Remove patches included in tarball.

OBS-URL: https://build.opensuse.org/package/show/Virtualization/xen?expand=0&rev=122
This commit is contained in:
Charles Arnold 2011-05-17 19:49:44 +00:00 committed by Git OBS Bridge
parent 143ac5571f
commit ca5758ba10
5 changed files with 0 additions and 724 deletions

View File

@ -1,57 +0,0 @@
# HG changeset patch
# User Wei Huang <wei.huang2@amd.com>
# Date 1302076891 -3600
# Node ID 8fb61c9ebe499b576687907d164da07802414925
# Parent 97763efc41f9b664cf6f7db653c9c3f51e50b358
x86, amd, MTRR: correct DramModEn bit of SYS_CFG MSR
Some buggy BIOS might set SYS_CFG DramModEn bit to 1, which can cause
unexpected behavior on AMD platforms. This patch clears DramModEn bit
if it is 1.
Signed-off-by: Wei Huang <wei.huang2@amd.com>
--- a/xen/arch/x86/cpu/amd.c
+++ b/xen/arch/x86/cpu/amd.c
@@ -318,6 +318,32 @@ static void check_disable_c1e(unsigned i
on_each_cpu(disable_c1e, NULL, 1);
}
+/*
+ * BIOS is expected to clear MtrrFixDramModEn bit. According to AMD BKDG :
+ * "The MtrrFixDramModEn bit should be set to 1 during BIOS initalization of
+ * the fixed MTRRs, then cleared to 0 for operation."
+ */
+static void check_syscfg_dram_mod_en(void)
+{
+ uint64_t syscfg;
+ static bool_t printed = 0;
+
+ if (!((boot_cpu_data.x86_vendor == X86_VENDOR_AMD) &&
+ (boot_cpu_data.x86 >= 0x0f)))
+ return;
+
+ rdmsrl(MSR_K8_SYSCFG, syscfg);
+ if (!(syscfg & K8_MTRRFIXRANGE_DRAM_MODIFY))
+ return;
+
+ if (!test_and_set_bool(printed))
+ printk(KERN_ERR "MTRR: SYSCFG[MtrrFixDramModEn] not "
+ "cleared by BIOS, clearing this bit\n");
+
+ syscfg &= ~K8_MTRRFIXRANGE_DRAM_MODIFY;
+ wrmsrl(MSR_K8_SYSCFG, syscfg);
+}
+
static void __devinit init_amd(struct cpuinfo_x86 *c)
{
u32 l, h;
@@ -587,6 +613,8 @@ static void __devinit init_amd(struct cp
disable_c1_ramping();
set_cpuidmask(c);
+
+ check_syscfg_dram_mod_en();
}
static unsigned int __cpuinit amd_size_cache(struct cpuinfo_x86 * c, unsigned int size)

View File

@ -1,51 +0,0 @@
# HG changeset patch
# User Wei Huang <wei.huang2@amd.com>
# Date 1302076933 -3600
# Node ID 42fa70e0761bbb0596618ca5323664f31a2faa76
# Parent 8fb61c9ebe499b576687907d164da07802414925
x86, amd, MTRR: remove k8_enable_fixed_iorrs()
AMD64 defines two special bits (bit 3 and 4) RdMem and WrMem in fixed
MTRR type. Their values are supposed to be 0 after BIOS hands the
control to OS according to AMD BKDG. Unless OS specificially turn them
on, they are kept 0 all the time. As a result, k8_enable_fixed_iorrs()
is unnecessary and removed from upstream kernel (see
https://patchwork.kernel.org/patch/11425/). This patch does the same
thing.
