Merge branch 'for-3.2-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup
* 'for-3.2-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup:
cgroup: Replace Paul Menage with Tejun Heo as cgroups maintainer
diff --git a/arch/sparc/include/asm/pgtable_32.h b/arch/sparc/include/asm/pgtable_32.h
index 5b31a8e..a790cc6 100644
--- a/arch/sparc/include/asm/pgtable_32.h
+++ b/arch/sparc/include/asm/pgtable_32.h
@@ -431,10 +431,6 @@
#define kern_addr_valid(addr) \
(test_bit(__pa((unsigned long)(addr))>>20, sparc_valid_addr_bitmap))
-extern int io_remap_pfn_range(struct vm_area_struct *vma,
- unsigned long from, unsigned long pfn,
- unsigned long size, pgprot_t prot);
-
/*
* For sparc32&64, the pfn in io_remap_pfn_range() carries <iospace> in
* its high 4 bits. These macros/functions put it there or get it from there.
@@ -443,6 +439,22 @@
#define GET_IOSPACE(pfn) (pfn >> (BITS_PER_LONG - 4))
#define GET_PFN(pfn) (pfn & 0x0fffffffUL)
+extern int remap_pfn_range(struct vm_area_struct *, unsigned long, unsigned long,
+ unsigned long, pgprot_t);
+
+static inline int io_remap_pfn_range(struct vm_area_struct *vma,
+ unsigned long from, unsigned long pfn,
+ unsigned long size, pgprot_t prot)
+{
+ unsigned long long offset, space, phys_base;
+
+ offset = ((unsigned long long) GET_PFN(pfn)) << PAGE_SHIFT;
+ space = GET_IOSPACE(pfn);
+ phys_base = offset | (space << 32ULL);
+
+ return remap_pfn_range(vma, from, phys_base >> PAGE_SHIFT, size, prot);
+}
+
#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
#define ptep_set_access_flags(__vma, __address, __ptep, __entry, __dirty) \
({ \
diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h
index adf8932..38ebb2c 100644
--- a/arch/sparc/include/asm/pgtable_64.h
+++ b/arch/sparc/include/asm/pgtable_64.h
@@ -757,10 +757,6 @@
extern int page_in_phys_avail(unsigned long paddr);
-extern int io_remap_pfn_range(struct vm_area_struct *vma, unsigned long from,
- unsigned long pfn,
- unsigned long size, pgprot_t prot);
-
/*
* For sparc32&64, the pfn in io_remap_pfn_range() carries <iospace> in
* its high 4 bits. These macros/functions put it there or get it from there.
@@ -769,6 +765,22 @@
#define GET_IOSPACE(pfn) (pfn >> (BITS_PER_LONG - 4))
#define GET_PFN(pfn) (pfn & 0x0fffffffffffffffUL)
+extern int remap_pfn_range(struct vm_area_struct *, unsigned long, unsigned long,
+ unsigned long, pgprot_t);
+
+static inline int io_remap_pfn_range(struct vm_area_struct *vma,
+ unsigned long from, unsigned long pfn,
+ unsigned long size, pgprot_t prot)
+{
+ unsigned long offset = GET_PFN(pfn) << PAGE_SHIFT;
+ int space = GET_IOSPACE(pfn);
+ unsigned long phys_base;
+
+ phys_base = offset | (((unsigned long) space) << 32UL);
+
+ return remap_pfn_range(vma, from, phys_base >> PAGE_SHIFT, size, prot);
+}
+
#include <asm-generic/pgtable.h>
/* We provide our own get_unmapped_area to cope with VA holes and
diff --git a/arch/sparc/kernel/entry.h b/arch/sparc/kernel/entry.h
index e27f8ea..0c218e4 100644
--- a/arch/sparc/kernel/entry.h
+++ b/arch/sparc/kernel/entry.h
@@ -42,6 +42,9 @@
extern void fpload(unsigned long *fpregs, unsigned long *fsr);
#else /* CONFIG_SPARC32 */
+
+#include <asm/trap_block.h>
+
struct popc_3insn_patch_entry {
unsigned int addr;
unsigned int insns[3];
@@ -57,6 +60,10 @@
__popc_6insn_patch_end;
extern void __init per_cpu_patch(void);
+extern void sun4v_patch_1insn_range(struct sun4v_1insn_patch_entry *,
+ struct sun4v_1insn_patch_entry *);
+extern void sun4v_patch_2insn_range(struct sun4v_2insn_patch_entry *,
+ struct sun4v_2insn_patch_entry *);
extern void __init sun4v_patch(void);
extern void __init boot_cpu_id_too_large(int cpu);
extern unsigned int dcache_parity_tl1_occurred;
diff --git a/arch/sparc/kernel/module.c b/arch/sparc/kernel/module.c
index da0c6c7..e551987 100644
--- a/arch/sparc/kernel/module.c
+++ b/arch/sparc/kernel/module.c
@@ -17,6 +17,8 @@
#include <asm/processor.h>
#include <asm/spitfire.h>
+#include "entry.h"
+
#ifdef CONFIG_SPARC64
#include <linux/jump_label.h>
@@ -203,6 +205,29 @@
}
#ifdef CONFIG_SPARC64
+static void do_patch_sections(const Elf_Ehdr *hdr,
+ const Elf_Shdr *sechdrs)
+{
+ const Elf_Shdr *s, *sun4v_1insn = NULL, *sun4v_2insn = NULL;
+ char *secstrings = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;
+
+ for (s = sechdrs; s < sechdrs + hdr->e_shnum; s++) {
+ if (!strcmp(".sun4v_1insn_patch", secstrings + s->sh_name))
+ sun4v_1insn = s;
