Implement xen apic_ops to fix early crash in Xen Dom0 (rhbz 804347)

This commit is contained in:
Josh Boyer 2012-03-27 12:13:33 -04:00
parent f1d2f5da9e
commit 46ad899861
5 changed files with 589 additions and 1 deletions

View File

@ -54,7 +54,7 @@ Summary: The Linux kernel
# For non-released -rc kernels, this will be appended after the rcX and
# gitX tags, so a 3 here would become part of release "0.rcX.gitX.3"
#
%global baserelease 5
%global baserelease 6
%global fedora_build %{baserelease}
# base_sublevel is the kernel version we're starting with and patching
@ -770,6 +770,13 @@ Patch21305: mac80211-fix-possible-tid_rx-reorder_timer-use-after-free.patch
#rhbz 804957 CVE-2012-1568
Patch21306: shlib_base_randomize.patch
Patch21350: x86-ioapic-add-register-checks-for-bogus-io-apic-entries.patch
#rhbz 804347
Patch21351: x86-add-io_apic_ops-to-allow-interception.patch
Patch21352: x86-apic_ops-Replace-apic_ops-with-x86_apic_ops.patch
Patch21353: xen-x86-Implement-x86_apic_ops.patch
Patch21400: unhandled-irqs-switch-to-polling.patch
Patch22000: weird-root-dentry-name-debug.patch
@ -1489,6 +1496,13 @@ ApplyPatch unhandled-irqs-switch-to-polling.patch
ApplyPatch weird-root-dentry-name-debug.patch
ApplyPatch x86-ioapic-add-register-checks-for-bogus-io-apic-entries.patch
#rhbz 804347
ApplyPatch x86-add-io_apic_ops-to-allow-interception.patch
ApplyPatch x86-apic_ops-Replace-apic_ops-with-x86_apic_ops.patch
ApplyPatch xen-x86-Implement-x86_apic_ops.patch
#rhbz 803809 CVE-2012-1179
ApplyPatch mm-thp-fix-pmd_bad-triggering.patch
@ -2334,6 +2348,9 @@ fi
# '-' | |
# '-'
%changelog
* Tue Mar 27 2012 Josh Boyer <jwboyer@redhat.com>
- Implement xen apic_ops to fix early crash in Xen Dom0 (rhbz 804347)
* Fri Mar 23 2012 Dave Jones <davej@redhat.com> 3.3.0-5
- Apply patches that should solve the bluetooth use-after-free oopses. (rhbz 806033)