Signed-off-by: Wei Huang <wei.huang2@amd.com>
--- a/xen/arch/x86/cpu/mtrr/generic.c
+++ b/xen/arch/x86/cpu/mtrr/generic.c
@@ -116,20 +116,6 @@ void mtrr_wrmsr(unsigned int msr, uint64
}
/**
- * Enable and allow read/write of extended fixed-range MTRR bits on K8 CPUs
- * see AMD publication no. 24593, chapter 3.2.1 for more information
- */
-static inline void k8_enable_fixed_iorrs(void)
-{
- uint64_t msr_content;
-
- rdmsrl(MSR_K8_SYSCFG, msr_content);
- mtrr_wrmsr(MSR_K8_SYSCFG, msr_content
- | K8_MTRRFIXRANGE_DRAM_ENABLE
- | K8_MTRRFIXRANGE_DRAM_MODIFY);
-}
-
-/**
* Checks and updates an fixed-range MTRR if it differs from the value it
* should have. If K8 extenstions are wanted, update the K8 SYSCFG MSR also.
* see AMD publication no. 24593, chapter 7.8.1, page 233 for more information
@@ -145,10 +131,6 @@ static void set_fixed_range(int msr, int
val = ((uint64_t)msrwords[1] << 32) | msrwords[0];
if (msr_content != val) {
- if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD &&
- boot_cpu_data.x86 == 15 &&
- ((msrwords[0] | msrwords[1]) & K8_MTRR_RDMEM_WRMEM_MASK))
- k8_enable_fixed_iorrs();
mtrr_wrmsr(msr, val);
*changed = TRUE;
}

View File

@ -1,179 +0,0 @@
References: bnc#680824
# HG changeset patch
# User Wei Wang <wei.wang2@amd.com>
# Date 1302611179 -3600
# Node ID 995a0c01a076e9c4fb124c090bc146a10d76bc7b
# Parent dbd98ab2f87facba8117bb881fa2ea5dfdb92960
AMD IOMMU: Fix an interrupt remapping issue
Some device could generate bogus interrupts if an IO-APIC RTE and an
iommu interrupt remapping entry are not consistent during 2 adjacent
64bits IO-APIC RTE updates. For example, if the 2nd operation updates
destination bits in RTE for SATA device and unmask it, in some case,
SATA device will assert ioapic pin to generate interrupt immediately
using new destination but iommu could still translate it into the old
destination, then dom0 would be confused. To fix that, we sync up
interrupt remapping entry with IO-APIC IRE on every 32 bits operation
and forward IOAPIC RTE updates after interrupt.
Signed-off-by: Wei Wang <wei.wang2@amd.com>
Acked-by: Jan Beulich <jbeulich@novell.com>
--- a/xen/drivers/passthrough/amd/iommu_intr.c
+++ b/xen/drivers/passthrough/amd/iommu_intr.c
@@ -117,8 +117,7 @@ void invalidate_interrupt_table(struct a
static void update_intremap_entry_from_ioapic(
int bdf,
struct amd_iommu *iommu,
- struct IO_APIC_route_entry *ioapic_rte,
- unsigned int rte_upper, unsigned int value)
+ struct IO_APIC_route_entry *ioapic_rte)
{
unsigned long flags;
u32* entry;
@@ -130,28 +129,26 @@ static void update_intremap_entry_from_i
req_id = get_intremap_requestor_id(bdf);
lock = get_intremap_lock(req_id);
- /* only remap interrupt vector when lower 32 bits in ioapic ire changed */
- if ( likely(!rte_upper) )
- {
- delivery_mode = rte->delivery_mode;
- vector = rte->vector;
- dest_mode = rte->dest_mode;
- dest = rte->dest.logical.logical_dest;
- spin_lock_irqsave(lock, flags);
- offset = get_intremap_offset(vector, delivery_mode);
- entry = (u32*)get_intremap_entry(req_id, offset);
+ delivery_mode = rte->delivery_mode;
+ vector = rte->vector;
+ dest_mode = rte->dest_mode;
+ dest = rte->dest.logical.logical_dest;
- update_intremap_entry(entry, vector, delivery_mode, dest_mode, dest);
- spin_unlock_irqrestore(lock, flags);
+ spin_lock_irqsave(lock, flags);
- if ( iommu->enabled )
- {
- spin_lock_irqsave(&iommu->lock, flags);
- invalidate_interrupt_table(iommu, req_id);
- flush_command_buffer(iommu);
- spin_unlock_irqrestore(&iommu->lock, flags);
- }
+ offset = get_intremap_offset(vector, delivery_mode);
+ entry = (u32*)get_intremap_entry(req_id, offset);
+ update_intremap_entry(entry, vector, delivery_mode, dest_mode, dest);
