From 58b7b53a36b0be8081fbfc91aeea24b83c20ca1b Mon Sep 17 00:00:00 2001 From: Konrad Rzeszutek Wilk Date: Tue, 29 May 2012 12:36:43 -0400 Subject: xen/balloon: Subtract from xen_released_pages the count that is populated. We did not take into account that xen_released_pages would be used outside the initial E820 parsing code. As such we would did not subtract from xen_released_pages the count of pages that we had populated back (instead we just did a simple extra_pages = released - populated). The balloon driver uses xen_released_pages to set the initial current_pages count. If this is wrong (too low) then when a new (higher) target is set, the balloon driver will request too many pages from Xen." This fixes errors such as: (XEN) memory.c:133:d0 Could not allocate order=0 extent: id=0 memflags=0 (51 of 512) during bootup and free_memory : 0 where the free_memory should be 128. Acked-by: David Vrabel [v1: Per David's review made the git commit better] Signed-off-by: Konrad Rzeszutek Wilk --- arch/x86/xen/setup.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'arch/x86') diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index 3ebba0753d3..a4790bf22c5 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -371,7 +371,8 @@ char * __init xen_memory_setup(void) populated = xen_populate_chunk(map, memmap.nr_entries, max_pfn, &last_pfn, xen_released_pages); - extra_pages += (xen_released_pages - populated); + xen_released_pages -= populated; + extra_pages += xen_released_pages; if (last_pfn > max_pfn) { max_pfn = min(MAX_DOMAIN_PAGES, last_pfn); -- cgit v1.2.3-70-g09d2 From 7c8d51848a88aafdb68f42b6b650c83485ea2f84 Mon Sep 17 00:00:00 2001 From: Mathias Krause Date: Wed, 30 May 2012 01:43:08 +0200 Subject: crypto: aesni-intel - fix unaligned cbc decrypt for x86-32 The 32 bit variant of cbc(aes) decrypt is using instructions requiring 128 bit aligned memory locations but fails to ensure this constraint in the code. Fix this by loading the data into intermediate registers with load unaligned instructions. This fixes reported general protection faults related to aesni. References: https://bugzilla.kernel.org/show_bug.cgi?id=43223 Reported-by: Daniel Cc: stable@kernel.org [v2.6.39+] Signed-off-by: Mathias Krause Signed-off-by: Herbert Xu --- arch/x86/crypto/aesni-intel_asm.S | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S index be6d9e365a8..3470624d783 100644 --- a/arch/x86/crypto/aesni-intel_asm.S +++ b/arch/x86/crypto/aesni-intel_asm.S @@ -2460,10 +2460,12 @@ ENTRY(aesni_cbc_dec) pxor IN3, STATE4 movaps IN4, IV #else - pxor (INP), STATE2 - pxor 0x10(INP), STATE3 pxor IN1, STATE4 movaps IN2, IV + movups (INP), IN1 + pxor IN1, STATE2 + movups 0x10(INP), IN2 + pxor IN2, STATE3 #endif movups STATE1, (OUTP) movups STATE2, 0x10(OUTP) -- cgit v1.2.3-70-g09d2 From 5e626254206a709c6e937f3dda69bf26c7344f6f Mon Sep 17 00:00:00 2001 From: Andre Przywara Date: Tue, 29 May 2012 13:07:31 +0200 Subject: xen/setup: filter APERFMPERF cpuid feature out Xen PV kernels allow access to the APERF/MPERF registers to read the effective frequency. Access to the MSRs is however redirected to the currently scheduled physical CPU, making consecutive read and compares unreliable. In addition each rdmsr traps into the hypervisor. So to avoid bogus readouts and expensive traps, disable the kernel internal feature flag for APERF/MPERF if running under Xen. This will a) remove the aperfmperf flag from /proc/cpuinfo b) not mislead the power scheduler (arch/x86/kernel/cpu/sched.c) to use the feature to improve scheduling (by default disabled) c) not mislead the cpufreq driver to use the MSRs This does not cover userland programs which access the MSRs via the device file interface, but this will be addressed separately. Signed-off-by: Andre Przywara Cc: stable@vger.kernel.org # v3.0+ Signed-off-by: Konrad Rzeszutek Wilk --- arch/x86/xen/enlighten.c | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'arch/x86') diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index d1f9a0472d4..272ebd0ce32 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -208,6 +208,9 @@ static void __init xen_banner(void) xen_feature(XENFEAT_mmu_pt_update_preserve_ad) ? " (preserve-AD)" : ""); } +#define CPUID_THERM_POWER_LEAF 6 +#define APERFMPERF_PRESENT 0 + static __read_mostly unsigned int cpuid_leaf1_edx_mask = ~0; static __read_mostly unsigned int cpuid_leaf1_ecx_mask = ~0; @@ -241,6 +244,11 @@ static void xen_cpuid(unsigned int *ax, unsigned int *bx, *dx = cpuid_leaf5_edx_val; return; + case CPUID_THERM_POWER_LEAF: + /* Disabling APERFMPERF for kernel usage */ + maskecx = ~(1 << APERFMPERF_PRESENT); + break; + case 0xb: /* Suppress extended topology stuff */ maskebx = 0; -- cgit v1.2.3-70-g09d2 From 76eb9a30db4bc8fd172f9155247264b5f2686d7b Mon Sep 17 00:00:00 2001 From: Zhang Rui Date: Mon, 20 Feb 2012 14:20:06 +0800 Subject: ACPI, x86: fix Dell M6600 ACPI reboot regression via DMI Dell Precision M6600 is known to require PCI reboot, so add it to the reboot blacklist in pci_reboot_dmi_table[]. https://bugzilla.kernel.org/show_bug.cgi?id=42749 cc: x86@kernel.org Signed-off-by: Zhang Rui Signed-off-by: Len Brown --- arch/x86/kernel/reboot.c | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'arch/x86') diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 79c45af8160..412db5716d9 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -451,6 +451,14 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 990"), }, }, + { /* Handle problems with rebooting on the Precision M6600. */ + .callback = set_pci_reboot, + .ident = "Dell OptiPlex 990", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Precision M6600"), + }, + }, { } }; -- cgit v1.2.3-70-g09d2 From 9271b0b4b2044c6db06051fe60bc58cdd4f17c7c Mon Sep 17 00:00:00 2001 From: Martin Pelikan Date: Sat, 9 Jun 2012 21:22:11 +0200 Subject: x86, um: Correct syscall table type attributes breaking gcc 4.8 The latest GCC 4.8 does some more checking on type attributes that break the build for ARCH=um -> fill them in. Specifically, the "asmlinkage" attributes is now tested for consistency. Signed-off-by: Martin Pelikan Link: http://lkml.kernel.org/r/1339269731-10772-1-git-send-email-pelikan@storkhole.cz Acked-by: Richard Weinberger Signed-off-by: H. Peter Anvin --- arch/x86/um/sys_call_table_32.