From e4a46f02b1d0eaadea4e6b00e29922cd00d6de53 Mon Sep 17 00:00:00 2001 From: Yevgeny Pats Date: Tue, 19 Jan 2016 22:09:04 +0000 Subject: [PATCH 001/325] KEYS: Fix keyring ref leak in join_session_keyring() commit 23567fd052a9abb6d67fe8e7a9ccdd9800a540f2 upstream. This fixes CVE-2016-0728. If a thread is asked to join as a session keyring the keyring that's already set as its session, we leak a keyring reference. This can be tested with the following program: #include #include #include #include int main(int argc, const char *argv[]) { int i = 0; key_serial_t serial; serial = keyctl(KEYCTL_JOIN_SESSION_KEYRING, "leaked-keyring"); if (serial < 0) { perror("keyctl"); return -1; } if (keyctl(KEYCTL_SETPERM, serial, KEY_POS_ALL | KEY_USR_ALL) < 0) { perror("keyctl"); return -1; } for (i = 0; i < 100; i++) { serial = keyctl(KEYCTL_JOIN_SESSION_KEYRING, "leaked-keyring"); if (serial < 0) { perror("keyctl"); return -1; } } return 0; } If, after the program has run, there something like the following line in /proc/keys: 3f3d898f I--Q--- 100 perm 3f3f0000 0 0 keyring leaked-keyring: empty with a usage count of 100 * the number of times the program has been run, then the kernel is malfunctioning. If leaked-keyring has zero usages or has been garbage collected, then the problem is fixed. Reported-by: Yevgeny Pats Signed-off-by: David Howells Acked-by: Don Zickus Acked-by: Prarit Bhargava Acked-by: Jarod Wilson Signed-off-by: James Morris Signed-off-by: Greg Kroah-Hartman --- security/keys/process_keys.c | 1 + 1 file changed, 1 insertion(+) diff --git a/security/keys/process_keys.c b/security/keys/process_keys.c index a3f85d2a00bb..e6d50172872f 100644 --- a/security/keys/process_keys.c +++ b/security/keys/process_keys.c @@ -794,6 +794,7 @@ long join_session_keyring(const char *name) ret = PTR_ERR(keyring); goto error2; } else if (keyring == new->session_keyring) { + key_put(keyring); ret = 0; goto error2; } From 7d391345b037f3834c851906ba05cc2fb5e266dc Mon Sep 17 00:00:00 2001 From: "Ouyang Zhaowei (Charles)" Date: Wed, 6 May 2015 09:47:04 +0800 Subject: [PATCH 002/325] x86/xen: don't reset vcpu_info on a cancelled suspend commit 6a1f513776b78c994045287073e55bae44ed9f8c upstream. On a cancelled suspend the vcpu_info location does not change (it's still in the per-cpu area registered by xen_vcpu_setup()). So do not call xen_hvm_init_shared_info() which would make the kernel think its back in the shared info. With the wrong vcpu_info, events cannot be received and the domain will hang after a cancelled suspend. Signed-off-by: Charles Ouyang Reviewed-by: Boris Ostrovsky Signed-off-by: David Vrabel Signed-off-by: Greg Kroah-Hartman --- arch/x86/xen/suspend.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c index df0c40559583..7f664c416faf 100644 --- a/arch/x86/xen/suspend.c +++ b/arch/x86/xen/suspend.c @@ -34,7 +34,8 @@ static void xen_hvm_post_suspend(int suspend_cancelled) { #ifdef CONFIG_XEN_PVHVM int cpu; - xen_hvm_init_shared_info(); + if (!suspend_cancelled) + xen_hvm_init_shared_info(); xen_callback_vector(); xen_unplug_emulated_devices(); if (xen_feature(XENFEAT_hvm_safe_pvclock)) { From 986a5de78e3e6f25466e25efac00e81e5f86f60a Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Thu, 12 Nov 2015 14:49:17 +0100 Subject: [PATCH 003/325] KVM: x86: expose MSR_TSC_AUX to userspace commit 9dbe6cf941a6fe82933aef565e4095fb10f65023 upstream. If we do not do this, it is not properly saved and restored across migration. Windows notices due to its self-protection mechanisms, and is very upset about it (blue screen of death). Cc: Radim Krcmar Signed-off-by: Paolo Bonzini Signed-off-by: Greg Kroah-Hartman --- arch/x86/kvm/x86.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 97592e190413..9a2ed8904513 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -951,7 +951,7 @@ static u32 msrs_to_save[] = { MSR_CSTAR, MSR_KERNEL_GS_BASE, MSR_SYSCALL_MASK, MSR_LSTAR, #endif MSR_IA32_TSC, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA, - MSR_IA32_FEATURE_CONTROL, MSR_IA32_BNDCFGS + MSR_IA32_FEATURE_CONTROL, MSR_IA32_BNDCFGS, MSR_TSC_AUX, }; static unsigned num_msrs_to_save; @@ -4006,16 +4006,17 @@ static void kvm_init_msr_list(void) /* * Even MSRs that are valid in the host may not be exposed - * to the guests in some cases. We could work around this - * in VMX with the generic MSR save/load machinery, but it - * is not really worthwhile since it will really only - * happen with nested virtualization. + * to the guests in some cases. */ switch (msrs_to_save[i]) { case MSR_IA32_BNDCFGS: if (!kvm_x86_ops->mpx_supported()) continue; break; + case MSR_TSC_AUX: + if (!kvm_x86_ops->rdtscp_supported()) + continue; + break; default: break; } From 25d53807a70375b9e56636f683383bc4e9df4640 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Thu, 12 Nov 2015 16:42:18 +0100 Subject: [PATCH 004/325] KVM: x86: correctly print #AC in traces commit aba2f06c070f604e388cf77b1dcc7f4cf4577eb0 upstream. Poor #AC was so unimportant until a few days ago that we were not even tracing its name correctly. But now it's all over the place. Signed-off-by: Paolo Bonzini Signed-off-by: Greg Kroah-Hartman --- arch/x86/kvm/trace.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index 120302511802..ab9ae67a80e4 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -268,7 +268,7 @@ TRACE_EVENT(kvm_inj_virq, #define kvm_trace_sym_exc \ EXS(DE), EXS(DB), EXS(BP), EXS(OF), EXS(BR), EXS(UD), EXS(NM), \ EXS(DF), EXS(TS), EXS(NP), EXS(SS), EXS(GP), EXS(PF), \ - EXS(MF), EXS(MC) + EXS(MF), EXS(AC), EXS(MC) /* * Tracepoint for kvm interrupt injection: From e24ed5519f61b7a5f4d660f1e0c4cabd6cf499fc Mon Sep 17 00:00:00 2001 From: Huaitong Han Date: Tue, 12 Jan 2016 16:04:20 +0800 Subject: [PATCH 005/325] kvm: x86: Fix vmwrite to SECONDARY_VM_EXEC_CONTROL commit 45bdbcfdf241149642fb6c25ab0c209d59c371b7 upstream. vmx_cpuid_tries to update SECONDARY_VM_EXEC_CONTROL in the VMCS, but it will cause a vmwrite error on older CPUs because the code does not check for the presence of CPU_BASED_ACTIVATE_SECONDARY_CONTROLS. This will get rid of the following trace on e.g. Core2 6600: vmwrite error: reg 401e value 10 (err 12) Call Trace: [] dump_stack+0x40/0x57 [] vmx_cpuid_update+0x5d/0x150 [kvm_intel] [] kvm_vcpu_ioctl_set_cpuid2+0x4c/0x70 [kvm] [] kvm_arch_vcpu_ioctl+0x903/0xfa0 [kvm] Fixes: feda805fe7c4ed9cf78158e73b1218752e3b4314 Reported-by: Zdenek Kaspar Signed-off-by: Huaitong Han Signed-off-by: Paolo Bonzini Signed-off-by: Greg Kroah-Hartman --- arch/x86/kvm/vmx.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 44976a596fa6..10e7693b3540 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -8932,7 +8932,8 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu) best->ebx &= ~bit(X86_FEATURE_INVPCID); } - vmcs_set_secondary_exec_control(secondary_exec_ctl); + if (cpu_has_secondary_exec_ctrls()) + vmcs_set_secondary_exec_control(secondary_exec_ctl); if (static_cpu_has(X86_FEATURE_PCOMMIT) && nested) { if (guest_cpuid_has_pcommit(vcpu)) From 8d9b56970b10369a7fe09e8d95096c6e33fe5b78 Mon Sep 17 00:00:00 2001 From: Mario Kleiner Date: Fri, 18 Dec 2015 20:24:06 +0100 Subject: [PATCH 006/325] x86/reboot/quirks: Add iMac10,1 to pci_reboot_dmi_table[] commit 2f0c0b2d96b1205efb14347009748d786c2d9ba5 upstream. Without the reboot=pci method, the iMac 10,1 simply hangs after printing "Restarting system" at the point when it should reboot. This fixes it. Signed-off-by: Mario Kleiner Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Dave Jones Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1450466646-26663-1-git-send-email-mario.kleiner.de@gmail.com Signed-off-by: Ingo Molnar Signed-off-by: Greg Kroah-Hartman --- arch/x86/kernel/reboot.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 02693dd9a079..f660d63f40fe 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -182,6 +182,14 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "iMac9,1"), }, }, + { /* Handle problems with rebooting on the iMac10,1. */ + .callback = set_pci_reboot, + .ident = "Apple iMac10,1", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "iMac10,1"), + }, + }, /* ASRock */ { /* Handle problems with rebooting on ASRock Q1900DC-ITX */ From 966ae5ea35b3a2da0fe504c0bea16ce170b1fc44 Mon Sep 17 00:00:00 2001 From: "H.J. Lu" Date: Mon, 4 Jan 2016 10:17:09 -0800 Subject: [PATCH 007/325] x86/boot: Double BOOT_HEAP_SIZE to 64KB commit 8c31902cffc4d716450be549c66a67a8a3dd479c upstream. When decompressing kernel image during x86 bootup, malloc memory for ELF program headers may run out of heap space, which leads to system halt. This patch doubles BOOT_HEAP_SIZE to 64KB. Tested with 32-bit kernel which failed to boot without this patch. Signed-off-by: H.J. Lu Acked-by: H. Peter Anvin Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar Signed-off-by: Greg Kroah-Hartman --- arch/x86/include/asm/boot.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/include/asm/boot.h b/arch/x86/include/asm/boot.h index 4fa687a47a62..6b8d6e8cd449 100644 --- a/arch/x86/include/asm/boot.h +++ b/arch/x86/include/asm/boot.h @@ -27,7 +27,7 @@ #define BOOT_HEAP_SIZE 0x400000 #else /* !CONFIG_KERNEL_BZIP2 */ -#define BOOT_HEAP_SIZE 0x8000 +#define BOOT_HEAP_SIZE 0x10000 #endif /* !CONFIG_KERNEL_BZIP2 */ From 43a2ba8c1a003c82d9f411af8ebcf0fe1e4cbe3e Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Wed, 6 Jan 2016 12:21:01 -0800 Subject: [PATCH 008/325] x86/mm: Add barriers and document switch_mm()-vs-flush synchronization commit 71b3c126e61177eb693423f2e18a1914205b165e upstream. When switch_mm() activates a new PGD, it also sets a bit that tells other CPUs that the PGD is in use so that TLB flush IPIs will be sent. In order for that to work correctly, the bit needs to be visible prior to loading the PGD and therefore starting to fill the local TLB. Document all the barriers that make this work correctly and add a couple that were missing. Signed-off-by: Andy Lutomirski Cc: Andrew Morton Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Dave Hansen Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Rik van Riel Cc: Thomas Gleixner Cc: linux-mm@kvack.org Signed-off-by: Ingo Molnar Signed-off-by: Greg Kroah-Hartman --- arch/x86/include/asm/mmu_context.h | 33 +++++++++++++++++++++++++++++- arch/x86/mm/tlb.c | 29 +++++++++++++++++++++++--- 2 files changed, 58 insertions(+), 4 deletions(-) diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index 379cd3658799..1edc9cd198b8 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -116,8 +116,34 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, #endif cpumask_set_cpu(cpu, mm_cpumask(next)); - /* Re-load page tables */ + /* + * Re-load page tables. + * + * This logic has an ordering constraint: + * + * CPU 0: Write to a PTE for 'next' + * CPU 0: load bit 1 in mm_cpumask. if nonzero, send IPI. + * CPU 1: set bit 1 in next's mm_cpumask + * CPU 1: load from the PTE that CPU 0 writes (implicit) + * + * We need to prevent an outcome in which CPU 1 observes + * the new PTE value and CPU 0 observes bit 1 clear in + * mm_cpumask. (If that occurs, then the IPI will never + * be sent, and CPU 0's TLB will contain a stale entry.) + * + * The bad outcome can occur if either CPU's load is + * reordered before that CPU's store, so both CPUs much + * execute full barriers to prevent this from happening. + * + * Thus, switch_mm needs a full barrier between the + * store to mm_cpumask and any operation that could load + * from next->pgd. This barrier synchronizes with + * remote TLB flushers. Fortunately, load_cr3 is + * serializing and thus acts as a full barrier. + * + */ load_cr3(next->pgd); + trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL); /* Stop flush ipis for the previous mm */ @@ -156,10 +182,15 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, * schedule, protecting us from simultaneous changes. */ cpumask_set_cpu(cpu, mm_cpumask(next)); + /* * We were in lazy tlb mode and leave_mm disabled * tlb flush IPI delivery. We must reload CR3 * to make sure to use no freed page tables. + * + * As above, this is a barrier that forces + * TLB repopulation to be ordered after the + * store to mm_cpumask. */ load_cr3(next->pgd); trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL); diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 8ddb5d0d66fb..8f4cc3dfac32 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -161,7 +161,10 @@ void flush_tlb_current_task(void) preempt_disable(); count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); + + /* This is an implicit full barrier that synchronizes with switch_mm. */ local_flush_tlb(); + trace_tlb_flush(TLB_LOCAL_SHOOTDOWN, TLB_FLUSH_ALL); if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids) flush_tlb_others(mm_cpumask(mm), mm, 0UL, TLB_FLUSH_ALL); @@ -188,17 +191,29 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, unsigned long base_pages_to_flush = TLB_FLUSH_ALL; preempt_disable(); - if (current->active_mm != mm) + if (current->active_mm != mm) { + /* Synchronize with switch_mm. */ + smp_mb(); + goto out; + } if (!current->mm) { leave_mm(smp_processor_id()); + + /* Synchronize with switch_mm. */ + smp_mb(); + goto out; } if ((end != TLB_FLUSH_ALL) && !(vmflag & VM_HUGETLB)) base_pages_to_flush = (end - start) >> PAGE_SHIFT; + /* + * Both branches below are implicit full barriers (MOV to CR or + * INVLPG) that synchronize with switch_mm. + */ if (base_pages_to_flush > tlb_single_page_flush_ceiling) { base_pages_to_flush = TLB_FLUSH_ALL; count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); @@ -228,10 +243,18 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long start) preempt_disable(); if (current->active_mm == mm) { - if (current->mm) + if (current->mm) { + /* + * Implicit full barrier (INVLPG) that synchronizes + * with switch_mm. + */ __flush_tlb_one(start); - else + } else { leave_mm(smp_processor_id()); + + /* Synchronize with switch_mm. */ + smp_mb(); + } } if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids) From 0dec73176d5592cac85c055bba90e22093e3b7e2 Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Tue, 12 Jan 2016 12:47:40 -0800 Subject: [PATCH 009/325] x86/mm: Improve switch_mm() barrier comments commit 4eaffdd5a5fe6ff9f95e1ab4de1ac904d5e0fa8b upstream. My previous comments were still a bit confusing and there was a typo. Fix it up. Reported-by: Peter Zijlstra Signed-off-by: Andy Lutomirski Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Dave Hansen Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Rik van Riel Cc: Thomas Gleixner Fixes: 71b3c126e611 ("x86/mm: Add barriers and document switch_mm()-vs-flush synchronization") Link: http://lkml.kernel.org/r/0a0b43cdcdd241c5faaaecfbcc91a155ddedc9a1.1452631609.git.luto@kernel.org Signed-off-by: Ingo Molnar Signed-off-by: Greg Kroah-Hartman --- arch/x86/include/asm/mmu_context.h | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index 1edc9cd198b8..bfd9b2a35a0b 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -132,14 +132,16 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, * be sent, and CPU 0's TLB will contain a stale entry.) * * The bad outcome can occur if either CPU's load is - * reordered before that CPU's store, so both CPUs much + * reordered before that CPU's store, so both CPUs must * execute full barriers to prevent this from happening. * * Thus, switch_mm needs a full barrier between the * store to mm_cpumask and any operation that could load - * from next->pgd. This barrier synchronizes with - * remote TLB flushers. Fortunately, load_cr3 is - * serializing and thus acts as a full barrier. + * from next->pgd. TLB fills are special and can happen + * due to instruction fetches or for no reason at all, + * and neither LOCK nor MFENCE orders them. + * Fortunately, load_cr3() is serializing and gives the + * ordering guarantee we need. * */ load_cr3(next->pgd); @@ -188,9 +190,8 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, * tlb flush IPI delivery. We must reload CR3 * to make sure to use no freed page tables. * - * As above, this is a barrier that forces - * TLB repopulation to be ordered after the - * store to mm_cpumask. + * As above, load_cr3() is serializing and orders TLB + * fills with respect to the mm_cpumask write. */ load_cr3(next->pgd); trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL); From b5398ab9d4540c953f097b28f575486db2331f52 Mon Sep 17 00:00:00 2001 From: Jurgen Kramer Date: Mon, 11 Jan 2016 08:16:58 +0100 Subject: [PATCH 010/325] ALSA: usb: Add native DSD support for Oppo HA-1 commit a4eae3a506ea4a7d4474cd74e20b423fa8053d91 upstream. This patch adds native DSD support for the Oppo HA-1. It uses a XMOS chipset but they use their own vendor ID. Signed-off-by: Jurgen Kramer Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/usb/quirks.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index b6c0c8e3b450..23ea6d800c4c 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -1269,6 +1269,7 @@ u64 snd_usb_interface_dsd_format_quirks(struct snd_usb_audio *chip, case USB_ID(0x20b1, 0x3008): /* iFi Audio micro/nano iDSD */ case USB_ID(0x20b1, 0x2008): /* Matrix Audio X-Sabre */ case USB_ID(0x20b1, 0x300a): /* Matrix Audio Mini-i Pro */ + case USB_ID(0x22d8, 0x0416): /* OPPO HA-1*/ if (fp->altsetting == 2) return SNDRV_PCM_FMTBIT_DSD_U32_BE; break; From efb8a443f256c65fca9ea41012d5702fe71248a6 Mon Sep 17 00:00:00 2001 From: David Henningsson Date: Mon, 11 Jan 2016 09:33:14 +0100 Subject: [PATCH 011/325] ALSA: hda - Fixup inverted internal mic for Lenovo E50-80 commit 56f27013482c0803d978b667fe85de04ce9357cd upstream. Inform userspace that one channel of the internal mic has reversed polarity, so it does not attempt to add both channels together and end up with silence. Reported-by: Andrzej Mendel Alsa-info: http://www.alsa-project.org/db/?f=3088f82a0cf977855f92af9db8ad406c04f71efa BugLink: https://bugs.launchpad.net/bugs/1529624 Signed-off-by: David Henningsson Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/pci/hda/patch_realtek.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 3a89d82f8057..2fdda51d07c4 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -4666,6 +4666,7 @@ enum { ALC290_FIXUP_SUBWOOFER, ALC290_FIXUP_SUBWOOFER_HSJACK, ALC269_FIXUP_THINKPAD_ACPI, + ALC269_FIXUP_DMIC_THINKPAD_ACPI, ALC255_FIXUP_DELL1_MIC_NO_PRESENCE, ALC255_FIXUP_DELL2_MIC_NO_PRESENCE, ALC255_FIXUP_HEADSET_MODE, @@ -5103,6 +5104,12 @@ static const struct hda_fixup alc269_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = hda_fixup_thinkpad_acpi, }, + [ALC269_FIXUP_DMIC_THINKPAD_ACPI] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc_fixup_inv_dmic, + .chained = true, + .chain_id = ALC269_FIXUP_THINKPAD_ACPI, + }, [ALC255_FIXUP_DELL1_MIC_NO_PRESENCE] = { .type = HDA_FIXUP_PINS, .v.pins = (const struct hda_pintbl[]) { @@ -5457,6 +5464,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x2226, "ThinkPad X250", ALC292_FIXUP_TPT440_DOCK), SND_PCI_QUIRK(0x17aa, 0x2233, "Thinkpad", ALC293_FIXUP_LENOVO_SPK_NOISE), SND_PCI_QUIRK(0x17aa, 0x30bb, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY), + SND_PCI_QUIRK(0x17aa, 0x3902, "Lenovo E50-80", ALC269_FIXUP_DMIC_THINKPAD_ACPI), SND_PCI_QUIRK(0x17aa, 0x3977, "IdeaPad S210", ALC283_FIXUP_INT_MIC), SND_PCI_QUIRK(0x17aa, 0x3978, "IdeaPad Y410P", ALC269_FIXUP_NO_SHUTUP), SND_PCI_QUIRK(0x17aa, 0x5013, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), From 36d3fc15f50c22bbddfceb6c585f851130fb005f Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Tue, 12 Jan 2016 12:38:02 +0100 Subject: [PATCH 012/325] ALSA: seq: Fix missing NULL check at remove_events ioctl commit 030e2c78d3a91dd0d27fef37e91950dde333eba1 upstream. snd_seq_ioctl_remove_events() calls snd_seq_fifo_clear() unconditionally even if there is no FIFO assigned, and this leads to an Oops due to NULL dereference. The fix is just to add a proper NULL check. Reported-by: Dmitry Vyukov Tested-by: Dmitry Vyukov Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/core/seq/seq_clientmgr.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/core/seq/seq_clientmgr.c b/sound/core/seq/seq_clientmgr.c index b64f20deba90..13cfa815732d 100644 --- a/sound/core/seq/seq_clientmgr.c +++ b/sound/core/seq/seq_clientmgr.c @@ -1962,7 +1962,7 @@ static int snd_seq_ioctl_remove_events(struct snd_seq_client *client, * No restrictions so for a user client we can clear * the whole fifo */ - if (client->type == USER_CLIENT) + if (client->type == USER_CLIENT && client->data.user.fifo) snd_seq_fifo_clear(client->data.user.fifo); } From 4aa59e944fbed2078a0c48872d7977a938c4753d Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Tue, 12 Jan 2016 14:03:33 +0100 Subject: [PATCH 013/325] ALSA: usb-audio: Avoid calling usb_autopm_put_interface() at disconnect commit 5c06d68bc2a174a6b82dce9f100f55173b9a5189 upstream. ALSA PCM may still have a leftover instance after disconnection and it delays its release. The problem is that the PCM close code path of USB-audio driver has a call of snd_usb_autosuspend(). This involves with the call of usb_autopm_put_interface() and it may lead to a kernel Oops due to the NULL object like: BUG: unable to handle kernel NULL pointer dereference at 0000000000000190 IP: [] usb_autopm_put_interface+0xf/0x30 PGD 0 Call Trace: [] snd_usb_autosuspend+0x14/0x20 [] snd_usb_pcm_close.isra.14+0x5c/0x90 [] snd_usb_playback_close+0xf/0x20 [] snd_pcm_release_substream.part.36+0x3a/0x90 [] snd_pcm_release+0xa3/0xb0 [] snd_disconnect_release+0xd0/0xe0 [] __fput+0x97/0x1d0 [] ____fput+0x9/0x10 [] task_work_run+0x72/0x90 [] do_exit+0x280/0xa80 [] do_group_exit+0x3a/0xa0 [] get_signal+0x1df/0x540 [] do_signal+0x23/0x620 [] ? do_readv_writev+0x128/0x200 [] prepare_exit_to_usermode+0x91/0xd0 [] syscall_return_slowpath+0x9a/0x120 [] ? __sys_recvmsg+0x5d/0x70 [] ? ktime_get_ts64+0x45/0xe0 [] ? SyS_poll+0x60/0xf0 [] int_ret_from_sys_call+0x25/0x8f We have already a check of disconnection in snd_usb_autoresume(), but the check is missing its counterpart. The fix is just to put the same check in snd_usb_autosuspend(), too. Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=109431 Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/usb/card.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/sound/usb/card.c b/sound/usb/card.c index 18f56646ce86..1f09d9591276 100644 --- a/sound/usb/card.c +++ b/sound/usb/card.c @@ -675,6 +675,8 @@ int snd_usb_autoresume(struct snd_usb_audio *chip) void snd_usb_autosuspend(struct snd_usb_audio *chip) { + if (atomic_read(&chip->shutdown)) + return; if (atomic_dec_and_test(&chip->active)) usb_autopm_put_interface(chip->pm_intf); } From 0058ede73e1f441c003666f61671dfddfcbd5811 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Tue, 12 Jan 2016 15:36:27 +0100 Subject: [PATCH 014/325] ALSA: seq: Fix race at timer setup and close commit 3567eb6af614dac436c4b16a8d426f9faed639b3 upstream. ALSA sequencer code has an open race between the timer setup ioctl and the close of the client. This was triggered by syzkaller fuzzer, and a use-after-free was caught there as a result. This patch papers over it by adding a proper queue->timer_mutex lock around the timer-related calls in the relevant code path. Reported-by: Dmitry Vyukov Tested-by: Dmitry Vyukov Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/core/seq/seq_queue.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/sound/core/seq/seq_queue.c b/sound/core/seq/seq_queue.c index 7dfd0f429410..0bec02e89d51 100644 --- a/sound/core/seq/seq_queue.c +++ b/sound/core/seq/seq_queue.c @@ -142,8 +142,10 @@ static struct snd_seq_queue *queue_new(int owner, int locked) static void queue_delete(struct snd_seq_queue *q) { /* stop and release the timer */ + mutex_lock(&q->timer_mutex); snd_seq_timer_stop(q->timer); snd_seq_timer_close(q); + mutex_unlock(&q->timer_mutex); /* wait until access free */ snd_use_lock_sync(&q->use_lock); /* release resources... */ From 7fee8d18ecb212ff0a0b99396f0980cd8d8aec07 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Tue, 12 Jan 2016 21:06:39 +0100 Subject: [PATCH 015/325] ALSA: hda - Fix white noise on Dell Latitude E5550 commit 98070576c4f77509459c83cd2358617ef0769a38 upstream. Dell Latitude E5550 (1028:062c) has a white noise problem like other Latitude E models, and it gets fixed by the very same quirk as well. Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=110591 Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/pci/hda/patch_realtek.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 2fdda51d07c4..f0ed41e1a884 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -5339,6 +5339,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1028, 0x05f6, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x0615, "Dell Vostro 5470", ALC290_FIXUP_SUBWOOFER_HSJACK), SND_PCI_QUIRK(0x1028, 0x0616, "Dell Vostro 5470", ALC290_FIXUP_SUBWOOFER_HSJACK), + SND_PCI_QUIRK(0x1028, 0x062c, "Dell Latitude E5550", ALC292_FIXUP_DELL_E7X), SND_PCI_QUIRK(0x1028, 0x062e, "Dell Latitude E7450", ALC292_FIXUP_DELL_E7X), SND_PCI_QUIRK(0x1028, 0x0638, "Dell Inspiron 5439", ALC290_FIXUP_MONO_SPEAKERS_HSJACK), SND_PCI_QUIRK(0x1028, 0x064a, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE), From bae71eb004d0272b6552e45fdff7e58233da27bd Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Wed, 13 Jan 2016 07:20:13 +0100 Subject: [PATCH 016/325] ALSA: usb-audio: Fix mixer ctl regression of Native Instrument devices commit c4a359a0049f2e17b012b31e801e96566f6391e5 upstream. The commit [da6d276957ea: ALSA: usb-audio: Add resume support for Native Instruments controls] brought a regression where the Native Instrument audio devices don't get the correct value at update due to the missing shift at writing. This patch addresses it. Fixes: da6d276957ea ('ALSA: usb-audio: Add resume support for Native Instruments controls') Reported-and-tested-by: Owen Williams Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/usb/mixer_quirks.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/usb/mixer_quirks.c b/sound/usb/mixer_quirks.c index 0ce888dceed0..279025650568 100644 --- a/sound/usb/mixer_quirks.c +++ b/sound/usb/mixer_quirks.c @@ -793,7 +793,7 @@ static int snd_nativeinstruments_control_put(struct snd_kcontrol *kcontrol, return 0; kcontrol->private_value &= ~(0xff << 24); - kcontrol->private_value |= newval; + kcontrol->private_value |= (unsigned int)newval << 24; err = snd_ni_update_cur_val(list); return err < 0 ? err : 1; } From 8eff3aa0a9bbb593dce0ec0344ec1961318e44c8 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Thu, 14 Jan 2016 16:30:58 +0100 Subject: [PATCH 017/325] ALSA: timer: Harden slave timer list handling commit b5a663aa426f4884c71cd8580adae73f33570f0d upstream. A slave timer instance might be still accessible in a racy way while operating the master instance as it lacks of locking. Since the master operation is mostly protected with timer->lock, we should cope with it while changing the slave instance, too. Also, some linked lists (active_list and ack_list) of slave instances aren't unlinked immediately at stopping or closing, and this may lead to unexpected accesses. This patch tries to address these issues. It adds spin lock of timer->lock (either from master or slave, which is equivalent) in a few places. For avoiding a deadlock, we ensure that the global slave_active_lock is always locked at first before each timer lock. Also, ack and active_list of slave instances are properly unlinked at snd_timer_stop() and snd_timer_close(). Last but not least, remove the superfluous call of _snd_timer_stop() at removing slave links. This is a noop, and calling it may confuse readers wrt locking. Further cleanup will follow in a later patch. Actually we've got reports of use-after-free by syzkaller fuzzer, and this hopefully fixes these issues. Reported-by: Dmitry Vyukov Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/core/timer.c | 18 ++++++++++++++---- 1 file changed, 14 insertions(+), 4 deletions(-) diff --git a/sound/core/timer.c b/sound/core/timer.c index 31f40f03e5b7..8b06413e967e 100644 --- a/sound/core/timer.c +++ b/sound/core/timer.c @@ -215,11 +215,13 @@ static void snd_timer_check_master(struct snd_timer_instance *master) slave->slave_id == master->slave_id) { list_move_tail(&slave->open_list, &master->slave_list_head); spin_lock_irq(&slave_active_lock); + spin_lock(&master->timer->lock); slave->master = master; slave->timer = master->timer; if (slave->flags & SNDRV_TIMER_IFLG_RUNNING) list_add_tail(&slave->active_list, &master->slave_active_head); + spin_unlock(&master->timer->lock); spin_unlock_irq(&slave_active_lock); } } @@ -346,15 +348,18 @@ int snd_timer_close(struct snd_timer_instance *timeri) timer->hw.close) timer->hw.close(timer); /* remove slave links */ + spin_lock_irq(&slave_active_lock); + spin_lock(&timer->lock); list_for_each_entry_safe(slave, tmp, &timeri->slave_list_head, open_list) { - spin_lock_irq(&slave_active_lock); - _snd_timer_stop(slave, 1, SNDRV_TIMER_EVENT_RESOLUTION); list_move_tail(&slave->open_list, &snd_timer_slave_list); slave->master = NULL; slave->timer = NULL; - spin_unlock_irq(&slave_active_lock); + list_del_init(&slave->ack_list); + list_del_init(&slave->active_list); } + spin_unlock(&timer->lock); + spin_unlock_irq(&slave_active_lock); mutex_unlock(®ister_mutex); } out: @@ -441,9 +446,12 @@ static int snd_timer_start_slave(struct snd_timer_instance *timeri) spin_lock_irqsave(&slave_active_lock, flags); timeri->flags |= SNDRV_TIMER_IFLG_RUNNING; - if (timeri->master) + if (timeri->master && timeri->timer) { + spin_lock(&timeri->timer->lock); list_add_tail(&timeri->active_list, &timeri->master->slave_active_head); + spin_unlock(&timeri->timer->lock); + } spin_unlock_irqrestore(&slave_active_lock, flags); return 1; /* delayed start */ } @@ -489,6 +497,8 @@ static int _snd_timer_stop(struct snd_timer_instance * timeri, if (!keep_flag) { spin_lock_irqsave(&slave_active_lock, flags); timeri->flags &= ~SNDRV_TIMER_IFLG_RUNNING; + list_del_init(&timeri->ack_list); + list_del_init(&timeri->active_list); spin_unlock_irqrestore(&slave_active_lock, flags); } goto __end; From af9bab84ca3c0e90053ba17744aa362b585e3ca3 Mon Sep 17 00:00:00 2001 From: Hui Wang Date: Wed, 13 Jan 2016 11:51:38 +0800 Subject: [PATCH 018/325] ALSA: hda - fix the headset mic detection problem for a Dell laptop commit 0a1f90a982e85f4921bed606a6b41a24f4de2ae1 upstream. The machine uses codec alc255, and the pin configuration value for pin 0x14 on this machine is 0x90171130 which is not in the pin quirk table yet. BugLink: https://bugs.launchpad.net/bugs/1533461 Signed-off-by: Hui Wang Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/pci/hda/patch_realtek.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index f0ed41e1a884..61d8502e6b08 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -5624,6 +5624,10 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = { {0x12, 0x90a60170}, {0x14, 0x90170130}, {0x21, 0x02211040}), + SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE, + {0x12, 0x90a60170}, + {0x14, 0x90171130}, + {0x21, 0x02211040}), SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE, {0x12, 0x90a60170}, {0x14, 0x90170140}, From d87622a1662af5782c94b88a613c09de0bde5288 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Wed, 13 Jan 2016 17:48:01 +0100 Subject: [PATCH 019/325] ALSA: timer: Fix race among timer ioctls commit af368027a49a751d6ff4ee9e3f9961f35bb4fede upstream. ALSA timer ioctls have an open race and this may lead to a use-after-free of timer instance object. A simplistic fix is to make each ioctl exclusive. We have already tread_sem for controlling the tread, and extend this as a global mutex to be applied to each ioctl. The downside is, of course, the worse concurrency. But these ioctls aren't to be parallel accessible, in anyway, so it should be fine to serialize there. Reported-by: Dmitry Vyukov Tested-by: Dmitry Vyukov Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/core/timer.c | 32 +++++++++++++++++++------------- 1 file changed, 19 insertions(+), 13 deletions(-) diff --git a/sound/core/timer.c b/sound/core/timer.c index 8b06413e967e..b0458285723a 100644 --- a/sound/core/timer.c +++ b/sound/core/timer.c @@ -73,7 +73,7 @@ struct snd_timer_user { struct timespec tstamp; /* trigger tstamp */ wait_queue_head_t qchange_sleep; struct fasync_struct *fasync; - struct mutex tread_sem; + struct mutex ioctl_lock; }; /* list of timers */ @@ -1263,7 +1263,7 @@ static int snd_timer_user_open(struct inode *inode, struct file *file) return -ENOMEM; spin_lock_init(&tu->qlock); init_waitqueue_head(&tu->qchange_sleep); - mutex_init(&tu->tread_sem); + mutex_init(&tu->ioctl_lock); tu->ticks = 1; tu->queue_size = 128; tu->queue = kmalloc(tu->queue_size * sizeof(struct snd_timer_read), @@ -1283,8 +1283,10 @@ static int snd_timer_user_release(struct inode *inode, struct file *file) if (file->private_data) { tu = file->private_data; file->private_data = NULL; + mutex_lock(&tu->ioctl_lock); if (tu->timeri) snd_timer_close(tu->timeri); + mutex_unlock(&tu->ioctl_lock); kfree(tu->queue); kfree(tu->tqueue); kfree(tu); @@ -1522,7 +1524,6 @@ static int snd_timer_user_tselect(struct file *file, int err = 0; tu = file->private_data; - mutex_lock(&tu->tread_sem); if (tu->timeri) { snd_timer_close(tu->timeri); tu->timeri = NULL; @@ -1566,7 +1567,6 @@ static int snd_timer_user_tselect(struct file *file, } __err: - mutex_unlock(&tu->tread_sem); return err; } @@ -1779,7 +1779,7 @@ enum { SNDRV_TIMER_IOCTL_PAUSE_OLD = _IO('T', 0x23), }; -static long snd_timer_user_ioctl(struct file *file, unsigned int cmd, +static long __snd_timer_user_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct snd_timer_user *tu; @@ -1796,17 +1796,11 @@ static long snd_timer_user_ioctl(struct file *file, unsigned int cmd, { int xarg; - mutex_lock(&tu->tread_sem); - if (tu->timeri) { /* too late */ - mutex_unlock(&tu->tread_sem); + if (tu->timeri) /* too late */ return -EBUSY; - } - if (get_user(xarg, p)) { - mutex_unlock(&tu->tread_sem); + if (get_user(xarg, p)) return -EFAULT; - } tu->tread = xarg ? 1 : 0; - mutex_unlock(&tu->tread_sem); return 0; } case SNDRV_TIMER_IOCTL_GINFO: @@ -1839,6 +1833,18 @@ static long snd_timer_user_ioctl(struct file *file, unsigned int cmd, return -ENOTTY; } +static long snd_timer_user_ioctl(struct file *file, unsigned int cmd, + unsigned long arg) +{ + struct snd_timer_user *tu = file->private_data; + long ret; + + mutex_lock(&tu->ioctl_lock); + ret = __snd_timer_user_ioctl(file, cmd, arg); + mutex_unlock(&tu->ioctl_lock); + return ret; +} + static int snd_timer_user_fasync(int fd, struct file * file, int on) { struct snd_timer_user *tu; From 3c0e535fee2e67d06220e676cbf7b69099d741ce Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Wed, 13 Jan 2016 21:35:06 +0100 Subject: [PATCH 020/325] ALSA: timer: Fix double unlink of active_list commit ee8413b01045c74340aa13ad5bdf905de32be736 upstream. ALSA timer instance object has a couple of linked lists and they are unlinked unconditionally at snd_timer_stop(). Meanwhile snd_timer_interrupt() unlinks it, but it calls list_del() which leaves the element list itself unchanged. This ends up with unlinking twice, and it was caught by syzkaller fuzzer. The fix is to use list_del_init() variant properly there, too. Reported-by: Dmitry Vyukov Tested-by: Dmitry Vyukov Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/core/timer.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/core/timer.c b/sound/core/timer.c index b0458285723a..4e8d7bfffff6 100644 --- a/sound/core/timer.c +++ b/sound/core/timer.c @@ -704,7 +704,7 @@ void snd_timer_interrupt(struct snd_timer * timer, unsigned long ticks_left) } else { ti->flags &= ~SNDRV_TIMER_IFLG_RUNNING; if (--timer->running) - list_del(&ti->active_list); + list_del_init(&ti->active_list); } if ((timer->hw.flags & SNDRV_TIMER_HW_TASKLET) || (ti->flags & SNDRV_TIMER_IFLG_FAST)) From 050decce5d7a096f37a24e5411bd950592f28415 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Fri, 15 Jan 2016 12:59:25 +0100 Subject: [PATCH 021/325] ALSA: hda - Add fixup for Dell Latitidue E6540 commit cf52103a218744f3fd18111325c28e95aa9cd226 upstream. Another Dell model, another fixup entry: Latitude E6540 needs the same fixup as other Latitude E series as workaround for noise problems. Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=104341 Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/pci/hda/patch_realtek.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 61d8502e6b08..8143c0e24a27 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -5331,6 +5331,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1028, 0x0470, "Dell M101z", ALC269_FIXUP_DELL_M101Z), SND_PCI_QUIRK(0x1028, 0x054b, "Dell XPS one 2710", ALC275_FIXUP_DELL_XPS), SND_PCI_QUIRK(0x1028, 0x05bd, "Dell Latitude E6440", ALC292_FIXUP_DELL_E7X), + SND_PCI_QUIRK(0x1028, 0x05be, "Dell Latitude E6540", ALC292_FIXUP_DELL_E7X), SND_PCI_QUIRK(0x1028, 0x05ca, "Dell Latitude E7240", ALC292_FIXUP_DELL_E7X), SND_PCI_QUIRK(0x1028, 0x05cb, "Dell Latitude E7440", ALC292_FIXUP_DELL_E7X), SND_PCI_QUIRK(0x1028, 0x05da, "Dell Vostro 5460", ALC290_FIXUP_SUBWOOFER), From f4593c9f401b4e2230c447825b2ce2a26e1f2c2d Mon Sep 17 00:00:00 2001 From: Nicolas Boichat Date: Mon, 18 Jan 2016 21:35:01 +0800 Subject: [PATCH 022/325] ALSA: seq: Fix snd_seq_call_port_info_ioctl in compat mode commit 9586495dc3011a80602329094e746dbce16cb1f1 upstream. This reverts one hunk of commit ef44a1ec6eee ("ALSA: sound/core: use memdup_user()"), which replaced a number of kmalloc followed by memcpy with memdup calls. In this case, we are copying from a struct snd_seq_port_info32 to a struct snd_seq_port_info, but the latter is 4 bytes longer than the 32-bit version, so we need to separate kmalloc and copy calls. Fixes: ef44a1ec6eee ('ALSA: sound/core: use memdup_user()') Signed-off-by: Nicolas Boichat Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/core/seq/seq_compat.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/sound/core/seq/seq_compat.c b/sound/core/seq/seq_compat.c index 81f7c109dc46..65175902a68a 100644 --- a/sound/core/seq/seq_compat.c +++ b/sound/core/seq/seq_compat.c @@ -49,11 +49,12 @@ static int snd_seq_call_port_info_ioctl(struct snd_seq_client *client, unsigned struct snd_seq_port_info *data; mm_segment_t fs; - data = memdup_user(data32, sizeof(*data32)); - if (IS_ERR(data)) - return PTR_ERR(data); + data = kmalloc(sizeof(*data), GFP_KERNEL); + if (!data) + return -ENOMEM; - if (get_user(data->flags, &data32->flags) || + if (copy_from_user(data, data32, sizeof(*data32)) || + get_user(data->flags, &data32->flags) || get_user(data->time_queue, &data32->time_queue)) goto error; data->kernel = NULL; From 1d8e11540fc94fc98c9d6215737e20eff514e376 Mon Sep 17 00:00:00 2001 From: Nicolas Boichat Date: Mon, 18 Jan 2016 21:35:00 +0800 Subject: [PATCH 023/325] ALSA: pcm: Fix snd_pcm_hw_params struct copy in compat mode commit 43c54b8c7cfe22f868a751ba8a59abf1724160b1 upstream. This reverts one hunk of commit ef44a1ec6eee ("ALSA: sound/core: use memdup_user()"), which replaced a number of kmalloc followed by memcpy with memdup calls. In this case, we are copying from a struct snd_pcm_hw_params32 to a struct snd_pcm_hw_params, but the latter is 4 bytes longer than the 32-bit version, so we need to separate kmalloc and copy calls. This actually leads to an out-of-bounds memory access later on in sound/soc/soc-pcm.c:soc_pcm_hw_params() (detected using KASan). Fixes: ef44a1ec6eee ('ALSA: sound/core: use memdup_user()') Signed-off-by: Nicolas Boichat Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/core/pcm_compat.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) diff --git a/sound/core/pcm_compat.c b/sound/core/pcm_compat.c index b48b434444ed..9630e9f72b7b 100644 --- a/sound/core/pcm_compat.c +++ b/sound/core/pcm_compat.c @@ -255,10 +255,15 @@ static int snd_pcm_ioctl_hw_params_compat(struct snd_pcm_substream *substream, if (! (runtime = substream->runtime)) return -ENOTTY; - /* only fifo_size is different, so just copy all */ - data = memdup_user(data32, sizeof(*data32)); - if (IS_ERR(data)) - return PTR_ERR(data); + data = kmalloc(sizeof(*data), GFP_KERNEL); + if (!data) + return -ENOMEM; + + /* only fifo_size (RO from userspace) is different, so just copy all */ + if (copy_from_user(data, data32, sizeof(*data32))) { + err = -EFAULT; + goto error; + } if (refine) err = snd_pcm_hw_refine(substream, data); From dafa57ee81748f6a6950c06f19a160d0a209795e Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Mon, 18 Jan 2016 13:52:47 +0100 Subject: [PATCH 024/325] ALSA: hrtimer: Fix stall by hrtimer_cancel() commit 2ba1fe7a06d3624f9a7586d672b55f08f7c670f3 upstream. hrtimer_cancel() waits for the completion from the callback, thus it must not be called inside the callback itself. This was already a problem in the past with ALSA hrtimer driver, and the early commit [fcfdebe70759: ALSA: hrtimer - Fix lock-up] tried to address it. However, the previous fix is still insufficient: it may still cause a lockup when the ALSA timer instance reprograms itself in its callback. Then it invokes the start function even in snd_timer_interrupt() that is called in hrtimer callback itself, results in a CPU stall. This is no hypothetical problem but actually triggered by syzkaller fuzzer. This patch tries to fix the issue again. Now we call hrtimer_try_to_cancel() at both start and stop functions so that it won't fall into a deadlock, yet giving some chance to cancel the queue if the functions have been called outside the callback. The proper hrtimer_cancel() is called in anyway at closing, so this should be enough. Reported-and-tested-by: Dmitry Vyukov Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/core/hrtimer.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/sound/core/hrtimer.c b/sound/core/hrtimer.c index f845ecf7e172..656d9a9032dc 100644 --- a/sound/core/hrtimer.c +++ b/sound/core/hrtimer.c @@ -90,7 +90,7 @@ static int snd_hrtimer_start(struct snd_timer *t) struct snd_hrtimer *stime = t->private_data; atomic_set(&stime->running, 0); - hrtimer_cancel(&stime->hrt); + hrtimer_try_to_cancel(&stime->hrt); hrtimer_start(&stime->hrt, ns_to_ktime(t->sticks * resolution), HRTIMER_MODE_REL); atomic_set(&stime->running, 1); @@ -101,6 +101,7 @@ static int snd_hrtimer_stop(struct snd_timer *t) { struct snd_hrtimer *stime = t->private_data; atomic_set(&stime->running, 0); + hrtimer_try_to_cancel(&stime->hrt); return 0; } From 66bd949b3a3680400ff53f4f847e16ad40a9edbd Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Mon, 18 Jan 2016 14:12:40 +0100 Subject: [PATCH 025/325] ALSA: control: Avoid kernel warnings from tlv ioctl with numid 0 commit c0bcdbdff3ff73a54161fca3cb8b6cdbd0bb8762 upstream. When a TLV ioctl with numid zero is handled, the driver may spew a kernel warning with a stack trace at each call. The check was intended obviously only for a kernel driver, but not for a user interaction. Let's fix it. This was spotted by syzkaller fuzzer. Reported-by: Dmitry Vyukov Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/core/control.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/sound/core/control.c b/sound/core/control.c index 196a6fe100ca..a85d45595d02 100644 --- a/sound/core/control.c +++ b/sound/core/control.c @@ -1405,6 +1405,8 @@ static int snd_ctl_tlv_ioctl(struct snd_ctl_file *file, return -EFAULT; if (tlv.length < sizeof(unsigned int) * 2) return -EINVAL; + if (!tlv.numid) + return -EINVAL; down_read(&card->controls_rwsem); kctl = snd_ctl_find_numid(card, tlv.numid); if (kctl == NULL) { From 658a9bb065d076eefd27b859d9e3012410f6cb63 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Mon, 18 Jan 2016 09:17:30 +0100 Subject: [PATCH 026/325] ALSA: hda - Fix bass pin fixup for ASUS N550JX commit db8948e653e12b218058bb6696f4a33fa7845f64 upstream. ASUS N550JX (PCI SSID 1043:13df) requires the same fixup for a bass speaker output pin as other N550 models. Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=110001 Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/pci/hda/patch_realtek.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 8143c0e24a27..33753244f48f 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -6566,6 +6566,7 @@ static const struct snd_pci_quirk alc662_fixup_tbl[] = { SND_PCI_QUIRK(0x1028, 0x069f, "Dell", ALC668_FIXUP_DELL_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x103c, 0x1632, "HP RP5800", ALC662_FIXUP_HP_RP5800), SND_PCI_QUIRK(0x1043, 0x11cd, "Asus N550", ALC662_FIXUP_BASS_1A), + SND_PCI_QUIRK(0x1043, 0x13df, "Asus N550JX", ALC662_FIXUP_BASS_1A), SND_PCI_QUIRK(0x1043, 0x1477, "ASUS N56VZ", ALC662_FIXUP_BASS_MODE4_CHMAP), SND_PCI_QUIRK(0x1043, 0x15a7, "ASUS UX51VZH", ALC662_FIXUP_BASS_16), SND_PCI_QUIRK(0x1043, 0x1b73, "ASUS N55SF", ALC662_FIXUP_BASS_16), From 5833733480affc449af06426c22dba0c05a44ec2 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Wed, 20 Jan 2016 15:46:44 +0100 Subject: [PATCH 027/325] ALSA: hda - Fix missing module loading with model=generic option commit bca8e988043e39483afd7872a2641f03ed7201a6 upstream. When the generic codec driver is specified via model option or such, the hda driver doesn't try to load the generic driver module but still loads the codec-specific driver, and this ends up with the binding failure. This patch fixes it by moving the generic module request in the common helper code. Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=111021 Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/pci/hda/hda_bind.c | 42 ++++++++++++++++++++++++++++++---------- 1 file changed, 32 insertions(+), 10 deletions(-) diff --git a/sound/pci/hda/hda_bind.c b/sound/pci/hda/hda_bind.c index 70671ad65d24..6efadbfb3fe3 100644 --- a/sound/pci/hda/hda_bind.c +++ b/sound/pci/hda/hda_bind.c @@ -174,14 +174,40 @@ static inline bool codec_probed(struct hda_codec *codec) return device_attach(hda_codec_dev(codec)) > 0 && codec->preset; } +/* try to auto-load codec module */ +static void request_codec_module(struct hda_codec *codec) +{ +#ifdef MODULE + char modalias[32]; + const char *mod = NULL; + + switch (codec->probe_id) { + case HDA_CODEC_ID_GENERIC_HDMI: +#if IS_MODULE(CONFIG_SND_HDA_CODEC_HDMI) + mod = "snd-hda-codec-hdmi"; +#endif + break; + case HDA_CODEC_ID_GENERIC: +#if IS_MODULE(CONFIG_SND_HDA_GENERIC) + mod = "snd-hda-codec-generic"; +#endif + break; + default: + snd_hdac_codec_modalias(&codec->core, modalias, sizeof(modalias)); + mod = modalias; + break; + } + + if (mod) + request_module(mod); +#endif /* MODULE */ +} + /* try to auto-load and bind the codec module */ static void codec_bind_module(struct hda_codec *codec) { #ifdef MODULE - char modalias[32]; - - snd_hdac_codec_modalias(&codec->core, modalias, sizeof(modalias)); - request_module(modalias); + request_codec_module(codec); if (codec_probed(codec)) return; #endif @@ -218,17 +244,13 @@ static int codec_bind_generic(struct hda_codec *codec) if (is_likely_hdmi_codec(codec)) { codec->probe_id = HDA_CODEC_ID_GENERIC_HDMI; -#if IS_MODULE(CONFIG_SND_HDA_CODEC_HDMI) - request_module("snd-hda-codec-hdmi"); -#endif + request_codec_module(codec); if (codec_probed(codec)) return 0; } codec->probe_id = HDA_CODEC_ID_GENERIC; -#if IS_MODULE(CONFIG_SND_HDA_GENERIC) - request_module("snd-hda-codec-generic"); -#endif + request_codec_module(codec); if (codec_probed(codec)) return 0; return -ENODEV; From f5b62074b31a2844579831499defca2cf2264df2 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Wed, 20 Jan 2016 17:19:02 +0100 Subject: [PATCH 028/325] ALSA: hda - Flush the pending probe work at remove commit 991f86d7ae4e1f8c15806e62f97af519e3cdd860 upstream. As HD-audio driver does deferred probe internally via workqueue, the driver might go into the mixed state doing both probe and remove when the module gets unloaded during the probe work. This eventually triggers an Oops, unsurprisingly. For avoiding this race, we just need to flush the pending probe work explicitly before actually starting the resource release. Bugzilla: https://bugzilla.opensuse.org/show_bug.cgi?id=960710 Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/pci/hda/hda_intel.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index 3b3658297070..614baff1f5d7 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -2126,9 +2126,17 @@ i915_power_fail: static void azx_remove(struct pci_dev *pci) { struct snd_card *card = pci_get_drvdata(pci); + struct azx *chip; + struct hda_intel *hda; + + if (card) { + /* flush the pending probing work */ + chip = card->private_data; + hda = container_of(chip, struct hda_intel, chip); + flush_work(&hda->probe_work); - if (card) snd_card_free(card); + } } static void azx_shutdown(struct pci_dev *pci) From b1d1b88c0d3ce4a566fa60ce68009e7e0881e590 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Thu, 21 Jan 2016 17:19:31 +0100 Subject: [PATCH 029/325] ALSA: timer: Handle disconnection more safely commit 230323dac060123c340cf75997971145a42661ee upstream. Currently ALSA timer device doesn't take the disconnection into account very well; it merely unlinks the timer device at disconnection callback but does nothing else. Because of this, when an application accessing the timer device is disconnected, it may release the resource before actually closed. In most cases, it results in a warning message indicating a leftover timer instance like: ALSA: timer xxxx is busy? But basically this is an open race. This patch tries to address it. The strategy is like other ALSA devices: namely, - Manage card's refcount at each open/close - Wake up the pending tasks at disconnection - Check the shutdown flag appropriately at each possible call Note that this patch has one ugly hack to handle the wakeup of pending tasks. It'd be cleaner to introduce a new disconnect op to snd_timer_instance ops. But since it would lead to internal ABI breakage and it eventually increase my own work when backporting to stable kernels, I took a different path to implement locally in timer.c. A cleanup patch will follow at next for 4.5 kernel. Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=109431 Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/core/timer.c | 48 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 48 insertions(+) diff --git a/sound/core/timer.c b/sound/core/timer.c index 4e8d7bfffff6..0a049c4578f1 100644 --- a/sound/core/timer.c +++ b/sound/core/timer.c @@ -65,6 +65,7 @@ struct snd_timer_user { int qtail; int qused; int queue_size; + bool disconnected; struct snd_timer_read *queue; struct snd_timer_tread *tqueue; spinlock_t qlock; @@ -290,6 +291,9 @@ int snd_timer_open(struct snd_timer_instance **ti, mutex_unlock(®ister_mutex); return -ENOMEM; } + /* take a card refcount for safe disconnection */ + if (timer->card) + get_device(&timer->card->card_dev); timeri->slave_class = tid->dev_sclass; timeri->slave_id = slave_id; if (list_empty(&timer->open_list_head) && timer->hw.open) @@ -360,6 +364,9 @@ int snd_timer_close(struct snd_timer_instance *timeri) } spin_unlock(&timer->lock); spin_unlock_irq(&slave_active_lock); + /* release a card refcount for safe disconnection */ + if (timer->card) + put_device(&timer->card->card_dev); mutex_unlock(®ister_mutex); } out: @@ -475,6 +482,8 @@ int snd_timer_start(struct snd_timer_instance *timeri, unsigned int ticks) timer = timeri->timer; if (timer == NULL) return -EINVAL; + if (timer->card && timer->card->shutdown) + return -ENODEV; spin_lock_irqsave(&timer->lock, flags); timeri->ticks = timeri->cticks = ticks; timeri->pticks = 0; @@ -509,6 +518,10 @@ static int _snd_timer_stop(struct snd_timer_instance * timeri, spin_lock_irqsave(&timer->lock, flags); list_del_init(&timeri->ack_list); list_del_init(&timeri->active_list); + if (timer->card && timer->card->shutdown) { + spin_unlock_irqrestore(&timer->lock, flags); + return 0; + } if ((timeri->flags & SNDRV_TIMER_IFLG_RUNNING) && !(--timer->running)) { timer->hw.stop(timer); @@ -571,6 +584,8 @@ int snd_timer_continue(struct snd_timer_instance *timeri) timer = timeri->timer; if (! timer) return -EINVAL; + if (timer->card && timer->card->shutdown) + return -ENODEV; spin_lock_irqsave(&timer->lock, flags); if (!timeri->cticks) timeri->cticks = 1; @@ -634,6 +649,9 @@ static void snd_timer_tasklet(unsigned long arg) unsigned long resolution, ticks; unsigned long flags; + if (timer->card && timer->card->shutdown) + return; + spin_lock_irqsave(&timer->lock, flags); /* now process all callbacks */ while (!list_empty(&timer->sack_list_head)) { @@ -674,6 +692,9 @@ void snd_timer_interrupt(struct snd_timer * timer, unsigned long ticks_left) if (timer == NULL) return; + if (timer->card && timer->card->shutdown) + return; + spin_lock_irqsave(&timer->lock, flags); /* remember the current resolution */ @@ -884,11 +905,28 @@ static int snd_timer_dev_register(struct snd_device *dev) return 0; } +/* just for reference in snd_timer_dev_disconnect() below */ +static void snd_timer_user_ccallback(struct snd_timer_instance *timeri, + int event, struct timespec *tstamp, + unsigned long resolution); + static int snd_timer_dev_disconnect(struct snd_device *device) { struct snd_timer *timer = device->device_data; + struct snd_timer_instance *ti; + mutex_lock(®ister_mutex); list_del_init(&timer->device_list); + /* wake up pending sleepers */ + list_for_each_entry(ti, &timer->open_list_head, open_list) { + /* FIXME: better to have a ti.disconnect() op */ + if (ti->ccallback == snd_timer_user_ccallback) { + struct snd_timer_user *tu = ti->callback_data; + + tu->disconnected = true; + wake_up(&tu->qchange_sleep); + } + } mutex_unlock(®ister_mutex); return 0; } @@ -899,6 +937,8 @@ void snd_timer_notify(struct snd_timer *timer, int event, struct timespec *tstam unsigned long resolution = 0; struct snd_timer_instance *ti, *ts; + if (timer->card && timer->card->shutdown) + return; if (! (timer->hw.flags & SNDRV_TIMER_HW_SLAVE)) return; if (snd_BUG_ON(event < SNDRV_TIMER_EVENT_MSTART || @@ -1057,6 +1097,8 @@ static void snd_timer_proc_read(struct snd_info_entry *entry, mutex_lock(®ister_mutex); list_for_each_entry(timer, &snd_timer_list, device_list) { + if (timer->card && timer->card->shutdown) + continue; switch (timer->tmr_class) { case SNDRV_TIMER_CLASS_GLOBAL: snd_iprintf(buffer, "G%i: ", timer->tmr_device); @@ -1882,6 +1924,10 @@ static ssize_t snd_timer_user_read(struct file *file, char __user *buffer, remove_wait_queue(&tu->qchange_sleep, &wait); + if (tu->disconnected) { + err = -ENODEV; + break; + } if (signal_pending(current)) { err = -ERESTARTSYS; break; @@ -1931,6 +1977,8 @@ static unsigned int snd_timer_user_poll(struct file *file, poll_table * wait) mask = 0; if (tu->qused) mask |= POLLIN | POLLRDNORM; + if (tu->disconnected) + mask |= POLLERR; return mask; } From 0aa263bba0ed12757fe639248c7c46e6a8d288d5 Mon Sep 17 00:00:00 2001 From: Charles Keepax Date: Wed, 6 Jan 2016 15:15:37 +0000 Subject: [PATCH 030/325] ASoC: wm5110: Fix PGA clear when disabling DRE commit 24338722cfa23fdf4e08c6189a11f7e3a902d86a upstream. We don't want to use a bypassed write in wm5110_clear_pga_volume, we might disable the DRE whilst the CODEC is powered down. A normal regmap_write will always go to the hardware (when not on cache_only) even if the written value matches the cache. As using a normal write will still achieve the desired behaviour of bring the cache and hardware in sync, this patch updates the function to use a normal write, which avoids issues when the CODEC is powered down. Signed-off-by: Charles Keepax Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- sound/soc/codecs/wm5110.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) diff --git a/sound/soc/codecs/wm5110.c b/sound/soc/codecs/wm5110.c index c04c0bc6f58a..52b9ccf6d389 100644 --- a/sound/soc/codecs/wm5110.c +++ b/sound/soc/codecs/wm5110.c @@ -360,15 +360,13 @@ static int wm5110_hp_ev(struct snd_soc_dapm_widget *w, static int wm5110_clear_pga_volume(struct arizona *arizona, int output) { - struct reg_sequence clear_pga = { - ARIZONA_OUTPUT_PATH_CONFIG_1L + output * 4, 0x80 - }; + unsigned int reg = ARIZONA_OUTPUT_PATH_CONFIG_1L + output * 4; int ret; - ret = regmap_multi_reg_write_bypassed(arizona->regmap, &clear_pga, 1); + ret = regmap_write(arizona->regmap, reg, 0x80); if (ret) dev_err(arizona->dev, "Failed to clear PGA (0x%x): %d\n", - clear_pga.reg, ret); + reg, ret); return ret; } From ee8d049d0c7bbd5d739f3e873c4e66123d4da32c Mon Sep 17 00:00:00 2001 From: Vinod Koul Date: Thu, 7 Jan 2016 21:48:14 +0530 Subject: [PATCH 031/325] ASoC: compress: Fix compress device direction check commit a1068045883ed4a18363a4ebad0c3d55e473b716 upstream. The detection of direction for compress was only taking into account codec capabilities and not CPU ones. Fix this by checking the CPU side capabilities as well Tested-by: Ashish Panwar Signed-off-by: Vinod Koul Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- sound/soc/soc-compress.c | 25 +++++++++++++++++++++---- 1 file changed, 21 insertions(+), 4 deletions(-) diff --git a/sound/soc/soc-compress.c b/sound/soc/soc-compress.c index 12a9820feac1..bb82bb966000 100644 --- a/sound/soc/soc-compress.c +++ b/sound/soc/soc-compress.c @@ -630,6 +630,7 @@ int snd_soc_new_compress(struct snd_soc_pcm_runtime *rtd, int num) struct snd_pcm *be_pcm; char new_name[64]; int ret = 0, direction = 0; + int playback = 0, capture = 0; if (rtd->num_codecs > 1) { dev_err(rtd->card->dev, "Multicodec not supported for compressed stream\n"); @@ -641,11 +642,27 @@ int snd_soc_new_compress(struct snd_soc_pcm_runtime *rtd, int num) rtd->dai_link->stream_name, codec_dai->name, num); if (codec_dai->driver->playback.channels_min) - direction = SND_COMPRESS_PLAYBACK; - else if (codec_dai->driver->capture.channels_min) - direction = SND_COMPRESS_CAPTURE; - else + playback = 1; + if (codec_dai->driver->capture.channels_min) + capture = 1; + + capture = capture && cpu_dai->driver->capture.channels_min; + playback = playback && cpu_dai->driver->playback.channels_min; + + /* + * Compress devices are unidirectional so only one of the directions + * should be set, check for that (xor) + */ + if (playback + capture != 1) { + dev_err(rtd->card->dev, "Invalid direction for compress P %d, C %d\n", + playback, capture); return -EINVAL; + } + + if(playback) + direction = SND_COMPRESS_PLAYBACK; + else + direction = SND_COMPRESS_CAPTURE; compr = kzalloc(sizeof(*compr), GFP_KERNEL); if (compr == NULL) { From 7e92cfc4783b49d077774d78ea5485aa82dc4953 Mon Sep 17 00:00:00 2001 From: Peter Wu Date: Mon, 7 Dec 2015 01:07:31 +0100 Subject: [PATCH 032/325] rtlwifi: fix memory leak for USB device commit 17bc55864f81dd730d05f09b1641312a7990d636 upstream. Free skb for received frames with a wrong checksum. This can happen pretty rapidly, exhausting all memory. This fixes a memleak (detected with kmemleak). Originally found while using monitor mode, but it also appears during managed mode (once the link is up). Signed-off-by: Peter Wu ACKed-by: Larry Finger Signed-off-by: Kalle Valo Signed-off-by: Greg Kroah-Hartman --- drivers/net/wireless/realtek/rtlwifi/usb.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/wireless/realtek/rtlwifi/usb.c b/drivers/net/wireless/realtek/rtlwifi/usb.c index 2721cf89fb16..aac1ed3f7bb4 100644 --- a/drivers/net/wireless/realtek/rtlwifi/usb.c +++ b/drivers/net/wireless/realtek/rtlwifi/usb.c @@ -531,6 +531,8 @@ static void _rtl_usb_rx_process_noagg(struct ieee80211_hw *hw, ieee80211_rx(hw, skb); else dev_kfree_skb_any(skb); + } else { + dev_kfree_skb_any(skb); } } From 739d010005bbb8107f06135d06f1d9b88c9942b5 Mon Sep 17 00:00:00 2001 From: Oliver Freyermuth Date: Mon, 28 Dec 2015 18:37:38 +0100 Subject: [PATCH 033/325] USB: cp210x: add ID for ELV Marble Sound Board 1 commit f7d7f59ab124748156ea551edf789994f05da342 upstream. Add the USB device ID for ELV Marble Sound Board 1. Signed-off-by: Oliver Freyermuth Signed-off-by: Johan Hovold Signed-off-by: Greg Kroah-Hartman --- drivers/usb/serial/cp210x.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c index 7d4f51a32e66..59b2126b21a3 100644 --- a/drivers/usb/serial/cp210x.c +++ b/drivers/usb/serial/cp210x.c @@ -160,6 +160,7 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x17F4, 0xAAAA) }, /* Wavesense Jazz blood glucose meter */ { USB_DEVICE(0x1843, 0x0200) }, /* Vaisala USB Instrument Cable */ { USB_DEVICE(0x18EF, 0xE00F) }, /* ELV USB-I2C-Interface */ + { USB_DEVICE(0x18EF, 0xE025) }, /* ELV Marble Sound Board 1 */ { USB_DEVICE(0x1ADB, 0x0001) }, /* Schweitzer Engineering C662 Cable */ { USB_DEVICE(0x1B1C, 0x1C00) }, /* Corsair USB Dongle */ { USB_DEVICE(0x1BA4, 0x0002) }, /* Silicon Labs 358x factory default */ From 877764274280a69a888e1fdb18d411b36dc25c31 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Sat, 14 Nov 2015 16:26:32 +0800 Subject: [PATCH 034/325] usb: core: lpm: fix usb3_hardware_lpm sysfs node commit bf5ce5bf3cc7136fd7fe5e8999a580bc93a9c8f6 upstream. Commit 655fe4effe0f ("usbcore: add sysfs support to xHCI usb3 hardware LPM") introduced usb3_hardware_lpm sysfs node. This doesn't show the correct status of USB3 U1 and U2 LPM status. This patch fixes this by replacing usb3_hardware_lpm with two nodes, usb3_hardware_lpm_u1 (for U1) and usb3_hardware_lpm_u2 (for U2), and recording the U1/U2 LPM status in right places. This patch should be back-ported to kernels as old as 4.3, that contains Commit 655fe4effe0f ("usbcore: add sysfs support to xHCI usb3 hardware LPM"). Signed-off-by: Lu Baolu Signed-off-by: Greg Kroah-Hartman --- Documentation/ABI/testing/sysfs-bus-usb | 16 +++++----- Documentation/usb/power-management.txt | 11 +++---- drivers/usb/core/hub.c | 39 +++++++++++++++++++------ drivers/usb/core/sysfs.c | 31 ++++++++++++++++---- include/linux/usb.h | 4 +++ 5 files changed, 75 insertions(+), 26 deletions(-) diff --git a/Documentation/ABI/testing/sysfs-bus-usb b/Documentation/ABI/testing/sysfs-bus-usb index 3a4abfc44f5e..136ba17d2da0 100644 --- a/Documentation/ABI/testing/sysfs-bus-usb +++ b/Documentation/ABI/testing/sysfs-bus-usb @@ -134,19 +134,21 @@ Description: enabled for the device. Developer can write y/Y/1 or n/N/0 to the file to enable/disable the feature. -What: /sys/bus/usb/devices/.../power/usb3_hardware_lpm -Date: June 2015 +What: /sys/bus/usb/devices/.../power/usb3_hardware_lpm_u1 + /sys/bus/usb/devices/.../power/usb3_hardware_lpm_u2 +Date: November 2015 Contact: Kevin Strasser + Lu Baolu Description: If CONFIG_PM is set and a USB 3.0 lpm-capable device is plugged in to a xHCI host which supports link PM, it will check if U1 and U2 exit latencies have been set in the BOS descriptor; if - the check is is passed and the host supports USB3 hardware LPM, + the check is passed and the host supports USB3 hardware LPM, USB3 hardware LPM will be enabled for the device and the USB - device directory will contain a file named - power/usb3_hardware_lpm. The file holds a string value (enable - or disable) indicating whether or not USB3 hardware LPM is - enabled for the device. + device directory will contain two files named + power/usb3_hardware_lpm_u1 and power/usb3_hardware_lpm_u2. These + files hold a string value (enable or disable) indicating whether + or not USB3 hardware LPM U1 or U2 is enabled for the device. What: /sys/bus/usb/devices/.../removable Date: February 2012 diff --git a/Documentation/usb/power-management.txt b/Documentation/usb/power-management.txt index 4a15c90bc11d..0a94ffe17ab6 100644 --- a/Documentation/usb/power-management.txt +++ b/Documentation/usb/power-management.txt @@ -537,17 +537,18 @@ relevant attribute files are usb2_hardware_lpm and usb3_hardware_lpm. can write y/Y/1 or n/N/0 to the file to enable/disable USB2 hardware LPM manually. This is for test purpose mainly. - power/usb3_hardware_lpm + power/usb3_hardware_lpm_u1 + power/usb3_hardware_lpm_u2 When a USB 3.0 lpm-capable device is plugged in to a xHCI host which supports link PM, it will check if U1 and U2 exit latencies have been set in the BOS descriptor; if the check is is passed and the host supports USB3 hardware LPM, USB3 hardware LPM will be - enabled for the device and this file will be created. - The file holds a string value (enable or disable) - indicating whether or not USB3 hardware LPM is - enabled for the device. + enabled for the device and these files will be created. + The files hold a string value (enable or disable) + indicating whether or not USB3 hardware LPM U1 or U2 + is enabled for the device. USB Port Power Control ---------------------- diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index ddbf32d599cb..8683436788c3 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -3895,17 +3895,30 @@ static void usb_enable_link_state(struct usb_hcd *hcd, struct usb_device *udev, return; } - if (usb_set_lpm_timeout(udev, state, timeout)) + if (usb_set_lpm_timeout(udev, state, timeout)) { /* If we can't set the parent hub U1/U2 timeout, * device-initiated LPM won't be allowed either, so let the xHCI * host know that this link state won't be enabled. */ hcd->driver->disable_usb3_lpm_timeout(hcd, udev, state); + } else { + /* Only a configured device will accept the Set Feature + * U1/U2_ENABLE + */ + if (udev->actconfig) + usb_set_device_initiated_lpm(udev, state, true); - /* Only a configured device will accept the Set Feature U1/U2_ENABLE */ - else if (udev->actconfig) - usb_set_device_initiated_lpm(udev, state, true); - + /* As soon as usb_set_lpm_timeout(timeout) returns 0, the + * hub-initiated LPM is enabled. Thus, LPM is enabled no + * matter the result of usb_set_device_initiated_lpm(). + * The only difference is whether device is able to initiate + * LPM. + */ + if (state == USB3_LPM_U1) + udev->usb3_lpm_u1_enabled = 1; + else if (state == USB3_LPM_U2) + udev->usb3_lpm_u2_enabled = 1; + } } /* @@ -3945,6 +3958,18 @@ static int usb_disable_link_state(struct usb_hcd *hcd, struct usb_device *udev, dev_warn(&udev->dev, "Could not disable xHCI %s timeout, " "bus schedule bandwidth may be impacted.\n", usb3_lpm_names[state]); + + /* As soon as usb_set_lpm_timeout(0) return 0, hub initiated LPM + * is disabled. Hub will disallows link to enter U1/U2 as well, + * even device is initiating LPM. Hence LPM is disabled if hub LPM + * timeout set to 0, no matter device-initiated LPM is disabled or + * not. + */ + if (state == USB3_LPM_U1) + udev->usb3_lpm_u1_enabled = 0; + else if (state == USB3_LPM_U2) + udev->usb3_lpm_u2_enabled = 0; + return 0; } @@ -3979,8 +4004,6 @@ int usb_disable_lpm(struct usb_device *udev) if (usb_disable_link_state(hcd, udev, USB3_LPM_U2)) goto enable_lpm; - udev->usb3_lpm_enabled = 0; - return 0; enable_lpm: @@ -4038,8 +4061,6 @@ void usb_enable_lpm(struct usb_device *udev) usb_enable_link_state(hcd, udev, USB3_LPM_U1); usb_enable_link_state(hcd, udev, USB3_LPM_U2); - - udev->usb3_lpm_enabled = 1; } EXPORT_SYMBOL_GPL(usb_enable_lpm); diff --git a/drivers/usb/core/sysfs.c b/drivers/usb/core/sysfs.c index d9ec2de6c4cf..65b6e6b84043 100644 --- a/drivers/usb/core/sysfs.c +++ b/drivers/usb/core/sysfs.c @@ -531,7 +531,7 @@ static ssize_t usb2_lpm_besl_store(struct device *dev, } static DEVICE_ATTR_RW(usb2_lpm_besl); -static ssize_t usb3_hardware_lpm_show(struct device *dev, +static ssize_t usb3_hardware_lpm_u1_show(struct device *dev, struct device_attribute *attr, char *buf) { struct usb_device *udev = to_usb_device(dev); @@ -539,7 +539,7 @@ static ssize_t usb3_hardware_lpm_show(struct device *dev, usb_lock_device(udev); - if (udev->usb3_lpm_enabled) + if (udev->usb3_lpm_u1_enabled) p = "enabled"; else p = "disabled"; @@ -548,7 +548,26 @@ static ssize_t usb3_hardware_lpm_show(struct device *dev, return sprintf(buf, "%s\n", p); } -static DEVICE_ATTR_RO(usb3_hardware_lpm); +static DEVICE_ATTR_RO(usb3_hardware_lpm_u1); + +static ssize_t usb3_hardware_lpm_u2_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct usb_device *udev = to_usb_device(dev); + const char *p; + + usb_lock_device(udev); + + if (udev->usb3_lpm_u2_enabled) + p = "enabled"; + else + p = "disabled"; + + usb_unlock_device(udev); + + return sprintf(buf, "%s\n", p); +} +static DEVICE_ATTR_RO(usb3_hardware_lpm_u2); static struct attribute *usb2_hardware_lpm_attr[] = { &dev_attr_usb2_hardware_lpm.attr, @@ -562,7 +581,8 @@ static struct attribute_group usb2_hardware_lpm_attr_group = { }; static struct attribute *usb3_hardware_lpm_attr[] = { - &dev_attr_usb3_hardware_lpm.attr, + &dev_attr_usb3_hardware_lpm_u1.attr, + &dev_attr_usb3_hardware_lpm_u2.attr, NULL, }; static struct attribute_group usb3_hardware_lpm_attr_group = { @@ -592,7 +612,8 @@ static int add_power_attributes(struct device *dev) if (udev->usb2_hw_lpm_capable == 1) rc = sysfs_merge_group(&dev->kobj, &usb2_hardware_lpm_attr_group); - if (udev->lpm_capable == 1) + if (udev->speed == USB_SPEED_SUPER && + udev->lpm_capable == 1) rc = sysfs_merge_group(&dev->kobj, &usb3_hardware_lpm_attr_group); } diff --git a/include/linux/usb.h b/include/linux/usb.h index b9a28074210f..b79925dd2b41 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -511,6 +511,8 @@ struct usb3_lpm_parameters { * @usb2_hw_lpm_enabled: USB2 hardware LPM is enabled * @usb2_hw_lpm_allowed: Userspace allows USB 2.0 LPM to be enabled * @usb3_lpm_enabled: USB3 hardware LPM enabled + * @usb3_lpm_u1_enabled: USB3 hardware U1 LPM enabled + * @usb3_lpm_u2_enabled: USB3 hardware U2 LPM enabled * @string_langid: language ID for strings * @product: iProduct string, if present (static) * @manufacturer: iManufacturer string, if present (static) @@ -584,6 +586,8 @@ struct usb_device { unsigned usb2_hw_lpm_enabled:1; unsigned usb2_hw_lpm_allowed:1; unsigned usb3_lpm_enabled:1; + unsigned usb3_lpm_u1_enabled:1; + unsigned usb3_lpm_u2_enabled:1; int string_langid; /* static strings from the device */ From 3767d554c088e1e8e4680c69d57c31e000dd7dec Mon Sep 17 00:00:00 2001 From: Oliver Neukum Date: Thu, 3 Dec 2015 15:03:34 +0100 Subject: [PATCH 035/325] xhci: refuse loading if nousb is used commit 1eaf35e4dd592c59041bc1ed3248c46326da1f5f upstream. The module should fail to load. Signed-off-by: Oliver Neukum Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index 3f912705dcef..dca0a4692f08 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -5059,6 +5059,10 @@ static int __init xhci_hcd_init(void) BUILD_BUG_ON(sizeof(struct xhci_intr_reg) != 8*32/8); /* xhci_run_regs has eight fields and embeds 128 xhci_intr_regs */ BUILD_BUG_ON(sizeof(struct xhci_run_regs) != (8+8*128)*32/8); + + if (usb_disabled()) + return -ENODEV; + return 0; } From 5e226f9689d90ad8ab21b4a969ae3058777f0aff Mon Sep 17 00:00:00 2001 From: willy tarreau Date: Sun, 10 Jan 2016 07:54:56 +0100 Subject: [PATCH 036/325] unix: properly account for FDs passed over unix sockets [ Upstream commit 712f4aad406bb1ed67f3f98d04c044191f0ff593 ] It is possible for a process to allocate and accumulate far more FDs than the process' limit by sending them over a unix socket then closing them to keep the process' fd count low. This change addresses this problem by keeping track of the number of FDs in flight per user and preventing non-privileged processes from having more FDs in flight than their configured FD limit. Reported-by: socketpair@gmail.com Reported-by: Tetsuo Handa Mitigates: CVE-2013-4312 (Linux 2.0+) Suggested-by: Linus Torvalds Acked-by: Hannes Frederic Sowa Signed-off-by: Willy Tarreau Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- include/linux/sched.h | 1 + net/unix/af_unix.c | 24 ++++++++++++++++++++---- net/unix/garbage.c | 13 ++++++++----- 3 files changed, 29 insertions(+), 9 deletions(-) diff --git a/include/linux/sched.h b/include/linux/sched.h index fa39434e3fdd..21a6e9649012 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -830,6 +830,7 @@ struct user_struct { unsigned long mq_bytes; /* How many bytes can be allocated to mqueue? */ #endif unsigned long locked_shm; /* How many pages of mlocked shm ? */ + unsigned long unix_inflight; /* How many files in flight in unix sockets */ #ifdef CONFIG_KEYS struct key *uid_keyring; /* UID specific keyring */ diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index ef05cd9403d4..e3f85bc8b135 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1513,6 +1513,21 @@ static void unix_destruct_scm(struct sk_buff *skb) sock_wfree(skb); } +/* + * The "user->unix_inflight" variable is protected by the garbage + * collection lock, and we just read it locklessly here. If you go + * over the limit, there might be a tiny race in actually noticing + * it across threads. Tough. + */ +static inline bool too_many_unix_fds(struct task_struct *p) +{ + struct user_struct *user = current_user(); + + if (unlikely(user->unix_inflight > task_rlimit(p, RLIMIT_NOFILE))) + return !