From c80c5ec1b2fa8d3675fc2a6807a64771ea156698 Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Sat, 10 Feb 2018 15:53:14 +0100 Subject: x86/MCE: Fix build warning introduced by "x86: do not use print_symbol()" The following commit: 7b6061627eb8 ("x86: do not use print_symbol()") ... introduced a new build warning on 32-bit x86: arch/x86/kernel/cpu/mcheck/mce.c:237:21: warning: cast to pointer from integer of different size [-Wint-to-pointer-cast] pr_cont("{%pS}", (void *)m->ip); ^ Fix the type mismatch between the 'void *' expected by %pS and the mce->ip field which is u64 by casting to long. Signed-off-by: Borislav Petkov Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Sergey Senozhatsky Cc: Thomas Gleixner Cc: Tony Luck Cc: linux-kernel@vger.kernel.org Fixes: 7b6061627eb8 ("x86: do not use print_symbol()") Link: http://lkml.kernel.org/r/20180210145314.22174-1-bp@alien8.de [ Cleaned up the changelog. ] Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/mcheck/mce.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 3a8e88a611eb..75f405ac085c 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -234,7 +234,7 @@ static void __print_mce(struct mce *m) m->cs, m->ip); if (m->cs == __KERNEL_CS) - pr_cont("{%pS}", (void *)m->ip); + pr_cont("{%pS}", (void *)(unsigned long)m->ip); pr_cont("\n"); } -- cgit v1.2.3 From 295cc7eb314eb3321fb6d67ca6f7305f5c50d10f Mon Sep 17 00:00:00 2001 From: Masayoshi Mizuma Date: Thu, 8 Feb 2018 09:19:08 -0500 Subject: x86/smpboot: Fix uncore_pci_remove() indexing bug when hot-removing a physical CPU When a physical CPU is hot-removed, the following warning messages are shown while the uncore device is removed in uncore_pci_remove(): WARNING: CPU: 120 PID: 5 at arch/x86/events/intel/uncore.c:988 uncore_pci_remove+0xf1/0x110 ... CPU: 120 PID: 5 Comm: kworker/u1024:0 Not tainted 4.15.0-rc8 #1 Workqueue: kacpi_hotplug acpi_hotplug_work_fn ... Call Trace: pci_device_remove+0x36/0xb0 device_release_driver_internal+0x145/0x210 pci_stop_bus_device+0x76/0xa0 pci_stop_root_bus+0x44/0x60 acpi_pci_root_remove+0x1f/0x80 acpi_bus_trim+0x54/0x90 acpi_bus_trim+0x2e/0x90 acpi_device_hotplug+0x2bc/0x4b0 acpi_hotplug_work_fn+0x1a/0x30 process_one_work+0x141/0x340 worker_thread+0x47/0x3e0 kthread+0xf5/0x130 When uncore_pci_remove() runs, it tries to get the package ID to clear the value of uncore_extra_pci_dev[].dev[] by using topology_phys_to_logical_pkg(). The warning messesages are shown because topology_phys_to_logical_pkg() returns -1. arch/x86/events/intel/uncore.c: static void uncore_pci_remove(struct pci_dev *pdev) { ... phys_id = uncore_pcibus_to_physid(pdev->bus); ... pkg = topology_phys_to_logical_pkg(phys_id); // returns -1 for (i = 0; i < UNCORE_EXTRA_PCI_DEV_MAX; i++) { if (uncore_extra_pci_dev[pkg].dev[i] == pdev) { uncore_extra_pci_dev[pkg].dev[i] = NULL; break; } } WARN_ON_ONCE(i >= UNCORE_EXTRA_PCI_DEV_MAX); // <=========== HERE!! topology_phys_to_logical_pkg() tries to find cpuinfo_x86->phys_proc_id that matches the phys_pkg argument. arch/x86/kernel/smpboot.c: int topology_phys_to_logical_pkg(unsigned int phys_pkg) { int cpu; for_each_possible_cpu(cpu) { struct cpuinfo_x86 *c = &cpu_data(cpu); if (c->initialized && c->phys_proc_id == phys_pkg) return c->logical_proc_id; } return -1; } However, the phys_proc_id was already set to 0 by remove_siblinginfo() when the CPU was offlined. So, topology_phys_to_logical_pkg() cannot find the correct logical_proc_id and always returns -1. As the result, uncore_pci_remove() calls WARN_ON_ONCE() and the warning messages are shown. What is worse is that the bogus 'pkg' index results in two bugs: - We dereference uncore_extra_pci_dev[] with a negative index - We fail to clean up a stale pointer in uncore_extra_pci_dev[][] To fix these bugs, remove the clearing of ->phys_proc_id from remove_siblinginfo(). This should not cause any problems, because ->phys_proc_id is not used after it is hot-removed and it is re-set while hot-adding. Signed-off-by: Masayoshi Mizuma Acked-by: Thomas Gleixner Cc: Linus Torvalds Cc: Peter Zijlstra Cc: yasu.isimatu@gmail.com Cc: Fixes: 30bb9811856f ("x86/topology: Avoid wasting 128k for package id array") Link: http://lkml.kernel.org/r/ed738d54-0f01-b38b-b794-c31dc118c207@gmail.com Signed-off-by: Ingo Molnar --- arch/x86/kernel/smpboot.c | 1 - 1 file changed, 1 deletion(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 