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/um/sys_call_table_32.c b/arch/x86/um/sys_call_table_32.c index 416bd40c0eb..68d1dc91b37 100644 --- a/arch/x86/um/sys_call_table_32.c +++ b/arch/x86/um/sys_call_table_32.c @@ -39,9 +39,9 @@ #undef __SYSCALL_I386 #define __SYSCALL_I386(nr, sym, compat) [ nr ] = sym, -typedef void (*sys_call_ptr_t)(void); +typedef asmlinkage void (*sys_call_ptr_t)(void); -extern void sys_ni_syscall(void); +extern asmlinkage void sys_ni_syscall(void); const sys_call_ptr_t sys_call_table[] __cacheline_aligned = { /* -- cgit v1.2.3-70-g09d2 From 9efc31b81d740487fd204fade0913ffa8cc97fc3 Mon Sep 17 00:00:00 2001 From: Wanpeng Li Date: Sun, 10 Jun 2012 10:50:52 +0800 Subject: x86/mm: Fix some kernel-doc warnings Fix kernel-doc warnings in arch/x86/mm/ioremap.c and arch/x86/mm/pageattr.c, just like this one: Warning(arch/x86/mm/ioremap.c:204): No description found for parameter 'phys_addr' Warning(arch/x86/mm/ioremap.c:204): Excess function parameter 'offset' description in 'ioremap_nocache' Signed-off-by: Wanpeng Li Cc: Gavin Shan Cc: Wanpeng Li Link: http://lkml.kernel.org/r/1339296652-2935-1-git-send-email-liwp.linux@gmail.com Signed-off-by: Ingo Molnar --- arch/x86/mm/ioremap.c | 4 ++-- arch/x86/mm/pageattr.c | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index be1ef574ce9..78fe3f1ac49 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -180,7 +180,7 @@ err_free_memtype: /** * ioremap_nocache - map bus memory into CPU space - * @offset: bus address of the memory + * @phys_addr: bus address of the memory * @size: size of the resource to map * * ioremap_nocache performs a platform specific sequence of operations to @@ -217,7 +217,7 @@ EXPORT_SYMBOL(ioremap_nocache); /** * ioremap_wc - map memory into CPU space write combined - * @offset: bus address of the memory + * @phys_addr: bus address of the memory * @size: size of the resource to map * * This version of ioremap ensures that the memory is marked write combining. diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index e1ebde31521..a718e0d2350 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -122,7 +122,7 @@ within(unsigned long addr, unsigned long start, unsigned long end) /** * clflush_cache_range - flush a cache range with clflush - * @addr: virtual start address + * @vaddr: virtual start address * @size: number of bytes to flush * * clflush is an unordered instruction which needs fencing with mfence -- cgit v1.2.3-70-g09d2 From ae10ccdc3093486f8c2369d227583f9d79f628e5 Mon Sep 17 00:00:00 2001 From: Feng Tang Date: Mon, 4 Jun 2012 15:00:04 +0800 Subject: ACPI: Make acpi_skip_timer_override cover all source_irq==0 cases Currently when acpi_skip_timer_override is set, it only cover the (source_irq == 0 && global_irq == 2) cases. While there is also platform which need use this option and its global_irq is not 2. This patch will extend acpi_skip_timer_override to cover all timer overriding cases as long as the source irq is 0. This is the first part of a fix to kernel bug bugzilla 40002: "IRQ 0 assigned to VGA" https://bugzilla.kernel.org/show_bug.cgi?id=40002 Reported-and-tested-by: Szymon Kowalczyk Signed-off-by: Feng Tang Signed-off-by: Len Brown --- arch/x86/kernel/acpi/boot.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 8afb6931981..e7c698e9c7e 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -422,12 +422,14 @@ acpi_parse_int_src_ovr(struct acpi_subtable_header * header, return 0; } - if (intsrc->source_irq == 0 && intsrc->global_irq == 2) { + if (intsrc->source_irq == 0) { if (acpi_skip_timer_override) { - printk(PREFIX "BIOS IRQ0 pin2 override ignored.\n"); + printk(PREFIX "BIOS IRQ0 override ignored.\n"); return 0; } - if (acpi_fix_pin2_polarity && (intsrc->inti_flags & ACPI_MADT_POLARITY_MASK)) { + + if ((intsrc->global_irq == 2) && acpi_fix_pin2_polarity + && (intsrc->inti_flags & ACPI_MADT_POLARITY_MASK)) { intsrc->inti_flags &= ~ACPI_MADT_POLARITY_MASK; printk(PREFIX "BIOS IRQ0 pin2 override: forcing polarity to high active.\n"); } @@ -1334,7 +1336,7 @@ static int __init dmi_disable_acpi(const struct dmi_system_id *d) } /* - * Force ignoring BIOS IRQ0 pin2 override + * Force ignoring BIOS IRQ0 override */ static int __init dmi_ignore_irq0_timer_override(const struct dmi_system_id *d) { @@ -1344,7 +1346,7 @@ static int __init dmi_ignore_irq0_timer_override(const struct dmi_system_id *d) */ if (!acpi_skip_timer_override) { WARN(1, KERN_ERR "ati_ixp4x0 quirk not complete.\n"); - pr_notice("%s detected: Ignoring BIOS IRQ0 pin2 override\n", + pr_notice("%s detected: Ignoring BIOS IRQ0 override\n", d->ident); acpi_skip_timer_override = 1; } @@ -1438,7 +1440,7 @@ static struct dmi_system_id __initdata acpi_dmi_table_late[] = { * is enabled. This input is incorrectly designated the * ISA IRQ 0 via an interrupt source override even though * it is wired to the output of the master 8259A and INTIN0 - * is not connected at all. Force ignoring BIOS IRQ0 pin2 + * is not connected at all. Force ignoring BIOS IRQ0 * override in that cases. */ { -- cgit v1.2.3-70-g09d2 From 7f68b4c2e158019c2ec494b5cfbd9c83b4e5b253 Mon Sep 17 00:00:00 2001 From: Feng Tang Date: Mon, 4 Jun 2012 15:00:05 +0800 Subject: ACPI: Remove one board specific WARN when ignoring timer overriding Current WARN msg is only for the ati_ixp4x0 board, while this function is used by mulitple platforms. So this one board specific warning is not appropriate any more. Signed-off-by: Feng Tang Signed-off-by: Len Brown --- arch/x86/kernel/acpi/boot.c | 5 ----- 1 file changed, 5 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index e7c698e9c7e..3a6afba6eca 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -1340,12 +1340,7 @@ static int __init dmi_disable_acpi(const struct dmi_system_id *d) */ static int __init dmi_ignore_irq0_timer_override(const struct dmi_system_id *d) { - /* - * The ati_ixp4x0_rev() early PCI quirk should have set - * the acpi_skip_timer_override flag already: - */ if (!acpi_skip_timer_override) { - WARN(1, KERN_ERR "ati_ixp4x0 quirk not complete.\n"); pr_notice("%s detected: Ignoring BIOS IRQ0 override\n", d->ident); acpi_skip_timer_override = 1; -- cgit v1.2.3-70-g09d2 From f6b54f083cc66cf9b11d2120d8df3c2ad4e0836d Mon Sep 17 00:00:00 2001 From: Feng Tang Date: Mon, 4 Jun 2012 15:00:06 +0800 Subject: ACPI: Add a quirk for "AMILO PRO V2030" to ignore the timer overriding This is the 2nd part of fix for kernel bugzilla 40002: "IRQ 0 assigned to VGA" https://bugzilla.kernel.org/show_bug.cgi?id=40002 The root cause is the buggy FW, whose ACPI tables assign the GSI 16 to 2 irqs 0 and 16(VGA), and the VGA is the right owner of GSI 16. So add a quirk to ignore the irq0 overriding GSI 16 for the FUJITSU SIEMENS AMILO PRO V2030 platform will solve this issue. Reported-and-tested-by: Szymon Kowalczyk Signed-off-by: Feng Tang Signed-off-by: Len Brown --- arch/x86/kernel/acpi/boot.c | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'arch/x86') diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 3a6afba6eca..b2297e58c6e 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -1470,6 +1470,14 @@ static struct dmi_system_id __initdata acpi_dmi_table_late[] = { DMI_MATCH(DMI_PRODUCT_NAME, "HP Compaq 6715b"), }, }, + { + .callback = dmi_ignore_irq0_timer_override, + .ident = "FUJITSU SIEMENS", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU SIEMENS"), + DMI_MATCH(DMI_PRODUCT_NAME, "AMILO PRO V2030"), + }, + }, {} }; -- cgit v1.2.3-70-g09d2 From e32025a56403df4386cd61a741c0a36afe79ae8a Mon Sep 17 00:00:00 2001 From: Marcelo Tosatti Date: Mon, 11 Jun 2012 23:18:33 -0300 Subject: x86: kvmclock: remove check_and_clear_guest_paused warning CPU offline path calls the hrtimer interrupt handler with interrupts disabled, without touching preempt_count, triggering this warning. Remove the warning since it is supposed to be used from hrtimer interrupt context only. Signed-off-by: Marcelo Tosatti --- arch/x86/kernel/kvmclock.c | 5 ----- 1 file changed, 5 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index 086eb58c6e8..f1b42b3a186 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -120,11 +120,6 @@ bool kvm_check_and_clear_guest_paused(void) bool ret = false; struct pvclock_vcpu_time_info *src; - /* - * per_cpu() is safe here because this function is only called from - * timer functions where preemption is already disabled. - */ - WARN_ON(!in_atomic()); src = &__get_cpu_var(hv_clock); if ((src->flags & PVCLOCK_GUEST_STOPPED) != 0) { __this_cpu_and(hv_clock.flags, ~PVCLOCK_GUEST_STOPPED); -- cgit v1.2.3-70-g09d2 From 161270fc1f9ddfc17154e0d49291472a9cdef7db Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Wed, 6 Jun 2012 17:31:26 +0200 Subject: x86/smp: Fix topology checks on AMD MCM CPUs The warning below triggers on AMD MCM packages because physical package IDs on the cores of a _physical_ socket are the same. I.e., this field says which CPUs belong to the same physical package. However, the same two CPUs belong to two different internal, i.e. "logical" nodes in the same physical socket which is reflected in the CPU-to-node map on x86 with NUMA. Which makes this check wrong on the above topologies so circumvent it. [ 0.444413] Booting Node 0, Processors #1 #2 #3 #4 #5 Ok. [ 0.461388] ------------[ cut here ]------------ [ 0.465997] WARNING: at arch/x86/kernel/smpboot.c:310 topology_sane.clone.1+0x6e/0x81() [ 0.473960] Hardware name: Dinar [ 0.477170] sched: CPU #6's mc-sibling CPU #0 is not on the same node! [node: 1 != 0]. Ignoring dependency. [ 0.486860] Booting Node 1, Processors #6 [ 0.491104] Modules linked in: [ 0.494141] Pid: 0, comm: swapper/6 Not tainted 3.4.0+ #1 [ 0.499510] Call Trace: [ 0.501946] [] ? topology_sane.clone.1+0x6e/0x81 [ 0.508185] [] warn_slowpath_common+0x85/0x9d [ 0.514163] [] warn_slowpath_fmt+0x46/0x48 [ 0.519881] [] topology_sane.clone.1+0x6e/0x81 [ 0.525943] [] set_cpu_sibling_map+0x251/0x371 [ 0.532004] [] start_secondary+0x19a/0x218 [ 0.537729] ---[ end trace 4eaa2a86a8e2da22 ]--- [ 0.628197] #7 #8 #9 #10 #11 Ok. [ 0.807108] Booting Node 3, Processors #12 #13 #14 #15 #16 #17 Ok. [ 0.897587] Booting Node 2, Processors #18 #19 #20 #21 #22 #23 Ok. [ 0.917443] Brought up 24 CPUs We ran a topology sanity check test we have here on it and it all looks ok... hopefully :). Signed-off-by: Borislav Petkov Cc: Andreas Herrmann Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/20120529135442.GE29157@aftab.osrc.amd.com Signed-off-by: Ingo Molnar --- arch/x86/kernel/smpboot.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index fd019d78b1f..c3a6bacc8a3 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -349,9 +349,12 @@ static bool __cpuinit match_llc(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) static bool __cpuinit match_mc(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) { - if (c->phys_proc_id == o->phys_proc_id) - return topology_sane(c, o, "mc"); + if (c->phys_proc_id == o->phys_proc_id) { + if (cpu_has(c, X86_FEATURE_AMD_DCM)) + return true; + return topology_sane(c, o, "mc"); + } return false; } -- cgit v1.2.3-70-g09d2 From c080e26edc3a2a3cdfa4c430c663ee1c3bbd8fae Mon Sep 17 00:00:00 2001 From: Marek Szyprowski Date: Thu, 14 Jun 2012 14:01:30 +0200 Subject: x86: dma-mapping: fix broken allocation when dma_mask has been provided Commit 0a2b9a6ea93 ("X86: integrate CMA with DMA-mapping subsystem") broke memory allocation with dma_mask. This patch fixes possible kernel ops caused by lack of resetting page variable when jumping to 'again' label. Reported-by: Konrad Rzeszutek Wilk Signed-off-by: Marek Szyprowski Acked-by: Michal Nazarewicz --- arch/x86/kernel/pci-dma.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index 62c9457ccd2..c0f420f76cd 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -100,7 +100,7 @@ void *dma_generic_alloc_coherent(struct device *dev, size_t size, struct dma_attrs *attrs) { unsigned long dma_mask; - struct page *page = NULL; + struct page *page; unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT; dma_addr_t addr; @@ -108,6 +108,7 @@ void *dma_generic_alloc_coherent(struct device *dev, size_t size, flag |= __GFP_ZERO; again: + page = NULL; if (!(flag & GFP_ATOMIC)) page = dma_alloc_from_contiguous(dev, count, get_order(size)); if (!page) -- cgit v1.2.3-70-g09d2 From b9e0d95c041ca2d7ad297ee37c2e9cfab67a188f Mon Sep 17 00:00:00 2001 From: Stefano Stabellini Date: Wed, 23 May 2012 18:57:20 +0100 Subject: xen: mark local pages as FOREIGN in the m2p_override When the frontend and the backend reside on the same domain, even if we add pages to the m2p_override, these pages will never be returned by mfn_to_pfn because the check "get_phys_to_machine(pfn) != mfn" will always fail, so the pfn of the frontend will be returned instead (resulting in a deadlock because the frontend pages are already locked). INFO: task qemu-system-i38:1085 blocked for more than 120 seconds. "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. qemu-system-i38 D ffff8800cfc137c0 0 1085 1 0x00000000 ffff8800c47ed898 0000000000000282 ffff8800be4596b0 00000000000137c0 ffff8800c47edfd8 ffff8800c47ec010 00000000000137c0 00000000000137c0 ffff8800c47edfd8 00000000000137c0 ffffffff82213020 ffff8800be4596b0 Call Trace: [] ? __lock_page+0x70/0x70 [] schedule+0x29/0x70 [] io_schedule+0x60/0x80 [] sleep_on_page+0xe/0x20 [] __wait_on_bit_lock+0x5a/0xc0 [] __lock_page+0x67/0x70 [] ? autoremove_wake_function+0x40/0x40 [] ? bio_add_page+0x36/0x40 [] set_page_dirty_lock+0x52/0x60 [] bio_set_pages_dirty+0x51/0x70 [] do_blockdev_direct_IO+0xb24/0xeb0 [] ? ext3_get_blocks_handle+0xe00/0xe00 [] __blockdev_direct_IO+0x55/0x60 [] ? ext3_get_blocks_handle+0xe00/0xe00 [] ext3_direct_IO+0xf8/0x390 [] ? ext3_get_blocks_handle+0xe00/0xe00 [] ? xen_mc_flush+0xb0/0x1b0 [] generic_file_aio_read+0x737/0x780 [] ? gnttab_map_refs+0x15b/0x1e0 [] ? find_get_pages+0x150/0x150 [] aio_rw_vect_retry+0x7c/0x1d0 [] ? lookup_ioctx+0x90/0x90 [] aio_run_iocb+0x66/0x1a0 [] do_io_submit+0x708/0xb90 [] sys_io_submit+0x10/0x20 [] system_call_fastpath+0x16/0x1b The explanation is in the comment within the code: We need to do this because the pages shared by the frontend (xen-blkfront) can be already locked (lock_page, called by do_read_cache_page); when the userspace backend tries to use them with direct_IO, mfn_to_pfn returns the pfn of the frontend, so do_blockdev_direct_IO is going to try to lock the same pages again resulting in a deadlock. A simplified call graph looks like this: pygrub QEMU ----------------------------------------------- do_read_cache_page io_submit | | lock_page ext3_direct_IO | bio_add_page | lock_page Internally the xen-blkback uses m2p_add_override to swizzle (temporarily) a 'struct page' to have a different MFN (so that it can point to another guest). It also can easily find out whether another pfn corresponding to the mfn exists in the m2p, and can set the FOREIGN bit in the p2m, making sure that mfn_to_pfn returns the pfn of the backend. This allows the backend to perform direct_IO on these