[git pull] x86 fixes

From: Ingo Molnar
Date: Tue Feb 17 2009 - 11:36:50 EST

Linus,

Please pull the latest x86-fixes-for-linus git tree from:

git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git x86-fixes-for-linus


out-of-topic modifications in x86-fixes-for-linus:
--------------------------------------------------
include/linux/mm.h # 9f339e7: x86, ptrace, mm: fix double-free
mm/mlock.c # 9f339e7: x86, ptrace, mm: fix double-free

Thanks,

Ingo

------------------>
Chris Ball (1):
x86, olpc: fix model detection without OFW

Jeremy Fitzhardinge (2):
x86/cpa: make sure cpa is safe to call in lazy mmu mode
x86/paravirt: make arch_flush_lazy_mmu/cpu disable preemption

John Stultz (1):
x86, hpet: fix for LS21 + HPET = boot hang

Markus Metzger (1):
x86, ptrace, mm: fix double-free on race

Suresh Siddha (1):
x86, pat: fix warn_on_once() while mapping 0-1MB range with /dev/mem

Thomas Gleixner (3):
x86: warn if arch_flush_lazy_mmu_cpu is called in preemptible context
x86: CPA avoid repeated lazy mmu flush
x86, vm86: fix preemption bug


arch/x86/include/asm/page.h | 1 -
arch/x86/include/asm/paravirt.h | 17 +-------
arch/x86/kernel/hpet.c | 2 +
arch/x86/kernel/olpc.c | 2 +-
arch/x86/kernel/paravirt.c | 26 ++++++++++++
arch/x86/kernel/ptrace.c | 16 +++++---
arch/x86/kernel/traps.c | 10 ++++-
arch/x86/mm/ioremap.c | 19 ---------
arch/x86/mm/pageattr.c | 15 +++++++-
arch/x86/mm/pat.c | 83 +++++++++++++++++++++------------------
include/linux/mm.h | 1 +
mm/mlock.c | 7 +++-
12 files changed, 116 insertions(+), 83 deletions(-)

diff --git a/arch/x86/include/asm/page.h b/arch/x86/include/asm/page.h
index e9873a2..7765791 100644
--- a/arch/x86/include/asm/page.h
+++ b/arch/x86/include/asm/page.h
@@ -57,7 +57,6 @@ typedef struct { pgdval_t pgd; } pgd_t;
typedef struct { pgprotval_t pgprot; } pgprot_t;

extern int page_is_ram(unsigned long pagenr);
-extern int pagerange_is_ram(unsigned long start, unsigned long end);
extern int devmem_is_allowed(unsigned long pagenr);
extern void map_devmem(unsigned long pfn, unsigned long size,
pgprot_t vma_prot);
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index ba3e2ff..a660ece 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -1352,14 +1352,7 @@ static inline void arch_leave_lazy_cpu_mode(void)
PVOP_VCALL0(pv_cpu_ops.lazy_mode.leave);
}

-static inline void arch_flush_lazy_cpu_mode(void)
-{
- if (unlikely(paravirt_get_lazy_mode() == PARAVIRT_LAZY_CPU)) {
- arch_leave_lazy_cpu_mode();
- arch_enter_lazy_cpu_mode();
- }
-}
-
+void arch_flush_lazy_cpu_mode(void);

#define __HAVE_ARCH_ENTER_LAZY_MMU_MODE
static inline void arch_enter_lazy_mmu_mode(void)
@@ -1372,13 +1365,7 @@ static inline void arch_leave_lazy_mmu_mode(void)
PVOP_VCALL0(pv_mmu_ops.lazy_mode.leave);
}

-static inline void arch_flush_lazy_mmu_mode(void)
-{
- if (unlikely(paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU)) {
- arch_leave_lazy_mmu_mode();
- arch_enter_lazy_mmu_mode();
- }
-}
+void arch_flush_lazy_mmu_mode(void);

static inline void __set_fixmap(unsigned /* enum fixed_addresses */ idx,
unsigned long phys, pgprot_t flags)
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 64d5ad0..5c8da2c 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -269,6 +269,8 @@ static void hpet_set_mode(enum clock_event_mode mode,
now = hpet_readl(HPET_COUNTER);
cmp = now + (unsigned long) delta;
cfg = hpet_readl(HPET_Tn_CFG(timer));
+ /* Make sure we use edge triggered interrupts */
+ cfg &= ~HPET_TN_LEVEL;
cfg |= HPET_TN_ENABLE | HPET_TN_PERIODIC |
HPET_TN_SETVAL | HPET_TN_32BIT;
hpet_writel(cfg, HPET_Tn_CFG(timer));
diff --git a/arch/x86/kernel/olpc.c b/arch/x86/kernel/olpc.c
index 7a13fac..4006c52 100644
--- a/arch/x86/kernel/olpc.c
+++ b/arch/x86/kernel/olpc.c
@@ -203,7 +203,7 @@ static void __init platform_detect(void)
static void __init platform_detect(void)
{
/* stopgap until OFW support is added to the kernel */
- olpc_platform_info.boardrev = 0xc2;
+ olpc_platform_info.boardrev = olpc_board(0xc2);
}
#endif

diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index e4c8fb6..c6520a4 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -268,6 +268,32 @@ enum paravirt_lazy_mode paravirt_get_lazy_mode(void)
return __get_cpu_var(paravirt_lazy_mode);
}

