18 @@ label:
EXCEPTION(0x0F00, Trap_0F, unknown_exception, EXC_XFER_EE)
/* 0x1000 - Programmable Interval Timer (PIT) Exception */
- START_EXCEPTION(0x1000, Decrementer)
- NORMAL_EXCEPTION_PROLOG
- lis r0,TSR_PIS@h
- mtspr SPRN_TSR,r0 /* Clear the PIT exception */
- addi r3,r1,STACK_FRAME_OVERHEAD
- EXC_XFER_LITE(0x1000, timer_interrupt)
-
-#if 0
-/* NOTE:
- * FIT and WDT handlers are not implemented yet.
- */
+ . = 0x1000
+ b Decrementer
/* 0x1010 - Fixed Interval Timer (FIT) Exception
*/
- STND_EXCEPTION(0x1010, FITException, unknown_exception)
+ . = 0x1010
+ b FITException
/* 0x1020 - Watchdog Timer (WDT) Exception
*/
-#ifdef CONFIG_BOOKE_WDT
- CRITICAL_EXCEPTION(0x1020, WDTException, WatchdogException)
-#else
- CRITICAL_EXCEPTION(0x1020, WDTException, unknown_exception)
-#endif
-#endif
+ . = 0x1020
+ b WDTException
/* 0x1100 - Data TLB Miss Exception
* As the name implies, translation is not in the MMU, so search the
@@ -738,6 +726,29 @@ label:
(MSR_KERNEL & ~(MSR_ME|MSR_DE|MSR_CE)), \
NOCOPY, crit_transfer_to_handler, ret_from_crit_exc)
+ /* Programmable Interval Timer (PIT) Exception. (from 0x1000) */
+Decrementer:
+ NORMAL_EXCEPTION_PROLOG
+ lis r0,TSR_PIS@h
+ mtspr SPRN_TSR,r0 /* Clear the PIT exception */
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ EXC_XFER_LITE(0x1000, timer_interrupt)
+
+ /* Fixed Interval Timer (FIT) Exception. (from 0x1010) */
+FITException:
+ NORMAL_EXCEPTION_PROLOG
+ addi r3,r1,STACK_FRAME_OVERHEAD;
+ EXC_XFER_EE(0x1010, unknown_exception)
+
+ /* Watchdog Timer (WDT) Exception. (from 0x1020) */
+WDTException:
+ CRITICAL_EXCEPTION_PROLOG;
+ addi r3,r1,STACK_FRAME_OVERHEAD;
+ EXC_XFER_TEMPLATE(WatchdogException, 0x1020+2,
+ (MSR_KERNEL & ~(MSR_ME|MSR_DE|MSR_CE)),
+ NOCOPY, crit_transfer_to_handler,
+ ret_from_crit_exc)
+
/*
* The other Data TLB exceptions bail out to this point
* if they can't resolve the lightweight TLB fault.
@@ -747,7 +758,7 @@ DataAccess:
mfspr r5,SPRN_ESR /* Grab the ESR, save it, pass arg3 */
stw r5,_ESR(r11)
mfspr r4,SPRN_DEAR /* Grab the DEAR, save it, pass arg2 */
- EXC_XFER_EE_LITE(0x300, handle_page_fault)
+ EXC_XFER_LITE(0x300, handle_page_fault)
/* Other PowerPC processors, namely those derived from the 6xx-series
* have vectors from 0x2100 through 0x2F00 defined, but marked as reserved.
@@ -811,14 +822,6 @@ finish_tlb_load:
rfi /* Should sync shadow TLBs */
b . /* prevent prefetch past rfi */
-/* extern void giveup_fpu(struct task_struct *prev)
- *
- * The PowerPC 4xx family of processors do not have an FPU, so this just
- * returns.
- */
-_ENTRY(giveup_fpu)
- blr
-
/* This is where the main kernel code starts.
*/
start_here:
@@ -927,25 +930,6 @@ initial_mmu:
tlbwe r4,r0,TLB_DATA /* Load the data portion of the entry */
tlbwe r3,r0,TLB_TAG /* Load the tag portion of the entry */
-#if defined(CONFIG_SERIAL_TEXT_DEBUG) && defined(SERIAL_DEBUG_IO_BASE)
-
- /* Load a TLB entry for the UART, so that ppc4xx_progress() can use
- * the UARTs nice and early. We use a 4k real==virtual mapping. */
-
- lis r3,SERIAL_DEBUG_IO_BASE@h
- ori r3,r3,SERIAL_DEBUG_IO_BASE@l
- mr r4,r3
- clrrwi r4,r4,12
- ori r4,r4,(TLB_WR|TLB_I|TLB_M|TLB_G)
-
- clrrwi r3,r3,12
- ori r3,r3,(TLB_VALID | TLB_PAGESZ(PAGESZ_4K))
-
- li r0,0 /* TLB slot 0 */
- tlbwe r4,r0,TLB_DATA
- tlbwe r3,r0,TLB_TAG
-#endif /* CONFIG_SERIAL_DEBUG_TEXT && SERIAL_DEBUG_IO_BASE */
-
isync
/* Establish the exception vector base
diff --git a/arch/powerpc/kernel/head_44x.S b/arch/powerpc/kernel/head_44x.S
index 7dd2981bcc5..c334f53453f 100644
--- a/arch/powerpc/kernel/head_44x.S
+++ b/arch/powerpc/kernel/head_44x.S
@@ -248,10 +248,11 @@ _ENTRY(_start);
interrupt_base:
/* Critical Input Interrupt */
- CRITICAL_EXCEPTION(0x0100, CriticalInput, unknown_exception)
+ CRITICAL_EXCEPTION(0x0100, CRITICAL, CriticalInput, unknown_exception)
/* Machine Check Interrupt */
- CRITICAL_EXCEPTION(0x0200, MachineCheck, machine_check_exception)
+ CRITICAL_EXCEPTION(0x0200, MACHINE_CHECK, MachineCheck, \
+ machine_check_exception)
MCHECK_EXCEPTION(0x0210, MachineCheckA, machine_check_exception)
/* Data Storage Interrupt */
@@ -261,7 +262,8 @@ interrupt_base:
INSTRUCTION_STORAGE_EXCEPTION
/* External Input Interrupt */
- EXCEPTION(0x0500, ExternalInput, do_IRQ, EXC_XFER_LITE)
+ EXCEPTION(0x0500, BOOKE_INTERRUPT_EXTERNAL, ExternalInput, \
+ do_IRQ, EXC_XFER_LITE)
/* Alignment Interrupt */
ALIGNMENT_EXCEPTION
@@ -273,29 +275,32 @@ interrupt_base:
#ifdef CONFIG_PPC_FPU
FP_UNAVAILABLE_EXCEPTION
#else
- EXCEPTION(0x2010, FloatingPointUnavailable, unknown_exception, EXC_XFER_EE)
+ EXCEPTION(0x2010, BOOKE_INTERRUPT_FP_UNAVAIL, \
+ FloatingPointUnavailable, unknown_exception, EXC_XFER_EE)
#endif
/* System Call Interrupt */
START_EXCEPTION(SystemCall)
- NORMAL_EXCEPTION_PROLOG
+ NORMAL_EXCEPTION_PROLOG(BOOKE_INTERRUPT_SYSCALL)
EXC_XFER_EE_LITE(0x0c00, DoSyscall)
/* Auxiliary Processor Unavailable Interrupt */
- EXCEPTION(0x2020, AuxillaryProcessorUnavailable, unknown_exception, EXC_XFER_EE)
+ EXCEPTION(0x2020, BOOKE_INTERRUPT_AP_UNAVAIL, \
+ AuxillaryProcessorUnavailable, unknown_exception, EXC_XFER_EE)
/* Decrementer Interrupt */
DECREMENTER_EXCEPTION
/* Fixed Internal Timer Interrupt */
/* TODO: Add FIT support */
- EXCEPTION(0x1010, FixedIntervalTimer, unknown_exception, EXC_XFER_EE)
+ EXCEPTION(0x1010, BOOKE_INTERRUPT_FIT, FixedIntervalTimer, \
+ unknown_exception, EXC_XFER_EE)
/* Watchdog Timer Interrupt */
/* TODO: Add watchdog support */
#ifdef CONFIG_BOOKE_WDT
- CRITICAL_EXCEPTION(0x1020, WatchdogTimer, WatchdogException)
+ CRITICAL_EXCEPTION(0x1020, WATCHDOG, WatchdogTimer, WatchdogException)
#else
- CRITICAL_EXCEPTION(0x1020, WatchdogTimer, unknown_exception)
+ CRITICAL_EXCEPTION(0x1020, WATCHDOG, WatchdogTimer, unknown_exception)
#endif
/* Data TLB Error Interrupt */
@@ -764,6 +769,8 @@ finish_tlb_load_47x:
*/
DEBUG_CRIT_EXCEPTION
+interrupt_end:
+
/*
* Global functions
*/
@@ -777,24 +784,6 @@ _GLOBAL(__fixup_440A_mcheck)
sync
blr
-/*
- * extern void giveup_altivec(struct task_struct *prev)
- *
- * The 44x core does not have an AltiVec unit.
- */
-_GLOBAL(giveup_altivec)
- blr
-
-/*
- * extern void giveup_fpu(struct task_struct *prev)
- *
- * The 44x core does not have an FPU.
- */
-#ifndef CONFIG_PPC_FPU
-_GLOBAL(giveup_fpu)
- blr
-#endif
-
_GLOBAL(set_context)
#ifdef CONFIG_BDI_SWITCH
diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S
index 06c7251c1bf..a95145d7f61 100644
--- a/arch/powerpc/kernel/head_64.S
+++ b/arch/powerpc/kernel/head_64.S
@@ -23,6 +23,7 @@
*/
#include <linux/threads.h>
+#include <linux/init.h>
#include <asm/reg.h>
#include <asm/page.h>
#include <asm/mmu.h>
@@ -32,13 +33,13 @@
#include <asm/cputable.h>
#include <asm/setup.h>
#include <asm/hvcall.h>
-#include <asm/iseries/lpar_map.h>
#include <asm/thread_info.h>
#include <asm/firmware.h>
#include <asm/page_64.h>
#include <asm/irqflags.h>
#include <asm/kvm_book3s_asm.h>
#include <asm/ptrace.h>
+#include <asm/hw_irq.h>
/* The physical memory is laid out such that the secondary processor
* spin code sits at 0x0000...0x00ff. On server, the vectors follow
@@ -57,10 +58,6 @@
* entry in r9 for debugging purposes
* 2. Secondary processors enter at 0x60 with PIR in gpr3
*
- * For iSeries:
- * 1. The MMU is on (as it always is for iSeries)
- * 2. The kernel is entered at system_reset_iSeries
- *
* For Book3E processors:
* 1. The MMU is on running in AS0 in a state defined in ePAPR
* 2. The kernel is entered at __start
@@ -72,17 +69,18 @@ _stext:
_GLOBAL(__start)
/* NOP this out unconditionally */
BEGIN_FTR_SECTION
- b .__start_initialization_multiplatform
+ FIXUP_ENDIAN
+ b __start_initialization_multiplatform
END_FTR_SECTION(0, 1)
/* Catch branch to 0 in real mode */
trap
- /* Secondary processors spin on this value until it becomes nonzero.
- * When it does it contains the real address of the descriptor
- * of the function that the cpu should jump to to continue
- * initialization.
+ /* Secondary processors spin on this value until it becomes non-zero.
+ * When non-zero, it contains the real address of the function the cpu
+ * should jump to.
*/
+ .balign 8
.globl __secondary_hold_spinloop
__secondary_hold_spinloop:
.llong 0x0
@@ -93,15 +91,6 @@ __secondary_hold_spinloop:
__secondary_hold_acknowledge:
.llong 0x0
-#ifdef CONFIG_PPC_ISERIES
- /*
- * At offset 0x20, there is a pointer to iSeries LPAR data.
- * This is required by the hypervisor
- */
- . = 0x20
- .llong hvReleaseData-KERNELBASE
-#endif /* CONFIG_PPC_ISERIES */
-
#ifdef CONFIG_RELOCATABLE
/* This flag is set to 1 by a loader if the kernel should run
* at the loaded address instead of the linked address. This
@@ -128,6 +117,7 @@ __run_at_load:
*/
.globl __secondary_hold
__secondary_hold:
+ FIXUP_ENDIAN
#ifndef CONFIG_PPC_BOOK3E
mfmsr r24
ori r24,r24,MSR_RI
@@ -135,6 +125,8 @@ __secondary_hold:
#endif
/* Grab our physical cpu number */
mr r24,r3
+ /* stash r4 for book3e */
+ mr r25,r4
/* Tell the master cpu we're here */
/* Relocation is off & we are located at an address less */
@@ -142,16 +134,30 @@ __secondary_hold:
std r24,__secondary_hold_acknowledge-_stext(0)
sync
+ li r26,0
+#ifdef CONFIG_PPC_BOOK3E
+ tovirt(r26,r26)
+#endif
/* All secondary cpus wait here until told to start. */
-100: ld r4,__secondary_hold_spinloop-_stext(0)
- cmpdi 0,r4,0
+100: ld r12,__secondary_hold_spinloop-_stext(r26)
+ cmpdi 0,r12,0
beq 100b
#if defined(CONFIG_SMP) || defined(CONFIG_KEXEC)
- ld r4,0(r4) /* deref function descriptor */
- mtctr r4
+#ifdef CONFIG_PPC_BOOK3E
+ tovirt(r12,r12)
+#endif
+ mtctr r12
mr r3,r24
+ /*
+ * it may be the case that other platforms have r4 right to
+ * begin with, this gives us some safety in case it is not
+ */
+#ifdef CONFIG_PPC_BOOK3E
+ mr r4,r25
+#else
li r4,0
+#endif
/* Make sure that patched code is visible */
isync
bctr
@@ -178,15 +184,16 @@ _GLOBAL(generic_secondary_thread_init)
mr r24,r3
/* turn on 64-bit mode */
- bl .enable_64b_mode
+ bl enable_64b_mode
/* get a valid TOC pointer, wherever we're mapped at */
- bl .relative_toc
+ bl relative_toc
+ tovirt(r2,r2)
#ifdef CONFIG_PPC_BOOK3E
/* Book3E initialization */
mr r3,r24
- bl .book3e_secondary_thread_init
+ bl book3e_secondary_thread_init
#endif
b generic_secondary_common_init
@@ -200,20 +207,22 @@ _GLOBAL(generic_secondary_thread_init)
* as SCOM before entry).
*/
_GLOBAL(generic_secondary_smp_init)
+ FIXUP_ENDIAN
mr r24,r3
mr r25,r4
/* turn on 64-bit mode */
- bl .enable_64b_mode
+ bl enable_64b_mode
/* get a valid TOC pointer, wherever we're mapped at */
- bl .relative_toc
+ bl relative_toc
+ tovirt(r2,r2)
#ifdef CONFIG_PPC_BOOK3E
/* Book3E initialization */
mr r3,r24
mr r4,r25
- bl .book3e_secondary_core_init
+ bl book3e_secondary_core_init
#endif
generic_secondary_common_init:
@@ -225,7 +234,7 @@ generic_secondary_common_init:
ld r13,0(r13) /* Get base vaddr of paca array */
#ifndef CONFIG_SMP
addi r13,r13,PACA_SIZE /* know r13 if used accidentally */
- b .kexec_wait /* wait for next kernel if !SMP */
+ b kexec_wait /* wait for next kernel if !SMP */
#else
LOAD_REG_ADDR(r7, nr_cpu_ids) /* Load nr_cpu_ids address */
lwz r7,0(r7) /* also the max paca allocated */
@@ -239,7 +248,7 @@ generic_secondary_common_init:
blt 1b
mr r3,r24 /* not found, copy phys to r3 */
- b .kexec_wait /* next kernel might do better */
+ b kexec_wait /* next kernel might do better */
2: SET_PACA(r13)
#ifdef CONFIG_PPC_BOOK3E
@@ -253,11 +262,13 @@ generic_secondary_common_init:
/* See if we need to call a cpu state restore handler */
LOAD_REG_ADDR(r23, cur_cpu_spec)
ld r23,0(r23)
- ld r23,CPU_SPEC_RESTORE(r23)
- cmpdi 0,r23,0
+ ld r12,CPU_SPEC_RESTORE(r23)
+ cmpdi 0,r12,0
beq 3f
- ld r23,0(r23)
- mtctr r23
+#if !defined(_CALL_ELF) || _CALL_ELF != 2
+ ld r12,0(r12)
+#endif
+ mtctr r12
bctrl
3: LOAD_REG_ADDR(r3, spinning_secondaries) /* Decrement spinning_secondaries */
@@ -288,7 +299,7 @@ generic_secondary_common_init:
* Assumes we're mapped EA == RA if the MMU is on.
*/
#ifdef CONFIG_PPC_BOOK3S
-_STATIC(__mmu_off)
+__mmu_off:
mfmsr r3
andi. r0,r3,MSR_IR|MSR_DR
beqlr
@@ -313,12 +324,12 @@ _STATIC(__mmu_off)
* DT block, r4 is a physical pointer to the kernel itself
*
*/
-_GLOBAL(__start_initialization_multiplatform)
+__start_initialization_multiplatform:
/* Make sure we are running in 64 bits mode */
- bl .enable_64b_mode
+ bl enable_64b_mode
/* Get TOC pointer (current runtime address) */
- bl .relative_toc
+ bl relative_toc
/* find out where we are now */
bcl 20,31,$+4
@@ -331,7 +342,7 @@ _GLOBAL(__start_initialization_multiplatform)
*/
cmpldi cr0,r5,0
beq 1f
- b .__boot_from_prom /* yes -> prom */
+ b __boot_from_prom /* yes -> prom */
1:
/* Save parameters */
mr r31,r3
@@ -343,8 +354,8 @@ _GLOBAL(__start_initialization_multiplatform)
#endif
#ifdef CONFIG_PPC_BOOK3E
- bl .start_initialization_book3e
- b .__after_prom_start
+ bl start_initialization_book3e
+ b __after_prom_start
#else
/* Setup some critical 970 SPRs before switching MMU off */
mfspr r0,SPRN_PVR
@@ -357,15 +368,15 @@ _GLOBAL(__start_initialization_multiplatform)
beq 1f
cmpwi r0,0x45 /* 970GX */
bne 2f
-1: bl .__cpu_preinit_ppc970
+1: bl __cpu_preinit_ppc970
2:
/* Switch off MMU if not already off */
- bl .__mmu_off
- b .__after_prom_start
+ bl __mmu_off
+ b __after_prom_start
#endif /* CONFIG_PPC_BOOK3E */
-_INIT_STATIC(__boot_from_prom)
+__boot_from_prom:
#ifdef CONFIG_PPC_OF_BOOT_TRAMPOLINE
/* Save parameters */
mr r31,r3
@@ -384,7 +395,7 @@ _INIT_STATIC(__boot_from_prom)
#ifdef CONFIG_RELOCATABLE
/* Relocate code for where we are now */
mr r3,r26
- bl .relocate
+ bl relocate
#endif
/* Restore parameters */
@@ -396,14 +407,14 @@ _INIT_STATIC(__boot_from_prom)
/* Do all of the interaction with OF client interface */
mr r8,r26
- bl .prom_init
+ bl prom_init
#endif /* #CONFIG_PPC_OF_BOOT_TRAMPOLINE */
/* We never return. We also hit that trap if trying to boot
* from OF while CONFIG_PPC_OF_BOOT_TRAMPOLINE isn't selected */
trap
-_STATIC(__after_prom_start)
+__after_prom_start:
#ifdef CONFIG_RELOCATABLE
/* process relocations for the final address of the kernel */
lis r25,PAGE_OFFSET@highest /* compute virtual base of kernel */
@@ -413,7 +424,7 @@ _STATIC(__after_prom_start)
bne 1f
add r25,r25,r26
1: mr r3,r25
- bl .relocate
+ bl relocate
#endif
/*
@@ -435,7 +446,7 @@ _STATIC(__after_prom_start)
tovirt(r6,r6) /* on booke, we already run at PAGE_OFFSET */
#endif
-#ifdef CONFIG_CRASH_DUMP
+#ifdef CONFIG_RELOCATABLE
/*
* Check if the kernel has to be running as relocatable kernel based on the
* variable __run_at_load, if it is set the kernel is treated as relocatable
@@ -445,29 +456,31 @@ _STATIC(__after_prom_start)
cmplwi cr0,r7,1
bne 3f
- li r5,__end_interrupts - _stext /* just copy interrupts */
+ /* just copy interrupts */
+ LOAD_REG_IMMEDIATE(r5, __end_interrupts - _stext)
b 5f
3:
#endif
lis r5,(copy_to_here - _stext)@ha
addi r5,r5,(copy_to_here - _stext)@l /* # bytes of memory to copy */
- bl .copy_and_flush /* copy the first n bytes */
+ bl copy_and_flush /* copy the first n bytes */
/* this includes the code being */
/* executed here. */
addis r8,r3,(4f - _stext)@ha /* Jump to the copy of this code */
- addi r8,r8,(4f - _stext)@l /* that we just made */
- mtctr r8
+ addi r12,r8,(4f - _stext)@l /* that we just made */
+ mtctr r12
bctr
+.balign 8
p_end: .llong _end - _stext
4: /* Now copy the rest of the kernel up to _end */
addis r5,r26,(p_end - _stext)@ha
ld r5,(p_end - _stext)@l(r5) /* get _end */
-5: bl .copy_and_flush /* copy the rest */
+5: bl copy_and_flush /* copy the rest */
-9: b .start_here_multiplatform
+9: b start_here_multiplatform
/*
* Copy routine used to copy the kernel to start at physical address 0
@@ -502,6 +515,7 @@ _GLOBAL(copy_and_flush)
sync
addi r5,r5,8
addi r6,r6,8
+ isync
blr
.align 8
@@ -530,7 +544,7 @@ __secondary_start_pmac_0:
_GLOBAL(pmac_secondary_start)
/* turn on 64-bit mode */
- bl .enable_64b_mode
+ bl enable_64b_mode
li r0,0
mfspr r3,SPRN_HID4
@@ -542,10 +556,11 @@ _GLOBAL(pmac_secondary_start)
slbia
/* get TOC pointer (real address) */
- bl .relative_toc
+ bl relative_toc
+ tovirt(r2,r2)
/* Copy some CPU settings from CPU 0 */
- bl .__restore_cpu_ppc970
+ bl __restore_cpu_ppc970
/* pSeries do that early though I don't think we really need it */
mfmsr r3
@@ -564,7 +579,8 @@ _GLOBAL(pmac_secondary_start)
*/
li r0,0
stb r0,PACASOFTIRQEN(r13)
- stb r0,PACAHARDIRQEN(r13)
+ li r0,PACA_IRQ_HARD_DIS
+ stb r0,PACAIRQHAPPENED(r13)
/* Create a temp kernel stack for use before relocation is on. */
ld r1,PACAEMERGSP(r13)
@@ -582,7 +598,7 @@ _GLOBAL(pmac_secondary_start)
* 1. Processor number
* 2. Segment table pointer (virtual address)
* On entry the following are set:
- * r1 = stack pointer. vaddr for iSeries, raddr (temp stack) for pSeries
+ * r1 = stack pointer (real addr of temp stack)
* r24 = cpu# (in Linux terms)
* r13 = paca virtual address
* SPRG_PACA = paca virtual address
@@ -595,7 +611,7 @@ __secondary_start:
/* Set thread priority to MEDIUM */
HMT_MEDIUM
- /* Initialize the kernel stack. Just a repeat for iSeries. */
+ /* Initialize the kernel stack */
LOAD_REG_ADDR(r3, current_set)
sldi r28,r24,3 /* get current_set[cpu#] */
ldx r14,r3,r28
@@ -603,7 +619,7 @@ __secondary_start:
std r14,PACAKSAVE(r13)
/* Do early setup for that CPU (stab, slb, hash table pointer) */
- bl .early_setup_secondary
+ bl early_setup_secondary
/*
* setup the new stack pointer, but *don't* use this until
@@ -615,20 +631,16 @@ __secondary_start:
li r7,0
mtlr r7
+ /* Mark interrupts soft and hard disabled (they might be enabled
+ * in the PACA when doing hotplug)
+ */
+ stb r7,PACASOFTIRQEN(r13)
+ li r0,PACA_IRQ_HARD_DIS
+ stb r0,PACAIRQHAPPENED(r13)
+
/* enable MMU and jump to start_secondary */
- LOAD_REG_ADDR(r3, .start_secondary_prolog)
+ LOAD_REG_ADDR(r3, start_secondary_prolog)
LOAD_REG_IMMEDIATE(r4, MSR_KERNEL)
-#ifdef CONFIG_PPC_ISERIES
-BEGIN_FW_FTR_SECTION
- ori r4,r4,MSR_EE
- li r8,1
- stb r8,PACAHARDIRQEN(r13)
-END_FW_FTR_SECTION_IFSET(FW_FEATURE_ISERIES)
-#endif
-BEGIN_FW_FTR_SECTION
- stb r7,PACAHARDIRQEN(r13)
-END_FW_FTR_SECTION_IFCLR(FW_FEATURE_ISERIES)
- stb r7,PACASOFTIRQEN(r13)
mtspr SPRN_SRR0,r3
mtspr SPRN_SRR1,r4
@@ -640,11 +652,11 @@ END_FW_FTR_SECTION_IFCLR(FW_FEATURE_ISERIES)
* zero the stack back-chain pointer and get the TOC virtual address
* before going into C code.
*/
-_GLOBAL(start_secondary_prolog)
+start_secondary_prolog:
ld r2,PACATOC(r13)
li r3,0
std r3,0(r1) /* Zero the stack frame pointer */
- bl .start_secondary
+ bl start_secondary
b .
/*
* Reset stack pointer and call start_secondary
@@ -655,14 +667,14 @@ _GLOBAL(start_secondary_resume)
ld r1,PACAKSAVE(r13) /* Reload kernel stack pointer */
li r3,0
std r3,0(r1) /* Zero the stack frame pointer */
- bl .start_secondary
+ bl start_secondary
b .
#endif
/*
* This subroutine clobbers r11 and r12
*/
-_GLOBAL(enable_64b_mode)
+enable_64b_mode:
mfmsr r11 /* grab the current MSR */
#ifdef CONFIG_PPC_BOOK3E
oris r11,r11,0x8000 /* CM bit set, we'll set ICM later */
@@ -680,6 +692,13 @@ _GLOBAL(enable_64b_mode)
* This puts the TOC pointer into r2, offset by 0x8000 (as expected
* by the toolchain). It computes the correct value for wherever we
* are running at the moment, using position-independent code.
+ *
+ * Note: The compiler constructs pointers using offsets from the
+ * TOC in -mcmodel=medium mode. After we relocate to 0 but before
+ * the MMU is on we need our TOC to be a virtual address otherwise
+ * these pointers will be real addresses which may get stored and
+ * accessed later with the MMU on. We use tovirt() at the call
+ * sites to handle this.
*/
_GLOBAL(relative_toc)
mflr r0
@@ -690,14 +709,16 @@ _GLOBAL(relative_toc)
mtlr r0
blr
+.balign 8
p_toc: .llong __toc_start + 0x8000 - 0b
/*
* This is where the main kernel code starts.
*/
-_INIT_STATIC(start_here_multiplatform)
- /* set up the TOC (real address) */
- bl .relative_toc
+start_here_multiplatform:
+ /* set up the TOC */
+ bl relative_toc
+ tovirt(r2,r2)
/* Clear out the BSS. It may have been done in prom_init,
* already but that's irrelevant since prom_init will soon
@@ -719,6 +740,7 @@ _INIT_STATIC(start_here_multiplatform)
#ifdef CONFIG_PPC_EARLY_DEBUG_OPAL
/* Setup OPAL entry */
+ LOAD_REG_ADDR(r11, opal)
std r28,0(r11);
std r29,8(r11);
#endif
@@ -754,9 +776,9 @@ _INIT_STATIC(start_here_multiplatform)
/* Restore parameters passed from prom_init/kexec */
mr r3,r31
- bl .early_setup /* also sets r13 and SPRG_PACA */
+ bl early_setup /* also sets r13 and SPRG_PACA */
- LOAD_REG_ADDR(r3, .start_here_common)
+ LOAD_REG_ADDR(r3, start_here_common)
ld r4,PACAKMSR(r13)
mtspr SPRN_SRR0,r3
mtspr SPRN_SRR1,r4
@@ -764,30 +786,27 @@ _INIT_STATIC(start_here_multiplatform)
b . /* prevent speculative execution */
/* This is where all platforms converge execution */
-_INIT_GLOBAL(start_here_common)
+
+start_here_common:
/* relocation is on at this point */
std r1,PACAKSAVE(r13)
/* Load the TOC (virtual address) */
ld r2,PACATOC(r13)
- bl .setup_system
-
- /* Load up the kernel context */
-5:
- li r5,0
- stb r5,PACASOFTIRQEN(r13) /* Soft Disabled */
-#ifdef CONFIG_PPC_ISERIES
-BEGIN_FW_FTR_SECTION
- mfmsr r5
- ori r5,r5,MSR_EE /* Hard Enabled on iSeries*/
- mtmsrd r5
- li r5,1
-END_FW_FTR_SECTION_IFSET(FW_FEATURE_ISERIES)
-#endif
- stb r5,PACAHARDIRQEN(r13) /* Hard Disabled on others */
+ /* Do more system initializations in virtual mode */
+ bl setup_system
+
+ /* Mark interrupts soft and hard disabled (they might be enabled
+ * in the PACA when doing hotplug)
+ */
+ li r0,0
+ stb r0,PACASOFTIRQEN(r13)
+ li r0,PACA_IRQ_HARD_DIS
+ stb r0,PACAIRQHAPPENED(r13)
- bl .start_kernel
+ /* Generic kernel entry */
+ bl start_kernel
/* Not reached */
BUG_OPCODE
diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S
index b68cb173ba2..7ee876d2adb 100644
--- a/arch/powerpc/kernel/head_8xx.S
+++ b/arch/powerpc/kernel/head_8xx.S
@@ -220,7 +220,7 @@ DataAccess:
mfspr r4,SPRN_DAR
li r10,0x00f0
mtspr SPRN_DAR,r10 /* Tag DAR, to be used in DTLB Error */
- EXC_XFER_EE_LITE(0x300, handle_page_fault)
+ EXC_XFER_LITE(0x300, handle_page_fault)
/* Instruction access exception.
* This is "never generated" by the MPC8xx. We jump to it for other
@@ -231,7 +231,7 @@ InstructionAccess:
EXCEPTION_PROLOG
mr r4,r12
mr r5,r9
- EXC_XFER_EE_LITE(0x400, handle_page_fault)
+ EXC_XFER_LITE(0x400, handle_page_fault)
/* External interrupt */
EXCEPTION(0x500, HardwareInterrupt, do_IRQ, EXC_XFER_LITE)
@@ -691,10 +691,6 @@ modified_instr:
b 151b
#endif
- .globl giveup_fpu
-giveup_fpu:
- blr
-
/*
* This is where the main kernel code starts.
*/
@@ -862,6 +858,9 @@ initial_mmu:
addis r11, r11, 0x0080 /* Add 8M */
mtspr SPRN_MD_RPN, r11
+ addi r10, r10, 0x0100
+ mtspr SPRN_MD_CTR, r10
+
addis r8, r8, 0x0080 /* Add 8M */
mtspr SPRN_MD_EPN, r8
mtspr SPRN_MD_TWC, r9
diff --git a/arch/powerpc/kernel/head_booke.h b/arch/powerpc/kernel/head_booke.h
index fc921bf62e1..a620203f7de 100644
--- a/arch/powerpc/kernel/head_booke.h
+++ b/arch/powerpc/kernel/head_booke.h
@@ -2,6 +2,9 @@
#define __HEAD_BOOKE_H__
#include <asm/ptrace.h> /* for STACK_FRAME_REGS_MARKER */
+#include <asm/kvm_asm.h>
+#include <asm/kvm_booke_hv_asm.h>
+
/*
* Macros used for common Book-e exception handling
*/
@@ -28,14 +31,15 @@
*/
#define THREAD_NORMSAVE(offset) (THREAD_NORMSAVES + (offset * 4))
-#define NORMAL_EXCEPTION_PROLOG \
+#define NORMAL_EXCEPTION_PROLOG(intno) \
mtspr SPRN_SPRG_WSCRATCH0, r10; /* save one register */ \
mfspr r10, SPRN_SPRG_THREAD; \
stw r11, THREAD_NORMSAVE(0)(r10); \
stw r13, THREAD_NORMSAVE(2)(r10); \
mfcr r13; /* save CR in r13 for now */\
- mfspr r11,SPRN_SRR1; /* check whether user or kernel */\
- andi. r11,r11,MSR_PR; \
+ mfspr r11, SPRN_SRR1; \
+ DO_KVM BOOKE_INTERRUPT_##intno SPRN_SRR1; \
+ andi. r11, r11, MSR_PR; /* check whether user or kernel */\
mr r11, r1; \
beq 1f; \
/* if from user, start at top of this thread's kernel stack */ \
@@ -113,7 +117,7 @@
* registers as the normal prolog above. Instead we use a portion of the
* critical/machine check exception stack at low physical addresses.
*/
-#define EXC_LEVEL_EXCEPTION_PROLOG(exc_level, exc_level_srr0, exc_level_srr1) \
+#define EXC_LEVEL_EXCEPTION_PROLOG(exc_level, intno, exc_level_srr0, exc_level_srr1) \
mtspr SPRN_SPRG_WSCRATCH_##exc_level,r8; \
BOOKE_LOAD_EXC_LEVEL_STACK(exc_level);/* r8 points to the exc_level stack*/ \
stw r9,GPR9(r8); /* save various registers */\
@@ -121,8 +125,9 @@
stw r10,GPR10(r8); \
stw r11,GPR11(r8); \
stw r9,_CCR(r8); /* save CR on stack */\
- mfspr r10,exc_level_srr1; /* check whether user or kernel */\
- andi. r10,r10,MSR_PR; \
+ mfspr r11,exc_level_srr1; /* check whether user or kernel */\
+ DO_KVM BOOKE_INTERRUPT_##intno exc_level_srr1; \
+ andi. r11,r11,MSR_PR; \
mfspr r11,SPRN_SPRG_THREAD; /* if from user, start at top of */\
lwz r11,THREAD_INFO-THREAD(r11); /* this thread's kernel stack */\
addi r11,r11,EXC_LVL_FRAME_OVERHEAD; /* allocate stack frame */\
@@ -162,12 +167,30 @@
SAVE_4GPRS(3, r11); \
SAVE_2GPRS(7, r11)
-#define CRITICAL_EXCEPTION_PROLOG \
- EXC_LEVEL_EXCEPTION_PROLOG(CRIT, SPRN_CSRR0, SPRN_CSRR1)
+#define CRITICAL_EXCEPTION_PROLOG(intno) \
+ EXC_LEVEL_EXCEPTION_PROLOG(CRIT, intno, SPRN_CSRR0, SPRN_CSRR1)
#define DEBUG_EXCEPTION_PROLOG \
- EXC_LEVEL_EXCEPTION_PROLOG(DBG, SPRN_DSRR0, SPRN_DSRR1)
+ EXC_LEVEL_EXCEPTION_PROLOG(DBG, DEBUG, SPRN_DSRR0, SPRN_DSRR1)
#define MCHECK_EXCEPTION_PROLOG \
- EXC_LEVEL_EXCEPTION_PROLOG(MC, SPRN_MCSRR0, SPRN_MCSRR1)
+ EXC_LEVEL_EXCEPTION_PROLOG(MC, MACHINE_CHECK, \
+ SPRN_MCSRR0, SPRN_MCSRR1)
+
+/*
+ * Guest Doorbell -- this is a bit odd in that uses GSRR0/1 despite
+ * being delivered to the host. This exception can only happen
+ * inside a KVM guest -- so we just handle up to the DO_KVM rather
+ * than try to fit this into one of the existing prolog macros.
+ */
+#define GUEST_DOORBELL_EXCEPTION \
+ START_EXCEPTION(GuestDoorbell); \
+ mtspr SPRN_SPRG_WSCRATCH0, r10; /* save one register */ \
+ mfspr r10, SPRN_SPRG_THREAD; \
+ stw r11, THREAD_NORMSAVE(0)(r10); \
+ mfspr r11, SPRN_SRR1; \
+ stw r13, THREAD_NORMSAVE(2)(r10); \
+ mfcr r13; /* save CR in r13 for now */\
+ DO_KVM BOOKE_INTERRUPT_GUEST_DBELL SPRN_GSRR1; \
+ trap
/*
* Exception vectors.
@@ -176,21 +199,16 @@
.align 5; \
label:
-#define FINISH_EXCEPTION(func) \
- bl transfer_to_handler_full; \
- .long func; \
- .long ret_from_except_full
-
-#define EXCEPTION(n, label, hdlr, xfer) \
+#define EXCEPTION(n, intno, label, hdlr, xfer) \
START_EXCEPTION(label); \
- NORMAL_EXCEPTION_PROLOG; \
+ NORMAL_EXCEPTION_PROLOG(intno); \
addi r3,r1,STACK_FRAME_OVERHEAD; \
xfer(n, hdlr)
-#define CRITICAL_EXCEPTION(n, label, hdlr) \
- START_EXCEPTION(label); \
- CRITICAL_EXCEPTION_PROLOG; \
- addi r3,r1,STACK_FRAME_OVERHEAD; \
+#define CRITICAL_EXCEPTION(n, intno, label, hdlr) \
+ START_EXCEPTION(label); \
+ CRITICAL_EXCEPTION_PROLOG(intno); \
+ addi r3,r1,STACK_FRAME_OVERHEAD; \
EXC_XFER_TEMPLATE(hdlr, n+2, (MSR_KERNEL & ~(MSR_ME|MSR_DE|MSR_CE)), \
NOCOPY, crit_transfer_to_handler, \
ret_from_crit_exc)
@@ -263,13 +281,13 @@ label:
andis. r10,r10,(DBSR_IC|DBSR_BT)@h; \
beq+ 2f; \
\
- lis r10,KERNELBASE@h; /* check if exception in vectors */ \
- ori r10,r10,KERNELBASE@l; \
+ lis r10,interrupt_base@h; /* check if exception in vectors */ \
+ ori r10,r10,interrupt_base@l; \
cmplw r12,r10; \
blt+ 2f; /* addr below exception vectors */ \
\
- lis r10,DebugDebug@h; \
- ori r10,r10,DebugDebug@l; \
+ lis r10,interrupt_end@h; \
+ ori r10,r10,interrupt_end@l; \
cmplw r12,r10; \
bgt+ 2f; /* addr above exception vectors */ \
\
@@ -302,7 +320,7 @@ label:
#define DEBUG_CRIT_EXCEPTION \
START_EXCEPTION(DebugCrit); \
- CRITICAL_EXCEPTION_PROLOG; \
+ CRITICAL_EXCEPTION_PROLOG(DEBUG); \
\
/* \
* If there is a single step or branch-taken exception in an \
@@ -316,13 +334,13 @@ label:
andis. r10,r10,(DBSR_IC|DBSR_BT)@h; \
beq+ 2f; \
\
- lis r10,KERNELBASE@h; /* check if exception in vectors */ \
- ori r10,r10,KERNELBASE@l; \
+ lis r10,interrupt_base@h; /* check if exception in vectors */ \
+ ori r10,r10,interrupt_base@l; \
cmplw r12,r10; \
blt+ 2f; /* addr below exception vectors */ \
\
- lis r10,DebugCrit@h; \
- ori r10,r10,DebugCrit@l; \
+ lis r10,interrupt_end@h; \
+ ori r10,r10,interrupt_end@l; \
cmplw r12,r10; \
bgt+ 2f; /* addr above exception vectors */ \
\
@@ -355,24 +373,24 @@ label:
#define DATA_STORAGE_EXCEPTION \
START_EXCEPTION(DataStorage) \
- NORMAL_EXCEPTION_PROLOG; \
+ NORMAL_EXCEPTION_PROLOG(DATA_STORAGE); \
mfspr r5,SPRN_ESR; /* Grab the ESR and save it */ \
stw r5,_ESR(r11); \
mfspr r4,SPRN_DEAR; /* Grab the DEAR */ \
- EXC_XFER_EE_LITE(0x0300, handle_page_fault)
+ EXC_XFER_LITE(0x0300, handle_page_fault)
#define INSTRUCTION_STORAGE_EXCEPTION \
START_EXCEPTION(InstructionStorage) \
- NORMAL_EXCEPTION_PROLOG; \
+ NORMAL_EXCEPTION_PROLOG(INST_STORAGE); \
mfspr r5,SPRN_ESR; /* Grab the ESR and save it */ \
stw r5,_ESR(r11); \
mr r4,r12; /* Pass SRR0 as arg2 */ \
li r5,0; /* Pass zero as arg3 */ \
- EXC_XFER_EE_LITE(0x0400, handle_page_fault)
+ EXC_XFER_LITE(0x0400, handle_page_fault)
#define ALIGNMENT_EXCEPTION \
START_EXCEPTION(Alignment) \
- NORMAL_EXCEPTION_PROLOG; \
+ NORMAL_EXCEPTION_PROLOG(ALIGNMENT); \
mfspr r4,SPRN_DEAR; /* Grab the DEAR and save it */ \
stw r4,_DEAR(r11); \
addi r3,r1,STACK_FRAME_OVERHEAD; \
@@ -380,7 +398,7 @@ label:
#define PROGRAM_EXCEPTION \
START_EXCEPTION(Program) \
- NORMAL_EXCEPTION_PROLOG; \
+ NORMAL_EXCEPTION_PROLOG(PROGRAM); \
mfspr r4,SPRN_ESR; /* Grab the ESR and save it */ \
stw r4,_ESR(r11); \
addi r3,r1,STACK_FRAME_OVERHEAD; \
@@ -388,7 +406,7 @@ label:
#define DECREMENTER_EXCEPTION \
START_EXCEPTION(Decrementer) \
- NORMAL_EXCEPTION_PROLOG; \
+ NORMAL_EXCEPTION_PROLOG(DECREMENTER); \
lis r0,TSR_DIS@h; /* Setup the DEC interrupt mask */ \
mtspr SPRN_TSR,r0; /* Clear the DEC interrupt */ \
addi r3,r1,STACK_FRAME_OVERHEAD; \
@@ -396,7 +414,7 @@ label:
#define FP_UNAVAILABLE_EXCEPTION \
START_EXCEPTION(FloatingPointUnavailable) \
- NORMAL_EXCEPTION_PROLOG; \
+ NORMAL_EXCEPTION_PROLOG(FP_UNAVAIL); \
beq 1f; \
bl load_up_fpu; /* if from user, just load it up */ \
b fast_exception_return; \
diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S
index d5d78c4ceef..b497188a94a 100644
--- a/arch/powerpc/kernel/head_fsl_booke.S
+++ b/arch/powerpc/kernel/head_fsl_booke.S
@@ -65,29 +65,78 @@ _ENTRY(_start);
nop
/* Translate device tree address to physical, save in r30/r31 */
- mfmsr r16
- mfspr r17,SPRN_PID
- rlwinm r17,r17,16,0x3fff0000 /* turn PID into MAS6[SPID] */
- rlwimi r17,r16,28,0x00000001 /* turn MSR[DS] into MAS6[SAS] */
- mtspr SPRN_MAS6,r17
-
- tlbsx 0,r3 /* must succeed */
-
- mfspr r16,SPRN_MAS1
- mfspr r20,SPRN_MAS3
- rlwinm r17,r16,25,0x1f /* r17 = log2(page size) */
- li r18,1024
- slw r18,r18,r17 /* r18 = page size */
- addi r18,r18,-1
- and r19,r3,r18 /* r19 = page offset */
- andc r31,r20,r18 /* r31 = page base */
- or r31,r31,r19 /* r31 = devtree phys addr */
- mfspr r30,SPRN_MAS7
+ bl get_phys_addr
+ mr r30,r3
+ mr r31,r4
li r25,0 /* phys kernel start (low) */
li r24,0 /* CPU number */
li r23,0 /* phys kernel start (high) */
+#ifdef CONFIG_RELOCATABLE
+ LOAD_REG_ADDR_PIC(r3, _stext) /* Get our current runtime base */
+
+ /* Translate _stext address to physical, save in r23/r25 */
+ bl get_phys_addr
+ mr r23,r3
+ mr r25,r4
+
+ bl 0f
+0: mflr r8
+ addis r3,r8,(is_second_reloc - 0b)@ha
+ lwz r19,(is_second_reloc - 0b)@l(r3)
+
+ /* Check if this is the second relocation. */
+ cmpwi r19,1
+ bne 1f
+
+ /*
+ * For the second relocation, we already get the real memstart_addr
+ * from device tree. So we will map PAGE_OFFSET to memstart_addr,
+ * then the virtual address of start kernel should be:
+ * PAGE_OFFSET + (kernstart_addr - memstart_addr)
+ * Since the offset between kernstart_addr and memstart_addr should
+ * never be beyond 1G, so we can just use the lower 32bit of them
+ * for the calculation.