View File

@ -0,0 +1,135 @@
From: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Xen dom0 needs to paravirtualize IO operations to the IO APIC, so add
a io_apic_ops for it to intercept. Do this as ops structure because
there's at least some chance that another paravirtualized environment
may want to intercept these.
[ Impact: indirect IO APIC access via io_apic_ops ]
Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Acked-by: Suresh Siddha <suresh.b.siddha@intel.com>
---
arch/x86/include/asm/io_apic.h | 9 +++++++
arch/x86/kernel/apic/io_apic.c | 50 +++++++++++++++++++++++++++++++++++++--
2 files changed, 56 insertions(+), 3 deletions(-)
diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h
index 690d1cc..190d8c2 100644
--- a/arch/x86/include/asm/io_apic.h
+++ b/arch/x86/include/asm/io_apic.h
@@ -21,6 +21,15 @@
#define IO_APIC_REDIR_LEVEL_TRIGGER (1 << 15)
#define IO_APIC_REDIR_MASKED (1 << 16)
+struct io_apic_ops {
+ void (*init)(void);
+ unsigned int (*read)(unsigned int apic, unsigned int reg);
+ void (*write)(unsigned int apic, unsigned int reg, unsigned int value);
+ void (*modify)(unsigned int apic, unsigned int reg, unsigned int value);
+};
+
+void __init set_io_apic_ops(const struct io_apic_ops *);
+
/*
* The structure of the IO-APIC:
*/
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index fb07275..bf120234 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -67,6 +67,25 @@
#define for_each_irq_pin(entry, head) \
for (entry = head; entry; entry = entry->next)
+static void __init __ioapic_init_mappings(void);
+static unsigned int __io_apic_read(unsigned int apic, unsigned int reg);
+static void __io_apic_write(unsigned int apic, unsigned int reg,
+ unsigned int val);
+static void __io_apic_modify(unsigned int apic, unsigned int reg,
+ unsigned int val);
+
+static struct io_apic_ops io_apic_ops = {
+ .init = __ioapic_init_mappings,
+ .read = __io_apic_read,
+ .write = __io_apic_write,
+ .modify = __io_apic_modify,
+};
+
+void __init set_io_apic_ops(const struct io_apic_ops *ops)
+{
+ io_apic_ops = *ops;
+}
+
/*
* Is the SiS APIC rmw bug present ?
* -1 = don't know, 0 = no, 1 = yes
@@ -294,6 +313,24 @@ static void free_irq_at(unsigned int at, struct irq_cfg *cfg)
irq_free_desc(at);
}
+static inline unsigned int io_apic_read(unsigned int apic, unsigned int reg)
+{
+ return io_apic_ops.read(apic, reg);
+}
+
+static inline void io_apic_write(unsigned int apic, unsigned int reg,
+ unsigned int value)
+{
+ io_apic_ops.write(apic, reg, value);
+}
+
+static inline void io_apic_modify(unsigned int apic, unsigned int reg,
+ unsigned int value)
+{
+ io_apic_ops.modify(apic, reg, value);
+}
+
+
struct io_apic {
unsigned int index;
unsigned int unused[3];
@@ -314,14 +351,15 @@ static inline void io_apic_eoi(unsigned int apic, unsigned int vector)
writel(vector, &io_apic->eoi);
}
-static inline unsigned int io_apic_read(unsigned int apic, unsigned int reg)
+static unsigned int __io_apic_read(unsigned int apic, unsigned int reg)
{
struct io_apic __iomem *io_apic = io_apic_base(apic);
writel(reg, &io_apic->index);
return readl(&io_apic->data);
}
-static inline void io_apic_write(unsigned int apic, unsigned int reg, unsigned int value)
+static void __io_apic_write(unsigned int apic, unsigned int reg,
+ unsigned int value)
{
struct io_apic __iomem *io_apic = io_apic_base(apic);
writel(reg, &io_apic->index);
@@ -334,7 +372,8 @@ static inline void io_apic_write(unsigned int apic, unsigned int reg, unsigned i
*
* Older SiS APIC requires we rewrite the index register
*/
-static inline void io_apic_modify(unsigned int apic, unsigned int reg, unsigned int value)
+static void __io_apic_modify(unsigned int apic, unsigned int reg,
+ unsigned int value)
{
struct io_apic __iomem *io_apic = io_apic_base(apic);
@@ -3873,6 +3912,11 @@ static struct resource * __init ioapic_setup_resources(int nr_ioapics)
void __init ioapic_and_gsi_init(void)
{
+ io_apic_ops.init();
+}
+
+static void __init __ioapic_init_mappings(void)
+{
unsigned long ioapic_phys, idx = FIX_IO_APIC_BASE_0;
struct resource *ioapic_res;
int i;
--
1.7.7.5