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN); + return false; +} + #define MAX_RECURSION_LEVEL 4 static int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb) @@ -1521,6 +1536,9 @@ static int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb) unsigned char max_level = 0; int unix_sock_count = 0; + if (too_many_unix_fds(current)) + return -ETOOMANYREFS; + for (i = scm->fp->count - 1; i >= 0; i--) { struct sock *sk = unix_get_socket(scm->fp->fp[i]); @@ -1542,10 +1560,8 @@ static int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb) if (!UNIXCB(skb).fp) return -ENOMEM; - if (unix_sock_count) { - for (i = scm->fp->count - 1; i >= 0; i--) - unix_inflight(scm->fp->fp[i]); - } + for (i = scm->fp->count - 1; i >= 0; i--) + unix_inflight(scm->fp->fp[i]); return max_level; } diff --git a/net/unix/garbage.c b/net/unix/garbage.c index a73a226f2d33..8fcdc2283af5 100644 --- a/net/unix/garbage.c +++ b/net/unix/garbage.c @@ -120,11 +120,11 @@ void unix_inflight(struct file *fp) { struct sock *s = unix_get_socket(fp); + spin_lock(&unix_gc_lock); + if (s) { struct unix_sock *u = unix_sk(s); - spin_lock(&unix_gc_lock); - if (atomic_long_inc_return(&u->inflight) == 1) { BUG_ON(!list_empty(&u->link)); list_add_tail(&u->link, &gc_inflight_list); @@ -132,25 +132,28 @@ void unix_inflight(struct file *fp) BUG_ON(list_empty(&u->link)); } unix_tot_inflight++; - spin_unlock(&unix_gc_lock); } + fp->f_cred->user->unix_inflight++; + spin_unlock(&unix_gc_lock); } void unix_notinflight(struct file *fp) { struct sock *s = unix_get_socket(fp); + spin_lock(&unix_gc_lock); + if (s) { struct unix_sock *u = unix_sk(s); - spin_lock(&unix_gc_lock); BUG_ON(list_empty(&u->link)); if (atomic_long_dec_and_test(&u->inflight)) list_del_init(&u->link); unix_tot_inflight--; - spin_unlock(&unix_gc_lock); } + fp->f_cred->user->unix_inflight--; + spin_unlock(&unix_gc_lock); } static void scan_inflight(struct sock *x, void (*func)(struct unix_sock *), From 0f3302adebc81256c724af7507909ad9b81f2036 Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Thu, 7 Jan 2016 11:26:53 +0100 Subject: [PATCH 037/325] vxlan: fix test which detect duplicate vxlan iface [ Upstream commit 07b9b37c227cb8d88d478b4a9c5634fee514ede1 ] When a vxlan interface is created, the driver checks that there is not another vxlan interface with the same properties. To do this, it checks the existing vxlan udp socket. Since commit 1c51a9159dde, the creation of the vxlan socket is done only when the interface is set up, thus it breaks that test. Example: $ ip l a vxlan10 type vxlan id 10 group 239.0.0.10 dev eth0 dstport 0 $ ip l a vxlan11 type vxlan id 10 group 239.0.0.10 dev eth0 dstport 0 $ ip -br l | grep vxlan vxlan10 DOWN f2:55:1c:6a:fb:00 vxlan11 DOWN 7a:cb:b9:38:59:0d Instead of checking sockets, let's loop over the vxlan iface list. Fixes: 1c51a9159dde ("vxlan: fix race caused by dropping rtnl_unlock") Reported-by: Thomas Faivre Signed-off-by: Nicolas Dichtel Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/vxlan.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index ba363cedef80..405a7b6cca25 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -2751,7 +2751,7 @@ static int vxlan_dev_configure(struct net *src_net, struct net_device *dev, struct vxlan_config *conf) { struct vxlan_net *vn = net_generic(src_net, vxlan_net_id); - struct vxlan_dev *vxlan = netdev_priv(dev); + struct vxlan_dev *vxlan = netdev_priv(dev), *tmp; struct vxlan_rdst *dst = &vxlan->default_dst; unsigned short needed_headroom = ETH_HLEN; int err; @@ -2817,9 +2817,15 @@ static int vxlan_dev_configure(struct net *src_net, struct net_device *dev, if (!vxlan->cfg.age_interval) vxlan->cfg.age_interval = FDB_AGE_DEFAULT; - if (vxlan_find_vni(src_net, conf->vni, use_ipv6 ? AF_INET6 : AF_INET, - vxlan->cfg.dst_port, vxlan->flags)) + list_for_each_entry(tmp, &vn->vxlan_list, next) { + if (tmp->cfg.vni == conf->vni && + (tmp->default_dst.remote_ip.sa.sa_family == AF_INET6 || + tmp->cfg.saddr.sa.sa_family == AF_INET6) == use_ipv6 && + tmp->cfg.dst_port == vxlan->cfg.dst_port && + (tmp->flags & VXLAN_F_RCV_FLAGS) == + (vxlan->flags & VXLAN_F_RCV_FLAGS)) return -EEXIST; + } dev->ethtool_ops = &vxlan_ethtool_ops; From 8534537d0b7914346c1d80dd374976b6bcbe508e Mon Sep 17 00:00:00 2001 From: Sasha Levin Date: Thu, 7 Jan 2016 14:52:43 -0500 Subject: [PATCH 038/325] net: sctp: prevent writes to cookie_hmac_alg from accessing invalid memory [ Upstream commit 320f1a4a175e7cd5d3f006f92b4d4d3e2cbb7bb5 ] proc_dostring() needs an initialized destination string, while the one provided in proc_sctp_do_hmac_alg() contains stack garbage. Thus, writing to cookie_hmac_alg would strlen() that garbage and end up accessing invalid memory. Fixes: 3c68198e7 ("sctp: Make hmac algorithm selection for cookie generation dynamic") Signed-off-by: Sasha Levin Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/sctp/sysctl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c index 26d50c565f54..3e0fc5127225 100644 --- a/net/sctp/sysctl.c +++ b/net/sctp/sysctl.c @@ -320,7 +320,7 @@ static int proc_sctp_do_hmac_alg(struct ctl_table *ctl, int write, struct ctl_table tbl; bool changed = false; char *none = "none"; - char tmp[8]; + char tmp[8] = {0}; int ret; memset(&tbl, 0, sizeof(struct ctl_table)); From 7caad825e2bfb40db53157000e9d15d324d07024 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 8 Jan 2016 09:35:51 -0800 Subject: [PATCH 039/325] ipv6: tcp: add rcu locking in tcp_v6_send_synack() [ Upstream commit 3e4006f0b86a5ae5eb0e8215f9a9e1db24506977 ] When first SYNACK is sent, we already hold rcu_read_lock(), but this is not true if a SYNACK is retransmitted, as a timer (soft) interrupt does not hold rcu_read_lock() Fixes: 45f6fad84cc30 ("ipv6: add complete rcu protection around np->opt") Reported-by: Dave Jones Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv6/tcp_ipv6.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 6b8a8a9091fa..bd100b47c717 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -462,8 +462,10 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst, if (np->repflow && ireq->pktopts) fl6->flowlabel = ip6_flowlabel(ipv6_hdr(ireq->pktopts)); + rcu_read_lock(); err = ip6_xmit(sk, skb, fl6, rcu_dereference(np->opt), np->tclass); + rcu_read_unlock(); err = net_xmit_eval(err); } From 5f15ae009e6fb268df7937082f3859eda34e6e38 Mon Sep 17 00:00:00 2001 From: Neal Cardwell Date: Mon, 11 Jan 2016 13:42:43 -0500 Subject: [PATCH 040/325] tcp_yeah: don't set ssthresh below 2 [ Upstream commit 83d15e70c4d8909d722c0d64747d8fb42e38a48f ] For tcp_yeah, use an ssthresh floor of 2, the same floor used by Reno and CUBIC, per RFC 5681 (equation 4). tcp_yeah_ssthresh() was sometimes returning a 0 or negative ssthresh value if the intended reduction is as big or bigger than the current cwnd. Congestion control modules should never return a zero or negative ssthresh. A zero ssthresh generally results in a zero cwnd, causing the connection to stall. A negative ssthresh value will be interpreted as a u32 and will set a target cwnd for PRR near 4 billion. Oleksandr Natalenko reported that a system using tcp_yeah with ECN could see a warning about a prior_cwnd of 0 in tcp_cwnd_reduction(). Testing verified that this was due to tcp_yeah_ssthresh() misbehaving in this way. Reported-by: Oleksandr Natalenko Signed-off-by: Neal Cardwell Signed-off-by: Yuchung Cheng Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv4/tcp_yeah.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/tcp_yeah.c b/net/ipv4/tcp_yeah.c index 17d35662930d..3e6a472e6b88 100644 --- a/net/ipv4/tcp_yeah.c +++ b/net/ipv4/tcp_yeah.c @@ -219,7 +219,7 @@ static u32 tcp_yeah_ssthresh(struct sock *sk) yeah->fast_count = 0; yeah->reno_count = max(yeah->reno_count>>1, 2U); - return tp->snd_cwnd - reduction; + return max_t(int, tp->snd_cwnd - reduction, 2); } static struct tcp_congestion_ops tcp_yeah __read_mostly = { From 8ece807074d09df2dc2a2ba12783cc5a36cb6cf2 Mon Sep 17 00:00:00 2001 From: Jamal Hadi Salim Date: Sun, 10 Jan 2016 11:47:01 -0500 Subject: [PATCH 041/325] sched,cls_flower: set key address type when present [ Upstream commit 66530bdf85eb1d72a0c399665e09a2c2298501c6 ] only when user space passes the addresses should we consider their presence Signed-off-by: Jamal Hadi Salim Acked-by: Jiri Pirko Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/sched/cls_flower.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 57692947ebbe..95b021243233 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -252,23 +252,28 @@ static int fl_set_key(struct net *net, struct nlattr **tb, fl_set_key_val(tb, key->eth.src, TCA_FLOWER_KEY_ETH_SRC, mask->eth.src, TCA_FLOWER_KEY_ETH_SRC_MASK, sizeof(key->eth.src)); + fl_set_key_val(tb, &key->basic.n_proto, TCA_FLOWER_KEY_ETH_TYPE, &mask->basic.n_proto, TCA_FLOWER_UNSPEC, sizeof(key->basic.n_proto)); + if (key->basic.n_proto == htons(ETH_P_IP) || key->basic.n_proto == htons(ETH_P_IPV6)) { fl_set_key_val(tb, &key->basic.ip_proto, TCA_FLOWER_KEY_IP_PROTO, &mask->basic.ip_proto, TCA_FLOWER_UNSPEC, sizeof(key->basic.ip_proto)); } - if (key->control.addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) { + + if (tb[TCA_FLOWER_KEY_IPV4_SRC] || tb[TCA_FLOWER_KEY_IPV4_DST]) { + key->control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; fl_set_key_val(tb, &key->ipv4.src, TCA_FLOWER_KEY_IPV4_SRC, &mask->ipv4.src, TCA_FLOWER_KEY_IPV4_SRC_MASK, sizeof(key->ipv4.src)); fl_set_key_val(tb, &key->ipv4.dst, TCA_FLOWER_KEY_IPV4_DST, &mask->ipv4.dst, TCA_FLOWER_KEY_IPV4_DST_MASK, sizeof(key->ipv4.dst)); - } else if (key->control.addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) { + } else if (tb[TCA_FLOWER_KEY_IPV6_SRC] || tb[TCA_FLOWER_KEY_IPV6_DST]) { + key->control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; fl_set_key_val(tb, &key->ipv6.src, TCA_FLOWER_KEY_IPV6_SRC, &mask->ipv6.src, TCA_FLOWER_KEY_IPV6_SRC_MASK, sizeof(key->ipv6.src)); @@ -276,6 +281,7 @@ static int fl_set_key(struct net *net, struct nlattr **tb, &mask->ipv6.dst, TCA_FLOWER_KEY_IPV6_DST_MASK, sizeof(key->ipv6.dst)); } + if (key->basic.ip_proto == IPPROTO_TCP) { fl_set_key_val(tb, &key->tp.src, TCA_FLOWER_KEY_TCP_SRC, &mask->tp.src, TCA_FLOWER_UNSPEC, From 4d90b0d1c15cf9daa3089faf163df75a68bba5b7 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Sun, 10 Jan 2016 21:38:44 -0800 Subject: [PATCH 042/325] net: pktgen: fix null ptr deref in skb allocation [ Upstream commit 3de03596dfeee48bc803c1d1a6daf60a459929f3 ] Fix possible null pointer dereference that may occur when calling skb_reserve() on a null skb. Fixes: 879c7220e82 ("net: pktgen: Observe needed_headroom of the device") Signed-off-by: John Fastabend Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/core/pktgen.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/net/core/pktgen.c b/net/core/pktgen.c index de8d5cc5eb24..4da4d51a2ccf 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -2787,7 +2787,9 @@ static struct sk_buff *pktgen_alloc_skb(struct net_device *dev, } else { skb = __netdev_alloc_skb(dev, size, GFP_NOWAIT); } - skb_reserve(skb, LL_RESERVED_SPACE(dev)); + + if (likely(skb)) + skb_reserve(skb, LL_RESERVED_SPACE(dev)); return skb; } From b856abbb45e83a7f61afb838b065e6175be61c61 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Michal=20Kube=C4=8Dek?= Date: Mon, 11 Jan 2016 07:50:30 +0100 Subject: [PATCH 043/325] udp: disallow UFO for sockets with SO_NO_CHECK option [ Upstream commit 40ba330227ad00b8c0cdf2f425736ff9549cc423 ] Commit acf8dd0a9d0b ("udp: only allow UFO for packets from SOCK_DGRAM sockets") disallows UFO for packets sent from raw sockets. We need to do the same also for SOCK_DGRAM sockets with SO_NO_CHECK options, even if for a bit different reason: while such socket would override the CHECKSUM_PARTIAL set by ip_ufo_append_data(), gso_size is still set and bad offloading flags warning is triggered in __skb_gso_segment(). In the IPv6 case, SO_NO_CHECK option is ignored but we need to disallow UFO for packets sent by sockets with UDP_NO_CHECK6_TX option. Signed-off-by: Michal Kubecek Tested-by: Shannon Nelson Acked-by: Hannes Frederic Sowa Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv4/ip_output.c | 2 +- net/ipv6/ip6_output.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 4233cbe47052..36ac9f3a6451 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -921,7 +921,7 @@ static int __ip_append_data(struct sock *sk, if (((length > mtu) || (skb && skb_is_gso(skb))) && (sk->sk_protocol == IPPROTO_UDP) && (rt->dst.dev->features & NETIF_F_UFO) && !rt->dst.header_len && - (sk->sk_type == SOCK_DGRAM)) { + (sk->sk_type == SOCK_DGRAM) && !sk->sk_no_check_tx) { err = ip_ufo_append_data(sk, queue, getfrag, from, length, hh_len, fragheaderlen, transhdrlen, maxfraglen, flags); diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index e6a7bd15b9b7..6473889f1736 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1353,7 +1353,7 @@ emsgsize: (skb && skb_is_gso(skb))) && (sk->sk_protocol == IPPROTO_UDP) && (rt->dst.dev->features & NETIF_F_UFO) && - (sk->sk_type == SOCK_DGRAM)) { + (sk->sk_type == SOCK_DGRAM) && !udp_get_no_check6_tx(sk)) { err = ip6_ufo_append_data(sk, queue, getfrag, from, length, hh_len, fragheaderlen, transhdrlen, mtu, flags, fl6); From 1f0bdf609240616452a2864df67493f9a93535ec Mon Sep 17 00:00:00 2001 From: Konstantin Khlebnikov Date: Fri, 8 Jan 2016 15:21:46 +0300 Subject: [PATCH 044/325] net: preserve IP control block during GSO segmentation [ Upstream commit 9207f9d45b0ad071baa128e846d7e7ed85016df3 ] Skb_gso_segment() uses skb control block during segmentation. This patch adds 32-bytes room for previous control block which will be copied into all resulting segments. This patch fixes kernel crash during fragmenting forwarded packets. Fragmentation requires valid IP CB in skb for clearing ip options. Also patch removes custom save/restore in ovs code, now it's redundant. Signed-off-by: Konstantin Khlebnikov Link: http://lkml.kernel.org/r/CALYGNiP-0MZ-FExV2HutTvE9U-QQtkKSoE--KN=JQE5STYsjAA@mail.gmail.com Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- include/linux/skbuff.h | 3 ++- net/core/dev.c | 5 +++++ net/ipv4/ip_output.c | 1 + net/openvswitch/datapath.c | 5 +---- net/xfrm/xfrm_output.c | 2 ++ 5 files changed, 11 insertions(+), 5 deletions(-) diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 4355129fff91..9147f9f34cbe 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3446,7 +3446,8 @@ struct skb_gso_cb { int encap_level; __u16 csum_start; }; -#define SKB_GSO_CB(skb) ((struct skb_gso_cb *)(skb)->cb) +#define SKB_SGO_CB_OFFSET 32 +#define SKB_GSO_CB(skb) ((struct skb_gso_cb *)((skb)->cb + SKB_SGO_CB_OFFSET)) static inline int skb_tnl_header_len(const struct sk_buff *inner_skb) { diff --git a/net/core/dev.c b/net/core/dev.c index ae00b894e675..7f00f2439770 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2542,6 +2542,8 @@ static inline bool skb_needs_check(struct sk_buff *skb, bool tx_path) * * It may return NULL if the skb requires no segmentation. This is * only possible when GSO is used for verifying header integrity. + * + * Segmentation preserves SKB_SGO_CB_OFFSET bytes of previous skb cb. */ struct sk_buff *__skb_gso_segment(struct sk_buff *skb, netdev_features_t features, bool tx_path) @@ -2556,6 +2558,9 @@ struct sk_buff *__skb_gso_segment(struct sk_buff *skb, return ERR_PTR(err); } + BUILD_BUG_ON(SKB_SGO_CB_OFFSET + + sizeof(*SKB_GSO_CB(skb)) > sizeof(skb->cb)); + SKB_GSO_CB(skb)->mac_offset = skb_headroom(skb); SKB_GSO_CB(skb)->encap_level = 0; diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 36ac9f3a6451..49f02856304d 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -240,6 +240,7 @@ static int ip_finish_output_gso(struct net *net, struct sock *sk, * from host network stack. */ features = netif_skb_features(skb); + BUILD_BUG_ON(sizeof(*IPCB(skb)) > SKB_SGO_CB_OFFSET); segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK); if (IS_ERR_OR_NULL(segs)) { kfree_skb(skb); diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 91a8b004dc51..deadfdab1bc3 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -336,12 +336,10 @@ static int queue_gso_packets(struct datapath *dp, struct sk_buff *skb, unsigned short gso_type = skb_shinfo(skb)->gso_type; struct sw_flow_key later_key; struct sk_buff *segs, *nskb; - struct ovs_skb_cb ovs_cb; int err; - ovs_cb = *OVS_CB(skb); + BUILD_BUG_ON(sizeof(*OVS_CB(skb)) > SKB_SGO_CB_OFFSET); segs = __skb_gso_segment(skb, NETIF_F_SG, false); - *OVS_CB(skb) = ovs_cb; if (IS_ERR(segs)) return PTR_ERR(segs); if (segs == NULL) @@ -359,7 +357,6 @@ static int queue_gso_packets(struct datapath *dp, struct sk_buff *skb, /* Queue all of the segments. */ skb = segs; do { - *OVS_CB(skb) = ovs_cb; if (gso_type & SKB_GSO_UDP && skb != segs) key = &later_key; diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index cc3676eb6239..ff4a91fcab9f 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -167,6 +167,8 @@ static int xfrm_output_gso(struct net *net, struct sock *sk, struct sk_buff *skb { struct sk_buff *segs; + BUILD_BUG_ON(sizeof(*IPCB(skb)) > SKB_SGO_CB_OFFSET); + BUILD_BUG_ON(sizeof(*IP6CB(skb)) > SKB_SGO_CB_OFFSET); segs = skb_gso_segment(skb, 0); kfree_skb(skb); if (IS_ERR(segs)) From 1338c946e62d36572284d770d2454566fe11fdb9 Mon Sep 17 00:00:00 2001 From: Karl Heiss Date: Mon, 11 Jan 2016 08:28:43 -0500 Subject: [PATCH 045/325] bonding: Prevent IPv6 link local address on enslaved devices [ Upstream commit 03d84a5f83a67e692af00a3d3901e7820e3e84d5 ] Commit 1f718f0f4f97 ("bonding: populate neighbour's private on enslave") undoes the fix provided by commit c2edacf80e15 ("bonding / ipv6: no addrconf for slaves separately from master") by effectively setting the slave flag after the slave has been opened. If the slave comes up quickly enough, it will go through the IPv6 addrconf before the slave flag has been set and will get a link local IPv6 address. In order to ensure that addrconf knows to ignore the slave devices on state change, set IFF_SLAVE before dev_open() during bonding enslavement. Fixes: 1f718f0f4f97 ("bonding: populate neighbour's private on enslave") Signed-off-by: Karl Heiss Signed-off-by: Jay Vosburgh Reviewed-by: Jarod Wilson Signed-off-by: Andy Gospodarek Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/bonding/bond_main.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 9e0f8a7ef8b1..f1692e418fe4 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1207,7 +1207,6 @@ static int bond_master_upper_dev_link(struct net_device *bond_dev, err = netdev_master_upper_dev_link_private(slave_dev, bond_dev, slave); if (err) return err; - slave_dev->flags |= IFF_SLAVE; rtmsg_ifinfo(RTM_NEWLINK, slave_dev, IFF_SLAVE, GFP_KERNEL); return 0; } @@ -1465,6 +1464,9 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) } } + /* set slave flag before open to prevent IPv6 addrconf */ + slave_dev->flags |= IFF_SLAVE; + /* open the slave since the application closed it */ res = dev_open(slave_dev); if (res) { @@ -1725,6 +1727,7 @@ err_close: dev_close(slave_dev); err_restore_mac: + slave_dev->flags &= ~IFF_SLAVE; if (!bond->params.fail_over_mac || BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) { /* XXX TODO - fom follow mode needs to change master's From ca0f94da27314276153d38ea02f514348515bf87 Mon Sep 17 00:00:00 2001 From: Lars Persson Date: Tue, 12 Jan 2016 15:28:13 +0100 Subject: [PATCH 046/325] dwc_eth_qos: Fix dma address for multi-fragment skbs [ Upstream commit d461873272169a3fc3a8d155d7b1c92e9d97b419 ] The offset inside the fragment was not used for the dma address and silent data corruption resulted because TSO makes the checksum match. Fixes: 077742dac2c7 ("dwc_eth_qos: Add support for Synopsys DWC Ethernet QoS") Signed-off-by: Lars Persson Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/synopsys/dwc_eth_qos.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/synopsys/dwc_eth_qos.c b/drivers/net/ethernet/synopsys/dwc_eth_qos.c index 9066d7a8483c..f96c6b3606f2 100644 --- a/drivers/net/ethernet/synopsys/dwc_eth_qos.c +++ b/drivers/net/ethernet/synopsys/dwc_eth_qos.c @@ -2107,7 +2107,7 @@ static int dwceqos_tx_frags(struct sk_buff *skb, struct net_local *lp, dd = &lp->tx_descs[lp->tx_next]; /* Set DMA Descriptor fields */ - dd->des0 = dma_handle; + dd->des0 = dma_handle + consumed_size; dd->des1 = 0; dd->des2 = dma_size; From f7c1aee0b421663447aef58f58f103502bdc47e5 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 12 Jan 2016 08:58:00 -0800 Subject: [PATCH 047/325] phonet: properly unshare skbs in phonet_rcv() [ Upstream commit 7aaed57c5c2890634cfadf725173c7c68ea4cb4f ] Ivaylo Dimitrov reported a regression caused by commit 7866a621043f ("dev: add per net_device packet type chains"). skb->dev becomes NULL and we crash in __netif_receive_skb_core(). Before above commit, different kind of bugs or corruptions could happen without major crash. But the root cause is that phonet_rcv() can queue skb without checking if skb is shared or not. Many thanks to Ivaylo Dimitrov for his help, diagnosis and tests. Reported-by: Ivaylo Dimitrov Tested-by: Ivaylo Dimitrov Signed-off-by: Eric Dumazet Cc: Remi Denis-Courmont Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/phonet/af_phonet.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/phonet/af_phonet.c b/net/phonet/af_phonet.c index 10d42f3220ab..f925753668a7 100644 --- a/net/phonet/af_phonet.c +++ b/net/phonet/af_phonet.c @@ -377,6 +377,10 @@ static int phonet_rcv(struct sk_buff *skb, struct net_device *dev, struct sockaddr_pn sa; u16 len; + skb = skb_share_check(skb, GFP_ATOMIC); + if (!skb) + return NET_RX_DROP; + /* check we have at least a full Phonet header */ if (!pskb_pull(skb, sizeof(struct phonethdr))) goto out; From 35987ff2eaa05d70154c5bd28ebb2b70a7d8368b Mon Sep 17 00:00:00 2001 From: Rabin Vincent Date: Tue, 12 Jan 2016 20:17:08 +0100 Subject: [PATCH 048/325] net: bpf: reject invalid shifts [ Upstream commit 229394e8e62a4191d592842cf67e80c62a492937 ] On ARM64, a BUG() is triggered in the eBPF JIT if a filter with a constant shift that can't be encoded in the immediate field of the UBFM/SBFM instructions is passed to the JIT. Since these shifts amounts, which are negative or >= regsize, are invalid, reject them in the eBPF verifier and the classic BPF filter checker, for all architectures. Signed-off-by: Rabin Vincent Acked-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- kernel/bpf/verifier.c | 10 ++++++++++ net/core/filter.c | 5 +++++ 2 files changed, 15 insertions(+) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index a7945d10b378..d1d3e8f57de9 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1121,6 +1121,16 @@ static int check_alu_op(struct verifier_env *env, struct bpf_insn *insn) return -EINVAL; } + if ((opcode == BPF_LSH || opcode == BPF_RSH || + opcode == BPF_ARSH) && BPF_SRC(insn->code) == BPF_K) { + int size = BPF_CLASS(insn->code) == BPF_ALU64 ? 64 : 32; + + if (insn->imm < 0 || insn->imm >= size) { + verbose("invalid shift %d\n", insn->imm); + return -EINVAL; + } + } + /* pattern match 'bpf_add Rx, imm' instruction */ if (opcode == BPF_ADD && BPF_CLASS(insn->code) == BPF_ALU64 && regs[insn->dst_reg].type == FRAME_PTR && diff --git a/net/core/filter.c b/net/core/filter.c index 672eefbfbe99..37157c4c1a78 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -777,6 +777,11 @@ static int bpf_check_classic(const struct sock_filter *filter, if (ftest->k == 0) return -EINVAL; break; + case BPF_ALU | BPF_LSH | BPF_K: + case BPF_ALU | BPF_RSH | BPF_K: + if (ftest->k >= 32) + return -EINVAL; + break; case BPF_LD | BPF_MEM: case BPF_LDX | BPF_MEM: case BPF_ST: From a744010bbd580833f1dfa1f274eca00175c78782 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 15 Jan 2016 04:56:56 -0800 Subject: [PATCH 049/325] ipv6: update skb->csum when CE mark is propagated [ Upstream commit 34ae6a1aa0540f0f781dd265366036355fdc8930 ] When a tunnel decapsulates the outer header, it has to comply with RFC 6080 and eventually propagate CE mark into inner header. It turns out IP6_ECN_set_ce() does not correctly update skb->csum for CHECKSUM_COMPLETE packets, triggering infamous "hw csum failure" messages and stack traces. Signed-off-by: Eric Dumazet Acked-by: Herbert Xu Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- include/net/inet_ecn.h | 19 ++++++++++++++++--- net/ipv6/xfrm6_mode_tunnel.c | 2 +- 2 files changed, 17 insertions(+), 4 deletions(-) diff --git a/include/net/inet_ecn.h b/include/net/inet_ecn.h index 84b20835b736..0dc0a51da38f 100644 --- a/include/net/inet_ecn.h +++ b/include/net/inet_ecn.h @@ -111,11 +111,24 @@ static inline void ipv4_copy_dscp(unsigned int dscp, struct iphdr *inner) struct ipv6hdr; -static inline int IP6_ECN_set_ce(struct ipv6hdr *iph) +/* Note: + * IP_ECN_set_ce() has to tweak IPV4 checksum when setting CE, + * meaning both changes have no effect on skb->csum if/when CHECKSUM_COMPLETE + * In IPv6 case, no checksum compensates the change in IPv6 header, + * so we have to update skb->csum. + */ +static inline int IP6_ECN_set_ce(struct sk_buff *skb, struct ipv6hdr *iph) { + __be32 from, to; + if (INET_ECN_is_not_ect(ipv6_get_dsfield(iph))) return 0; - *(__be32*)iph |= htonl(INET_ECN_CE << 20); + + from = *(__be32 *)iph; + to = from | htonl(INET_ECN_CE << 20); + *(__be32 *)iph = to; + if (skb->ip_summed == CHECKSUM_COMPLETE) + skb->csum = csum_add(csum_sub(skb->csum, from), to); return 1; } @@ -142,7 +155,7 @@ static inline int INET_ECN_set_ce(struct sk_buff *skb) case cpu_to_be16(ETH_P_IPV6): if (skb_network_header(skb) + sizeof(struct ipv6hdr) <= skb_tail_pointer(skb)) - return IP6_ECN_set_ce(ipv6_hdr(skb)); + return IP6_ECN_set_ce(skb, ipv6_hdr(skb)); break; } diff --git a/net/ipv6/xfrm6_mode_tunnel.c b/net/ipv6/xfrm6_mode_tunnel.c index f7fbdbabe50e..372855eeaf42 100644 --- a/net/ipv6/xfrm6_mode_tunnel.c +++ b/net/ipv6/xfrm6_mode_tunnel.c @@ -23,7 +23,7 @@ static inline void ipip6_ecn_decapsulate(struct sk_buff *skb) struct ipv6hdr *inner_iph = ipipv6_hdr(skb); if (INET_ECN_is_ce(XFRM_MODE_SKB_CB(skb)->tos)) - IP6_ECN_set_ce(inner_iph); + IP6_ECN_set_ce(skb, inner_iph); } /* Add encapsulation header. From db4dca1ade8fedc227ddd32e49d60f99cbcfceee Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Fri, 15 Jan 2016 19:03:54 +0100 Subject: [PATCH 050/325] bridge: fix lockdep addr_list_lock false positive splat [ Upstream commit c6894dec8ea9ae05747124dce98b3b5c2e69b168 ] After promisc mode management was introduced a bridge device could do dev_set_promiscuity from its ndo_change_rx_flags() callback which in turn can be called after the bridge's addr_list_lock has been taken (e.g. by dev_uc_add). This causes a false positive lockdep splat because the port interfaces' addr_list_lock is taken when br_manage_promisc() runs after the bridge's addr list lock was already taken. To remove the false positive introduce a custom bridge addr_list_lock class and set it on bridge init. A simple way to reproduce this is with the following: $ brctl addbr br0 $ ip l add l br0 br0.100 type vlan id 100 $ ip l set br0 up $ ip l set br0.100 up $ echo 1 > /sys/class/net/br0/bridge/vlan_filtering $ brctl addif br0 eth0 Splat: [ 43.684325] ============================================= [ 43.684485] [ INFO: possible recursive locking detected ] [ 43.684636] 4.4.0-rc8+ #54 Not tainted [ 43.684755] --------------------------------------------- [ 43.684906] brctl/1187 is trying to acquire lock: [ 43.685047] (_xmit_ETHER){+.....}, at: [] dev_set_rx_mode+0x1e/0x40 [ 43.685460] but task is already holding lock: [ 43.685618] (_xmit_ETHER){+.....}, at: [] dev_uc_add+0x27/0x80 [ 43.686015] other info that might help us debug this: [ 43.686316] Possible unsafe locking scenario: [ 43.686743] CPU0 [ 43.686967] ---- [ 43.687197] lock(_xmit_ETHER); [ 43.687544] lock(_xmit_ETHER); [ 43.687886] *** DEADLOCK *** [ 43.688438] May be due to missing lock nesting notation [ 43.688882] 2 locks held by brctl/1187: [ 43.689134] #0: (rtnl_mutex){+.+.+.}, at: [] rtnl_lock+0x17/0x20 [ 43.689852] #1: (_xmit_ETHER){+.....}, at: [] dev_uc_add+0x27/0x80 [ 43.690575] stack backtrace: [ 43.690970] CPU: 0 PID: 1187 Comm: brctl Not tainted 4.4.0-rc8+ #54 [ 43.691270] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.8.1-20150318_183358- 04/01/2014 [ 43.691770] ffffffff826a25c0 ffff8800369fb8e0 ffffffff81360ceb ffffffff826a25c0 [ 43.692425] ffff8800369fb9b8 ffffffff810d0466 ffff8800369fb968 ffffffff81537139 [ 43.693071] ffff88003a08c880 0000000000000000 00000000ffffffff 0000000002080020 [ 43.693709] Call Trace: [ 43.693931] [] dump_stack+0x4b/0x70 [ 43.694199] [] __lock_acquire+0x1e46/0x1e90 [ 43.694483] [] ? netlink_broadcast_filtered+0x139/0x3e0 [ 43.694789] [] ? nlmsg_notify+0x5a/0xc0 [ 43.695064] [] lock_acquire+0xe5/0x1f0 [ 43.695340] [] ? dev_set_rx_mode+0x1e/0x40 [ 43.695623] [] _raw_spin_lock_bh+0x45/0x80 [ 43.695901] [] ? dev_set_rx_mode+0x1e/0x40 [ 43.696180] [] dev_set_rx_mode+0x1e/0x40 [ 43.696460] [] dev_set_promiscuity+0x3c/0x50 [ 43.696750] [] br_port_set_promisc+0x25/0x50 [bridge] [ 43.697052] [] br_manage_promisc+0x8a/0xe0 [bridge] [ 43.697348] [] br_dev_change_rx_flags+0x1e/0x20 [bridge] [ 43.697655] [] __dev_set_promiscuity+0x132/0x1f0 [ 43.697943] [] __dev_set_rx_mode+0x82/0x90 [ 43.698223] [] dev_uc_add+0x5e/0x80 [ 43.698498] [] vlan_device_event+0x542/0x650 [8021q] [ 43.698798] [] notifier_call_chain+0x5d/0x80 [ 43.699083] [] raw_notifier_call_chain+0x16/0x20 [ 43.699374] [] call_netdevice_notifiers_info+0x6e/0x80 [ 43.699678] [] call_netdevice_notifiers+0x16/0x20 [ 43.699973] [] br_add_if+0x47e/0x4c0 [bridge] [ 43.700259] [] add_del_if+0x6e/0x80 [bridge] [ 43.700548] [] br_dev_ioctl+0xaf/0xc0 [bridge] [ 43.700836] [] dev_ifsioc+0x30c/0x3c0 [ 43.701106] [] dev_ioctl+0xf9/0x6f0 [ 43.701379] [] ? mntput_no_expire+0x5/0x450 [ 43.701665] [] ? mntput_no_expire+0xae/0x450 [ 43.701947] [] sock_do_ioctl+0x42/0x50 [ 43.702219] [] sock_ioctl+0x1e5/0x290 [ 43.702500] [] do_vfs_ioctl+0x2cb/0x5c0 [ 43.702771] [] SyS_ioctl+0x79/0x90 [ 43.703033] [] entry_SYSCALL_64_fastpath+0x16/0x7a CC: Vlad Yasevich CC: Stephen Hemminger CC: Bridge list CC: Andy Gospodarek CC: Roopa Prabhu Fixes: 2796d0c648c9 ("bridge: Automatically manage port promiscuous mode.") Reported-by: Andy Gospodarek Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/bridge/br_device.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index 5e88d3e17546..2c8095a5d824 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -28,6 +28,8 @@ const struct nf_br_ops __rcu *nf_br_ops __read_mostly; EXPORT_SYMBOL_GPL(nf_br_ops); +static struct lock_class_key bridge_netdev_addr_lock_key; + /* net device transmit always called with BH disabled */ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) { @@ -87,6 +89,11 @@ out: return NETDEV_TX_OK; } +static void br_set_lockdep_class(struct net_device *dev) +{ + lockdep_set_class(&dev->addr_list_lock, &bridge_netdev_addr_lock_key); +} + static int br_dev_init(struct net_device *dev) { struct net_bridge *br = netdev_priv(dev); @@ -99,6 +106,7 @@ static int br_dev_init(struct net_device *dev) err = br_vlan_init(br); if (err) free_percpu(br->stats); + br_set_lockdep_class(dev); return err; } From 9ef3ceb4e78d12e1f1a81f6ebb88986e6344c7c8 Mon Sep 17 00:00:00 2001 From: Doron Tsur Date: Sun, 17 Jan 2016 11:25:47 +0200 Subject: [PATCH 051/325] net/mlx5_core: Fix trimming down IRQ number [ Upstream commit 0b6e26ce89391327d955a756a7823272238eb867 ] With several ConnectX-4 cards installed on a server, one may receive irqn > 255 from the kernel API, which we mistakenly trim to 8bit. This causes EQ creation failure with the following stack trace: [] dump_stack+0x48/0x64 [] __setup_irq+0x3a1/0x4f0 [] request_threaded_irq+0x120/0x180 [] ? mlx5_eq_int+0x450/0x450 [mlx5_core] [] mlx5_create_map_eq+0x1e4/0x2b0 [mlx5_core] [] alloc_comp_eqs+0xb1/0x180 [mlx5_core] [] mlx5_dev_init+0x5e9/0x6e0 [mlx5_core] [] init_one+0x99/0x1c0 [mlx5_core] [] local_pci_probe+0x4c/0xa0 Fixing it by changing of the irqn type from u8 to unsigned int to support values > 255 Fixes: 61d0e73e0a5a ('net/mlx5_core: Use the the real irqn in eq->irqn') Reported-by: Jiri Pirko Signed-off-by: Doron Tsur Signed-off-by: Matan Barak Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/infiniband/hw/mlx5/cq.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 6 +++--- drivers/net/ethernet/mellanox/mlx5/core/main.c | 3 ++- include/linux/mlx5/cq.h | 2 +- include/linux/mlx5/driver.h | 5 +++-- 5 files changed, 10 insertions(+), 8 deletions(-) diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/cq.c index 3dfd287256d6..92ddae101ecc 100644 --- a/drivers/infiniband/hw/mlx5/cq.c +++ b/drivers/infiniband/hw/mlx5/cq.c @@ -756,7 +756,7 @@ struct ib_cq *mlx5_ib_create_cq(struct ib_device *ibdev, int uninitialized_var(index); int uninitialized_var(inlen); int cqe_size; - int irqn; + unsigned int irqn; int eqn; int err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 1e52db32c73d..1203d892e842 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -746,7 +746,7 @@ static int mlx5e_create_cq(struct mlx5e_channel *c, struct mlx5_core_dev *mdev = priv->mdev; struct mlx5_core_cq *mcq = &cq->mcq; int eqn_not_used; - int irqn; + unsigned int irqn; int err; u32 i; @@ -800,7 +800,7 @@ static int mlx5e_enable_cq(struct mlx5e_cq *cq, struct mlx5e_cq_param *param) void *in; void *cqc; int inlen; - int irqn_not_used; + unsigned int irqn_not_used; int eqn; int err; @@ -1504,7 +1504,7 @@ static int mlx5e_create_drop_cq(struct mlx5e_priv *priv, struct mlx5_core_dev *mdev = priv->mdev; struct mlx5_core_cq *mcq = &cq->mcq; int eqn_not_used; - int irqn; + unsigned int irqn; int err; err = mlx5_cqwq_create(mdev, ¶m->wq, param->cqc, &cq->wq, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 4ac8d4cc4973..6cf6d93d8831 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -568,7 +568,8 @@ static void mlx5_irq_clear_affinity_hints(struct mlx5_core_dev *mdev) mlx5_irq_clear_affinity_hint(mdev, i); } -int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn, int *irqn) +int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn, + unsigned int *irqn) { struct mlx5_eq_table *table = &dev->priv.eq_table; struct mlx5_eq *eq, *n; diff --git a/include/linux/mlx5/cq.h b/include/linux/mlx5/cq.h index abc4767695e4..b2c9fada8eac 100644 --- a/include/linux/mlx5/cq.h +++ b/include/linux/mlx5/cq.h @@ -45,7 +45,7 @@ struct mlx5_core_cq { atomic_t refcount; struct completion free; unsigned vector; - int irqn; + unsigned int irqn; void (*comp) (struct mlx5_core_cq *); void (*event) (struct mlx5_core_cq *, enum mlx5_event); struct mlx5_uar *uar; diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 5c857f2a20d7..af3efd9157f0 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -303,7 +303,7 @@ struct mlx5_eq { u32 cons_index; struct mlx5_buf buf; int size; - u8 irqn; + unsigned int irqn; u8 eqn; int nent; u64 mask; @@ -762,7 +762,8 @@ int mlx5_create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, u8 vecidx, int mlx5_destroy_unmap_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq); int mlx5_start_eqs(struct mlx5_core_dev *dev); int mlx5_stop_eqs(struct mlx5_core_dev *dev); -int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn, int *irqn); +int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn, + unsigned int *irqn); int mlx5_core_attach_mcg(struct mlx5_core_dev *dev, union ib_gid *mgid, u32 qpn); int mlx5_core_detach_mcg(struct mlx5_core_dev *dev, union ib_gid *mgid, u32 qpn); From 442f7b481616c81a3f9dd1832a971dac044fd92b Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Mon, 18 Jan 2016 17:30:22 +0200 Subject: [PATCH 052/325] team: Replace rcu_read_lock with a mutex in team_vlan_rx_kill_vid [ Upstream commit 60a6531bfe49555581ccd65f66a350cc5693fcde ] We can't be within an RCU read-side critical section when deleting VLANs, as underlying drivers might sleep during the hardware operation. Therefore, replace the RCU critical section with a mutex. This is consistent with team_vlan_rx_add_vid. Fixes: 3d249d4ca7d0 ("net: introduce ethernet teaming device") Acked-by: Jiri Pirko Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/team/team.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index 651d35ea22c5..59fefca74263 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -1845,10 +1845,10 @@ static int team_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, u16 vid) struct team *team = netdev_priv(dev); struct team_port *port; - rcu_read_lock(); - list_for_each_entry_rcu(port, &team->port_list, list) + mutex_lock(&team->lock); + list_for_each_entry(port, &team->port_list, list) vlan_vid_del(port->dev, proto, vid); - rcu_read_unlock(); + mutex_unlock(&team->lock); return 0; } From 4473483399586fe8ffb266b0519f525d55b28010 Mon Sep 17 00:00:00 2001 From: Sven Eckelmann Date: Thu, 14 Jan 2016 15:28:19 +0100 Subject: [PATCH 053/325] batman-adv: Avoid recursive call_rcu for batadv_bla_claim [ Upstream commit 63b399272294e7a939cde41792dca38c549f0484 ] The batadv_claim_free_ref function uses call_rcu to delay the free of the batadv_bla_claim object until no (already started) rcu_read_lock is enabled anymore. This makes sure that no context is still trying to access the object which should be removed. But batadv_bla_claim also contains a reference to backbone_gw which must be removed. The reference drop of backbone_gw was done in the call_rcu function batadv_claim_free_rcu but should actually be done in the batadv_claim_release function to avoid nested call_rcus. This is important because rcu_barrier (e.g. batadv_softif_free or batadv_exit) will not detect the inner call_rcu as relevant for its execution. Otherwise this barrier will most likely be inserted in the queue before the callback of the first call_rcu was executed. The caller of rcu_barrier will therefore continue to run before the inner call_rcu callback finished. Fixes: 23721387c409 ("batman-adv: add basic bridge loop avoidance code") Signed-off-by: Sven Eckelmann Acked-by: Simon Wunderlich Signed-off-by: Marek Lindner Signed-off-by: Antonio Quartulli Signed-off-by: Greg Kroah-Hartman --- net/batman-adv/bridge_loop_avoidance.c | 10 +++------- 1 file changed, 3 insertions(+), 7 deletions(-) diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index 191a70290dca..f5d2fe5e31cc 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -127,21 +127,17 @@ batadv_backbone_gw_free_ref(struct batadv_bla_backbone_gw *backbone_gw) } /* finally deinitialize the claim */ -static void batadv_claim_free_rcu(struct rcu_head *rcu) +static void batadv_claim_release(struct batadv_bla_claim *claim) { - struct batadv_bla_claim *claim; - - claim = container_of(rcu, struct batadv_bla_claim, rcu); - batadv_backbone_gw_free_ref(claim->backbone_gw); - kfree(claim); + kfree_rcu(claim, rcu); } /* free a claim, call claim_free_rcu if its the last reference */ static void batadv_claim_free_ref(struct batadv_bla_claim *claim) { if (atomic_dec_and_test(&claim->refcount)) - call_rcu(&claim->rcu, batadv_claim_free_rcu); + batadv_claim_release(claim); } /** From d3a4a363d8d3a6c8c9e7419e168b409ff3f31dd2 Mon Sep 17 00:00:00 2001 From: Sven Eckelmann Date: Tue, 5 Jan 2016 12:06:19 +0100 Subject: [PATCH 054/325] batman-adv: Avoid recursive call_rcu for batadv_nc_node [ Upstream commit 44e8e7e91d6c7c7ab19688750f7257292640d1a0 ] The batadv_nc_node_free_ref function uses call_rcu to delay the free of the batadv_nc_node object until no (already started) rcu_read_lock is enabled anymore. This makes sure that no context is still trying to access the object which should be removed. But batadv_nc_node also contains a reference to orig_node which must be removed. The reference drop of orig_node was done in the call_rcu function batadv_nc_node_free_rcu but should actually be done in the batadv_nc_node_release function to avoid nested call_rcus. This is important because rcu_barrier (e.g. batadv_softif_free or batadv_exit) will not detect the inner call_rcu as relevant for its execution. Otherwise this barrier will most likely be inserted in the queue before the callback of the first call_rcu was executed. The caller of rcu_barrier will therefore continue to run before the inner call_rcu callback finished. Fixes: d56b1705e28c ("batman-adv: network coding - detect coding nodes and remove these after timeout") Signed-off-by: Sven Eckelmann Signed-off-by: Marek Lindner Signed-off-by: Antonio Quartulli Signed-off-by: Greg Kroah-Hartman --- net/batman-adv/network-coding.c | 19 ++++++++----------- 1 file changed, 8 insertions(+), 11 deletions(-) diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c index f5276be2c77c..d0956f726547 100644 --- a/net/batman-adv/network-coding.c +++ b/net/batman-adv/network-coding.c @@ -203,28 +203,25 @@ void batadv_nc_init_orig(struct batadv_orig_node *orig_node) } /** - * batadv_nc_node_free_rcu - rcu callback to free an nc node and remove - * its refcount on the orig_node - * @rcu: rcu pointer of the nc node + * batadv_nc_node_release - release nc_node from lists and queue for free after + * rcu grace period + * @nc_node: the nc node to free */ -static void batadv_nc_node_free_rcu(struct rcu_head *rcu) +static void batadv_nc_node_release(struct batadv_nc_node *nc_node) { - struct batadv_nc_node *nc_node; - - nc_node = container_of(rcu, struct batadv_nc_node, rcu); batadv_orig_node_free_ref(nc_node->orig_node); - kfree(nc_node); + kfree_rcu(nc_node, rcu); } /** - * batadv_nc_node_free_ref - decrements the nc node refcounter and possibly - * frees it + * batadv_nc_node_free_ref - decrement the nc node refcounter and possibly + * release it * @nc_node: the nc node to free */ static void batadv_nc_node_free_ref(struct batadv_nc_node *nc_node) { if (atomic_dec_and_test(&nc_node->refcount)) - call_rcu(&nc_node->rcu, batadv_nc_node_free_rcu); + batadv_nc_node_release(nc_node); } /** From 53ab5ef03bf07b96b6c595efc941c8d06e76858c Mon Sep 17 00:00:00 2001 From: Sven Eckelmann Date: Tue, 5 Jan 2016 12:06:21 +0100 Subject: [PATCH 055/325] batman-adv: Drop immediate batadv_orig_ifinfo free function [ Upstream commit deed96605f5695cb945e0b3d79429581857a2b9d ] It is not allowed to free the memory of an object which is part of a list which is protected by rcu-read-side-critical sections without making sure that no other context is accessing the object anymore. This usually happens by removing the references to this object and then waiting until the rcu grace period is over and no one (allowedly) accesses it anymore. But the _now functions ignore this completely. They free the object directly even when a different context still tries to access it. This has to be avoided and thus these functions must be removed and all functions have to use batadv_orig_ifinfo_free_ref. Fixes: 7351a4822d42 ("batman-adv: split out router from orig_node") Signed-off-by: Sven Eckelmann Signed-off-by: Marek Lindner Signed-off-by: Antonio Quartulli Signed-off-by: Greg Kroah-Hartman --- net/batman-adv/originator.c | 77 +++++++++++++++++++------------------ 1 file changed, 40 insertions(+), 37 deletions(-) diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c index 7486df9ed48d..a0728948fada 100644 --- a/net/batman-adv/originator.c +++ b/net/batman-adv/originator.c @@ -553,19 +553,7 @@ static void batadv_orig_ifinfo_free_rcu(struct rcu_head *rcu) } /** - * batadv_orig_ifinfo_free_ref - decrement the refcounter and possibly free - * the orig_ifinfo (without rcu callback) - * @orig_ifinfo: the orig_ifinfo object to release - */ -static void -batadv_orig_ifinfo_free_ref_now(struct batadv_orig_ifinfo *orig_ifinfo) -{ - if (atomic_dec_and_test(&orig_ifinfo->refcount)) - batadv_orig_ifinfo_free_rcu(&orig_ifinfo->rcu); -} - -/** - * batadv_orig_ifinfo_free_ref - decrement the refcounter and possibly free + * batadv_orig_ifinfo_free_ref - decrement the refcounter and possibly release * the orig_ifinfo * @orig_ifinfo: the orig_ifinfo object to release */ @@ -575,36 +563,18 @@ void batadv_orig_ifinfo_free_ref(struct batadv_orig_ifinfo *orig_ifinfo) call_rcu(&orig_ifinfo->rcu, batadv_orig_ifinfo_free_rcu); } +/** + * batadv_orig_node_free_rcu - free the orig_node + * @rcu: rcu pointer of the orig_node + */ static void batadv_orig_node_free_rcu(struct rcu_head *rcu) { - struct hlist_node *node_tmp; - struct batadv_neigh_node *neigh_node; struct batadv_orig_node *orig_node; - struct batadv_orig_ifinfo *orig_ifinfo; orig_node = container_of(rcu, struct batadv_orig_node, rcu); - spin_lock_bh(&orig_node->neigh_list_lock); - - /* for all neighbors towards this originator ... */ - hlist_for_each_entry_safe(neigh_node, node_tmp, - &orig_node->neigh_list, list) { - hlist_del_rcu(&neigh_node->list); - batadv_neigh_node_free_ref_now(neigh_node); - } - - hlist_for_each_entry_safe(orig_ifinfo, node_tmp, - &orig_node->ifinfo_list, list) { - hlist_del_rcu(&orig_ifinfo->list); - batadv_orig_ifinfo_free_ref_now(orig_ifinfo); - } - spin_unlock_bh(&orig_node->neigh_list_lock); - batadv_mcast_purge_orig(orig_node); - /* Free nc_nodes */ - batadv_nc_purge_orig(orig_node->bat_priv, orig_node, NULL); - batadv_frag_purge_orig(orig_node, NULL); if (orig_node->bat_priv->bat_algo_ops->bat_orig_free) @@ -614,15 +584,48 @@ static void batadv_orig_node_free_rcu(struct rcu_head *rcu) kfree(orig_node); } +/** + * batadv_orig_node_release - release orig_node from lists and queue for + * free after rcu grace period + * @orig_node: the orig node to free + */ +static void batadv_orig_node_release(struct batadv_orig_node *orig_node) +{ + struct hlist_node *node_tmp; + struct batadv_neigh_node *neigh_node; + struct batadv_orig_ifinfo *orig_ifinfo; + + spin_lock_bh(&orig_node->neigh_list_lock); + + /* for all neighbors towards this originator ... */ + hlist_for_each_entry_safe(neigh_node, node_tmp, + &orig_node->neigh_list, list) { + hlist_del_rcu(&neigh_node->list); + batadv_neigh_node_free_ref(neigh_node); + } + + hlist_for_each_entry_safe(orig_ifinfo, node_tmp, + &orig_node->ifinfo_list, list) { + hlist_del_rcu(&orig_ifinfo->list); + batadv_orig_ifinfo_free_ref(orig_ifinfo); + } + spin_unlock_bh(&orig_node->neigh_list_lock); + + /* Free nc_nodes */ + batadv_nc_purge_orig(orig_node->bat_priv, orig_node, NULL); + + call_rcu(&orig_node->rcu, batadv_orig_node_free_rcu); +} + /** * batadv_orig_node_free_ref - decrement the orig node refcounter and possibly - * schedule an rcu callback for freeing it + * release it * @orig_node: the orig node to free */ void batadv_orig_node_free_ref(struct batadv_orig_node *orig_node) { if (atomic_dec_and_test(&orig_node->refcount)) - call_rcu(&orig_node->rcu, batadv_orig_node_free_rcu); + batadv_orig_node_release(orig_node); } /** From 31459b9b4502c50140e2e16373bb59121d5ac293 Mon Sep 17 00:00:00 2001 From: Sven Eckelmann Date: Tue, 5 Jan 2016 12:06:22 +0100 Subject: [PATCH 056/325] batman-adv: Drop immediate batadv_neigh_node free function [ Upstream commit 2baa753c276f27f8e844637561ad597867aa6fb6 ] It is not allowed to free the memory of an object which is part of a list which is protected by rcu-read-side-critical sections without making sure that no other context is accessing the object anymore. This usually happens by removing the references to this object and then waiting until the rcu grace period is over and no one (allowedly) accesses it anymore. But the _now functions ignore this completely. They free the object directly even when a different context still tries to access it. This has to be avoided and thus these functions must be removed and all functions have to use batadv_neigh_node_free_ref. Fixes: 89652331c00f ("batman-adv: split tq information in neigh_node struct") Signed-off-by: Sven Eckelmann Signed-off-by: Marek Lindner Signed-off-by: Antonio Quartulli Signed-off-by: Greg Kroah-Hartman --- net/batman-adv/originator.c | 33 ++++++++++----------------------- 1 file changed, 10 insertions(+), 23 deletions(-) diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c index a0728948fada..a8e68eba8349 100644 --- a/net/batman-adv/originator.c +++ b/net/batman-adv/originator.c @@ -228,21 +228,9 @@ static void batadv_neigh_node_free_rcu(struct rcu_head *rcu) kfree(neigh_node); } -/** - * batadv_neigh_node_free_ref_now - decrement the neighbors refcounter - * and possibly free it (without rcu callback) - * @neigh_node: neigh neighbor to free - */ -static void -batadv_neigh_node_free_ref_now(struct batadv_neigh_node *neigh_node) -{ - if (atomic_dec_and_test(&neigh_node->refcount)) - batadv_neigh_node_free_rcu(&neigh_node->rcu); -} - /** * batadv_neigh_node_free_ref - decrement the neighbors refcounter - * and possibly free it + * and possibly release it * @neigh_node: neigh neighbor to free */ void batadv_neigh_node_free_ref(struct batadv_neigh_node *neigh_node) @@ -532,24 +520,23 @@ out: } /** - * batadv_orig_ifinfo_free_rcu - free the orig_ifinfo object - * @rcu: rcu pointer of the orig_ifinfo object + * batadv_orig_ifinfo_release - release orig_ifinfo from lists and queue for + * free after rcu grace period + * @orig_ifinfo: the orig_ifinfo object to release */ -static void batadv_orig_ifinfo_free_rcu(struct rcu_head *rcu) +static void batadv_orig_ifinfo_release(struct batadv_orig_ifinfo *orig_ifinfo) { - struct batadv_orig_ifinfo *orig_ifinfo; struct batadv_neigh_node *router; - orig_ifinfo = container_of(rcu, struct batadv_orig_ifinfo, rcu); - if (orig_ifinfo->if_outgoing != BATADV_IF_DEFAULT) - batadv_hardif_free_ref_now(orig_ifinfo->if_outgoing); + batadv_hardif_free_ref(orig_ifinfo->if_outgoing); /* this is the last reference to this object */ router = rcu_dereference_protected(orig_ifinfo->router, true); if (router) - batadv_neigh_node_free_ref_now(router); - kfree(orig_ifinfo); + batadv_neigh_node_free_ref(router); + + kfree_rcu(orig_ifinfo, rcu); } /** @@ -560,7 +547,7 @@ static void batadv_orig_ifinfo_free_rcu(struct rcu_head *rcu) void batadv_orig_ifinfo_free_ref(struct batadv_orig_ifinfo *orig_ifinfo) { if (atomic_dec_and_test(&orig_ifinfo->refcount)) - call_rcu(&orig_ifinfo->rcu, batadv_orig_ifinfo_free_rcu); + batadv_orig_ifinfo_release(orig_ifinfo); } /** From 568f95d027967fcfe287d9dddd3669eebbed96b3 Mon Sep 17 00:00:00 2001 From: Sven Eckelmann Date: Tue, 5 Jan 2016 12:06:24 +0100 Subject: [PATCH 057/325] batman-adv: Drop immediate neigh_ifinfo free function [ Upstream commit ae3e1e36e3cb6c686a7a2725af20ca86aa46d62a ] It is not allowed to free the memory of an object which is part of a list which is protected by rcu-read-side-critical sections without making sure that no other context is accessing the object anymore. This usually happens by removing the references to this object and then waiting until the rcu grace period is over and no one (allowedly) accesses it anymore. But the _now functions ignore this completely. They free the object directly even when a different context still tries to access it. This has to be avoided and thus these functions must be removed and all functions have to use batadv_neigh_ifinfo_free_ref. Fixes: 89652331c00f ("batman-adv: split tq information in neigh_node struct") Signed-off-by: Sven Eckelmann Signed-off-by: Marek Lindner Signed-off-by: Antonio Quartulli Signed-off-by: Greg Kroah-Hartman --- net/batman-adv/originator.c | 34 ++++++++++------------------------ 1 file changed, 10 insertions(+), 24 deletions(-) diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c index a8e68eba8349..0c27f07b5396 100644 --- a/net/batman-adv/originator.c +++ b/net/batman-adv/originator.c @@ -163,42 +163,28 @@ err: } /** - * batadv_neigh_ifinfo_free_rcu - free the neigh_ifinfo object - * @rcu: rcu pointer of the neigh_ifinfo object - */ -static void batadv_neigh_ifinfo_free_rcu(struct rcu_head *rcu) -{ - struct batadv_neigh_ifinfo *neigh_ifinfo; - - neigh_ifinfo = container_of(rcu, struct batadv_neigh_ifinfo, rcu); - - if (neigh_ifinfo->if_outgoing != BATADV_IF_DEFAULT) - batadv_hardif_free_ref_now(neigh_ifinfo->if_outgoing); - - kfree(neigh_ifinfo); -} - -/** - * batadv_neigh_ifinfo_free_now - decrement the refcounter and possibly free - * the neigh_ifinfo (without rcu callback) + * batadv_neigh_ifinfo_release - release neigh_ifinfo from lists and queue for + * free after rcu grace period * @neigh_ifinfo: the neigh_ifinfo object to release */ static void -batadv_neigh_ifinfo_free_ref_now(struct batadv_neigh_ifinfo *neigh_ifinfo) +batadv_neigh_ifinfo_release(struct batadv_neigh_ifinfo *neigh_ifinfo) { - if (atomic_dec_and_test(&neigh_ifinfo->refcount)) - batadv_neigh_ifinfo_free_rcu(&neigh_ifinfo->rcu); + if (neigh_ifinfo->if_outgoing != BATADV_IF_DEFAULT) + batadv_hardif_free_ref(neigh_ifinfo->if_outgoing); + + kfree_rcu(neigh_ifinfo, rcu); } /** - * batadv_neigh_ifinfo_free_ref - decrement the refcounter and possibly free + * batadv_neigh_ifinfo_free_ref - decrement the refcounter and possibly release * the neigh_ifinfo * @neigh_ifinfo: the neigh_ifinfo object to release */ void batadv_neigh_ifinfo_free_ref(struct batadv_neigh_ifinfo *neigh_ifinfo) { if (atomic_dec_and_test(&neigh_ifinfo->refcount)) - call_rcu(&neigh_ifinfo->rcu, batadv_neigh_ifinfo_free_rcu); + batadv_neigh_ifinfo_release(neigh_ifinfo); } /** @@ -217,7 +203,7 @@ static void batadv_neigh_node_free_rcu(struct rcu_head *rcu) hlist_for_each_entry_safe(neigh_ifinfo, node_tmp, &neigh_node->ifinfo_list, list) { - batadv_neigh_ifinfo_free_ref_now(neigh_ifinfo); + batadv_neigh_ifinfo_free_ref(neigh_ifinfo); } if (bao->bat_neigh_free) From 11ed67672827aa98eaa0fe78510bb33eb3251407 Mon Sep 17 00:00:00 2001 From: Sven Eckelmann Date: Tue, 5 Jan 2016 12:06:25 +0100 Subject: [PATCH 058/325] batman-adv: Drop immediate batadv_hard_iface free function [ Upstream commit b4d922cfc9c08318eeb77d53b7633740e6b0efb0 ] It is not allowed to free the memory of an object which is part of a list which is protected by rcu-read-side-critical sections without making sure that no other context is accessing the object anymore. This usually happens by removing the references to this object and then waiting until the rcu grace period is over and no one (allowedly) accesses it anymore. But the _now functions ignore this completely. They free the object directly even when a different context still tries to access it. This has to be avoided and thus these functions must be removed and all functions have to use batadv_hardif_free_ref. Fixes: 89652331c00f ("batman-adv: split tq information in neigh_node struct") Signed-off-by: Sven Eckelmann Signed-off-by: Marek Lindner Signed-off-by: Antonio Quartulli Signed-off-by: Greg Kroah-Hartman --- net/batman-adv/hard-interface.h | 12 ------------ net/batman-adv/originator.c | 14 +++++++------- 2 files changed, 7 insertions(+), 19 deletions(-) diff --git a/net/batman-adv/hard-interface.h b/net/batman-adv/hard-interface.h index 5a31420513e1..7b12ea8ea29d 100644 --- a/net/batman-adv/hard-interface.h +++ b/net/batman-adv/hard-interface.h @@ -75,18 +75,6 @@ batadv_hardif_free_ref(struct batadv_hard_iface *hard_iface) call_rcu(&hard_iface->rcu, batadv_hardif_free_rcu); } -/** - * batadv_hardif_free_ref_now - decrement the hard interface refcounter and - * possibly free it (without rcu callback) - * @hard_iface: the hard interface to free - */ -static inline void -batadv_hardif_free_ref_now(struct batadv_hard_iface *hard_iface) -{ - if (atomic_dec_and_test(&hard_iface->refcount)) - batadv_hardif_free_rcu(&hard_iface->rcu); -} - static inline struct batadv_hard_iface * batadv_primary_if_get_selected(struct batadv_priv *bat_priv) { diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c index 0c27f07b5396..d9d2ceed69f2 100644 --- a/net/batman-adv/originator.c +++ b/net/batman-adv/originator.c @@ -189,16 +189,16 @@ void batadv_neigh_ifinfo_free_ref(struct batadv_neigh_ifinfo *neigh_ifinfo) /** * batadv_neigh_node_free_rcu - free the neigh_node - * @rcu: rcu pointer of the neigh_node + * batadv_neigh_node_release - release neigh_node from lists and queue for + * free after rcu grace period + * @neigh_node: neigh neighbor to free */ -static void batadv_neigh_node_free_rcu(struct rcu_head *rcu) +static void batadv_neigh_node_release(struct batadv_neigh_node *neigh_node) { struct hlist_node *node_tmp; - struct batadv_neigh_node *neigh_node; struct batadv_neigh_ifinfo *neigh_ifinfo; struct batadv_algo_ops *bao; - neigh_node = container_of(rcu, struct batadv_neigh_node, rcu); bao = neigh_node->orig_node->bat_priv->bat_algo_ops; hlist_for_each_entry_safe(neigh_ifinfo, node_tmp, @@ -209,9 +209,9 @@ static void batadv_neigh_node_free_rcu(struct rcu_head *rcu) if (bao->bat_neigh_free) bao->bat_neigh_free(neigh_node); - batadv_hardif_free_ref_now(neigh_node->if_incoming); + batadv_hardif_free_ref(neigh_node->if_incoming); - kfree(neigh_node); + kfree_rcu(neigh_node, rcu); } /** @@ -222,7 +222,7 @@ static void batadv_neigh_node_free_rcu(struct rcu_head *rcu) void batadv_neigh_node_free_ref(struct batadv_neigh_node *neigh_node) { if (atomic_dec_and_test(&neigh_node->refcount)) - call_rcu(&neigh_node->rcu, batadv_neigh_node_free_rcu); + batadv_neigh_node_release(neigh_node); } /** From d29da8824b88622d6c9c6d55de309a297a34d0f4 Mon Sep 17 00:00:00 2001 From: Sven Eckelmann Date: Tue, 5 Jan 2016 12:06:20 +0100 Subject: [PATCH 059/325] batman-adv: Drop immediate orig_node free function [ Upstream commit 42eff6a617e23b691f8e4467f4687ed7245a92db ] It is not allowed to free the memory of an object which is part of a list which is protected by rcu-read-side-critical sections without making sure that no other context is accessing the object anymore. This usually happens by removing the references to this object and then waiting until the rcu grace period is over and no one (allowedly) accesses it anymore. But the _now functions ignore this completely. They free the object directly even when a different context still tries to access it. This has to be avoided and thus these functions must be removed and all functions have to use batadv_orig_node_free_ref. Fixes: 72822225bd41 ("batman-adv: Fix rcu_barrier() miss due to double call_rcu() in TT code") Signed-off-by: Sven Eckelmann Signed-off-by: Marek Lindner Signed-off-by: Antonio Quartulli Signed-off-by: Greg Kroah-Hartman --- net/batman-adv/originator.c | 11 ----------- net/batman-adv/originator.h | 1 - net/batman-adv/translation-table.c | 28 +++++++++++++--------------- 3 files changed, 13 insertions(+), 27 deletions(-) diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c index d9d2ceed69f2..17851d3aaf22 100644 --- a/net/batman-adv/originator.c +++ b/net/batman-adv/originator.c @@ -601,17 +601,6 @@ void batadv_orig_node_free_ref(struct batadv_orig_node *orig_node) batadv_orig_node_release(orig_node); } -/** - * batadv_orig_node_free_ref_now - decrement the orig node refcounter and - * possibly free it (without rcu callback) - * @orig_node: the orig node to free - */ -void batadv_orig_node_free_ref_now(struct batadv_orig_node *orig_node) -{ - if (atomic_dec_and_test(&orig_node->refcount)) - batadv_orig_node_free_rcu(&orig_node->rcu); -} - void batadv_originator_free(struct batadv_priv *bat_priv) { struct batadv_hashtable *hash = bat_priv->orig_hash; diff --git a/net/batman-adv/originator.h b/net/batman-adv/originator.h index fa18f9bf266b..a5c37882b409 100644 --- a/net/batman-adv/originator.h +++ b/net/batman-adv/originator.h @@ -38,7 +38,6 @@ int batadv_originator_init(struct batadv_priv *bat_priv); void batadv_originator_free(struct batadv_priv *bat_priv); void batadv_purge_orig_ref(struct batadv_priv *bat_priv); void batadv_orig_node_free_ref(struct batadv_orig_node *orig_node); -void batadv_orig_node_free_ref_now(struct batadv_orig_node *orig_node); struct batadv_orig_node *batadv_orig_node_new(struct batadv_priv *bat_priv, const u8 *addr); struct batadv_neigh_node * diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index 76f19ba62462..83b0ca27a45e 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -240,20 +240,6 @@ int batadv_tt_global_hash_count(struct batadv_priv *bat_priv, return count; } -static void batadv_tt_orig_list_entry_free_rcu(struct rcu_head *rcu) -{ - struct batadv_tt_orig_list_entry *orig_entry; - - orig_entry = container_of(rcu, struct batadv_tt_orig_list_entry, rcu); - - /* We are in an rcu callback here, therefore we cannot use - * batadv_orig_node_free_ref() and its call_rcu(): - * An rcu_barrier() wouldn't wait for that to finish - */ - batadv_orig_node_free_ref_now(orig_entry->orig_node); - kfree(orig_entry); -} - /** * batadv_tt_local_size_mod - change the size by v of the local table identified * by vid @@ -349,13 +335,25 @@ static void batadv_tt_global_size_dec(struct batadv_orig_node *orig_node, batadv_tt_global_size_mod(orig_node, vid, -1); } +/** + * batadv_tt_orig_list_entry_release - release tt orig entry from lists and + * queue for free after rcu grace period + * @orig_entry: tt orig entry to be free'd + */ +static void +batadv_tt_orig_list_entry_release(struct batadv_tt_orig_list_entry *orig_entry) +{ + batadv_orig_node_free_ref(orig_entry->orig_node); + kfree_rcu(orig_entry, rcu); +} + static void batadv_tt_orig_list_entry_free_ref(struct batadv_tt_orig_list_entry *orig_entry) { if (!atomic_dec_and_test(&orig_entry->refcount)) return; - call_rcu(&orig_entry->rcu, batadv_tt_orig_list_entry_free_rcu); + batadv_tt_orig_list_entry_release(orig_entry); } /** From e924c60db1b4891e45d15a33474ac5fab62cf029 Mon Sep 17 00:00:00 2001 From: Michael Neuling Date: Thu, 19 Nov 2015 15:44:45 +1100 Subject: [PATCH 060/325] powerpc/tm: Check for already reclaimed tasks commit 7f821fc9c77a9b01fe7b1d6e72717b33d8d64142 upstream. Currently we can hit a scenario where we'll tm_reclaim() twice. This results in a TM bad thing exception because the second reclaim occurs when not in suspend mode. The scenario in which this can happen is the following. We attempt to deliver a signal to userspace. To do this we need obtain the stack pointer to write the signal context. To get this stack pointer we must tm_reclaim() in case we need to use the checkpointed stack pointer (see get_tm_stackpointer()). Normally we'd then return directly to userspace to deliver the signal without going through __switch_to(). Unfortunatley, if at this point we get an error (such as a bad userspace stack pointer), we need to exit the process. The exit will result in a __switch_to(). __switch_to() will attempt to save the process state which results in another tm_reclaim(). This tm_reclaim() now causes a TM Bad Thing exception as this state has already been saved and the processor is no longer in TM suspend mode. Whee! This patch checks the state of the MSR to ensure we are TM suspended before we attempt the tm_reclaim(). If we've already saved the state away, we should no longer be in TM suspend mode. This has the additional advantage of checking for a potential TM Bad Thing exception. Found using syscall fuzzer. Fixes: fb09692e71f1 ("powerpc: Add reclaim and recheckpoint functions for context switching transactional memory processes") Signed-off-by: Michael Neuling Signed-off-by: Michael Ellerman Signed-off-by: Greg Kroah-Hartman --- arch/powerpc/kernel/process.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 646bf4d222c1..ef2ad2d682da 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -551,6 +551,24 @@ static void tm_reclaim_thread(struct thread_struct *thr, msr_diff &= MSR_FP | MSR_VEC | MSR_VSX | MSR_FE0 | MSR_FE1; } + /* + * Use the current MSR TM suspended bit to track if we have + * checkpointed state outstanding. + * On signal delivery, we'd normally reclaim the checkpointed + * state to obtain stack pointer (see:get_tm_stackpointer()). + * This will then directly return to userspace without going + * through __switch_to(). However, if the stack frame is bad, + * we need to exit this thread which calls __switch_to() which + * will again attempt to reclaim the already saved tm state. + * Hence we need to check that we've not already reclaimed + * this state. + * We do this using the current MSR, rather tracking it in + * some specific thread_struct bit, as it has the additional + * benifit of checking for a potential TM bad thing exception. + */ + if (!MSR_TM_SUSPENDED(mfmsr())) + return; + /* * Use the current MSR TM suspended bit to track if we have * checkpointed state outstanding. From 2ed6c101147879faa253fdf045d87651a6cb8f18 Mon Sep 17 00:00:00 2001 From: Boqun Feng Date: Mon, 2 Nov 2015 09:30:31 +0800 Subject: [PATCH 061/325] powerpc: Make value-returning atomics fully ordered commit 49e9cf3f0c04bf76ffa59242254110309554861d upstream. According to memory-barriers.txt: > Any atomic operation that modifies some state in memory and returns > information about the state (old or new) implies an SMP-conditional > general memory barrier (smp_mb()) on each side of the actual > operation ... Which mean these operations should be fully ordered. However on PPC, PPC_ATOMIC_ENTRY_BARRIER is the barrier before the actual operation, which is currently "lwsync" if SMP=y. The leading "lwsync" can not guarantee fully ordered atomics, according to Paul Mckenney: https://lkml.org/lkml/2015/10/14/970 To fix this, we define PPC_ATOMIC_ENTRY_BARRIER as "sync" to guarantee the fully-ordered semantics. This also makes futex atomics fully ordered, which can avoid possible memory ordering problems if userspace code relies on futex system call for fully ordered semantics. Fixes: b97021f85517 ("powerpc: Fix atomic_xxx_return barrier semantics") Signed-off-by: Boqun Feng Reviewed-by: Paul E. McKenney Acked-by: Peter Zijlstra (Intel) Signed-off-by: Michael Ellerman Signed-off-by: Greg Kroah-Hartman --- arch/powerpc/include/asm/synch.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/include/asm/synch.h b/arch/powerpc/include/asm/synch.h index e682a7143edb..c50868681f9e 100644 --- a/arch/powerpc/include/asm/synch.h +++ b/arch/powerpc/include/asm/synch.h @@ -44,7 +44,7 @@ static inline void isync(void) MAKE_LWSYNC_SECTION_ENTRY(97, __lwsync_fixup); #define PPC_ACQUIRE_BARRIER "\n" stringify_in_c(__PPC_ACQUIRE_BARRIER) #define PPC_RELEASE_BARRIER stringify_in_c(LWSYNC) "\n" -#define PPC_ATOMIC_ENTRY_BARRIER "\n" stringify_in_c(LWSYNC) "\n" +#define PPC_ATOMIC_ENTRY_BARRIER "\n" stringify_in_c(sync) "\n" #define PPC_ATOMIC_EXIT_BARRIER "\n" stringify_in_c(sync) "\n" #else #define PPC_ACQUIRE_BARRIER From badc688439f09f440e8d3dcd5d23457e54dfa8eb Mon Sep 17 00:00:00 2001 From: Boqun Feng Date: Mon, 2 Nov 2015 09:30:32 +0800 Subject: [PATCH 062/325] powerpc: Make {cmp}xchg* and their atomic_ versions fully ordered commit 81d7a3294de7e9828310bbf986a67246b13fa01e upstream. According to memory-barriers.txt, xchg*, cmpxchg* and their atomic_ versions all need to be fully ordered, however they are now just RELEASE+ACQUIRE, which are not fully ordered. So also replace PPC_RELEASE_BARRIER and PPC_ACQUIRE_BARRIER with PPC_ATOMIC_ENTRY_BARRIER and PPC_ATOMIC_EXIT_BARRIER in __{cmp,}xchg_{u32,u64} respectively to guarantee fully ordered semantics of atomic{,64}_{cmp,}xchg() and {cmp,}xchg(), as a complement of commit b97021f85517 ("powerpc: Fix atomic_xxx_return barrier semantics") This patch depends on patch "powerpc: Make value-returning atomics fully ordered" for PPC_ATOMIC_ENTRY_BARRIER definition. Signed-off-by: Boqun Feng Reviewed-by: Paul E. McKenney Acked-by: Peter Zijlstra (Intel) Signed-off-by: Michael Ellerman Signed-off-by: Greg Kroah-Hartman --- arch/powerpc/include/asm/cmpxchg.h | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/arch/powerpc/include/asm/cmpxchg.h b/arch/powerpc/include/asm/cmpxchg.h index ad6263cffb0f..d1a8d93cccfd 100644 --- a/arch/powerpc/include/asm/cmpxchg.h +++ b/arch/powerpc/include/asm/cmpxchg.h @@ -18,12 +18,12 @@ __xchg_u32(volatile void *p, unsigned long val) unsigned long prev; __asm__ __volatile__( - PPC_RELEASE_BARRIER + PPC_ATOMIC_ENTRY_BARRIER "1: lwarx %0,0,%2 \n" PPC405_ERR77(0,%2) " stwcx. %3,0,%2 \n\ bne- 1b" - PPC_ACQUIRE_BARRIER + PPC_ATOMIC_EXIT_BARRIER : "=&r" (prev), "+m" (*(volatile unsigned int *)p) : "r" (p), "r" (val) : "cc", "memory"); @@ -61,12 +61,12 @@ __xchg_u64(volatile void *p, unsigned long val) unsigned long prev; __asm__ __volatile__( - PPC_RELEASE_BARRIER + PPC_ATOMIC_ENTRY_BARRIER "1: ldarx %0,0,%2 \n" PPC405_ERR77(0,%2) " stdcx. %3,0,%2 \n\ bne- 1b" - PPC_ACQUIRE_BARRIER + PPC_ATOMIC_EXIT_BARRIER : "=&r" (prev), "+m" (*(volatile unsigned long *)p) : "r" (p), "r" (val) : "cc", "memory"); @@ -151,14 +151,14 @@ __cmpxchg_u32(volatile unsigned int *p, unsigned long old, unsigned long new) unsigned int prev; __asm__ __volatile__ ( - PPC_RELEASE_BARRIER + PPC_ATOMIC_ENTRY_BARRIER "1: lwarx %0,0,%2 # __cmpxchg_u32\n\ cmpw 0,%0,%3\n\ bne- 2f\n" PPC405_ERR77(0,%2) " stwcx. %4,0,%2\n\ bne- 1b" - PPC_ACQUIRE_BARRIER + PPC_ATOMIC_EXIT_BARRIER "\n\ 2:" : "=&r" (prev), "+m" (*p) @@ -197,13 +197,13 @@ __cmpxchg_u64(volatile unsigned long *p, unsigned long old, unsigned long new) unsigned long prev; __asm__ __volatile__ ( - PPC_RELEASE_BARRIER + PPC_ATOMIC_ENTRY_BARRIER "1: ldarx %0,0,%2 # __cmpxchg_u64\n\ cmpd 0,%0,%3\n\ bne- 2f\n\ stdcx. %4,0,%2\n\ bne- 1b" - PPC_ACQUIRE_BARRIER + PPC_ATOMIC_EXIT_BARRIER "\n\ 2:" : "=&r" (prev), "+m" (*p) From 3e96fc5b40e20872e4abdea213b80e5f5e21e71c Mon Sep 17 00:00:00 2001 From: Ulrich Weigand Date: Tue, 12 Jan 2016 23:14:22 +1100 Subject: [PATCH 063/325] scripts/recordmcount.pl: support data in text section on powerpc commit 2e50c4bef77511b42cc226865d6bc568fa7f8769 upstream. If a text section starts out with a data blob before the first function start label, disassembly parsing doing in recordmcount.pl gets confused on powerpc, leading to creation of corrupted module objects. This was not a problem so far since the compiler would never create such text sections. However, this has changed with a recent change in GCC 6 to support distances of > 2GB between a function and its assoicated TOC in the ELFv2 ABI, exposing this problem. There is already code in recordmcount.pl to handle such data blobs on the sparc64 platform. This patch uses the same method to handle those on powerpc as well. Acked-by: Steven Rostedt Signed-off-by: Ulrich Weigand Signed-off-by: Michael Ellerman Signed-off-by: Greg Kroah-Hartman --- scripts/recordmcount.pl | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/scripts/recordmcount.pl b/scripts/recordmcount.pl index 826470d7f000..96e2486a6fc4 100755 --- a/scripts/recordmcount.pl +++ b/scripts/recordmcount.pl @@ -263,7 +263,8 @@ if ($arch eq "x86_64") { } elsif ($arch eq "powerpc") { $local_regex = "^[0-9a-fA-F]+\\s+t\\s+(\\.?\\S+)"; - $function_regex = "^([0-9a-fA-F]+)\\s+<(\\.?.*?)>:"; + # See comment in the sparc64 section for why we use '\w'. + $function_regex = "^([0-9a-fA-F]+)\\s+<(\\.?\\w*?)>:"; $mcount_regex = "^\\s*([0-9a-fA-F]+):.*\\s\\.?_mcount\$"; if ($bits == 64) { From e268f8484851cf11ca1a08283d04ab35226f8967 Mon Sep 17 00:00:00 2001 From: Ulrich Weigand Date: Tue, 12 Jan 2016 23:14:23 +1100 Subject: [PATCH 064/325] powerpc/module: Handle R_PPC64_ENTRY relocations commit a61674bdfc7c2bf909c4010699607b62b69b7bec upstream. GCC 6 will include changes to generated code with -mcmodel=large, which is used to build kernel modules on powerpc64le. This was necessary because the large model is supposed to allow arbitrary sizes and locations of the code and data sections, but the ELFv2 global entry point prolog still made the unconditional assumption that the TOC associated with any particular function can be found within 2 GB of the function entry point: func: addis r2,r12,(.TOC.-func)@ha addi r2,r2,(.TOC.-func)@l .localentry func, .-func To remove this assumption, GCC will now generate instead this global entry point prolog sequence when using -mcmodel=large: .quad .TOC.-func func: .reloc ., R_PPC64_ENTRY ld r2, -8(r12) add r2, r2, r12 .localentry func, .