6f27facbaa9b..cfc61e1d45e2 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -1430,7 +1430,6 @@ static void remove_siblinginfo(int cpu) cpumask_clear(cpu_llc_shared_mask(cpu)); cpumask_clear(topology_sibling_cpumask(cpu)); cpumask_clear(topology_core_cpumask(cpu)); - c->phys_proc_id = 0; c->cpu_core_id = 0; cpumask_clear_cpu(cpu, cpu_sibling_setup_mask); recompute_smt_state(); -- cgit v1.2.3 From c25d99d20ba69824a1e2cc118e04b877cd427afc Mon Sep 17 00:00:00 2001 From: "mike.travis@hpe.com" Date: Mon, 5 Feb 2018 16:15:04 -0600 Subject: x86/platform/UV: Fix GAM Range Table entries less than 1GB The latest UV platforms include the new ApachePass NVDIMMs into the UV address space. This has introduced address ranges in the Global Address Map Table that are less than the previous lowest range, which was 2GB. Fix the address calculation so it accommodates address ranges from bytes to exabytes. Signed-off-by: Mike Travis Reviewed-by: Andrew Banman Reviewed-by: Dimitri Sivanich Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Russ Anderson Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20180205221503.190219903@stormcage.americas.sgi.com Signed-off-by: Ingo Molnar --- arch/x86/kernel/apic/x2apic_uv_x.c | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index 46b675aaf20b..f11910b44638 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -1176,16 +1176,25 @@ static void __init decode_gam_rng_tbl(unsigned long ptr) uv_gre_table = gre; for (; gre->type != UV_GAM_RANGE_TYPE_UNUSED; gre++) { + unsigned long size = ((unsigned long)(gre->limit - lgre) + << UV_GAM_RANGE_SHFT); + int order = 0; + char suffix[] = " KMGTPE"; + + while (size > 9999 && order < sizeof(suffix)) { + size /= 1024; + order++; + } + if (!index) { pr_info("UV: GAM Range Table...\n"); pr_info("UV: # %20s %14s %5s %4s %5s %3s %2s\n", "Range", "", "Size", "Type", "NASID", "SID", "PN"); } - pr_info("UV: %2d: 0x%014lx-0x%014lx %5luG %3d %04x %02x %02x\n", + pr_info("UV: %2d: 0x%014lx-0x%014lx %5lu%c %3d %04x %02x %02x\n", index++, (unsigned long)lgre << UV_GAM_RANGE_SHFT, (unsigned long)gre->limit << UV_GAM_RANGE_SHFT, - ((unsigned long)(gre->limit - lgre)) >> - (30 - UV_GAM_RANGE_SHFT), /* 64M -> 1G */ + size, suffix[order], gre->type, gre->nasid, gre->sockid, gre->pnode); lgre = gre->limit; -- cgit v1.2.3 From fd0e786d9d09024f67bd71ec094b110237dc3840 Mon Sep 17 00:00:00 2001 From: Tony Luck Date: Thu, 25 Jan 2018 14:23:48 -0800 Subject: x86/mm, mm/hwpoison: Don't unconditionally unmap kernel 1:1 pages In the following commit: ce0fa3e56ad2 ("x86/mm, mm/hwpoison: Clear PRESENT bit for kernel 1:1 mappings of poison pages") ... we added code to memory_failure() to unmap the page from the kernel 1:1 virtual address space to avoid speculative access to the page logging additional errors. But memory_failure() may not always succeed in taking the page offline, especially if the page belongs to the kernel. This can happen if there are too many corrected errors on a page and either mcelog(8) or drivers/ras/cec.c asks to take a page offline. Since we remove the 1:1 mapping early in memory_failure(), we can end up with the page unmapped, but still in use. On the next access the kernel crashes :-( There are also various debug paths that call memory_failure() to simulate occurrence of an error. Since there is no actual error in memory, we don't need to map out the page for those cases. Revert most of the previous attempt and keep the solution local to arch/x86/kernel/cpu/mcheck/mce.c. Unmap the page only when: 1) there is a real error 2) memory_failure() succeeds. All of this only applies to 64-bit systems. 32-bit kernel doesn't map all of memory into kernel space. It isn't worth adding the code to unmap the piece that is mapped because nobody would run a 32-bit kernel on a machine that has recoverable machine checks. Signed-off-by: Tony Luck Cc: Andrew Morton Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Dave Cc: Denys Vlasenko Cc: Josh Poimboeuf Cc: Linus Torvalds Cc: Naoya Horiguchi Cc: Peter Zijlstra Cc: Robert (Persistent Memory) Cc: Thomas Gleixner Cc: linux-mm@kvack.org Cc: stable@vger.kernel.org #v4.14 Fixes: ce0fa3e56ad2 ("x86/mm, mm/hwpoison: Clear PRESENT bit for kernel 1:1 mappings of poison pages") Signed-off-by: Ingo Molnar --- arch/x86/include/asm/page_64.h | 4 ---- arch/x86/kernel/cpu/mcheck/mce-internal.h | 15 +++++++++++++++ arch/x86/kernel/cpu/mcheck/mce.c | 17 +++++++++++------ include/linux/mm_inline.h | 6 ------ mm/memory-failure.c | 2 -- 5 files changed, 26 insertions(+), 18 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/include/asm/page_64.h b/arch/x86/include/asm/page_64.h index 4baa6bceb232..d652a3808065 100644 --- a/arch/x86/include/asm/page_64.h +++ b/arch/x86/include/asm/page_64.h @@ -52,10 +52,6 @@ static inline void clear_page(void *page) void copy_page(void *to, void *from); -#ifdef CONFIG_X86_MCE -#define arch_unmap_kpfn arch_unmap_kpfn -#endif - #endif /* !