+ */
+ lis r3,PAGE_OFFSET@h
+
+ addis r4,r8,(kernstart_addr - 0b)@ha
+ addi r4,r4,(kernstart_addr - 0b)@l
+ lwz r5,4(r4)
+
+ addis r6,r8,(memstart_addr - 0b)@ha
+ addi r6,r6,(memstart_addr - 0b)@l
+ lwz r7,4(r6)
+
+ subf r5,r7,r5
+ add r3,r3,r5
+ b 2f
+
+1:
+ /*
+ * We have the runtime (virutal) address of our base.
+ * We calculate our shift of offset from a 64M page.
+ * We could map the 64M page we belong to at PAGE_OFFSET and
+ * get going from there.
+ */
+ lis r4,KERNELBASE@h
+ ori r4,r4,KERNELBASE@l
+ rlwinm r6,r25,0,0x3ffffff /* r6 = PHYS_START % 64M */
+ rlwinm r5,r4,0,0x3ffffff /* r5 = KERNELBASE % 64M */
+ subf r3,r5,r6 /* r3 = r6 - r5 */
+ add r3,r4,r3 /* Required Virtual Address */
+
+2: bl relocate
+
+ /*
+ * For the second relocation, we already set the right tlb entries
+ * for the kernel space, so skip the code in fsl_booke_entry_mapping.S
+ */
+ cmpwi r19,1
+ beq set_ivor
+#endif
+
/* We try to not make any assumptions about how the boot loader
* setup or used the TLBs. We invalidate all mappings from the
* boot loader and load a single entry in TLB1[0] to map the
@@ -113,6 +162,7 @@ _ENTRY(__early_start)
#include "fsl_booke_entry_mapping.S"
#undef ENTRY_MAPPING_BOOT_SETUP
+set_ivor:
/* Establish the interrupt vector offsets */
SET_IVOR(0, CriticalInput);
SET_IVOR(1, MachineCheck);
@@ -166,8 +216,7 @@ _ENTRY(__early_start)
/* Check to see if we're the second processor, and jump
* to the secondary_start code if so
*/
- lis r24, boot_cpuid@h
- ori r24, r24, boot_cpuid@l
+ LOAD_REG_ADDR_PIC(r24, boot_cpuid)
lwz r24, 0(r24)
cmpwi r24, -1
mfspr r24,SPRN_PIR
@@ -192,11 +241,23 @@ _ENTRY(__early_start)
li r0,0
stwu r0,THREAD_SIZE-STACK_FRAME_OVERHEAD(r1)
- rlwinm r22,r1,0,0,31-THREAD_SHIFT /* current thread_info */
+ CURRENT_THREAD_INFO(r22, r1)
stw r24, TI_CPU(r22)
bl early_init
+#ifdef CONFIG_RELOCATABLE
+ mr r3,r30
+ mr r4,r31
+#ifdef CONFIG_PHYS_64BIT
+ mr r5,r23
+ mr r6,r25
+#else
+ mr r5,r25
+#endif
+ bl relocate_init
+#endif
+
#ifdef CONFIG_DYNAMIC_MEMSTART
lis r3,kernstart_addr@ha
la r3,kernstart_addr@l(r3)
@@ -301,25 +362,26 @@ _ENTRY(__early_start)
interrupt_base:
/* Critical Input Interrupt */
- CRITICAL_EXCEPTION(0x0100, CriticalInput, unknown_exception)
+ CRITICAL_EXCEPTION(0x0100, CRITICAL, CriticalInput, unknown_exception)
/* Machine Check Interrupt */
#ifdef CONFIG_E200
/* no RFMCI, MCSRRs on E200 */
- CRITICAL_EXCEPTION(0x0200, MachineCheck, machine_check_exception)
+ CRITICAL_EXCEPTION(0x0200, MACHINE_CHECK, MachineCheck, \
+ machine_check_exception)
#else
MCHECK_EXCEPTION(0x0200, MachineCheck, machine_check_exception)
#endif
/* Data Storage Interrupt */
START_EXCEPTION(DataStorage)
- NORMAL_EXCEPTION_PROLOG
+ NORMAL_EXCEPTION_PROLOG(DATA_STORAGE)
mfspr r5,SPRN_ESR /* Grab the ESR, save it, pass arg3 */
stw r5,_ESR(r11)
mfspr r4,SPRN_DEAR /* Grab the DEAR, save it, pass arg2 */
andis. r10,r5,(ESR_ILK|ESR_DLK)@h
bne 1f
- EXC_XFER_EE_LITE(0x0300, handle_page_fault)
+ EXC_XFER_LITE(0x0300, handle_page_fault)
1:
addi r3,r1,STACK_FRAME_OVERHEAD
EXC_XFER_EE_LITE(0x0300, CacheLockingException)
@@ -328,7 +390,7 @@ interrupt_base:
INSTRUCTION_STORAGE_EXCEPTION
/* External Input Interrupt */
- EXCEPTION(0x0500, ExternalInput, do_IRQ, EXC_XFER_LITE)
+ EXCEPTION(0x0500, EXTERNAL, ExternalInput, do_IRQ, EXC_XFER_LITE)
/* Alignment Interrupt */
ALIGNMENT_EXCEPTION
@@ -342,32 +404,36 @@ interrupt_base:
#else
#ifdef CONFIG_E200
/* E200 treats 'normal' floating point instructions as FP Unavail exception */
- EXCEPTION(0x0800, FloatingPointUnavailable, program_check_exception, EXC_XFER_EE)
+ EXCEPTION(0x0800, FP_UNAVAIL, FloatingPointUnavailable, \
+ program_check_exception, EXC_XFER_EE)
#else
- EXCEPTION(0x0800, FloatingPointUnavailable, unknown_exception, EXC_XFER_EE)
+ EXCEPTION(0x0800, FP_UNAVAIL, FloatingPointUnavailable, \
+ unknown_exception, EXC_XFER_EE)
#endif
#endif
/* System Call Interrupt */
START_EXCEPTION(SystemCall)
- NORMAL_EXCEPTION_PROLOG
+ NORMAL_EXCEPTION_PROLOG(SYSCALL)
EXC_XFER_EE_LITE(0x0c00, DoSyscall)
/* Auxiliary Processor Unavailable Interrupt */
- EXCEPTION(0x2900, AuxillaryProcessorUnavailable, unknown_exception, EXC_XFER_EE)
+ EXCEPTION(0x2900, AP_UNAVAIL, AuxillaryProcessorUnavailable, \
+ unknown_exception, EXC_XFER_EE)
/* Decrementer Interrupt */
DECREMENTER_EXCEPTION
/* Fixed Internal Timer Interrupt */
/* TODO: Add FIT support */
- EXCEPTION(0x3100, FixedIntervalTimer, unknown_exception, EXC_XFER_EE)
+ EXCEPTION(0x3100, FIT, FixedIntervalTimer, \
+ unknown_exception, EXC_XFER_EE)
/* Watchdog Timer Interrupt */
#ifdef CONFIG_BOOKE_WDT
- CRITICAL_EXCEPTION(0x3200, WatchdogTimer, WatchdogException)
+ CRITICAL_EXCEPTION(0x3200, WATCHDOG, WatchdogTimer, WatchdogException)
#else
- CRITICAL_EXCEPTION(0x3200, WatchdogTimer, unknown_exception)
+ CRITICAL_EXCEPTION(0x3200, WATCHDOG, WatchdogTimer, unknown_exception)
#endif
/* Data TLB Error Interrupt */
@@ -375,10 +441,16 @@ interrupt_base:
mtspr SPRN_SPRG_WSCRATCH0, r10 /* Save some working registers */
mfspr r10, SPRN_SPRG_THREAD
stw r11, THREAD_NORMSAVE(0)(r10)
+#ifdef CONFIG_KVM_BOOKE_HV
+BEGIN_FTR_SECTION
+ mfspr r11, SPRN_SRR1
+END_FTR_SECTION_IFSET(CPU_FTR_EMB_HV)
+#endif
stw r12, THREAD_NORMSAVE(1)(r10)
stw r13, THREAD_NORMSAVE(2)(r10)
mfcr r13
stw r13, THREAD_NORMSAVE(3)(r10)
+ DO_KVM BOOKE_INTERRUPT_DTLB_MISS SPRN_SRR1
mfspr r10, SPRN_DEAR /* Get faulting address */
/* If we are faulting a kernel address, we have to use the
@@ -463,10 +535,16 @@ interrupt_base:
mtspr SPRN_SPRG_WSCRATCH0, r10 /* Save some working registers */
mfspr r10, SPRN_SPRG_THREAD
stw r11, THREAD_NORMSAVE(0)(r10)
+#ifdef CONFIG_KVM_BOOKE_HV
+BEGIN_FTR_SECTION
+ mfspr r11, SPRN_SRR1
+END_FTR_SECTION_IFSET(CPU_FTR_EMB_HV)
+#endif
stw r12, THREAD_NORMSAVE(1)(r10)
stw r13, THREAD_NORMSAVE(2)(r10)
mfcr r13
stw r13, THREAD_NORMSAVE(3)(r10)
+ DO_KVM BOOKE_INTERRUPT_ITLB_MISS SPRN_SRR1
mfspr r10, SPRN_SRR0 /* Get faulting address */
/* If we are faulting a kernel address, we have to use the
@@ -538,36 +616,58 @@ interrupt_base:
#ifdef CONFIG_SPE
/* SPE Unavailable */
START_EXCEPTION(SPEUnavailable)
- NORMAL_EXCEPTION_PROLOG
- bne load_up_spe
- addi r3,r1,STACK_FRAME_OVERHEAD
+ NORMAL_EXCEPTION_PROLOG(SPE_ALTIVEC_UNAVAIL)
+ beq 1f
+ bl load_up_spe
+ b fast_exception_return
+1: addi r3,r1,STACK_FRAME_OVERHEAD
EXC_XFER_EE_LITE(0x2010, KernelSPE)
#else
- EXCEPTION(0x2020, SPEUnavailable, unknown_exception, EXC_XFER_EE)
+ EXCEPTION(0x2020, SPE_ALTIVEC_UNAVAIL, SPEUnavailable, \
+ unknown_exception, EXC_XFER_EE)
#endif /* CONFIG_SPE */
/* SPE Floating Point Data */
#ifdef CONFIG_SPE
- EXCEPTION(0x2030, SPEFloatingPointData, SPEFloatingPointException, EXC_XFER_EE);
+ EXCEPTION(0x2030, SPE_FP_DATA_ALTIVEC_ASSIST, SPEFloatingPointData,
+ SPEFloatingPointException, EXC_XFER_EE)
/* SPE Floating Point Round */
- EXCEPTION(0x2050, SPEFloatingPointRound, SPEFloatingPointRoundException, EXC_XFER_EE)
+ EXCEPTION(0x2050, SPE_FP_ROUND, SPEFloatingPointRound, \
+ SPEFloatingPointRoundException, EXC_XFER_EE)
#else
- EXCEPTION(0x2040, SPEFloatingPointData, unknown_exception, EXC_XFER_EE)
- EXCEPTION(0x2050, SPEFloatingPointRound, unknown_exception, EXC_XFER_EE)
+ EXCEPTION(0x2040, SPE_FP_DATA_ALTIVEC_ASSIST, SPEFloatingPointData,
+ unknown_exception, EXC_XFER_EE)
+ EXCEPTION(0x2050, SPE_FP_ROUND, SPEFloatingPointRound, \
+ unknown_exception, EXC_XFER_EE)
#endif /* CONFIG_SPE */
/* Performance Monitor */
- EXCEPTION(0x2060, PerformanceMonitor, performance_monitor_exception, EXC_XFER_STD)
+ EXCEPTION(0x2060, PERFORMANCE_MONITOR, PerformanceMonitor, \
+ performance_monitor_exception, EXC_XFER_STD)
- EXCEPTION(0x2070, Doorbell, doorbell_exception, EXC_XFER_STD)
+ EXCEPTION(0x2070, DOORBELL, Doorbell, doorbell_exception, EXC_XFER_STD)
- CRITICAL_EXCEPTION(0x2080, CriticalDoorbell, unknown_exception)
+ CRITICAL_EXCEPTION(0x2080, DOORBELL_CRITICAL, \
+ CriticalDoorbell, unknown_exception)
/* Debug Interrupt */
DEBUG_DEBUG_EXCEPTION
DEBUG_CRIT_EXCEPTION
+ GUEST_DOORBELL_EXCEPTION
+
+ CRITICAL_EXCEPTION(0, GUEST_DBELL_CRIT, CriticalGuestDoorbell, \
+ unknown_exception)
+
+ /* Hypercall */
+ EXCEPTION(0, HV_SYSCALL, Hypercall, unknown_exception, EXC_XFER_EE)
+
+ /* Embedded Hypervisor Privilege */
+ EXCEPTION(0, HV_PRIV, Ehvpriv, unknown_exception, EXC_XFER_EE)
+
+interrupt_end:
+
/*
* Local functions
*/
@@ -743,7 +843,7 @@ tlb_write_entry:
/* Note that the SPE support is closely modeled after the AltiVec
* support. Changes to one are likely to be applicable to the
* other! */
-load_up_spe:
+_GLOBAL(load_up_spe)
/*
* Disable SPE for the task which had SPE previously,
* and save its SPE registers in its thread_struct.
@@ -791,20 +891,7 @@ load_up_spe:
subi r4,r5,THREAD
stw r4,last_task_used_spe@l(r3)
#endif /* !CONFIG_SMP */
- /* restore registers and return */
-2: REST_4GPRS(3, r11)
- lwz r10,_CCR(r11)
- REST_GPR(1, r11)
- mtcr r10
- lwz r10,_LINK(r11)
- mtlr r10
- REST_GPR(10, r11)
- mtspr SPRN_SRR1,r9
- mtspr SPRN_SRR0,r12
- REST_GPR(9, r11)
- REST_GPR(12, r11)
- lwz r11,GPR11(r11)
- rfi
+ blr
/*
* SPE unavailable trap from kernel - print a message, but let
@@ -830,6 +917,33 @@ KernelSPE:
#endif /* CONFIG_SPE */
/*
+ * Translate the effec addr in r3 to phys addr. The phys addr will be put
+ * into r3(higher 32bit) and r4(lower 32bit)
+ */
+get_phys_addr:
+ mfmsr r8
+ mfspr r9,SPRN_PID
+ rlwinm r9,r9,16,0x3fff0000 /* turn PID into MAS6[SPID] */
+ rlwimi r9,r8,28,0x00000001 /* turn MSR[DS] into MAS6[SAS] */
+ mtspr SPRN_MAS6,r9
+
+ tlbsx 0,r3 /* must succeed */
+
+ mfspr r8,SPRN_MAS1
+ mfspr r12,SPRN_MAS3
+ rlwinm r9,r8,25,0x1f /* r9 = log2(page size) */
+ li r10,1024
+ slw r10,r10,r9 /* r10 = page size */
+ addi r10,r10,-1
+ and r11,r3,r10 /* r11 = page offset */
+ andc r4,r12,r10 /* r4 = page base */
+ or r4,r4,r11 /* r4 = devtree phys addr */
+#ifdef CONFIG_PHYS_64BIT
+ mfspr r3,SPRN_MAS7
+#endif
+ blr
+
+/*
* Global functions
*/
@@ -874,12 +988,17 @@ _GLOBAL(__setup_e500mc_ivors)
sync
blr
-/*
- * extern void giveup_altivec(struct task_struct *prev)
- *
- * The e500 core does not have an AltiVec unit.
- */
-_GLOBAL(giveup_altivec)
+/* setup ehv ivors for */
+_GLOBAL(__setup_ehv_ivors)
+ li r3,GuestDoorbell@l
+ mtspr SPRN_IVOR38,r3
+ li r3,CriticalGuestDoorbell@l
+ mtspr SPRN_IVOR39,r3
+ li r3,Hypercall@l
+ mtspr SPRN_IVOR40,r3
+ li r3,Ehvpriv@l
+ mtspr SPRN_IVOR41,r3
+ sync
blr
#ifdef CONFIG_SPE
@@ -917,16 +1036,6 @@ _GLOBAL(giveup_spe)
#endif /* CONFIG_SPE */
/*
- * extern void giveup_fpu(struct task_struct *prev)
- *
- * Not all FSL Book-E cores have an FPU
- */
-#ifndef CONFIG_PPC_FPU
-_GLOBAL(giveup_fpu)
- blr
-#endif
-
-/*
* extern void abort(void)
*
* At present, this routine just applies a system reset.
@@ -1004,28 +1113,68 @@ _GLOBAL(flush_dcache_L1)
blr
+/* Flush L1 d-cache, invalidate and disable d-cache and i-cache */
+_GLOBAL(__flush_disable_L1)
+ mflr r10
+ bl flush_dcache_L1 /* Flush L1 d-cache */
+ mtlr r10
+
+ mfspr r4, SPRN_L1CSR0 /* Invalidate and disable d-cache */
+ li r5, 2
+ rlwimi r4, r5, 0, 3
+
+ msync
+ isync
+ mtspr SPRN_L1CSR0, r4
+ isync
+
+1: mfspr r4, SPRN_L1CSR0 /* Wait for the invalidate to finish */
+ andi. r4, r4, 2
+ bne 1b
+
+ mfspr r4, SPRN_L1CSR1 /* Invalidate and disable i-cache */
+ li r5, 2
+ rlwimi r4, r5, 0, 3
+
+ mtspr SPRN_L1CSR1, r4
+ isync
+
+ blr
+
#ifdef CONFIG_SMP
/* When we get here, r24 needs to hold the CPU # */
.globl __secondary_start
__secondary_start:
- lis r3,__secondary_hold_acknowledge@h
- ori r3,r3,__secondary_hold_acknowledge@l
- stw r24,0(r3)
-
- li r3,0
- mr r4,r24 /* Why? */
- bl call_setup_cpu
-
- lis r3,tlbcam_index@ha
- lwz r3,tlbcam_index@l(r3)
+ LOAD_REG_ADDR_PIC(r3, tlbcam_index)
+ lwz r3,0(r3)
mtctr r3
li r26,0 /* r26 safe? */
+ bl switch_to_as1
+ mr r27,r3 /* tlb entry */
/* Load each CAM entry */
1: mr r3,r26
bl loadcam_entry
addi r26,r26,1
bdnz 1b
+ mr r3,r27 /* tlb entry */
+ LOAD_REG_ADDR_PIC(r4, memstart_addr)
+ lwz r4,0(r4)
+ mr r5,r25 /* phys kernel start */
+ rlwinm r5,r5,0,~0x3ffffff /* aligned 64M */
+ subf r4,r5,r4 /* memstart_addr - phys kernel start */
+ li r5,0 /* no device tree */
+ li r6,0 /* not boot cpu */
+ bl restore_to_as0
+
+
+ lis r3,__secondary_hold_acknowledge@h
+ ori r3,r3,__secondary_hold_acknowledge@l
+ stw r24,0(r3)
+
+ li r3,0
+ mr r4,r24 /* Why? */
+ bl call_setup_cpu
/* get current_thread_info and current */
lis r1,secondary_ti@ha
@@ -1062,6 +1211,112 @@ __secondary_hold_acknowledge:
#endif
/*
+ * Create a tlb entry with the same effective and physical address as
+ * the tlb entry used by the current running code. But set the TS to 1.
+ * Then switch to the address space 1. It will return with the r3 set to
+ * the ESEL of the new created tlb.
+ */
+_GLOBAL(switch_to_as1)
+ mflr r5
+
+ /* Find a entry not used */
+ mfspr r3,SPRN_TLB1CFG
+ andi. r3,r3,0xfff
+ mfspr r4,SPRN_PID
+ rlwinm r4,r4,16,0x3fff0000 /* turn PID into MAS6[SPID] */
+ mtspr SPRN_MAS6,r4
+1: lis r4,0x1000 /* Set MAS0(TLBSEL) = 1 */
+ addi r3,r3,-1
+ rlwimi r4,r3,16,4,15 /* Setup MAS0 = TLBSEL | ESEL(r3) */
+ mtspr SPRN_MAS0,r4
+ tlbre
+ mfspr r4,SPRN_MAS1
+ andis. r4,r4,MAS1_VALID@h
+ bne 1b
+
+ /* Get the tlb entry used by the current running code */
+ bl 0f
+0: mflr r4
+ tlbsx 0,r4
+
+ mfspr r4,SPRN_MAS1
+ ori r4,r4,MAS1_TS /* Set the TS = 1 */
+ mtspr SPRN_MAS1,r4
+
+ mfspr r4,SPRN_MAS0
+ rlwinm r4,r4,0,~MAS0_ESEL_MASK
+ rlwimi r4,r3,16,4,15 /* Setup MAS0 = TLBSEL | ESEL(r3) */
+ mtspr SPRN_MAS0,r4
+ tlbwe
+ isync
+ sync
+
+ mfmsr r4
+ ori r4,r4,MSR_IS | MSR_DS
+ mtspr SPRN_SRR0,r5
+ mtspr SPRN_SRR1,r4
+ sync
+ rfi
+
+/*
+ * Restore to the address space 0 and also invalidate the tlb entry created
+ * by switch_to_as1.
+ * r3 - the tlb entry which should be invalidated
+ * r4 - __pa(PAGE_OFFSET in AS1) - __pa(PAGE_OFFSET in AS0)
+ * r5 - device tree virtual address. If r4 is 0, r5 is ignored.
+ * r6 - boot cpu
+*/
+_GLOBAL(restore_to_as0)
+ mflr r0
+
+ bl 0f
+0: mflr r9
+ addi r9,r9,1f - 0b
+
+ /*
+ * We may map the PAGE_OFFSET in AS0 to a different physical address,
+ * so we need calculate the right jump and device tree address based
+ * on the offset passed by r4.
+ */
+ add r9,r9,r4
+ add r5,r5,r4
+ add r0,r0,r4
+
+2: mfmsr r7
+ li r8,(MSR_IS | MSR_DS)
+ andc r7,r7,r8
+
+ mtspr SPRN_SRR0,r9
+ mtspr SPRN_SRR1,r7
+ sync
+ rfi
+
+ /* Invalidate the temporary tlb entry for AS1 */
+1: lis r9,0x1000 /* Set MAS0(TLBSEL) = 1 */
+ rlwimi r9,r3,16,4,15 /* Setup MAS0 = TLBSEL | ESEL(r3) */
+ mtspr SPRN_MAS0,r9
+ tlbre
+ mfspr r9,SPRN_MAS1
+ rlwinm r9,r9,0,2,31 /* Clear MAS1 Valid and IPPROT */
+ mtspr SPRN_MAS1,r9
+ tlbwe
+ isync
+
+ cmpwi r4,0
+ cmpwi cr1,r6,0
+ cror eq,4*cr1+eq,eq
+ bne 3f /* offset != 0 && is_boot_cpu */
+ mtlr r0
+ blr
+
+ /*
+ * The PAGE_OFFSET will map to a different physical address,
+ * jump to _start to do another relocation again.
+ */
+3: mr r3,r5
+ bl _start
+
+/*
* We put a few things here that have to be page-aligned. This stuff
* goes at the beginning of the data segment, which is page-aligned.
*/
diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c
index 2bc0584be81..0bb5918faaa 100644
--- a/arch/powerpc/kernel/hw_breakpoint.c
+++ b/arch/powerpc/kernel/hw_breakpoint.c
@@ -28,7 +28,6 @@
#include <linux/percpu.h>
#include <linux/kernel.h>
#include <linux/sched.h>
-#include <linux/init.h>
#include <linux/smp.h>
#include <asm/hw_breakpoint.h>
@@ -73,7 +72,7 @@ int arch_install_hw_breakpoint(struct perf_event *bp)
* If so, DABR will be populated in single_step_dabr_instruction().
*/
if (current->thread.last_hit_ubp != bp)
- set_dabr(info->address | info->type | DABR_TRANSLATION);
+ __set_breakpoint(info);
return 0;
}
@@ -97,7 +96,7 @@ void arch_uninstall_hw_breakpoint(struct perf_event *bp)
}
*slot = NULL;
- set_dabr(0);
+ hw_breakpoint_disable();
}
/*
@@ -111,7 +110,7 @@ void arch_unregister_hw_breakpoint(struct perf_event *bp)
* and the single_step_dabr_instruction(), then cleanup the breakpoint
* restoration variables to prevent dangling pointers.
*/
- if (bp->ctx->task)
+ if (bp->ctx && bp->ctx->task)
bp->ctx->task->thread.last_hit_ubp = NULL;
}
@@ -127,19 +126,13 @@ int arch_check_bp_in_kernelspace(struct perf_event *bp)
int arch_bp_generic_fields(int type, int *gen_bp_type)
{
- switch (type) {
- case DABR_DATA_READ:
- *gen_bp_type = HW_BREAKPOINT_R;
- break;
- case DABR_DATA_WRITE:
- *gen_bp_type = HW_BREAKPOINT_W;
- break;
- case (DABR_DATA_WRITE | DABR_DATA_READ):
- *gen_bp_type = (HW_BREAKPOINT_W | HW_BREAKPOINT_R);
- break;
- default:
+ *gen_bp_type = 0;
+ if (type & HW_BRK_TYPE_READ)
+ *gen_bp_type |= HW_BREAKPOINT_R;
+ if (type & HW_BRK_TYPE_WRITE)
+ *gen_bp_type |= HW_BREAKPOINT_W;
+ if (*gen_bp_type == 0)
return -EINVAL;
- }
return 0;
}
@@ -148,26 +141,26 @@ int arch_bp_generic_fields(int type, int *gen_bp_type)
*/
int arch_validate_hwbkpt_settings(struct perf_event *bp)
{
- int ret = -EINVAL;
+ int ret = -EINVAL, length_max;
struct arch_hw_breakpoint *info = counter_arch_bp(bp);
if (!bp)
return ret;
- switch (bp->attr.bp_type) {
- case HW_BREAKPOINT_R:
- info->type = DABR_DATA_READ;
- break;
- case HW_BREAKPOINT_W:
- info->type = DABR_DATA_WRITE;
- break;
- case HW_BREAKPOINT_R | HW_BREAKPOINT_W:
- info->type = (DABR_DATA_READ | DABR_DATA_WRITE);
- break;
- default:
+ info->type = HW_BRK_TYPE_TRANSLATE;
+ if (bp->attr.bp_type & HW_BREAKPOINT_R)
+ info->type |= HW_BRK_TYPE_READ;
+ if (bp->attr.bp_type & HW_BREAKPOINT_W)
+ info->type |= HW_BRK_TYPE_WRITE;
+ if (info->type == HW_BRK_TYPE_TRANSLATE)
+ /* must set alteast read or write */
return ret;
- }
-
+ if (!(bp->attr.exclude_user))
+ info->type |= HW_BRK_TYPE_USER;
+ if (!(bp->attr.exclude_kernel))
+ info->type |= HW_BRK_TYPE_KERNEL;
+ if (!(bp->attr.exclude_hv))
+ info->type |= HW_BRK_TYPE_HYP;
info->address = bp->attr.bp_addr;
info->len = bp->attr.bp_len;
@@ -177,8 +170,16 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp)
* HW_BREAKPOINT_ALIGN by rounding off to the lower address, the
* 'symbolsize' should satisfy the check below.
*/
+ length_max = 8; /* DABR */
+ if (cpu_has_feature(CPU_FTR_DAWR)) {
+ length_max = 512 ; /* 64 doublewords */
+ /* DAWR region can't cross 512 boundary */
+ if ((bp->attr.bp_addr >> 10) !=
+ ((bp->attr.bp_addr + bp->attr.bp_len - 1) >> 10))
+ return -EINVAL;
+ }
if (info->len >
- (HW_BREAKPOINT_LEN - (info->address & HW_BREAKPOINT_ALIGN)))
+ (length_max - (info->address & HW_BREAKPOINT_ALIGN)))
return -EINVAL;
return 0;
}
@@ -197,7 +198,7 @@ void thread_change_pc(struct task_struct *tsk, struct pt_regs *regs)
info = counter_arch_bp(tsk->thread.last_hit_ubp);
regs->msr &= ~MSR_SE;
- set_dabr(info->address | info->type | DABR_TRANSLATION);
+ __set_breakpoint(info);
tsk->thread.last_hit_ubp = NULL;
}
@@ -215,7 +216,7 @@ int __kprobes hw_breakpoint_handler(struct die_args *args)
unsigned long dar = regs->dar;
/* Disable breakpoints during exception handling */
- set_dabr(0);
+ hw_breakpoint_disable();
/*
* The counter may be concurrently released but that can only
@@ -248,12 +249,14 @@ int __kprobes hw_breakpoint_handler(struct die_args *args)
* we still need to single-step the instruction, but we don't
* generate an event.
*/
- info->extraneous_interrupt = !((bp->attr.bp_addr <= dar) &&
- (dar - bp->attr.bp_addr < bp->attr.bp_len));
+ info->type &= ~HW_BRK_TYPE_EXTRANEOUS_IRQ;
+ if (!((bp->attr.bp_addr <= dar) &&
+ (dar - bp->attr.bp_addr < bp->attr.bp_len)))
+ info->type |= HW_BRK_TYPE_EXTRANEOUS_IRQ;
/* Do not emulate user-space instructions, instead single-step them */
if (user_mode(regs)) {
- bp->ctx->task->thread.last_hit_ubp = bp;
+ current->thread.last_hit_ubp = bp;
regs->msr |= MSR_SE;
goto out;
}
@@ -278,10 +281,10 @@ int __kprobes hw_breakpoint_handler(struct die_args *args)
* As a policy, the callback is invoked in a 'trigger-after-execute'
* fashion
*/
- if (!info->extraneous_interrupt)
+ if (!(info->type & HW_BRK_TYPE_EXTRANEOUS_IRQ))
perf_bp_event(bp, regs);
- set_dabr(info->address | info->type | DABR_TRANSLATION);
+ __set_breakpoint(info);
out:
rcu_read_unlock();
return rc;
@@ -294,7 +297,7 @@ int __kprobes single_step_dabr_instruction(struct die_args *args)
{
struct pt_regs *regs = args->regs;
struct perf_event *bp = NULL;
- struct arch_hw_breakpoint *bp_info;
+ struct arch_hw_breakpoint *info;
bp = current->thread.last_hit_ubp;
/*
@@ -304,16 +307,16 @@ int __kprobes single_step_dabr_instruction(struct die_args *args)
if (!bp)
return NOTIFY_DONE;
- bp_info = counter_arch_bp(bp);
+ info = counter_arch_bp(bp);
/*
* We shall invoke the user-defined callback function in the single
* stepping handler to confirm to 'trigger-after-execute' semantics
*/
- if (!bp_info->extraneous_interrupt)
+ if (!(info->type & HW_BRK_TYPE_EXTRANEOUS_IRQ))
perf_bp_event(bp, regs);
- set_dabr(bp_info->address | bp_info->type | DABR_TRANSLATION);
+ __set_breakpoint(info);
current->thread.last_hit_ubp = NULL;
/*
diff --git a/arch/powerpc/kernel/ibmebus.c b/arch/powerpc/kernel/ibmebus.c
index d39ae606ff8..1114d13ac19 100644
--- a/arch/powerpc/kernel/ibmebus.c
+++ b/arch/powerpc/kernel/ibmebus.c
@@ -47,7 +47,6 @@
#include <linux/stat.h>
#include <linux/of_platform.h>
#include <asm/ibmebus.h>
-#include <asm/abs_addr.h>
static struct device ibmebus_bus_device = { /* fake "parent" device */
.init_name = "ibmebus",
@@ -65,7 +64,8 @@ static struct of_device_id __initdata ibmebus_matches[] = {
static void *ibmebus_alloc_coherent(struct device *dev,
size_t size,
dma_addr_t *dma_handle,
- gfp_t flag)
+ gfp_t flag,
+ struct dma_attrs *attrs)
{
void *mem;
@@ -77,7 +77,8 @@ static void *ibmebus_alloc_coherent(struct device *dev,
static void ibmebus_free_coherent(struct device *dev,
size_t size, void *vaddr,
- dma_addr_t dma_handle)
+ dma_addr_t dma_handle,
+ struct dma_attrs *attrs)
{
kfree(vaddr);
}
@@ -136,8 +137,8 @@ static u64 ibmebus_dma_get_required_mask(struct device *dev)
}
static struct dma_map_ops ibmebus_dma_ops = {
- .alloc_coherent = ibmebus_alloc_coherent,
- .free_coherent = ibmebus_free_coherent,
+ .alloc = ibmebus_alloc_coherent,
+ .free = ibmebus_free_coherent,
.map_sg = ibmebus_map_sg,
.unmap_sg = ibmebus_unmap_sg,
.dma_supported = ibmebus_dma_supported,
@@ -204,7 +205,7 @@ static int ibmebus_create_devices(const struct of_device_id *matches)
return ret;
}
-int ibmebus_register_driver(struct of_platform_driver *drv)
+int ibmebus_register_driver(struct platform_driver *drv)
{
/* If the driver uses devices that ibmebus doesn't know, add them */
ibmebus_create_devices(drv->driver.of_match_table);
@@ -214,7 +215,7 @@ int ibmebus_register_driver(struct of_platform_driver *drv)
}
EXPORT_SYMBOL(ibmebus_register_driver);
-void ibmebus_unregister_driver(struct of_platform_driver *drv)
+void ibmebus_unregister_driver(struct platform_driver *drv)
{
driver_unregister(&drv->driver);
}
@@ -291,6 +292,7 @@ out:
return rc;
return count;
}
+static BUS_ATTR(probe, S_IWUSR, NULL, ibmebus_store_probe);
static ssize_t ibmebus_store_remove(struct bus_type *bus,
const char *buf, size_t count)
@@ -316,13 +318,14 @@ static ssize_t ibmebus_store_remove(struct bus_type *bus,
return -ENODEV;
}
}
+static BUS_ATTR(remove, S_IWUSR, NULL, ibmebus_store_remove);
-
-static struct bus_attribute ibmebus_bus_attrs[] = {
- __ATTR(probe, S_IWUSR, NULL, ibmebus_store_probe),
- __ATTR(remove, S_IWUSR, NULL, ibmebus_store_remove),
- __ATTR_NULL
+static struct attribute *ibmbus_bus_attrs[] = {
+ &bus_attr_probe.attr,
+ &bus_attr_remove.attr,
+ NULL,
};
+ATTRIBUTE_GROUPS(ibmbus_bus);
static int ibmebus_bus_bus_match(struct device *dev, struct device_driver *drv)
{
@@ -337,11 +340,10 @@ static int ibmebus_bus_bus_match(struct device *dev, struct device_driver *drv)
static int ibmebus_bus_device_probe(struct device *dev)
{
int error = -ENODEV;
- struct of_platform_driver *drv;
+ struct platform_driver *drv;
struct platform_device *of_dev;
- const struct of_device_id *match;
- drv = to_of_platform_driver(dev->driver);
+ drv = to_platform_driver(dev->driver);
of_dev = to_platform_device(dev);
if (!drv->probe)
@@ -349,9 +351,8 @@ static int ibmebus_bus_device_probe(struct device *dev)
of_dev_get(of_dev);
- match = of_match_device(drv->driver.of_match_table, dev);
- if (match)
- error = drv->probe(of_dev, match);
+ if (of_driver_match_device(dev, dev->driver))
+ error = drv->probe(of_dev);
if (error)
of_dev_put(of_dev);
@@ -361,7 +362,7 @@ static int ibmebus_bus_device_probe(struct device *dev)
static int ibmebus_bus_device_remove(struct device *dev)
{
struct platform_device *of_dev = to_platform_device(dev);
- struct of_platform_driver *drv = to_of_platform_driver(dev->driver);
+ struct platform_driver *drv = to_platform_driver(dev->driver);
if (dev->driver && drv->remove)
drv->remove(of_dev);
@@ -371,7 +372,7 @@ static int ibmebus_bus_device_remove(struct device *dev)
static void ibmebus_bus_device_shutdown(struct device *dev)
{
struct platform_device *of_dev = to_platform_device(dev);
- struct of_platform_driver *drv = to_of_platform_driver(dev->driver);
+ struct platform_driver *drv = to_platform_driver(dev->driver);
if (dev->driver && drv->shutdown)
drv->shutdown(of_dev);
@@ -418,7 +419,7 @@ struct device_attribute ibmebus_bus_device_attrs[] = {
static int ibmebus_bus_legacy_suspend(struct device *dev, pm_message_t mesg)
{
struct platform_device *of_dev = to_platform_device(dev);
- struct of_platform_driver *drv = to_of_platform_driver(dev->driver);
+ struct platform_driver *drv = to_platform_driver(dev->driver);
int ret = 0;
if (dev->driver && drv->suspend)
@@ -429,7 +430,7 @@ static int ibmebus_bus_legacy_suspend(struct device *dev, pm_message_t mesg)
static int ibmebus_bus_legacy_resume(struct device *dev)
{
struct platform_device *of_dev = to_platform_device(dev);
- struct of_platform_driver *drv = to_of_platform_driver(dev->driver);
+ struct platform_driver *drv = to_platform_driver(dev->driver);
int ret = 0;
if (dev->driver && drv->resume)
@@ -713,8 +714,8 @@ static struct dev_pm_ops ibmebus_bus_dev_pm_ops = {
struct bus_type ibmebus_bus_type = {
.name = "ibmebus",
- .uevent = of_device_uevent,
- .bus_attrs = ibmebus_bus_attrs,
+ .uevent = of_device_uevent_modalias,
+ .bus_groups = ibmbus_bus_groups,
.match = ibmebus_bus_bus_match,
.probe = ibmebus_bus_device_probe,
.remove = ibmebus_bus_device_remove,
diff --git a/arch/powerpc/kernel/idle.c b/arch/powerpc/kernel/idle.c
index 0a48bf5db6c..d7216c9abda 100644
--- a/arch/powerpc/kernel/idle.c
+++ b/arch/powerpc/kernel/idle.c
@@ -26,18 +26,13 @@
#include <linux/sysctl.h>
#include <linux/tick.h>
-#include <asm/system.h>
#include <asm/processor.h>
#include <asm/cputable.h>
#include <asm/time.h>
#include <asm/machdep.h>
+#include <asm/runlatch.h>
#include <asm/smp.h>
-#ifdef CONFIG_HOTPLUG_CPU
-#define cpu_should_die() cpu_is_offline(smp_processor_id())
-#else
-#define cpu_should_die() 0
-#endif
unsigned long cpuidle_disable = IDLE_NO_OVERRIDE;
EXPORT_SYMBOL(cpuidle_disable);
@@ -50,87 +45,39 @@ static int __init powersave_off(char *arg)
}
__setup("powersave=off", powersave_off);
-/*
- * The body of the idle task.
- */
-void cpu_idle(void)
+#ifdef CONFIG_HOTPLUG_CPU
+void arch_cpu_idle_dead(void)
{
- if (ppc_md.idle_loop)
- ppc_md.idle_loop(); /* doesn't return */
-
- set_thread_flag(TIF_POLLING_NRFLAG);
- while (1) {
- tick_nohz_idle_enter();
- rcu_idle_enter();
-
- while (!need_resched() && !cpu_should_die()) {
- ppc64_runlatch_off();
-
- if (ppc_md.power_save) {
- clear_thread_flag(TIF_POLLING_NRFLAG);
- /*
- * smp_mb is so clearing of TIF_POLLING_NRFLAG
- * is ordered w.r.t. need_resched() test.
- */
- smp_mb();
- local_irq_disable();
-
- /* Don't trace irqs off for idle */
- stop_critical_timings();
-
- /* check again after disabling irqs */
- if (!need_resched() && !cpu_should_die())
- ppc_md.power_save();
-
- start_critical_timings();
-
- local_irq_enable();
- set_thread_flag(TIF_POLLING_NRFLAG);
-
- } else {
- /*
- * Go into low thread priority and possibly
- * low power mode.
- */
- HMT_low();
- HMT_very_low();
- }
- }
-
- HMT_medium();
- ppc64_runlatch_on();
- rcu_idle_exit();
- tick_nohz_idle_exit();
- preempt_enable_no_resched();
- if (cpu_should_die())
- cpu_die();
- schedule();
- preempt_disable();
- }
+ sched_preempt_enable_no_resched();
+ cpu_die();
}
+#endif
-
-/*
- * cpu_idle_wait - Used to ensure that all the CPUs come out of the old
- * idle loop and start using the new idle loop.
- * Required while changing idle handler on SMP systems.
- * Caller must have changed idle handler to the new value before the call.
- * This window may be larger on shared systems.
- */
-void cpu_idle_wait(void)
+void arch_cpu_idle(void)
{
- int cpu;
- smp_mb();
-
- /* kick all the CPUs so that they exit out of old idle routine */
- get_online_cpus();
- for_each_online_cpu(cpu) {
- if (cpu != smp_processor_id())
- smp_send_reschedule(cpu);
+ ppc64_runlatch_off();
+
+ if (ppc_md.power_save) {
+ ppc_md.power_save();
+ /*
+ * Some power_save functions return with
+ * interrupts enabled, some don't.
+ */
+ if (irqs_disabled())
+ local_irq_enable();
+ } else {
+ local_irq_enable();
+ /*
+ * Go into low thread priority and possibly
+ * low power mode.
+ */
+ HMT_low();
+ HMT_very_low();
}
- put_online_cpus();
+
+ HMT_medium();
+ ppc64_runlatch_on();
}
-EXPORT_SYMBOL_GPL(cpu_idle_wait);
int powersave_nap;
@@ -138,7 +85,7 @@ int powersave_nap;
/*
* Register the sysctl to set/clear powersave_nap.
*/
-static ctl_table powersave_nap_ctl_table[]={
+static struct ctl_table powersave_nap_ctl_table[] = {
{
.procname = "powersave-nap",
.data = &powersave_nap,
@@ -148,7 +95,7 @@ static ctl_table powersave_nap_ctl_table[]={
},
{}
};
-static ctl_table powersave_nap_sysctl_root[] = {
+static struct ctl_table powersave_nap_sysctl_root[] = {
{
.procname = "kernel",
.mode = 0555,
diff --git a/arch/powerpc/kernel/idle_6xx.S b/arch/powerpc/kernel/idle_6xx.S
index 15c611de1ee..1686916cc7f 100644
--- a/arch/powerpc/kernel/idle_6xx.S
+++ b/arch/powerpc/kernel/idle_6xx.S
@@ -135,7 +135,7 @@ BEGIN_FTR_SECTION
DSSALL
sync
END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
- rlwinm r9,r1,0,0,31-THREAD_SHIFT /* current thread_info */
+ CURRENT_THREAD_INFO(r9, r1)
lwz r8,TI_LOCAL_FLAGS(r9) /* set napping bit */
ori r8,r8,_TLF_NAPPING /* so when we take an exception */
stw r8,TI_LOCAL_FLAGS(r9) /* it will return to our caller */
@@ -158,7 +158,7 @@ _GLOBAL(power_save_ppc32_restore)
stw r9,_NIP(r11) /* make it do a blr */
#ifdef CONFIG_SMP
- rlwinm r12,r11,0,0,31-THREAD_SHIFT
+ CURRENT_THREAD_INFO(r12, r11)
lwz r11,TI_CPU(r12) /* get cpu number * 4 */
slwi r11,r11,2
#else
diff --git a/arch/powerpc/kernel/idle_book3e.S b/arch/powerpc/kernel/idle_book3e.S
index 16c002d6bdf..48c21acef91 100644
--- a/arch/powerpc/kernel/idle_book3e.S
+++ b/arch/powerpc/kernel/idle_book3e.S
@@ -16,11 +16,13 @@
#include <asm/ppc-opcode.h>
#include <asm/processor.h>
#include <asm/thread_info.h>
+#include <asm/epapr_hcalls.h>
/* 64-bit version only for now */
#ifdef CONFIG_PPC64
-_GLOBAL(book3e_idle)
+.macro BOOK3E_IDLE name loop
+_GLOBAL(\name)
/* Save LR for later */
mflr r0
std r0,16(r1)
@@ -29,43 +31,30 @@ _GLOBAL(book3e_idle)
wrteei 0
/* Now check if an interrupt came in while we were soft disabled
- * since we may otherwise lose it (doorbells etc...). We know
- * that since PACAHARDIRQEN will have been cleared in that case.
+ * since we may otherwise lose it (doorbells etc...).
*/
- lbz r3,PACAHARDIRQEN(r13)
+ lbz r3,PACAIRQHAPPENED(r13)
cmpwi cr0,r3,0
- beqlr
+ bnelr
- /* Now we are going to mark ourselves as soft and hard enables in
+ /* Now we are going to mark ourselves as soft and hard enabled in
* order to be able to take interrupts while asleep. We inform lockdep
* of that. We don't actually turn interrupts on just yet tho.