pages, but as a side effect prevents the frontend from using get_user_pages_fast on them while they are being shared with the backend. Signed-off-by: Stefano Stabellini Signed-off-by: Konrad Rzeszutek Wilk --- arch/x86/xen/p2m.c | 36 ++++++++++++++++++++++++++++++++++++ 1 file changed, 36 insertions(+) (limited to 'arch/x86') diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index ffd08c414e9..64effdc6da9 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -706,6 +706,7 @@ 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)) { @@ -741,6 +742,24 @@ int m2p_add_override(unsigned long mfn, struct page *page, list_add(&page->lru, &m2p_overrides[mfn_hash(mfn)]); spin_unlock_irqrestore(&m2p_override_lock, flags); + /* p2m(m2p(mfn)) == mfn: the mfn is already present somewhere in + * this domain. Set the FOREIGN_FRAME_BIT in the p2m for the other + * pfn so that the following mfn_to_pfn(mfn) calls will return the + * pfn from the m2p_override (the backend pfn) instead. + * We need to do this because the pages shared by the frontend + * (xen-blkfront) can be already locked (lock_page, called by + * do_read_cache_page); when the userspace backend tries to use them + * with direct_IO, mfn_to_pfn returns the pfn of the frontend, so + * do_blockdev_direct_IO is going to try to lock the same pages + * again resulting in a deadlock. + * As a side effect get_user_pages_fast might not be safe on the + * 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) + set_phys_to_machine(pfn, FOREIGN_FRAME(mfn)); + return 0; } EXPORT_SYMBOL_GPL(m2p_add_override); @@ -752,6 +771,7 @@ int m2p_remove_override(struct page *page, bool clear_pte) 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); @@ -821,6 +841,22 @@ int m2p_remove_override(struct page *page, bool clear_pte) } else set_phys_to_machine(pfn, page->index); + /* p2m(m2p(mfn)) == FOREIGN_FRAME(mfn): the mfn is already present + * somewhere in this domain, even before being added to the + * m2p_override (see comment above in m2p_add_override). + * If there are no other entries in the m2p_override corresponding + * to this mfn, then remove the FOREIGN_FRAME_BIT from the p2m for + * the original pfn (the one shared by the frontend): the backend + * cannot do any IO on this page anymore because it has been + * unshared. Removing the FOREIGN_FRAME_BIT from the p2m entry of + * 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) && + m2p_find_override(mfn) == NULL) + set_phys_to_machine(pfn, mfn); + return 0; } EXPORT_SYMBOL_GPL(m2p_remove_override); -- cgit v1.2.3-70-g09d2 From 0b91f45b23cb73ce11acdc3cf4c6efd4441e3b3e Mon Sep 17 00:00:00 2001 From: Suresh Siddha Date: Thu, 14 Jun 2012 18:07:15 -0700 Subject: x86, compat: Use test_thread_flag(TIF_IA32) in compat signal delivery Signal delivery compat path may not have the 'TS_COMPAT' flag (that flag indicates how we entered the kernel). So use test_thread_flag(TIF_IA32) instead of is_ia32_task(): one of the functions of TIF_IA32 is just what kind of signal frame we want. Signed-off-by: Suresh Siddha Link: http://lkml.kernel.org/r/1339722435.3475.57.camel@sbsiddha-desk.sc.intel.com Cc: stable@kernel.org # v3.4 Signed-off-by: H. Peter Anvin --- arch/x86/ia32/ia32_signal.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86') diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c index daeca56211e..673ac9b63d6 100644 --- a/arch/x86/ia32/ia32_signal.c +++ b/arch/x86/ia32/ia32_signal.c @@ -38,7 +38,7 @@ int copy_siginfo_to_user32(compat_siginfo_t __user *to, siginfo_t *from) { int err = 0; - bool ia32 = is_ia32_task(); + bool ia32 = test_thread_flag(TIF_IA32); if (!access_ok(VERIFY_WRITE, to, sizeof(compat_siginfo_t))) return -EFAULT; -- cgit v1.2.3-70-g09d2 From e2ae715d66bf4becfb85eb84b7150e23cf27df30 Mon Sep 17 00:00:00 2001 From: Kay Sievers Date: Fri, 15 Jun 2012 14:07:51 +0200 Subject: kmsg - kmsg_dump() use iterator to receive log buffer content Provide an iterator to receive the log buffer content, and convert all kmsg_dump() users to it. The structured data in the kmsg buffer now contains binary data, which should no longer be copied verbatim to the kmsg_dump() users. The iterator should provide reliable access to the buffer data, and also supports proper log line-aware chunking of data while iterating. Signed-off-by: Kay Sievers Tested-by: Tony Luck Reported-by: Anton Vorontsov Tested-by: Anton Vorontsov Signed-off-by: Greg Kroah-Hartman --- arch/powerpc/platforms/pseries/nvram.c | 61 +------- arch/x86/platform/mrst/early_printk_mrst.c | 13 +- drivers/mtd/mtdoops.c | 22 +-- fs/pstore/platform.c | 34 ++--- include/linux/kmsg_dump.h | 45 +++++- kernel/printk.c | 220 +++++++++++++++++++++++++---- 6 files changed, 258 insertions(+), 137 deletions(-) (limited to 'arch/x86') diff --git a/arch/powerpc/platforms/pseries/nvram.c b/arch/powerpc/platforms/pseries/nvram.c index 36f957f3184..8733a86ad52 100644 --- a/arch/powerpc/platforms/pseries/nvram.c +++ b/arch/powerpc/platforms/pseries/nvram.c @@ -68,9 +68,7 @@ static const char *pseries_nvram_os_partitions[] = { }; static void oops_to_nvram(struct kmsg_dumper *dumper, - enum kmsg_dump_reason reason, - const char *old_msgs, unsigned long old_len, - const char *new_msgs, unsigned long new_len); + enum kmsg_dump_reason reason); static struct kmsg_dumper nvram_kmsg_dumper = { .dump = oops_to_nvram @@ -503,28 +501,6 @@ int __init pSeries_nvram_init(void) return 0; } -/* - * Try to capture the last capture_len bytes of the printk buffer. Return - * the amount actually captured. - */ -static size_t capture_last_msgs(const char *old_msgs, size_t old_len, - const char *new_msgs, size_t new_len, - char *captured, size_t capture_len) -{ - if (new_len >= capture_len) { - memcpy(captured, new_msgs + (new_len - capture_len), - capture_len); - return capture_len; - } else { - /* Grab the end of old_msgs. */ - size_t old_tail_len = min(old_len, capture_len - new_len); - memcpy(captured, old_msgs + (old_len - old_tail_len), - old_tail_len); - memcpy(captured + old_tail_len, new_msgs, new_len); - return old_tail_len + new_len; - } -} - /* * Are we using the ibm,rtas-log for oops/panic reports? And if so, * would logging this oops/panic overwrite an RTAS event that rtas_errd @@ -541,27 +517,6 @@ static int clobbering_unread_rtas_event(void) NVRAM_RTAS_READ_TIMEOUT); } -/* Squeeze out each line's severity prefix. */ -static size_t elide_severities(char *buf, size_t len) -{ - char *in, *out, *buf_end = buf + len; - /* Assume a at the very beginning marks the start of a line. */ - int newline = 1; - - in = out = buf; - while (in < buf_end) { - if (newline && in+3 <= buf_end && - *in == '<' && isdigit(in[1]) && in[2] == '>') { - in += 3; - newline = 0; - } else { - newline = (*in == '\n'); - *out++ = *in++; - } - } - return out - buf; -} - /* Derived from logfs_compress() */ static int nvram_compress(const void *in, void *out, size_t inlen, size_t outlen) @@ -619,9 +574,7 @@ static int zip_oops(size_t text_len) * partition. If that's too much, go back and capture uncompressed text. */ static void oops_to_nvram(struct kmsg_dumper *dumper, - enum