From b0c4d952a158a6a2547672cf4fc9d55e415410de Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Thu, 6 May 2010 02:24:34 -0700 Subject: x86: Fix fake apicid to node mapping for numa emulation With NUMA emulation, it's possible for a single cpu to be bound to multiple nodes since more than one may have affinity if allocated on a physical node that is local to the cpu. APIC ids must therefore be mapped to the lowest node ids to maintain generic kernel use of functions such as cpu_to_node() that determine device affinity. For example, if a device has proximity to physical node 1, for instance, and a cpu happens to be mapped to a higher emulated node id 8, the proximity may not be correctly determined by comparison in generic code even though the cpu may be truly local and allocated on physical node 1. When this happens, the true topology of the machine isn't accurately represented in the emulated environment; although this isn't critical to the system's uptime, any generic code that is NUMA aware benefits from the physical topology being accurately represented. This can affect any system that maps multiple APIC ids to a single node and is booted with numa=fake=N where N is greater than the number of physical nodes. Signed-off-by: David Rientjes Cc: Yinghai Lu Cc: Suresh Siddha LKML-Reference: Signed-off-by: Ingo Molnar --- arch/x86/mm/srat_64.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/x86/mm/srat_64.c b/arch/x86/mm/srat_64.c index 28c68762648f..38512d0c4742 100644 --- a/arch/x86/mm/srat_64.c +++ b/arch/x86/mm/srat_64.c @@ -461,7 +461,8 @@ void __init acpi_fake_nodes(const struct bootnode *fake_nodes, int num_nodes) * node, it must now point to the fake node ID. */ for (j = 0; j < MAX_LOCAL_APIC; j++) - if (apicid_to_node[j] == nid) + if (apicid_to_node[j] == nid && + fake_apicid_to_node[j] == NUMA_NO_NODE) fake_apicid_to_node[j] = i; } for (i = 0; i < num_nodes; i++) -- cgit v1.2.3 From f01487119dda3d9f58c9729c7361ecc50a61c188 Mon Sep 17 00:00:00 2001 From: Andreas Herrmann Date: Tue, 27 Apr 2010 12:13:48 +0200 Subject: x86, amd: Check X86_FEATURE_OSVW bit before accessing OSVW MSRs If host CPU is exposed to a guest the OSVW MSRs are not guaranteed to be present and a GP fault occurs. Thus checking the feature flag is essential. Cc: # .32.x .33.x Signed-off-by: Andreas Herrmann LKML-Reference: <20100427101348.GC4489@alberich.amd.com> Signed-off-by: H. Peter Anvin --- arch/x86/kernel/process.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 28ad9f4d8b94..0415c3ef91b5 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -546,11 +546,13 @@ static int __cpuinit check_c1e_idle(const struct cpuinfo_x86 *c) * check OSVW bit for CPUs that are not affected * by erratum #400 */ - rdmsrl(MSR_AMD64_OSVW_ID_LENGTH, val); - if (val >= 2) { - rdmsrl(MSR_AMD64_OSVW_STATUS, val); - if (!(val & BIT(1))) - goto no_c1e_idle; + if (cpu_has(c, X86_FEATURE_OSVW)) { + rdmsrl(MSR_AMD64_OSVW_ID_LENGTH, val); + if (val >= 2) { + rdmsrl(MSR_AMD64_OSVW_STATUS, val); + if (!(val & BIT(1))) + goto no_c1e_idle; + } } return 1; } -- cgit v1.2.3 From ade029e2aaacc8965a548b0b0f80c5bee97ffc68 Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Sat, 24 Apr 2010 09:56:53 +0200 Subject: x86, k8: Fix build error when K8_NB is disabled K8_NB depends on PCI and when the last is disabled (allnoconfig) we fail at the final linking stage due to missing exported num_k8_northbridges. Add a header stub for that. Signed-off-by: Borislav Petkov LKML-Reference: <20100503183036.GJ26107@aftab> Signed-off-by: H. Peter Anvin Cc: --- arch/x86/include/asm/k8.h | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/arch/x86/include/asm/k8.h b/arch/x86/include/asm/k8.h index f70e60071fe8..af00bd1d2089 100644 --- a/arch/x86/include/asm/k8.h +++ b/arch/x86/include/asm/k8.h @@ -16,11 +16,16 @@ extern int k8_numa_init(unsigned long start_pfn, unsigned