+void arch_flush_lazy_mmu_mode(void)
+{
+ preempt_disable();
+
+ if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU) {
+ WARN_ON(preempt_count() == 1);
+ arch_leave_lazy_mmu_mode();
+ arch_enter_lazy_mmu_mode();
+ }
+
+ preempt_enable();
+}
+
+void arch_flush_lazy_cpu_mode(void)
+{
+ preempt_disable();
+
+ if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_CPU) {
+ WARN_ON(preempt_count() == 1);
+ arch_leave_lazy_cpu_mode();
+ arch_enter_lazy_cpu_mode();
+ }
+
+ preempt_enable();
+}
+
struct pv_info pv_info = {
.name = "bare hardware",
.paravirt_enabled = 0,
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index 0a5df5f..5a4c23d 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -810,12 +810,16 @@ static void ptrace_bts_untrace(struct task_struct *child)

static void ptrace_bts_detach(struct task_struct *child)
{
- if (unlikely(child->bts)) {
- ds_release_bts(child->bts);
- child->bts = NULL;
-
- ptrace_bts_free_buffer(child);
- }
+ /*
+ * Ptrace_detach() races with ptrace_untrace() in case
+ * the child dies and is reaped by another thread.
+ *
+ * We only do the memory accounting at this point and
+ * leave the buffer deallocation and the bts tracer
+ * release to ptrace_bts_untrace() which will be called
+ * later on with tasklist_lock held.
+ */
+ release_locked_buffer(child->bts_buffer, child->bts_size);
}
#else
static inline void ptrace_bts_fork(struct task_struct *tsk) {}
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 7932338..a9e7548 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -99,6 +99,12 @@ static inline void preempt_conditional_sti(struct pt_regs *regs)
local_irq_enable();
}

+static inline void conditional_cli(struct pt_regs *regs)
+{
+ if (regs->flags & X86_EFLAGS_IF)
+ local_irq_disable();
+}
+
static inline void preempt_conditional_cli(struct pt_regs *regs)
{
if (regs->flags & X86_EFLAGS_IF)
@@ -626,8 +632,10 @@ clear_dr7:

#ifdef CONFIG_X86_32
debug_vm86:
+ /* reenable preemption: handle_vm86_trap() might sleep */
+ dec_preempt_count();
handle_vm86_trap((struct kernel_vm86_regs *) regs, error_code, 1);
- preempt_conditional_cli(regs);
+ conditional_cli(regs);
return;
#endif

diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index af750ab..f45d5e2 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -134,25 +134,6 @@ int page_is_ram(unsigned long pagenr)
return 0;
}

-int pagerange_is_ram(unsigned long start, unsigned long end)
-{
- int ram_page = 0, not_rampage = 0;
- unsigned long page_nr;
-
- for (page_nr = (start >> PAGE_SHIFT); page_nr < (end >> PAGE_SHIFT);
- ++page_nr) {
- if (page_is_ram(page_nr))
- ram_page = 1;
- else
- not_rampage = 1;
-
- if (ram_page == not_rampage)
- return -1;
- }
-
- return ram_page;
-}
-
/*
* Fix up the linear direct mapping of the kernel to avoid cache attribute
* conflicts.
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 84ba748..8ca0d85 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -575,7 +575,6 @@ static int __change_page_attr(struct cpa_data *cpa, int primary)
address = cpa->vaddr[cpa->curpage];
else
address = *cpa->vaddr;
-
repeat:
kpte = lookup_address(address, &level);
if (!kpte)
@@ -812,6 +811,13 @@ static int change_page_attr_set_clr(unsigned long *addr, int numpages,

vm_unmap_aliases();

+ /*
+ * If we're called with lazy mmu updates enabled, the
+ * in-memory pte state may be stale. Flush pending updates to
+ * bring them up to date.
+ */
+ arch_flush_lazy_mmu_mode();
+
cpa.vaddr = addr;
cpa.numpages = numpages;
cpa.mask_set = mask_set;
@@ -854,6 +860,13 @@ static int change_page_attr_set_clr(unsigned long *addr, int numpages,
} else
cpa_flush_all(cache);

+ /*
+ * If we've been called with lazy mmu updates enabled, then
+ * make sure that everything gets flushed out before we
+ * return.
+ */
+ arch_flush_lazy_mmu_mode();
+
out:
return ret;
}
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index 7b61036..aebbf67 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -211,6 +211,33 @@ chk_conflict(struct memtype *new, struct memtype *entry, unsigned long *type)
static struct memtype *cached_entry;
static u64 cached_start;