-func The new .reloc triggers an optimization in the linker that will replace this new prolog with the original code (see above) if the linker determines that the distance between .TOC. and func is in range after all. Since this new relocation is now present in module object files, the kernel module loader is required to handle them too. This patch adds support for the new relocation and implements the same optimization done by the GNU linker. Signed-off-by: Ulrich Weigand Signed-off-by: Michael Ellerman Signed-off-by: Greg Kroah-Hartman --- arch/powerpc/include/uapi/asm/elf.h | 2 ++ arch/powerpc/kernel/module_64.c | 27 +++++++++++++++++++++++++++ 2 files changed, 29 insertions(+) diff --git a/arch/powerpc/include/uapi/asm/elf.h b/arch/powerpc/include/uapi/asm/elf.h index 59dad113897b..c2d21d11c2d2 100644 --- a/arch/powerpc/include/uapi/asm/elf.h +++ b/arch/powerpc/include/uapi/asm/elf.h @@ -295,6 +295,8 @@ do { \ #define R_PPC64_TLSLD 108 #define R_PPC64_TOCSAVE 109 +#define R_PPC64_ENTRY 118 + #define R_PPC64_REL16 249 #define R_PPC64_REL16_LO 250 #define R_PPC64_REL16_HI 251 diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c index 68384514506b..59663af9315f 100644 --- a/arch/powerpc/kernel/module_64.c +++ b/arch/powerpc/kernel/module_64.c @@ -635,6 +635,33 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, */ break; + case R_PPC64_ENTRY: + /* + * Optimize ELFv2 large code model entry point if + * the TOC is within 2GB range of current location. + */ + value = my_r2(sechdrs, me) - (unsigned long)location; + if (value + 0x80008000 > 0xffffffff) + break; + /* + * Check for the large code model prolog sequence: + * ld r2, ...(r12) + * add r2, r2, r12 + */ + if ((((uint32_t *)location)[0] & ~0xfffc) + != 0xe84c0000) + break; + if (((uint32_t *)location)[1] != 0x7c426214) + break; + /* + * If found, replace it with: + * addis r2, r12, (.TOC.-func)@ha + * addi r2, r12, (.TOC.-func)@l + */ + ((uint32_t *)location)[0] = 0x3c4c0000 + PPC_HA(value); + ((uint32_t *)location)[1] = 0x38420000 + PPC_LO(value); + break; + case R_PPC64_REL16_HA: /* Subtract location pointer */ value -= (unsigned long)location; From c01afb9239eaee84a93e7b0319e3935f55604361 Mon Sep 17 00:00:00 2001 From: John Blackwood Date: Mon, 7 Dec 2015 11:50:34 +0000 Subject: [PATCH 065/325] arm64: Clear out any singlestep state on a ptrace detach operation commit 5db4fd8c52810bd9740c1240ebf89223b171aa70 upstream. Make sure to clear out any ptrace singlestep state when a ptrace(2) PTRACE_DETACH call is made on arm64 systems. Otherwise, the previously ptraced task will die off with a SIGTRAP signal if the debugger just previously singlestepped the ptraced task. Signed-off-by: John Blackwood [will: added comment to justify why this is in the arch code] Signed-off-by: Will Deacon Signed-off-by: Greg Kroah-Hartman --- arch/arm64/kernel/ptrace.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 1971f491bb90..ff7f13239515 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -58,6 +58,12 @@ */ void ptrace_disable(struct task_struct *child) { + /* + * This would be better off in core code, but PTRACE_DETACH has + * grown its fair share of arch-specific worts and changing it + * is likely to cause regressions on obscure architectures. + */ + user_disable_single_step(child); } #ifdef CONFIG_HAVE_HW_BREAKPOINT From 8182d4cf11a77f2c2b6afe85366e9328107b6256 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Thu, 10 Dec 2015 16:05:36 +0000 Subject: [PATCH 066/325] arm64: mm: ensure that the zero page is visible to the page table walker commit 32d6397805d00573ce1fa55f408ce2bca15b0ad3 upstream. In paging_init, we allocate the zero page, memset it to zero and then point TTBR0 to it in order to avoid speculative fetches through the identity mapping. In order to guarantee that the freshly zeroed page is indeed visible to the page table walker, we need to execute a dsb instruction prior to writing the TTBR. Signed-off-by: Will Deacon Signed-off-by: Greg Kroah-Hartman --- arch/arm64/mm/mmu.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 873e363048c6..116ad654dd59 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -456,6 +456,9 @@ void __init paging_init(void) empty_zero_page = virt_to_page(zero_page); + /* Ensure the zero page is visible to the page table walker */ + dsb(ishst); + /* * TTBR0 is only used for the identity mapping at this stage. Make it * point to zero page to avoid speculatively fetching new entries. From f50c2907a9b3dfc1ba840e6cc9884cf77d9e44cc Mon Sep 17 00:00:00 2001 From: Lorenzo Pieralisi Date: Fri, 18 Dec 2015 10:35:54 +0000 Subject: [PATCH 067/325] arm64: kernel: enforce pmuserenr_el0 initialization and restore commit 60792ad349f3c6dc5735aafefe5dc9121c79e320 upstream. The pmuserenr_el0 register value is architecturally UNKNOWN on reset. Current kernel code resets that register value iff the core pmu device is correctly probed in the kernel. On platforms with missing DT pmu nodes (or disabled perf events in the kernel), the pmu is not probed, therefore the pmuserenr_el0 register is not reset in the kernel, which means that its value retains the reset value that is architecturally UNKNOWN (system may run with eg pmuserenr_el0 == 0x1, which means that PMU counters access is available at EL0, which must be disallowed). This patch adds code that resets pmuserenr_el0 on cold boot and restores it on core resume from shutdown, so that the pmuserenr_el0 setup is always enforced in the kernel. Cc: Mark Rutland Signed-off-by: Lorenzo Pieralisi Signed-off-by: Will Deacon Signed-off-by: Greg Kroah-Hartman --- arch/arm64/kernel/perf_event.c | 3 --- arch/arm64/mm/proc.S | 2 ++ 2 files changed, 2 insertions(+), 3 deletions(-) diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c index 5b1897e8ca24..62d3dc60ca09 100644 --- a/arch/arm64/kernel/perf_event.c +++ b/arch/arm64/kernel/perf_event.c @@ -574,9 +574,6 @@ static void armv8pmu_reset(void *info) /* Initialize & Reset PMNC: C and P bits. */ armv8pmu_pmcr_write(ARMV8_PMCR_P | ARMV8_PMCR_C); - - /* Disable access from userspace. */ - asm volatile("msr pmuserenr_el0, %0" :: "r" (0)); } static int armv8_pmuv3_map_event(struct perf_event *event) diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index cacecc4ad3e5..9c4dce312b2b 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -117,6 +117,7 @@ ENTRY(cpu_do_resume) */ ubfx x11, x11, #1, #1 msr oslar_el1, x11 + msr pmuserenr_el0, xzr // Disable PMU access from EL0 mov x0, x12 dsb nsh // Make sure local tlb invalidation completed isb @@ -155,6 +156,7 @@ ENTRY(__cpu_setup) msr cpacr_el1, x0 // Enable FP/ASIMD mov x0, #1 << 12 // Reset mdscr_el1 and disable msr mdscr_el1, x0 // access to the DCC from EL0 + msr pmuserenr_el0, xzr // Disable PMU access from EL0 /* * Memory region attributes for LPAE: * From 9497f702ab82314dffa457823be91783ca5a4531 Mon Sep 17 00:00:00 2001 From: Lorenzo Pieralisi Date: Wed, 13 Jan 2016 14:50:03 +0000 Subject: [PATCH 068/325] arm64: kernel: fix architected PMU registers unconditional access commit f436b2ac90a095746beb6729b8ee8ed87c9eaede upstream. The Performance Monitors extension is an optional feature of the AArch64 architecture, therefore, in order to access Performance Monitors registers safely, the kernel should detect the architected PMU unit presence through the ID_AA64DFR0_EL1 register PMUVer field before accessing them. This patch implements a guard by reading the ID_AA64DFR0_EL1 register PMUVer field to detect the architected PMU presence and prevent accessing PMU system registers if the Performance Monitors extension is not implemented in the core. Cc: Peter Maydell Cc: Mark Rutland Fixes: 60792ad349f3 ("arm64: kernel: enforce pmuserenr_el0 initialization and restore") Signed-off-by: Lorenzo Pieralisi Reported-by: Guenter Roeck Tested-by: Guenter Roeck Signed-off-by: Will Deacon Signed-off-by: Greg Kroah-Hartman --- arch/arm64/kernel/head.S | 5 +++++ arch/arm64/mm/proc-macros.S | 12 ++++++++++++ arch/arm64/mm/proc.S | 4 ++-- 3 files changed, 19 insertions(+), 2 deletions(-) diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index 23cfc08fc8ba..b685257926f0 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -512,9 +512,14 @@ CPU_LE( movk x0, #0x30d0, lsl #16 ) // Clear EE and E0E on LE systems #endif /* EL2 debug */ + mrs x0, id_aa64dfr0_el1 // Check ID_AA64DFR0_EL1 PMUVer + sbfx x0, x0, #8, #4 + cmp x0, #1 + b.lt 4f // Skip if no PMU present mrs x0, pmcr_el0 // Disable debug access traps ubfx x0, x0, #11, #5 // to EL2 and allow access to msr mdcr_el2, x0 // all PMU counters from EL1 +4: /* Stage-2 translation */ msr vttbr_el2, xzr diff --git a/arch/arm64/mm/proc-macros.S b/arch/arm64/mm/proc-macros.S index 4c4d93c4bf65..d69dffffaa89 100644 --- a/arch/arm64/mm/proc-macros.S +++ b/arch/arm64/mm/proc-macros.S @@ -62,3 +62,15 @@ bfi \valreg, \tmpreg, #TCR_T0SZ_OFFSET, #TCR_TxSZ_WIDTH #endif .endm + +/* + * reset_pmuserenr_el0 - reset PMUSERENR_EL0 if PMUv3 present + */ + .macro reset_pmuserenr_el0, tmpreg + mrs \tmpreg, id_aa64dfr0_el1 // Check ID_AA64DFR0_EL1 PMUVer + sbfx \tmpreg, \tmpreg, #8, #4 + cmp \tmpreg, #1 // Skip if no PMU present + b.lt 9000f + msr pmuserenr_el0, xzr // Disable PMU access from EL0 +9000: + .endm diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index 9c4dce312b2b..b8f04b3f2786 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -117,7 +117,7 @@ ENTRY(cpu_do_resume) */ ubfx x11, x11, #1, #1 msr oslar_el1, x11 - msr pmuserenr_el0, xzr // Disable PMU access from EL0 + reset_pmuserenr_el0 x0 // Disable PMU access from EL0 mov x0, x12 dsb nsh // Make sure local tlb invalidation completed isb @@ -156,7 +156,7 @@ ENTRY(__cpu_setup) msr cpacr_el1, x0 // Enable FP/ASIMD mov x0, #1 << 12 // Reset mdscr_el1 and disable msr mdscr_el1, x0 // access to the DCC from EL0 - msr pmuserenr_el0, xzr // Disable PMU access from EL0 + reset_pmuserenr_el0 x0 // Disable PMU access from EL0 /* * Memory region attributes for LPAE: * From f1ab5eafa3625b41c74326a1994a820ff805d5b2 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Sun, 31 Jan 2016 11:29:37 -0800 Subject: [PATCH 069/325] Linux 4.4.1 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 70dea02f1346..c6a265b52c93 100644 --- a/Makefile +++ b/Makefile @@ -1,6 +1,6 @@ VERSION = 4 PATCHLEVEL = 4 -SUBLEVEL = 0 +SUBLEVEL = 1 EXTRAVERSION = NAME = Blurry Fish Butt From 6abc65624a647f5e27d2dbccff03335f3c28504a Mon Sep 17 00:00:00 2001 From: LABBE Corentin Date: Mon, 16 Nov 2015 09:35:54 +0100 Subject: [PATCH 070/325] crypto: sun4i-ss - add missing statesize commit 4f9ea86604e3ba64edd2817795798168fbb3c1a6 upstream. sun4i-ss implementaton of md5/sha1 is via ahash algorithms. Commit 8996eafdcbad ("crypto: ahash - ensure statesize is non-zero") made impossible to load them without giving statesize. This patch specifiy statesize for sha1 and md5. Fixes: 6298e948215f ("crypto: sunxi-ss - Add Allwinner Security System crypto accelerator") Tested-by: Chen-Yu Tsai Signed-off-by: LABBE Corentin Signed-off-by: Herbert Xu Signed-off-by: Greg Kroah-Hartman --- drivers/crypto/sunxi-ss/sun4i-ss-core.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/crypto/sunxi-ss/sun4i-ss-core.c b/drivers/crypto/sunxi-ss/sun4i-ss-core.c index eab6fe227fa0..107cd2a41cae 100644 --- a/drivers/crypto/sunxi-ss/sun4i-ss-core.c +++ b/drivers/crypto/sunxi-ss/sun4i-ss-core.c @@ -39,6 +39,7 @@ static struct sun4i_ss_alg_template ss_algs[] = { .import = sun4i_hash_import_md5, .halg = { .digestsize = MD5_DIGEST_SIZE, + .statesize = sizeof(struct md5_state), .base = { .cra_name = "md5", .cra_driver_name = "md5-sun4i-ss", @@ -66,6 +67,7 @@ static struct sun4i_ss_alg_template ss_algs[] = { .import = sun4i_hash_import_sha1, .halg = { .digestsize = SHA1_DIGEST_SIZE, + .statesize = sizeof(struct sha1_state), .base = { .cra_name = "sha1", .cra_driver_name = "sha1-sun4i-ss", From 1f1c9c9befd45d61ff0a91ea78892be03a4087e7 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 28 Dec 2015 11:27:15 -0500 Subject: [PATCH 071/325] NFSv4.1/pnfs: Fixup an lo->plh_block_lgets imbalance in layoutreturn commit 1a093ceb053832c25b92f3cf26b957543c7baf9b upstream. Since commit 2d8ae84fbc32, nothing is bumping lo->plh_block_lgets in the layoutreturn path, so it should not be touched in nfs4_layoutreturn_release either. Fixes: 2d8ae84fbc32 ("NFSv4.1/pnfs: Remove redundant lo->plh_block_lgets...") Signed-off-by: Trond Myklebust Signed-off-by: Greg Kroah-Hartman --- fs/nfs/nfs4proc.c | 1 - 1 file changed, 1 deletion(-) diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 89818036f035..343b0f1f15b1 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -8054,7 +8054,6 @@ static void nfs4_layoutreturn_release(void *calldata) pnfs_set_layout_stateid(lo, &lrp->res.stateid, true); pnfs_mark_matching_lsegs_invalid(lo, &freeme, &lrp->args.range); pnfs_clear_layoutreturn_waitbit(lo); - lo->plh_block_lgets--; spin_unlock(&lo->plh_inode->i_lock); pnfs_free_lseg_list(&freeme); pnfs_put_layout_hdr(lrp->args.layout); From d2081cfe624b5decaaf68088ca256ed1b140672c Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Tue, 12 Jan 2016 15:08:39 -0700 Subject: [PATCH 072/325] block: split bios to max possible length commit e36f6204288088fda50d1c84830340ccb70f85ff upstream. This splits bio in the middle of a vector to form the largest possible bio at the h/w's desired alignment, and guarantees the bio being split will have some data. The criteria for splitting is changed from the max sectors to the h/w's optimal sector alignment if it is provided. For h/w that advertise their block storage's underlying chunk size, it's a big performance win to not submit commands that cross them. If sector alignment is not provided, this patch uses the max sectors as before. This addresses the performance issue commit d380561113 attempted to fix, but was reverted due to splitting logic error. Signed-off-by: Keith Busch Cc: Jens Axboe Cc: Ming Lei Cc: Kent Overstreet Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- block/blk-merge.c | 19 ++++++++++++++++--- 1 file changed, 16 insertions(+), 3 deletions(-) diff --git a/block/blk-merge.c b/block/blk-merge.c index e01405a3e8b3..6b982cacaea8 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -81,9 +81,6 @@ static struct bio *blk_bio_segment_split(struct request_queue *q, struct bio *new = NULL; bio_for_each_segment(bv, bio, iter) { - if (sectors + (bv.bv_len >> 9) > queue_max_sectors(q)) - goto split; - /* * If the queue doesn't support SG gaps and adding this * offset would create a gap, disallow it. @@ -91,6 +88,22 @@ static struct bio *blk_bio_segment_split(struct request_queue *q, if (bvprvp && bvec_gap_to_prev(q, bvprvp, bv.bv_offset)) goto split; + if (sectors + (bv.bv_len >> 9) > + blk_max_size_offset(q, bio->bi_iter.bi_sector)) { + /* + * Consider this a new segment if we're splitting in + * the middle of this vector. + */ + if (nsegs < queue_max_segments(q) && + sectors < blk_max_size_offset(q, + bio->bi_iter.bi_sector)) { + nsegs++; + sectors = blk_max_size_offset(q, + bio->bi_iter.bi_sector); + } + goto split; + } + if (bvprvp && blk_queue_cluster(q)) { if (seg_size + bv.bv_len > queue_max_segment_size(q)) goto new_segment; From 001915457e3488b8c647ea77cb475e2374136a31 Mon Sep 17 00:00:00 2001 From: Tariq Saeed Date: Thu, 21 Jan 2016 16:40:39 -0800 Subject: [PATCH 073/325] ocfs2: NFS hangs in __ocfs2_cluster_lock due to race with ocfs2_unblock_lock commit b1b1e15ef6b80facf76d6757649dfd7295eda29f upstream. NFS on a 2 node ocfs2 cluster each node exporting dir. The lock causing the hang is the global bit map inode lock. Node 1 is master, has the lock granted in PR mode; Node 2 is in the converting list (PR -> EX). There are no holders of the lock on the master node so it should downconvert to NL and grant EX to node 2 but that does not happen. BLOCKED + QUEUED in lock res are set and it is on osb blocked list. Threads are waiting in __ocfs2_cluster_lock on BLOCKED. One thread wants EX, rest want PR. So it is as though the downconvert thread needs to be kicked to complete the conv. The hang is caused by an EX req coming into __ocfs2_cluster_lock on the heels of a PR req after it sets BUSY (drops l_lock, releasing EX thread), forcing the incoming EX to wait on BUSY without doing anything. PR has called ocfs2_dlm_lock, which sets the node 1 lock from NL -> PR, queues ast. At this time, upconvert (PR ->EX) arrives from node 2, finds conflict with node 1 lock in PR, so the lock res is put on dlm thread's dirty listt. After ret from ocf2_dlm_lock, PR thread now waits behind EX on BUSY till awoken by ast. Now it is dlm_thread that serially runs dlm_shuffle_lists, ast, bast, in that order. dlm_shuffle_lists ques a bast on behalf of node 2 (which will be run by dlm_thread right after the ast). ast does its part, sets UPCONVERT_FINISHING, clears BUSY and wakes its waiters. Next, dlm_thread runs bast. It sets BLOCKED and kicks dc thread. dc thread runs ocfs2_unblock_lock, but since UPCONVERT_FINISHING set, skips doing anything and reques. Inside of __ocfs2_cluster_lock, since EX has been waiting on BUSY ahead of PR, it wakes up first, finds BLOCKED set and skips doing anything but clearing UPCONVERT_FINISHING (which was actually "meant" for the PR thread), and this time waits on BLOCKED. Next, the PR thread comes out of wait but since UPCONVERT_FINISHING is not set, it skips updating the l_ro_holders and goes straight to wait on BLOCKED. So there, we have a hang! Threads in __ocfs2_cluster_lock wait on BLOCKED, lock res in osb blocked list. Only when dc thread is awoken, it will run ocfs2_unblock_lock and things will unhang. One way to fix this is to wake the dc thread on the flag after clearing UPCONVERT_FINISHING Orabug: 20933419 Signed-off-by: Tariq Saeed Signed-off-by: Santosh Shilimkar Reviewed-by: Wengang Wang Reviewed-by: Mark Fasheh Cc: Joel Becker Cc: Junxiao Bi Reviewed-by: Joseph Qi Cc: Eric Ren Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- fs/ocfs2/dlmglue.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c index 20276e340339..b002acf50203 100644 --- a/fs/ocfs2/dlmglue.c +++ b/fs/ocfs2/dlmglue.c @@ -1390,6 +1390,7 @@ static int __ocfs2_cluster_lock(struct ocfs2_super *osb, unsigned int gen; int noqueue_attempted = 0; int dlm_locked = 0; + int kick_dc = 0; if (!(lockres->l_flags & OCFS2_LOCK_INITIALIZED)) { mlog_errno(-EINVAL); @@ -1524,7 +1525,12 @@ update_holders: unlock: lockres_clear_flags(lockres, OCFS2_LOCK_UPCONVERT_FINISHING); + /* ocfs2_unblock_lock reques on seeing OCFS2_LOCK_UPCONVERT_FINISHING */ + kick_dc = (lockres->l_flags & OCFS2_LOCK_BLOCKED); + spin_unlock_irqrestore(&lockres->l_lock, flags); + if (kick_dc) + ocfs2_wake_downconvert_thread(osb); out: /* * This is helping work around a lock inversion between the page lock From 0fc93ba93bdbd73b94c67fc6250ac6e9ae9deb97 Mon Sep 17 00:00:00 2001 From: Ioan-Adrian Ratiu Date: Fri, 20 Nov 2015 22:19:02 +0200 Subject: [PATCH 074/325] HID: usbhid: fix recursive deadlock commit e470127e9606b1fa151c4184243e61296d1e0c0f upstream. The critical section protected by usbhid->lock in hid_ctrl() is too big and because of this it causes a recursive deadlock. "Too big" means the case statement and the call to hid_input_report() do not need to be protected by the spinlock (no URB operations are done inside them). The deadlock happens because in certain rare cases drivers try to grab the lock while handling the ctrl irq which grabs the lock before them as described above. For example newer wacom tablets like 056a:033c try to reschedule proximity reads from wacom_intuos_schedule_prox_event() calling hid_hw_request() -> usbhid_request() -> usbhid_submit_report() which tries to grab the usbhid lock already held by hid_ctrl(). There are two ways to get out of this deadlock: 1. Make the drivers work "around" the ctrl critical region, in the wacom case for ex. by delaying the scheduling of the proximity read request itself to a workqueue. 2. Shrink the critical region so the usbhid lock protects only the instructions which modify usbhid state, calling hid_input_report() with the spinlock unlocked, allowing the device driver to grab the lock first, finish and then grab the lock afterwards in hid_ctrl(). This patch implements the 2nd solution. Signed-off-by: Ioan-Adrian Ratiu Signed-off-by: Jiri Kosina Signed-off-by: Jason Gerecke Signed-off-by: Greg Kroah-Hartman --- drivers/hid/usbhid/hid-core.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/hid/usbhid/hid-core.c b/drivers/hid/usbhid/hid-core.c index 36712e9f56c2..5dd426fee8cc 100644 --- a/drivers/hid/usbhid/hid-core.c +++ b/drivers/hid/usbhid/hid-core.c @@ -477,8 +477,6 @@ static void hid_ctrl(struct urb *urb) struct usbhid_device *usbhid = hid->driver_data; int unplug = 0, status = urb->status; - spin_lock(&usbhid->lock); - switch (status) { case 0: /* success */ if (usbhid->ctrl[usbhid->ctrltail].dir == USB_DIR_IN) @@ -498,6 +496,8 @@ static void hid_ctrl(struct urb *urb) hid_warn(urb->dev, "ctrl urb status %d received\n", status); } + spin_lock(&usbhid->lock); + if (unplug) { usbhid->ctrltail = usbhid->ctrlhead; } else { From 9e5d4a6c799565346b677484f7348effd6f2d877 Mon Sep 17 00:00:00 2001 From: Martin Wilck Date: Mon, 30 Nov 2015 12:50:05 +0100 Subject: [PATCH 075/325] base/platform: Fix platform drivers with no probe callback commit 25cad69f21f5532d99e2ee73c8ab6512bcab614c upstream. Since b8b2c7d845d5, platform_drv_probe() is called for all platform devices. If drv->probe is NULL, and dev_pm_domain_attach() fails, platform_drv_probe() will return the error code from dev_pm_domain_attach(). This causes real_probe() to enter the "probe_failed" path and set dev->driver to NULL. Before b8b2c7d845d5, real_probe() would assume success if both dev->bus->probe and drv->probe were missing. As a result, a device and driver could be "bound" together just by matching their names; this doesn't work any more after b8b2c7d845d5. This may cause problems later for certain usage of platform_driver_register() and platform_device_register_simple(). I observed a panic while loading the tpm_tis driver with parameter "force=1" (i.e. registering tpm_tis as a platform driver), because tpm_tis_init's assumption that the device returned by platform_device_register_simple() was bound didn't hold any more (tpmm_chip_alloc() dereferences chip->pdev->driver, causing panic). This patch restores the previous (4.3.0 and earlier) behavior of platform_drv_probe() in the case when the associated platform driver has no "probe" function. Fixes: b8b2c7d845d5 ("base/platform: assert that dev_pm_domain callbacks are called unconditionally") Signed-off-by: Martin Wilck Cc: Martin Fuzzey Acked-by: Jarkko Sakkinen Signed-off-by: Greg Kroah-Hartman Signed-off-by: Greg Kroah-Hartman --- drivers/base/platform.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) diff --git a/drivers/base/platform.c b/drivers/base/platform.c index 1dd6d3bf1098..176b59f5bc47 100644 --- a/drivers/base/platform.c +++ b/drivers/base/platform.c @@ -513,10 +513,15 @@ static int platform_drv_probe(struct device *_dev) return ret; ret = dev_pm_domain_attach(_dev, true); - if (ret != -EPROBE_DEFER && drv->probe) { - ret = drv->probe(dev); - if (ret) - dev_pm_domain_detach(_dev, true); + if (ret != -EPROBE_DEFER) { + if (drv->probe) { + ret = drv->probe(dev); + if (ret) + dev_pm_domain_detach(_dev, true); + } else { + /* don't fail if just dev_pm_domain_attach failed */ + ret = 0; + } } if (drv->prevent_deferred_probe && ret == -EPROBE_DEFER) { From bfc5caf7569e39999c6515bd9f945bde14f2990f Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Sat, 23 Jan 2016 08:05:33 +0800 Subject: [PATCH 076/325] block: fix bio splitting on max sectors commit d0e5fbb01a67e400e82fefe4896ea40c6447ab98 upstream. After commit e36f62042880(block: split bios to maxpossible length), bio can be splitted in the middle of a vector entry, then it is easy to split out one bio which size isn't aligned with block size, especially when the block size is bigger than 512. This patch fixes the issue by making the max io size aligned to logical block size. Fixes: e36f62042880(block: split bios to maxpossible length) Reported-by: Stefan Haberland Cc: Keith Busch Suggested-by: Linus Torvalds Signed-off-by: Ming Lei Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- block/blk-merge.c | 26 +++++++++++++++++++------- 1 file changed, 19 insertions(+), 7 deletions(-) diff --git a/block/blk-merge.c b/block/blk-merge.c index 6b982cacaea8..b966db8f3556 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -68,6 +68,18 @@ static struct bio *blk_bio_write_same_split(struct request_queue *q, return bio_split(bio, q->limits.max_write_same_sectors, GFP_NOIO, bs); } +static inline unsigned get_max_io_size(struct request_queue *q, + struct bio *bio) +{ + unsigned sectors = blk_max_size_offset(q, bio->bi_iter.bi_sector); + unsigned mask = queue_logical_block_size(q) - 1; + + /* aligned to logical block size */ + sectors &= ~(mask >> 9); + + return sectors; +} + static struct bio *blk_bio_segment_split(struct request_queue *q, struct bio *bio, struct bio_set *bs, @@ -79,6 +91,7 @@ static struct bio *blk_bio_segment_split(struct request_queue *q, unsigned front_seg_size = bio->bi_seg_front_size; bool do_split = true; struct bio *new = NULL; + const unsigned max_sectors = get_max_io_size(q, bio); bio_for_each_segment(bv, bio, iter) { /* @@ -88,20 +101,19 @@ static struct bio *blk_bio_segment_split(struct request_queue *q, if (bvprvp && bvec_gap_to_prev(q, bvprvp, bv.bv_offset)) goto split; - if (sectors + (bv.bv_len >> 9) > - blk_max_size_offset(q, bio->bi_iter.bi_sector)) { + if (sectors + (bv.bv_len >> 9) > max_sectors) { /* * Consider this a new segment if we're splitting in * the middle of this vector. */ if (nsegs < queue_max_segments(q) && - sectors < blk_max_size_offset(q, - bio->bi_iter.bi_sector)) { + sectors < max_sectors) { nsegs++; - sectors = blk_max_size_offset(q, - bio->bi_iter.bi_sector); + sectors = max_sectors; } - goto split; + if (sectors) + goto split; + /* Make this single bvec as the 1st segment */ } if (bvprvp && blk_queue_cluster(q)) { From 5feecbf0568ab2395e57d0bdd9eb4babb58e4b1f Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Tue, 8 Dec 2015 17:00:42 +0100 Subject: [PATCH 077/325] ALSA: hda - Implement loopback control switch for Realtek and other codecs commit e7fdd52779a6c2b49d457f452296a77c8cffef6a upstream. Many codecs, typically found on Realtek codecs, have the analog loopback path merged to the secondary input of the middle of the output paths. Currently, we don't offer the dynamic switching in such configuration but let each loopback path mute by itself. This should work well in theory, but in reality, we often see that such a dead loopback path causes some background noises even if all the elements get muted. Such a problem has been fixed by adding the quirk accordingly to disable aamix, and it's the right fix, per se. The only problem is that it's not so trivial to achieve it; user needs to pass a hint string via patch module option or sysfs. This patch gives a bit improvement on the situation: it adds "Loopback Mixing" control element for such codecs like other codecs (e.g. IDT or VIA codecs) with the individual loopback paths. User can turn on/off the loopback path simply via a mixer app. For keeping the compatibility, the loopback is still enabled on these codecs. But user can try to turn it off if experiencing a suspicious background or click noise on the fly, then build a static fixup later once after the problem is addressed. Other than the addition of the loopback enable/disablement control, there should be no changes. Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/pci/hda/hda_generic.c | 87 +++++++++++++++++++++++++++++-------- 1 file changed, 68 insertions(+), 19 deletions(-) diff --git a/sound/pci/hda/hda_generic.c b/sound/pci/hda/hda_generic.c index c6e8a651cea1..9d6be68c611b 100644 --- a/sound/pci/hda/hda_generic.c +++ b/sound/pci/hda/hda_generic.c @@ -771,9 +771,6 @@ static void activate_amp(struct hda_codec *codec, hda_nid_t nid, int dir, unsigned int caps; unsigned int mask, val; - if (!enable && is_active_nid(codec, nid, dir, idx_to_check)) - return; - caps = query_amp_caps(codec, nid, dir); val = get_amp_val_to_activate(codec, nid, dir, caps, enable); mask = get_amp_mask_to_modify(codec, nid, dir, idx_to_check, caps); @@ -784,12 +781,22 @@ static void activate_amp(struct hda_codec *codec, hda_nid_t nid, int dir, update_amp(codec, nid, dir, idx, mask, val); } +static void check_and_activate_amp(struct hda_codec *codec, hda_nid_t nid, + int dir, int idx, int idx_to_check, + bool enable) +{ + /* check whether the given amp is still used by others */ + if (!enable && is_active_nid(codec, nid, dir, idx_to_check)) + return; + activate_amp(codec, nid, dir, idx, idx_to_check, enable); +} + static void activate_amp_out(struct hda_codec *codec, struct nid_path *path, int i, bool enable) { hda_nid_t nid = path->path[i]; init_amp(codec, nid, HDA_OUTPUT, 0); - activate_amp(codec, nid, HDA_OUTPUT, 0, 0, enable); + check_and_activate_amp(codec, nid, HDA_OUTPUT, 0, 0, enable); } static void activate_amp_in(struct hda_codec *codec, struct nid_path *path, @@ -817,9 +824,16 @@ static void activate_amp_in(struct hda_codec *codec, struct nid_path *path, * when aa-mixer is available, we need to enable the path as well */ for (n = 0; n < nums; n++) { - if (n != idx && (!add_aamix || conn[n] != spec->mixer_merge_nid)) - continue; - activate_amp(codec, nid, HDA_INPUT, n, idx, enable); + if (n != idx) { + if (conn[n] != spec->mixer_merge_nid) + continue; + /* when aamix is disabled, force to off */ + if (!add_aamix) { + activate_amp(codec, nid, HDA_INPUT, n, n, false); + continue; + } + } + check_and_activate_amp(codec, nid, HDA_INPUT, n, idx, enable); } } @@ -1580,6 +1594,12 @@ static bool map_singles(struct hda_codec *codec, int outs, return found; } +static inline bool has_aamix_out_paths(struct hda_gen_spec *spec) +{ + return spec->aamix_out_paths[0] || spec->aamix_out_paths[1] || + spec->aamix_out_paths[2]; +} + /* create a new path including aamix if available, and return its index */ static int check_aamix_out_path(struct hda_codec *codec, int path_idx) { @@ -2422,25 +2442,51 @@ static void update_aamix_paths(struct hda_codec *codec, bool do_mix, } } +/* re-initialize the output paths; only called from loopback_mixing_put() */ +static void update_output_paths(struct hda_codec *codec, int num_outs, + const int *paths) +{ + struct hda_gen_spec *spec = codec->spec; + struct nid_path *path; + int i; + + for (i = 0; i < num_outs; i++) { + path = snd_hda_get_path_from_idx(codec, paths[i]); + if (path) + snd_hda_activate_path(codec, path, path->active, + spec->aamix_mode); + } +} + static int loopback_mixing_put(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol) { struct hda_codec *codec = snd_kcontrol_chip(kcontrol); struct hda_gen_spec *spec = codec->spec; + const struct auto_pin_cfg *cfg = &spec->autocfg; unsigned int val = ucontrol->value.enumerated.item[0]; if (val == spec->aamix_mode) return 0; spec->aamix_mode = val; - update_aamix_paths(codec, val, spec->out_paths[0], - spec->aamix_out_paths[0], - spec->autocfg.line_out_type); - update_aamix_paths(codec, val, spec->hp_paths[0], - spec->aamix_out_paths[1], - AUTO_PIN_HP_OUT); - update_aamix_paths(codec, val, spec->speaker_paths[0], - spec->aamix_out_paths[2], - AUTO_PIN_SPEAKER_OUT); + if (has_aamix_out_paths(spec)) { + update_aamix_paths(codec, val, spec->out_paths[0], + spec->aamix_out_paths[0], + cfg->line_out_type); + update_aamix_paths(codec, val, spec->hp_paths[0], + spec->aamix_out_paths[1], + AUTO_PIN_HP_OUT); + update_aamix_paths(codec, val, spec->speaker_paths[0], + spec->aamix_out_paths[2], + AUTO_PIN_SPEAKER_OUT); + } else { + update_output_paths(codec, cfg->line_outs, spec->out_paths); + if (cfg->line_out_type != AUTO_PIN_HP_OUT) + update_output_paths(codec, cfg->hp_outs, spec->hp_paths); + if (cfg->line_out_type != AUTO_PIN_SPEAKER_OUT) + update_output_paths(codec, cfg->speaker_outs, + spec->speaker_paths); + } return 1; } @@ -2458,12 +2504,13 @@ static int create_loopback_mixing_ctl(struct hda_codec *codec) if (!spec->mixer_nid) return 0; - if (!(spec->aamix_out_paths[0] || spec->aamix_out_paths[1] || - spec->aamix_out_paths[2])) - return 0; if (!snd_hda_gen_add_kctl(spec, NULL, &loopback_mixing_enum)) return -ENOMEM; spec->have_aamix_ctl = 1; + /* if no explicit aamix path is present (e.g. for Realtek codecs), + * enable aamix as default -- just for compatibility + */ + spec->aamix_mode = !has_aamix_out_paths(spec); return 0; } @@ -5664,6 +5711,8 @@ static void init_aamix_paths(struct hda_codec *codec) if (!spec->have_aamix_ctl) return; + if (!has_aamix_out_paths(spec)) + return; update_aamix_paths(codec, spec->aamix_mode, spec->out_paths[0], spec->aamix_out_paths[0], spec->autocfg.line_out_type); From 7889b844ba4b9dc0b311b6daa6f6376a10fa9a75 Mon Sep 17 00:00:00 2001 From: xuejiufei Date: Thu, 14 Jan 2016 15:17:38 -0800 Subject: [PATCH 078/325] ocfs2/dlm: ignore cleaning the migration mle that is inuse commit bef5502de074b6f6fa647b94b73155d675694420 upstream. We have found that migration source will trigger a BUG that the refcount of mle is already zero before put when the target is down during migration. The situation is as follows: dlm_migrate_lockres dlm_add_migration_mle dlm_mark_lockres_migrating dlm_get_mle_inuse <<<<<< Now the refcount of the mle is 2. dlm_send_one_lockres and wait for the target to become the new master. <<<<<< o2hb detect the target down and clean the migration mle. Now the refcount is 1. dlm_migrate_lockres woken, and put the mle twice when found the target goes down which trigger the BUG with the following message: "ERROR: bad mle: ". Signed-off-by: Jiufei Xue Reviewed-by: Joseph Qi Cc: Mark Fasheh Cc: Joel Becker Cc: Junxiao Bi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- fs/ocfs2/dlm/dlmmaster.c | 26 +++++++++++++++----------- 1 file changed, 15 insertions(+), 11 deletions(-) diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c index 84f2f8079466..4e2162b355db 100644 --- a/fs/ocfs2/dlm/dlmmaster.c +++ b/fs/ocfs2/dlm/dlmmaster.c @@ -2519,6 +2519,11 @@ static int dlm_migrate_lockres(struct dlm_ctxt *dlm, spin_lock(&dlm->master_lock); ret = dlm_add_migration_mle(dlm, res, mle, &oldmle, name, namelen, target, dlm->node_num); + /* get an extra reference on the mle. + * otherwise the assert_master from the new + * master will destroy this. + */ + dlm_get_mle_inuse(mle); spin_unlock(&dlm->master_lock); spin_unlock(&dlm->spinlock); @@ -2554,6 +2559,7 @@ fail: if (mle_added) { dlm_mle_detach_hb_events(dlm, mle); dlm_put_mle(mle); + dlm_put_mle_inuse(mle); } else if (mle) { kmem_cache_free(dlm_mle_cache, mle); mle = NULL; @@ -2571,17 +2577,6 @@ fail: * ensure that all assert_master work is flushed. */ flush_workqueue(dlm->dlm_worker); - /* get an extra reference on the mle. - * otherwise the assert_master from the new - * master will destroy this. - * also, make sure that all callers of dlm_get_mle - * take both dlm->spinlock and dlm->master_lock */ - spin_lock(&dlm->spinlock); - spin_lock(&dlm->master_lock); - dlm_get_mle_inuse(mle); - spin_unlock(&dlm->master_lock); - spin_unlock(&dlm->spinlock); - /* notify new node and send all lock state */ /* call send_one_lockres with migration flag. * this serves as notice to the target node that a @@ -3312,6 +3307,15 @@ top: mle->new_master != dead_node) continue; + if (mle->new_master == dead_node && mle->inuse) { + mlog(ML_NOTICE, "%s: target %u died during " + "migration from %u, the MLE is " + "still keep used, ignore it!\n", + dlm->name, dead_node, + mle->master); + continue; + } + /* If we have reached this point, this mle needs to be * removed from the list and freed. */ dlm_clean_migration_mle(dlm, mle); From e6fe2687ef2727b687f31340da8edda25ed4e472 Mon Sep 17 00:00:00 2001 From: xuejiufei Date: Fri, 5 Feb 2016 15:36:47 -0800 Subject: [PATCH 079/325] ocfs2/dlm: clear refmap bit of recovery lock while doing local recovery cleanup commit c95a51807b730e4681e2ecbdfd669ca52601959e upstream. When recovery master down, dlm_do_local_recovery_cleanup() only remove the $RECOVERY lock owned by dead node, but do not clear the refmap bit. Which will make umount thread falling in dead loop migrating $RECOVERY to the dead node. Signed-off-by: xuejiufei Reviewed-by: Joseph Qi Cc: Mark Fasheh Cc: Joel Becker Cc: Junxiao Bi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- fs/ocfs2/dlm/dlmrecovery.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c index 9e4f862d20fe..42f0cae93a0a 100644 --- a/fs/ocfs2/dlm/dlmrecovery.c +++ b/fs/ocfs2/dlm/dlmrecovery.c @@ -2360,6 +2360,8 @@ static void dlm_do_local_recovery_cleanup(struct dlm_ctxt *dlm, u8 dead_node) break; } } + dlm_lockres_clear_refmap_bit(dlm, res, + dead_node); spin_unlock(&res->spinlock); continue; } From 1463df0fa8e286d50edd897a6f61eed999031e48 Mon Sep 17 00:00:00 2001 From: Uri Mashiach Date: Thu, 10 Dec 2015 15:12:56 +0200 Subject: [PATCH 080/325] wlcore/wl12xx: spi: fix oops on firmware load commit 9b2761cb72dc41e1948c8a5512b4efd384eda130 upstream. The maximum chunks used by the function is (SPI_AGGR_BUFFER_SIZE / WSPI_MAX_CHUNK_SIZE + 1). The original commands array had space for (SPI_AGGR_BUFFER_SIZE / WSPI_MAX_CHUNK_SIZE) commands. When the last chunk is used (len > 4 * WSPI_MAX_CHUNK_SIZE), the last command is stored outside the bounds of the commands array. Oops 5 (page fault) is generated during current wl1271 firmware load attempt: root@debian-armhf:~# ifconfig wlan0 up [ 294.312399] Unable to handle kernel paging request at virtual address 00203fc4 [ 294.320173] pgd = de528000 [ 294.323028] [00203fc4] *pgd=00000000 [ 294.326916] Internal error: Oops: 5 [#1] SMP ARM [ 294.331789] Modules linked in: bnep rfcomm bluetooth ipv6 arc4 wl12xx wlcore mac80211 musb_dsps cfg80211 musb_hdrc usbcore usb_common wlcore_spi omap_rng rng_core musb_am335x omap_wdt cpufreq_dt thermal_sys hwmon [ 294.351838] CPU: 0 PID: 1827 Comm: ifconfig Not tainted 4.2.0-00002-g3e9ad27-dirty #78 [ 294.360154] Hardware name: Generic AM33XX (Flattened Device Tree) [ 294.366557] task: dc9d6d40 ti: de550000 task.ti: de550000 [ 294.372236] PC is at __spi_validate+0xa8/0x2ac [ 294.376902] LR is at __spi_sync+0x78/0x210 [ 294.381200] pc : [] lr : [] psr: 60000013 [ 294.381200] sp : de551998 ip : de5519d8 fp : 00200000 [ 294.393242] r10: de551c8c r9 : de5519d8 r8 : de3a9000 [ 294.398730] r7 : de3a9258 r6 : de3a9400 r5 : de551a48 r4 : 00203fbc [ 294.405577] r3 : 00000000 r2 : 00000000 r1 : 00000000 r0 : de3a9000 [ 294.412420] Flags: nZCv IRQs on FIQs on Mode SVC_32 ISA ARM Segment user [ 294.419918] Control: 10c5387d Table: 9e528019 DAC: 00000015 [ 294.425954] Process ifconfig (pid: 1827, stack limit = 0xde550218) [ 294.432437] Stack: (0xde551998 to 0xde552000) ... [ 294.883613] [] (__spi_validate) from [] (__spi_sync+0x78/0x210) [ 294.891670] [] (__spi_sync) from [] (wl12xx_spi_raw_write+0xfc/0x148 [wlcore_spi]) [ 294.901661] [] (wl12xx_spi_raw_write [wlcore_spi]) from [] (wlcore_boot_upload_firmware+0x1ec/0x458 [wlcore]) [ 294.914038] [] (wlcore_boot_upload_firmware [wlcore]) from [] (wl12xx_boot+0xc10/0xfac [wl12xx]) [ 294.925161] [] (wl12xx_boot [wl12xx]) from [] (wl1271_op_add_interface+0x5b0/0x910 [wlcore]) [ 294.936364] [] (wl1271_op_add_interface [wlcore]) from [] (ieee80211_do_open+0x44c/0xf7c [mac80211]) [ 294.947963] [] (ieee80211_do_open [mac80211]) from [] (__dev_open+0xa8/0x110) [ 294.957307] [] (__dev_open) from [] (__dev_change_flags+0x88/0x148) [ 294.965713] [] (__dev_change_flags) from [] (dev_change_flags+0x18/0x48) [ 294.974576] [] (dev_change_flags) from [] (devinet_ioctl+0x6b4/0x7d0) [ 294.983191] [] (devinet_ioctl) from [] (sock_ioctl+0x1e4/0x2bc) [ 294.991244] [] (sock_ioctl) from [] (do_vfs_ioctl+0x420/0x6b0) [ 294.999208] [] (do_vfs_ioctl) from [] (SyS_ioctl+0x6c/0x7c) [ 295.006880] [] (SyS_ioctl) from [] (ret_fast_syscall+0x0/0x54) [ 295.014835] Code: e1550004 e2444034 0a00007d e5953018 (e5942008) [ 295.021544] ---[ end trace 66ed188198f4e24e ]--- Signed-off-by: Uri Mashiach Acked-by: Igor Grinberg Signed-off-by: Kalle Valo Signed-off-by: Greg Kroah-Hartman --- drivers/net/wireless/ti/wlcore/spi.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/drivers/net/wireless/ti/wlcore/spi.c b/drivers/net/wireless/ti/wlcore/spi.c index 236b41090827..44f059f7f34e 100644 --- a/drivers/net/wireless/ti/wlcore/spi.c +++ b/drivers/net/wireless/ti/wlcore/spi.c @@ -73,7 +73,10 @@ */ #define SPI_AGGR_BUFFER_SIZE (4 * PAGE_SIZE) -#define WSPI_MAX_NUM_OF_CHUNKS (SPI_AGGR_BUFFER_SIZE / WSPI_MAX_CHUNK_SIZE) +/* Maximum number of SPI write chunks */ +#define WSPI_MAX_NUM_OF_CHUNKS \ + ((SPI_AGGR_BUFFER_SIZE / WSPI_MAX_CHUNK_SIZE) + 1) + struct wl12xx_spi_glue { struct device *dev; @@ -268,9 +271,10 @@ static int __must_check wl12xx_spi_raw_write(struct device *child, int addr, void *buf, size_t len, bool fixed) { struct wl12xx_spi_glue *glue = dev_get_drvdata(child->parent); - struct spi_transfer t[2 * (WSPI_MAX_NUM_OF_CHUNKS + 1)]; + /* SPI write buffers - 2 for each chunk */ + struct spi_transfer t[2 * WSPI_MAX_NUM_OF_CHUNKS]; struct spi_message m; - u32 commands[WSPI_MAX_NUM_OF_CHUNKS]; + u32 commands[WSPI_MAX_NUM_OF_CHUNKS]; /* 1 command per chunk */ u32 *cmd; u32 chunk_len; int i; From c13c92acfa9b46470de819db0706e4457f503399 Mon Sep 17 00:00:00 2001 From: Uri Mashiach Date: Thu, 24 Dec 2015 16:05:00 +0200 Subject: [PATCH 081/325] wlcore/wl12xx: spi: fix NULL pointer dereference (Oops) commit e47301b06d5a65678690f04c2248fd181db1e59a upstream. Fix the below Oops when trying to modprobe wlcore_spi. The oops occurs because the wl1271_power_{off,on}() function doesn't check the power() function pointer. [ 23.401447] Unable to handle kernel NULL pointer dereference at virtual address 00000000 [ 23.409954] pgd = c0004000 [ 23.412922] [00000000] *pgd=00000000 [ 23.416693] Internal error: Oops: 80000007 [#1] SMP ARM [ 23.422168] Modules linked in: wl12xx wlcore mac80211 cfg80211 musb_dsps musb_hdrc usbcore usb_common snd_soc_simple_card evdev joydev omap_rng wlcore_spi snd_soc_tlv320aic23_i2c rng_core snd_soc_tlv320aic23 c_can_platform c_can can_dev snd_soc_davinci_mcasp snd_soc_edma snd_soc_omap omap_wdt musb_am335x cpufreq_dt thermal_sys hwmon [ 23.453253] CPU: 0 PID: 36 Comm: kworker/0:2 Not tainted 4.2.0-00002-g951efee-dirty #233 [ 23.461720] Hardware name: Generic AM33XX (Flattened Device Tree) [ 23.468123] Workqueue: events request_firmware_work_func [ 23.473690] task: de32efc0 ti: de4ee000 task.ti: de4ee000 [ 23.479341] PC is at 0x0 [ 23.482112] LR is at wl12xx_set_power_on+0x28/0x124 [wlcore] [ 23.488074] pc : [<00000000>] lr : [] psr: 60000013 [ 23.488074] sp : de4efe50 ip : 00000002 fp : 00000000 [ 23.500162] r10: de7cdd00 r9 : dc848800 r8 : bf27af00 [ 23.505663] r7 : bf27a1a8 r6 : dcbd8a80 r5 : dce0e2e0 r4 : dce0d2e0 [ 23.512536] r3 : 00000000 r2 : 00000000 r1 : 00000001 r0 : dc848810 [ 23.519412] Flags: nZCv IRQs on FIQs on Mode SVC_32 ISA ARM Segment kernel [ 23.527109] Control: 10c5387d Table: 9cb78019 DAC: 00000015 [ 23.533160] Process kworker/0:2 (pid: 36, stack limit = 0xde4ee218) [ 23.539760] Stack: (0xde4efe50 to 0xde4f0000) [...] [ 23.665030] [] (wl12xx_set_power_on [wlcore]) from [] (wlcore_nvs_cb+0x118/0xa4c [wlcore]) [ 23.675604] [] (wlcore_nvs_cb [wlcore]) from [] (request_firmware_work_func+0x30/0x58) [ 23.685784] [] (request_firmware_work_func) from [] (process_one_work+0x1b4/0x4b4) [ 23.695591] [] (process_one_work) from [] (worker_thread+0x3c/0x4a4) [ 23.704124] [] (worker_thread) from [] (kthread+0xd4/0xf0) [ 23.711747] [] (kthread) from [] (ret_from_fork+0x14/0x3c) [ 23.719357] Code: bad PC value [ 23.722760] ---[ end trace 981be8510db9b3a9 ]--- Prevent oops by validationg power() pointer value before calling the function. Signed-off-by: Uri Mashiach Acked-by: Igor Grinberg Signed-off-by: Kalle Valo Signed-off-by: Greg Kroah-Hartman --- drivers/net/wireless/ti/wlcore/io.h | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/drivers/net/wireless/ti/wlcore/io.h b/drivers/net/wireless/ti/wlcore/io.h index 0305729d0986..10cf3747694d 100644 --- a/drivers/net/wireless/ti/wlcore/io.h +++ b/drivers/net/wireless/ti/wlcore/io.h @@ -207,19 +207,23 @@ static inline int __must_check wlcore_write_reg(struct wl1271 *wl, int reg, static inline void wl1271_power_off(struct wl1271 *wl) { - int ret; + int ret = 0; if (!test_bit(WL1271_FLAG_GPIO_POWER, &wl->flags)) return; - ret = wl->if_ops->power(wl->dev, false); + if (wl->if_ops->power) + ret = wl->if_ops->power(wl->dev, false); if (!ret) clear_bit(WL1271_FLAG_GPIO_POWER, &wl->flags); } static inline int wl1271_power_on(struct wl1271 *wl) { - int ret = wl->if_ops->power(wl->dev, true); + int ret = 0; + + if (wl->if_ops->power) + ret = wl->if_ops->power(wl->dev, true); if (ret == 0) set_bit(WL1271_FLAG_GPIO_POWER, &wl->flags); From e18da11fc0f95979d14adc8e506707ed2fdab602 Mon Sep 17 00:00:00 2001 From: Brian Norris Date: Tue, 5 Jan 2016 10:39:45 -0800 Subject: [PATCH 082/325] mtd: nand: assign reasonable default name for NAND drivers commit f7a8e38f07a17be90758559fe66fe7337096053f upstream. Commits such as commit 853f1c58c4b2 ("mtd: nand: omap2: show parent device structure in sysfs") attempt to rely on the core MTD code to set the MTD name based on the parent device. However, nand_base tries to set a different default name according to the flash name (e.g., extracted from the ONFI parameter page), which means NAND drivers will never make use of the MTD defaults. This is not the intention of commit 853f1c58c4b2. This results in problems when trying to use the cmdline partition parser, since the MTD name is different than expected. Let's fix this by providing a default NAND name, where possible. Note that this is not really a great default name in the long run, since this means that if there are multiple MTDs attached to the same controller device, they will have the same name. But that is an existing issue and requires future work on a better controller vs. flash chip abstraction to fix properly. Fixes: 853f1c58c4b2 ("mtd: nand: omap2: show parent device structure in sysfs") Reported-by: Heiko Schocher Signed-off-by: Brian Norris Reviewed-by: Boris Brezillon Tested-by: Heiko Schocher Cc: Heiko Schocher Cc: Frans Klaver Signed-off-by: Greg Kroah-Hartman --- drivers/mtd/nand/nand_base.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/mtd/nand/nand_base.c b/drivers/mtd/nand/nand_base.c index ece544efccc3..3ff583f165cd 100644 --- a/drivers/mtd/nand/nand_base.c +++ b/drivers/mtd/nand/nand_base.c @@ -3995,6 +3995,9 @@ int nand_scan_ident(struct mtd_info *mtd, int maxchips, return ret; } + if (!mtd->name && mtd->dev.parent) + mtd->name = dev_name(mtd->dev.parent); + /* Set the default functions */ nand_set_defaults(chip, chip->options & NAND_BUSWIDTH_16); From ad53ae59587bcd110229d2594e059349b4306b6c Mon Sep 17 00:00:00 2001 From: Grygorii Strashko Date: Thu, 10 Dec 2015 21:18:20 +0200 Subject: [PATCH 083/325] PCI: host: Mark PCIe/PCI (MSI) IRQ cascade handlers as IRQF_NO_THREAD MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 8ff0ef996ca00028519c70e8d51d32bd37eb51dc upstream. On -RT and if kernel is booting with "threadirqs" cmd line parameter, PCIe/PCI (MSI) IRQ cascade handlers (like dra7xx_pcie_msi_irq_handler()) will be forced threaded and, as result, will generate warnings like this: WARNING: CPU: 1 PID: 82 at kernel/irq/handle.c:150 handle_irq_event_percpu+0x14c/0x174() irq 460 handler irq_default_primary_handler+0x0/0x14 enabled interrupts Backtrace: (warn_slowpath_common) from (warn_slowpath_fmt+0x38/0x40) (warn_slowpath_fmt) from (handle_irq_event_percpu+0x14c/0x174) (handle_irq_event_percpu) from (handle_irq_event+0x84/0xb8) (handle_irq_event) from (handle_simple_irq+0x90/0x118) (handle_simple_irq) from (generic_handle_irq+0x30/0x44) (generic_handle_irq) from (dra7xx_pcie_msi_irq_handler+0x7c/0x8c) (dra7xx_pcie_msi_irq_handler) from (irq_forced_thread_fn+0x28/0x5c) (irq_forced_thread_fn) from (irq_thread+0x128/0x204) This happens because all of them invoke generic_handle_irq() from the requested handler. generic_handle_irq() grabs raw_locks and thus needs to run in raw-IRQ context. This issue was originally reproduced on TI dra7-evem, but, as was identified during discussion [1], other hosts can also suffer from this issue. Fix all them at once by marking PCIe/PCI (MSI) IRQ cascade handlers IRQF_NO_THREAD explicitly. [1] http://lkml.kernel.org/r/1448027966-21610-1-git-send-email-grygorii.strashko@ti.com [bhelgaas: add stable tag, fix typos] Signed-off-by: Grygorii Strashko Signed-off-by: Bjorn Helgaas Acked-by: Lucas Stach CC: Kishon Vijay Abraham I CC: Jingoo Han CC: Kukjin Kim CC: Krzysztof Kozlowski CC: Richard Zhu CC: Thierry Reding CC: Stephen Warren CC: Alexandre Courbot CC: Simon Horman CC: Pratyush Anand CC: Michal Simek CC: "Sören Brinkmann" CC: Sebastian Andrzej Siewior Signed-off-by: Greg Kroah-Hartman --- drivers/pci/host/pci-dra7xx.c | 3 ++- drivers/pci/host/pci-exynos.c | 3 ++- drivers/pci/host/pci-imx6.c | 3 ++- drivers/pci/host/pci-tegra.c | 2 +- drivers/pci/host/pcie-rcar.c | 6 ++++-- drivers/pci/host/pcie-spear13xx.c | 3 ++- drivers/pci/host/pcie-xilinx.c | 3 ++- 7 files changed, 15 insertions(+), 8 deletions(-) diff --git a/drivers/pci/host/pci-dra7xx.c b/drivers/pci/host/pci-dra7xx.c index 8c3688046c02..923607bdabc5 100644 --- a/drivers/pci/host/pci-dra7xx.c +++ b/drivers/pci/host/pci-dra7xx.c @@ -302,7 +302,8 @@ static int __init dra7xx_add_pcie_port(struct dra7xx_pcie *dra7xx, } ret = devm_request_irq(&pdev->dev, pp->irq, - dra7xx_pcie_msi_irq_handler, IRQF_SHARED, + dra7xx_pcie_msi_irq_handler, + IRQF_SHARED | IRQF_NO_THREAD, "dra7-pcie-msi", pp); if (ret) { dev_err(&pdev->dev, "failed to request irq\n"); diff --git a/drivers/pci/host/pci-exynos.c b/drivers/pci/host/pci-exynos.c index 01095e1160a4..d997d22d4231 100644 --- a/drivers/pci/host/pci-exynos.c +++ b/drivers/pci/host/pci-exynos.c @@ -522,7 +522,8 @@ static int __init exynos_add_pcie_port(struct pcie_port *pp, ret = devm_request_irq(&pdev->dev, pp->msi_irq, exynos_pcie_msi_irq_handler, - IRQF_SHARED, "exynos-pcie", pp); + IRQF_SHARED | IRQF_NO_THREAD, + "exynos-pcie", pp); if (ret) { dev_err(&pdev->dev, "failed to request msi irq\n"); return ret; diff --git a/drivers/pci/host/pci-imx6.c b/drivers/pci/host/pci-imx6.c index 22e8224126fd..9ce7cd148c86 100644 --- a/drivers/pci/host/pci-imx6.c +++ b/drivers/pci/host/pci-imx6.c @@ -537,7 +537,8 @@ static int __init imx6_add_pcie_port(struct pcie_port *pp, ret = devm_request_irq(&pdev->dev, pp->msi_irq, imx6_pcie_msi_handler, - IRQF_SHARED, "mx6-pcie-msi", pp); + IRQF_SHARED | IRQF_NO_THREAD, + "mx6-pcie-msi", pp); if (ret) { dev_err(&pdev->dev, "failed to request MSI irq\n"); return ret; diff --git a/drivers/pci/host/pci-tegra.c b/drivers/pci/host/pci-tegra.c index 3018ae52e092..30323114c53c 100644 --- a/drivers/pci/host/pci-tegra.c +++ b/drivers/pci/host/pci-tegra.c @@ -1288,7 +1288,7 @@ static int tegra_pcie_enable_msi(struct tegra_pcie *pcie) msi->irq = err; - err = request_irq(msi->irq, tegra_pcie_msi_irq, 0, + err = request_irq(msi->irq, tegra_pcie_msi_irq, IRQF_NO_THREAD, tegra_msi_irq_chip.name, pcie); if (err < 0) { dev_err(&pdev->dev, "failed to request IRQ: %d\n", err); diff --git a/drivers/pci/host/pcie-rcar.c b/drivers/pci/host/pcie-rcar.c index f4fa6c537448..414c33686621 100644 --- a/drivers/pci/host/pcie-rcar.c +++ b/drivers/pci/host/pcie-rcar.c @@ -720,14 +720,16 @@ static int rcar_pcie_enable_msi(struct rcar_pcie *pcie) /* Two irqs are for MSI, but they are also used for non-MSI irqs */ err = devm_request_irq(&pdev->dev, msi->irq1, rcar_pcie_msi_irq, - IRQF_SHARED, rcar_msi_irq_chip.name, pcie); + IRQF_SHARED | IRQF_NO_THREAD, + rcar_msi_irq_chip.name, pcie); if (err < 0) { dev_err(&pdev->dev, "failed to request IRQ: %d\n", err); goto err; } err = devm_request_irq(&pdev->dev, msi->irq2, rcar_pcie_msi_irq, - IRQF_SHARED, rcar_msi_irq_chip.name, pcie); + IRQF_SHARED | IRQF_NO_THREAD, + rcar_msi_irq_chip.name, pcie); if (err < 0) { dev_err(&pdev->dev, "failed to request IRQ: %d\n", err); goto err; diff --git a/drivers/pci/host/pcie-spear13xx.c b/drivers/pci/host/pcie-spear13xx.c index b95b7563c052..a6cd8233e8c0 100644 --- a/drivers/pci/host/pcie-spear13xx.c +++ b/drivers/pci/host/pcie-spear13xx.c @@ -279,7 +279,8 @@ static int spear13xx_add_pcie_port(struct pcie_port *pp, return -ENODEV; } ret = devm_request_irq(dev, pp->irq, spear13xx_pcie_irq_handler, - IRQF_SHARED, "spear1340-pcie", pp); + IRQF_SHARED | IRQF_NO_THREAD, + "spear1340-pcie", pp); if (ret) { dev_err(dev, "failed to request irq %d\n", pp->irq); return ret; diff --git a/drivers/pci/host/pcie-xilinx.c b/drivers/pci/host/pcie-xilinx.c index 3c7a0d580b1e..4cfa46360d12 100644 --- a/drivers/pci/host/pcie-xilinx.c +++ b/drivers/pci/host/pcie-xilinx.c @@ -781,7 +781,8 @@ static int xilinx_pcie_parse_dt(struct xilinx_pcie_port *port) port->irq = irq_of_parse_and_map(node, 0); err = devm_request_irq(dev, port->irq, xilinx_pcie_intr_handler, - IRQF_SHARED, "xilinx-pcie", port); + IRQF_SHARED | IRQF_NO_THREAD, + "xilinx-pcie", port); if (err) { dev_err(dev, "unable to request irq %d\n", port->irq); return err; From 695f6c8798c6c4a0be6df79082e9890b22af4d8b Mon Sep 17 00:00:00 2001 From: Christoph Biedl Date: Wed, 23 Dec 2015 16:51:57 +0100 Subject: [PATCH 084/325] PCI: Fix minimum allocation address overwrite commit 3460baa620685c20f5ee19afb6d99d26150c382c upstream. Commit 36e097a8a297 ("PCI: Split out bridge window override of minimum allocation address") claimed to do no functional changes but unfortunately did: The "min" variable is altered. At least the AVM A1 PCMCIA adapter was no longer detected, breaking ISDN operation. Use a local copy of "min" to restore the previous behaviour. [bhelgaas: avoid gcc "?:" extension for portability and readability] Fixes: 36e097a8a297 ("PCI: Split out bridge window override of minimum allocation address") Signed-off-by: Christoph Biedl Signed-off-by: Bjorn Helgaas Signed-off-by: Greg Kroah-Hartman --- drivers/pci/bus.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c index d3346d23963b..89b3befc7155 100644 --- a/drivers/pci/bus.c +++ b/drivers/pci/bus.c @@ -140,6 +140,8 @@ static int pci_bus_alloc_from_region(struct pci_bus *bus, struct resource *res, type_mask |= IORESOURCE_TYPE_BITS; pci_bus_for_each_resource(bus, r, i) { + resource_size_t min_used = min; + if (!r) continue; @@ -163,12 +165,12 @@ static int pci_bus_alloc_from_region(struct pci_bus *bus, struct resource *res, * overrides "min". */ if (avail.start) - min = avail.start; + min_used = avail.start; max = avail.end; /* Ok, try it out.. */ - ret = allocate_resource(r, res, size, min, max, + ret = allocate_resource(r, res, size, min_used, max, align, alignf, alignf_data); if (ret == 0) return 0; From cc6d98006b1a713abaa8852de02a3c6f7ce62941 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Wed, 13 Jan 2016 15:48:54 -0500 Subject: [PATCH 085/325] tracing: Fix stacktrace skip depth in trace_buffer_unlock_commit_regs() commit 7717c6be699975f6733d278b13b7c4295d73caf6 upstream. While cleaning the stacktrace code I unintentially changed the skip depth of trace_buffer_unlock_commit_regs() from 0 to 6. kprobes uses this function, and with skipping 6 call backs, it can easily produce no stack. Here's how I tested it: # echo 'p:ext4_sync_fs ext4_sync_fs ' > /sys/kernel/debug/tracing/kprobe_events # echo 1 > /sys/kernel/debug/tracing/events/kprobes/enable # cat /sys/kernel/debug/trace sync-2394 [005] 502.457060: ext4_sync_fs: (ffffffff81317650) sync-2394 [005] 502.457063: kernel_stack: sync-2394 [005] 502.457086: ext4_sync_fs: (ffffffff81317650) sync-2394 [005] 502.457087: kernel_stack: sync-2394 [005] 502.457091: ext4_sync_fs: (ffffffff81317650) After putting back the skip stack to zero, we have: sync-2270 [000] 748.052693: ext4_sync_fs: (ffffffff81317650) sync-2270 [000] 748.052695: kernel_stack: => iterate_supers (ffffffff8126412e) => sys_sync (ffffffff8129c4b6) => entry_SYSCALL_64_fastpath (ffffffff8181f0b2) sync-2270 [000] 748.053017: ext4_sync_fs: (ffffffff81317650) sync-2270 [000] 748.053019: kernel_stack: => iterate_supers (ffffffff8126412e) => sys_sync (ffffffff8129c4b6) => entry_SYSCALL_64_fastpath (ffffffff8181f0b2) sync-2270 [000] 748.053381: ext4_sync_fs: (ffffffff81317650) sync-2270 [000] 748.053383: kernel_stack: => iterate_supers (ffffffff8126412e) => sys_sync (ffffffff8129c4b6) => entry_SYSCALL_64_fastpath (ffffffff8181f0b2) Fixes: 73dddbb57bb0 "tracing: Only create stacktrace option when STACKTRACE is configured" Reported-by: Brendan Gregg Tested-by: Brendan Gregg Signed-off-by: Steven Rostedt Signed-off-by: Greg Kroah-Hartman --- kernel/trace/trace.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 87fb9801bd9e..d9293402ee68 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1751,7 +1751,7 @@ void trace_buffer_unlock_commit_regs(struct trace_array *tr, { __buffer_unlock_commit(buffer, event); - ftrace_trace_stack(tr, buffer, flags, 6, pc, regs); + ftrace_trace_stack(tr, buffer, flags, 0, pc, regs); ftrace_trace_userstack(buffer, flags, pc); } EXPORT_SYMBOL_GPL(trace_buffer_unlock_commit_regs); From bf46aa7ec7417cab8b4402dc8117e17af54f5d8e Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 29 Jan 2016 10:22:41 -0500 Subject: [PATCH 086/325] tracing/stacktrace: Show entire trace if passed in function not found commit 6ccd83714a009ee301b50c15f6c3a5dc1f30164c upstream. When a max stack trace is discovered, the stack dump is saved. In order to not record the overhead of the stack tracer, the ip of the traced function is looked for within the dump. The trace is started from the location of that function. But if for some reason the ip is not found, the entire stack trace is then truncated. That's not very useful. Instead, print everything if the ip of the traced function is not found within the trace. This issue showed up on s390. Link: http://lkml.kernel.org/r/20160129102241.1b3c9c04@gandalf.local.home Fixes: 72ac426a5bb0 ("tracing: Clean up stack tracing and fix fentry updates") Reported-by: Heiko Carstens Tested-by: Heiko Carstens Signed-off-by: Steven Rostedt Signed-off-by: Greg Kroah-Hartman --- kernel/trace/trace_stack.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index dda9e6742950..202df6cffcca 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -125,6 +125,13 @@ check_stack(unsigned long ip, unsigned long *stack) break; } + /* + * Some archs may not have the passed in ip in the dump. + * If that happens, we need to show everything. + */ + if (i == stack_trace_max.nr_entries) + i = 0; + /* * Now find where in the stack these are. */ From a623f87a72de35096a9eae7cc7764d0c9533c2e9 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 15 Jan 2016 16:58:24 -0800 Subject: [PATCH 087/325] printk: do cond_resched() between lines while outputting to consoles commit 8d91f8b15361dfb438ab6eb3b319e2ded43458ff upstream. @console_may_schedule tracks whether console_sem was acquired through lock or trylock. If the former, we're inside a sleepable context and console_conditional_schedule() performs cond_resched(). This allows console drivers which use console_lock for synchronization to yield while performing time-consuming operations such as scrolling. However, the actual console outputting is performed while holding irq-safe logbuf_lock, so console_unlock() clears @console_may_schedule before starting outputting lines. Also, only a few drivers call console_conditional_schedule() to begin with. This means that when a lot of lines need to be output by console_unlock(), for example on a console registration, the task doing console_unlock() may not yield for a long time on a non-preemptible kernel. If this happens with a slow console devices, for example a serial console, the outputting task may occupy the cpu for a very long time. Long enough to trigger softlockup and/or RCU stall warnings, which in turn pile more messages, sometimes enough to trigger the next cycle of warnings incapacitating the system. Fix it by making console_unlock() insert cond_resched() between lines if @console_may_schedule. Signed-off-by: Tejun Heo Reported-by: Calvin Owens Acked-by: Jan Kara Cc: Dave Jones Cc: Kyle McMartin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- include/linux/console.h | 1 + kernel/panic.c | 3 +-- kernel/printk/printk.c | 35 ++++++++++++++++++++++++++++++++++- 3 files changed, 36 insertions(+), 3 deletions(-) diff --git a/include/linux/console.h b/include/linux/console.h index bd194343c346..ea731af2451e 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -150,6 +150,7 @@ extern int console_trylock(void); extern void console_unlock(void); extern void console_conditional_schedule(void); extern void console_unblank(void); +extern void console_flush_on_panic(void); extern struct tty_driver *console_device(int *); extern void console_stop(struct console *); extern void console_start(struct console *); diff --git a/kernel/panic.c b/kernel/panic.c index 4b150bc0c6c1..41e2b54f36b5 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -157,8 +157,7 @@ void panic(const char *fmt, ...) * panic() is not being callled from OOPS. */ debug_locks_off(); - console_trylock(); - console_unlock(); + console_flush_on_panic(); if (!panic_blink) panic_blink = no_blink; diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 2ce8826f1053..c048e34b177f 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -2233,13 +2233,24 @@ void console_unlock(void) static u64 seen_seq; unsigned long flags; bool wake_klogd = false; - bool retry; + bool do_cond_resched, retry; if (console_suspended) { up_console_sem(); return; } + /* + * Console drivers are called under logbuf_lock, so + * @console_may_schedule should be cleared before; however, we may + * end up dumping a lot of lines, for example, if called from + * console registration path, and should invoke cond_resched() + * between lines if allowable. Not doing so can cause a very long + * scheduling stall on a slow console leading to RCU stall and + * softlockup warnings which exacerbate the issue with more + * messages practically incapacitating the system. + */ + do_cond_resched = console_may_schedule; console_may_schedule = 0; /* flush buffered message fragment immediately to console */ @@ -2311,6 +2322,9 @@ skip: call_console_drivers(level, ext_text, ext_len, text, len); start_critical_timings(); local_irq_restore(flags); + + if (do_cond_resched) + cond_resched(); } console_locked = 0; @@ -2378,6 +2392,25 @@ void console_unblank(void) console_unlock(); } +/** + * console_flush_on_panic - flush console content on panic + * + * Immediately output all pending messages no matter what. + */ +void console_flush_on_panic(void) +{ + /* + * If someone else is holding the console lock, trylock will fail + * and may_schedule may be set. Ignore and proceed to unlock so + * that messages are flushed out. As this can be called from any + * context and we don't want to get preempted while flushing, + * ensure may_schedule is cleared. + */ + console_trylock(); + console_may_schedule = 0; + console_unlock(); +} + /* * Return the console tty driver structure and its associated index */ From 583097a3b2cef0bee535c8acc4189ceacb8bb6c6 Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Thu, 26 Nov 2015 21:14:02 +0100 Subject: [PATCH 088/325] parisc: Protect huge page pte changes with spinlocks commit b0e551313ebde17764f3a5ed273df524d1e7e690 upstream. PA-RISC doesn't have atomic instructions to modify page table entries, so it takes spinlock in the TLB handler and modifies the page table entry non-atomically. If you modify the page table entry without the spinlock, you may race with TLB handler on another CPU and your modification may be lost. Protect against that with usage of purge_tlb_start() and purge_tlb_end() which handles the TLB spinlock. Signed-off-by: Helge Deller Signed-off-by: Greg Kroah-Hartman --- arch/parisc/include/asm/hugetlb.h | 20 +++-------- arch/parisc/mm/hugetlbpage.c | 60 ++++++++++++++++++++++++------- 2 files changed, 52 insertions(+), 28 deletions(-) diff --git a/arch/parisc/include/asm/hugetlb.h b/arch/parisc/include/asm/hugetlb.h index 7d56a9ccb752..a65d888716c4 100644 --- a/arch/parisc/include/asm/hugetlb.h +++ b/arch/parisc/include/asm/hugetlb.h @@ -54,24 +54,12 @@ static inline pte_t huge_pte_wrprotect(pte_t pte) return pte_wrprotect(pte); } -static inline void huge_ptep_set_wrprotect(struct mm_struct *mm, - unsigned long addr, pte_t *ptep) -{ - pte_t old_pte = *ptep; - set_huge_pte_at(mm, addr, ptep, pte_wrprotect(old_pte)); -} +void huge_ptep_set_wrprotect(struct mm_struct *mm, + unsigned long addr, pte_t *ptep); -static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma, +int huge_ptep_set_access_flags(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, - pte_t pte, int dirty) -{ - int changed = !pte_same(*ptep, pte); - if (changed) { - set_huge_pte_at(vma->vm_mm, addr, ptep, pte); - flush_tlb_page(vma, addr); - } - return changed; -} + pte_t pte, int dirty); static inline pte_t huge_ptep_get(pte_t *ptep) { diff --git a/arch/parisc/mm/hugetlbpage.c b/arch/parisc/mm/hugetlbpage.c index f6fdc77a72bd..54ba39262b82 100644 --- a/arch/parisc/mm/hugetlbpage.c +++ b/arch/parisc/mm/hugetlbpage.c @@ -105,15 +105,13 @@ static inline void purge_tlb_entries_huge(struct mm_struct *mm, unsigned long ad addr |= _HUGE_PAGE_SIZE_ENCODING_DEFAULT; for (i = 0; i < (1 << (HPAGE_SHIFT-REAL_HPAGE_SHIFT)); i++) { - mtsp(mm->context, 1); - pdtlb(addr); - if (unlikely(split_tlb)) - pitlb(addr); + purge_tlb_entries(mm, addr); addr += (1UL << REAL_HPAGE_SHIFT); } } -void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, +/* __set_huge_pte_at() must be called holding the pa_tlb_lock. */ +static void __set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t entry) { unsigned long addr_start; @@ -123,14 +121,9 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, addr_start = addr; for (i = 0; i < (1 << HUGETLB_PAGE_ORDER); i++) { - /* Directly write pte entry. We could call set_pte_at(mm, addr, ptep, entry) - * instead, but then we get double locking on pa_tlb_lock. */ - *ptep = entry; + set_pte(ptep, entry); ptep++; - /* Drop the PAGE_SIZE/non-huge tlb entry */ - purge_tlb_entries(mm, addr); - addr += PAGE_SIZE; pte_val(entry) += PAGE_SIZE; } @@ -138,18 +131,61 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, purge_tlb_entries_huge(mm, addr_start); } +void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t entry) +{ + unsigned long flags; + + purge_tlb_start(flags); + __set_huge_pte_at(mm, addr, ptep, entry); + purge_tlb_end(flags); +} + pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { + unsigned long flags; pte_t entry; + purge_tlb_start(flags); entry = *ptep; - set_huge_pte_at(mm, addr, ptep, __pte(0)); + __set_huge_pte_at(mm, addr, ptep, __pte(0)); + purge_tlb_end(flags); return entry; } + +void huge_ptep_set_wrprotect(struct mm_struct *mm, + unsigned long addr, pte_t *ptep) +{ + unsigned long flags; + pte_t old_pte; + + purge_tlb_start(flags); + old_pte = *ptep; + __set_huge_pte_at(mm, addr, ptep, pte_wrprotect(old_pte)); + purge_tlb_end(flags); +} + +int huge_ptep_set_access_flags(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + pte_t pte, int dirty) +{ + unsigned long flags; + int changed; + + purge_tlb_start(flags); + changed = !pte_same(*ptep, pte); + if (changed) { + __set_huge_pte_at(vma->vm_mm, addr, ptep, pte); + } + purge_tlb_end(flags); + return changed; +} + + int pmd_huge(pmd_t pmd) { return 0; From 702ea6de7132e65ca41e8055a02910a695b447e7 Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Sun, 10 Jan 2016 09:30:42 +0100 Subject: [PATCH 089/325] parisc: Fix __ARCH_SI_PREAMBLE_SIZE commit e60fc5aa608eb38b47ba4ee058f306f739eb70a0 upstream. On a 64bit kernel build the compiler aligns the _sifields union in the struct siginfo_t on a 64bit address. The __ARCH_SI_PREAMBLE_SIZE define compensates for this alignment and thus fixes the wait testcase of the strace package. The symptoms of a wrong __ARCH_SI_PREAMBLE_SIZE value is that _sigchld.si_stime variable is missed to be copied and thus after a copy_siginfo() will have uninitialized values. Signed-off-by: Helge Deller Signed-off-by: Greg Kroah-Hartman --- arch/parisc/include/uapi/asm/siginfo.h | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/parisc/include/uapi/asm/siginfo.h b/arch/parisc/include/uapi/asm/siginfo.h index d7034728f377..1c75565d984b 100644 --- a/arch/parisc/include/uapi/asm/siginfo.h +++ b/arch/parisc/include/uapi/asm/siginfo.h @@ -1,6 +1,10 @@ #ifndef _PARISC_SIGINFO_H #define _PARISC_SIGINFO_H +#if defined(__LP64__) +#define __ARCH_SI_PREAMBLE_SIZE (4 * sizeof(int)) +#endif + #include #undef NSIGTRAP From 3809abbacf588dc2fa020a984ddf13d9ab71e752 Mon Sep 17 00:00:00 2001 From: Javier Martinez Canillas Date: Wed, 27 Jan 2016 12:03:23 -0200 Subject: [PATCH 090/325] media: i2c: Don't export ir-kbd-i2c module alias commit 329d88da4df9a96da43018aceabd3a06e6a7e7ae upstream. This is a partial revert of commit ed8d1cf07cb16d ("[media] Export I2C module alias information in missing drivers") that exported the module aliases for the I2C drivers that were missing to make autoload to work. But there is a bug report [0] that auto load of the ir-kbd-i2c driver cause the Hauppauge HD-PVR driver to not behave correctly. This is a hdpvr latent bug that was just exposed by ir-kbd-i2c module autoloading working and will also happen if the I2C driver is built-in or a user calls modprobe to load the module and register the driver. But there is a regression experimented by users so until the real bug is fixed, let's not export the module alias for the ir-kbd-i2c driver even when this just masks the actual issue. [0]: https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=810726 Fixes: ed8d1cf07cb1 ("[media] Export I2C module alias information in missing drivers") Signed-off-by: Javier Martinez Canillas Signed-off-by: Greg Kroah-Hartman --- drivers/media/i2c/ir-kbd-i2c.