+ if (!strcmp(".sun4v_2insn_patch", secstrings + s->sh_name))
+ sun4v_2insn = s;
+ }
+
+ if (sun4v_1insn && tlb_type == hypervisor) {
+ void *p = (void *) sun4v_1insn->sh_addr;
+ sun4v_patch_1insn_range(p, p + sun4v_1insn->sh_size);
+ }
+ if (sun4v_2insn && tlb_type == hypervisor) {
+ void *p = (void *) sun4v_2insn->sh_addr;
+ sun4v_patch_2insn_range(p, p + sun4v_2insn->sh_size);
+ }
+}
+
int module_finalize(const Elf_Ehdr *hdr,
const Elf_Shdr *sechdrs,
struct module *me)
@@ -210,6 +235,8 @@
/* make jump label nops */
jump_label_apply_nops(me);
+ do_patch_sections(hdr, sechdrs);
+
/* Cheetah's I-cache is fully coherent. */
if (tlb_type == spitfire) {
unsigned long va;
diff --git a/arch/sparc/kernel/setup_64.c b/arch/sparc/kernel/setup_64.c
index c965595a..a854a1c 100644
--- a/arch/sparc/kernel/setup_64.c
+++ b/arch/sparc/kernel/setup_64.c
@@ -234,40 +234,50 @@
}
}
+void sun4v_patch_1insn_range(struct sun4v_1insn_patch_entry *start,
+ struct sun4v_1insn_patch_entry *end)
+{
+ while (start < end) {
+ unsigned long addr = start->addr;
+
+ *(unsigned int *) (addr + 0) = start->insn;
+ wmb();
+ __asm__ __volatile__("flush %0" : : "r" (addr + 0));
+
+ start++;
+ }
+}
+
+void sun4v_patch_2insn_range(struct sun4v_2insn_patch_entry *start,
+ struct sun4v_2insn_patch_entry *end)
+{
+ while (start < end) {
+ unsigned long addr = start->addr;
+
+ *(unsigned int *) (addr + 0) = start->insns[0];
+ wmb();
+ __asm__ __volatile__("flush %0" : : "r" (addr + 0));
+
+ *(unsigned int *) (addr + 4) = start->insns[1];
+ wmb();
+ __asm__ __volatile__("flush %0" : : "r" (addr + 4));
+
+ start++;
+ }
+}
+
void __init sun4v_patch(void)
{
extern void sun4v_hvapi_init(void);
- struct sun4v_1insn_patch_entry *p1;
- struct sun4v_2insn_patch_entry *p2;
if (tlb_type != hypervisor)
return;
- p1 = &__sun4v_1insn_patch;
- while (p1 < &__sun4v_1insn_patch_end) {
- unsigned long addr = p1->addr;
+ sun4v_patch_1insn_range(&__sun4v_1insn_patch,
+ &__sun4v_1insn_patch_end);
- *(unsigned int *) (addr + 0) = p1->insn;
- wmb();
- __asm__ __volatile__("flush %0" : : "r" (addr + 0));
-
- p1++;
- }
-
- p2 = &__sun4v_2insn_patch;
- while (p2 < &__sun4v_2insn_patch_end) {
- unsigned long addr = p2->addr;
-
- *(unsigned int *) (addr + 0) = p2->insns[0];
- wmb();
- __asm__ __volatile__("flush %0" : : "r" (addr + 0));
-
- *(unsigned int *) (addr + 4) = p2->insns[1];
- wmb();
- __asm__ __volatile__("flush %0" : : "r" (addr + 4));
-
- p2++;
- }
+ sun4v_patch_2insn_range(&__sun4v_2insn_patch,
+ &__sun4v_2insn_patch_end);
sun4v_hvapi_init();
}
diff --git a/arch/sparc/kernel/signal32.c b/arch/sparc/kernel/signal32.c
index 2caa556..023b886 100644
--- a/arch/sparc/kernel/signal32.c
+++ b/arch/sparc/kernel/signal32.c
@@ -822,21 +822,23 @@
* want to handle. Thus you cannot kill init even with a SIGKILL even by
* mistake.
*/
-void do_signal32(sigset_t *oldset, struct pt_regs * regs,
- int restart_syscall, unsigned long orig_i0)
+void do_signal32(sigset_t *oldset, struct pt_regs * regs)
{
struct k_sigaction ka;
+ unsigned long orig_i0;
+ int restart_syscall;
siginfo_t info;
int signr;
signr = get_signal_to_deliver(&info, &ka, regs, NULL);
- /* If the debugger messes with the program counter, it clears
- * the "in syscall" bit, directing us to not perform a syscall
- * restart.
- */
- if (restart_syscall && !pt_regs_is_syscall(regs))
- restart_syscall = 0;
+ restart_syscall = 0;
+ orig_i0 = 0;
+ if (pt_regs_is_syscall(regs) &&
+ (regs->tstate & (TSTATE_XCARRY | TSTATE_ICARRY))) {
+ restart_syscall = 1;
+ orig_i0 = regs->u_regs[UREG_G6];
+ }
if (signr > 0) {
if (restart_syscall)
diff --git a/arch/sparc/kernel/signal_32.c b/arch/sparc/kernel/signal_32.c
index 8ce247a..d54c6e5 100644
--- a/arch/sparc/kernel/signal_32.c
+++ b/arch/sparc/kernel/signal_32.c
@@ -519,10 +519,26 @@
siginfo_t info;
int signr;
+ /* It's a lot of work and synchronization to add a new ptrace
+ * register for GDB to save and restore in order to get
+ * orig_i0 correct for syscall restarts when debugging.
+ *
+ * Although it should be the case that most of the global
+ * registers are volatile across a system call, glibc already
+ * depends upon that fact that we preserve them. So we can't
+ * just use any global register to save away the orig_i0 value.
+ *
+ * In particular %g2, %g3, %g4, and %g5 are all assumed to be
+ * preserved across a system call trap by various pieces of
+ * code in glibc.
