summaryrefslogtreecommitdiff
path: root/arch
diff options
context:
space:
mode:
authorDavid S. Miller <davem@davemloft.net>2017-06-07 05:20:08 +0300
committerDavid S. Miller <davem@davemloft.net>2017-06-07 05:20:08 +0300
commit216fe8f021e33c36e3b27c49c9f1951f6b037d7f (patch)
treea43daec41b4d3955e7a4f8d0ed0654a7c80527ec /arch
parent9747e2313838ee8f5d8073fd6aa7289255c3c51b (diff)
parentb29794ec95c6856b316c2295904208bf11ffddd9 (diff)
downloadlinux-216fe8f021e33c36e3b27c49c9f1951f6b037d7f.tar.xz
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net
Just some simple overlapping changes in marvell PHY driver and the DSA core code. Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'arch')
-rw-r--r--arch/arm/boot/compressed/efi-header.S4
-rw-r--r--arch/arm/boot/compressed/head.S17
-rw-r--r--arch/arm/boot/dts/imx6ul-14x14-evk.dts6
-rw-r--r--arch/arm/common/mcpm_entry.c6
-rw-r--r--arch/arm/include/asm/pgtable-nommu.h1
-rw-r--r--arch/arm64/include/asm/acpi.h6
-rw-r--r--arch/arm64/kernel/pci.c4
-rw-r--r--arch/frv/include/asm/timex.h6
-rw-r--r--arch/mips/kernel/process.c1
-rw-r--r--arch/openrisc/kernel/process.c2
-rw-r--r--arch/powerpc/include/uapi/asm/cputable.h2
-rw-r--r--arch/powerpc/kernel/cputable.c3
-rw-r--r--arch/powerpc/kernel/prom.c2
-rw-r--r--arch/powerpc/platforms/cell/spu_base.c4
-rw-r--r--arch/powerpc/platforms/powernv/npu-dma.c5
-rw-r--r--arch/sparc/Kconfig12
-rw-r--r--arch/sparc/include/asm/mmu_64.h2
-rw-r--r--arch/sparc/include/asm/mmu_context_64.h32
-rw-r--r--arch/sparc/include/asm/pil.h1
-rw-r--r--arch/sparc/include/asm/vio.h1
-rw-r--r--arch/sparc/kernel/ds.c2
-rw-r--r--arch/sparc/kernel/irq_64.c17
-rw-r--r--arch/sparc/kernel/kernel.h1
-rw-r--r--arch/sparc/kernel/smp_64.c31
-rw-r--r--arch/sparc/kernel/tsb.S11
-rw-r--r--arch/sparc/kernel/ttable_64.S2
-rw-r--r--arch/sparc/kernel/vio.c68
-rw-r--r--arch/sparc/lib/Makefile1
-rw-r--r--arch/sparc/lib/multi3.S35
-rw-r--r--arch/sparc/mm/init_64.c89
-rw-r--r--arch/sparc/mm/tsb.c7
-rw-r--r--arch/sparc/mm/ultra.S5
-rw-r--r--arch/x86/Kconfig2
-rw-r--r--arch/x86/Makefile2
-rw-r--r--arch/x86/boot/compressed/Makefile2
-rw-r--r--arch/x86/entry/entry_32.S30
-rw-r--r--arch/x86/entry/entry_64.S11
-rw-r--r--arch/x86/include/asm/mce.h1
-rw-r--r--arch/x86/kernel/alternative.c9
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce.c13
-rw-r--r--arch/x86/kernel/cpu/microcode/amd.c16
-rw-r--r--arch/x86/kernel/ftrace.c20
-rw-r--r--arch/x86/kernel/kprobes/core.c9
-rw-r--r--arch/x86/kernel/process_32.c2
-rw-r--r--arch/x86/kernel/setup.c4
-rw-r--r--arch/x86/kernel/unwind_frame.c49
-rw-r--r--arch/x86/kvm/lapic.c5
-rw-r--r--arch/x86/kvm/svm.c26
-rw-r--r--arch/x86/kvm/vmx.c147
-rw-r--r--arch/x86/kvm/x86.c7
-rw-r--r--arch/x86/mm/pageattr.c2
-rw-r--r--arch/x86/platform/efi/efi.c6
-rw-r--r--arch/x86/platform/efi/efi_64.c79
-rw-r--r--arch/x86/platform/efi/quirks.c3
54 files changed, 521 insertions, 310 deletions
diff --git a/arch/arm/boot/compressed/efi-header.S b/arch/arm/boot/compressed/efi-header.S
index 9d5dc4fda3c1..3f7d1b74c5e0 100644
--- a/arch/arm/boot/compressed/efi-header.S
+++ b/arch/arm/boot/compressed/efi-header.S
@@ -17,14 +17,12 @@
@ there.
.inst 'M' | ('Z' << 8) | (0x1310 << 16) @ tstne r0, #0x4d000
#else
- mov r0, r0
+ W(mov) r0, r0
#endif
.endm
.macro __EFI_HEADER
#ifdef CONFIG_EFI_STUB
- b __efi_start
-
.set start_offset, __efi_start - start
.org start + 0x3c
@
diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S
index 7c711ba61417..8a756870c238 100644
--- a/arch/arm/boot/compressed/head.S
+++ b/arch/arm/boot/compressed/head.S
@@ -130,19 +130,22 @@ start:
.rept 7
__nop
.endr
- ARM( mov r0, r0 )
- ARM( b 1f )
- THUMB( badr r12, 1f )
- THUMB( bx r12 )
+#ifndef CONFIG_THUMB2_KERNEL
+ mov r0, r0
+#else
+ AR_CLASS( sub pc, pc, #3 ) @ A/R: switch to Thumb2 mode
+ M_CLASS( nop.w ) @ M: already in Thumb2 mode
+ .thumb
+#endif
+ W(b) 1f
.word _magic_sig @ Magic numbers to help the loader
.word _magic_start @ absolute load/run zImage address
.word _magic_end @ zImage end address
.word 0x04030201 @ endianness flag
- THUMB( .thumb )
-1: __EFI_HEADER
-
+ __EFI_HEADER
+1:
ARM_BE8( setend be ) @ go BE8 if compiled for BE8
AR_CLASS( mrs r9, cpsr )
#ifdef CONFIG_ARM_VIRT_EXT
diff --git a/arch/arm/boot/dts/imx6ul-14x14-evk.dts b/arch/arm/boot/dts/imx6ul-14x14-evk.dts
index f18e1f1d0ce2..d2be8aa3370b 100644
--- a/arch/arm/boot/dts/imx6ul-14x14-evk.dts
+++ b/arch/arm/boot/dts/imx6ul-14x14-evk.dts
@@ -120,10 +120,16 @@
ethphy0: ethernet-phy@2 {
reg = <2>;
+ micrel,led-mode = <1>;
+ clocks = <&clks IMX6UL_CLK_ENET_REF>;
+ clock-names = "rmii-ref";
};
ethphy1: ethernet-phy@1 {
reg = <1>;
+ micrel,led-mode = <1>;
+ clocks = <&clks IMX6UL_CLK_ENET2_REF>;
+ clock-names = "rmii-ref";
};
};
};
diff --git a/arch/arm/common/mcpm_entry.c b/arch/arm/common/mcpm_entry.c
index cf062472e07b..2b913f17d50f 100644
--- a/arch/arm/common/mcpm_entry.c
+++ b/arch/arm/common/mcpm_entry.c
@@ -235,7 +235,7 @@ int mcpm_cpu_power_up(unsigned int cpu, unsigned int cluster)
return ret;
}
-typedef void (*phys_reset_t)(unsigned long);
+typedef typeof(cpu_reset) phys_reset_t;
void mcpm_cpu_power_down(void)
{
@@ -300,7 +300,7 @@ void mcpm_cpu_power_down(void)
* on the CPU.
*/
phys_reset = (phys_reset_t)(unsigned long)__pa_symbol(cpu_reset);
- phys_reset(__pa_symbol(mcpm_entry_point));
+ phys_reset(__pa_symbol(mcpm_entry_point), false);
/* should never get here */
BUG();
@@ -389,7 +389,7 @@ static int __init nocache_trampoline(unsigned long _arg)
__mcpm_cpu_down(cpu, cluster);
phys_reset = (phys_reset_t)(unsigned long)__pa_symbol(cpu_reset);
- phys_reset(__pa_symbol(mcpm_entry_point));
+ phys_reset(__pa_symbol(mcpm_entry_point), false);
BUG();
}
diff --git a/arch/arm/include/asm/pgtable-nommu.h b/arch/arm/include/asm/pgtable-nommu.h
index 302240c19a5a..a0d726a47c8a 100644
--- a/arch/arm/include/asm/pgtable-nommu.h
+++ b/arch/arm/include/asm/pgtable-nommu.h
@@ -66,6 +66,7 @@ typedef pte_t *pte_addr_t;
#define pgprot_noncached(prot) (prot)
#define pgprot_writecombine(prot) (prot)
#define pgprot_dmacoherent(prot) (prot)
+#define pgprot_device(prot) (prot)
/*
diff --git a/arch/arm64/include/asm/acpi.h b/arch/arm64/include/asm/acpi.h
index 0e99978da3f0..59cca1d6ec54 100644
--- a/arch/arm64/include/asm/acpi.h
+++ b/arch/arm64/include/asm/acpi.h
@@ -23,9 +23,9 @@
#define ACPI_MADT_GICC_LENGTH \
(acpi_gbl_FADT.header.revision < 6 ? 76 : 80)
-#define BAD_MADT_GICC_ENTRY(entry, end) \
- (!(entry) || (unsigned long)(entry) + sizeof(*(entry)) > (end) || \
- (entry)->header.length != ACPI_MADT_GICC_LENGTH)
+#define BAD_MADT_GICC_ENTRY(entry, end) \
+ (!(entry) || (entry)->header.length != ACPI_MADT_GICC_LENGTH || \
+ (unsigned long)(entry) + ACPI_MADT_GICC_LENGTH > (end))
/* Basic configuration for ACPI */
#ifdef CONFIG_ACPI
diff --git a/arch/arm64/kernel/pci.c b/arch/arm64/kernel/pci.c
index 4f0e3ebfea4b..c7e3e6387a49 100644
--- a/arch/arm64/kernel/pci.c
+++ b/arch/arm64/kernel/pci.c
@@ -191,8 +191,10 @@ struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root)
return NULL;
root_ops = kzalloc_node(sizeof(*root_ops), GFP_KERNEL, node);
- if (!root_ops)
+ if (!root_ops) {
+ kfree(ri);
return NULL;
+ }
ri->cfg = pci_acpi_setup_ecam_mapping(root);
if (!ri->cfg) {
diff --git a/arch/frv/include/asm/timex.h b/arch/frv/include/asm/timex.h
index a89bddefdacf..139093fab326 100644
--- a/arch/frv/include/asm/timex.h
+++ b/arch/frv/include/asm/timex.h
@@ -16,5 +16,11 @@ static inline cycles_t get_cycles(void)
#define vxtime_lock() do {} while (0)
#define vxtime_unlock() do {} while (0)
+/* This attribute is used in include/linux/jiffies.h alongside with
+ * __cacheline_aligned_in_smp. It is assumed that __cacheline_aligned_in_smp
+ * for frv does not contain another section specification.