+
+ spin_unlock_irqrestore(lock, flags);
+
+ if ( iommu->enabled )
+ {
+ spin_lock_irqsave(&iommu->lock, flags);
+ invalidate_interrupt_table(iommu, req_id);
+ flush_command_buffer(iommu);
+ spin_unlock_irqrestore(&iommu->lock, flags);
}
}
@@ -199,7 +196,8 @@ int __init amd_iommu_setup_ioapic_remapp
spin_lock_irqsave(lock, flags);
offset = get_intremap_offset(vector, delivery_mode);
entry = (u32*)get_intremap_entry(req_id, offset);
- update_intremap_entry(entry, vector, delivery_mode, dest_mode, dest);
+ update_intremap_entry(entry, vector,
+ delivery_mode, dest_mode, dest);
spin_unlock_irqrestore(lock, flags);
if ( iommu->enabled )
@@ -217,16 +215,17 @@ int __init amd_iommu_setup_ioapic_remapp
void amd_iommu_ioapic_update_ire(
unsigned int apic, unsigned int reg, unsigned int value)
{
- struct IO_APIC_route_entry ioapic_rte = { 0 };
- unsigned int rte_upper = (reg & 1) ? 1 : 0;
+ struct IO_APIC_route_entry old_rte = { 0 };
+ struct IO_APIC_route_entry new_rte = { 0 };
+ unsigned int rte_lo = (reg & 1) ? reg - 1 : reg;
int saved_mask, bdf;
struct amd_iommu *iommu;
- *IO_APIC_BASE(apic) = reg;
- *(IO_APIC_BASE(apic)+4) = value;
-
if ( !iommu_intremap )
+ {
+ __io_apic_write(apic, reg, value);
return;
+ }
/* get device id of ioapic devices */
bdf = ioapic_bdf[IO_APIC_ID(apic)];
@@ -235,30 +234,49 @@ void amd_iommu_ioapic_update_ire(
{
AMD_IOMMU_DEBUG("Fail to find iommu for ioapic device id = 0x%x\n",
bdf);
+ __io_apic_write(apic, reg, value);
return;
}
- if ( rte_upper )
- return;
- /* read both lower and upper 32-bits of rte entry */
- *IO_APIC_BASE(apic) = reg;
- *(((u32 *)&ioapic_rte) + 0) = *(IO_APIC_BASE(apic)+4);
- *IO_APIC_BASE(apic) = reg + 1;
- *(((u32 *)&ioapic_rte) + 1) = *(IO_APIC_BASE(apic)+4);
+ /* save io-apic rte lower 32 bits */
+ *((u32 *)&old_rte) = __io_apic_read(apic, rte_lo);
+ saved_mask = old_rte.mask;
+
+ if ( reg == rte_lo )
+ {
+ *((u32 *)&new_rte) = value;
+ /* read upper 32 bits from io-apic rte */
+ *(((u32 *)&new_rte) + 1) = __io_apic_read(apic, reg + 1);
+ }
+ else
+ {
+ *((u32 *)&new_rte) = *((u32 *)&old_rte);
+ *(((u32 *)&new_rte) + 1) = value;
+ }
/* mask the interrupt while we change the intremap table */
- saved_mask = ioapic_rte.mask;
- ioapic_rte.mask = 1;
- *IO_APIC_BASE(apic) = reg;
- *(IO_APIC_BASE(apic)+4) = *(((int *)&ioapic_rte)+0);
- ioapic_rte.mask = saved_mask;
+ if ( !saved_mask )
+ {
+ old_rte.mask = 1;
+ __io_apic_write(apic, rte_lo, *((u32 *)&old_rte));
+ }
- update_intremap_entry_from_ioapic(
- bdf, iommu, &ioapic_rte, rte_upper, value);
+ /* Update interrupt remapping entry */
+ update_intremap_entry_from_ioapic(bdf, iommu, &new_rte);
+
+ /* Forward write access to IO-APIC RTE */
+ __io_apic_write(apic, reg, value);
+
+ /* For lower bits access, return directly to avoid double writes */
+ if ( reg == rte_lo )
+ return;
/* unmask the interrupt after we have updated the intremap table */
- *IO_APIC_BASE(apic) = reg;
- *(IO_APIC_BASE(apic)+4) = *(((u32 *)&ioapic_rte)+0);
+ if ( !saved_mask )
+ {
+ old_rte.mask = saved_mask;
+ __io_apic_write(apic, rte_lo, *((u32 *)&old_rte));
+ }
}
static void update_intremap_entry_from_msi_msg(

View File

@ -1,220 +0,0 @@
References: bnc#623680
# HG changeset patch
# User Keir Fraser <keir@xen.org>
# Date 1302853928 -3600
# Node ID 1329d99b4f161b7617a667f601077cc92559f248
# Parent b5165fb66b56d9438d77b475eaa9db67318d1ea1
x86: don't write_tsc() non-zero values on CPUs updating only the lower 32 bits
This means suppressing the uses in time_calibration_tsc_rendezvous(),
cstate_restore_tsc(), and synchronize_tsc_slave(), and fixes a boot
hang of Linux Dom0 when loading processor.ko on such systems that
have support for C states above C1.