*/
#ifdef CONFIG_TRACE_IRQFLAGS
stdu r1,-128(r1)
- bl .trace_hardirqs_on
+ bl trace_hardirqs_on
+ addi r1,r1,128
#endif
li r0,1
stb r0,PACASOFTIRQEN(r13)
- stb r0,PACAHARDIRQEN(r13)
/* Interrupts will make use return to LR, so get something we want
* in there
*/
bl 1f
- /* Hard disable interrupts again */
- wrteei 0
-
- /* Mark them off again in the PACA as well */
- li r0,0
- stb r0,PACASOFTIRQEN(r13)
- stb r0,PACAHARDIRQEN(r13)
-
- /* Tell lockdep about it */
-#ifdef CONFIG_TRACE_IRQFLAGS
- bl .trace_hardirqs_off
- addi r1,r1,128
-#endif
+ /* And return (interrupts are on) */
ld r0,16(r1)
mtlr r0
blr
@@ -73,14 +62,40 @@ _GLOBAL(book3e_idle)
1: /* Let's set the _TLF_NAPPING flag so interrupts make us return
* to the right spot
*/
- clrrdi r11,r1,THREAD_SHIFT
+ CURRENT_THREAD_INFO(r11, r1)
ld r10,TI_LOCAL_FLAGS(r11)
ori r10,r10,_TLF_NAPPING
std r10,TI_LOCAL_FLAGS(r11)
/* We can now re-enable hard interrupts and go to sleep */
wrteei 1
-1: PPC_WAIT(0)
+ \loop
+
+.endm
+
+.macro BOOK3E_IDLE_LOOP
+1:
+ PPC_WAIT(0)
b 1b
+.endm
+
+/* epapr_ev_idle_start below is patched with the proper hcall
+ opcodes during kernel initialization */
+.macro EPAPR_EV_IDLE_LOOP
+idle_loop:
+ LOAD_REG_IMMEDIATE(r11, EV_HCALL_TOKEN(EV_IDLE))
+
+.global epapr_ev_idle_start
+epapr_ev_idle_start:
+ li r3, -1
+ nop
+ nop
+ nop
+ b idle_loop
+.endm
+
+BOOK3E_IDLE epapr_ev_idle EPAPR_EV_IDLE_LOOP
+
+BOOK3E_IDLE book3e_idle BOOK3E_IDLE_LOOP
#endif /* CONFIG_PPC64 */
diff --git a/arch/powerpc/kernel/idle_e500.S b/arch/powerpc/kernel/idle_e500.S
index 4f0ab85f378..15448668988 100644
--- a/arch/powerpc/kernel/idle_e500.S
+++ b/arch/powerpc/kernel/idle_e500.S
@@ -21,7 +21,7 @@
.text
_GLOBAL(e500_idle)
- rlwinm r3,r1,0,0,31-THREAD_SHIFT /* current thread_info */
+ CURRENT_THREAD_INFO(r3, r1)
lwz r4,TI_LOCAL_FLAGS(r3) /* set napping bit */
ori r4,r4,_TLF_NAPPING /* so when we take an exception */
stw r4,TI_LOCAL_FLAGS(r3) /* it will return to our caller */
@@ -96,7 +96,7 @@ _GLOBAL(power_save_ppc32_restore)
stw r9,_NIP(r11) /* make it do a blr */
#ifdef CONFIG_SMP
- rlwinm r12,r1,0,0,31-THREAD_SHIFT
+ CURRENT_THREAD_INFO(r12, r1)
lwz r11,TI_CPU(r12) /* get cpu number * 4 */
slwi r11,r11,2
#else
diff --git a/arch/powerpc/kernel/idle_power4.S b/arch/powerpc/kernel/idle_power4.S
index ba319547860..f57a19348bd 100644
--- a/arch/powerpc/kernel/idle_power4.S
+++ b/arch/powerpc/kernel/idle_power4.S
@@ -14,6 +14,7 @@
#include <asm/thread_info.h>
#include <asm/ppc_asm.h>
#include <asm/asm-offsets.h>
+#include <asm/irqflags.h>
#undef DEBUG
@@ -29,19 +30,36 @@ END_FTR_SECTION_IFCLR(CPU_FTR_CAN_NAP)
cmpwi 0,r4,0
beqlr
- /* Go to NAP now */
+ /* Hard disable interrupts */
mfmsr r7
rldicl r0,r7,48,1
rotldi r0,r0,16
- mtmsrd r0,1 /* hard-disable interrupts */
+ mtmsrd r0,1
+
+ /* Check if something happened while soft-disabled */
+ lbz r0,PACAIRQHAPPENED(r13)
+ cmpwi cr0,r0,0
+ bnelr
+
+ /* Soft-enable interrupts */
+#ifdef CONFIG_TRACE_IRQFLAGS
+ mflr r0
+ std r0,16(r1)
+ stdu r1,-128(r1)
+ bl trace_hardirqs_on
+ addi r1,r1,128
+ ld r0,16(r1)
+ mtlr r0
+ mfmsr r7
+#endif /* CONFIG_TRACE_IRQFLAGS */
+
li r0,1
stb r0,PACASOFTIRQEN(r13) /* we'll hard-enable shortly */
- stb r0,PACAHARDIRQEN(r13)
BEGIN_FTR_SECTION
DSSALL
sync
END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
- clrrdi r9,r1,THREAD_SHIFT /* current thread_info */
+ CURRENT_THREAD_INFO(r9, r1)
ld r8,TI_LOCAL_FLAGS(r9) /* set napping bit */
ori r8,r8,_TLF_NAPPING /* so when we take an exception */
std r8,TI_LOCAL_FLAGS(r9) /* it will return to our caller */
diff --git a/arch/powerpc/kernel/idle_power7.S b/arch/powerpc/kernel/idle_power7.S
index fcdff198da4..5cf3d367190 100644
--- a/arch/powerpc/kernel/idle_power7.S
+++ b/arch/powerpc/kernel/idle_power7.S
@@ -1,5 +1,5 @@
/*
- * This file contains the power_save function for 970-family CPUs.
+ * This file contains the power_save function for Power7 CPUs.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
@@ -15,18 +15,37 @@
#include <asm/ppc_asm.h>
#include <asm/asm-offsets.h>
#include <asm/ppc-opcode.h>
+#include <asm/hw_irq.h>
+#include <asm/kvm_book3s_asm.h>
+#include <asm/opal.h>
#undef DEBUG
- .text
+/* Idle state entry routines */
-_GLOBAL(power7_idle)
- /* Now check if user or arch enabled NAP mode */
- LOAD_REG_ADDRBASE(r3,powersave_nap)
- lwz r4,ADDROFF(powersave_nap)(r3)
- cmpwi 0,r4,0
- beqlr
+#define IDLE_STATE_ENTER_SEQ(IDLE_INST) \
+ /* Magic NAP/SLEEP/WINKLE mode enter sequence */ \
+ std r0,0(r1); \
+ ptesync; \
+ ld r0,0(r1); \
+1: cmp cr0,r0,r0; \
+ bne 1b; \
+ IDLE_INST; \
+ b .
+ .text
+
+/*
+ * Pass requested state in r3:
+ * 0 - nap
+ * 1 - sleep
+ *
+ * To check IRQ_HAPPENED in r4
+ * 0 - don't check
+ * 1 - check
+ */
+_GLOBAL(power7_powersave_common)
+ /* Use r3 to pass state nap/sleep/winkle */
/* NAP is a state loss, we create a regs frame on the
* stack, fill it up with the state we care about and
* stick a pointer to it in PACAR1. We really only
@@ -43,7 +62,7 @@ _GLOBAL(power7_idle)
/* Make sure FPU, VSX etc... are flushed as we may lose
* state when going to nap mode
*/
- bl .discard_lazy_cpu_state
+ bl discard_lazy_cpu_state
#endif /* CONFIG_SMP */
/* Hard disable interrupts */
@@ -51,27 +70,96 @@ _GLOBAL(power7_idle)
rldicl r9,r9,48,1
rotldi r9,r9,16
mtmsrd r9,1 /* hard-disable interrupts */
+
+ /* Check if something happened while soft-disabled */
+ lbz r0,PACAIRQHAPPENED(r13)
+ cmpwi cr0,r0,0
+ beq 1f
+ cmpwi cr0,r4,0
+ beq 1f
+ addi r1,r1,INT_FRAME_SIZE
+ ld r0,16(r1)
+ mtlr r0
+ blr
+
+1: /* We mark irqs hard disabled as this is the state we'll
+ * be in when returning and we need to tell arch_local_irq_restore()
+ * about it
+ */
+ li r0,PACA_IRQ_HARD_DIS
+ stb r0,PACAIRQHAPPENED(r13)
+
+ /* We haven't lost state ... yet */
li r0,0
- stb r0,PACASOFTIRQEN(r13) /* we'll hard-enable shortly */
- stb r0,PACAHARDIRQEN(r13)
stb r0,PACA_NAPSTATELOST(r13)
/* Continue saving state */
SAVE_GPR(2, r1)
SAVE_NVGPRS(r1)
- mfcr r3
- std r3,_CCR(r1)
+ mfcr r4
+ std r4,_CCR(r1)
std r9,_MSR(r1)
std r1,PACAR1(r13)
- /* Magic NAP mode enter sequence */
- std r0,0(r1)
- ptesync
- ld r0,0(r1)
-1: cmp cr0,r0,r0
- bne 1b
- PPC_NAP
- b .
+_GLOBAL(power7_enter_nap_mode)
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+ /* Tell KVM we're napping */
+ li r4,KVM_HWTHREAD_IN_NAP
+ stb r4,HSTATE_HWTHREAD_STATE(r13)
+#endif
+ cmpwi cr0,r3,1
+ beq 2f
+ IDLE_STATE_ENTER_SEQ(PPC_NAP)
+ /* No return */
+2: IDLE_STATE_ENTER_SEQ(PPC_SLEEP)
+ /* No return */
+
+_GLOBAL(power7_idle)
+ /* Now check if user or arch enabled NAP mode */
+ LOAD_REG_ADDRBASE(r3,powersave_nap)
+ lwz r4,ADDROFF(powersave_nap)(r3)
+ cmpwi 0,r4,0
+ beqlr
+ li r3, 1
+ /* fall through */
+
+_GLOBAL(power7_nap)
+ mr r4,r3
+ li r3,0
+ b power7_powersave_common
+ /* No return */
+
+_GLOBAL(power7_sleep)
+ li r3,1
+ li r4,1
+ b power7_powersave_common
+ /* No return */
+
+_GLOBAL(power7_wakeup_tb_loss)
+ ld r2,PACATOC(r13);
+ ld r1,PACAR1(r13)
+
+ /* Time base re-sync */
+ li r0,OPAL_RESYNC_TIMEBASE
+ LOAD_REG_ADDR(r11,opal);
+ ld r12,8(r11);
+ ld r2,0(r11);
+ mtctr r12
+ bctrl
+
+ /* TODO: Check r3 for failure */
+
+ REST_NVGPRS(r1)
+ REST_GPR(2, r1)
+ ld r3,_CCR(r1)
+ ld r4,_MSR(r1)
+ ld r5,_NIP(r1)
+ addi r1,r1,INT_FRAME_SIZE
+ mtcr r3
+ mfspr r3,SPRN_SRR1 /* Return SRR1 */
+ mtspr SPRN_SRR1,r4
+ mtspr SPRN_SRR0,r5
+ rfid
_GLOBAL(power7_wakeup_loss)
ld r1,PACAR1(r13)
@@ -89,7 +177,7 @@ _GLOBAL(power7_wakeup_loss)
_GLOBAL(power7_wakeup_noloss)
lbz r0,PACA_NAPSTATELOST(r13)
cmpwi r0,0
- bne .power7_wakeup_loss
+ bne power7_wakeup_loss
ld r1,PACAR1(r13)
ld r4,_MSR(r1)
ld r5,_NIP(r1)
diff --git a/arch/powerpc/kernel/init_task.c b/arch/powerpc/kernel/init_task.c
deleted file mode 100644
index d076d465dbd..00000000000
--- a/arch/powerpc/kernel/init_task.c
+++ /dev/null
@@ -1,29 +0,0 @@
-#include <linux/mm.h>
-#include <linux/export.h>
-#include <linux/sched.h>
-#include <linux/init.h>
-#include <linux/init_task.h>
-#include <linux/fs.h>
-#include <linux/mqueue.h>
-#include <asm/uaccess.h>
-
-static struct signal_struct init_signals = INIT_SIGNALS(init_signals);
-static struct sighand_struct init_sighand = INIT_SIGHAND(init_sighand);
-/*
- * Initial thread structure.
- *
- * We need to make sure that this is 16384-byte aligned due to the
- * way process stacks are handled. This is done by having a special
- * "init_task" linker map entry..
- */
-union thread_union init_thread_union __init_task_data =
- { INIT_THREAD_INFO(init_task) };
-
-/*
- * Initial task structure.
- *
- * All other task structs will be allocated on slabs in fork.c
- */
-struct task_struct init_task = INIT_TASK(init_task);
-
-EXPORT_SYMBOL(init_task);
diff --git a/arch/powerpc/kernel/io-workarounds.c b/arch/powerpc/kernel/io-workarounds.c
index 12d329bcbb9..24b968f8e4d 100644
--- a/arch/powerpc/kernel/io-workarounds.c
+++ b/arch/powerpc/kernel/io-workarounds.c
@@ -53,8 +53,10 @@ static struct iowa_bus *iowa_pci_find(unsigned long vaddr, unsigned long paddr)
return NULL;
}
+#ifdef CONFIG_PPC_INDIRECT_MMIO
struct iowa_bus *iowa_mem_find_bus(const PCI_IO_ADDR addr)
{
+ unsigned hugepage_shift;
struct iowa_bus *bus;
int token;
@@ -70,11 +72,17 @@ struct iowa_bus *iowa_mem_find_bus(const PCI_IO_ADDR addr)
if (vaddr < PHB_IO_BASE || vaddr >= PHB_IO_END)
return NULL;
- ptep = find_linux_pte(init_mm.pgd, vaddr);
+ ptep = find_linux_pte_or_hugepte(init_mm.pgd, vaddr,
+ &hugepage_shift);
if (ptep == NULL)
paddr = 0;
- else
+ else {
+ /*
+ * we don't have hugepages backing iomem
+ */
+ WARN_ON(hugepage_shift);
paddr = pte_pfn(*ptep) << PAGE_SHIFT;
+ }
bus = iowa_pci_find(vaddr, paddr);
if (bus == NULL)
@@ -83,13 +91,25 @@ struct iowa_bus *iowa_mem_find_bus(const PCI_IO_ADDR addr)
return bus;
}
+#else /* CONFIG_PPC_INDIRECT_MMIO */
+struct iowa_bus *iowa_mem_find_bus(const PCI_IO_ADDR addr)
+{
+ return NULL;
+}
+#endif /* !CONFIG_PPC_INDIRECT_MMIO */
+#ifdef CONFIG_PPC_INDIRECT_PIO
struct iowa_bus *iowa_pio_find_bus(unsigned long port)
{
unsigned long vaddr = (unsigned long)pci_io_base + port;
return iowa_pci_find(vaddr, 0);
}
-
+#else
+struct iowa_bus *iowa_pio_find_bus(unsigned long port)
+{
+ return NULL;
+}
+#endif
#define DEF_PCI_AC_RET(name, ret, at, al, space, aa) \
static ret iowa_##name at \
@@ -118,7 +138,7 @@ static void iowa_##name at \
#undef DEF_PCI_AC_RET
#undef DEF_PCI_AC_NORET
-static const struct ppc_pci_io __devinitconst iowa_pci_io = {
+static const struct ppc_pci_io iowa_pci_io = {
#define DEF_PCI_AC_RET(name, ret, at, al, space, aa) .name = iowa_##name,
#define DEF_PCI_AC_NORET(name, at, al, space, aa) .name = iowa_##name,
@@ -130,6 +150,7 @@ static const struct ppc_pci_io __devinitconst iowa_pci_io = {
};
+#ifdef CONFIG_PPC_INDIRECT_MMIO
static void __iomem *iowa_ioremap(phys_addr_t addr, unsigned long size,
unsigned long flags, void *caller)
{
@@ -144,9 +165,12 @@ static void __iomem *iowa_ioremap(phys_addr_t addr, unsigned long size,
}
return res;
}
+#else /* CONFIG_PPC_INDIRECT_MMIO */
+#define iowa_ioremap NULL
+#endif /* !CONFIG_PPC_INDIRECT_MMIO */
/* Enable IO workaround */
-static void __devinit io_workaround_init(void)
+static void io_workaround_init(void)
{
static int io_workaround_inited;
@@ -158,9 +182,8 @@ static void __devinit io_workaround_init(void)
}
/* Register new bus to support workaround */
-void __devinit iowa_register_bus(struct pci_controller *phb,
- struct ppc_pci_io *ops,
- int (*initfunc)(struct iowa_bus *, void *), void *data)
+void iowa_register_bus(struct pci_controller *phb, struct ppc_pci_io *ops,
+ int (*initfunc)(struct iowa_bus *, void *), void *data)
{
struct iowa_bus *bus;
struct device_node *np = phb->dn;
diff --git a/arch/powerpc/kernel/io.c b/arch/powerpc/kernel/io.c
index 886381f32c3..2a2b4aeab80 100644
--- a/arch/powerpc/kernel/io.c
+++ b/arch/powerpc/kernel/io.c
@@ -25,6 +25,9 @@
#include <asm/firmware.h>
#include <asm/bug.h>
+/* See definition in io.h */
+bool isa_io_special;
+
void _insb(const volatile u8 __iomem *port, void *buf, long count)
{
u8 *tbuf = buf;
diff --git a/arch/powerpc/kernel/iomap.c b/arch/powerpc/kernel/iomap.c
index 97a3715ac8b..12e48d56f77 100644
--- a/arch/powerpc/kernel/iomap.c
+++ b/arch/powerpc/kernel/iomap.c
@@ -3,7 +3,6 @@
*
* (C) Copyright 2004 Linus Torvalds
*/
-#include <linux/init.h>
#include <linux/pci.h>
#include <linux/mm.h>
#include <linux/export.h>
@@ -24,7 +23,7 @@ unsigned int ioread16(void __iomem *addr)
}
unsigned int ioread16be(void __iomem *addr)
{
- return in_be16(addr);
+ return readw_be(addr);
}
unsigned int ioread32(void __iomem *addr)
{
@@ -32,7 +31,7 @@ unsigned int ioread32(void __iomem *addr)
}
unsigned int ioread32be(void __iomem *addr)
{
- return in_be32(addr);
+ return readl_be(addr);
}
EXPORT_SYMBOL(ioread8);
EXPORT_SYMBOL(ioread16);
@@ -50,7 +49,7 @@ void iowrite16(u16 val, void __iomem *addr)
}
void iowrite16be(u16 val, void __iomem *addr)
{
- out_be16(addr, val);
+ writew_be(val, addr);
}
void iowrite32(u32 val, void __iomem *addr)
{
@@ -58,7 +57,7 @@ void iowrite32(u32 val, void __iomem *addr)
}
void iowrite32be(u32 val, void __iomem *addr)
{
- out_be32(addr, val);
+ writel_be(val, addr);
}
EXPORT_SYMBOL(iowrite8);
EXPORT_SYMBOL(iowrite16);
@@ -76,15 +75,15 @@ EXPORT_SYMBOL(iowrite32be);
*/
void ioread8_rep(void __iomem *addr, void *dst, unsigned long count)
{
- _insb((u8 __iomem *) addr, dst, count);
+ readsb(addr, dst, count);
}
void ioread16_rep(void __iomem *addr, void *dst, unsigned long count)
{
- _insw_ns((u16 __iomem *) addr, dst, count);
+ readsw(addr, dst, count);
}
void ioread32_rep(void __iomem *addr, void *dst, unsigned long count)
{
- _insl_ns((u32 __iomem *) addr, dst, count);
+ readsl(addr, dst, count);
}
EXPORT_SYMBOL(ioread8_rep);
EXPORT_SYMBOL(ioread16_rep);
@@ -92,15 +91,15 @@ EXPORT_SYMBOL(ioread32_rep);
void iowrite8_rep(void __iomem *addr, const void *src, unsigned long count)
{
- _outsb((u8 __iomem *) addr, src, count);
+ writesb(addr, src, count);
}
void iowrite16_rep(void __iomem *addr, const void *src, unsigned long count)
{
- _outsw_ns((u16 __iomem *) addr, src, count);
+ writesw(addr, src, count);
}
void iowrite32_rep(void __iomem *addr, const void *src, unsigned long count)
{
- _outsl_ns((u32 __iomem *) addr, src, count);
+ writesl(addr, src, count);
}
EXPORT_SYMBOL(iowrite8_rep);
EXPORT_SYMBOL(iowrite16_rep);
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index 0cfcf98aafc..88e3ec6e1d9 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -33,12 +33,20 @@
#include <linux/bitmap.h>
#include <linux/iommu-helper.h>
#include <linux/crash_dump.h>
+#include <linux/hash.h>
+#include <linux/fault-inject.h>
+#include <linux/pci.h>
+#include <linux/iommu.h>
+#include <linux/sched.h>
#include <asm/io.h>
#include <asm/prom.h>
#include <asm/iommu.h>
#include <asm/pci-bridge.h>
#include <asm/machdep.h>
#include <asm/kdump.h>
+#include <asm/fadump.h>
+#include <asm/vio.h>
+#include <asm/tce.h>
#define DBG(...)
@@ -57,6 +65,114 @@ static int __init setup_iommu(char *str)
__setup("iommu=", setup_iommu);
+static DEFINE_PER_CPU(unsigned int, iommu_pool_hash);
+
+/*
+ * We precalculate the hash to avoid doing it on every allocation.
+ *
+ * The hash is important to spread CPUs across all the pools. For example,
+ * on a POWER7 with 4 way SMT we want interrupts on the primary threads and
+ * with 4 pools all primary threads would map to the same pool.
+ */
+static int __init setup_iommu_pool_hash(void)
+{
+ unsigned int i;
+
+ for_each_possible_cpu(i)
+ per_cpu(iommu_pool_hash, i) = hash_32(i, IOMMU_POOL_HASHBITS);
+
+ return 0;
+}
+subsys_initcall(setup_iommu_pool_hash);
+
+#ifdef CONFIG_FAIL_IOMMU
+
+static DECLARE_FAULT_ATTR(fail_iommu);
+
+static int __init setup_fail_iommu(char *str)
+{
+ return setup_fault_attr(&fail_iommu, str);
+}
+__setup("fail_iommu=", setup_fail_iommu);
+
+static bool should_fail_iommu(struct device *dev)
+{
+ return dev->archdata.fail_iommu && should_fail(&fail_iommu, 1);
+}
+
+static int __init fail_iommu_debugfs(void)
+{
+ struct dentry *dir = fault_create_debugfs_attr("fail_iommu",
+ NULL, &fail_iommu);
+
+ return PTR_ERR_OR_ZERO(dir);
+}
+late_initcall(fail_iommu_debugfs);
+
+static ssize_t fail_iommu_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ return sprintf(buf, "%d\n", dev->archdata.fail_iommu);
+}
+
+static ssize_t fail_iommu_store(struct device *dev,
+ struct device_attribute *attr, const char *buf,
+ size_t count)
+{
+ int i;
+
+ if (count > 0 && sscanf(buf, "%d", &i) > 0)
+ dev->archdata.fail_iommu = (i == 0) ? 0 : 1;
+
+ return count;
+}
+
+static DEVICE_ATTR(fail_iommu, S_IRUGO|S_IWUSR, fail_iommu_show,
+ fail_iommu_store);
+
+static int fail_iommu_bus_notify(struct notifier_block *nb,
+ unsigned long action, void *data)
+{
+ struct device *dev = data;
+
+ if (action == BUS_NOTIFY_ADD_DEVICE) {
+ if (device_create_file(dev, &dev_attr_fail_iommu))
+ pr_warn("Unable to create IOMMU fault injection sysfs "
+ "entries\n");
+ } else if (action == BUS_NOTIFY_DEL_DEVICE) {
+ device_remove_file(dev, &dev_attr_fail_iommu);
+ }
+
+ return 0;
+}
+
+static struct notifier_block fail_iommu_bus_notifier = {
+ .notifier_call = fail_iommu_bus_notify
+};
+
+static int __init fail_iommu_setup(void)
+{
+#ifdef CONFIG_PCI
+ bus_register_notifier(&pci_bus_type, &fail_iommu_bus_notifier);
+#endif
+#ifdef CONFIG_IBMVIO
+ bus_register_notifier(&vio_bus_type, &fail_iommu_bus_notifier);
+#endif
+
+ return 0;
+}
+/*
+ * Must execute after PCI and VIO subsystem have initialised but before
+ * devices are probed.
+ */
+arch_initcall(fail_iommu_setup);
+#else
+static inline bool should_fail_iommu(struct device *dev)
+{
+ return false;
+}
+#endif
+
static unsigned long iommu_range_alloc(struct device *dev,
struct iommu_table *tbl,
unsigned long npages,
@@ -70,6 +186,9 @@ static unsigned long iommu_range_alloc(struct device *dev,
int pass = 0;
unsigned long align_mask;
unsigned long boundary_size;
+ unsigned long flags;
+ unsigned int pool_nr;
+ struct iommu_pool *pool;
align_mask = 0xffffffffffffffffl >> (64 - align_order);
@@ -82,59 +201,83 @@ static unsigned long iommu_range_alloc(struct device *dev,
return DMA_ERROR_CODE;
}
- if (handle && *handle)
- start = *handle;
+ if (should_fail_iommu(dev))
+ return DMA_ERROR_CODE;
+
+ /*
+ * We don't need to disable preemption here because any CPU can
+ * safely use any IOMMU pool.
+ */
+ pool_nr = __raw_get_cpu_var(iommu_pool_hash) & (tbl->nr_pools - 1);
+
+ if (largealloc)
+ pool = &(tbl->large_pool);
else
- start = largealloc ? tbl->it_largehint : tbl->it_hint;
+ pool = &(tbl->pools[pool_nr]);
+
+ spin_lock_irqsave(&(pool->lock), flags);
- /* Use only half of the table for small allocs (15 pages or less) */
- limit = largealloc ? tbl->it_size : tbl->it_halfpoint;
+again:
+ if ((pass == 0) && handle && *handle &&
+ (*handle >= pool->start) && (*handle < pool->end))
+ start = *handle;
+ else
+ start = pool->hint;
- if (largealloc && start < tbl->it_halfpoint)
- start = tbl->it_halfpoint;
+ limit = pool->end;
/* The case below can happen if we have a small segment appended
* to a large, or when the previous alloc was at the very end of
* the available space. If so, go back to the initial start.
*/
if (start >= limit)
- start = largealloc ? tbl->it_largehint : tbl->it_hint;
-
- again:
+ start = pool->start;
if (limit + tbl->it_offset > mask) {
limit = mask - tbl->it_offset + 1;
/* If we're constrained on address range, first try
* at the masked hint to avoid O(n) search complexity,
- * but on second pass, start at 0.
+ * but on second pass, start at 0 in pool 0.
*/
- if ((start & mask) >= limit || pass > 0)
- start = 0;
- else
+ if ((start & mask) >= limit || pass > 0) {
+ spin_unlock(&(pool->lock));
+ pool = &(tbl->pools[0]);
+ spin_lock(&(pool->lock));
+ start = pool->start;
+ } else {
start &= mask;
+ }
}
if (dev)
boundary_size = ALIGN(dma_get_seg_boundary(dev) + 1,
- 1 << IOMMU_PAGE_SHIFT);
+ 1 << tbl->it_page_shift);
else
- boundary_size = ALIGN(1UL << 32, 1 << IOMMU_PAGE_SHIFT);
+ boundary_size = ALIGN(1UL << 32, 1 << tbl->it_page_shift);
/* 4GB boundary for iseries_hv_alloc and iseries_hv_map */
- n = iommu_area_alloc(tbl->it_map, limit, start, npages,
- tbl->it_offset, boundary_size >> IOMMU_PAGE_SHIFT,
- align_mask);
+ n = iommu_area_alloc(tbl->it_map, limit, start, npages, tbl->it_offset,
+ boundary_size >> tbl->it_page_shift, align_mask);
if (n == -1) {
- if (likely(pass < 2)) {
- /* First failure, just rescan the half of the table.
- * Second failure, rescan the other half of the table.
- */
- start = (largealloc ^ pass) ? tbl->it_halfpoint : 0;
- limit = pass ? tbl->it_size : limit;
+ if (likely(pass == 0)) {
+ /* First try the pool from the start */
+ pool->hint = pool->start;
+ pass++;
+ goto again;
+
+ } else if (pass <= tbl->nr_pools) {
+ /* Now try scanning all the other pools */
+ spin_unlock(&(pool->lock));
+ pool_nr = (pool_nr + 1) & (tbl->nr_pools - 1);
+ pool = &tbl->pools[pool_nr];
+ spin_lock(&(pool->lock));
+ pool->hint = pool->start;
pass++;
goto again;
+
} else {
- /* Third failure, give up */
+ /* Give up */
+ spin_unlock_irqrestore(&(pool->lock), flags);
return DMA_ERROR_CODE;
}
}
@@ -144,10 +287,10 @@ static unsigned long iommu_range_alloc(struct device *dev,
/* Bump the hint to a new block for small allocs. */
if (largealloc) {
/* Don't bump to new block to avoid fragmentation */
- tbl->it_largehint = end;
+ pool->hint = end;
} else {
/* Overflow will be taken care of at the next allocation */
- tbl->it_hint = (end + tbl->it_blocksize - 1) &
+ pool->hint = (end + tbl->it_blocksize - 1) &
~(tbl->it_blocksize - 1);
}
@@ -155,6 +298,8 @@ static unsigned long iommu_range_alloc(struct device *dev,
if (handle)
*handle = end;
+ spin_unlock_irqrestore(&(pool->lock), flags);
+
return n;
}
@@ -164,26 +309,22 @@ static dma_addr_t iommu_alloc(struct device *dev, struct iommu_table *tbl,
unsigned long mask, unsigned int align_order,
struct dma_attrs *attrs)
{
- unsigned long entry, flags;
+ unsigned long entry;
dma_addr_t ret = DMA_ERROR_CODE;
int build_fail;
- spin_lock_irqsave(&(tbl->it_lock), flags);
-
entry = iommu_range_alloc(dev, tbl, npages, NULL, mask, align_order);
- if (unlikely(entry == DMA_ERROR_CODE)) {
- spin_unlock_irqrestore(&(tbl->it_lock), flags);
+ if (unlikely(entry == DMA_ERROR_CODE))
return DMA_ERROR_CODE;
- }
entry += tbl->it_offset; /* Offset into real TCE table */
- ret = entry << IOMMU_PAGE_SHIFT; /* Set the return dma address */
+ ret = entry << tbl->it_page_shift; /* Set the return dma address */
/* Put the TCEs in the HW table */
build_fail = ppc_md.tce_build(tbl, entry, npages,
- (unsigned long)page & IOMMU_PAGE_MASK,
- direction, attrs);
+ (unsigned long)page &
+ IOMMU_PAGE_MASK(tbl), direction, attrs);
/* ppc_md.tce_build() only returns non-zero for transient errors.
* Clean up the table bitmap in this case and return
@@ -192,8 +333,6 @@ static dma_addr_t iommu_alloc(struct device *dev, struct iommu_table *tbl,
*/
if (unlikely(build_fail)) {
__iommu_free(tbl, ret, npages);
-
- spin_unlock_irqrestore(&(tbl->it_lock), flags);
return DMA_ERROR_CODE;
}
@@ -201,20 +340,18 @@ static dma_addr_t iommu_alloc(struct device *dev, struct iommu_table *tbl,
if (ppc_md.tce_flush)
ppc_md.tce_flush(tbl);
- spin_unlock_irqrestore(&(tbl->it_lock), flags);
-
/* Make sure updates are seen by hardware */
mb();
return ret;
}
-static void __iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr,
- unsigned int npages)
+static bool iommu_free_check(struct iommu_table *tbl, dma_addr_t dma_addr,
+ unsigned int npages)
{
unsigned long entry, free_entry;
- entry = dma_addr >> IOMMU_PAGE_SHIFT;
+ entry = dma_addr >> tbl->it_page_shift;
free_entry = entry - tbl->it_offset;
if (((free_entry + npages) > tbl->it_size) ||
@@ -230,20 +367,57 @@ static void __iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr,
printk(KERN_INFO "\tindex = 0x%llx\n", (u64)tbl->it_index);
WARN_ON(1);
}
- return;
+
+ return false;
}
+ return true;
+}
+
+static struct iommu_pool *get_pool(struct iommu_table *tbl,
+ unsigned long entry)
+{
+ struct iommu_pool *p;
+ unsigned long largepool_start = tbl->large_pool.start;
+
+ /* The large pool is the last pool at the top of the table */
+ if (entry >= largepool_start) {
+ p = &tbl->large_pool;
+ } else {
+ unsigned int pool_nr = entry / tbl->poolsize;
+
+ BUG_ON(pool_nr > tbl->nr_pools);
+ p = &tbl->pools[pool_nr];
+ }
+
+ return p;
+}
+
+static void __iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr,
+ unsigned int npages)
+{
+ unsigned long entry, free_entry;
+ unsigned long flags;
+ struct iommu_pool *pool;
+
+ entry = dma_addr >> tbl->it_page_shift;
+ free_entry = entry - tbl->it_offset;
+
+ pool = get_pool(tbl, free_entry);
+
+ if (!iommu_free_check(tbl, dma_addr, npages))
+ return;
+
ppc_md.tce_free(tbl, entry, npages);
+
+ spin_lock_irqsave(&(pool->lock), flags);
bitmap_clear(tbl->it_map, free_entry, npages);
+ spin_unlock_irqrestore(&(pool->lock), flags);
}
static void iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr,
unsigned int npages)
{
- unsigned long flags;
-
- spin_lock_irqsave(&(tbl->it_lock), flags);
-
__iommu_free(tbl, dma_addr, npages);
/* Make sure TLB cache is flushed if the HW needs it. We do
@@ -252,8 +426,6 @@ static void iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr,
*/
if (ppc_md.tce_flush)
ppc_md.tce_flush(tbl);
-
- spin_unlock_irqrestore(&(tbl->it_lock), flags);
}
int iommu_map_sg(struct device *dev, struct iommu_table *tbl,
@@ -262,7 +434,6 @@ int iommu_map_sg(struct device *dev, struct iommu_table *tbl,
struct dma_attrs *attrs)
{
dma_addr_t dma_next = 0, dma_addr;
- unsigned long flags;
struct scatterlist *s, *outs, *segstart;
int outcount, incount, i, build_fail = 0;
unsigned int align;
@@ -284,8 +455,6 @@ int iommu_map_sg(struct device *dev, struct iommu_table *tbl,
DBG("sg mapping %d elements:\n", nelems);
- spin_lock_irqsave(&(tbl->it_lock), flags);
-
max_seg_size = dma_get_max_seg_size(dev);
for_each_sg(sglist, s, nelems, i) {
unsigned long vaddr, npages, entry, slen;
@@ -298,13 +467,13 @@ int iommu_map_sg(struct device *dev, struct iommu_table *tbl,
}
/* Allocate iommu entries for that segment */
vaddr = (unsigned long) sg_virt(s);
- npages = iommu_num_pages(vaddr, slen, IOMMU_PAGE_SIZE);
+ npages = iommu_num_pages(vaddr, slen, IOMMU_PAGE_SIZE(tbl));
align = 0;
- if (IOMMU_PAGE_SHIFT < PAGE_SHIFT && slen >= PAGE_SIZE &&
+ if (tbl->it_page_shift < PAGE_SHIFT && slen >= PAGE_SIZE &&
(vaddr & ~PAGE_MASK) == 0)
- align = PAGE_SHIFT - IOMMU_PAGE_SHIFT;
+ align = PAGE_SHIFT - tbl->it_page_shift;
entry = iommu_range_alloc(dev, tbl, npages, &handle,
- mask >> IOMMU_PAGE_SHIFT, align);
+ mask >> tbl->it_page_shift, align);
DBG(" - vaddr: %lx, size: %lx\n", vaddr, slen);
@@ -319,16 +488,16 @@ int iommu_map_sg(struct device *dev, struct iommu_table *tbl,
/* Convert entry to a dma_addr_t */
entry += tbl->it_offset;
- dma_addr = entry << IOMMU_PAGE_SHIFT;
- dma_addr |= (s->offset & ~IOMMU_PAGE_MASK);
+ dma_addr = entry << tbl->it_page_shift;
+ dma_addr |= (s->offset & ~IOMMU_PAGE_MASK(tbl));
DBG(" - %lu pages, entry: %lx, dma_addr: %lx\n",
npages, entry, dma_addr);
/* Insert into HW table */
build_fail = ppc_md.tce_build(tbl, entry, npages,
- vaddr & IOMMU_PAGE_MASK,
- direction, attrs);
+ vaddr & IOMMU_PAGE_MASK(tbl),
+ direction, attrs);
if(unlikely(build_fail))
goto failure;
@@ -368,8 +537,6 @@ int iommu_map_sg(struct device *dev, struct iommu_table *tbl,
if (ppc_md.tce_flush)
ppc_md.tce_flush(tbl);
- spin_unlock_irqrestore(&(tbl->it_lock), flags);
-
DBG("mapped %d elements:\n", outcount);
/* For the sake of iommu_unmap_sg, we clear out the length in the
@@ -391,9 +558,9 @@ int iommu_map_sg(struct device *dev, struct iommu_table *tbl,
if (s->dma_length != 0) {
unsigned long vaddr, npages;
- vaddr = s->dma_address & IOMMU_PAGE_MASK;
+ vaddr = s->dma_address & IOMMU_PAGE_MASK(tbl);
npages = iommu_num_pages(s->dma_address, s->dma_length,
- IOMMU_PAGE_SIZE);
+ IOMMU_PAGE_SIZE(tbl));
__iommu_free(tbl, vaddr, npages);
s->dma_address = DMA_ERROR_CODE;
s->dma_length = 0;
@@ -401,7 +568,6 @@ int iommu_map_sg(struct device *dev, struct iommu_table *tbl,
if (s == outs)
break;
}
- spin_unlock_irqrestore(&(tbl->it_lock), flags);
return 0;
}
@@ -411,15 +577,12 @@ void iommu_unmap_sg(struct iommu_table *tbl, struct scatterlist *sglist,
struct dma_attrs *attrs)
{
struct scatterlist *sg;
- unsigned long flags;
BUG_ON(direction == DMA_NONE);
if (!tbl)
return;
- spin_lock_irqsave(&(tbl->it_lock), flags);
-
sg = sglist;
while (nelems--) {
unsigned int npages;
@@ -428,7 +591,7 @@ void iommu_unmap_sg(struct iommu_table *tbl, struct scatterlist *sglist,
if (sg->dma_length == 0)
break;
npages = iommu_num_pages(dma_handle, sg->dma_length,
- IOMMU_PAGE_SIZE);
+ IOMMU_PAGE_SIZE(tbl));
__iommu_free(tbl, dma_handle, npages);
sg = sg_next(sg);
}
@@ -439,13 +602,16 @@ void iommu_unmap_sg(struct iommu_table *tbl, struct scatterlist *sglist,
*/
if (ppc_md.tce_flush)
ppc_md.tce_flush(tbl);
-
- spin_unlock_irqrestore(&(tbl->it_lock), flags);
}
static void iommu_table_clear(struct iommu_table *tbl)
{
- if (!is_kdump_kernel()) {
+ /*
+ * In case of firmware assisted dump system goes through clean
+ * reboot process at the time of system crash. Hence it's safe to
+ * clear the TCE entries if firmware assisted dump is active.
+ */
+ if (!is_kdump_kernel() || is_fadump_active()) {
/* Clear the table in case firmware left allocations in it */
ppc_md.tce_free(tbl, tbl->it_offset, tbl->it_size);
return;
@@ -488,14 +654,13 @@ struct iommu_table *iommu_init_table(struct iommu_table *tbl, int nid)
unsigned long sz;
static int welcomed = 0;
struct page *page;
-
- /* Set aside 1/4 of the table for large allocations. */
- tbl->it_halfpoint = tbl->it_size * 3 / 4;
+ unsigned int i;
+ struct iommu_pool *p;
/* number of bytes needed for the bitmap */
- sz = (tbl->it_size + 7) >> 3;
+ sz = BITS_TO_LONGS(tbl->it_size) * sizeof(unsigned long);
- page = alloc_pages_node(nid, GFP_ATOMIC, get_order(sz));
+ page = alloc_pages_node(nid, GFP_KERNEL, get_order(sz));
if (!page)
panic("iommu_init_table: Can't allocate %ld bytes\n", sz);
tbl->it_map = page_address(page);
@@ -509,9 +674,28 @@ struct iommu_table *iommu_init_table(struct iommu_table *tbl, int nid)
if (tbl->it_offset == 0)
set_bit(0, tbl->it_map);
- tbl->it_hint = 0;
- tbl->it_largehint = tbl->it_halfpoint;
- spin_lock_init(&tbl->it_lock);
+ /* We only split the IOMMU table if we have 1GB or more of space */
+ if ((tbl->it_size << tbl->it_page_shift) >= (1UL * 1024 * 1024 * 1024))
+ tbl->nr_pools = IOMMU_NR_POOLS;
+ else
+ tbl->nr_pools = 1;
+
+ /* We reserve the top 1/4 of the table for large allocations */
+ tbl->poolsize = (tbl->it_size * 3 / 4) / tbl->nr_pools;
+
+ for (i = 0; i < tbl->nr_pools; i++) {
+ p = &tbl->pools[i];
+ spin_lock_init(&(p->lock));
+ p->start = tbl->poolsize * i;
+ p->hint = p->start;
+ p->end = p->start + tbl->poolsize;
+ }
+
+ p = &tbl->large_pool;
+ spin_lock_init(&(p->lock));
+ p->start = tbl->poolsize * i;
+ p->hint = p->start;
+ p->end = tbl->it_size;
iommu_table_clear(tbl);
@@ -526,7 +710,7 @@ struct iommu_table *iommu_init_table(struct iommu_table *tbl, int nid)
void iommu_free_table(struct iommu_table *tbl, const char *node_name)
{
- unsigned long bitmap_sz, i;
+ unsigned long bitmap_sz;
unsigned int order;
if (!tbl || !tbl->it_map) {
@@ -535,18 +719,26 @@ void iommu_free_table(struct iommu_table *tbl, const char *node_name)
return;
}
- /* verify that table contains no entries */
- /* it_size is in entries, and we're examining 64 at a time */
- for (i = 0; i < (tbl->it_size/64); i++) {
- if (tbl->it_map[i] != 0) {
- printk(KERN_WARNING "%s: Unexpected TCEs for %s\n",
- __func__, node_name);
- break;
- }
+ /*
+ * In case we have reserved the first bit, we should not emit
+ * the warning below.