+ */
+#define __jiffy_arch_data __attribute__((__section__(".data")))
+
#endif
diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c
index 918d4c73e951..5351e1f3950d 100644
--- a/arch/mips/kernel/process.c
+++ b/arch/mips/kernel/process.c
@@ -120,7 +120,6 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long usp,
struct thread_info *ti = task_thread_info(p);
struct pt_regs *childregs, *regs = current_pt_regs();
unsigned long childksp;
- p->set_child_tid = p->clear_child_tid = NULL;
childksp = (unsigned long)task_stack_page(p) + THREAD_SIZE - 32;
diff --git a/arch/openrisc/kernel/process.c b/arch/openrisc/kernel/process.c
index f8da545854f9..106859ae27ff 100644
--- a/arch/openrisc/kernel/process.c
+++ b/arch/openrisc/kernel/process.c
@@ -167,8 +167,6 @@ copy_thread(unsigned long clone_flags, unsigned long usp,
top_of_kernel_stack = sp;
- p->set_child_tid = p->clear_child_tid = NULL;
-
/* Locate userspace context on stack... */
sp -= STACK_FRAME_OVERHEAD; /* redzone */
sp -= sizeof(struct pt_regs);
diff --git a/arch/powerpc/include/uapi/asm/cputable.h b/arch/powerpc/include/uapi/asm/cputable.h
index 3e7ce86d5c13..4d877144f377 100644
--- a/arch/powerpc/include/uapi/asm/cputable.h
+++ b/arch/powerpc/include/uapi/asm/cputable.h
@@ -46,6 +46,8 @@
#define PPC_FEATURE2_HTM_NOSC 0x01000000
#define PPC_FEATURE2_ARCH_3_00 0x00800000 /* ISA 3.00 */
#define PPC_FEATURE2_HAS_IEEE128 0x00400000 /* VSX IEEE Binary Float 128-bit */
+#define PPC_FEATURE2_DARN 0x00200000 /* darn random number insn */
+#define PPC_FEATURE2_SCV 0x00100000 /* scv syscall */
/*
* IMPORTANT!
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index 9b3e88b1a9c8..6f849832a669 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -124,7 +124,8 @@ extern void __restore_cpu_e6500(void);
#define COMMON_USER_POWER9 COMMON_USER_POWER8
#define COMMON_USER2_POWER9 (COMMON_USER2_POWER8 | \
PPC_FEATURE2_ARCH_3_00 | \
- PPC_FEATURE2_HAS_IEEE128)
+ PPC_FEATURE2_HAS_IEEE128 | \
+ PPC_FEATURE2_DARN )
#ifdef CONFIG_PPC_BOOK3E_64
#define COMMON_USER_BOOKE (COMMON_USER_PPC64 | PPC_FEATURE_BOOKE)
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index 40c4887c27b6..f83056297441 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -161,7 +161,9 @@ static struct ibm_pa_feature {
{ .pabyte = 0, .pabit = 3, .cpu_features = CPU_FTR_CTRL },
{ .pabyte = 0, .pabit = 6, .cpu_features = CPU_FTR_NOEXECUTE },
{ .pabyte = 1, .pabit = 2, .mmu_features = MMU_FTR_CI_LARGE_PAGE },
+#ifdef CONFIG_PPC_RADIX_MMU
{ .pabyte = 40, .pabit = 0, .mmu_features = MMU_FTR_TYPE_RADIX },
+#endif
{ .pabyte = 1, .pabit = 1, .invert = 1, .cpu_features = CPU_FTR_NODSISRALIGN },
{ .pabyte = 5, .pabit = 0, .cpu_features = CPU_FTR_REAL_LE,
.cpu_user_ftrs = PPC_FEATURE_TRUE_LE },
diff --git a/arch/powerpc/platforms/cell/spu_base.c b/arch/powerpc/platforms/cell/spu_base.c
index 96c2b8a40630..0c45cdbac4cf 100644
--- a/arch/powerpc/platforms/cell/spu_base.c
+++ b/arch/powerpc/platforms/cell/spu_base.c
@@ -197,7 +197,9 @@ static int __spu_trap_data_map(struct spu *spu, unsigned long ea, u64 dsisr)
(REGION_ID(ea) != USER_REGION_ID)) {
spin_unlock(&spu->register_lock);
- ret = hash_page(ea, _PAGE_PRESENT | _PAGE_READ, 0x300, dsisr);
+ ret = hash_page(ea,
+ _PAGE_PRESENT | _PAGE_READ | _PAGE_PRIVILEGED,
+ 0x300, dsisr);
spin_lock(&spu->register_lock);
if (!ret) {
diff --git a/arch/powerpc/platforms/powernv/npu-dma.c b/arch/powerpc/platforms/powernv/npu-dma.c
index 067defeea691..78fa9395b8c5 100644
--- a/arch/powerpc/platforms/powernv/npu-dma.c
+++ b/arch/powerpc/platforms/powernv/npu-dma.c
@@ -714,7 +714,7 @@ static void pnv_npu2_release_context(struct kref *kref)
void pnv_npu2_destroy_context(struct npu_context *npu_context,
struct pci_dev *gpdev)
{
- struct pnv_phb *nphb, *phb;
+ struct pnv_phb *nphb;
struct npu *npu;
struct pci_dev *npdev = pnv_pci_get_npu_dev(gpdev, 0);
struct device_node *nvlink_dn;
@@ -728,13 +728,12 @@ void pnv_npu2_destroy_context(struct npu_context *npu_context,
nphb = pci_bus_to_host(npdev->bus)->private_data;
npu = &nphb->npu;
- phb = pci_bus_to_host(gpdev->bus)->private_data;
nvlink_dn = of_parse_phandle(npdev->dev.of_node, "ibm,nvlink", 0);
if (WARN_ON(of_property_read_u32(nvlink_dn, "ibm,npu-link-index",
&nvlink_index)))
return;
npu_context->npdev[npu->index][nvlink_index] = NULL;
- opal_npu_destroy_context(phb->opal_id, npu_context->mm->context.id,
+ opal_npu_destroy_context(nphb->opal_id, npu_context->mm->context.id,
PCI_DEVID(gpdev->bus->number, gpdev->devfn));
kref_put(&npu_context->kref, pnv_npu2_release_context);
}
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index 58243b0d21c0..b558c9e29de3 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -192,9 +192,9 @@ config NR_CPUS
int "Maximum number of CPUs"
depends on SMP
range 2 32 if SPARC32
- range 2 1024 if SPARC64
+ range 2 4096 if SPARC64
default 32 if SPARC32
- default 64 if SPARC64
+ default 4096 if SPARC64
source kernel/Kconfig.hz
@@ -295,9 +295,13 @@ config NUMA
depends on SPARC64 && SMP
config NODES_SHIFT
- int
- default "4"
+ int "Maximum NUMA Nodes (as a power of 2)"
+ range 4 5 if SPARC64
+ default "5"
depends on NEED_MULTIPLE_NODES
+ help
+ Specify the maximum number of NUMA Nodes available on the target
+ system. Increases memory reserved to accommodate various tables.
# Some NUMA nodes have memory ranges that span
# other nodes. Even though a pfn is valid and
diff --git a/arch/sparc/include/asm/mmu_64.h b/arch/sparc/include/asm/mmu_64.h
index f7de0dbc38af..83b36a5371ff 100644
--- a/arch/sparc/include/asm/mmu_64.h
+++ b/arch/sparc/include/asm/mmu_64.h
@@ -52,7 +52,7 @@
#define CTX_NR_MASK TAG_CONTEXT_BITS
#define CTX_HW_MASK (CTX_NR_MASK | CTX_PGSZ_MASK)
-#define CTX_FIRST_VERSION ((_AC(1,UL) << CTX_VERSION_SHIFT) + _AC(1,UL))
+#define CTX_FIRST_VERSION BIT(CTX_VERSION_SHIFT)
#define CTX_VALID(__ctx) \
(!(((__ctx.sparc64_ctx_val) ^ tlb_context_cache) & CTX_VERSION_MASK))
#define CTX_HWBITS(__ctx) ((__ctx.sparc64_ctx_val) & CTX_HW_MASK)
diff --git a/arch/sparc/include/asm/mmu_context_64.h b/arch/sparc/include/asm/mmu_context_64.h
index 22fede6eba11..2cddcda4f85f 100644
--- a/arch/sparc/include/asm/mmu_context_64.h
+++ b/arch/sparc/include/asm/mmu_context_64.h
@@ -19,13 +19,8 @@ extern spinlock_t ctx_alloc_lock;
extern unsigned long tlb_context_cache;
extern unsigned long mmu_context_bmap[];
+DECLARE_PER_CPU(struct mm_struct *, per_cpu_secondary_mm);
void get_new_mmu_context(struct mm_struct *mm);
-#ifdef CONFIG_SMP
-void smp_new_mmu_context_version(void);
-#else
-#define smp_new_mmu_context_version() do { } while (0)
-#endif
-
int init_new_context(struct task_struct *tsk, struct mm_struct *mm);
void destroy_context(struct mm_struct *mm);
@@ -76,8 +71,9 @@ void __flush_tlb_mm(unsigned long, unsigned long);
static inline void switch_mm(struct mm_struct *old_mm, struct mm_struct *mm, struct task_struct *tsk)
{
unsigned long ctx_valid, flags;
- int cpu;
+ int cpu = smp_processor_id();
+ per_cpu(per_cpu_secondary_mm, cpu) = mm;
if (unlikely(mm == &init_mm))
return;
@@ -123,7 +119,6 @@ static inline void switch_mm(struct mm_struct *old_mm, struct mm_struct *mm, str
* for the first time, we must flush that context out of the
* local TLB.