kmsg_dump_reason reason, - const char *old_msgs, unsigned long old_len, - const char *new_msgs, unsigned long new_len) + enum kmsg_dump_reason reason) { static unsigned int oops_count = 0; static bool panicking = false; @@ -660,14 +613,14 @@ static void oops_to_nvram(struct kmsg_dumper *dumper, return; if (big_oops_buf) { - text_len = capture_last_msgs(old_msgs, old_len, - new_msgs, new_len, big_oops_buf, big_oops_buf_sz); - text_len = elide_severities(big_oops_buf, text_len); + kmsg_dump_get_buffer(dumper, false, + big_oops_buf, big_oops_buf_sz, &text_len); rc = zip_oops(text_len); } if (rc != 0) { - text_len = capture_last_msgs(old_msgs, old_len, - new_msgs, new_len, oops_data, oops_data_sz); + kmsg_dump_rewind(dumper); + kmsg_dump_get_buffer(dumper, true, + oops_data, oops_data_sz, &text_len); err_type = ERR_TYPE_KERNEL_PANIC; *oops_len = (u16) text_len; } diff --git a/arch/x86/platform/mrst/early_printk_mrst.c b/arch/x86/platform/mrst/early_printk_mrst.c index 3c6e328483c..028454f0c3a 100644 --- a/arch/x86/platform/mrst/early_printk_mrst.c +++ b/arch/x86/platform/mrst/early_printk_mrst.c @@ -110,19 +110,16 @@ static struct kmsg_dumper dw_dumper; static int dumper_registered; static void dw_kmsg_dump(struct kmsg_dumper *dumper, - enum kmsg_dump_reason reason, - const char *s1, unsigned long l1, - const char *s2, unsigned long l2) + enum kmsg_dump_reason reason) { - int i; + static char line[1024]; + size_t len; /* When run to this, we'd better re-init the HW */ mrst_early_console_init(); - for (i = 0; i < l1; i++) - early_mrst_console.write(&early_mrst_console, s1 + i, 1); - for (i = 0; i < l2; i++) - early_mrst_console.write(&early_mrst_console, s2 + i, 1); + while (kmsg_dump_get_line(dumper, true, line, sizeof(line), &len)) + early_mrst_console.write(&early_mrst_console, line, len); } /* Set the ratio rate to 115200, 8n1, IRQ disabled */ diff --git a/drivers/mtd/mtdoops.c b/drivers/mtd/mtdoops.c index ae36d7e1e91..551e316e445 100644 --- a/drivers/mtd/mtdoops.c +++ b/drivers/mtd/mtdoops.c @@ -304,32 +304,17 @@ static void find_next_position(struct mtdoops_context *cxt) } static void mtdoops_do_dump(struct kmsg_dumper *dumper, - enum kmsg_dump_reason reason, const char *s1, unsigned long l1, - const char *s2, unsigned long l2) + enum kmsg_dump_reason reason) { struct mtdoops_context *cxt = container_of(dumper, struct mtdoops_context, dump); - unsigned long s1_start, s2_start; - unsigned long l1_cpy, l2_cpy; - char *dst; - - if (reason != KMSG_DUMP_OOPS && - reason != KMSG_DUMP_PANIC) - return; /* Only dump oopses if dump_oops is set */ if (reason == KMSG_DUMP_OOPS && !dump_oops) return; - dst = cxt->oops_buf + MTDOOPS_HEADER_SIZE; /* Skip the header */ - l2_cpy = min(l2, record_size - MTDOOPS_HEADER_SIZE); - l1_cpy = min(l1, record_size - MTDOOPS_HEADER_SIZE - l2_cpy); - - s2_start = l2 - l2_cpy; - s1_start = l1 - l1_cpy; - - memcpy(dst, s1 + s1_start, l1_cpy); - memcpy(dst + l1_cpy, s2 + s2_start, l2_cpy); + kmsg_dump_get_buffer(dumper, true, cxt->oops_buf + MTDOOPS_HEADER_SIZE, + record_size - MTDOOPS_HEADER_SIZE, NULL); /* Panics must be written immediately */ if (reason != KMSG_DUMP_OOPS) @@ -375,6 +360,7 @@ static void mtdoops_notify_add(struct mtd_info *mtd) return; } + cxt->dump.max_reason = KMSG_DUMP_OOPS; cxt->dump.dump = mtdoops_do_dump; err = kmsg_dump_register(&cxt->dump); if (err) { diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c index 82c585f715e..03ce7a9b81c 100644 --- a/fs/pstore/platform.c +++ b/fs/pstore/platform.c @@ -94,20 +94,15 @@ static const char *get_reason_str(enum kmsg_dump_reason reason) * as we can from the end of the buffer. */ static void pstore_dump(struct kmsg_dumper *dumper, - enum kmsg_dump_reason reason, - const char *s1, unsigned long l1, - const char *s2, unsigned long l2) + enum kmsg_dump_reason reason) { - unsigned long s1_start, s2_start; - unsigned long l1_cpy, l2_cpy; - unsigned long size, total = 0; - char *dst; + unsigned long total = 0; const char *why; u64 id; - int hsize, ret; unsigned int part = 1; unsigned long flags = 0; int is_locked = 0; + int ret; why = get_reason_str(reason); @@ -119,30 +114,25 @@ static void pstore_dump(struct kmsg_dumper *dumper, spin_lock_irqsave(&psinfo->buf_lock, flags); oopscount++; while (total < kmsg_bytes) { + char *dst; + unsigned long size; + int hsize; + size_t len; + dst = psinfo->buf; hsize = sprintf(dst, "%s#%d Part%d\n", why, oopscount, part); size = psinfo->bufsize - hsize; dst += hsize; - l2_cpy = min(l2, size); - l1_cpy = min(l1, size - l2_cpy); - - if (l1_cpy + l2_cpy == 0) + if (!kmsg_dump_get_buffer(dumper, true, dst, size, &len)) break; - s2_start = l2 - l2_cpy; - s1_start = l1 - l1_cpy; - - memcpy(dst, s1 + s1_start, l1_cpy); - memcpy(dst + l1_cpy, s2 + s2_start, l2_cpy); - ret = psinfo->write(PSTORE_TYPE_DMESG, reason, &id, part, - hsize + l1_cpy + l2_cpy, psinfo); + hsize + len, psinfo); if (ret == 0 && reason == KMSG_DUMP_OOPS && pstore_is_mounted()) pstore_new_entry = 1; - l1 -= l1_cpy; - l2 -= l2_cpy; - total += l1_cpy + l2_cpy; + + total += hsize + len; part++; } if (in_nmi()) { diff --git a/include/linux/kmsg_dump.h b/include/linux/kmsg_dump.h index 35f7237ec97..af4eb5a39d9 100644 --- a/include/linux/kmsg_dump.h +++ b/include/linux/kmsg_dump.h @@ -21,6 +21,7 @@ * is passed to the kernel. */ enum kmsg_dump_reason { + KMSG_DUMP_UNDEF, KMSG_DUMP_PANIC, KMSG_DUMP_OOPS, KMSG_DUMP_EMERG, @@ -31,23 +32,37 @@ enum kmsg_dump_reason { /** * struct kmsg_dumper - kernel crash message dumper structure - * @dump: The callback which gets called on crashes. The buffer is passed - * as two sections, where s1 (length l1) contains the older - * messages and s2 (length l2) contains the newer. * @list: Entry in the dumper list (private) + * @dump: Call into dumping code which will retrieve the data with + * through the record iterator + * @max_reason: filter for highest reason number that should be dumped * @registered: Flag that specifies if this is already registered */ struct kmsg_dumper { - void (*dump)(struct kmsg_dumper *dumper, enum kmsg_dump_reason reason, - const char *s1, unsigned long l1, - const char *s2, unsigned long l2); struct list_head list; - int registered; + void (*dump)(struct kmsg_dumper *dumper, enum kmsg_dump_reason reason); + enum kmsg_dump_reason max_reason; + bool active; + bool registered; + + /* private state of the kmsg iterator */ + u32 cur_idx; + u32 next_idx; + u64 cur_seq; + u64 next_seq; }; #ifdef CONFIG_PRINTK void kmsg_dump(enum kmsg_dump_reason reason); +bool kmsg_dump_get_line(struct kmsg_dumper *dumper, bool syslog, + char *line, size_t size, size_t *len); + +bool kmsg_dump_get_buffer(struct kmsg_dumper *dumper, bool syslog, + char *buf, size_t size, size_t *len); + +void kmsg_dump_rewind(struct kmsg_dumper *dumper); + int kmsg_dump_register(struct kmsg_dumper *dumper); int kmsg_dump_unregister(struct kmsg_dumper *dumper); @@ -56,6 +71,22 @@ static inline void kmsg_dump(enum kmsg_dump_reason reason) { } +bool kmsg_dump_get_line(struct kmsg_dumper *dumper, bool syslog, + const char *line, size_t size, size_t *len) +{ + return false; +} + +bool