+ */
+ if (tbl->it_offset == 0)
+ clear_bit(0, tbl->it_map);
+
+#ifdef CONFIG_IOMMU_API
+ if (tbl->it_group) {
+ iommu_group_put(tbl->it_group);
+ BUG_ON(tbl->it_group);
}
+#endif
+
+ /* verify that table contains no entries */
+ if (!bitmap_empty(tbl->it_map, tbl->it_size))
+ pr_warn("%s: Unexpected TCEs for %s\n", __func__, node_name);
/* calculate bitmap size in bytes */
- bitmap_sz = (tbl->it_size + 7) / 8;
+ bitmap_sz = BITS_TO_LONGS(tbl->it_size) * sizeof(unsigned long);
/* free bitmap */
order = get_order(bitmap_sz);
@@ -575,16 +767,16 @@ dma_addr_t iommu_map_page(struct device *dev, struct iommu_table *tbl,
vaddr = page_address(page) + offset;
uaddr = (unsigned long)vaddr;
- npages = iommu_num_pages(uaddr, size, IOMMU_PAGE_SIZE);
+ npages = iommu_num_pages(uaddr, size, IOMMU_PAGE_SIZE(tbl));
if (tbl) {
align = 0;
- if (IOMMU_PAGE_SHIFT < PAGE_SHIFT && size >= PAGE_SIZE &&
+ if (tbl->it_page_shift < PAGE_SHIFT && size >= PAGE_SIZE &&
((unsigned long)vaddr & ~PAGE_MASK) == 0)
- align = PAGE_SHIFT - IOMMU_PAGE_SHIFT;
+ align = PAGE_SHIFT - tbl->it_page_shift;
dma_handle = iommu_alloc(dev, tbl, vaddr, npages, direction,
- mask >> IOMMU_PAGE_SHIFT, align,
+ mask >> tbl->it_page_shift, align,
attrs);
if (dma_handle == DMA_ERROR_CODE) {
if (printk_ratelimit()) {
@@ -593,7 +785,7 @@ dma_addr_t iommu_map_page(struct device *dev, struct iommu_table *tbl,
npages);
}
} else
- dma_handle |= (uaddr & ~IOMMU_PAGE_MASK);
+ dma_handle |= (uaddr & ~IOMMU_PAGE_MASK(tbl));
}
return dma_handle;
@@ -608,7 +800,8 @@ void iommu_unmap_page(struct iommu_table *tbl, dma_addr_t dma_handle,
BUG_ON(direction == DMA_NONE);
if (tbl) {
- npages = iommu_num_pages(dma_handle, size, IOMMU_PAGE_SIZE);
+ npages = iommu_num_pages(dma_handle, size,
+ IOMMU_PAGE_SIZE(tbl));
iommu_free(tbl, dma_handle, npages);
}
}
@@ -652,10 +845,10 @@ void *iommu_alloc_coherent(struct device *dev, struct iommu_table *tbl,
memset(ret, 0, size);
/* Set up tces to cover the allocated range */
- nio_pages = size >> IOMMU_PAGE_SHIFT;
- io_order = get_iommu_order(size);
+ nio_pages = size >> tbl->it_page_shift;
+ io_order = get_iommu_order(size, tbl);
mapping = iommu_alloc(dev, tbl, ret, nio_pages, DMA_BIDIRECTIONAL,
- mask >> IOMMU_PAGE_SHIFT, io_order, NULL);
+ mask >> tbl->it_page_shift, io_order, NULL);
if (mapping == DMA_ERROR_CODE) {
free_pages((unsigned long)ret, order);
return NULL;
@@ -671,9 +864,311 @@ void iommu_free_coherent(struct iommu_table *tbl, size_t size,
unsigned int nio_pages;
size = PAGE_ALIGN(size);
- nio_pages = size >> IOMMU_PAGE_SHIFT;
+ nio_pages = size >> tbl->it_page_shift;
iommu_free(tbl, dma_handle, nio_pages);
size = PAGE_ALIGN(size);
free_pages((unsigned long)vaddr, get_order(size));
}
}
+
+#ifdef CONFIG_IOMMU_API
+/*
+ * SPAPR TCE API
+ */
+static void group_release(void *iommu_data)
+{
+ struct iommu_table *tbl = iommu_data;
+ tbl->it_group = NULL;
+}
+
+void iommu_register_group(struct iommu_table *tbl,
+ int pci_domain_number, unsigned long pe_num)
+{
+ struct iommu_group *grp;
+ char *name;
+
+ grp = iommu_group_alloc();
+ if (IS_ERR(grp)) {
+ pr_warn("powerpc iommu api: cannot create new group, err=%ld\n",
+ PTR_ERR(grp));
+ return;
+ }
+ tbl->it_group = grp;
+ iommu_group_set_iommudata(grp, tbl, group_release);
+ name = kasprintf(GFP_KERNEL, "domain%d-pe%lx",
+ pci_domain_number, pe_num);
+ if (!name)
+ return;
+ iommu_group_set_name(grp, name);
+ kfree(name);
+}
+
+enum dma_data_direction iommu_tce_direction(unsigned long tce)
+{
+ if ((tce & TCE_PCI_READ) && (tce & TCE_PCI_WRITE))
+ return DMA_BIDIRECTIONAL;
+ else if (tce & TCE_PCI_READ)
+ return DMA_TO_DEVICE;
+ else if (tce & TCE_PCI_WRITE)
+ return DMA_FROM_DEVICE;
+ else
+ return DMA_NONE;
+}
+EXPORT_SYMBOL_GPL(iommu_tce_direction);
+
+void iommu_flush_tce(struct iommu_table *tbl)
+{
+ /* Flush/invalidate TLB caches if necessary */
+ if (ppc_md.tce_flush)
+ ppc_md.tce_flush(tbl);
+
+ /* Make sure updates are seen by hardware */
+ mb();
+}
+EXPORT_SYMBOL_GPL(iommu_flush_tce);
+
+int iommu_tce_clear_param_check(struct iommu_table *tbl,
+ unsigned long ioba, unsigned long tce_value,
+ unsigned long npages)
+{
+ /* ppc_md.tce_free() does not support any value but 0 */
+ if (tce_value)
+ return -EINVAL;
+
+ if (ioba & ~IOMMU_PAGE_MASK(tbl))
+ return -EINVAL;
+
+ ioba >>= tbl->it_page_shift;
+ if (ioba < tbl->it_offset)
+ return -EINVAL;
+
+ if ((ioba + npages) > (tbl->it_offset + tbl->it_size))
+ return -EINVAL;
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(iommu_tce_clear_param_check);
+
+int iommu_tce_put_param_check(struct iommu_table *tbl,
+ unsigned long ioba, unsigned long tce)
+{
+ if (!(tce & (TCE_PCI_WRITE | TCE_PCI_READ)))
+ return -EINVAL;
+
+ if (tce & ~(IOMMU_PAGE_MASK(tbl) | TCE_PCI_WRITE | TCE_PCI_READ))
+ return -EINVAL;
+
+ if (ioba & ~IOMMU_PAGE_MASK(tbl))
+ return -EINVAL;
+
+ ioba >>= tbl->it_page_shift;
+ if (ioba < tbl->it_offset)
+ return -EINVAL;
+
+ if ((ioba + 1) > (tbl->it_offset + tbl->it_size))
+ return -EINVAL;
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(iommu_tce_put_param_check);
+
+unsigned long iommu_clear_tce(struct iommu_table *tbl, unsigned long entry)
+{
+ unsigned long oldtce;
+ struct iommu_pool *pool = get_pool(tbl, entry);
+
+ spin_lock(&(pool->lock));
+
+ oldtce = ppc_md.tce_get(tbl, entry);
+ if (oldtce & (TCE_PCI_WRITE | TCE_PCI_READ))
+ ppc_md.tce_free(tbl, entry, 1);
+ else
+ oldtce = 0;
+
+ spin_unlock(&(pool->lock));
+
+ return oldtce;
+}
+EXPORT_SYMBOL_GPL(iommu_clear_tce);
+
+int iommu_clear_tces_and_put_pages(struct iommu_table *tbl,
+ unsigned long entry, unsigned long pages)
+{
+ unsigned long oldtce;
+ struct page *page;
+
+ for ( ; pages; --pages, ++entry) {
+ oldtce = iommu_clear_tce(tbl, entry);
+ if (!oldtce)
+ continue;
+
+ page = pfn_to_page(oldtce >> PAGE_SHIFT);
+ WARN_ON(!page);
+ if (page) {
+ if (oldtce & TCE_PCI_WRITE)
+ SetPageDirty(page);
+ put_page(page);
+ }
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(iommu_clear_tces_and_put_pages);
+
+/*
+ * hwaddr is a kernel virtual address here (0xc... bazillion),
+ * tce_build converts it to a physical address.
+ */
+int iommu_tce_build(struct iommu_table *tbl, unsigned long entry,
+ unsigned long hwaddr, enum dma_data_direction direction)
+{
+ int ret = -EBUSY;
+ unsigned long oldtce;
+ struct iommu_pool *pool = get_pool(tbl, entry);
+
+ spin_lock(&(pool->lock));
+
+ oldtce = ppc_md.tce_get(tbl, entry);
+ /* Add new entry if it is not busy */
+ if (!(oldtce & (TCE_PCI_WRITE | TCE_PCI_READ)))
+ ret = ppc_md.tce_build(tbl, entry, 1, hwaddr, direction, NULL);
+
+ spin_unlock(&(pool->lock));
+
+ /* if (unlikely(ret))
+ pr_err("iommu_tce: %s failed on hwaddr=%lx ioba=%lx kva=%lx ret=%d\n",
+ __func__, hwaddr, entry << IOMMU_PAGE_SHIFT(tbl),
+ hwaddr, ret); */
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(iommu_tce_build);
+
+int iommu_put_tce_user_mode(struct iommu_table *tbl, unsigned long entry,
+ unsigned long tce)
+{
+ int ret;
+ struct page *page = NULL;
+ unsigned long hwaddr, offset = tce & IOMMU_PAGE_MASK(tbl) & ~PAGE_MASK;
+ enum dma_data_direction direction = iommu_tce_direction(tce);
+
+ ret = get_user_pages_fast(tce & PAGE_MASK, 1,
+ direction != DMA_TO_DEVICE, &page);
+ if (unlikely(ret != 1)) {
+ /* pr_err("iommu_tce: get_user_pages_fast failed tce=%lx ioba=%lx ret=%d\n",
+ tce, entry << IOMMU_PAGE_SHIFT(tbl), ret); */
+ return -EFAULT;
+ }
+ hwaddr = (unsigned long) page_address(page) + offset;
+
+ ret = iommu_tce_build(tbl, entry, hwaddr, direction);
+ if (ret)
+ put_page(page);
+
+ if (ret < 0)
+ pr_err("iommu_tce: %s failed ioba=%lx, tce=%lx, ret=%d\n",
+ __func__, entry << tbl->it_page_shift, tce, ret);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(iommu_put_tce_user_mode);
+
+int iommu_take_ownership(struct iommu_table *tbl)
+{
+ unsigned long sz = (tbl->it_size + 7) >> 3;
+
+ if (tbl->it_offset == 0)
+ clear_bit(0, tbl->it_map);
+
+ if (!bitmap_empty(tbl->it_map, tbl->it_size)) {
+ pr_err("iommu_tce: it_map is not empty");
+ return -EBUSY;
+ }
+
+ memset(tbl->it_map, 0xff, sz);
+ iommu_clear_tces_and_put_pages(tbl, tbl->it_offset, tbl->it_size);
+
+ /*
+ * Disable iommu bypass, otherwise the user can DMA to all of
+ * our physical memory via the bypass window instead of just
+ * the pages that has been explicitly mapped into the iommu
+ */
+ if (tbl->set_bypass)
+ tbl->set_bypass(tbl, false);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(iommu_take_ownership);
+
+void iommu_release_ownership(struct iommu_table *tbl)
+{
+ unsigned long sz = (tbl->it_size + 7) >> 3;
+
+ iommu_clear_tces_and_put_pages(tbl, tbl->it_offset, tbl->it_size);
+ memset(tbl->it_map, 0, sz);
+
+ /* Restore bit#0 set by iommu_init_table() */
+ if (tbl->it_offset == 0)
+ set_bit(0, tbl->it_map);
+
+ /* The kernel owns the device now, we can restore the iommu bypass */
+ if (tbl->set_bypass)
+ tbl->set_bypass(tbl, true);
+}
+EXPORT_SYMBOL_GPL(iommu_release_ownership);
+
+int iommu_add_device(struct device *dev)
+{
+ struct iommu_table *tbl;
+ int ret = 0;
+
+ if (WARN_ON(dev->iommu_group)) {
+ pr_warn("iommu_tce: device %s is already in iommu group %d, skipping\n",
+ dev_name(dev),
+ iommu_group_id(dev->iommu_group));
+ return -EBUSY;
+ }
+
+ tbl = get_iommu_table_base(dev);
+ if (!tbl || !tbl->it_group) {
+ pr_debug("iommu_tce: skipping device %s with no tbl\n",
+ dev_name(dev));
+ return 0;
+ }
+
+ pr_debug("iommu_tce: adding %s to iommu group %d\n",
+ dev_name(dev), iommu_group_id(tbl->it_group));
+
+ if (PAGE_SIZE < IOMMU_PAGE_SIZE(tbl)) {
+ pr_err("iommu_tce: unsupported iommu page size.");
+ pr_err("%s has not been added\n", dev_name(dev));
+ return -EINVAL;
+ }
+
+ ret = iommu_group_add_device(tbl->it_group, dev);
+ if (ret < 0)
+ pr_err("iommu_tce: %s has not been added, ret=%d\n",
+ dev_name(dev), ret);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(iommu_add_device);
+
+void iommu_del_device(struct device *dev)
+{
+ /*
+ * Some devices might not have IOMMU table and group
+ * and we needn't detach them from the associated
+ * IOMMU groups
+ */
+ if (!dev->iommu_group) {
+ pr_debug("iommu_tce: skipping device %s with no tbl\n",
+ dev_name(dev));
+ return;
+ }
+
+ iommu_group_remove_device(dev);
+}
+EXPORT_SYMBOL_GPL(iommu_del_device);
+
+#endif /* CONFIG_IOMMU_API */
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 701d4aceb4f..248ee7e5beb 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -57,7 +57,6 @@
#include <linux/of_irq.h>
#include <asm/uaccess.h>
-#include <asm/system.h>
#include <asm/io.h>
#include <asm/pgtable.h>
#include <asm/irq.h>
@@ -67,6 +66,7 @@
#include <asm/machdep.h>
#include <asm/udbg.h>
#include <asm/smp.h>
+#include <asm/debug.h>
#ifdef CONFIG_PPC64
#include <asm/paca.h>
@@ -93,20 +93,16 @@ extern int tau_interrupts(int);
#ifdef CONFIG_PPC64
-#ifndef CONFIG_SPARSE_IRQ
-EXPORT_SYMBOL(irq_desc);
-#endif
-
int distribute_irqs = 1;
-static inline notrace unsigned long get_hard_enabled(void)
+static inline notrace unsigned long get_irq_happened(void)
{
- unsigned long enabled;
+ unsigned long happened;
__asm__ __volatile__("lbz %0,%1(13)"
- : "=r" (enabled) : "i" (offsetof(struct paca_struct, hard_enabled)));
+ : "=r" (happened) : "i" (offsetof(struct paca_struct, irq_happened)));
- return enabled;
+ return happened;
}
static inline notrace void set_soft_enabled(unsigned long enable)
@@ -115,84 +111,232 @@ static inline notrace void set_soft_enabled(unsigned long enable)
: : "r" (enable), "i" (offsetof(struct paca_struct, soft_enabled)));
}
-static inline notrace void decrementer_check_overflow(void)
+static inline notrace int decrementer_check_overflow(void)
{
- u64 now = get_tb_or_rtc();
- u64 *next_tb = &__get_cpu_var(decrementers_next_tb);
-
- if (now >= *next_tb)
- set_dec(1);
+ u64 now = get_tb_or_rtc();
+ u64 *next_tb = &__get_cpu_var(decrementers_next_tb);
+
+ return now >= *next_tb;
}
-notrace void arch_local_irq_restore(unsigned long en)
+/* This is called whenever we are re-enabling interrupts
+ * and returns either 0 (nothing to do) or 500/900/280/a00/e80 if
+ * there's an EE, DEC or DBELL to generate.
+ *
+ * This is called in two contexts: From arch_local_irq_restore()
+ * before soft-enabling interrupts, and from the exception exit
+ * path when returning from an interrupt from a soft-disabled to
+ * a soft enabled context. In both case we have interrupts hard
+ * disabled.
+ *
+ * We take care of only clearing the bits we handled in the
+ * PACA irq_happened field since we can only re-emit one at a
+ * time and we don't want to "lose" one.
+ */
+notrace unsigned int __check_irq_replay(void)
{
/*
- * get_paca()->soft_enabled = en;
- * Is it ever valid to use local_irq_restore(0) when soft_enabled is 1?
- * That was allowed before, and in such a case we do need to take care
- * that gcc will set soft_enabled directly via r13, not choose to use
- * an intermediate register, lest we're preempted to a different cpu.
+ * We use local_paca rather than get_paca() to avoid all
+ * the debug_smp_processor_id() business in this low level
+ * function
+ */
+ unsigned char happened = local_paca->irq_happened;
+
+ /* Clear bit 0 which we wouldn't clear otherwise */
+ local_paca->irq_happened &= ~PACA_IRQ_HARD_DIS;
+
+ /*
+ * Force the delivery of pending soft-disabled interrupts on PS3.
+ * Any HV call will have this side effect.
+ */
+ if (firmware_has_feature(FW_FEATURE_PS3_LV1)) {
+ u64 tmp, tmp2;
+ lv1_get_version_info(&tmp, &tmp2);
+ }
+
+ /*
+ * We may have missed a decrementer interrupt. We check the
+ * decrementer itself rather than the paca irq_happened field
+ * in case we also had a rollover while hard disabled
+ */
+ local_paca->irq_happened &= ~PACA_IRQ_DEC;
+ if ((happened & PACA_IRQ_DEC) || decrementer_check_overflow())
+ return 0x900;
+
+ /* Finally check if an external interrupt happened */
+ local_paca->irq_happened &= ~PACA_IRQ_EE;
+ if (happened & PACA_IRQ_EE)
+ return 0x500;
+
+#ifdef CONFIG_PPC_BOOK3E
+ /* Finally check if an EPR external interrupt happened
+ * this bit is typically set if we need to handle another
+ * "edge" interrupt from within the MPIC "EPR" handler
*/
+ local_paca->irq_happened &= ~PACA_IRQ_EE_EDGE;
+ if (happened & PACA_IRQ_EE_EDGE)
+ return 0x500;
+
+ local_paca->irq_happened &= ~PACA_IRQ_DBELL;
+ if (happened & PACA_IRQ_DBELL)
+ return 0x280;
+#else
+ local_paca->irq_happened &= ~PACA_IRQ_DBELL;
+ if (happened & PACA_IRQ_DBELL) {
+ if (cpu_has_feature(CPU_FTR_HVMODE))
+ return 0xe80;
+ return 0xa00;
+ }
+#endif /* CONFIG_PPC_BOOK3E */
+
+ /* There should be nothing left ! */
+ BUG_ON(local_paca->irq_happened != 0);
+
+ return 0;
+}
+
+notrace void arch_local_irq_restore(unsigned long en)
+{
+ unsigned char irq_happened;
+ unsigned int replay;
+
+ /* Write the new soft-enabled value */
set_soft_enabled(en);
if (!en)
return;
+ /*
+ * From this point onward, we can take interrupts, preempt,
+ * etc... unless we got hard-disabled. We check if an event
+ * happened. If none happened, we know we can just return.
+ *
+ * We may have preempted before the check below, in which case
+ * we are checking the "new" CPU instead of the old one. This
+ * is only a problem if an event happened on the "old" CPU.
+ *
+ * External interrupt events will have caused interrupts to
+ * be hard-disabled, so there is no problem, we
+ * cannot have preempted.
+ */
+ irq_happened = get_irq_happened();
+ if (!irq_happened)
+ return;
-#ifdef CONFIG_PPC_STD_MMU_64
- if (firmware_has_feature(FW_FEATURE_ISERIES)) {
+ /*
+ * We need to hard disable to get a trusted value from
+ * __check_irq_replay(). We also need to soft-disable
+ * again to avoid warnings in there due to the use of
+ * per-cpu variables.
+ *
+ * We know that if the value in irq_happened is exactly 0x01
+ * then we are already hard disabled (there are other less
+ * common cases that we'll ignore for now), so we skip the
+ * (expensive) mtmsrd.
+ */
+ if (unlikely(irq_happened != PACA_IRQ_HARD_DIS))
+ __hard_irq_disable();
+#ifdef CONFIG_TRACE_IRQFLAGS
+ else {
/*
- * Do we need to disable preemption here? Not really: in the
- * unlikely event that we're preempted to a different cpu in
- * between getting r13, loading its lppaca_ptr, and loading
- * its any_int, we might call iseries_handle_interrupts without
- * an interrupt pending on the new cpu, but that's no disaster,
- * is it? And the business of preempting us off the old cpu
- * would itself involve a local_irq_restore which handles the
- * interrupt to that cpu.
- *
- * But use "local_paca->lppaca_ptr" instead of "get_lppaca()"
- * to avoid any preemption checking added into get_paca().
+ * We should already be hard disabled here. We had bugs
+ * where that wasn't the case so let's dbl check it and
+ * warn if we are wrong. Only do that when IRQ tracing
+ * is enabled as mfmsr() can be costly.
*/
- if (local_paca->lppaca_ptr->int_dword.any_int)
- iseries_handle_interrupts();
+ if (WARN_ON(mfmsr() & MSR_EE))
+ __hard_irq_disable();
}
-#endif /* CONFIG_PPC_STD_MMU_64 */
+#endif /* CONFIG_TRACE_IRQFLAG */
+
+ set_soft_enabled(0);
+
+ /*
+ * Check if anything needs to be re-emitted. We haven't
+ * soft-enabled yet to avoid warnings in decrementer_check_overflow
+ * accessing per-cpu variables
+ */
+ replay = __check_irq_replay();
+
+ /* We can soft-enable now */
+ set_soft_enabled(1);
/*
- * if (get_paca()->hard_enabled) return;
- * But again we need to take care that gcc gets hard_enabled directly
- * via r13, not choose to use an intermediate register, lest we're
- * preempted to a different cpu in between the two instructions.
+ * And replay if we have to. This will return with interrupts
+ * hard-enabled.
*/
- if (get_hard_enabled())
+ if (replay) {
+ __replay_interrupt(replay);
return;
+ }
+
+ /* Finally, let's ensure we are hard enabled */
+ __hard_irq_enable();
+}
+EXPORT_SYMBOL(arch_local_irq_restore);
+/*
+ * This is specifically called by assembly code to re-enable interrupts
+ * if they are currently disabled. This is typically called before
+ * schedule() or do_signal() when returning to userspace. We do it
+ * in C to avoid the burden of dealing with lockdep etc...
+ *
+ * NOTE: This is called with interrupts hard disabled but not marked
+ * as such in paca->irq_happened, so we need to resync this.
+ */
+void notrace restore_interrupts(void)
+{
+ if (irqs_disabled()) {
+ local_paca->irq_happened |= PACA_IRQ_HARD_DIS;
+ local_irq_enable();
+ } else
+ __hard_irq_enable();
+}
+
+/*
+ * This is a helper to use when about to go into idle low-power
+ * when the latter has the side effect of re-enabling interrupts
+ * (such as calling H_CEDE under pHyp).
+ *
+ * You call this function with interrupts soft-disabled (this is
+ * already the case when ppc_md.power_save is called). The function
+ * will return whether to enter power save or just return.
+ *
+ * In the former case, it will have notified lockdep of interrupts
+ * being re-enabled and generally sanitized the lazy irq state,
+ * and in the latter case it will leave with interrupts hard
+ * disabled and marked as such, so the local_irq_enable() call
+ * in arch_cpu_idle() will properly re-enable everything.
+ */
+bool prep_irq_for_idle(void)
+{
/*
- * Need to hard-enable interrupts here. Since currently disabled,
- * no need to take further asm precautions against preemption; but
- * use local_paca instead of get_paca() to avoid preemption checking.
+ * First we need to hard disable to ensure no interrupt
+ * occurs before we effectively enter the low power state
*/
- local_paca->hard_enabled = en;
+ hard_irq_disable();
/*
- * Trigger the decrementer if we have a pending event. Some processors
- * only trigger on edge transitions of the sign bit. We might also
- * have disabled interrupts long enough that the decrementer wrapped
- * to positive.
+ * If anything happened while we were soft-disabled,
+ * we return now and do not enter the low power state.
*/
- decrementer_check_overflow();
+ if (lazy_irq_pending())
+ return false;
+
+ /* Tell lockdep we are about to re-enable */
+ trace_hardirqs_on();
/*
- * Force the delivery of pending soft-disabled interrupts on PS3.
- * Any HV call will have this side effect.
+ * Mark interrupts as soft-enabled and clear the
+ * PACA_IRQ_HARD_DIS from the pending mask since we
+ * are about to hard enable as well as a side effect
+ * of entering the low power state.
*/
- if (firmware_has_feature(FW_FEATURE_PS3_LV1)) {
- u64 tmp, tmp2;
- lv1_get_version_info(&tmp, &tmp2);
- }
+ local_paca->irq_happened &= ~PACA_IRQ_HARD_DIS;
+ local_paca->soft_enabled = 1;
- __hard_irq_enable();
+ /* Tell the caller to enter the low power state */
+ return true;
}
-EXPORT_SYMBOL(arch_local_irq_restore);
+
#endif /* CONFIG_PPC64 */
int arch_show_interrupts(struct seq_file *p, int prec)
@@ -210,15 +354,20 @@ int arch_show_interrupts(struct seq_file *p, int prec)
seq_printf(p, "%*s: ", prec, "LOC");
for_each_online_cpu(j)
- seq_printf(p, "%10u ", per_cpu(irq_stat, j).timer_irqs);
- seq_printf(p, " Local timer interrupts\n");
+ seq_printf(p, "%10u ", per_cpu(irq_stat, j).timer_irqs_event);
+ seq_printf(p, " Local timer interrupts for timer event device\n");
+
+ seq_printf(p, "%*s: ", prec, "LOC");
+ for_each_online_cpu(j)
+ seq_printf(p, "%10u ", per_cpu(irq_stat, j).timer_irqs_others);
+ seq_printf(p, " Local timer interrupts for others\n");
seq_printf(p, "%*s: ", prec, "SPU");
for_each_online_cpu(j)
seq_printf(p, "%10u ", per_cpu(irq_stat, j).spurious_irqs);
seq_printf(p, " Spurious interrupts\n");
- seq_printf(p, "%*s: ", prec, "CNT");
+ seq_printf(p, "%*s: ", prec, "PMI");
for_each_online_cpu(j)
seq_printf(p, "%10u ", per_cpu(irq_stat, j).pmu_irqs);
seq_printf(p, " Performance monitoring interrupts\n");
@@ -228,6 +377,15 @@ int arch_show_interrupts(struct seq_file *p, int prec)
seq_printf(p, "%10u ", per_cpu(irq_stat, j).mce_exceptions);
seq_printf(p, " Machine check exceptions\n");
+#ifdef CONFIG_PPC_DOORBELL
+ if (cpu_has_feature(CPU_FTR_DBELL)) {
+ seq_printf(p, "%*s: ", prec, "DBL");
+ for_each_online_cpu(j)
+ seq_printf(p, "%10u ", per_cpu(irq_stat, j).doorbell_irqs);
+ seq_printf(p, " Doorbell interrupts\n");
+ }
+#endif
+
return 0;
}
@@ -236,11 +394,15 @@ int arch_show_interrupts(struct seq_file *p, int prec)
*/
u64 arch_irq_stat_cpu(unsigned int cpu)
{
- u64 sum = per_cpu(irq_stat, cpu).timer_irqs;
+ u64 sum = per_cpu(irq_stat, cpu).timer_irqs_event;
sum += per_cpu(irq_stat, cpu).pmu_irqs;
sum += per_cpu(irq_stat, cpu).mce_exceptions;
sum += per_cpu(irq_stat, cpu).spurious_irqs;
+ sum += per_cpu(irq_stat, cpu).timer_irqs_others;
+#ifdef CONFIG_PPC_DOORBELL
+ sum += per_cpu(irq_stat, cpu).doorbell_irqs;
+#endif
return sum;
}
@@ -256,14 +418,10 @@ void migrate_irqs(void)
alloc_cpumask_var(&mask, GFP_KERNEL);
- for_each_irq(irq) {
+ for_each_irq_desc(irq, desc) {
struct irq_data *data;
struct irq_chip *chip;
- desc = irq_to_desc(irq);
- if (!desc)
- continue;
-
data = irq_desc_get_irq_data(desc);
if (irqd_is_per_cpu(data))
continue;
@@ -289,50 +447,6 @@ void migrate_irqs(void)
}
#endif
-static inline void handle_one_irq(unsigned int irq)
-{
- struct thread_info *curtp, *irqtp;
- unsigned long saved_sp_limit;
- struct irq_desc *desc;
-
- desc = irq_to_desc(irq);
- if (!desc)
- return;
-
- /* Switch to the irq stack to handle this */
- curtp = current_thread_info();
- irqtp = hardirq_ctx[smp_processor_id()];
-
- if (curtp == irqtp) {
- /* We're already on the irq stack, just handle it */
- desc->handle_irq(irq, desc);
- return;
- }
-
- saved_sp_limit = current->thread.ksp_limit;
-
- irqtp->task = curtp->task;
- irqtp->flags = 0;
-
- /* Copy the softirq bits in preempt_count so that the
- * softirq checks work in the hardirq context. */
- irqtp->preempt_count = (irqtp->preempt_count & ~SOFTIRQ_MASK) |
- (curtp->preempt_count & SOFTIRQ_MASK);
-
- current->thread.ksp_limit = (unsigned long)irqtp +
- _ALIGN_UP(sizeof(struct thread_info), 16);
-
- call_handle_irq(irq, desc, irqtp, desc->handle_irq);
- current->thread.ksp_limit = saved_sp_limit;
- irqtp->task = NULL;
-
- /* Set any flag that may have been set on the
- * alternate stack
- */
- if (irqtp->flags)
- set_bits(irqtp->flags, &curtp->flags);
-}
-
static inline void check_stack_overflow(void)
{
#ifdef CONFIG_DEBUG_STACKOVERFLOW
@@ -349,37 +463,72 @@ static inline void check_stack_overflow(void)
#endif
}
-void do_IRQ(struct pt_regs *regs)
+void __do_irq(struct pt_regs *regs)
{
- struct pt_regs *old_regs = set_irq_regs(regs);
unsigned int irq;
- trace_irq_entry(regs);
-
irq_enter();
+ trace_irq_entry(regs);
+
check_stack_overflow();
+ /*
+ * Query the platform PIC for the interrupt & ack it.
+ *
+ * This will typically lower the interrupt line to the CPU
+ */
irq = ppc_md.get_irq();
- if (irq != NO_IRQ && irq != NO_IRQ_IGNORE)
- handle_one_irq(irq);
- else if (irq != NO_IRQ_IGNORE)
+ /* We can hard enable interrupts now to allow perf interrupts */
+ may_hard_irq_enable();
+
+ /* And finally process it */
+ if (unlikely(irq == NO_IRQ))
__get_cpu_var(irq_stat).spurious_irqs++;
+ else
+ generic_handle_irq(irq);
+
+ trace_irq_exit(regs);
irq_exit();
- set_irq_regs(old_regs);
+}
+
+void do_IRQ(struct pt_regs *regs)
+{
+ struct pt_regs *old_regs = set_irq_regs(regs);
+ struct thread_info *curtp, *irqtp, *sirqtp;
-#ifdef CONFIG_PPC_ISERIES
- if (firmware_has_feature(FW_FEATURE_ISERIES) &&
- get_lppaca()->int_dword.fields.decr_int) {
- get_lppaca()->int_dword.fields.decr_int = 0;
- /* Signal a fake decrementer interrupt */
- timer_interrupt(regs);
+ /* Switch to the irq stack to handle this */
+ curtp = current_thread_info();
+ irqtp = hardirq_ctx[raw_smp_processor_id()];
+ sirqtp = softirq_ctx[raw_smp_processor_id()];
+
+ /* Already there ? */
+ if (unlikely(curtp == irqtp || curtp == sirqtp)) {
+ __do_irq(regs);
+ set_irq_regs(old_regs);
+ return;
}
-#endif
- trace_irq_exit(regs);
+ /* Prepare the thread_info in the irq stack */
+ irqtp->task = curtp->task;
+ irqtp->flags = 0;
+
+ /* Copy the preempt_count so that the [soft]irq checks work. */
+ irqtp->preempt_count = curtp->preempt_count;
+
+ /* Switch stack and call */
+ call_do_irq(regs, irqtp);
+
+ /* Restore stack limit */
+ irqtp->task = NULL;
+
+ /* Copy back updates to the thread_info */
+ if (irqtp->flags)
+ set_bits(irqtp->flags, &curtp->flags);
+
+ set_irq_regs(old_regs);
}
void __init init_IRQ(void)
@@ -406,8 +555,13 @@ void exc_lvl_ctx_init(void)
#ifdef CONFIG_PPC64
cpu_nr = i;
#else
+#ifdef CONFIG_SMP
cpu_nr = get_hard_smp_processor_id(i);
+#else
+ cpu_nr = 0;
+#endif
#endif
+
memset((void *)critirq_ctx[cpu_nr], 0, THREAD_SIZE);
tp = critirq_ctx[cpu_nr];
tp->cpu = cpu_nr;
@@ -440,28 +594,22 @@ void irq_ctx_init(void)
memset((void *)softirq_ctx[i], 0, THREAD_SIZE);
tp = softirq_ctx[i];
tp->cpu = i;
- tp->preempt_count = 0;
memset((void *)hardirq_ctx[i], 0, THREAD_SIZE);
tp = hardirq_ctx[i];
tp->cpu = i;
- tp->preempt_count = HARDIRQ_OFFSET;
}
}
-static inline void do_softirq_onstack(void)
+void do_softirq_own_stack(void)
{
struct thread_info *curtp, *irqtp;
- unsigned long saved_sp_limit = current->thread.ksp_limit;
curtp = current_thread_info();
irqtp = softirq_ctx[smp_processor_id()];
irqtp->task = curtp->task;
irqtp->flags = 0;
- current->thread.ksp_limit = (unsigned long)irqtp +
- _ALIGN_UP(sizeof(struct thread_info), 16);
call_do_softirq(irqtp);
- current->thread.ksp_limit = saved_sp_limit;
irqtp->task = NULL;
/* Set any flag that may have been set on the
@@ -471,430 +619,19 @@ static inline void do_softirq_onstack(void)
set_bits(irqtp->flags, &curtp->flags);
}
-void do_softirq(void)
-{
- unsigned long flags;
-
- if (in_interrupt())
- return;
-
- local_irq_save(flags);
-
- if (local_softirq_pending())
- do_softirq_onstack();
-
- local_irq_restore(flags);
-}
-
-
-/*
- * IRQ controller and virtual interrupts
- */
-
-/* The main irq map itself is an array of NR_IRQ entries containing the
- * associate host and irq number. An entry with a host of NULL is free.
- * An entry can be allocated if it's free, the allocator always then sets
- * hwirq first to the host's invalid irq number and then fills ops.
- */
-struct irq_map_entry {
- irq_hw_number_t hwirq;
- struct irq_host *host;
-};
-
-static LIST_HEAD(irq_hosts);
-static DEFINE_RAW_SPINLOCK(irq_big_lock);
-static DEFINE_MUTEX(revmap_trees_mutex);
-static struct irq_map_entry irq_map[NR_IRQS];
-static unsigned int irq_virq_count = NR_IRQS;
-static struct irq_host *irq_default_host;
-
-irq_hw_number_t irqd_to_hwirq(struct irq_data *d)
-{
- return irq_map[d->irq].hwirq;
-}
-EXPORT_SYMBOL_GPL(irqd_to_hwirq);
-
irq_hw_number_t virq_to_hw(unsigned int virq)
{
- return irq_map[virq].hwirq;
+ struct irq_data *irq_data = irq_get_irq_data(virq);
+ return WARN_ON(!irq_data) ? 0 : irq_data->hwirq;
}
EXPORT_SYMBOL_GPL(virq_to_hw);
-bool virq_is_host(unsigned int virq, struct irq_host *host)
-{
- return irq_map[virq].host == host;
-}
-EXPORT_SYMBOL_GPL(virq_is_host);
-
-static int default_irq_host_match(struct irq_host *h, struct device_node *np)
-{
- return h->of_node != NULL && h->of_node == np;
-}
-
-struct irq_host *irq_alloc_host(struct device_node *of_node,
- unsigned int revmap_type,
- unsigned int revmap_arg,
- struct irq_host_ops *ops,
- irq_hw_number_t inval_irq)
-{
- struct irq_host *host;
- unsigned int size = sizeof(struct irq_host);
- unsigned int i;
- unsigned int *rmap;
- unsigned long flags;
-
- /* Allocate structure and revmap table if using linear mapping */
- if (revmap_type == IRQ_HOST_MAP_LINEAR)
- size += revmap_arg * sizeof(unsigned int);
- host = kzalloc(size, GFP_KERNEL);
- if (host == NULL)
- return NULL;
-
- /* Fill structure */
- host->revmap_type = revmap_type;
- host->inval_irq = inval_irq;
- host->ops = ops;
- host->of_node = of_node_get(of_node);
-
- if (host->ops->match == NULL)
- host->ops->match = default_irq_host_match;
-
- raw_spin_lock_irqsave(&irq_big_lock, flags);
-
- /* If it's a legacy controller, check for duplicates and
- * mark it as allocated (we use irq 0 host pointer for that
- */
- if (revmap_type == IRQ_HOST_MAP_LEGACY) {
- if (irq_map[0].host != NULL) {
- raw_spin_unlock_irqrestore(&irq_big_lock, flags);
- of_node_put(host->of_node);
- kfree(host);
- return NULL;
- }
- irq_map[0].host = host;
- }
-
- list_add(&host->link, &irq_hosts);
- raw_spin_unlock_irqrestore(&irq_big_lock, flags);
-
- /* Additional setups per revmap type */
- switch(revmap_type) {
- case IRQ_HOST_MAP_LEGACY:
- /* 0 is always the invalid number for legacy */
- host->inval_irq = 0;
- /* setup us as the host for all legacy interrupts */
- for (i = 1; i < NUM_ISA_INTERRUPTS; i++) {
- irq_map[i].hwirq = i;
- smp_wmb();
- irq_map[i].host = host;
- smp_wmb();
-
- /* Legacy flags are left to default at this point,
- * one can then use irq_create_mapping() to
- * explicitly change them
- */
- ops->map(host, i, i);
-
- /* Clear norequest flags */
- irq_clear_status_flags(i, IRQ_NOREQUEST);
- }
- break;
- case IRQ_HOST_MAP_LINEAR:
- rmap = (unsigned int *)(host + 1);
- for (i = 0; i < revmap_arg; i++)
- rmap[i] = NO_IRQ;
- host->revmap_data.linear.size = revmap_arg;
- smp_wmb();
- host->revmap_data.linear.revmap = rmap;
- break;
- case IRQ_HOST_MAP_TREE:
- INIT_RADIX_TREE(&host->revmap_data.tree, GFP_KERNEL);
- break;
- default:
- break;
- }
-
- pr_debug("irq: Allocated host of type %d @0x%p\n", revmap_type, host);
-
- return host;
-}
-
-struct irq_host *irq_find_host(struct device_node *node)
-{
- struct irq_host *h, *found = NULL;
- unsigned long flags;
-
- /* We might want to match the legacy controller last since
- * it might potentially be set to match all interrupts in
- * the absence of a device node. This isn't a problem so far
- * yet though...
- */
- raw_spin_lock_irqsave(&irq_big_lock, flags);
- list_for_each_entry(h, &irq_hosts, link)
- if (h->ops->match(h, node)) {
- found = h;
- break;
- }
- raw_spin_unlock_irqrestore(&irq_big_lock, flags);
- return found;
-}
-EXPORT_SYMBOL_GPL(irq_find_host);
-
-void irq_set_default_host(struct irq_host *host)
-{
- pr_debug("irq: Default host set to @0x%p\n", host);
-
- irq_default_host = host;
-}
-
-void irq_set_virq_count(unsigned int count)
-{
- pr_debug("irq: Trying to set virq count to %d\n", count);
-
- BUG_ON(count < NUM_ISA_INTERRUPTS);
- if (count < NR_IRQS)
- irq_virq_count = count;
-}
-
-static int irq_setup_virq(struct irq_host *host, unsigned int virq,
- irq_hw_number_t hwirq)
-{
- int res;
-
- res = irq_alloc_desc_at(virq, 0);
- if (res != virq) {
- pr_debug("irq: -> allocating desc failed\n");
- goto error;
- }
-
- /* map it */
- smp_wmb();
- irq_map[virq].hwirq = hwirq;
- smp_mb();
-
- if (host->ops->map(host, virq, hwirq)) {
- pr_debug("irq: -> mapping failed, freeing\n");
- goto errdesc;
- }
-
- irq_clear_status_flags(virq, IRQ_NOREQUEST);
-
- return 0;
-
-errdesc:
- irq_free_descs(virq, 1);
-error:
- irq_free_virt(virq, 1);
- return -1;
-}
-
-unsigned int irq_create_direct_mapping(struct irq_host *host)
-{
- unsigned int virq;
-
- if (host == NULL)
- host = irq_default_host;
-
- BUG_ON(host == NULL);
- WARN_ON(host->revmap_type != IRQ_HOST_MAP_NOMAP);
-
- virq = irq_alloc_virt(host, 1, 0);
- if (virq == NO_IRQ) {
- pr_debug("irq: create_direct virq allocation failed\n");
- return NO_IRQ;
- }
-
- pr_debug("irq: create_direct obtained virq %d\n", virq);
-
- if (irq_setup_virq(host, virq, virq))
- return NO_IRQ;
-
- return virq;
-}
-
-unsigned int irq_create_mapping(struct irq_host *host,
- irq_hw_number_t hwirq)
-{
- unsigned int virq, hint;
-
- pr_debug("irq: irq_create_mapping(0x%p, 0x%lx)\n", host, hwirq);
-
- /* Look for default host if nececssary */
- if (host == NULL)
- host = irq_default_host;
- if (host == NULL) {
- printk(KERN_WARNING "irq_create_mapping called for"
- " NULL host, hwirq=%lx\n", hwirq);
- WARN_ON(1);
- return NO_IRQ;
- }
- pr_debug("irq: -> using host @%p\n", host);
-
- /* Check if mapping already exists */
- virq = irq_find_mapping(host, hwirq);
- if (virq != NO_IRQ) {
- pr_debug("irq: -> existing mapping on virq %d\n", virq);
- return virq;
- }
-
- /* Get a virtual interrupt number */
- if (host->revmap_type == IRQ_HOST_MAP_LEGACY) {
- /* Handle legacy */
- virq = (unsigned int)hwirq;
- if (virq == 0 || virq >= NUM_ISA_INTERRUPTS)
- return NO_IRQ;
- return virq;
- } else {
- /* Allocate a virtual interrupt number */
- hint = hwirq % irq_virq_count;
- virq = irq_alloc_virt(host, 1, hint);
- if (virq == NO_IRQ) {
- pr_debug("irq: -> virq allocation failed\n");
- return NO_IRQ;
- }
- }
-
- if (irq_setup_virq(host, virq, hwirq))
- return NO_IRQ;
-
- pr_debug("irq: irq %lu on host %s mapped to virtual irq %u\n",
- hwirq, host->of_node ? host->of_node->full_name : "null", virq);
-
- return virq;
-}
-EXPORT_SYMBOL_GPL(irq_create_mapping);
-
-unsigned int irq_create_of_mapping(struct device_node *controller,
- const u32 *intspec, unsigned int intsize)
-{
- struct irq_host *host;
- irq_hw_number_t hwirq;
- unsigned int type = IRQ_TYPE_NONE;
- unsigned int virq;
-
- if (controller == NULL)
- host = irq_default_host;
- else
- host = irq_find_host(controller);
- if (host == NULL) {
- printk(KERN_WARNING "irq: no irq host found for %s !\n",
- controller->full_name);
- return NO_IRQ;
- }
-
- /* If host has no translation, then we assume interrupt line */
- if (host->ops->xlate == NULL)
- hwirq = intspec[0];
- else {
- if (host->ops->xlate(host, controller, intspec, intsize,
- &hwirq, &type))
- return NO_IRQ;
- }
-
- /* Create mapping */
- virq = irq_create_mapping(host, hwirq);
- if (virq == NO_IRQ)
- return virq;
-
- /* Set type if specified and different than the current one */
- if (type != IRQ_TYPE_NONE &&
- type != (irqd_get_trigger_type(irq_get_irq_data(virq))))
- irq_set_irq_type(virq, type);
- return virq;
-}
-EXPORT_SYMBOL_GPL(irq_create_of_mapping);
-
-void irq_dispose_mapping(unsigned int virq)
-{
- struct irq_host *host;
- irq_hw_number_t hwirq;
-
- if (virq == NO_IRQ)
- return;
-
- host = irq_map[virq].host;
- if (WARN_ON(host == NULL))
- return;
-
- /* Never unmap legacy interrupts */
- if (host->revmap_type == IRQ_HOST_MAP_LEGACY)
- return;
-
- irq_set_status_flags(virq, IRQ_NOREQUEST);
-
- /* remove chip and handler */
- irq_set_chip_and_handler(virq, NULL, NULL);
-
- /* Make sure it's completed */
- synchronize_irq(virq);
-
- /* Tell the PIC about it */
- if (host->ops->unmap)
- host->ops->unmap(host, virq);
- smp_mb();
-
- /* Clear reverse map */
- hwirq = irq_map[virq].hwirq;
- switch(host->revmap_type) {
- case IRQ_HOST_MAP_LINEAR:
- if (hwirq < host->revmap_data.linear.size)
- host->revmap_data.linear.revmap[hwirq] = NO_IRQ;
- break;
- case IRQ_HOST_MAP_TREE:
- mutex_lock(&revmap_trees_mutex);
- radix_tree_delete(&host->revmap_data.tree, hwirq);
- mutex_unlock(&revmap_trees_mutex);
- break;
- }
-
- /* Destroy map */
- smp_mb();
- irq_map[virq].hwirq = host->inval_irq;
-
- irq_free_descs(virq, 1);
- /* Free it */
- irq_free_virt(virq, 1);
-}
-EXPORT_SYMBOL_GPL(irq_dispose_mapping);
-
-unsigned int irq_find_mapping(struct irq_host *host,
- irq_hw_number_t hwirq)
-{
- unsigned int i;
- unsigned int hint = hwirq % irq_virq_count;
-
- /* Look for default host if nececssary */
- if (host == NULL)
- host = irq_default_host;
- if (host == NULL)
- return NO_IRQ;
-
- /* legacy -> bail early */
- if (host->revmap_type == IRQ_HOST_MAP_LEGACY)
- return hwirq;
-
- /* Slow path does a linear search of the map */
- if (hint < NUM_ISA_INTERRUPTS)
- hint = NUM_ISA_INTERRUPTS;
- i = hint;
- do {
- if (irq_map[i].host == host &&
- irq_map[i].hwirq == hwirq)
- return i;
- i++;
- if (i >= irq_virq_count)
- i = NUM_ISA_INTERRUPTS;
- } while(i != hint);
- return NO_IRQ;
-}
-EXPORT_SYMBOL_GPL(irq_find_mapping);
-
#ifdef CONFIG_SMP
int irq_choose_cpu(const struct cpumask *mask)
{
int cpuid;
- if (cpumask_equal(mask, cpu_all_mask)) {
+ if (cpumask_equal(mask, cpu_online_mask)) {
static int irq_rover;
static DEFINE_RAW_SPINLOCK(irq_rover_lock);
unsigned long flags;
@@ -925,232 +662,11 @@ int irq_choose_cpu(const struct cpumask *mask)
}
#endif
-unsigned int irq_radix_revmap_lookup(struct irq_host *host,
- irq_hw_number_t hwirq)
-{
- struct irq_map_entry *ptr;
- unsigned int virq;
-
- if (WARN_ON_ONCE(host->revmap_type != IRQ_HOST_MAP_TREE))
- return irq_find_mapping(host, hwirq);
-
- /*
- * The ptr returned references the static global irq_map.