+ *
+ * %g7 is used as the "thread register". %g6 is not used in
+ * any fixed manner. %g6 is used as a scratch register and
+ * a compiler temporary, but it's value is never used across
+ * a system call. Therefore %g6 is usable for orig_i0 storage.
+ */
if (pt_regs_is_syscall(regs) && (regs->psr & PSR_C))
- restart_syscall = 1;
- else
- restart_syscall = 0;
+ regs->u_regs[UREG_G6] = orig_i0;
if (test_thread_flag(TIF_RESTORE_SIGMASK))
oldset = ¤t->saved_sigmask;
@@ -535,8 +551,12 @@
* the software "in syscall" bit, directing us to not perform
* a syscall restart.
*/
- if (restart_syscall && !pt_regs_is_syscall(regs))
- restart_syscall = 0;
+ restart_syscall = 0;
+ if (pt_regs_is_syscall(regs) && (regs->psr & PSR_C)) {
+ restart_syscall = 1;
+ orig_i0 = regs->u_regs[UREG_G6];
+ }
+
if (signr > 0) {
if (restart_syscall)
diff --git a/arch/sparc/kernel/signal_64.c b/arch/sparc/kernel/signal_64.c
index a2b8159..f0836cd 100644
--- a/arch/sparc/kernel/signal_64.c
+++ b/arch/sparc/kernel/signal_64.c
@@ -529,11 +529,27 @@
siginfo_t info;
int signr;
+ /* It's a lot of work and synchronization to add a new ptrace
+ * register for GDB to save and restore in order to get
+ * orig_i0 correct for syscall restarts when debugging.
+ *
+ * Although it should be the case that most of the global
+ * registers are volatile across a system call, glibc already
+ * depends upon that fact that we preserve them. So we can't
+ * just use any global register to save away the orig_i0 value.
+ *
+ * In particular %g2, %g3, %g4, and %g5 are all assumed to be
+ * preserved across a system call trap by various pieces of
+ * code in glibc.
+ *
+ * %g7 is used as the "thread register". %g6 is not used in
+ * any fixed manner. %g6 is used as a scratch register and
+ * a compiler temporary, but it's value is never used across
+ * a system call. Therefore %g6 is usable for orig_i0 storage.
+ */
if (pt_regs_is_syscall(regs) &&
- (regs->tstate & (TSTATE_XCARRY | TSTATE_ICARRY))) {
- restart_syscall = 1;
- } else
- restart_syscall = 0;
+ (regs->tstate & (TSTATE_XCARRY | TSTATE_ICARRY)))
+ regs->u_regs[UREG_G6] = orig_i0;
if (current_thread_info()->status & TS_RESTORE_SIGMASK)
oldset = ¤t->saved_sigmask;
@@ -542,22 +558,20 @@
#ifdef CONFIG_COMPAT
if (test_thread_flag(TIF_32BIT)) {
- extern void do_signal32(sigset_t *, struct pt_regs *,
- int restart_syscall,
- unsigned long orig_i0);
- do_signal32(oldset, regs, restart_syscall, orig_i0);
+ extern void do_signal32(sigset_t *, struct pt_regs *);
+ do_signal32(oldset, regs);
return;
}
#endif
signr = get_signal_to_deliver(&info, &ka, regs, NULL);
- /* If the debugger messes with the program counter, it clears
- * the software "in syscall" bit, directing us to not perform
- * a syscall restart.
- */
- if (restart_syscall && !pt_regs_is_syscall(regs))
- restart_syscall = 0;
+ restart_syscall = 0;
+ if (pt_regs_is_syscall(regs) &&
+ (regs->tstate & (TSTATE_XCARRY | TSTATE_ICARRY))) {
+ restart_syscall = 1;
+ orig_i0 = regs->u_regs[UREG_G6];
+ }
if (signr > 0) {
if (restart_syscall)
diff --git a/arch/sparc/kernel/sigutil_64.c b/arch/sparc/kernel/sigutil_64.c
index e7dc508..b19570d 100644
--- a/arch/sparc/kernel/sigutil_64.c
+++ b/arch/sparc/kernel/sigutil_64.c
@@ -2,6 +2,7 @@
#include <linux/types.h>
#include <linux/thread_info.h>
#include <linux/uaccess.h>
+#include <linux/errno.h>
#include <asm/sigcontext.h>
#include <asm/fpumacro.h>
diff --git a/arch/sparc/mm/Makefile b/arch/sparc/mm/Makefile
index e3cda21..301421c 100644
--- a/arch/sparc/mm/Makefile
+++ b/arch/sparc/mm/Makefile
@@ -8,7 +8,6 @@
obj-y += fault_$(BITS).o
obj-y += init_$(BITS).o
obj-$(CONFIG_SPARC32) += loadmmu.o
-obj-y += generic_$(BITS).o
obj-$(CONFIG_SPARC32) += extable.o btfixup.o srmmu.o iommu.o io-unit.o
obj-$(CONFIG_SPARC32) += hypersparc.o viking.o tsunami.o swift.o
obj-$(CONFIG_SPARC_LEON)+= leon_mm.o
diff --git a/arch/sparc/mm/generic_32.c b/arch/sparc/mm/generic_32.c
deleted file mode 100644
index 6ca39a6..0000000
--- a/arch/sparc/mm/generic_32.c
+++ /dev/null
@@ -1,99 +0,0 @@
-/*
- * generic.c: Generic Sparc mm routines that are not dependent upon
- * MMU type but are Sparc specific.
- *
- * Copyright (C) 1996 David S. Miller (davem@caip.rutgers.edu)
- */
-
-#include <linux/kernel.h>
-#include <linux/mm.h>
-#include <linux/swap.h>
-#include <linux/pagemap.h>
-#include <linux/export.h>
-
-#include <asm/pgalloc.h>
-#include <asm/pgtable.h>
-#include <asm/page.h>
-#include <asm/cacheflush.h>
-#include <asm/tlbflush.h>
-
-/* Remap IO memory, the same way as remap_pfn_range(), but use
- * the obio memory space.
