summaryrefslogtreecommitdiff
path: root/arch
diff options
context:
space:
mode:
authorBlagovest Kolenichev <bkolenichev@codeaurora.org>2017-07-26 08:12:21 -0700
committerBlagovest Kolenichev <bkolenichev@codeaurora.org>2017-08-04 07:53:32 -0700
commitb65ef4723782d7e5f75604ba17bf5dd6e41c1d57 (patch)
treed37206c8a823ffede15fe9482689ef24fe0cf34a /arch
parent6ce32a69b7f19cb98df4b70f382d7b8bb3f142cd (diff)
parent59ff2e15be118b70755d9709be67ed1b842cd5e6 (diff)
Merge android-4.4@59ff2e1 (v4.4.78) into msm-4.4
* refs/heads/tmp-59ff2e1 Linux 4.4.78 kvm: vmx: allow host to access guest MSR_IA32_BNDCFGS kvm: vmx: Check value written to IA32_BNDCFGS kvm: x86: Guest BNDCFGS requires guest MPX support kvm: vmx: Do not disable intercepts for BNDCFGS KVM: x86: disable MPX if host did not enable MPX XSAVE features tracing: Use SOFTIRQ_OFFSET for softirq dectection for more accurate results PM / QoS: return -EINVAL for bogus strings PM / wakeirq: Convert to SRCU sched/topology: Optimize build_group_mask() sched/topology: Fix overlapping sched_group_mask crypto: caam - fix signals handling crypto: sha1-ssse3 - Disable avx2 crypto: atmel - only treat EBUSY as transient if backlog crypto: talitos - Extend max key length for SHA384/512-HMAC and AEAD mm: fix overflow check in expand_upwards() tpm: Issue a TPM2_Shutdown for TPM2 devices. Add "shutdown" to "struct class". tpm: Provide strong locking for device removal tpm: Get rid of chip->pdev selftests/capabilities: Fix the test_execve test mnt: Make propagate_umount less slow for overlapping mount propagation trees mnt: In propgate_umount handle visiting mounts in any order mnt: In umount propagation reparent in a separate pass vt: fix unchecked __put_user() in tioclinux ioctls exec: Limit arg stack to at most 75% of _STK_LIM s390: reduce ELF_ET_DYN_BASE powerpc: move ELF_ET_DYN_BASE to 4GB / 4MB arm64: move ELF_ET_DYN_BASE to 4GB / 4MB arm: move ELF_ET_DYN_BASE to 4MB binfmt_elf: use ELF_ET_DYN_BASE only for PIE checkpatch: silence perl 5.26.0 unescaped left brace warnings fs/dcache.c: fix spin lockup issue on nlru->lock mm/list_lru.c: fix list_lru_count_node() to be race free kernel/extable.c: mark core_kernel_text notrace tools/lib/lockdep: Reduce MAX_LOCK_DEPTH to avoid overflowing lock_chain/: Depth parisc/mm: Ensure IRQs are off in switch_mm() parisc: DMA API: return error instead of BUG_ON for dma ops on non dma devs parisc: use compat_sys_keyctl() parisc: Report SIGSEGV instead of SIGBUS when running out of stack irqchip/gic-v3: Fix out-of-bound access in gic_set_affinity cfg80211: Check if PMKID attribute is of expected size cfg80211: Validate frequencies nested in NL80211_ATTR_SCAN_FREQUENCIES cfg80211: Define nla_policy for NL80211_ATTR_LOCAL_MESH_POWER_MODE brcmfmac: fix possible buffer overflow in brcmf_cfg80211_mgmt_tx() rds: tcp: use sock_create_lite() to create the accept socket vrf: fix bug_on triggered by rx when destroying a vrf net: ipv6: Compare lwstate in detecting duplicate nexthops ipv6: dad: don't remove dynamic addresses if link is down net: handle NAPI_GRO_FREE_STOLEN_HEAD case also in napi_frags_finish() bpf: prevent leaking pointer via xadd on unpriviledged net: prevent sign extension in dev_get_stats() tcp: reset sk_rx_dst in tcp_disconnect() net: dp83640: Avoid NULL pointer dereference. ipv6: avoid unregistering inet6_dev for loopback net/phy: micrel: configure intterupts after autoneg workaround net: sched: Fix one possible panic when no destroy callback net_sched: fix error recovery at qdisc creation ANDROID: android-verity: mark dev as rw for linear target ANDROID: sdcardfs: Remove unnecessary lock ANDROID: binder: don't check prio permissions on restore. Add BINDER_GET_NODE_DEBUG_INFO ioctl UPSTREAM: cpufreq: schedutil: Trace frequency only if it has changed UPSTREAM: cpufreq: schedutil: Avoid reducing frequency of busy CPUs prematurely UPSTREAM: cpufreq: schedutil: Refactor sugov_next_freq_shared() UPSTREAM: cpufreq: schedutil: Fix per-CPU structure initialization in sugov_start() UPSTREAM: cpufreq: schedutil: Pass sg_policy to get_next_freq() UPSTREAM: cpufreq: schedutil: move cached_raw_freq to struct sugov_policy UPSTREAM: cpufreq: schedutil: Rectify comment in sugov_irq_work() function UPSTREAM: cpufreq: schedutil: irq-work and mutex are only used in slow path UPSTREAM: cpufreq: schedutil: enable fast switch earlier UPSTREAM: cpufreq: schedutil: Avoid indented labels Linux 4.4.77 saa7134: fix warm Medion 7134 EEPROM read x86/mm/pat: Don't report PAT on CPUs that don't support it ext4: check return value of kstrtoull correctly in reserved_clusters_store staging: comedi: fix clean-up of comedi_class in comedi_init() staging: vt6556: vnt_start Fix missing call to vnt_key_init_table. tcp: fix tcp_mark_head_lost to check skb len before fragmenting md: fix super_offset endianness in super_1_rdev_size_change md: fix incorrect use of lexx_to_cpu in does_sb_need_changing perf tools: Use readdir() instead of deprecated readdir_r() again perf tests: Remove wrong semicolon in while loop in CQM test perf trace: Do not process PERF_RECORD_LOST twice perf dwarf: Guard !x86_64 definitions under #ifdef else clause perf pmu: Fix misleadingly indented assignment (whitespace) perf annotate browser: Fix behaviour of Shift-Tab with nothing focussed perf tools: Remove duplicate const qualifier perf script: Use readdir() instead of deprecated readdir_r() perf thread_map: Use readdir() instead of deprecated readdir_r() perf tools: Use readdir() instead of deprecated readdir_r() perf bench numa: Avoid possible truncation when using snprintf() perf tests: Avoid possible truncation with dirent->d_name + snprintf perf scripting perl: Fix compile error with some perl5 versions perf thread_map: Correctly size buffer used with dirent->dt_name perf intel-pt: Use __fallthrough perf top: Use __fallthrough tools strfilter: Use __fallthrough tools string: Use __fallthrough in perf_atoll() tools include: Add a __fallthrough statement mqueue: fix a use-after-free in sys_mq_notify() RDMA/uverbs: Check port number supplied by user verbs cmds KEYS: Fix an error code in request_master_key() ath10k: override CE5 config for QCA9377 x86/uaccess: Optimize copy_user_enhanced_fast_string() for short strings x86/tools: Fix gcc-7 warning in relocs.c gfs2: Fix glock rhashtable rcu bug USB: serial: qcserial: new Sierra Wireless EM7305 device ID USB: serial: option: add two Longcheer device ids pinctrl: sh-pfc: Update info pointer after SoC-specific init pinctrl: mxs: atomically switch mux and drive strength config pinctrl: sunxi: Fix SPDIF function name for A83T pinctrl: meson: meson8b: fix the NAND DQS pins pinctrl: sh-pfc: r8a7791: Fix SCIF2 pinmux data sysctl: report EINVAL if value is larger than UINT_MAX for proc_douintvec sysctl: don't print negative flag for proc_douintvec mac80211_hwsim: Replace bogus hrtimer clockid usb: Fix typo in the definition of Endpoint[out]Request usb: usbip: set buffer pointers to NULL after free Add USB quirk for HVR-950q to avoid intermittent device resets USB: serial: cp210x: add ID for CEL EM3588 USB ZigBee stick usb: dwc3: replace %p with %pK drm/virtio: don't leak bo on drm_gem_object_init failure tracing/kprobes: Allow to create probe with a module name starting with a digit mm: fix classzone_idx underflow in shrink_zones() bgmac: reset & enable Ethernet core before using it driver core: platform: fix race condition with driver_override fs: completely ignore unknown open flags fs: add a VALID_OPEN_FLAGS ANDROID: binder: add RT inheritance flag to node. ANDROID: binder: improve priority inheritance. ANDROID: binder: add min sched_policy to node. ANDROID: binder: add support for RT prio inheritance. ANDROID: binder: push new transactions to waiting threads. ANDROID: binder: remove proc waitqueue FROMLIST: binder: remove global binder lock FROMLIST: binder: fix death race conditions FROMLIST: binder: protect against stale pointers in print_binder_transaction FROMLIST: binder: protect binder_ref with outer lock FROMLIST: binder: use inner lock to protect thread accounting FROMLIST: binder: protect transaction_stack with inner lock. FROMLIST: binder: protect proc->threads with inner_lock FROMLIST: binder: protect proc->nodes with inner lock FROMLIST: binder: add spinlock to protect binder_node FROMLIST: binder: add spinlocks to protect todo lists FROMLIST: binder: use inner lock to sync work dq and node counts FROMLIST: binder: introduce locking helper functions FROMLIST: binder: use node->tmp_refs to ensure node safety FROMLIST: binder: refactor binder ref inc/dec for thread safety FROMLIST: binder: make sure accesses to proc/thread are safe FROMLIST: binder: make sure target_node has strong ref FROMLIST: binder: guarantee txn complete / errors delivered in-order FROMLIST: binder: refactor binder_pop_transaction FROMLIST: binder: use atomic for transaction_log index FROMLIST: binder: add more debug info when allocation fails. FROMLIST: binder: protect against two threads freeing buffer FROMLIST: binder: remove dead code in binder_get_ref_for_node FROMLIST: binder: don't modify thread->looper from other threads FROMLIST: binder: avoid race conditions when enqueuing txn FROMLIST: binder: refactor queue management in binder_thread_read FROMLIST: binder: add log information for binder transaction failures FROMLIST: binder: make binder_last_id an atomic FROMLIST: binder: change binder_stats to atomics FROMLIST: binder: add protection for non-perf cases FROMLIST: binder: remove binder_debug_no_lock mechanism FROMLIST: binder: move binder_alloc to separate file FROMLIST: binder: separate out binder_alloc functions FROMLIST: binder: remove unneeded cleanup code FROMLIST: binder: separate binder allocator structure from binder proc FROMLIST: binder: Use wake up hint for synchronous transactions. Revert "android: binder: move global binder state into context struct." sched: walt: fix window misalignment when HZ=300 ANDROID: android-base.cfg: remove CONFIG_CGROUP_DEBUG ANDROID: sdcardfs: use mount_nodev and fix a issue in sdcardfs_kill_sb Conflicts: drivers/android/binder.c drivers/net/wireless/ath/ath10k/pci.c Change-Id: Ic6f82c2ec9929733a16a03bb3b745187e002f4f6 Signed-off-by: Blagovest Kolenichev <bkolenichev@codeaurora.org>
Diffstat (limited to 'arch')
-rw-r--r--arch/arm/include/asm/elf.h8
-rw-r--r--arch/arm64/include/asm/elf.h12
-rw-r--r--arch/parisc/include/asm/dma-mapping.h11
-rw-r--r--arch/parisc/include/asm/mmu_context.h15
-rw-r--r--arch/parisc/kernel/syscall_table.S2
-rw-r--r--arch/parisc/mm/fault.c2
-rw-r--r--arch/powerpc/include/asm/elf.h13
-rw-r--r--arch/s390/include/asm/elf.h15
-rw-r--r--arch/x86/crypto/sha1_ssse3_glue.c2
-rw-r--r--arch/x86/include/asm/elf.h13
-rw-r--r--arch/x86/include/asm/msr-index.h2
-rw-r--r--arch/x86/include/asm/pat.h1
-rw-r--r--arch/x86/kernel/setup.c7
-rw-r--r--arch/x86/kvm/cpuid.c13
-rw-r--r--arch/x86/kvm/cpuid.h9
-rw-r--r--arch/x86/kvm/vmx.c19
-rw-r--r--arch/x86/lib/copy_user_64.S7
-rw-r--r--arch/x86/mm/pat.c28
-rw-r--r--arch/x86/tools/relocs.c3
19 files changed, 107 insertions, 75 deletions
diff --git a/arch/arm/include/asm/elf.h b/arch/arm/include/asm/elf.h
index d2315ffd8f12..f13ae153fb24 100644
--- a/arch/arm/include/asm/elf.h
+++ b/arch/arm/include/asm/elf.h
@@ -112,12 +112,8 @@ int dump_task_regs(struct task_struct *t, elf_gregset_t *elfregs);
#define CORE_DUMP_USE_REGSET
#define ELF_EXEC_PAGESIZE 4096
-/* This is the location that an ET_DYN program is loaded if exec'ed. Typical
- use of this is to invoke "./ld.so someprog" to test out a new version of
- the loader. We need to make sure that it is out of the way of the program
- that it will "exec", and that there is sufficient room for the brk. */
-
-#define ELF_ET_DYN_BASE (TASK_SIZE / 3 * 2)
+/* This is the base location for PIE (ET_DYN with INTERP) loads. */
+#define ELF_ET_DYN_BASE 0x400000UL
/* When the program starts, a1 contains a pointer to a function to be
registered with atexit, as per the SVR4 ABI. A value of 0 means we
diff --git a/arch/arm64/include/asm/elf.h b/arch/arm64/include/asm/elf.h
index a383c288ef49..b98332269462 100644
--- a/arch/arm64/include/asm/elf.h
+++ b/arch/arm64/include/asm/elf.h
@@ -114,12 +114,11 @@
#define ELF_EXEC_PAGESIZE PAGE_SIZE
/*
- * This is the location that an ET_DYN program is loaded if exec'ed. Typical
- * use of this is to invoke "./ld.so someprog" to test out a new version of
- * the loader. We need to make sure that it is out of the way of the program
- * that it will "exec", and that there is sufficient room for the brk.
