[git pull] xen, x86 fixes

From: Ingo Molnar
Date: Mon Jun 23 2008 - 15:41:35 EST


Linus,

please pull the latest x86 fixes tree from:

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

NOTE: contains the second, lguest half of the FPU fixlet from Suresh.

Ingo

------------------>
Isaku Yamahata (1):
xen: Use wmb instead of rmb in xen_evtchn_do_upcall().

Jeremy Fitzhardinge (2):
xen: mask unwanted pte bits in __supported_pte_mask
xen: don't drop NX bit

Suresh Siddha (1):
x86: fix NULL pointer deref in __switch_to

arch/x86/xen/enlighten.c | 5 ++++
arch/x86/xen/mmu.c | 56 ++++++++++++++++++++++++---------------------
arch/x86/xen/xen-head.S | 2 +-
drivers/lguest/x86/core.c | 15 +++++++-----
drivers/xen/events.c | 2 +-
5 files changed, 46 insertions(+), 34 deletions(-)

diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index c8a56e4..c048de3 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1228,6 +1228,11 @@ asmlinkage void __init xen_start_kernel(void)
if (xen_feature(XENFEAT_supervisor_mode_kernel))
pv_info.kernel_rpl = 0;

+ /* Prevent unwanted bits from being set in PTEs. */
+ __supported_pte_mask &= ~_PAGE_GLOBAL;
+ if (!is_initial_xendomain())
+ __supported_pte_mask &= ~(_PAGE_PWT | _PAGE_PCD);
+
/* set the limit of our address space */
xen_reserve_top();

diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 3525ef5..265601d 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -179,48 +179,54 @@ out:
preempt_enable();
}

-pteval_t xen_pte_val(pte_t pte)
+/* Assume pteval_t is equivalent to all the other *val_t types. */
+static pteval_t pte_mfn_to_pfn(pteval_t val)
{
- pteval_t ret = pte.pte;
+ if (val & _PAGE_PRESENT) {
+ unsigned long mfn = (val & PTE_MASK) >> PAGE_SHIFT;
+ pteval_t flags = val & ~PTE_MASK;
+ val = (mfn_to_pfn(mfn) << PAGE_SHIFT) | flags;
+ }
+
+ return val;
+}
+
+static pteval_t pte_pfn_to_mfn(pteval_t val)
+{
+ if (val & _PAGE_PRESENT) {
+ unsigned long pfn = (val & PTE_MASK) >> PAGE_SHIFT;
+ pteval_t flags = val & ~PTE_MASK;
+ val = (pfn_to_mfn(pfn) << PAGE_SHIFT) | flags;
+ }

- if (ret & _PAGE_PRESENT)
- ret = machine_to_phys(XMADDR(ret)).paddr | _PAGE_PRESENT;
+ return val;
+}

- return ret;
+pteval_t xen_pte_val(pte_t pte)
+{
+ return pte_mfn_to_pfn(pte.pte);
}

pgdval_t xen_pgd_val(pgd_t pgd)
{
- pgdval_t ret = pgd.pgd;
- if (ret & _PAGE_PRESENT)
- ret = machine_to_phys(XMADDR(ret)).paddr | _PAGE_PRESENT;
- return ret;
+ return pte_mfn_to_pfn(pgd.pgd);
}

pte_t xen_make_pte(pteval_t pte)
{
- if (pte & _PAGE_PRESENT) {
- pte = phys_to_machine(XPADDR(pte)).maddr;
- pte &= ~(_PAGE_PCD | _PAGE_PWT);
- }
-
- return (pte_t){ .pte = pte };
+ pte = pte_pfn_to_mfn(pte);
+ return native_make_pte(pte);
}

pgd_t xen_make_pgd(pgdval_t pgd)
{
- if (pgd & _PAGE_PRESENT)
- pgd = phys_to_machine(XPADDR(pgd)).maddr;
-
- return (pgd_t){ pgd };
+ pgd = pte_pfn_to_mfn(pgd);
+ return native_make_pgd(pgd);
}