- *
- * They use a pgprot that sets PAGE_IO and does not check the
- * mem_map table as this is independent of normal memory.
- */
-static inline void io_remap_pte_range(struct mm_struct *mm, pte_t * pte, unsigned long address, unsigned long size,
- unsigned long offset, pgprot_t prot, int space)
-{
- unsigned long end;
-
- address &= ~PMD_MASK;
- end = address + size;
- if (end > PMD_SIZE)
- end = PMD_SIZE;
- do {
- set_pte_at(mm, address, pte, mk_pte_io(offset, prot, space));
- address += PAGE_SIZE;
- offset += PAGE_SIZE;
- pte++;
- } while (address < end);
-}
-
-static inline int io_remap_pmd_range(struct mm_struct *mm, pmd_t * pmd, unsigned long address, unsigned long size,
- unsigned long offset, pgprot_t prot, int space)
-{
- unsigned long end;
-
- address &= ~PGDIR_MASK;
- end = address + size;
- if (end > PGDIR_SIZE)
- end = PGDIR_SIZE;
- offset -= address;
- do {
- pte_t *pte = pte_alloc_map(mm, NULL, pmd, address);
- if (!pte)
- return -ENOMEM;
- io_remap_pte_range(mm, pte, address, end - address, address + offset, prot, space);
- address = (address + PMD_SIZE) & PMD_MASK;
- pmd++;
- } while (address < end);
- return 0;
-}
-
-int io_remap_pfn_range(struct vm_area_struct *vma, unsigned long from,
- unsigned long pfn, unsigned long size, pgprot_t prot)
-{
- int error = 0;
- pgd_t * dir;
- unsigned long beg = from;
- unsigned long end = from + size;
- struct mm_struct *mm = vma->vm_mm;
- int space = GET_IOSPACE(pfn);
- unsigned long offset = GET_PFN(pfn) << PAGE_SHIFT;
-
- /* See comment in mm/memory.c remap_pfn_range */
- vma->vm_flags |= VM_IO | VM_RESERVED | VM_PFNMAP;
- vma->vm_pgoff = (offset >> PAGE_SHIFT) |
- ((unsigned long)space << 28UL);
-
- offset -= from;
- dir = pgd_offset(mm, from);
- flush_cache_range(vma, beg, end);
-
- while (from < end) {
- pmd_t *pmd = pmd_alloc(mm, dir, from);
- error = -ENOMEM;
- if (!pmd)
- break;
- error = io_remap_pmd_range(mm, pmd, from, end - from, offset + from, prot, space);
- if (error)
- break;
- from = (from + PGDIR_SIZE) & PGDIR_MASK;
- dir++;
- }
-
- flush_tlb_range(vma, beg, end);
- return error;
-}
-EXPORT_SYMBOL(io_remap_pfn_range);
diff --git a/arch/sparc/mm/generic_64.c b/arch/sparc/mm/generic_64.c
deleted file mode 100644
index 9b357dd..0000000
--- a/arch/sparc/mm/generic_64.c
+++ /dev/null
@@ -1,165 +0,0 @@
-/*
- * generic.c: Generic Sparc mm routines that are not dependent upon
- * MMU type but are Sparc specific.
- *
- * Copyright (C) 1996 David S. Miller (davem@caip.rutgers.edu)
- */
-
-#include <linux/kernel.h>
-#include <linux/mm.h>
-#include <linux/swap.h>
-#include <linux/export.h>
-#include <linux/pagemap.h>
-
-#include <asm/pgalloc.h>
-#include <asm/pgtable.h>
-#include <asm/page.h>
-#include <asm/tlbflush.h>
-
-/* Remap IO memory, the same way as remap_pfn_range(), but use
- * the obio memory space.
- *
- * They use a pgprot that sets PAGE_IO and does not check the
- * mem_map table as this is independent of normal memory.