+ * This is the base location for PIE (ET_DYN with INTERP) loads. On
+ * 64-bit, this is raised to 4GB to leave the entire 32-bit address
+ * space open for things that want to use the area for 32-bit pointers.
*/
-#define ELF_ET_DYN_BASE (2 * TASK_SIZE_64 / 3)
+#define ELF_ET_DYN_BASE 0x100000000UL
#ifndef __ASSEMBLY__
@@ -170,7 +169,8 @@ extern int arch_setup_additional_pages(struct linux_binprm *bprm,
#ifdef CONFIG_COMPAT
-#define COMPAT_ELF_ET_DYN_BASE (2 * TASK_SIZE_32 / 3)
+/* PIE load location for compat arm. Must match ARM ELF_ET_DYN_BASE. */
+#define COMPAT_ELF_ET_DYN_BASE 0x000400000UL
/* AArch32 registers. */
#define COMPAT_ELF_NGREG 18
diff --git a/arch/parisc/include/asm/dma-mapping.h b/arch/parisc/include/asm/dma-mapping.h
index d8d60a57183f..f53725202955 100644
--- a/arch/parisc/include/asm/dma-mapping.h
+++ b/arch/parisc/include/asm/dma-mapping.h
@@ -39,6 +39,8 @@ struct hppa_dma_ops {
** flush/purge and allocate "regular" cacheable pages for everything.
*/
+#define DMA_ERROR_CODE (~(dma_addr_t)0)
+
#ifdef CONFIG_PA11
extern struct hppa_dma_ops pcxl_dma_ops;
extern struct hppa_dma_ops pcx_dma_ops;
@@ -209,12 +211,13 @@ parisc_walk_tree(struct device *dev)
break;
}
}
- BUG_ON(!dev->platform_data);
return dev->platform_data;
}
-
-#define GET_IOC(dev) (HBA_DATA(parisc_walk_tree(dev))->iommu)
-
+
+#define GET_IOC(dev) ({ \
+ void *__pdata = parisc_walk_tree(dev); \
+ __pdata ? HBA_DATA(__pdata)->iommu : NULL; \
+})
#ifdef CONFIG_IOMMU_CCIO
struct parisc_device;
diff --git a/arch/parisc/include/asm/mmu_context.h b/arch/parisc/include/asm/mmu_context.h
index 59be25764433..a81226257878 100644
--- a/arch/parisc/include/asm/mmu_context.h
+++ b/arch/parisc/include/asm/mmu_context.h
@@ -49,15 +49,26 @@ static inline void load_context(mm_context_t context)
mtctl(__space_to_prot(context), 8);
}
-static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, struct task_struct *tsk)
+static inline void switch_mm_irqs_off(struct mm_struct *prev,
+ struct mm_struct *next, struct task_struct *tsk)
{
-
if (prev != next) {
mtctl(__pa(next->pgd), 25);
load_context(next->context);
}
}
+static inline void switch_mm(struct mm_struct *prev,
+ struct mm_struct *next, struct task_struct *tsk)
+{
+ unsigned long flags;
+
+ local_irq_save(flags);
+ switch_mm_irqs_off(prev, next, tsk);
+ local_irq_restore(flags);
+}
+#define switch_mm_irqs_off switch_mm_irqs_off
+
#define deactivate_mm(tsk,mm) do { } while (0)
static inline void activate_mm(struct mm_struct *prev, struct mm_struct *next)
diff --git a/arch/parisc/kernel/syscall_table.S b/arch/parisc/kernel/syscall_table.S
index d4ffcfbc9885..041e1f9ec129 100644
--- a/arch/parisc/kernel/syscall_table.S
+++ b/arch/parisc/kernel/syscall_table.S
@@ -361,7 +361,7 @@
ENTRY_SAME(ni_syscall) /* 263: reserved for vserver */
ENTRY_SAME(add_key)
ENTRY_SAME(request_key) /* 265 */
- ENTRY_SAME(keyctl)
+ ENTRY_COMP(keyctl)
ENTRY_SAME(ioprio_set)
ENTRY_SAME(ioprio_get)
ENTRY_SAME(inotify_init)
diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c
index 16dbe81c97c9..2f33a67bc531 100644
--- a/arch/parisc/mm/fault.c
+++ b/arch/parisc/mm/fault.c
@@ -298,7 +298,7 @@ bad_area:
case 15: /* Data TLB miss fault/Data page fault */
/* send SIGSEGV when outside of vma */
if (!vma ||
- address < vma->vm_start || address > vma->vm_end) {
+ address < vma->vm_start || address >= vma->vm_end) {
si.si_signo = SIGSEGV;
si.si_code = SEGV_MAPERR;
break;