View File

@ -0,0 +1,258 @@
. which makes the code fit within the rest of the x86_ops functions.
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
[v1: Changed x86_apic -> x86_ioapic per Yinghai Lu <yinghai@kernel.org> suggestion]
Acked-by: Suresh Siddha <suresh.b.siddha@intel.com>
---
arch/x86/include/asm/io_apic.h | 40 +++++++++++++++++++++--------
arch/x86/include/asm/x86_init.h | 8 ++++++
arch/x86/kernel/apic/io_apic.c | 54 ++++----------------------------------
arch/x86/kernel/setup.c | 2 +-
arch/x86/kernel/x86_init.c | 8 ++++++
5 files changed, 52 insertions(+), 60 deletions(-)
diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h
index 190d8c2..ba1b11a 100644
--- a/arch/x86/include/asm/io_apic.h
+++ b/arch/x86/include/asm/io_apic.h
@@ -5,6 +5,7 @@
#include <asm/mpspec.h>
#include <asm/apicdef.h>
#include <asm/irq_vectors.h>
+#include <asm/x86_init.h>
/*
* Intel IO-APIC support for SMP and UP systems.
@@ -21,15 +22,6 @@
#define IO_APIC_REDIR_LEVEL_TRIGGER (1 << 15)
#define IO_APIC_REDIR_MASKED (1 << 16)
-struct io_apic_ops {
- void (*init)(void);
- unsigned int (*read)(unsigned int apic, unsigned int reg);
- void (*write)(unsigned int apic, unsigned int reg, unsigned int value);
- void (*modify)(unsigned int apic, unsigned int reg, unsigned int value);
-};
-
-void __init set_io_apic_ops(const struct io_apic_ops *);
-
/*
* The structure of the IO-APIC:
*/
@@ -156,7 +148,6 @@ struct io_apic_irq_attr;
extern int io_apic_set_pci_routing(struct device *dev, int irq,
struct io_apic_irq_attr *irq_attr);
void setup_IO_APIC_irq_extra(u32 gsi);
-extern void ioapic_and_gsi_init(void);
extern void ioapic_insert_resources(void);
int io_apic_setup_irq_pin_once(unsigned int irq, int node, struct io_apic_irq_attr *attr);
@@ -185,12 +176,35 @@ extern void mp_save_irq(struct mpc_intsrc *m);
extern void disable_ioapic_support(void);
+
+void __init native_ioapic_init_mappings(void);
+unsigned int native_ioapic_read(unsigned int apic, unsigned int reg);
+void native_ioapic_write(unsigned int apic, unsigned int reg,
+ unsigned int val);
+void native_ioapic_modify(unsigned int apic, unsigned int reg,
+ unsigned int val);
+
+static inline unsigned int io_apic_read(unsigned int apic, unsigned int reg)
+{
+ return x86_ioapic.read(apic, reg);
+}
+
+static inline void io_apic_write(unsigned int apic, unsigned int reg,
+ unsigned int value)
+{
+ x86_ioapic.write(apic, reg, value);
+}
+
+static inline void io_apic_modify(unsigned int apic, unsigned int reg,
+ unsigned int value)
+{
+ x86_ioapic.modify(apic, reg, value);
+}
#else /* !CONFIG_X86_IO_APIC */
#define io_apic_assign_pci_irqs 0
#define setup_ioapic_ids_from_mpc x86_init_noop
static const int timer_through_8259 = 0;
-static inline void ioapic_and_gsi_init(void) { }
static inline void ioapic_insert_resources(void) { }
#define gsi_top (NR_IRQS_LEGACY)
static inline int mp_find_ioapic(u32 gsi) { return 0; }
@@ -212,6 +226,10 @@ static inline int restore_ioapic_entries(void)
static inline void mp_save_irq(struct mpc_intsrc *m) { };
static inline void disable_ioapic_support(void) { }
+#define native_ioapic_init_mappings NULL
+#define native_ioapic_read NULL
+#define native_ioapic_write NULL
+#define native_ioapic_modify NULL
#endif
#endif /* _ASM_X86_IO_APIC_H */
diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h
index 517d476..a3730cc 100644
--- a/arch/x86/include/asm/x86_init.h
+++ b/arch/x86/include/asm/x86_init.h
@@ -182,10 +182,18 @@ struct x86_msi_ops {
void (*restore_msi_irqs)(struct pci_dev *dev, int irq);
};
+struct x86_ioapic_ops {
+ void (*init)(void);
+ unsigned int (*read)(unsigned int apic, unsigned int reg);
+ void (*write)(unsigned int apic, unsigned int reg, unsigned int value);
+ void (*modify)(unsigned int apic, unsigned int reg, unsigned int value);
+};
+
extern struct x86_init_ops x86_init;
extern struct x86_cpuinit_ops x86_cpuinit;
extern struct x86_platform_ops x86_platform;