*/
- cpu = smp_processor_id();
if (!ctx_valid || !cpumask_test_cpu(cpu, mm_cpumask(mm))) {
cpumask_set_cpu(cpu, mm_cpumask(mm));
__flush_tlb_mm(CTX_HWBITS(mm->context),
@@ -133,26 +128,7 @@ static inline void switch_mm(struct mm_struct *old_mm, struct mm_struct *mm, str
}
#define deactivate_mm(tsk,mm) do { } while (0)
-
-/* Activate a new MM instance for the current task. */
-static inline void activate_mm(struct mm_struct *active_mm, struct mm_struct *mm)
-{
- unsigned long flags;
- int cpu;
-
- spin_lock_irqsave(&mm->context.lock, flags);
- if (!CTX_VALID(mm->context))
- get_new_mmu_context(mm);
- cpu = smp_processor_id();
- if (!cpumask_test_cpu(cpu, mm_cpumask(mm)))
- cpumask_set_cpu(cpu, mm_cpumask(mm));
-
- load_secondary_context(mm);
- __flush_tlb_mm(CTX_HWBITS(mm->context), SECONDARY_CONTEXT);
- tsb_context_switch(mm);
- spin_unlock_irqrestore(&mm->context.lock, flags);
-}
-
+#define activate_mm(active_mm, mm) switch_mm(active_mm, mm, NULL)
#endif /* !(__ASSEMBLY__) */
#endif /* !(__SPARC64_MMU_CONTEXT_H) */
diff --git a/arch/sparc/include/asm/pil.h b/arch/sparc/include/asm/pil.h
index 266937030546..522b43db2ed3 100644
--- a/arch/sparc/include/asm/pil.h
+++ b/arch/sparc/include/asm/pil.h
@@ -20,7 +20,6 @@
#define PIL_SMP_CALL_FUNC 1
#define PIL_SMP_RECEIVE_SIGNAL 2
#define PIL_SMP_CAPTURE 3
-#define PIL_SMP_CTX_NEW_VERSION 4
#define PIL_DEVICE_IRQ 5
#define PIL_SMP_CALL_FUNC_SNGL 6
#define PIL_DEFERRED_PCR_WORK 7
diff --git a/arch/sparc/include/asm/vio.h b/arch/sparc/include/asm/vio.h
index 8174f6cdbbbb..9dca7a892978 100644
--- a/arch/sparc/include/asm/vio.h
+++ b/arch/sparc/include/asm/vio.h
@@ -327,6 +327,7 @@ struct vio_dev {
int compat_len;
u64 dev_no;
+ u64 id;
unsigned long channel_id;
diff --git a/arch/sparc/kernel/ds.c b/arch/sparc/kernel/ds.c
index b542cc7c8d94..f87265afb175 100644
--- a/arch/sparc/kernel/ds.c
+++ b/arch/sparc/kernel/ds.c
@@ -909,7 +909,7 @@ static int register_services(struct ds_info *dp)
pbuf.req.handle = cp->handle;
pbuf.req.major = 1;
pbuf.req.minor = 0;
- strcpy(pbuf.req.svc_id, cp->service_id);
+ strcpy(pbuf.id_buf, cp->service_id);
err = __ds_send(lp, &pbuf, msg_len);
if (err > 0)
diff --git a/arch/sparc/kernel/irq_64.c b/arch/sparc/kernel/irq_64.c
index 4d0248aa0928..99dd133a029f 100644
--- a/arch/sparc/kernel/irq_64.c
+++ b/arch/sparc/kernel/irq_64.c
@@ -1034,17 +1034,26 @@ static void __init init_cpu_send_mondo_info(struct trap_per_cpu *tb)
{
#ifdef CONFIG_SMP
unsigned long page;
+ void *mondo, *p;
- BUILD_BUG_ON((NR_CPUS * sizeof(u16)) > (PAGE_SIZE - 64));
+ BUILD_BUG_ON((NR_CPUS * sizeof(u16)) > PAGE_SIZE);
+
+ /* Make sure mondo block is 64byte aligned */
+ p = kzalloc(127, GFP_KERNEL);
+ if (!p) {
+ prom_printf("SUN4V: Error, cannot allocate mondo block.\n");
+ prom_halt();
+ }
+ mondo = (void *)(((unsigned long)p + 63) & ~0x3f);
+ tb->cpu_mondo_block_pa = __pa(mondo);
page = get_zeroed_page(GFP_KERNEL);
if (!page) {
- prom_printf("SUN4V: Error, cannot allocate cpu mondo page.\n");
+ prom_printf("SUN4V: Error, cannot allocate cpu list page.\n");
prom_halt();
}
- tb->cpu_mondo_block_pa = __pa(page);
- tb->cpu_list_pa = __pa(page + 64);
+ tb->cpu_list_pa = __pa(page);
#endif
}
diff --git a/arch/sparc/kernel/kernel.h b/arch/sparc/kernel/kernel.h
index c9804551262c..6ae1e77be0bf 100644
--- a/arch/sparc/kernel/kernel.h
+++ b/arch/sparc/kernel/kernel.h
@@ -37,7 +37,6 @@ void handle_stdfmna(struct pt_regs *regs, unsigned long sfar, unsigned long sfsr
/* smp_64.c */
void __irq_entry smp_call_function_client(int irq, struct pt_regs *regs);
void __irq_entry smp_call_function_single_client(int irq, struct pt_regs *regs);
-void __irq_entry smp_new_mmu_context_version_client(int irq, struct pt_regs *regs);
void __irq_entry smp_penguin_jailcell(int irq, struct pt_regs *regs);
void __irq_entry smp_receive_signal_client(int irq, struct pt_regs *regs);
diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c
index b3bc0ac757cc..fdf31040a7dc 100644
--- a/arch/sparc/kernel/smp_64.c
+++ b/arch/sparc/kernel/smp_64.c
@@ -964,37 +964,6 @@ void flush_dcache_page_all(struct mm_struct *mm, struct page *page)
preempt_enable();
}
-void __irq_entry smp_new_mmu_context_version_client(int irq, struct pt_regs *regs)
-{
- struct mm_struct *mm;
- unsigned long flags;
-
- clear_softint(1 << irq);
-
- /* See if we need to allocate a new TLB context because
- * the version of the one we are using is now out of date.
- */
- mm = current->active_mm;
- if (unlikely(!mm || (mm == &init_mm)))
- return;
-
- spin_lock_irqsave(&mm->context.lock, flags);
-
- if (unlikely(!CTX_VALID(mm->context)))
- get_new_mmu_context(mm);
-
- spin_unlock_irqrestore(&mm->context.lock, flags);
-
- load_secondary_context(mm);
- __flush_tlb_mm(CTX_HWBITS(mm->context),
- SECONDARY_CONTEXT);
-}
-
-void smp_new_mmu_context_version(void)
-{
- smp_cross_call(&xcall_new_mmu_context_version, 0, 0, 0);
-}
-
#ifdef CONFIG_KGDB
void kgdb_roundup_cpus(unsigned long flags)
{
diff --git a/arch/sparc/kernel/tsb.S b/arch/sparc/kernel/tsb.S
index 10689cfd0ad4..07c0df924960 100644
--- a/arch/sparc/kernel/tsb.S
+++ b/arch/sparc/kernel/tsb.S
@@ -455,13 +455,16 @@ __tsb_context_switch:
.type copy_tsb,#function
copy_tsb: /* %o0=old_tsb_base, %o1=old_tsb_size
* %o2=new_tsb_base, %o3=new_tsb_size
+ * %o4=page_size_shift
*/
sethi %uhi(TSB_PASS_BITS), %g7
srlx %o3, 4, %o3
- add %o0, %o1, %g1 /* end of old tsb */
+ add %o0, %o1, %o1 /* end of old tsb */
sllx %g7, 32, %g7
sub %o3, 1, %o3 /* %o3 == new tsb hash mask */
+ mov %o4, %g1 /* page_size_shift */
+
661: prefetcha [%o0] ASI_N, #one_read
.section .tsb_phys_patch, "ax"
.word 661b
@@ -486,9 +489,9 @@ copy_tsb: /* %o0=old_tsb_base, %o1=old_tsb_size
/* This can definitely be computed faster... */
srlx %o0, 4, %o5 /* Build index */
and %o5, 511, %o5 /* Mask index */
- sllx %o5, PAGE_SHIFT, %o5 /* Put into vaddr position */
+ sllx %o5, %g1, %o5 /* Put into vaddr position */
or %o4, %o5, %o4 /* Full VADDR. */
- srlx %o4, PAGE_SHIFT, %o4 /* Shift down to create index */
+ srlx %o4, %g1, %o4 /* Shift down to create index */
and %o4, %o3, %o4 /* Mask with new_tsb_nents-1 */
sllx %o4, 4, %o4 /* Shift back up into tsb ent offset */
TSB_STORE(%o2 + %o4, %g2) /* Store TAG */
@@ -496,7 +499,7 @@ copy_tsb: /* %o0=old_tsb_base, %o1=old_tsb_size
TSB_STORE(%o2 + %o4, %g3) /* Store TTE */
80: add %o0, 16, %o0
- cmp %o0, %g1
+ cmp %o0, %o1
bne,pt %xcc, 90b
nop
diff --git a/arch/sparc/kernel/ttable_64.S b/arch/sparc/kernel/ttable_64.S
index 7bd8f6556352..efe93ab4a9c0 100644
--- a/arch/sparc/kernel/ttable_64.S
+++ b/arch/sparc/kernel/ttable_64.S
@@ -50,7 +50,7 @@ tl0_resv03e: BTRAP(0x3e) BTRAP(0x3f) BTRAP(0x40)
tl0_irq1: TRAP_IRQ(smp_call_function_client, 1)
tl0_irq2: TRAP_IRQ(smp_receive_signal_client, 2)
tl0_irq3: TRAP_IRQ(smp_penguin_jailcell, 3)
-tl0_irq4: TRAP_IRQ(smp_new_mmu_context_version_client, 4)
+tl0_irq4: BTRAP(0x44)
#else
tl0_irq1: BTRAP(0x41)
tl0_irq2: BTRAP(0x42)
diff --git a/arch/sparc/kernel/vio.c b/arch/sparc/kernel/vio.c
index f6bb857254fc..075d38980dee 100644
