From 700870119f49084da004ab588ea2b799689efaf7 Mon Sep 17 00:00:00 2001 From: Josh Boyer Date: Thu, 18 Apr 2013 07:51:34 -0700 Subject: x86, efi: Don't map Boot Services on i386 Add patch to fix 32bit EFI service mapping (rhbz 726701) Multiple people are reporting hitting the following WARNING on i386, WARNING: at arch/x86/mm/ioremap.c:102 __ioremap_caller+0x3d3/0x440() Modules linked in: Pid: 0, comm: swapper Not tainted 3.9.0-rc7+ #95 Call Trace: [] warn_slowpath_common+0x5f/0x80 [] ? __ioremap_caller+0x3d3/0x440 [] ? __ioremap_caller+0x3d3/0x440 [] warn_slowpath_null+0x1d/0x20 [] __ioremap_caller+0x3d3/0x440 [] ? get_usage_chars+0xfb/0x110 [] ? vprintk_emit+0x147/0x480 [] ? efi_enter_virtual_mode+0x1e4/0x3de [] ioremap_cache+0x1a/0x20 [] ? efi_enter_virtual_mode+0x1e4/0x3de [] efi_enter_virtual_mode+0x1e4/0x3de [] start_kernel+0x286/0x2f4 [] ? repair_env_string+0x51/0x51 [] i386_start_kernel+0x12c/0x12f Due to the workaround described in commit 916f676f8 ("x86, efi: Retain boot service code until after switching to virtual mode") EFI Boot Service regions are mapped for a period during boot. Unfortunately, with the limited size of the i386 direct kernel map it's possible that some of the Boot Service regions will not be directly accessible, which causes them to be ioremap()'d, triggering the above warning as the regions are marked as E820_RAM in the e820 memmap. There are currently only two situations where we need to map EFI Boot Service regions, 1. To workaround the firmware bug described in 916f676f8 2. To access the ACPI BGRT image but since we haven't seen an i386 implementation that requires either, this simple fix should suffice for now. [ Added to changelog - Matt ] Reported-by: Bryan O'Donoghue Acked-by: Tom Zanussi Acked-by: Darren Hart Cc: Josh Triplett Cc: Matthew Garrett Cc: H. Peter Anvin Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Greg Kroah-Hartman Cc: Signed-off-by: Josh Boyer Signed-off-by: Matt Fleming --- arch/x86/platform/efi/efi.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index 90f6ed127096..c7e22ab29a5a 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -912,10 +912,13 @@ void __init efi_enter_virtual_mode(void) for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) { md = p; - if (!(md->attribute & EFI_MEMORY_RUNTIME) && - md->type != EFI_BOOT_SERVICES_CODE && - md->type != EFI_BOOT_SERVICES_DATA) - continue; + if (!(md->attribute & EFI_MEMORY_RUNTIME)) { +#ifdef CONFIG_X86_64 + if (md->type != EFI_BOOT_SERVICES_CODE && + md->type != EFI_BOOT_SERVICES_DATA) +#endif + continue; + } size = md->num_pages << EFI_PAGE_SHIFT; end = md->phys_addr + size; -- cgit v1.2.3 From 73c4427c6ca3b32fa0441791e9c6eadceff7242f Mon Sep 17 00:00:00 2001 From: "Yan, Zheng" Date: Tue, 17 Sep 2013 14:48:13 +0800 Subject: perf/x86/intel/uncore: Don't use smp_processor_id() in validate_group() uncore_validate_group() can't call smp_processor_id() because it is in preemptible context. Pass NUMA_NO_NODE to the allocator instead. Signed-off-by: Yan, Zheng Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/1379400493-11505-1-git-send-email-zheng.z.yan@intel.com Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/perf_event_intel_uncore.