extern struct x86_msi_ops x86_msi;
+extern struct x86_ioapic_ops x86_ioapic;
extern void x86_init_noop(void);
extern void x86_init_uint_noop(unsigned int unused);
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index bf120234..9a15d4b 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -67,25 +67,6 @@
#define for_each_irq_pin(entry, head) \
for (entry = head; entry; entry = entry->next)
-static void __init __ioapic_init_mappings(void);
-static unsigned int __io_apic_read(unsigned int apic, unsigned int reg);
-static void __io_apic_write(unsigned int apic, unsigned int reg,
- unsigned int val);
-static void __io_apic_modify(unsigned int apic, unsigned int reg,
- unsigned int val);
-
-static struct io_apic_ops io_apic_ops = {
- .init = __ioapic_init_mappings,
- .read = __io_apic_read,
- .write = __io_apic_write,
- .modify = __io_apic_modify,
-};
-
-void __init set_io_apic_ops(const struct io_apic_ops *ops)
-{
- io_apic_ops = *ops;
-}
-
/*
* Is the SiS APIC rmw bug present ?
* -1 = don't know, 0 = no, 1 = yes
@@ -313,24 +294,6 @@ static void free_irq_at(unsigned int at, struct irq_cfg *cfg)
irq_free_desc(at);
}
-static inline unsigned int io_apic_read(unsigned int apic, unsigned int reg)
-{
- return io_apic_ops.read(apic, reg);
-}
-
-static inline void io_apic_write(unsigned int apic, unsigned int reg,
- unsigned int value)
-{
- io_apic_ops.write(apic, reg, value);
-}
-
-static inline void io_apic_modify(unsigned int apic, unsigned int reg,
- unsigned int value)
-{
- io_apic_ops.modify(apic, reg, value);
-}
-
-
struct io_apic {
unsigned int index;
unsigned int unused[3];
@@ -351,15 +314,15 @@ static inline void io_apic_eoi(unsigned int apic, unsigned int vector)
writel(vector, &io_apic->eoi);
}
-static unsigned int __io_apic_read(unsigned int apic, unsigned int reg)
+unsigned int native_ioapic_read(unsigned int apic, unsigned int reg)
{
struct io_apic __iomem *io_apic = io_apic_base(apic);
writel(reg, &io_apic->index);
return readl(&io_apic->data);
}
-static void __io_apic_write(unsigned int apic, unsigned int reg,
- unsigned int value)
+void native_ioapic_write(unsigned int apic, unsigned int reg,
+ unsigned int value)
{
struct io_apic __iomem *io_apic = io_apic_base(apic);
writel(reg, &io_apic->index);
@@ -372,8 +335,8 @@ static void __io_apic_write(unsigned int apic, unsigned int reg,
*
* Older SiS APIC requires we rewrite the index register
*/
-static void __io_apic_modify(unsigned int apic, unsigned int reg,
- unsigned int value)
+void native_ioapic_modify(unsigned int apic, unsigned int reg,
+ unsigned int value)
{
struct io_apic __iomem *io_apic = io_apic_base(apic);
@@ -3910,12 +3873,7 @@ static struct resource * __init ioapic_setup_resources(int nr_ioapics)
return res;
}
-void __init ioapic_and_gsi_init(void)
-{
- io_apic_ops.init();
-}
-
-static void __init __ioapic_init_mappings(void)
+void __init native_ioapic_init_mappings(void)
{
unsigned long ioapic_phys, idx = FIX_IO_APIC_BASE_0;
struct resource *ioapic_res;
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index d7d5099..7eaef1a 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1016,7 +1016,7 @@ void __init setup_arch(char **cmdline_p)
init_cpu_to_node();
init_apic_mappings();
- ioapic_and_gsi_init();
+ x86_ioapic.init();
kvm_guest_init();
diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c
index 947a06c..df870d3 100644
--- a/arch/x86/kernel/x86_init.c
+++ b/arch/x86/kernel/x86_init.c
@@ -18,6 +18,7 @@
#include <asm/e820.h>
#include <asm/time.h>
#include <asm/irq.h>
+#include <asm/io_apic.h>
#include <asm/pat.h>
#include <asm/tsc.h>
#include <asm/iommu.h>
@@ -117,3 +118,10 @@ struct x86_msi_ops x86_msi = {
.teardown_msi_irqs = default_teardown_msi_irqs,
.restore_msi_irqs = default_restore_msi_irqs,
};
+
+struct x86_ioapic_ops x86_ioapic = {
+ .init = native_ioapic_init_mappings,
+ .read = native_ioapic_read,
+ .write = native_ioapic_write,
+ .modify = native_ioapic_modify,
+};
--
1.7.7.5