--- a/arch/sparc/kernel/vio.c
+++ b/arch/sparc/kernel/vio.c
@@ -302,13 +302,16 @@ static struct vio_dev *vio_create_one(struct mdesc_handle *hp, u64 mp,
if (!id) {
dev_set_name(&vdev->dev, "%s", bus_id_name);
vdev->dev_no = ~(u64)0;
+ vdev->id = ~(u64)0;
} else if (!cfg_handle) {
dev_set_name(&vdev->dev, "%s-%llu", bus_id_name, *id);
vdev->dev_no = *id;
+ vdev->id = ~(u64)0;
} else {
dev_set_name(&vdev->dev, "%s-%llu-%llu", bus_id_name,
*cfg_handle, *id);
vdev->dev_no = *cfg_handle;
+ vdev->id = *id;
}
vdev->dev.parent = parent;
@@ -351,27 +354,84 @@ static void vio_add(struct mdesc_handle *hp, u64 node)
(void) vio_create_one(hp, node, &root_vdev->dev);
}
+struct vio_md_node_query {
+ const char *type;
+ u64 dev_no;
+ u64 id;
+};
+
static int vio_md_node_match(struct device *dev, void *arg)
{
+ struct vio_md_node_query *query = (struct vio_md_node_query *) arg;
struct vio_dev *vdev = to_vio_dev(dev);
- if (vdev->mp == (u64) arg)
- return 1;
+ if (vdev->dev_no != query->dev_no)
+ return 0;
+ if (vdev->id != query->id)
+ return 0;
+ if (strcmp(vdev->type, query->type))
+ return 0;
- return 0;
+ return 1;
}
static void vio_remove(struct mdesc_handle *hp, u64 node)
{
+ const char *type;
+ const u64 *id, *cfg_handle;
+ u64 a;
+ struct vio_md_node_query query;
struct device *dev;
- dev = device_find_child(&root_vdev->dev, (void *) node,
+ type = mdesc_get_property(hp, node, "device-type", NULL);
+ if (!type) {
+ type = mdesc_get_property(hp, node, "name", NULL);
+ if (!type)
+ type = mdesc_node_name(hp, node);
+ }
+
+ query.type = type;
+
+ id = mdesc_get_property(hp, node, "id", NULL);
+ cfg_handle = NULL;
+ mdesc_for_each_arc(a, hp, node, MDESC_ARC_TYPE_BACK) {
+ u64 target;
+
+ target = mdesc_arc_target(hp, a);
+ cfg_handle = mdesc_get_property(hp, target,
+ "cfg-handle", NULL);
+ if (cfg_handle)
+ break;
+ }
+
+ if (!id) {
+ query.dev_no = ~(u64)0;
+ query.id = ~(u64)0;
+ } else if (!cfg_handle) {
+ query.dev_no = *id;
+ query.id = ~(u64)0;
+ } else {
+ query.dev_no = *cfg_handle;
+ query.id = *id;
+ }
+
+ dev = device_find_child(&root_vdev->dev, &query,
vio_md_node_match);
if (dev) {
printk(KERN_INFO "VIO: Removing device %s\n", dev_name(dev));
device_unregister(dev);
put_device(dev);
+ } else {
+ if (!id)
+ printk(KERN_ERR "VIO: Removed unknown %s node.\n",
+ type);
+ else if (!cfg_handle)
+ printk(KERN_ERR "VIO: Removed unknown %s node %llu.\n",
+ type, *id);
+ else
+ printk(KERN_ERR "VIO: Removed unknown %s node %llu-%llu.\n",
+ type, *cfg_handle, *id);
}
}
diff --git a/arch/sparc/lib/Makefile b/arch/sparc/lib/Makefile
index 69912d2f8b54..07c03e72d812 100644
--- a/arch/sparc/lib/Makefile
+++ b/arch/sparc/lib/Makefile
@@ -15,6 +15,7 @@ lib-$(CONFIG_SPARC32) += copy_user.o locks.o
lib-$(CONFIG_SPARC64) += atomic_64.o
lib-$(CONFIG_SPARC32) += lshrdi3.o ashldi3.o
lib-$(CONFIG_SPARC32) += muldi3.o bitext.o cmpdi2.o
+lib-$(CONFIG_SPARC64) += multi3.o
lib-$(CONFIG_SPARC64) += copy_page.o clear_page.o bzero.o
lib-$(CONFIG_SPARC64) += csum_copy.o csum_copy_from_user.o csum_copy_to_user.o
diff --git a/arch/sparc/lib/multi3.S b/arch/sparc/lib/multi3.S
new file mode 100644
index 000000000000..d6b6c97fe3c7
--- /dev/null
+++ b/arch/sparc/lib/multi3.S
@@ -0,0 +1,35 @@
+#include <linux/linkage.h>
+#include <asm/export.h>
+
+ .text
+ .align 4
+ENTRY(__multi3) /* %o0 = u, %o1 = v */
+ mov %o1, %g1
+ srl %o3, 0, %g4
+ mulx %g4, %g1, %o1
+ srlx %g1, 0x20, %g3
+ mulx %g3, %g4, %g5
+ sllx %g5, 0x20, %o5
+ srl %g1, 0, %g4
+ sub %o1, %o5, %o5
+ srlx %o5, 0x20, %o5
+ addcc %g5, %o5, %g5
+ srlx %o3, 0x20, %o5
+ mulx %g4, %o5, %g4
+ mulx %g3, %o5, %o5
+ sethi %hi(0x80000000), %g3
+ addcc %g5, %g4, %g5
+ srlx %g5, 0x20, %g5
+ add %g3, %g3, %g3
+ movcc %xcc, %g0, %g3
+ addcc %o5, %g5, %o5
+ sllx %g4, 0x20, %g4
+ add %o1, %g4, %o1
+ add %o5, %g3, %g2
+ mulx %g1, %o2, %g1
+ add %g1, %g2, %g1
+ mulx %o0, %o3, %o0
+ retl
+ add %g1, %o0, %o0
+ENDPROC(__multi3)
+EXPORT_SYMBOL(__multi3)
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index 0cda653ae007..3c40ebd50f92 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -358,7 +358,8 @@ static int __init setup_hugepagesz(char *string)
}
if ((hv_pgsz_mask & cpu_pgsz_mask) == 0U) {
- pr_warn("hugepagesz=%llu not supported by MMU.\n",
+ hugetlb_bad_size();
+ pr_err("hugepagesz=%llu not supported by MMU.\n",
hugepage_size);
goto out;
}
@@ -706,10 +707,58 @@ EXPORT_SYMBOL(__flush_dcache_range);
/* get_new_mmu_context() uses "cache + 1". */
DEFINE_SPINLOCK(ctx_alloc_lock);
-unsigned long tlb_context_cache = CTX_FIRST_VERSION - 1;
+unsigned long tlb_context_cache = CTX_FIRST_VERSION;
#define MAX_CTX_NR (1UL << CTX_NR_BITS)
#define CTX_BMAP_SLOTS BITS_TO_LONGS(MAX_CTX_NR)
DECLARE_BITMAP(mmu_context_bmap, MAX_CTX_NR);
+DEFINE_PER_CPU(struct mm_struct *, per_cpu_secondary_mm) = {0};
+
+static void mmu_context_wrap(void)
+{
+ unsigned long old_ver = tlb_context_cache & CTX_VERSION_MASK;
+ unsigned long new_ver, new_ctx, old_ctx;
+ struct mm_struct *mm;
+ int cpu;
+
+ bitmap_zero(mmu_context_bmap, 1 << CTX_NR_BITS);
+
+ /* Reserve kernel context */
+ set_bit(0, mmu_context_bmap);
+
+ new_ver = (tlb_context_cache & CTX_VERSION_MASK) + CTX_FIRST_VERSION;
+ if (unlikely(new_ver == 0))
+ new_ver = CTX_FIRST_VERSION;
+ tlb_context_cache = new_ver;
+
+ /*
+ * Make sure that any new mm that are added into per_cpu_secondary_mm,
+ * are going to go through get_new_mmu_context() path.
+ */
+ mb();
+
+ /*
+ * Updated versions to current on those CPUs that had valid secondary
+ * contexts
+ */
+ for_each_online_cpu(cpu) {
+ /*
+ * If a new mm is stored after we took this mm from the array,
+ * it will go into get_new_mmu_context() path, because we
+ * already bumped the version in tlb_context_cache.
+ */
+ mm = per_cpu(per_cpu_secondary_mm, cpu);
+
+ if (unlikely(!mm || mm == &init_mm))
+ continue;
+
+ old_ctx = mm->context.sparc64_ctx_val;
+ if (likely((old_ctx & CTX_VERSION_MASK) == old_ver)) {
+ new_ctx = (old_ctx & ~CTX_VERSION_MASK) | new_ver;
+ set_bit(new_ctx & CTX_NR_MASK, mmu_context_bmap);
+ mm->context.sparc64_ctx_val = new_ctx;
+ }
+ }
+}
/* Caller does TLB context flushing on local CPU if necessary.
* The caller also ensures that CTX_VALID(mm->context) is false.
@@ -725,48 +774,30 @@ void get_new_mmu_context(struct mm_struct *mm)
{
unsigned long ctx, new_ctx;
unsigned long orig_pgsz_bits;
- int new_version;
spin_lock(&ctx_alloc_lock);
+retry:
+ /* wrap might have happened, test again if our context became valid */
+ if (unlikely(CTX_VALID(mm->context)))
+ goto out;
orig_pgsz_bits = (mm->context.sparc64_ctx_val & CTX_PGSZ_MASK);
ctx = (tlb_context_cache + 1) & CTX_NR_MASK;
new_ctx = find_next_zero_bit(mmu_context_bmap, 1 << CTX_NR_BITS, ctx);
- new_version = 0;
if (new_ctx >= (1 << CTX_NR_BITS)) {
new_ctx = find_next_zero_bit(mmu_context_bmap, ctx, 1);
if (new_ctx >= ctx) {
- int i;
- new_ctx = (tlb_context_cache & CTX_VERSION_MASK) +
- CTX_FIRST_VERSION;
- if (new_ctx == 1)
- new_ctx = CTX_FIRST_VERSION;
-
- /* Don't call memset, for 16 entries that's just
- * plain silly...