+static int pat_pagerange_is_ram(unsigned long start, unsigned long end)
+{
+ int ram_page = 0, not_rampage = 0;
+ unsigned long page_nr;
+
+ for (page_nr = (start >> PAGE_SHIFT); page_nr < (end >> PAGE_SHIFT);
+ ++page_nr) {
+ /*
+ * For legacy reasons, physical address range in the legacy ISA
+ * region is tracked as non-RAM. This will allow users of
+ * /dev/mem to map portions of legacy ISA region, even when
+ * some of those portions are listed(or not even listed) with
+ * different e820 types(RAM/reserved/..)
+ */
+ if (page_nr >= (ISA_END_ADDRESS >> PAGE_SHIFT) &&
+ page_is_ram(page_nr))
+ ram_page = 1;
+ else
+ not_rampage = 1;
+
+ if (ram_page == not_rampage)
+ return -1;
+ }
+
+ return ram_page;
+}
+
/*
* For RAM pages, mark the pages as non WB memory type using
* PageNonWB (PG_arch_1). We allow only one set_memory_uc() or
@@ -336,20 +363,12 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
if (new_type)
*new_type = actual_type;

- /*
- * For legacy reasons, some parts of the physical address range in the
- * legacy 1MB region is treated as non-RAM (even when listed as RAM in
- * the e820 tables). So we will track the memory attributes of this
- * legacy 1MB region using the linear memtype_list always.
- */
- if (end >= ISA_END_ADDRESS) {
- is_range_ram = pagerange_is_ram(start, end);
- if (is_range_ram == 1)
- return reserve_ram_pages_type(start, end, req_type,
- new_type);
- else if (is_range_ram < 0)
- return -EINVAL;
- }
+ is_range_ram = pat_pagerange_is_ram(start, end);
+ if (is_range_ram == 1)
+ return reserve_ram_pages_type(start, end, req_type,
+ new_type);
+ else if (is_range_ram < 0)
+ return -EINVAL;

new = kmalloc(sizeof(struct memtype), GFP_KERNEL);
if (!new)
@@ -446,19 +465,11 @@ int free_memtype(u64 start, u64 end)
if (is_ISA_range(start, end - 1))
return 0;

- /*
- * For legacy reasons, some parts of the physical address range in the
- * legacy 1MB region is treated as non-RAM (even when listed as RAM in
- * the e820 tables). So we will track the memory attributes of this
- * legacy 1MB region using the linear memtype_list always.
- */
- if (end >= ISA_END_ADDRESS) {
- is_range_ram = pagerange_is_ram(start, end);
- if (is_range_ram == 1)
- return free_ram_pages_type(start, end);
- else if (is_range_ram < 0)
- return -EINVAL;
- }
+ is_range_ram = pat_pagerange_is_ram(start, end);
+ if (is_range_ram == 1)
+ return free_ram_pages_type(start, end);
+ else if (is_range_ram < 0)
+ return -EINVAL;

spin_lock(&memtype_lock);
list_for_each_entry(entry, &memtype_list, nd) {
@@ -626,17 +637,13 @@ static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot,
unsigned long flags;
unsigned long want_flags = (pgprot_val(*vma_prot) & _PAGE_CACHE_MASK);

- is_ram = pagerange_is_ram(paddr, paddr + size);
+ is_ram = pat_pagerange_is_ram(paddr, paddr + size);

- if (is_ram != 0) {
- /*
- * For mapping RAM pages, drivers need to call
- * set_memory_[uc|wc|wb] directly, for reserve and free, before
- * setting up the PTE.
- */
- WARN_ON_ONCE(1);
- return 0;
- }
+ /*
+ * reserve_pfn_range() doesn't support RAM pages.
+ */
+ if (is_ram != 0)
+ return -EINVAL;

ret = reserve_memtype(paddr, paddr + size, want_flags, &flags);
if (ret)
@@ -693,7 +700,7 @@ static void free_pfn_range(u64 paddr, unsigned long size)
{
int is_ram;

- is_ram = pagerange_is_ram(paddr, paddr + size);
+ is_ram = pat_pagerange_is_ram(paddr, paddr + size);
if (is_ram == 0)
free_memtype(paddr, paddr + size);
}
diff --git a/include/linux/mm.h b/include/linux/mm.h
index e8ddc98..3d7fb44 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1305,5 +1305,6 @@ void vmemmap_populate_print_last(void);

extern void *alloc_locked_buffer(size_t size);
extern void free_locked_buffer(void *buffer, size_t size);
+extern void release_locked_buffer(void *buffer, size_t size);
#endif /* __KERNEL__ */
#endif /* _LINUX_MM_H */
diff --git a/mm/mlock.c b/mm/mlock.c
index 028ec48..2b57f7e 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -657,7 +657,7 @@ void *alloc_locked_buffer(size_t size)
return buffer;
}

-void free_locked_buffer(void *buffer, size_t size)
+void release_locked_buffer(void *buffer, size_t size)
{
unsigned long pgsz = PAGE_ALIGN(size) >> PAGE_SHIFT;

@@ -667,6 +667,11 @@ void free_locked_buffer(void *buffer, size_t size)
current->mm->locked_vm -= pgsz;

up_write(&current->mm->mmap_sem);
+}
+
+void free_locked_buffer(void *buffer, size_t size)
+{
+ release_locked_buffer(buffer, size);

kfree(buffer);
}
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/