View File

@ -0,0 +1,93 @@
On Tue, 2012-01-31 at 09:26 -0500, Josh Boyer wrote:
> On Wed, Jan 25, 2012 at 06:15:35PM -0500, Josh Boyer wrote:
> > On Wed, Jan 25, 2012 at 02:04:08PM -0800, Suresh Siddha wrote:
> > > On Wed, 2012-01-25 at 08:49 -0500, Josh Boyer wrote:
> > > > [ 0.000000] IOAPIC[1]: apic_id 2, version 255, address 0xfec28000, GSI 24-279
> > >
> > > This looks indeed like a bogus entry probably returning all 1's for
> > > RTE's etc. Can you please send me a dmesg with "apic=verbose" boot
> > > parameter?
> >
> > Here you go:
> >
> > https://bugzilla.redhat.com/attachment.cgi?id=557552
>
> Was this helpful at all? I've been watching lkml for a related patch
> in case I was missed on CC but haven't seen anything as of yet.
Yes, it was helpful. Something like the appended patch should ignore the
bogus io-apic entry all together. As I can't test this, can you or the
reporter give the appended patch a try and ack please?
thanks,
suresh
---
From: Suresh Siddha <suresh.b.siddha@intel.com>
Subject: x86, ioapic: add register checks for bogus io-apic entries
With the recent changes to clear_IO_APIC_pin() which tries to clear
remoteIRR bit explicitly, some of the users started to see
"Unable to reset IRR for apic .." messages.
Close look shows that these are related to bogus IO-APIC entries which
return's all 1's for their io-apic registers. And the above mentioned error
messages are benign. But kernel should have ignored such io-apic's in the
first place.
Check if register 0, 1, 2 of the listed io-apic are all 1's and ignore
such io-apic.
Reported-by: Álvaro Castillo <midgoon@gmail.com>
Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
---
arch/x86/kernel/apic/io_apic.c | 26 ++++++++++++++++++++++++++
1 files changed, 26 insertions(+), 0 deletions(-)
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index fb07275..953e54d 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -3979,6 +3979,26 @@ static __init int bad_ioapic(unsigned long address)
return 0;
}
+static __init int bad_ioapic_regs(int idx)
+{
+ union IO_APIC_reg_00 reg_00;
+ union IO_APIC_reg_01 reg_01;
+ union IO_APIC_reg_02 reg_02;
+
+ reg_00.raw = io_apic_read(idx, 0);
+ reg_01.raw = io_apic_read(idx, 1);
+ reg_02.raw = io_apic_read(idx, 2);
+
+ if (reg_00.raw == -1 && reg_01.raw == -1 && reg_02.raw == -1) {
+ printk(KERN_WARNING
+ "I/O APIC 0x%x regs return all ones, skipping!\n",
+ mpc_ioapic_addr(idx));
+ return 1;
+ }
+
+ return 0;
+}
+
void __init mp_register_ioapic(int id, u32 address, u32 gsi_base)
{
int idx = 0;
@@ -3995,6 +4015,12 @@ void __init mp_register_ioapic(int id, u32 address, u32 gsi_base)
ioapics[idx].mp_config.apicaddr = address;
set_fixmap_nocache(FIX_IO_APIC_BASE_0 + idx, address);
+
+ if (bad_ioapic_regs(idx)) {
+ clear_fixmap(FIX_IO_APIC_BASE_0 + idx);
+ return;
+ }
+
ioapics[idx].mp_config.apicid = io_apic_unique_id(id);
ioapics[idx].mp_config.apicver = io_apic_get_version(idx);