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/media/i2c/ir-kbd-i2c.c b/drivers/media/i2c/ir-kbd-i2c.c index 728d2cc8a3e7..175a76114953 100644 --- a/drivers/media/i2c/ir-kbd-i2c.c +++ b/drivers/media/i2c/ir-kbd-i2c.c @@ -478,7 +478,6 @@ static const struct i2c_device_id ir_kbd_id[] = { { "ir_rx_z8f0811_hdpvr", 0 }, { } }; -MODULE_DEVICE_TABLE(i2c, ir_kbd_id); static struct i2c_driver ir_kbd_driver = { .driver = { From 2c4b95da2335088ba85dcdfa39d374491d76fbba Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Wed, 13 Jan 2016 16:00:07 -0800 Subject: [PATCH 091/325] md/raid: only permit hot-add of compatible integrity profiles commit 1501efadc524a0c99494b576923091589a52d2a4 upstream. It is not safe for an integrity profile to be changed while i/o is in-flight in the queue. Prevent adding new disks or otherwise online spares to an array if the device has an incompatible integrity profile. The original change to the blk_integrity_unregister implementation in md, commmit c7bfced9a671 "md: suspend i/o during runtime blk_integrity_unregister" introduced an immediate hang regression. This policy of disallowing changes the integrity profile once one has been established is shared with DM. Here is an abbreviated log from a test run that: 1/ Creates a degraded raid1 with an integrity-enabled device (pmem0s) [ 59.076127] 2/ Tries to add an integrity-disabled device (pmem1m) [ 90.489209] 3/ Retries with an integrity-enabled device (pmem1s) [ 205.671277] [ 59.076127] md/raid1:md0: active with 1 out of 2 mirrors [ 59.078302] md: data integrity enabled on md0 [..] [ 90.489209] md0: incompatible integrity profile for pmem1m [..] [ 205.671277] md: super_written gets error=-5 [ 205.677386] md/raid1:md0: Disk failure on pmem1m, disabling device. [ 205.677386] md/raid1:md0: Operation continuing on 1 devices. [ 205.683037] RAID1 conf printout: [ 205.684699] --- wd:1 rd:2 [ 205.685972] disk 0, wo:0, o:1, dev:pmem0s [ 205.687562] disk 1, wo:1, o:1, dev:pmem1s [ 205.691717] md: recovery of RAID array md0 Fixes: c7bfced9a671 ("md: suspend i/o during runtime blk_integrity_unregister") Cc: Mike Snitzer Reported-by: NeilBrown Signed-off-by: Dan Williams Signed-off-by: NeilBrown Signed-off-by: Greg Kroah-Hartman --- drivers/md/md.c | 28 ++++++++++++++++------------ drivers/md/md.h | 2 +- drivers/md/multipath.c | 6 +++--- drivers/md/raid1.c | 6 +++--- drivers/md/raid10.c | 6 +++--- 5 files changed, 26 insertions(+), 22 deletions(-) diff --git a/drivers/md/md.c b/drivers/md/md.c index 61aacab424cf..b1e1f6b95782 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -2017,28 +2017,32 @@ int md_integrity_register(struct mddev *mddev) } EXPORT_SYMBOL(md_integrity_register); -/* Disable data integrity if non-capable/non-matching disk is being added */ -void md_integrity_add_rdev(struct md_rdev *rdev, struct mddev *mddev) +/* + * Attempt to add an rdev, but only if it is consistent with the current + * integrity profile + */ +int md_integrity_add_rdev(struct md_rdev *rdev, struct mddev *mddev) { struct blk_integrity *bi_rdev; struct blk_integrity *bi_mddev; + char name[BDEVNAME_SIZE]; if (!mddev->gendisk) - return; + return 0; bi_rdev = bdev_get_integrity(rdev->bdev); bi_mddev = blk_get_integrity(mddev->gendisk); if (!bi_mddev) /* nothing to do */ - return; - if (rdev->raid_disk < 0) /* skip spares */ - return; - if (bi_rdev && blk_integrity_compare(mddev->gendisk, - rdev->bdev->bd_disk) >= 0) - return; - WARN_ON_ONCE(!mddev->suspended); - printk(KERN_NOTICE "disabling data integrity on %s\n", mdname(mddev)); - blk_integrity_unregister(mddev->gendisk); + return 0; + + if (blk_integrity_compare(mddev->gendisk, rdev->bdev->bd_disk) != 0) { + printk(KERN_NOTICE "%s: incompatible integrity profile for %s\n", + mdname(mddev), bdevname(rdev->bdev, name)); + return -ENXIO; + } + + return 0; } EXPORT_SYMBOL(md_integrity_add_rdev); diff --git a/drivers/md/md.h b/drivers/md/md.h index ca0b643fe3c1..dfa57b41541b 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -657,7 +657,7 @@ extern void md_wait_for_blocked_rdev(struct md_rdev *rdev, struct mddev *mddev); extern void md_set_array_sectors(struct mddev *mddev, sector_t array_sectors); extern int md_check_no_bitmap(struct mddev *mddev); extern int md_integrity_register(struct mddev *mddev); -extern void md_integrity_add_rdev(struct md_rdev *rdev, struct mddev *mddev); +extern int md_integrity_add_rdev(struct md_rdev *rdev, struct mddev *mddev); extern int strict_strtoul_scaled(const char *cp, unsigned long *res, int scale); extern void mddev_init(struct mddev *mddev); diff --git a/drivers/md/multipath.c b/drivers/md/multipath.c index 7331a80d89f1..0a72ab6e6c20 100644 --- a/drivers/md/multipath.c +++ b/drivers/md/multipath.c @@ -257,6 +257,9 @@ static int multipath_add_disk(struct mddev *mddev, struct md_rdev *rdev) disk_stack_limits(mddev->gendisk, rdev->bdev, rdev->data_offset << 9); + err = md_integrity_add_rdev(rdev, mddev); + if (err) + break; spin_lock_irq(&conf->device_lock); mddev->degraded--; rdev->raid_disk = path; @@ -264,9 +267,6 @@ static int multipath_add_disk(struct mddev *mddev, struct md_rdev *rdev) spin_unlock_irq(&conf->device_lock); rcu_assign_pointer(p->rdev, rdev); err = 0; - mddev_suspend(mddev); - md_integrity_add_rdev(rdev, mddev); - mddev_resume(mddev); break; } diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index e2169ff6e0f0..c4b913409226 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -1589,6 +1589,9 @@ static int raid1_add_disk(struct mddev *mddev, struct md_rdev *rdev) if (mddev->recovery_disabled == conf->recovery_disabled) return -EBUSY; + if (md_integrity_add_rdev(rdev, mddev)) + return -ENXIO; + if (rdev->raid_disk >= 0) first = last = rdev->raid_disk; @@ -1632,9 +1635,6 @@ static int raid1_add_disk(struct mddev *mddev, struct md_rdev *rdev) break; } } - mddev_suspend(mddev); - md_integrity_add_rdev(rdev, mddev); - mddev_resume(mddev); if (mddev->queue && blk_queue_discard(bdev_get_queue(rdev->bdev))) queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, mddev->queue); print_conf(conf); diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 84e597e1c489..ce959b4ae4df 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -1698,6 +1698,9 @@ static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev) if (rdev->saved_raid_disk < 0 && !_enough(conf, 1, -1)) return -EINVAL; + if (md_integrity_add_rdev(rdev, mddev)) + return -ENXIO; + if (rdev->raid_disk >= 0) first = last = rdev->raid_disk; @@ -1739,9 +1742,6 @@ static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev) rcu_assign_pointer(p->rdev, rdev); break; } - mddev_suspend(mddev); - md_integrity_add_rdev(rdev, mddev); - mddev_resume(mddev); if (mddev->queue && blk_queue_discard(bdev_get_queue(rdev->bdev))) queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, mddev->queue); From dd0d511548ea1ad8f233e9fa4a4acfb83af9bd29 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 14 Jan 2016 16:54:46 +0000 Subject: [PATCH 092/325] hrtimer: Handle remaining time proper for TIME_LOW_RES commit 203cbf77de59fc8f13502dcfd11350c6d4a5c95f upstream. If CONFIG_TIME_LOW_RES is enabled we add a jiffie to the relative timeout to prevent short sleeps, but we do not account for that in interfaces which retrieve the remaining time. Helge observed that timerfd can return a remaining time larger than the relative timeout. That's not expected and breaks userland test programs. Store the information that the timer was armed relative and provide functions to adjust the remaining time. To avoid bloating the hrtimer struct make state a u8, which as a bonus results in better code on x86 at least. Reported-and-tested-by: Helge Deller Signed-off-by: Thomas Gleixner Cc: Peter Zijlstra Cc: John Stultz Cc: linux-m68k@lists.linux-m68k.org Cc: dhowells@redhat.com Link: http://lkml.kernel.org/r/20160114164159.273328486@linutronix.de Signed-off-by: Thomas Gleixner Signed-off-by: Greg Kroah-Hartman --- include/linux/hrtimer.h | 34 ++++++++++++++++++++++--- kernel/time/hrtimer.c | 55 +++++++++++++++++++++++++++------------- kernel/time/timer_list.c | 2 +- 3 files changed, 69 insertions(+), 22 deletions(-) diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index 76dd4f0da5ca..2ead22dd74a0 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -87,7 +87,8 @@ enum hrtimer_restart { * @function: timer expiry callback function * @base: pointer to the timer base (per cpu and per clock) * @state: state information (See bit values above) - * @start_pid: timer statistics field to store the pid of the task which + * @is_rel: Set if the timer was armed relative + * @start_pid: timer statistics field to store the pid of the task which * started the timer * @start_site: timer statistics field to store the site where the timer * was started @@ -101,7 +102,8 @@ struct hrtimer { ktime_t _softexpires; enum hrtimer_restart (*function)(struct hrtimer *); struct hrtimer_clock_base *base; - unsigned long state; + u8 state; + u8 is_rel; #ifdef CONFIG_TIMER_STATS int start_pid; void *start_site; @@ -321,6 +323,27 @@ static inline void clock_was_set_delayed(void) { } #endif +static inline ktime_t +__hrtimer_expires_remaining_adjusted(const struct hrtimer *timer, ktime_t now) +{ + ktime_t rem = ktime_sub(timer->node.expires, now); + + /* + * Adjust relative timers for the extra we added in + * hrtimer_start_range_ns() to prevent short timeouts. + */ + if (IS_ENABLED(CONFIG_TIME_LOW_RES) && timer->is_rel) + rem.tv64 -= hrtimer_resolution; + return rem; +} + +static inline ktime_t +hrtimer_expires_remaining_adjusted(const struct hrtimer *timer) +{ + return __hrtimer_expires_remaining_adjusted(timer, + timer->base->get_time()); +} + extern void clock_was_set(void); #ifdef CONFIG_TIMERFD extern void timerfd_clock_was_set(void); @@ -390,7 +413,12 @@ static inline void hrtimer_restart(struct hrtimer *timer) } /* Query timers: */ -extern ktime_t hrtimer_get_remaining(const struct hrtimer *timer); +extern ktime_t __hrtimer_get_remaining(const struct hrtimer *timer, bool adjust); + +static inline ktime_t hrtimer_get_remaining(const struct hrtimer *timer) +{ + return __hrtimer_get_remaining(timer, false); +} extern u64 hrtimer_get_next_event(void); diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index 435b8850dd80..fa909f9fd559 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -897,10 +897,10 @@ static int enqueue_hrtimer(struct hrtimer *timer, */ static void __remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base, - unsigned long newstate, int reprogram) + u8 newstate, int reprogram) { struct hrtimer_cpu_base *cpu_base = base->cpu_base; - unsigned int state = timer->state; + u8 state = timer->state; timer->state = newstate; if (!(state & HRTIMER_STATE_ENQUEUED)) @@ -930,7 +930,7 @@ static inline int remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base, bool restart) { if (hrtimer_is_queued(timer)) { - unsigned long state = timer->state; + u8 state = timer->state; int reprogram; /* @@ -954,6 +954,22 @@ remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base, bool rest return 0; } +static inline ktime_t hrtimer_update_lowres(struct hrtimer *timer, ktime_t tim, + const enum hrtimer_mode mode) +{ +#ifdef CONFIG_TIME_LOW_RES + /* + * CONFIG_TIME_LOW_RES indicates that the system has no way to return + * granular time values. For relative timers we add hrtimer_resolution + * (i.e. one jiffie) to prevent short timeouts. + */ + timer->is_rel = mode & HRTIMER_MODE_REL; + if (timer->is_rel) + tim = ktime_add_safe(tim, ktime_set(0, hrtimer_resolution)); +#endif + return tim; +} + /** * hrtimer_start_range_ns - (re)start an hrtimer on the current CPU * @timer: the timer to be added @@ -974,19 +990,10 @@ void hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, /* Remove an active timer from the queue: */ remove_hrtimer(timer, base, true); - if (mode & HRTIMER_MODE_REL) { + if (mode & HRTIMER_MODE_REL) tim = ktime_add_safe(tim, base->get_time()); - /* - * CONFIG_TIME_LOW_RES is a temporary way for architectures - * to signal that they simply return xtime in - * do_gettimeoffset(). In this case we want to round up by - * resolution when starting a relative timer, to avoid short - * timeouts. This will go away with the GTOD framework. - */ -#ifdef CONFIG_TIME_LOW_RES - tim = ktime_add_safe(tim, ktime_set(0, hrtimer_resolution)); -#endif - } + + tim = hrtimer_update_lowres(timer, tim, mode); hrtimer_set_expires_range_ns(timer, tim, delta_ns); @@ -1074,19 +1081,23 @@ EXPORT_SYMBOL_GPL(hrtimer_cancel); /** * hrtimer_get_remaining - get remaining time for the timer * @timer: the timer to read + * @adjust: adjust relative timers when CONFIG_TIME_LOW_RES=y */ -ktime_t hrtimer_get_remaining(const struct hrtimer *timer) +ktime_t __hrtimer_get_remaining(const struct hrtimer *timer, bool adjust) { unsigned long flags; ktime_t rem; lock_hrtimer_base(timer, &flags); - rem = hrtimer_expires_remaining(timer); + if (IS_ENABLED(CONFIG_TIME_LOW_RES) && adjust) + rem = hrtimer_expires_remaining_adjusted(timer); + else + rem = hrtimer_expires_remaining(timer); unlock_hrtimer_base(timer, &flags); return rem; } -EXPORT_SYMBOL_GPL(hrtimer_get_remaining); +EXPORT_SYMBOL_GPL(__hrtimer_get_remaining); #ifdef CONFIG_NO_HZ_COMMON /** @@ -1219,6 +1230,14 @@ static void __run_hrtimer(struct hrtimer_cpu_base *cpu_base, timer_stats_account_hrtimer(timer); fn = timer->function; + /* + * Clear the 'is relative' flag for the TIME_LOW_RES case. If the + * timer is restarted with a period then it becomes an absolute + * timer. If its not restarted it does not matter. + */ + if (IS_ENABLED(CONFIG_TIME_LOW_RES)) + timer->is_rel = false; + /* * Because we run timers from hardirq context, there is no chance * they get migrated to another cpu, therefore its safe to unlock diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c index f75e35b60149..ba7d8b288bb3 100644 --- a/kernel/time/timer_list.c +++ b/kernel/time/timer_list.c @@ -69,7 +69,7 @@ print_timer(struct seq_file *m, struct hrtimer *taddr, struct hrtimer *timer, print_name_offset(m, taddr); SEQ_printf(m, ", "); print_name_offset(m, timer->function); - SEQ_printf(m, ", S:%02lx", timer->state); + SEQ_printf(m, ", S:%02x", timer->state); #ifdef CONFIG_TIMER_STATS SEQ_printf(m, ", "); print_name_offset(m, timer->start_site); From 1eb90d90eadad21dfae3d31b7865abe17e9c5d91 Mon Sep 17 00:00:00 2001 From: Guillaume Fougnies Date: Tue, 26 Jan 2016 00:28:27 +0100 Subject: [PATCH 093/325] ALSA: usb-audio: Fix TEAC UD-501/UD-503/NT-503 usb delay commit 5a4ff9ec8d6edd2ab1cfe8ce6a080d6e57cbea9a upstream. TEAC UD-501/UD-503/NT-503 fail to switch properly between different rate/format. Similar to 'Playback Design', this patch corrects the invalid clock source error for TEAC products and avoids complete freeze of the usb interface of 503 series. Signed-off-by: Guillaume Fougnies Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/usb/quirks.c | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index 23ea6d800c4c..a75d9ce7d77a 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -1205,8 +1205,12 @@ void snd_usb_set_interface_quirk(struct usb_device *dev) * "Playback Design" products need a 50ms delay after setting the * USB interface. */ - if (le16_to_cpu(dev->descriptor.idVendor) == 0x23ba) + switch (le16_to_cpu(dev->descriptor.idVendor)) { + case 0x23ba: /* Playback Design */ + case 0x0644: /* TEAC Corp. */ mdelay(50); + break; + } } void snd_usb_ctl_msg_quirk(struct usb_device *dev, unsigned int pipe, @@ -1221,6 +1225,14 @@ void snd_usb_ctl_msg_quirk(struct usb_device *dev, unsigned int pipe, (requesttype & USB_TYPE_MASK) == USB_TYPE_CLASS) mdelay(20); + /* + * "TEAC Corp." products need a 20ms delay after each + * class compliant request + */ + if ((le16_to_cpu(dev->descriptor.idVendor) == 0x0644) && + (requesttype & USB_TYPE_MASK) == USB_TYPE_CLASS) + mdelay(20); + /* Marantz/Denon devices with USB DAC functionality need a delay * after each class compliant request */ From 11e7913d54c97bd999724264ac7f2d78900bbbd5 Mon Sep 17 00:00:00 2001 From: Lev Lybin Date: Fri, 29 Jan 2016 22:55:11 +0700 Subject: [PATCH 094/325] ALSA: usb-audio: Add quirk for Microsoft LifeCam HD-6000 commit 1b3c993a699bed282e47c3f7c49d539c331dae04 upstream. Microsoft LifeCam HD-6000 (045e:076f) requires the similar quirk for avoiding the stall due to the invalid sample rate reads. Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=111491 Signed-off-by: Lev Lybin Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/usb/quirks.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index a75d9ce7d77a..2d929701a077 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -1121,6 +1121,7 @@ bool snd_usb_get_sample_rate_quirk(struct snd_usb_audio *chip) switch (chip->usb_id) { case USB_ID(0x045E, 0x075D): /* MS Lifecam Cinema */ case USB_ID(0x045E, 0x076D): /* MS Lifecam HD-5000 */ + case USB_ID(0x045E, 0x076F): /* MS Lifecam HD-6000 */ case USB_ID(0x045E, 0x0772): /* MS Lifecam Studio */ case USB_ID(0x045E, 0x0779): /* MS Lifecam HD-3000 */ case USB_ID(0x04D8, 0xFEEA): /* Benchmark DAC1 Pre */ From 29a928ff8c1055ab34a0b40d285cbb2e4b0a4fd0 Mon Sep 17 00:00:00 2001 From: Jurgen Kramer Date: Fri, 29 Jan 2016 14:49:55 +0100 Subject: [PATCH 095/325] ALSA: usb-audio: Fix OPPO HA-1 vendor ID commit 5327d6ba975042fd3da50ac6e94d1e9551ebeaec upstream. In my patch adding native DSD support for the Oppo HA-1, the wrong vendor ID got through. This patch fixes the vendor ID and aligns the comment. Fixes: a4eae3a506ea ('ALSA: usb: Add native DSD support for Oppo HA-1') Signed-off-by: Jurgen Kramer Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/usb/quirks.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index 2d929701a077..8fbb917e3864 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -1282,7 +1282,7 @@ u64 snd_usb_interface_dsd_format_quirks(struct snd_usb_audio *chip, case USB_ID(0x20b1, 0x3008): /* iFi Audio micro/nano iDSD */ case USB_ID(0x20b1, 0x2008): /* Matrix Audio X-Sabre */ case USB_ID(0x20b1, 0x300a): /* Matrix Audio Mini-i Pro */ - case USB_ID(0x22d8, 0x0416): /* OPPO HA-1*/ + case USB_ID(0x22d9, 0x0416): /* OPPO HA-1 */ if (fp->altsetting == 2) return SNDRV_PCM_FMTBIT_DSD_U32_BE; break; From bb1066e621a195c5e9013f05b4f3d7dc46809923 Mon Sep 17 00:00:00 2001 From: Jurgen Kramer Date: Fri, 29 Jan 2016 14:59:25 +0100 Subject: [PATCH 096/325] ALSA: usb-audio: Add native DSD support for PS Audio NuWave DAC commit ad678b4ccd41aa51cf5f142c0e8cffe9d61fc2bf upstream. This patch adds native DSD support for the PS Audio NuWave DAC. Signed-off-by: Jurgen Kramer Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/usb/quirks.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index 8fbb917e3864..4f6ce1cac8e2 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -1291,6 +1291,7 @@ u64 snd_usb_interface_dsd_format_quirks(struct snd_usb_audio *chip, case USB_ID(0x20b1, 0x2009): /* DIYINHK DSD DXD 384kHz USB to I2S/DSD */ case USB_ID(0x20b1, 0x2023): /* JLsounds I2SoverUSB */ case USB_ID(0x20b1, 0x3023): /* Aune X1S 32BIT/384 DSD DAC */ + case USB_ID(0x2616, 0x0106): /* PS Audio NuWave DAC */ if (fp->altsetting == 3) return SNDRV_PCM_FMTBIT_DSD_U32_BE; break; From fbb430c51d7ac989b79bf1adb40cce7af581682a Mon Sep 17 00:00:00 2001 From: Andrey Konovalov Date: Sat, 13 Feb 2016 11:08:06 +0300 Subject: [PATCH 097/325] ALSA: usb-audio: avoid freeing umidi object twice commit 07d86ca93db7e5cdf4743564d98292042ec21af7 upstream. The 'umidi' object will be free'd on the error path by snd_usbmidi_free() when tearing down the rawmidi interface. So we shouldn't try to free it in snd_usbmidi_create() after having registered the rawmidi interface. Found by KASAN. Signed-off-by: Andrey Konovalov Acked-by: Clemens Ladisch Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/usb/midi.c | 1 - 1 file changed, 1 deletion(-) diff --git a/sound/usb/midi.c b/sound/usb/midi.c index 5b4c58c3e2c5..b21b76690b31 100644 --- a/sound/usb/midi.c +++ b/sound/usb/midi.c @@ -2454,7 +2454,6 @@ int snd_usbmidi_create(struct snd_card *card, else err = snd_usbmidi_create_endpoints(umidi, endpoints); if (err < 0) { - snd_usbmidi_free(umidi); return err; } From 2f32c8c003b35510b4b4515e70046e6a6e5967ca Mon Sep 17 00:00:00 2001 From: Lucas Tanure Date: Mon, 25 Jan 2016 19:30:23 -0200 Subject: [PATCH 098/325] ALSA: bebob: Use a signed return type for get_formation_index commit 07905298e4d5777eb58516cdc242f7ac1ca387a2 upstream. The return type "unsigned int" was used by the get_formation_index function despite of the aspect that it will eventually return a negative error code. So, change to signed int and get index by reference in the parameters. Done with the help of Coccinelle. [Fix the missing braces suggested by Julia Lawall -- tiwai] Signed-off-by: Lucas Tanure Reviewed-by: Takashi Sakamoto Tested-by: Takashi Sakamoto Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/firewire/bebob/bebob_stream.c | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) diff --git a/sound/firewire/bebob/bebob_stream.c b/sound/firewire/bebob/bebob_stream.c index 926e5dcbb66a..5022c9b97ddf 100644 --- a/sound/firewire/bebob/bebob_stream.c +++ b/sound/firewire/bebob/bebob_stream.c @@ -47,14 +47,16 @@ static const unsigned int bridgeco_freq_table[] = { [6] = 0x07, }; -static unsigned int -get_formation_index(unsigned int rate) +static int +get_formation_index(unsigned int rate, unsigned int *index) { unsigned int i; for (i = 0; i < ARRAY_SIZE(snd_bebob_rate_table); i++) { - if (snd_bebob_rate_table[i] == rate) - return i; + if (snd_bebob_rate_table[i] == rate) { + *index = i; + return 0; + } } return -EINVAL; } @@ -425,7 +427,9 @@ make_both_connections(struct snd_bebob *bebob, unsigned int rate) goto end; /* confirm params for both streams */ - index = get_formation_index(rate); + err = get_formation_index(rate, &index); + if (err < 0) + goto end; pcm_channels = bebob->tx_stream_formations[index].pcm; midi_channels = bebob->tx_stream_formations[index].midi; err = amdtp_am824_set_parameters(&bebob->tx_stream, rate, From 9f080d37c73948b187698c368cc87b191afd269a Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Wed, 27 Jan 2016 07:05:56 +0100 Subject: [PATCH 099/325] ALSA: Add missing dependency on CONFIG_SND_TIMER commit 61595dca742a9ba9a4c998b9af1f468adc816275 upstream. Since the build of PCM timer may be disabled via Kconfig now, each driver that provides a timer interface needs to set CONFIG_SND_TIMER explicitly. Otherwise it may get a build error due to missing symbol. Fixes: 90bbaf66ee7b ('ALSA: timer: add config item to export PCM timer disabling for expert') Reported-by: kbuild test robot Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/isa/Kconfig | 4 ++++ sound/pci/Kconfig | 3 +++ sound/sparc/Kconfig | 1 + 3 files changed, 8 insertions(+) diff --git a/sound/isa/Kconfig b/sound/isa/Kconfig index 0216475fc759..37adcc6cbe6b 100644 --- a/sound/isa/Kconfig +++ b/sound/isa/Kconfig @@ -3,6 +3,7 @@ config SND_WSS_LIB tristate select SND_PCM + select SND_TIMER config SND_SB_COMMON tristate @@ -42,6 +43,7 @@ config SND_AD1816A select SND_OPL3_LIB select SND_MPU401_UART select SND_PCM + select SND_TIMER help Say Y here to include support for Analog Devices SoundPort AD1816A or compatible sound chips. @@ -209,6 +211,7 @@ config SND_GUSCLASSIC tristate "Gravis UltraSound Classic" select SND_RAWMIDI select SND_PCM + select SND_TIMER help Say Y here to include support for Gravis UltraSound Classic soundcards. @@ -221,6 +224,7 @@ config SND_GUSEXTREME select SND_OPL3_LIB select SND_MPU401_UART select SND_PCM + select SND_TIMER help Say Y here to include support for Gravis UltraSound Extreme soundcards. diff --git a/sound/pci/Kconfig b/sound/pci/Kconfig index 656ce39bddbc..8f6594a7d37f 100644 --- a/sound/pci/Kconfig +++ b/sound/pci/Kconfig @@ -155,6 +155,7 @@ config SND_AZT3328 select SND_PCM select SND_RAWMIDI select SND_AC97_CODEC + select SND_TIMER depends on ZONE_DMA help Say Y here to include support for Aztech AZF3328 (PCI168) @@ -463,6 +464,7 @@ config SND_EMU10K1 select SND_HWDEP select SND_RAWMIDI select SND_AC97_CODEC + select SND_TIMER depends on ZONE_DMA help Say Y to include support for Sound Blaster PCI 512, Live!, @@ -889,6 +891,7 @@ config SND_YMFPCI select SND_OPL3_LIB select SND_MPU401_UART select SND_AC97_CODEC + select SND_TIMER help Say Y here to include support for Yamaha PCI audio chips - YMF724, YMF724F, YMF740, YMF740C, YMF744, YMF754. diff --git a/sound/sparc/Kconfig b/sound/sparc/Kconfig index d75deba5617d..dfcd38647606 100644 --- a/sound/sparc/Kconfig +++ b/sound/sparc/Kconfig @@ -22,6 +22,7 @@ config SND_SUN_AMD7930 config SND_SUN_CS4231 tristate "Sun CS4231" select SND_PCM + select SND_TIMER help Say Y here to include support for CS4231 sound device on Sun. From fc3e5563763429755a652b365b04c3cca562b92b Mon Sep 17 00:00:00 2001 From: Libin Yang Date: Fri, 29 Jan 2016 20:39:09 +0800 Subject: [PATCH 100/325] ALSA: hda - disable dynamic clock gating on Broxton before reset commit 6639484ddaf6707b41082c9fa9ca9af342df6402 upstream. On Broxton, to make sure the reset controller works properly, MISCBDCGE bit (bit 6) in CGCTL (0x48) of PCI configuration space need be cleared before reset and set back to 1 after reset. Otherwise, it may prevent the CORB/RIRB logic from being reset. Signed-off-by: Libin Yang Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/pci/hda/hda_intel.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index 614baff1f5d7..02a86ba5ba22 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -90,6 +90,8 @@ enum { #define NVIDIA_HDA_ENABLE_COHBIT 0x01 /* Defines for Intel SCH HDA snoop control */ +#define INTEL_HDA_CGCTL 0x48 +#define INTEL_HDA_CGCTL_MISCBDCGE (0x1 << 6) #define INTEL_SCH_HDA_DEVC 0x78 #define INTEL_SCH_HDA_DEVC_NOSNOOP (0x1<<11) @@ -528,10 +530,21 @@ static void hda_intel_init_chip(struct azx *chip, bool full_reset) { struct hdac_bus *bus = azx_bus(chip); struct pci_dev *pci = chip->pci; + u32 val; if (chip->driver_caps & AZX_DCAPS_I915_POWERWELL) snd_hdac_set_codec_wakeup(bus, true); + if (IS_BROXTON(pci)) { + pci_read_config_dword(pci, INTEL_HDA_CGCTL, &val); + val = val & ~INTEL_HDA_CGCTL_MISCBDCGE; + pci_write_config_dword(pci, INTEL_HDA_CGCTL, val); + } azx_init_chip(chip, full_reset); + if (IS_BROXTON(pci)) { + pci_read_config_dword(pci, INTEL_HDA_CGCTL, &val); + val = val | INTEL_HDA_CGCTL_MISCBDCGE; + pci_write_config_dword(pci, INTEL_HDA_CGCTL, val); + } if (chip->driver_caps & AZX_DCAPS_I915_POWERWELL) snd_hdac_set_codec_wakeup(bus, false); From 1963ffef4a1a92a07773bf8a30ce1224dd861bd5 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Mon, 25 Jan 2016 13:59:21 +0100 Subject: [PATCH 101/325] ALSA: compress: Disable GET_CODEC_CAPS ioctl for some architectures commit 462b3f161beb62eeb290f4ec52f5ead29a2f8ac7 upstream. Some architectures like PowerPC can handle the maximum struct size in an ioctl only up to 13 bits, and struct snd_compr_codec_caps used by SNDRV_COMPRESS_GET_CODEC_CAPS ioctl overflows this limit. This problem was revealed recently by a powerpc change, as it's now treated as a fatal build error. This patch is a stop-gap for that: for architectures with less than 14 bit ioctl struct size, get rid of the handling of the relevant ioctl. We should provide an alternative equivalent ioctl code later, but for now just paper over it. Luckily, the compress API hasn't been used on such architectures, so the impact must be effectively zero. Reviewed-by: Mark Brown Acked-by: Sudip Mukherjee Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/core/compress_offload.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/sound/core/compress_offload.c b/sound/core/compress_offload.c index b123c42e7dc8..b554d7f9e3be 100644 --- a/sound/core/compress_offload.c +++ b/sound/core/compress_offload.c @@ -44,6 +44,13 @@ #include #include +/* struct snd_compr_codec_caps overflows the ioctl bit size for some + * architectures, so we need to disable the relevant ioctls. + */ +#if _IOC_SIZEBITS < 14 +#define COMPR_CODEC_CAPS_OVERFLOW +#endif + /* TODO: * - add substream support for multiple devices in case of * SND_DYNAMIC_MINORS is not used @@ -438,6 +445,7 @@ out: return retval; } +#ifndef COMPR_CODEC_CAPS_OVERFLOW static int snd_compr_get_codec_caps(struct snd_compr_stream *stream, unsigned long arg) { @@ -461,6 +469,7 @@ out: kfree(caps); return retval; } +#endif /* !COMPR_CODEC_CAPS_OVERFLOW */ /* revisit this with snd_pcm_preallocate_xxx */ static int snd_compr_allocate_buffer(struct snd_compr_stream *stream, @@ -799,9 +808,11 @@ static long snd_compr_ioctl(struct file *f, unsigned int cmd, unsigned long arg) case _IOC_NR(SNDRV_COMPRESS_GET_CAPS): retval = snd_compr_get_caps(stream, arg); break; +#ifndef COMPR_CODEC_CAPS_OVERFLOW case _IOC_NR(SNDRV_COMPRESS_GET_CODEC_CAPS): retval = snd_compr_get_codec_caps(stream, arg); break; +#endif case _IOC_NR(SNDRV_COMPRESS_SET_PARAMS): retval = snd_compr_set_params(stream, arg); break; From d0cc6515b1238f90c61b713160e94ff768b43325 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Thu, 28 Jan 2016 07:54:16 +0100 Subject: [PATCH 102/325] ALSA: dummy: Disable switching timer backend via sysfs commit 7ee96216c31aabe1eb42fb91ff50dae9fcd014b2 upstream. ALSA dummy driver can switch the timer backend between system timer and hrtimer via its hrtimer module option. This can be also switched dynamically via sysfs, but it may lead to a memory corruption when switching is done while a PCM stream is running; the stream instance for the newly switched timer method tries to access the memory that was allocated by another timer method although the sizes differ. As the simplest fix, this patch just disables the switch via sysfs by dropping the writable bit. BugLink: http://lkml.kernel.org/r/CACT4Y+ZGEeEBntHW5WHn2GoeE0G_kRrCmUh6=dWyy-wfzvuJLg@mail.gmail.com Reported-by: Dmitry Vyukov Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/drivers/dummy.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/drivers/dummy.c b/sound/drivers/dummy.c index 016e451ed506..df8e757deb58 100644 --- a/sound/drivers/dummy.c +++ b/sound/drivers/dummy.c @@ -87,7 +87,7 @@ MODULE_PARM_DESC(pcm_substreams, "PCM substreams # (1-128) for dummy driver."); module_param(fake_buffer, bool, 0444); MODULE_PARM_DESC(fake_buffer, "Fake buffer allocations."); #ifdef CONFIG_HIGH_RES_TIMERS -module_param(hrtimer, bool, 0644); +module_param(hrtimer, bool, 0444); MODULE_PARM_DESC(hrtimer, "Use hrtimer as the timer source."); #endif From fa8fcbe38317a90094a29120ea959fb361b895fb Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Mon, 25 Jan 2016 11:01:47 +0100 Subject: [PATCH 103/325] ALSA: seq: Fix incorrect sanity check at snd_seq_oss_synth_cleanup() commit 599151336638d57b98d92338aa59c048e3a3e97d upstream. ALSA sequencer OSS emulation code has a sanity check for currently opened devices, but there is a thinko there, eventually it spews warnings and skips the operation wrongly like: WARNING: CPU: 1 PID: 7573 at sound/core/seq/oss/seq_oss_synth.c:311 Fix this off-by-one error. Reported-by: Dmitry Vyukov Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/core/seq/oss/seq_oss_synth.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/core/seq/oss/seq_oss_synth.c b/sound/core/seq/oss/seq_oss_synth.c index 0f3b38184fe5..b16dbef04174 100644 --- a/sound/core/seq/oss/seq_oss_synth.c +++ b/sound/core/seq/oss/seq_oss_synth.c @@ -308,7 +308,7 @@ snd_seq_oss_synth_cleanup(struct seq_oss_devinfo *dp) struct seq_oss_synth *rec; struct seq_oss_synthinfo *info; - if (snd_BUG_ON(dp->max_synthdev >= SNDRV_SEQ_OSS_MAX_SYNTH_DEVS)) + if (snd_BUG_ON(dp->max_synthdev > SNDRV_SEQ_OSS_MAX_SYNTH_DEVS)) return; for (i = 0; i < dp->max_synthdev; i++) { info = &dp->synths[i]; From aef1181d08fd293398fb3bda39cca05dc07c95e0 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Mon, 25 Jan 2016 11:24:56 +0100 Subject: [PATCH 104/325] ALSA: seq: Degrade the error message for too many opens commit da10816e3d923565b470fec78a674baba794ed33 upstream. ALSA OSS sequencer spews a kernel error message ("ALSA: seq_oss: too many applications") when user-space tries to open more than the limit. This means that it can easily fill the log buffer. Since it's merely a normal error, it's safe to suppress it via pr_debug() instead. Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/core/seq/oss/seq_oss_init.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/core/seq/oss/seq_oss_init.c b/sound/core/seq/oss/seq_oss_init.c index b1221b29728e..6779e82b46dd 100644 --- a/sound/core/seq/oss/seq_oss_init.c +++ b/sound/core/seq/oss/seq_oss_init.c @@ -202,7 +202,7 @@ snd_seq_oss_open(struct file *file, int level) dp->index = i; if (i >= SNDRV_SEQ_OSS_MAX_CLIENTS) { - pr_err("ALSA: seq_oss: too many applications\n"); + pr_debug("ALSA: seq_oss: too many applications\n"); rc = -ENOMEM; goto _error; } From c3f8a5000e75da9dc40215bf1acf3aa5515c75fe Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Sun, 31 Jan 2016 11:57:41 +0100 Subject: [PATCH 105/325] ALSA: rawmidi: Make snd_rawmidi_transmit() race-free commit 06ab30034ed9c200a570ab13c017bde248ddb2a6 upstream. A kernel WARNING in snd_rawmidi_transmit_ack() is triggered by syzkaller fuzzer: WARNING: CPU: 1 PID: 20739 at sound/core/rawmidi.c:1136 Call Trace: [< inline >] __dump_stack lib/dump_stack.c:15 [] dump_stack+0x6f/0xa2 lib/dump_stack.c:50 [] warn_slowpath_common+0xd9/0x140 kernel/panic.c:482 [] warn_slowpath_null+0x29/0x30 kernel/panic.c:515 [] snd_rawmidi_transmit_ack+0x275/0x400 sound/core/rawmidi.c:1136 [] snd_virmidi_output_trigger+0x4b1/0x5a0 sound/core/seq/seq_virmidi.c:163 [< inline >] snd_rawmidi_output_trigger sound/core/rawmidi.c:150 [] snd_rawmidi_kernel_write1+0x549/0x780 sound/core/rawmidi.c:1223 [] snd_rawmidi_write+0x543/0xb30 sound/core/rawmidi.c:1273 [] __vfs_write+0x113/0x480 fs/read_write.c:528 [] vfs_write+0x167/0x4a0 fs/read_write.c:577 [< inline >] SYSC_write fs/read_write.c:624 [] SyS_write+0x111/0x220 fs/read_write.c:616 [] entry_SYSCALL_64_fastpath+0x16/0x7a arch/x86/entry/entry_64.S:185 Also a similar warning is found but in another path: Call Trace: [< inline >] __dump_stack lib/dump_stack.c:15 [] dump_stack+0x6f/0xa2 lib/dump_stack.c:50 [] warn_slowpath_common+0xd9/0x140 kernel/panic.c:482 [] warn_slowpath_null+0x29/0x30 kernel/panic.c:515 [] rawmidi_transmit_ack+0x24a/0x3b0 sound/core/rawmidi.c:1133 [] snd_rawmidi_transmit_ack+0x51/0x80 sound/core/rawmidi.c:1163 [] snd_virmidi_output_trigger+0x2b6/0x570 sound/core/seq/seq_virmidi.c:185 [< inline >] snd_rawmidi_output_trigger sound/core/rawmidi.c:150 [] snd_rawmidi_kernel_write1+0x4bb/0x760 sound/core/rawmidi.c:1252 [] snd_rawmidi_write+0x543/0xb30 sound/core/rawmidi.c:1302 [] __vfs_write+0x113/0x480 fs/read_write.c:528 [] vfs_write+0x167/0x4a0 fs/read_write.c:577 [< inline >] SYSC_write fs/read_write.c:624 [] SyS_write+0x111/0x220 fs/read_write.c:616 [] entry_SYSCALL_64_fastpath+0x16/0x7a arch/x86/entry/entry_64.S:185 In the former case, the reason is that virmidi has an open code calling snd_rawmidi_transmit_ack() with the value calculated outside the spinlock. We may use snd_rawmidi_transmit() in a loop just for consuming the input data, but even there, there is a race between snd_rawmidi_transmit_peek() and snd_rawmidi_tranmit_ack(). Similarly in the latter case, it calls snd_rawmidi_transmit_peek() and snd_rawmidi_tranmit_ack() separately without protection, so they are racy as well. The patch tries to address these issues by the following ways: - Introduce the unlocked versions of snd_rawmidi_transmit_peek() and snd_rawmidi_transmit_ack() to be called inside the explicit lock. - Rewrite snd_rawmidi_transmit() to be race-free (the former case). - Make the split calls (the latter case) protected in the rawmidi spin lock. BugLink: http://lkml.kernel.org/r/CACT4Y+YPq1+cYLkadwjWa5XjzF1_Vki1eHnVn-Lm0hzhSpu5PA@mail.gmail.com BugLink: http://lkml.kernel.org/r/CACT4Y+acG4iyphdOZx47Nyq_VHGbpJQK-6xNpiqUjaZYqsXOGw@mail.gmail.com Reported-by: Dmitry Vyukov Tested-by: Dmitry Vyukov Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- include/sound/rawmidi.h | 4 ++ sound/core/rawmidi.c | 110 +++++++++++++++++++++++++---------- sound/core/seq/seq_virmidi.c | 17 ++++-- 3 files changed, 94 insertions(+), 37 deletions(-) diff --git a/include/sound/rawmidi.h b/include/sound/rawmidi.h index f6cbef78db62..3b91ad5d5115 100644 --- a/include/sound/rawmidi.h +++ b/include/sound/rawmidi.h @@ -167,6 +167,10 @@ int snd_rawmidi_transmit_peek(struct snd_rawmidi_substream *substream, int snd_rawmidi_transmit_ack(struct snd_rawmidi_substream *substream, int count); int snd_rawmidi_transmit(struct snd_rawmidi_substream *substream, unsigned char *buffer, int count); +int __snd_rawmidi_transmit_peek(struct snd_rawmidi_substream *substream, + unsigned char *buffer, int count); +int __snd_rawmidi_transmit_ack(struct snd_rawmidi_substream *substream, + int count); /* main midi functions */ diff --git a/sound/core/rawmidi.c b/sound/core/rawmidi.c index a7759846fbaa..c7dfa571875f 100644 --- a/sound/core/rawmidi.c +++ b/sound/core/rawmidi.c @@ -1055,23 +1055,16 @@ int snd_rawmidi_transmit_empty(struct snd_rawmidi_substream *substream) EXPORT_SYMBOL(snd_rawmidi_transmit_empty); /** - * snd_rawmidi_transmit_peek - copy data from the internal buffer + * __snd_rawmidi_transmit_peek - copy data from the internal buffer * @substream: the rawmidi substream * @buffer: the buffer pointer * @count: data size to transfer * - * Copies data from the internal output buffer to the given buffer. - * - * Call this in the interrupt handler when the midi output is ready, - * and call snd_rawmidi_transmit_ack() after the transmission is - * finished. - * - * Return: The size of copied data, or a negative error code on failure. + * This is a variant of snd_rawmidi_transmit_peek() without spinlock. */ -int snd_rawmidi_transmit_peek(struct snd_rawmidi_substream *substream, +int __snd_rawmidi_transmit_peek(struct snd_rawmidi_substream *substream, unsigned char *buffer, int count) { - unsigned long flags; int result, count1; struct snd_rawmidi_runtime *runtime = substream->runtime; @@ -1081,7 +1074,6 @@ int snd_rawmidi_transmit_peek(struct snd_rawmidi_substream *substream, return -EINVAL; } result = 0; - spin_lock_irqsave(&runtime->lock, flags); if (runtime->avail >= runtime->buffer_size) { /* warning: lowlevel layer MUST trigger down the hardware */ goto __skip; @@ -1106,11 +1098,67 @@ int snd_rawmidi_transmit_peek(struct snd_rawmidi_substream *substream, } } __skip: + return result; +} +EXPORT_SYMBOL(__snd_rawmidi_transmit_peek); + +/** + * snd_rawmidi_transmit_peek - copy data from the internal buffer + * @substream: the rawmidi substream + * @buffer: the buffer pointer + * @count: data size to transfer + * + * Copies data from the internal output buffer to the given buffer. + * + * Call this in the interrupt handler when the midi output is ready, + * and call snd_rawmidi_transmit_ack() after the transmission is + * finished. + * + * Return: The size of copied data, or a negative error code on failure. + */ +int snd_rawmidi_transmit_peek(struct snd_rawmidi_substream *substream, + unsigned char *buffer, int count) +{ + struct snd_rawmidi_runtime *runtime = substream->runtime; + int result; + unsigned long flags; + + spin_lock_irqsave(&runtime->lock, flags); + result = __snd_rawmidi_transmit_peek(substream, buffer, count); spin_unlock_irqrestore(&runtime->lock, flags); return result; } EXPORT_SYMBOL(snd_rawmidi_transmit_peek); +/** + * __snd_rawmidi_transmit_ack - acknowledge the transmission + * @substream: the rawmidi substream + * @count: the transferred count + * + * This is a variant of __snd_rawmidi_transmit_ack() without spinlock. + */ +int __snd_rawmidi_transmit_ack(struct snd_rawmidi_substream *substream, int count) +{ + struct snd_rawmidi_runtime *runtime = substream->runtime; + + if (runtime->buffer == NULL) { + rmidi_dbg(substream->rmidi, + "snd_rawmidi_transmit_ack: output is not active!!!\n"); + return -EINVAL; + } + snd_BUG_ON(runtime->avail + count > runtime->buffer_size); + runtime->hw_ptr += count; + runtime->hw_ptr %= runtime->buffer_size; + runtime->avail += count; + substream->bytes += count; + if (count > 0) { + if (runtime->drain || snd_rawmidi_ready(substream)) + wake_up(&runtime->sleep); + } + return count; +} +EXPORT_SYMBOL(__snd_rawmidi_transmit_ack); + /** * snd_rawmidi_transmit_ack - acknowledge the transmission * @substream: the rawmidi substream @@ -1124,26 +1172,14 @@ EXPORT_SYMBOL(snd_rawmidi_transmit_peek); */ int snd_rawmidi_transmit_ack(struct snd_rawmidi_substream *substream, int count) { - unsigned long flags; struct snd_rawmidi_runtime *runtime = substream->runtime; + int result; + unsigned long flags; - if (runtime->buffer == NULL) { - rmidi_dbg(substream->rmidi, - "snd_rawmidi_transmit_ack: output is not active!!!\n"); - return -EINVAL; - } spin_lock_irqsave(&runtime->lock, flags); - snd_BUG_ON(runtime->avail + count > runtime->buffer_size); - runtime->hw_ptr += count; - runtime->hw_ptr %= runtime->buffer_size; - runtime->avail += count; - substream->bytes += count; - if (count > 0) { - if (runtime->drain || snd_rawmidi_ready(substream)) - wake_up(&runtime->sleep); - } + result = __snd_rawmidi_transmit_ack(substream, count); spin_unlock_irqrestore(&runtime->lock, flags); - return count; + return result; } EXPORT_SYMBOL(snd_rawmidi_transmit_ack); @@ -1160,12 +1196,22 @@ EXPORT_SYMBOL(snd_rawmidi_transmit_ack); int snd_rawmidi_transmit(struct snd_rawmidi_substream *substream, unsigned char *buffer, int count) { + struct snd_rawmidi_runtime *runtime = substream->runtime; + int result; + unsigned long flags; + + spin_lock_irqsave(&runtime->lock, flags); if (!substream->opened) - return -EBADFD; - count = snd_rawmidi_transmit_peek(substream, buffer, count); - if (count < 0) - return count; - return snd_rawmidi_transmit_ack(substream, count); + result = -EBADFD; + else { + count = __snd_rawmidi_transmit_peek(substream, buffer, count); + if (count <= 0) + result = count; + else + result = __snd_rawmidi_transmit_ack(substream, count); + } + spin_unlock_irqrestore(&runtime->lock, flags); + return result; } EXPORT_SYMBOL(snd_rawmidi_transmit); diff --git a/sound/core/seq/seq_virmidi.c b/sound/core/seq/seq_virmidi.c index 56e0f4cd3f82..09b26cb8265a 100644 --- a/sound/core/seq/seq_virmidi.c +++ b/sound/core/seq/seq_virmidi.c @@ -155,21 +155,26 @@ static void snd_virmidi_output_trigger(struct snd_rawmidi_substream *substream, struct snd_virmidi *vmidi = substream->runtime->private_data; int count, res; unsigned char buf[32], *pbuf; + unsigned long flags; if (up) { vmidi->trigger = 1; if (vmidi->seq_mode == SNDRV_VIRMIDI_SEQ_DISPATCH && !(vmidi->rdev->flags & SNDRV_VIRMIDI_SUBSCRIBE)) { - snd_rawmidi_transmit_ack(substream, substream->runtime->buffer_size - substream->runtime->avail); - return; /* ignored */ + while (snd_rawmidi_transmit(substream, buf, + sizeof(buf)) > 0) { + /* ignored */ + } + return; } if (vmidi->event.type != SNDRV_SEQ_EVENT_NONE) { if (snd_seq_kernel_client_dispatch(vmidi->client, &vmidi->event, in_atomic(), 0) < 0) return; vmidi->event.type = SNDRV_SEQ_EVENT_NONE; } + spin_lock_irqsave(&substream->runtime->lock, flags); while (1) { - count = snd_rawmidi_transmit_peek(substream, buf, sizeof(buf)); + count = __snd_rawmidi_transmit_peek(substream, buf, sizeof(buf)); if (count <= 0) break; pbuf = buf; @@ -179,16 +184,18 @@ static void snd_virmidi_output_trigger(struct snd_rawmidi_substream *substream, snd_midi_event_reset_encode(vmidi->parser); continue; } - snd_rawmidi_transmit_ack(substream, res); + __snd_rawmidi_transmit_ack(substream, res); pbuf += res; count -= res; if (vmidi->event.type != SNDRV_SEQ_EVENT_NONE) { if (snd_seq_kernel_client_dispatch(vmidi->client, &vmidi->event, in_atomic(), 0) < 0) - return; + goto out; vmidi->event.type = SNDRV_SEQ_EVENT_NONE; } } } + out: + spin_unlock_irqrestore(&substream->runtime->lock, flags); } else { vmidi->trigger = 0; } From 8af97f7c418ddc9c3e7a649414c70e798b134e50 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Mon, 1 Feb 2016 12:04:55 +0100 Subject: [PATCH 106/325] ALSA: rawmidi: Remove kernel WARNING for NULL user-space buffer check commit cc85f7a634cfaf9f0713c6aa06d08817424db37a upstream. NULL user-space buffer can be passed even in a normal path, thus it's not good to spew a kernel warning with stack trace at each time. Just drop snd_BUG_ON() macro usage there. BugLink: http://lkml.kernel.org/r/CACT4Y+YfVJ3L+q0i-4vyQVyyPD7V=OMX0PWPi29x9Bo3QaBLdw@mail.gmail.com Reported-by: Dmitry Vyukov Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/core/rawmidi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/core/rawmidi.c b/sound/core/rawmidi.c index c7dfa571875f..26ca02248885 100644 --- a/sound/core/rawmidi.c +++ b/sound/core/rawmidi.c @@ -1224,7 +1224,7 @@ static long snd_rawmidi_kernel_write1(struct snd_rawmidi_substream *substream, long count1, result; struct snd_rawmidi_runtime *runtime = substream->runtime; - if (snd_BUG_ON(!kernelbuf && !userbuf)) + if (!kernelbuf && !userbuf) return -EINVAL; if (snd_BUG_ON(!runtime->buffer)) return -EINVAL; From 49ba9e222aa5a079cf89d2a86da9838aa0213a60 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Wed, 3 Feb 2016 14:41:22 +0100 Subject: [PATCH 107/325] ALSA: rawmidi: Fix race at copying & updating the position commit 81f577542af15640cbcb6ef68baa4caa610cbbfc upstream. The rawmidi read and write functions manage runtime stream status such as runtime->appl_ptr and runtime->avail. These point where to copy the new data and how many bytes have been copied (or to be read). The problem is that rawmidi read/write call copy_from_user() or copy_to_user(), and the runtime spinlock is temporarily unlocked and relocked while copying user-space. Since the current code advances and updates the runtime status after the spin unlock/relock, the copy and the update may be asynchronous, and eventually runtime->avail might go to a negative value when many concurrent accesses are done. This may lead to memory corruption in the end. For fixing this race, in this patch, the status update code is performed in the same lock before the temporary unlock. Also, the spinlock is now taken more widely in snd_rawmidi_kernel_read1() for protecting more properly during the whole operation. BugLink: http://lkml.kernel.org/r/CACT4Y+b-dCmNf1GpgPKfDO0ih+uZCL2JV4__j-r1kdhPLSgQCQ@mail.gmail.com Reported-by: Dmitry Vyukov Tested-by: Dmitry Vyukov Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/core/rawmidi.c | 34 ++++++++++++++++++++++------------ 1 file changed, 22 insertions(+), 12 deletions(-) diff --git a/sound/core/rawmidi.c b/sound/core/rawmidi.c index 26ca02248885..795437b10082 100644 --- a/sound/core/rawmidi.c +++ b/sound/core/rawmidi.c @@ -942,31 +942,36 @@ static long snd_rawmidi_kernel_read1(struct snd_rawmidi_substream *substream, unsigned long flags; long result = 0, count1; struct snd_rawmidi_runtime *runtime = substream->runtime; + unsigned long appl_ptr; + spin_lock_irqsave(&runtime->lock, flags); while (count > 0 && runtime->avail) { count1 = runtime->buffer_size - runtime->appl_ptr; if (count1 > count) count1 = count; - spin_lock_irqsave(&runtime->lock, flags); if (count1 > (int)runtime->avail) count1 = runtime->avail; + + /* update runtime->appl_ptr before unlocking for userbuf */ + appl_ptr = runtime->appl_ptr; + runtime->appl_ptr += count1; + runtime->appl_ptr %= runtime->buffer_size; + runtime->avail -= count1; + if (kernelbuf) - memcpy(kernelbuf + result, runtime->buffer + runtime->appl_ptr, count1); + memcpy(kernelbuf + result, runtime->buffer + appl_ptr, count1); if (userbuf) { spin_unlock_irqrestore(&runtime->lock, flags); if (copy_to_user(userbuf + result, - runtime->buffer + runtime->appl_ptr, count1)) { + runtime->buffer + appl_ptr, count1)) { return result > 0 ? result : -EFAULT; } spin_lock_irqsave(&runtime->lock, flags); } - runtime->appl_ptr += count1; - runtime->appl_ptr %= runtime->buffer_size; - runtime->avail -= count1; - spin_unlock_irqrestore(&runtime->lock, flags); result += count1; count -= count1; } + spin_unlock_irqrestore(&runtime->lock, flags); return result; } @@ -1223,6 +1228,7 @@ static long snd_rawmidi_kernel_write1(struct snd_rawmidi_substream *substream, unsigned long flags; long count1, result; struct snd_rawmidi_runtime *runtime = substream->runtime; + unsigned long appl_ptr; if (!kernelbuf && !userbuf) return -EINVAL; @@ -1243,12 +1249,19 @@ static long snd_rawmidi_kernel_write1(struct snd_rawmidi_substream *substream, count1 = count; if (count1 > (long)runtime->avail) count1 = runtime->avail; + + /* update runtime->appl_ptr before unlocking for userbuf */ + appl_ptr = runtime->appl_ptr; + runtime->appl_ptr += count1; + runtime->appl_ptr %= runtime->buffer_size; + runtime->avail -= count1; + if (kernelbuf) - memcpy(runtime->buffer + runtime->appl_ptr, + memcpy(runtime->buffer + appl_ptr, kernelbuf + result, count1); else if (userbuf) { spin_unlock_irqrestore(&runtime->lock, flags); - if (copy_from_user(runtime->buffer + runtime->appl_ptr, + if (copy_from_user(runtime->buffer + appl_ptr, userbuf + result, count1)) { spin_lock_irqsave(&runtime->lock, flags); result = result > 0 ? result : -EFAULT; @@ -1256,9 +1269,6 @@ static long snd_rawmidi_kernel_write1(struct snd_rawmidi_substream *substream, } spin_lock_irqsave(&runtime->lock, flags); } - runtime->appl_ptr += count1; - runtime->appl_ptr %= runtime->buffer_size; - runtime->avail -= count1; result += count1; count -= count1; } From 1732e58646b4b2adf0cfaff757365a4472e4b6ab Mon Sep 17 00:00:00 2001 From: Kailang Yang Date: Wed, 3 Feb 2016 15:03:50 +0800 Subject: [PATCH 108/325] ALSA: hda/realtek - New codec support of ALC225 commit 4231430da9607fb2eb7ea92f3b93ceef3bc2ed93 upstream. Add new support for ALC225, yet another variant of ALC298 codec. Signed-off-by: Kailang Yang Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/pci/hda/patch_realtek.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 33753244f48f..0b05ae2bc2f7 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -327,6 +327,7 @@ static void alc_fill_eapd_coef(struct hda_codec *codec) case 0x10ec0292: alc_update_coef_idx(codec, 0x4, 1<<15, 0); break; + case 0x10ec0225: case 0x10ec0233: case 0x10ec0255: case 0x10ec0256: @@ -900,6 +901,7 @@ static struct alc_codec_rename_pci_table rename_pci_tbl[] = { { 0x10ec0899, 0x1028, 0, "ALC3861" }, { 0x10ec0298, 0x1028, 0, "ALC3266" }, { 0x10ec0256, 0x1028, 0, "ALC3246" }, + { 0x10ec0225, 0x1028, 0, "ALC3253" }, { 0x10ec0670, 0x1025, 0, "ALC669X" }, { 0x10ec0676, 0x1025, 0, "ALC679X" }, { 0x10ec0282, 0x1043, 0, "ALC3229" }, @@ -2651,6 +2653,7 @@ enum { ALC269_TYPE_ALC298, ALC269_TYPE_ALC255, ALC269_TYPE_ALC256, + ALC269_TYPE_ALC225, }; /* @@ -2680,6 +2683,7 @@ static int alc269_parse_auto_config(struct hda_codec *codec) case ALC269_TYPE_ALC298: case ALC269_TYPE_ALC255: case ALC269_TYPE_ALC256: + case ALC269_TYPE_ALC225: ssids = alc269_ssids; break; default: @@ -5906,6 +5910,9 @@ static int patch_alc269(struct hda_codec *codec) spec->gen.mixer_nid = 0; /* ALC256 does not have any loopback mixer path */ alc_update_coef_idx(codec, 0x36, 1 << 13, 1 << 5); /* Switch pcbeep path to Line in path*/ break; + case 0x10ec0225: + spec->codec_variant = ALC269_TYPE_ALC225; + break; } if (snd_hda_codec_read(codec, 0x51, 0, AC_VERB_PARAMETERS, 0) == 0x10ec5505) { @@ -6796,6 +6803,7 @@ static int patch_alc680(struct hda_codec *codec) */ static const struct hda_device_id snd_hda_id_realtek[] = { HDA_CODEC_ENTRY(0x10ec0221, "ALC221", patch_alc269), + HDA_CODEC_ENTRY(0x10ec0225, "ALC225", patch_alc269), HDA_CODEC_ENTRY(0x10ec0231, "ALC231", patch_alc269), HDA_CODEC_ENTRY(0x10ec0233, "ALC233", patch_alc269), HDA_CODEC_ENTRY(0x10ec0235, "ALC233", patch_alc269), From fbc546e238785fae3085a8e0318fa628281c61fc Mon Sep 17 00:00:00 2001 From: Kailang Yang Date: Wed, 3 Feb 2016 15:09:35 +0800 Subject: [PATCH 109/325] ALSA: hda/realtek - Support headset mode for ALC225 commit 4cc9b9d627af2c443cf98e651e3738d84f991cec upstream. Support headset mode for ALC225 platforms. Signed-off-by: Kailang Yang Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/pci/hda/patch_realtek.c | 57 +++++++++++++++++++++++++++++++++++ 1 file changed, 57 insertions(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 0b05ae2bc2f7..fbacbf8b7e50 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -3662,6 +3662,16 @@ static void alc_headset_mode_unplugged(struct hda_codec *codec) WRITE_COEF(0xb7, 0x802b), {} }; + static struct coef_fw coef0225[] = { + UPDATE_COEF(0x4a, 1<<8, 0), + UPDATE_COEFEX(0x57, 0x05, 1<<14, 0), + UPDATE_COEF(0x63, 3<<14, 3<<14), + UPDATE_COEF(0x4a, 3<<4, 2<<4), + UPDATE_COEF(0x4a, 3<<10, 3<<10), + UPDATE_COEF(0x45, 0x3f<<10, 0x34<<10), + UPDATE_COEF(0x4a, 3<<10, 0), + {} + }; switch (codec->core.vendor_id) { case 0x10ec0255: @@ -3686,6 +3696,9 @@ static void alc_headset_mode_unplugged(struct hda_codec *codec) case 0x10ec0668: alc_process_coef_fw(codec, coef0668); break; + case 0x10ec0225: + alc_process_coef_fw(codec, coef0225); + break; } codec_dbg(codec, "Headset jack set to unplugged mode.\n"); } @@ -3731,6 +3744,13 @@ static void alc_headset_mode_mic_in(struct hda_codec *codec, hda_nid_t hp_pin, UPDATE_COEF(0xc3, 0, 1<<12), {} }; + static struct coef_fw coef0225[] = { + UPDATE_COEFEX(0x57, 0x05, 1<<14, 1<<14), + UPDATE_COEF(0x4a, 3<<4, 2<<4), + UPDATE_COEF(0x63, 3<<14, 0), + {} + }; + switch (codec->core.vendor_id) { case 0x10ec0255: @@ -3776,6 +3796,12 @@ static void alc_headset_mode_mic_in(struct hda_codec *codec, hda_nid_t hp_pin, alc_process_coef_fw(codec, coef0688); snd_hda_set_pin_ctl_cache(codec, mic_pin, PIN_VREF50); break; + case 0x10ec0225: + alc_update_coef_idx(codec, 0x45, 0x3f<<10, 0x31<<10); + snd_hda_set_pin_ctl_cache(codec, hp_pin, 0); + alc_process_coef_fw(codec, coef0225); + snd_hda_set_pin_ctl_cache(codec, mic_pin, PIN_VREF50); + break; } codec_dbg(codec, "Headset jack set to mic-in mode.\n"); } @@ -3888,6 +3914,13 @@ static void alc_headset_mode_ctia(struct hda_codec *codec) WRITE_COEF(0xc3, 0x0000), {} }; + static struct coef_fw coef0225[] = { + UPDATE_COEF(0x45, 0x3f<<10, 0x35<<10), + UPDATE_COEF(0x49, 1<<8, 1<<8), + UPDATE_COEF(0x4a, 7<<6, 7<<6), + UPDATE_COEF(0x4a, 3<<4, 3<<4), + {} + }; switch (codec->core.vendor_id) { case 0x10ec0255: @@ -3916,6 +3949,9 @@ static void alc_headset_mode_ctia(struct hda_codec *codec) case 0x10ec0668: alc_process_coef_fw(codec, coef0688); break; + case 0x10ec0225: + alc_process_coef_fw(codec, coef0225); + break; } codec_dbg(codec, "Headset jack set to iPhone-style headset mode.\n"); } @@ -3959,6 +3995,13 @@ static void alc_headset_mode_omtp(struct hda_codec *codec) WRITE_COEF(0xc3, 0x0000), {} }; + static struct coef_fw coef0225[] = { + UPDATE_COEF(0x45, 0x3f<<10, 0x39<<10), + UPDATE_COEF(0x49, 1<<8, 1<<8), + UPDATE_COEF(0x4a, 7<<6, 7<<6), + UPDATE_COEF(0x4a, 3<<4, 3<<4), + {} + }; switch (codec->core.vendor_id) { case 0x10ec0255: @@ -3987,6 +4030,9 @@ static void alc_headset_mode_omtp(struct hda_codec *codec) case 0x10ec0668: alc_process_coef_fw(codec, coef0688); break; + case 0x10ec0225: + alc_process_coef_fw(codec, coef0225); + break; } codec_dbg(codec, "Headset jack set to Nokia-style headset mode.\n"); } @@ -4018,6 +4064,11 @@ static void alc_determine_headset_type(struct hda_codec *codec) WRITE_COEF(0xc3, 0x0c00), {} }; + static struct coef_fw coef0225[] = { + UPDATE_COEF(0x45, 0x3f<<10, 0x34<<10), + UPDATE_COEF(0x49, 1<<8, 1<<8), + {} + }; switch (codec->core.vendor_id) { case 0x10ec0255: @@ -4062,6 +4113,12 @@ static void alc_determine_headset_type(struct hda_codec *codec) val = alc_read_coef_idx(codec, 0xbe); is_ctia = (val & 0x1c02) == 0x1c02; break; + case 0x10ec0225: + alc_process_coef_fw(codec, coef0225); + msleep(800); + val = alc_read_coef_idx(codec, 0x46); + is_ctia = (val & 0x00f0) == 0x00f0; + break; } codec_dbg(codec, "Headset jack detected iPhone-style headset: %s\n", From f7fd4634b65c517321f1e7f30f5632d77b4208b4 Mon Sep 17 00:00:00 2001 From: Kailang Yang Date: Wed, 3 Feb 2016 15:20:39 +0800 Subject: [PATCH 110/325] ALSA: hda/realtek - Support Dell headset mode for ALC225 commit cfc5a845e62853edd36e564c23c64588f4adcae6 upstream. Dell create new platform with ALC298 codec. This patch will enable headset mode for ALC225/ALC3253 platform. Signed-off-by: Kailang Yang Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/pci/hda/patch_realtek.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index fbacbf8b7e50..21992fb7035d 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -5621,6 +5621,9 @@ static const struct hda_model_fixup alc269_fixup_models[] = { {.id = ALC292_FIXUP_TPT440, .name = "tpt440"}, {} }; +#define ALC225_STANDARD_PINS \ + {0x12, 0xb7a60130}, \ + {0x21, 0x04211020} #define ALC256_STANDARD_PINS \ {0x12, 0x90a60140}, \ @@ -5642,6 +5645,12 @@ static const struct hda_model_fixup alc269_fixup_models[] = { {0x21, 0x03211020} static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = { + SND_HDA_PIN_QUIRK(0x10ec0225, 0x1028, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE, + ALC225_STANDARD_PINS, + {0x14, 0x901701a0}), + SND_HDA_PIN_QUIRK(0x10ec0225, 0x1028, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE, + ALC225_STANDARD_PINS, + {0x14, 0x901701b0}), SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell", ALC255_FIXUP_DELL2_MIC_NO_PRESENCE, {0x14, 0x90170110}, {0x21, 0x02211020}), From 195988d298fc4c2af1162a960fd7772c311dc747 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Sun, 31 Jan 2016 10:32:37 +0100 Subject: [PATCH 111/325] ALSA: pcm: Fix potential deadlock in OSS emulation commit b248371628aad599a48540962f6b85a21a8a0c3f upstream. There are potential deadlocks in PCM OSS emulation code while accessing read/write and mmap concurrently. This comes from the infamous mmap_sem usage in copy_from/to_user(). Namely, snd_pcm_oss_write() -> &runtime->oss.params_lock -> copy_to_user() -> &mm->mmap_sem mmap() -> &mm->mmap_sem -> snd_pcm_oss_mmap() -> &runtime->oss.params_lock Since we can't avoid taking params_lock from mmap code path, use trylock variant and aborts with -EAGAIN as a workaround of this AB/BA deadlock. BugLink: http://lkml.kernel.org/r/CACT4Y+bVrBKDG0G2_AcUgUQa+X91VKTeS4v+wN7BSHwHtqn3kQ@mail.gmail.com Reported-by: Dmitry Vyukov Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/core/oss/pcm_oss.c | 21 +++++++++++++++------ 1 file changed, 15 insertions(+), 6 deletions(-) diff --git a/sound/core/oss/pcm_oss.c b/sound/core/oss/pcm_oss.c index 58550cc93f28..33e72c809e50 100644 --- a/sound/core/oss/pcm_oss.c +++ b/sound/core/oss/pcm_oss.c @@ -834,7 +834,8 @@ static int choose_rate(struct snd_pcm_substream *substream, return snd_pcm_hw_param_near(substream, params, SNDRV_PCM_HW_PARAM_RATE, best_rate, NULL); } -static int snd_pcm_oss_change_params(struct snd_pcm_substream *substream) +static int snd_pcm_oss_change_params(struct snd_pcm_substream *substream, + bool trylock) { struct snd_pcm_runtime *runtime = substream->runtime; struct snd_pcm_hw_params *params, *sparams; @@ -848,7 +849,10 @@ static int snd_pcm_oss_change_params(struct snd_pcm_substream *substream) struct snd_mask sformat_mask; struct snd_mask mask; - if (mutex_lock_interruptible(&runtime->oss.params_lock)) + if (trylock) { + if (!(mutex_trylock(&runtime->oss.params_lock))) + return -EAGAIN; + } else if (mutex_lock_interruptible(&runtime->oss.params_lock)) return -EINTR; sw_params = kmalloc(sizeof(*sw_params), GFP_KERNEL); params = kmalloc(sizeof(*params), GFP_KERNEL); @@ -1092,7 +1096,7 @@ static int snd_pcm_oss_get_active_substream(struct snd_pcm_oss_file *pcm_oss_fil if (asubstream == NULL) asubstream = substream; if (substream->runtime->oss.params) { - err = snd_pcm_oss_change_params(substream); + err = snd_pcm_oss_change_params(substream, false); if (err < 0) return err; } @@ -1132,7 +1136,7 @@ static int snd_pcm_oss_make_ready(struct snd_pcm_substream *substream) return 0; runtime = substream->runtime; if (runtime->oss.params) { - err = snd_pcm_oss_change_params(substream); + err = snd_pcm_oss_change_params(substream, false); if (err < 0) return err; } @@ -2163,7 +2167,7 @@ static int snd_pcm_oss_get_space(struct snd_pcm_oss_file *pcm_oss_file, int stre runtime = substream->runtime; if (runtime->oss.params && - (err = snd_pcm_oss_change_params(substream)) < 0) + (err = snd_pcm_oss_change_params(substream, false)) < 0) return err; info.fragsize = runtime->oss.period_bytes; @@ -2800,7 +2804,12 @@ static int snd_pcm_oss_mmap(struct file *file, struct vm_area_struct *area) return -EIO; if (runtime->oss.params) { - if ((err = snd_pcm_oss_change_params(substream)) < 0) + /* use mutex_trylock() for params_lock for avoiding a deadlock + * between mmap_sem and params_lock taken by + * copy_from/to_user() in snd_pcm_oss_write/read() + */ + err = snd_pcm_oss_change_params(substream, true); + if (err < 0) return err; } #ifdef CONFIG_SND_PCM_OSS_PLUGINS From f8ae77d05089c8a7d3b626cd783970a55dba5577 Mon Sep 17 00:00:00 2001 From: Vinod Koul Date: Mon, 1 Feb 2016 22:26:40 +0530 Subject: [PATCH 112/325] ASoC: dpcm: fix the BE state on hw_free commit 5e82d2be6ee53275c72e964507518d7964c82753 upstream. While performing hw_free, DPCM checks the BE state but leaves out the suspend state. The suspend state needs to be checked as well, as we might be suspended and then usermode closes rather than resuming the audio stream. This was found by a stress testing of system with playback in loop and killed after few seconds running in background and second script running suspend-resume test in loop Signed-off-by: Vinod Koul Acked-by: Liam Girdwood Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- sound/soc/soc-pcm.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c index c86dc96e8986..65b936e251ea 100644 --- a/sound/soc/soc-pcm.c +++ b/sound/soc/soc-pcm.c @@ -1743,7 +1743,8 @@ int dpcm_be_dai_hw_free(struct snd_soc_pcm_runtime *fe, int stream) (be->dpcm[stream].state != SND_SOC_DPCM_STATE_PREPARE) && (be->dpcm[stream].state != SND_SOC_DPCM_STATE_HW_FREE) && (be->dpcm[stream].state != SND_SOC_DPCM_STATE_PAUSED) && - (be->dpcm[stream].state != SND_SOC_DPCM_STATE_STOP)) + (be->dpcm[stream].state != SND_SOC_DPCM_STATE_STOP) && + (be->dpcm[stream].state != SND_SOC_DPCM_STATE_SUSPEND)) continue; dev_dbg(be->dev, "ASoC: hw_free BE %s\n", From 3ed5d283254aab50d90525d8ea4dd713aac08d1d Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Sat, 30 Jan 2016 23:30:25 +0100 Subject: [PATCH 113/325] ALSA: seq: Fix yet another races among ALSA timer accesses commit 2cdc7b636d55cbcf42e1e6c8accd85e62d3e9ae8 upstream. ALSA sequencer may open/close and control ALSA timer instance dynamically either via sequencer events or direct ioctls. These are done mostly asynchronously, and it may call still some timer action like snd_timer_start() while another is calling snd_timer_close(). Since the instance gets removed by snd_timer_close(), it may lead to a use-after-free. This patch tries to address such a race by protecting each snd_timer_*() call via the existing spinlock and also by avoiding the access to timer during close call. BugLink: http://lkml.kernel.org/r/CACT4Y+Z6RzW5MBr-HUdV-8zwg71WQfKTdPpYGvOeS7v4cyurNQ@mail.gmail.com Reported-by: Dmitry Vyukov Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/core/seq/seq_timer.c | 87 +++++++++++++++++++++++++++++--------- 1 file changed, 67 insertions(+), 20 deletions(-) diff --git a/sound/core/seq/seq_timer.c b/sound/core/seq/seq_timer.c index 82b220c769c1..293104926098 100644 --- a/sound/core/seq/seq_timer.c +++ b/sound/core/seq/seq_timer.c @@ -90,6 +90,9 @@ void snd_seq_timer_delete(struct snd_seq_timer **tmr) void snd_seq_timer_defaults(struct snd_seq_timer * tmr) { + unsigned long flags; + + spin_lock_irqsave(&tmr->lock, flags); /* setup defaults */ tmr->ppq = 96; /* 96 PPQ */ tmr->tempo = 500000; /* 120 BPM */ @@ -105,21 +108,25 @@ void snd_seq_timer_defaults(struct snd_seq_timer * tmr) tmr->preferred_resolution = seq_default_timer_resolution; tmr->skew = tmr->skew_base = SKEW_BASE; + spin_unlock_irqrestore(&tmr->lock, flags); } -void snd_seq_timer_reset(struct snd_seq_timer * tmr) +static void seq_timer_reset(struct snd_seq_timer *tmr) { - unsigned long flags; - - spin_lock_irqsave(&tmr->lock, flags); - /* reset time & songposition */ tmr->cur_time.tv_sec = 0; tmr->cur_time.tv_nsec = 0; tmr->tick.cur_tick = 0; tmr->tick.fraction = 0; +} +void snd_seq_timer_reset(struct snd_seq_timer *tmr) +{ + unsigned long flags; + + spin_lock_irqsave(&tmr->lock, flags); + seq_timer_reset(tmr); spin_unlock_irqrestore(&tmr->lock, flags); } @@ -138,8 +145,11 @@ static void snd_seq_timer_interrupt(struct snd_timer_instance *timeri, tmr = q->timer; if (tmr == NULL) return; - if (!tmr->running) + spin_lock_irqsave(&tmr->lock, flags); + if (!tmr->running) { + spin_unlock_irqrestore(&tmr->lock, flags); return; + } resolution *= ticks; if (tmr->skew != tmr->skew_base) { @@ -148,8 +158,6 @@ static void snd_seq_timer_interrupt(struct snd_timer_instance *timeri, (((resolution & 0xffff) * tmr->skew) >> 16); } - spin_lock_irqsave(&tmr->lock, flags); - /* update timer */ snd_seq_inc_time_nsec(&tmr->cur_time, resolution); @@ -296,26 +304,30 @@ int snd_seq_timer_open(struct snd_seq_queue *q) t->callback = snd_seq_timer_interrupt; t->callback_data = q; t->flags |= SNDRV_TIMER_IFLG_AUTO; + spin_lock_irq(&tmr->lock); tmr->timeri = t; + spin_unlock_irq(&tmr->lock); return 0; } int snd_seq_timer_close(struct snd_seq_queue *q) { struct snd_seq_timer *tmr; + struct snd_timer_instance *t; tmr = q->timer; if (snd_BUG_ON(!tmr)) return -EINVAL; - if (tmr->timeri) { - snd_timer_stop(tmr->timeri); - snd_timer_close(tmr->timeri); - tmr->timeri = NULL; - } + spin_lock_irq(&tmr->lock); + t = tmr->timeri; + tmr->timeri = NULL; + spin_unlock_irq(&tmr->lock); + if (t) + snd_timer_close(t); return 0; } -int snd_seq_timer_stop(struct snd_seq_timer * tmr) +static int seq_timer_stop(struct snd_seq_timer *tmr) { if (! tmr->timeri) return -EINVAL; @@ -326,6 +338,17 @@ int snd_seq_timer_stop(struct snd_seq_timer * tmr) return 0; } +int snd_seq_timer_stop(struct snd_seq_timer *tmr) +{ + unsigned long flags; + int err; + + spin_lock_irqsave(&tmr->lock, flags); + err = seq_timer_stop(tmr); + spin_unlock_irqrestore(&tmr->lock, flags); + return err; +} + static int initialize_timer(struct snd_seq_timer *tmr) { struct snd_timer *t; @@ -358,13 +381,13 @@ static int initialize_timer(struct snd_seq_timer *tmr) return 0; } -int snd_seq_timer_start(struct snd_seq_timer * tmr) +static int seq_timer_start(struct snd_seq_timer *tmr) { if (! tmr->timeri) return -EINVAL; if (tmr->running) - snd_seq_timer_stop(tmr); - snd_seq_timer_reset(tmr); + seq_timer_stop(tmr); + seq_timer_reset(tmr); if (initialize_timer(tmr) < 0) return -EINVAL; snd_timer_start(tmr->timeri, tmr->ticks); @@ -373,14 +396,25 @@ int snd_seq_timer_start(struct snd_seq_timer * tmr) return 0; } -int snd_seq_timer_continue(struct snd_seq_timer * tmr) +int snd_seq_timer_start(struct snd_seq_timer *tmr) +{ + unsigned long flags; + int err; + + spin_lock_irqsave(&tmr->lock, flags); + err = seq_timer_start(tmr); + spin_unlock_irqrestore(&tmr->lock, flags); + return err; +} + +static int seq_timer_continue(struct snd_seq_timer *tmr) { if (! tmr->timeri) return -EINVAL; if (tmr->running) return -EBUSY; if (! tmr->initialized) { - snd_seq_timer_reset(tmr); + seq_timer_reset(tmr); if (initialize_timer(tmr) < 0) return -EINVAL; } @@ -390,11 +424,24 @@ int snd_seq_timer_continue(struct snd_seq_timer * tmr) return 0; } +int snd_seq_timer_continue(struct snd_seq_timer *tmr) +{ + unsigned long flags; + int err; + + spin_lock_irqsave(&tmr->lock, flags); + err = seq_timer_continue(tmr); + spin_unlock_irqrestore(&tmr->lock, flags); + return err; +} + /* return current 'real' time. use timeofday() to get better granularity. */ snd_seq_real_time_t snd_seq_timer_get_cur_time(struct snd_seq_timer *tmr) { snd_seq_real_time_t cur_time; + unsigned long flags; + spin_lock_irqsave(&tmr->lock, flags); cur_time = tmr->cur_time; if (tmr->running) { struct timeval tm; @@ -410,7 +457,7 @@ snd_seq_real_time_t snd_seq_timer_get_cur_time(struct snd_seq_timer *tmr) } snd_seq_sanity_real_time(&cur_time); } - + spin_unlock_irqrestore(&tmr->lock, flags); return cur_time; } From 80f6a124a398b6e08ee86d3253dd461cfff85fe3 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Mon, 1 Feb 2016 12:06:42 +0100 Subject: [PATCH 114/325] ALSA: seq: Fix race at closing in virmidi driver commit 2d1b5c08366acd46c35a2e9aba5d650cb5bf5c19 upstream. The virmidi driver has an open race at closing its assigned rawmidi device, and this may lead to use-after-free in snd_seq_deliver_single_event(). Plug the hole by properly protecting the linked list deletion and calling in the right order in snd_virmidi_input_close(). BugLink: http://lkml.kernel.org/r/CACT4Y+Zd66+w12fNN85-425cVQT=K23kWbhnCEcMB8s3us-Frw@mail.gmail.com Reported-by: Dmitry Vyukov Tested-by: Dmitry Vyukov Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/core/seq/seq_virmidi.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/sound/core/seq/seq_virmidi.c b/sound/core/seq/seq_virmidi.c index 09b26cb8265a..81134e067184 100644 --- a/sound/core/seq/seq_virmidi.c +++ b/sound/core/seq/seq_virmidi.c @@ -261,9 +261,13 @@ static int snd_virmidi_output_open(struct snd_rawmidi_substream *substream) */ static int snd_virmidi_input_close(struct snd_rawmidi_substream *substream) { + struct snd_virmidi_dev *rdev = substream->rmidi->private_data; struct snd_virmidi *vmidi = substream->runtime->private_data; - snd_midi_event_free(vmidi->parser); + + write_lock_irq(&rdev->filelist_lock); list_del(&vmidi->list); + write_unlock_irq(&rdev->filelist_lock); + snd_midi_event_free(vmidi->parser); substream->runtime->private_data = NULL; kfree(vmidi); return 0; From 144b7ecc3bd6fdf791d54def453d73168d99569f Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Wed, 3 Feb 2016 08:32:44 +0100 Subject: [PATCH 115/325] ALSA: seq: Fix lockdep warnings due to double mutex locks commit 7f0973e973cd74aa40747c9d38844560cd184ee8 upstream. The port subscription code uses double mutex locks for source and destination ports, and this may become racy once when wrongly set up. It leads to lockdep warning splat, typically triggered by fuzzer like syzkaller, although the actual deadlock hasn't been seen, so far. This patch simplifies the handling by reducing to two single locks, so that no lockdep warning will be trigger any longer. By splitting to two actions, a still-in-progress element shall be added in one list while handling another. For ignoring this element, a new check is added in deliver_to_subscribers(). Along with it, the code to add/remove the subscribers list element was cleaned up and refactored. BugLink: http://lkml.kernel.org/r/CACT4Y+aKQXV7xkBW9hpQbzaDO7LrUvohxWh-UwMxXjDy-yBD=A@mail.gmail.com Reported-by: Dmitry Vyukov Tested-by: Dmitry Vyukov Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/core/seq/seq_clientmgr.c | 3 + sound/core/seq/seq_ports.c | 233 ++++++++++++++++++--------------- 2 files changed, 133 insertions(+), 103 deletions(-) diff --git a/sound/core/seq/seq_clientmgr.c b/sound/core/seq/seq_clientmgr.c index 13cfa815732d..58e79e02f217 100644 --- a/sound/core/seq/seq_clientmgr.c +++ b/sound/core/seq/seq_clientmgr.c @@ -678,6 +678,9 @@ static int deliver_to_subscribers(struct snd_seq_client *client, else down_read(&grp->list_mutex); list_for_each_entry(subs, &grp->list_head, src_list) { + /* both ports ready? */ + if (atomic_read(&subs->ref_count) != 2) + continue; event->dest = subs->info.dest; if (subs->info.flags & SNDRV_SEQ_PORT_SUBS_TIMESTAMP) /* convert time according to flag with subscription */ diff --git a/sound/core/seq/seq_ports.c b/sound/core/seq/seq_ports.c index 55170a20ae72..921fb2bd8fad 100644 --- a/sound/core/seq/seq_ports.c +++ b/sound/core/seq/seq_ports.c @@ -173,10 +173,6 @@ struct snd_seq_client_port *snd_seq_create_port(struct snd_seq_client *client, } /* */ -enum group_type { - SRC_LIST, DEST_LIST -}; - static int subscribe_port(struct snd_seq_client *client, struct snd_seq_client_port *port, struct snd_seq_port_subs_info *grp, @@ -203,6 +199,20 @@ static struct snd_seq_client_port *get_client_port(struct snd_seq_addr *addr, return NULL; } +static void delete_and_unsubscribe_port(struct snd_seq_client *client, + struct snd_seq_client_port *port, + struct snd_seq_subscribers *subs, + bool is_src, bool ack); + +static inline struct snd_seq_subscribers * +get_subscriber(struct list_head *p, bool is_src) +{ + if (is_src) + return list_entry(p, struct snd_seq_subscribers, src_list); + else + return list_entry(p, struct snd_seq_subscribers, dest_list); +} + /* * remove all subscribers on the list * this is called from port_delete, for each src and dest list. @@ -210,7 +220,7 @@ static struct snd_seq_client_port *get_client_port(struct snd_seq_addr *addr, static void clear_subscriber_list(struct snd_seq_client *client, struct snd_seq_client_port *port, struct snd_seq_port_subs_info *grp, - int grptype) + int is_src) { struct list_head *p, *n; @@ -219,15 +229,13 @@ static void clear_subscriber_list(struct snd_seq_client *client, struct snd_seq_client *c; struct snd_seq_client_port *aport; - if (grptype == SRC_LIST) { - subs = list_entry(p, struct snd_seq_subscribers, src_list); + subs = get_subscriber(p, is_src); + if (is_src) aport = get_client_port(&subs->info.dest, &c); - } else { - subs = list_entry(p, struct snd_seq_subscribers, dest_list); + else aport = get_client_port(&subs->info.sender, &c); - } - list_del(p); - unsubscribe_port(client, port, grp, &subs->info, 0); + delete_and_unsubscribe_port(client, port, subs, is_src, false); + if (!aport) { /* looks like the connected port is being deleted. * we decrease the counter, and when both ports are deleted @@ -235,21 +243,14 @@ static void clear_subscriber_list(struct snd_seq_client *client, */ if (atomic_dec_and_test(&subs->ref_count)) kfree(subs); - } else { - /* ok we got the connected port */ - struct snd_seq_port_subs_info *agrp; - agrp = (grptype == SRC_LIST) ? &aport->c_dest : &aport->c_src; - down_write(&agrp->list_mutex); - if (grptype == SRC_LIST) - list_del(&subs->dest_list); - else - list_del(&subs->src_list); - up_write(&agrp->list_mutex); - unsubscribe_port(c, aport, agrp, &subs->info, 1); - kfree(subs); - snd_seq_port_unlock(aport); - snd_seq_client_unlock(c); + continue; } + + /* ok we got the connected port */ + delete_and_unsubscribe_port(c, aport, subs, !is_src, true); + kfree(subs); + snd_seq_port_unlock(aport); + snd_seq_client_unlock(c); } } @@ -262,8 +263,8 @@ static int port_delete(struct snd_seq_client *client, snd_use_lock_sync(&port->use_lock); /* clear subscribers info */ - clear_subscriber_list(client, port, &port->c_src, SRC_LIST); - clear_subscriber_list(client, port, &port->c_dest, DEST_LIST); + clear_subscriber_list(client, port, &port->c_src, true); + clear_subscriber_list(client, port, &port->c_dest, false); if (port->private_free) port->private_free(port->private_data); @@ -479,6 +480,75 @@ static int match_subs_info(struct snd_seq_port_subscribe *r, return 0; } +static int check_and_subscribe_port(struct snd_seq_client *client, + struct snd_seq_client_port *port, + struct snd_seq_subscribers *subs, + bool is_src, bool exclusive, bool ack) +{ + struct snd_seq_port_subs_info *grp; + struct list_head *p; + struct snd_seq_subscribers *s; + int err; + + grp = is_src ? &port->c_src : &port->c_dest; + err = -EBUSY; + down_write(&grp->list_mutex); + if (exclusive) { + if (!list_empty(&grp->list_head)) + goto __error; + } else { + if (grp->exclusive) + goto __error; + /* check whether already exists */ + list_for_each(p, &grp->list_head) { + s = get_subscriber(p, is_src); + if (match_subs_info(&subs->info, &s->info)) + goto __error; + } + } + + err = subscribe_port(client, port, grp, &subs->info, ack); + if (err < 0) { + grp->exclusive = 0; + goto __error; + } + + /* add to list */ + write_lock_irq(&grp->list_lock); + if (is_src) + list_add_tail(&subs->src_list, &grp->list_head); + else + list_add_tail(&subs->dest_list, &grp->list_head); + grp->exclusive = exclusive; + atomic_inc(&subs->ref_count); + write_unlock_irq(&grp->list_lock); + err = 0; + + __error: + up_write(&grp->list_mutex); + return err; +} + +static void delete_and_unsubscribe_port(struct snd_seq_client *client, + struct snd_seq_client_port *port, + struct snd_seq_subscribers *subs, + bool is_src, bool ack) +{ + struct snd_seq_port_subs_info *grp; + + grp = is_src ? &port->c_src : &port->c_dest; + down_write(&grp->list_mutex); + write_lock_irq(&grp->list_lock); + if (is_src) + list_del(&subs->src_list); + else + list_del(&subs->dest_list); + grp->exclusive = 0; + write_unlock_irq(&grp->list_lock); + up_write(&grp->list_mutex); + + unsubscribe_port(client, port, grp, &subs->info, ack); +} /* connect two ports */ int snd_seq_port_connect(struct snd_seq_client *connector, @@ -488,76 +558,42 @@ int snd_seq_port_connect(struct snd_seq_client *connector, struct snd_seq_client_port *dest_port, struct snd_seq_port_subscribe *info) { - struct snd_seq_port_subs_info *src = &src_port->c_src; - struct snd_seq_port_subs_info *dest = &dest_port->c_dest; - struct snd_seq_subscribers *subs, *s; - int err, src_called = 0; - unsigned long flags; - int exclusive; + struct snd_seq_subscribers *subs; + bool exclusive; + int err; subs = kzalloc(sizeof(*subs), GFP_KERNEL); - if (! subs) + if (!subs) return -ENOMEM; subs->info = *info; - atomic_set(&subs->ref_count, 2); + atomic_set(&subs->ref_count, 0); + INIT_LIST_HEAD(&subs->src_list); + INIT_LIST_HEAD(&subs->dest_list); - down_write(&src->list_mutex); - down_write_nested(&dest->list_mutex, SINGLE_DEPTH_NESTING); + exclusive = !!