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c index 8ed44589b0e4..4118f9f68315 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c @@ -2706,14 +2706,14 @@ static void uncore_pmu_init_hrtimer(struct intel_uncore_box *box) box->hrtimer.function = uncore_pmu_hrtimer; } -struct intel_uncore_box *uncore_alloc_box(struct intel_uncore_type *type, int cpu) +static struct intel_uncore_box *uncore_alloc_box(struct intel_uncore_type *type, int node) { struct intel_uncore_box *box; int i, size; size = sizeof(*box) + type->num_shared_regs * sizeof(struct intel_uncore_extra_reg); - box = kzalloc_node(size, GFP_KERNEL, cpu_to_node(cpu)); + box = kzalloc_node(size, GFP_KERNEL, node); if (!box) return NULL; @@ -3031,7 +3031,7 @@ static int uncore_validate_group(struct intel_uncore_pmu *pmu, struct intel_uncore_box *fake_box; int ret = -EINVAL, n; - fake_box = uncore_alloc_box(pmu->type, smp_processor_id()); + fake_box = uncore_alloc_box(pmu->type, NUMA_NO_NODE); if (!fake_box) return -ENOMEM; @@ -3294,7 +3294,7 @@ static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id } type = pci_uncores[UNCORE_PCI_DEV_TYPE(id->driver_data)]; - box = uncore_alloc_box(type, 0); + box = uncore_alloc_box(type, NUMA_NO_NODE); if (!box) return -ENOMEM; @@ -3499,7 +3499,7 @@ static int uncore_cpu_prepare(int cpu, int phys_id) if (pmu->func_id < 0) pmu->func_id = j; - box = uncore_alloc_box(type, cpu); + box = uncore_alloc_box(type, cpu_to_node(cpu)); if (!box) return -ENOMEM; -- cgit v1.2.3 From fa7315871046b9a4c48627905691dbde57e51033 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 19 Sep 2013 10:16:42 +0200 Subject: perf: Fix capabilities bitfield compatibility in 'struct perf_event_mmap_page' Solve the problems around the broken definition of perf_event_mmap_page:: cap_usr_time and cap_usr_rdpmc fields which used to overlap, partially fixed by: 860f085b74e9 ("perf: Fix broken union in 'struct perf_event_mmap_page'") The problem with the fix (merged in v3.12-rc1 and not yet released officially), noticed by Vince Weaver is that the new behavior is not detectable by new user-space, and that due to the reuse of the field names it's easy to mis-compile a binary if old headers are used on a new kernel or new headers are used on an old kernel. To solve all that make this change explicit, detectable and self-contained, by iterating the ABI the following way: - Always clear bit 0, and rename it to usrpage->cap_bit0, to at least not confuse old user-space binaries. RDPMC will be marked as unavailable to old binaries but that's within the ABI, this is a capability bit. - Rename bit 1 to ->cap_bit0_is_deprecated and always set it to 1, so new libraries can reliably detect that bit 0 is deprecated and perma-zero without having to check the kernel version. - Use bits 2, 3, 4 for the newly defined, correct functionality: cap_user_rdpmc : 1, /* The RDPMC instruction can be used to read counts */ cap_user_time : 1, /* The time_* fields are used */ cap_user_time_zero : 1, /* The time_zero field is used */ - Rename all the bitfield names in perf_event.h to be different from the old names, to make sure it's not possible to mis-compile it accidentally with old assumptions. The 'size' field can then be used in the future to add new fields and it will act as a natural ABI version indicator as well. Also adjust tools/perf/ userspace for the new definitions, noticed by Adrian Hunter. Reported-by: Vince Weaver Signed-off-by: Peter Zijlstra Also-Fixed-by: Adrian Hunter Link: http://lkml.kernel.org/n/tip-zr03yxjrpXesOzzupszqglbv@git.kernel.org Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/perf_event.c | 10 +++++----- include/uapi/linux/perf_event.h | 14 +++++++++----- kernel/events/core.c | 21 +++++++++++++++++++++ tools/perf/arch/x86/util/tsc.c | 6 +++--- 4 files changed, 38 insertions(+), 13 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 8355c84b9729..a9c606bb4945 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -1883,9 +1883,9 @@ static