long end_pfn); extern int k8_scan_nodes(void); #ifdef CONFIG_K8_NB +extern int num_k8_northbridges; + static inline struct pci_dev *node_to_k8_nb_misc(int node) { return (node < num_k8_northbridges) ? k8_northbridges[node] : NULL; } + #else +#define num_k8_northbridges 0 + static inline struct pci_dev *node_to_k8_nb_misc(int node) { return NULL; -- cgit v1.2.3 From 7f284d3cc96e02468a42e045f77af11e5ff8b095 Mon Sep 17 00:00:00 2001 From: Frank Arnold Date: Thu, 22 Apr 2010 16:06:59 +0200 Subject: x86, cacheinfo: Turn off L3 cache index disable feature in virtualized environments When running a quest kernel on xen we get: BUG: unable to handle kernel NULL pointer dereference at 0000000000000038 IP: [] cpuid4_cache_lookup_regs+0x2ca/0x3df PGD 0 Oops: 0000 [#1] SMP last sysfs file: CPU 0 Modules linked in: Pid: 0, comm: swapper Tainted: G W 2.6.34-rc3 #1 /HVM domU RIP: 0010:[] [] cpuid4_cache_lookup_regs+0x 2ca/0x3df RSP: 0018:ffff880002203e08 EFLAGS: 00010046 RAX: 0000000000000000 RBX: 0000000000000003 RCX: 0000000000000060 RDX: 0000000000000000 RSI: 0000000000000040 RDI: 0000000000000000 RBP: ffff880002203ed8 R08: 00000000000017c0 R09: ffff880002203e38 R10: ffff8800023d5d40 R11: ffffffff81a01e28 R12: ffff880187e6f5c0 R13: ffff880002203e34 R14: ffff880002203e58 R15: ffff880002203e68 FS: 0000000000000000(0000) GS:ffff880002200000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b CR2: 0000000000000038 CR3: 0000000001a3c000 CR4: 00000000000006f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Process swapper (pid: 0, threadinfo ffffffff81a00000, task ffffffff81a44020) Stack: ffffffff810d7ecb ffff880002203e20 ffffffff81059140 ffff880002203e30 <0> ffffffff810d7ec9 0000000002203e40 000000000050d140 ffff880002203e70 <0> 0000000002008140 0000000000000086 ffff880040020140 ffffffff81068b8b Call Trace: [] ? sync_supers_timer_fn+0x0/0x1c [] ? mod_timer+0x23/0x25 [] ? arm_supers_timer+0x34/0x36 [] ? hrtimer_get_next_event+0xa7/0xc3 [] ? get_next_timer_interrupt+0x19a/0x20d [] get_cpu_leaves+0x5c/0x232 [] ? sched_clock_local+0x1c/0x82 [] ? sched_clock_tick+0x75/0x7a [] generic_smp_call_function_single_interrupt+0xae/0xd0 [] smp_call_function_single_interrupt+0x18/0x27 [] call_function_single_interrupt+0x13/0x20 [] ? notifier_call_chain+0x14/0x63 [] ? native_safe_halt+0xc/0xd [] ? default_idle+0x36/0x53 [] cpu_idle+0xaa/0xe4 [] rest_init+0x7e/0x80 [] start_kernel+0x40e/0x419 [] x86_64_start_reservations+0xb3/0xb7 [] x86_64_start_kernel+0xf8/0x107 Code: 14 d5 40 ff ae 81 8b 14 02 31 c0 3b 15 47 1c 8b 00 7d 0e 48 8b 05 36 1c 8b 00 48 63 d2 48 8b 04 d0 c7 85 5c ff ff ff 00 00 00 00 <8b> 70 38 48 8d 8d 5c ff ff ff 48 8b 78 10 ba c4 01 00 00 e8 eb RIP [] cpuid4_cache_lookup_regs+0x2ca/0x3df RSP CR2: 0000000000000038 ---[ end trace a7919e7f17c0a726 ]--- The L3 cache index disable feature of AMD CPUs has to be disabled if the kernel is running as guest on top of a hypervisor because northbridge devices are not available to the guest. Currently, this fixes a boot crash on top of Xen. In the future this will become an issue on KVM as well. Check if northbridge devices are present and do not enable the feature if there are none. [ hpa: backported to 2.6.34 ] Signed-off-by: Frank Arnold LKML-Reference: <1271945222-5283-3-git-send-email-bp@amd64.org> Acked-by: Borislav Petkov Signed-off-by: H. Peter Anvin Cc: --- arch/x86/kernel/cpu/intel_cacheinfo.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c index b3eeb66c0a51..95962a93f99a 100644 --- a/arch/x86/kernel/cpu/intel_cacheinfo.c +++ b/arch/x86/kernel/cpu/intel_cacheinfo.c @@ -340,6 +340,10 @@ amd_check_l3_disable(int index, struct _cpuid4_info_regs *this_leaf) (boot_cpu_data.x86_mask < 0x1))) return; + /* not in virtualized environments */ + if (num_k8_northbridges == 0) + return; + this_leaf->can_disable = true; this_leaf->l3_indices = amd_calc_l3_indices(); } -- cgit v1.2.3