pmdval_t xen_pmd_val(pmd_t pmd)
{
- pmdval_t ret = native_pmd_val(pmd);
- if (ret & _PAGE_PRESENT)
- ret = machine_to_phys(XMADDR(ret)).paddr | _PAGE_PRESENT;
- return ret;
+ return pte_mfn_to_pfn(pmd.pmd);
}
#ifdef CONFIG_X86_PAE
void xen_set_pud(pud_t *ptr, pud_t val)
@@ -267,9 +273,7 @@ void xen_pmd_clear(pmd_t *pmdp)

pmd_t xen_make_pmd(pmdval_t pmd)
{
- if (pmd & _PAGE_PRESENT)
- pmd = phys_to_machine(XPADDR(pmd)).maddr;
-
+ pmd = pte_pfn_to_mfn(pmd);
return native_make_pmd(pmd);
}
#else /* !PAE */
diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S
index 288d587..3175e97 100644
--- a/arch/x86/xen/xen-head.S
+++ b/arch/x86/xen/xen-head.S
@@ -17,7 +17,7 @@ ENTRY(startup_xen)

__FINIT

-.pushsection .bss.page_aligned
+.pushsection .text
.align PAGE_SIZE_asm
ENTRY(hypercall_page)
.skip 0x1000
diff --git a/drivers/lguest/x86/core.c b/drivers/lguest/x86/core.c
index 5126d5d..2e554a4 100644
--- a/drivers/lguest/x86/core.c
+++ b/drivers/lguest/x86/core.c
@@ -176,7 +176,7 @@ void lguest_arch_run_guest(struct lg_cpu *cpu)
* we set it now, so we can trap and pass that trap to the Guest if it
* uses the FPU. */
if (cpu->ts)
- lguest_set_ts();
+ unlazy_fpu(current);

/* SYSENTER is an optimized way of doing system calls. We can't allow
* it because it always jumps to privilege level 0. A normal Guest
@@ -196,6 +196,10 @@ void lguest_arch_run_guest(struct lg_cpu *cpu)
* trap made the switcher code come back, and an error code which some
* traps set. */

+ /* Restore SYSENTER if it's supposed to be on. */
+ if (boot_cpu_has(X86_FEATURE_SEP))
+ wrmsr(MSR_IA32_SYSENTER_CS, __KERNEL_CS, 0);
+
/* If the Guest page faulted, then the cr2 register will tell us the
* bad virtual address. We have to grab this now, because once we
* re-enable interrupts an interrupt could fault and thus overwrite
@@ -203,13 +207,12 @@ void lguest_arch_run_guest(struct lg_cpu *cpu)
if (cpu->regs->trapnum == 14)
cpu->arch.last_pagefault = read_cr2();
/* Similarly, if we took a trap because the Guest used the FPU,
- * we have to restore the FPU it expects to see. */
+ * we have to restore the FPU it expects to see.
+ * math_state_restore() may sleep and we may even move off to
+ * a different CPU. So all the critical stuff should be done
+ * before this. */
else if (cpu->regs->trapnum == 7)
math_state_restore();
-
- /* Restore SYSENTER if it's supposed to be on. */
- if (boot_cpu_has(X86_FEATURE_SEP))
- wrmsr(MSR_IA32_SYSENTER_CS, __KERNEL_CS, 0);
}

/*H:130 Now we've examined the hypercall code; our Guest can make requests.
diff --git a/drivers/xen/events.c b/drivers/xen/events.c
index 4f0f22b..76e5b73 100644
--- a/drivers/xen/events.c
+++ b/drivers/xen/events.c
@@ -529,7 +529,7 @@ void xen_evtchn_do_upcall(struct pt_regs *regs)

#ifndef CONFIG_X86 /* No need for a barrier -- XCHG is a barrier on x86. */
/* Clear master flag /before/ clearing selector flag. */
- rmb();
+ wmb();
#endif
pending_words = xchg(&vcpu_info->evtchn_pending_sel, 0);
while (pending_words != 0) {
--
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/