struct pmu pmu = { void arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now) { - userpg->cap_usr_time = 0; - userpg->cap_usr_time_zero = 0; - userpg->cap_usr_rdpmc = x86_pmu.attr_rdpmc; + userpg->cap_user_time = 0; + userpg->cap_user_time_zero = 0; + userpg->cap_user_rdpmc = x86_pmu.attr_rdpmc; userpg->pmc_width = x86_pmu.cntval_bits; if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) @@ -1894,13 +1894,13 @@ void arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now) if (!boot_cpu_has(X86_FEATURE_NONSTOP_TSC)) return; - userpg->cap_usr_time = 1; + userpg->cap_user_time = 1; userpg->time_mult = this_cpu_read(cyc2ns); userpg->time_shift = CYC2NS_SCALE_FACTOR; userpg->time_offset = this_cpu_read(cyc2ns_offset) - now; if (sched_clock_stable && !check_tsc_disabled()) { - userpg->cap_usr_time_zero = 1; + userpg->cap_user_time_zero = 1; userpg->time_zero = this_cpu_read(cyc2ns_offset); } } diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index 7f6d584c267b..009a655a5d35 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -380,10 +380,13 @@ struct perf_event_mmap_page { union { __u64 capabilities; struct { - __u64 cap_usr_time : 1, - cap_usr_rdpmc : 1, - cap_usr_time_zero : 1, - cap_____res : 61; + __u64 cap_bit0 : 1, /* Always 0, deprecated, see commit 860f085b74e9 */ + cap_bit0_is_deprecated : 1, /* Always 1, signals that bit 0 is zero */ + + cap_user_rdpmc : 1, /* The RDPMC instruction can be used to read counts */ + cap_user_time : 1, /* The time_* fields are used */ + cap_user_time_zero : 1, /* The time_zero field is used */ + cap_____res : 59; }; }; @@ -442,12 +445,13 @@ struct perf_event_mmap_page { * ((rem * time_mult) >> time_shift); */ __u64 time_zero; + __u32 size; /* Header size up to __reserved[] fields. */ /* * Hole for extension of the self monitor capabilities */ - __u64 __reserved[119]; /* align to 1k */ + __u8 __reserved[118*8+4]; /* align to 1k. */ /* * Control data for the mmap() data buffer. diff --git a/kernel/events/core.c b/kernel/events/core.c index dd236b66ca3a..cb4238e85b38 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -3660,6 +3660,26 @@ static void calc_timer_values(struct perf_event *event, *running = ctx_time - event->tstamp_running; } +static void perf_event_init_userpage(struct perf_event *event) +{ + struct perf_event_mmap_page *userpg; + struct ring_buffer *rb; + + rcu_read_lock(); + rb = rcu_dereference(event->rb); + if (!rb) + goto unlock; + + userpg = rb->user_page; + + /* Allow new userspace to detect that bit 0 is deprecated */ + userpg->cap_bit0_is_deprecated = 1; + userpg->size = offsetof(struct perf_event_mmap_page, __reserved); + +unlock: + rcu_read_unlock(); +} + void __weak arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now) { } @@ -4044,6 +4064,7 @@ again: ring_buffer_attach(event, rb); rcu_assign_pointer(event->rb, rb); + perf_event_init_userpage(event); perf_event_update_userpage(event); unlock: diff --git a/tools/perf/arch/x86/util/tsc.c b/tools/perf/arch/x86/util/tsc.c index 9570c2b0f83c..b2519e49424f 100644 --- a/tools/perf/arch/x86/util/tsc.c +++ b/tools/perf/arch/x86/util/tsc.c @@ -32,7 +32,7 @@ u64 tsc_to_perf_time(u64 cyc, struct perf_tsc_conversion *tc) int perf_read_tsc_conversion(const struct perf_event_mmap_page *pc, struct perf_tsc_conversion *tc) { - bool cap_usr_time_zero; + bool cap_user_time_zero; u32 seq; int i = 0; @@ -42,7 +42,7 @@ int perf_read_tsc_conversion(const struct perf_event_mmap_page *pc, tc->time_mult = pc->time_mult; tc->time_shift = pc->time_shift; tc->time_zero = pc->time_zero; - cap_usr_time_zero = pc->cap_usr_time_zero; + cap_user_time_zero = pc->cap_user_time_zero; rmb(); if (pc->lock == seq && !