Signed-off-by: Jan Beulich <jbeulich@novell.com>
Signed-off-by: Keir Fraser <keir@xen.org>
--- a/xen/arch/x86/acpi/cpu_idle.c
+++ b/xen/arch/x86/acpi/cpu_idle.c
@@ -1099,3 +1099,7 @@ void cpuidle_disable_deep_cstate(void)
hpet_disable_legacy_broadcast();
}
+bool_t cpuidle_using_deep_cstate(void)
+{
+ return xen_cpuidle && max_cstate > (local_apic_timer_c2_ok ? 2 : 1);
+}
--- a/xen/arch/x86/hpet.c
+++ b/xen/arch/x86/hpet.c
@@ -634,6 +634,9 @@ void hpet_disable_legacy_broadcast(void)
u32 cfg;
unsigned long flags;
+ if ( !legacy_hpet_event.shift )
+ return;
+
spin_lock_irqsave(&legacy_hpet_event.lock, flags);
legacy_hpet_event.flags |= HPET_EVT_DISABLE;
--- a/xen/arch/x86/smpboot.c
+++ b/xen/arch/x86/smpboot.c
@@ -41,6 +41,7 @@
#include <asm/flushtlb.h>
#include <asm/msr.h>
#include <asm/mtrr.h>
+#include <asm/time.h>
#include <mach_apic.h>
#include <mach_wakecpu.h>
#include <smpboot_hooks.h>
@@ -134,6 +135,12 @@ static void smp_store_cpu_info(int id)
;
}
+/*
+ * TSC's upper 32 bits can't be written in earlier CPUs (before
+ * Prescott), there is no way to resync one AP against BP.
+ */
+bool_t disable_tsc_sync;
+
static atomic_t tsc_count;
static uint64_t tsc_value;
static cpumask_t tsc_sync_cpu_mask;
@@ -142,6 +149,9 @@ static void synchronize_tsc_master(unsig
{
unsigned int i;
+ if ( disable_tsc_sync )
+ return;
+
if ( boot_cpu_has(X86_FEATURE_TSC_RELIABLE) &&
!cpu_isset(slave, tsc_sync_cpu_mask) )
return;
@@ -163,6 +173,9 @@ static void synchronize_tsc_slave(unsign
{
unsigned int i;
+ if ( disable_tsc_sync )
+ return;
+
if ( boot_cpu_has(X86_FEATURE_TSC_RELIABLE) &&
!cpu_isset(slave, tsc_sync_cpu_mask) )
return;
--- a/xen/arch/x86/time.c
+++ b/xen/arch/x86/time.c
@@ -21,6 +21,7 @@
#include <xen/smp.h>
#include <xen/irq.h>
#include <xen/softirq.h>
+#include <xen/cpuidle.h>
#include <xen/keyhandler.h>
#include <xen/guest_access.h>
#include <asm/io.h>
@@ -682,6 +683,8 @@ void cstate_restore_tsc(void)
if ( boot_cpu_has(X86_FEATURE_NONSTOP_TSC) )
return;
+ ASSERT(boot_cpu_has(X86_FEATURE_TSC_RELIABLE));
+
write_tsc(stime2tsc(read_platform_stime()));
}
@@ -1384,6 +1387,66 @@ void init_percpu_time(void)
}
}
+/*
+ * On certain older Intel CPUs writing the TSC MSR clears the upper 32 bits.