- * but freeing an irq can delete nodes along the path to
- * do the lookup via call_rcu.
- */
- rcu_read_lock();
- ptr = radix_tree_lookup(&host->revmap_data.tree, hwirq);
- rcu_read_unlock();
-
- /*
- * If found in radix tree, then fine.
- * Else fallback to linear lookup - this should not happen in practice
- * as it means that we failed to insert the node in the radix tree.
- */
- if (ptr)
- virq = ptr - irq_map;
- else
- virq = irq_find_mapping(host, hwirq);
-
- return virq;
-}
-
-void irq_radix_revmap_insert(struct irq_host *host, unsigned int virq,
- irq_hw_number_t hwirq)
-{
- if (WARN_ON(host->revmap_type != IRQ_HOST_MAP_TREE))
- return;
-
- if (virq != NO_IRQ) {
- mutex_lock(&revmap_trees_mutex);
- radix_tree_insert(&host->revmap_data.tree, hwirq,
- &irq_map[virq]);
- mutex_unlock(&revmap_trees_mutex);
- }
-}
-
-unsigned int irq_linear_revmap(struct irq_host *host,
- irq_hw_number_t hwirq)
-{
- unsigned int *revmap;
-
- if (WARN_ON_ONCE(host->revmap_type != IRQ_HOST_MAP_LINEAR))
- return irq_find_mapping(host, hwirq);
-
- /* Check revmap bounds */
- if (unlikely(hwirq >= host->revmap_data.linear.size))
- return irq_find_mapping(host, hwirq);
-
- /* Check if revmap was allocated */
- revmap = host->revmap_data.linear.revmap;
- if (unlikely(revmap == NULL))
- return irq_find_mapping(host, hwirq);
-
- /* Fill up revmap with slow path if no mapping found */
- if (unlikely(revmap[hwirq] == NO_IRQ))
- revmap[hwirq] = irq_find_mapping(host, hwirq);
-
- return revmap[hwirq];
-}
-
-unsigned int irq_alloc_virt(struct irq_host *host,
- unsigned int count,
- unsigned int hint)
-{
- unsigned long flags;
- unsigned int i, j, found = NO_IRQ;
-
- if (count == 0 || count > (irq_virq_count - NUM_ISA_INTERRUPTS))
- return NO_IRQ;
-
- raw_spin_lock_irqsave(&irq_big_lock, flags);
-
- /* Use hint for 1 interrupt if any */
- if (count == 1 && hint >= NUM_ISA_INTERRUPTS &&
- hint < irq_virq_count && irq_map[hint].host == NULL) {
- found = hint;
- goto hint_found;
- }
-
- /* Look for count consecutive numbers in the allocatable
- * (non-legacy) space
- */
- for (i = NUM_ISA_INTERRUPTS, j = 0; i < irq_virq_count; i++) {
- if (irq_map[i].host != NULL)
- j = 0;
- else
- j++;
-
- if (j == count) {
- found = i - count + 1;
- break;
- }
- }
- if (found == NO_IRQ) {
- raw_spin_unlock_irqrestore(&irq_big_lock, flags);
- return NO_IRQ;
- }
- hint_found:
- for (i = found; i < (found + count); i++) {
- irq_map[i].hwirq = host->inval_irq;
- smp_wmb();
- irq_map[i].host = host;
- }
- raw_spin_unlock_irqrestore(&irq_big_lock, flags);
- return found;
-}
-
-void irq_free_virt(unsigned int virq, unsigned int count)
-{
- unsigned long flags;
- unsigned int i;
-
- WARN_ON (virq < NUM_ISA_INTERRUPTS);
- WARN_ON (count == 0 || (virq + count) > irq_virq_count);
-
- if (virq < NUM_ISA_INTERRUPTS) {
- if (virq + count < NUM_ISA_INTERRUPTS)
- return;
- count =- NUM_ISA_INTERRUPTS - virq;
- virq = NUM_ISA_INTERRUPTS;
- }
-
- if (count > irq_virq_count || virq > irq_virq_count - count) {
- if (virq > irq_virq_count)
- return;
- count = irq_virq_count - virq;
- }
-
- raw_spin_lock_irqsave(&irq_big_lock, flags);
- for (i = virq; i < (virq + count); i++) {
- struct irq_host *host;
-
- host = irq_map[i].host;
- irq_map[i].hwirq = host->inval_irq;
- smp_wmb();
- irq_map[i].host = NULL;
- }
- raw_spin_unlock_irqrestore(&irq_big_lock, flags);
-}
-
int arch_early_irq_init(void)
{
return 0;
}
-#ifdef CONFIG_VIRQ_DEBUG
-static int virq_debug_show(struct seq_file *m, void *private)
-{
- unsigned long flags;
- struct irq_desc *desc;
- const char *p;
- static const char none[] = "none";
- void *data;
- int i;
-
- seq_printf(m, "%-5s %-7s %-15s %-18s %s\n", "virq", "hwirq",
- "chip name", "chip data", "host name");
-
- for (i = 1; i < nr_irqs; i++) {
- desc = irq_to_desc(i);
- if (!desc)
- continue;
-
- raw_spin_lock_irqsave(&desc->lock, flags);
-
- if (desc->action && desc->action->handler) {
- struct irq_chip *chip;
-
- seq_printf(m, "%5d ", i);
- seq_printf(m, "0x%05lx ", irq_map[i].hwirq);
-
- chip = irq_desc_get_chip(desc);
- if (chip && chip->name)
- p = chip->name;
- else
- p = none;
- seq_printf(m, "%-15s ", p);
-
- data = irq_desc_get_chip_data(desc);
- seq_printf(m, "0x%16p ", data);
-
- if (irq_map[i].host && irq_map[i].host->of_node)
- p = irq_map[i].host->of_node->full_name;
- else
- p = none;
- seq_printf(m, "%s\n", p);
- }
-
- raw_spin_unlock_irqrestore(&desc->lock, flags);
- }
-
- return 0;
-}
-
-static int virq_debug_open(struct inode *inode, struct file *file)
-{
- return single_open(file, virq_debug_show, inode->i_private);
-}
-
-static const struct file_operations virq_debug_fops = {
- .open = virq_debug_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
-static int __init irq_debugfs_init(void)
-{
- if (debugfs_create_file("virq_mapping", S_IRUGO, powerpc_debugfs_root,
- NULL, &virq_debug_fops) == NULL)
- return -ENOMEM;
-
- return 0;
-}
-__initcall(irq_debugfs_init);
-#endif /* CONFIG_VIRQ_DEBUG */
-
#ifdef CONFIG_PPC64
static int __init setup_noirqdistrib(char *str)
{
diff --git a/arch/powerpc/kernel/isa-bridge.c b/arch/powerpc/kernel/isa-bridge.c
index 479752901ec..0f199709796 100644
--- a/arch/powerpc/kernel/isa-bridge.c
+++ b/arch/powerpc/kernel/isa-bridge.c
@@ -29,7 +29,6 @@
#include <asm/pci-bridge.h>
#include <asm/machdep.h>
#include <asm/ppc-pci.h>
-#include <asm/firmware.h>
unsigned long isa_io_base; /* NULL if no ISA bus */
EXPORT_SYMBOL(isa_io_base);
@@ -42,8 +41,8 @@ EXPORT_SYMBOL_GPL(isa_bridge_pcidev);
#define ISA_SPACE_MASK 0x1
#define ISA_SPACE_IO 0x1
-static void __devinit pci_process_ISA_OF_ranges(struct device_node *isa_node,
- unsigned long phb_io_base_phys)
+static void pci_process_ISA_OF_ranges(struct device_node *isa_node,
+ unsigned long phb_io_base_phys)
{
/* We should get some saner parsing here and remove these structs */
struct pci_address {
@@ -171,8 +170,8 @@ void __init isa_bridge_find_early(struct pci_controller *hose)
* isa_bridge_find_late - Find and map the ISA IO space upon discovery of
* a new ISA bridge
*/
-static void __devinit isa_bridge_find_late(struct pci_dev *pdev,
- struct device_node *devnode)
+static void isa_bridge_find_late(struct pci_dev *pdev,
+ struct device_node *devnode)
{
struct pci_controller *hose = pci_bus_to_host(pdev->bus);
@@ -216,8 +215,8 @@ static void isa_bridge_remove(void)
/**
* isa_bridge_notify - Get notified of PCI devices addition/removal
*/
-static int __devinit isa_bridge_notify(struct notifier_block *nb,
- unsigned long action, void *data)
+static int isa_bridge_notify(struct notifier_block *nb, unsigned long action,
+ void *data)
{
struct device *dev = data;
struct pci_dev *pdev = to_pci_dev(dev);
@@ -261,8 +260,6 @@ static struct notifier_block isa_bridge_notifier = {
*/
static int __init isa_bridge_init(void)
{
- if (firmware_has_feature(FW_FEATURE_ISERIES))
- return 0;
bus_register_notifier(&pci_bus_type, &isa_bridge_notifier);
return 0;
}
diff --git a/arch/powerpc/kernel/kgdb.c b/arch/powerpc/kernel/kgdb.c
index 76a6e40a6f7..8504657379f 100644
--- a/arch/powerpc/kernel/kgdb.c
+++ b/arch/powerpc/kernel/kgdb.c
@@ -15,7 +15,6 @@
*/
#include <linux/kernel.h>
-#include <linux/init.h>
#include <linux/kgdb.h>
#include <linux/smp.h>
#include <linux/signal.h>
@@ -24,6 +23,8 @@
#include <asm/current.h>
#include <asm/processor.h>
#include <asm/machdep.h>
+#include <asm/debug.h>
+#include <linux/slab.h>
/*
* This table contains the mapping between PowerPC hardware trap types, and
@@ -100,6 +101,21 @@ static int computeSignal(unsigned int tt)
return SIGHUP; /* default for things we don't know about */
}
+/**
+ *
+ * kgdb_skipexception - Bail out of KGDB when we've been triggered.
+ * @exception: Exception vector number
+ * @regs: Current &struct pt_regs.
+ *
+ * On some architectures we need to skip a breakpoint exception when
+ * it occurs after a breakpoint has been removed.
+ *
+ */
+int kgdb_skipexception(int exception, struct pt_regs *regs)
+{
+ return kgdb_isremovedbreak(regs->nip);
+}
+
static int kgdb_call_nmi_hook(struct pt_regs *regs)
{
kgdb_nmicallback(raw_smp_processor_id(), regs);
@@ -134,9 +150,12 @@ static int kgdb_handle_breakpoint(struct pt_regs *regs)
return 1;
}
+static DEFINE_PER_CPU(struct thread_info, kgdb_thread_info);
static int kgdb_singlestep(struct pt_regs *regs)
{
struct thread_info *thread_info, *exception_thread_info;
+ struct thread_info *backup_current_thread_info =
+ &__get_cpu_var(kgdb_thread_info);
if (user_mode(regs))
return 0;
@@ -154,13 +173,17 @@ static int kgdb_singlestep(struct pt_regs *regs)
thread_info = (struct thread_info *)(regs->gpr[1] & ~(THREAD_SIZE-1));
exception_thread_info = current_thread_info();
- if (thread_info != exception_thread_info)
+ if (thread_info != exception_thread_info) {
+ /* Save the original current_thread_info. */
+ memcpy(backup_current_thread_info, exception_thread_info, sizeof *thread_info);
memcpy(exception_thread_info, thread_info, sizeof *thread_info);
+ }
kgdb_handle_exception(0, SIGTRAP, 0, regs);
if (thread_info != exception_thread_info)
- memcpy(thread_info, exception_thread_info, sizeof *thread_info);
+ /* Restore current_thread_info lastly. */
+ memcpy(exception_thread_info, backup_current_thread_info, sizeof *thread_info);
return 1;
}
@@ -175,7 +198,7 @@ static int kgdb_iabr_match(struct pt_regs *regs)
return 1;
}
-static int kgdb_dabr_match(struct pt_regs *regs)
+static int kgdb_break_match(struct pt_regs *regs)
{
if (user_mode(regs))
return 0;
@@ -409,7 +432,6 @@ int kgdb_arch_handle_exception(int vector, int signo, int err_code,
#else
linux_regs->msr |= MSR_SE;
#endif
- kgdb_single_step = 1;
atomic_set(&kgdb_cpu_doing_single_step,
raw_smp_processor_id());
}
@@ -436,7 +458,7 @@ static void *old__debugger;
static void *old__debugger_bpt;
static void *old__debugger_sstep;
static void *old__debugger_iabr_match;
-static void *old__debugger_dabr_match;
+static void *old__debugger_break_match;
static void *old__debugger_fault_handler;
int kgdb_arch_init(void)
@@ -446,7 +468,7 @@ int kgdb_arch_init(void)
old__debugger_bpt = __debugger_bpt;
old__debugger_sstep = __debugger_sstep;
old__debugger_iabr_match = __debugger_iabr_match;
- old__debugger_dabr_match = __debugger_dabr_match;
+ old__debugger_break_match = __debugger_break_match;
old__debugger_fault_handler = __debugger_fault_handler;
__debugger_ipi = kgdb_call_nmi_hook;
@@ -454,7 +476,7 @@ int kgdb_arch_init(void)
__debugger_bpt = kgdb_handle_breakpoint;
__debugger_sstep = kgdb_singlestep;
__debugger_iabr_match = kgdb_iabr_match;
- __debugger_dabr_match = kgdb_dabr_match;
+ __debugger_break_match = kgdb_break_match;
__debugger_fault_handler = kgdb_not_implemented;
return 0;
@@ -467,6 +489,6 @@ void kgdb_arch_exit(void)
__debugger_bpt = old__debugger_bpt;
__debugger_sstep = old__debugger_sstep;
__debugger_iabr_match = old__debugger_iabr_match;
- __debugger_dabr_match = old__debugger_dabr_match;
+ __debugger_break_match = old__debugger_break_match;
__debugger_fault_handler = old__debugger_fault_handler;
}
diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c
index bc47352deb1..2f72af82513 100644
--- a/arch/powerpc/kernel/kprobes.c
+++ b/arch/powerpc/kernel/kprobes.c
@@ -32,16 +32,10 @@
#include <linux/module.h>
#include <linux/kdebug.h>
#include <linux/slab.h>
+#include <asm/code-patching.h>
#include <asm/cacheflush.h>
#include <asm/sstep.h>
#include <asm/uaccess.h>
-#include <asm/system.h>
-
-#ifdef CONFIG_PPC_ADV_DEBUG_REGS
-#define MSR_SINGLESTEP (MSR_DE)
-#else
-#define MSR_SINGLESTEP (MSR_SE)
-#endif
DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL;
DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
@@ -105,19 +99,7 @@ void __kprobes arch_remove_kprobe(struct kprobe *p)
static void __kprobes prepare_singlestep(struct kprobe *p, struct pt_regs *regs)
{
- /* We turn off async exceptions to ensure that the single step will
- * be for the instruction we have the kprobe on, if we dont its
- * possible we'd get the single step reported for an exception handler
- * like Decrementer or External Interrupt */
- regs->msr &= ~MSR_EE;
- regs->msr |= MSR_SINGLESTEP;
-#ifdef CONFIG_PPC_ADV_DEBUG_REGS
- regs->msr &= ~MSR_CE;
- mtspr(SPRN_DBCR0, mfspr(SPRN_DBCR0) | DBCR0_IC | DBCR0_IDM);
-#ifdef CONFIG_PPC_47x
- isync();
-#endif
-#endif
+ enable_single_step(regs);
/*
* On powerpc we should single step on the original
@@ -311,7 +293,7 @@ static int __kprobes trampoline_probe_handler(struct kprobe *p,
{
struct kretprobe_instance *ri = NULL;
struct hlist_head *head, empty_rp;
- struct hlist_node *node, *tmp;
+ struct hlist_node *tmp;
unsigned long flags, orig_ret_address = 0;
unsigned long trampoline_address =(unsigned long)&kretprobe_trampoline;
@@ -331,7 +313,7 @@ static int __kprobes trampoline_probe_handler(struct kprobe *p,
* real return address, and all the rest will point to
* kretprobe_trampoline
*/
- hlist_for_each_entry_safe(ri, node, tmp, head, hlist) {
+ hlist_for_each_entry_safe(ri, tmp, head, hlist) {
if (ri->task != current)
/* another task is sharing our hash bucket */
continue;
@@ -358,7 +340,7 @@ static int __kprobes trampoline_probe_handler(struct kprobe *p,
kretprobe_hash_unlock(current, &flags);
preempt_enable_no_resched();
- hlist_for_each_entry_safe(ri, node, tmp, &empty_rp, hlist) {
+ hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
hlist_del(&ri->hlist);
kfree(ri);
}
@@ -448,7 +430,7 @@ int __kprobes kprobe_fault_handler(struct pt_regs *regs, int trapnr)
case KPROBE_HIT_SSDONE:
/*
* We increment the nmissed count for accounting,
- * we can also use npre/npostfault count for accouting
+ * we can also use npre/npostfault count for accounting
* these specific fault cases.
*/
kprobes_inc_nmissed_count(cur);
@@ -510,12 +492,10 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self,
return ret;
}
-#ifdef CONFIG_PPC64
unsigned long arch_deref_entry_point(void *entry)
{
- return ((func_descr_t *)entry)->entry;
+ return ppc_global_function_entry(entry);
}
-#endif
int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
{
@@ -527,8 +507,12 @@ int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
/* setup return addr to the jprobe handler routine */
regs->nip = arch_deref_entry_point(jp->entry);
#ifdef CONFIG_PPC64
+#if defined(_CALL_ELF) && _CALL_ELF == 2
+ regs->gpr[12] = (unsigned long)jp->entry;
+#else
regs->gpr[2] = (unsigned long)(((func_descr_t *)jp->entry)->toc);
#endif
+#endif
return 1;
}
diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c
index 2985338d0e1..33aa4ddf597 100644
--- a/arch/powerpc/kernel/kvm.c
+++ b/arch/powerpc/kernel/kvm.c
@@ -1,5 +1,6 @@
/*
* Copyright (C) 2010 SUSE Linux Products GmbH. All rights reserved.
+ * Copyright 2010-2011 Freescale Semiconductor, Inc.
*
* Authors:
* Alexander Graf <agraf@suse.de>
@@ -29,6 +30,8 @@
#include <asm/sections.h>
#include <asm/cacheflush.h>
#include <asm/disassemble.h>
+#include <asm/ppc-opcode.h>
+#include <asm/epapr_hcalls.h>
#define KVM_MAGIC_PAGE (-4096L)
#define magic_var(x) KVM_MAGIC_PAGE + offsetof(struct kvm_vcpu_arch_shared, x)
@@ -41,41 +44,37 @@
#define KVM_INST_B 0x48000000
#define KVM_INST_B_MASK 0x03ffffff
#define KVM_INST_B_MAX 0x01ffffff
+#define KVM_INST_LI 0x38000000
#define KVM_MASK_RT 0x03e00000
#define KVM_RT_30 0x03c00000
#define KVM_MASK_RB 0x0000f800
#define KVM_INST_MFMSR 0x7c0000a6
-#define KVM_INST_MFSPR_SPRG0 0x7c1042a6
-#define KVM_INST_MFSPR_SPRG1 0x7c1142a6
-#define KVM_INST_MFSPR_SPRG2 0x7c1242a6
-#define KVM_INST_MFSPR_SPRG3 0x7c1342a6
-#define KVM_INST_MFSPR_SRR0 0x7c1a02a6
-#define KVM_INST_MFSPR_SRR1 0x7c1b02a6
-#define KVM_INST_MFSPR_DAR 0x7c1302a6
-#define KVM_INST_MFSPR_DSISR 0x7c1202a6
-
-#define KVM_INST_MTSPR_SPRG0 0x7c1043a6
-#define KVM_INST_MTSPR_SPRG1 0x7c1143a6
-#define KVM_INST_MTSPR_SPRG2 0x7c1243a6
-#define KVM_INST_MTSPR_SPRG3 0x7c1343a6
-#define KVM_INST_MTSPR_SRR0 0x7c1a03a6
-#define KVM_INST_MTSPR_SRR1 0x7c1b03a6
-#define KVM_INST_MTSPR_DAR 0x7c1303a6
-#define KVM_INST_MTSPR_DSISR 0x7c1203a6
+
+#define SPR_FROM 0
+#define SPR_TO 0x100
+
+#define KVM_INST_SPR(sprn, moveto) (0x7c0002a6 | \
+ (((sprn) & 0x1f) << 16) | \
+ (((sprn) & 0x3e0) << 6) | \
+ (moveto))
+
+#define KVM_INST_MFSPR(sprn) KVM_INST_SPR(sprn, SPR_FROM)
+#define KVM_INST_MTSPR(sprn) KVM_INST_SPR(sprn, SPR_TO)
#define KVM_INST_TLBSYNC 0x7c00046c
#define KVM_INST_MTMSRD_L0 0x7c000164
#define KVM_INST_MTMSRD_L1 0x7c010164
#define KVM_INST_MTMSR 0x7c000124
+#define KVM_INST_WRTEE 0x7c000106
#define KVM_INST_WRTEEI_0 0x7c000146
#define KVM_INST_WRTEEI_1 0x7c008146
#define KVM_INST_MTSRIN 0x7c0001e4
static bool kvm_patching_worked = true;
-static char kvm_tmp[1024 * 1024];
+char kvm_tmp[1024 * 1024];
static int kvm_tmp_index;
static inline void kvm_patch_ins(u32 *inst, u32 new_inst)
@@ -270,26 +269,27 @@ static void kvm_patch_ins_mtmsr(u32 *inst, u32 rt)
#ifdef CONFIG_BOOKE
-extern u32 kvm_emulate_wrteei_branch_offs;
-extern u32 kvm_emulate_wrteei_ee_offs;
-extern u32 kvm_emulate_wrteei_len;
-extern u32 kvm_emulate_wrteei[];
+extern u32 kvm_emulate_wrtee_branch_offs;
+extern u32 kvm_emulate_wrtee_reg_offs;
+extern u32 kvm_emulate_wrtee_orig_ins_offs;
+extern u32 kvm_emulate_wrtee_len;
+extern u32 kvm_emulate_wrtee[];
-static void kvm_patch_ins_wrteei(u32 *inst)
+static void kvm_patch_ins_wrtee(u32 *inst, u32 rt, int imm_one)
{
u32 *p;
int distance_start;
int distance_end;
ulong next_inst;
- p = kvm_alloc(kvm_emulate_wrteei_len * 4);
+ p = kvm_alloc(kvm_emulate_wrtee_len * 4);
if (!p)
return;
/* Find out where we are and put everything there */
distance_start = (ulong)p - (ulong)inst;
next_inst = ((ulong)inst + 4);
- distance_end = next_inst - (ulong)&p[kvm_emulate_wrteei_branch_offs];
+ distance_end = next_inst - (ulong)&p[kvm_emulate_wrtee_branch_offs];
/* Make sure we only write valid b instructions */
if (distance_start > KVM_INST_B_MAX) {
@@ -298,10 +298,65 @@ static void kvm_patch_ins_wrteei(u32 *inst)
}
/* Modify the chunk to fit the invocation */
- memcpy(p, kvm_emulate_wrteei, kvm_emulate_wrteei_len * 4);
- p[kvm_emulate_wrteei_branch_offs] |= distance_end & KVM_INST_B_MASK;
- p[kvm_emulate_wrteei_ee_offs] |= (*inst & MSR_EE);
- flush_icache_range((ulong)p, (ulong)p + kvm_emulate_wrteei_len * 4);
+ memcpy(p, kvm_emulate_wrtee, kvm_emulate_wrtee_len * 4);
+ p[kvm_emulate_wrtee_branch_offs] |= distance_end & KVM_INST_B_MASK;
+
+ if (imm_one) {
+ p[kvm_emulate_wrtee_reg_offs] =
+ KVM_INST_LI | __PPC_RT(R30) | MSR_EE;
+ } else {
+ /* Make clobbered registers work too */
+ switch (get_rt(rt)) {
+ case 30:
+ kvm_patch_ins_ll(&p[kvm_emulate_wrtee_reg_offs],
+ magic_var(scratch2), KVM_RT_30);
+ break;
+ case 31:
+ kvm_patch_ins_ll(&p[kvm_emulate_wrtee_reg_offs],
+ magic_var(scratch1), KVM_RT_30);
+ break;
+ default:
+ p[kvm_emulate_wrtee_reg_offs] |= rt;
+ break;
+ }
+ }
+
+ p[kvm_emulate_wrtee_orig_ins_offs] = *inst;
+ flush_icache_range((ulong)p, (ulong)p + kvm_emulate_wrtee_len * 4);
+
+ /* Patch the invocation */
+ kvm_patch_ins_b(inst, distance_start);
+}
+
+extern u32 kvm_emulate_wrteei_0_branch_offs;
+extern u32 kvm_emulate_wrteei_0_len;
+extern u32 kvm_emulate_wrteei_0[];
+
+static void kvm_patch_ins_wrteei_0(u32 *inst)
+{
+ u32 *p;
+ int distance_start;
+ int distance_end;
+ ulong next_inst;
+
+ p = kvm_alloc(kvm_emulate_wrteei_0_len * 4);
+ if (!p)
+ return;
+
+ /* Find out where we are and put everything there */
+ distance_start = (ulong)p - (ulong)inst;
+ next_inst = ((ulong)inst + 4);
+ distance_end = next_inst - (ulong)&p[kvm_emulate_wrteei_0_branch_offs];
+
+ /* Make sure we only write valid b instructions */
+ if (distance_start > KVM_INST_B_MAX) {
+ kvm_patching_worked = false;
+ return;
+ }
+
+ memcpy(p, kvm_emulate_wrteei_0, kvm_emulate_wrteei_0_len * 4);
+ p[kvm_emulate_wrteei_0_branch_offs] |= distance_end & KVM_INST_B_MASK;
+ flush_icache_range((ulong)p, (ulong)p + kvm_emulate_wrteei_0_len * 4);
/* Patch the invocation */
kvm_patch_ins_b(inst, distance_start);
@@ -358,13 +413,13 @@ static void kvm_map_magic_page(void *data)
{
u32 *features = data;
- ulong in[8];
+ ulong in[8] = {0};
ulong out[8];
in[0] = KVM_MAGIC_PAGE;
- in[1] = KVM_MAGIC_PAGE;
+ in[1] = KVM_MAGIC_PAGE | MAGIC_PAGE_FLAG_NOT_MAPPED_NX;
- kvm_hypercall(in, out, HC_VENDOR_KVM | KVM_HC_PPC_MAP_MAGIC_PAGE);
+ epapr_hypercall(in, out, KVM_HCALL_TOKEN(KVM_HC_PPC_MAP_MAGIC_PAGE));
*features = out[0];
}
@@ -380,56 +435,191 @@ static void kvm_check_ins(u32 *inst, u32 features)
case KVM_INST_MFMSR:
kvm_patch_ins_ld(inst, magic_var(msr), inst_rt);
break;
- case KVM_INST_MFSPR_SPRG0:
+ case KVM_INST_MFSPR(SPRN_SPRG0):
kvm_patch_ins_ld(inst, magic_var(sprg0), inst_rt);
break;
- case KVM_INST_MFSPR_SPRG1:
+ case KVM_INST_MFSPR(SPRN_SPRG1):
kvm_patch_ins_ld(inst, magic_var(sprg1), inst_rt);
break;
- case KVM_INST_MFSPR_SPRG2:
+ case KVM_INST_MFSPR(SPRN_SPRG2):
kvm_patch_ins_ld(inst, magic_var(sprg2), inst_rt);
break;
- case KVM_INST_MFSPR_SPRG3:
+ case KVM_INST_MFSPR(SPRN_SPRG3):
kvm_patch_ins_ld(inst, magic_var(sprg3), inst_rt);
break;
- case KVM_INST_MFSPR_SRR0:
+ case KVM_INST_MFSPR(SPRN_SRR0):
kvm_patch_ins_ld(inst, magic_var(srr0), inst_rt);
break;
- case KVM_INST_MFSPR_SRR1:
+ case KVM_INST_MFSPR(SPRN_SRR1):
kvm_patch_ins_ld(inst, magic_var(srr1), inst_rt);
break;
- case KVM_INST_MFSPR_DAR:
+#ifdef CONFIG_BOOKE
+ case KVM_INST_MFSPR(SPRN_DEAR):
+#else
+ case KVM_INST_MFSPR(SPRN_DAR):
+#endif
kvm_patch_ins_ld(inst, magic_var(dar), inst_rt);
break;
- case KVM_INST_MFSPR_DSISR:
+ case KVM_INST_MFSPR(SPRN_DSISR):
kvm_patch_ins_lwz(inst, magic_var(dsisr), inst_rt);
break;
+#ifdef CONFIG_PPC_BOOK3E_MMU
+ case KVM_INST_MFSPR(SPRN_MAS0):
+ if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+ kvm_patch_ins_lwz(inst, magic_var(mas0), inst_rt);
+ break;
+ case KVM_INST_MFSPR(SPRN_MAS1):
+ if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+ kvm_patch_ins_lwz(inst, magic_var(mas1), inst_rt);
+ break;
+ case KVM_INST_MFSPR(SPRN_MAS2):
+ if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+ kvm_patch_ins_ld(inst, magic_var(mas2), inst_rt);
+ break;
+ case KVM_INST_MFSPR(SPRN_MAS3):
+ if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+ kvm_patch_ins_lwz(inst, magic_var(mas7_3) + 4, inst_rt);
+ break;
+ case KVM_INST_MFSPR(SPRN_MAS4):
+ if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+ kvm_patch_ins_lwz(inst, magic_var(mas4), inst_rt);
+ break;
+ case KVM_INST_MFSPR(SPRN_MAS6):
+ if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+ kvm_patch_ins_lwz(inst, magic_var(mas6), inst_rt);
+ break;
+ case KVM_INST_MFSPR(SPRN_MAS7):
+ if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+ kvm_patch_ins_lwz(inst, magic_var(mas7_3), inst_rt);
+ break;
+#endif /* CONFIG_PPC_BOOK3E_MMU */
+
+ case KVM_INST_MFSPR(SPRN_SPRG4):
+#ifdef CONFIG_BOOKE
+ case KVM_INST_MFSPR(SPRN_SPRG4R):
+#endif
+ if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+ kvm_patch_ins_ld(inst, magic_var(sprg4), inst_rt);
+ break;
+ case KVM_INST_MFSPR(SPRN_SPRG5):
+#ifdef CONFIG_BOOKE
+ case KVM_INST_MFSPR(SPRN_SPRG5R):
+#endif
+ if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+ kvm_patch_ins_ld(inst, magic_var(sprg5), inst_rt);
+ break;
+ case KVM_INST_MFSPR(SPRN_SPRG6):
+#ifdef CONFIG_BOOKE
+ case KVM_INST_MFSPR(SPRN_SPRG6R):
+#endif
+ if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+ kvm_patch_ins_ld(inst, magic_var(sprg6), inst_rt);
+ break;
+ case KVM_INST_MFSPR(SPRN_SPRG7):
+#ifdef CONFIG_BOOKE
+ case KVM_INST_MFSPR(SPRN_SPRG7R):
+#endif
+ if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+ kvm_patch_ins_ld(inst, magic_var(sprg7), inst_rt);
+ break;
+
+#ifdef CONFIG_BOOKE
+ case KVM_INST_MFSPR(SPRN_ESR):
+ if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+ kvm_patch_ins_lwz(inst, magic_var(esr), inst_rt);
+ break;
+#endif
+
+ case KVM_INST_MFSPR(SPRN_PIR):
+ if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+ kvm_patch_ins_lwz(inst, magic_var(pir), inst_rt);
+ break;
+
+
/* Stores */
- case KVM_INST_MTSPR_SPRG0:
+ case KVM_INST_MTSPR(SPRN_SPRG0):
kvm_patch_ins_std(inst, magic_var(sprg0), inst_rt);
break;
- case KVM_INST_MTSPR_SPRG1:
+ case KVM_INST_MTSPR(SPRN_SPRG1):
kvm_patch_ins_std(inst, magic_var(sprg1), inst_rt);
break;
- case KVM_INST_MTSPR_SPRG2:
+ case KVM_INST_MTSPR(SPRN_SPRG2):
kvm_patch_ins_std(inst, magic_var(sprg2), inst_rt);
break;
- case KVM_INST_MTSPR_SPRG3:
+ case KVM_INST_MTSPR(SPRN_SPRG3):
kvm_patch_ins_std(inst, magic_var(sprg3), inst_rt);
break;
- case KVM_INST_MTSPR_SRR0:
+ case KVM_INST_MTSPR(SPRN_SRR0):
kvm_patch_ins_std(inst, magic_var(srr0), inst_rt);
break;
- case KVM_INST_MTSPR_SRR1:
+ case KVM_INST_MTSPR(SPRN_SRR1):
kvm_patch_ins_std(inst, magic_var(srr1), inst_rt);
break;
- case KVM_INST_MTSPR_DAR:
+#ifdef CONFIG_BOOKE
+ case KVM_INST_MTSPR(SPRN_DEAR):
+#else
+ case KVM_INST_MTSPR(SPRN_DAR):
+#endif
kvm_patch_ins_std(inst, magic_var(dar), inst_rt);
break;
- case KVM_INST_MTSPR_DSISR:
+ case KVM_INST_MTSPR(SPRN_DSISR):
kvm_patch_ins_stw(inst, magic_var(dsisr), inst_rt);
break;
+#ifdef CONFIG_PPC_BOOK3E_MMU
+ case KVM_INST_MTSPR(SPRN_MAS0):
+ if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+ kvm_patch_ins_stw(inst, magic_var(mas0), inst_rt);
+ break;
+ case KVM_INST_MTSPR(SPRN_MAS1):
+ if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+ kvm_patch_ins_stw(inst, magic_var(mas1), inst_rt);
+ break;
+ case KVM_INST_MTSPR(SPRN_MAS2):
+ if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+ kvm_patch_ins_std(inst, magic_var(mas2), inst_rt);
+ break;
+ case KVM_INST_MTSPR(SPRN_MAS3):
+ if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+ kvm_patch_ins_stw(inst, magic_var(mas7_3) + 4, inst_rt);
+ break;
+ case KVM_INST_MTSPR(SPRN_MAS4):
+ if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+ kvm_patch_ins_stw(inst, magic_var(mas4), inst_rt);
+ break;
+ case KVM_INST_MTSPR(SPRN_MAS6):
+ if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+ kvm_patch_ins_stw(inst, magic_var(mas6), inst_rt);
+ break;
+ case KVM_INST_MTSPR(SPRN_MAS7):
+ if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+ kvm_patch_ins_stw(inst, magic_var(mas7_3), inst_rt);
+ break;
+#endif /* CONFIG_PPC_BOOK3E_MMU */
+
+ case KVM_INST_MTSPR(SPRN_SPRG4):
+ if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+ kvm_patch_ins_std(inst, magic_var(sprg4), inst_rt);
+ break;
+ case KVM_INST_MTSPR(SPRN_SPRG5):
+ if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+ kvm_patch_ins_std(inst, magic_var(sprg5), inst_rt);
+ break;
+ case KVM_INST_MTSPR(SPRN_SPRG6):
+ if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+ kvm_patch_ins_std(inst, magic_var(sprg6), inst_rt);
+ break;
+ case KVM_INST_MTSPR(SPRN_SPRG7):
+ if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+ kvm_patch_ins_std(inst, magic_var(sprg7), inst_rt);
+ break;
+
+#ifdef CONFIG_BOOKE
+ case KVM_INST_MTSPR(SPRN_ESR):
+ if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+ kvm_patch_ins_stw(inst, magic_var(esr), inst_rt);
+ break;
+#endif
/* Nops */
case KVM_INST_TLBSYNC:
@@ -444,6 +634,11 @@ static void kvm_check_ins(u32 *inst, u32 features)
case KVM_INST_MTMSRD_L0:
kvm_patch_ins_mtmsr(inst, inst_rt);
break;
+#ifdef CONFIG_BOOKE
+ case KVM_INST_WRTEE:
+ kvm_patch_ins_wrtee(inst, inst_rt, 0);
+ break;
+#endif
}
switch (inst_no_rt & ~KVM_MASK_RB) {
@@ -461,13 +656,19 @@ static void kvm_check_ins(u32 *inst, u32 features)
switch (_inst) {
#ifdef CONFIG_BOOKE
case KVM_INST_WRTEEI_0:
+ kvm_patch_ins_wrteei_0(inst);
+ break;
+
case KVM_INST_WRTEEI_1:
- kvm_patch_ins_wrteei(inst);
+ kvm_patch_ins_wrtee(inst, 0, 1);
break;
#endif
}
}
+extern u32 kvm_template_start[];
+extern u32 kvm_template_end[];
+
static void kvm_use_magic_page(void)
{
u32 *p;
@@ -488,87 +689,32 @@ static void kvm_use_magic_page(void)
start = (void*)_stext;
end = (void*)_etext;
- for (p = start; p < end; p++)
+ /*
+ * Being interrupted in the middle of patching would
+ * be bad for SPRG4-7, which KVM can't keep in sync
+ * with emulated accesses because reads don't trap.
+ */
+ local_irq_disable();
+
+ for (p = start; p < end; p++) {
+ /* Avoid patching the template code */
+ if (p >= kvm_template_start && p < kvm_template_end) {
+ p = kvm_template_end - 1;
+ continue;
+ }
kvm_check_ins(p, features);
+ }
+
+ local_irq_enable();
printk(KERN_INFO "KVM: Live patching for a fast VM %s\n",
kvm_patching_worked ? "worked" : "failed");
}
-unsigned long kvm_hypercall(unsigned long *in,
- unsigned long *out,
- unsigned long nr)
-{
- unsigned long register r0 asm("r0");
- unsigned long register r3 asm("r3") = in[0];
- unsigned long register r4 asm("r4") = in[1];
- unsigned long register r5 asm("r5") = in[2];
- unsigned long register r6 asm("r6") = in[3];
- unsigned long register r7 asm("r7") = in[4];
- unsigned long register r8 asm("r8") = in[5];
- unsigned long register r9 asm("r9") = in[6];
- unsigned long register r10 asm("r10") = in[7];
- unsigned long register r11 asm("r11") = nr;
- unsigned long register r12 asm("r12");
-
- asm volatile("bl kvm_hypercall_start"
- : "=r"(r0), "=r"(r3), "=r"(r4), "=r"(r5), "=r"(r6),
- "=r"(r7), "=r"(r8), "=r"(r9), "=r"(r10), "=r"(r11),
- "=r"(r12)
- : "r"(r3), "r"(r4), "r"(r5), "r"(r6), "r"(r7), "r"(r8),
- "r"(r9), "r"(r10), "r"(r11)
- : "memory", "cc", "xer", "ctr", "lr");
-
- out[0] = r4;
- out[1] = r5;
- out[2] = r6;
- out[3] = r7;
- out[4] = r8;
- out[5] = r9;
- out[6] = r10;
- out[7] = r11;
-
- return r3;
-}
-EXPORT_SYMBOL_GPL(kvm_hypercall);
-
-static int kvm_para_setup(void)
-{
- extern u32 kvm_hypercall_start;
- struct device_node *hyper_node;
- u32 *insts;
- int len, i;
-
- hyper_node = of_find_node_by_path("/hypervisor");
- if (!hyper_node)
- return -1;
-
- insts = (u32*)of_get_property(hyper_node, "hcall-instructions", &len);
- if (len % 4)
- return -1;
- if (len > (4 * 4))
- return -1;
-
- for (i = 0; i < (len / 4); i++)
- kvm_patch_ins(&(&kvm_hypercall_start)[i], insts[i]);
-
- return 0;
-}
-
static __init void kvm_free_tmp(void)
{
- unsigned long start, end;
-
- start = (ulong)&kvm_tmp[kvm_tmp_index + (PAGE_SIZE - 1)] & PAGE_MASK;
- end = (ulong)&kvm_tmp[ARRAY_SIZE(kvm_tmp)] & PAGE_MASK;
-
- /* Free the tmp space we don't need */
- for (; start < end; start += PAGE_SIZE) {
- ClearPageReserved(virt_to_page(start));
- init_page_count(virt_to_page(start));
- free_page(start);
- totalram_pages++;
- }
+ free_reserved_area(&kvm_tmp[kvm_tmp_index],
+ &kvm_tmp[ARRAY_SIZE(kvm_tmp)], -1, NULL);
}
static int __init kvm_guest_init(void)
@@ -576,7 +722,7 @@ static int __init kvm_guest_init(void)
if (!kvm_para_available())
goto free_tmp;
- if (kvm_para_setup())
+ if (!epapr_paravirt_enabled)
goto free_tmp;
if (kvm_para_has_feature(KVM_FEATURE_MAGIC_PAGE))
diff --git a/arch/powerpc/kernel/kvm_emul.S b/arch/powerpc/kernel/kvm_emul.S
index f2b1b2523e6..e100ff324a8 100644
--- a/arch/powerpc/kernel/kvm_emul.S
+++ b/arch/powerpc/kernel/kvm_emul.S
@@ -13,6 +13,7 @@
* Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
*
* Copyright SUSE Linux Products GmbH 2010
+ * Copyright 2010-2011 Freescale Semiconductor, Inc.
*
* Authors: Alexander Graf <agraf@suse.de>
*/
@@ -23,16 +24,6 @@
#include <asm/page.h>
#include <asm/asm-offsets.h>
-/* Hypercall entry point. Will be patched with device tree instructions. */
-
-.global kvm_hypercall_start
-kvm_hypercall_start:
- li r3, -1
- nop
- nop
- nop
- blr
-
#define KVM_MAGIC_PAGE (-4096)
#ifdef CONFIG_64BIT
@@ -65,6 +56,9 @@ kvm_hypercall_start:
shared->critical == r1 and r2 is always != r1 */ \
STL64(r2, KVM_MAGIC_PAGE + KVM_MAGIC_CRITICAL, 0);
+.global kvm_template_start
+kvm_template_start:
+
.global kvm_emulate_mtmsrd
kvm_emulate_mtmsrd:
@@ -128,7 +122,7 @@ kvm_emulate_mtmsrd_len:
.long (kvm_emulate_mtmsrd_end - kvm_emulate_mtmsrd) / 4
-#define MSR_SAFE_BITS (MSR_EE | MSR_CE | MSR_ME | MSR_RI)
+#define MSR_SAFE_BITS (MSR_EE | MSR_RI)
#define MSR_CRITICAL_BITS ~MSR_SAFE_BITS
.global kvm_emulate_mtmsr
@@ -167,6 +161,9 @@ maybe_stay_in_guest:
kvm_emulate_mtmsr_reg2:
ori r30, r0, 0
+ /* Put MSR into magic page because we don't call mtmsr */
+ STL64(r30, KVM_MAGIC_PAGE + KVM_MAGIC_MSR, 0)
+
/* Check if we have to fetch an interrupt */
lwz r31, (KVM_MAGIC_PAGE + KVM_MAGIC_INT)(0)
cmpwi r31, 0
@@ -174,15 +171,10 @@ kvm_emulate_mtmsr_reg2:
/* Check if we may trigger an interrupt */
andi. r31, r30, MSR_EE
- beq no_mtmsr
-
- b do_mtmsr
+ bne do_mtmsr
no_mtmsr:
- /* Put MSR into magic page because we don't call mtmsr */
- STL64(r30, KVM_MAGIC_PAGE + KVM_MAGIC_MSR, 0)
-
SCRATCH_RESTORE
/* Go back to caller */
@@ -210,24 +202,80 @@ kvm_emulate_mtmsr_orig_ins_offs:
kvm_emulate_mtmsr_len:
.long (kvm_emulate_mtmsr_end - kvm_emulate_mtmsr) / 4
+/* also used for wrteei 1 */
+.global kvm_emulate_wrtee
+kvm_emulate_wrtee:
+
+ SCRATCH_SAVE
+ /* Fetch old MSR in r31 */
+ LL64(r31, KVM_MAGIC_PAGE + KVM_MAGIC_MSR, 0)
-.global kvm_emulate_wrteei
-kvm_emulate_wrteei:
+ /* Insert new MSR[EE] */
+kvm_emulate_wrtee_reg:
+ ori r30, r0, 0
+ rlwimi r31, r30, 0, MSR_EE
+
+ /*
+ * If MSR[EE] is now set, check for a pending interrupt.