(info->flags & SNDRV_SEQ_PORT_SUBS_EXCLUSIVE); - exclusive = info->flags & SNDRV_SEQ_PORT_SUBS_EXCLUSIVE ? 1 : 0; - err = -EBUSY; - if (exclusive) { - if (! list_empty(&src->list_head) || ! list_empty(&dest->list_head)) - goto __error; - } else { - if (src->exclusive || dest->exclusive) - goto __error; - /* check whether already exists */ - list_for_each_entry(s, &src->list_head, src_list) { - if (match_subs_info(info, &s->info)) - goto __error; - } - list_for_each_entry(s, &dest->list_head, dest_list) { - if (match_subs_info(info, &s->info)) - goto __error; - } - } + err = check_and_subscribe_port(src_client, src_port, subs, true, + exclusive, + connector->number != src_client->number); + if (err < 0) + goto error; + err = check_and_subscribe_port(dest_client, dest_port, subs, false, + exclusive, + connector->number != dest_client->number); + if (err < 0) + goto error_dest; - if ((err = subscribe_port(src_client, src_port, src, info, - connector->number != src_client->number)) < 0) - goto __error; - src_called = 1; - - if ((err = subscribe_port(dest_client, dest_port, dest, info, - connector->number != dest_client->number)) < 0) - goto __error; - - /* add to list */ - write_lock_irqsave(&src->list_lock, flags); - // write_lock(&dest->list_lock); // no other lock yet - list_add_tail(&subs->src_list, &src->list_head); - list_add_tail(&subs->dest_list, &dest->list_head); - // write_unlock(&dest->list_lock); // no other lock yet - write_unlock_irqrestore(&src->list_lock, flags); - - src->exclusive = dest->exclusive = exclusive; - - up_write(&dest->list_mutex); - up_write(&src->list_mutex); return 0; - __error: - if (src_called) - unsubscribe_port(src_client, src_port, src, info, - connector->number != src_client->number); + error_dest: + delete_and_unsubscribe_port(src_client, src_port, subs, true, + connector->number != src_client->number); + error: kfree(subs); - up_write(&dest->list_mutex); - up_write(&src->list_mutex); return err; } - /* remove the connection */ int snd_seq_port_disconnect(struct snd_seq_client *connector, struct snd_seq_client *src_client, @@ -567,37 +603,28 @@ int snd_seq_port_disconnect(struct snd_seq_client *connector, struct snd_seq_port_subscribe *info) { struct snd_seq_port_subs_info *src = &src_port->c_src; - struct snd_seq_port_subs_info *dest = &dest_port->c_dest; struct snd_seq_subscribers *subs; int err = -ENOENT; - unsigned long flags; down_write(&src->list_mutex); - down_write_nested(&dest->list_mutex, SINGLE_DEPTH_NESTING); - /* look for the connection */ list_for_each_entry(subs, &src->list_head, src_list) { if (match_subs_info(info, &subs->info)) { - write_lock_irqsave(&src->list_lock, flags); - // write_lock(&dest->list_lock); // no lock yet - list_del(&subs->src_list); - list_del(&subs->dest_list); - // write_unlock(&dest->list_lock); - write_unlock_irqrestore(&src->list_lock, flags); - src->exclusive = dest->exclusive = 0; - unsubscribe_port(src_client, src_port, src, info, - connector->number != src_client->number); - unsubscribe_port(dest_client, dest_port, dest, info, - connector->number != dest_client->number); - kfree(subs); + atomic_dec(&subs->ref_count); /* mark as not ready */ err = 0; break; } } - - up_write(&dest->list_mutex); up_write(&src->list_mutex); - return err; + if (err < 0) + return err; + + delete_and_unsubscribe_port(src_client, src_port, subs, true, + connector->number != src_client->number); + delete_and_unsubscribe_port(dest_client, dest_port, subs, false, + connector->number != dest_client->number); + kfree(subs); + return 0; } From 3f75d8ad63e42d5e1f46bd7fc2ba643cda3aa5e7 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Thu, 14 Jan 2016 17:01:46 +0100 Subject: [PATCH 116/325] ALSA: timer: Code cleanup commit c3b1681375dc6e71d89a3ae00cc3ce9e775a8917 upstream. This is a minor code cleanup without any functional changes: - Kill keep_flag argument from _snd_timer_stop(), as all callers pass only it false. - Remove redundant NULL check in _snd_timer_stop(). Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/core/timer.c | 28 +++++++++++----------------- 1 file changed, 11 insertions(+), 17 deletions(-) diff --git a/sound/core/timer.c b/sound/core/timer.c index 0a049c4578f1..681fb051b9eb 100644 --- a/sound/core/timer.c +++ b/sound/core/timer.c @@ -305,8 +305,7 @@ int snd_timer_open(struct snd_timer_instance **ti, return 0; } -static int _snd_timer_stop(struct snd_timer_instance *timeri, - int keep_flag, int event); +static int _snd_timer_stop(struct snd_timer_instance *timeri, int event); /* * close a timer instance @@ -348,7 +347,7 @@ int snd_timer_close(struct snd_timer_instance *timeri) spin_unlock_irq(&timer->lock); mutex_lock(®ister_mutex); list_del(&timeri->open_list); - if (timer && list_empty(&timer->open_list_head) && + if (list_empty(&timer->open_list_head) && timer->hw.close) timer->hw.close(timer); /* remove slave links */ @@ -493,8 +492,7 @@ int snd_timer_start(struct snd_timer_instance *timeri, unsigned int ticks) return result; } -static int _snd_timer_stop(struct snd_timer_instance * timeri, - int keep_flag, int event) +static int _snd_timer_stop(struct snd_timer_instance *timeri, int event) { struct snd_timer *timer; unsigned long flags; @@ -503,13 +501,11 @@ static int _snd_timer_stop(struct snd_timer_instance * timeri, return -ENXIO; if (timeri->flags & SNDRV_TIMER_IFLG_SLAVE) { - if (!keep_flag) { - spin_lock_irqsave(&slave_active_lock, flags); - timeri->flags &= ~SNDRV_TIMER_IFLG_RUNNING; - list_del_init(&timeri->ack_list); - list_del_init(&timeri->active_list); - spin_unlock_irqrestore(&slave_active_lock, flags); - } + spin_lock_irqsave(&slave_active_lock, flags); + timeri->flags &= ~SNDRV_TIMER_IFLG_RUNNING; + list_del_init(&timeri->ack_list); + list_del_init(&timeri->active_list); + spin_unlock_irqrestore(&slave_active_lock, flags); goto __end; } timer = timeri->timer; @@ -534,9 +530,7 @@ static int _snd_timer_stop(struct snd_timer_instance * timeri, } } } - if (!keep_flag) - timeri->flags &= - ~(SNDRV_TIMER_IFLG_RUNNING | SNDRV_TIMER_IFLG_START); + timeri->flags &= ~(SNDRV_TIMER_IFLG_RUNNING | SNDRV_TIMER_IFLG_START); spin_unlock_irqrestore(&timer->lock, flags); __end: if (event != SNDRV_TIMER_EVENT_RESOLUTION) @@ -555,7 +549,7 @@ int snd_timer_stop(struct snd_timer_instance *timeri) unsigned long flags; int err; - err = _snd_timer_stop(timeri, 0, SNDRV_TIMER_EVENT_STOP); + err = _snd_timer_stop(timeri, SNDRV_TIMER_EVENT_STOP); if (err < 0) return err; timer = timeri->timer; @@ -601,7 +595,7 @@ int snd_timer_continue(struct snd_timer_instance *timeri) */ int snd_timer_pause(struct snd_timer_instance * timeri) { - return _snd_timer_stop(timeri, 0, SNDRV_TIMER_EVENT_PAUSE); + return _snd_timer_stop(timeri, SNDRV_TIMER_EVENT_PAUSE); } /* From 43d2ac7b542a862b55d22d179468df5290590801 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Thu, 4 Feb 2016 17:06:13 +0100 Subject: [PATCH 117/325] ALSA: timer: Fix leftover link at closing commit 094fd3be87b0f102589e2d5c3fa5d06b7e20496d upstream. In ALSA timer core, the active timer instance is managed in active_list linked list. Each element is added / removed dynamically at timer start, stop and in timer interrupt. The problem is that snd_timer_interrupt() has a thinko and leaves the element in active_list when it's the last opened element. This eventually leads to list corruption or use-after-free error. This hasn't been revealed because we used to delete the list forcibly in snd_timer_stop() in the past. However, the recent fix avoids the double-stop behavior (in commit [f784beb75ce8: ALSA: timer: Fix link corruption due to double start or stop]), and this leak hits reality. This patch fixes the link management in snd_timer_interrupt(). Now it simply unlinks no matter which stream is. BugLink: http://lkml.kernel.org/r/CACT4Y+Yy2aukHP-EDp8-ziNqNNmb-NTf=jDWXMP7jB8HDa2vng@mail.gmail.com Reported-by: Dmitry Vyukov Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/core/timer.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/sound/core/timer.c b/sound/core/timer.c index 681fb051b9eb..b036e080382c 100644 --- a/sound/core/timer.c +++ b/sound/core/timer.c @@ -718,8 +718,8 @@ void snd_timer_interrupt(struct snd_timer * timer, unsigned long ticks_left) ti->cticks = ti->ticks; } else { ti->flags &= ~SNDRV_TIMER_IFLG_RUNNING; - if (--timer->running) - list_del_init(&ti->active_list); + --timer->running; + list_del_init(&ti->active_list); } if ((timer->hw.flags & SNDRV_TIMER_HW_TASKLET) || (ti->flags & SNDRV_TIMER_IFLG_FAST)) From ce60478a9959a8e1d1dcc70325e72678e78d85c5 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Sat, 30 Jan 2016 23:09:08 +0100 Subject: [PATCH 118/325] ALSA: timer: Fix link corruption due to double start or stop commit f784beb75ce82f4136f8a0960d3ee872f7109e09 upstream. Although ALSA timer code got hardening for races, it still causes use-after-free error. This is however rather a corrupted linked list, not actually the concurrent accesses. Namely, when timer start is triggered twice, list_add_tail() is called twice, too. This ends up with the link corruption and triggers KASAN error. The simplest fix would be replacing list_add_tail() with list_move_tail(), but fundamentally it's the problem that we don't check the double start/stop correctly. So, the right fix here is to add the proper checks to snd_timer_start() and snd_timer_stop() (and their variants). BugLink: http://lkml.kernel.org/r/CACT4Y+ZyPRoMQjmawbvmCEDrkBD2BQuH7R09=eOkf5ESK8kJAw@mail.gmail.com Reported-by: Dmitry Vyukov Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/core/timer.c | 30 ++++++++++++++++++++++++++++-- 1 file changed, 28 insertions(+), 2 deletions(-) diff --git a/sound/core/timer.c b/sound/core/timer.c index b036e080382c..a011b67cf2b6 100644 --- a/sound/core/timer.c +++ b/sound/core/timer.c @@ -451,6 +451,10 @@ static int snd_timer_start_slave(struct snd_timer_instance *timeri) unsigned long flags; spin_lock_irqsave(&slave_active_lock, flags); + if (timeri->flags & SNDRV_TIMER_IFLG_RUNNING) { + spin_unlock_irqrestore(&slave_active_lock, flags); + return -EBUSY; + } timeri->flags |= SNDRV_TIMER_IFLG_RUNNING; if (timeri->master && timeri->timer) { spin_lock(&timeri->timer->lock); @@ -475,7 +479,8 @@ int snd_timer_start(struct snd_timer_instance *timeri, unsigned int ticks) return -EINVAL; if (timeri->flags & SNDRV_TIMER_IFLG_SLAVE) { result = snd_timer_start_slave(timeri); - snd_timer_notify1(timeri, SNDRV_TIMER_EVENT_START); + if (result >= 0) + snd_timer_notify1(timeri, SNDRV_TIMER_EVENT_START); return result; } timer = timeri->timer; @@ -484,11 +489,18 @@ int snd_timer_start(struct snd_timer_instance *timeri, unsigned int ticks) if (timer->card && timer->card->shutdown) return -ENODEV; spin_lock_irqsave(&timer->lock, flags); + if (timeri->flags & (SNDRV_TIMER_IFLG_RUNNING | + SNDRV_TIMER_IFLG_START)) { + result = -EBUSY; + goto unlock; + } timeri->ticks = timeri->cticks = ticks; timeri->pticks = 0; result = snd_timer_start1(timer, timeri, ticks); + unlock: spin_unlock_irqrestore(&timer->lock, flags); - snd_timer_notify1(timeri, SNDRV_TIMER_EVENT_START); + if (result >= 0) + snd_timer_notify1(timeri, SNDRV_TIMER_EVENT_START); return result; } @@ -502,6 +514,10 @@ static int _snd_timer_stop(struct snd_timer_instance *timeri, int event) if (timeri->flags & SNDRV_TIMER_IFLG_SLAVE) { spin_lock_irqsave(&slave_active_lock, flags); + if (!(timeri->flags & SNDRV_TIMER_IFLG_RUNNING)) { + spin_unlock_irqrestore(&slave_active_lock, flags); + return -EBUSY; + } timeri->flags &= ~SNDRV_TIMER_IFLG_RUNNING; list_del_init(&timeri->ack_list); list_del_init(&timeri->active_list); @@ -512,6 +528,11 @@ static int _snd_timer_stop(struct snd_timer_instance *timeri, int event) if (!timer) return -EINVAL; spin_lock_irqsave(&timer->lock, flags); + if (!(timeri->flags & (SNDRV_TIMER_IFLG_RUNNING | + SNDRV_TIMER_IFLG_START))) { + spin_unlock_irqrestore(&timer->lock, flags); + return -EBUSY; + } list_del_init(&timeri->ack_list); list_del_init(&timeri->active_list); if (timer->card && timer->card->shutdown) { @@ -581,10 +602,15 @@ int snd_timer_continue(struct snd_timer_instance *timeri) if (timer->card && timer->card->shutdown) return -ENODEV; spin_lock_irqsave(&timer->lock, flags); + if (timeri->flags & SNDRV_TIMER_IFLG_RUNNING) { + result = -EBUSY; + goto unlock; + } if (!timeri->cticks) timeri->cticks = 1; timeri->pticks = 0; result = snd_timer_start1(timer, timeri, timer->sticks); + unlock: spin_unlock_irqrestore(&timer->lock, flags); snd_timer_notify1(timeri, SNDRV_TIMER_EVENT_CONTINUE); return result; From 925249d5172a31d7d430fdf364fc9229223c7942 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Mon, 8 Feb 2016 17:26:58 +0100 Subject: [PATCH 119/325] ALSA: timer: Fix race at concurrent reads commit 4dff5c7b7093b19c19d3a100f8a3ad87cb7cd9e7 upstream. snd_timer_user_read() has a potential race among parallel reads, as qhead and qused are updated outside the critical section due to copy_to_user() calls. Move them into the critical section, and also sanitize the relevant code a bit. Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/core/timer.c | 34 +++++++++++++++------------------- 1 file changed, 15 insertions(+), 19 deletions(-) diff --git a/sound/core/timer.c b/sound/core/timer.c index a011b67cf2b6..87be17112573 100644 --- a/sound/core/timer.c +++ b/sound/core/timer.c @@ -1920,6 +1920,7 @@ static ssize_t snd_timer_user_read(struct file *file, char __user *buffer, { struct snd_timer_user *tu; long result = 0, unit; + int qhead; int err = 0; tu = file->private_data; @@ -1931,7 +1932,7 @@ static ssize_t snd_timer_user_read(struct file *file, char __user *buffer, if ((file->f_flags & O_NONBLOCK) != 0 || result > 0) { err = -EAGAIN; - break; + goto _error; } set_current_state(TASK_INTERRUPTIBLE); @@ -1946,42 +1947,37 @@ static ssize_t snd_timer_user_read(struct file *file, char __user *buffer, if (tu->disconnected) { err = -ENODEV; - break; + goto _error; } if (signal_pending(current)) { err = -ERESTARTSYS; - break; + goto _error; } } + qhead = tu->qhead++; + tu->qhead %= tu->queue_size; spin_unlock_irq(&tu->qlock); - if (err < 0) - goto _error; if (tu->tread) { - if (copy_to_user(buffer, &tu->tqueue[tu->qhead++], - sizeof(struct snd_timer_tread))) { + if (copy_to_user(buffer, &tu->tqueue[qhead], + sizeof(struct snd_timer_tread))) err = -EFAULT; - goto _error; - } } else { - if (copy_to_user(buffer, &tu->queue[tu->qhead++], - sizeof(struct snd_timer_read))) { + if (copy_to_user(buffer, &tu->queue[qhead], + sizeof(struct snd_timer_read))) err = -EFAULT; - goto _error; - } } - tu->qhead %= tu->queue_size; - - result += unit; - buffer += unit; - spin_lock_irq(&tu->qlock); tu->qused--; + if (err < 0) + goto _error; + result += unit; + buffer += unit; } - spin_unlock_irq(&tu->qlock); _error: + spin_unlock_irq(&tu->qlock); return result > 0 ? result : err; } From 4333cce1e75701f5ffb0f17cbe43c170e09e7e46 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Mon, 8 Feb 2016 17:36:25 +0100 Subject: [PATCH 120/325] ALSA: timer: Fix wrong instance passed to slave callbacks commit 117159f0b9d392fb433a7871426fad50317f06f7 upstream. In snd_timer_notify1(), the wrong timer instance was passed for slave ccallback function. This leads to the access to the wrong data when an incompatible master is handled (e.g. the master is the sequencer timer and the slave is a user timer), as spotted by syzkaller fuzzer. This patch fixes that wrong assignment. BugLink: http://lkml.kernel.org/r/CACT4Y+Y_Bm+7epAb=8Wi=AaWd+DYS7qawX52qxdCfOfY49vozQ@mail.gmail.com Reported-by: Dmitry Vyukov Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/core/timer.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/core/timer.c b/sound/core/timer.c index 87be17112573..9e45178231fa 100644 --- a/sound/core/timer.c +++ b/sound/core/timer.c @@ -422,7 +422,7 @@ static void snd_timer_notify1(struct snd_timer_instance *ti, int event) spin_lock_irqsave(&timer->lock, flags); list_for_each_entry(ts, &ti->slave_active_head, active_list) if (ts->ccallback) - ts->ccallback(ti, event + 100, &tstamp, resolution); + ts->ccallback(ts, event + 100, &tstamp, resolution); spin_unlock_irqrestore(&timer->lock, flags); } From 92cc7c5788b090c2a15d5dfdfdcb772d9b25e91a Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Tue, 9 Feb 2016 12:02:32 +0100 Subject: [PATCH 121/325] ALSA: timer: Fix race between stop and interrupt commit ed8b1d6d2c741ab26d60d499d7fbb7ac801f0f51 upstream. A slave timer element also unlinks at snd_timer_stop() but it takes only slave_active_lock. When a slave is assigned to a master, however, this may become a race against the master's interrupt handling, eventually resulting in a list corruption. The actual bug could be seen with a syzkaller fuzzer test case in BugLink below. As a fix, we need to take timeri->timer->lock when timer isn't NULL, i.e. assigned to a master, while the assignment to a master itself is protected by slave_active_lock. BugLink: http://lkml.kernel.org/r/CACT4Y+Y_Bm+7epAb=8Wi=AaWd+DYS7qawX52qxdCfOfY49vozQ@mail.gmail.com Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/core/timer.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/sound/core/timer.c b/sound/core/timer.c index 9e45178231fa..f24c9fccf008 100644 --- a/sound/core/timer.c +++ b/sound/core/timer.c @@ -518,9 +518,13 @@ static int _snd_timer_stop(struct snd_timer_instance *timeri, int event) spin_unlock_irqrestore(&slave_active_lock, flags); return -EBUSY; } + if (timeri->timer) + spin_lock(&timeri->timer->lock); timeri->flags &= ~SNDRV_TIMER_IFLG_RUNNING; list_del_init(&timeri->ack_list); list_del_init(&timeri->active_list); + if (timeri->timer) + spin_unlock(&timeri->timer->lock); spin_unlock_irqrestore(&slave_active_lock, flags); goto __end; } From 32495f0543b10630a2ecc2ed5432b13d85358496 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Wed, 3 Feb 2016 12:32:51 +0100 Subject: [PATCH 122/325] ALSA: hda - Add fixup for Mac Mini 7,1 model commit 2154cc0e2d4ae15132d005d17e473327c70c9a06 upstream. Mac Mini 7,1 model with CS4208 codec reports the headphone jack detection wrongly in an inverted way. Moreover, the advertised pins for the audio input and SPDIF output have actually no jack detection. This patch addresses these issues. The inv_jack_detect flag is set for fixing the headphone jack detection, and the pin configs for audio input and SPDIF output are marked as non-detectable. Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=105161 Report-and-tested-by: moosotc@gmail.com Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/pci/hda/patch_cirrus.c | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) diff --git a/sound/pci/hda/patch_cirrus.c b/sound/pci/hda/patch_cirrus.c index a12ae8ac0914..c1c855a6c0af 100644 --- a/sound/pci/hda/patch_cirrus.c +++ b/sound/pci/hda/patch_cirrus.c @@ -614,6 +614,7 @@ enum { CS4208_MAC_AUTO, CS4208_MBA6, CS4208_MBP11, + CS4208_MACMINI, CS4208_GPIO0, }; @@ -621,6 +622,7 @@ static const struct hda_model_fixup cs4208_models[] = { { .id = CS4208_GPIO0, .name = "gpio0" }, { .id = CS4208_MBA6, .name = "mba6" }, { .id = CS4208_MBP11, .name = "mbp11" }, + { .id = CS4208_MACMINI, .name = "macmini" }, {} }; @@ -632,6 +634,7 @@ static const struct snd_pci_quirk cs4208_fixup_tbl[] = { /* codec SSID matching */ static const struct snd_pci_quirk cs4208_mac_fixup_tbl[] = { SND_PCI_QUIRK(0x106b, 0x5e00, "MacBookPro 11,2", CS4208_MBP11), + SND_PCI_QUIRK(0x106b, 0x6c00, "MacMini 7,1", CS4208_MACMINI), SND_PCI_QUIRK(0x106b, 0x7100, "MacBookAir 6,1", CS4208_MBA6), SND_PCI_QUIRK(0x106b, 0x7200, "MacBookAir 6,2", CS4208_MBA6), SND_PCI_QUIRK(0x106b, 0x7b00, "MacBookPro 12,1", CS4208_MBP11), @@ -666,6 +669,24 @@ static void cs4208_fixup_mac(struct hda_codec *codec, snd_hda_apply_fixup(codec, action); } +/* MacMini 7,1 has the inverted jack detection */ +static void cs4208_fixup_macmini(struct hda_codec *codec, + const struct hda_fixup *fix, int action) +{ + static const struct hda_pintbl pincfgs[] = { + { 0x18, 0x00ab9150 }, /* mic (audio-in) jack: disable detect */ + { 0x21, 0x004be140 }, /* SPDIF: disable detect */ + { } + }; + + if (action == HDA_FIXUP_ACT_PRE_PROBE) { + /* HP pin (0x10) has an inverted detection */ + codec->inv_jack_detect = 1; + /* disable the bogus Mic and SPDIF jack detections */ + snd_hda_apply_pincfgs(codec, pincfgs); + } +} + static int cs4208_spdif_sw_put(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol) { @@ -709,6 +730,12 @@ static const struct hda_fixup cs4208_fixups[] = { .chained = true, .chain_id = CS4208_GPIO0, }, + [CS4208_MACMINI] = { + .type = HDA_FIXUP_FUNC, + .v.func = cs4208_fixup_macmini, + .chained = true, + .chain_id = CS4208_GPIO0, + }, [CS4208_GPIO0] = { .type = HDA_FIXUP_FUNC, .v.func = cs4208_fixup_gpio0, From c9a35bd4bc91c98895b1f2d4392f003828caa9ed Mon Sep 17 00:00:00 2001 From: David Henningsson Date: Fri, 5 Feb 2016 09:05:41 +0100 Subject: [PATCH 123/325] ALSA: hda - Fix static checker warning in patch_hdmi.c commit 360a8245680053619205a3ae10e6bfe624a5da1d upstream. The static checker warning is: sound/pci/hda/patch_hdmi.c:460 hdmi_eld_ctl_get() error: __memcpy() 'eld->eld_buffer' too small (256 vs 512) I have a hard time figuring out if this can ever cause an information leak (I don't think so), but nonetheless it does not hurt to increase the robustness of the code. Fixes: 68e03de98507 ('ALSA: hda - hdmi: Do not expose eld data when eld is invalid') Reported-by: Dan Carpenter Signed-off-by: David Henningsson Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/pci/hda/patch_hdmi.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index 4b6fb668c91c..24582e7cccbb 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -438,7 +438,8 @@ static int hdmi_eld_ctl_get(struct snd_kcontrol *kcontrol, eld = &per_pin->sink_eld; mutex_lock(&per_pin->lock); - if (eld->eld_size > ARRAY_SIZE(ucontrol->value.bytes.data)) { + if (eld->eld_size > ARRAY_SIZE(ucontrol->value.bytes.data) || + eld->eld_size > ELD_MAX_SIZE) { mutex_unlock(&per_pin->lock); snd_BUG(); return -EINVAL; From dc4d5c42bf59682a82ccd8c67eee5313e6c43c63 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Fri, 5 Feb 2016 20:12:24 +0100 Subject: [PATCH 124/325] Revert "ALSA: hda - Fix noise on Gigabyte Z170X mobo" commit 6c361d10e0eb859233c71954abcd20d2d8700587 upstream. This reverts commit 0c25ad80408e95e0a4fbaf0056950206e95f726f. The original commit disabled the aamixer path due to the noise problem, but it turned out that some mobo with the same PCI SSID doesn't suffer from the issue, and the disabled function (analog loopback) is still demanded by users. Since the recent commit [e7fdd52779a6: ALSA: hda - Implement loopback control switch for Realtek and other codecs], we have the dynamic mixer switch to enable/disable the aamix path, and we don't have to disable the path statically any longer. So, let's revert the disablement, so that only the user suffering from the noise problem can turn off the aamix on the fly. Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=108301 Reported-by: Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/pci/hda/patch_realtek.c | 8 -------- 1 file changed, 8 deletions(-) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 21992fb7035d..a733e5dc701d 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -1787,7 +1787,6 @@ enum { ALC882_FIXUP_NO_PRIMARY_HP, ALC887_FIXUP_ASUS_BASS, ALC887_FIXUP_BASS_CHMAP, - ALC882_FIXUP_DISABLE_AAMIX, }; static void alc889_fixup_coef(struct hda_codec *codec, @@ -1949,8 +1948,6 @@ static void alc882_fixup_no_primary_hp(struct hda_codec *codec, static void alc_fixup_bass_chmap(struct hda_codec *codec, const struct hda_fixup *fix, int action); -static void alc_fixup_disable_aamix(struct hda_codec *codec, - const struct hda_fixup *fix, int action); static const struct hda_fixup alc882_fixups[] = { [ALC882_FIXUP_ABIT_AW9D_MAX] = { @@ -2188,10 +2185,6 @@ static const struct hda_fixup alc882_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = alc_fixup_bass_chmap, }, - [ALC882_FIXUP_DISABLE_AAMIX] = { - .type = HDA_FIXUP_FUNC, - .v.func = alc_fixup_disable_aamix, - }, }; static const struct snd_pci_quirk alc882_fixup_tbl[] = { @@ -2259,7 +2252,6 @@ static const struct snd_pci_quirk alc882_fixup_tbl[] = { SND_PCI_QUIRK(0x1462, 0x7350, "MSI-7350", ALC889_FIXUP_CD), SND_PCI_QUIRK_VENDOR(0x1462, "MSI", ALC882_FIXUP_GPIO3), SND_PCI_QUIRK(0x1458, 0xa002, "Gigabyte EP45-DS3/Z87X-UD3H", ALC889_FIXUP_FRONT_HP_NO_PRESENCE), - SND_PCI_QUIRK(0x1458, 0xa182, "Gigabyte Z170X-UD3", ALC882_FIXUP_DISABLE_AAMIX), SND_PCI_QUIRK(0x147b, 0x107a, "Abit AW9D-MAX", ALC882_FIXUP_ABIT_AW9D_MAX), SND_PCI_QUIRK_VENDOR(0x1558, "Clevo laptop", ALC882_FIXUP_EAPD), SND_PCI_QUIRK(0x161f, 0x2054, "Medion laptop", ALC883_FIXUP_EAPD), From 1d9c34c147785319d16cb0e9be6a791bc446b334 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Sun, 7 Feb 2016 09:38:26 +0100 Subject: [PATCH 125/325] ALSA: hda - Fix speaker output from VAIO AiO machines commit c44d9b1181cf34e0860c72cc8a00e0c47417aac0 upstream. Some Sony VAIO AiO models (VGC-JS4EF and VGC-JS25G, both with PCI SSID 104d:9044) need the same quirk to make the speaker working properly. Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=112031 Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/pci/hda/patch_realtek.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index a733e5dc701d..b43c0f7994eb 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -2223,6 +2223,7 @@ static const struct snd_pci_quirk alc882_fixup_tbl[] = { SND_PCI_QUIRK(0x104d, 0x9047, "Sony Vaio TT", ALC889_FIXUP_VAIO_TT), SND_PCI_QUIRK(0x104d, 0x905a, "Sony Vaio Z", ALC882_FIXUP_NO_PRIMARY_HP), SND_PCI_QUIRK(0x104d, 0x9043, "Sony Vaio VGC-LN51JGB", ALC882_FIXUP_NO_PRIMARY_HP), + SND_PCI_QUIRK(0x104d, 0x9044, "Sony VAIO AiO", ALC882_FIXUP_NO_PRIMARY_HP), /* All Apple entries are in codec SSIDs */ SND_PCI_QUIRK(0x106b, 0x00a0, "MacBookPro 3,1", ALC889_FIXUP_MBP_VREF), From fc1cf67cbf44ea100c9994d8d6a594415926eab8 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Tue, 9 Feb 2016 10:23:52 +0100 Subject: [PATCH 126/325] ALSA: hda - Fix bad dereference of jack object commit 2ebab40eb74a0225d5dfba72bfae317dd948fa2d upstream. The hda_jack_tbl entries are managed by snd_array for allowing multiple jacks. It's good per se, but the problem is that struct hda_jack_callback keeps the hda_jack_tbl pointer. Since snd_array doesn't preserve each pointer at resizing the array, we can't keep the original pointer but have to deduce the pointer at each time via snd_array_entry() instead. Actually, this resulted in the deference to the wrong pointer on codecs that have many pins such as CS4208. This patch replaces the pointer to the NID value as the search key. As an unexpected good side effect, this even simplifies the code, as only NID is needed in most cases. Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/pci/hda/hda_generic.c | 4 ++-- sound/pci/hda/hda_jack.c | 2 +- sound/pci/hda/hda_jack.h | 2 +- sound/pci/hda/patch_ca0132.c | 5 ++++- sound/pci/hda/patch_hdmi.c | 2 +- sound/pci/hda/patch_realtek.c | 2 +- sound/pci/hda/patch_sigmatel.c | 6 +++--- 7 files changed, 13 insertions(+), 10 deletions(-) diff --git a/sound/pci/hda/hda_generic.c b/sound/pci/hda/hda_generic.c index 9d6be68c611b..5c4fa8eba1d0 100644 --- a/sound/pci/hda/hda_generic.c +++ b/sound/pci/hda/hda_generic.c @@ -4045,9 +4045,9 @@ static void pin_power_callback(struct hda_codec *codec, struct hda_jack_callback *jack, bool on) { - if (jack && jack->tbl->nid) + if (jack && jack->nid) sync_power_state_change(codec, - set_pin_power_jack(codec, jack->tbl->nid, on)); + set_pin_power_jack(codec, jack->nid, on)); } /* callback only doing power up -- called at first */ diff --git a/sound/pci/hda/hda_jack.c b/sound/pci/hda/hda_jack.c index c945e257d368..a33234e04d4f 100644 --- a/sound/pci/hda/hda_jack.c +++ b/sound/pci/hda/hda_jack.c @@ -259,7 +259,7 @@ snd_hda_jack_detect_enable_callback(struct hda_codec *codec, hda_nid_t nid, if (!callback) return ERR_PTR(-ENOMEM); callback->func = func; - callback->tbl = jack; + callback->nid = jack->nid; callback->next = jack->callback; jack->callback = callback; } diff --git a/sound/pci/hda/hda_jack.h b/sound/pci/hda/hda_jack.h index 858708a044f5..e9814c0168ea 100644 --- a/sound/pci/hda/hda_jack.h +++ b/sound/pci/hda/hda_jack.h @@ -21,7 +21,7 @@ struct hda_jack_callback; typedef void (*hda_jack_callback_fn) (struct hda_codec *, struct hda_jack_callback *); struct hda_jack_callback { - struct hda_jack_tbl *tbl; + hda_nid_t nid; hda_jack_callback_fn func; unsigned int private_data; /* arbitrary data */ struct hda_jack_callback *next; diff --git a/sound/pci/hda/patch_ca0132.c b/sound/pci/hda/patch_ca0132.c index 4ef2259f88ca..9ceb2bc36e68 100644 --- a/sound/pci/hda/patch_ca0132.c +++ b/sound/pci/hda/patch_ca0132.c @@ -4427,13 +4427,16 @@ static void ca0132_process_dsp_response(struct hda_codec *codec, static void hp_callback(struct hda_codec *codec, struct hda_jack_callback *cb) { struct ca0132_spec *spec = codec->spec; + struct hda_jack_tbl *tbl; /* Delay enabling the HP amp, to let the mic-detection * state machine run. */ cancel_delayed_work_sync(&spec->unsol_hp_work); schedule_delayed_work(&spec->unsol_hp_work, msecs_to_jiffies(500)); - cb->tbl->block_report = 1; + tbl = snd_hda_jack_tbl_get(codec, cb->nid); + if (tbl) + tbl->block_report = 1; } static void amic_callback(struct hda_codec *codec, struct hda_jack_callback *cb) diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index 24582e7cccbb..70c945603379 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -1184,7 +1184,7 @@ static void check_presence_and_report(struct hda_codec *codec, hda_nid_t nid) static void jack_callback(struct hda_codec *codec, struct hda_jack_callback *jack) { - check_presence_and_report(codec, jack->tbl->nid); + check_presence_and_report(codec, jack->nid); } static void hdmi_intrinsic_event(struct hda_codec *codec, unsigned int res) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index b43c0f7994eb..efd4980cffb8 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -282,7 +282,7 @@ static void alc_update_knob_master(struct hda_codec *codec, uctl = kzalloc(sizeof(*uctl), GFP_KERNEL); if (!uctl) return; - val = snd_hda_codec_read(codec, jack->tbl->nid, 0, + val = snd_hda_codec_read(codec, jack->nid, 0, AC_VERB_GET_VOLUME_KNOB_CONTROL, 0); val &= HDA_AMP_VOLMASK; uctl->value.integer.value[0] = val; diff --git a/sound/pci/hda/patch_sigmatel.c b/sound/pci/hda/patch_sigmatel.c index 2c7c5eb8b1e9..37b70f8e878f 100644 --- a/sound/pci/hda/patch_sigmatel.c +++ b/sound/pci/hda/patch_sigmatel.c @@ -493,9 +493,9 @@ static void jack_update_power(struct hda_codec *codec, if (!spec->num_pwrs) return; - if (jack && jack->tbl->nid) { - stac_toggle_power_map(codec, jack->tbl->nid, - snd_hda_jack_detect(codec, jack->tbl->nid), + if (jack && jack->nid) { + stac_toggle_power_map(codec, jack->nid, + snd_hda_jack_detect(codec, jack->nid), true); return; } From 4634f985fb4a43a89f1b6523509d30de4651ef89 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Tue, 2 Feb 2016 15:27:36 +0100 Subject: [PATCH 127/325] ALSA: dummy: Implement timer backend switching more safely commit ddce57a6f0a2d8d1bfacfa77f06043bc760403c2 upstream. Currently the selected timer backend is referred at any moment from the running PCM callbacks. When the backend is switched, it's possible to lead to inconsistency from the running backend. This was pointed by syzkaller fuzzer, and the commit [7ee96216c31a: ALSA: dummy: Disable switching timer backend via sysfs] disabled the dynamic switching for avoiding the crash. This patch improves the handling of timer backend switching. It keeps the reference to the selected backend during the whole operation of an opened stream so that it won't be changed by other streams. Together with this change, the hrtimer parameter is reenabled as writable now. NOTE: this patch also turned out to fix the still remaining race. Namely, ops was still replaced dynamically at dummy_pcm_open: static int dummy_pcm_open(struct snd_pcm_substream *substream) { .... dummy->timer_ops = &dummy_systimer_ops; if (hrtimer) dummy->timer_ops = &dummy_hrtimer_ops; Since dummy->timer_ops is common among all streams, and when the replacement happens during accesses of other streams, it may lead to a crash. This was actually triggered by syzkaller fuzzer and KASAN. This patch rewrites the code not to use the ops shared by all streams any longer, too. BugLink: http://lkml.kernel.org/r/CACT4Y+aZ+xisrpuM6cOXbL21DuM0yVxPYXf4cD4Md9uw0C3dBQ@mail.gmail.com Reported-by: Dmitry Vyukov Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/drivers/dummy.c | 37 +++++++++++++++++++------------------ 1 file changed, 19 insertions(+), 18 deletions(-) diff --git a/sound/drivers/dummy.c b/sound/drivers/dummy.c index df8e757deb58..a9f7a75702d2 100644 --- a/sound/drivers/dummy.c +++ b/sound/drivers/dummy.c @@ -87,7 +87,7 @@ MODULE_PARM_DESC(pcm_substreams, "PCM substreams # (1-128) for dummy driver."); module_param(fake_buffer, bool, 0444); MODULE_PARM_DESC(fake_buffer, "Fake buffer allocations."); #ifdef CONFIG_HIGH_RES_TIMERS -module_param(hrtimer, bool, 0444); +module_param(hrtimer, bool, 0644); MODULE_PARM_DESC(hrtimer, "Use hrtimer as the timer source."); #endif @@ -109,6 +109,9 @@ struct dummy_timer_ops { snd_pcm_uframes_t (*pointer)(struct snd_pcm_substream *); }; +#define get_dummy_ops(substream) \ + (*(const struct dummy_timer_ops **)(substream)->runtime->private_data) + struct dummy_model { const char *name; int (*playback_constraints)(struct snd_pcm_runtime *runtime); @@ -137,7 +140,6 @@ struct snd_dummy { int iobox; struct snd_kcontrol *cd_volume_ctl; struct snd_kcontrol *cd_switch_ctl; - const struct dummy_timer_ops *timer_ops; }; /* @@ -231,6 +233,8 @@ static struct dummy_model *dummy_models[] = { */ struct dummy_systimer_pcm { + /* ops must be the first item */ + const struct dummy_timer_ops *timer_ops; spinlock_t lock; struct timer_list timer; unsigned long base_time; @@ -366,6 +370,8 @@ static struct dummy_timer_ops dummy_systimer_ops = { */ struct dummy_hrtimer_pcm { + /* ops must be the first item */ + const struct dummy_timer_ops *timer_ops; ktime_t base_time; ktime_t period_time; atomic_t running; @@ -492,31 +498,25 @@ static struct dummy_timer_ops dummy_hrtimer_ops = { static int dummy_pcm_trigger(struct snd_pcm_substream *substream, int cmd) { - struct snd_dummy *dummy = snd_pcm_substream_chip(substream); - switch (cmd) { case SNDRV_PCM_TRIGGER_START: case SNDRV_PCM_TRIGGER_RESUME: - return dummy->timer_ops->start(substream); + return get_dummy_ops(substream)->start(substream); case SNDRV_PCM_TRIGGER_STOP: case SNDRV_PCM_TRIGGER_SUSPEND: - return dummy->timer_ops->stop(substream); + return get_dummy_ops(substream)->stop(substream); } return -EINVAL; } static int dummy_pcm_prepare(struct snd_pcm_substream *substream) { - struct snd_dummy *dummy = snd_pcm_substream_chip(substream); - - return dummy->timer_ops->prepare(substream); + return get_dummy_ops(substream)->prepare(substream); } static snd_pcm_uframes_t dummy_pcm_pointer(struct snd_pcm_substream *substream) { - struct snd_dummy *dummy = snd_pcm_substream_chip(substream); - - return dummy->timer_ops->pointer(substream); + return get_dummy_ops(substream)->pointer(substream); } static struct snd_pcm_hardware dummy_pcm_hardware = { @@ -562,17 +562,19 @@ static int dummy_pcm_open(struct snd_pcm_substream *substream) struct snd_dummy *dummy = snd_pcm_substream_chip(substream); struct dummy_model *model = dummy->model; struct snd_pcm_runtime *runtime = substream->runtime; + const struct dummy_timer_ops *ops; int err; - dummy->timer_ops = &dummy_systimer_ops; + ops = &dummy_systimer_ops; #ifdef CONFIG_HIGH_RES_TIMERS if (hrtimer) - dummy->timer_ops = &dummy_hrtimer_ops; + ops = &dummy_hrtimer_ops; #endif - err = dummy->timer_ops->create(substream); + err = ops->create(substream); if (err < 0) return err; + get_dummy_ops(substream) = ops; runtime->hw = dummy->pcm_hw; if (substream->pcm->device & 1) { @@ -594,7 +596,7 @@ static int dummy_pcm_open(struct snd_pcm_substream *substream) err = model->capture_constraints(substream->runtime); } if (err < 0) { - dummy->timer_ops->free(substream); + get_dummy_ops(substream)->free(substream); return err; } return 0; @@ -602,8 +604,7 @@ static int dummy_pcm_open(struct snd_pcm_substream *substream) static int dummy_pcm_close(struct snd_pcm_substream *substream) { - struct snd_dummy *dummy = snd_pcm_substream_chip(substream); - dummy->timer_ops->free(substream); + get_dummy_ops(substream)->free(substream); return 0; } From 18203289cea5010bc5dac4cebcdff91af76b8b6c Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Thu, 4 Feb 2016 15:59:43 -0200 Subject: [PATCH 128/325] saa7134-alsa: Only frees registered sound cards commit ac75fe5d8fe4a0bf063be18fb29684405279e79e upstream. That prevents this bug: [ 2382.269496] BUG: unable to handle kernel NULL pointer dereference at 0000000000000540 [ 2382.270013] IP: [] snd_card_free+0x36/0x70 [snd] [ 2382.270013] PGD 0 [ 2382.270013] Oops: 0002 [#1] SMP [ 2382.270013] Modules linked in: saa7134_alsa(-) tda1004x saa7134_dvb videobuf2_dvb dvb_core tda827x tda8290 tuner saa7134 tveeprom videobuf2_dma_sg videobuf2_memops videobuf2_v4l2 videobuf2_core v4l2_common videodev media auth_rpcgss nfsv4 dns_resolver nfs lockd grace sunrpc tun bridge stp llc ebtables ip6table_filter ip6_tables nf_conntrack_ipv4 nf_defrag_ipv4 xt_conntrack nf_conntrack it87 hwmon_vid snd_hda_codec_idt snd_hda_codec_generic iTCO_wdt iTCO_vendor_support snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core snd_seq pcspkr i2c_i801 snd_seq_device snd_pcm snd_timer lpc_ich snd mfd_core soundcore binfmt_misc i915 video i2c_algo_bit drm_kms_helper drm r8169 ata_generic serio_raw pata_acpi mii i2c_core [last unloaded: videobuf2_memops] [ 2382.270013] CPU: 0 PID: 4899 Comm: rmmod Not tainted 4.5.0-rc1+ #4 [ 2382.270013] Hardware name: PCCHIPS P17G/P17G, BIOS 080012 05/14/2008 [ 2382.270013] task: ffff880039c38000 ti: ffff88003c764000 task.ti: ffff88003c764000 [ 2382.270013] RIP: 0010:[] [] snd_card_free+0x36/0x70 [snd] [ 2382.270013] RSP: 0018:ffff88003c767ea0 EFLAGS: 00010286 [ 2382.270013] RAX: ffff88003c767eb8 RBX: 0000000000000000 RCX: 0000000000006260 [ 2382.270013] RDX: ffffffffa020a060 RSI: ffffffffa0206de1 RDI: ffff88003c767eb0 [ 2382.270013] RBP: ffff88003c767ed8 R08: 0000000000019960 R09: ffffffff811a5412 [ 2382.270013] R10: ffffea0000d7c200 R11: 0000000000000000 R12: ffff88003c767ea8 [ 2382.270013] R13: 00007ffe760617f7 R14: 0000000000000000 R15: 0000557625d7f1e0 [ 2382.270013] FS: 00007f80bb1c0700(0000) GS:ffff88003f400000(0000) knlGS:0000000000000000 [ 2382.270013] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b [ 2382.270013] CR2: 0000000000000540 CR3: 000000003c00f000 CR4: 00000000000006f0 [ 2382.270013] Stack: [ 2382.270013] 000000003c767ed8 ffffffff00000000 ffff880000000000 ffff88003c767eb8 [ 2382.270013] ffff88003c767eb8 ffffffffa049a890 00007ffe76060060 ffff88003c767ef0 [ 2382.270013] ffffffffa049889d ffffffffa049a500 ffff88003c767f48 ffffffff8111079c [ 2382.270013] Call Trace: [ 2382.270013] [] saa7134_alsa_exit+0x1d/0x780 [saa7134_alsa] [ 2382.270013] [] SyS_delete_module+0x19c/0x1f0 [ 2382.270013] [] entry_SYSCALL_64_fastpath+0x12/0x71 [ 2382.270013] Code: 20 a0 48 c7 c6 e1 6d 20 a0 48 89 e5 41 54 53 4c 8d 65 d0 48 89 fb 48 83 ec 28 c7 45 d0 00 00 00 00 49 8d 7c 24 08 e8 7a 55 ed e0 <4c> 89 a3 40 05 00 00 48 89 df e8 eb fd ff ff 85 c0 75 1a 48 8d [ 2382.270013] RIP [] snd_card_free+0x36/0x70 [snd] [ 2382.270013] RSP [ 2382.270013] CR2: 0000000000000540 Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Greg Kroah-Hartman --- drivers/media/pci/saa7134/saa7134-alsa.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/media/pci/saa7134/saa7134-alsa.c b/drivers/media/pci/saa7134/saa7134-alsa.c index 1d2c310ce838..94f816244407 100644 --- a/drivers/media/pci/saa7134/saa7134-alsa.c +++ b/drivers/media/pci/saa7134/saa7134-alsa.c @@ -1211,6 +1211,8 @@ static int alsa_device_init(struct saa7134_dev *dev) static int alsa_device_exit(struct saa7134_dev *dev) { + if (!snd_saa7134_cards[dev->nr]) + return 1; snd_card_free(snd_saa7134_cards[dev->nr]); snd_saa7134_cards[dev->nr] = NULL; @@ -1260,7 +1262,8 @@ static void saa7134_alsa_exit(void) int idx; for (idx = 0; idx < SNDRV_CARDS; idx++) { - snd_card_free(snd_saa7134_cards[idx]); + if (snd_saa7134_cards[idx]) + snd_card_free(snd_saa7134_cards[idx]); } saa7134_dmasound_init = NULL; From 2bbe5162bacd8b8f120b08f641bf695329d90017 Mon Sep 17 00:00:00 2001 From: Bard Liao Date: Thu, 21 Jan 2016 13:13:40 +0800 Subject: [PATCH 129/325] ASoC: rt5645: fix the shift bit of IN1 boost commit b28785fa9cede0d4f47310ca0dd2a4e1d50478b5 upstream. The shift bit of IN1 boost gain control is 12. Signed-off-by: Bard Liao Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- sound/soc/codecs/rt5645.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/soc/codecs/rt5645.c b/sound/soc/codecs/rt5645.c index 3e3c7f6be29d..b74840b5becf 100644 --- a/sound/soc/codecs/rt5645.c +++ b/sound/soc/codecs/rt5645.c @@ -621,7 +621,7 @@ static const struct snd_kcontrol_new rt5645_snd_controls[] = { /* IN1/IN2 Control */ SOC_SINGLE_TLV("IN1 Boost", RT5645_IN1_CTRL1, - RT5645_BST_SFT1, 8, 0, bst_tlv), + RT5645_BST_SFT1, 12, 0, bst_tlv), SOC_SINGLE_TLV("IN2 Boost", RT5645_IN2_CTRL, RT5645_BST_SFT2, 8, 0, bst_tlv), From 2dc803d0740f0c493a7db8a1baf6514d5b95b6a3 Mon Sep 17 00:00:00 2001 From: Vladis Dronov Date: Tue, 12 Jan 2016 15:10:50 +0100 Subject: [PATCH 130/325] USB: serial: visor: fix crash on detecting device without write_urbs commit cb3232138e37129e88240a98a1d2aba2187ff57c upstream. The visor driver crashes in clie_5_attach() when a specially crafted USB device without bulk-out endpoint is detected. This fix adds a check that the device has proper configuration expected by the driver. Reported-by: Ralf Spenneberg Signed-off-by: Vladis Dronov Fixes: cfb8da8f69b8 ("USB: visor: fix initialisation of UX50/TH55 devices") Signed-off-by: Johan Hovold Signed-off-by: Greg Kroah-Hartman --- drivers/usb/serial/visor.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/usb/serial/visor.c b/drivers/usb/serial/visor.c index 60afb39eb73c..bbc90c059002 100644 --- a/drivers/usb/serial/visor.c +++ b/drivers/usb/serial/visor.c @@ -597,8 +597,10 @@ static int clie_5_attach(struct usb_serial *serial) */ /* some sanity check */ - if (serial->num_ports < 2) - return -1; + if (serial->num_bulk_out < 2) { + dev_err(&serial->interface->dev, "missing bulk out endpoints\n"); + return -ENODEV; + } /* port 0 now uses the modified endpoint Address */ port = serial->port[0]; From ee4207bda5e15d0eecb834c4fc39c6069487279d Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Tue, 12 Jan 2016 12:05:20 +0100 Subject: [PATCH 131/325] USB: visor: fix null-deref at probe commit cac9b50b0d75a1d50d6c056ff65c005f3224c8e0 upstream. Fix null-pointer dereference at probe should a (malicious) Treo device lack the expected endpoints. Specifically, the Treo port-setup hack was dereferencing the bulk-in and interrupt-in urbs without first making sure they had been allocated by core. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Johan Hovold Signed-off-by: Greg Kroah-Hartman --- drivers/usb/serial/visor.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/usb/serial/visor.c b/drivers/usb/serial/visor.c index bbc90c059002..337a0be89fcf 100644 --- a/drivers/usb/serial/visor.c +++ b/drivers/usb/serial/visor.c @@ -544,6 +544,11 @@ static int treo_attach(struct usb_serial *serial) (serial->num_interrupt_in == 0)) return 0; + if (serial->num_bulk_in < 2 || serial->num_interrupt_in < 2) { + dev_err(&serial->interface->dev, "missing endpoints\n"); + return -ENODEV; + } + /* * It appears that Treos and Kyoceras want to use the * 1st bulk in endpoint to communicate with the 2nd bulk out endpoint, From c9b1074e18b607f54ac195959d5a4daacaa81325 Mon Sep 17 00:00:00 2001 From: "Du, Changbin" Date: Mon, 18 Jan 2016 21:02:42 +0800 Subject: [PATCH 132/325] usb: hub: do not clear BOS field during reset device commit d8f00cd685f5c8e0def8593e520a7fef12c22407 upstream. In function usb_reset_and_verify_device, the old BOS descriptor may still be used before allocating a new one. (usb_unlocked_disable_lpm function uses it under the situation that it fails to disable lpm.) So we cannot set the udev->bos to NULL before that, just keep what it was. It will be overwrite when allocating a new one. Crash log: BUG: unable to handle kernel NULL pointer dereference at 0000000000000010 IP: [] usb_enable_link_state+0x2d/0x2f0 Call Trace: [] ? usb_set_lpm_timeout+0x12b/0x140 [] usb_enable_lpm+0x81/0xa0 [] usb_disable_lpm+0xa8/0xc0 [] usb_unlocked_disable_lpm+0x2c/0x50 [] usb_reset_and_verify_device+0xc3/0x710 [] ? usb_sg_wait+0x13d/0x190 [] usb_reset_device+0x133/0x280 [] usb_stor_port_reset+0x61/0x70 [] usb_stor_invoke_transport+0x88/0x520 Signed-off-by: Du, Changbin Signed-off-by: Greg Kroah-Hartman --- drivers/usb/core/hub.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index 8683436788c3..1560f3f3e756 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -5386,7 +5386,6 @@ static int usb_reset_and_verify_device(struct usb_device *udev) } bos = udev->bos; - udev->bos = NULL; for (i = 0; i < SET_CONFIG_TRIES; ++i) { @@ -5479,8 +5478,11 @@ done: usb_set_usb2_hardware_lpm(udev, 1); usb_unlocked_enable_lpm(udev); usb_enable_ltm(udev); - usb_release_bos_descriptor(udev); - udev->bos = bos; + /* release the new BOS descriptor allocated by hub_port_init() */ + if (udev->bos != bos) { + usb_release_bos_descriptor(udev); + udev->bos = bos; + } return 0; re_enumerate: From f463b2e192a0576fe988c694fbd4c4c809ddae7f Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 19 Jan 2016 23:43:13 -0800 Subject: [PATCH 133/325] USB: serial: ftdi_sio: add support for Yaesu SCU-18 cable commit e03cdf22a2727c60307be6a729233edab3bfda9c upstream. Harald Linden reports that the ftdi_sio driver works properly for the Yaesu SCU-18 cable if the device ids are added to the driver. So let's add them. Reported-by: Harald Linden Signed-off-by: Greg Kroah-Hartman Signed-off-by: Johan Hovold Signed-off-by: Greg Kroah-Hartman --- drivers/usb/serial/ftdi_sio.c | 1 + drivers/usb/serial/ftdi_sio_ids.h | 1 + 2 files changed, 2 insertions(+) diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c index a5a0376bbd48..8c660ae401d8 100644 --- a/drivers/usb/serial/ftdi_sio.c +++ b/drivers/usb/serial/ftdi_sio.c @@ -824,6 +824,7 @@ static const struct usb_device_id id_table_combined[] = { { USB_DEVICE(FTDI_VID, FTDI_TURTELIZER_PID), .driver_info = (kernel_ulong_t)&ftdi_jtag_quirk }, { USB_DEVICE(RATOC_VENDOR_ID, RATOC_PRODUCT_ID_USB60F) }, + { USB_DEVICE(RATOC_VENDOR_ID, RATOC_PRODUCT_ID_SCU18) }, { USB_DEVICE(FTDI_VID, FTDI_REU_TINY_PID) }, /* Papouch devices based on FTDI chip */ diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h index 67c6d4469730..a84df2513994 100644 --- a/drivers/usb/serial/ftdi_sio_ids.h +++ b/drivers/usb/serial/ftdi_sio_ids.h @@ -615,6 +615,7 @@ */ #define RATOC_VENDOR_ID 0x0584 #define RATOC_PRODUCT_ID_USB60F 0xb020 +#define RATOC_PRODUCT_ID_SCU18 0xb03a /* * Infineon Technologies From 7e13854aa55956198eda63095bb0ec9022816811 Mon Sep 17 00:00:00 2001 From: Peter Dedecker Date: Fri, 8 Jan 2016 12:34:41 +0100 Subject: [PATCH 134/325] USB: cp210x: add ID for IAI USB to RS485 adaptor commit f487c54ddd544e1c9172cd510954f697b77b76e3 upstream. Added the USB serial console device ID for IAI Corp. RCB-CV-USB USB to RS485 adaptor. Signed-off-by: Peter Dedecker Signed-off-by: Johan Hovold Signed-off-by: Greg Kroah-Hartman --- drivers/usb/serial/cp210x.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c index 59b2126b21a3..1dd9919081f8 100644 --- a/drivers/usb/serial/cp210x.c +++ b/drivers/usb/serial/cp210x.c @@ -98,6 +98,7 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x10C4, 0x81AC) }, /* MSD Dash Hawk */ { USB_DEVICE(0x10C4, 0x81AD) }, /* INSYS USB Modem */ { USB_DEVICE(0x10C4, 0x81C8) }, /* Lipowsky Industrie Elektronik GmbH, Baby-JTAG */ + { USB_DEVICE(0x10C4, 0x81D7) }, /* IAI Corp. RCB-CV-USB USB to RS485 Adaptor */ { USB_DEVICE(0x10C4, 0x81E2) }, /* Lipowsky Industrie Elektronik GmbH, Baby-LIN */ { USB_DEVICE(0x10C4, 0x81E7) }, /* Aerocomm Radio */ { USB_DEVICE(0x10C4, 0x81E8) }, /* Zephyr Bioharness */ From 185db3a5ab58e2d4fbc54176e755bf53398e37e1 Mon Sep 17 00:00:00 2001 From: Daniele Palmas Date: Tue, 12 Jan 2016 17:22:06 +0100 Subject: [PATCH 135/325] USB: serial: option: Adding support for Telit LE922 commit ff4e2494dc17b173468e1713fdf6237fd8578bc7 upstream. This patch adds support for two PIDs of LE922. Signed-off-by: Daniele Palmas Signed-off-by: Johan Hovold Signed-off-by: Greg Kroah-Hartman --- drivers/usb/serial/option.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index f2280606b73c..75350fc550a1 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -268,6 +268,8 @@ static void option_instat_callback(struct urb *urb); #define TELIT_PRODUCT_CC864_SINGLE 0x1006 #define TELIT_PRODUCT_DE910_DUAL 0x1010 #define TELIT_PRODUCT_UE910_V2 0x1012 +#define TELIT_PRODUCT_LE922_USBCFG0 0x1042 +#define TELIT_PRODUCT_LE922_USBCFG3 0x1043 #define TELIT_PRODUCT_LE920 0x1200 #define TELIT_PRODUCT_LE910 0x1201 @@ -615,6 +617,16 @@ static const struct option_blacklist_info telit_le920_blacklist = { .reserved = BIT(1) | BIT(5), }; +static const struct option_blacklist_info telit_le922_blacklist_usbcfg0 = { + .sendsetup = BIT(2), + .reserved = BIT(0) | BIT(1) | BIT(3), +}; + +static const struct option_blacklist_info telit_le922_blacklist_usbcfg3 = { + .sendsetup = BIT(0), + .reserved = BIT(1) | BIT(2) | BIT(3), +}; + static const struct usb_device_id option_ids[] = { { USB_DEVICE(OPTION_VENDOR_ID, OPTION_PRODUCT_COLT) }, { USB_DEVICE(OPTION_VENDOR_ID, OPTION_PRODUCT_RICOLA) }, @@ -1160,6 +1172,10 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_CC864_SINGLE) }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_DE910_DUAL) }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_UE910_V2) }, + { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE922_USBCFG0), + .driver_info = (kernel_ulong_t)&telit_le922_blacklist_usbcfg0 }, + { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE922_USBCFG3), + .driver_info = (kernel_ulong_t)&telit_le922_blacklist_usbcfg3 }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE910), .driver_info = (kernel_ulong_t)&telit_le910_blacklist }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE920), From 8d85f027360ac66c481751b458153ee0cc0da37c Mon Sep 17 00:00:00 2001 From: John Ernberg Date: Mon, 25 Jan 2016 12:27:17 +0000 Subject: [PATCH 136/325] USB: option: fix Cinterion AHxx enumeration commit 4152b387da81617c80cb2946b2d56e3958906b3e upstream. In certain kernel configurations where the cdc_ether and option drivers are compiled as modules there can occur a race condition in enumeration. This causes the option driver to enumerate the ethernet(wwan) interface as usb-serial interfaces. usb-devices output for the modem: T: Bus=01 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#= 5 Spd=480 MxCh= 0 D: Ver= 2.00 Cls=ef(misc ) Sub=02 Prot=01 MxPS=64 #Cfgs= 1 P: Vendor=1e2d ProdID=0055 Rev=00.00 S: Manufacturer=Cinterion S: Product=AHx C: #Ifs= 6 Cfg#= 1 Atr=e0 MxPwr=10mA I: If#= 0 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option I: If#= 1 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option I: If#= 2 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option I: If#= 3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=option I: If#= 4 Alt= 0 #EPs= 1 Cls=02(commc) Sub=06 Prot=00 Driver=cdc_ether I: If#= 5 Alt= 1 #EPs= 2 Cls=0a(data ) Sub=00 Prot=00 Driver=cdc_ether Signed-off-by: John Ernberg Fixes: 1941138e1c02 ("USB: added support for Cinterion's products...") Signed-off-by: Johan Hovold Signed-off-by: Greg Kroah-Hartman --- drivers/usb/serial/option.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 75350fc550a1..db86e512e0fc 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -1695,7 +1695,7 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE(CINTERION_VENDOR_ID, CINTERION_PRODUCT_EU3_P) }, { USB_DEVICE(CINTERION_VENDOR_ID, CINTERION_PRODUCT_PH8), .driver_info = (kernel_ulong_t)&net_intf4_blacklist }, - { USB_DEVICE(CINTERION_VENDOR_ID, CINTERION_PRODUCT_AHXX) }, + { USB_DEVICE_INTERFACE_CLASS(CINTERION_VENDOR_ID, CINTERION_PRODUCT_AHXX, 0xff) }, { USB_DEVICE(CINTERION_VENDOR_ID, CINTERION_PRODUCT_PLXX), .driver_info = (kernel_ulong_t)&net_intf4_blacklist }, { USB_DEVICE(CINTERION_VENDOR_ID, CINTERION_PRODUCT_HC28_MDM) }, From 858e9d4a226435e45401757ccda952254e4e251c Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Wed, 30 Dec 2015 12:59:08 +0800 Subject: [PATCH 137/325] usb: cdc-acm: handle unlinked urb in acm read callback commit 19454462acb1bdef80542061bdc9b410e4ed1ff6 upstream. In current acm driver, the bulk-in callback function ignores the URBs unlinked in usb core. This causes unexpected data loss in some cases. For example, runtime suspend entry will unlinked all urbs and set urb->status to -ENOENT even those urbs might have data not processed yet. Hence, data loss occurs. This patch lets bulk-in callback function handle unlinked urbs to avoid data loss. Signed-off-by: Tang Jian Qiang Signed-off-by: Lu Baolu Acked-by: Oliver Neukum Signed-off-by: Greg Kroah-Hartman --- drivers/usb/class/cdc-acm.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c index 26ca4f910cb0..8cd193bbd044 100644 --- a/drivers/usb/class/cdc-acm.c +++ b/drivers/usb/class/cdc-acm.c @@ -428,7 +428,8 @@ static void acm_read_bulk_callback(struct urb *urb) set_bit(rb->index, &acm->read_urbs_free); dev_dbg(&acm->data->dev, "%s - non-zero urb status: %d\n", __func__, status); - return; + if ((status != -ENOENT) || (urb->actual_length == 0)) + return; } usb_mark_last_busy(acm->dev); From dde53ae3ad07b6b3978d5dc22633edbaa42db431 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Wed, 6 Jan 2016 15:10:04 +0800 Subject: [PATCH 138/325] usb: cdc-acm: send zero packet for intel 7260 modem commit ffdb1e369a73b380fce95b05f8498d92c43842b4 upstream. For Intel 7260 modem, it is needed for host side to send zero packet if the BULK OUT size is equal to USB endpoint max packet length. Otherwise, modem side may still wait for more data and cannot give response to host side. Signed-off-by: Konrad Leszczynski Signed-off-by: Lu Baolu Signed-off-by: Greg Kroah-Hartman --- drivers/usb/class/cdc-acm.c | 6 ++++++ drivers/usb/class/cdc-acm.h | 1 + 2 files changed, 7 insertions(+) diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c index 8cd193bbd044..e4c70dce3e7c 100644 --- a/drivers/usb/class/cdc-acm.c +++ b/drivers/usb/class/cdc-acm.c @@ -1405,6 +1405,8 @@ made_compressed_probe: usb_sndbulkpipe(usb_dev, epwrite->bEndpointAddress), NULL, acm->writesize, acm_write_bulk, snd); snd->urb->transfer_flags |= URB_NO_TRANSFER_DMA_MAP; + if (quirks & SEND_ZERO_PACKET) + snd->urb->transfer_flags |= URB_ZERO_PACKET; snd->instance = acm; } @@ -1862,6 +1864,10 @@ static const struct usb_device_id acm_ids[] = { { USB_INTERFACE_INFO(USB_CLASS_COMM, USB_CDC_SUBCLASS_ACM, USB_CDC_ACM_PROTO_AT_CDMA) }, + { USB_DEVICE(0x1519, 0x0452), /* Intel 7260 modem */ + .driver_info = SEND_ZERO_PACKET, + }, + { } }; diff --git a/drivers/usb/class/cdc-acm.h b/drivers/usb/class/cdc-acm.h index dd9af38e7cda..ccfaba9ab4e4 100644 --- a/drivers/usb/class/cdc-acm.h +++ b/drivers/usb/class/cdc-acm.h @@ -134,3 +134,4 @@ struct acm { #define IGNORE_DEVICE BIT(5) #define QUIRK_CONTROL_LINE_STATE BIT(6) #define CLEAR_HALT_CONDITIONS BIT(7) +#define SEND_ZERO_PACKET BIT(8) From 7ab0e9d0a2283c6d1f2337847b89f86c53a1f9b7 Mon Sep 17 00:00:00 2001 From: Srinivas Kandagatla Date: Wed, 13 Jan 2016 09:13:10 +0000 Subject: [PATCH 139/325] usb: phy: msm: fix error handling in probe. commit a38a08dfaaab978dced63aa9cad45f0f62e23a66 upstream. This driver registers for extcon events as part of its probe, but never unregisters them in case of error in the probe path. There were multiple issues noticed due to this missing error handling. One of them is random crashes if the regulators are not ready yet by the time probe is invoked. Ivan's previous attempt [1] to fix this issue, did not really address all the failure cases like regualtor/get_irq failures. [1] https://lkml.org/lkml/2015/9/7/62 Without this patch the kernel would carsh with log: ... Unable to handle kernel paging request at virtual address 17d78410 pgd = ffffffc001a5c000 [17d78410] *pgd=00000000b6806003, *pud=00000000b6806003, *pmd=0000000000000000 Internal error: Oops: 96000005 [#1] PREEMPT SMP Modules linked in: CPU: 0 PID: 6 Comm: kworker/u8:0 Not tainted 4.4.0+ #48 Hardware name: Qualcomm Technologies, Inc. APQ 8016 SBC (DT) Workqueue: deferwq deferred_probe_work_func task: ffffffc03686e900 ti: ffffffc0368b0000 task.ti: ffffffc0368b0000 PC is at raw_notifier_chain_register+0x1c/0x44 LR is at extcon_register_notifier+0x88/0xc8 pc : [] lr : [] pstate: 80000085 sp : ffffffc0368b3a70 x29: ffffffc0368b3a70 x28: ffffffc03680c310 x27: ffffffc035518000 x26: ffffffc035518000 x25: ffffffc03bfa20e0 x24: ffffffc035580a18 x23: 0000000000000000 x22: ffffffc035518458 x21: ffffffc0355e9a60 x20: ffffffc035518000 x19: 0000000000000000 x18: 0000000000000028 x17: 0000000000000003 x16: ffffffc0018153c8 x15: 0000000000000001 x14: ffffffc03686f0f8 x13: ffffffc03686f0f8 x12: 0000000000000003 x11: 0000000000000001 x10: 0000000000000001 x9 : ffffffc03686f0f8 x8 : 0000e3872014c1a1 x7 : 0000000000000028 x6 : 0000000000000000 x5 : 0000000000000001 x4 : 0000000000000000 x3 : 00000000354fb170 x2 : 0000000017d78400 x1 : ffffffc0355e9a60 x0 : ffffffc0354fb268 Fixes: 591fc116f330 ("usb: phy: msm: Use extcon framework for VBUS and ID detection") Signed-off-by: Srinivas Kandagatla Signed-off-by: Felipe Balbi Signed-off-by: Greg Kroah-Hartman --- drivers/usb/phy/phy-msm-usb.c | 37 +++++++++++++++++++++++------------ 1 file changed, 24 insertions(+), 13 deletions(-) diff --git a/drivers/usb/phy/phy-msm-usb.c b/drivers/usb/phy/phy-msm-usb.c index 0d19a6d61a71..970a30e155cb 100644 --- a/drivers/usb/phy/phy-msm-usb.c +++ b/drivers/usb/phy/phy-msm-usb.c @@ -1599,6 +1599,8 @@ static int msm_otg_read_dt(struct platform_device *pdev, struct msm_otg *motg) &motg->id.nb); if (ret < 0) { dev_err(&pdev->dev, "register ID notifier failed\n"); + extcon_unregister_notifier(motg->vbus.extcon, + EXTCON_USB, &motg->vbus.nb); return ret; } @@ -1660,15 +1662,6 @@ static int msm_otg_probe(struct platform_device *pdev) if (!motg) return -ENOMEM; - pdata = dev_get_platdata(&pdev->dev); - if (!pdata) { - if (!np) - return -ENXIO; - ret = msm_otg_read_dt(pdev, motg); - if (ret) - return ret; - } - motg->phy.otg = devm_kzalloc(&pdev->dev, sizeof(struct usb_otg), GFP_KERNEL); if (!motg->phy.otg) @@ -1710,6 +1703,15 @@ static int msm_otg_probe(struct platform_device *pdev) if (!motg->regs) return -ENOMEM; + pdata = dev_get_platdata(&pdev->dev); + if (!pdata) { + if (!np) + return -ENXIO; + ret = msm_otg_read_dt(pdev, motg); + if (ret) + return ret; + } + /* * NOTE: The PHYs can be multiplexed between the chipidea controller * and the dwc3 controller, using a single bit. It is important that @@ -1717,8 +1719,10 @@ static int msm_otg_probe(struct platform_device *pdev) */ if (motg->phy_number) { phy_select = devm_ioremap_nocache(&pdev->dev, USB2_PHY_SEL, 4); - if (!phy_select) - return -ENOMEM; + if (!phy_select) { + ret = -ENOMEM; + goto unregister_extcon; + } /* Enable second PHY with the OTG port */ writel(0x1, phy_select); } @@ -1728,7 +1732,8 @@ static int msm_otg_probe(struct platform_device *pdev) motg->irq = platform_get_irq(pdev, 0); if (motg->irq < 0) { dev_err(&pdev->dev, "platform_get_irq failed\n"); - return motg->irq; + ret = motg->irq; + goto unregister_extcon; } regs[0].supply = "vddcx"; @@ -1737,7 +1742,7 @@ static int msm_otg_probe(struct platform_device *pdev) ret = devm_regulator_bulk_get(motg->phy.dev, ARRAY_SIZE(regs), regs); if (ret) - return ret; + goto unregister_extcon; motg->vddcx = regs[0].consumer; motg->v3p3 = regs[1].consumer; @@ -1834,6 +1839,12 @@ disable_clks: clk_disable_unprepare(motg->clk); if (!IS_ERR(motg->core_clk)) clk_disable_unprepare(motg->core_clk); +unregister_extcon: + extcon_unregister_notifier(motg->id.extcon, + EXTCON_USB_HOST, &motg->id.nb); + extcon_unregister_notifier(motg->vbus.extcon, + EXTCON_USB, &motg->vbus.nb); + return ret; } From bfa2ee5ddf3dd102f2ffc9842225591461a08f16 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Tue, 26 Jan 2016 17:50:05 +0200 Subject: [PATCH 140/325] usb: xhci: handle both SSIC ports in PME stuck quirk commit fa89537783cb442263fa5a14df6c7693eaf32f11 upstream. Commit abce329c27b3 ("xhci: Workaround to get D3 working in Intel xHCI") adds a workaround for a limitation of PME storm caused by SSIC port in some Intel SoCs. This commit only handled one SSIC port, while there are actually two SSIC ports in the chips. This patch handles both SSIC ports. Without this fix, users still see PME storm. Signed-off-by: Zhuang Jin Can Signed-off-by: Lu Baolu Signed-off-by: Mathias Nyman Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci-pci.c | 42 +++++++++++++++++++++++-------------- 1 file changed, 26 insertions(+), 16 deletions(-) diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index c62109091d12..1502803304f3 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -28,7 +28,9 @@ #include "xhci.h" #include "xhci-trace.h" -#define PORT2_SSIC_CONFIG_REG2 0x883c +#define SSIC_PORT_NUM 2 +#define SSIC_PORT_CFG2 0x880c +#define SSIC_PORT_CFG2_OFFSET 0x30 #define PROG_DONE (1 << 30) #define SSIC_PORT_UNUSED (1 << 31) @@ -322,28 +324,36 @@ static void xhci_pme_quirk(struct usb_hcd *hcd, bool suspend) struct pci_dev *pdev = to_pci_dev(hcd->self.controller); u32 val; void __iomem *reg; + int i; if (pdev->vendor == PCI_VENDOR_ID_INTEL && pdev->device == PCI_DEVICE_ID_INTEL_CHERRYVIEW_XHCI) { - reg = (void __iomem *) xhci->cap_regs + PORT2_SSIC_CONFIG_REG2; + for (i = 0; i < SSIC_PORT_NUM; i++) { + reg = (void __iomem *) xhci->cap_regs + + SSIC_PORT_CFG2 + + i * SSIC_PORT_CFG2_OFFSET; - /* Notify SSIC that SSIC profile programming is not done */ - val = readl(reg) & ~PROG_DONE; - writel(val, reg); + /* + * Notify SSIC that SSIC profile programming + * is not done. + */ + val = readl(reg) & ~PROG_DONE; + writel(val, reg); - /* Mark SSIC port as unused(suspend) or used(resume) */ - val = readl(reg); - if (suspend) - val |= SSIC_PORT_UNUSED; - else - val &= ~SSIC_PORT_UNUSED; - writel(val, reg); + /* Mark SSIC port as unused(suspend) or used(resume) */ + val = readl(reg); + if (suspend) + val |= SSIC_PORT_UNUSED; + else + val &= ~SSIC_PORT_UNUSED; + writel(val, reg); - /* Notify SSIC that SSIC profile programming is done */ - val = readl(reg) | PROG_DONE; - writel(val, reg); - readl(reg); + /* Notify SSIC that SSIC profile programming is done */ + val = readl(reg) | PROG_DONE; + writel(val, reg); + readl(reg); + } } reg = (void __iomem *) xhci->cap_regs + 0x80a4; From 46f0b319cd828cc52bce8a94ff6c010efbfbb660 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Tue, 26 Jan 2016 17:50:08 +0200 Subject: [PATCH 141/325] usb: xhci: apply XHCI_PME_STUCK_QUIRK to Intel Broxton-M platforms commit ccc04afb72cddbdf7c0e1c17e92886405a71b754 upstream. Intel Broxton M was verifed to require XHCI_PME_STUCK_QUIRK quirk as well. Signed-off-by: Lu Baolu Signed-off-by: Mathias Nyman Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci-pci.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index 1502803304f3..c2d65206ec6c 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -47,6 +47,7 @@ #define PCI_DEVICE_ID_INTEL_CHERRYVIEW_XHCI 0x22b5 #define PCI_DEVICE_ID_INTEL_SUNRISEPOINT_H_XHCI 0xa12f #define PCI_DEVICE_ID_INTEL_SUNRISEPOINT_LP_XHCI 0x9d2f +#define PCI_DEVICE_ID_INTEL_BROXTON_M_XHCI 0x0aa8 static const char hcd_name[] = "xhci_hcd"; @@ -154,7 +155,8 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci) if (pdev->vendor == PCI_VENDOR_ID_INTEL && (pdev->device == PCI_DEVICE_ID_INTEL_SUNRISEPOINT_LP_XHCI || pdev->device == PCI_DEVICE_ID_INTEL_SUNRISEPOINT_H_XHCI || - pdev->device == PCI_DEVICE_ID_INTEL_CHERRYVIEW_XHCI)) { + pdev->device == PCI_DEVICE_ID_INTEL_CHERRYVIEW_XHCI || + pdev->device == PCI_DEVICE_ID_INTEL_BROXTON_M_XHCI)) { xhci->quirks |= XHCI_PME_STUCK_QUIRK; } if (pdev->vendor == PCI_VENDOR_ID_ETRON && From cccd9546e993ddcd10a482e43a821420cb09c05d Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sun, 10 Jan 2016 22:40:56 -0800 Subject: [PATCH 142/325] n_tty: Fix unsafe reference to "other" ldisc commit 6d27a63caad3f13e96cf065d2d96828c2006be6b upstream. Although n_tty_check_unthrottle() has a valid ldisc reference (since the tty core gets the ldisc ref in tty_read() before calling the line discipline read() method), it does not have a valid ldisc reference to the "other" pty of a pty pair. Since getting an ldisc reference for tty->link essentially open-codes tty_wakeup(), just replace with the equivalent tty_wakeup(). Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- drivers/tty/n_tty.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/drivers/tty/n_tty.c b/drivers/tty/n_tty.c index e49c2bce551d..cf000b331eed 100644 --- a/drivers/tty/n_tty.c +++ b/drivers/tty/n_tty.c @@ -258,16 +258,13 @@ static void n_tty_check_throttle(struct tty_struct *tty) static void n_tty_check_unthrottle(struct tty_struct *tty) { - if (tty->driver->type == TTY_DRIVER_TYPE_PTY && - tty->link->ldisc->ops->write_wakeup == n_tty_write_wakeup) { + if (tty->driver->type == TTY_DRIVER_TYPE_PTY) { if (chars_in_buffer(tty) > TTY_THRESHOLD_UNTHROTTLE) return; if (!tty->count) return; n_tty_kick_worker(tty); - n_tty_write_wakeup(tty->link); - if (waitqueue_active(&tty->link->write_wait)) - wake_up_interruptible_poll(&tty->link->write_wait, POLLOUT); + tty_wakeup(tty->link); return; } From c35f1234931e2cae81726440ad4df8ef1f313219 Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sat, 9 Jan 2016 21:13:44 -0800 Subject: [PATCH 143/325] tty: Wait interruptibly for tty lock on reopen commit 0bfd464d3fdd5bb322f9cace4cc47f1796545cf7 upstream. Allow a signal to interrupt the wait for a tty reopen; eg., if the tty has starting final close and is waiting for the device to drain. Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- drivers/tty/tty_io.c | 8 +++++++- drivers/tty/tty_mutex.c | 8 ++++++++ include/linux/tty.h | 1 + 3 files changed, 16 insertions(+), 1 deletion(-) diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c index bcc8e1e8bb72..4d34116842a6 100644 --- a/drivers/tty/tty_io.c +++ b/drivers/tty/tty_io.c @@ -2069,7 +2069,12 @@ retry_open: if (tty) { mutex_unlock(&tty_mutex); - tty_lock(tty); + retval = tty_lock_interruptible(tty); + if (retval) { + if (retval == -EINTR) + retval = -ERESTARTSYS; + goto err_unref; + } /* safe to drop the kref from tty_driver_lookup_tty() */ tty_kref_put(tty); retval = tty_reopen(tty); @@ -2156,6 +2161,7 @@ retry_open: return 0; err_unlock: mutex_unlock(&tty_mutex); +err_unref: /* after locks to avoid deadlock */ if (!IS_ERR_OR_NULL(driver)) tty_driver_kref_put(driver); diff --git a/drivers/tty/tty_mutex.c b/drivers/tty/tty_mutex.c index 0efcf713b756..d09293bc0e04 100644 --- a/drivers/tty/tty_mutex.c +++ b/drivers/tty/tty_mutex.c @@ -22,6 +22,14 @@ void __lockfunc tty_lock(struct tty_struct *tty) } EXPORT_SYMBOL(tty_lock); +int tty_lock_interruptible(struct tty_struct *tty) +{ + if (WARN(tty->magic != TTY_MAGIC, "L Bad %p\n", tty)) + return -EIO; + tty_kref_get(tty); + return mutex_lock_interruptible(&tty->legacy_mutex); +} + void __lockfunc tty_unlock(struct tty_struct *tty) { if (tty->magic != TTY_MAGIC) { diff --git a/include/linux/tty.h b/include/linux/tty.h index 5e31f1b99037..6b6e811f4575 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -654,6 +654,7 @@ extern long vt_compat_ioctl(struct tty_struct *tty, /* tty_mutex.c */ /* functions for preparation of BKL removal */ extern void __lockfunc tty_lock(struct tty_struct *tty); +extern int tty_lock_interruptible(struct tty_struct *tty); extern void __lockfunc tty_unlock(struct tty_struct *tty); extern void __lockfunc tty_lock_slave(struct tty_struct *tty); extern void __lockfunc tty_unlock_slave(struct tty_struct *tty); From b4312250147d42dceed6c8d44aa02cb29539db19 Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sat, 9 Jan 2016 21:13:45 -0800 Subject: [PATCH 144/325] tty: Retry failed reopen if tty teardown in-progress commit 7f22f6c935cda600660e623a411fe380015d28d9 upstream. A small window exists where a tty reopen will observe the tty just prior to imminent teardown (tty->count == 0); in this case, open() returns EIO to userspace. Instead, retry the open after checking for signals and yielding; this interruptible retry loop allows teardown to commence and initialize a new tty on retry. Never retry the BSD master pty reopen; there is no guarantee the pty pair teardown is imminent since the slave file descriptors may remain open indefinitely. Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- drivers/tty/tty_io.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c index 4d34116842a6..8eda897ec2a0 100644 --- a/drivers/tty/tty_io.c +++ b/drivers/tty/tty_io.c @@ -1462,13 +1462,13 @@ static int tty_reopen(struct tty_struct *tty) { struct tty_driver *driver = tty->driver; - if (!tty->count) - return -EIO; - if (driver->type == TTY_DRIVER_TYPE_PTY && driver->subtype == PTY_TYPE_MASTER) return -EIO; + if (!tty->count) + return -EAGAIN; + if (test_bit(TTY_EXCLUSIVE, &tty->flags) && !capable(CAP_SYS_ADMIN)) return -EBUSY; @@ -2092,7 +2092,11 @@ retry_open: if (IS_ERR(tty)) { retval = PTR_ERR(tty); - goto err_file; + if (retval != -EAGAIN || signal_pending(current)) + goto err_file; + tty_free_file(filp); + schedule(); + goto retry_open; } tty_add_file(tty, filp); From d343601a19410f71bf1765df5e2edda66fe5de5f Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sun, 10 Jan 2016 22:40:55 -0800 Subject: [PATCH 145/325] tty: Fix unsafe ldisc reference via ioctl(TIOCGETD) commit 5c17c861a357e9458001f021a7afa7aab9937439 upstream. ioctl(TIOCGETD) retrieves the line discipline id directly from the ldisc because the line discipline id (c_line) in termios is untrustworthy; userspace may have set termios via ioctl(TCSETS*) without actually changing the line discipline via ioctl(TIOCSETD). However, directly accessing the current ldisc via tty->ldisc is unsafe; the ldisc ptr dereferenced may be stale if the line discipline is changing via ioctl(TIOCSETD) or hangup. Wait for the line discipline reference (just like read() or write()) to retrieve the "current" line discipline id. Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- drivers/tty/tty_io.c | 24 +++++++++++++++++++++++- 1 file changed, 23 insertions(+), 1 deletion(-) diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c index 8eda897ec2a0..7cef54334b12 100644 --- a/drivers/tty/tty_io.c +++ b/drivers/tty/tty_io.c @@ -2662,6 +2662,28 @@ static int tiocsetd(struct tty_struct *tty, int __user *p) return ret; } +/** + * tiocgetd - get line discipline + * @tty: tty device + * @p: pointer to user data + * + * Retrieves the line discipline id directly from the ldisc. + * + * Locking: waits for ldisc reference (in case the line discipline + * is changing or the tty is being hungup) + */ + +static int tiocgetd(struct tty_struct *tty, int __user *p) +{ + struct tty_ldisc *ld; + int ret; + + ld = tty_ldisc_ref_wait(tty); + ret = put_user(ld->ops->num, p); + tty_ldisc_deref(ld); + return ret; +} + /** * send_break - performed time break * @tty: device to break on @@ -2888,7 +2910,7 @@ long tty_ioctl(struct file *file, unsigned int cmd, unsigned long arg) case TIOCGSID: return tiocgsid(tty, real_tty, p); case TIOCGETD: - return put_user(tty->ldisc->ops->num, (int __user *)p); + return tiocgetd(tty, p); case TIOCSETD: return tiocsetd(tty, p); case TIOCVHANGUP: From 740c56110a2548ae353af93d07354f67f14f4b4e Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Tue, 15 Dec 2015 16:08:12 +0000 Subject: [PATCH 146/325] iommu/io-pgtable-arm: Ensure we free the final level on teardown commit 12c2ab09571e8aae3a87da2a4a452632a5fac1e5 upstream. When tearing down page tables, we return early for the final level since we know that we won't have any table pointers to follow. Unfortunately, this also means that we forget to free the final level, so we end up leaking memory. Fix the issue by always freeing the current level, but just don't bother to iterate over the ptes if we're at the final level. Reported-by: Zhang Bo Signed-off-by: Will Deacon Signed-off-by: Greg Kroah-Hartman --- drivers/iommu/io-pgtable-arm.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c index 7df97777662d..dad768caa9c5 100644 --- a/drivers/iommu/io-pgtable-arm.c +++ b/drivers/iommu/io-pgtable-arm.c @@ -405,17 +405,18 @@ static void __arm_lpae_free_pgtable(struct arm_lpae_io_pgtable *data, int lvl, arm_lpae_iopte *start, *end; unsigned long table_size; - /* Only leaf entries at the last level */ - if (lvl == ARM_LPAE_MAX_LEVELS - 1) - return; - if (lvl == ARM_LPAE_START_LVL(data)) table_size = data->pgd_size; else table_size = 1UL << data->pg_shift; start = ptep; - end = (void *)ptep + table_size; + + /* Only leaf entries at the last level */ + if (lvl == ARM_LPAE_MAX_LEVELS - 1) + end = ptep; + else + end = (void *)ptep + table_size; while (ptep != end) { arm_lpae_iopte pte = *ptep++; From b80b70ef40459ec9e7493cef5e91e4e11dad9e42 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Thu, 10 Dec 2015 00:57:58 -0500 Subject: [PATCH 147/325] ext4 crypto: add missing locking for keyring_key access commit db7730e3091a52c2fcd8fcc952b964d88998e675 upstream. Signed-off-by: Theodore Ts'o Signed-off-by: Greg Kroah-Hartman --- fs/ext4/crypto_key.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/fs/ext4/crypto_key.c b/fs/ext4/crypto_key.c index c5882b36e558..9a16d1e75a49 100644 --- a/fs/ext4/crypto_key.c +++ b/fs/ext4/crypto_key.c @@ -213,9 +213,11 @@ retry: res = -ENOKEY; goto out; } + down_read(&keyring_key->sem); ukp = user_key_payload(keyring_key); if (ukp->datalen != sizeof(struct ext4_encryption_key)) { res = -EINVAL; + up_read(&keyring_key->sem); goto out; } master_key = (struct ext4_encryption_key *)ukp->data; @@ -226,10 +228,12 @@ retry: "ext4: key size incorrect: %d\n", master_key->size); res = -ENOKEY; + up_read(&keyring_key->sem); goto out; } res = ext4_derive_key_aes(ctx.nonce, master_key->raw, raw_key); + up_read(&keyring_key->sem); if (res) goto out; got_key: From a800cbddbc2042b042491867e96e2f3c5c0d3e3b Mon Sep 17 00:00:00 2001 From: Raghavendra K T Date: Sat, 16 Jan 2016 00:31:23 +0530 Subject: [PATCH 148/325] sched: Fix crash in sched_init_numa() commit 9c03ee147193645be4c186d3688232fa438c57c7 upstream. The following PowerPC commit: c118baf80256 ("arch/powerpc/mm/numa.c: do not allocate bootmem memory for non existing nodes") avoids allocating bootmem memory for non existent nodes. But when DEBUG_PER_CPU_MAPS=y is enabled, my powerNV system failed to boot because in sched_init_numa(), cpumask_or() operation was done on unallocated nodes. Fix that by making cpumask_or() operation only on existing nodes. [ Tested with and w/o DEBUG_PER_CPU_MAPS=y on x86 and PowerPC. ] Reported-by: Jan Stancek Tested-by: Jan Stancek Signed-off-by: Raghavendra K T Cc: Cc: Cc: Cc: Cc: Cc: Cc: Cc: Cc: Cc: Cc: Link: http://lkml.kernel.org/r/1452884483-11676-1-git-send-email-raghavendra.kt@linux.vnet.ibm.com Signed-off-by: Ingo Molnar Signed-off-by: Greg Kroah-Hartman --- kernel/sched/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 732e993b564b..eb70592f03f6 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -6738,7 +6738,7 @@ static void sched_init_numa(void) sched_domains_numa_masks[i][j] = mask; - for (k = 0; k < nr_node_ids; k++) { + for_each_node(k) { if (node_distance(j, k) > sched_domains_numa_distance[i]) continue; From b238717c0bb4606e2e36fc0de745306b0c900d83 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Fri, 25 Dec 2015 15:40:05 +0800 Subject: [PATCH 149/325] crypto: algif_skcipher - Require setkey before accept(2) commit dd504589577d8e8e70f51f997ad487a4cb6c026f upstream. Some cipher implementations will crash if you try to use them without calling setkey first. This patch adds a check so that the accept(2) call will fail with -ENOKEY if setkey hasn't been done on the socket yet. Reported-by: Dmitry Vyukov Signed-off-by: Herbert Xu Tested-by: Dmitry Vyukov Signed-off-by: Greg Kroah-Hartman --- crypto/algif_skcipher.c | 48 +++++++++++++++++++++++++++++++++++------ 1 file changed, 41 insertions(+), 7 deletions(-) diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c index 634b4d1ab681..df483f9bb811 100644 --- a/crypto/algif_skcipher.c +++ b/crypto/algif_skcipher.c @@ -31,6 +31,11 @@ struct skcipher_sg_list { struct scatterlist sg[0]; }; +struct skcipher_tfm { + struct crypto_skcipher *skcipher; + bool has_key; +}; + struct skcipher_ctx { struct list_head tsgl; struct af_alg_sgl rsgl; @@ -750,17 +755,41 @@ static struct proto_ops algif_skcipher_ops = { static void *skcipher_bind(const char *name, u32 type, u32 mask) { - return crypto_alloc_skcipher(name, type, mask); + struct skcipher_tfm *tfm; + struct crypto_skcipher *skcipher; + + tfm = kzalloc(sizeof(*tfm), GFP_KERNEL); + if (!tfm) + return ERR_PTR(-ENOMEM); + + skcipher = crypto_alloc_skcipher(name, type, mask); + if (IS_ERR(skcipher)) { + kfree(tfm); + return ERR_CAST(skcipher); + } + + tfm->skcipher = skcipher; + + return tfm; } static void skcipher_release(void *private) { - crypto_free_skcipher(private); + struct skcipher_tfm *tfm = private; + + crypto_free_skcipher(tfm->skcipher); + kfree(tfm); } static int skcipher_setkey(void *private, const u8 *key, unsigned int keylen) { - return crypto_skcipher_setkey(private, key, keylen); + struct skcipher_tfm *tfm = private; + int err; + + err = crypto_skcipher_setkey(tfm->skcipher, key, keylen); + tfm->has_key = !err; + + return err; } static void skcipher_wait(struct sock *sk) @@ -792,20 +821,25 @@ static int skcipher_accept_parent(void *private, struct sock *sk) { struct skcipher_ctx *ctx; struct alg_sock *ask = alg_sk(sk); - unsigned int len = sizeof(*ctx) + crypto_skcipher_reqsize(private); + struct skcipher_tfm *tfm = private; + struct crypto_skcipher *skcipher = tfm->skcipher; + unsigned int len = sizeof(*ctx) + crypto_skcipher_reqsize(skcipher); + + if (!tfm->has_key) + return -ENOKEY; ctx = sock_kmalloc(sk, len, GFP_KERNEL); if (!ctx) return -ENOMEM; - ctx->iv = sock_kmalloc(sk, crypto_skcipher_ivsize(private), + ctx->iv = sock_kmalloc(sk, crypto_skcipher_ivsize(skcipher), GFP_KERNEL); if (!ctx->iv) { sock_kfree_s(sk, ctx, len); return -ENOMEM; } - memset(ctx->iv, 0, crypto_skcipher_ivsize(private)); + memset(ctx->iv, 0, crypto_skcipher_ivsize(skcipher)); INIT_LIST_HEAD(&ctx->tsgl); ctx->len = len; @@ -818,7 +852,7 @@ static int skcipher_accept_parent(void *private, struct sock *sk) ask->private = ctx; - skcipher_request_set_tfm(&ctx->req, private); + skcipher_request_set_tfm(&ctx->req, skcipher); skcipher_request_set_callback(&ctx->req, CRYPTO_TFM_REQ_MAY_BACKLOG, af_alg_complete, &ctx->completion); From 7509864bb2ec8a4dfbda52a9bda577ecdcb6b2c4 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Wed, 30 Dec 2015 11:47:53 +0800 Subject: [PATCH 150/325] crypto: af_alg - Disallow bind/setkey/... after accept(2) commit c840ac6af3f8713a71b4d2363419145760bd6044 upstream. Each af_alg parent socket obtained by socket(2) corresponds to a tfm object once bind(2) has succeeded. An accept(2) call on that parent socket creates a context which then uses the tfm object. Therefore as long as any child sockets created by accept(2) exist the parent socket must not be modified or freed. This patch guarantees this by using locks and a reference count on the parent socket. Any attempt to modify the parent socket will fail with EBUSY. Reported-by: Dmitry Vyukov Signed-off-by: Herbert Xu Signed-off-by: Greg Kroah-Hartman --- crypto/af_alg.c | 35 ++++++++++++++++++++++++++++++++--- include/crypto/if_alg.h | 8 +++----- 2 files changed, 35 insertions(+), 8 deletions(-) diff --git a/crypto/af_alg.c b/crypto/af_alg.c index a8e7aa3e257b..7b5b5926c767 100644 --- a/crypto/af_alg.c +++ b/crypto/af_alg.c @@ -125,6 +125,23 @@ int af_alg_release(struct socket *sock) } EXPORT_SYMBOL_GPL(af_alg_release); +void af_alg_release_parent(struct sock *sk) +{ + struct alg_sock *ask = alg_sk(sk); + bool last; + + sk = ask->parent; + ask = alg_sk(sk); + + lock_sock(sk); + last = !--ask->refcnt; + release_sock(sk); + + if (last) + sock_put(sk); +} +EXPORT_SYMBOL_GPL(af_alg_release_parent); + static int alg_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) { const u32 forbidden = CRYPTO_ALG_INTERNAL; @@ -133,6 +150,7 @@ static int alg_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) struct sockaddr_alg *sa = (void *)uaddr; const struct af_alg_type *type; void *private; + int err; if (sock->state == SS_CONNECTED) return -EINVAL; @@ -160,16 +178,22 @@ static int alg_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) return PTR_ERR(private); } + err = -EBUSY; lock_sock(sk); + if (ask->refcnt) + goto unlock; swap(ask->type, type); swap(ask->private, private); + err = 0; + +unlock: release_sock(sk); alg_do_release(type, private); - return 0; + return err; } static int alg_setkey(struct sock *sk, char __user *ukey, @@ -202,11 +226,15 @@ static int alg_setsockopt(struct socket *sock, int level, int optname, struct sock *sk = sock->sk; struct alg_sock *ask = alg_sk(sk); const struct af_alg_type *type; - int err = -ENOPROTOOPT; + int err = -EBUSY; lock_sock(sk); + if (ask->refcnt) + goto unlock; + type = ask->type; + err = -ENOPROTOOPT; if (level != SOL_ALG || !type) goto unlock; @@ -264,7 +292,8 @@ int af_alg_accept(struct sock *sk, struct socket *newsock) sk2->sk_family = PF_ALG; - sock_hold(sk); + if (!ask->refcnt++) + sock_hold(sk); alg_sk(sk2)->parent = sk; alg_sk(sk2)->type = type; diff --git a/include/crypto/if_alg.h b/include/crypto/if_alg.h index 018afb264ac2..589716f2ee8a 100644 --- a/include/crypto/if_alg.h +++ b/include/crypto/if_alg.h @@ -30,6 +30,8 @@ struct alg_sock { struct sock *parent; + unsigned int refcnt; + const struct af_alg_type *type; void *private; }; @@ -67,6 +69,7 @@ int af_alg_register_type(const struct af_alg_type *type); int af_alg_unregister_type(const struct af_alg_type *type); int af_alg_release(struct socket *sock); +void af_alg_release_parent(struct sock *sk); int af_alg_accept(struct sock *sk, struct socket *newsock); int af_alg_make_sg(struct af_alg_sgl *sgl, struct iov_iter *iter, int len); @@ -83,11 +86,6 @@ static inline struct alg_sock *alg_sk(struct sock *sk) return (struct alg_sock *)sk; } -static inline void af_alg_release_parent(struct sock *sk) -{ - sock_put(alg_sk(sk)->parent); -} - static inline void af_alg_init_completion(struct af_alg_completion *completion) { init_completion(&completion->completion); From aa435a11e4bb37e23dbfc45fea2c11ddf6b813e0 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Wed, 30 Dec 2015 20:24:17 +0800 Subject: [PATCH 151/325] crypto: af_alg - Fix socket double-free when accept fails commit a383292c86663bbc31ac62cc0c04fc77504636a6 upstream. When we fail an accept(2) call we will end up freeing the socket twice, once due to the direct sk_free call and once again through newsock. This patch fixes this by removing the sk_free call. Reported-by: Dmitry Vyukov Signed-off-by: Herbert Xu Signed-off-by: Greg Kroah-Hartman --- crypto/af_alg.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/crypto/af_alg.c b/crypto/af_alg.c index 7b5b5926c767..eaf98e287d89 100644 --- a/crypto/af_alg.c +++ b/crypto/af_alg.c @@ -285,10 +285,8 @@ int af_alg_accept(struct sock *sk, struct socket *newsock) security_sk_clone(sk, sk2); err = type->accept(ask->private, sk2); - if (err) { - sk_free(sk2); + if (err) goto unlock; - } sk2->sk_family = PF_ALG; From d1b886e326f3578e8d6066c590d32a5c7028afbd Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Mon, 4 Jan 2016 13:35:18 +0900 Subject: [PATCH 152/325] crypto: af_alg - Add nokey compatibility path commit 37766586c965d63758ad542325a96d5384f4a8c9 upstream. This patch adds a compatibility path to support old applications that do acept(2) before setkey. Signed-off-by: Herbert Xu Signed-off-by: Greg Kroah-Hartman --- crypto/af_alg.c | 13 ++++++++++++- include/crypto/if_alg.h | 2 ++ 2 files changed, 14 insertions(+), 1 deletion(-) diff --git a/crypto/af_alg.c b/crypto/af_alg.c index eaf98e287d89..6566d2eb0142 100644 --- a/crypto/af_alg.c +++ b/crypto/af_alg.c @@ -76,6 +76,8 @@ int af_alg_register_type(const struct af_alg_type *type) goto unlock; type->ops->owner = THIS_MODULE; + if (type->ops_nokey) + type->ops_nokey->owner = THIS_MODULE; node->type = type; list_add(&node->list, &alg_types); err = 0; @@ -267,6 +269,7 @@ int af_alg_accept(struct sock *sk, struct socket *newsock) const struct af_alg_type *type; struct sock *sk2; int err; + bool nokey; lock_sock(sk); type = ask->type; @@ -285,12 +288,17 @@ int af_alg_accept(struct sock *sk, struct socket *newsock) security_sk_clone(sk, sk2); err = type->accept(ask->private, sk2); + + nokey = err == -ENOKEY; + if (nokey && type->accept_nokey) + err = type->accept_nokey(ask->private, sk2); + if (err) goto unlock; sk2->sk_family = PF_ALG; - if (!ask->refcnt++) + if (nokey || !ask->refcnt++) sock_hold(sk); alg_sk(sk2)->parent = sk; alg_sk(sk2)->type = type; @@ -298,6 +306,9 @@ int af_alg_accept(struct sock *sk, struct socket *newsock) newsock->ops = type->ops; newsock->state = SS_CONNECTED; + if (nokey) + newsock->ops = type->ops_nokey; + err = 0; unlock: diff --git a/include/crypto/if_alg.h b/include/crypto/if_alg.h index 589716f2ee8a..df8284415c56 100644 --- a/include/crypto/if_alg.h +++ b/include/crypto/if_alg.h @@ -52,9 +52,11 @@ struct af_alg_type { void (*release)(void *private); int (*setkey)(void *private, const u8 *key, unsigned int keylen); int (*accept)(void *private, struct sock *sk); + int (*accept_nokey)(void *private, struct sock *sk); int (*setauthsize)(void *private, unsigned int authsize); struct proto_ops *ops; + struct proto_ops *ops_nokey; struct module *owner; char name[14]; }; From eeb2e2e72bce3c4f3e74d1ea2c621aa574b8ef18 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Mon, 4 Jan 2016 13:36:12 +0900 Subject: [PATCH 153/325] crypto: algif_skcipher - Add nokey compatibility path commit a0fa2d037129a9849918a92d91b79ed6c7bd2818 upstream. This patch adds a compatibility path to support old applications that do acept(2) before setkey. Signed-off-by: Herbert Xu Signed-off-by: Greg Kroah-Hartman --- crypto/algif_skcipher.c | 149 ++++++++++++++++++++++++++++++++++++++-- 1 file changed, 144 insertions(+), 5 deletions(-) diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c index df483f9bb811..bb0ee129a775 100644 --- a/crypto/algif_skcipher.c +++ b/crypto/algif_skcipher.c @@ -753,6 +753,99 @@ static struct proto_ops algif_skcipher_ops = { .poll = skcipher_poll, }; +static int skcipher_check_key(struct socket *sock) +{ + int err; + struct sock *psk; + struct alg_sock *pask; + struct skcipher_tfm *tfm; + struct sock *sk = sock->sk; + struct alg_sock *ask = alg_sk(sk); + + if (ask->refcnt) + return 0; + + psk = ask->parent; + pask = alg_sk(ask->parent); + tfm = pask->private; + + err = -ENOKEY; + lock_sock(psk); + if (!tfm->has_key) + goto unlock; + + if (!pask->refcnt++) + sock_hold(psk); + + ask->refcnt = 1; + sock_put(psk); + + err = 0; + +unlock: + release_sock(psk); + + return err; +} + +static int skcipher_sendmsg_nokey(struct socket *sock, struct msghdr *msg, + size_t size) +{ + int err; + + err = skcipher_check_key(sock); + if (err) + return err; + + return skcipher_sendmsg(sock, msg, size); +} + +static ssize_t skcipher_sendpage_nokey(struct socket *sock, struct page *page, + int offset, size_t size, int flags) +{ + int err; + + err = skcipher_check_key(sock); + if (err) + return err; + + return skcipher_sendpage(sock, page, offset, size, flags); +} + +static int skcipher_recvmsg_nokey(struct socket *sock, struct msghdr *msg, + size_t ignored, int flags) +{ + int err; + + err = skcipher_check_key(sock); + if (err) + return err; + + return skcipher_recvmsg(sock, msg, ignored, flags); +} + +static struct proto_ops algif_skcipher_ops_nokey = { + .family = PF_ALG, + + .connect = sock_no_connect, + .socketpair = sock_no_socketpair, + .getname = sock_no_getname, + .ioctl = sock_no_ioctl, + .listen = sock_no_listen, + .shutdown = sock_no_shutdown, + .getsockopt = sock_no_getsockopt, + .mmap = sock_no_mmap, + .bind = sock_no_bind, + .accept = sock_no_accept, + .setsockopt = sock_no_setsockopt, + + .release = af_alg_release, + .sendmsg = skcipher_sendmsg_nokey, + .sendpage = skcipher_sendpage_nokey, + .recvmsg = skcipher_recvmsg_nokey, + .poll = skcipher_poll, +}; + static void *skcipher_bind(const char *name, u32 type, u32 mask) { struct skcipher_tfm *tfm; @@ -802,7 +895,7 @@ static void skcipher_wait(struct sock *sk) msleep(100); } -static void skcipher_sock_destruct(struct sock *sk) +static void skcipher_sock_destruct_common(struct sock *sk) { struct alg_sock *ask = alg_sk(sk); struct skcipher_ctx *ctx = ask->private; @@ -814,10 +907,33 @@ static void skcipher_sock_destruct(struct sock *sk) skcipher_free_sgl(sk); sock_kzfree_s(sk, ctx->iv, crypto_skcipher_ivsize(tfm)); sock_kfree_s(sk, ctx, ctx->len); +} + +static void skcipher_sock_destruct(struct sock *sk) +{ + skcipher_sock_destruct_common(sk); af_alg_release_parent(sk); } -static int skcipher_accept_parent(void *private, struct sock *sk) +static void skcipher_release_parent_nokey(struct sock *sk) +{ + struct alg_sock *ask = alg_sk(sk); + + if (!ask->refcnt) { + sock_put(ask->parent); + return; + } + + af_alg_release_parent(sk); +} + +static void skcipher_sock_destruct_nokey(struct sock *sk) +{ + skcipher_sock_destruct_common(sk); + skcipher_release_parent_nokey(sk); +} + +static int skcipher_accept_parent_common(void *private, struct sock *sk) { struct skcipher_ctx *ctx; struct alg_sock *ask = alg_sk(sk); @@ -825,9 +941,6 @@ static int skcipher_accept_parent(void *private, struct sock *sk) struct crypto_skcipher *skcipher = tfm->skcipher; unsigned int len = sizeof(*ctx) + crypto_skcipher_reqsize(skcipher); - if (!tfm->has_key) - return -ENOKEY; - ctx = sock_kmalloc(sk, len, GFP_KERNEL); if (!ctx) return -ENOMEM; @@ -861,12 +974,38 @@ static int skcipher_accept_parent(void *private, struct sock *sk) return 0; } +static int skcipher_accept_parent(void *private, struct sock *sk) +{ + struct skcipher_tfm *tfm = private; + + if (!tfm->has_key) + return -ENOKEY; + + return skcipher_accept_parent_common(private, sk); +} + +static int skcipher_accept_parent_nokey(void *private, struct sock *sk) +{ + int err; + + err = skcipher_accept_parent_common(private, sk); + if (err) + goto out; + + sk->sk_destruct = skcipher_sock_destruct_nokey; + +out: + return err; +} + static const struct af_alg_type algif_type_skcipher = { .bind = skcipher_bind, .release = skcipher_release, .setkey = skcipher_setkey, .accept = skcipher_accept_parent, + .accept_nokey = skcipher_accept_parent_nokey, .ops = &algif_skcipher_ops, + .ops_nokey = &algif_skcipher_ops_nokey, .name = "skcipher", .owner = THIS_MODULE }; From f2e274ce8bfe8ab928ab1968a82a3b7eec27a69b Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Fri, 8 Jan 2016 21:28:26 +0800 Subject: [PATCH 154/325] crypto: hash - Add crypto_ahash_has_setkey commit a5596d6332787fd383b3b5427b41f94254430827 upstream. This patch adds a way for ahash users to determine whether a key is required by a crypto_ahash transform. Signed-off-by: Herbert Xu Signed-off-by: Greg Kroah-Hartman --- crypto/ahash.c | 5 ++++- crypto/shash.c | 4 +++- include/crypto/hash.h | 6 ++++++ 3 files changed, 13 insertions(+), 2 deletions(-) diff --git a/crypto/ahash.c b/crypto/ahash.c index 9c1dc8d6106a..d19b52324cf5 100644 --- a/crypto/ahash.c +++ b/crypto/ahash.c @@ -451,6 +451,7 @@ static int crypto_ahash_init_tfm(struct crypto_tfm *tfm) struct ahash_alg *alg = crypto_ahash_alg(hash); hash->setkey = ahash_nosetkey; + hash->has_setkey = false; hash->export = ahash_no_export; hash->import = ahash_no_import; @@ -463,8 +464,10 @@ static int crypto_ahash_init_tfm(struct crypto_tfm *tfm) hash->finup = alg->finup ?: ahash_def_finup; hash->digest = alg->digest; - if (alg->setkey) + if (alg->setkey) { hash->setkey = alg->setkey; + hash->has_setkey = true; + } if (alg->export) hash->export = alg->export; if (alg->import) diff --git a/crypto/shash.c b/crypto/shash.c index ecb1e3d39bf0..88a27de79848 100644 --- a/crypto/shash.c +++ b/crypto/shash.c @@ -355,8 +355,10 @@ int crypto_init_shash_ops_async(struct crypto_tfm *tfm) crt->finup = shash_async_finup; crt->digest = shash_async_digest; - if (alg->setkey) + if (alg->setkey) { crt->setkey = shash_async_setkey; + crt->has_setkey = true; + } if (alg->export) crt->export = shash_async_export; if (alg->import) diff --git a/include/crypto/hash.h b/include/crypto/hash.h index 3d69c93d50e8..6361892ea737 100644 --- a/include/crypto/hash.h +++ b/include/crypto/hash.h @@ -204,6 +204,7 @@ struct crypto_ahash { unsigned int keylen); unsigned int reqsize; + bool has_setkey; struct crypto_tfm base; }; @@ -375,6 +376,11 @@ static inline void *ahash_request_ctx(struct ahash_request *req) int crypto_ahash_setkey(struct crypto_ahash *tfm, const u8 *key, unsigned int keylen); +static inline bool crypto_ahash_has_setkey(struct crypto_ahash *tfm) +{ + return tfm->has_setkey; +} + /** * crypto_ahash_finup() - update and finalize message digest * @req: reference to the ahash_request handle that holds all information From 017db8bc9a1d62710af99b0eec605ee1f0285277 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Fri, 8 Jan 2016 21:31:04 +0800 Subject: [PATCH 155/325] crypto: algif_hash - Require setkey before accept(2) commit 6de62f15b581f920ade22d758f4c338311c2f0d4 upstream. Hash implementations that require a key may crash if you use them without setting a key. This patch adds the necessary checks so that if you do attempt to use them without a key that we return -ENOKEY instead of proceeding. This patch also adds a compatibility path to support old applications that do acept(2) before setkey. Signed-off-by: Herbert Xu Signed-off-by: Greg Kroah-Hartman --- crypto/algif_hash.c | 201 ++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 193 insertions(+), 8 deletions(-) diff --git a/crypto/algif_hash.c b/crypto/algif_hash.c index b4c24fe3dcfb..46637bed4db8 100644 --- a/crypto/algif_hash.c +++ b/crypto/algif_hash.c @@ -34,6 +34,11 @@ struct hash_ctx { struct ahash_request req; }; +struct algif_hash_tfm { + struct crypto_ahash *hash; + bool has_key; +}; + static int hash_sendmsg(struct socket *sock, struct msghdr *msg, size_t ignored) { @@ -235,22 +240,151 @@ static struct proto_ops algif_hash_ops = { .accept = hash_accept, }; +static int hash_check_key(struct socket *sock) +{ + int err; + struct sock *psk; + struct alg_sock *pask; + struct algif_hash_tfm *tfm; + struct sock *sk = sock->sk; + struct alg_sock *ask = alg_sk(sk); + + if (ask->refcnt) + return 0; + + psk = ask->parent; + pask = alg_sk(ask->parent); + tfm = pask->private; + + err = -ENOKEY; + lock_sock(psk); + if (!tfm->has_key) + goto unlock; + + if (!pask->refcnt++) + sock_hold(psk); + + ask->refcnt = 1; + sock_put(psk); + + err = 0; + +unlock: + release_sock(psk); + + return err; +} + +static int hash_sendmsg_nokey(struct socket *sock, struct msghdr *msg, + size_t size) +{ + int err; + + err = hash_check_key(sock); + if (err) + return err; + + return hash_sendmsg(sock, msg, size); +} + +static ssize_t hash_sendpage_nokey(struct socket *sock, struct page *page, + int offset, size_t size, int flags) +{ + int err; + + err = hash_check_key(sock); + if (err) + return err; + + return hash_sendpage(sock, page, offset, size, flags); +} + +static int hash_recvmsg_nokey(struct socket *sock, struct msghdr *msg, + size_t ignored, int flags) +{ + int err; + + err = hash_check_key(sock); + if (err) + return err; + + return hash_recvmsg(sock, msg, ignored, flags); +} + +static int hash_accept_nokey(struct socket *sock, struct socket *newsock, + int flags) +{ + int err; + + err = hash_check_key(sock); + if (err) + return err; + + return hash_accept(sock, newsock, flags); +} + +static struct proto_ops algif_hash_ops_nokey = { + .family = PF_ALG, + + .connect = sock_no_connect, + .socketpair = sock_no_socketpair, + .getname = sock_no_getname, + .ioctl = sock_no_ioctl, + .listen = sock_no_listen, + .shutdown = sock_no_shutdown, + .getsockopt = sock_no_getsockopt, + .mmap = sock_no_mmap, + .bind = sock_no_bind, + .setsockopt = sock_no_setsockopt, + .poll = sock_no_poll, + + .release = af_alg_release, + .sendmsg = hash_sendmsg_nokey, + .sendpage = hash_sendpage_nokey, + .recvmsg = hash_recvmsg_nokey, + .accept = hash_accept_nokey, +}; + static void *hash_bind(const char *name, u32 type, u32 mask) { - return crypto_alloc_ahash(name, type, mask); + struct algif_hash_tfm *tfm; + struct crypto_ahash *hash; + + tfm = kzalloc(sizeof(*tfm), GFP_KERNEL); + if (!tfm) + return ERR_PTR(-ENOMEM); + + hash = crypto_alloc_ahash(name, type, mask); + if (IS_ERR(hash)) { + kfree(tfm); + return ERR_CAST(hash); + } + + tfm->hash = hash; + + return tfm; } static void hash_release(void *private) { - crypto_free_ahash(private); + struct algif_hash_tfm *tfm = private; + + crypto_free_ahash(tfm->hash); + kfree(tfm); } static int hash_setkey(void *private, const u8 *key, unsigned int keylen) { - return crypto_ahash_setkey(private, key, keylen); + struct algif_hash_tfm *tfm = private; + int err; + + err = crypto_ahash_setkey(tfm->hash, key, keylen); + tfm->has_key = !err; + + return err; } -static void hash_sock_destruct(struct sock *sk) +static void hash_sock_destruct_common(struct sock *sk) { struct alg_sock *ask = alg_sk(sk); struct hash_ctx *ctx = ask->private; @@ -258,15 +392,40 @@ static void hash_sock_destruct(struct sock *sk) sock_kzfree_s(sk, ctx->result, crypto_ahash_digestsize(crypto_ahash_reqtfm(&ctx->req))); sock_kfree_s(sk, ctx, ctx->len); +} + +static void hash_sock_destruct(struct sock *sk) +{ + hash_sock_destruct_common(sk); af_alg_release_parent(sk); } -static int hash_accept_parent(void *private, struct sock *sk) +static void hash_release_parent_nokey(struct sock *sk) +{ + struct alg_sock *ask = alg_sk(sk); + + if (!ask->refcnt) { + sock_put(ask->parent); + return; + } + + af_alg_release_parent(sk); +} + +static void hash_sock_destruct_nokey(struct sock *sk) +{ + hash_sock_destruct_common(sk); + hash_release_parent_nokey(sk); +} + +static int hash_accept_parent_common(void *private, struct sock *sk) { struct hash_ctx *ctx; struct alg_sock *ask = alg_sk(sk); - unsigned len = sizeof(*ctx) + crypto_ahash_reqsize(private); - unsigned ds = crypto_ahash_digestsize(private); + struct algif_hash_tfm *tfm = private; + struct crypto_ahash *hash = tfm->hash; + unsigned len = sizeof(*ctx) + crypto_ahash_reqsize(hash); + unsigned ds = crypto_ahash_digestsize(hash); ctx = sock_kmalloc(sk, len, GFP_KERNEL); if (!ctx) @@ -286,7 +445,7 @@ static int hash_accept_parent(void *private, struct sock *sk) ask->private = ctx; - ahash_request_set_tfm(&ctx->req, private); + ahash_request_set_tfm(&ctx->req, hash); ahash_request_set_callback(&ctx->req, CRYPTO_TFM_REQ_MAY_BACKLOG, af_alg_complete, &ctx->completion); @@ -295,12 +454,38 @@ static int hash_accept_parent(void *private, struct sock *sk) return 0; } +static int hash_accept_parent(void *private, struct sock *sk) +{ + struct algif_hash_tfm *tfm = private; + + if (!tfm->has_key && crypto_ahash_has_setkey(tfm->hash)) + return -ENOKEY; + + return hash_accept_parent_common(private, sk); +} + +static int hash_accept_parent_nokey(void *private, struct sock *sk) +{ + int err; + + err = hash_accept_parent_common(private, sk); + if (err) + goto out; + + sk->sk_destruct = hash_sock_destruct_nokey; + +out: + return err; +} + static const struct af_alg_type algif_type_hash = { .bind = hash_bind, .release = hash_release, .setkey = hash_setkey, .accept = hash_accept_parent, + .accept_nokey = hash_accept_parent_nokey, .ops = &algif_hash_ops, + .ops_nokey = &algif_hash_ops_nokey, .name = "hash", .owner = THIS_MODULE }; From 7f5c995746ebc3f431c596ffabb98af1b3e3de86 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Mon, 11 Jan 2016 21:26:50 +0800 Subject: [PATCH 156/325] crypto: skcipher - Add crypto_skcipher_has_setkey commit a1383cd86a062fc798899ab20f0ec2116cce39cb upstream. This patch adds a way for skcipher users to determine whether a key is required by a transform. Signed-off-by: Herbert Xu Signed-off-by: Greg Kroah-Hartman --- crypto/skcipher.c | 2 ++ include/crypto/skcipher.h | 7 +++++++ 2 files changed, 9 insertions(+) diff --git a/crypto/skcipher.c b/crypto/skcipher.c index 7591928be7ca..d199c0b1751c 100644 --- a/crypto/skcipher.c +++ b/crypto/skcipher.c @@ -118,6 +118,7 @@ static int crypto_init_skcipher_ops_blkcipher(struct crypto_tfm *tfm) skcipher->decrypt = skcipher_decrypt_blkcipher; skcipher->ivsize = crypto_blkcipher_ivsize(blkcipher); + skcipher->has_setkey = calg->cra_blkcipher.max_keysize; return 0; } @@ -210,6 +211,7 @@ static int crypto_init_skcipher_ops_ablkcipher(struct crypto_tfm *tfm) skcipher->ivsize = crypto_ablkcipher_ivsize(ablkcipher); skcipher->reqsize = crypto_ablkcipher_reqsize(ablkcipher) + sizeof(struct ablkcipher_request); + skcipher->has_setkey = calg->cra_ablkcipher.max_keysize; return 0; } diff --git a/include/crypto/skcipher.h b/include/crypto/skcipher.h index d8dd41fb034f..fd8742a40ff3 100644 --- a/include/crypto/skcipher.h +++ b/include/crypto/skcipher.h @@ -61,6 +61,8 @@ struct crypto_skcipher { unsigned int ivsize; unsigned int reqsize; + bool has_setkey; + struct crypto_tfm base; }; @@ -305,6 +307,11 @@ static inline int crypto_skcipher_setkey(struct crypto_skcipher *tfm, return tfm->setkey(tfm, key, keylen); } +static inline bool crypto_skcipher_has_setkey(struct crypto_skcipher *tfm) +{ + return tfm->has_setkey; +} + /** * crypto_skcipher_reqtfm() - obtain cipher handle from request * @req: skcipher_request out of which the cipher handle is to be obtained From a8e70a1a4fd6c0bc634a2b3f7b4b77ee378c3134 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Mon, 11 Jan 2016 21:29:41 +0800 Subject: [PATCH 157/325] crypto: algif_skcipher - Add key check exception for cipher_null commit 6e8d8ecf438792ecf7a3207488fb4eebc4edb040 upstream. This patch adds an exception to the key check so that cipher_null users may continue to use algif_skcipher without setting a key. Signed-off-by: Herbert Xu Signed-off-by: Greg Kroah-Hartman --- crypto/algif_skcipher.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c index bb0ee129a775..c3b5c91b22d9 100644 --- a/crypto/algif_skcipher.c +++ b/crypto/algif_skcipher.c @@ -978,7 +978,7 @@ static int skcipher_accept_parent(void *private, struct sock *sk) { struct skcipher_tfm *tfm = private; - if (!tfm->has_key) + if (!tfm->has_key && crypto_skcipher_has_setkey(tfm->skcipher)) return -ENOKEY; return skcipher_accept_parent_common(private, sk); From 1489f5d951089debd2a533e3a109fba9b36e3461 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 15 Jan 2016 15:13:05 -0500 Subject: [PATCH 158/325] libata: disable forced PORTS_IMPL for >= AHCI 1.3 commit 566d1827df2ef0cbe921d3d6946ac3007b1a6938 upstream. Some early controllers incorrectly reported zero ports in PORTS_IMPL register and the ahci driver fabricates PORTS_IMPL from the number of ports in those cases. This hasn't mattered but with the new nvme controllers there are cases where zero PORTS_IMPL is valid and should be honored. Disable the workaround for >= AHCI 1.3. Signed-off-by: Tejun Heo Reported-by: Andy Lutomirski Link: http://lkml.kernel.org/g/CALCETrU7yMvXEDhjAUShoHEhDwifJGapdw--BKxsP0jmjKGmRw@mail.gmail.com Cc: Sergei Shtylyov Signed-off-by: Greg Kroah-Hartman --- drivers/ata/libahci.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c index 4665512dae44..1f225cc1827f 100644 --- a/drivers/ata/libahci.c +++ b/drivers/ata/libahci.c @@ -495,8 +495,8 @@ void ahci_save_initial_config(struct device *dev, struct ahci_host_priv *hpriv) } } - /* fabricate port_map from cap.nr_ports */ - if (!port_map) { + /* fabricate port_map from cap.nr_ports for < AHCI 1.3 */ + if (!port_map && vers < 0x10300) { port_map = (1 << ahci_nr_ports(cap)) - 1; dev_warn(dev, "forcing PORTS_IMPL to 0x%x\n", port_map); From 2f129c2d4fdbdf159a5a86e0ee071406a4dd7a20 Mon Sep 17 00:00:00 2001 From: Alexandra Yates Date: Fri, 5 Feb 2016 15:27:49 -0800 Subject: [PATCH 159/325] ahci: Intel DNV device IDs SATA commit 342decff2b846b46fa61eb5ee40986fab79a9a32 upstream. Adding Intel codename DNV platform device IDs for SATA. Signed-off-by: Alexandra Yates Signed-off-by: Tejun Heo Signed-off-by: Greg Kroah-Hartman --- drivers/ata/ahci.c | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index cdfbcc54821f..99921aa0daca 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -264,6 +264,26 @@ static const struct pci_device_id ahci_pci_tbl[] = { { PCI_VDEVICE(INTEL, 0x3b2b), board_ahci }, /* PCH RAID */ { PCI_VDEVICE(INTEL, 0x3b2c), board_ahci }, /* PCH RAID */ { PCI_VDEVICE(INTEL, 0x3b2f), board_ahci }, /* PCH AHCI */ + { PCI_VDEVICE(INTEL, 0x19b0), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19b1), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19b2), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19b3), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19b4), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19b5), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19b6), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19b7), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19bE), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19bF), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19c0), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19c1), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19c2), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19c3), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19c4), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19c5), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19c6), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19c7), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19cE), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19cF), board_ahci }, /* DNV AHCI */ { PCI_VDEVICE(INTEL, 0x1c02), board_ahci }, /* CPT AHCI */ { PCI_VDEVICE(INTEL, 0x1c03), board_ahci }, /* CPT AHCI */ { PCI_VDEVICE(INTEL, 0x1c04), board_ahci }, /* CPT RAID */ From 758c560bcbc7d7814a391597fbcba02f087fb7f7 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Wed, 13 Jan 2016 14:59:03 +0800 Subject: [PATCH 160/325] crypto: af_alg - Allow af_af_alg_release_parent to be called on nokey path commit 6a935170a980024dd29199e9dbb5c4da4767a1b9 upstream. This patch allows af_alg_release_parent to be called even for nokey sockets. Signed-off-by: Herbert Xu Signed-off-by: Greg Kroah-Hartman --- crypto/af_alg.c | 9 ++++++++- include/crypto/if_alg.h | 1 + 2 files changed, 9 insertions(+), 1 deletion(-) diff --git a/crypto/af_alg.c b/crypto/af_alg.c index 6566d2eb0142..e7cb8367771d 100644 --- a/crypto/af_alg.c +++ b/crypto/af_alg.c @@ -133,6 +133,12 @@ void af_alg_release_parent(struct sock *sk) bool last; sk = ask->parent; + + if (ask->nokey_refcnt && !ask->refcnt) { + sock_put(sk); + return; + } + ask = alg_sk(sk); lock_sock(sk); @@ -268,8 +274,8 @@ int af_alg_accept(struct sock *sk, struct socket *newsock) struct alg_sock *ask = alg_sk(sk); const struct af_alg_type *type; struct sock *sk2; + unsigned int nokey; int err; - bool nokey; lock_sock(sk); type = ask->type; @@ -302,6 +308,7 @@ int af_alg_accept(struct sock *sk, struct socket *newsock) sock_hold(sk); alg_sk(sk2)->parent = sk; alg_sk(sk2)->type = type; + alg_sk(sk2)->nokey_refcnt = nokey; newsock->ops = type->ops; newsock->state = SS_CONNECTED; diff --git a/include/crypto/if_alg.h b/include/crypto/if_alg.h index df8284415c56..a2bfd7843f18 100644 --- a/include/crypto/if_alg.h +++ b/include/crypto/if_alg.h @@ -31,6 +31,7 @@ struct alg_sock { struct sock *parent; unsigned int refcnt; + unsigned int nokey_refcnt; const struct af_alg_type *type; void *private; From 20509d916186a2fcc6f248d9fb8882d3988834d2 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Wed, 13 Jan 2016 15:00:36 +0800 Subject: [PATCH 161/325] crypto: algif_hash - Remove custom release parent function commit f1d84af1835846a5a2b827382c5848faf2bb0e75 upstream. This patch removes the custom release parent function as the generic af_alg_release_parent now works for nokey sockets too. Signed-off-by: Herbert Xu Signed-off-by: Greg Kroah-Hartman --- crypto/algif_hash.c | 43 +++---------------------------------------- 1 file changed, 3 insertions(+), 40 deletions(-) diff --git a/crypto/algif_hash.c b/crypto/algif_hash.c index 46637bed4db8..3653ab60ec79 100644 --- a/crypto/algif_hash.c +++ b/crypto/algif_hash.c @@ -384,7 +384,7 @@ static int hash_setkey(void *private, const u8 *key, unsigned int keylen) return err; } -static void hash_sock_destruct_common(struct sock *sk) +static void hash_sock_destruct(struct sock *sk) { struct alg_sock *ask = alg_sk(sk); struct hash_ctx *ctx = ask->private; @@ -392,33 +392,10 @@ static void hash_sock_destruct_common(struct sock *sk) sock_kzfree_s(sk, ctx->result, crypto_ahash_digestsize(crypto_ahash_reqtfm(&ctx->req))); sock_kfree_s(sk, ctx, ctx->len); -} - -static void hash_sock_destruct(struct sock *sk) -{ - hash_sock_destruct_common(sk); af_alg_release_parent(sk); } -static void hash_release_parent_nokey(struct sock *sk) -{ - struct alg_sock *ask = alg_sk(sk); - - if (!ask->refcnt) { - sock_put(ask->parent); - return; - } - - af_alg_release_parent(sk); -} - -static void hash_sock_destruct_nokey(struct sock *sk) -{ - hash_sock_destruct_common(sk); - hash_release_parent_nokey(sk); -} - -static int hash_accept_parent_common(void *private, struct sock *sk) +static int hash_accept_parent_nokey(void *private, struct sock *sk) { struct hash_ctx *ctx; struct alg_sock *ask = alg_sk(sk); @@ -461,21 +438,7 @@ static int hash_accept_parent(void *private, struct sock *sk) if (!tfm->has_key && crypto_ahash_has_setkey(tfm->hash)) return -ENOKEY; - return hash_accept_parent_common(private, sk); -} - -static int hash_accept_parent_nokey(void *private, struct sock *sk) -{ - int err; - - err = hash_accept_parent_common(private, sk); - if (err) - goto out; - - sk->sk_destruct = hash_sock_destruct_nokey; - -out: - return err; + return hash_accept_parent_nokey(private, sk); } static const struct af_alg_type algif_type_hash = { From 40bfd37ab95c89b20d1fa63aeea25ba5799bc125 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Wed, 13 Jan 2016 15:01:06 +0800 Subject: [PATCH 162/325] crypto: algif_skcipher - Remove custom release parent function commit d7b65aee1e7b4c87922b0232eaba56a8a143a4a0 upstream. This patch removes the custom release parent function as the generic af_alg_release_parent now works for nokey sockets too. Signed-off-by: Herbert Xu Signed-off-by: Greg Kroah-Hartman --- crypto/algif_skcipher.c | 43 +++-------------------------------------- 1 file changed, 3 insertions(+), 40 deletions(-) diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c index c3b5c91b22d9..1fbdd497702f 100644 --- a/crypto/algif_skcipher.c +++ b/crypto/algif_skcipher.c @@ -895,7 +895,7 @@ static void skcipher_wait(struct sock *sk) msleep(100); } -static void skcipher_sock_destruct_common(struct sock *sk) +static void skcipher_sock_destruct(struct sock *sk) { struct alg_sock *ask = alg_sk(sk); struct skcipher_ctx *ctx = ask->private; @@ -907,33 +907,10 @@ static void skcipher_sock_destruct_common(struct sock *sk) skcipher_free_sgl(sk); sock_kzfree_s(sk, ctx->iv, crypto_skcipher_ivsize(tfm)); sock_kfree_s(sk, ctx, ctx->len); -} - -static void skcipher_sock_destruct(struct sock *sk) -{ - skcipher_sock_destruct_common(sk); af_alg_release_parent(sk); } -static void skcipher_release_parent_nokey(struct sock *sk) -{ - struct alg_sock *ask = alg_sk(sk); - - if (!ask->refcnt) { - sock_put(ask->parent); - return; - } - - af_alg_release_parent(sk); -} - -static void skcipher_sock_destruct_nokey(struct sock *sk) -{ - skcipher_sock_destruct_common(sk); - skcipher_release_parent_nokey(sk); -} - -static int skcipher_accept_parent_common(void *private, struct sock *sk) +static int skcipher_accept_parent_nokey(void *private, struct sock *sk) { struct skcipher_ctx *ctx; struct alg_sock *ask = alg_sk(sk); @@ -981,21 +958,7 @@ static int skcipher_accept_parent(void *private, struct sock *sk) if (!tfm->has_key && crypto_skcipher_has_setkey(tfm->skcipher)) return -ENOKEY; - return skcipher_accept_parent_common(private, sk); -} - -static int skcipher_accept_parent_nokey(void *private, struct sock *sk) -{ - int err; - - err = skcipher_accept_parent_common(private, sk); - if (err) - goto out; - - sk->sk_destruct = skcipher_sock_destruct_nokey; - -out: - return err; + return skcipher_accept_parent_nokey(private, sk); } static const struct af_alg_type algif_type_skcipher = { From 1bdbb041755b19975a9b87e22a02bd584a45e99c Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Wed, 13 Jan 2016 15:03:32 +0800 Subject: [PATCH 163/325] crypto: af_alg - Forbid bind(2) when nokey child sockets are present commit a6a48c565f6f112c6983e2a02b1602189ed6e26e upstream. This patch forbids the calling of bind(2) when there are child sockets created by accept(2) in existence, even if they are created on the nokey path. This is needed as those child sockets have references to the tfm object which bind(2) will destroy. Signed-off-by: Herbert Xu Signed-off-by: Greg Kroah-Hartman --- crypto/af_alg.c | 16 +++++++--------- 1 file changed, 7 insertions(+), 9 deletions(-) diff --git a/crypto/af_alg.c b/crypto/af_alg.c index e7cb8367771d..f5e18c2a4852 100644 --- a/crypto/af_alg.c +++ b/crypto/af_alg.c @@ -130,19 +130,16 @@ EXPORT_SYMBOL_GPL(af_alg_release); void af_alg_release_parent(struct sock *sk) { struct alg_sock *ask = alg_sk(sk); - bool last; + unsigned int nokey = ask->nokey_refcnt; + bool last = nokey && !ask->refcnt; sk = ask->parent; - - if (ask->nokey_refcnt && !ask->refcnt) { - sock_put(sk); - return; - } - ask = alg_sk(sk); lock_sock(sk); - last = !--ask->refcnt; + ask->nokey_refcnt -= nokey; + if (!last) + last = !--ask->refcnt; release_sock(sk); if (last) @@ -188,7 +185,7 @@ static int alg_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) err = -EBUSY; lock_sock(sk); - if (ask->refcnt) + if (ask->refcnt | ask->nokey_refcnt) goto unlock; swap(ask->type, type); @@ -306,6 +303,7 @@ int af_alg_accept(struct sock *sk, struct socket *newsock) if (nokey || !ask->refcnt++) sock_hold(sk); + ask->nokey_refcnt += nokey; alg_sk(sk2)->parent = sk; alg_sk(sk2)->type = type; alg_sk(sk2)->nokey_refcnt = nokey; From aa51954b30e7d07522689452aba08b24f748a005 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Fri, 15 Jan 2016 22:01:08 +0800 Subject: [PATCH 164/325] crypto: algif_hash - Fix race condition in hash_check_key commit ad46d7e33219218605ea619e32553daf4f346b9f upstream. We need to lock the child socket in hash_check_key as otherwise two simultaneous calls can cause the parent socket to be freed. Signed-off-by: Herbert Xu Signed-off-by: Greg Kroah-Hartman --- crypto/algif_hash.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/crypto/algif_hash.c b/crypto/algif_hash.c index 3653ab60ec79..608a7562839d 100644 --- a/crypto/algif_hash.c +++ b/crypto/algif_hash.c @@ -242,22 +242,23 @@ static struct proto_ops algif_hash_ops = { static int hash_check_key(struct socket *sock) { - int err; + int err = 0; struct sock *psk; struct alg_sock *pask; struct algif_hash_tfm *tfm; struct sock *sk = sock->sk; struct alg_sock *ask = alg_sk(sk); + lock_sock(sk); if (ask->refcnt) - return 0; + goto unlock_child; psk = ask->parent; pask = alg_sk(ask->parent); tfm = pask->private; err = -ENOKEY; - lock_sock(psk); + lock_sock_nested(psk, SINGLE_DEPTH_NESTING); if (!tfm->has_key) goto unlock; @@ -271,6 +272,8 @@ static int hash_check_key(struct socket *sock) unlock: release_sock(psk); +unlock_child: + release_sock(sk); return err; } From f84d1fcb59c6b17dec972932c05674127babf476 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Fri, 15 Jan 2016 22:02:20 +0800 Subject: [PATCH 165/325] crypto: algif_skcipher - Fix race condition in skcipher_check_key commit 1822793a523e5d5730b19cc21160ff1717421bc8 upstream. We need to lock the child socket in skcipher_check_key as otherwise two simultaneous calls can cause the parent socket to be freed. Signed-off-by: Herbert Xu Signed-off-by: Greg Kroah-Hartman --- crypto/algif_skcipher.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c index 1fbdd497702f..1b02e372a770 100644 --- a/crypto/algif_skcipher.c +++ b/crypto/algif_skcipher.c @@ -755,22 +755,23 @@ static struct proto_ops algif_skcipher_ops = { static int skcipher_check_key(struct socket *sock) { - int err; + int err = 0; struct sock *psk; struct alg_sock *pask; struct skcipher_tfm *tfm; struct sock *sk = sock->sk; struct alg_sock *ask = alg_sk(sk); + lock_sock(sk); if (ask->refcnt) - return 0; + goto unlock_child; psk = ask->parent; pask = alg_sk(ask->parent); tfm = pask->private; err = -ENOKEY; - lock_sock(psk); + lock_sock_nested(psk, SINGLE_DEPTH_NESTING); if (!tfm->has_key) goto unlock; @@ -784,6 +785,8 @@ static int skcipher_check_key(struct socket *sock) unlock: release_sock(psk); +unlock_child: + release_sock(sk); return err; } From d175a4ee836be6be37de8637b0fed5b4daedea77 Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Mon, 18 Jan 2016 17:06:05 +0100 Subject: [PATCH 166/325] crypto: crc32c - Fix crc32c soft dependency commit fd7f6727102a1ccf6b4c1dfcc631f9b546526b26 upstream. I don't think it makes sense for a module to have a soft dependency on itself. This seems quite cyclic by nature and I can't see what purpose it could serve. OTOH libcrc32c calls crypto_alloc_shash("crc32c", 0, 0) so it pretty much assumes that some incarnation of the "crc32c" hash algorithm has been loaded. Therefore it makes sense to have the soft dependency there (as crc-t10dif does.) Cc: Tim Chen Cc: "David S. Miller" Signed-off-by: Jean Delvare Signed-off-by: Herbert Xu Signed-off-by: Greg Kroah-Hartman --- crypto/crc32c_generic.c | 1 - lib/libcrc32c.c | 1 + 2 files changed, 1 insertion(+), 1 deletion(-) diff --git a/crypto/crc32c_generic.c b/crypto/crc32c_generic.c index 06f1b60f02b2..4c0a0e271876 100644 --- a/crypto/crc32c_generic.c +++ b/crypto/crc32c_generic.c @@ -172,4 +172,3 @@ MODULE_DESCRIPTION("CRC32c (Castagnoli) calculations wrapper for lib/crc32c"); MODULE_LICENSE("GPL"); MODULE_ALIAS_CRYPTO("crc32c"); MODULE_ALIAS_CRYPTO("crc32c-generic"); -MODULE_SOFTDEP("pre: crc32c"); diff --git a/lib/libcrc32c.c b/lib/libcrc32c.c index 6a08ce7d6adc..acf9da449f81 100644 --- a/lib/libcrc32c.c +++ b/lib/libcrc32c.c @@ -74,3 +74,4 @@ module_exit(libcrc32c_mod_fini); MODULE_AUTHOR("Clay Haapala "); MODULE_DESCRIPTION("CRC32c (Castagnoli) calculations"); MODULE_LICENSE("GPL"); +MODULE_SOFTDEP("pre: crc32c"); From fec8beab63283003b546f83eebbbe32efb9acc53 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Mon, 18 Jan 2016 18:46:10 +0800 Subject: [PATCH 167/325] crypto: algif_skcipher - Load TX SG list after waiting commit 4f0414e54e4d1893c6f08260693f8ef84c929293 upstream. We need to load the TX SG list in sendmsg(2) after waiting for incoming data, not before. Reported-by: Dmitry Vyukov Signed-off-by: Herbert Xu Tested-by: Dmitry Vyukov Signed-off-by: Greg Kroah-Hartman --- crypto/algif_skcipher.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c index 1b02e372a770..afb43392524f 100644 --- a/crypto/algif_skcipher.c +++ b/crypto/algif_skcipher.c @@ -647,13 +647,6 @@ static int skcipher_recvmsg_sync(struct socket *sock, struct msghdr *msg, lock_sock(sk); while (msg_data_left(msg)) { - sgl = list_first_entry(&ctx->tsgl, - struct skcipher_sg_list, list); - sg = sgl->sg; - - while (!sg->length) - sg++; - if (!ctx->used) { err = skcipher_wait_for_data(sk, flags); if (err) @@ -674,6 +667,13 @@ static int skcipher_recvmsg_sync(struct socket *sock, struct msghdr *msg, if (!used) goto free; + sgl = list_first_entry(&ctx->tsgl, + struct skcipher_sg_list, list); + sg = sgl->sg; + + while (!sg->length) + sg++; + skcipher_request_set_crypt(&ctx->req, sg, ctx->rsgl.sg, used, ctx->iv); From 3dd3e2544c48d55e975efca5f34b77dbbe8895c9 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Tue, 19 Jan 2016 21:23:57 +0800 Subject: [PATCH 168/325] crypto: algif_skcipher - sendmsg SG marking is off by one commit 202736d99b7f29279db9da61587f11a08a04a9c6 upstream. We mark the end of the SG list in sendmsg and sendpage and unmark it on the next send call. Unfortunately the unmarking in sendmsg is off-by-one, leading to an SG list that is too short. Fixes: 0f477b655a52 ("crypto: algif - Mark sgl end at the end of data") Signed-off-by: Herbert Xu Signed-off-by: Greg Kroah-Hartman --- crypto/algif_skcipher.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c index afb43392524f..76175e316e6b 100644 --- a/crypto/algif_skcipher.c +++ b/crypto/algif_skcipher.c @@ -392,7 +392,8 @@ static int skcipher_sendmsg(struct socket *sock, struct msghdr *msg, sgl = list_entry(ctx->tsgl.prev, struct skcipher_sg_list, list); sg = sgl->sg; - sg_unmark_end(sg + sgl->cur); + if (sgl->cur) + sg_unmark_end(sg + sgl->cur - 1); do { i = sgl->cur; plen = min_t(int, len, PAGE_SIZE); From 2a6c3d5457e0e63c20125845ff7ccd41b32b53d3 Mon Sep 17 00:00:00 2001 From: Horia Geant? Date: Tue, 12 Jan 2016 17:59:29 +0200 Subject: [PATCH 169/325] crypto: caam - make write transactions bufferable on PPC platforms commit e7a7104e432c0db8469ca3568daf4f1d1afe3e73 upstream. Previous change (see "Fixes" tag) to the MCFGR register clears AWCACHE[0] ("bufferable" AXI3 attribute) (which is "1" at POR). This makes all writes non-bufferable, causing a ~ 5% performance drop for PPC-based platforms. Rework previous change such that MCFGR[AWCACHE]=4'b0011 (bufferable + cacheable) for all platforms. Note: For ARM-based platforms, AWCACHE[0] is ignored by the interconnect IP. Fixes: f10967495144 ("crypto: caam - fix snooping for write transactions") Signed-off-by: Horia Geant? Signed-off-by: Herbert Xu Signed-off-by: Greg Kroah-Hartman --- drivers/crypto/caam/ctrl.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/crypto/caam/ctrl.c b/drivers/crypto/caam/ctrl.c index 8abb4bc548cc..69d4a1326fee 100644 --- a/drivers/crypto/caam/ctrl.c +++ b/drivers/crypto/caam/ctrl.c @@ -534,8 +534,8 @@ static int caam_probe(struct platform_device *pdev) * long pointers in master configuration register */ clrsetbits_32(&ctrl->mcr, MCFGR_AWCACHE_MASK, MCFGR_AWCACHE_CACH | - MCFGR_WDENABLE | (sizeof(dma_addr_t) == sizeof(u64) ? - MCFGR_LONG_PTR : 0)); + MCFGR_AWCACHE_BUFF | MCFGR_WDENABLE | + (sizeof(dma_addr_t) == sizeof(u64) ? MCFGR_LONG_PTR : 0)); /* * Read the Compile Time paramters and SCFGR to determine From 936a322b57b4d98b42724af04c2d457bf1292514 Mon Sep 17 00:00:00 2001 From: Eli Cooper Date: Fri, 22 Jan 2016 00:24:08 +0800 Subject: [PATCH 170/325] crypto: chacha20-ssse3 - Align stack pointer to 64 bytes commit cbe09bd51bf23b42c3a94c5fb6815e1397c5fc3f upstream. This aligns the stack pointer in chacha20_4block_xor_ssse3 to 64 bytes. Fixes general protection faults and potential kernel panics. Signed-off-by: Eli Cooper Acked-by: Martin Willi Signed-off-by: Herbert Xu Signed-off-by: Greg Kroah-Hartman --- arch/x86/crypto/chacha20-ssse3-x86_64.S | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/arch/x86/crypto/chacha20-ssse3-x86_64.S b/arch/x86/crypto/chacha20-ssse3-x86_64.S index 712b13047b41..3a33124e9112 100644 --- a/arch/x86/crypto/chacha20-ssse3-x86_64.S +++ b/arch/x86/crypto/chacha20-ssse3-x86_64.S @@ -157,7 +157,9 @@ ENTRY(chacha20_4block_xor_ssse3) # done with the slightly better performing SSSE3 byte shuffling, # 7/12-bit word rotation uses traditional shift+OR. - sub $0x40,%rsp + mov %rsp,%r11 + sub $0x80,%rsp + and $~63,%rsp # x0..15[0-3] = s0..3[0..3] movq 0x00(%rdi),%xmm1 @@ -620,6 +622,6 @@ ENTRY(chacha20_4block_xor_ssse3) pxor %xmm1,%xmm15 movdqu %xmm15,0xf0(%rsi) - add $0x40,%rsp + mov %r11,%rsp ret ENDPROC(chacha20_4block_xor_ssse3) From 6bb06a4fa1894533beaab22f0c657866b0e61b06 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Wed, 27 Jan 2016 00:16:37 +0800 Subject: [PATCH 171/325] crypto: shash - Fix has_key setting commit 00420a65fa2beb3206090ead86942484df2275f3 upstream. The has_key logic is wrong for shash algorithms as they always have a setkey function. So we should instead be testing against shash_no_setkey. Fixes: a5596d633278 ("crypto: hash - Add crypto_ahash_has_setkey") Reported-by: Stephan Mueller Signed-off-by: Herbert Xu Tested-by: Stephan Mueller Signed-off-by: Greg Kroah-Hartman --- crypto/shash.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/crypto/shash.c b/crypto/shash.c index 88a27de79848..359754591653 100644 --- a/crypto/shash.c +++ b/crypto/shash.c @@ -354,11 +354,10 @@ int crypto_init_shash_ops_async(struct crypto_tfm *tfm) crt->final = shash_async_final; crt->finup = shash_async_finup; crt->digest = shash_async_digest; + crt->setkey = shash_async_setkey; + + crt->has_setkey = alg->setkey != shash_no_setkey; - if (alg->setkey) { - crt->setkey = shash_async_setkey; - crt->has_setkey = true; - } if (alg->export) crt->export = shash_async_export; if (alg->import) From 792c6ff0d8ce1a3d1da9f7b657aa6a8017515216 Mon Sep 17 00:00:00 2001 From: "Wang, Rui Y" Date: Wed, 27 Jan 2016 17:08:37 +0800 Subject: [PATCH 172/325] crypto: algif_hash - wait for crypto_ahash_init() to complete commit fe09786178f9df713a4b2dd6b93c0a722346bf5e upstream. hash_sendmsg/sendpage() need to wait for the completion of crypto_ahash_init() otherwise it can cause panic. Signed-off-by: Rui Wang Signed-off-by: Herbert Xu Signed-off-by: Greg Kroah-Hartman --- crypto/algif_hash.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/crypto/algif_hash.c b/crypto/algif_hash.c index 608a7562839d..68a5ceaa04c8 100644 --- a/crypto/algif_hash.c +++ b/crypto/algif_hash.c @@ -54,7 +54,8 @@ static int hash_sendmsg(struct socket *sock, struct msghdr *msg, lock_sock(sk); if (!ctx->more) { - err = crypto_ahash_init(&ctx->req); + err = af_alg_wait_for_completion(crypto_ahash_init(&ctx->req), + &ctx->completion); if (err) goto unlock; } @@ -125,6 +126,7 @@ static ssize_t hash_sendpage(struct socket *sock, struct page *page, } else { if (!ctx->more) { err = crypto_ahash_init(&ctx->req); + err = af_alg_wait_for_completion(err, &ctx->completion); if (err) goto unlock; } From 8592536bcfcbc717a3bf7cec57d7c1b38f4eec1d Mon Sep 17 00:00:00 2001 From: Ryan Ware Date: Thu, 11 Feb 2016 15:58:44 -0800 Subject: [PATCH 173/325] EVM: Use crypto_memneq() for digest comparisons commit 613317bd212c585c20796c10afe5daaa95d4b0a1 upstream. This patch fixes vulnerability CVE-2016-2085. The problem exists because the vm_verify_hmac() function includes a use of memcmp(). Unfortunately, this allows timing side channel attacks; specifically a MAC forgery complexity drop from 2^128 to 2^12. This patch changes the memcmp() to the cryptographically safe crypto_memneq(). Reported-by: Xiaofei Rex Guo Signed-off-by: Ryan Ware Signed-off-by: Mimi Zohar Signed-off-by: James Morris Signed-off-by: Greg Kroah-Hartman --- security/integrity/evm/evm_main.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/security/integrity/evm/evm_main.c b/security/integrity/evm/evm_main.c index 1334e02ae8f4..3d145a3ffccf 100644 --- a/security/integrity/evm/evm_main.c +++ b/security/integrity/evm/evm_main.c @@ -23,6 +23,7 @@ #include #include #include +#include #include "evm.h" int evm_initialized; @@ -148,7 +149,7 @@ static enum integrity_status evm_verify_hmac(struct dentry *dentry, xattr_value_len, calc.digest); if (rc) break; - rc = memcmp(xattr_data->digest, calc.digest, + rc = crypto_memneq(xattr_data->digest, calc.digest, sizeof(calc.digest)); if (rc) rc = -EINVAL; From cfeab1cf35bcd023bb5db62635eccf8e8def7527 Mon Sep 17 00:00:00 2001 From: Mathias Krause Date: Mon, 1 Feb 2016 14:27:30 +0100 Subject: [PATCH 174/325] crypto: user - lock crypto_alg_list on alg dump commit 63e41ebc6630f39422d87f8a4bade1e793f37a01 upstream. We miss to take the crypto_alg_sem semaphore when traversing the crypto_alg_list for CRYPTO_MSG_GETALG dumps. This allows a race with crypto_unregister_alg() removing algorithms from the list while we're still traversing it, thereby leading to a use-after-free as show below: [ 3482.071639] general protection fault: 0000 [#1] SMP [ 3482.075639] Modules linked in: aes_x86_64 glue_helper lrw ablk_helper cryptd gf128mul ipv6 pcspkr serio_raw virtio_net microcode virtio_pci virtio_ring virtio sr_mod cdrom [last unloaded: aesni_intel] [ 3482.075639] CPU: 1 PID: 11065 Comm: crconf Not tainted 4.3.4-grsec+ #126 [ 3482.075639] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.7.5-20140531_083030-gandalf 04/01/2014 [ 3482.075639] task: ffff88001cd41a40 ti: ffff88001cd422c8 task.ti: ffff88001cd422c8 [ 3482.075639] RIP: 0010:[] [] strncpy+0x13/0x30 [ 3482.075639] RSP: 0018:ffff88001f713b60 EFLAGS: 00010202 [ 3482.075639] RAX: ffff88001f6c4430 RBX: ffff88001f6c43a0 RCX: ffff88001f6c4430 [ 3482.075639] RDX: 0000000000000040 RSI: fefefefefefeff16 RDI: ffff88001f6c4430 [ 3482.075639] RBP: ffff88001f713b60 R08: ffff88001f6c4470 R09: ffff88001f6c4480 [ 3482.075639] R10: 0000000000000002 R11: 0000000000000246 R12: ffff88001ce2aa28 [ 3482.075639] R13: ffff880000093700 R14: ffff88001f5e4bf8 R15: 0000000000003b20 [ 3482.075639] FS: 0000033826fa2700(0000) GS:ffff88001e900000(0000) knlGS:0000000000000000 [ 3482.075639] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 3482.075639] CR2: ffffffffff600400 CR3: 00000000139ec000 CR4: 00000000001606f0 [ 3482.075639] Stack: [ 3482.075639] ffff88001f713bd8 ffffffff936ccd00 ffff88001e5c4200 ffff880000093700 [ 3482.075639] ffff88001f713bd0 ffffffff938ef4bf 0000000000000000 0000000000003b20 [ 3482.075639] ffff88001f5e4bf8 ffff88001f5e4848 0000000000000000 0000000000003b20 [ 3482.075639] Call Trace: [ 3482.075639] [] crypto_report_alg+0xc0/0x3e0 [ 3482.075639] [] ? __alloc_skb+0x16f/0x300 [ 3482.075639] [] crypto_dump_report+0x6a/0x90 [ 3482.075639] [] netlink_dump+0x147/0x2e0 [ 3482.075639] [] __netlink_dump_start+0x159/0x190 [ 3482.075639] [] crypto_user_rcv_msg+0xc3/0x130 [ 3482.075639] [] ? crypto_report_alg+0x3e0/0x3e0 [ 3482.075639] [] ? alg_test_crc32c+0x120/0x120 [ 3482.075639] [] ? __netlink_lookup+0xd5/0x120 [ 3482.075639] [] ? crypto_add_alg+0x1d0/0x1d0 [ 3482.075639] [] netlink_rcv_skb+0xe1/0x130 [ 3482.075639] [] crypto_netlink_rcv+0x28/0x40 [ 3482.075639] [] netlink_unicast+0x108/0x180 [ 3482.075639] [] netlink_sendmsg+0x541/0x770 [ 3482.075639] [] sock_sendmsg+0x21/0x40 [ 3482.075639] [] SyS_sendto+0xf3/0x130 [ 3482.075639] [] ? bad_area_nosemaphore+0x13/0x20 [ 3482.075639] [] ? __do_page_fault+0x80/0x3a0 [ 3482.075639] [] entry_SYSCALL_64_fastpath+0x12/0x6e [ 3482.075639] Code: 88 4a ff 75 ed 5d 48 0f ba 2c 24 3f c3 66 66 2e 0f 1f 84 00 00 00 00 00 55 48 85 d2 48 89 f8 48 89 f9 4c 8d 04 17 48 89 e5 74 15 <0f> b6 16 80 fa 01 88 11 48 83 de ff 48 83 c1 01 4c 39 c1 75 eb [ 3482.075639] RIP [] strncpy+0x13/0x30 To trigger the race run the following loops simultaneously for a while: $ while : ; do modprobe aesni-intel; rmmod aesni-intel; done $ while : ; do crconf show all > /dev/null; done Fix the race by taking the crypto_alg_sem read lock, thereby preventing crypto_unregister_alg() from modifying the algorithm list during the dump. This bug has been detected by the PaX memory sanitize feature. Signed-off-by: Mathias Krause Cc: Steffen Klassert Cc: PaX Team Signed-off-by: Herbert Xu Signed-off-by: Greg Kroah-Hartman --- crypto/crypto_user.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/crypto/crypto_user.c b/crypto/crypto_user.c index 237f3795cfaa..43fe85f20d57 100644 --- a/crypto/crypto_user.c +++ b/crypto/crypto_user.c @@ -499,6 +499,7 @@ static int crypto_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) if (link->dump == NULL) return -EINVAL; + down_read(&crypto_alg_sem); list_for_each_entry(alg, &crypto_alg_list, cra_list) dump_alloc += CRYPTO_REPORT_MAXSIZE; @@ -508,8 +509,11 @@ static int crypto_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) .done = link->done, .min_dump_alloc = dump_alloc, }; - return netlink_dump_start(crypto_nlsk, skb, nlh, &c); + err = netlink_dump_start(crypto_nlsk, skb, nlh, &c); } + up_read(&crypto_alg_sem); + + return err; } err = nlmsg_parse(nlh, crypto_msg_min[type], attrs, CRYPTOCFGA_MAX, From 3e597bb7c3be2c69c03a6af95d27d5ed16b7b882 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Wed, 3 Feb 2016 21:39:24 +0800 Subject: [PATCH 175/325] crypto: algif_skcipher - Do not assume that req is unchanged commit ec69bbfb9902c32a5c1492f2b1b8ad032a66d724 upstream. The async path in algif_skcipher assumes that the crypto completion function will be called with the original request. This is not necessarily the case. In fact there is no need for this anyway since we already embed information into the request with struct skcipher_async_req. This patch adds a pointer to that struct and then passes it as the data to the callback function. Signed-off-by: Herbert Xu Tested-by: Tadeusz Struk Signed-off-by: Greg Kroah-Hartman --- crypto/algif_skcipher.c | 64 +++++++++++++++++++---------------------- 1 file changed, 30 insertions(+), 34 deletions(-) diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c index 76175e316e6b..5b65779b1577 100644 --- a/crypto/algif_skcipher.c +++ b/crypto/algif_skcipher.c @@ -65,18 +65,10 @@ struct skcipher_async_req { struct skcipher_async_rsgl first_sgl; struct list_head list; struct scatterlist *tsg; - char iv[]; + atomic_t *inflight; + struct skcipher_request req; }; -#define GET_SREQ(areq, ctx) (struct skcipher_async_req *)((char *)areq + \ - crypto_skcipher_reqsize(crypto_skcipher_reqtfm(&ctx->req))) - -#define GET_REQ_SIZE(ctx) \ - crypto_skcipher_reqsize(crypto_skcipher_reqtfm(&ctx->req)) - -#define GET_IV_SIZE(ctx) \ - crypto_skcipher_ivsize(crypto_skcipher_reqtfm(&ctx->req)) - #define MAX_SGL_ENTS ((4096 - sizeof(struct skcipher_sg_list)) / \ sizeof(struct scatterlist) - 1) @@ -102,15 +94,12 @@ static void skcipher_free_async_sgls(struct skcipher_async_req *sreq) static void skcipher_async_cb(struct crypto_async_request *req, int err) { - struct sock *sk = req->data; - struct alg_sock *ask = alg_sk(sk); - struct skcipher_ctx *ctx = ask->private; - struct skcipher_async_req *sreq = GET_SREQ(req, ctx); + struct skcipher_async_req *sreq = req->data; struct kiocb *iocb = sreq->iocb; - atomic_dec(&ctx->inflight); + atomic_dec(sreq->inflight); skcipher_free_async_sgls(sreq); - kfree(req); + kzfree(sreq); iocb->ki_complete(iocb, err, err); } @@ -509,37 +498,42 @@ static int skcipher_recvmsg_async(struct socket *sock, struct msghdr *msg, { struct sock *sk = sock->sk; struct alg_sock *ask = alg_sk(sk); + struct sock *psk = ask->parent; + struct alg_sock *pask = alg_sk(psk); struct skcipher_ctx *ctx = ask->private; + struct skcipher_tfm *skc = pask->private; + struct crypto_skcipher *tfm = skc->skcipher; struct skcipher_sg_list *sgl; struct scatterlist *sg; struct skcipher_async_req *sreq; struct skcipher_request *req; struct skcipher_async_rsgl *last_rsgl = NULL; unsigned int txbufs = 0, len = 0, tx_nents = skcipher_all_sg_nents(ctx); - unsigned int reqlen = sizeof(struct skcipher_async_req) + - GET_REQ_SIZE(ctx) + GET_IV_SIZE(ctx); + unsigned int reqsize = crypto_skcipher_reqsize(tfm); + unsigned int ivsize = crypto_skcipher_ivsize(tfm); int err = -ENOMEM; bool mark = false; + char *iv; + + sreq = kzalloc(sizeof(*sreq) + reqsize + ivsize, GFP_KERNEL); + if (unlikely(!sreq)) + goto out; + + req = &sreq->req; + iv = (char *)(req + 1) + reqsize; + sreq->iocb = msg->msg_iocb; + INIT_LIST_HEAD(&sreq->list); + sreq->inflight = &ctx->inflight; lock_sock(sk); - req = kmalloc(reqlen, GFP_KERNEL); - if (unlikely(!req)) - goto unlock; - - sreq = GET_SREQ(req, ctx); - sreq->iocb = msg->msg_iocb; - memset(&sreq->first_sgl, '\0', sizeof(struct skcipher_async_rsgl)); - INIT_LIST_HEAD(&sreq->list); sreq->tsg = kcalloc(tx_nents, sizeof(*sg), GFP_KERNEL); - if (unlikely(!sreq->tsg)) { - kfree(req); + if (unlikely(!sreq->tsg)) goto unlock; - } sg_init_table(sreq->tsg, tx_nents); - memcpy(sreq->iv, ctx->iv, GET_IV_SIZE(ctx)); - skcipher_request_set_tfm(req, crypto_skcipher_reqtfm(&ctx->req)); + memcpy(iv, ctx->iv, ivsize); + skcipher_request_set_tfm(req, tfm); skcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG, - skcipher_async_cb, sk); + skcipher_async_cb, sreq); while (iov_iter_count(&msg->msg_iter)) { struct skcipher_async_rsgl *rsgl; @@ -615,20 +609,22 @@ static int skcipher_recvmsg_async(struct socket *sock, struct msghdr *msg, sg_mark_end(sreq->tsg + txbufs - 1); skcipher_request_set_crypt(req, sreq->tsg, sreq->first_sgl.sgl.sg, - len, sreq->iv); + len, iv); err = ctx->enc ? crypto_skcipher_encrypt(req) : crypto_skcipher_decrypt(req); if (err == -EINPROGRESS) { atomic_inc(&ctx->inflight); err = -EIOCBQUEUED; + sreq = NULL; goto unlock; } free: skcipher_free_async_sgls(sreq); - kfree(req); unlock: skcipher_wmem_wakeup(sk); release_sock(sk); + kzfree(sreq); +out: return err; } From 66bca97f21762ba58ce3d6767b27f782c702ef65 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Wed, 3 Feb 2016 21:39:26 +0800 Subject: [PATCH 176/325] crypto: algif_skcipher - Do not dereference ctx without socket lock commit 6454c2b83f719057069777132b13949e4c6b6350 upstream. Any access to non-constant bits of the private context must be done under the socket lock, in particular, this includes ctx->req. This patch moves such accesses under the lock, and fetches the tfm from the parent socket which is guaranteed to be constant, rather than from ctx->req. Signed-off-by: Herbert Xu Signed-off-by: Greg Kroah-Hartman --- crypto/algif_skcipher.c | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c index 5b65779b1577..a82804e2a9bd 100644 --- a/crypto/algif_skcipher.c +++ b/crypto/algif_skcipher.c @@ -295,8 +295,11 @@ static int skcipher_sendmsg(struct socket *sock, struct msghdr *msg, { struct sock *sk = sock->sk; struct alg_sock *ask = alg_sk(sk); + struct sock *psk = ask->parent; + struct alg_sock *pask = alg_sk(psk); struct skcipher_ctx *ctx = ask->private; - struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(&ctx->req); + struct skcipher_tfm *skc = pask->private; + struct crypto_skcipher *tfm = skc->skcipher; unsigned ivsize = crypto_skcipher_ivsize(tfm); struct skcipher_sg_list *sgl; struct af_alg_control con = {}; @@ -508,7 +511,7 @@ static int skcipher_recvmsg_async(struct socket *sock, struct msghdr *msg, struct skcipher_async_req *sreq; struct skcipher_request *req; struct skcipher_async_rsgl *last_rsgl = NULL; - unsigned int txbufs = 0, len = 0, tx_nents = skcipher_all_sg_nents(ctx); + unsigned int txbufs = 0, len = 0, tx_nents; unsigned int reqsize = crypto_skcipher_reqsize(tfm); unsigned int ivsize = crypto_skcipher_ivsize(tfm); int err = -ENOMEM; @@ -526,6 +529,7 @@ static int skcipher_recvmsg_async(struct socket *sock, struct msghdr *msg, sreq->inflight = &ctx->inflight; lock_sock(sk); + tx_nents = skcipher_all_sg_nents(ctx); sreq->tsg = kcalloc(tx_nents, sizeof(*sg), GFP_KERNEL); if (unlikely(!sreq->tsg)) goto unlock; @@ -633,9 +637,12 @@ static int skcipher_recvmsg_sync(struct socket *sock, struct msghdr *msg, { struct sock *sk = sock->sk; struct alg_sock *ask = alg_sk(sk); + struct sock *psk = ask->parent; + struct alg_sock *pask = alg_sk(psk); struct skcipher_ctx *ctx = ask->private; - unsigned bs = crypto_skcipher_blocksize(crypto_skcipher_reqtfm( - &ctx->req)); + struct skcipher_tfm *skc = pask->private; + struct crypto_skcipher *tfm = skc->skcipher; + unsigned bs = crypto_skcipher_blocksize(tfm); struct skcipher_sg_list *sgl; struct scatterlist *sg; int err = -EAGAIN; From 12426bd6b05f286fe252ddb69c4aea3209d01d5b Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Wed, 3 Feb 2016 21:39:27 +0800 Subject: [PATCH 177/325] crypto: algif_skcipher - Do not set MAY_BACKLOG on the async path commit dad41997063723eaf5f77bc2015606a5a9bce320 upstream. The async path cannot use MAY_BACKLOG because it is not meant to block, which is what MAY_BACKLOG does. On the other hand, both the sync and async paths can make use of MAY_SLEEP. Signed-off-by: Herbert Xu Signed-off-by: Greg Kroah-Hartman --- crypto/algif_skcipher.