diff --git a/arch/powerpc/include/asm/elf.h b/arch/powerpc/include/asm/elf.h
index ee46ffef608e..743ad7a400d6 100644
--- a/arch/powerpc/include/asm/elf.h
+++ b/arch/powerpc/include/asm/elf.h
@@ -23,12 +23,13 @@
#define CORE_DUMP_USE_REGSET
#define ELF_EXEC_PAGESIZE PAGE_SIZE
-/* This is the location that an ET_DYN program is loaded if exec'ed. Typical
- use of this is to invoke "./ld.so someprog" to test out a new version of
- the loader. We need to make sure that it is out of the way of the program
- that it will "exec", and that there is sufficient room for the brk. */
-
-#define ELF_ET_DYN_BASE 0x20000000
+/*
+ * This is the base location for PIE (ET_DYN with INTERP) loads. On
+ * 64-bit, this is raised to 4GB to leave the entire 32-bit address
+ * space open for things that want to use the area for 32-bit pointers.
+ */
+#define ELF_ET_DYN_BASE (is_32bit_task() ? 0x000400000UL : \
+ 0x100000000UL)
#define ELF_CORE_EFLAGS (is_elf2_task() ? 2 : 0)
diff --git a/arch/s390/include/asm/elf.h b/arch/s390/include/asm/elf.h
index bab6739a1154..b9eb7b1a49d2 100644
--- a/arch/s390/include/asm/elf.h
+++ b/arch/s390/include/asm/elf.h
@@ -154,14 +154,13 @@ extern unsigned int vdso_enabled;
#define CORE_DUMP_USE_REGSET
#define ELF_EXEC_PAGESIZE 4096
-/* This is the location that an ET_DYN program is loaded if exec'ed. Typical
- use of this is to invoke "./ld.so someprog" to test out a new version of
- the loader. We need to make sure that it is out of the way of the program
- that it will "exec", and that there is sufficient room for the brk. 64-bit
- tasks are aligned to 4GB. */
-#define ELF_ET_DYN_BASE (is_32bit_task() ? \
- (STACK_TOP / 3 * 2) : \
- (STACK_TOP / 3 * 2) & ~((1UL << 32) - 1))
+/*
+ * This is the base location for PIE (ET_DYN with INTERP) loads. On
+ * 64-bit, this is raised to 4GB to leave the entire 32-bit address
+ * space open for things that want to use the area for 32-bit pointers.
+ */
+#define ELF_ET_DYN_BASE (is_compat_task() ? 0x000400000UL : \
+ 0x100000000UL)
/* This yields a mask that user programs can use to figure out what
instruction set this CPU supports. */
diff --git a/arch/x86/crypto/sha1_ssse3_glue.c b/arch/x86/crypto/sha1_ssse3_glue.c
index dd14616b7739..7de207a11014 100644
--- a/arch/x86/crypto/sha1_ssse3_glue.c
+++ b/arch/x86/crypto/sha1_ssse3_glue.c
@@ -201,7 +201,7 @@ asmlinkage void sha1_transform_avx2(u32 *digest, const char *data,
static bool avx2_usable(void)
{
- if (avx_usable() && boot_cpu_has(X86_FEATURE_AVX2)
+ if (false && avx_usable() && boot_cpu_has(X86_FEATURE_AVX2)
&& boot_cpu_has(X86_FEATURE_BMI1)
&& boot_cpu_has(X86_FEATURE_BMI2))
return true;
diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h
index d262f985bbc8..07cf288b692e 100644
--- a/arch/x86/include/asm/elf.h
+++ b/arch/x86/include/asm/elf.h
@@ -245,12 +245,13 @@ extern int force_personality32;
#define CORE_DUMP_USE_REGSET
#define ELF_EXEC_PAGESIZE 4096
-/* This is the location that an ET_DYN program is loaded if exec'ed. Typical
- use of this is to invoke "./ld.so someprog" to test out a new version of
- the loader. We need to make sure that it is out of the way of the program
- that it will "exec", and that there is sufficient room for the brk. */
-
-#define ELF_ET_DYN_BASE (TASK_SIZE / 3 * 2)
+/*
+ * This is the base location for PIE (ET_DYN with INTERP) loads. On
+ * 64-bit, this is raised to 4GB to leave the entire 32-bit address
+ * space open for things that want to use the area for 32-bit pointers.