+ * We could skip this if MSR[EE] was already on, but that
+ * should be rare, so don't bother.
+ */
+ andi. r30, r30, MSR_EE
+
+ /* Put MSR into magic page because we don't call wrtee */
+ STL64(r31, KVM_MAGIC_PAGE + KVM_MAGIC_MSR, 0)
+ beq no_wrtee
+
+ /* Check if we have to fetch an interrupt */
+ lwz r30, (KVM_MAGIC_PAGE + KVM_MAGIC_INT)(0)
+ cmpwi r30, 0
+ bne do_wrtee
+
+no_wrtee:
+ SCRATCH_RESTORE
+
+ /* Go back to caller */
+kvm_emulate_wrtee_branch:
+ b .
+
+do_wrtee:
+ SCRATCH_RESTORE
+
+ /* Just fire off the wrtee if it's critical */
+kvm_emulate_wrtee_orig_ins:
+ wrtee r0
+
+ b kvm_emulate_wrtee_branch
+
+kvm_emulate_wrtee_end:
+
+.global kvm_emulate_wrtee_branch_offs
+kvm_emulate_wrtee_branch_offs:
+ .long (kvm_emulate_wrtee_branch - kvm_emulate_wrtee) / 4
+
+.global kvm_emulate_wrtee_reg_offs
+kvm_emulate_wrtee_reg_offs:
+ .long (kvm_emulate_wrtee_reg - kvm_emulate_wrtee) / 4
+
+.global kvm_emulate_wrtee_orig_ins_offs
+kvm_emulate_wrtee_orig_ins_offs:
+ .long (kvm_emulate_wrtee_orig_ins - kvm_emulate_wrtee) / 4
+
+.global kvm_emulate_wrtee_len
+kvm_emulate_wrtee_len:
+ .long (kvm_emulate_wrtee_end - kvm_emulate_wrtee) / 4
+
+.global kvm_emulate_wrteei_0
+kvm_emulate_wrteei_0:
SCRATCH_SAVE
/* Fetch old MSR in r31 */
LL64(r31, KVM_MAGIC_PAGE + KVM_MAGIC_MSR, 0)
/* Remove MSR_EE from old MSR */
- li r30, 0
- ori r30, r30, MSR_EE
- andc r31, r31, r30
-
- /* OR new MSR_EE onto the old MSR */
-kvm_emulate_wrteei_ee:
- ori r31, r31, 0
+ rlwinm r31, r31, 0, ~MSR_EE
/* Write new MSR value back */
STL64(r31, KVM_MAGIC_PAGE + KVM_MAGIC_MSR, 0)
@@ -235,22 +283,17 @@ kvm_emulate_wrteei_ee:
SCRATCH_RESTORE
/* Go back to caller */
-kvm_emulate_wrteei_branch:
+kvm_emulate_wrteei_0_branch:
b .
-kvm_emulate_wrteei_end:
-
-.global kvm_emulate_wrteei_branch_offs
-kvm_emulate_wrteei_branch_offs:
- .long (kvm_emulate_wrteei_branch - kvm_emulate_wrteei) / 4
+kvm_emulate_wrteei_0_end:
-.global kvm_emulate_wrteei_ee_offs
-kvm_emulate_wrteei_ee_offs:
- .long (kvm_emulate_wrteei_ee - kvm_emulate_wrteei) / 4
-
-.global kvm_emulate_wrteei_len
-kvm_emulate_wrteei_len:
- .long (kvm_emulate_wrteei_end - kvm_emulate_wrteei) / 4
+.global kvm_emulate_wrteei_0_branch_offs
+kvm_emulate_wrteei_0_branch_offs:
+ .long (kvm_emulate_wrteei_0_branch - kvm_emulate_wrteei_0) / 4
+.global kvm_emulate_wrteei_0_len
+kvm_emulate_wrteei_0_len:
+ .long (kvm_emulate_wrteei_0_end - kvm_emulate_wrteei_0) / 4
.global kvm_emulate_mtsrin
kvm_emulate_mtsrin:
@@ -300,3 +343,6 @@ kvm_emulate_mtsrin_orig_ins_offs:
.global kvm_emulate_mtsrin_len
kvm_emulate_mtsrin_len:
.long (kvm_emulate_mtsrin_end - kvm_emulate_mtsrin) / 4
+
+.global kvm_template_end
+kvm_template_end:
diff --git a/arch/powerpc/kernel/legacy_serial.c b/arch/powerpc/kernel/legacy_serial.c
index bedd12e1cfb..936258881c9 100644
--- a/arch/powerpc/kernel/legacy_serial.c
+++ b/arch/powerpc/kernel/legacy_serial.c
@@ -35,7 +35,7 @@ static struct legacy_serial_info {
phys_addr_t taddr;
} legacy_serial_infos[MAX_LEGACY_SERIAL_PORTS];
-static struct __initdata of_device_id legacy_serial_parents[] = {
+static struct of_device_id legacy_serial_parents[] __initdata = {
{.type = "soc",},
{.type = "tsi-bridge",},
{.type = "opb", },
@@ -48,6 +48,9 @@ static struct __initdata of_device_id legacy_serial_parents[] = {
static unsigned int legacy_serial_count;
static int legacy_serial_console = -1;
+static const upf_t legacy_port_flags = UPF_BOOT_AUTOCONF | UPF_SKIP_TEST |
+ UPF_SHARE_IRQ | UPF_FIXED_PORT;
+
static unsigned int tsi_serial_in(struct uart_port *p, int offset)
{
unsigned int tmp;
@@ -71,8 +74,9 @@ static int __init add_legacy_port(struct device_node *np, int want_index,
phys_addr_t taddr, unsigned long irq,
upf_t flags, int irq_check_parent)
{
- const __be32 *clk, *spd;
+ const __be32 *clk, *spd, *rs;
u32 clock = BASE_BAUD * 16;
+ u32 shift = 0;
int index;
/* get clock freq. if present */
@@ -83,6 +87,11 @@ static int __init add_legacy_port(struct device_node *np, int want_index,
/* get default speed if present */
spd = of_get_property(np, "current-speed", NULL);
+ /* get register shift if present */
+ rs = of_get_property(np, "reg-shift", NULL);
+ if (rs && *rs)
+ shift = be32_to_cpup(rs);
+
/* If we have a location index, then try to use it */
if (want_index >= 0 && want_index < MAX_LEGACY_SERIAL_PORTS)
index = want_index;
@@ -99,7 +108,7 @@ static int __init add_legacy_port(struct device_node *np, int want_index,
legacy_serial_count = index + 1;
/* Check if there is a port who already claimed our slot */
- if (legacy_serial_infos[index].np != 0) {
+ if (legacy_serial_infos[index].np != NULL) {
/* if we still have some room, move it, else override */
if (legacy_serial_count < MAX_LEGACY_SERIAL_PORTS) {
printk(KERN_DEBUG "Moved legacy port %d -> %d\n",
@@ -126,6 +135,7 @@ static int __init add_legacy_port(struct device_node *np, int want_index,
legacy_serial_ports[index].uartclk = clock;
legacy_serial_ports[index].irq = irq;
legacy_serial_ports[index].flags = flags;
+ legacy_serial_ports[index].regshift = shift;
legacy_serial_infos[index].taddr = taddr;
legacy_serial_infos[index].np = of_node_get(np);
legacy_serial_infos[index].clock = clock;
@@ -152,9 +162,7 @@ static int __init add_legacy_soc_port(struct device_node *np,
struct device_node *soc_dev)
{
u64 addr;
- const u32 *addrp;
- upf_t flags = UPF_BOOT_AUTOCONF | UPF_SKIP_TEST | UPF_SHARE_IRQ
- | UPF_FIXED_PORT;
+ const __be32 *addrp;
struct device_node *tsi = of_get_parent(np);
/* We only support ports that have a clock frequency properly
@@ -163,9 +171,8 @@ static int __init add_legacy_soc_port(struct device_node *np,
if (of_get_property(np, "clock-frequency", NULL) == NULL)
return -1;
- /* if reg-shift or offset, don't try to use it */
- if ((of_get_property(np, "reg-shift", NULL) != NULL) ||
- (of_get_property(np, "reg-offset", NULL) != NULL))
+ /* if reg-offset don't try to use it */
+ if ((of_get_property(np, "reg-offset", NULL) != NULL))
return -1;
/* if rtas uses this device, don't try to use it as well */
@@ -185,9 +192,11 @@ static int __init add_legacy_soc_port(struct device_node *np,
* IO port value. It will be fixed up later along with the irq
*/
if (tsi && !strcmp(tsi->type, "tsi-bridge"))
- return add_legacy_port(np, -1, UPIO_TSI, addr, addr, NO_IRQ, flags, 0);
+ return add_legacy_port(np, -1, UPIO_TSI, addr, addr,
+ NO_IRQ, legacy_port_flags, 0);
else
- return add_legacy_port(np, -1, UPIO_MEM, addr, addr, NO_IRQ, flags, 0);
+ return add_legacy_port(np, -1, UPIO_MEM, addr, addr,
+ NO_IRQ, legacy_port_flags, 0);
}
static int __init add_legacy_isa_port(struct device_node *np,
@@ -221,14 +230,19 @@ static int __init add_legacy_isa_port(struct device_node *np,
/* Translate ISA address. If it fails, we still register the port
* with no translated address so that it can be picked up as an IO
* port later by the serial driver
+ *
+ * Note: Don't even try on P8 lpc, we know it's not directly mapped
*/
- taddr = of_translate_address(np, reg);
- if (taddr == OF_BAD_ADDR)
+ if (!of_device_is_compatible(isa_brg, "ibm,power8-lpc")) {
+ taddr = of_translate_address(np, reg);
+ if (taddr == OF_BAD_ADDR)
+ taddr = 0;
+ } else
taddr = 0;
/* Add port, irq will be dealt with later */
- return add_legacy_port(np, index, UPIO_PORT, be32_to_cpu(reg[1]), taddr,
- NO_IRQ, UPF_BOOT_AUTOCONF, 0);
+ return add_legacy_port(np, index, UPIO_PORT, be32_to_cpu(reg[1]),
+ taddr, NO_IRQ, legacy_port_flags, 0);
}
@@ -237,7 +251,7 @@ static int __init add_legacy_pci_port(struct device_node *np,
struct device_node *pci_dev)
{
u64 addr, base;
- const u32 *addrp;
+ const __be32 *addrp;
unsigned int flags;
int iotype, index = -1, lindex = 0;
@@ -270,7 +284,7 @@ static int __init add_legacy_pci_port(struct device_node *np,
if (iotype == UPIO_MEM)
base = addr;
else
- base = addrp[2];
+ base = of_read_number(&addrp[2], 1);
/* Try to guess an index... If we have subdevices of the pci dev,
* we get to their "reg" property
@@ -301,25 +315,40 @@ static int __init add_legacy_pci_port(struct device_node *np,
* IO port value. It will be fixed up later along with the irq
*/
return add_legacy_port(np, index, iotype, base, addr, NO_IRQ,
- UPF_BOOT_AUTOCONF, np != pci_dev);
+ legacy_port_flags, np != pci_dev);
}
#endif
static void __init setup_legacy_serial_console(int console)
{
- struct legacy_serial_info *info =
- &legacy_serial_infos[console];
+ struct legacy_serial_info *info = &legacy_serial_infos[console];
+ struct plat_serial8250_port *port = &legacy_serial_ports[console];
void __iomem *addr;
+ unsigned int stride;
- if (info->taddr == 0)
- return;
- addr = ioremap(info->taddr, 0x1000);
- if (addr == NULL)
- return;
+ stride = 1 << port->regshift;
+
+ /* Check if a translated MMIO address has been found */
+ if (info->taddr) {
+ addr = ioremap(info->taddr, 0x1000);
+ if (addr == NULL)
+ return;
+ udbg_uart_init_mmio(addr, stride);
+ } else {
+ /* Check if it's PIO and we support untranslated PIO */
+ if (port->iotype == UPIO_PORT && isa_io_special)
+ udbg_uart_init_pio(port->iobase, stride);
+ else
+ return;
+ }
+
+ /* Try to query the current speed */
if (info->speed == 0)
- info->speed = udbg_probe_uart_speed(addr, info->clock);
+ info->speed = udbg_probe_uart_speed(info->clock);
+
+ /* Set it up */
DBG("default console speed = %d\n", info->speed);
- udbg_init_uart(addr, info->speed, info->clock);
+ udbg_uart_setup(info->speed, info->clock);
}
/*
@@ -367,10 +396,13 @@ void __init find_legacy_serial_ports(void)
/* Next, fill our array with ISA ports */
for_each_node_by_type(np, "serial") {
struct device_node *isa = of_get_parent(np);
- if (isa && !strcmp(isa->name, "isa")) {
- index = add_legacy_isa_port(np, isa);
- if (index >= 0 && np == stdout)
- legacy_serial_console = index;
+ if (isa && (!strcmp(isa->name, "isa") ||
+ !strcmp(isa->name, "lpc"))) {
+ if (of_device_is_available(np)) {
+ index = add_legacy_isa_port(np, isa);
+ if (index >= 0 && np == stdout)
+ legacy_serial_console = index;
+ }
}
of_node_put(isa);
}
@@ -387,7 +419,7 @@ void __init find_legacy_serial_ports(void)
of_node_put(parent);
continue;
}
- /* Check for known pciclass, and also check wether we have
+ /* Check for known pciclass, and also check whether we have
* a device with child nodes for ports or not
*/
if (of_device_is_compatible(np, "pciclass,0700") ||
diff --git a/arch/powerpc/kernel/lparcfg.c b/arch/powerpc/kernel/lparcfg.c
deleted file mode 100644
index 578f35f1872..00000000000
--- a/arch/powerpc/kernel/lparcfg.c
+++ /dev/null
@@ -1,813 +0,0 @@
-/*
- * PowerPC64 LPAR Configuration Information Driver
- *
- * Dave Engebretsen engebret@us.ibm.com
- * Copyright (c) 2003 Dave Engebretsen
- * Will Schmidt willschm@us.ibm.com
- * SPLPAR updates, Copyright (c) 2003 Will Schmidt IBM Corporation.
- * seq_file updates, Copyright (c) 2004 Will Schmidt IBM Corporation.
- * Nathan Lynch nathanl@austin.ibm.com
- * Added lparcfg_write, Copyright (C) 2004 Nathan Lynch IBM Corporation.
- *
- * 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 driver creates a proc file at /proc/ppc64/lparcfg which contains
- * keyword - value pairs that specify the configuration of the partition.
- */
-
-#include <linux/module.h>
-#include <linux/types.h>
-#include <linux/errno.h>
-#include <linux/proc_fs.h>
-#include <linux/init.h>
-#include <linux/seq_file.h>
-#include <linux/slab.h>
-#include <asm/uaccess.h>
-#include <asm/iseries/hv_lp_config.h>
-#include <asm/lppaca.h>
-#include <asm/hvcall.h>
-#include <asm/firmware.h>
-#include <asm/rtas.h>
-#include <asm/system.h>
-#include <asm/time.h>
-#include <asm/prom.h>
-#include <asm/vdso_datapage.h>
-#include <asm/vio.h>
-#include <asm/mmu.h>
-
-#define MODULE_VERS "1.9"
-#define MODULE_NAME "lparcfg"
-
-/* #define LPARCFG_DEBUG */
-
-static struct proc_dir_entry *proc_ppc64_lparcfg;
-
-/*
- * Track sum of all purrs across all processors. This is used to further
- * calculate usage values by different applications
- */
-static unsigned long get_purr(void)
-{
- unsigned long sum_purr = 0;
- int cpu;
-
- for_each_possible_cpu(cpu) {
- if (firmware_has_feature(FW_FEATURE_ISERIES))
- sum_purr += lppaca_of(cpu).emulated_time_base;
- else {
- struct cpu_usage *cu;
-
- cu = &per_cpu(cpu_usage_array, cpu);
- sum_purr += cu->current_tb;
- }
- }
- return sum_purr;
-}
-
-#ifdef CONFIG_PPC_ISERIES
-
-/*
- * Methods used to fetch LPAR data when running on an iSeries platform.
- */
-static int iseries_lparcfg_data(struct seq_file *m, void *v)
-{
- unsigned long pool_id;
- int shared, entitled_capacity, max_entitled_capacity;
- int processors, max_processors;
- unsigned long purr = get_purr();
-
- shared = (int)(local_paca->lppaca_ptr->shared_proc);
-
- seq_printf(m, "system_active_processors=%d\n",
- (int)HvLpConfig_getSystemPhysicalProcessors());
-
- seq_printf(m, "system_potential_processors=%d\n",
- (int)HvLpConfig_getSystemPhysicalProcessors());
-
- processors = (int)HvLpConfig_getPhysicalProcessors();
- seq_printf(m, "partition_active_processors=%d\n", processors);
-
- max_processors = (int)HvLpConfig_getMaxPhysicalProcessors();
- seq_printf(m, "partition_potential_processors=%d\n", max_processors);
-
- if (shared) {
- entitled_capacity = HvLpConfig_getSharedProcUnits();
- max_entitled_capacity = HvLpConfig_getMaxSharedProcUnits();
- } else {
- entitled_capacity = processors * 100;
- max_entitled_capacity = max_processors * 100;
- }
- seq_printf(m, "partition_entitled_capacity=%d\n", entitled_capacity);
-
- seq_printf(m, "partition_max_entitled_capacity=%d\n",
- max_entitled_capacity);
-
- if (shared) {
- pool_id = HvLpConfig_getSharedPoolIndex();
- seq_printf(m, "pool=%d\n", (int)pool_id);
- seq_printf(m, "pool_capacity=%d\n",
- (int)(HvLpConfig_getNumProcsInSharedPool(pool_id) *
- 100));
- seq_printf(m, "purr=%ld\n", purr);
- }
-
- seq_printf(m, "shared_processor_mode=%d\n", shared);
-
- return 0;
-}
-
-#else /* CONFIG_PPC_ISERIES */
-
-static int iseries_lparcfg_data(struct seq_file *m, void *v)
-{
- return 0;
-}
-
-#endif /* CONFIG_PPC_ISERIES */
-
-#ifdef CONFIG_PPC_PSERIES
-/*
- * Methods used to fetch LPAR data when running on a pSeries platform.
- */
-
-struct hvcall_ppp_data {
- u64 entitlement;
- u64 unallocated_entitlement;
- u16 group_num;
- u16 pool_num;
- u8 capped;
- u8 weight;
- u8 unallocated_weight;
- u16 active_procs_in_pool;
- u16 active_system_procs;
- u16 phys_platform_procs;
- u32 max_proc_cap_avail;
- u32 entitled_proc_cap_avail;
-};
-
-/*
- * H_GET_PPP hcall returns info in 4 parms.
- * entitled_capacity,unallocated_capacity,
- * aggregation, resource_capability).
- *
- * R4 = Entitled Processor Capacity Percentage.
- * R5 = Unallocated Processor Capacity Percentage.
- * R6 (AABBCCDDEEFFGGHH).
- * XXXX - reserved (0)
- * XXXX - reserved (0)
- * XXXX - Group Number
- * XXXX - Pool Number.
- * R7 (IIJJKKLLMMNNOOPP).
- * XX - reserved. (0)
- * XX - bit 0-6 reserved (0). bit 7 is Capped indicator.
- * XX - variable processor Capacity Weight
- * XX - Unallocated Variable Processor Capacity Weight.
- * XXXX - Active processors in Physical Processor Pool.
- * XXXX - Processors active on platform.
- * R8 (QQQQRRRRRRSSSSSS). if ibm,partition-performance-parameters-level >= 1
- * XXXX - Physical platform procs allocated to virtualization.
- * XXXXXX - Max procs capacity % available to the partitions pool.
- * XXXXXX - Entitled procs capacity % available to the
- * partitions pool.
- */
-static unsigned int h_get_ppp(struct hvcall_ppp_data *ppp_data)
-{
- unsigned long rc;
- unsigned long retbuf[PLPAR_HCALL9_BUFSIZE];
-
- rc = plpar_hcall9(H_GET_PPP, retbuf);
-
- ppp_data->entitlement = retbuf[0];
- ppp_data->unallocated_entitlement = retbuf[1];
-
- ppp_data->group_num = (retbuf[2] >> 2 * 8) & 0xffff;
- ppp_data->pool_num = retbuf[2] & 0xffff;
-
- ppp_data->capped = (retbuf[3] >> 6 * 8) & 0x01;
- ppp_data->weight = (retbuf[3] >> 5 * 8) & 0xff;
- ppp_data->unallocated_weight = (retbuf[3] >> 4 * 8) & 0xff;
- ppp_data->active_procs_in_pool = (retbuf[3] >> 2 * 8) & 0xffff;
- ppp_data->active_system_procs = retbuf[3] & 0xffff;
-
- ppp_data->phys_platform_procs = retbuf[4] >> 6 * 8;
- ppp_data->max_proc_cap_avail = (retbuf[4] >> 3 * 8) & 0xffffff;
- ppp_data->entitled_proc_cap_avail = retbuf[4] & 0xffffff;
-
- return rc;
-}
-
-static unsigned h_pic(unsigned long *pool_idle_time,
- unsigned long *num_procs)
-{
- unsigned long rc;
- unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
-
- rc = plpar_hcall(H_PIC, retbuf);
-
- *pool_idle_time = retbuf[0];
- *num_procs = retbuf[1];
-
- return rc;
-}
-
-/*
- * parse_ppp_data
- * Parse out the data returned from h_get_ppp and h_pic
- */
-static void parse_ppp_data(struct seq_file *m)
-{
- struct hvcall_ppp_data ppp_data;
- struct device_node *root;
- const int *perf_level;
- int rc;
-
- rc = h_get_ppp(&ppp_data);
- if (rc)
- return;
-
- seq_printf(m, "partition_entitled_capacity=%lld\n",
- ppp_data.entitlement);
- seq_printf(m, "group=%d\n", ppp_data.group_num);
- seq_printf(m, "system_active_processors=%d\n",
- ppp_data.active_system_procs);
-
- /* pool related entries are appropriate for shared configs */
- if (lppaca_of(0).shared_proc) {
- unsigned long pool_idle_time, pool_procs;
-
- seq_printf(m, "pool=%d\n", ppp_data.pool_num);
-
- /* report pool_capacity in percentage */
- seq_printf(m, "pool_capacity=%d\n",
- ppp_data.active_procs_in_pool * 100);
-
- h_pic(&pool_idle_time, &pool_procs);
- seq_printf(m, "pool_idle_time=%ld\n", pool_idle_time);
- seq_printf(m, "pool_num_procs=%ld\n", pool_procs);
- }
-
- seq_printf(m, "unallocated_capacity_weight=%d\n",
- ppp_data.unallocated_weight);
- seq_printf(m, "capacity_weight=%d\n", ppp_data.weight);
- seq_printf(m, "capped=%d\n", ppp_data.capped);
- seq_printf(m, "unallocated_capacity=%lld\n",
- ppp_data.unallocated_entitlement);
-
- /* The last bits of information returned from h_get_ppp are only
- * valid if the ibm,partition-performance-parameters-level
- * property is >= 1.
- */
- root = of_find_node_by_path("/");
- if (root) {
- perf_level = of_get_property(root,
- "ibm,partition-performance-parameters-level",
- NULL);
- if (perf_level && (*perf_level >= 1)) {
- seq_printf(m,
- "physical_procs_allocated_to_virtualization=%d\n",
- ppp_data.phys_platform_procs);
- seq_printf(m, "max_proc_capacity_available=%d\n",
- ppp_data.max_proc_cap_avail);
- seq_printf(m, "entitled_proc_capacity_available=%d\n",
- ppp_data.entitled_proc_cap_avail);
- }
-
- of_node_put(root);
- }
-}
-
-/**
- * parse_mpp_data
- * Parse out data returned from h_get_mpp
- */
-static void parse_mpp_data(struct seq_file *m)
-{
- struct hvcall_mpp_data mpp_data;
- int rc;
-
- rc = h_get_mpp(&mpp_data);
- if (rc)
- return;
-
- seq_printf(m, "entitled_memory=%ld\n", mpp_data.entitled_mem);
-
- if (mpp_data.mapped_mem != -1)
- seq_printf(m, "mapped_entitled_memory=%ld\n",
- mpp_data.mapped_mem);
-
- seq_printf(m, "entitled_memory_group_number=%d\n", mpp_data.group_num);
- seq_printf(m, "entitled_memory_pool_number=%d\n", mpp_data.pool_num);
-
- seq_printf(m, "entitled_memory_weight=%d\n", mpp_data.mem_weight);
- seq_printf(m, "unallocated_entitled_memory_weight=%d\n",
- mpp_data.unallocated_mem_weight);
- seq_printf(m, "unallocated_io_mapping_entitlement=%ld\n",
- mpp_data.unallocated_entitlement);
-
- if (mpp_data.pool_size != -1)
- seq_printf(m, "entitled_memory_pool_size=%ld bytes\n",
- mpp_data.pool_size);
-
- seq_printf(m, "entitled_memory_loan_request=%ld\n",
- mpp_data.loan_request);
-
- seq_printf(m, "backing_memory=%ld bytes\n", mpp_data.backing_mem);
-}
-
-/**
- * parse_mpp_x_data
- * Parse out data returned from h_get_mpp_x
- */
-static void parse_mpp_x_data(struct seq_file *m)
-{
- struct hvcall_mpp_x_data mpp_x_data;
-
- if (!firmware_has_feature(FW_FEATURE_XCMO))
- return;
- if (h_get_mpp_x(&mpp_x_data))
- return;
-
- seq_printf(m, "coalesced_bytes=%ld\n", mpp_x_data.coalesced_bytes);
-
- if (mpp_x_data.pool_coalesced_bytes)
- seq_printf(m, "pool_coalesced_bytes=%ld\n",
- mpp_x_data.pool_coalesced_bytes);
- if (mpp_x_data.pool_purr_cycles)
- seq_printf(m, "coalesce_pool_purr=%ld\n", mpp_x_data.pool_purr_cycles);
- if (mpp_x_data.pool_spurr_cycles)
- seq_printf(m, "coalesce_pool_spurr=%ld\n", mpp_x_data.pool_spurr_cycles);
-}
-
-#define SPLPAR_CHARACTERISTICS_TOKEN 20
-#define SPLPAR_MAXLENGTH 1026*(sizeof(char))
-
-/*
- * parse_system_parameter_string()
- * Retrieve the potential_processors, max_entitled_capacity and friends
- * through the get-system-parameter rtas call. Replace keyword strings as
- * necessary.
- */
-static void parse_system_parameter_string(struct seq_file *m)
-{
- int call_status;
-
- unsigned char *local_buffer = kmalloc(SPLPAR_MAXLENGTH, GFP_KERNEL);
- if (!local_buffer) {
- printk(KERN_ERR "%s %s kmalloc failure at line %d\n",
- __FILE__, __func__, __LINE__);
- return;
- }
-
- spin_lock(&rtas_data_buf_lock);
- memset(rtas_data_buf, 0, SPLPAR_MAXLENGTH);
- call_status = rtas_call(rtas_token("ibm,get-system-parameter"), 3, 1,
- NULL,
- SPLPAR_CHARACTERISTICS_TOKEN,
- __pa(rtas_data_buf),
- RTAS_DATA_BUF_SIZE);
- memcpy(local_buffer, rtas_data_buf, SPLPAR_MAXLENGTH);
- spin_unlock(&rtas_data_buf_lock);
-
- if (call_status != 0) {
- printk(KERN_INFO
- "%s %s Error calling get-system-parameter (0x%x)\n",
- __FILE__, __func__, call_status);
- } else {
- int splpar_strlen;
- int idx, w_idx;
- char *workbuffer = kzalloc(SPLPAR_MAXLENGTH, GFP_KERNEL);
- if (!workbuffer) {
- printk(KERN_ERR "%s %s kmalloc failure at line %d\n",
- __FILE__, __func__, __LINE__);
- kfree(local_buffer);
- return;
- }
-#ifdef LPARCFG_DEBUG
- printk(KERN_INFO "success calling get-system-parameter\n");
-#endif
- splpar_strlen = local_buffer[0] * 256 + local_buffer[1];
- local_buffer += 2; /* step over strlen value */
-
- w_idx = 0;
- idx = 0;
- while ((*local_buffer) && (idx < splpar_strlen)) {
- workbuffer[w_idx++] = local_buffer[idx++];
- if ((local_buffer[idx] == ',')
- || (local_buffer[idx] == '\0')) {
- workbuffer[w_idx] = '\0';
- if (w_idx) {
- /* avoid the empty string */
- seq_printf(m, "%s\n", workbuffer);
- }
- memset(workbuffer, 0, SPLPAR_MAXLENGTH);
- idx++; /* skip the comma */
- w_idx = 0;
- } else if (local_buffer[idx] == '=') {
- /* code here to replace workbuffer contents
- with different keyword strings */
- if (0 == strcmp(workbuffer, "MaxEntCap")) {
- strcpy(workbuffer,
- "partition_max_entitled_capacity");
- w_idx = strlen(workbuffer);
- }
- if (0 == strcmp(workbuffer, "MaxPlatProcs")) {
- strcpy(workbuffer,
- "system_potential_processors");
- w_idx = strlen(workbuffer);
- }
- }
- }
- kfree(workbuffer);
- local_buffer -= 2; /* back up over strlen value */
- }
- kfree(local_buffer);
-}
-
-/* Return the number of processors in the system.
- * This function reads through the device tree and counts
- * the virtual processors, this does not include threads.
- */
-static int lparcfg_count_active_processors(void)
-{
- struct device_node *cpus_dn = NULL;
- int count = 0;
-
- while ((cpus_dn = of_find_node_by_type(cpus_dn, "cpu"))) {
-#ifdef LPARCFG_DEBUG
- printk(KERN_ERR "cpus_dn %p\n", cpus_dn);
-#endif
- count++;
- }
- return count;
-}
-
-static void pseries_cmo_data(struct seq_file *m)
-{
- int cpu;
- unsigned long cmo_faults = 0;
- unsigned long cmo_fault_time = 0;
-
- seq_printf(m, "cmo_enabled=%d\n", firmware_has_feature(FW_FEATURE_CMO));
-
- if (!firmware_has_feature(FW_FEATURE_CMO))
- return;
-
- for_each_possible_cpu(cpu) {
- cmo_faults += lppaca_of(cpu).cmo_faults;
- cmo_fault_time += lppaca_of(cpu).cmo_fault_time;
- }
-
- seq_printf(m, "cmo_faults=%lu\n", cmo_faults);
- seq_printf(m, "cmo_fault_time_usec=%lu\n",
- cmo_fault_time / tb_ticks_per_usec);
- seq_printf(m, "cmo_primary_psp=%d\n", cmo_get_primary_psp());
- seq_printf(m, "cmo_secondary_psp=%d\n", cmo_get_secondary_psp());
- seq_printf(m, "cmo_page_size=%lu\n", cmo_get_page_size());
-}
-
-static void splpar_dispatch_data(struct seq_file *m)
-{
- int cpu;
- unsigned long dispatches = 0;
- unsigned long dispatch_dispersions = 0;
-
- for_each_possible_cpu(cpu) {
- dispatches += lppaca_of(cpu).yield_count;
- dispatch_dispersions += lppaca_of(cpu).dispersion_count;
- }
-
- seq_printf(m, "dispatches=%lu\n", dispatches);
- seq_printf(m, "dispatch_dispersions=%lu\n", dispatch_dispersions);
-}
-
-static void parse_em_data(struct seq_file *m)
-{
- unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
-
- if (plpar_hcall(H_GET_EM_PARMS, retbuf) == H_SUCCESS)
- seq_printf(m, "power_mode_data=%016lx\n", retbuf[0]);
-}
-
-static int pseries_lparcfg_data(struct seq_file *m, void *v)
-{
- int partition_potential_processors;
- int partition_active_processors;
- struct device_node *rtas_node;
- const int *lrdrp = NULL;
-
- rtas_node = of_find_node_by_path("/rtas");
- if (rtas_node)
- lrdrp = of_get_property(rtas_node, "ibm,lrdr-capacity", NULL);
-
- if (lrdrp == NULL) {
- partition_potential_processors = vdso_data->processorCount;
- } else {
- partition_potential_processors = *(lrdrp + 4);
- }
- of_node_put(rtas_node);
-
- partition_active_processors = lparcfg_count_active_processors();
-
- if (firmware_has_feature(FW_FEATURE_SPLPAR)) {
- /* this call handles the ibm,get-system-parameter contents */
- parse_system_parameter_string(m);
- parse_ppp_data(m);
- parse_mpp_data(m);
- parse_mpp_x_data(m);
- pseries_cmo_data(m);
- splpar_dispatch_data(m);
-
- seq_printf(m, "purr=%ld\n", get_purr());
- } else { /* non SPLPAR case */
-
- seq_printf(m, "system_active_processors=%d\n",
- partition_potential_processors);
-
- seq_printf(m, "system_potential_processors=%d\n",
- partition_potential_processors);
-
- seq_printf(m, "partition_max_entitled_capacity=%d\n",
- partition_potential_processors * 100);
-
- seq_printf(m, "partition_entitled_capacity=%d\n",
- partition_active_processors * 100);
- }
-
- seq_printf(m, "partition_active_processors=%d\n",
- partition_active_processors);
-
- seq_printf(m, "partition_potential_processors=%d\n",
- partition_potential_processors);
-
- seq_printf(m, "shared_processor_mode=%d\n", lppaca_of(0).shared_proc);
-
- seq_printf(m, "slb_size=%d\n", mmu_slb_size);
-
- parse_em_data(m);
-
- return 0;
-}
-
-static ssize_t update_ppp(u64 *entitlement, u8 *weight)
-{
- struct hvcall_ppp_data ppp_data;
- u8 new_weight;
- u64 new_entitled;
- ssize_t retval;
-
- /* Get our current parameters */
- retval = h_get_ppp(&ppp_data);
- if (retval)
- return retval;
-
- if (entitlement) {
- new_weight = ppp_data.weight;
- new_entitled = *entitlement;
- } else if (weight) {
- new_weight = *weight;
- new_entitled = ppp_data.entitlement;
- } else
- return -EINVAL;
-
- pr_debug("%s: current_entitled = %llu, current_weight = %u\n",
- __func__, ppp_data.entitlement, ppp_data.weight);
-
- pr_debug("%s: new_entitled = %llu, new_weight = %u\n",
- __func__, new_entitled, new_weight);
-
- retval = plpar_hcall_norets(H_SET_PPP, new_entitled, new_weight);
- return retval;
-}
-
-/**
- * update_mpp
- *
- * Update the memory entitlement and weight for the partition. Caller must
- * specify either a new entitlement or weight, not both, to be updated
- * since the h_set_mpp call takes both entitlement and weight as parameters.
- */
-static ssize_t update_mpp(u64 *entitlement, u8 *weight)
-{
- struct hvcall_mpp_data mpp_data;
- u64 new_entitled;
- u8 new_weight;
- ssize_t rc;
-
- if (entitlement) {
- /* Check with vio to ensure the new memory entitlement
- * can be handled.
- */
- rc = vio_cmo_entitlement_update(*entitlement);
- if (rc)
- return rc;
- }
-
- rc = h_get_mpp(&mpp_data);
- if (rc)
- return rc;
-
- if (entitlement) {
- new_weight = mpp_data.mem_weight;
- new_entitled = *entitlement;
- } else if (weight) {
- new_weight = *weight;
- new_entitled = mpp_data.entitled_mem;
- } else
- return -EINVAL;
-
- pr_debug("%s: current_entitled = %lu, current_weight = %u\n",
- __func__, mpp_data.entitled_mem, mpp_data.mem_weight);
-
- pr_debug("%s: new_entitled = %llu, new_weight = %u\n",
- __func__, new_entitled, new_weight);
-
- rc = plpar_hcall_norets(H_SET_MPP, new_entitled, new_weight);
- return rc;
-}
-
-/*
- * Interface for changing system parameters (variable capacity weight
- * and entitled capacity). Format of input is "param_name=value";
- * anything after value is ignored. Valid parameters at this time are
- * "partition_entitled_capacity" and "capacity_weight". We use
- * H_SET_PPP to alter parameters.
- *
- * This function should be invoked only on systems with
- * FW_FEATURE_SPLPAR.
- */
-static ssize_t lparcfg_write(struct file *file, const char __user * buf,
- size_t count, loff_t * off)
-{
- int kbuf_sz = 64;
- char kbuf[kbuf_sz];
- char *tmp;
- u64 new_entitled, *new_entitled_ptr = &new_entitled;
- u8 new_weight, *new_weight_ptr = &new_weight;
- ssize_t retval;
-
- if (!firmware_has_feature(FW_FEATURE_SPLPAR) ||
- firmware_has_feature(FW_FEATURE_ISERIES))
- return -EINVAL;
-
- if (count > kbuf_sz)
- return -EINVAL;
-
- if (copy_from_user(kbuf, buf, count))
- return -EFAULT;
-
- kbuf[count - 1] = '\0';
- tmp = strchr(kbuf, '=');
- if (!tmp)
- return -EINVAL;
-
- *tmp++ = '\0';
-
- if (!strcmp(kbuf, "partition_entitled_capacity")) {
- char *endp;
- *new_entitled_ptr = (u64) simple_strtoul(tmp, &endp, 10);
- if (endp == tmp)
- return -EINVAL;
-
- retval = update_ppp(new_entitled_ptr, NULL);
- } else if (!strcmp(kbuf, "capacity_weight")) {
- char *endp;
- *new_weight_ptr = (u8) simple_strtoul(tmp, &endp, 10);
- if (endp == tmp)
- return -EINVAL;
-
- retval = update_ppp(NULL, new_weight_ptr);
- } else if (!strcmp(kbuf, "entitled_memory")) {
- char *endp;
- *new_entitled_ptr = (u64) simple_strtoul(tmp, &endp, 10);
- if (endp == tmp)
- return -EINVAL;
-
- retval = update_mpp(new_entitled_ptr, NULL);
- } else if (!strcmp(kbuf, "entitled_memory_weight")) {
- char *endp;
- *new_weight_ptr = (u8) simple_strtoul(tmp, &endp, 10);
- if (endp == tmp)
- return -EINVAL;
-
- retval = update_mpp(NULL, new_weight_ptr);
- } else
- return -EINVAL;
-
- if (retval == H_SUCCESS || retval == H_CONSTRAINED) {
- retval = count;
- } else if (retval == H_BUSY) {
- retval = -EBUSY;
- } else if (retval == H_HARDWARE) {
- retval = -EIO;
- } else if (retval == H_PARAMETER) {
- retval = -EINVAL;
- }
-
- return retval;
-}
-
-#else /* CONFIG_PPC_PSERIES */
-
-static int pseries_lparcfg_data(struct seq_file *m, void *v)
-{
- return 0;
-}
-
-static ssize_t lparcfg_write(struct file *file, const char __user * buf,
- size_t count, loff_t * off)
-{
- return -EINVAL;
-}
-
-#endif /* CONFIG_PPC_PSERIES */
-
-static int lparcfg_data(struct seq_file *m, void *v)
-{
- struct device_node *rootdn;
- const char *model = "";
- const char *system_id = "";
- const char *tmp;
- const unsigned int *lp_index_ptr;
- unsigned int lp_index = 0;
-
- seq_printf(m, "%s %s\n", MODULE_NAME, MODULE_VERS);
-
- rootdn = of_find_node_by_path("/");
- if (rootdn) {
- tmp = of_get_property(rootdn, "model", NULL);
- if (tmp) {
- model = tmp;
- /* Skip "IBM," - see platforms/iseries/dt.c */
- if (firmware_has_feature(FW_FEATURE_ISERIES))
- model += 4;
- }
- tmp = of_get_property(rootdn, "system-id", NULL);
- if (tmp) {
- system_id = tmp;
- /* Skip "IBM," - see platforms/iseries/dt.c */
- if (firmware_has_feature(FW_FEATURE_ISERIES))
- system_id += 4;
- }
- lp_index_ptr = of_get_property(rootdn, "ibm,partition-no",
- NULL);
- if (lp_index_ptr)
- lp_index = *lp_index_ptr;
- of_node_put(rootdn);
- }
- seq_printf(m, "serial_number=%s\n", system_id);
- seq_printf(m, "system_type=%s\n", model);
- seq_printf(m, "partition_id=%d\n", (int)lp_index);
-
- if (firmware_has_feature(FW_FEATURE_ISERIES))
- return iseries_lparcfg_data(m, v);
- return pseries_lparcfg_data(m, v);
-}
-
-static int lparcfg_open(struct inode *inode, struct file *file)
-{
- return single_open(file, lparcfg_data, NULL);
-}
-
-static const struct file_operations lparcfg_fops = {
- .owner = THIS_MODULE,
- .read = seq_read,
- .write = lparcfg_write,
- .open = lparcfg_open,
- .release = single_release,
- .llseek = seq_lseek,
-};
-
-static int __init lparcfg_init(void)
-{
- struct proc_dir_entry *ent;
- umode_t mode = S_IRUSR | S_IRGRP | S_IROTH;
-
- /* Allow writing if we have FW_FEATURE_SPLPAR */
- if (firmware_has_feature(FW_FEATURE_SPLPAR) &&
- !firmware_has_feature(FW_FEATURE_ISERIES))
- mode |= S_IWUSR;
-
- ent = proc_create("powerpc/lparcfg", mode, NULL, &lparcfg_fops);
- if (!ent) {
- printk(KERN_ERR "Failed to create powerpc/lparcfg\n");
- return -EIO;
- }
-
- proc_ppc64_lparcfg = ent;
- return 0;
-}
-
-static void __exit lparcfg_cleanup(void)
-{
- if (proc_ppc64_lparcfg)
- remove_proc_entry("lparcfg", proc_ppc64_lparcfg->parent);
-}
-
-module_init(lparcfg_init);
-module_exit(lparcfg_cleanup);
-MODULE_DESCRIPTION("Interface for LPAR configuration data");
-MODULE_AUTHOR("Dave Engebretsen");
-MODULE_LICENSE("GPL");
diff --git a/arch/powerpc/kernel/machine_kexec.c b/arch/powerpc/kernel/machine_kexec.c
index c957b1202bd..015ae55c186 100644
--- a/arch/powerpc/kernel/machine_kexec.c
+++ b/arch/powerpc/kernel/machine_kexec.c
@@ -18,19 +18,17 @@
#include <linux/ftrace.h>
#include <asm/machdep.h>
+#include <asm/pgalloc.h>
#include <asm/prom.h>
#include <asm/sections.h>
void machine_kexec_mask_interrupts(void) {
unsigned int i;
+ struct irq_desc *desc;
- for_each_irq(i) {
- struct irq_desc *desc = irq_to_desc(i);
+ for_each_irq_desc(i, desc) {
struct irq_chip *chip;
- if (!desc)
- continue;
-
chip = irq_desc_get_chip(desc);
if (!chip)
continue;
@@ -78,6 +76,17 @@ void arch_crash_save_vmcoreinfo(void)
#ifndef CONFIG_NEED_MULTIPLE_NODES
VMCOREINFO_SYMBOL(contig_page_data);
#endif
+#if defined(CONFIG_PPC64) && defined(CONFIG_SPARSEMEM_VMEMMAP)
+ VMCOREINFO_SYMBOL(vmemmap_list);
+ VMCOREINFO_SYMBOL(mmu_vmemmap_psize);
+ VMCOREINFO_SYMBOL(mmu_psize_defs);
+ VMCOREINFO_STRUCT_SIZE(vmemmap_backing);
+ VMCOREINFO_OFFSET(vmemmap_backing, list);
+ VMCOREINFO_OFFSET(vmemmap_backing, phys);
+ VMCOREINFO_OFFSET(vmemmap_backing, virt_addr);
+ VMCOREINFO_STRUCT_SIZE(mmu_psize_def);
+ VMCOREINFO_OFFSET(mmu_psize_def, shift);
+#endif
}
/*
@@ -139,7 +148,7 @@ void __init reserve_crashkernel(void)
* a small SLB (128MB) since the crash kernel needs to place
* itself and some stacks to be in the first segment.