- */
- mmu_context_bmap[0] = 3;
- mmu_context_bmap[1] = 0;
- mmu_context_bmap[2] = 0;
- mmu_context_bmap[3] = 0;
- for (i = 4; i < CTX_BMAP_SLOTS; i += 4) {
- mmu_context_bmap[i + 0] = 0;
- mmu_context_bmap[i + 1] = 0;
- mmu_context_bmap[i + 2] = 0;
- mmu_context_bmap[i + 3] = 0;
- }
- new_version = 1;
- goto out;
+ mmu_context_wrap();
+ goto retry;
}
}
+ if (mm->context.sparc64_ctx_val)
+ cpumask_clear(mm_cpumask(mm));
mmu_context_bmap[new_ctx>>6] |= (1UL << (new_ctx & 63));
new_ctx |= (tlb_context_cache & CTX_VERSION_MASK);
-out:
tlb_context_cache = new_ctx;
mm->context.sparc64_ctx_val = new_ctx | orig_pgsz_bits;
+out:
spin_unlock(&ctx_alloc_lock);
-
- if (unlikely(new_version))
- smp_new_mmu_context_version();
}
static int numa_enabled = 1;
diff --git a/arch/sparc/mm/tsb.c b/arch/sparc/mm/tsb.c
index bedf08b22a47..0d4b998c7d7b 100644
--- a/arch/sparc/mm/tsb.c
+++ b/arch/sparc/mm/tsb.c
@@ -496,7 +496,8 @@ retry_tsb_alloc:
extern void copy_tsb(unsigned long old_tsb_base,
unsigned long old_tsb_size,
unsigned long new_tsb_base,
- unsigned long new_tsb_size);
+ unsigned long new_tsb_size,
+ unsigned long page_size_shift);
unsigned long old_tsb_base = (unsigned long) old_tsb;
unsigned long new_tsb_base = (unsigned long) new_tsb;
@@ -504,7 +505,9 @@ retry_tsb_alloc:
old_tsb_base = __pa(old_tsb_base);
new_tsb_base = __pa(new_tsb_base);
}
- copy_tsb(old_tsb_base, old_size, new_tsb_base, new_size);
+ copy_tsb(old_tsb_base, old_size, new_tsb_base, new_size,
+ tsb_index == MM_TSB_BASE ?
+ PAGE_SHIFT : REAL_HPAGE_SHIFT);
}
mm->context.tsb_block[tsb_index].tsb = new_tsb;
diff --git a/arch/sparc/mm/ultra.S b/arch/sparc/mm/ultra.S
index 5d2fd6cd3189..fcf4d27a38fb 100644
--- a/arch/sparc/mm/ultra.S
+++ b/arch/sparc/mm/ultra.S
@@ -971,11 +971,6 @@ xcall_capture:
wr %g0, (1 << PIL_SMP_CAPTURE), %set_softint
retry
- .globl xcall_new_mmu_context_version
-xcall_new_mmu_context_version:
- wr %g0, (1 << PIL_SMP_CTX_NEW_VERSION), %set_softint
- retry
-
#ifdef CONFIG_KGDB
.globl xcall_kgdb_capture
xcall_kgdb_capture:
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index cd18994a9555..4ccfacc7232a 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -360,7 +360,7 @@ config SMP
Management" code will be disabled if you say Y here.
See also <file:Documentation/x86/i386/IO-APIC.txt>,
- <file:Documentation/nmi_watchdog.txt> and the SMP-HOWTO available at
+ <file:Documentation/lockup-watchdogs.txt> and the SMP-HOWTO available at
<http://www.tldp.org/docs.html#howto>.
If you don't know what to do here, say N.
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 5851411e60fb..bf240b920473 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -159,7 +159,7 @@ ifdef CONFIG_FUNCTION_GRAPH_TRACER
# If '-Os' is enabled, disable it and print a warning.
ifdef CONFIG_CC_OPTIMIZE_FOR_SIZE
undefine CONFIG_CC_OPTIMIZE_FOR_SIZE
- $(warning Disabling CONFIG_CC_OPTIMIZE_FOR_SIZE. Your compiler does not have -mfentry so you cannot optimize for size with CONFIG_FUNCTION_GRAPH_TRACER.)
+ $(warning Disabling CONFIG_CC_OPTIMIZE_FOR_SIZE. Your compiler does not have -mfentry so you cannot optimize for size with CONFIG_FUNCTION_GRAPH_TRACER.)
endif
endif
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index 44163e8c3868..2c860ad4fe06 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -94,7 +94,7 @@ vmlinux-objs-$(CONFIG_EFI_MIXED) += $(obj)/efi_thunk_$(BITS).o
quiet_cmd_check_data_rel = DATAREL $@
define cmd_check_data_rel
for obj in $(filter %.o,$^); do \
- readelf -S $$obj | grep -qF .rel.local && { \
+ ${CROSS_COMPILE}readelf -S $$obj | grep -qF .rel.local && { \
echo "error: $$obj has data relocations!" >&2; \
exit 1; \
} || true; \
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index 50bc26949e9e..48ef7bb32c42 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -252,6 +252,23 @@ ENTRY(__switch_to_asm)
END(__switch_to_asm)
/*
+ * The unwinder expects the last frame on the stack to always be at the same
+ * offset from the end of the page, which allows it to validate the stack.
+ * Calling schedule_tail() directly would break that convention because its an
+ * asmlinkage function so its argument has to be pushed on the stack. This
+ * wrapper creates a proper "end of stack" frame header before the call.
+ */
+ENTRY(schedule_tail_wrapper)
+ FRAME_BEGIN
+
+ pushl %eax
+ call schedule_tail
+ popl %eax
+
+ FRAME_END
+ ret
+ENDPROC(schedule_tail_wrapper)
+/*
* A newly forked process directly context switches into this address.
*
* eax: prev task we switched from
@@ -259,24 +276,15 @@ END(__switch_to_asm)
* edi: kernel thread arg
*/
ENTRY(ret_from_fork)
- FRAME_BEGIN /* help unwinder find end of stack */
-
- /*
- * schedule_tail() is asmlinkage so we have to put its 'prev' argument
- * on the stack.
- */
- pushl %eax
- call schedule_tail
- popl %eax
+ call schedule_tail_wrapper
testl %ebx, %ebx
jnz 1f /* kernel threads are uncommon */
2:
/* When we fork, we trace the syscall return in the child, too. */
- leal FRAME_OFFSET(%esp), %eax
+ movl %esp, %eax
call syscall_return_slowpath
- FRAME_END
jmp restore_all
/* kernel thread */
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 607d72c4a485..4a4c0834f965 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -36,7 +36,6 @@
#include <asm/smap.h>
#include <asm/pgtable_types.h>
#include <asm/export.h>
-#include <asm/frame.h>
#include <linux/err.h>
.code64
@@ -406,19 +405,17 @@ END(__switch_to_asm)
* r12: kernel thread arg
*/
ENTRY(ret_from_fork)
- FRAME_BEGIN /* help unwinder find end of stack */
movq %rax, %rdi
- call schedule_tail /* rdi: 'prev' task parameter */
+ call schedule_tail /* rdi: 'prev' task parameter */
- testq %rbx, %rbx /* from kernel_thread? */
- jnz 1f /* kernel threads are uncommon */
+ testq %rbx, %rbx /* from kernel_thread? */
+ jnz 1f /* kernel threads are uncommon */
2:
- leaq FRAME_OFFSET(%rsp),%rdi /* pt_regs pointer */
+ movq %rsp, %rdi
call syscall_return_slowpath /* returns with IRQs disabled */
TRACE_IRQS_ON /* user mode is traced as IRQS on */
SWAPGS
- FRAME_END
jmp restore_regs_and_iret
1:
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index 4fd5195deed0..3f9a3d2a5209 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -266,6 +266,7 @@ static inline int umc_normaddr_to_sysaddr(u64 norm_addr, u16 nid, u8 umc, u64 *s
#endif
int mce_available(struct cpuinfo_x86 *c);
+bool mce_is_memory_error(struct mce *m);
DECLARE_PER_CPU(unsigned, mce_exception_count);
DECLARE_PER_CPU(unsigned, mce_poll_count);
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index c5b8f760473c..32e14d137416 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -409,8 +409,13 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start,
memcpy(insnbuf, replacement, a->replacementlen);
insnbuf_sz = a->replacementlen;
- /* 0xe8 is a relative jump; fix the offset. */
- if (*insnbuf == 0xe8 && a->replacementlen == 5) {
+ /*
+ * 0xe8 is a relative jump; fix the offset.
+ *
+ * Instruction length is checked before the opcode to avoid
+ * accessing uninitialized bytes for zero-length replacements.