+ */
+#define ELF_ET_DYN_BASE (mmap_is_ia32() ? 0x000400000UL : \
+ 0x100000000UL)
/* This yields a mask that user programs can use to figure out what
instruction set this CPU supports. This could be done in user space,
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 690b4027e17c..37db36fddc88 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -405,6 +405,8 @@
#define MSR_IA32_TSC_ADJUST 0x0000003b
#define MSR_IA32_BNDCFGS 0x00000d90
+#define MSR_IA32_BNDCFGS_RSVD 0x00000ffc
+
#define MSR_IA32_XSS 0x00000da0
#define FEATURE_CONTROL_LOCKED (1<<0)
diff --git a/arch/x86/include/asm/pat.h b/arch/x86/include/asm/pat.h
index 0b1ff4c1c14e..fffb2794dd89 100644
--- a/arch/x86/include/asm/pat.h
+++ b/arch/x86/include/asm/pat.h
@@ -7,6 +7,7 @@
bool pat_enabled(void);
void pat_disable(const char *reason);
extern void pat_init(void);
+extern void init_cache_modes(void);
extern int reserve_memtype(u64 start, u64 end,
enum page_cache_mode req_pcm, enum page_cache_mode *ret_pcm);
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index d2bbe343fda7..e67b834279b2 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1048,6 +1048,13 @@ void __init setup_arch(char **cmdline_p)
if (mtrr_trim_uncached_memory(max_pfn))
max_pfn = e820_end_of_ram_pfn();
+ /*
+ * This call is required when the CPU does not support PAT. If
+ * mtrr_bp_init() invoked it already via pat_init() the call has no
+ * effect.
+ */
+ init_cache_modes();
+
#ifdef CONFIG_X86_32
/* max_low_pfn get updated here */
find_low_pfn_range();
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 9357b29de9bc..83d6369c45f5 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -46,11 +46,18 @@ static u32 xstate_required_size(u64 xstate_bv, bool compacted)
return ret;
}
+bool kvm_mpx_supported(void)
+{
+ return ((host_xcr0 & (XFEATURE_MASK_BNDREGS | XFEATURE_MASK_BNDCSR))
+ && kvm_x86_ops->mpx_supported());
+}
+EXPORT_SYMBOL_GPL(kvm_mpx_supported);
+
u64 kvm_supported_xcr0(void)
{
u64 xcr0 = KVM_SUPPORTED_XCR0 & host_xcr0;
- if (!kvm_x86_ops->mpx_supported())
+ if (!kvm_mpx_supported())
xcr0 &= ~(XFEATURE_MASK_BNDREGS | XFEATURE_MASK_BNDCSR);
return xcr0;
@@ -97,7 +104,7 @@ int kvm_update_cpuid(struct kvm_vcpu *vcpu)
if (best && (best->eax & (F(XSAVES) | F(XSAVEC))))
best->ebx = xstate_required_size(vcpu->arch.xcr0, true);
- vcpu->arch.eager_fpu = use_eager_fpu() || guest_cpuid_has_mpx(vcpu);
+ vcpu->arch.eager_fpu = use_eager_fpu();
if (vcpu->arch.eager_fpu)
kvm_x86_ops->fpu_activate(vcpu);
@@ -295,7 +302,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
#endif
unsigned f_rdtscp = kvm_x86_ops->rdtscp_supported() ? F(RDTSCP) : 0;
unsigned f_invpcid = kvm_x86_ops->invpcid_supported() ? F(INVPCID) : 0;
- unsigned f_mpx = kvm_x86_ops->mpx_supported() ? F(MPX) : 0;
+ unsigned f_mpx = kvm_mpx_supported() ? F(MPX) : 0;
unsigned f_xsaves = kvm_x86_ops->xsaves_supported() ? F(XSAVES) : 0;
/* cpuid 1.edx */
diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index 3f5c48ddba45..d1534feefcfe 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -4,6 +4,7 @@
#include "x86.h"
int kvm_update_cpuid(struct kvm_vcpu *vcpu);
+bool kvm_mpx_supported(void);
struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu,
u32 function, u32 index);
int kvm_dev_ioctl_get_cpuid(struct kvm_cpuid2 *cpuid,
@@ -134,20 +135,20 @@ static inline bool guest_cpuid_has_rtm(struct kvm_vcpu *vcpu)
return best && (best->ebx & bit(X86_FEATURE_RTM));
}
-static inline bool guest_cpuid_has_mpx(struct kvm_vcpu *vcpu)