View File

@ -0,0 +1,85 @@
Or rather just implement one different function as opposed
to the native one : the read function.
We synthesize the values.
Acked-by: Suresh Siddha <suresh.b.siddha@intel.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
---
arch/x86/xen/Makefile | 2 +-
arch/x86/xen/apic.c | 17 +++++++++++++++++
arch/x86/xen/enlighten.c | 2 ++
arch/x86/xen/xen-ops.h | 4 ++++
4 files changed, 24 insertions(+), 1 deletions(-)
create mode 100644 arch/x86/xen/apic.c
diff --git a/arch/x86/xen/Makefile b/arch/x86/xen/Makefile
index add2c2d..96ab2c0 100644
--- a/arch/x86/xen/Makefile
+++ b/arch/x86/xen/Makefile
@@ -20,5 +20,5 @@ obj-$(CONFIG_EVENT_TRACING) += trace.o
obj-$(CONFIG_SMP) += smp.o
obj-$(CONFIG_PARAVIRT_SPINLOCKS)+= spinlock.o
obj-$(CONFIG_XEN_DEBUG_FS) += debugfs.o
-obj-$(CONFIG_XEN_DOM0) += vga.o
+obj-$(CONFIG_XEN_DOM0) += apic.o vga.o
obj-$(CONFIG_SWIOTLB_XEN) += pci-swiotlb-xen.o
diff --git a/arch/x86/xen/apic.c b/arch/x86/xen/apic.c
new file mode 100644
index 0000000..71ed91c
--- /dev/null
+++ b/arch/x86/xen/apic.c
@@ -0,0 +1,17 @@
+#include <linux/init.h>
+#include <asm/x86_init.h>
+
+unsigned int xen_io_apic_read(unsigned apic, unsigned reg)
+{
+ if (reg == 0x1)
+ return 0x00170020;
+ else if (reg == 0x0)
+ return apic << 24;
+
+ return 0xff;
+}
+
+void __init xen_init_apic(void)
+{
+ x86_ioapic.read = xen_io_apic_read;
+}
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 0732326..93a03195 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1377,6 +1377,8 @@ asmlinkage void __init xen_start_kernel(void)
xen_start_info->console.domU.mfn = 0;
xen_start_info->console.domU.evtchn = 0;
+ xen_init_apic();
+
/* Make sure ACS will be enabled */
pci_request_acs();
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index b095739..45c0c06 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -92,11 +92,15 @@ struct dom0_vga_console_info;
#ifdef CONFIG_XEN_DOM0
void __init xen_init_vga(const struct dom0_vga_console_info *, size_t size);
+void __init xen_init_apic(void);
#else
static inline void __init xen_init_vga(const struct dom0_vga_console_info *info,
size_t size)
{
}
+static inline void __init xen_init_apic(void)
+{
+}
#endif
/* Declare an asm function, along with symbols needed to make it
--
1.7.7.5