+ * Obviously we must not use write_tsc() on such CPUs.
+ *
+ * Additionally, AMD specifies that being able to write the TSC MSR is not an
+ * architectural feature (but, other than their manual says, also cannot be
+ * determined from CPUID bits).
+ */
+static void __init tsc_check_writability(void)
+{
+ const char *what = NULL;
+ uint64_t tsc;
+
+ /*
+ * If all CPUs are reported as synchronised and in sync, we never write
+ * the TSCs (except unavoidably, when a CPU is physically hot-plugged).
+ * Hence testing for writability is pointless and even harmful.
+ */
+ if ( boot_cpu_has(X86_FEATURE_TSC_RELIABLE) )
+ return;
+
+ rdtscll(tsc);
+ if ( wrmsr_safe(MSR_IA32_TSC, 0) == 0 )
+ {
+ uint64_t tmp, tmp2;
+ rdtscll(tmp2);
+ write_tsc(tsc | (1ULL << 32));
+ rdtscll(tmp);
+ if ( ABS((s64)tmp - (s64)tmp2) < (1LL << 31) )
+ what = "only partially";
+ }
+ else
+ {
+ what = "not";
+ }
+
+ /* Nothing to do if the TSC is fully writable. */
+ if ( !what )
+ {
+ /*
+ * Paranoia - write back original TSC value. However, APs get synced
+ * with BSP as they are brought up, so this doesn't much matter.
+ */
+ write_tsc(tsc);
+ return;
+ }
+
+ printk(XENLOG_WARNING "TSC %s writable\n", what);
+
+ /* time_calibration_tsc_rendezvous() must not be used */
+ setup_clear_cpu_cap(X86_FEATURE_CONSTANT_TSC);
+
+ /* cstate_restore_tsc() must not be used (or do nothing) */
+ if ( !boot_cpu_has(X86_FEATURE_NONSTOP_TSC) )
+ cpuidle_disable_deep_cstate();
+
+ /* synchronize_tsc_slave() must do nothing */
+ disable_tsc_sync = 1;
+}
+
/* Late init function (after all CPUs are booted). */
int __init init_xen_time(void)
{
@@ -1400,6 +1463,8 @@ int __init init_xen_time(void)
setup_clear_cpu_cap(X86_FEATURE_TSC_RELIABLE);
}
+ tsc_check_writability();
+
/* If we have constant-rate TSCs then scale factor can be shared. */
if ( boot_cpu_has(X86_FEATURE_CONSTANT_TSC) )
{
@@ -1451,7 +1516,7 @@ static int disable_pit_irq(void)
* XXX dom0 may rely on RTC interrupt delivery, so only enable
* hpet_broadcast if FSB mode available or if force_hpet_broadcast.