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c index a82804e2a9bd..f5e9f9310b48 100644 --- a/crypto/algif_skcipher.c +++ b/crypto/algif_skcipher.c @@ -536,7 +536,7 @@ static int skcipher_recvmsg_async(struct socket *sock, struct msghdr *msg, sg_init_table(sreq->tsg, tx_nents); memcpy(iv, ctx->iv, ivsize); skcipher_request_set_tfm(req, tfm); - skcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG, + skcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_SLEEP, skcipher_async_cb, sreq); while (iov_iter_count(&msg->msg_iter)) { @@ -950,7 +950,8 @@ static int skcipher_accept_parent_nokey(void *private, struct sock *sk) ask->private = ctx; skcipher_request_set_tfm(&ctx->req, skcipher); - skcipher_request_set_callback(&ctx->req, CRYPTO_TFM_REQ_MAY_BACKLOG, + skcipher_request_set_callback(&ctx->req, CRYPTO_TFM_REQ_MAY_SLEEP | + CRYPTO_TFM_REQ_MAY_BACKLOG, af_alg_complete, &ctx->completion); sk->sk_destruct = skcipher_sock_destruct; From 714e7964f79e3b74e16b1d040efa34705da891f8 Mon Sep 17 00:00:00 2001 From: Cyrille Pitchen Date: Fri, 5 Feb 2016 13:45:12 +0100 Subject: [PATCH 178/325] crypto: atmel-sha - fix atmel_sha_remove() commit d961436c11482e974b702c8324426208f00cd7c4 upstream. Since atmel_sha_probe() uses devm_xxx functions to allocate resources, atmel_sha_remove() should no longer explicitly release them. Signed-off-by: Cyrille Pitchen Fixes: b0e8b3417a62 ("crypto: atmel - use devm_xxx() managed function") Signed-off-by: Herbert Xu Signed-off-by: Greg Kroah-Hartman --- drivers/crypto/atmel-sha.c | 7 ------- 1 file changed, 7 deletions(-) diff --git a/drivers/crypto/atmel-sha.c b/drivers/crypto/atmel-sha.c index 660d8c06540b..7a11c285af6d 100644 --- a/drivers/crypto/atmel-sha.c +++ b/drivers/crypto/atmel-sha.c @@ -1484,13 +1484,6 @@ static int atmel_sha_remove(struct platform_device *pdev) if (sha_dd->caps.has_dma) atmel_sha_dma_cleanup(sha_dd); - iounmap(sha_dd->io_base); - - clk_put(sha_dd->iclk); - - if (sha_dd->irq >= 0) - free_irq(sha_dd->irq, sha_dd); - return 0; } From ee36c87a655325a7b5e442a9650a782db4ea20d2 Mon Sep 17 00:00:00 2001 From: Cyrille Pitchen Date: Fri, 5 Feb 2016 13:45:13 +0100 Subject: [PATCH 179/325] crypto: atmel-sha - remove calls of clk_prepare() from atomic contexts commit c033042aa8f69894df37dabcaa0231594834a4e4 upstream. clk_prepare()/clk_unprepare() must not be called within atomic context. This patch calls clk_prepare() once for all from atmel_sha_probe() and clk_unprepare() from atmel_sha_remove(). Then calls of clk_prepare_enable()/clk_disable_unprepare() were replaced by calls of clk_enable()/clk_disable(). Signed-off-by: Cyrille Pitchen Reported-by: Matthias Mayr Signed-off-by: Herbert Xu Signed-off-by: Greg Kroah-Hartman --- drivers/crypto/atmel-sha.c | 18 +++++++++++++----- 1 file changed, 13 insertions(+), 5 deletions(-) diff --git a/drivers/crypto/atmel-sha.c b/drivers/crypto/atmel-sha.c index 7a11c285af6d..3178f84d2757 100644 --- a/drivers/crypto/atmel-sha.c +++ b/drivers/crypto/atmel-sha.c @@ -783,7 +783,7 @@ static void atmel_sha_finish_req(struct ahash_request *req, int err) dd->flags &= ~(SHA_FLAGS_BUSY | SHA_FLAGS_FINAL | SHA_FLAGS_CPU | SHA_FLAGS_DMA_READY | SHA_FLAGS_OUTPUT_READY); - clk_disable_unprepare(dd->iclk); + clk_disable(dd->iclk); if (req->base.complete) req->base.complete(&req->base, err); @@ -796,7 +796,7 @@ static int atmel_sha_hw_init(struct atmel_sha_dev *dd) { int err; - err = clk_prepare_enable(dd->iclk); + err = clk_enable(dd->iclk); if (err) return err; @@ -823,7 +823,7 @@ static void atmel_sha_hw_version_init(struct atmel_sha_dev *dd) dev_info(dd->dev, "version: 0x%x\n", dd->hw_version); - clk_disable_unprepare(dd->iclk); + clk_disable(dd->iclk); } static int atmel_sha_handle_queue(struct atmel_sha_dev *dd, @@ -1411,6 +1411,10 @@ static int atmel_sha_probe(struct platform_device *pdev) goto res_err; } + err = clk_prepare(sha_dd->iclk); + if (err) + goto res_err; + atmel_sha_hw_version_init(sha_dd); atmel_sha_get_cap(sha_dd); @@ -1422,12 +1426,12 @@ static int atmel_sha_probe(struct platform_device *pdev) if (IS_ERR(pdata)) { dev_err(&pdev->dev, "platform data not available\n"); err = PTR_ERR(pdata); - goto res_err; + goto iclk_unprepare; } } if (!pdata->dma_slave) { err = -ENXIO; - goto res_err; + goto iclk_unprepare; } err = atmel_sha_dma_init(sha_dd, pdata); if (err) @@ -1458,6 +1462,8 @@ err_algs: if (sha_dd->caps.has_dma) atmel_sha_dma_cleanup(sha_dd); err_sha_dma: +iclk_unprepare: + clk_unprepare(sha_dd->iclk); res_err: tasklet_kill(&sha_dd->done_task); sha_dd_err: @@ -1484,6 +1490,8 @@ static int atmel_sha_remove(struct platform_device *pdev) if (sha_dd->caps.has_dma) atmel_sha_dma_cleanup(sha_dd); + clk_unprepare(sha_dd->iclk); + return 0; } From 2827c1d0344b3d8e43b5ac17aa211d141b94302c Mon Sep 17 00:00:00 2001 From: Boris BREZILLON Date: Fri, 5 Feb 2016 17:45:48 +0100 Subject: [PATCH 180/325] crypto: marvell/cesa - fix test in mv_cesa_dev_dma_init() commit 8a3978ad55fb4c0564d285fb2f6cdee2313fce01 upstream. We are checking twice if dma->cache_pool is not NULL but are never testing dma->padding_pool value. Signed-off-by: Boris Brezillon Signed-off-by: Herbert Xu Signed-off-by: Greg Kroah-Hartman --- drivers/crypto/marvell/cesa.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/crypto/marvell/cesa.c b/drivers/crypto/marvell/cesa.c index 0643e3366e33..c0656e7f37b5 100644 --- a/drivers/crypto/marvell/cesa.c +++ b/drivers/crypto/marvell/cesa.c @@ -306,7 +306,7 @@ static int mv_cesa_dev_dma_init(struct mv_cesa_dev *cesa) return -ENOMEM; dma->padding_pool = dmam_pool_create("cesa_padding", dev, 72, 1, 0); - if (!dma->cache_pool) + if (!dma->padding_pool) return -ENOMEM; cesa->dma = dma; From 7d4bf40d4e2cdf59f83a96cb32ed0411530a547d Mon Sep 17 00:00:00 2001 From: Larry Finger Date: Mon, 14 Dec 2015 16:34:33 -0600 Subject: [PATCH 181/325] rtlwifi: rtl8821ae: Fix errors in parameter initialization commit 78bae1de422a7f6f2b4b61f6a5c379e3d7f96f44 upstream. This driver failed to copy parameters sw_crypto and disable_watchdog into the locations actually used by the driver. In addition, msi_support was initialized three times and one of them used the wrong variable. The initialization of parameter int_clear was moved so that it is near that of the rest of the parameters. Signed-off-by: Larry Finger Signed-off-by: Kalle Valo Signed-off-by: Greg Kroah-Hartman --- drivers/net/wireless/realtek/rtlwifi/rtl8821ae/sw.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/sw.c index 142bdff4ed60..4159f9b14db6 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/sw.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/sw.c @@ -95,8 +95,6 @@ int rtl8821ae_init_sw_vars(struct ieee80211_hw *hw) struct rtl_hal *rtlhal = rtl_hal(rtl_priv(hw)); rtl8821ae_bt_reg_init(hw); - rtlpci->msi_support = rtlpriv->cfg->mod_params->msi_support; - rtlpci->int_clear = rtlpriv->cfg->mod_params->int_clear; rtlpriv->btcoexist.btc_ops = rtl_btc_get_ops_pointer(); rtlpriv->dm.dm_initialgain_enable = 1; @@ -168,12 +166,15 @@ int rtl8821ae_init_sw_vars(struct ieee80211_hw *hw) rtlpriv->psc.swctrl_lps = rtlpriv->cfg->mod_params->swctrl_lps; rtlpriv->psc.fwctrl_lps = rtlpriv->cfg->mod_params->fwctrl_lps; rtlpci->msi_support = rtlpriv->cfg->mod_params->msi_support; - rtlpci->msi_support = rtlpriv->cfg->mod_params->int_clear; + rtlpci->int_clear = rtlpriv->cfg->mod_params->int_clear; + rtlpriv->cfg->mod_params->sw_crypto = + rtlpriv->cfg->mod_params->sw_crypto; + rtlpriv->cfg->mod_params->disable_watchdog = + rtlpriv->cfg->mod_params->disable_watchdog; if (rtlpriv->cfg->mod_params->disable_watchdog) pr_info("watchdog disabled\n"); rtlpriv->psc.reg_fwctrl_lps = 3; rtlpriv->psc.reg_max_lps_awakeintvl = 5; - rtlpci->msi_support = rtlpriv->cfg->mod_params->msi_support; /* for ASPM, you can close aspm through * set const_support_pciaspm = 0 From 724f135b755a628a5e3f8693f105553152e02c23 Mon Sep 17 00:00:00 2001 From: Larry Finger Date: Wed, 20 Jan 2016 21:58:39 -0600 Subject: [PATCH 182/325] rtlwifi: rtl8821ae: Fix 5G failure when EEPROM is incorrectly encoded commit c72fc9093718a3f8597249863a1bac345ba00859 upstream. Recently, it has been reported that D-Link DWA-582 cards, which use an RTL8812AE chip are not able to scan for 5G networks. The problems started with kernel 4.2, which is the first version that had commit d10101a60372 ("rtlwifi: rtl8821ae: Fix problem with regulatory information"). With this patch, the driver went from setting a default channel plan to using the value derived from EEPROM. Bug reports at https://bugzilla.kernel.org/show_bug.cgi?id=111031 and https://bugzilla.redhat.com/show_bug.cgi?id=1279653 are examples of this problem. The problem was solved once I learned that the internal country code was resulting in a regulatory set with only 2.4 GHz channels. With the RTL8821AE chips available to me, the country code was such that both 2.4 and 5 GHz channels are allowed. The fix is to allow both bands even when the EEPROM is incorrectly encoded. Fixes: d10101a60372 ("rtlwifi: rtl8821ae: Fix problem with regulatory information") Signed-off-by: Larry Finger Cc: littlesmartguy@gmail.com Cc: gabe@codehaus.org Signed-off-by: Kalle Valo Signed-off-by: Greg Kroah-Hartman --- drivers/net/wireless/realtek/rtlwifi/regd.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/wireless/realtek/rtlwifi/regd.c b/drivers/net/wireless/realtek/rtlwifi/regd.c index a62bf0a65c32..5be34118e0af 100644 --- a/drivers/net/wireless/realtek/rtlwifi/regd.c +++ b/drivers/net/wireless/realtek/rtlwifi/regd.c @@ -351,7 +351,6 @@ static const struct ieee80211_regdomain *_rtl_regdomain_select( case COUNTRY_CODE_SPAIN: case COUNTRY_CODE_FRANCE: case COUNTRY_CODE_ISRAEL: - case COUNTRY_CODE_WORLD_WIDE_13: return &rtl_regdom_12_13; case COUNTRY_CODE_MKK: case COUNTRY_CODE_MKK1: @@ -360,6 +359,7 @@ static const struct ieee80211_regdomain *_rtl_regdomain_select( return &rtl_regdom_14_60_64; case COUNTRY_CODE_GLOBAL_DOMAIN: return &rtl_regdom_14; + case COUNTRY_CODE_WORLD_WIDE_13: case COUNTRY_CODE_WORLD_WIDE_13_5G_ALL: return &rtl_regdom_12_13_5g_all; default: From 80c554f5f22f9760472ad47b24246cea59474e15 Mon Sep 17 00:00:00 2001 From: Sergey Senozhatsky Date: Thu, 14 Jan 2016 15:22:26 -0800 Subject: [PATCH 183/325] zram/zcomp: use GFP_NOIO to allocate streams commit 3d5fe03a3ea013060ebba2a811aeb0f23f56aefa upstream. We can end up allocating a new compression stream with GFP_KERNEL from within the IO path, which may result is nested (recursive) IO operations. That can introduce problems if the IO path in question is a reclaimer, holding some locks that will deadlock nested IOs. Allocate streams and working memory using GFP_NOIO flag, forbidding recursive IO and FS operations. An example: inconsistent {IN-RECLAIM_FS-W} -> {RECLAIM_FS-ON-W} usage. git/20158 [HC0[0]:SC0[0]:HE1:SE1] takes: (jbd2_handle){+.+.?.}, at: start_this_handle+0x4ca/0x555 {IN-RECLAIM_FS-W} state was registered at: __lock_acquire+0x8da/0x117b lock_acquire+0x10c/0x1a7 start_this_handle+0x52d/0x555 jbd2__journal_start+0xb4/0x237 __ext4_journal_start_sb+0x108/0x17e ext4_dirty_inode+0x32/0x61 __mark_inode_dirty+0x16b/0x60c iput+0x11e/0x274 __dentry_kill+0x148/0x1b8 shrink_dentry_list+0x274/0x44a prune_dcache_sb+0x4a/0x55 super_cache_scan+0xfc/0x176 shrink_slab.part.14.constprop.25+0x2a2/0x4d3 shrink_zone+0x74/0x140 kswapd+0x6b7/0x930 kthread+0x107/0x10f ret_from_fork+0x3f/0x70 irq event stamp: 138297 hardirqs last enabled at (138297): debug_check_no_locks_freed+0x113/0x12f hardirqs last disabled at (138296): debug_check_no_locks_freed+0x33/0x12f softirqs last enabled at (137818): __do_softirq+0x2d3/0x3e9 softirqs last disabled at (137813): irq_exit+0x41/0x95 other info that might help us debug this: Possible unsafe locking scenario: CPU0 ---- lock(jbd2_handle); lock(jbd2_handle); *** DEADLOCK *** 5 locks held by git/20158: #0: (sb_writers#7){.+.+.+}, at: [] mnt_want_write+0x24/0x4b #1: (&type->i_mutex_dir_key#2/1){+.+.+.}, at: [] lock_rename+0xd9/0xe3 #2: (&sb->s_type->i_mutex_key#11){+.+.+.}, at: [] lock_two_nondirectories+0x3f/0x6b #3: (&sb->s_type->i_mutex_key#11/4){+.+.+.}, at: [] lock_two_nondirectories+0x66/0x6b #4: (jbd2_handle){+.+.?.}, at: [] start_this_handle+0x4ca/0x555 stack backtrace: CPU: 2 PID: 20158 Comm: git Not tainted 4.1.0-rc7-next-20150615-dbg-00016-g8bdf555-dirty #211 Call Trace: dump_stack+0x4c/0x6e mark_lock+0x384/0x56d mark_held_locks+0x5f/0x76 lockdep_trace_alloc+0xb2/0xb5 kmem_cache_alloc_trace+0x32/0x1e2 zcomp_strm_alloc+0x25/0x73 [zram] zcomp_strm_multi_find+0xe7/0x173 [zram] zcomp_strm_find+0xc/0xe [zram] zram_bvec_rw+0x2ca/0x7e0 [zram] zram_make_request+0x1fa/0x301 [zram] generic_make_request+0x9c/0xdb submit_bio+0xf7/0x120 ext4_io_submit+0x2e/0x43 ext4_bio_write_page+0x1b7/0x300 mpage_submit_page+0x60/0x77 mpage_map_and_submit_buffers+0x10f/0x21d ext4_writepages+0xc8c/0xe1b do_writepages+0x23/0x2c __filemap_fdatawrite_range+0x84/0x8b filemap_flush+0x1c/0x1e ext4_alloc_da_blocks+0xb8/0x117 ext4_rename+0x132/0x6dc ? mark_held_locks+0x5f/0x76 ext4_rename2+0x29/0x2b vfs_rename+0x540/0x636 SyS_renameat2+0x359/0x44d SyS_rename+0x1e/0x20 entry_SYSCALL_64_fastpath+0x12/0x6f [minchan@kernel.org: add stable mark] Signed-off-by: Sergey Senozhatsky Acked-by: Minchan Kim Cc: Kyeongdon Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- drivers/block/zram/zcomp.c | 4 ++-- drivers/block/zram/zcomp_lz4.c | 2 +- drivers/block/zram/zcomp_lzo.c | 2 +- 3 files changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/block/zram/zcomp.c b/drivers/block/zram/zcomp.c index 5cb13ca3a3ac..c53617752b93 100644 --- a/drivers/block/zram/zcomp.c +++ b/drivers/block/zram/zcomp.c @@ -76,7 +76,7 @@ static void zcomp_strm_free(struct zcomp *comp, struct zcomp_strm *zstrm) */ static struct zcomp_strm *zcomp_strm_alloc(struct zcomp *comp) { - struct zcomp_strm *zstrm = kmalloc(sizeof(*zstrm), GFP_KERNEL); + struct zcomp_strm *zstrm = kmalloc(sizeof(*zstrm), GFP_NOIO); if (!zstrm) return NULL; @@ -85,7 +85,7 @@ static struct zcomp_strm *zcomp_strm_alloc(struct zcomp *comp) * allocate 2 pages. 1 for compressed data, plus 1 extra for the * case when compressed size is larger than the original one */ - zstrm->buffer = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, 1); + zstrm->buffer = (void *)__get_free_pages(GFP_NOIO | __GFP_ZERO, 1); if (!zstrm->private || !zstrm->buffer) { zcomp_strm_free(comp, zstrm); zstrm = NULL; diff --git a/drivers/block/zram/zcomp_lz4.c b/drivers/block/zram/zcomp_lz4.c index f2afb7e988c3..ee44b51130a4 100644 --- a/drivers/block/zram/zcomp_lz4.c +++ b/drivers/block/zram/zcomp_lz4.c @@ -15,7 +15,7 @@ static void *zcomp_lz4_create(void) { - return kzalloc(LZ4_MEM_COMPRESS, GFP_KERNEL); + return kzalloc(LZ4_MEM_COMPRESS, GFP_NOIO); } static void zcomp_lz4_destroy(void *private) diff --git a/drivers/block/zram/zcomp_lzo.c b/drivers/block/zram/zcomp_lzo.c index da1bc47d588e..683ce049e070 100644 --- a/drivers/block/zram/zcomp_lzo.c +++ b/drivers/block/zram/zcomp_lzo.c @@ -15,7 +15,7 @@ static void *lzo_create(void) { - return kzalloc(LZO1X_MEM_COMPRESS, GFP_KERNEL); + return kzalloc(LZO1X_MEM_COMPRESS, GFP_NOIO); } static void lzo_destroy(void *private) From 73f6736093323247103ad59ef04676ea2bb000c7 Mon Sep 17 00:00:00 2001 From: Kyeongdon Kim Date: Thu, 14 Jan 2016 15:22:29 -0800 Subject: [PATCH 184/325] zram: try vmalloc() after kmalloc() commit d913897abace843bba20249f3190167f7895e9c3 upstream. When we're using LZ4 multi compression streams for zram swap, we found out page allocation failure message in system running test. That was not only once, but a few(2 - 5 times per test). Also, some failure cases were continually occurring to try allocation order 3. In order to make parallel compression private data, we should call kzalloc() with order 2/3 in runtime(lzo/lz4). But if there is no order 2/3 size memory to allocate in that time, page allocation fails. This patch makes to use vmalloc() as fallback of kmalloc(), this prevents page alloc failure warning. After using this, we never found warning message in running test, also It could reduce process startup latency about 60-120ms in each case. For reference a call trace : Binder_1: page allocation failure: order:3, mode:0x10c0d0 CPU: 0 PID: 424 Comm: Binder_1 Tainted: GW 3.10.49-perf-g991d02b-dirty #20 Call trace: dump_backtrace+0x0/0x270 show_stack+0x10/0x1c dump_stack+0x1c/0x28 warn_alloc_failed+0xfc/0x11c __alloc_pages_nodemask+0x724/0x7f0 __get_free_pages+0x14/0x5c kmalloc_order_trace+0x38/0xd8 zcomp_lz4_create+0x2c/0x38 zcomp_strm_alloc+0x34/0x78 zcomp_strm_multi_find+0x124/0x1ec zcomp_strm_find+0xc/0x18 zram_bvec_rw+0x2fc/0x780 zram_make_request+0x25c/0x2d4 generic_make_request+0x80/0xbc submit_bio+0xa4/0x15c __swap_writepage+0x218/0x230 swap_writepage+0x3c/0x4c shrink_page_list+0x51c/0x8d0 shrink_inactive_list+0x3f8/0x60c shrink_lruvec+0x33c/0x4cc shrink_zone+0x3c/0x100 try_to_free_pages+0x2b8/0x54c __alloc_pages_nodemask+0x514/0x7f0 __get_free_pages+0x14/0x5c proc_info_read+0x50/0xe4 vfs_read+0xa0/0x12c SyS_read+0x44/0x74 DMA: 3397*4kB (MC) 26*8kB (RC) 0*16kB 0*32kB 0*64kB 0*128kB 0*256kB 0*512kB 0*1024kB 0*2048kB 0*4096kB = 13796kB [minchan@kernel.org: change vmalloc gfp and adding comment about gfp] [sergey.senozhatsky@gmail.com: tweak comments and styles] Signed-off-by: Kyeongdon Kim Signed-off-by: Minchan Kim Acked-by: Sergey Senozhatsky Sergey Senozhatsky Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- drivers/block/zram/zcomp_lz4.c | 23 +++++++++++++++++++++-- drivers/block/zram/zcomp_lzo.c | 23 +++++++++++++++++++++-- 2 files changed, 42 insertions(+), 4 deletions(-) diff --git a/drivers/block/zram/zcomp_lz4.c b/drivers/block/zram/zcomp_lz4.c index ee44b51130a4..dd6083124276 100644 --- a/drivers/block/zram/zcomp_lz4.c +++ b/drivers/block/zram/zcomp_lz4.c @@ -10,17 +10,36 @@ #include #include #include +#include +#include #include "zcomp_lz4.h" static void *zcomp_lz4_create(void) { - return kzalloc(LZ4_MEM_COMPRESS, GFP_NOIO); + void *ret; + + /* + * This function can be called in swapout/fs write path + * so we can't use GFP_FS|IO. And it assumes we already + * have at least one stream in zram initialization so we + * don't do best effort to allocate more stream in here. + * A default stream will work well without further multiple + * streams. That's why we use NORETRY | NOWARN. + */ + ret = kzalloc(LZ4_MEM_COMPRESS, GFP_NOIO | __GFP_NORETRY | + __GFP_NOWARN); + if (!ret) + ret = __vmalloc(LZ4_MEM_COMPRESS, + GFP_NOIO | __GFP_NORETRY | __GFP_NOWARN | + __GFP_ZERO | __GFP_HIGHMEM, + PAGE_KERNEL); + return ret; } static void zcomp_lz4_destroy(void *private) { - kfree(private); + kvfree(private); } static int zcomp_lz4_compress(const unsigned char *src, unsigned char *dst, diff --git a/drivers/block/zram/zcomp_lzo.c b/drivers/block/zram/zcomp_lzo.c index 683ce049e070..edc549920fa0 100644 --- a/drivers/block/zram/zcomp_lzo.c +++ b/drivers/block/zram/zcomp_lzo.c @@ -10,17 +10,36 @@ #include #include #include +#include +#include #include "zcomp_lzo.h" static void *lzo_create(void) { - return kzalloc(LZO1X_MEM_COMPRESS, GFP_NOIO); + void *ret; + + /* + * This function can be called in swapout/fs write path + * so we can't use GFP_FS|IO. And it assumes we already + * have at least one stream in zram initialization so we + * don't do best effort to allocate more stream in here. + * A default stream will work well without further multiple + * streams. That's why we use NORETRY | NOWARN. + */ + ret = kzalloc(LZO1X_MEM_COMPRESS, GFP_NOIO | __GFP_NORETRY | + __GFP_NOWARN); + if (!ret) + ret = __vmalloc(LZO1X_MEM_COMPRESS, + GFP_NOIO | __GFP_NORETRY | __GFP_NOWARN | + __GFP_ZERO | __GFP_HIGHMEM, + PAGE_KERNEL); + return ret; } static void lzo_destroy(void *private) { - kfree(private); + kvfree(private); } static int lzo_compress(const unsigned char *src, unsigned char *dst, From aee0848f2e83f9a2a6acfcae0cdd411a8e8222f9 Mon Sep 17 00:00:00 2001 From: Jerome Marchand Date: Fri, 15 Jan 2016 16:54:48 -0800 Subject: [PATCH 185/325] zram: don't call idr_remove() from zram_remove() commit 17ec4cd985780a7e30aa45bb8f272237c12502a4 upstream. The use of idr_remove() is forbidden in the callback functions of idr_for_each(). It is therefore unsafe to call idr_remove in zram_remove(). This patch moves the call to idr_remove() from zram_remove() to hot_remove_store(). In the detroy_devices() path, idrs are removed by idr_destroy(). This solves an use-after-free detected by KASan. [akpm@linux-foundation.org: fix coding stype, per Sergey] Signed-off-by: Jerome Marchand Acked-by: Sergey Senozhatsky Cc: Minchan Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- drivers/block/zram/zram_drv.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 47915d736f8d..370c2f76016d 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -1325,7 +1325,6 @@ static int zram_remove(struct zram *zram) pr_info("Removed device: %s\n", zram->disk->disk_name); - idr_remove(&zram_index_idr, zram->disk->first_minor); blk_cleanup_queue(zram->disk->queue); del_gendisk(zram->disk); put_disk(zram->disk); @@ -1367,10 +1366,12 @@ static ssize_t hot_remove_store(struct class *class, mutex_lock(&zram_index_mutex); zram = idr_find(&zram_index_idr, dev_id); - if (zram) + if (zram) { ret = zram_remove(zram); - else + idr_remove(&zram_index_idr, dev_id); + } else { ret = -ENODEV; + } mutex_unlock(&zram_index_mutex); return ret ? ret : count; From bddaf79195c4b9bae86b494fb6cfe855f8415afb Mon Sep 17 00:00:00 2001 From: Junil Lee Date: Wed, 20 Jan 2016 14:58:18 -0800 Subject: [PATCH 186/325] zsmalloc: fix migrate_zspage-zs_free race condition commit c102f07ca0b04f2cb49cfc161c83f6239d17f491 upstream. record_obj() in migrate_zspage() does not preserve handle's HANDLE_PIN_BIT, set by find_aloced_obj()->trypin_tag(), and implicitly (accidentally) un-pins the handle, while migrate_zspage() still performs an explicit unpin_tag() on the that handle. This additional explicit unpin_tag() introduces a race condition with zs_free(), which can pin that handle by this time, so the handle becomes un-pinned. Schematically, it goes like this: CPU0 CPU1 migrate_zspage find_alloced_obj trypin_tag set HANDLE_PIN_BIT zs_free() pin_tag() obj_malloc() -- new object, no tag record_obj() -- remove HANDLE_PIN_BIT set HANDLE_PIN_BIT unpin_tag() -- remove zs_free's HANDLE_PIN_BIT The race condition may result in a NULL pointer dereference: Unable to handle kernel NULL pointer dereference at virtual address 00000000 CPU: 0 PID: 19001 Comm: CookieMonsterCl Tainted: PC is at get_zspage_mapping+0x0/0x24 LR is at obj_free.isra.22+0x64/0x128 Call trace: get_zspage_mapping+0x0/0x24 zs_free+0x88/0x114 zram_free_page+0x64/0xcc zram_slot_free_notify+0x90/0x108 swap_entry_free+0x278/0x294 free_swap_and_cache+0x38/0x11c unmap_single_vma+0x480/0x5c8 unmap_vmas+0x44/0x60 exit_mmap+0x50/0x110 mmput+0x58/0xe0 do_exit+0x320/0x8dc do_group_exit+0x44/0xa8 get_signal+0x538/0x580 do_signal+0x98/0x4b8 do_notify_resume+0x14/0x5c This patch keeps the lock bit in migration path and update value atomically. Signed-off-by: Junil Lee Signed-off-by: Minchan Kim Acked-by: Vlastimil Babka Cc: Sergey Senozhatsky Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- mm/zsmalloc.c | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index 9f15bdd9163c..fc083996e40a 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -309,7 +309,12 @@ static void free_handle(struct zs_pool *pool, unsigned long handle) static void record_obj(unsigned long handle, unsigned long obj) { - *(unsigned long *)handle = obj; + /* + * lsb of @obj represents handle lock while other bits + * represent object value the handle is pointing so + * updating shouldn't do store tearing. + */ + WRITE_ONCE(*(unsigned long *)handle, obj); } /* zpool driver */ @@ -1635,6 +1640,13 @@ static int migrate_zspage(struct zs_pool *pool, struct size_class *class, free_obj = obj_malloc(d_page, class, handle); zs_object_copy(free_obj, used_obj, class); index++; + /* + * record_obj updates handle's value to free_obj and it will + * invalidate lock bit(ie, HANDLE_PIN_BIT) of handle, which + * breaks synchronization using pin_tag(e,g, zs_free) so + * let's keep the lock bit. + */ + free_obj |= BIT(HANDLE_PIN_BIT); record_obj(handle, free_obj); unpin_tag(handle); obj_free(pool, class, used_obj); From fe5c164ef32ffbf441b33ff24088e09fca266dad Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Fri, 5 Feb 2016 15:36:30 -0800 Subject: [PATCH 187/325] mm, vmstat: fix wrong WQ sleep when memory reclaim doesn't make any progress commit 564e81a57f9788b1475127012e0fd44e9049e342 upstream. Jan Stancek has reported that system occasionally hanging after "oom01" testcase from LTP triggers OOM. Guessing from a result that there is a kworker thread doing memory allocation and the values between "Node 0 Normal free:" and "Node 0 Normal:" differs when hanging, vmstat is not up-to-date for some reason. According to commit 373ccbe59270 ("mm, vmstat: allow WQ concurrency to discover memory reclaim doesn't make any progress"), it meant to force the kworker thread to take a short sleep, but it by error used schedule_timeout(1). We missed that schedule_timeout() in state TASK_RUNNING doesn't do anything. Fix it by using schedule_timeout_uninterruptible(1) which forces the kworker thread to take a short sleep in order to make sure that vmstat is up-to-date. Fixes: 373ccbe59270 ("mm, vmstat: allow WQ concurrency to discover memory reclaim doesn't make any progress") Signed-off-by: Tetsuo Handa Reported-by: Jan Stancek Acked-by: Michal Hocko Cc: Tejun Heo Cc: Cristopher Lameter Cc: Joonsoo Kim Cc: Arkadiusz Miskiewicz Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- mm/backing-dev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 7340353f8aea..cbe6f0b96f29 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -989,7 +989,7 @@ long wait_iff_congested(struct zone *zone, int sync, long timeout) * here rather than calling cond_resched(). */ if (current->flags & PF_WQ_WORKER) - schedule_timeout(1); + schedule_timeout_uninterruptible(1); else cond_resched(); From bedd67e92725dc7742f53fda328bfc90119fe1e0 Mon Sep 17 00:00:00 2001 From: Benjamin Tissoires Date: Tue, 1 Dec 2015 12:41:38 +0100 Subject: [PATCH 188/325] HID: multitouch: fix input mode switching on some Elan panels commit 73e7d63efb4d774883a338997943bfa59e127085 upstream. as reported by https://bugzilla.kernel.org/show_bug.cgi?id=108481 This bug reports mentions 6d4f5440 ("HID: multitouch: Fetch feature reports on demand for Win8 devices") as the origin of the problem but this commit actually masked 2 firmware bugs that are annihilating each other: The report descriptor declares two features in reports 3 and 5: 0x05, 0x0d, // Usage Page (Digitizers) 318 0x09, 0x0e, // Usage (Device Configuration) 320 0xa1, 0x01, // Collection (Application) 322 0x85, 0x03, // Report ID (3) 324 0x09, 0x22, // Usage (Finger) 326 0xa1, 0x00, // Collection (Physical) 328 0x09, 0x52, // Usage (Inputmode) 330 0x15, 0x00, // Logical Minimum (0) 332 0x25, 0x0a, // Logical Maximum (10) 334 0x75, 0x08, // Report Size (8) 336 0x95, 0x02, // Report Count (2) 338 0xb1, 0x02, // Feature (Data,Var,Abs) 340 0xc0, // End Collection 342 0x09, 0x22, // Usage (Finger) 343 0xa1, 0x00, // Collection (Physical) 345 0x85, 0x05, // Report ID (5) 347 0x09, 0x57, // Usage (Surface Switch) 349 0x09, 0x58, // Usage (Button Switch) 351 0x15, 0x00, // Logical Minimum (0) 353 0x75, 0x01, // Report Size (1) 355 0x95, 0x02, // Report Count (2) 357 0x25, 0x03, // Logical Maximum (3) 359 0xb1, 0x02, // Feature (Data,Var,Abs) 361 0x95, 0x0e, // Report Count (14) 363 0xb1, 0x03, // Feature (Cnst,Var,Abs) 365 0xc0, // End Collection 367 The report ID 3 presents 2 input mode features, while only the first one is handled by the device. Given that we did not checked if one was previously assigned, we were dealing with the ignored featured and we should never have been able to switch this panel into the multitouch mode. However, the firmware presents an other bugs which allowed 6d4f5440 to counteract the faulty report descriptor. When we request the values of the feature 5, the firmware answers "03 03 00". The fields are correct but the report id is wrong. Before 6d4f5440, we retrieved all the features and injected them in the system. So when we called report 5, we injected in the system the report 3 with the values "03 00". Setting the second input mode to 03 in this report changed it to "03 03" and the touchpad switched to the mt mode. We could have set anything in the second field because the actual value (the first 03 in this report) was given by the query of report ID 5. To sum up: 2 bugs in the firmware were hiding that we were accessing the wrong feature. Signed-off-by: Benjamin Tissoires Signed-off-by: Jiri Kosina Signed-off-by: Greg Kroah-Hartman --- drivers/hid/hid-multitouch.c | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c index 3d664d01305e..2b8ff18d3713 100644 --- a/drivers/hid/hid-multitouch.c +++ b/drivers/hid/hid-multitouch.c @@ -357,8 +357,19 @@ static void mt_feature_mapping(struct hid_device *hdev, break; } - td->inputmode = field->report->id; - td->inputmode_index = usage->usage_index; + if (td->inputmode < 0) { + td->inputmode = field->report->id; + td->inputmode_index = usage->usage_index; + } else { + /* + * Some elan panels wrongly declare 2 input mode + * features, and silently ignore when we set the + * value in the second field. Skip the second feature + * and hope for the best. + */ + dev_info(&hdev->dev, + "Ignoring the extra HID_DG_INPUTMODE\n"); + } break; case HID_DG_CONTACTMAX: From 1cb8570bf04ab12a03c31c397a4d158f24895d9c Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 17 Feb 2016 12:31:25 -0800 Subject: [PATCH 189/325] Linux 4.4.2 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index c6a265b52c93..e7a2958eb771 100644 --- a/Makefile +++ b/Makefile @@ -1,6 +1,6 @@ VERSION = 4 PATCHLEVEL = 4 -SUBLEVEL = 1 +SUBLEVEL = 2 EXTRAVERSION = NAME = Blurry Fish Butt From 75a101ba31faf1047da55e26338d800fba9a86bc Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Tue, 26 Jan 2016 04:15:18 -0700 Subject: [PATCH 190/325] x86/mm: Fix types used in pgprot cacheability flags translations commit 3625c2c234ef66acf21a72d47a5ffa94f6c5ebf2 upstream. For PAE kernels "unsigned long" is not suitable to hold page protection flags, since _PAGE_NX doesn't fit there. This is the reason for quite a few W+X pages getting reported as insecure during boot (observed namely for the entire initrd range). Fixes: 281d4078be ("x86: Make page cache mode a real type") Signed-off-by: Jan Beulich Reviewed-by: Juergen Gross Link: http://lkml.kernel.org/r/56A7635602000078000CAFF1@prv-mh.provo.novell.com Signed-off-by: Thomas Gleixner Signed-off-by: Greg Kroah-Hartman --- arch/x86/include/asm/pgtable_types.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index a471cadb9630..79c91853e50e 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -363,20 +363,18 @@ static inline enum page_cache_mode pgprot2cachemode(pgprot_t pgprot) } static inline pgprot_t pgprot_4k_2_large(pgprot_t pgprot) { + pgprotval_t val = pgprot_val(pgprot); pgprot_t new; - unsigned long val; - val = pgprot_val(pgprot); pgprot_val(new) = (val & ~(_PAGE_PAT | _PAGE_PAT_LARGE)) | ((val & _PAGE_PAT) << (_PAGE_BIT_PAT_LARGE - _PAGE_BIT_PAT)); return new; } static inline pgprot_t pgprot_large_2_4k(pgprot_t pgprot) { + pgprotval_t val = pgprot_val(pgprot); pgprot_t new; - unsigned long val; - val = pgprot_val(pgprot); pgprot_val(new) = (val & ~(_PAGE_PAT | _PAGE_PAT_LARGE)) | ((val & _PAGE_PAT_LARGE) >> (_PAGE_BIT_PAT_LARGE - _PAGE_BIT_PAT)); From 4f298c10c35dbaa3c328bc5360b9c46cc52d9f93 Mon Sep 17 00:00:00 2001 From: Matt Fleming Date: Fri, 29 Jan 2016 11:36:10 +0000 Subject: [PATCH 191/325] x86/mm/pat: Avoid truncation when converting cpa->numpages to address MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 742563777e8da62197d6cb4b99f4027f59454735 upstream. There are a couple of nasty truncation bugs lurking in the pageattr code that can be triggered when mapping EFI regions, e.g. when we pass a cpa->pgd pointer. Because cpa->numpages is a 32-bit value, shifting left by PAGE_SHIFT will truncate the resultant address to 32-bits. Viorel-Cătălin managed to trigger this bug on his Dell machine that provides a ~5GB EFI region which requires 1236992 pages to be mapped. When calling populate_pud() the end of the region gets calculated incorrectly in the following buggy expression, end = start + (cpa->numpages << PAGE_SHIFT); And only 188416 pages are mapped. Next, populate_pud() gets invoked for a second time because of the loop in __change_page_attr_set_clr(), only this time no pages get mapped because shifting the remaining number of pages (1048576) by PAGE_SHIFT is zero. At which point the loop in __change_page_attr_set_clr() spins forever because we fail to map progress. Hitting this bug depends very much on the virtual address we pick to map the large region at and how many pages we map on the initial run through the loop. This explains why this issue was only recently hit with the introduction of commit a5caa209ba9c ("x86/efi: Fix boot crash by mapping EFI memmap entries bottom-up at runtime, instead of top-down") It's interesting to note that safe uses of cpa->numpages do exist in the pageattr code. If instead of shifting ->numpages we multiply by PAGE_SIZE, no truncation occurs because PAGE_SIZE is a UL value, and so the result is unsigned long. To avoid surprises when users try to convert very large cpa->numpages values to addresses, change the data type from 'int' to 'unsigned long', thereby making it suitable for shifting by PAGE_SHIFT without any type casting. The alternative would be to make liberal use of casting, but that is far more likely to cause problems in the future when someone adds more code and fails to cast properly; this bug was difficult enough to track down in the first place. Reported-and-tested-by: Viorel-Cătălin RăpiÈ›eanu Acked-by: Borislav Petkov Cc: Sai Praneeth Prakhya Signed-off-by: Matt Fleming Link: https://bugzilla.kernel.org/show_bug.cgi?id=110131 Link: http://lkml.kernel.org/r/1454067370-10374-1-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Thomas Gleixner Signed-off-by: Greg Kroah-Hartman --- arch/x86/mm/pageattr.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index a3137a4feed1..db20ee9a413a 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -33,7 +33,7 @@ struct cpa_data { pgd_t *pgd; pgprot_t mask_set; pgprot_t mask_clr; - int numpages; + unsigned long numpages; int flags; unsigned long pfn; unsigned force_split : 1; @@ -1345,7 +1345,7 @@ static int __change_page_attr_set_clr(struct cpa_data *cpa, int checkalias) * CPA operation. Either a large page has been * preserved or a single page update happened. */ - BUG_ON(cpa->numpages > numpages); + BUG_ON(cpa->numpages > numpages || !cpa->numpages); numpages -= cpa->numpages; if (cpa->flags & (CPA_PAGES_ARRAY | CPA_ARRAY)) cpa->curpage++; From 1e2e0ad1cc1643fdfea0610805c253f53ec1aaa1 Mon Sep 17 00:00:00 2001 From: Toshi Kani Date: Thu, 11 Feb 2016 14:24:16 -0700 Subject: [PATCH 192/325] x86/uaccess/64: Make the __copy_user_nocache() assembly code more readable commit ee9737c924706aaa72c2ead93e3ad5644681dc1c upstream. Add comments to __copy_user_nocache() to clarify its procedures and alignment requirements. Also change numeric branch target labels to named local labels. No code changed: arch/x86/lib/copy_user_64.o: text data bss dec hex filename 1239 0 0 1239 4d7 copy_user_64.o.before 1239 0 0 1239 4d7 copy_user_64.o.after md5: 58bed94c2db98c1ca9a2d46d0680aaae copy_user_64.o.before.asm 58bed94c2db98c1ca9a2d46d0680aaae copy_user_64.o.after.asm Signed-off-by: Toshi Kani Cc: Andrew Morton Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Luis R. Rodriguez Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Toshi Kani Cc: brian.boylston@hpe.com Cc: dan.j.williams@intel.com Cc: linux-nvdimm@lists.01.org Cc: micah.parrish@hpe.com Cc: ross.zwisler@linux.intel.com Cc: vishal.l.verma@intel.com Link: http://lkml.kernel.org/r/1455225857-12039-2-git-send-email-toshi.kani@hpe.com [ Small readability edits and added object file comparison. ] Signed-off-by: Ingo Molnar Signed-off-by: Greg Kroah-Hartman --- arch/x86/lib/copy_user_64.S | 114 +++++++++++++++++++++++------------- 1 file changed, 73 insertions(+), 41 deletions(-) diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S index 982ce34f4a9b..a644aad1f112 100644 --- a/arch/x86/lib/copy_user_64.S +++ b/arch/x86/lib/copy_user_64.S @@ -232,17 +232,30 @@ ENDPROC(copy_user_enhanced_fast_string) /* * copy_user_nocache - Uncached memory copy with exception handling - * This will force destination/source out of cache for more performance. + * This will force destination out of cache for more performance. + * + * Note: Cached memory copy is used when destination or size is not + * naturally aligned. That is: + * - Require 8-byte alignment when size is 8 bytes or larger. */ ENTRY(__copy_user_nocache) ASM_STAC + + /* If size is less than 8 bytes, go to byte copy */ cmpl $8,%edx - jb 20f /* less then 8 bytes, go to byte copy loop */ + jb .L_1b_cache_copy_entry + + /* If destination is not 8-byte aligned, "cache" copy to align it */ ALIGN_DESTINATION + + /* Set 4x8-byte copy count and remainder */ movl %edx,%ecx andl $63,%edx shrl $6,%ecx - jz 17f + jz .L_8b_nocache_copy_entry /* jump if count is 0 */ + + /* Perform 4x8-byte nocache loop-copy */ +.L_4x8b_nocache_copy_loop: 1: movq (%rsi),%r8 2: movq 1*8(%rsi),%r9 3: movq 2*8(%rsi),%r10 @@ -262,60 +275,79 @@ ENTRY(__copy_user_nocache) leaq 64(%rsi),%rsi leaq 64(%rdi),%rdi decl %ecx - jnz 1b -17: movl %edx,%ecx + jnz .L_4x8b_nocache_copy_loop + + /* Set 8-byte copy count and remainder */ +.L_8b_nocache_copy_entry: + movl %edx,%ecx andl $7,%edx shrl $3,%ecx - jz 20f -18: movq (%rsi),%r8 -19: movnti %r8,(%rdi) + jz .L_1b_cache_copy_entry /* jump if count is 0 */ + + /* Perform 8-byte nocache loop-copy */ +.L_8b_nocache_copy_loop: +20: movq (%rsi),%r8 +21: movnti %r8,(%rdi) leaq 8(%rsi),%rsi leaq 8(%rdi),%rdi decl %ecx - jnz 18b -20: andl %edx,%edx - jz 23f + jnz .L_8b_nocache_copy_loop + + /* If no byte left, we're done */ +.L_1b_cache_copy_entry: + andl %edx,%edx + jz .L_finish_copy + + /* Perform byte "cache" loop-copy for the remainder */ movl %edx,%ecx -21: movb (%rsi),%al -22: movb %al,(%rdi) +.L_1b_cache_copy_loop: +40: movb (%rsi),%al +41: movb %al,(%rdi) incq %rsi incq %rdi decl %ecx - jnz 21b -23: xorl %eax,%eax + jnz .L_1b_cache_copy_loop + + /* Finished copying; fence the prior stores */ +.L_finish_copy: + xorl %eax,%eax ASM_CLAC sfence ret .section .fixup,"ax" -30: shll $6,%ecx +.L_fixup_4x8b_copy: + shll $6,%ecx addl %ecx,%edx - jmp 60f -40: lea (%rdx,%rcx,8),%rdx - jmp 60f -50: movl %ecx,%edx -60: sfence + jmp .L_fixup_handle_tail +.L_fixup_8b_copy: + lea (%rdx,%rcx,8),%rdx + jmp .L_fixup_handle_tail +.L_fixup_1b_copy: + movl %ecx,%edx +.L_fixup_handle_tail: + sfence jmp copy_user_handle_tail .previous - _ASM_EXTABLE(1b,30b) - _ASM_EXTABLE(2b,30b) - _ASM_EXTABLE(3b,30b) - _ASM_EXTABLE(4b,30b) - _ASM_EXTABLE(5b,30b) - _ASM_EXTABLE(6b,30b) - _ASM_EXTABLE(7b,30b) - _ASM_EXTABLE(8b,30b) - _ASM_EXTABLE(9b,30b) - _ASM_EXTABLE(10b,30b) - _ASM_EXTABLE(11b,30b) - _ASM_EXTABLE(12b,30b) - _ASM_EXTABLE(13b,30b) - _ASM_EXTABLE(14b,30b) - _ASM_EXTABLE(15b,30b) - _ASM_EXTABLE(16b,30b) - _ASM_EXTABLE(18b,40b) - _ASM_EXTABLE(19b,40b) - _ASM_EXTABLE(21b,50b) - _ASM_EXTABLE(22b,50b) + _ASM_EXTABLE(1b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(2b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(3b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(4b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(5b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(6b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(7b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(8b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(9b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(10b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(11b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(12b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(13b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(14b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(15b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(16b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(20b,.L_fixup_8b_copy) + _ASM_EXTABLE(21b,.L_fixup_8b_copy) + _ASM_EXTABLE(40b,.L_fixup_1b_copy) + _ASM_EXTABLE(41b,.L_fixup_1b_copy) ENDPROC(__copy_user_nocache) From e0c89043e71ae8af6a8cd4a9dac99f46b7ff1d83 Mon Sep 17 00:00:00 2001 From: Toshi Kani Date: Thu, 11 Feb 2016 14:24:17 -0700 Subject: [PATCH 193/325] x86/uaccess/64: Handle the caching of 4-byte nocache copies properly in __copy_user_nocache() commit a82eee7424525e34e98d821dd059ce14560a1e35 upstream. Data corruption issues were observed in tests which initiated a system crash/reset while accessing BTT devices. This problem is reproducible. The BTT driver calls pmem_rw_bytes() to update data in pmem devices. This interface calls __copy_user_nocache(), which uses non-temporal stores so that the stores to pmem are persistent. __copy_user_nocache() uses non-temporal stores when a request size is 8 bytes or larger (and is aligned by 8 bytes). The BTT driver updates the BTT map table, which entry size is 4 bytes. Therefore, updates to the map table entries remain cached, and are not written to pmem after a crash. Change __copy_user_nocache() to use non-temporal store when a request size is 4 bytes. The change extends the current byte-copy path for a less-than-8-bytes request, and does not add any overhead to the regular path. Reported-and-tested-by: Micah Parrish Reported-and-tested-by: Brian Boylston Signed-off-by: Toshi Kani Cc: Andrew Morton Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Borislav Petkov Cc: Brian Gerst Cc: Dan Williams Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Luis R. Rodriguez Cc: Peter Zijlstra Cc: Ross Zwisler Cc: Thomas Gleixner Cc: Toshi Kani Cc: Vishal Verma Cc: linux-nvdimm@lists.01.org Link: http://lkml.kernel.org/r/1455225857-12039-3-git-send-email-toshi.kani@hpe.com [ Small readability edits. ] Signed-off-by: Ingo Molnar Signed-off-by: Greg Kroah-Hartman --- arch/x86/lib/copy_user_64.S | 36 ++++++++++++++++++++++++++++++++---- 1 file changed, 32 insertions(+), 4 deletions(-) diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S index a644aad1f112..27f89c79a44b 100644 --- a/arch/x86/lib/copy_user_64.S +++ b/arch/x86/lib/copy_user_64.S @@ -237,13 +237,14 @@ ENDPROC(copy_user_enhanced_fast_string) * Note: Cached memory copy is used when destination or size is not * naturally aligned. That is: * - Require 8-byte alignment when size is 8 bytes or larger. + * - Require 4-byte alignment when size is 4 bytes. */ ENTRY(__copy_user_nocache) ASM_STAC - /* If size is less than 8 bytes, go to byte copy */ + /* If size is less than 8 bytes, go to 4-byte copy */ cmpl $8,%edx - jb .L_1b_cache_copy_entry + jb .L_4b_nocache_copy_entry /* If destination is not 8-byte aligned, "cache" copy to align it */ ALIGN_DESTINATION @@ -282,7 +283,7 @@ ENTRY(__copy_user_nocache) movl %edx,%ecx andl $7,%edx shrl $3,%ecx - jz .L_1b_cache_copy_entry /* jump if count is 0 */ + jz .L_4b_nocache_copy_entry /* jump if count is 0 */ /* Perform 8-byte nocache loop-copy */ .L_8b_nocache_copy_loop: @@ -294,11 +295,33 @@ ENTRY(__copy_user_nocache) jnz .L_8b_nocache_copy_loop /* If no byte left, we're done */ -.L_1b_cache_copy_entry: +.L_4b_nocache_copy_entry: + andl %edx,%edx + jz .L_finish_copy + + /* If destination is not 4-byte aligned, go to byte copy: */ + movl %edi,%ecx + andl $3,%ecx + jnz .L_1b_cache_copy_entry + + /* Set 4-byte copy count (1 or 0) and remainder */ + movl %edx,%ecx + andl $3,%edx + shrl $2,%ecx + jz .L_1b_cache_copy_entry /* jump if count is 0 */ + + /* Perform 4-byte nocache copy: */ +30: movl (%rsi),%r8d +31: movnti %r8d,(%rdi) + leaq 4(%rsi),%rsi + leaq 4(%rdi),%rdi + + /* If no bytes left, we're done: */ andl %edx,%edx jz .L_finish_copy /* Perform byte "cache" loop-copy for the remainder */ +.L_1b_cache_copy_entry: movl %edx,%ecx .L_1b_cache_copy_loop: 40: movb (%rsi),%al @@ -323,6 +346,9 @@ ENTRY(__copy_user_nocache) .L_fixup_8b_copy: lea (%rdx,%rcx,8),%rdx jmp .L_fixup_handle_tail +.L_fixup_4b_copy: + lea (%rdx,%rcx,4),%rdx + jmp .L_fixup_handle_tail .L_fixup_1b_copy: movl %ecx,%edx .L_fixup_handle_tail: @@ -348,6 +374,8 @@ ENTRY(__copy_user_nocache) _ASM_EXTABLE(16b,.L_fixup_4x8b_copy) _ASM_EXTABLE(20b,.L_fixup_8b_copy) _ASM_EXTABLE(21b,.L_fixup_8b_copy) + _ASM_EXTABLE(30b,.L_fixup_4b_copy) + _ASM_EXTABLE(31b,.L_fixup_4b_copy) _ASM_EXTABLE(40b,.L_fixup_1b_copy) _ASM_EXTABLE(41b,.L_fixup_1b_copy) ENDPROC(__copy_user_nocache) From 6deb0ec93da69d60f28c54b48d24c35e92b2155f Mon Sep 17 00:00:00 2001 From: Toshi Kani Date: Wed, 17 Feb 2016 18:16:54 -0700 Subject: [PATCH 194/325] x86/mm: Fix vmalloc_fault() to handle large pages properly commit f4eafd8bcd5229e998aa252627703b8462c3b90f upstream. A kernel page fault oops with the callstack below was observed when a read syscall was made to a pmem device after a huge amount (>512GB) of vmalloc ranges was allocated by ioremap() on a x86_64 system: BUG: unable to handle kernel paging request at ffff880840000ff8 IP: vmalloc_fault+0x1be/0x300 PGD c7f03a067 PUD 0 Oops: 0000 [#1] SM Call Trace: __do_page_fault+0x285/0x3e0 do_page_fault+0x2f/0x80 ? put_prev_entity+0x35/0x7a0 page_fault+0x28/0x30 ? memcpy_erms+0x6/0x10 ? schedule+0x35/0x80 ? pmem_rw_bytes+0x6a/0x190 [nd_pmem] ? schedule_timeout+0x183/0x240 btt_log_read+0x63/0x140 [nd_btt] : ? __symbol_put+0x60/0x60 ? kernel_read+0x50/0x80 SyS_finit_module+0xb9/0xf0 entry_SYSCALL_64_fastpath+0x1a/0xa4 Since v4.1, ioremap() supports large page (pud/pmd) mappings in x86_64 and PAE. vmalloc_fault() however assumes that the vmalloc range is limited to pte mappings. vmalloc faults do not normally happen in ioremap'd ranges since ioremap() sets up the kernel page tables, which are shared by user processes. pgd_ctor() sets the kernel's PGD entries to user's during fork(). When allocation of the vmalloc ranges crosses a 512GB boundary, ioremap() allocates a new pud table and updates the kernel PGD entry to point it. If user process's PGD entry does not have this update yet, a read/write syscall to the range will cause a vmalloc fault, which hits the Oops above as it does not handle a large page properly. Following changes are made to vmalloc_fault(). 64-bit: - No change for the PGD sync operation as it handles large pages already. - Add pud_huge() and pmd_huge() to the validation code to handle large pages. - Change pud_page_vaddr() to pud_pfn() since an ioremap range is not directly mapped (while the if-statement still works with a bogus addr). - Change pmd_page() to pmd_pfn() since an ioremap range is not backed by struct page (while the if-statement still works with a bogus addr). 32-bit: - No change for the sync operation since the index3 PGD entry covers the entire vmalloc range, which is always valid. (A separate change to sync PGD entry is necessary if this memory layout is changed regardless of the page size.) - Add pmd_huge() to the validation code to handle large pages. This is for completeness since vmalloc_fault() won't happen in ioremap'd ranges as its PGD entry is always valid. Reported-by: Henning Schild Signed-off-by: Toshi Kani Acked-by: Borislav Petkov Cc: Andrew Morton Cc: Andy Lutomirski Cc: Brian Gerst Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Luis R. Rodriguez Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Toshi Kani Cc: linux-mm@kvack.org Cc: linux-nvdimm@lists.01.org Link: http://lkml.kernel.org/r/1455758214-24623-1-git-send-email-toshi.kani@hpe.com Signed-off-by: Ingo Molnar Signed-off-by: Greg Kroah-Hartman --- arch/x86/mm/fault.c | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index eef44d9a3f77..e830c71a1323 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -287,6 +287,9 @@ static noinline int vmalloc_fault(unsigned long address) if (!pmd_k) return -1; + if (pmd_huge(*pmd_k)) + return 0; + pte_k = pte_offset_kernel(pmd_k, address); if (!pte_present(*pte_k)) return -1; @@ -360,8 +363,6 @@ void vmalloc_sync_all(void) * 64-bit: * * Handle a fault on the vmalloc area - * - * This assumes no large pages in there. */ static noinline int vmalloc_fault(unsigned long address) { @@ -403,17 +404,23 @@ static noinline int vmalloc_fault(unsigned long address) if (pud_none(*pud_ref)) return -1; - if (pud_none(*pud) || pud_page_vaddr(*pud) != pud_page_vaddr(*pud_ref)) + if (pud_none(*pud) || pud_pfn(*pud) != pud_pfn(*pud_ref)) BUG(); + if (pud_huge(*pud)) + return 0; + pmd = pmd_offset(pud, address); pmd_ref = pmd_offset(pud_ref, address); if (pmd_none(*pmd_ref)) return -1; - if (pmd_none(*pmd) || pmd_page(*pmd) != pmd_page(*pmd_ref)) + if (pmd_none(*pmd) || pmd_pfn(*pmd) != pmd_pfn(*pmd_ref)) BUG(); + if (pmd_huge(*pmd)) + return 0; + pte_ref = pte_offset_kernel(pmd_ref, address); if (!pte_present(*pte_ref)) return -1; From 434e26d6f6a000b8585c0eb64764a55daff65d20 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Mon, 15 Feb 2016 16:37:24 +0100 Subject: [PATCH 195/325] ALSA: hda - Cancel probe work instead of flush at remove commit 0b8c82190c12e530eb6003720dac103bf63e146e upstream. The commit [991f86d7ae4e: ALSA: hda - Flush the pending probe work at remove] introduced the sync of async probe work at remove for fixing the race. However, this may lead to another hangup when the module removal is performed quickly before starting the probe work, because it issues flush_work() and it's blocked forever. The workaround is to use cancel_work_sync() instead of flush_work() there. Fixes: 991f86d7ae4e ('ALSA: hda - Flush the pending probe work at remove') Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/pci/hda/hda_intel.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index 02a86ba5ba22..2c13298e80b7 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -2143,10 +2143,10 @@ static void azx_remove(struct pci_dev *pci) struct hda_intel *hda; if (card) { - /* flush the pending probing work */ + /* cancel the pending probing work */ chip = card->private_data; hda = container_of(chip, struct hda_intel, chip); - flush_work(&hda->probe_work); + cancel_work_sync(&hda->probe_work); snd_card_free(card); } From ef0ca96169a23551c8f8961c9a081a1c071703a4 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Wed, 17 Feb 2016 14:30:26 +0100 Subject: [PATCH 196/325] ALSA: pcm: Fix rwsem deadlock for non-atomic PCM stream commit 67ec1072b053c15564e6090ab30127895dc77a89 upstream. A non-atomic PCM stream may take snd_pcm_link_rwsem rw semaphore twice in the same code path, e.g. one in snd_pcm_action_nonatomic() and another in snd_pcm_stream_lock(). Usually this is OK, but when a write lock is issued between these two read locks, the problem happens: the write lock is blocked due to the first reade lock, and the second read lock is also blocked by the write lock. This eventually deadlocks. The reason is the way rwsem manages waiters; it's queued like FIFO, so even if the writer itself doesn't take the lock yet, it blocks all the waiters (including reads) queued after it. As a workaround, in this patch, we replace the standard down_write() with an spinning loop. This is far from optimal, but it's good enough, as the spinning time is supposed to be relatively short for normal PCM operations, and the code paths requiring the write lock aren't called so often. Reported-by: Vinod Koul Tested-by: Ramesh Babu Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/core/pcm_native.c | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c index a8b27cdc2844..4ba64fd49759 100644 --- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -74,6 +74,18 @@ static int snd_pcm_open(struct file *file, struct snd_pcm *pcm, int stream); static DEFINE_RWLOCK(snd_pcm_link_rwlock); static DECLARE_RWSEM(snd_pcm_link_rwsem); +/* Writer in rwsem may block readers even during its waiting in queue, + * and this may lead to a deadlock when the code path takes read sem + * twice (e.g. one in snd_pcm_action_nonatomic() and another in + * snd_pcm_stream_lock()). As a (suboptimal) workaround, let writer to + * spin until it gets the lock. + */ +static inline void down_write_nonblock(struct rw_semaphore *lock) +{ + while (!down_write_trylock(lock)) + cond_resched(); +} + /** * snd_pcm_stream_lock - Lock the PCM stream * @substream: PCM substream @@ -1813,7 +1825,7 @@ static int snd_pcm_link(struct snd_pcm_substream *substream, int fd) res = -ENOMEM; goto _nolock; } - down_write(&snd_pcm_link_rwsem); + down_write_nonblock(&snd_pcm_link_rwsem); write_lock_irq(&snd_pcm_link_rwlock); if (substream->runtime->status->state == SNDRV_PCM_STATE_OPEN || substream->runtime->status->state != substream1->runtime->status->state || @@ -1860,7 +1872,7 @@ static int snd_pcm_unlink(struct snd_pcm_substream *substream) struct snd_pcm_substream *s; int res = 0; - down_write(&snd_pcm_link_rwsem); + down_write_nonblock(&snd_pcm_link_rwsem); write_lock_irq(&snd_pcm_link_rwlock); if (!snd_pcm_stream_linked(substream)) { res = -EALREADY; From 6bb345ac7b30680018be6d7e6b4738fab7283b4f Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Mon, 15 Feb 2016 16:20:24 +0100 Subject: [PATCH 197/325] ALSA: seq: Fix leak of pool buffer at concurrent writes commit d99a36f4728fcbcc501b78447f625bdcce15b842 upstream. When multiple concurrent writes happen on the ALSA sequencer device right after the open, it may try to allocate vmalloc buffer for each write and leak some of them. It's because the presence check and the assignment of the buffer is done outside the spinlock for the pool. The fix is to move the check and the assignment into the spinlock. (The current implementation is suboptimal, as there can be multiple unnecessary vmallocs because the allocation is done before the check in the spinlock. But the pool size is already checked beforehand, so this isn't a big problem; that is, the only possible path is the multiple writes before any pool assignment, and practically seen, the current coverage should be "good enough".) The issue was triggered by syzkaller fuzzer. BugLink: http://lkml.kernel.org/r/CACT4Y+bSzazpXNvtAr=WXaL8hptqjHwqEyFA+VN2AWEx=aurkg@mail.gmail.com Reported-by: Dmitry Vyukov Tested-by: Dmitry Vyukov Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/core/seq/seq_memory.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) diff --git a/sound/core/seq/seq_memory.c b/sound/core/seq/seq_memory.c index 801076687bb1..c850345c43b5 100644 --- a/sound/core/seq/seq_memory.c +++ b/sound/core/seq/seq_memory.c @@ -383,15 +383,20 @@ int snd_seq_pool_init(struct snd_seq_pool *pool) if (snd_BUG_ON(!pool)) return -EINVAL; - if (pool->ptr) /* should be atomic? */ - return 0; - pool->ptr = vmalloc(sizeof(struct snd_seq_event_cell) * pool->size); - if (!pool->ptr) + cellptr = vmalloc(sizeof(struct snd_seq_event_cell) * pool->size); + if (!cellptr) return -ENOMEM; /* add new cells to the free cell list */ spin_lock_irqsave(&pool->lock, flags); + if (pool->ptr) { + spin_unlock_irqrestore(&pool->lock, flags); + vfree(cellptr); + return 0; + } + + pool->ptr = cellptr; pool->free = NULL; for (cell = 0; cell < pool->size; cell++) { From a40efb855068a20cf769425a799642aa95c57635 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Tue, 16 Feb 2016 14:15:59 +0100 Subject: [PATCH 198/325] ALSA: seq: Fix double port list deletion commit 13d5e5d4725c64ec06040d636832e78453f477b7 upstream. The commit [7f0973e973cd: ALSA: seq: Fix lockdep warnings due to double mutex locks] split the management of two linked lists (source and destination) into two individual calls for avoiding the AB/BA deadlock. However, this may leave the possible double deletion of one of two lists when the counterpart is being deleted concurrently. It ends up with a list corruption, as revealed by syzkaller fuzzer. This patch fixes it by checking the list emptiness and skipping the deletion and the following process. BugLink: http://lkml.kernel.org/r/CACT4Y+bay9qsrz6dQu31EcGaH9XwfW7o3oBzSQUG9fMszoh=Sg@mail.gmail.com Fixes: 7f0973e973cd ('ALSA: seq: Fix lockdep warnings due to 'double mutex locks) Reported-by: Dmitry Vyukov Tested-by: Dmitry Vyukov Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/core/seq/seq_ports.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/sound/core/seq/seq_ports.c b/sound/core/seq/seq_ports.c index 921fb2bd8fad..fe686ee41c6d 100644 --- a/sound/core/seq/seq_ports.c +++ b/sound/core/seq/seq_ports.c @@ -535,19 +535,22 @@ static void delete_and_unsubscribe_port(struct snd_seq_client *client, bool is_src, bool ack) { struct snd_seq_port_subs_info *grp; + struct list_head *list; + bool empty; grp = is_src ? &port->c_src : &port->c_dest; + list = is_src ? &subs->src_list : &subs->dest_list; down_write(&grp->list_mutex); write_lock_irq(&grp->list_lock); - if (is_src) - list_del(&subs->src_list); - else - list_del(&subs->dest_list); + empty = list_empty(list); + if (!empty) + list_del_init(list); grp->exclusive = 0; write_unlock_irq(&grp->list_lock); up_write(&grp->list_mutex); - unsubscribe_port(client, port, grp, &subs->info, ack); + if (!empty) + unsubscribe_port(client, port, grp, &subs->info, ack); } /* connect two ports */ From a90e66cb949a59298d74638e5db4e888711b4fa0 Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Mon, 30 Nov 2015 21:39:53 -0800 Subject: [PATCH 199/325] phy: twl4030-usb: Relase usb phy on unload commit b241d31ef2f6a289d33dcaa004714b26e06f476f upstream. Otherwise rmmod omap2430; rmmod phy-twl4030-usb; modprobe omap2430 will try to use a non-existing phy and oops: Unable to handle kernel paging request at virtual address b6f7c1f0 ... [] (devm_usb_get_phy_by_node) from [] (omap2430_musb_init+0x44/0x2b4 [omap2430]) [] (omap2430_musb_init [omap2430]) from [] (musb_init_controller+0x194/0x878 [musb_hdrc]) Cc: Bin Liu Cc: Felipe Balbi Cc: Kishon Vijay Abraham I Cc: NeilBrown Signed-off-by: Tony Lindgren Signed-off-by: Kishon Vijay Abraham I Signed-off-by: Greg Kroah-Hartman --- drivers/phy/phy-twl4030-usb.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/phy/phy-twl4030-usb.c b/drivers/phy/phy-twl4030-usb.c index 3a707dd14238..79870c4ff731 100644 --- a/drivers/phy/phy-twl4030-usb.c +++ b/drivers/phy/phy-twl4030-usb.c @@ -750,6 +750,7 @@ static int twl4030_usb_remove(struct platform_device *pdev) struct twl4030_usb *twl = platform_get_drvdata(pdev); int val; + usb_remove_phy(&twl->phy); pm_runtime_get_sync(twl->dev); cancel_delayed_work(&twl->id_workaround_work); device_remove_file(twl->dev, &dev_attr_vbus); From 3375ee8b9964979f6f1f745053e21ded1afdb1b6 Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Mon, 30 Nov 2015 21:39:54 -0800 Subject: [PATCH 200/325] phy: twl4030-usb: Fix unbalanced pm_runtime_enable on module reload commit 58a66dba1beac2121d931cda4682ae4d40816af5 upstream. If we reload phy-twl4030-usb, we get a warning about unbalanced pm_runtime_enable. Let's fix the issue and also fix idling of the device on unload before we attempt to shut it down. If we don't properly idle the PHY before shutting it down on removal, the twl4030 ends up consuming about 62mW of extra power compared to running idle with the module loaded. Cc: Bin Liu Cc: Felipe Balbi Cc: Kishon Vijay Abraham I Cc: NeilBrown Signed-off-by: Tony Lindgren Signed-off-by: Kishon Vijay Abraham I Signed-off-by: Greg Kroah-Hartman --- drivers/phy/phy-twl4030-usb.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/drivers/phy/phy-twl4030-usb.c b/drivers/phy/phy-twl4030-usb.c index 79870c4ff731..f96065a81d1e 100644 --- a/drivers/phy/phy-twl4030-usb.c +++ b/drivers/phy/phy-twl4030-usb.c @@ -715,6 +715,7 @@ static int twl4030_usb_probe(struct platform_device *pdev) pm_runtime_use_autosuspend(&pdev->dev); pm_runtime_set_autosuspend_delay(&pdev->dev, 2000); pm_runtime_enable(&pdev->dev); + pm_runtime_get_sync(&pdev->dev); /* Our job is to use irqs and status from the power module * to keep the transceiver disabled when nothing's connected. @@ -758,6 +759,13 @@ static int twl4030_usb_remove(struct platform_device *pdev) /* set transceiver mode to power on defaults */ twl4030_usb_set_mode(twl, -1); + /* idle ulpi before powering off */ + if (cable_present(twl->linkstat)) + pm_runtime_put_noidle(twl->dev); + pm_runtime_mark_last_busy(twl->dev); + pm_runtime_put_sync_suspend(twl->dev); + pm_runtime_disable(twl->dev); + /* autogate 60MHz ULPI clock, * clear dpll clock request for i2c access, * disable 32KHz @@ -772,11 +780,6 @@ static int twl4030_usb_remove(struct platform_device *pdev) /* disable complete OTG block */ twl4030_usb_clear_bits(twl, POWER_CTRL, POWER_CTRL_OTG_ENAB); - if (cable_present(twl->linkstat)) - pm_runtime_put_noidle(twl->dev); - pm_runtime_mark_last_busy(twl->dev); - pm_runtime_put(twl->dev); - return 0; } From a45f23edb00e017289c5263fef25ad920009edb0 Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sun, 10 Jan 2016 22:40:58 -0800 Subject: [PATCH 201/325] staging/speakup: Use tty_ldisc_ref() for paste kworker commit f4f9edcf9b5289ed96113e79fa65a7bf27ecb096 upstream. As the function documentation for tty_ldisc_ref_wait() notes, it is only callable from a tty file_operations routine; otherwise there is no guarantee the ref won't be NULL. The key difference with the VT's paste_selection() is that is an ioctl, where __speakup_paste_selection() is completely async kworker, kicked off from interrupt context. Fixes: 28a821c30688 ("Staging: speakup: Update __speakup_paste_selection() tty (ab)usage to match vt") Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman Signed-off-by: Greg Kroah-Hartman --- drivers/staging/speakup/selection.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/staging/speakup/selection.c b/drivers/staging/speakup/selection.c index aa5ab6c80ed4..41ef099b7aa6 100644 --- a/drivers/staging/speakup/selection.c +++ b/drivers/staging/speakup/selection.c @@ -142,7 +142,9 @@ static void __speakup_paste_selection(struct work_struct *work) struct tty_ldisc *ld; DECLARE_WAITQUEUE(wait, current); - ld = tty_ldisc_ref_wait(tty); + ld = tty_ldisc_ref(tty); + if (!ld) + goto tty_unref; tty_buffer_lock_exclusive(&vc->port); add_wait_queue(&vc->paste_wait, &wait); @@ -162,6 +164,7 @@ static void __speakup_paste_selection(struct work_struct *work) tty_buffer_unlock_exclusive(&vc->port); tty_ldisc_deref(ld); +tty_unref: tty_kref_put(tty); } From 3ceeb564198cf81863c16d76572306e57e833963 Mon Sep 17 00:00:00 2001 From: "Herton R. Krzesinski" Date: Mon, 11 Jan 2016 12:07:43 -0200 Subject: [PATCH 202/325] pty: fix possible use after free of tty->driver_data commit 2831c89f42dcde440cfdccb9fee9f42d54bbc1ef upstream. This change fixes a bug for a corner case where we have the the last release from a pty master/slave coming from a previously opened /dev/tty file. When this happens, the tty->driver_data can be stale, due to all ptmx or pts/N files having already been closed before (and thus the inode related to these files, which tty->driver_data points to, being already freed/destroyed). The fix here is to keep a reference on the opened master ptmx inode. We maintain the inode referenced until the final pty_unix98_shutdown, and only pass this inode to devpts_kill_index. Signed-off-by: Herton R. Krzesinski Reviewed-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- drivers/tty/pty.c | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-) diff --git a/drivers/tty/pty.c b/drivers/tty/pty.c index a45660f62db5..96016e5fe532 100644 --- a/drivers/tty/pty.c +++ b/drivers/tty/pty.c @@ -681,7 +681,14 @@ static void pty_unix98_remove(struct tty_driver *driver, struct tty_struct *tty) /* this is called once with whichever end is closed last */ static void pty_unix98_shutdown(struct tty_struct *tty) { - devpts_kill_index(tty->driver_data, tty->index); + struct inode *ptmx_inode; + + if (tty->driver->subtype == PTY_TYPE_MASTER) + ptmx_inode = tty->driver_data; + else + ptmx_inode = tty->link->driver_data; + devpts_kill_index(ptmx_inode, tty->index); + iput(ptmx_inode); /* drop reference we acquired at ptmx_open */ } static const struct tty_operations ptm_unix98_ops = { @@ -773,6 +780,15 @@ static int ptmx_open(struct inode *inode, struct file *filp) set_bit(TTY_PTY_LOCK, &tty->flags); /* LOCK THE SLAVE */ tty->driver_data = inode; + /* + * In the case where all references to ptmx inode are dropped and we + * still have /dev/tty opened pointing to the master/slave pair (ptmx + * is closed/released before /dev/tty), we must make sure that the inode + * is still valid when we call the final pty_unix98_shutdown, thus we + * hold an additional reference to the ptmx inode + */ + ihold(inode); + tty_add_file(tty, filp); slave_inode = devpts_pty_new(inode, From 1bdf16025dfc5ed335f3d7d8bbe78461583105fc Mon Sep 17 00:00:00 2001 From: "Herton R. Krzesinski" Date: Thu, 14 Jan 2016 17:56:58 -0200 Subject: [PATCH 203/325] pty: make sure super_block is still valid in final /dev/tty close commit 1f55c718c290616889c04946864a13ef30f64929 upstream. Considering current pty code and multiple devpts instances, it's possible to umount a devpts file system while a program still has /dev/tty opened pointing to a previosuly closed pty pair in that instance. In the case all ptmx and pts/N files are closed, umount can be done. If the program closes /dev/tty after umount is done, devpts_kill_index will use now an invalid super_block, which was already destroyed in the umount operation after running ->kill_sb. This is another "use after free" type of issue, but now related to the allocated super_block instance. To avoid the problem (warning at ida_remove and potential crashes) for this specific case, I added two functions in devpts which grabs additional references to the super_block, which pty code now uses so it makes sure the super block structure is still valid until pty shutdown is done. I also moved the additional inode references to the same functions, which also covered similar case with inode being freed before /dev/tty final close/shutdown. Signed-off-by: Herton R. Krzesinski Reviewed-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- drivers/tty/pty.c | 9 ++++++--- fs/devpts/inode.c | 20 ++++++++++++++++++++ include/linux/devpts_fs.h | 4 ++++ 3 files changed, 30 insertions(+), 3 deletions(-) diff --git a/drivers/tty/pty.c b/drivers/tty/pty.c index 96016e5fe532..78e983677339 100644 --- a/drivers/tty/pty.c +++ b/drivers/tty/pty.c @@ -688,7 +688,7 @@ static void pty_unix98_shutdown(struct tty_struct *tty) else ptmx_inode = tty->link->driver_data; devpts_kill_index(ptmx_inode, tty->index); - iput(ptmx_inode); /* drop reference we acquired at ptmx_open */ + devpts_del_ref(ptmx_inode); } static const struct tty_operations ptm_unix98_ops = { @@ -785,9 +785,12 @@ static int ptmx_open(struct inode *inode, struct file *filp) * still have /dev/tty opened pointing to the master/slave pair (ptmx * is closed/released before /dev/tty), we must make sure that the inode * is still valid when we call the final pty_unix98_shutdown, thus we - * hold an additional reference to the ptmx inode + * hold an additional reference to the ptmx inode. For the same /dev/tty + * last close case, we also need to make sure the super_block isn't + * destroyed (devpts instance unmounted), before /dev/tty is closed and + * on its release devpts_kill_index is called. */ - ihold(inode); + devpts_add_ref(inode); tty_add_file(tty, filp); diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c index c35ffdc12bba..706de324f2a6 100644 --- a/fs/devpts/inode.c +++ b/fs/devpts/inode.c @@ -575,6 +575,26 @@ void devpts_kill_index(struct inode *ptmx_inode, int idx) mutex_unlock(&allocated_ptys_lock); } +/* + * pty code needs to hold extra references in case of last /dev/tty close + */ + +void devpts_add_ref(struct inode *ptmx_inode) +{ + struct super_block *sb = pts_sb_from_inode(ptmx_inode); + + atomic_inc(&sb->s_active); + ihold(ptmx_inode); +} + +void devpts_del_ref(struct inode *ptmx_inode) +{ + struct super_block *sb = pts_sb_from_inode(ptmx_inode); + + iput(ptmx_inode); + deactivate_super(sb); +} + /** * devpts_pty_new -- create a new inode in /dev/pts/ * @ptmx_inode: inode of the master diff --git a/include/linux/devpts_fs.h b/include/linux/devpts_fs.h index 251a2090a554..e0ee0b3000b2 100644 --- a/include/linux/devpts_fs.h +++ b/include/linux/devpts_fs.h @@ -19,6 +19,8 @@ int devpts_new_index(struct inode *ptmx_inode); void devpts_kill_index(struct inode *ptmx_inode, int idx); +void devpts_add_ref(struct inode *ptmx_inode); +void devpts_del_ref(struct inode *ptmx_inode); /* mknod in devpts */ struct inode *devpts_pty_new(struct inode *ptmx_inode, dev_t device, int index, void *priv); @@ -32,6 +34,8 @@ void devpts_pty_kill(struct inode *inode); /* Dummy stubs in the no-pty case */ static inline int devpts_new_index(struct inode *ptmx_inode) { return -EINVAL; } static inline void devpts_kill_index(struct inode *ptmx_inode, int idx) { } +static inline void devpts_add_ref(struct inode *ptmx_inode) { } +static inline void devpts_del_ref(struct inode *ptmx_inode) { } static inline struct inode *devpts_pty_new(struct inode *ptmx_inode, dev_t device, int index, void *priv) { From 124efa9fd5679ed68fd69e5b899e55b0452c68a4 Mon Sep 17 00:00:00 2001 From: Jeremy McNicoll Date: Tue, 2 Feb 2016 13:00:45 -0800 Subject: [PATCH 204/325] tty: Add support for PCIe WCH382 2S multi-IO card commit 7dde55787b43a8f2b4021916db38d90c03a2ec64 upstream. WCH382 2S board is a PCIe card with 2 DB9 COM ports detected as Serial controller: Device 1c00:3253 (rev 10) (prog-if 05 [16850]) Signed-off-by: Jeremy McNicoll Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/8250/8250_pci.c | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c index 4097f3f65b3b..ac24c8e997fe 100644 --- a/drivers/tty/serial/8250/8250_pci.c +++ b/drivers/tty/serial/8250/8250_pci.c @@ -1936,6 +1936,7 @@ pci_wch_ch38x_setup(struct serial_private *priv, #define PCIE_VENDOR_ID_WCH 0x1c00 #define PCIE_DEVICE_ID_WCH_CH382_2S1P 0x3250 #define PCIE_DEVICE_ID_WCH_CH384_4S 0x3470 +#define PCIE_DEVICE_ID_WCH_CH382_2S 0x3253 #define PCI_VENDOR_ID_PERICOM 0x12D8 #define PCI_DEVICE_ID_PERICOM_PI7C9X7951 0x7951 @@ -2618,6 +2619,14 @@ static struct pci_serial_quirk pci_serial_quirks[] __refdata = { .subdevice = PCI_ANY_ID, .setup = pci_wch_ch353_setup, }, + /* WCH CH382 2S card (16850 clone) */ + { + .vendor = PCIE_VENDOR_ID_WCH, + .device = PCIE_DEVICE_ID_WCH_CH382_2S, + .subvendor = PCI_ANY_ID, + .subdevice = PCI_ANY_ID, + .setup = pci_wch_ch38x_setup, + }, /* WCH CH382 2S1P card (16850 clone) */ { .vendor = PCIE_VENDOR_ID_WCH, @@ -2936,6 +2945,7 @@ enum pci_board_num_t { pbn_fintek_4, pbn_fintek_8, pbn_fintek_12, + pbn_wch382_2, pbn_wch384_4, pbn_pericom_PI7C9X7951, pbn_pericom_PI7C9X7952, @@ -3756,6 +3766,13 @@ static struct pciserial_board pci_boards[] = { .base_baud = 115200, .first_offset = 0x40, }, + [pbn_wch382_2] = { + .flags = FL_BASE0, + .num_ports = 2, + .base_baud = 115200, + .uart_offset = 8, + .first_offset = 0xC0, + }, [pbn_wch384_4] = { .flags = FL_BASE0, .num_ports = 4, @@ -5545,6 +5562,10 @@ static struct pci_device_id serial_pci_tbl[] = { PCI_ANY_ID, PCI_ANY_ID, 0, 0, pbn_b0_bt_2_115200 }, + { PCIE_VENDOR_ID_WCH, PCIE_DEVICE_ID_WCH_CH382_2S, + PCI_ANY_ID, PCI_ANY_ID, + 0, 0, pbn_wch382_2 }, + { PCIE_VENDOR_ID_WCH, PCIE_DEVICE_ID_WCH_CH384_4S, PCI_ANY_ID, PCI_ANY_ID, 0, 0, pbn_wch384_4 }, From 76e88140aa9111605768e7725ec1c5b709d51865 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Fri, 29 Jan 2016 16:49:47 +0200 Subject: [PATCH 205/325] serial: 8250_pci: Add Intel Broadwell ports commit 6c55d9b98335f7f6bd5f061866ff1633401f3a44 upstream. Some recent (early 2015) macbooks have Intel Broadwell where LPSS UARTs are PCI enumerated instead of ACPI. The LPSS UART block is pretty much same as used on Intel Baytrail so we can reuse the existing Baytrail setup code. Add both Broadwell LPSS UART ports to the list of supported devices. Signed-off-by: Leif Liddy Signed-off-by: Mika Westerberg Reviewed-by: Andy Shevchenko Reviewed-by: Heikki Krogerus Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/8250/8250_pci.c | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c index ac24c8e997fe..7cd6f9a90542 100644 --- a/drivers/tty/serial/8250/8250_pci.c +++ b/drivers/tty/serial/8250/8250_pci.c @@ -1379,6 +1379,9 @@ ce4100_serial_setup(struct serial_private *priv, #define PCI_DEVICE_ID_INTEL_BSW_UART1 0x228a #define PCI_DEVICE_ID_INTEL_BSW_UART2 0x228c +#define PCI_DEVICE_ID_INTEL_BDW_UART1 0x9ce3 +#define PCI_DEVICE_ID_INTEL_BDW_UART2 0x9ce4 + #define BYT_PRV_CLK 0x800 #define BYT_PRV_CLK_EN (1 << 0) #define BYT_PRV_CLK_M_VAL_SHIFT 1 @@ -1461,11 +1464,13 @@ byt_serial_setup(struct serial_private *priv, switch (pdev->device) { case PCI_DEVICE_ID_INTEL_BYT_UART1: case PCI_DEVICE_ID_INTEL_BSW_UART1: + case PCI_DEVICE_ID_INTEL_BDW_UART1: rx_param->src_id = 3; tx_param->dst_id = 2; break; case PCI_DEVICE_ID_INTEL_BYT_UART2: case PCI_DEVICE_ID_INTEL_BSW_UART2: + case PCI_DEVICE_ID_INTEL_BDW_UART2: rx_param->src_id = 5; tx_param->dst_id = 4; break; @@ -2063,6 +2068,20 @@ static struct pci_serial_quirk pci_serial_quirks[] __refdata = { .subdevice = PCI_ANY_ID, .setup = byt_serial_setup, }, + { + .vendor = PCI_VENDOR_ID_INTEL, + .device = PCI_DEVICE_ID_INTEL_BDW_UART1, + .subvendor = PCI_ANY_ID, + .subdevice = PCI_ANY_ID, + .setup = byt_serial_setup, + }, + { + .vendor = PCI_VENDOR_ID_INTEL, + .device = PCI_DEVICE_ID_INTEL_BDW_UART2, + .subvendor = PCI_ANY_ID, + .subdevice = PCI_ANY_ID, + .setup = byt_serial_setup, + }, /* * ITE */ @@ -5523,6 +5542,16 @@ static struct pci_device_id serial_pci_tbl[] = { PCI_CLASS_COMMUNICATION_SERIAL << 8, 0xff0000, pbn_byt }, + /* Intel Broadwell */ + { PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_BDW_UART1, + PCI_ANY_ID, PCI_ANY_ID, + PCI_CLASS_COMMUNICATION_SERIAL << 8, 0xff0000, + pbn_byt }, + { PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_BDW_UART2, + PCI_ANY_ID, PCI_ANY_ID, + PCI_CLASS_COMMUNICATION_SERIAL << 8, 0xff0000, + pbn_byt }, + /* * Intel Quark x1000 */ From 5859b9077763ea1c3f4db47522bdcf300aedb080 Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Tue, 12 Jan 2016 15:14:46 -0800 Subject: [PATCH 206/325] serial: omap: Prevent DoS using unprivileged ioctl(TIOCSRS485) commit 308bbc9ab838d0ace0298268c7970ba9513e2c65 upstream. The omap-serial driver emulates RS485 delays using software timers, but neglects to clamp the input values from the unprivileged ioctl(TIOCSRS485). Because the software implementation busy-waits, malicious userspace could stall the cpu for ~49 days. Clamp the input values to < 100ms. Fixes: 4a0ac0f55b18 ("OMAP: add RS485 support") Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/omap-serial.