*/
- crashk_res.start = min(0x80000000ULL, (ppc64_rma_size / 2));
+ crashk_res.start = min(0x8000000ULL, (ppc64_rma_size / 2));
#else
crashk_res.start = KDUMP_KERNELBASE;
#endif
@@ -168,7 +177,7 @@ void __init reserve_crashkernel(void)
if (memory_limit && memory_limit <= crashk_res.end) {
memory_limit = crashk_res.end + 1;
printk("Adjusted memory limit for crashkernel, now 0x%llx\n",
- (unsigned long long)memory_limit);
+ memory_limit);
}
printk(KERN_INFO "Reserving %ldMB of memory at %ldMB "
@@ -187,7 +196,9 @@ int overlaps_crashkernel(unsigned long start, unsigned long size)
/* Values we need to export to the second kernel via the device tree. */
static phys_addr_t kernel_end;
+static phys_addr_t crashk_base;
static phys_addr_t crashk_size;
+static unsigned long long mem_limit;
static struct property kernel_end_prop = {
.name = "linux,kernel-end",
@@ -198,7 +209,7 @@ static struct property kernel_end_prop = {
static struct property crashk_base_prop = {
.name = "linux,crashkernel-base",
.length = sizeof(phys_addr_t),
- .value = &crashk_res.start,
+ .value = &crashk_base
};
static struct property crashk_size_prop = {
@@ -207,6 +218,14 @@ static struct property crashk_size_prop = {
.value = &crashk_size,
};
+static struct property memory_limit_prop = {
+ .name = "linux,memory-limit",
+ .length = sizeof(unsigned long long),
+ .value = &mem_limit,
+};
+
+#define cpu_to_be_ulong __PASTE(cpu_to_be, BITS_PER_LONG)
+
static void __init export_crashk_values(struct device_node *node)
{
struct property *prop;
@@ -215,17 +234,25 @@ static void __init export_crashk_values(struct device_node *node)
* be sure what's in them, so remove them. */
prop = of_find_property(node, "linux,crashkernel-base", NULL);
if (prop)
- prom_remove_property(node, prop);
+ of_remove_property(node, prop);
prop = of_find_property(node, "linux,crashkernel-size", NULL);
if (prop)
- prom_remove_property(node, prop);
+ of_remove_property(node, prop);
if (crashk_res.start != 0) {
- prom_add_property(node, &crashk_base_prop);
- crashk_size = resource_size(&crashk_res);
- prom_add_property(node, &crashk_size_prop);
+ crashk_base = cpu_to_be_ulong(crashk_res.start),
+ of_add_property(node, &crashk_base_prop);
+ crashk_size = cpu_to_be_ulong(resource_size(&crashk_res));
+ of_add_property(node, &crashk_size_prop);
}
+
+ /*
+ * memory_limit is required by the kexec-tools to limit the
+ * crash regions to the actual memory used.
+ */
+ mem_limit = cpu_to_be_ulong(memory_limit);
+ of_update_property(node, &memory_limit_prop);
}
static int __init kexec_setup(void)
@@ -240,11 +267,11 @@ static int __init kexec_setup(void)
/* remove any stale properties so ours can be found */
prop = of_find_property(node, kernel_end_prop.name, NULL);
if (prop)
- prom_remove_property(node, prop);
+ of_remove_property(node, prop);
/* information needed by userspace when using default_machine_kexec */
- kernel_end = __pa(_end);
- prom_add_property(node, &kernel_end_prop);
+ kernel_end = cpu_to_be_ulong(__pa(_end));
+ of_add_property(node, &kernel_end_prop);
export_crashk_values(node);
diff --git a/arch/powerpc/kernel/machine_kexec_64.c b/arch/powerpc/kernel/machine_kexec_64.c
index d7f609086a9..879b3aacac3 100644
--- a/arch/powerpc/kernel/machine_kexec_64.c
+++ b/arch/powerpc/kernel/machine_kexec_64.c
@@ -17,6 +17,7 @@
#include <linux/errno.h>
#include <linux/kernel.h>
#include <linux/cpu.h>
+#include <linux/hardirq.h>
#include <asm/page.h>
#include <asm/current.h>
@@ -162,6 +163,8 @@ static int kexec_all_irq_disabled = 0;
static void kexec_smp_down(void *arg)
{
local_irq_disable();
+ hard_irq_disable();
+
mb(); /* make sure our irqs are disabled before we say they are */
get_paca()->kexec_state = KEXEC_STATE_IRQS_OFF;
while(kexec_all_irq_disabled == 0)
@@ -234,7 +237,7 @@ static void wake_offline_cpus(void)
if (!cpu_online(cpu)) {
printk(KERN_INFO "kexec: Waking offline cpu %d.\n",
cpu);
- cpu_up(cpu);
+ WARN_ON(cpu_up(cpu));
}
}
}
@@ -244,6 +247,8 @@ static void kexec_prepare_cpus(void)
wake_offline_cpus();
smp_call_function(kexec_smp_down, NULL, /* wait */0);
local_irq_disable();
+ hard_irq_disable();
+
mb(); /* make sure IRQs are disabled before we say they are */
get_paca()->kexec_state = KEXEC_STATE_IRQS_OFF;
@@ -281,6 +286,7 @@ static void kexec_prepare_cpus(void)
if (ppc_md.kexec_cpu_down)
ppc_md.kexec_cpu_down(0, 0);
local_irq_disable();
+ hard_irq_disable();
}
#endif /* SMP */
@@ -306,7 +312,7 @@ static union thread_union kexec_stack __init_task_data =
*/
struct paca_struct kexec_paca;
-/* Our assembly helper, in kexec_stub.S */
+/* Our assembly helper, in misc_64.S */
extern void kexec_sequence(void *newstack, unsigned long start,
void *image, void *control,
void (*clear_all)(void)) __noreturn;
@@ -330,10 +336,13 @@ void default_machine_kexec(struct kimage *image)
pr_debug("kexec: Starting switchover sequence.\n");
/* switch to a staticly allocated stack. Based on irq stack code.
+ * We setup preempt_count to avoid using VMX in memcpy.
* XXX: the task struct will likely be invalid once we do the copy!
*/
kexec_stack.thread_info.task = current_thread_info()->task;
kexec_stack.thread_info.flags = 0;
+ kexec_stack.thread_info.preempt_count = HARDIRQ_OFFSET;
+ kexec_stack.thread_info.cpu = current_thread_info()->cpu;
/* We need a static PACA, too; copy this CPU's PACA over and switch to
* it. Also poison per_cpu_offset to catch anyone using non-static
@@ -360,6 +369,7 @@ void default_machine_kexec(struct kimage *image)
/* Values we need to export to the second kernel via the device tree. */
static unsigned long htab_base;
+static unsigned long htab_size;
static struct property htab_base_prop = {
.name = "linux,htab-base",
@@ -370,7 +380,7 @@ static struct property htab_base_prop = {
static struct property htab_size_prop = {
.name = "linux,htab-size",
.length = sizeof(unsigned long),
- .value = &htab_size_bytes,
+ .value = &htab_size,
};
static int __init export_htab_values(void)
@@ -389,14 +399,15 @@ static int __init export_htab_values(void)
/* remove any stale propertys so ours can be found */
prop = of_find_property(node, htab_base_prop.name, NULL);
if (prop)
- prom_remove_property(node, prop);
+ of_remove_property(node, prop);
prop = of_find_property(node, htab_size_prop.name, NULL);
if (prop)
- prom_remove_property(node, prop);
+ of_remove_property(node, prop);
- htab_base = __pa(htab_address);
- prom_add_property(node, &htab_base_prop);
- prom_add_property(node, &htab_size_prop);
+ htab_base = cpu_to_be64(__pa(htab_address));
+ of_add_property(node, &htab_base_prop);
+ htab_size = cpu_to_be64(htab_size_bytes);
+ of_add_property(node, &htab_size_prop);
of_node_put(node);
return 0;
diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c
new file mode 100644
index 00000000000..a7fd4cb78b7
--- /dev/null
+++ b/arch/powerpc/kernel/mce.c
@@ -0,0 +1,352 @@
+/*
+ * Machine check exception handling.
+ *
+ * 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.
+ *
+ * Copyright 2013 IBM Corporation
+ * Author: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
+ */
+
+#undef DEBUG
+#define pr_fmt(fmt) "mce: " fmt
+
+#include <linux/types.h>
+#include <linux/ptrace.h>
+#include <linux/percpu.h>
+#include <linux/export.h>
+#include <linux/irq_work.h>
+#include <asm/mce.h>
+
+static DEFINE_PER_CPU(int, mce_nest_count);
+static DEFINE_PER_CPU(struct machine_check_event[MAX_MC_EVT], mce_event);
+
+/* Queue for delayed MCE events. */
+static DEFINE_PER_CPU(int, mce_queue_count);
+static DEFINE_PER_CPU(struct machine_check_event[MAX_MC_EVT], mce_event_queue);
+
+static void machine_check_process_queued_event(struct irq_work *work);
+struct irq_work mce_event_process_work = {
+ .func = machine_check_process_queued_event,
+};
+
+static void mce_set_error_info(struct machine_check_event *mce,
+ struct mce_error_info *mce_err)
+{
+ mce->error_type = mce_err->error_type;
+ switch (mce_err->error_type) {
+ case MCE_ERROR_TYPE_UE:
+ mce->u.ue_error.ue_error_type = mce_err->u.ue_error_type;
+ break;
+ case MCE_ERROR_TYPE_SLB:
+ mce->u.slb_error.slb_error_type = mce_err->u.slb_error_type;
+ break;
+ case MCE_ERROR_TYPE_ERAT:
+ mce->u.erat_error.erat_error_type = mce_err->u.erat_error_type;
+ break;
+ case MCE_ERROR_TYPE_TLB:
+ mce->u.tlb_error.tlb_error_type = mce_err->u.tlb_error_type;
+ break;
+ case MCE_ERROR_TYPE_UNKNOWN:
+ default:
+ break;
+ }
+}
+
+/*
+ * Decode and save high level MCE information into per cpu buffer which
+ * is an array of machine_check_event structure.
+ */
+void save_mce_event(struct pt_regs *regs, long handled,
+ struct mce_error_info *mce_err,
+ uint64_t nip, uint64_t addr)
+{
+ uint64_t srr1;
+ int index = __get_cpu_var(mce_nest_count)++;
+ struct machine_check_event *mce = &__get_cpu_var(mce_event[index]);
+
+ /*
+ * Return if we don't have enough space to log mce event.
+ * mce_nest_count may go beyond MAX_MC_EVT but that's ok,
+ * the check below will stop buffer overrun.
+ */
+ if (index >= MAX_MC_EVT)
+ return;
+
+ /* Populate generic machine check info */
+ mce->version = MCE_V1;
+ mce->srr0 = nip;
+ mce->srr1 = regs->msr;
+ mce->gpr3 = regs->gpr[3];
+ mce->in_use = 1;
+
+ mce->initiator = MCE_INITIATOR_CPU;
+ if (handled)
+ mce->disposition = MCE_DISPOSITION_RECOVERED;
+ else
+ mce->disposition = MCE_DISPOSITION_NOT_RECOVERED;
+ mce->severity = MCE_SEV_ERROR_SYNC;
+
+ srr1 = regs->msr;
+
+ /*
+ * Populate the mce error_type and type-specific error_type.
+ */
+ mce_set_error_info(mce, mce_err);
+
+ if (!addr)
+ return;
+
+ if (mce->error_type == MCE_ERROR_TYPE_TLB) {
+ mce->u.tlb_error.effective_address_provided = true;
+ mce->u.tlb_error.effective_address = addr;
+ } else if (mce->error_type == MCE_ERROR_TYPE_SLB) {
+ mce->u.slb_error.effective_address_provided = true;
+ mce->u.slb_error.effective_address = addr;
+ } else if (mce->error_type == MCE_ERROR_TYPE_ERAT) {
+ mce->u.erat_error.effective_address_provided = true;
+ mce->u.erat_error.effective_address = addr;
+ } else if (mce->error_type == MCE_ERROR_TYPE_UE) {
+ mce->u.ue_error.effective_address_provided = true;
+ mce->u.ue_error.effective_address = addr;
+ }
+ return;
+}
+
+/*
+ * get_mce_event:
+ * mce Pointer to machine_check_event structure to be filled.
+ * release Flag to indicate whether to free the event slot or not.
+ * 0 <= do not release the mce event. Caller will invoke
+ * release_mce_event() once event has been consumed.
+ * 1 <= release the slot.
+ *
+ * return 1 = success
+ * 0 = failure
+ *
+ * get_mce_event() will be called by platform specific machine check
+ * handle routine and in KVM.
+ * When we call get_mce_event(), we are still in interrupt context and
+ * preemption will not be scheduled until ret_from_expect() routine
+ * is called.
+ */
+int get_mce_event(struct machine_check_event *mce, bool release)
+{
+ int index = __get_cpu_var(mce_nest_count) - 1;
+ struct machine_check_event *mc_evt;
+ int ret = 0;
+
+ /* Sanity check */
+ if (index < 0)
+ return ret;
+
+ /* Check if we have MCE info to process. */
+ if (index < MAX_MC_EVT) {
+ mc_evt = &__get_cpu_var(mce_event[index]);
+ /* Copy the event structure and release the original */
+ if (mce)
+ *mce = *mc_evt;
+ if (release)
+ mc_evt->in_use = 0;
+ ret = 1;
+ }
+ /* Decrement the count to free the slot. */
+ if (release)
+ __get_cpu_var(mce_nest_count)--;
+
+ return ret;
+}
+
+void release_mce_event(void)
+{
+ get_mce_event(NULL, true);
+}
+
+/*
+ * Queue up the MCE event which then can be handled later.
+ */
+void machine_check_queue_event(void)
+{
+ int index;
+ struct machine_check_event evt;
+
+ if (!get_mce_event(&evt, MCE_EVENT_RELEASE))
+ return;
+
+ index = __get_cpu_var(mce_queue_count)++;
+ /* If queue is full, just return for now. */
+ if (index >= MAX_MC_EVT) {
+ __get_cpu_var(mce_queue_count)--;
+ return;
+ }
+ __get_cpu_var(mce_event_queue[index]) = evt;
+
+ /* Queue irq work to process this event later. */
+ irq_work_queue(&mce_event_process_work);
+}
+
+/*
+ * process pending MCE event from the mce event queue. This function will be
+ * called during syscall exit.
+ */
+static void machine_check_process_queued_event(struct irq_work *work)
+{
+ int index;
+
+ /*
+ * For now just print it to console.
+ * TODO: log this error event to FSP or nvram.
+ */
+ while (__get_cpu_var(mce_queue_count) > 0) {
+ index = __get_cpu_var(mce_queue_count) - 1;
+ machine_check_print_event_info(
+ &__get_cpu_var(mce_event_queue[index]));
+ __get_cpu_var(mce_queue_count)--;
+ }
+}
+
+void machine_check_print_event_info(struct machine_check_event *evt)
+{
+ const char *level, *sevstr, *subtype;
+ static const char *mc_ue_types[] = {
+ "Indeterminate",
+ "Instruction fetch",
+ "Page table walk ifetch",
+ "Load/Store",
+ "Page table walk Load/Store",
+ };
+ static const char *mc_slb_types[] = {
+ "Indeterminate",
+ "Parity",
+ "Multihit",
+ };
+ static const char *mc_erat_types[] = {
+ "Indeterminate",
+ "Parity",
+ "Multihit",
+ };
+ static const char *mc_tlb_types[] = {
+ "Indeterminate",
+ "Parity",
+ "Multihit",
+ };
+
+ /* Print things out */
+ if (evt->version != MCE_V1) {
+ pr_err("Machine Check Exception, Unknown event version %d !\n",
+ evt->version);
+ return;
+ }
+ switch (evt->severity) {
+ case MCE_SEV_NO_ERROR:
+ level = KERN_INFO;
+ sevstr = "Harmless";
+ break;
+ case MCE_SEV_WARNING:
+ level = KERN_WARNING;
+ sevstr = "";
+ break;
+ case MCE_SEV_ERROR_SYNC:
+ level = KERN_ERR;
+ sevstr = "Severe";
+ break;
+ case MCE_SEV_FATAL:
+ default:
+ level = KERN_ERR;
+ sevstr = "Fatal";
+ break;
+ }
+
+ printk("%s%s Machine check interrupt [%s]\n", level, sevstr,
+ evt->disposition == MCE_DISPOSITION_RECOVERED ?
+ "Recovered" : "[Not recovered");
+ printk("%s Initiator: %s\n", level,
+ evt->initiator == MCE_INITIATOR_CPU ? "CPU" : "Unknown");
+ switch (evt->error_type) {
+ case MCE_ERROR_TYPE_UE:
+ subtype = evt->u.ue_error.ue_error_type <
+ ARRAY_SIZE(mc_ue_types) ?
+ mc_ue_types[evt->u.ue_error.ue_error_type]
+ : "Unknown";
+ printk("%s Error type: UE [%s]\n", level, subtype);
+ if (evt->u.ue_error.effective_address_provided)
+ printk("%s Effective address: %016llx\n",
+ level, evt->u.ue_error.effective_address);
+ if (evt->u.ue_error.physical_address_provided)
+ printk("%s Physial address: %016llx\n",
+ level, evt->u.ue_error.physical_address);
+ break;
+ case MCE_ERROR_TYPE_SLB:
+ subtype = evt->u.slb_error.slb_error_type <
+ ARRAY_SIZE(mc_slb_types) ?
+ mc_slb_types[evt->u.slb_error.slb_error_type]
+ : "Unknown";
+ printk("%s Error type: SLB [%s]\n", level, subtype);
+ if (evt->u.slb_error.effective_address_provided)
+ printk("%s Effective address: %016llx\n",
+ level, evt->u.slb_error.effective_address);
+ break;
+ case MCE_ERROR_TYPE_ERAT:
+ subtype = evt->u.erat_error.erat_error_type <
+ ARRAY_SIZE(mc_erat_types) ?
+ mc_erat_types[evt->u.erat_error.erat_error_type]
+ : "Unknown";
+ printk("%s Error type: ERAT [%s]\n", level, subtype);
+ if (evt->u.erat_error.effective_address_provided)
+ printk("%s Effective address: %016llx\n",
+ level, evt->u.erat_error.effective_address);
+ break;
+ case MCE_ERROR_TYPE_TLB:
+ subtype = evt->u.tlb_error.tlb_error_type <
+ ARRAY_SIZE(mc_tlb_types) ?
+ mc_tlb_types[evt->u.tlb_error.tlb_error_type]
+ : "Unknown";
+ printk("%s Error type: TLB [%s]\n", level, subtype);
+ if (evt->u.tlb_error.effective_address_provided)
+ printk("%s Effective address: %016llx\n",
+ level, evt->u.tlb_error.effective_address);
+ break;
+ default:
+ case MCE_ERROR_TYPE_UNKNOWN:
+ printk("%s Error type: Unknown\n", level);
+ break;
+ }
+}
+
+uint64_t get_mce_fault_addr(struct machine_check_event *evt)
+{
+ switch (evt->error_type) {
+ case MCE_ERROR_TYPE_UE:
+ if (evt->u.ue_error.effective_address_provided)
+ return evt->u.ue_error.effective_address;
+ break;
+ case MCE_ERROR_TYPE_SLB:
+ if (evt->u.slb_error.effective_address_provided)
+ return evt->u.slb_error.effective_address;
+ break;
+ case MCE_ERROR_TYPE_ERAT:
+ if (evt->u.erat_error.effective_address_provided)
+ return evt->u.erat_error.effective_address;
+ break;
+ case MCE_ERROR_TYPE_TLB:
+ if (evt->u.tlb_error.effective_address_provided)
+ return evt->u.tlb_error.effective_address;
+ break;
+ default:
+ case MCE_ERROR_TYPE_UNKNOWN:
+ break;
+ }
+ return 0;
+}
+EXPORT_SYMBOL(get_mce_fault_addr);
diff --git a/arch/powerpc/kernel/mce_power.c b/arch/powerpc/kernel/mce_power.c
new file mode 100644
index 00000000000..aa9aff3d6ad
--- /dev/null
+++ b/arch/powerpc/kernel/mce_power.c
@@ -0,0 +1,313 @@
+/*
+ * Machine check exception handling CPU-side for power7 and power8
+ *
+ * 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.
+ *
+ * Copyright 2013 IBM Corporation
+ * Author: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
+ */
+
+#undef DEBUG
+#define pr_fmt(fmt) "mce_power: " fmt
+
+#include <linux/types.h>
+#include <linux/ptrace.h>
+#include <asm/mmu.h>
+#include <asm/mce.h>
+#include <asm/machdep.h>
+
+/* flush SLBs and reload */
+static void flush_and_reload_slb(void)
+{
+ struct slb_shadow *slb;
+ unsigned long i, n;
+
+ /* Invalidate all SLBs */
+ asm volatile("slbmte %0,%0; slbia" : : "r" (0));
+
+#ifdef CONFIG_KVM_BOOK3S_HANDLER
+ /*
+ * If machine check is hit when in guest or in transition, we will
+ * only flush the SLBs and continue.
+ */
+ if (get_paca()->kvm_hstate.in_guest)
+ return;
+#endif
+
+ /* For host kernel, reload the SLBs from shadow SLB buffer. */
+ slb = get_slb_shadow();
+ if (!slb)
+ return;
+
+ n = min_t(u32, be32_to_cpu(slb->persistent), SLB_MIN_SIZE);
+
+ /* Load up the SLB entries from shadow SLB */
+ for (i = 0; i < n; i++) {
+ unsigned long rb = be64_to_cpu(slb->save_area[i].esid);
+ unsigned long rs = be64_to_cpu(slb->save_area[i].vsid);
+
+ rb = (rb & ~0xFFFul) | i;
+ asm volatile("slbmte %0,%1" : : "r" (rs), "r" (rb));
+ }
+}
+
+static long mce_handle_derror(uint64_t dsisr, uint64_t slb_error_bits)
+{
+ long handled = 1;
+
+ /*
+ * flush and reload SLBs for SLB errors and flush TLBs for TLB errors.
+ * reset the error bits whenever we handle them so that at the end
+ * we can check whether we handled all of them or not.
+ * */
+ if (dsisr & slb_error_bits) {
+ flush_and_reload_slb();
+ /* reset error bits */
+ dsisr &= ~(slb_error_bits);
+ }
+ if (dsisr & P7_DSISR_MC_TLB_MULTIHIT_MFTLB) {
+ if (cur_cpu_spec && cur_cpu_spec->flush_tlb)
+ cur_cpu_spec->flush_tlb(TLBIEL_INVAL_PAGE);
+ /* reset error bits */
+ dsisr &= ~P7_DSISR_MC_TLB_MULTIHIT_MFTLB;
+ }
+ /* Any other errors we don't understand? */
+ if (dsisr & 0xffffffffUL)
+ handled = 0;
+
+ return handled;
+}
+
+static long mce_handle_derror_p7(uint64_t dsisr)
+{
+ return mce_handle_derror(dsisr, P7_DSISR_MC_SLB_ERRORS);
+}
+
+static long mce_handle_common_ierror(uint64_t srr1)
+{
+ long handled = 0;
+
+ switch (P7_SRR1_MC_IFETCH(srr1)) {
+ case 0:
+ break;
+ case P7_SRR1_MC_IFETCH_SLB_PARITY:
+ case P7_SRR1_MC_IFETCH_SLB_MULTIHIT:
+ /* flush and reload SLBs for SLB errors. */
+ flush_and_reload_slb();
+ handled = 1;
+ break;
+ case P7_SRR1_MC_IFETCH_TLB_MULTIHIT:
+ if (cur_cpu_spec && cur_cpu_spec->flush_tlb) {
+ cur_cpu_spec->flush_tlb(TLBIEL_INVAL_PAGE);
+ handled = 1;
+ }
+ break;
+ default:
+ break;
+ }
+
+ return handled;
+}
+
+static long mce_handle_ierror_p7(uint64_t srr1)
+{
+ long handled = 0;
+
+ handled = mce_handle_common_ierror(srr1);
+
+ if (P7_SRR1_MC_IFETCH(srr1) == P7_SRR1_MC_IFETCH_SLB_BOTH) {
+ flush_and_reload_slb();
+ handled = 1;
+ }
+ return handled;
+}
+
+static void mce_get_common_ierror(struct mce_error_info *mce_err, uint64_t srr1)
+{
+ switch (P7_SRR1_MC_IFETCH(srr1)) {
+ case P7_SRR1_MC_IFETCH_SLB_PARITY:
+ mce_err->error_type = MCE_ERROR_TYPE_SLB;
+ mce_err->u.slb_error_type = MCE_SLB_ERROR_PARITY;
+ break;
+ case P7_SRR1_MC_IFETCH_SLB_MULTIHIT:
+ mce_err->error_type = MCE_ERROR_TYPE_SLB;
+ mce_err->u.slb_error_type = MCE_SLB_ERROR_MULTIHIT;
+ break;
+ case P7_SRR1_MC_IFETCH_TLB_MULTIHIT:
+ mce_err->error_type = MCE_ERROR_TYPE_TLB;
+ mce_err->u.tlb_error_type = MCE_TLB_ERROR_MULTIHIT;
+ break;
+ case P7_SRR1_MC_IFETCH_UE:
+ case P7_SRR1_MC_IFETCH_UE_IFU_INTERNAL:
+ mce_err->error_type = MCE_ERROR_TYPE_UE;
+ mce_err->u.ue_error_type = MCE_UE_ERROR_IFETCH;
+ break;
+ case P7_SRR1_MC_IFETCH_UE_TLB_RELOAD:
+ mce_err->error_type = MCE_ERROR_TYPE_UE;
+ mce_err->u.ue_error_type =
+ MCE_UE_ERROR_PAGE_TABLE_WALK_IFETCH;
+ break;
+ }
+}
+
+static void mce_get_ierror_p7(struct mce_error_info *mce_err, uint64_t srr1)
+{
+ mce_get_common_ierror(mce_err, srr1);
+ if (P7_SRR1_MC_IFETCH(srr1) == P7_SRR1_MC_IFETCH_SLB_BOTH) {
+ mce_err->error_type = MCE_ERROR_TYPE_SLB;
+ mce_err->u.slb_error_type = MCE_SLB_ERROR_INDETERMINATE;
+ }
+}
+
+static void mce_get_derror_p7(struct mce_error_info *mce_err, uint64_t dsisr)
+{
+ if (dsisr & P7_DSISR_MC_UE) {
+ mce_err->error_type = MCE_ERROR_TYPE_UE;
+ mce_err->u.ue_error_type = MCE_UE_ERROR_LOAD_STORE;
+ } else if (dsisr & P7_DSISR_MC_UE_TABLEWALK) {
+ mce_err->error_type = MCE_ERROR_TYPE_UE;
+ mce_err->u.ue_error_type =
+ MCE_UE_ERROR_PAGE_TABLE_WALK_LOAD_STORE;
+ } else if (dsisr & P7_DSISR_MC_ERAT_MULTIHIT) {
+ mce_err->error_type = MCE_ERROR_TYPE_ERAT;
+ mce_err->u.erat_error_type = MCE_ERAT_ERROR_MULTIHIT;
+ } else if (dsisr & P7_DSISR_MC_SLB_MULTIHIT) {
+ mce_err->error_type = MCE_ERROR_TYPE_SLB;
+ mce_err->u.slb_error_type = MCE_SLB_ERROR_MULTIHIT;
+ } else if (dsisr & P7_DSISR_MC_SLB_PARITY_MFSLB) {
+ mce_err->error_type = MCE_ERROR_TYPE_SLB;
+ mce_err->u.slb_error_type = MCE_SLB_ERROR_PARITY;
+ } else if (dsisr & P7_DSISR_MC_TLB_MULTIHIT_MFTLB) {
+ mce_err->error_type = MCE_ERROR_TYPE_TLB;
+ mce_err->u.tlb_error_type = MCE_TLB_ERROR_MULTIHIT;
+ } else if (dsisr & P7_DSISR_MC_SLB_MULTIHIT_PARITY) {
+ mce_err->error_type = MCE_ERROR_TYPE_SLB;
+ mce_err->u.slb_error_type = MCE_SLB_ERROR_INDETERMINATE;
+ }
+}
+
+static long mce_handle_ue_error(struct pt_regs *regs)
+{
+ long handled = 0;
+
+ /*
+ * On specific SCOM read via MMIO we may get a machine check
+ * exception with SRR0 pointing inside opal. If that is the
+ * case OPAL may have recovery address to re-read SCOM data in
+ * different way and hence we can recover from this MC.
+ */
+
+ if (ppc_md.mce_check_early_recovery) {
+ if (ppc_md.mce_check_early_recovery(regs))
+ handled = 1;
+ }
+ return handled;
+}
+
+long __machine_check_early_realmode_p7(struct pt_regs *regs)
+{
+ uint64_t srr1, nip, addr;
+ long handled = 1;
+ struct mce_error_info mce_error_info = { 0 };
+
+ srr1 = regs->msr;
+ nip = regs->nip;
+
+ /*
+ * Handle memory errors depending whether this was a load/store or
+ * ifetch exception. Also, populate the mce error_type and
+ * type-specific error_type from either SRR1 or DSISR, depending
+ * whether this was a load/store or ifetch exception
+ */
+ if (P7_SRR1_MC_LOADSTORE(srr1)) {
+ handled = mce_handle_derror_p7(regs->dsisr);
+ mce_get_derror_p7(&mce_error_info, regs->dsisr);
+ addr = regs->dar;
+ } else {
+ handled = mce_handle_ierror_p7(srr1);
+ mce_get_ierror_p7(&mce_error_info, srr1);
+ addr = regs->nip;
+ }
+
+ /* Handle UE error. */
+ if (mce_error_info.error_type == MCE_ERROR_TYPE_UE)
+ handled = mce_handle_ue_error(regs);
+
+ save_mce_event(regs, handled, &mce_error_info, nip, addr);
+ return handled;
+}
+
+static void mce_get_ierror_p8(struct mce_error_info *mce_err, uint64_t srr1)
+{
+ mce_get_common_ierror(mce_err, srr1);
+ if (P7_SRR1_MC_IFETCH(srr1) == P8_SRR1_MC_IFETCH_ERAT_MULTIHIT) {
+ mce_err->error_type = MCE_ERROR_TYPE_ERAT;
+ mce_err->u.erat_error_type = MCE_ERAT_ERROR_MULTIHIT;
+ }
+}
+
+static void mce_get_derror_p8(struct mce_error_info *mce_err, uint64_t dsisr)
+{
+ mce_get_derror_p7(mce_err, dsisr);
+ if (dsisr & P8_DSISR_MC_ERAT_MULTIHIT_SEC) {
+ mce_err->error_type = MCE_ERROR_TYPE_ERAT;
+ mce_err->u.erat_error_type = MCE_ERAT_ERROR_MULTIHIT;
+ }
+}
+
+static long mce_handle_ierror_p8(uint64_t srr1)
+{
+ long handled = 0;
+
+ handled = mce_handle_common_ierror(srr1);
+
+ if (P7_SRR1_MC_IFETCH(srr1) == P8_SRR1_MC_IFETCH_ERAT_MULTIHIT) {
+ flush_and_reload_slb();
+ handled = 1;
+ }
+ return handled;
+}
+
+static long mce_handle_derror_p8(uint64_t dsisr)
+{
+ return mce_handle_derror(dsisr, P8_DSISR_MC_SLB_ERRORS);
+}
+
+long __machine_check_early_realmode_p8(struct pt_regs *regs)
+{
+ uint64_t srr1, nip, addr;
+ long handled = 1;
+ struct mce_error_info mce_error_info = { 0 };
+
+ srr1 = regs->msr;
+ nip = regs->nip;
+
+ if (P7_SRR1_MC_LOADSTORE(srr1)) {
+ handled = mce_handle_derror_p8(regs->dsisr);
+ mce_get_derror_p8(&mce_error_info, regs->dsisr);
+ addr = regs->dar;
+ } else {
+ handled = mce_handle_ierror_p8(srr1);
+ mce_get_ierror_p8(&mce_error_info, srr1);
+ addr = regs->nip;
+ }
+
+ /* Handle UE error. */
+ if (mce_error_info.error_type == MCE_ERROR_TYPE_UE)
+ handled = mce_handle_ue_error(regs);
+
+ save_mce_event(regs, handled, &mce_error_info, nip, addr);
+ return handled;
+}
diff --git a/arch/powerpc/kernel/misc.S b/arch/powerpc/kernel/misc.S
index b69463ec201..7ce26d45777 100644
--- a/arch/powerpc/kernel/misc.S
+++ b/arch/powerpc/kernel/misc.S
@@ -5,7 +5,6 @@
* Largely rewritten by Cort Dougan (cort@cs.nmt.edu)
* and Paul Mackerras.
*
- * Adapted for iSeries by Mike Corrigan (mikejc@us.ibm.com)
* PPC64 updates by Dave Engebretsen (engebret@us.ibm.com)
*
* setjmp/longjmp code by Paul Mackerras.
@@ -55,13 +54,6 @@ _GLOBAL(add_reloc_offset)
.align 3
2: PPC_LONG 1b
-_GLOBAL(kernel_execve)
- li r0,__NR_execve
- sc
- bnslr
- neg r3,r3
- blr
-
_GLOBAL(setjmp)
mflr r0
PPC_STL r0,0(r3)
diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S
index 7cd07b42ca1..7c6bb4b17b4 100644
--- a/arch/powerpc/kernel/misc_32.S
+++ b/arch/powerpc/kernel/misc_32.S
@@ -36,26 +36,44 @@
.text
+/*
+ * We store the saved ksp_limit in the unused part
+ * of the STACK_FRAME_OVERHEAD
+ */
_GLOBAL(call_do_softirq)
mflr r0
stw r0,4(r1)
+ lwz r10,THREAD+KSP_LIMIT(r2)
+ addi r11,r3,THREAD_INFO_GAP
stwu r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r3)
mr r1,r3
+ stw r10,8(r1)
+ stw r11,THREAD+KSP_LIMIT(r2)
bl __do_softirq
+ lwz r10,8(r1)
lwz r1,0(r1)
lwz r0,4(r1)
+ stw r10,THREAD+KSP_LIMIT(r2)
mtlr r0
blr
-_GLOBAL(call_handle_irq)
+/*
+ * void call_do_irq(struct pt_regs *regs, struct thread_info *irqtp);
+ */
+_GLOBAL(call_do_irq)
mflr r0
stw r0,4(r1)
- mtctr r6
- stwu r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r5)
- mr r1,r5
- bctrl
+ lwz r10,THREAD+KSP_LIMIT(r2)
+ addi r11,r4,THREAD_INFO_GAP
+ stwu r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r4)
+ mr r1,r4
+ stw r10,8(r1)
+ stw r11,THREAD+KSP_LIMIT(r2)
+ bl __do_irq
+ lwz r10,8(r1)
lwz r1,0(r1)
lwz r0,4(r1)
+ stw r10,THREAD+KSP_LIMIT(r2)
mtlr r0
blr
@@ -179,7 +197,7 @@ _GLOBAL(low_choose_750fx_pll)
mtspr SPRN_HID1,r4
/* Store new HID1 image */
- rlwinm r6,r1,0,0,(31-THREAD_SHIFT)
+ CURRENT_THREAD_INFO(r6, r1)
lwz r6,TI_CPU(r6)
slwi r6,r6,2
addis r6,r6,nap_save_hid1@ha
@@ -327,8 +345,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_UNIFIED_ID_CACHE)
*
* flush_icache_range(unsigned long start, unsigned long stop)
*/
-_KPROBE(__flush_icache_range)
+_KPROBE(flush_icache_range)
BEGIN_FTR_SECTION
+ PURGE_PREFETCHED_INS
blr /* for 601, do nothing */
END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE)
li r5,L1_CACHE_BYTES-1
@@ -432,6 +451,7 @@ _GLOBAL(invalidate_dcache_range)
*/
_GLOBAL(__flush_dcache_icache)
BEGIN_FTR_SECTION
+ PURGE_PREFETCHED_INS
blr
END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE)
rlwinm r3,r3,0,0,31-PAGE_SHIFT /* Get page base address */
@@ -473,6 +493,7 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_44x)
*/
_GLOBAL(__flush_dcache_icache_phys)
BEGIN_FTR_SECTION
+ PURGE_PREFETCHED_INS
blr /* for 601, do nothing */
END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE)
mfmsr r10
@@ -643,6 +664,20 @@ _GLOBAL(__lshrdi3)
blr
/*
+ * 64-bit comparison: __cmpdi2(s64 a, s64 b)
+ * Returns 0 if a < b, 1 if a == b, 2 if a > b.
+ */
+_GLOBAL(__cmpdi2)
+ cmpw r3,r5
+ li r3,1
+ bne 1f
+ cmplw r4,r6
+ beqlr
+1: li r3,0
+ bltlr
+ li r3,2
+ blr
+/*
* 64-bit comparison: __ucmpdi2(u64 a, u64 b)
* Returns 0 if a < b, 1 if a == b, 2 if a > b.
*/
@@ -657,49 +692,27 @@ _GLOBAL(__ucmpdi2)
li r3,2
blr
+_GLOBAL(__bswapdi2)
+ rotlwi r9,r4,8
+ rotlwi r10,r3,8
+ rlwimi r9,r4,24,0,7
+ rlwimi r10,r3,24,0,7
+ rlwimi r9,r4,24,16,23
+ rlwimi r10,r3,24,16,23
+ mr r3,r9
+ mr r4,r10
+ blr
+
_GLOBAL(abs)
srawi r4,r3,31
xor r3,r3,r4
sub r3,r3,r4
blr
-/*
- * Create a kernel thread
- * kernel_thread(fn, arg, flags)
- */
-_GLOBAL(kernel_thread)
- stwu r1,-16(r1)
- stw r30,8(r1)
- stw r31,12(r1)
- mr r30,r3 /* function */
- mr r31,r4 /* argument */
- ori r3,r5,CLONE_VM /* flags */
- oris r3,r3,CLONE_UNTRACED>>16
- li r4,0 /* new sp (unused) */
- li r0,__NR_clone
- sc
- bns+ 1f /* did system call indicate error? */
- neg r3,r3 /* if so, make return code negative */
-1: cmpwi 0,r3,0 /* parent or child? */
- bne 2f /* return if parent */
- li r0,0 /* make top-level stack frame */
- stwu r0,-16(r1)
- mtlr r30 /* fn addr in lr */
- mr r3,r31 /* load arg and call fn */
- PPC440EP_ERR42
- blrl
- li r0,__NR_exit /* exit if function returns */
- li r3,0
- sc
-2: lwz r30,8(r1)
- lwz r31,12(r1)
- addi r1,r1,16
- blr
-
#ifdef CONFIG_SMP
_GLOBAL(start_secondary_resume)
/* Reset stack */
- rlwinm r1,r1,0,0,(31-THREAD_SHIFT) /* current_thread_info() */
+ CURRENT_THREAD_INFO(r1, r1)
addi r1,r1,THREAD_SIZE-STACK_FRAME_OVERHEAD
li r3,0
stw r3,0(r1) /* Zero the stack frame pointer */
@@ -738,8 +751,23 @@ relocate_new_kernel:
mr r5, r31
li r0, 0
-#elif defined(CONFIG_44x) && !defined(CONFIG_PPC_47x)
+#elif defined(CONFIG_44x)
+ /* Save our parameters */
+ mr r29, r3
+ mr r30, r4
+ mr r31, r5
+
+#ifdef CONFIG_PPC_47x
+ /* Check for 47x cores */
+ mfspr r3,SPRN_PVR
+ srwi r3,r3,16
+ cmplwi cr0,r3,PVR_476@h
+ beq setup_map_47x
+ cmplwi cr0,r3,PVR_476_ISS@h
+ beq setup_map_47x
+#endif /* CONFIG_PPC_47x */
+
/*
* Code for setting up 1:1 mapping for PPC440x for KEXEC
*
@@ -753,16 +781,15 @@ relocate_new_kernel:
* 5) Invalidate the tmp mapping.
*
* - Based on the kexec support code for FSL BookE
- * - Doesn't support 47x yet.
*
*/
- /* Save our parameters */
- mr r29, r3
- mr r30, r4
- mr r31, r5
- /* Load our MSR_IS and TID to MMUCR for TLB search */
- mfspr r3,SPRN_PID
+ /*
+ * Load the PID with kernel PID (0).
+ * Also load our MSR_IS and TID to MMUCR for TLB search.
+ */
+ li r3, 0
+ mtspr SPRN_PID, r3
mfmsr r4
andi. r4,r4,MSR_IS@l
beq wmmucr
@@ -900,6 +927,179 @@ next_tlb:
li r3, 0
tlbwe r3, r24, PPC44x_TLB_PAGEID
sync
+ b ppc44x_map_done
+
+#ifdef CONFIG_PPC_47x
+
+ /* 1:1 mapping for 47x */
+
+setup_map_47x:
+
+ /*
+ * Load the kernel pid (0) to PID and also to MMUCR[TID].
+ * Also set the MSR IS->MMUCR STS
+ */
+ li r3, 0
+ mtspr SPRN_PID, r3 /* Set PID */
+ mfmsr r4 /* Get MSR */
+ andi. r4, r4, MSR_IS@l /* TS=1? */
+ beq 1f /* If not, leave STS=0 */
+ oris r3, r3, PPC47x_MMUCR_STS@h /* Set STS=1 */
+1: mtspr SPRN_MMUCR, r3 /* Put MMUCR */
+ sync
+
+ /* Find the entry we are running from */
+ bl 2f
+2: mflr r23
+ tlbsx r23, 0, r23
+ tlbre r24, r23, 0 /* TLB Word 0 */
+ tlbre r25, r23, 1 /* TLB Word 1 */
+ tlbre r26, r23, 2 /* TLB Word 2 */
+
+
+ /*
+ * Invalidates all the tlb entries by writing to 256 RPNs(r4)
+ * of 4k page size in all 4 ways (0-3 in r3).
+ * This would invalidate the entire UTLB including the one we are
+ * running from. However the shadow TLB entries would help us
+ * to continue the execution, until we flush them (rfi/isync).
+ */
+ addis r3, 0, 0x8000 /* specify the way */
+ addi r4, 0, 0 /* TLB Word0 = (EPN=0, VALID = 0) */
+ addi r5, 0, 0
+ b clear_utlb_entry
+
+ /* Align the loop to speed things up. from head_44x.S */
+ .align 6
+
+clear_utlb_entry:
+
+ tlbwe r4, r3, 0
+ tlbwe r5, r3, 1
+ tlbwe r5, r3, 2
+ addis r3, r3, 0x2000 /* Increment the way */
+ cmpwi r3, 0
+ bne clear_utlb_entry
+ addis r3, 0, 0x8000
+ addis r4, r4, 0x100 /* Increment the EPN */
+ cmpwi r4, 0
+ bne clear_utlb_entry
+
+ /* Create the entries in the other address space */
+ mfmsr r5
+ rlwinm r7, r5, 27, 31, 31 /* Get the TS (Bit 26) from MSR */
+ xori r7, r7, 1 /* r7 = !TS */
+
+ insrwi r24, r7, 1, 21 /* Change the TS in the saved TLB word 0 */
+
+ /*
+ * write out the TLB entries for the tmp mapping
+ * Use way '0' so that we could easily invalidate it later.
+ */
+ lis r3, 0x8000 /* Way '0' */
+
+ tlbwe r24, r3, 0
+ tlbwe r25, r3, 1
+ tlbwe r26, r3, 2
+
+ /* Update the msr to the new TS */
+ insrwi r5, r7, 1, 26
+
+ bl 1f
+1: mflr r6
+ addi r6, r6, (2f-1b)
+
+ mtspr SPRN_SRR0, r6
+ mtspr SPRN_SRR1, r5
+ rfi
+
+ /*
+ * Now we are in the tmp address space.
+ * Create a 1:1 mapping for 0-2GiB in the original TS.