(seq & 1)) break; @@ -52,7 +52,7 @@ int perf_read_tsc_conversion(const struct perf_event_mmap_page *pc, } } - if (!cap_usr_time_zero) + if (!cap_user_time_zero) return -EOPNOTSUPP; return 0; -- cgit v1.2.3 From cf3b425dd8d99e01214515a6754f9e69ecc6dce8 Mon Sep 17 00:00:00 2001 From: "Yan, Zheng" Date: Sun, 22 Sep 2013 16:19:13 +0800 Subject: perf/x86/intel: Add model number for Avoton Silvermont Signed-off-by: Yan, Zheng Cc: a.p.zijlstra@chello.nl Cc: eranian@google.com Cc: ak@linux.intel.com Link: http://lkml.kernel.org/r/1379837953-17755-1-git-send-email-zheng.z.yan@intel.com Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/perf_event_intel.c | 1 + 1 file changed, 1 insertion(+) (limited to 'arch/x86') diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index 9db76c31b3c3..f31a1655d1ff 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -2325,6 +2325,7 @@ __init int intel_pmu_init(void) break; case 55: /* Atom 22nm "Silvermont" */ + case 77: /* Avoton "Silvermont" */ memcpy(hw_cache_event_ids, slm_hw_cache_event_ids, sizeof(hw_cache_event_ids)); memcpy(hw_cache_extra_regs, slm_hw_cache_extra_regs, -- cgit v1.2.3 From 4f0acd31c31f03ba42494c8baf6c0465150e2621 Mon Sep 17 00:00:00 2001 From: Masoud Sharbiani Date: Fri, 20 Sep 2013 15:59:07 -0700 Subject: x86/reboot: Add quirk to make Dell C6100 use reboot=pci automatically Dell PowerEdge C6100 machines fail to completely reboot about 20% of the time. Signed-off-by: Masoud Sharbiani Signed-off-by: Vinson Lee Cc: Robin Holt Cc: Russell King Cc: Guan Xuetao Cc: Link: http://lkml.kernel.org/r/1379717947-18042-1-git-send-email-vlee@freedesktop.org Signed-off-by: Ingo Molnar --- arch/x86/kernel/reboot.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'arch/x86') diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 563ed91e6faa..5f4ad2714109 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -358,6 +358,22 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "Precision M6600"), }, }, + { /* Handle problems with rebooting on the Dell PowerEdge C6100. */ + .callback = set_pci_reboot, + .ident = "Dell PowerEdge C6100", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "C6100"), + }, + }, + { /* Some C6100 machines were shipped with vendor being 'Dell'. */ + .callback = set_pci_reboot, + .ident = "Dell PowerEdge C6100", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell"), + DMI_MATCH(DMI_PRODUCT_NAME, "C6100"), + }, + }, { } }; -- cgit v1.2.3 From a945928ea2709bc0e8e8165d33aed855a0110279 Mon Sep 17 00:00:00 2001 From: Konrad Rzeszutek Wilk Date: Thu, 12 Sep 2013 22:29:44 -0400 Subject: xen: Do not enable spinlocks before jump_label_init() has executed xen_init_spinlocks() currently calls static_key_slow_inc() before jump_label_init() is invoked. When CONFIG_JUMP_LABEL is set (which usually is the case) the effect of this static_key_slow_inc() is deferred until after jump_label_init(). This is different from when CONFIG_JUMP_LABEL is not set, in which case the key is set immediately. Thus, depending on the value of config option, we may observe different behavior. In addition, when we come to __jump_label_transform() from jump_label_init(), the key (paravirt_ticketlocks_enabled) is already enabled. On processors where ideal_nop is not the same as default_nop this will cause a BUG() since it is expected that before a key is enabled the latter is replaced by the former during initialization. To address this problem we need to move static_key_slow_inc(¶virt_ticketlocks_enabled) so that it is called after