__ASSEMBLY__ */ #ifdef CONFIG_X86_VSYSCALL_EMULATION diff --git a/arch/x86/kernel/cpu/mcheck/mce-internal.h b/arch/x86/kernel/cpu/mcheck/mce-internal.h index aa0d5df9dc60..e956eb267061 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-internal.h +++ b/arch/x86/kernel/cpu/mcheck/mce-internal.h @@ -115,4 +115,19 @@ static inline void mce_unregister_injector_chain(struct notifier_block *nb) { } extern struct mca_config mca_cfg; +#ifndef CONFIG_X86_64 +/* + * On 32-bit systems it would be difficult to safely unmap a poison page + * from the kernel 1:1 map because there are no non-canonical addresses that + * we can use to refer to the address without risking a speculative access. + * However, this isn't much of an issue because: + * 1) Few unmappable pages are in the 1:1 map. Most are in HIGHMEM which + * are only mapped into the kernel as needed + * 2) Few people would run a 32-bit kernel on a machine that supports + * recoverable errors because they have too much memory to boot 32-bit. + */ +static inline void mce_unmap_kpfn(unsigned long pfn) {} +#define mce_unmap_kpfn mce_unmap_kpfn +#endif + #endif /* __X86_MCE_INTERNAL_H__ */ diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 75f405ac085c..8ff94d1e2dce 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -105,6 +105,10 @@ static struct irq_work mce_irq_work; static void (*quirk_no_way_out)(int bank, struct mce *m, struct pt_regs *regs); +#ifndef mce_unmap_kpfn +static void mce_unmap_kpfn(unsigned long pfn); +#endif + /* * CPU/chipset specific EDAC code can register a notifier call here to print * MCE errors in a human-readable form. @@ -590,7 +594,8 @@ static int srao_decode_notifier(struct notifier_block *nb, unsigned long val, if (mce_usable_address(mce) && (mce->severity == MCE_AO_SEVERITY)) { pfn = mce->addr >> PAGE_SHIFT; - memory_failure(pfn, 0); + if (!memory_failure(pfn, 0)) + mce_unmap_kpfn(pfn); } return NOTIFY_OK; @@ -1057,12 +1062,13 @@ static int do_memory_failure(struct mce *m) ret = memory_failure(m->addr >> PAGE_SHIFT, flags); if (ret) pr_err("Memory error not recovered"); + else + mce_unmap_kpfn(m->addr >> PAGE_SHIFT); return ret; } -#if defined(arch_unmap_kpfn) && defined(CONFIG_MEMORY_FAILURE) - -void arch_unmap_kpfn(unsigned long pfn) +#ifndef mce_unmap_kpfn +static void mce_unmap_kpfn(unsigned long pfn) { unsigned long decoy_addr; @@ -1073,7 +1079,7 @@ void arch_unmap_kpfn(unsigned long pfn) * We would like to just call: * set_memory_np((unsigned long)pfn_to_kaddr(pfn), 1); * but doing that would radically increase the odds of a - * speculative access to the posion page because we'd have + * speculative access to the poison page because we'd have * the virtual address of the kernel 1:1 mapping sitting * around in registers. * Instead we get tricky. We create a non-canonical address @@ -1098,7 +1104,6 @@ void arch_unmap_kpfn(unsigned long pfn) if (set_memory_np(decoy_addr, 1)) pr_warn("Could not invalidate pfn=0x%lx from 1:1 map\n", pfn); - } #endif diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index c30b32e3c862..10191c28fc04 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -127,10 +127,4 @@ static __always_inline enum lru_list page_lru(struct page *page) #define lru_to_page(head) (list_entry((head)->prev, struct page, lru)) -#ifdef arch_unmap_kpfn -extern void arch_unmap_kpfn(unsigned long pfn); -#else -static __always_inline void arch_unmap_kpfn(unsigned long pfn) { } -#endif - #endif diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 4b80ccee4535..8291b75f42c8 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1139,8 +1139,6 @@ int memory_failure(unsigned long pfn, int flags) return 0; } - arch_unmap_kpfn(pfn); - orig_head = hpage = compound_head(p); num_poisoned_pages_inc(); -- cgit v1.2.3