+ */
+ if (a->replacementlen == 5 && *insnbuf == 0xe8) {
*(s32 *)(insnbuf + 1) += replacement - instr;
DPRINTK("Fix CALL offset: 0x%x, CALL 0x%lx",
*(s32 *)(insnbuf + 1),
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 5abd4bf73d6e..5cfbaeb6529a 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -499,16 +499,14 @@ static int mce_usable_address(struct mce *m)
return 1;
}
-static bool memory_error(struct mce *m)
+bool mce_is_memory_error(struct mce *m)
{
- struct cpuinfo_x86 *c = &boot_cpu_data;
-
- if (c->x86_vendor == X86_VENDOR_AMD) {
+ if (m->cpuvendor == X86_VENDOR_AMD) {
/* ErrCodeExt[20:16] */
u8 xec = (m->status >> 16) & 0x1f;
return (xec == 0x0 || xec == 0x8);
- } else if (c->x86_vendor == X86_VENDOR_INTEL) {
+ } else if (m->cpuvendor == X86_VENDOR_INTEL) {
/*
* Intel SDM Volume 3B - 15.9.2 Compound Error Codes
*
@@ -529,6 +527,7 @@ static bool memory_error(struct mce *m)
return false;
}
+EXPORT_SYMBOL_GPL(mce_is_memory_error);
static bool cec_add_mce(struct mce *m)
{
@@ -536,7 +535,7 @@ static bool cec_add_mce(struct mce *m)
return false;
/* We eat only correctable DRAM errors with usable addresses. */
- if (memory_error(m) &&
+ if (mce_is_memory_error(m) &&
!(m->status & MCI_STATUS_UC) &&
mce_usable_address(m))
if (!cec_add_elem(m->addr >> PAGE_SHIFT))
@@ -713,7 +712,7 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
severity = mce_severity(&m, mca_cfg.tolerant, NULL, false);
- if (severity == MCE_DEFERRED_SEVERITY && memory_error(&m))
+ if (severity == MCE_DEFERRED_SEVERITY && mce_is_memory_error(&m))
if (m.status & MCI_STATUS_ADDRV)
m.severity = severity;
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index 45db4d2ebd01..e9f4d762aa5b 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -320,7 +320,7 @@ void load_ucode_amd_ap(unsigned int cpuid_1_eax)
}
static enum ucode_state
-load_microcode_amd(int cpu, u8 family, const u8 *data, size_t size);
+load_microcode_amd(bool save, u8 family, const u8 *data, size_t size);
int __init save_microcode_in_initrd_amd(unsigned int cpuid_1_eax)
{
@@ -338,8 +338,7 @@ int __init save_microcode_in_initrd_amd(unsigned int cpuid_1_eax)
if (!desc.mc)
return -EINVAL;
- ret = load_microcode_amd(smp_processor_id(), x86_family(cpuid_1_eax),
- desc.data, desc.size);
+ ret = load_microcode_amd(true, x86_family(cpuid_1_eax), desc.data, desc.size);
if (ret != UCODE_OK)
return -EINVAL;
@@ -675,7 +674,7 @@ static enum ucode_state __load_microcode_amd(u8 family, const u8 *data,
}
static enum ucode_state
-load_microcode_amd(int cpu, u8 family, const u8 *data, size_t size)
+load_microcode_amd(bool save, u8 family, const u8 *data, size_t size)
{
enum ucode_state ret;
@@ -689,8 +688,8 @@ load_microcode_amd(int cpu, u8 family, const u8 *data, size_t size)
#ifdef CONFIG_X86_32
/* save BSP's matching patch for early load */
- if (cpu_data(cpu).cpu_index == boot_cpu_data.cpu_index) {
- struct ucode_patch *p = find_patch(cpu);
+ if (save) {
+ struct ucode_patch *p = find_patch(0);
if (p) {
memset(amd_ucode_patch, 0, PATCH_MAX_SIZE);
memcpy(amd_ucode_patch, p->data, min_t(u32, ksize(p->data),
@@ -722,11 +721,12 @@ static enum ucode_state request_microcode_amd(int cpu, struct device *device,
{
char fw_name[36] = "amd-ucode/microcode_amd.bin";
struct cpuinfo_x86 *c = &cpu_data(cpu);
+ bool bsp = c->cpu_index == boot_cpu_data.cpu_index;
enum ucode_state ret = UCODE_NFOUND;
const struct firmware *fw;
/* reload ucode container only on the boot cpu */
- if (!refresh_fw || c->cpu_index != boot_cpu_data.cpu_index)
+ if (!refresh_fw || !bsp)
return UCODE_OK;
if (c->x86 >= 0x15)
@@ -743,7 +743,7 @@ static enum ucode_state request_microcode_amd(int cpu, struct device *device,
goto fw_release;
}
- ret = load_microcode_amd(cpu, c->x86, fw->data, fw->size);
+ ret = load_microcode_amd(bsp, c->x86, fw->data, fw->size);
fw_release:
release_firmware(fw);
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 0651e974dcb3..9bef1bbeba63 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -689,8 +689,12 @@ static inline void *alloc_tramp(unsigned long size)
{
return module_alloc(size);
}
-static inline void tramp_free(void *tramp)
+static inline void tramp_free(void *tramp, int size)
{
+ int npages = PAGE_ALIGN(size) >> PAGE_SHIFT;
+
+ set_memory_nx((unsigned long)tramp, npages);
+ set_memory_rw((unsigned long)tramp, npages);
module_memfree(tramp);
}
#else
@@ -699,7 +703,7 @@ static inline void *alloc_tramp(unsigned long size)
{
return NULL;
}
-static inline void tramp_free(void *tramp) { }
+static inline void tramp_free(void *tramp, int size) { }
#endif
/* Defined as markers to the end of the ftrace default trampolines */
@@ -771,7 +775,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
/* Copy ftrace_caller onto the trampoline memory */
ret = probe_kernel_read(trampoline, (void *)start_offset, size);
if (WARN_ON(ret < 0)) {
- tramp_free(trampoline);
+ tramp_free(trampoline, *tramp_size);
return 0;
}
@@ -797,7 +801,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
/* Are we pointing to the reference? */
if (WARN_ON(memcmp(op_ptr.op, op_ref, 3) != 0)) {
- tramp_free(trampoline);
+ tramp_free(trampoline, *tramp_size);
return 0;
}
@@ -839,7 +843,7 @@ void arch_ftrace_update_trampoline(struct ftrace_ops *ops)
unsigned long offset;
unsigned long ip;
unsigned int size;
- int ret;
+ int ret, npages;
if (ops->trampoline) {
/*
@@ -848,11 +852,14 @@ void arch_ftrace_update_trampoline(struct ftrace_ops *ops)
*/
if (!(ops->flags & FTRACE_OPS_FL_ALLOC_TRAMP))
return;
+ npages = PAGE_ALIGN(ops->trampoline_size) >> PAGE_SHIFT;
+ set_memory_rw(ops->trampoline, npages);
} else {
ops->trampoline = create_trampoline(ops, &size);
if (!ops->trampoline)
return;
ops->trampoline_size = size;
+ npages = PAGE_ALIGN(size) >> PAGE_SHIFT;
}
offset = calc_trampoline_call_offset(ops->flags & FTRACE_OPS_FL_SAVE_REGS);
@@ -863,6 +870,7 @@ void arch_ftrace_update_trampoline(struct ftrace_ops *ops)
/* Do a safe modify in case the trampoline is executing */
new = ftrace_call_replace(ip, (unsigned long)func);
ret = update_ftrace_func(ip, new);
+ set_memory_ro(ops->trampoline, npages);
/* The update should never fail */
WARN_ON(ret);
@@ -939,7 +947,7 @@ void arch_ftrace_trampoline_free(struct ftrace_ops *ops)
if (!ops || !(ops->flags & FTRACE_OPS_FL_ALLOC_TRAMP))
return;
- tramp_free((void *)ops->trampoline);
+ tramp_free((void *)ops->trampoline, ops->trampoline_size);
ops->trampoline = 0;
}
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 5b2bbfbb3712..6b877807598b 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -52,6 +52,7 @@
#include <linux/ftrace.h>
#include <linux/frame.h>
#include <linux/kasan.h>
+#include <linux/moduleloader.h>
#include <asm/text-patching.h>
#include <asm/cacheflush.h>
@@ -417,6 +418,14 @@ static void prepare_boost(struct kprobe *p, struct insn *insn)
}
}
+/* Recover page to RW mode before releasing it */
+void free_insn_page(void *page)
+{
+ set_memory_nx((unsigned long)page & PAGE_MASK, 1);
+ set_memory_rw((unsigned long)page & PAGE_MASK, 1);
+ module_memfree(page);
+}
+
static int arch_copy_kprobe(struct kprobe *p)
{
struct insn insn;
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index ff40e74c9181..ffeae818aa7a 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -78,7 +78,7 @@ void __show_regs(struct pt_regs *regs, int all)
printk(KERN_DEFAULT "EIP: %pS\n", (void *)regs->ip);
printk(KERN_DEFAULT "EFLAGS: %08lx CPU: %d\n", regs->flags,
- smp_processor_id());
+ raw_smp_processor_id());
printk(KERN_DEFAULT "EAX: %08lx EBX: %08lx ECX: %08lx EDX: %08lx\n",
regs->ax, regs->bx, regs->cx, regs->dx);
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 0b4d3c686b1e..f81823695014 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -980,8 +980,6 @@ void __init setup_arch(char **cmdline_p)
*/
x86_configure_nx();
- simple_udelay_calibration();
-
parse_early_param();
#ifdef CONFIG_MEMORY_HOTPLUG
@@ -1041,6 +1039,8 @@ void __init setup_arch(char **cmdline_p)
*/
init_hypervisor_platform();
+ simple_udelay_calibration();
+
x86_init.resources.probe_roms();
/* after parse_early_param, so could debug it */
diff --git a/arch/x86/kernel/unwind_frame.c b/arch/x86/kernel/unwind_frame.c
index 82c6d7f1fd73..b9389d72b2f7 100644
--- a/arch/x86/kernel/unwind_frame.c
+++ b/arch/x86/kernel/unwind_frame.c
@@ -104,6 +104,11 @@ static inline unsigned long *last_frame(struct unwind_state *state)
return (unsigned long *)task_pt_regs(state->task) - 2;
}
+static bool is_last_frame(struct unwind_state *state)
+{
+ return state->bp == last_frame(state);
+}
+
#ifdef CONFIG_X86_32
#define GCC_REALIGN_WORDS 3
#else
@@ -115,16 +120,15 @@ static inline unsigned long *last_aligned_frame(struct unwind_state *state)
return last_frame(state) - GCC_REALIGN_WORDS;
}
-static bool is_last_task_frame(struct unwind_state *state)
+static bool is_last_aligned_frame(struct unwind_state *state)
{
unsigned long *last_bp = last_frame(state);
unsigned long *aligned_bp = last_aligned_frame(state);
/*
- * We have to check for the last task frame at two different locations
- * because gcc can occasionally decide to realign the stack pointer and
- * change the offset of the stack frame in the prologue of a function
- * called by head/entry code. Examples:
+ * GCC can occasionally decide to realign the stack pointer and change
+ * the offset of the stack frame in the prologue of a function called
+ * by head/entry code. Examples:
*
* <start_secondary>:
* push %edi
@@ -141,11 +145,38 @@ static bool is_last_task_frame(struct unwind_state *state)
* push %rbp
* mov %rsp,%rbp
*
- * Note that after aligning the stack, it pushes a duplicate copy of
- * the return address before pushing the frame pointer.
+ * After aligning the stack, it pushes a duplicate copy of the return
+ * address before pushing the frame pointer.