jump_label_init(). We also need to make sure that this is done before other cpus start to boot. early_initcall appears to be a good place to do so. (Note that we cannot move whole xen_init_spinlocks() there since pv_lock_ops need to be set before alternative_instructions() runs.) Signed-off-by: Konrad Rzeszutek Wilk [v2: Added extra comments in the code] Signed-off-by: Boris Ostrovsky Signed-off-by: Konrad Rzeszutek Wilk Reviewed-by: Steven Rostedt --- arch/x86/xen/spinlock.c | 26 ++++++++++++++++++++++++-- 1 file changed, 24 insertions(+), 2 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c index 253f63fceea1..be6b86078957 100644 --- a/arch/x86/xen/spinlock.c +++ b/arch/x86/xen/spinlock.c @@ -259,6 +259,14 @@ void xen_uninit_lock_cpu(int cpu) } +/* + * Our init of PV spinlocks is split in two init functions due to us + * using paravirt patching and jump labels patching and having to do + * all of this before SMP code is invoked. + * + * The paravirt patching needs to be done _before_ the alternative asm code + * is started, otherwise we would not patch the core kernel code. + */ void __init xen_init_spinlocks(void) { @@ -267,12 +275,26 @@ void __init xen_init_spinlocks(void) return; } - static_key_slow_inc(¶virt_ticketlocks_enabled); - pv_lock_ops.lock_spinning = PV_CALLEE_SAVE(xen_lock_spinning); pv_lock_ops.unlock_kick = xen_unlock_kick; } +/* + * While the jump_label init code needs to happend _after_ the jump labels are + * enabled and before SMP is started. Hence we use pre-SMP initcall level + * init. We cannot do it in xen_init_spinlocks as that is done before + * jump labels are activated. + */ +static __init int xen_init_spinlocks_jump(void) +{ + if (!xen_pvspin) + return 0; + + static_key_slow_inc(¶virt_ticketlocks_enabled); + return 0; +} +early_initcall(xen_init_spinlocks_jump); + static __init int xen_parse_nopvspin(char *arg) { xen_pvspin = false; -- cgit v1.2.3 From 7a20c2fad61aa3624e83c671d36dbd36b2661476 Mon Sep 17 00:00:00 2001 From: Dave Jones Date: Tue, 24 Sep 2013 20:13:44 -0400 Subject: x86/reboot: Fix apparent cut-n-paste mistake in Dell reboot workaround This seems to have been copied from the Optiplex 990 entry above, but somoene forgot to change the ident text. Signed-off-by: Dave Jones Link: http://lkml.kernel.org/r/20130925001344.GA13554@redhat.com Signed-off-by: Ingo Molnar --- arch/x86/kernel/reboot.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 5f4ad2714109..e643e744e4d8 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -352,7 +352,7 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = { }, { /* Handle problems with rebooting on the Precision M6600. */ .callback = set_pci_reboot, - .ident = "Dell OptiPlex 990", + .ident = "Dell Precision M6600", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), DMI_MATCH(DMI_PRODUCT_NAME, "Precision M6600"), -- cgit v1.2.3 From 0160676bba69523e8b0ac83f306cce7d342ed7c8 Mon Sep 17 00:00:00 2001 From: David Vrabel Date: Fri, 13 Sep 2013 15:13:30 +0100 Subject: xen/p2m: check MFN is in range before using the m2p table On hosts with more than 168 GB of memory, a 32-bit guest may attempt to grant map an MFN that is error cannot lookup in its mapping of the m2p table. There is an m2p lookup as part of m2p_add_override() and m2p_remove_override(). The lookup falls off the end of the mapped portion of the m2p and (because the mapping is at the highest virtual address) wraps around and the lookup causes a fault on what appears to be a user space address. do_page_fault() (thinking it's a fault to a userspace address), tries to lock mm->mmap_sem. If the gntdev