+static inline bool guest_cpuid_has_pcommit(struct kvm_vcpu *vcpu)
{
struct kvm_cpuid_entry2 *best;
best = kvm_find_cpuid_entry(vcpu, 7, 0);
- return best && (best->ebx & bit(X86_FEATURE_MPX));
+ return best && (best->ebx & bit(X86_FEATURE_PCOMMIT));
}
-static inline bool guest_cpuid_has_pcommit(struct kvm_vcpu *vcpu)
+static inline bool guest_cpuid_has_mpx(struct kvm_vcpu *vcpu)
{
struct kvm_cpuid_entry2 *best;
best = kvm_find_cpuid_entry(vcpu, 7, 0);
- return best && (best->ebx & bit(X86_FEATURE_PCOMMIT));
+ return best && (best->ebx & bit(X86_FEATURE_MPX));
}
static inline bool guest_cpuid_has_rdtscp(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index bbaa11f4e74b..b12391119ce8 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -863,7 +863,6 @@ static unsigned long nested_ept_get_cr3(struct kvm_vcpu *vcpu);
static u64 construct_eptp(unsigned long root_hpa);
static void kvm_cpu_vmxon(u64 addr);
static void kvm_cpu_vmxoff(void);
-static bool vmx_mpx_supported(void);
static bool vmx_xsaves_supported(void);
static int vmx_cpu_uses_apicv(struct kvm_vcpu *vcpu);
static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr);
@@ -2541,7 +2540,7 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx)
VM_EXIT_LOAD_IA32_EFER | VM_EXIT_SAVE_IA32_EFER |
VM_EXIT_SAVE_VMX_PREEMPTION_TIMER | VM_EXIT_ACK_INTR_ON_EXIT;
- if (vmx_mpx_supported())
+ if (kvm_mpx_supported())
vmx->nested.nested_vmx_exit_ctls_high |= VM_EXIT_CLEAR_BNDCFGS;
/* We support free control of debug control saving. */
@@ -2562,7 +2561,7 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx)
VM_ENTRY_LOAD_IA32_PAT;
vmx->nested.nested_vmx_entry_ctls_high |=
(VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR | VM_ENTRY_LOAD_IA32_EFER);
- if (vmx_mpx_supported())
+ if (kvm_mpx_supported())
vmx->nested.nested_vmx_entry_ctls_high |= VM_ENTRY_LOAD_BNDCFGS;
/* We support free control of debug control loading. */
@@ -2813,7 +2812,8 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
msr_info->data = vmcs_readl(GUEST_SYSENTER_ESP);
break;
case MSR_IA32_BNDCFGS:
- if (!vmx_mpx_supported())
+ if (!kvm_mpx_supported() ||
+ (!msr_info->host_initiated && !guest_cpuid_has_mpx(vcpu)))
return 1;
msr_info->data = vmcs_read64(GUEST_BNDCFGS);
break;
@@ -2890,7 +2890,11 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
vmcs_writel(GUEST_SYSENTER_ESP, data);
break;
case MSR_IA32_BNDCFGS:
- if (!vmx_mpx_supported())
+ if (!kvm_mpx_supported() ||
+ (!msr_info->host_initiated && !guest_cpuid_has_mpx(vcpu)))
+ return 1;
+ if (is_noncanonical_address(data & PAGE_MASK) ||
+ (data & MSR_IA32_BNDCFGS_RSVD))
return 1;
vmcs_write64(GUEST_BNDCFGS, data);
break;
@@ -3363,7 +3367,7 @@ static void init_vmcs_shadow_fields(void)
for (i = j = 0; i < max_shadow_read_write_fields; i++) {
switch (shadow_read_write_fields[i]) {
case GUEST_BNDCFGS:
- if (!vmx_mpx_supported())
+ if (!kvm_mpx_supported())
continue;
break;
default:
@@ -6253,7 +6257,6 @@ static __init int hardware_setup(void)
vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_CS, false);
vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_ESP, false);
vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_EIP, false);
- vmx_disable_intercept_for_msr(MSR_IA32_BNDCFGS, true);
memcpy(vmx_msr_bitmap_legacy_x2apic,
vmx_msr_bitmap_legacy, PAGE_SIZE);
@@ -10265,7 +10268,7 @@ static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
vmcs12->guest_sysenter_cs = vmcs_read32(GUEST_SYSENTER_CS);
vmcs12->guest_sysenter_esp = vmcs_readl(GUEST_SYSENTER_ESP);