- */
-static inline void io_remap_pte_range(struct mm_struct *mm, pte_t * pte,
- unsigned long address,
- unsigned long size,
- unsigned long offset, pgprot_t prot,
- int space)
-{
- unsigned long end;
-
- /* clear hack bit that was used as a write_combine side-effect flag */
- offset &= ~0x1UL;
- address &= ~PMD_MASK;
- end = address + size;
- if (end > PMD_SIZE)
- end = PMD_SIZE;
- do {
- pte_t entry;
- unsigned long curend = address + PAGE_SIZE;
-
- entry = mk_pte_io(offset, prot, space, PAGE_SIZE);
- if (!(address & 0xffff)) {
- if (PAGE_SIZE < (4 * 1024 * 1024) &&
- !(address & 0x3fffff) &&
- !(offset & 0x3ffffe) &&
- end >= address + 0x400000) {
- entry = mk_pte_io(offset, prot, space,
- 4 * 1024 * 1024);
- curend = address + 0x400000;
- offset += 0x400000;
- } else if (PAGE_SIZE < (512 * 1024) &&
- !(address & 0x7ffff) &&
- !(offset & 0x7fffe) &&
- end >= address + 0x80000) {
- entry = mk_pte_io(offset, prot, space,
- 512 * 1024 * 1024);
- curend = address + 0x80000;
- offset += 0x80000;
- } else if (PAGE_SIZE < (64 * 1024) &&
- !(offset & 0xfffe) &&
- end >= address + 0x10000) {
- entry = mk_pte_io(offset, prot, space,
- 64 * 1024);
- curend = address + 0x10000;
- offset += 0x10000;
- } else
- offset += PAGE_SIZE;
- } else
- offset += PAGE_SIZE;
-
- if (pte_write(entry))
- entry = pte_mkdirty(entry);
- do {
- BUG_ON(!pte_none(*pte));
- set_pte_at(mm, address, pte, entry);
- address += PAGE_SIZE;
- pte_val(entry) += PAGE_SIZE;
- pte++;
- } while (address < curend);
- } while (address < end);
-}
-
-static inline int io_remap_pmd_range(struct mm_struct *mm, pmd_t * pmd, unsigned long address, unsigned long size,
- unsigned long offset, pgprot_t prot, int space)
-{
- unsigned long end;
-
- address &= ~PGDIR_MASK;
- end = address + size;
- if (end > PGDIR_SIZE)
- end = PGDIR_SIZE;
- offset -= address;
- do {
- pte_t *pte = pte_alloc_map(mm, NULL, pmd, address);
- if (!pte)
- return -ENOMEM;
- io_remap_pte_range(mm, pte, address, end - address, address + offset, prot, space);
- pte_unmap(pte);
- address = (address + PMD_SIZE) & PMD_MASK;
- pmd++;
- } while (address < end);
- return 0;
-}
-
-static inline int io_remap_pud_range(struct mm_struct *mm, pud_t * pud, unsigned long address, unsigned long size,
- unsigned long offset, pgprot_t prot, int space)
-{
- unsigned long end;
-
- address &= ~PUD_MASK;
- end = address + size;
- if (end > PUD_SIZE)
- end = PUD_SIZE;
- offset -= address;
- do {
- pmd_t *pmd = pmd_alloc(mm, pud, address);
- if (!pud)
- return -ENOMEM;
- io_remap_pmd_range(mm, pmd, address, end - address, address + offset, prot, space);
- address = (address + PUD_SIZE) & PUD_MASK;
- pud++;
- } while (address < end);
- return 0;
-}
-
-int io_remap_pfn_range(struct vm_area_struct *vma, unsigned long from,
- unsigned long pfn, unsigned long size, pgprot_t prot)
-{
- int error = 0;
- pgd_t * dir;
- unsigned long beg = from;
- unsigned long end = from + size;
- struct mm_struct *mm = vma->vm_mm;
- int space = GET_IOSPACE(pfn);
- unsigned long offset = GET_PFN(pfn) << PAGE_SHIFT;
- unsigned long phys_base;
-
- phys_base = offset | (((unsigned long) space) << 32UL);
-
- /* See comment in mm/memory.c remap_pfn_range */
- vma->vm_flags |= VM_IO | VM_RESERVED | VM_PFNMAP;
- vma->vm_pgoff = phys_base >> PAGE_SHIFT;
-
- offset -= from;
- dir = pgd_offset(mm, from);
- flush_cache_range(vma, beg, end);
-
- while (from < end) {
- pud_t *pud = pud_alloc(mm, dir, from);
- error = -ENOMEM;
- if (!pud)
- break;
- error = io_remap_pud_range(mm, pud, from, end - from, offset + from, prot, space);
- if (error)
- break;
- from = (from + PGDIR_SIZE) & PGDIR_MASK;
- dir++;
- }
-
- flush_tlb_range(vma, beg, end);
- return error;
-}
-EXPORT_SYMBOL(io_remap_pfn_range);
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 9b7273c..1a6c09a 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -49,6 +49,7 @@
extern int local_apic_timer_c2_ok;
extern int disable_apic;
+extern unsigned int lapic_timer_frequency;
#ifdef CONFIG_SMP
extern void __inquire_remote_apic(int apicid);
diff --git a/arch/x86/include/asm/mach_traps.h b/arch/x86/include/asm/mach_traps.h
index 72a8b52..a01e7ec7 100644
--- a/arch/x86/include/asm/mach_traps.h
+++ b/arch/x86/include/asm/mach_traps.h
@@ -17,7 +17,7 @@
#define NMI_REASON_CLEAR_IOCHK 0x08
#define NMI_REASON_CLEAR_MASK 0x0f
-static inline unsigned char get_nmi_reason(void)
+static inline unsigned char default_get_nmi_reason(void)
{
return inb(NMI_REASON_PORT);
}
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index c9321f3..0e8ae57 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -201,7 +201,10 @@
void mce_notify_process(void);
DECLARE_PER_CPU(struct mce, injectm);
-extern struct file_operations mce_chrdev_ops;
+
+extern void register_mce_write_callback(ssize_t (*)(struct file *filp,
+ const char __user *ubuf,
+ size_t usize, loff_t *off));
/*
* Exception handler
diff --git a/arch/x86/include/asm/mrst.h b/arch/x86/include/asm/mrst.h
index 719f00b..e628312 100644
--- a/arch/x86/include/asm/mrst.h
+++ b/arch/x86/include/asm/mrst.h
@@ -44,6 +44,13 @@
extern enum mrst_timer_options mrst_timer_options;
+/*
+ * Penwell uses spread spectrum clock, so the freq number is not exactly
+ * the same as reported by MSR based on SDM.
+ */
+#define PENWELL_FSB_FREQ_83SKU 83200
+#define PENWELL_FSB_FREQ_100SKU 99840
+
#define SFI_MTMR_MAX_NUM 8
#define SFI_MRTC_MAX 8
diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h
index d3d8590..1971e65 100644
--- a/arch/x86/include/asm/x86_init.h
+++ b/arch/x86/include/asm/x86_init.h
@@ -152,6 +152,7 @@
/**
* struct x86_platform_ops - platform specific runtime functions
* @calibrate_tsc: calibrate TSC
+ * @wallclock_init: init the wallclock device
* @get_wallclock: get time from HW clock like RTC etc.