device is used for the grant map, m2p_add_override() is called from from gnttab_mmap() with mm->mmap_sem already locked. do_page_fault() then deadlocks. The deadlock would most commonly occur when a 64-bit guest is started and xenconsoled attempts to grant map its console ring. Introduce mfn_to_pfn_no_overrides() which checks the MFN is within the mapped portion of the m2p table before accessing the table and use this in m2p_add_override(), m2p_remove_override(), and mfn_to_pfn() (which already had the correct range check). All faults caused by accessing the non-existant parts of the m2p are thus within the kernel address space and exception_fixup() is called without trying to lock mm->mmap_sem. This means that for MFNs that are outside the mapped range of the m2p then mfn_to_pfn() will always look in the m2p overrides. This is correct because it must be a foreign MFN (and the PFN in the m2p in this case is only relevant for the other domain). Signed-off-by: David Vrabel Cc: Stefano Stabellini Cc: Jan Beulich -- v3: check for auto_translated_physmap in mfn_to_pfn_no_overrides() v2: in mfn_to_pfn() look in m2p_overrides if the MFN is out of range as it's probably foreign. Signed-off-by: Konrad Rzeszutek Wilk Acked-by: Stefano Stabellini --- arch/x86/include/asm/xen/page.h | 31 ++++++++++++++++++++----------- arch/x86/xen/p2m.c | 10 ++++------ 2 files changed, 24 insertions(+), 17 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h index 6aef9fbc09b7..b913915e8e63 100644 --- a/arch/x86/include/asm/xen/page.h +++ b/arch/x86/include/asm/xen/page.h @@ -79,30 +79,38 @@ static inline int phys_to_machine_mapping_valid(unsigned long pfn) return get_phys_to_machine(pfn) != INVALID_P2M_ENTRY; } -static inline unsigned long mfn_to_pfn(unsigned long mfn) +static inline unsigned long mfn_to_pfn_no_overrides(unsigned long mfn) { unsigned long pfn; - int ret = 0; + int ret; if (xen_feature(XENFEAT_auto_translated_physmap)) return mfn; - if (unlikely(mfn >= machine_to_phys_nr)) { - pfn = ~0; - goto try_override; - } - pfn = 0; + if (unlikely(mfn >= machine_to_phys_nr)) + return ~0; + /* * The array access can fail (e.g., device space beyond end of RAM). * In such cases it doesn't matter what we return (we return garbage), * but we must handle the fault without crashing! */ ret = __get_user(pfn, &machine_to_phys_mapping[mfn]); -try_override: - /* ret might be < 0 if there are no entries in the m2p for mfn */ if (ret < 0) - pfn = ~0; - else if (get_phys_to_machine(pfn) != mfn) + return ~0; + + return pfn; +} + +static inline unsigned long mfn_to_pfn(unsigned long mfn) +{ + unsigned long pfn; + + if (xen_feature(XENFEAT_auto_translated_physmap)) + return mfn; + + pfn = mfn_to_pfn_no_overrides(mfn); + if (get_phys_to_machine(pfn) != mfn) { /* * If this appears to be a foreign mfn (because the pfn * doesn't map back to the mfn), then check the local override @@ -111,6 +119,7 @@ try_override: * m2p_find_override_pfn returns ~0 if it doesn't find anything. */ pfn = m2p_find_override_pfn(mfn, ~0); + } /* * pfn is ~0 if there are no entries in the m2p for mfn or if the diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index 8b901e8d782d..a61c7d5811be 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -879,7 +879,6 @@ int m2p_add_override(unsigned long mfn, struct page *page, unsigned long uninitialized_var(address); unsigned level; pte_t *ptep = NULL; - int ret = 0; pfn = page_to_pfn(page); if (!PageHighMem(page)) { @@ -926,8 +925,8 @@ int m2p_add_override(unsigned long mfn, struct page *page, * frontend pages while they are being shared with the