+ */
+2:
+ li r3, 0
+ li r4, 0 /* TLB Word 0 */
+ li r5, 0 /* TLB Word 1 */
+ li r6, 0
+ ori r6, r6, PPC47x_TLB2_S_RWX /* TLB word 2 */
+
+ li r8, 0 /* PageIndex */
+
+ xori r7, r7, 1 /* revert back to original TS */
+
+write_utlb:
+ rotlwi r5, r8, 28 /* RPN = PageIndex * 256M */
+ /* ERPN = 0 as we don't use memory above 2G */
+
+ mr r4, r5 /* EPN = RPN */
+ ori r4, r4, (PPC47x_TLB0_VALID | PPC47x_TLB0_256M)
+ insrwi r4, r7, 1, 21 /* Insert the TS to Word 0 */
+
+ tlbwe r4, r3, 0 /* Write out the entries */
+ tlbwe r5, r3, 1
+ tlbwe r6, r3, 2
+ addi r8, r8, 1
+ cmpwi r8, 8 /* Have we completed ? */
+ bne write_utlb
+
+ /* make sure we complete the TLB write up */
+ isync
+
+ /*
+ * Prepare to jump to the 1:1 mapping.
+ * 1) Extract page size of the tmp mapping
+ * DSIZ = TLB_Word0[22:27]
+ * 2) Calculate the physical address of the address
+ * to jump to.
+ */
+ rlwinm r10, r24, 0, 22, 27
+
+ cmpwi r10, PPC47x_TLB0_4K
+ bne 0f
+ li r10, 0x1000 /* r10 = 4k */
+ bl 1f
+
+0:
+ /* Defaults to 256M */
+ lis r10, 0x1000
+
+ bl 1f
+1: mflr r4
+ addi r4, r4, (2f-1b) /* virtual address of 2f */
+
+ subi r11, r10, 1 /* offsetmask = Pagesize - 1 */
+ not r10, r11 /* Pagemask = ~(offsetmask) */
+
+ and r5, r25, r10 /* Physical page */
+ and r6, r4, r11 /* offset within the current page */
+
+ or r5, r5, r6 /* Physical address for 2f */
+
+ /* Switch the TS in MSR to the original one */
+ mfmsr r8
+ insrwi r8, r7, 1, 26
+
+ mtspr SPRN_SRR1, r8
+ mtspr SPRN_SRR0, r5
+ rfi
+
+2:
+ /* Invalidate the tmp mapping */
+ lis r3, 0x8000 /* Way '0' */
+
+ clrrwi r24, r24, 12 /* Clear the valid bit */
+ tlbwe r24, r3, 0
+ tlbwe r25, r3, 1
+ tlbwe r26, r3, 2
+
+ /* Make sure we complete the TLB write and flush the shadow TLB */
+ isync
+
+#endif
+
+ppc44x_map_done:
+
/* Restore the parameters */
mr r3, r29
diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S
index 616921ef143..4e314b90c75 100644
--- a/arch/powerpc/kernel/misc_64.S
+++ b/arch/powerpc/kernel/misc_64.S
@@ -34,20 +34,18 @@ _GLOBAL(call_do_softirq)
std r0,16(r1)
stdu r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r3)
mr r1,r3
- bl .__do_softirq
+ bl __do_softirq
ld r1,0(r1)
ld r0,16(r1)
mtlr r0
blr
-_GLOBAL(call_handle_irq)
- ld r8,0(r6)
+_GLOBAL(call_do_irq)
mflr r0
std r0,16(r1)
- mtctr r8
- stdu r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r5)
- mr r1,r5
- bctrl
+ stdu r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r4)
+ mr r1,r4
+ bl __do_irq
ld r1,0(r1)
ld r0,16(r1)
mtlr r0
@@ -67,8 +65,11 @@ PPC64_CACHES:
* flush all bytes from start through stop-1 inclusive
*/
-_KPROBE(__flush_icache_range)
-
+_KPROBE(flush_icache_range)
+BEGIN_FTR_SECTION
+ PURGE_PREFETCHED_INS
+ blr
+END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE)
/*
* Flush the data cache to memory
*
@@ -211,6 +212,11 @@ _GLOBAL(__flush_dcache_icache)
* Different systems have different cache line sizes
*/
+BEGIN_FTR_SECTION
+ PURGE_PREFETCHED_INS
+ blr
+END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE)
+
/* Flush the dcache */
ld r7,PPC64_CACHES@toc(r2)
clrrdi r3,r3,PAGE_SHIFT /* Page align */
@@ -234,8 +240,53 @@ _GLOBAL(__flush_dcache_icache)
isync
blr
+_GLOBAL(__bswapdi2)
+ srdi r8,r3,32
+ rlwinm r7,r3,8,0xffffffff
+ rlwimi r7,r3,24,0,7
+ rlwinm r9,r8,8,0xffffffff
+ rlwimi r7,r3,24,16,23
+ rlwimi r9,r8,24,0,7
+ rlwimi r9,r8,24,16,23
+ sldi r7,r7,32
+ or r3,r7,r9
+ blr
+
+
+#ifdef CONFIG_PPC_EARLY_DEBUG_BOOTX
+_GLOBAL(rmci_on)
+ sync
+ isync
+ li r3,0x100
+ rldicl r3,r3,32,0
+ mfspr r5,SPRN_HID4
+ or r5,r5,r3
+ sync
+ mtspr SPRN_HID4,r5
+ isync
+ slbia
+ isync
+ sync
+ blr
+
+_GLOBAL(rmci_off)
+ sync
+ isync
+ li r3,0x100
+ rldicl r3,r3,32,0
+ mfspr r5,SPRN_HID4
+ andc r5,r5,r3
+ sync
+ mtspr SPRN_HID4,r5
+ isync
+ slbia
+ isync
+ sync
+ blr
+#endif /* CONFIG_PPC_EARLY_DEBUG_BOOTX */
#if defined(CONFIG_PPC_PMAC) || defined(CONFIG_PPC_MAPLE)
+
/*
* Do an IO access in real mode
*/
@@ -301,11 +352,6 @@ _GLOBAL(real_writeb)
#ifdef CONFIG_PPC_PASEMI
-/* No support in all binutils for these yet, so use defines */
-#define LBZCIX(RT,RA,RB) .long (0x7c0006aa|(RT<<21)|(RA<<16)|(RB << 11))
-#define STBCIX(RS,RA,RB) .long (0x7c0007aa|(RS<<21)|(RA<<16)|(RB << 11))
-
-
_GLOBAL(real_205_readb)
mfmsr r7
ori r0,r7,MSR_DR
@@ -314,7 +360,7 @@ _GLOBAL(real_205_readb)
mtmsrd r0
sync
isync
- LBZCIX(r3,0,r3)
+ LBZCIX(R3,R0,R3)
isync
mtmsrd r7
sync
@@ -329,7 +375,7 @@ _GLOBAL(real_205_writeb)
mtmsrd r0
sync
isync
- STBCIX(r3,0,r4)
+ STBCIX(R3,R0,R4)
isync
mtmsrd r7
sync
@@ -410,53 +456,6 @@ _GLOBAL(scom970_write)
blr
#endif /* CONFIG_CPU_FREQ_PMAC64 || CONFIG_CPU_FREQ_MAPLE */
-
-/*
- * Create a kernel thread
- * kernel_thread(fn, arg, flags)
- */
-_GLOBAL(kernel_thread)
- std r29,-24(r1)
- std r30,-16(r1)
- stdu r1,-STACK_FRAME_OVERHEAD(r1)
- mr r29,r3
- mr r30,r4
- ori r3,r5,CLONE_VM /* flags */
- oris r3,r3,(CLONE_UNTRACED>>16)
- li r4,0 /* new sp (unused) */
- li r0,__NR_clone
- sc
- bns+ 1f /* did system call indicate error? */
- neg r3,r3 /* if so, make return code negative */
-1: cmpdi 0,r3,0 /* parent or child? */
- bne 2f /* return if parent */
- li r0,0
- stdu r0,-STACK_FRAME_OVERHEAD(r1)
- ld r2,8(r29)
- ld r29,0(r29)
- mtlr r29 /* fn addr in lr */
- mr r3,r30 /* load arg and call fn */
- blrl
- li r0,__NR_exit /* exit after child exits */
- li r3,0
- sc
-2: addi r1,r1,STACK_FRAME_OVERHEAD
- ld r29,-24(r1)
- ld r30,-16(r1)
- blr
-
-/*
- * disable_kernel_fp()
- * Disable the FPU.
- */
-_GLOBAL(disable_kernel_fp)
- mfmsr r3
- rldicl r0,r3,(63-MSR_FP_LG),1
- rldicl r3,r0,(MSR_FP_LG+1),0
- mtmsrd r3 /* disable use of fpu now */
- isync
- blr
-
/* kexec_wait(phys_cpu)
*
* wait for the flag to change, indicating this kernel is going away but
@@ -507,7 +506,7 @@ _GLOBAL(kexec_smp_wait)
stb r4,PACAKEXECSTATE(r13)
SYNC
- b .kexec_wait
+ b kexec_wait
/*
* switch to real mode (turn mmu off)
@@ -577,7 +576,7 @@ _GLOBAL(kexec_sequence)
/* copy dest pages, flush whole dest image */
mr r3,r29
- bl .kexec_copy_flush /* (image) */
+ bl kexec_copy_flush /* (image) */
/* turn off mmu */
bl real_mode
@@ -587,7 +586,7 @@ _GLOBAL(kexec_sequence)
mr r4,r30 /* start, aka phys mem offset */
li r5,0x100
li r6,0
- bl .copy_and_flush /* (dest, src, copy limit, start offset) */
+ bl copy_and_flush /* (dest, src, copy limit, start offset) */
1: /* assume normal blr return */
/* release other cpus to the new kernel secondary start at 0x60 */
@@ -596,8 +595,12 @@ _GLOBAL(kexec_sequence)
stw r6,kexec_flag-1b(5)
/* clear out hardware hash page table and tlb */
- ld r5,0(r27) /* deref function descriptor */
- mtctr r5
+#if !defined(_CALL_ELF) || _CALL_ELF != 2
+ ld r12,0(r27) /* deref function descriptor */
+#else
+ mr r12,r27
+#endif
+ mtctr r12
bctrl /* ppc_md.hpte_clear_all(void); */
/*
@@ -631,3 +634,31 @@ _GLOBAL(kexec_sequence)
li r5,0
blr /* image->start(physid, image->start, 0); */
#endif /* CONFIG_KEXEC */
+
+#ifdef CONFIG_MODULES
+#if defined(_CALL_ELF) && _CALL_ELF == 2
+
+#ifdef CONFIG_MODVERSIONS
+.weak __crc_TOC.
+.section "___kcrctab+TOC.","a"
+.globl __kcrctab_TOC.
+__kcrctab_TOC.:
+ .llong __crc_TOC.
+#endif
+
+/*
+ * Export a fake .TOC. since both modpost and depmod will complain otherwise.
+ * Both modpost and depmod strip the leading . so we do the same here.
+ */
+.section "__ksymtab_strings","a"
+__kstrtab_TOC.:
+ .asciz "TOC."
+
+.section "___ksymtab+TOC.","a"
+/* This symbol name is important: it's used by modpost to find exported syms */
+.globl __ksymtab_TOC.
+__ksymtab_TOC.:
+ .llong 0 /* .value */
+ .llong __kstrtab_TOC.
+#endif /* ELFv2 */
+#endif /* MODULES */
diff --git a/arch/powerpc/kernel/module.c b/arch/powerpc/kernel/module.c
index 2d275707f41..9547381b631 100644
--- a/arch/powerpc/kernel/module.c
+++ b/arch/powerpc/kernel/module.c
@@ -25,8 +25,7 @@
#include <asm/uaccess.h>
#include <asm/firmware.h>
#include <linux/sort.h>
-
-#include "setup.h"
+#include <asm/setup.h>
LIST_HEAD(module_bug_list);
diff --git a/arch/powerpc/kernel/module_32.c b/arch/powerpc/kernel/module_32.c
index 0b6d79617d7..6cff040bf45 100644
--- a/arch/powerpc/kernel/module_32.c
+++ b/arch/powerpc/kernel/module_32.c
@@ -26,8 +26,7 @@
#include <linux/cache.h>
#include <linux/bug.h>
#include <linux/sort.h>
-
-#include "setup.h"
+#include <asm/setup.h>
#if 0
#define DEBUGP printk
@@ -176,8 +175,8 @@ int module_frob_arch_sections(Elf32_Ehdr *hdr,
static inline int entry_matches(struct ppc_plt_entry *entry, Elf32_Addr val)
{
- if (entry->jump[0] == 0x3d600000 + ((val + 0x8000) >> 16)
- && entry->jump[1] == 0x396b0000 + (val & 0xffff))
+ if (entry->jump[0] == 0x3d800000 + ((val + 0x8000) >> 16)
+ && entry->jump[1] == 0x398c0000 + (val & 0xffff))
return 1;
return 0;
}
@@ -204,10 +203,9 @@ static uint32_t do_plt_call(void *location,
entry++;
}
- /* Stolen from Paul Mackerras as well... */
- entry->jump[0] = 0x3d600000+((val+0x8000)>>16); /* lis r11,sym@ha */
- entry->jump[1] = 0x396b0000 + (val&0xffff); /* addi r11,r11,sym@l*/
- entry->jump[2] = 0x7d6903a6; /* mtctr r11 */
+ entry->jump[0] = 0x3d800000+((val+0x8000)>>16); /* lis r12,sym@ha */
+ entry->jump[1] = 0x398c0000 + (val&0xffff); /* addi r12,r12,sym@l*/
+ entry->jump[2] = 0x7d8903a6; /* mtctr r12 */
entry->jump[3] = 0x4e800420; /* bctr */
DEBUGP("Initialized plt for 0x%x at %p\n", val, entry);
diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c
index 9f44a775a10..d807ee626af 100644
--- a/arch/powerpc/kernel/module_64.c
+++ b/arch/powerpc/kernel/module_64.c
@@ -22,12 +22,12 @@
#include <linux/vmalloc.h>
#include <linux/ftrace.h>
#include <linux/bug.h>
+#include <linux/uaccess.h>
#include <asm/module.h>
#include <asm/firmware.h>
#include <asm/code-patching.h>
#include <linux/sort.h>
-
-#include "setup.h"
+#include <asm/setup.h>
/* FIXME: We don't do .init separately. To do this, we'd need to have
a separate r2 value in the init and core section, and stub between
@@ -42,35 +42,170 @@
#define DEBUGP(fmt , ...)
#endif
+#if defined(_CALL_ELF) && _CALL_ELF == 2
+#define R2_STACK_OFFSET 24
+
+/* An address is simply the address of the function. */
+typedef unsigned long func_desc_t;
+
+static func_desc_t func_desc(unsigned long addr)
+{
+ return addr;
+}
+static unsigned long func_addr(unsigned long addr)
+{
+ return addr;
+}
+static unsigned long stub_func_addr(func_desc_t func)
+{
+ return func;
+}
+
+/* PowerPC64 specific values for the Elf64_Sym st_other field. */
+#define STO_PPC64_LOCAL_BIT 5
+#define STO_PPC64_LOCAL_MASK (7 << STO_PPC64_LOCAL_BIT)
+#define PPC64_LOCAL_ENTRY_OFFSET(other) \
+ (((1 << (((other) & STO_PPC64_LOCAL_MASK) >> STO_PPC64_LOCAL_BIT)) >> 2) << 2)
+
+static unsigned int local_entry_offset(const Elf64_Sym *sym)
+{
+ /* sym->st_other indicates offset to local entry point
+ * (otherwise it will assume r12 is the address of the start
+ * of function and try to derive r2 from it). */
+ return PPC64_LOCAL_ENTRY_OFFSET(sym->st_other);
+}
+#else
+#define R2_STACK_OFFSET 40
+
+/* An address is address of the OPD entry, which contains address of fn. */
+typedef struct ppc64_opd_entry func_desc_t;
+
+static func_desc_t func_desc(unsigned long addr)
+{
+ return *(struct ppc64_opd_entry *)addr;
+}
+static unsigned long func_addr(unsigned long addr)
+{
+ return func_desc(addr).funcaddr;
+}
+static unsigned long stub_func_addr(func_desc_t func)
+{
+ return func.funcaddr;
+}
+static unsigned int local_entry_offset(const Elf64_Sym *sym)
+{
+ return 0;
+}
+#endif
+
/* Like PPC32, we need little trampolines to do > 24-bit jumps (into
the kernel itself). But on PPC64, these need to be used for every
jump, actually, to reset r2 (TOC+0x8000). */
struct ppc64_stub_entry
{
- /* 28 byte jump instruction sequence (7 instructions) */
- unsigned char jump[28];
- unsigned char unused[4];
+ /* 28 byte jump instruction sequence (7 instructions). We only
+ * need 6 instructions on ABIv2 but we always allocate 7 so
+ * so we don't have to modify the trampoline load instruction. */
+ u32 jump[7];
+ u32 unused;
/* Data for the above code */
- struct ppc64_opd_entry opd;
+ func_desc_t funcdata;
};
-/* We use a stub to fix up r2 (TOC ptr) and to jump to the (external)
- function which may be more than 24-bits away. We could simply
- patch the new r2 value and function pointer into the stub, but it's
- significantly shorter to put these values at the end of the stub
- code, and patch the stub address (32-bits relative to the TOC ptr,
- r2) into the stub. */
-static struct ppc64_stub_entry ppc64_stub =
-{ .jump = {
- 0x3d, 0x82, 0x00, 0x00, /* addis r12,r2, <high> */
- 0x39, 0x8c, 0x00, 0x00, /* addi r12,r12, <low> */
+/*
+ * PPC64 uses 24 bit jumps, but we need to jump into other modules or
+ * the kernel which may be further. So we jump to a stub.
+ *
+ * For ELFv1 we need to use this to set up the new r2 value (aka TOC
+ * pointer). For ELFv2 it's the callee's responsibility to set up the
+ * new r2, but for both we need to save the old r2.
+ *
+ * We could simply patch the new r2 value and function pointer into
+ * the stub, but it's significantly shorter to put these values at the
+ * end of the stub code, and patch the stub address (32-bits relative
+ * to the TOC ptr, r2) into the stub.
+ */
+
+static u32 ppc64_stub_insns[] = {
+ 0x3d620000, /* addis r11,r2, <high> */
+ 0x396b0000, /* addi r11,r11, <low> */
/* Save current r2 value in magic place on the stack. */
- 0xf8, 0x41, 0x00, 0x28, /* std r2,40(r1) */
- 0xe9, 0x6c, 0x00, 0x20, /* ld r11,32(r12) */
- 0xe8, 0x4c, 0x00, 0x28, /* ld r2,40(r12) */
- 0x7d, 0x69, 0x03, 0xa6, /* mtctr r11 */
- 0x4e, 0x80, 0x04, 0x20 /* bctr */
-} };
+ 0xf8410000|R2_STACK_OFFSET, /* std r2,R2_STACK_OFFSET(r1) */
+ 0xe98b0020, /* ld r12,32(r11) */
+#if !defined(_CALL_ELF) || _CALL_ELF != 2
+ /* Set up new r2 from function descriptor */
+ 0xe84b0028, /* ld r2,40(r11) */
+#endif
+ 0x7d8903a6, /* mtctr r12 */
+ 0x4e800420 /* bctr */
+};
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+
+static u32 ppc64_stub_mask[] = {
+ 0xffff0000,
+ 0xffff0000,
+ 0xffffffff,
+ 0xffffffff,
+#if !defined(_CALL_ELF) || _CALL_ELF != 2
+ 0xffffffff,
+#endif
+ 0xffffffff,
+ 0xffffffff
+};
+
+bool is_module_trampoline(u32 *p)
+{
+ unsigned int i;
+ u32 insns[ARRAY_SIZE(ppc64_stub_insns)];
+
+ BUILD_BUG_ON(sizeof(ppc64_stub_insns) != sizeof(ppc64_stub_mask));
+
+ if (probe_kernel_read(insns, p, sizeof(insns)))
+ return -EFAULT;
+
+ for (i = 0; i < ARRAY_SIZE(ppc64_stub_insns); i++) {
+ u32 insna = insns[i];
+ u32 insnb = ppc64_stub_insns[i];
+ u32 mask = ppc64_stub_mask[i];
+
+ if ((insna & mask) != (insnb & mask))
+ return false;
+ }
+
+ return true;
+}
+
+int module_trampoline_target(struct module *mod, u32 *trampoline,
+ unsigned long *target)
+{
+ u32 buf[2];
+ u16 upper, lower;
+ long offset;
+ void *toc_entry;
+
+ if (probe_kernel_read(buf, trampoline, sizeof(buf)))
+ return -EFAULT;
+
+ upper = buf[0] & 0xffff;
+ lower = buf[1] & 0xffff;
+
+ /* perform the addis/addi, both signed */
+ offset = ((short)upper << 16) + (short)lower;
+
+ /*
+ * Now get the address this trampoline jumps to. This
+ * is always 32 bytes into our trampoline stub.
+ */
+ toc_entry = (void *)mod->arch.toc + offset + 32;
+
+ if (probe_kernel_read(target, toc_entry, sizeof(*target)))
+ return -EFAULT;
+
+ return 0;
+}
+
+#endif
/* Count how many different 24-bit relocations (different symbol,
different addend) */
@@ -173,17 +308,27 @@ static unsigned long get_stubs_size(const Elf64_Ehdr *hdr,
return relocs * sizeof(struct ppc64_stub_entry);
}
+/* Still needed for ELFv2, for .TOC. */
static void dedotify_versions(struct modversion_info *vers,
unsigned long size)
{
struct modversion_info *end;
for (end = (void *)vers + size; vers < end; vers++)
- if (vers->name[0] == '.')
+ if (vers->name[0] == '.') {
memmove(vers->name, vers->name+1, strlen(vers->name));
+#ifdef ARCH_RELOCATES_KCRCTAB
+ /* The TOC symbol has no CRC computed. To avoid CRC
+ * check failing, we must force it to the expected
+ * value (see CRC check in module.c).
+ */
+ if (!strcmp(vers->name, "TOC."))
+ vers->crc = -(unsigned long)reloc_start;
+#endif
+ }
}
-/* Undefined symbols which refer to .funcname, hack to funcname */
+/* Undefined symbols which refer to .funcname, hack to funcname (or .TOC.) */
static void dedotify(Elf64_Sym *syms, unsigned int numsyms, char *strtab)
{
unsigned int i;
@@ -197,6 +342,24 @@ static void dedotify(Elf64_Sym *syms, unsigned int numsyms, char *strtab)
}
}
+static Elf64_Sym *find_dot_toc(Elf64_Shdr *sechdrs,
+ const char *strtab,
+ unsigned int symindex)
+{
+ unsigned int i, numsyms;
+ Elf64_Sym *syms;
+
+ syms = (Elf64_Sym *)sechdrs[symindex].sh_addr;
+ numsyms = sechdrs[symindex].sh_size / sizeof(Elf64_Sym);
+
+ for (i = 1; i < numsyms; i++) {
+ if (syms[i].st_shndx == SHN_UNDEF
+ && strcmp(strtab + syms[i].st_name, "TOC.") == 0)
+ return &syms[i];
+ }
+ return NULL;
+}
+
int module_frob_arch_sections(Elf64_Ehdr *hdr,
Elf64_Shdr *sechdrs,
char *secstrings,
@@ -261,16 +424,12 @@ static inline unsigned long my_r2(Elf64_Shdr *sechdrs, struct module *me)
/* Patch stub to reference function and correct r2 value. */
static inline int create_stub(Elf64_Shdr *sechdrs,
struct ppc64_stub_entry *entry,
- struct ppc64_opd_entry *opd,
+ unsigned long addr,
struct module *me)
{
- Elf64_Half *loc1, *loc2;
long reladdr;
- *entry = ppc64_stub;
-
- loc1 = (Elf64_Half *)&entry->jump[2];
- loc2 = (Elf64_Half *)&entry->jump[6];
+ memcpy(entry->jump, ppc64_stub_insns, sizeof(ppc64_stub_insns));
/* Stub uses address relative to r2. */
reladdr = (unsigned long)entry - my_r2(sechdrs, me);
@@ -281,35 +440,33 @@ static inline int create_stub(Elf64_Shdr *sechdrs,
}
DEBUGP("Stub %p get data from reladdr %li\n", entry, reladdr);
- *loc1 = PPC_HA(reladdr);
- *loc2 = PPC_LO(reladdr);
- entry->opd.funcaddr = opd->funcaddr;
- entry->opd.r2 = opd->r2;
+ entry->jump[0] |= PPC_HA(reladdr);
+ entry->jump[1] |= PPC_LO(reladdr);
+ entry->funcdata = func_desc(addr);
return 1;
}
-/* Create stub to jump to function described in this OPD: we need the
+/* Create stub to jump to function described in this OPD/ptr: we need the
stub to set up the TOC ptr (r2) for the function. */
static unsigned long stub_for_addr(Elf64_Shdr *sechdrs,
- unsigned long opdaddr,
+ unsigned long addr,
struct module *me)
{
struct ppc64_stub_entry *stubs;
- struct ppc64_opd_entry *opd = (void *)opdaddr;
unsigned int i, num_stubs;
num_stubs = sechdrs[me->arch.stubs_section].sh_size / sizeof(*stubs);
/* Find this stub, or if that fails, the next avail. entry */
stubs = (void *)sechdrs[me->arch.stubs_section].sh_addr;
- for (i = 0; stubs[i].opd.funcaddr; i++) {
+ for (i = 0; stub_func_addr(stubs[i].funcdata); i++) {
BUG_ON(i >= num_stubs);
- if (stubs[i].opd.funcaddr == opd->funcaddr)
+ if (stub_func_addr(stubs[i].funcdata) == func_addr(addr))
return (unsigned long)&stubs[i];
}
- if (!create_stub(sechdrs, &stubs[i], opd, me))
+ if (!create_stub(sechdrs, &stubs[i], addr, me))
return 0;
return (unsigned long)&stubs[i];
@@ -324,7 +481,8 @@ static int restore_r2(u32 *instruction, struct module *me)
me->name, *instruction);
return 0;
}
- *instruction = 0xe8410028; /* ld r2,40(r1) */
+ /* ld r2,R2_STACK_OFFSET(r1) */
+ *instruction = 0xe8410000 | R2_STACK_OFFSET;
return 1;
}
@@ -342,6 +500,17 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
DEBUGP("Applying ADD relocate section %u to %u\n", relsec,
sechdrs[relsec].sh_info);
+
+ /* First time we're called, we can fix up .TOC. */
+ if (!me->arch.toc_fixed) {
+ sym = find_dot_toc(sechdrs, strtab, symindex);
+ /* It's theoretically possible that a module doesn't want a
+ * .TOC. so don't fail it just for that. */
+ if (sym)
+ sym->st_value = my_r2(sechdrs, me);
+ me->arch.toc_fixed = true;
+ }
+
for (i = 0; i < sechdrs[relsec].sh_size / sizeof(*rela); i++) {
/* This is where to make the change */
location = (void *)sechdrs[sechdrs[relsec].sh_info].sh_addr
@@ -386,6 +555,14 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
| (value & 0xffff);
break;
+ case R_PPC64_TOC16_LO:
+ /* Subtract TOC pointer */
+ value -= my_r2(sechdrs, me);
+ *((uint16_t *) location)
+ = (*((uint16_t *) location) & ~0xffff)
+ | (value & 0xffff);
+ break;
+
case R_PPC64_TOC16_DS:
/* Subtract TOC pointer */
value -= my_r2(sechdrs, me);
@@ -399,6 +576,28 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
| (value & 0xfffc);
break;
+ case R_PPC64_TOC16_LO_DS:
+ /* Subtract TOC pointer */
+ value -= my_r2(sechdrs, me);
+ if ((value & 3) != 0) {
+ printk("%s: bad TOC16_LO_DS relocation (%lu)\n",
+ me->name, value);
+ return -ENOEXEC;
+ }
+ *((uint16_t *) location)
+ = (*((uint16_t *) location) & ~0xfffc)
+ | (value & 0xfffc);
+ break;
+
+ case R_PPC64_TOC16_HA:
+ /* Subtract TOC pointer */
+ value -= my_r2(sechdrs, me);
+ value = ((value + 0x8000) >> 16);
+ *((uint16_t *) location)
+ = (*((uint16_t *) location) & ~0xffff)
+ | (value & 0xffff);
+ break;
+
case R_PPC_REL24:
/* FIXME: Handle weak symbols here --RR */
if (sym->st_shndx == SHN_UNDEF) {
@@ -408,7 +607,8 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
return -ENOENT;
if (!restore_r2((u32 *)location + 1, me))
return -ENOEXEC;
- }
+ } else
+ value += local_entry_offset(sym);
/* Convert value to relative */
value -= (unsigned long)location;
@@ -429,6 +629,31 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
*location = value - (unsigned long)location;
break;
+ case R_PPC64_TOCSAVE:
+ /*
+ * Marker reloc indicates we don't have to save r2.
+ * That would only save us one instruction, so ignore
+ * it.
+ */
+ break;
+
+ case R_PPC64_REL16_HA:
+ /* Subtract location pointer */
+ value -= (unsigned long)location;
+ value = ((value + 0x8000) >> 16);
+ *((uint16_t *) location)
+ = (*((uint16_t *) location) & ~0xffff)
+ | (value & 0xffff);
+ break;
+
+ case R_PPC64_REL16_LO:
+ /* Subtract location pointer */
+ value -= (unsigned long)location;
+ *((uint16_t *) location)
+ = (*((uint16_t *) location) & ~0xffff)
+ | (value & 0xffff);
+ break;
+
default:
printk("%s: Unknown ADD relocation: %lu\n",
me->name,
diff --git a/arch/powerpc/kernel/mpc7450-pmu.c b/arch/powerpc/kernel/mpc7450-pmu.c
deleted file mode 100644
index fe21b515ca4..00000000000
--- a/arch/powerpc/kernel/mpc7450-pmu.c
+++ /dev/null
@@ -1,422 +0,0 @@
-/*
- * Performance counter support for MPC7450-family processors.
- *
- * Copyright 2008-2009 Paul Mackerras, IBM Corporation.
- *
- * 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.
- */
-#include <linux/string.h>
-#include <linux/perf_event.h>
-#include <asm/reg.h>
-#include <asm/cputable.h>
-
-#define N_COUNTER 6 /* Number of hardware counters */
-#define MAX_ALT 3 /* Maximum number of event alternative codes */
-
-/*
- * Bits in event code for MPC7450 family
- */
-#define PM_THRMULT_MSKS 0x40000
-#define PM_THRESH_SH 12
-#define PM_THRESH_MSK 0x3f
-#define PM_PMC_SH 8
-#define PM_PMC_MSK 7
-#define PM_PMCSEL_MSK 0x7f
-
-/*
- * Classify events according to how specific their PMC requirements are.
- * Result is:
- * 0: can go on any PMC
- * 1: can go on PMCs 1-4
- * 2: can go on PMCs 1,2,4
- * 3: can go on PMCs 1 or 2
- * 4: can only go on one PMC
- * -1: event code is invalid
- */
-#define N_CLASSES 5
-
-static int mpc7450_classify_event(u32 event)
-{
- int pmc;
-
- pmc = (event >> PM_PMC_SH) & PM_PMC_MSK;
- if (pmc) {
- if (pmc > N_COUNTER)
- return -1;
- return 4;
- }
- event &= PM_PMCSEL_MSK;
- if (event <= 1)
- return 0;
- if (event <= 7)
- return 1;
- if (event <= 13)
- return 2;
- if (event <= 22)
- return 3;
- return -1;
-}
-
-/*
- * Events using threshold and possible threshold scale:
- * code scale? name
- * 11e N PM_INSTQ_EXCEED_CYC
- * 11f N PM_ALTV_IQ_EXCEED_CYC
- * 128 Y PM_DTLB_SEARCH_EXCEED_CYC
- * 12b Y PM_LD_MISS_EXCEED_L1_CYC
- * 220 N PM_CQ_EXCEED_CYC
- * 30c N PM_GPR_RB_EXCEED_CYC
- * 30d ? PM_FPR_IQ_EXCEED_CYC ?
- * 311 Y PM_ITLB_SEARCH_EXCEED
- * 410 N PM_GPR_IQ_EXCEED_CYC
- */
-
-/*
- * Return use of threshold and threshold scale bits:
- * 0 = uses neither, 1 = uses threshold, 2 = uses both
- */
-static int mpc7450_threshold_use(u32 event)
-{
- int pmc, sel;
-
- pmc = (event >> PM_PMC_SH) & PM_PMC_MSK;
- sel = event & PM_PMCSEL_MSK;
- switch (pmc) {
- case 1:
- if (sel == 0x1e || sel == 0x1f)
- return 1;
- if (sel == 0x28 || sel == 0x2b)
- return 2;
- break;
- case 2:
- if (sel == 0x20)
- return 1;
- break;
- case 3:
- if (sel == 0xc || sel == 0xd)
- return 1;
- if (sel == 0x11)
- return 2;
- break;
- case 4:
- if (sel == 0x10)
- return 1;
- break;
- }
- return 0;
-}
-
-/*
- * Layout of constraint bits:
- * 33222222222211111111110000000000
- * 10987654321098765432109876543210
- * |< >< > < > < ><><><><><><>
- * TS TV G4 G3 G2P6P5P4P3P2P1
- *
- * P1 - P6
- * 0 - 11: Count of events needing PMC1 .. PMC6
- *
- * G2
- * 12 - 14: Count of events needing PMC1 or PMC2
- *
- * G3
- * 16 - 18: Count of events needing PMC1, PMC2 or PMC4
- *
- * G4
- * 20 - 23: Count of events needing PMC1, PMC2, PMC3 or PMC4
- *
- * TV
- * 24 - 29: Threshold value requested
- *
- * TS
- * 30: Threshold scale value requested
- */
-
-static u32 pmcbits[N_COUNTER][2] = {
- { 0x00844002, 0x00111001 }, /* PMC1 mask, value: P1,G2,G3,G4 */
- { 0x00844008, 0x00111004 }, /* PMC2: P2,G2,G3,G4 */
- { 0x00800020, 0x00100010 }, /* PMC3: P3,G4 */
- { 0x00840080, 0x00110040 }, /* PMC4: P4,G3,G4 */
- { 0x00000200, 0x00000100 }, /* PMC5: P5 */
- { 0x00000800, 0x00000400 } /* PMC6: P6 */
-};
-
-static u32 classbits[N_CLASSES - 1][2] = {
- { 0x00000000, 0x00000000 }, /* class 0: no constraint */
- { 0x00800000, 0x00100000 }, /* class 1: G4 */
- { 0x00040000, 0x00010000 }, /* class 2: G3 */
- { 0x00004000, 0x00001000 }, /* class 3: G2 */
-};
-
-static int mpc7450_get_constraint(u64 event, unsigned long *maskp,
- unsigned long *valp)
-{
- int pmc, class;
- u32 mask, value;
- int thresh, tuse;
-
- class = mpc7450_classify_event(event);
- if (class < 0)
- return -1;
- if (class == 4) {
- pmc = ((unsigned int)event >> PM_PMC_SH) & PM_PMC_MSK;
- mask = pmcbits[pmc - 1][0];
- value = pmcbits[pmc - 1][1];
- } else {
- mask = classbits[class][0];
- value = classbits[class][1];
- }
-
- tuse = mpc7450_threshold_use(event);
- if (tuse) {
- thresh = ((unsigned int)event >> PM_THRESH_SH) & PM_THRESH_MSK;
- mask |= 0x3f << 24;
- value |= thresh << 24;
- if (tuse == 2) {
- mask |= 0x40000000;
- if ((unsigned int)event & PM_THRMULT_MSKS)
- value |= 0x40000000;
- }
- }
-
- *maskp = mask;
- *valp = value;
- return 0;
-}
-
-static const unsigned int event_alternatives[][MAX_ALT] = {
- { 0x217, 0x317 }, /* PM_L1_DCACHE_MISS */
- { 0x418, 0x50f, 0x60f }, /* PM_SNOOP_RETRY */
- { 0x502, 0x602 }, /* PM_L2_HIT */
- { 0x503, 0x603 }, /* PM_L3_HIT */
- { 0x504, 0x604 }, /* PM_L2_ICACHE_MISS */
- { 0x505, 0x605 }, /* PM_L3_ICACHE_MISS */
- { 0x506, 0x606 }, /* PM_L2_DCACHE_MISS */
- { 0x507, 0x607 }, /* PM_L3_DCACHE_MISS */
- { 0x50a, 0x623 }, /* PM_LD_HIT_L3 */
- { 0x50b, 0x624 }, /* PM_ST_HIT_L3 */
- { 0x50d, 0x60d }, /* PM_L2_TOUCH_HIT */
- { 0x50e, 0x60e }, /* PM_L3_TOUCH_HIT */
- { 0x512, 0x612 }, /* PM_INT_LOCAL */
- { 0x513, 0x61d }, /* PM_L2_MISS */
- { 0x514, 0x61e }, /* PM_L3_MISS */
-};
-
-/*
- * Scan the alternatives table for a match and return the
- * index into the alternatives table if found, else -1.
- */
-static int find_alternative(u32 event)
-{
- int i, j;
-
- for (i = 0; i < ARRAY_SIZE(event_alternatives); ++i) {
- if (event < event_alternatives[i][0])
- break;
- for (j = 0; j < MAX_ALT && event_alternatives[i][j]; ++j)
- if (event == event_alternatives[i][j])
- return i;
- }
- return -1;
-}
-
-static int mpc7450_get_alternatives(u64 event, unsigned int flags, u64 alt[])
-{
- int i, j, nalt = 1;
- u32 ae;
-
- alt[0] = event;
- nalt = 1;
- i = find_alternative((u32)event);
- if (i >= 0) {
- for (j = 0; j < MAX_ALT; ++j) {
- ae = event_alternatives[i][j];
- if (ae && ae != (u32)event)
- alt[nalt++] = ae;
- }
- }
- return nalt;
-}
-
-/*
- * Bitmaps of which PMCs each class can use for classes 0 - 3.
- * Bit i is set if PMC i+1 is usable.
- */
-static const u8 classmap[N_CLASSES] = {
- 0x3f, 0x0f, 0x0b, 0x03, 0
-};
-
-/* Bit position and width of each PMCSEL field */
-static const int pmcsel_shift[N_COUNTER] = {
- 6, 0, 27, 22, 17, 11
-};
-static const u32 pmcsel_mask[N_COUNTER] = {
- 0x7f, 0x3f, 0x1f, 0x1f, 0x1f, 0x3f
-};
-
-/*
- * Compute MMCR0/1/2 values for a set of events.
- */
-static int mpc7450_compute_mmcr(u64 event[], int n_ev,
- unsigned int hwc[], unsigned long mmcr[])
-{
- u8 event_index[N_CLASSES][N_COUNTER];
- int n_classevent[N_CLASSES];
- int i, j, class, tuse;
- u32 pmc_inuse = 0, pmc_avail;
- u32 mmcr0 = 0, mmcr1 = 0, mmcr2 = 0;
- u32 ev, pmc, thresh;
-
- if (n_ev > N_COUNTER)
- return -1;
-
- /* First pass: count usage in each class */
- for (i = 0; i < N_CLASSES; ++i)
- n_classevent[i] = 0;
- for (i = 0; i < n_ev; ++i) {
- class = mpc7450_classify_event(event[i]);
- if (class < 0)
- return -1;
- j = n_classevent[class]++;
- event_index[class][j] = i;
- }
-
- /* Second pass: allocate PMCs from most specific event to least */
- for (class = N_CLASSES - 1; class >= 0; --class) {
- for (i = 0; i < n_classevent[class]; ++i) {
- ev = event[event_index[class][i]];
- if (class == 4) {
- pmc = (ev >> PM_PMC_SH) & PM_PMC_MSK;
- if (pmc_inuse & (1 << (pmc - 1)))
- return -1;
- } else {
- /* Find a suitable PMC */
- pmc_avail = classmap[class] & ~pmc_inuse;
- if (!pmc_avail)
- return -1;
- pmc = ffs(pmc_avail);
- }
- pmc_inuse |= 1 << (pmc - 1);
-
- tuse = mpc7450_threshold_use(ev);
- if (tuse) {
- thresh = (ev >> PM_THRESH_SH) & PM_THRESH_MSK;
- mmcr0 |= thresh << 16;
- if (tuse == 2 && (ev & PM_THRMULT_MSKS))
- mmcr2 = 0x80000000;
- }
- ev &= pmcsel_mask[pmc - 1];
- ev <<= pmcsel_shift[pmc - 1];
- if (pmc <= 2)
- mmcr0 |= ev;
- else
- mmcr1 |= ev;
- hwc[event_index[class][i]] = pmc - 1;
- }
- }
-
- if (pmc_inuse & 1)
- mmcr0 |= MMCR0_PMC1CE;
- if (pmc_inuse & 0x3e)
- mmcr0 |= MMCR0_PMCnCE;
-
- /* Return MMCRx values */
- mmcr[0] = mmcr0;
- mmcr[1] = mmcr1;
- mmcr[2] = mmcr2;
- return 0;
-}
-
-/*
- * Disable counting by a PMC.
- * Note that the pmc argument is 0-based here, not 1-based.
- */
-static void mpc7450_disable_pmc(unsigned int pmc, unsigned long mmcr[])
-{
- if (pmc <= 1)
- mmcr[0] &= ~(pmcsel_mask[pmc] << pmcsel_shift[pmc]);
- else
- mmcr[1] &= ~(pmcsel_mask[pmc] << pmcsel_shift[pmc]);
-}
-
-static int mpc7450_generic_events[] = {
- [PERF_COUNT_HW_CPU_CYCLES] = 1,
- [PERF_COUNT_HW_INSTRUCTIONS] = 2,
- [PERF_COUNT_HW_CACHE_MISSES] = 0x217, /* PM_L1_DCACHE_MISS */
- [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x122, /* PM_BR_CMPL */
- [PERF_COUNT_HW_BRANCH_MISSES] = 0x41c, /* PM_BR_MPRED */
-};
-
-#define C(x) PERF_COUNT_HW_CACHE_##x
-
-/*
- * Table of generalized cache-related events.
- * 0 means not supported, -1 means nonsensical, other values
- * are event codes.
- */
-static int mpc7450_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
- [C(L1D)] = { /* RESULT_ACCESS RESULT_MISS */
- [C(OP_READ)] = { 0, 0x225 },
- [C(OP_WRITE)] = { 0, 0x227 },
- [C(OP_PREFETCH)] = { 0, 0 },
- },
- [C(L1I)] = { /* RESULT_ACCESS RESULT_MISS */
- [C(OP_READ)] = { 0x129, 0x115 },
- [C(OP_WRITE)] = { -1, -1 },
- [C(OP_PREFETCH)] = { 0x634, 0 },
- },
- [C(LL)] = { /* RESULT_ACCESS RESULT_MISS */
- [C(OP_READ)] = { 0, 0 },
- [C(OP_WRITE)] = { 0, 0 },
- [C(OP_PREFETCH)] = { 0, 0 },
- },
- [C(DTLB)] = { /* RESULT_ACCESS RESULT_MISS */
- [C(OP_READ)] = { 0, 0x312 },
- [C(OP_WRITE)] = { -1, -1 },
- [C(OP_PREFETCH)] = { -1, -1 },
- },
- [C(ITLB)] = { /* RESULT_ACCESS RESULT_MISS */
- [C(OP_READ)] = { 0, 0x223 },
- [C(OP_WRITE)] = { -1, -1 },
- [C(OP_PREFETCH)] = { -1, -1 },
- },
- [C(BPU)] = { /* RESULT_ACCESS RESULT_MISS */
- [C(OP_READ)] = { 0x122, 0x41c },
- [C(OP_WRITE)] = { -1, -1 },
- [C(OP_PREFETCH)] = { -1, -1 },
- },
- [C(NODE)] = { /* RESULT_ACCESS RESULT_MISS */
- [C(OP_READ)] = { -1, -1 },
- [C(OP_WRITE)] = { -1, -1 },
- [C(OP_PREFETCH)] = { -1, -1 },
- },
-};
-
-struct power_pmu mpc7450_pmu = {
- .name = "MPC7450 family",
- .n_counter = N_COUNTER,
- .max_alternatives = MAX_ALT,
- .add_fields = 0x00111555ul,
- .test_adder = 0x00301000ul,
- .compute_mmcr = mpc7450_compute_mmcr,
- .get_constraint = mpc7450_get_constraint,
- .get_alternatives = mpc7450_get_alternatives,
- .disable_pmc = mpc7450_disable_pmc,
- .n_generic = ARRAY_SIZE(mpc7450_generic_events),
- .generic_events = mpc7450_generic_events,
- .cache_events = &mpc7450_cache_events,
-};
-
-static int __init init_mpc7450_pmu(void)
-{
- if (!cur_cpu_spec->oprofile_cpu_type ||
- strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc/7450"))
- return -ENODEV;
-
- return register_power_pmu(&mpc7450_pmu);
-}
-
-early_initcall(init_mpc7450_pmu);
diff --git a/arch/powerpc/kernel/nvram_64.c b/arch/powerpc/kernel/nvram_64.c