* @set_wallclock: set time back to HW clock
* @is_untracked_pat_range exclude from PAT logic
@@ -160,11 +161,13 @@
*/
struct x86_platform_ops {
unsigned long (*calibrate_tsc)(void);
+ void (*wallclock_init)(void);
unsigned long (*get_wallclock)(void);
int (*set_wallclock)(unsigned long nowtime);
void (*iommu_shutdown)(void);
bool (*is_untracked_pat_range)(u64 start, u64 end);
void (*nmi_init)(void);
+ unsigned char (*get_nmi_reason)(void);
int (*i8042_detect)(void);
};
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index c638228..1f84794 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -738,5 +738,5 @@
atomic_set(&stop_machine_first, 1);
wrote_text = 0;
- __stop_machine(stop_machine_text_poke, (void *)&tpp, NULL);
+ __stop_machine(stop_machine_text_poke, (void *)&tpp, cpu_online_mask);
}
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index a2fd72e..f98d84c 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -186,7 +186,7 @@
.flags = IORESOURCE_MEM | IORESOURCE_BUSY,
};
-static unsigned int calibration_result;
+unsigned int lapic_timer_frequency = 0;
static void apic_pm_activate(void);
@@ -454,7 +454,7 @@
switch (mode) {
case CLOCK_EVT_MODE_PERIODIC:
case CLOCK_EVT_MODE_ONESHOT:
- __setup_APIC_LVTT(calibration_result,
+ __setup_APIC_LVTT(lapic_timer_frequency,
mode != CLOCK_EVT_MODE_PERIODIC, 1);
break;
case CLOCK_EVT_MODE_UNUSED:
@@ -638,6 +638,25 @@
long delta, deltatsc;
int pm_referenced = 0;
+ /**
+ * check if lapic timer has already been calibrated by platform
+ * specific routine, such as tsc calibration code. if so, we just fill
+ * in the clockevent structure and return.
+ */
+
+ if (lapic_timer_frequency) {
+ apic_printk(APIC_VERBOSE, "lapic timer already calibrated %d\n",
+ lapic_timer_frequency);
+ lapic_clockevent.mult = div_sc(lapic_timer_frequency/APIC_DIVISOR,
+ TICK_NSEC, lapic_clockevent.shift);
+ lapic_clockevent.max_delta_ns =
+ clockevent_delta2ns(0x7FFFFF, &lapic_clockevent);
+ lapic_clockevent.min_delta_ns =
+ clockevent_delta2ns(0xF, &lapic_clockevent);
+ lapic_clockevent.features &= ~CLOCK_EVT_FEAT_DUMMY;
+ return 0;
+ }
+
local_irq_disable();
/* Replace the global interrupt handler */
@@ -679,12 +698,12 @@
lapic_clockevent.min_delta_ns =
clockevent_delta2ns(0xF, &lapic_clockevent);
- calibration_result = (delta * APIC_DIVISOR) / LAPIC_CAL_LOOPS;
+ lapic_timer_frequency = (delta * APIC_DIVISOR) / LAPIC_CAL_LOOPS;
apic_printk(APIC_VERBOSE, "..... delta %ld\n", delta);
apic_printk(APIC_VERBOSE, "..... mult: %u\n", lapic_clockevent.mult);
apic_printk(APIC_VERBOSE, "..... calibration result: %u\n",
- calibration_result);
+ lapic_timer_frequency);
if (cpu_has_tsc) {
apic_printk(APIC_VERBOSE, "..... CPU clock speed is "
@@ -695,13 +714,13 @@
apic_printk(APIC_VERBOSE, "..... host bus clock speed is "
"%u.%04u MHz.\n",
- calibration_result / (1000000 / HZ),
- calibration_result % (1000000 / HZ));
+ lapic_timer_frequency / (1000000 / HZ),
+ lapic_timer_frequency % (1000000 / HZ));
/*
* Do a sanity check on the APIC calibration result
*/
- if (calibration_result < (1000000 / HZ)) {
+ if (lapic_timer_frequency < (1000000 / HZ)) {
local_irq_enable();
pr_warning("APIC frequency too slow, disabling apic timer\n");
return -1;
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 3c31fa9..6d939d7 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -193,10 +193,8 @@
struct irq_cfg *cfg;
int count, node, i;
- if (!legacy_pic->nr_legacy_irqs) {
- nr_irqs_gsi = 0;
+ if (!legacy_pic->nr_legacy_irqs)
io_apic_irqs = ~0UL;
- }
for (i = 0; i < nr_ioapics; i++) {
ioapics[i].saved_registers =
@@ -1696,6 +1694,7 @@
int ioapic_idx;
struct irq_cfg *cfg;
unsigned int irq;
+ struct irq_chip *chip;
printk(KERN_DEBUG "number of MP IRQ sources: %d.\n", mp_irq_entries);
for (ioapic_idx = 0; ioapic_idx < nr_ioapics; ioapic_idx++)
@@ -1716,6 +1715,10 @@
for_each_active_irq(irq) {
struct irq_pin_list *entry;
+ chip = irq_get_chip(irq);
+ if (chip != &ioapic_chip)
+ continue;
+
cfg = irq_get_chip_data(irq);
if (!cfg)
continue;
diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c
index 6199232..319882e 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-inject.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-inject.c
@@ -208,7 +208,7 @@
if (!alloc_cpumask_var(&mce_inject_cpumask, GFP_KERNEL))
return -ENOMEM;
printk(KERN_INFO "Machine check injector initialized\n");
- mce_chrdev_ops.write = mce_write;
+ register_mce_write_callback(mce_write);
register_nmi_handler(NMI_LOCAL, mce_raise_notify, 0,
"mce_notify");
return 0;