kmsg_dump_get_buffer(struct kmsg_dumper *dumper, bool syslog, + char *buf, size_t size, size_t *len) +{ + return false; +} + +void kmsg_dump_rewind(struct kmsg_dumper *dumper) +{ +} + static inline int kmsg_dump_register(struct kmsg_dumper *dumper) { return -EINVAL; diff --git a/kernel/printk.c b/kernel/printk.c index f205c25c37e..ceb4a2f775a 100644 --- a/kernel/printk.c +++ b/kernel/printk.c @@ -909,7 +909,7 @@ static int syslog_print_all(char __user *buf, int size, bool clear) /* * Find first record that fits, including all following records, * into the user-provided buffer for this dump. - */ + */ seq = clear_seq; idx = clear_idx; while (seq < log_next_seq) { @@ -919,6 +919,8 @@ static int syslog_print_all(char __user *buf, int size, bool clear) idx = log_next(idx); seq++; } + + /* move first record forward until length fits into the buffer */ seq = clear_seq; idx = clear_idx; while (len > size && seq < log_next_seq) { @@ -929,7 +931,7 @@ static int syslog_print_all(char __user *buf, int size, bool clear) seq++; } - /* last message in this dump */ + /* last message fitting into this dump */ next_seq = log_next_seq; len = 0; @@ -2300,48 +2302,210 @@ module_param_named(always_kmsg_dump, always_kmsg_dump, bool, S_IRUGO | S_IWUSR); * kmsg_dump - dump kernel log to kernel message dumpers. * @reason: the reason (oops, panic etc) for dumping * - * Iterate through each of the dump devices and call the oops/panic - * callbacks with the log buffer. + * Call each of the registered dumper's dump() callback, which can + * retrieve the kmsg records with kmsg_dump_get_line() or + * kmsg_dump_get_buffer(). */ void kmsg_dump(enum kmsg_dump_reason reason) { - u64 idx; struct kmsg_dumper *dumper; - const char *s1, *s2; - unsigned long l1, l2; unsigned long flags; if ((reason > KMSG_DUMP_OOPS) && !always_kmsg_dump) return; - /* Theoretically, the log could move on after we do this, but - there's not a lot we can do about that. The new messages - will overwrite the start of what we dump. */ + rcu_read_lock(); + list_for_each_entry_rcu(dumper, &dump_list, list) { + if (dumper->max_reason && reason > dumper->max_reason) + continue; + + /* initialize iterator with data about the stored records */ + dumper->active = true; + + raw_spin_lock_irqsave(&logbuf_lock, flags); + dumper->cur_seq = clear_seq; + dumper->cur_idx = clear_idx; + dumper->next_seq = log_next_seq; + dumper->next_idx = log_next_idx; + raw_spin_unlock_irqrestore(&logbuf_lock, flags); + + /* invoke dumper which will iterate over records */ + dumper->dump(dumper, reason); + + /* reset iterator */ + dumper->active = false; + } + rcu_read_unlock(); +} + +/** + * kmsg_dump_get_line - retrieve one kmsg log line + * @dumper: registered kmsg dumper + * @syslog: include the "<4>" prefixes + * @line: buffer to copy the line to + * @size: maximum size of the buffer + * @len: length of line placed into buffer + * + * Start at the beginning of the kmsg buffer, with the oldest kmsg + * record, and copy one record into the provided buffer. + * + * Consecutive calls will return the next available record moving + * towards the end of the buffer with the youngest messages. + * + * A return value of FALSE indicates that there are no more records to + * read. + */ +bool kmsg_dump_get_line(struct kmsg_dumper *dumper, bool syslog, + char *line, size_t size, size_t *len) +{ + unsigned long flags; + struct log *msg; + size_t l = 0; + bool ret = false; + + if (!dumper->active) + goto out; raw_spin_lock_irqsave(&logbuf_lock, flags); - if (syslog_seq < log_first_seq) - idx = syslog_idx; - else - idx = log_first_idx; + if (dumper->cur_seq < log_first_seq) { + /* messages are gone, move to first available one */ + dumper->cur_seq = log_first_seq; + dumper->cur_idx = log_first_idx; + } - if (idx > log_next_idx) { - s1 = log_buf; - l1 = log_next_idx; + /* last entry */ + if (dumper->cur_seq >= log_next_seq) { + raw_spin_unlock_irqrestore(&logbuf_lock, flags); + goto out; + } - s2 = log_buf + idx; - l2 = log_buf_len - idx; - } else { - s1 = ""; - l1 = 0; + msg = log_from_idx(dumper->cur_idx); + l = msg_print_text(msg, syslog, + line, size); + + dumper->cur_idx = log_next(dumper->cur_idx); + dumper->cur_seq++; + ret = true; + raw_spin_unlock_irqrestore(&logbuf_lock, flags); +out: + if (len) + *len = l; + return ret; +} +EXPORT_SYMBOL_GPL(kmsg_dump_get_line); + +/** + * kmsg_dump_get_buffer - copy kmsg log lines + * @dumper: registered kmsg dumper + * @syslog: include the "<4>" prefixes + * @line: buffer to copy the line to + * @size: maximum size of the buffer + * @len: length of line placed into buffer + * + * Start at the end of the kmsg buffer and fill the provided buffer + * with as many of the the *youngest* kmsg records that fit into it. + * If the buffer is large enough, all available kmsg records will be + * copied with a single call. + * + * Consecutive calls will fill the buffer with the next block of + * available older records, not including the earlier retrieved ones. + * + * A return value of FALSE indicates that there are no more records to + * read. + */ +bool kmsg_dump_get_buffer(struct kmsg_dumper *dumper, bool syslog, + char *buf, size_t size, size_t *len) +{ + unsigned long flags; + u64 seq; + u32 idx; + u64 next_seq; + u32 next_idx; + size_t l = 0; + bool ret = false; + + if (!dumper->active) + goto out; + + raw_spin_lock_irqsave(&logbuf_lock, flags); + if (dumper->cur_seq < log_first_seq) { + /* messages are gone, move to first available one */ + dumper->cur_seq = log_first_seq; + dumper->cur_idx = log_first_idx; + } + + /* last entry */ + if (dumper->cur_seq >= dumper->next_seq) { + raw_spin_unlock_irqrestore(&logbuf_lock, flags); + goto out; + } + + /* calculate length of entire buffer */ + seq = dumper->cur_seq; + idx = dumper->cur_idx; + while (seq < dumper->next_seq) { + struct log *msg = log_from_idx(idx); + + l += msg_print_text(msg, true, NULL, 0); + idx = log_next(idx); + seq++; + } + + /* move first record forward until length fits into the buffer */ + seq = dumper->cur_seq; + idx = dumper->cur_idx; + while (l > size && seq < dumper->next_seq) { + struct log *msg = log_from_idx(idx); - s2 = log_buf + idx; - l2 = log_next_idx - idx; + l -= msg_print_text(msg, true, NULL, 0); + idx = log_next(idx); + seq++; } + + /* last message in next interation */ + next_seq = seq; + next_idx = idx; + + l = 0; + while (seq < dumper->next_seq) { + struct log *msg = log_from_idx(idx); + + l += msg_print_text(msg, syslog, + buf + l, size - l); + + idx = log_next(idx); + seq++; + } + + dumper->next_seq = next_seq; + dumper->next_idx = next_idx; + ret = true; raw_spin_unlock_irqrestore(&logbuf_lock, flags); +out: + if (len) + *len = l; + return ret; +} +EXPORT_SYMBOL_GPL(kmsg_dump_get_buffer); - rcu_read_lock(); - list_for_each_entry_rcu(dumper, &dump_list, list) - dumper->dump(dumper, reason, s1, l1, s2, l2); - rcu_read_unlock(); +/** + * kmsg_dump_rewind - reset the interator + * @dumper: registered kmsg dumper + * + * Reset the dumper's iterator so that kmsg_dump_get_line() and + * kmsg_dump_get_buffer() can be called again and used