vmcs12->guest_sysenter_eip = vmcs_readl(GUEST_SYSENTER_EIP);
- if (vmx_mpx_supported())
+ if (kvm_mpx_supported())
vmcs12->guest_bndcfgs = vmcs_read64(GUEST_BNDCFGS);
if (nested_cpu_has_xsaves(vmcs12))
vmcs12->xss_exit_bitmap = vmcs_read64(XSS_EXIT_BITMAP);
diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S
index 27f89c79a44b..423644c230e7 100644
--- a/arch/x86/lib/copy_user_64.S
+++ b/arch/x86/lib/copy_user_64.S
@@ -80,7 +80,7 @@ ENTRY(copy_user_generic_unrolled)
movl %edx,%ecx
andl $63,%edx
shrl $6,%ecx
- jz 17f
+ jz .L_copy_short_string
1: movq (%rsi),%r8
2: movq 1*8(%rsi),%r9
3: movq 2*8(%rsi),%r10
@@ -101,7 +101,8 @@ ENTRY(copy_user_generic_unrolled)
leaq 64(%rdi),%rdi
decl %ecx
jnz 1b
-17: movl %edx,%ecx
+.L_copy_short_string:
+ movl %edx,%ecx
andl $7,%edx
shrl $3,%ecx
jz 20f
@@ -215,6 +216,8 @@ ENDPROC(copy_user_generic_string)
*/
ENTRY(copy_user_enhanced_fast_string)
ASM_STAC
+ cmpl $64,%edx
+ jb .L_copy_short_string /* less then 64 bytes, avoid the costly 'rep' */
movl %edx,%ecx
1: rep
movsb
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index 6ad687d104ca..3f1bb4f93a5a 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -36,14 +36,14 @@
#undef pr_fmt
#define pr_fmt(fmt) "" fmt
-static bool boot_cpu_done;
-
-static int __read_mostly __pat_enabled = IS_ENABLED(CONFIG_X86_PAT);
-static void init_cache_modes(void);
+static bool __read_mostly boot_cpu_done;
+static bool __read_mostly pat_disabled = !IS_ENABLED(CONFIG_X86_PAT);
+static bool __read_mostly pat_initialized;
+static bool __read_mostly init_cm_done;
void pat_disable(const char *reason)
{
- if (!__pat_enabled)
+ if (pat_disabled)
return;
if (boot_cpu_done) {
@@ -51,10 +51,8 @@ void pat_disable(const char *reason)
return;
}
- __pat_enabled = 0;
+ pat_disabled = true;
pr_info("x86/PAT: %s\n", reason);
-
- init_cache_modes();
}
static int __init nopat(char *str)
@@ -66,7 +64,7 @@ early_param("nopat", nopat);
bool pat_enabled(void)
{
- return !!__pat_enabled;
+ return pat_initialized;
}
EXPORT_SYMBOL_GPL(pat_enabled);
@@ -204,6 +202,8 @@ static void __init_cache_modes(u64 pat)
update_cache_mode_entry(i, cache);
}
pr_info("x86/PAT: Configuration [0-7]: %s\n", pat_msg);
+
+ init_cm_done = true;
}
#define PAT(x, y) ((u64)PAT_ ## y << ((x)*8))
@@ -224,6 +224,7 @@ static void pat_bsp_init(u64 pat)
}
wrmsrl(MSR_IA32_CR_PAT, pat);
+ pat_initialized = true;
__init_cache_modes(pat);
}
@@ -241,10 +242,9 @@ static void pat_ap_init(u64 pat)
wrmsrl(MSR_IA32_CR_PAT, pat);
}
-static void init_cache_modes(void)
+void init_cache_modes(void)
{
u64 pat = 0;
- static int init_cm_done;
if (init_cm_done)
return;
@@ -286,8 +286,6 @@ static void init_cache_modes(void)
}
__init_cache_modes(pat);
-
- init_cm_done = 1;
}
/**
@@ -305,10 +303,8 @@ void pat_init(void)
u64 pat;
struct cpuinfo_x86 *c = &boot_cpu_data;
- if (!pat_enabled()) {
- init_cache_modes();
+ if (pat_disabled)
return;
- }
if ((c->x86_vendor == X86_VENDOR_INTEL) &&
(((c->x86 == 0x6) && (c->x86_model <= 0xd)) ||
diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c
index 0c2fae8d929d..73eb7fd4aec4 100644
--- a/arch/x86/tools/relocs.c
+++ b/arch/x86/tools/relocs.c
@@ -992,11 +992,12 @@ static void emit_relocs(int as_text, int use_real_mode)
die("Segment relocations found but --realmode not specified\n");
/* Order the relocations for more efficient processing */
- sort_relocs(&relocs16);
sort_relocs(&relocs32);
#if ELF_BITS == 64
sort_relocs(&relocs32neg);
sort_relocs(&relocs64);
+#else
+ sort_relocs(&relocs16);
#endif
/* Print the relocations */