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 362056a..2af127d 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -1634,16 +1634,35 @@
}
}
-/* Modified in mce-inject.c, so not static or const */
-struct file_operations mce_chrdev_ops = {
+static ssize_t (*mce_write)(struct file *filp, const char __user *ubuf,
+ size_t usize, loff_t *off);
+
+void register_mce_write_callback(ssize_t (*fn)(struct file *filp,
+ const char __user *ubuf,
+ size_t usize, loff_t *off))
+{
+ mce_write = fn;
+}
+EXPORT_SYMBOL_GPL(register_mce_write_callback);
+
+ssize_t mce_chrdev_write(struct file *filp, const char __user *ubuf,
+ size_t usize, loff_t *off)
+{
+ if (mce_write)
+ return mce_write(filp, ubuf, usize, off);
+ else
+ return -EINVAL;
+}
+
+static const struct file_operations mce_chrdev_ops = {
.open = mce_chrdev_open,
.release = mce_chrdev_release,
.read = mce_chrdev_read,
+ .write = mce_chrdev_write,
.poll = mce_chrdev_poll,
.unlocked_ioctl = mce_chrdev_ioctl,
.llseek = no_llseek,
};
-EXPORT_SYMBOL_GPL(mce_chrdev_ops);
static struct miscdevice mce_chrdev_device = {
MISC_MCELOG_MINOR,
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index b9c8628..e88f37b 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -29,6 +29,7 @@
#include <asm/traps.h>
#include <asm/mach_traps.h>
#include <asm/nmi.h>
+#include <asm/x86_init.h>
#define NMI_MAX_NAMELEN 16
struct nmiaction {
@@ -348,7 +349,7 @@
/* Non-CPU-specific NMI: NMI sources can be processed on any CPU */
raw_spin_lock(&nmi_reason_lock);
- reason = get_nmi_reason();
+ reason = x86_platform.get_nmi_reason();
if (reason & NMI_REASON_MASK) {
if (reason & NMI_REASON_SERR)
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index afaf384..cf0ef98 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1045,6 +1045,8 @@
x86_init.timers.wallclock_init();
+ x86_platform.wallclock_init();
+
mcheck_init();
arch_init_ideal_nops();
diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c
index 6f164bd..c1d6cd5 100644
--- a/arch/x86/kernel/x86_init.c
+++ b/arch/x86/kernel/x86_init.c
@@ -21,12 +21,14 @@
#include <asm/pat.h>
#include <asm/tsc.h>
#include <asm/iommu.h>
+#include <asm/mach_traps.h>
void __cpuinit x86_init_noop(void) { }
void __init x86_init_uint_noop(unsigned int unused) { }
void __init x86_init_pgd_noop(pgd_t *unused) { }
int __init iommu_init_noop(void) { return 0; }
void iommu_shutdown_noop(void) { }
+void wallclock_init_noop(void) { }
/*
* The platform setup functions are preset with the default functions
@@ -97,11 +99,13 @@
struct x86_platform_ops x86_platform = {
.calibrate_tsc = native_calibrate_tsc,
+ .wallclock_init = wallclock_init_noop,
.get_wallclock = mach_get_cmos_time,
.set_wallclock = mach_set_rtc_mmss,
.iommu_shutdown = iommu_shutdown_noop,
.is_untracked_pat_range = is_ISA_range,
.nmi_init = default_nmi_init,
+ .get_nmi_reason = default_get_nmi_reason,
.i8042_detect = default_i8042_detect
};
diff --git a/arch/x86/platform/mrst/mrst.c b/arch/x86/platform/mrst/mrst.c
index 541020d..b1489a0 100644
--- a/arch/x86/platform/mrst/mrst.c
+++ b/arch/x86/platform/mrst/mrst.c
@@ -187,11 +187,34 @@
static unsigned long __init mrst_calibrate_tsc(void)
{
unsigned long flags, fast_calibrate;
+ if (__mrst_cpu_chip == MRST_CPU_CHIP_PENWELL) {
+ u32 lo, hi, ratio, fsb;
- local_irq_save(flags);
- fast_calibrate = apbt_quick_calibrate();
- local_irq_restore(flags);
-
+ rdmsr(MSR_IA32_PERF_STATUS, lo, hi);
+ pr_debug("IA32 perf status is 0x%x, 0x%0x\n", lo, hi);
+ ratio = (hi >> 8) & 0x1f;
+ pr_debug("ratio is %d\n", ratio);
+ if (!ratio) {
+ pr_err("read a zero ratio, should be incorrect!\n");
+ pr_err("force tsc ratio to 16 ...\n");
+ ratio = 16;
+ }
+ rdmsr(MSR_FSB_FREQ, lo, hi);
+ if ((lo & 0x7) == 0x7)
+ fsb = PENWELL_FSB_FREQ_83SKU;
+ else
+ fsb = PENWELL_FSB_FREQ_100SKU;
+ fast_calibrate = ratio * fsb;
+ pr_debug("read penwell tsc %lu khz\n", fast_calibrate);
+ lapic_timer_frequency = fsb * 1000 / HZ;
+ /* mark tsc clocksource as reliable */
+ set_cpu_cap(&boot_cpu_data, X86_FEATURE_TSC_RELIABLE);
+ } else {
+ local_irq_save(flags);
+ fast_calibrate = apbt_quick_calibrate();
+ local_irq_restore(flags);
+ }
+
if (fast_calibrate)
return fast_calibrate;
@@ -254,6 +277,17 @@
}
/*
+ * Moorestown does not have external NMI source nor port 0x61 to report
+ * NMI status. The possible NMI sources are from pmu as a result of NMI
+ * watchdog or lock debug. Reading io port 0x61 results in 0xff which
+ * misled NMI handler.
+ */
+static unsigned char mrst_get_nmi_reason(void)
+{
+ return 0;
+}
+
+/*
* Moorestown specific x86_init function overrides and early setup
* calls.