+ */
+ return (state->bp == aligned_bp && *(aligned_bp + 1) == *(last_bp + 1));
+}
+
+static bool is_last_ftrace_frame(struct unwind_state *state)
+{
+ unsigned long *last_bp = last_frame(state);
+ unsigned long *last_ftrace_bp = last_bp - 3;
+
+ /*
+ * When unwinding from an ftrace handler of a function called by entry
+ * code, the stack layout of the last frame is:
+ *
+ * bp
+ * parent ret addr
+ * bp
+ * function ret addr
+ * parent ret addr
+ * pt_regs
+ * -----------------
*/
- return (state->bp == last_bp ||
- (state->bp == aligned_bp && *(aligned_bp+1) == *(last_bp+1)));
+ return (state->bp == last_ftrace_bp &&
+ *state->bp == *(state->bp + 2) &&
+ *(state->bp + 1) == *(state->bp + 4));
+}
+
+static bool is_last_task_frame(struct unwind_state *state)
+{
+ return is_last_frame(state) || is_last_aligned_frame(state) ||
+ is_last_ftrace_frame(state);
}
/*
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index c329d2894905..d24c8742d9b0 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1495,8 +1495,10 @@ EXPORT_SYMBOL_GPL(kvm_lapic_hv_timer_in_use);
static void cancel_hv_timer(struct kvm_lapic *apic)
{
+ preempt_disable();
kvm_x86_ops->cancel_hv_timer(apic->vcpu);
apic->lapic_timer.hv_timer_in_use = false;
+ preempt_enable();
}
static bool start_hv_timer(struct kvm_lapic *apic)
@@ -1934,7 +1936,8 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event)
for (i = 0; i < KVM_APIC_LVT_NUM; i++)
kvm_lapic_set_reg(apic, APIC_LVTT + 0x10 * i, APIC_LVT_MASKED);
apic_update_lvtt(apic);
- if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_LINT0_REENABLED))
+ if (kvm_vcpu_is_reset_bsp(vcpu) &&
+ kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_LINT0_REENABLED))
kvm_lapic_set_reg(apic, APIC_LVT0,
SET_APIC_DELIVERY_MODE(0, APIC_MODE_EXTINT));
apic_manage_nmi_watchdog(apic, kvm_lapic_get_reg(apic, APIC_LVT0));
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 183ddb235fb4..ba9891ac5c56 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -1807,7 +1807,7 @@ static void svm_get_segment(struct kvm_vcpu *vcpu,
* AMD's VMCB does not have an explicit unusable field, so emulate it
* for cross vendor migration purposes by "not present"
*/
- var->unusable = !var->present || (var->type == 0);
+ var->unusable = !var->present;
switch (seg) {
case VCPU_SREG_TR:
@@ -1840,6 +1840,7 @@ static void svm_get_segment(struct kvm_vcpu *vcpu,
*/
if (var->unusable)
var->db = 0;
+ /* This is symmetric with svm_set_segment() */
var->dpl = to_svm(vcpu)->vmcb->save.cpl;
break;
}
@@ -1980,18 +1981,14 @@ static void svm_set_segment(struct kvm_vcpu *vcpu,
s->base = var->base;
s->limit = var->limit;
s->selector = var->selector;
- if (var->unusable)
- s->attrib = 0;
- else {
- s->attrib = (var->type & SVM_SELECTOR_TYPE_MASK);
- s->attrib |= (var->s & 1) << SVM_SELECTOR_S_SHIFT;
- s->attrib |= (var->dpl & 3) << SVM_SELECTOR_DPL_SHIFT;
- s->attrib |= (var->present & 1) << SVM_SELECTOR_P_SHIFT;
- s->attrib |= (var->avl & 1) << SVM_SELECTOR_AVL_SHIFT;
- s->attrib |= (var->l & 1) << SVM_SELECTOR_L_SHIFT;
- s->attrib |= (var->db & 1) << SVM_SELECTOR_DB_SHIFT;
- s->attrib |= (var->g & 1) << SVM_SELECTOR_G_SHIFT;
- }
+ s->attrib = (var->type & SVM_SELECTOR_TYPE_MASK);
+ s->attrib |= (var->s & 1) << SVM_SELECTOR_S_SHIFT;
+ s->attrib |= (var->dpl & 3) << SVM_SELECTOR_DPL_SHIFT;
+ s->attrib |= ((var->present & 1) && !var->unusable) << SVM_SELECTOR_P_SHIFT;
+ s->attrib |= (var->avl & 1) << SVM_SELECTOR_AVL_SHIFT;
+ s->attrib |= (var->l & 1) << SVM_SELECTOR_L_SHIFT;
+ s->attrib |= (var->db & 1) << SVM_SELECTOR_DB_SHIFT;
+ s->attrib |= (var->g & 1) << SVM_SELECTOR_G_SHIFT;
/*
* This is always accurate, except if SYSRET returned to a segment
@@ -2000,7 +1997,8 @@ static void svm_set_segment(struct kvm_vcpu *vcpu,
* would entail passing the CPL to userspace and back.
*/
if (seg == VCPU_SREG_SS)
- svm->vmcb->save.cpl = (s->attrib >> SVM_SELECTOR_DPL_SHIFT) & 3;
+ /* This is symmetric with svm_get_segment() */
+ svm->vmcb->save.cpl = (var->dpl & 3);
mark_dirty(svm->vmcb, VMCB_SEG);
}
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 72f78396bc09..9b4b5d6dcd34 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -6914,97 +6914,21 @@ static int get_vmx_mem_address(struct kvm_vcpu *vcpu,
return 0;
}
-/*
- * This function performs the various checks including
- * - if it's 4KB aligned
- * - No bits beyond the physical address width are set
- * - Returns 0 on success or else 1
- * (Intel SDM Section 30.3)
- */
-static int nested_vmx_check_vmptr(struct kvm_vcpu *vcpu, int exit_reason,
- gpa_t *vmpointer)
+static int nested_vmx_get_vmptr(struct kvm_vcpu *vcpu, gpa_t *vmpointer)
{
gva_t gva;
- gpa_t vmptr;
struct x86_exception e;
- struct page *page;
- struct vcpu_vmx *vmx = to_vmx(vcpu);
- int maxphyaddr = cpuid_maxphyaddr(vcpu);
if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION),
vmcs_read32(VMX_INSTRUCTION_INFO), false, &gva))
return 1;
- if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, &vmptr,
- sizeof(vmptr), &e)) {
+ if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, vmpointer,
+ sizeof(*vmpointer), &e)) {
kvm_inject_page_fault(vcpu, &e);
return 1;
}
- switch (exit_reason) {
- case EXIT_REASON_VMON:
- /*
- * SDM 3: 24.11.5
- * The first 4 bytes of VMXON region contain the supported
- * VMCS revision identifier
- *
- * Note - IA32_VMX_BASIC[48] will never be 1
- * for the nested case;
- * which replaces physical address width with 32
- *
- */
- if (!PAGE_ALIGNED(vmptr) || (vmptr >> maxphyaddr)) {
- nested_vmx_failInvalid(vcpu);
- return kvm_skip_emulated_instruction(vcpu);
- }
-
- page = nested_get_page(vcpu, vmptr);
- if (page == NULL) {
- nested_vmx_failInvalid(vcpu);
- return kvm_skip_emulated_instruction(vcpu);
- }
- if (*(u32 *)kmap(page) != VMCS12_REVISION) {
- kunmap(page);
- nested_release_page_clean(page);
- nested_vmx_failInvalid(vcpu);
- return kvm_skip_emulated_instruction(vcpu);
- }
- kunmap(page);
- nested_release_page_clean(page);
- vmx->nested.vmxon_ptr = vmptr;
- break;
- case EXIT_REASON_VMCLEAR:
- if (!PAGE_ALIGNED(vmptr) || (vmptr >> maxphyaddr)) {
- nested_vmx_failValid(vcpu,
- VMXERR_VMCLEAR_INVALID_ADDRESS);
- return kvm_skip_emulated_instruction(vcpu);
- }
-
- if (vmptr == vmx->nested.vmxon_ptr) {
- nested_vmx_failValid(vcpu,
- VMXERR_VMCLEAR_VMXON_POINTER);
- return kvm_skip_emulated_instruction(vcpu);
- }
- break;
- case EXIT_REASON_VMPTRLD:
- if (!PAGE_ALIGNED(vmptr) || (vmptr >> maxphyaddr)) {
- nested_vmx_failValid(vcpu,
- VMXERR_VMPTRLD_INVALID_ADDRESS);
- return kvm_skip_emulated_instruction(vcpu);
- }
-
- if (vmptr == vmx->nested.vmxon_ptr) {
- nested_vmx_failValid(vcpu,
- VMXERR_VMPTRLD_VMXON_POINTER);
- return kvm_skip_emulated_instruction(vcpu);
- }
- break;
- default:
- return 1; /* shouldn't happen */
- }
-
- if (vmpointer)
- *vmpointer = vmptr;
return 0;
}
@@ -7066,6 +6990,8 @@ out_msr_bitmap:
static int handle_vmon(struct kvm_vcpu *vcpu)
{
int ret;
+ gpa_t vmptr;
+ struct page *page;
struct vcpu_vmx *vmx = to_vmx(vcpu);
const u64 VMXON_NEEDED_FEATURES = FEATURE_CONTROL_LOCKED
| FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX;
@@ -7095,9 +7021,37 @@ static int handle_vmon(struct kvm_vcpu *vcpu)
return 1;
}
- if (nested_vmx_check_vmptr(vcpu, EXIT_REASON_VMON, NULL))
+ if (nested_vmx_get_vmptr(vcpu, &vmptr))
return 1;
-
+
+ /*
+ * SDM 3: 24.11.5
+ * The first 4 bytes of VMXON region contain the supported
+ * VMCS revision identifier
+ *
+ * Note - IA32_VMX_BASIC[48] will never be 1 for the nested case;
+ * which replaces physical address width with 32
+ */
+ if (!PAGE_ALIGNED(vmptr) || (vmptr >> cpuid_maxphyaddr(vcpu))) {
+ nested_vmx_failInvalid(vcpu);
+ return kvm_skip_emulated_instruction(vcpu);
+ }
+
+ page = nested_get_page(vcpu, vmptr);
+ if (page == NULL) {
+ nested_vmx_failInvalid(vcpu);
+ return kvm_skip_emulated_instruction(vcpu);
+ }
+ if (*(u32 *)kmap(page) != VMCS12_REVISION) {
+ kunmap(page);
+ nested_release_page_clean(page);
+ nested_vmx_failInvalid(vcpu);
+ return kvm_skip_emulated_instruction(vcpu);
+ }
+ kunmap(page);
+ nested_release_page_clean(page);
+
+ vmx->nested.vmxon_ptr = vmptr;
ret = enter_vmx_operation(vcpu);
if (ret)
return ret;
@@ -7213,9 +7167,19 @@ static int handle_vmclear(struct kvm_vcpu *vcpu)
if (!nested_vmx_check_permission(vcpu))
return 1;
- if (nested_vmx_check_vmptr(vcpu, EXIT_REASON_VMCLEAR, &vmptr))
+ if (nested_vmx_get_vmptr(vcpu, &vmptr))
return 1;
+ if (!PAGE_ALIGNED(vmptr) || (vmptr >> cpuid_maxphyaddr(vcpu))) {
+ nested_vmx_failValid(vcpu, VMXERR_VMCLEAR_INVALID_ADDRESS);
+ return kvm_skip_emulated_instruction(vcpu);
+ }
+
+ if (vmptr == vmx->nested.vmxon_ptr) {
+ nested_vmx_failValid(vcpu, VMXERR_VMCLEAR_VMXON_POINTER);
+ return kvm_skip_emulated_instruction(vcpu);
+ }
+
if (vmptr == vmx->nested.current_vmptr)
nested_release_vmcs12(vmx);
@@ -7545,9 +7509,19 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu)
if (!nested_vmx_check_permission(vcpu))
return 1;
- if (nested_vmx_check_vmptr(vcpu, EXIT_REASON_VMPTRLD, &vmptr))
+ if (nested_vmx_get_vmptr(vcpu, &vmptr))
return 1;
+ if (!PAGE_ALIGNED(vmptr) || (vmptr >> cpuid_maxphyaddr(vcpu))) {
+ nested_vmx_failValid(vcpu, VMXERR_VMPTRLD_INVALID_ADDRESS);
+ return kvm_skip_emulated_instruction(vcpu);
+ }
+
+ if (vmptr == vmx->nested.vmxon_ptr) {
+ nested_vmx_failValid(vcpu, VMXERR_VMPTRLD_VMXON_POINTER);
+ return kvm_skip_emulated_instruction(vcpu);
+ }
+
if (vmx->nested.current_vmptr != vmptr) {
struct vmcs12 *new_vmcs12;
struct page *page;
@@ -7913,11 +7887,13 @@ static bool nested_vmx_exit_handled_cr(struct kvm_vcpu *vcpu,
{
unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
int cr = exit_qualification & 15;
- int reg = (exit_qualification >> 8) & 15;
- unsigned long val = kvm_register_readl(vcpu, reg);
+ int reg;
+ unsigned long val;
switch ((exit_qualification >> 4) & 3) {
case 0: /* mov to cr */
+ reg = (exit_qualification >> 8) & 15;
+ val = kvm_register_readl(vcpu, reg);
switch (cr) {
case 0:
if (vmcs12->cr0_guest_host_mask &
@@ -7972,6 +7948,7 @@ static bool nested_vmx_exit_handled_cr(struct kvm_vcpu *vcpu,
* lmsw can change bits 1..3 of cr0, and only set bit 0 of
* cr0. Other attempted changes are ignored, with no exit.