multiple + * times within the same dumper.dump() callback. + */ +void kmsg_dump_rewind(struct kmsg_dumper *dumper) +{ + unsigned long flags; + + raw_spin_lock_irqsave(&logbuf_lock, flags); + dumper->cur_seq = clear_seq; + dumper->cur_idx = clear_idx; + dumper->next_seq = log_next_seq; + dumper->next_idx = log_next_idx; + raw_spin_unlock_irqrestore(&logbuf_lock, flags); } +EXPORT_SYMBOL_GPL(kmsg_dump_rewind); #endif -- cgit v1.2.3-70-g09d2 From c15acff337ca5c2f101fee99f36c89d47839d387 Mon Sep 17 00:00:00 2001 From: Wanpeng Li Date: Tue, 12 Jun 2012 12:53:21 +0800 Subject: x86: Fix kernel-doc warnings Signed-off-by: Wanpeng Li Cc: Peter Zijlstra Cc: Jason Wessel Cc: Jan Kiszka Cc: Gavin Shan Cc: Wanpeng Li Signed-off-by: Ingo Molnar --- arch/x86/kernel/kgdb.c | 8 ++++---- arch/x86/lib/csum-wrappers_64.c | 2 +- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c index 8bfb6146f75..3f61904365c 100644 --- a/arch/x86/kernel/kgdb.c +++ b/arch/x86/kernel/kgdb.c @@ -444,12 +444,12 @@ void kgdb_roundup_cpus(unsigned long flags) /** * kgdb_arch_handle_exception - Handle architecture specific GDB packets. - * @vector: The error vector of the exception that happened. + * @e_vector: The error vector of the exception that happened. * @signo: The signal number of the exception that happened. * @err_code: The error code of the exception that happened. - * @remcom_in_buffer: The buffer of the packet we have read. - * @remcom_out_buffer: The buffer of %BUFMAX bytes to write a packet into. - * @regs: The &struct pt_regs of the current process. + * @remcomInBuffer: The buffer of the packet we have read. + * @remcomOutBuffer: The buffer of %BUFMAX bytes to write a packet into. + * @linux_regs: The &struct pt_regs of the current process. * * This function MUST handle the 'c' and 's' command packets, * as well packets to set / remove a hardware breakpoint, if used. diff --git a/arch/x86/lib/csum-wrappers_64.c b/arch/x86/lib/csum-wrappers_64.c index 459b58a8a15..25b7ae8d058 100644 --- a/arch/x86/lib/csum-wrappers_64.c +++ b/arch/x86/lib/csum-wrappers_64.c @@ -115,7 +115,7 @@ EXPORT_SYMBOL(csum_partial_copy_to_user); * @src: source address * @dst: destination address * @len: number of bytes to be copied. - * @isum: initial sum that is added into the result (32bit unfolded) + * @sum: initial sum that is added into the result (32bit unfolded) * * Returns an 32bit unfolded checksum of the buffer. */ -- cgit v1.2.3-70-g09d2 From e4eed03fd06578571c01d4f1478c874bb432c815 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Wed, 20 Jun 2012 12:52:57 -0700 Subject: thp: avoid atomic64_read in pmd_read_atomic for 32bit PAE In the x86 32bit PAE CONFIG_TRANSPARENT_HUGEPAGE=y case while holding the mmap_sem for reading, cmpxchg8b cannot be used to read pmd contents under Xen. So instead of dealing only with "consistent" pmdvals in pmd_none_or_trans_huge_or_clear_bad() (which would be conceptually simpler) we let pmd_none_or_trans_huge_or_clear_bad() deal with pmdvals where the low 32bit and high 32bit could be inconsistent (to avoid having to use cmpxchg8b). The only guarantee we get from pmd_read_atomic is that if the low part of the pmd was found null, the high part will be null too (so the pmd will be considered unstable). And if the low part of the pmd is found "stable" later, then it means the whole pmd was read atomically (because after a pmd is stable, neither MADV_DONTNEED nor page faults can alter it anymore, and we read the high part after the low part). In the 32bit PAE x86 case, it is enough to read the low part of the pmdval atomically to declare the pmd as "stable" and that's true for THP and no THP, furthermore in the THP case we also have a barrier() that will prevent any inconsistent pmdvals to be cached by a later re-read of the *pmd. Signed-off-by: Andrea Arcangeli Cc: Jonathan Nieder Cc: Ulrich Obergfell Cc: Mel Gorman Cc: Hugh Dickins Cc: Larry Woodman Cc: Petr Matousek Cc: Rik van Riel Cc: Jan Beulich Cc: KOSAKI Motohiro Tested-by: Andrew Jones Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/include/asm/pgtable-3level.h | 30 +++++++++++++++++------------- include/asm-generic/pgtable.h | 10 ++++++++++ 2 files changed, 27 insertions(+), 13 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h index 43876f16caf..cb00ccc7d57 100644 --- a/arch/x86/include/asm/pgtable-3level.h +++ b/arch/x86/include/asm/pgtable-3level.h @@ -47,16 +47,26 @@ static inline void native_set_pte(pte_t *ptep, pte_t pte) * they can run pmd_offset_map_lock or pmd_trans_huge or other pmd * operations. * - * Without THP if the mmap_sem is hold for reading, the - * pmd can only transition from null to not null while pmd_read_atomic runs. - * So there's no need of literally reading it atomically. + * Without THP if the mmap_sem is hold for reading, the pmd can only + * transition from null to not null while pmd_read_atomic runs. So + * we can always return atomic pmd values with this function. * * With THP if the mmap_sem is hold for reading, the pmd can become - * THP or null or point to a pte (and in turn become "stable") at any - * time under pmd_read_atomic, so it's mandatory to read it atomically - * with cmpxchg8b. + * trans_huge or none or point to a pte (and in turn become "stable") + * at any time under pmd_read_atomic. We could read it really + * atomically here with a atomic64_read for the THP enabled case (and + * it would be a whole lot simpler), but to avoid using cmpxchg8b we + * only return an atomic pmdval if the low part of the pmdval is later + * found stable (i.e. pointing to a pte). And we're returning a none + * pmdval if the low part of the pmd is none. In some cases the high + * and low part of the pmdval returned may not be consistent if THP is + * enabled (the low part may point to previously mapped hugepage, + * while the high part may point to a more recently mapped hugepage), + * but pmd_none_or_trans_huge_or_clear_bad() only needs the low part + * of the pmd to be read atomically to decide if the pmd is unstable + * or not, with the only exception of when the low part of the pmd is + * zero in which case we return a none pmd. */ -#ifndef CONFIG_TRANSPARENT_HUGEPAGE static inline pmd_t pmd_read_atomic(pmd_t *pmdp) { pmdval_t ret; @@ -74,12 +84,6 @@ static inline pmd_t pmd_read_atomic(pmd_t *pmdp) return (pmd_t) { ret }; } -#else /* CONFIG_TRANSPARENT_HUGEPAGE */ -static inline pmd_t pmd_read_atomic(pmd_t *pmdp) -{ - return (pmd_t) { atomic64_read((atomic64_t *)pmdp) }; -} -#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ static inline void native_set_pte_atomic(pte_t *ptep, pte_t pte) { diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h index 6f2b45a9b6b..ff4947b7a97 100644 --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -484,6 +484,16 @@ static inline int pmd_none_or_trans_huge_or_clear_bad(pmd_t *pmd) /* * The barrier will stabilize the pmdval in a register or on * the stack so that it will stop changing under the code. + * + * When CONFIG_TRANSPARENT_HUGEPAGE=y on x86 32bit PAE, + * pmd_read_atomic is allowed to return a not atomic pmdval + * (for example pointing