*/
@@ -274,6 +308,8 @@
x86_platform.calibrate_tsc = mrst_calibrate_tsc;
x86_platform.i8042_detect = mrst_i8042_detect;
x86_init.timers.wallclock_init = mrst_rtc_init;
+ x86_platform.get_nmi_reason = mrst_get_nmi_reason;
+
x86_init.pci.init = pci_mrst_init;
x86_init.pci.fixup_irqs = x86_init_noop;
diff --git a/drivers/ide/cy82c693.c b/drivers/ide/cy82c693.c
index 67cbcfa..847553f 100644
--- a/drivers/ide/cy82c693.c
+++ b/drivers/ide/cy82c693.c
@@ -1,7 +1,7 @@
/*
* Copyright (C) 1998-2000 Andreas S. Krebs (akrebs@altavista.net), Maintainer
* Copyright (C) 1998-2002 Andre Hedrick <andre@linux-ide.org>, Integrator
- * Copyright (C) 2007-2010 Bartlomiej Zolnierkiewicz
+ * Copyright (C) 2007-2011 Bartlomiej Zolnierkiewicz
*
* CYPRESS CY82C693 chipset IDE controller
*
@@ -90,7 +90,7 @@
u8 time_16, time_8;
/* select primary or secondary channel */
- if (hwif->index > 0) { /* drive is on the secondary channel */
+ if (drive->dn > 1) { /* drive is on the secondary channel */
dev = pci_get_slot(dev->bus, dev->devfn+1);
if (!dev) {
printk(KERN_ERR "%s: tune_drive: "
@@ -141,7 +141,7 @@
pci_write_config_byte(dev, CY82_IDE_SLAVE_IOW, time_16);
pci_write_config_byte(dev, CY82_IDE_SLAVE_8BIT, time_8);
}
- if (hwif->index > 0)
+ if (drive->dn > 1)
pci_dev_put(dev);
}
diff --git a/drivers/ide/icside.c b/drivers/ide/icside.c
index 4a697a2..8716066 100644
--- a/drivers/ide/icside.c
+++ b/drivers/ide/icside.c
@@ -521,8 +521,8 @@
if (ec->dma != NO_DMA && !request_dma(ec->dma, DRV_NAME)) {
d.init_dma = icside_dma_init;
d.port_ops = &icside_v6_port_ops;
+ } else
d.dma_ops = NULL;
- }
ret = ide_host_register(host, &d, hws);
if (ret)
diff --git a/drivers/ide/piix.c b/drivers/ide/piix.c
index b59d04c..1892e81 100644
--- a/drivers/ide/piix.c
+++ b/drivers/ide/piix.c
@@ -331,7 +331,7 @@
.udma_mask = udma, \
}
-#define DECLARE_ICH_DEV(udma) \
+#define DECLARE_ICH_DEV(mwdma, udma) \
{ \
.name = DRV_NAME, \
.init_chipset = init_chipset_ich, \
@@ -340,7 +340,7 @@
.port_ops = &ich_port_ops, \
.pio_mask = ATA_PIO4, \
.swdma_mask = ATA_SWDMA2_ONLY, \
- .mwdma_mask = ATA_MWDMA12_ONLY, \
+ .mwdma_mask = mwdma, \
.udma_mask = udma, \
}
@@ -362,13 +362,15 @@
/* 2: PIIX4 */
DECLARE_PIIX_DEV(ATA_UDMA2),
/* 3: ICH0 */
- DECLARE_ICH_DEV(ATA_UDMA2),
+ DECLARE_ICH_DEV(ATA_MWDMA12_ONLY, ATA_UDMA2),
/* 4: ICH */
- DECLARE_ICH_DEV(ATA_UDMA4),
+ DECLARE_ICH_DEV(ATA_MWDMA12_ONLY, ATA_UDMA4),
/* 5: PIIX4 */
DECLARE_PIIX_DEV(ATA_UDMA4),
- /* 6: ICH[2-7]/ICH[2-3]M/C-ICH/ICH5-SATA/ESB2/ICH8M */
- DECLARE_ICH_DEV(ATA_UDMA5),
+ /* 6: ICH[2-6]/ICH[2-3]M/C-ICH/ICH5-SATA/ESB2/ICH8M */
+ DECLARE_ICH_DEV(ATA_MWDMA12_ONLY, ATA_UDMA5),
+ /* 7: ICH7/7-R, no MWDMA1 */
+ DECLARE_ICH_DEV(ATA_MWDMA2_ONLY, ATA_UDMA5),
};
/**
@@ -438,9 +440,9 @@
#endif
{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ESB_2), 6 },
{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ICH6_19), 6 },
- { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ICH7_21), 6 },
+ { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ICH7_21), 7 },
{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_82801DB_1), 6 },
- { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ESB2_18), 6 },
+ { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ESB2_18), 7 },
{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ICH8_6), 6 },
{ 0, },
};
diff --git a/drivers/ide/triflex.c b/drivers/ide/triflex.c
index e53a1b7..281c914 100644
--- a/drivers/ide/triflex.c
+++ b/drivers/ide/triflex.c
@@ -113,12 +113,26 @@
};
MODULE_DEVICE_TABLE(pci, triflex_pci_tbl);
+#ifdef CONFIG_PM
+static int triflex_ide_pci_suspend(struct pci_dev *dev, pm_message_t state)
+{
+ /*
+ * We must not disable or powerdown the device.
+ * APM bios refuses to suspend if IDE is not accessible.
+ */
+ pci_save_state(dev);
+ return 0;
+}
+#else
+#define triflex_ide_pci_suspend NULL
+#endif
+
static struct pci_driver triflex_pci_driver = {
.name = "TRIFLEX_IDE",
.id_table = triflex_pci_tbl,
.probe = triflex_init_one,
.remove = ide_pci_remove,
- .suspend = ide_pci_suspend,
+ .suspend = triflex_ide_pci_suspend,
.resume = ide_pci_resume,
};