backend, * because mfn_to_pfn (that ends up being called by GUPF) will * return the backend pfn rather than the frontend pfn. */ - ret = __get_user(pfn, &machine_to_phys_mapping[mfn]); - if (ret == 0 && get_phys_to_machine(pfn) == mfn) + pfn = mfn_to_pfn_no_overrides(mfn); + if (get_phys_to_machine(pfn) == mfn) set_phys_to_machine(pfn, FOREIGN_FRAME(mfn)); return 0; @@ -942,7 +941,6 @@ int m2p_remove_override(struct page *page, unsigned long uninitialized_var(address); unsigned level; pte_t *ptep = NULL; - int ret = 0; pfn = page_to_pfn(page); mfn = get_phys_to_machine(pfn); @@ -1029,8 +1027,8 @@ int m2p_remove_override(struct page *page, * the original pfn causes mfn_to_pfn(mfn) to return the frontend * pfn again. */ mfn &= ~FOREIGN_FRAME_BIT; - ret = __get_user(pfn, &machine_to_phys_mapping[mfn]); - if (ret == 0 && get_phys_to_machine(pfn) == FOREIGN_FRAME(mfn) && + pfn = mfn_to_pfn_no_overrides(mfn); + if (get_phys_to_machine(pfn) == FOREIGN_FRAME(mfn) && m2p_find_override(mfn) == NULL) set_phys_to_machine(pfn, mfn); -- cgit v1.2.3 From accd1e823ed1d5980106dd522a4c535084400830 Mon Sep 17 00:00:00 2001 From: Suravee Suthikulpanit Date: Wed, 29 Sep 2010 19:27:12 -0500 Subject: x86/microcode/AMD: Fix patch level reporting for family 15h On AMD family 14h, applying microcode patch on the a core (core0) would also affect the other core (core1) in the same compute unit. The driver would skip applying the patch on core1, but it still need to update kernel structures to reflect the proper patch level. The current logic is not updating the struct ucode_cpu_info.cpu_sig.rev of the skipped core. This causes the /sys/devices/system/cpu/cpu1/microcode/version to report incorrect patch level as shown below: $ grep . cpu?/microcode/version cpu0/microcode/version:0x600063d cpu1/microcode/version:0x6000626 cpu2/microcode/version:0x600063d cpu3/microcode/version:0x6000626 cpu4/microcode/version:0x600063d Signed-off-by: Suravee Suthikulpanit Acked-by: Borislav Petkov Cc: Cc: Cc: Link: http://lkml.kernel.org/r/1285806432-1995-1-git-send-email-suravee.suthikulpanit@amd.com Signed-off-by: Ingo Molnar --- arch/x86/kernel/microcode_amd.c | 1 + 1 file changed, 1 insertion(+) (limited to 'arch/x86') diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c index 7123b5df479d..af99f71aeb7f 100644 --- a/arch/x86/kernel/microcode_amd.c +++ b/arch/x86/kernel/microcode_amd.c @@ -216,6 +216,7 @@ int apply_microcode_amd(int cpu) /* need to apply patch? */ if (rev >= mc_amd->hdr.patch_id) { c->microcode = rev; + uci->cpu_sig.rev = rev; return 0; } -- cgit v1.2.3 From 8a3da6c7d0031fcb6a0d17f9c7a68b0e01f52855 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Sat, 28 Sep 2013 15:48:48 +0200 Subject: perf/x86: Fix PMU detection printout when no PMU is detected Ran into this cryptic PMU bootup log recently: [ 0.124047] Performance Events: [ 0.125000] smpboot: ... Turns out we print this if no PMU is detected. Fall back to the right condition so that the following is printed: [ 0.122381] Performance Events: no PMU driver, software events only. Cc: Peter Zijlstra Cc: Arnaldo Carvalho de Melo Link: http://lkml.kernel.org/n/tip-u2fwaUffakjp0qkpRfqljgsn@git.kernel.org Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/perf_event.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index a9c606bb4945..897783b3302a 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -1506,7 +1506,7 @@ static int __init init_hw_perf_events(void) err = amd_pmu_init(); break; default: - return 0; + err = -ENOTSUPP; } if (err != 0) { pr_cont("no PMU driver, software events only.\n"); -- cgit v1.2.3