*/
+ val = (exit_qualification >> LMSW_SOURCE_DATA_SHIFT) & 0x0f;
if (vmcs12->cr0_guest_host_mask & 0xe &
(val ^ vmcs12->cr0_read_shadow))
return true;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 02363e37d4a6..a2cd0997343c 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -8394,10 +8394,13 @@ static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu)
if (vcpu->arch.pv.pv_unhalted)
return true;
- if (atomic_read(&vcpu->arch.nmi_queued))
+ if (kvm_test_request(KVM_REQ_NMI, vcpu) ||
+ (vcpu->arch.nmi_pending &&
+ kvm_x86_ops->nmi_allowed(vcpu)))
return true;
- if (kvm_test_request(KVM_REQ_SMI, vcpu))
+ if (kvm_test_request(KVM_REQ_SMI, vcpu) ||
+ (vcpu->arch.smi_pending && !is_smm(vcpu)))
return true;
if (kvm_arch_interrupt_allowed(vcpu) &&
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 1dcd2be4cce4..c8520b2c62d2 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -186,7 +186,7 @@ static void cpa_flush_range(unsigned long start, int numpages, int cache)
unsigned int i, level;
unsigned long addr;
- BUG_ON(irqs_disabled());
+ BUG_ON(irqs_disabled() && !early_boot_irqs_disabled);
WARN_ON(PAGE_ALIGN(start) != start);
on_each_cpu(__cpa_flush_range, NULL, 1);
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index 7e76a4d8304b..43b96f5f78ba 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -828,9 +828,11 @@ static void __init kexec_enter_virtual_mode(void)
/*
* We don't do virtual mode, since we don't do runtime services, on
- * non-native EFI
+ * non-native EFI. With efi=old_map, we don't do runtime services in
+ * kexec kernel because in the initial boot something else might
+ * have been mapped at these virtual addresses.
*/
- if (!efi_is_native()) {
+ if (!efi_is_native() || efi_enabled(EFI_OLD_MEMMAP)) {
efi_memmap_unmap();
clear_bit(EFI_RUNTIME_SERVICES, &efi.flags);
return;
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index c488625c9712..eb8dff15a7f6 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -71,11 +71,13 @@ static void __init early_code_mapping_set_exec(int executable)
pgd_t * __init efi_call_phys_prolog(void)
{
- unsigned long vaddress;
- pgd_t *save_pgd;
+ unsigned long vaddr, addr_pgd, addr_p4d, addr_pud;
+ pgd_t *save_pgd, *pgd_k, *pgd_efi;
+ p4d_t *p4d, *p4d_k, *p4d_efi;
+ pud_t *pud;
int pgd;
- int n_pgds;
+ int n_pgds, i, j;
if (!efi_enabled(EFI_OLD_MEMMAP)) {
save_pgd = (pgd_t *)read_cr3();
@@ -88,10 +90,49 @@ pgd_t * __init efi_call_phys_prolog(void)
n_pgds = DIV_ROUND_UP((max_pfn << PAGE_SHIFT), PGDIR_SIZE);
save_pgd = kmalloc_array(n_pgds, sizeof(*save_pgd), GFP_KERNEL);
+ /*
+ * Build 1:1 identity mapping for efi=old_map usage. Note that
+ * PAGE_OFFSET is PGDIR_SIZE aligned when KASLR is disabled, while
+ * it is PUD_SIZE ALIGNED with KASLR enabled. So for a given physical
+ * address X, the pud_index(X) != pud_index(__va(X)), we can only copy
+ * PUD entry of __va(X) to fill in pud entry of X to build 1:1 mapping.
+ * This means here we can only reuse the PMD tables of the direct mapping.
+ */
for (pgd = 0; pgd < n_pgds; pgd++) {
- save_pgd[pgd] = *pgd_offset_k(pgd * PGDIR_SIZE);
- vaddress = (unsigned long)__va(pgd * PGDIR_SIZE);
- set_pgd(pgd_offset_k(pgd * PGDIR_SIZE), *pgd_offset_k(vaddress));
+ addr_pgd = (unsigned long)(pgd * PGDIR_SIZE);
+ vaddr = (unsigned long)__va(pgd * PGDIR_SIZE);
+ pgd_efi = pgd_offset_k(addr_pgd);
+ save_pgd[pgd] = *pgd_efi;
+
+ p4d = p4d_alloc(&init_mm, pgd_efi, addr_pgd);
+ if (!p4d) {
+ pr_err("Failed to allocate p4d table!\n");
+ goto out;
+ }
+
+ for (i = 0; i < PTRS_PER_P4D; i++) {
+ addr_p4d = addr_pgd + i * P4D_SIZE;
+ p4d_efi = p4d + p4d_index(addr_p4d);
+
+ pud = pud_alloc(&init_mm, p4d_efi, addr_p4d);
+ if (!pud) {
+ pr_err("Failed to allocate pud table!\n");
+ goto out;
+ }
+
+ for (j = 0; j < PTRS_PER_PUD; j++) {
+ addr_pud = addr_p4d + j * PUD_SIZE;
+
+ if (addr_pud > (max_pfn << PAGE_SHIFT))
+ break;
+
+ vaddr = (unsigned long)__va(addr_pud);
+
+ pgd_k = pgd_offset_k(vaddr);
+ p4d_k = p4d_offset(pgd_k, vaddr);
+ pud[j] = *pud_offset(p4d_k, vaddr);
+ }
+ }
}
out:
__flush_tlb_all();
@@ -104,8 +145,11 @@ void __init efi_call_phys_epilog(pgd_t *save_pgd)
/*
* After the lock is released, the original page table is restored.
*/
- int pgd_idx;
+ int pgd_idx, i;
int nr_pgds;
+ pgd_t *pgd;
+ p4d_t *p4d;
+ pud_t *pud;
if (!efi_enabled(EFI_OLD_MEMMAP)) {
write_cr3((unsigned long)save_pgd);
@@ -115,9 +159,28 @@ void __init efi_call_phys_epilog(pgd_t *save_pgd)
nr_pgds = DIV_ROUND_UP((max_pfn << PAGE_SHIFT) , PGDIR_SIZE);
- for (pgd_idx = 0; pgd_idx < nr_pgds; pgd_idx++)
+ for (pgd_idx = 0; pgd_idx < nr_pgds; pgd_idx++) {
+ pgd = pgd_offset_k(pgd_idx * PGDIR_SIZE);
set_pgd(pgd_offset_k(pgd_idx * PGDIR_SIZE), save_pgd[pgd_idx]);
+ if (!(pgd_val(*pgd) & _PAGE_PRESENT))
+ continue;
+
+ for (i = 0; i < PTRS_PER_P4D; i++) {
+ p4d = p4d_offset(pgd,
+ pgd_idx * PGDIR_SIZE + i * P4D_SIZE);
+
+ if (!(p4d_val(*p4d) & _PAGE_PRESENT))
+ continue;
+
+ pud = (pud_t *)p4d_page_vaddr(*p4d);
+ pud_free(&init_mm, pud);
+ }
+
+ p4d = (p4d_t *)pgd_page_vaddr(*pgd);
+ p4d_free(&init_mm, p4d);
+ }
+
kfree(save_pgd);
__flush_tlb_all();
diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c
index 26615991d69c..e0cf95a83f3f 100644
--- a/arch/x86/platform/efi/quirks.c
+++ b/arch/x86/platform/efi/quirks.c
@@ -360,6 +360,9 @@ void __init efi_free_boot_services(void)
free_bootmem_late(start, size);
}
+ if (!num_entries)
+ return;
+
new_size = efi.memmap.desc_size * num_entries;
new_phys = efi_memmap_alloc(num_entries);
if (!new_phys) {