to an hugepage that has never been + * mapped in the pmd). The below checks will only care about + * the low part of the pmd with 32bit PAE x86 anyway, with the + * exception of pmd_none(). So the important thing is that if + * the low part of the pmd is found null, the high part will + * be also null or the pmd_none() check below would be + * confused. */ #ifdef CONFIG_TRANSPARENT_HUGEPAGE barrier(); -- cgit v1.2.3-70-g09d2 From 4ad33411308596f2f918603509729922a1ec4411 Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin" Date: Fri, 22 Jun 2012 10:58:06 -0700 Subject: x86, cpufeature: Rename X86_FEATURE_DTS to X86_FEATURE_DTHERM It makes sense to label "Digital Thermal Sensor" as "DTS", but unfortunately the string "dts" was already used for "Debug Store", and /proc/cpuinfo is a user space ABI. Therefore, rename this to "dtherm". This conflict went into mainline via the hwmon tree without any x86 maintainer ack, and without any kind of hint in the subject. a4659053 x86/hwmon: fix initialization of coretemp Reported-by: Jean Delvare Link: http://lkml.kernel.org/r/4FE34BCB.5050305@linux.intel.com Cc: Jan Beulich Cc: v2.6.36..v3.4 Signed-off-by: H. Peter Anvin --- arch/x86/include/asm/cpufeature.h | 2 +- arch/x86/kernel/cpu/scattered.c | 2 +- drivers/hwmon/coretemp.c | 4 ++-- 3 files changed, 4 insertions(+), 4 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 340ee49961a..f91e80f4f18 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -176,7 +176,7 @@ #define X86_FEATURE_XSAVEOPT (7*32+ 4) /* Optimized Xsave */ #define X86_FEATURE_PLN (7*32+ 5) /* Intel Power Limit Notification */ #define X86_FEATURE_PTS (7*32+ 6) /* Intel Package Thermal Status */ -#define X86_FEATURE_DTS (7*32+ 7) /* Digital Thermal Sensor */ +#define X86_FEATURE_DTHERM (7*32+ 7) /* Digital Thermal Sensor */ #define X86_FEATURE_HW_PSTATE (7*32+ 8) /* AMD HW-PState */ /* Virtualization flags: Linux defined, word 8 */ diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index addf9e82a7f..ee8e9abc859 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -31,7 +31,7 @@ void __cpuinit init_scattered_cpuid_features(struct cpuinfo_x86 *c) const struct cpuid_bit *cb; static const struct cpuid_bit __cpuinitconst cpuid_bits[] = { - { X86_FEATURE_DTS, CR_EAX, 0, 0x00000006, 0 }, + { X86_FEATURE_DTHERM, CR_EAX, 0, 0x00000006, 0 }, { X86_FEATURE_IDA, CR_EAX, 1, 0x00000006, 0 }, { X86_FEATURE_ARAT, CR_EAX, 2, 0x00000006, 0 }, { X86_FEATURE_PLN, CR_EAX, 4, 0x00000006, 0 }, diff --git a/drivers/hwmon/coretemp.c b/drivers/hwmon/coretemp.c index b9d512331ed..0f52799973d 100644 --- a/drivers/hwmon/coretemp.c +++ b/drivers/hwmon/coretemp.c @@ -664,7 +664,7 @@ static void __cpuinit get_core_online(unsigned int cpu) * sensors. We check this bit only, all the early CPUs * without thermal sensors will be filtered out. */ - if (!cpu_has(c, X86_FEATURE_DTS)) + if (!cpu_has(c, X86_FEATURE_DTHERM)) return; if (!pdev) { @@ -765,7 +765,7 @@ static struct notifier_block coretemp_cpu_notifier __refdata = { }; static const struct x86_cpu_id coretemp_ids[] = { - { X86_VENDOR_INTEL, X86_FAMILY_ANY, X86_MODEL_ANY, X86_FEATURE_DTS }, + { X86_VENDOR_INTEL, X86_FAMILY_ANY, X86_MODEL_ANY, X86_FEATURE_DTHERM }, {} }; MODULE_DEVICE_TABLE(x86cpu, coretemp_ids); -- cgit v1.2.3-70-g09d2 From 55f6cb9d0b364e7e8cb65b51193f5e4743c44fde Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin" Date: Fri, 22 Jun 2012 11:47:15 -0700 Subject: x86, cpufeature: Catch duplicate CPU feature strings We had a case of duplicate CPU feature strings, a user space ABI violation, for almost two years. Make it a build error so that doesn't happen again. Link: http://lkml.kernel.org/r/4FE34BCB.5050305@linux.intel.com Cc: Jan Beulich Cc: Jean Delvare --- arch/x86/kernel/cpu/mkcapflags.pl | 23 ++++++++++++++++++----- 1 file changed, 18 insertions(+), 5 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/cpu/mkcapflags.pl b/arch/x86/kernel/cpu/mkcapflags.pl index dfea390e160..0c5b54919c7 100644 --- a/arch/x86/kernel/cpu/mkcapflags.pl +++ b/arch/x86/kernel/cpu/mkcapflags.pl @@ -11,22 +11,35 @@ open(OUT, "> $out\0") or die "$0: cannot create: $out: $!\n"; print OUT "#include \n\n"; print OUT "const char * const x86_cap_flags[NCAPINTS*32] = {\n"; +%features = (); +$err = 0; + while (defined($line = )) { if ($line =~ /^\s*\#\s*define\s+(X86_FEATURE_(\S+))\s+(.*)$/) { $macro = $1; - $feature = $2; + $feature = "\L$2"; $tail = $3; if ($tail =~ /\/\*\s*\"([^"]*)\".*\*\//) { - $feature = $1; + $feature = "\L$1"; } - if ($feature ne '') { - printf OUT "\t%-32s = \"%s\",\n", - "[$macro]", "\L$feature"; + next if ($feature eq ''); + + if ($features{$feature}++) { + print STDERR "$in: duplicate feature name: $feature\n"; + $err++; } + printf OUT "\t%-32s = \"%s\",%s\n", "[$macro]", $feature; } } print OUT "};\n"; close(IN); close(OUT); + +if ($err) { + unlink($out); + exit(1); +} + +exit(0); -- cgit v1.2.3-70-g09d2 From 1b6b7c9ff3514772958c075f8c89e42dddf6a4d8 Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin" Date: Tue, 26 Jun 2012 07:58:23 -0700 Subject: x86, cpufeature: Remove stray %s, add -w to mkcapflags.pl There was a stray %s left from testing, remove it. Add -w to the #! line (which is parsed by Perl even if the Perl interpreter is invoked explicitly on the command line) to catch these kinds of errors in the future. Reported-by: Jean Delvare Link: http://lkml.kernel.org/r/20120626143246.0c9bf301@endymion.delvare Signed-off-by: H. Peter Anvin --- arch/x86/kernel/cpu/mkcapflags.pl | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/cpu/mkcapflags.pl b/arch/x86/kernel/cpu/mkcapflags.pl index 0c5b54919c7..c7b3fe2d72e 100644 --- a/arch/x86/kernel/cpu/mkcapflags.pl +++ b/arch/x86/kernel/cpu/mkcapflags.pl @@ -1,4 +1,4 @@ -#!/usr/bin/perl +#!/usr/bin/perl -w # # Generate the x86_cap_flags[] array from include/asm-x86/cpufeature.h # @@ -29,7 +29,7 @@ while (defined($line = )) { print STDERR "$in: duplicate feature name: $feature\n"; $err++; } - printf OUT "\t%-32s = \"%s\",%s\n", "[$macro]", $feature; + printf OUT "\t%-32s = \"%s\",\n", "[$macro]", $feature; } } print OUT "};\n"; -- cgit v1.2.3-70-g09d2 From ce5c1fe9a9e059b5c58f0a7e2a3e687d0efac815 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 20 Jun 2012 11:11:38 +0200 Subject: perf/x86: Fix USER/KERNEL tagging of samples Several perf interrupt handlers (PEBS,IBS,BTS) re-write regs->ip but do not update the segment registers. So use an regs->ip based test instead of an regs->cs/regs->flags based test. Reported-and-tested-by: Stephane Eranian Signed-off-by: Peter Zijlstra Cc: Linus Torvalds Cc: Andrew Morton Cc: Thomas Gleixner Cc: Frederic Weisbecker Link: http://lkml.kernel.org/n/tip-xxrt0a1zronm1sm36obwc2vy@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 c4706cf9c01..6ef9d41b87f 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -1863,7 +1863,7 @@ unsigned long perf_misc_flags(struct pt_regs *regs) else misc |= PERF_RECORD_MISC_GUEST_KERNEL; } else { - if (user_mode(regs)) + if (!kernel_ip(regs->ip)) misc |= PERF_RECORD_MISC_USER; else misc |= PERF_RECORD_MISC_KERNEL; -- cgit v1.2.3-70-g09d2