*/
- if ( xen_cpuidle && !boot_cpu_has(X86_FEATURE_ARAT) )
+ if ( cpuidle_using_deep_cstate() && !boot_cpu_has(X86_FEATURE_ARAT) )
{
hpet_broadcast_init();
if ( !hpet_broadcast_is_available() )
--- a/xen/include/asm-x86/setup.h
+++ b/xen/include/asm-x86/setup.h
@@ -4,7 +4,6 @@
#include <xen/multiboot.h>
extern bool_t early_boot;
-extern s8 xen_cpuidle;
extern unsigned long xenheap_initial_phys_start;
void init_done(void);
--- a/xen/include/asm-x86/time.h
+++ b/xen/include/asm-x86/time.h
@@ -24,6 +24,8 @@
typedef u64 cycles_t;
+extern bool_t disable_tsc_sync;
+
static inline cycles_t get_cycles(void)
{
cycles_t c;
--- a/xen/include/xen/cpuidle.h
+++ b/xen/include/xen/cpuidle.h
@@ -85,7 +85,10 @@ struct cpuidle_governor
void (*reflect) (struct acpi_processor_power *dev);
};
+extern s8 xen_cpuidle;
extern struct cpuidle_governor *cpuidle_current_governor;
+
+bool_t cpuidle_using_deep_cstate(void);
void cpuidle_disable_deep_cstate(void);
extern void cpuidle_wakeup_mwait(cpumask_t *mask);

View File

@ -1,217 +0,0 @@
diff -r dbf2ddf652dc tools/libxc/xc_dom_bzimageloader.c
--- a/tools/libxc/xc_dom_bzimageloader.c Thu Apr 07 15:26:58 2011 +0100
+++ b/tools/libxc/xc_dom_bzimageloader.c Thu Apr 21 12:05:57 2011 +0100
@@ -82,8 +82,29 @@ static int xc_try_bzip2_decode(
for ( ; ; )
{
ret = BZ2_bzDecompress(&stream);
- if ( (stream.avail_out == 0) || (ret != BZ_OK) )
+ if ( ret == BZ_STREAM_END )
{
+ DOMPRINTF("BZIP2: Saw data stream end");
+ retval = 0;
+ break;
+ }
+ if ( ret != BZ_OK )
+ {
+ DOMPRINTF("BZIP2: error %d", ret);
+ free(out_buf);
+ goto bzip2_cleanup;
+ }
+
+ if ( stream.avail_out == 0 )
+ {
+ /* Protect against output buffer overflow */
+ if ( outsize > INT_MAX / 2 )
+ {
+ DOMPRINTF("BZIP2: output buffer overflow");
+ free(out_buf);
+ goto bzip2_cleanup;
+ }
+
tmp_buf = realloc(out_buf, outsize * 2);
if ( tmp_buf == NULL )
{
@@ -97,16 +118,18 @@ static int xc_try_bzip2_decode(
stream.avail_out = (outsize * 2) - outsize;
outsize *= 2;
}
-
- if ( ret != BZ_OK )
+ else if ( stream.avail_in == 0 )
{
- if ( ret == BZ_STREAM_END )
- {
- DOMPRINTF("BZIP2: Saw data stream end");
- retval = 0;
- break;
- }
- DOMPRINTF("BZIP2: error");
+ /*
+ * If there is output buffer available then this indicates
+ * that BZ2_bzDecompress would like more input data to be
+ * provided. However our complete input buffer is in
+ * memory and provided upfront so if avail_in is zero this
+ * actually indicates a truncated input.
+ */
+ DOMPRINTF("BZIP2: not enough input");
+ free(out_buf);
+ goto bzip2_cleanup;
}
}
@@ -180,31 +203,14 @@ static int xc_try_lzma_decode(
for ( ; ; )
{
ret = lzma_code(&stream, action);
- if ( (stream.avail_out == 0) || (ret != LZMA_OK) )
+ if ( ret == LZMA_STREAM_END )
{
- tmp_buf = realloc(out_buf, outsize * 2);
- if ( tmp_buf == NULL )
- {
- DOMPRINTF("LZMA: Failed to realloc memory");
- free(out_buf);
- goto lzma_cleanup;
- }
- out_buf = tmp_buf;
-
- stream.next_out = out_buf + outsize;
- stream.avail_out = (outsize * 2) - outsize;
- outsize *= 2;
+ DOMPRINTF("LZMA: Saw data stream end");
+ retval = 0;
+ break;
}
-
if ( ret != LZMA_OK )
{
- if ( ret == LZMA_STREAM_END )
- {
- DOMPRINTF("LZMA: Saw data stream end");
- retval = 0;
- break;
- }
-
switch ( ret )
{
case LZMA_MEM_ERROR:
@@ -238,7 +244,32 @@ static int xc_try_lzma_decode(
}
DOMPRINTF("%s: LZMA decompression error %s",
__FUNCTION__, msg);
- break;
+ free(out_buf);
+ goto lzma_cleanup;
+ }
+
+ if ( stream.avail_out == 0 )
+ {
+ /* Protect against output buffer overflow */
+ if ( outsize > INT_MAX / 2 )
+ {
+ DOMPRINTF("LZMA: output buffer overflow");
+ free(out_buf);
+ goto lzma_cleanup;
+ }
+
+ tmp_buf = realloc(out_buf, outsize * 2);
+ if ( tmp_buf == NULL )
+ {
+ DOMPRINTF("LZMA: Failed to realloc memory");
+ free(out_buf);
+ goto lzma_cleanup;
+ }
+ out_buf = tmp_buf;
+
+ stream.next_out = out_buf + outsize;
+ stream.avail_out = (outsize * 2) - outsize;
+ outsize *= 2;
}
}
@@ -489,18 +520,18 @@ struct setup_header {
extern struct xc_dom_loader elf_loader;
-static unsigned int payload_offset(struct setup_header *hdr)
+static int check_magic(struct xc_dom_image *dom, const void *magic, size_t len)
{
- unsigned int off;
+ if (len > dom->kernel_size)
+ return 0;
- off = (hdr->setup_sects + 1) * 512;
- off += hdr->payload_offset;
- return off;
+ return (memcmp(dom->kernel_blob, magic, len) == 0);
}
static int xc_dom_probe_bzimage_kernel(struct xc_dom_image *dom)
{
struct setup_header *hdr;
+ uint64_t payload_offset, payload_length;
int ret;
if ( dom->kernel_blob == NULL )
@@ -533,10 +564,30 @@ static int xc_dom_probe_bzimage_kernel(s
return -EINVAL;
}
- dom->kernel_blob = dom->kernel_blob + payload_offset(hdr);
- dom->kernel_size = hdr->payload_length;
- if ( memcmp(dom->kernel_blob, "\037\213", 2) == 0 )
+ /* upcast to 64 bits to avoid overflow */
+ /* setup_sects is u8 and so cannot overflow */
+ payload_offset = (hdr->setup_sects + 1) * 512;
+ payload_offset += hdr->payload_offset;
+ payload_length = hdr->payload_length;
+
+ if ( payload_offset >= dom->kernel_size )
+ {
+ xc_dom_panic(dom->xch, XC_INVALID_KERNEL, "%s: payload offset overflow",
+ __FUNCTION__);
+ return -EINVAL;
+ }
+ if ( (payload_offset + payload_length) > dom->kernel_size )
+ {
+ xc_dom_panic(dom->xch, XC_INVALID_KERNEL, "%s: payload length overflow",
+ __FUNCTION__);
+ return -EINVAL;
+ }
+
+ dom->kernel_blob = dom->kernel_blob + payload_offset;
+ dom->kernel_size = payload_length;
+
+ if ( check_magic(dom, "\037\213", 2) )
{
ret = xc_dom_try_gunzip(dom, &dom->kernel_blob, &dom->kernel_size);
if ( ret == -1 )
@@ -546,7 +597,7 @@ static int xc_dom_probe_bzimage_kernel(s
return -EINVAL;
}
}
- else if ( memcmp(dom->kernel_blob, "\102\132\150", 3) == 0 )
+ else if ( check_magic(dom, "\102\132\150", 3) )
{
ret = xc_try_bzip2_decode(dom, &dom->kernel_blob, &dom->kernel_size);
if ( ret < 0 )
@@ -557,7 +608,7 @@ static int xc_dom_probe_bzimage_kernel(s
return -EINVAL;
}
}
- else if ( memcmp(dom->kernel_blob, "\135\000", 2) == 0 )
+ else if ( check_magic(dom, "\135\000", 2) )
{
ret = xc_try_lzma_decode(dom, &dom->kernel_blob, &dom->kernel_size);
if ( ret < 0 )
@@ -568,7 +619,7 @@ static int xc_dom_probe_bzimage_kernel(s
return -EINVAL;
}
}
- else if ( memcmp(dom->kernel_blob, "\x89LZO", 5) == 0 )
+ else if ( check_magic(dom, "\x89LZO", 5) )
{
ret = xc_try_lzo1x_decode(dom, &dom->kernel_blob, &dom->kernel_size);
if ( ret < 0 )