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/tty/serial/omap-serial.c b/drivers/tty/serial/omap-serial.c index 9d4c84f7485f..24280d9a05e9 100644 --- a/drivers/tty/serial/omap-serial.c +++ b/drivers/tty/serial/omap-serial.c @@ -1343,7 +1343,7 @@ static inline void serial_omap_add_console_port(struct uart_omap_port *up) /* Enable or disable the rs485 support */ static int -serial_omap_config_rs485(struct uart_port *port, struct serial_rs485 *rs485conf) +serial_omap_config_rs485(struct uart_port *port, struct serial_rs485 *rs485) { struct uart_omap_port *up = to_uart_omap_port(port); unsigned int mode; @@ -1356,8 +1356,12 @@ serial_omap_config_rs485(struct uart_port *port, struct serial_rs485 *rs485conf) up->ier = 0; serial_out(up, UART_IER, 0); + /* Clamp the delays to [0, 100ms] */ + rs485->delay_rts_before_send = min(rs485->delay_rts_before_send, 100U); + rs485->delay_rts_after_send = min(rs485->delay_rts_after_send, 100U); + /* store new config */ - port->rs485 = *rs485conf; + port->rs485 = *rs485; /* * Just as a precaution, only allow rs485 From 33f48f8ab0b94fdd1249f561b15c872c36e560c8 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 11 Feb 2016 23:15:12 -0500 Subject: [PATCH 207/325] ext4: fix scheduling in atomic on group checksum failure commit 05145bd799e498ce4e3b5145894174ee881f02b0 upstream. When block group checksum is wrong, we call ext4_error() while holding group spinlock from ext4_init_block_bitmap() or ext4_init_inode_bitmap() which results in scheduling while in atomic. Fix the issue by calling ext4_error() later after dropping the spinlock. Reported-by: Dmitry Vyukov Signed-off-by: Jan Kara Signed-off-by: Theodore Ts'o Reviewed-by: Darrick J. Wong Signed-off-by: Greg Kroah-Hartman --- fs/ext4/balloc.c | 7 ++++--- fs/ext4/ialloc.c | 6 ++++-- 2 files changed, 8 insertions(+), 5 deletions(-) diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index ec0668a60678..fe1f50fe764f 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -191,7 +191,6 @@ static int ext4_init_block_bitmap(struct super_block *sb, /* If checksum is bad mark all blocks used to prevent allocation * essentially implementing a per-group read-only flag. */ if (!ext4_group_desc_csum_verify(sb, block_group, gdp)) { - ext4_error(sb, "Checksum bad for group %u", block_group); grp = ext4_get_group_info(sb, block_group); if (!EXT4_MB_GRP_BBITMAP_CORRUPT(grp)) percpu_counter_sub(&sbi->s_freeclusters_counter, @@ -442,14 +441,16 @@ ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group) } ext4_lock_group(sb, block_group); if (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) { - err = ext4_init_block_bitmap(sb, bh, block_group, desc); set_bitmap_uptodate(bh); set_buffer_uptodate(bh); ext4_unlock_group(sb, block_group); unlock_buffer(bh); - if (err) + if (err) { + ext4_error(sb, "Failed to init block bitmap for group " + "%u: %d", block_group, err); goto out; + } goto verify; } ext4_unlock_group(sb, block_group); diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index 1b8024d26f65..53f2b98a69f3 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -76,7 +76,6 @@ static int ext4_init_inode_bitmap(struct super_block *sb, /* If checksum is bad mark all blocks and inodes use to prevent * allocation, essentially implementing a per-group read-only flag. */ if (!ext4_group_desc_csum_verify(sb, block_group, gdp)) { - ext4_error(sb, "Checksum bad for group %u", block_group); grp = ext4_get_group_info(sb, block_group); if (!EXT4_MB_GRP_BBITMAP_CORRUPT(grp)) percpu_counter_sub(&sbi->s_freeclusters_counter, @@ -191,8 +190,11 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group) set_buffer_verified(bh); ext4_unlock_group(sb, block_group); unlock_buffer(bh); - if (err) + if (err) { + ext4_error(sb, "Failed to init inode bitmap for group " + "%u: %d", block_group, err); goto out; + } return bh; } ext4_unlock_group(sb, block_group); From 600d41f4ecb53edb540fa00a34a78ea6e5c9f9f7 Mon Sep 17 00:00:00 2001 From: Insu Yun Date: Fri, 12 Feb 2016 01:15:59 -0500 Subject: [PATCH 208/325] ext4: fix potential integer overflow commit 46901760b46064964b41015d00c140c83aa05bcf upstream. Since sizeof(ext_new_group_data) > sizeof(ext_new_flex_group_data), integer overflow could be happened. Therefore, need to fix integer overflow sanitization. Signed-off-by: Insu Yun Signed-off-by: Theodore Ts'o Signed-off-by: Greg Kroah-Hartman --- fs/ext4/resize.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index ad62d7acc315..34038e3598d5 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -198,7 +198,7 @@ static struct ext4_new_flex_group_data *alloc_flex_gd(unsigned long flexbg_size) if (flex_gd == NULL) goto out3; - if (flexbg_size >= UINT_MAX / sizeof(struct ext4_new_flex_group_data)) + if (flexbg_size >= UINT_MAX / sizeof(struct ext4_new_group_data)) goto out2; flex_gd->count = flexbg_size; From bbfe21c87bd0f529d19f077051a52d779c785c6c Mon Sep 17 00:00:00 2001 From: Eryu Guan Date: Fri, 12 Feb 2016 01:20:43 -0500 Subject: [PATCH 209/325] ext4: don't read blocks from disk after extents being swapped commit bcff24887d00bce102e0857d7b0a8c44a40f53d1 upstream. I notice ext4/307 fails occasionally on ppc64 host, reporting md5 checksum mismatch after moving data from original file to donor file. The reason is that move_extent_per_page() calls __block_write_begin() and block_commit_write() to write saved data from original inode blocks to donor inode blocks, but __block_write_begin() not only maps buffer heads but also reads block content from disk if the size is not block size aligned. At this time the physical block number in mapped buffer head is pointing to the donor file not the original file, and that results in reading wrong data to page, which get written to disk in following block_commit_write call. This also can be reproduced by the following script on 1k block size ext4 on x86_64 host: mnt=/mnt/ext4 donorfile=$mnt/donor testfile=$mnt/testfile e4compact=~/xfstests/src/e4compact rm -f $donorfile $testfile # reserve space for donor file, written by 0xaa and sync to disk to # avoid EBUSY on EXT4_IOC_MOVE_EXT xfs_io -fc "pwrite -S 0xaa 0 1m" -c "fsync" $donorfile # create test file written by 0xbb xfs_io -fc "pwrite -S 0xbb 0 1023" -c "fsync" $testfile # compute initial md5sum md5sum $testfile | tee md5sum.txt # drop cache, force e4compact to read data from disk echo 3 > /proc/sys/vm/drop_caches # test defrag echo "$testfile" | $e4compact -i -v -f $donorfile # check md5sum md5sum -c md5sum.txt Fix it by creating & mapping buffer heads only but not reading blocks from disk, because all the data in page is guaranteed to be up-to-date in mext_page_mkuptodate(). Signed-off-by: Eryu Guan Signed-off-by: Theodore Ts'o Signed-off-by: Greg Kroah-Hartman --- fs/ext4/move_extent.c | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c index fb6f11709ae6..e032a0423e35 100644 --- a/fs/ext4/move_extent.c +++ b/fs/ext4/move_extent.c @@ -265,11 +265,12 @@ move_extent_per_page(struct file *o_filp, struct inode *donor_inode, ext4_lblk_t orig_blk_offset, donor_blk_offset; unsigned long blocksize = orig_inode->i_sb->s_blocksize; unsigned int tmp_data_size, data_size, replaced_size; - int err2, jblocks, retries = 0; + int i, err2, jblocks, retries = 0; int replaced_count = 0; int from = data_offset_in_page << orig_inode->i_blkbits; int blocks_per_page = PAGE_CACHE_SIZE >> orig_inode->i_blkbits; struct super_block *sb = orig_inode->i_sb; + struct buffer_head *bh = NULL; /* * It needs twice the amount of ordinary journal buffers because @@ -380,8 +381,16 @@ data_copy: } /* Perform all necessary steps similar write_begin()/write_end() * but keeping in mind that i_size will not change */ - *err = __block_write_begin(pagep[0], from, replaced_size, - ext4_get_block); + if (!page_has_buffers(pagep[0])) + create_empty_buffers(pagep[0], 1 << orig_inode->i_blkbits, 0); + bh = page_buffers(pagep[0]); + for (i = 0; i < data_offset_in_page; i++) + bh = bh->b_this_page; + for (i = 0; i < block_len_in_page; i++) { + *err = ext4_get_block(orig_inode, orig_blk_offset + i, bh, 0); + if (*err < 0) + break; + } if (!*err) *err = block_commit_write(pagep[0], from, from + replaced_size); From c57e49b50bc5ab5089bc1295bab9106925033c40 Mon Sep 17 00:00:00 2001 From: David Sterba Date: Mon, 30 Nov 2015 17:27:06 +0100 Subject: [PATCH 210/325] btrfs: handle invalid num_stripes in sys_array commit f5cdedd73fa71b74dcc42f2a11a5735d89ce7c4f upstream. We can handle the special case of num_stripes == 0 directly inside btrfs_read_sys_array. The BUG_ON in btrfs_chunk_item_size is there to catch other unhandled cases where we fail to validate external data. A crafted or corrupted image crashes at mount time: BTRFS: device fsid 9006933e-2a9a-44f0-917f-514252aeec2c devid 1 transid 7 /dev/loop0 BTRFS info (device loop0): disk space caching is enabled BUG: failure at fs/btrfs/ctree.h:337/btrfs_chunk_item_size()! Kernel panic - not syncing: BUG! CPU: 0 PID: 313 Comm: mount Not tainted 4.2.5-00657-ge047887-dirty #25 Stack: 637af890 60062489 602aeb2e 604192ba 60387961 00000011 637af8a0 6038a835 637af9c0 6038776b 634ef32b 00000000 Call Trace: [<6001c86d>] show_stack+0xfe/0x15b [<6038a835>] dump_stack+0x2a/0x2c [<6038776b>] panic+0x13e/0x2b3 [<6020f099>] btrfs_read_sys_array+0x25d/0x2ff [<601cfbbe>] open_ctree+0x192d/0x27af [<6019c2c1>] btrfs_mount+0x8f5/0xb9a [<600bc9a7>] mount_fs+0x11/0xf3 [<600d5167>] vfs_kern_mount+0x75/0x11a [<6019bcb0>] btrfs_mount+0x2e4/0xb9a [<600bc9a7>] mount_fs+0x11/0xf3 [<600d5167>] vfs_kern_mount+0x75/0x11a [<600d710b>] do_mount+0xa35/0xbc9 [<600d7557>] SyS_mount+0x95/0xc8 [<6001e884>] handle_syscall+0x6b/0x8e Reported-by: Jiri Slaby Reported-by: Vegard Nossum Signed-off-by: David Sterba Signed-off-by: Greg Kroah-Hartman --- fs/btrfs/volumes.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index a23399e8e3ab..a5094b8ca281 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -6512,6 +6512,14 @@ int btrfs_read_sys_array(struct btrfs_root *root) goto out_short_read; num_stripes = btrfs_chunk_num_stripes(sb, chunk); + if (!num_stripes) { + printk(KERN_ERR + "BTRFS: invalid number of stripes %u in sys_array at offset %u\n", + num_stripes, cur_offset); + ret = -EIO; + break; + } + len = btrfs_chunk_item_size(num_stripes); if (cur_offset + len > array_size) goto out_short_read; From 4e6943903a8eb700bf13a7be572249b34d438574 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Wed, 6 Jan 2016 22:42:35 +0000 Subject: [PATCH 211/325] Btrfs: fix fitrim discarding device area reserved for boot loader's use commit 8cdc7c5b00d945a3c823fc4277af304abb9cb43d upstream. As of the 4.3 kernel release, the fitrim ioctl can now discard any region of a disk that is not allocated to any chunk/block group, including the first megabyte which is used for our primary superblock and by the boot loader (grub for example). Fix this by not allowing to trim/discard any region in the device starting with an offset not greater than min(alloc_start_mount_option, 1Mb), just as it was not possible before 4.3. A reproducer test case for xfstests follows. seq=`basename $0` seqres=$RESULT_DIR/$seq echo "QA output created by $seq" tmp=/tmp/$$ status=1 # failure is the default! trap "_cleanup; exit \$status" 0 1 2 3 15 _cleanup() { cd / rm -f $tmp.* } # get standard environment, filters and checks . ./common/rc . ./common/filter # real QA test starts here _need_to_be_root _supported_fs btrfs _supported_os Linux _require_scratch rm -f $seqres.full _scratch_mkfs >>$seqres.full 2>&1 # Write to the [0, 64Kb[ and [68Kb, 1Mb[ ranges of the device. These ranges are # reserved for a boot loader to use (GRUB for example) and btrfs should never # use them - neither for allocating metadata/data nor should trim/discard them. # The range [64Kb, 68Kb[ is used for the primary superblock of the filesystem. $XFS_IO_PROG -c "pwrite -S 0xfd 0 64K" $SCRATCH_DEV | _filter_xfs_io $XFS_IO_PROG -c "pwrite -S 0xfd 68K 956K" $SCRATCH_DEV | _filter_xfs_io # Now mount the filesystem and perform a fitrim against it. _scratch_mount _require_batched_discard $SCRATCH_MNT $FSTRIM_PROG $SCRATCH_MNT # Now unmount the filesystem and verify the content of the ranges was not # modified (no trim/discard happened on them). _scratch_unmount echo "Content of the ranges [0, 64Kb] and [68Kb, 1Mb[ after fitrim:" od -t x1 -N $((64 * 1024)) $SCRATCH_DEV od -t x1 -j $((68 * 1024)) -N $((956 * 1024)) $SCRATCH_DEV status=0 exit Reported-by: Vincent Petry Reported-by: Andrei Borzenkov Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=109341 Fixes: 499f377f49f0 (btrfs: iterate over unused chunk space in FITRIM) Signed-off-by: Filipe Manana Signed-off-by: Greg Kroah-Hartman --- fs/btrfs/volumes.c | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index a5094b8ca281..9e084477d320 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -1257,6 +1257,15 @@ int find_free_dev_extent_start(struct btrfs_transaction *transaction, int ret; int slot; struct extent_buffer *l; + u64 min_search_start; + + /* + * We don't want to overwrite the superblock on the drive nor any area + * used by the boot loader (grub for example), so we make sure to start + * at an offset of at least 1MB. + */ + min_search_start = max(root->fs_info->alloc_start, 1024ull * 1024); + search_start = max(search_start, min_search_start); path = btrfs_alloc_path(); if (!path) @@ -1397,18 +1406,9 @@ int find_free_dev_extent(struct btrfs_trans_handle *trans, struct btrfs_device *device, u64 num_bytes, u64 *start, u64 *len) { - struct btrfs_root *root = device->dev_root; - u64 search_start; - /* FIXME use last free of some kind */ - - /* - * we don't want to overwrite the superblock on the drive, - * so we make sure to start at an offset of at least 1MB - */ - search_start = max(root->fs_info->alloc_start, 1024ull * 1024); return find_free_dev_extent_start(trans->transaction, device, - num_bytes, search_start, start, len); + num_bytes, 0, start, len); } static int btrfs_free_dev_extent(struct btrfs_trans_handle *trans, From dfd2961ab6eda6c39aa9d7ddc5e6fb754b16a750 Mon Sep 17 00:00:00 2001 From: David Sterba Date: Mon, 25 Jan 2016 11:02:06 +0100 Subject: [PATCH 212/325] Revert "btrfs: clear PF_NOFREEZE in cleaner_kthread()" commit 80ad623edd2d0ccb47d85357ee31c97e6c684e82 upstream. This reverts commit 696249132158014d594896df3a81390616069c5c. The cleaner thread can block freezing when there's a snapshot cleaning in progress and the other threads get suspended first. From the logs provided by Martin we're waiting for reading extent pages: kernel: PM: Syncing filesystems ... done. kernel: Freezing user space processes ... (elapsed 0.015 seconds) done. kernel: Freezing remaining freezable tasks ... kernel: Freezing of tasks failed after 20.003 seconds (1 tasks refusing to freeze, wq_busy=0): kernel: btrfs-cleaner D ffff88033dd13bc0 0 152 2 0x00000000 kernel: ffff88032ebc2e00 ffff88032e750000 ffff88032e74fa50 7fffffffffffffff kernel: ffffffff814a58df 0000000000000002 ffffea000934d580 ffffffff814a5451 kernel: 7fffffffffffffff ffffffff814a6e8f 0000000000000000 0000000000000020 kernel: Call Trace: kernel: [] ? bit_wait+0x2c/0x2c kernel: [] ? schedule+0x6f/0x7c kernel: [] ? schedule_timeout+0x2f/0xd8 kernel: [] ? timekeeping_get_ns+0xa/0x2e kernel: [] ? ktime_get+0x36/0x44 kernel: [] ? io_schedule_timeout+0x94/0xf2 kernel: [] ? io_schedule_timeout+0x94/0xf2 kernel: [] ? bit_wait_io+0x2c/0x30 kernel: [] ? __wait_on_bit+0x41/0x73 kernel: [] ? wait_on_page_bit+0x6d/0x72 kernel: [] ? autoremove_wake_function+0x2a/0x2a kernel: [] ? read_extent_buffer_pages+0x1bd/0x203 kernel: [] ? free_root_pointers+0x4c/0x4c kernel: [] ? btree_read_extent_buffer_pages.constprop.57+0x5a/0xe9 kernel: [] ? read_tree_block+0x2d/0x45 kernel: [] ? read_block_for_search.isra.34+0x22a/0x26b kernel: [] ? btrfs_set_path_blocking+0x1e/0x4a kernel: [] ? btrfs_search_slot+0x648/0x736 kernel: [] ? btrfs_lookup_extent_info+0xb7/0x2c7 kernel: [] ? walk_down_proc+0x9c/0x1ae kernel: [] ? walk_down_tree+0x40/0xa4 kernel: [] ? btrfs_drop_snapshot+0x2da/0x664 kernel: [] ? finish_task_switch+0x126/0x167 kernel: [] ? btrfs_clean_one_deleted_snapshot+0xa6/0xb0 kernel: [] ? cleaner_kthread+0x13e/0x17b kernel: [] ? btrfs_item_end+0x33/0x33 kernel: [] ? kthread+0x95/0x9d kernel: [] ? kthread_parkme+0x16/0x16 kernel: [] ? ret_from_fork+0x3f/0x70 kernel: [] ? kthread_parkme+0x16/0x16 As this affects a released kernel (4.4) we need a minimal fix for stable kernels. Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=108361 Reported-by: Martin Ziegler CC: Jiri Kosina Signed-off-by: David Sterba Signed-off-by: Chris Mason Signed-off-by: Greg Kroah-Hartman --- fs/btrfs/disk-io.c | 1 - 1 file changed, 1 deletion(-) diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 974be09e7556..0ddca6734494 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1762,7 +1762,6 @@ static int cleaner_kthread(void *arg) int again; struct btrfs_trans_handle *trans; - set_freezable(); do { again = 0; From b58081d430b4eaf6bf7d407cc5d4bfa39488b6c1 Mon Sep 17 00:00:00 2001 From: David Sterba Date: Fri, 13 Nov 2015 13:44:28 +0100 Subject: [PATCH 213/325] btrfs: properly set the termination value of ctx->pos in readdir MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit bc4ef7592f657ae81b017207a1098817126ad4cb upstream. The value of ctx->pos in the last readdir call is supposed to be set to INT_MAX due to 32bit compatibility, unless 'pos' is intentially set to a larger value, then it's LLONG_MAX. There's a report from PaX SIZE_OVERFLOW plugin that "ctx->pos++" overflows (https://forums.grsecurity.net/viewtopic.php?f=1&t=4284), on a 64bit arch, where the value is 0x7fffffffffffffff ie. LLONG_MAX before the increment. We can get to that situation like that: * emit all regular readdir entries * still in the same call to readdir, bump the last pos to INT_MAX * next call to readdir will not emit any entries, but will reach the bump code again, finds pos to be INT_MAX and sets it to LLONG_MAX Normally this is not a problem, but if we call readdir again, we'll find 'pos' set to LLONG_MAX and the unconditional increment will overflow. The report from Victor at (http://thread.gmane.org/gmane.comp.file-systems.btrfs/49500) with debugging print shows that pattern: Overflow: e Overflow: 7fffffff Overflow: 7fffffffffffffff PAX: size overflow detected in function btrfs_real_readdir fs/btrfs/inode.c:5760 cicus.935_282 max, count: 9, decl: pos; num: 0; context: dir_context; CPU: 0 PID: 2630 Comm: polkitd Not tainted 4.2.3-grsec #1 Hardware name: Gigabyte Technology Co., Ltd. H81ND2H/H81ND2H, BIOS F3 08/11/2015 ffffffff81901608 0000000000000000 ffffffff819015e6 ffffc90004973d48 ffffffff81742f0f 0000000000000007 ffffffff81901608 ffffc90004973d78 ffffffff811cb706 0000000000000000 ffff8800d47359e0 ffffc90004973ed8 Call Trace: [] dump_stack+0x4c/0x7f [] report_size_overflow+0x36/0x40 [] btrfs_real_readdir+0x69c/0x6d0 [] iterate_dir+0xa8/0x150 [] ? __fget_light+0x2d/0x70 [] SyS_getdents+0xba/0x1c0 Overflow: 1a [] ? iterate_dir+0x150/0x150 [] entry_SYSCALL_64_fastpath+0x12/0x83 The jump from 7fffffff to 7fffffffffffffff happens when new dir entries are not yet synced and are processed from the delayed list. Then the code could go to the bump section again even though it might not emit any new dir entries from the delayed list. The fix avoids entering the "bump" section again once we've finished emitting the entries, both for synced and delayed entries. References: https://forums.grsecurity.net/viewtopic.php?f=1&t=4284 Reported-by: Victor Signed-off-by: David Sterba Tested-by: Holger Hoffstätte Signed-off-by: Chris Mason Signed-off-by: Greg Kroah-Hartman --- fs/btrfs/delayed-inode.c | 3 ++- fs/btrfs/delayed-inode.h | 2 +- fs/btrfs/inode.c | 14 +++++++++++++- 3 files changed, 16 insertions(+), 3 deletions(-) diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index e0941fbb913c..02b934d0ee65 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -1694,7 +1694,7 @@ int btrfs_should_delete_dir_index(struct list_head *del_list, * */ int btrfs_readdir_delayed_dir_index(struct dir_context *ctx, - struct list_head *ins_list) + struct list_head *ins_list, bool *emitted) { struct btrfs_dir_item *di; struct btrfs_delayed_item *curr, *next; @@ -1738,6 +1738,7 @@ int btrfs_readdir_delayed_dir_index(struct dir_context *ctx, if (over) return 1; + *emitted = true; } return 0; } diff --git a/fs/btrfs/delayed-inode.h b/fs/btrfs/delayed-inode.h index f70119f25421..0167853c84ae 100644 --- a/fs/btrfs/delayed-inode.h +++ b/fs/btrfs/delayed-inode.h @@ -144,7 +144,7 @@ void btrfs_put_delayed_items(struct list_head *ins_list, int btrfs_should_delete_dir_index(struct list_head *del_list, u64 index); int btrfs_readdir_delayed_dir_index(struct dir_context *ctx, - struct list_head *ins_list); + struct list_head *ins_list, bool *emitted); /* for init */ int __init btrfs_delayed_inode_init(void); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index a70c5790f8f5..e31fac20e36e 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -5741,6 +5741,7 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx) char *name_ptr; int name_len; int is_curr = 0; /* ctx->pos points to the current index? */ + bool emitted; /* FIXME, use a real flag for deciding about the key type */ if (root->fs_info->tree_root == root) @@ -5769,6 +5770,7 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx) if (ret < 0) goto err; + emitted = false; while (1) { leaf = path->nodes[0]; slot = path->slots[0]; @@ -5848,6 +5850,7 @@ skip: if (over) goto nopos; + emitted = true; di_len = btrfs_dir_name_len(leaf, di) + btrfs_dir_data_len(leaf, di) + sizeof(*di); di_cur += di_len; @@ -5860,11 +5863,20 @@ next: if (key_type == BTRFS_DIR_INDEX_KEY) { if (is_curr) ctx->pos++; - ret = btrfs_readdir_delayed_dir_index(ctx, &ins_list); + ret = btrfs_readdir_delayed_dir_index(ctx, &ins_list, &emitted); if (ret) goto nopos; } + /* + * If we haven't emitted any dir entry, we must not touch ctx->pos as + * it was was set to the termination value in previous call. We assume + * that "." and ".." were emitted if we reach this point and set the + * termination value as well for an empty directory. + */ + if (ctx->pos > 2 && !emitted) + goto nopos; + /* Reached end of directory/root. Bump pos past the last item. */ ctx->pos++; From df567e6dcd22097d2f31b6a8bf481959f1352b6a Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Wed, 27 Jan 2016 10:20:58 +0000 Subject: [PATCH 214/325] Btrfs: fix invalid page accesses in extent_same (dedup) ioctl commit e0bd70c67bf996b360f706b6c643000f2e384681 upstream. In the extent_same ioctl we are getting the pages for the source and target ranges and unlocking them immediately after, which is incorrect because later we attempt to map them (with kmap_atomic) and access their contents at btrfs_cmp_data(). When we do such access the pages might have been relocated or removed from memory, which leads to an invalid memory access. This issue is detected on a kernel with CONFIG_DEBUG_PAGEALLOC=y which produces a trace like the following: 186736.677437] general protection fault: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC [186736.680382] Modules linked in: btrfs dm_flakey dm_mod ppdev xor raid6_pq sha256_generic hmac drbg ansi_cprng acpi_cpufreq evdev sg aesni_intel aes_x86_64 parport_pc ablk_helper tpm_tis psmouse parport i2c_piix4 tpm cryptd i2c_core lrw processor button serio_raw pcspkr gf128mul glue_helper loop autofs4 ext4 crc16 mbcache jbd2 sd_mod sr_mod cdrom ata_generic virtio_scsi ata_piix libata virtio_pci virtio_ring crc32c_intel scsi_mod e1000 virtio floppy [last unloaded: btrfs] [186736.681319] CPU: 13 PID: 10222 Comm: duperemove Tainted: G W 4.4.0-rc6-btrfs-next-18+ #1 [186736.681319] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS by qemu-project.org 04/01/2014 [186736.681319] task: ffff880132600400 ti: ffff880362284000 task.ti: ffff880362284000 [186736.681319] RIP: 0010:[] [] memcmp+0xb/0x22 [186736.681319] RSP: 0018:ffff880362287d70 EFLAGS: 00010287 [186736.681319] RAX: 000002c002468acf RBX: 0000000012345678 RCX: 0000000000000000 [186736.681319] RDX: 0000000000001000 RSI: 0005d129c5cf9000 RDI: 0005d129c5cf9000 [186736.681319] RBP: ffff880362287d70 R08: 0000000000000000 R09: 0000000000001000 [186736.681319] R10: ffff880000000000 R11: 0000000000000476 R12: 0000000000001000 [186736.681319] R13: ffff8802f91d4c88 R14: ffff8801f2a77830 R15: ffff880352e83e40 [186736.681319] FS: 00007f27b37fe700(0000) GS:ffff88043dda0000(0000) knlGS:0000000000000000 [186736.681319] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [186736.681319] CR2: 00007f27a406a000 CR3: 0000000217421000 CR4: 00000000001406e0 [186736.681319] Stack: [186736.681319] ffff880362287ea0 ffffffffa048d0bd 000000000009f000 0000000000001000 [186736.681319] 0100000000000000 ffff8801f2a77850 ffff8802f91d49b0 ffff880132600400 [186736.681319] 00000000000004f8 ffff8801c1efbe41 0000000000000000 0000000000000038 [186736.681319] Call Trace: [186736.681319] [] btrfs_ioctl+0x24cb/0x2731 [btrfs] [186736.681319] [] ? arch_local_irq_save+0x9/0xc [186736.681319] [] ? rcu_read_unlock+0x3e/0x5d [186736.681319] [] do_vfs_ioctl+0x42b/0x4ea [186736.681319] [] ? __fget_light+0x62/0x71 [186736.681319] [] SyS_ioctl+0x57/0x79 [186736.681319] [] entry_SYSCALL_64_fastpath+0x12/0x6f [186736.681319] Code: 0a 3c 6e 74 0d 3c 79 74 04 3c 59 75 0c c6 06 01 eb 03 c6 06 00 31 c0 eb 05 b8 ea ff ff ff 5d c3 55 31 c9 48 89 e5 48 39 d1 74 13 <0f> b6 04 0f 44 0f b6 04 0e 48 ff c1 44 29 c0 74 ea eb 02 31 c0 (gdb) list *(btrfs_ioctl+0x24cb) 0x5e0e1 is in btrfs_ioctl (fs/btrfs/ioctl.c:2972). 2967 dst_addr = kmap_atomic(dst_page); 2968 2969 flush_dcache_page(src_page); 2970 flush_dcache_page(dst_page); 2971 2972 if (memcmp(addr, dst_addr, cmp_len)) 2973 ret = BTRFS_SAME_DATA_DIFFERS; 2974 2975 kunmap_atomic(addr); 2976 kunmap_atomic(dst_addr); So fix this by making sure we keep the pages locked and respect the same locking order as everywhere else: get and lock the pages first and then lock the range in the inode's io tree (like for example at __btrfs_buffered_write() and extent_readpages()). If an ordered extent is found after locking the range in the io tree, unlock the range, unlock the pages, wait for the ordered extent to complete and repeat the entire locking process until no overlapping ordered extents are found. Signed-off-by: Filipe Manana Signed-off-by: Greg Kroah-Hartman --- fs/btrfs/ioctl.c | 90 ++++++++++++++++++++++++++++++++++++++++-------- 1 file changed, 76 insertions(+), 14 deletions(-) diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index da94138eb85e..e225a615ad03 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -2799,7 +2799,6 @@ static struct page *extent_same_get_page(struct inode *inode, pgoff_t index) return NULL; } } - unlock_page(page); return page; } @@ -2818,10 +2817,17 @@ static int gather_extent_pages(struct inode *inode, struct page **pages, return 0; } -static inline void lock_extent_range(struct inode *inode, u64 off, u64 len) +static int lock_extent_range(struct inode *inode, u64 off, u64 len, + bool retry_range_locking) { - /* do any pending delalloc/csum calc on src, one way or - another, and lock file content */ + /* + * Do any pending delalloc/csum calculations on inode, one way or + * another, and lock file content. + * The locking order is: + * + * 1) pages + * 2) range in the inode's io tree + */ while (1) { struct btrfs_ordered_extent *ordered; lock_extent(&BTRFS_I(inode)->io_tree, off, off + len - 1); @@ -2839,8 +2845,11 @@ static inline void lock_extent_range(struct inode *inode, u64 off, u64 len) unlock_extent(&BTRFS_I(inode)->io_tree, off, off + len - 1); if (ordered) btrfs_put_ordered_extent(ordered); + if (!retry_range_locking) + return -EAGAIN; btrfs_wait_ordered_range(inode, off, len); } + return 0; } static void btrfs_double_inode_unlock(struct inode *inode1, struct inode *inode2) @@ -2865,15 +2874,24 @@ static void btrfs_double_extent_unlock(struct inode *inode1, u64 loff1, unlock_extent(&BTRFS_I(inode2)->io_tree, loff2, loff2 + len - 1); } -static void btrfs_double_extent_lock(struct inode *inode1, u64 loff1, - struct inode *inode2, u64 loff2, u64 len) +static int btrfs_double_extent_lock(struct inode *inode1, u64 loff1, + struct inode *inode2, u64 loff2, u64 len, + bool retry_range_locking) { + int ret; + if (inode1 < inode2) { swap(inode1, inode2); swap(loff1, loff2); } - lock_extent_range(inode1, loff1, len); - lock_extent_range(inode2, loff2, len); + ret = lock_extent_range(inode1, loff1, len, retry_range_locking); + if (ret) + return ret; + ret = lock_extent_range(inode2, loff2, len, retry_range_locking); + if (ret) + unlock_extent(&BTRFS_I(inode1)->io_tree, loff1, + loff1 + len - 1); + return ret; } struct cmp_pages { @@ -2889,11 +2907,15 @@ static void btrfs_cmp_data_free(struct cmp_pages *cmp) for (i = 0; i < cmp->num_pages; i++) { pg = cmp->src_pages[i]; - if (pg) + if (pg) { + unlock_page(pg); page_cache_release(pg); + } pg = cmp->dst_pages[i]; - if (pg) + if (pg) { + unlock_page(pg); page_cache_release(pg); + } } kfree(cmp->src_pages); kfree(cmp->dst_pages); @@ -2954,6 +2976,8 @@ static int btrfs_cmp_data(struct inode *src, u64 loff, struct inode *dst, src_page = cmp->src_pages[i]; dst_page = cmp->dst_pages[i]; + ASSERT(PageLocked(src_page)); + ASSERT(PageLocked(dst_page)); addr = kmap_atomic(src_page); dst_addr = kmap_atomic(dst_page); @@ -3066,14 +3090,46 @@ static int btrfs_extent_same(struct inode *src, u64 loff, u64 olen, goto out_unlock; } +again: ret = btrfs_cmp_data_prepare(src, loff, dst, dst_loff, olen, &cmp); if (ret) goto out_unlock; if (same_inode) - lock_extent_range(src, same_lock_start, same_lock_len); + ret = lock_extent_range(src, same_lock_start, same_lock_len, + false); else - btrfs_double_extent_lock(src, loff, dst, dst_loff, len); + ret = btrfs_double_extent_lock(src, loff, dst, dst_loff, len, + false); + /* + * If one of the inodes has dirty pages in the respective range or + * ordered extents, we need to flush dellaloc and wait for all ordered + * extents in the range. We must unlock the pages and the ranges in the + * io trees to avoid deadlocks when flushing delalloc (requires locking + * pages) and when waiting for ordered extents to complete (they require + * range locking). + */ + if (ret == -EAGAIN) { + /* + * Ranges in the io trees already unlocked. Now unlock all + * pages before waiting for all IO to complete. + */ + btrfs_cmp_data_free(&cmp); + if (same_inode) { + btrfs_wait_ordered_range(src, same_lock_start, + same_lock_len); + } else { + btrfs_wait_ordered_range(src, loff, len); + btrfs_wait_ordered_range(dst, dst_loff, len); + } + goto again; + } + ASSERT(ret == 0); + if (WARN_ON(ret)) { + /* ranges in the io trees already unlocked */ + btrfs_cmp_data_free(&cmp); + return ret; + } /* pass original length for comparison so we stay within i_size */ ret = btrfs_cmp_data(src, loff, dst, dst_loff, olen, &cmp); @@ -3895,9 +3951,15 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd, u64 lock_start = min_t(u64, off, destoff); u64 lock_len = max_t(u64, off, destoff) + len - lock_start; - lock_extent_range(src, lock_start, lock_len); + ret = lock_extent_range(src, lock_start, lock_len, true); } else { - btrfs_double_extent_lock(src, off, inode, destoff, len); + ret = btrfs_double_extent_lock(src, off, inode, destoff, len, + true); + } + ASSERT(ret == 0); + if (WARN_ON(ret)) { + /* ranges in the io trees already unlocked */ + goto out_unlock; } ret = btrfs_clone(src, inode, off, olen, len, destoff, 0); From be1232bcea113204523b7d530cc5d6d534916276 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Wed, 27 Jan 2016 18:37:47 +0000 Subject: [PATCH 215/325] Btrfs: fix page reading in extent_same ioctl leading to csum errors commit 313140023026ae542ad76e7e268c56a1eaa2c28e upstream. In the extent_same ioctl, we were grabbing the pages (locked) and attempting to read them without bothering about any concurrent IO against them. That is, we were not checking for any ongoing ordered extents nor waiting for them to complete, which leads to a race where the extent_same() code gets a checksum verification error when it reads the pages, producing a message like the following in dmesg and making the operation fail to user space with -ENOMEM: [18990.161265] BTRFS warning (device sdc): csum failed ino 259 off 495616 csum 685204116 expected csum 1515870868 Fix this by using btrfs_readpage() for reading the pages instead of extent_read_full_page_nolock(), which waits for any concurrent ordered extents to complete and locks the io range. Also do better error handling and don't treat all failures as -ENOMEM, as that's clearly misleasing, becoming identical to the checks and operation of prepare_uptodate_page(). The use of extent_read_full_page_nolock() was required before commit f441460202cb ("btrfs: fix deadlock with extent-same and readpage"), as we had the range locked in an inode's io tree before attempting to read the pages. Fixes: f441460202cb ("btrfs: fix deadlock with extent-same and readpage") Signed-off-by: Filipe Manana Signed-off-by: Greg Kroah-Hartman --- fs/btrfs/ioctl.c | 29 +++++++++++++++++++++-------- 1 file changed, 21 insertions(+), 8 deletions(-) diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index e225a615ad03..08fd3f0f34fd 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -2782,21 +2782,27 @@ out: static struct page *extent_same_get_page(struct inode *inode, pgoff_t index) { struct page *page; - struct extent_io_tree *tree = &BTRFS_I(inode)->io_tree; page = grab_cache_page(inode->i_mapping, index); if (!page) - return NULL; + return ERR_PTR(-ENOMEM); if (!PageUptodate(page)) { - if (extent_read_full_page_nolock(tree, page, btrfs_get_extent, - 0)) - return NULL; + int ret; + + ret = btrfs_readpage(NULL, page); + if (ret) + return ERR_PTR(ret); lock_page(page); if (!PageUptodate(page)) { unlock_page(page); page_cache_release(page); - return NULL; + return ERR_PTR(-EIO); + } + if (page->mapping != inode->i_mapping) { + unlock_page(page); + page_cache_release(page); + return ERR_PTR(-EAGAIN); } } @@ -2810,9 +2816,16 @@ static int gather_extent_pages(struct inode *inode, struct page **pages, pgoff_t index = off >> PAGE_CACHE_SHIFT; for (i = 0; i < num_pages; i++) { +again: pages[i] = extent_same_get_page(inode, index + i); - if (!pages[i]) - return -ENOMEM; + if (IS_ERR(pages[i])) { + int err = PTR_ERR(pages[i]); + + if (err == -EAGAIN) + goto again; + pages[i] = NULL; + return err; + } } return 0; } From e8eced78e0252040c4e6bb633b40afb11a176416 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Wed, 3 Feb 2016 19:17:27 +0000 Subject: [PATCH 216/325] Btrfs: fix hang on extent buffer lock caused by the inode_paths ioctl commit 0c0fe3b0fa45082cd752553fdb3a4b42503a118e upstream. While doing some tests I ran into an hang on an extent buffer's rwlock that produced the following trace: [39389.800012] NMI watchdog: BUG: soft lockup - CPU#15 stuck for 22s! [fdm-stress:32166] [39389.800016] NMI watchdog: BUG: soft lockup - CPU#14 stuck for 22s! [fdm-stress:32165] [39389.800016] Modules linked in: btrfs dm_mod ppdev xor sha256_generic hmac raid6_pq drbg ansi_cprng aesni_intel i2c_piix4 acpi_cpufreq aes_x86_64 ablk_helper tpm_tis parport_pc i2c_core sg cryptd evdev psmouse lrw tpm parport gf128mul serio_raw pcspkr glue_helper processor button loop autofs4 ext4 crc16 mbcache jbd2 sd_mod sr_mod cdrom ata_generic virtio_scsi ata_piix libata virtio_pci virtio_ring crc32c_intel scsi_mod e1000 virtio floppy [last unloaded: btrfs] [39389.800016] irq event stamp: 0 [39389.800016] hardirqs last enabled at (0): [< (null)>] (null) [39389.800016] hardirqs last disabled at (0): [] copy_process+0x638/0x1a35 [39389.800016] softirqs last enabled at (0): [] copy_process+0x638/0x1a35 [39389.800016] softirqs last disabled at (0): [< (null)>] (null) [39389.800016] CPU: 14 PID: 32165 Comm: fdm-stress Not tainted 4.4.0-rc6-btrfs-next-18+ #1 [39389.800016] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS by qemu-project.org 04/01/2014 [39389.800016] task: ffff880175b1ca40 ti: ffff8800a185c000 task.ti: ffff8800a185c000 [39389.800016] RIP: 0010:[] [] queued_spin_lock_slowpath+0x57/0x158 [39389.800016] RSP: 0018:ffff8800a185fb80 EFLAGS: 00000202 [39389.800016] RAX: 0000000000000101 RBX: ffff8801710c4e9c RCX: 0000000000000101 [39389.800016] RDX: 0000000000000100 RSI: 0000000000000001 RDI: 0000000000000001 [39389.800016] RBP: ffff8800a185fb98 R08: 0000000000000001 R09: 0000000000000000 [39389.800016] R10: ffff8800a185fb68 R11: 6db6db6db6db6db7 R12: ffff8801710c4e98 [39389.800016] R13: ffff880175b1ca40 R14: ffff8800a185fc10 R15: ffff880175b1ca40 [39389.800016] FS: 00007f6d37fff700(0000) GS:ffff8802be9c0000(0000) knlGS:0000000000000000 [39389.800016] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [39389.800016] CR2: 00007f6d300019b8 CR3: 0000000037c93000 CR4: 00000000001406e0 [39389.800016] Stack: [39389.800016] ffff8801710c4e98 ffff8801710c4e98 ffff880175b1ca40 ffff8800a185fbb0 [39389.800016] ffffffff81091e11 ffff8801710c4e98 ffff8800a185fbc8 ffffffff81091895 [39389.800016] ffff8801710c4e98 ffff8800a185fbe8 ffffffff81486c5c ffffffffa067288c [39389.800016] Call Trace: [39389.800016] [] queued_read_lock_slowpath+0x46/0x60 [39389.800016] [] do_raw_read_lock+0x3e/0x41 [39389.800016] [] _raw_read_lock+0x3d/0x44 [39389.800016] [] ? btrfs_tree_read_lock+0x54/0x125 [btrfs] [39389.800016] [] btrfs_tree_read_lock+0x54/0x125 [btrfs] [39389.800016] [] ? btrfs_find_item+0xa7/0xd2 [btrfs] [39389.800016] [] btrfs_ref_to_path+0xd6/0x174 [btrfs] [39389.800016] [] inode_to_path+0x53/0xa2 [btrfs] [39389.800016] [] paths_from_inode+0x117/0x2ec [btrfs] [39389.800016] [] btrfs_ioctl+0xd5b/0x2793 [btrfs] [39389.800016] [] ? arch_local_irq_save+0x9/0xc [39389.800016] [] ? __this_cpu_preempt_check+0x13/0x15 [39389.800016] [] ? arch_local_irq_save+0x9/0xc [39389.800016] [] ? rcu_read_unlock+0x3e/0x5d [39389.800016] [] do_vfs_ioctl+0x42b/0x4ea [39389.800016] [] ? __fget_light+0x62/0x71 [39389.800016] [] SyS_ioctl+0x57/0x79 [39389.800016] [] entry_SYSCALL_64_fastpath+0x12/0x6f [39389.800016] Code: b9 01 01 00 00 f7 c6 00 ff ff ff 75 32 83 fe 01 89 ca 89 f0 0f 45 d7 f0 0f b1 13 39 f0 74 04 89 c6 eb e2 ff ca 0f 84 fa 00 00 00 <8b> 03 84 c0 74 04 f3 90 eb f6 66 c7 03 01 00 e9 e6 00 00 00 e8 [39389.800012] Modules linked in: btrfs dm_mod ppdev xor sha256_generic hmac raid6_pq drbg ansi_cprng aesni_intel i2c_piix4 acpi_cpufreq aes_x86_64 ablk_helper tpm_tis parport_pc i2c_core sg cryptd evdev psmouse lrw tpm parport gf128mul serio_raw pcspkr glue_helper processor button loop autofs4 ext4 crc16 mbcache jbd2 sd_mod sr_mod cdrom ata_generic virtio_scsi ata_piix libata virtio_pci virtio_ring crc32c_intel scsi_mod e1000 virtio floppy [last unloaded: btrfs] [39389.800012] irq event stamp: 0 [39389.800012] hardirqs last enabled at (0): [< (null)>] (null) [39389.800012] hardirqs last disabled at (0): [] copy_process+0x638/0x1a35 [39389.800012] softirqs last enabled at (0): [] copy_process+0x638/0x1a35 [39389.800012] softirqs last disabled at (0): [< (null)>] (null) [39389.800012] CPU: 15 PID: 32166 Comm: fdm-stress Tainted: G L 4.4.0-rc6-btrfs-next-18+ #1 [39389.800012] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS by qemu-project.org 04/01/2014 [39389.800012] task: ffff880179294380 ti: ffff880034a60000 task.ti: ffff880034a60000 [39389.800012] RIP: 0010:[] [] queued_write_lock_slowpath+0x62/0x72 [39389.800012] RSP: 0018:ffff880034a639f0 EFLAGS: 00000206 [39389.800012] RAX: 0000000000000101 RBX: ffff8801710c4e98 RCX: 0000000000000000 [39389.800012] RDX: 00000000000000ff RSI: 0000000000000000 RDI: ffff8801710c4e9c [39389.800012] RBP: ffff880034a639f8 R08: 0000000000000001 R09: 0000000000000000 [39389.800012] R10: ffff880034a639b0 R11: 0000000000001000 R12: ffff8801710c4e98 [39389.800012] R13: 0000000000000001 R14: ffff880172cbc000 R15: ffff8801710c4e00 [39389.800012] FS: 00007f6d377fe700(0000) GS:ffff8802be9e0000(0000) knlGS:0000000000000000 [39389.800012] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [39389.800012] CR2: 00007f6d3d3c1000 CR3: 0000000037c93000 CR4: 00000000001406e0 [39389.800012] Stack: [39389.800012] ffff8801710c4e98 ffff880034a63a10 ffffffff81091963 ffff8801710c4e98 [39389.800012] ffff880034a63a30 ffffffff81486f1b ffffffffa0672cb3 ffff8801710c4e00 [39389.800012] ffff880034a63a78 ffffffffa0672cb3 ffff8801710c4e00 ffff880034a63a58 [39389.800012] Call Trace: [39389.800012] [] do_raw_write_lock+0x72/0x8c [39389.800012] [] _raw_write_lock+0x3a/0x41 [39389.800012] [] ? btrfs_tree_lock+0x119/0x251 [btrfs] [39389.800012] [] btrfs_tree_lock+0x119/0x251 [btrfs] [39389.800012] [] ? rcu_read_unlock+0x5b/0x5d [btrfs] [39389.800012] [] ? btrfs_root_node+0xda/0xe6 [btrfs] [39389.800012] [] btrfs_lock_root_node+0x22/0x42 [btrfs] [39389.800012] [] btrfs_search_slot+0x1b8/0x758 [btrfs] [39389.800012] [] ? time_hardirqs_on+0x15/0x28 [39389.800012] [] btrfs_lookup_inode+0x31/0x95 [btrfs] [39389.800012] [] ? trace_hardirqs_on+0xd/0xf [39389.800012] [] ? mutex_lock_nested+0x397/0x3bc [39389.800012] [] __btrfs_update_delayed_inode+0x59/0x1c0 [btrfs] [39389.800012] [] __btrfs_commit_inode_delayed_items+0x194/0x5aa [btrfs] [39389.800012] [] ? _raw_spin_unlock+0x31/0x44 [39389.800012] [] __btrfs_run_delayed_items+0xa4/0x15c [btrfs] [39389.800012] [] btrfs_run_delayed_items+0x11/0x13 [btrfs] [39389.800012] [] btrfs_commit_transaction+0x234/0x96e [btrfs] [39389.800012] [] btrfs_sync_fs+0x145/0x1ad [btrfs] [39389.800012] [] btrfs_ioctl+0x11d2/0x2793 [btrfs] [39389.800012] [] ? arch_local_irq_save+0x9/0xc [39389.800012] [] ? __might_fault+0x4c/0xa7 [39389.800012] [] ? __might_fault+0x4c/0xa7 [39389.800012] [] ? arch_local_irq_save+0x9/0xc [39389.800012] [] ? rcu_read_unlock+0x3e/0x5d [39389.800012] [] do_vfs_ioctl+0x42b/0x4ea [39389.800012] [] ? __fget_light+0x62/0x71 [39389.800012] [] SyS_ioctl+0x57/0x79 [39389.800012] [] entry_SYSCALL_64_fastpath+0x12/0x6f [39389.800012] Code: f0 0f b1 13 85 c0 75 ef eb 2a f3 90 8a 03 84 c0 75 f8 f0 0f b0 13 84 c0 75 f0 ba ff 00 00 00 eb 0a f0 0f b1 13 ff c8 74 0b f3 90 <8b> 03 83 f8 01 75 f7 eb ed c6 43 04 00 5b 5d c3 0f 1f 44 00 00 This happens because in the code path executed by the inode_paths ioctl we end up nesting two calls to read lock a leaf's rwlock when after the first call to read_lock() and before the second call to read_lock(), another task (running the delayed items as part of a transaction commit) has already called write_lock() against the leaf's rwlock. This situation is illustrated by the following diagram: Task A Task B btrfs_ref_to_path() btrfs_commit_transaction() read_lock(&eb->lock); btrfs_run_delayed_items() __btrfs_commit_inode_delayed_items() __btrfs_update_delayed_inode() btrfs_lookup_inode() write_lock(&eb->lock); --> task waits for lock read_lock(&eb->lock); --> makes this task hang forever (and task B too of course) So fix this by avoiding doing the nested read lock, which is easily avoidable. This issue does not happen if task B calls write_lock() after task A does the second call to read_lock(), however there does not seem to exist anything in the documentation that mentions what is the expected behaviour for recursive locking of rwlocks (leaving the idea that doing so is not a good usage of rwlocks). Also, as a side effect necessary for this fix, make sure we do not needlessly read lock extent buffers when the input path has skip_locking set (used when called from send). Signed-off-by: Filipe Manana Signed-off-by: Greg Kroah-Hartman --- fs/btrfs/backref.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index d453d62ab0c6..e2f659dc5745 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -1417,7 +1417,8 @@ char *btrfs_ref_to_path(struct btrfs_root *fs_root, struct btrfs_path *path, read_extent_buffer(eb, dest + bytes_left, name_off, name_len); if (eb != eb_in) { - btrfs_tree_read_unlock_blocking(eb); + if (!path->skip_locking) + btrfs_tree_read_unlock_blocking(eb); free_extent_buffer(eb); } ret = btrfs_find_item(fs_root, path, parent, 0, @@ -1437,9 +1438,10 @@ char *btrfs_ref_to_path(struct btrfs_root *fs_root, struct btrfs_path *path, eb = path->nodes[0]; /* make sure we can use eb after releasing the path */ if (eb != eb_in) { - atomic_inc(&eb->refs); - btrfs_tree_read_lock(eb); - btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK); + if (!path->skip_locking) + btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK); + path->nodes[0] = NULL; + path->locks[0] = 0; } btrfs_release_path(path); iref = btrfs_item_ptr(eb, slot, struct btrfs_inode_ref); From ba6d92801ba4e4c0262b70ea00922a71092999bb Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Mon, 15 Feb 2016 16:20:26 +0000 Subject: [PATCH 217/325] Btrfs: fix direct IO requests not reporting IO error to user space commit 1636d1d77ef4e01e57f706a4cae3371463896136 upstream. If a bio for a direct IO request fails, we were not setting the error in the parent bio (the main DIO bio), making us not return the error to user space in btrfs_direct_IO(), that is, it made __blockdev_direct_IO() return the number of bytes issued for IO and not the error a bio created and submitted by btrfs_submit_direct() got from the block layer. This essentially happens because when we call: dio_end_io(dio_bio, bio->bi_error); It does not set dio_bio->bi_error to the value of the second argument. So just add this missing assignment in endio callbacks, just as we do in the error path at btrfs_submit_direct() when we fail to clone the dio bio or allocate its private object. This follows the convention of what is done with other similar APIs such as bio_endio() where the caller is responsible for setting the bi_error field in the bio it passes as an argument to bio_endio(). This was detected by the new generic test cases in xfstests: 271, 272, 276 and 278. Which essentially setup a dm error target, then load the error table, do a direct IO write and unload the error table. They expect the write to fail with -EIO, which was not getting reported when testing against btrfs. Fixes: 4246a0b63bd8 ("block: add a bi_error field to struct bio") Signed-off-by: Filipe Manana Signed-off-by: Greg Kroah-Hartman --- fs/btrfs/inode.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index e31fac20e36e..54b5f0de623b 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -7997,6 +7997,7 @@ static void btrfs_endio_direct_read(struct bio *bio) kfree(dip); + dio_bio->bi_error = bio->bi_error; dio_end_io(dio_bio, bio->bi_error); if (io_bio->end_io) @@ -8042,6 +8043,7 @@ out_test: kfree(dip); + dio_bio->bi_error = bio->bi_error; dio_end_io(dio_bio, bio->bi_error); bio_put(bio); } From 969624b7c1c8c9784651eb97431e6f2bbb7a024c Mon Sep 17 00:00:00 2001 From: Jann Horn Date: Wed, 20 Jan 2016 15:00:04 -0800 Subject: [PATCH 218/325] ptrace: use fsuid, fsgid, effective creds for fs access checks commit caaee6234d05a58c5b4d05e7bf766131b810a657 upstream. By checking the effective credentials instead of the real UID / permitted capabilities, ensure that the calling process actually intended to use its credentials. To ensure that all ptrace checks use the correct caller credentials (e.g. in case out-of-tree code or newly added code omits the PTRACE_MODE_*CREDS flag), use two new flags and require one of them to be set. The problem was that when a privileged task had temporarily dropped its privileges, e.g. by calling setreuid(0, user_uid), with the intent to perform following syscalls with the credentials of a user, it still passed ptrace access checks that the user would not be able to pass. While an attacker should not be able to convince the privileged task to perform a ptrace() syscall, this is a problem because the ptrace access check is reused for things in procfs. In particular, the following somewhat interesting procfs entries only rely on ptrace access checks: /proc/$pid/stat - uses the check for determining whether pointers should be visible, useful for bypassing ASLR /proc/$pid/maps - also useful for bypassing ASLR /proc/$pid/cwd - useful for gaining access to restricted directories that contain files with lax permissions, e.g. in this scenario: lrwxrwxrwx root root /proc/13020/cwd -> /root/foobar drwx------ root root /root drwxr-xr-x root root /root/foobar -rw-r--r-- root root /root/foobar/secret Therefore, on a system where a root-owned mode 6755 binary changes its effective credentials as described and then dumps a user-specified file, this could be used by an attacker to reveal the memory layout of root's processes or reveal the contents of files he is not allowed to access (through /proc/$pid/cwd). [akpm@linux-foundation.org: fix warning] Signed-off-by: Jann Horn Acked-by: Kees Cook Cc: Casey Schaufler Cc: Oleg Nesterov Cc: Ingo Molnar Cc: James Morris Cc: "Serge E. Hallyn" Cc: Andy Shevchenko Cc: Andy Lutomirski Cc: Al Viro Cc: "Eric W. Biederman" Cc: Willy Tarreau Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- fs/proc/array.c | 2 +- fs/proc/base.c | 21 +++++++++++---------- fs/proc/namespaces.c | 4 ++-- include/linux/ptrace.h | 24 +++++++++++++++++++++++- kernel/events/core.c | 2 +- kernel/futex.c | 2 +- kernel/futex_compat.c | 2 +- kernel/kcmp.c | 4 ++-- kernel/ptrace.c | 39 +++++++++++++++++++++++++++++++-------- mm/process_vm_access.c | 2 +- security/commoncap.c | 7 ++++++- 11 files changed, 80 insertions(+), 29 deletions(-) diff --git a/fs/proc/array.c b/fs/proc/array.c index d73291f5f0fc..b6c00ce0e29e 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -395,7 +395,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, state = *get_task_state(task); vsize = eip = esp = 0; - permitted = ptrace_may_access(task, PTRACE_MODE_READ | PTRACE_MODE_NOAUDIT); + permitted = ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS | PTRACE_MODE_NOAUDIT); mm = get_task_mm(task); if (mm) { vsize = task_vsize(mm); diff --git a/fs/proc/base.c b/fs/proc/base.c index 4bd5d3118acd..b7de324bec11 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -403,7 +403,7 @@ static const struct file_operations proc_pid_cmdline_ops = { static int proc_pid_auxv(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { - struct mm_struct *mm = mm_access(task, PTRACE_MODE_READ); + struct mm_struct *mm = mm_access(task, PTRACE_MODE_READ_FSCREDS); if (mm && !IS_ERR(mm)) { unsigned int nwords = 0; do { @@ -430,7 +430,8 @@ static int proc_pid_wchan(struct seq_file *m, struct pid_namespace *ns, wchan = get_wchan(task); - if (wchan && ptrace_may_access(task, PTRACE_MODE_READ) && !lookup_symbol_name(wchan, symname)) + if (wchan && ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS) + && !lookup_symbol_name(wchan, symname)) seq_printf(m, "%s", symname); else seq_putc(m, '0'); @@ -444,7 +445,7 @@ static int lock_trace(struct task_struct *task) int err = mutex_lock_killable(&task->signal->cred_guard_mutex); if (err) return err; - if (!ptrace_may_access(task, PTRACE_MODE_ATTACH)) { + if (!ptrace_may_access(task, PTRACE_MODE_ATTACH_FSCREDS)) { mutex_unlock(&task->signal->cred_guard_mutex); return -EPERM; } @@ -697,7 +698,7 @@ static int proc_fd_access_allowed(struct inode *inode) */ task = get_proc_task(inode); if (task) { - allowed = ptrace_may_access(task, PTRACE_MODE_READ); + allowed = ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS); put_task_struct(task); } return allowed; @@ -732,7 +733,7 @@ static bool has_pid_permissions(struct pid_namespace *pid, return true; if (in_group_p(pid->pid_gid)) return true; - return ptrace_may_access(task, PTRACE_MODE_READ); + return ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS); } @@ -809,7 +810,7 @@ struct mm_struct *proc_mem_open(struct inode *inode, unsigned int mode) struct mm_struct *mm = ERR_PTR(-ESRCH); if (task) { - mm = mm_access(task, mode); + mm = mm_access(task, mode | PTRACE_MODE_FSCREDS); put_task_struct(task); if (!IS_ERR_OR_NULL(mm)) { @@ -1856,7 +1857,7 @@ static int map_files_d_revalidate(struct dentry *dentry, unsigned int flags) if (!task) goto out_notask; - mm = mm_access(task, PTRACE_MODE_READ); + mm = mm_access(task, PTRACE_MODE_READ_FSCREDS); if (IS_ERR_OR_NULL(mm)) goto out; @@ -2007,7 +2008,7 @@ static struct dentry *proc_map_files_lookup(struct inode *dir, goto out; result = -EACCES; - if (!ptrace_may_access(task, PTRACE_MODE_READ)) + if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) goto out_put_task; result = -ENOENT; @@ -2060,7 +2061,7 @@ proc_map_files_readdir(struct file *file, struct dir_context *ctx) goto out; ret = -EACCES; - if (!ptrace_may_access(task, PTRACE_MODE_READ)) + if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) goto out_put_task; ret = 0; @@ -2530,7 +2531,7 @@ static int do_io_accounting(struct task_struct *task, struct seq_file *m, int wh if (result) return result; - if (!ptrace_may_access(task, PTRACE_MODE_READ)) { + if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) { result = -EACCES; goto out_unlock; } diff --git a/fs/proc/namespaces.c b/fs/proc/namespaces.c index f6e8354b8cea..1b0ea4a5d89e 100644 --- a/fs/proc/namespaces.c +++ b/fs/proc/namespaces.c @@ -42,7 +42,7 @@ static const char *proc_ns_follow_link(struct dentry *dentry, void **cookie) if (!task) return error; - if (ptrace_may_access(task, PTRACE_MODE_READ)) { + if (ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) { error = ns_get_path(&ns_path, task, ns_ops); if (!error) nd_jump_link(&ns_path); @@ -63,7 +63,7 @@ static int proc_ns_readlink(struct dentry *dentry, char __user *buffer, int bufl if (!task) return res; - if (ptrace_may_access(task, PTRACE_MODE_READ)) { + if (ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) { res = ns_get_name(name, sizeof(name), task, ns_ops); if (res >= 0) res = readlink_copy(buffer, buflen, name); diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index 061265f92876..504c98a278d4 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -57,7 +57,29 @@ extern void exit_ptrace(struct task_struct *tracer, struct list_head *dead); #define PTRACE_MODE_READ 0x01 #define PTRACE_MODE_ATTACH 0x02 #define PTRACE_MODE_NOAUDIT 0x04 -/* Returns true on success, false on denial. */ +#define PTRACE_MODE_FSCREDS 0x08 +#define PTRACE_MODE_REALCREDS 0x10 + +/* shorthands for READ/ATTACH and FSCREDS/REALCREDS combinations */ +#define PTRACE_MODE_READ_FSCREDS (PTRACE_MODE_READ | PTRACE_MODE_FSCREDS) +#define PTRACE_MODE_READ_REALCREDS (PTRACE_MODE_READ | PTRACE_MODE_REALCREDS) +#define PTRACE_MODE_ATTACH_FSCREDS (PTRACE_MODE_ATTACH | PTRACE_MODE_FSCREDS) +#define PTRACE_MODE_ATTACH_REALCREDS (PTRACE_MODE_ATTACH | PTRACE_MODE_REALCREDS) + +/** + * ptrace_may_access - check whether the caller is permitted to access + * a target task. + * @task: target task + * @mode: selects type of access and caller credentials + * + * Returns true on success, false on denial. + * + * One of the flags PTRACE_MODE_FSCREDS and PTRACE_MODE_REALCREDS must + * be set in @mode to specify whether the access was requested through + * a filesystem syscall (should use effective capabilities and fsuid + * of the caller) or through an explicit syscall such as + * process_vm_writev or ptrace (and should use the real credentials). + */ extern bool ptrace_may_access(struct task_struct *task, unsigned int mode); static inline int ptrace_reparented(struct task_struct *child) diff --git a/kernel/events/core.c b/kernel/events/core.c index cfc227ccfceb..1087bbeb152b 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -3434,7 +3434,7 @@ find_lively_task_by_vpid(pid_t vpid) /* Reuse ptrace permission checks for now. */ err = -EACCES; - if (!ptrace_may_access(task, PTRACE_MODE_READ)) + if (!ptrace_may_access(task, PTRACE_MODE_READ_REALCREDS)) goto errout; return task; diff --git a/kernel/futex.c b/kernel/futex.c index 684d7549825a..495a1d06915b 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -2881,7 +2881,7 @@ SYSCALL_DEFINE3(get_robust_list, int, pid, } ret = -EPERM; - if (!ptrace_may_access(p, PTRACE_MODE_READ)) + if (!ptrace_may_access(p, PTRACE_MODE_READ_REALCREDS)) goto err_unlock; head = p->robust_list; diff --git a/kernel/futex_compat.c b/kernel/futex_compat.c index 55c8c9349cfe..4ae3232e7a28 100644 --- a/kernel/futex_compat.c +++ b/kernel/futex_compat.c @@ -155,7 +155,7 @@ COMPAT_SYSCALL_DEFINE3(get_robust_list, int, pid, } ret = -EPERM; - if (!ptrace_may_access(p, PTRACE_MODE_READ)) + if (!ptrace_may_access(p, PTRACE_MODE_READ_REALCREDS)) goto err_unlock; head = p->compat_robust_list; diff --git a/kernel/kcmp.c b/kernel/kcmp.c index 0aa69ea1d8fd..3a47fa998fe0 100644 --- a/kernel/kcmp.c +++ b/kernel/kcmp.c @@ -122,8 +122,8 @@ SYSCALL_DEFINE5(kcmp, pid_t, pid1, pid_t, pid2, int, type, &task2->signal->cred_guard_mutex); if (ret) goto err; - if (!ptrace_may_access(task1, PTRACE_MODE_READ) || - !ptrace_may_access(task2, PTRACE_MODE_READ)) { + if (!ptrace_may_access(task1, PTRACE_MODE_READ_REALCREDS) || + !ptrace_may_access(task2, PTRACE_MODE_READ_REALCREDS)) { ret = -EPERM; goto err_unlock; } diff --git a/kernel/ptrace.c b/kernel/ptrace.c index b760bae64cf1..3189e51db7e8 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -219,6 +219,14 @@ static int ptrace_has_cap(struct user_namespace *ns, unsigned int mode) static int __ptrace_may_access(struct task_struct *task, unsigned int mode) { const struct cred *cred = current_cred(), *tcred; + int dumpable = 0; + kuid_t caller_uid; + kgid_t caller_gid; + + if (!(mode & PTRACE_MODE_FSCREDS) == !(mode & PTRACE_MODE_REALCREDS)) { + WARN(1, "denying ptrace access check without PTRACE_MODE_*CREDS\n"); + return -EPERM; + } /* May we inspect the given task? * This check is used both for attaching with ptrace @@ -228,18 +236,33 @@ static int __ptrace_may_access(struct task_struct *task, unsigned int mode) * because setting up the necessary parent/child relationship * or halting the specified task is impossible. */ - int dumpable = 0; + /* Don't let security modules deny introspection */ if (same_thread_group(task, current)) return 0; rcu_read_lock(); + if (mode & PTRACE_MODE_FSCREDS) { + caller_uid = cred->fsuid; + caller_gid = cred->fsgid; + } else { + /* + * Using the euid would make more sense here, but something + * in userland might rely on the old behavior, and this + * shouldn't be a security problem since + * PTRACE_MODE_REALCREDS implies that the caller explicitly + * used a syscall that requests access to another process + * (and not a filesystem syscall to procfs). + */ + caller_uid = cred->uid; + caller_gid = cred->gid; + } tcred = __task_cred(task); - if (uid_eq(cred->uid, tcred->euid) && - uid_eq(cred->uid, tcred->suid) && - uid_eq(cred->uid, tcred->uid) && - gid_eq(cred->gid, tcred->egid) && - gid_eq(cred->gid, tcred->sgid) && - gid_eq(cred->gid, tcred->gid)) + if (uid_eq(caller_uid, tcred->euid) && + uid_eq(caller_uid, tcred->suid) && + uid_eq(caller_uid, tcred->uid) && + gid_eq(caller_gid, tcred->egid) && + gid_eq(caller_gid, tcred->sgid) && + gid_eq(caller_gid, tcred->gid)) goto ok; if (ptrace_has_cap(tcred->user_ns, mode)) goto ok; @@ -306,7 +329,7 @@ static int ptrace_attach(struct task_struct *task, long request, goto out; task_lock(task); - retval = __ptrace_may_access(task, PTRACE_MODE_ATTACH); + retval = __ptrace_may_access(task, PTRACE_MODE_ATTACH_REALCREDS); task_unlock(task); if (retval) goto unlock_creds; diff --git a/mm/process_vm_access.c b/mm/process_vm_access.c index e88d071648c2..5d453e58ddbf 100644 --- a/mm/process_vm_access.c +++ b/mm/process_vm_access.c @@ -194,7 +194,7 @@ static ssize_t process_vm_rw_core(pid_t pid, struct iov_iter *iter, goto free_proc_pages; } - mm = mm_access(task, PTRACE_MODE_ATTACH); + mm = mm_access(task, PTRACE_MODE_ATTACH_REALCREDS); if (!mm || IS_ERR(mm)) { rc = IS_ERR(mm) ? PTR_ERR(mm) : -ESRCH; /* diff --git a/security/commoncap.c b/security/commoncap.c index 1832cf701c3d..48071ed7c445 100644 --- a/security/commoncap.c +++ b/security/commoncap.c @@ -137,12 +137,17 @@ int cap_ptrace_access_check(struct task_struct *child, unsigned int mode) { int ret = 0; const struct cred *cred, *child_cred; + const kernel_cap_t *caller_caps; rcu_read_lock(); cred = current_cred(); child_cred = __task_cred(child); + if (mode & PTRACE_MODE_FSCREDS) + caller_caps = &cred->cap_effective; + else + caller_caps = &cred->cap_permitted; if (cred->user_ns == child_cred->user_ns && - cap_issubset(child_cred->cap_permitted, cred->cap_permitted)) + cap_issubset(child_cred->cap_permitted, *caller_caps)) goto out; if (ns_capable(child_cred->user_ns, CAP_SYS_PTRACE)) goto out; From 6e50ddaf0991285f6b6abb4d575f0cc0e8ed7834 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Mon, 16 Nov 2015 17:25:16 -0500 Subject: [PATCH 219/325] tools lib traceevent: Fix output of %llu for 64 bit values read on 32 bit machines commit 32abc2ede536aae52978d6c0a8944eb1df14f460 upstream. When a long value is read on 32 bit machines for 64 bit output, the parsing needs to change "%lu" into "%llu", as the value is read natively. Unfortunately, if "%llu" is already there, the code will add another "l" to it and fail to parse it properly. Signed-off-by: Steven Rostedt Acked-by: Namhyung Kim Link: http://lkml.kernel.org/r/20151116172516.4b79b109@gandalf.local.home Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Greg Kroah-Hartman --- tools/lib/traceevent/event-parse.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c index 2a912df6771b..68276f35e323 100644 --- a/tools/lib/traceevent/event-parse.c +++ b/tools/lib/traceevent/event-parse.c @@ -4968,13 +4968,12 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct event sizeof(long) != 8) { char *p; - ls = 2; /* make %l into %ll */ - p = strchr(format, 'l'); - if (p) + if (ls == 1 && (p = strchr(format, 'l'))) memmove(p+1, p, strlen(p)+1); else if (strcmp(format, "%p") == 0) strcpy(format, "0x%llx"); + ls = 2; } switch (ls) { case -2: From 6fa74f50e357b0d87fad34a4b7ccbc2beb42b859 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Tue, 26 Jan 2016 14:05:20 +0200 Subject: [PATCH 220/325] perf tools: tracepoint_error() can receive e=NULL, robustify it commit ec183d22cc284a7a1e17f0341219d8ec8ca070cc upstream. Fixes segmentation fault using, for instance: (gdb) run record -I -e intel_pt/tsc=1,noretcomp=1/u /bin/ls Starting program: /home/acme/bin/perf record -I -e intel_pt/tsc=1,noretcomp=1/u /bin/ls Missing separate debuginfos, use: dnf debuginfo-install glibc-2.22-7.fc23.x86_64 [Thread debugging using libthread_db enabled] Using host libthread_db library "/lib64/libthread_db.so.1". Program received signal SIGSEGV, Segmentation fault. 0 x00000000004b9ea5 in tracepoint_error (e=0x0, err=13, sys=0x19b1370 "sched", name=0x19a5d00 "sched_switch") at util/parse-events.c:410 (gdb) bt #0 0x00000000004b9ea5 in tracepoint_error (e=0x0, err=13, sys=0x19b1370 "sched", name=0x19a5d00 "sched_switch") at util/parse-events.c:410 #1 0x00000000004b9fc5 in add_tracepoint (list=0x19a5d20, idx=0x7fffffffb8c0, sys_name=0x19b1370 "sched", evt_name=0x19a5d00 "sched_switch", err=0x0, head_config=0x0) at util/parse-events.c:433 #2 0x00000000004ba334 in add_tracepoint_event (list=0x19a5d20, idx=0x7fffffffb8c0, sys_name=0x19b1370 "sched", evt_name=0x19a5d00 "sched_switch", err=0x0, head_config=0x0) at util/parse-events.c:498 #3 0x00000000004bb699 in parse_events_add_tracepoint (list=0x19a5d20, idx=0x7fffffffb8c0, sys=0x19b1370 "sched", event=0x19a5d00 "sched_switch", err=0x0, head_config=0x0) at util/parse-events.c:936 #4 0x00000000004f6eda in parse_events_parse (_data=0x7fffffffb8b0, scanner=0x19a49d0) at util/parse-events.y:391 #5 0x00000000004bc8e5 in parse_events__scanner (str=0x663ff2 "sched:sched_switch", data=0x7fffffffb8b0, start_token=258) at util/parse-events.c:1361 #6 0x00000000004bca57 in parse_events (evlist=0x19a5220, str=0x663ff2 "sched:sched_switch", err=0x0) at util/parse-events.c:1401 #7 0x0000000000518d5f in perf_evlist__can_select_event (evlist=0x19a3b90, str=0x663ff2 "sched:sched_switch") at util/record.c:253 #8 0x0000000000553c42 in intel_pt_track_switches (evlist=0x19a3b90) at arch/x86/util/intel-pt.c:364 #9 0x00000000005549d1 in intel_pt_recording_options (itr=0x19a2c40, evlist=0x19a3b90, opts=0x8edf68 ) at arch/x86/util/intel-pt.c:664 #10 0x000000000051e076 in auxtrace_record__options (itr=0x19a2c40, evlist=0x19a3b90, opts=0x8edf68 ) at util/auxtrace.c:539 #11 0x0000000000433368 in cmd_record (argc=1, argv=0x7fffffffde60, prefix=0x0) at builtin-record.c:1264 #12 0x000000000049bec2 in run_builtin (p=0x8fa2a8 , argc=5, argv=0x7fffffffde60) at perf.c:390 #13 0x000000000049c12a in handle_internal_command (argc=5, argv=0x7fffffffde60) at perf.c:451 #14 0x000000000049c278 in run_argv (argcp=0x7fffffffdcbc, argv=0x7fffffffdcb0) at perf.c:495 #15 0x000000000049c60a in main (argc=5, argv=0x7fffffffde60) at perf.c:618 (gdb) Intel PT attempts to find the sched:sched_switch tracepoint but that seg faults if tracefs is not readable, because the error reporting structure is null, as errors are not reported when automatically adding tracepoints. Fix by checking before using. Committer note: This doesn't take place in a kernel that supports perf_event_attr.context_switch, that is the default way that will be used for tracking context switches, only in older kernels, like 4.2, in a machine with Intel PT (e.g. Broadwell) for non-priviledged users. Further info from a similar patch by Wang: The error is in tracepoint_error: it assumes the 'e' parameter is valid. However, there are many situation a parse_event() can be called without parse_events_error. See result of $ grep 'parse_events(.*NULL)' ./tools/perf/ -r' Signed-off-by: Adrian Hunter Tested-by: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Josh Poimboeuf Cc: Tong Zhang Cc: Wang Nan Fixes: 196581717d85 ("perf tools: Enhance parsing events tracepoint error output") Link: http://lkml.kernel.org/r/1453809921-24596-2-git-send-email-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Greg Kroah-Hartman --- tools/perf/util/parse-events.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 6fc8cd753e1a..b48e87693aa5 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -399,6 +399,9 @@ static void tracepoint_error(struct parse_events_error *e, int err, { char help[BUFSIZ]; + if (!e) + return; + /* * We get error directly from syscall errno ( > 0), * or from encoded pointer's error ( < 0). From 2fa82bbbc73a7d8716e3f7aba6b2b5c84147a2fc Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 12 Feb 2016 22:26:42 +0100 Subject: [PATCH 221/325] tracing: Fix freak link error caused by branch tracer commit b33c8ff4431a343561e2319f17c14286f2aa52e2 upstream. In my randconfig tests, I came across a bug that involves several components: * gcc-4.9 through at least 5.3 * CONFIG_GCOV_PROFILE_ALL enabling -fprofile-arcs for all files * CONFIG_PROFILE_ALL_BRANCHES overriding every if() * The optimized implementation of do_div() that tries to replace a library call with an division by multiplication * code in drivers/media/dvb-frontends/zl10353.c doing u32 adc_clock = 450560; /* 45.056 MHz */ if (state->config.adc_clock) adc_clock = state->config.adc_clock; do_div(value, adc_clock); In this case, gcc fails to determine whether the divisor in do_div() is __builtin_constant_p(). In particular, it concludes that __builtin_constant_p(adc_clock) is false, while __builtin_constant_p(!!adc_clock) is true. That in turn throws off the logic in do_div() that also uses __builtin_constant_p(), and instead of picking either the constant- optimized division, and the code in ilog2() that uses __builtin_constant_p() to figure out whether it knows the answer at compile time. The result is a link error from failing to find multiple symbols that should never have been called based on the __builtin_constant_p(): dvb-frontends/zl10353.c:138: undefined reference to `____ilog2_NaN' dvb-frontends/zl10353.c:138: undefined reference to `__aeabi_uldivmod' ERROR: "____ilog2_NaN" [drivers/media/dvb-frontends/zl10353.ko] undefined! ERROR: "__aeabi_uldivmod" [drivers/media/dvb-frontends/zl10353.ko] undefined! This patch avoids the problem by changing __trace_if() to check whether the condition is known at compile-time to be nonzero, rather than checking whether it is actually a constant. I see this one link error in roughly one out of 1600 randconfig builds on ARM, and the patch fixes all known instances. Link: http://lkml.kernel.org/r/1455312410-1058841-1-git-send-email-arnd@arndb.de Acked-by: Nicolas Pitre Fixes: ab3c9c686e22 ("branch tracer, intel-iommu: fix build with CONFIG_BRANCH_TRACER=y") Signed-off-by: Arnd Bergmann Signed-off-by: Steven Rostedt Signed-off-by: Greg Kroah-Hartman --- include/linux/compiler.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 4dac1036594f..6fc9a6dd5ed2 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -144,7 +144,7 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect); */ #define if(cond, ...) __trace_if( (cond , ## __VA_ARGS__) ) #define __trace_if(cond) \ - if (__builtin_constant_p((cond)) ? !!(cond) : \ + if (__builtin_constant_p(!!(cond)) ? !!(cond) : \ ({ \ int ______r; \ static struct ftrace_branch_data \ From 152fb02241b60ffb8d406b87c68d1908478a205f Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Mon, 15 Feb 2016 12:36:14 -0500 Subject: [PATCH 222/325] tracepoints: Do not trace when cpu is offline commit f37755490fe9bf76f6ba1d8c6591745d3574a6a6 upstream. The tracepoint infrastructure uses RCU sched protection to enable and disable tracepoints safely. There are some instances where tracepoints are used in infrastructure code (like kfree()) that get called after a CPU is going offline, and perhaps when it is coming back online but hasn't been registered yet. This can probuce the following warning: [ INFO: suspicious RCU usage. ] 4.4.0-00006-g0fe53e8-dirty #34 Tainted: G S ------------------------------- include/trace/events/kmem.h:141 suspicious rcu_dereference_check() usage! other info that might help us debug this: RCU used illegally from offline CPU! rcu_scheduler_active = 1, debug_locks = 1 no locks held by swapper/8/0. stack backtrace: CPU: 8 PID: 0 Comm: swapper/8 Tainted: G S 4.4.0-00006-g0fe53e8-dirty #34 Call Trace: [c0000005b76c78d0] [c0000000008b9540] .dump_stack+0x98/0xd4 (unreliable) [c0000005b76c7950] [c00000000010c898] .lockdep_rcu_suspicious+0x108/0x170 [c0000005b76c79e0] [c00000000029adc0] .kfree+0x390/0x440 [c0000005b76c7a80] [c000000000055f74] .destroy_context+0x44/0x100 [c0000005b76c7b00] [c0000000000934a0] .__mmdrop+0x60/0x150 [c0000005b76c7b90] [c0000000000e3ff0] .idle_task_exit+0x130/0x140 [c0000005b76c7c20] [c000000000075804] .pseries_mach_cpu_die+0x64/0x310 [c0000005b76c7cd0] [c000000000043e7c] .cpu_die+0x3c/0x60 [c0000005b76c7d40] [c0000000000188d8] .arch_cpu_idle_dead+0x28/0x40 [c0000005b76c7db0] [c000000000101e6c] .cpu_startup_entry+0x50c/0x560 [c0000005b76c7ed0] [c000000000043bd8] .start_secondary+0x328/0x360 [c0000005b76c7f90] [c000000000008a6c] start_secondary_prolog+0x10/0x14 This warning is not a false positive either. RCU is not protecting code that is being executed while the CPU is offline. Instead of playing "whack-a-mole(TM)" and adding conditional statements to the tracepoints we find that are used in this instance, simply add a cpu_online() test to the tracepoint code where the tracepoint will be ignored if the CPU is offline. Use of raw_smp_processor_id() is fine, as there should never be a case where the tracepoint code goes from running on a CPU that is online and suddenly gets migrated to a CPU that is offline. Link: http://lkml.kernel.org/r/1455387773-4245-1-git-send-email-kda@linux-powerpc.org Reported-by: Denis Kirjanov Fixes: 97e1c18e8d17b ("tracing: Kernel Tracepoints") Signed-off-by: Steven Rostedt Signed-off-by: Greg Kroah-Hartman --- include/linux/tracepoint.h | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index 696a339c592c..03c7efb60c91 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -14,8 +14,10 @@ * See the file COPYING for more details. */ +#include #include #include +#include #include #include @@ -146,6 +148,9 @@ extern void syscall_unregfunc(void); void *it_func; \ void *__data; \ \ + if (!cpu_online(raw_smp_processor_id())) \ + return; \ + \ if (!(cond)) \ return; \ prercu; \ From 5b27adfac012bd383de3e950e2c8c431da9ebfd5 Mon Sep 17 00:00:00 2001 From: James Bottomley Date: Wed, 13 Jan 2016 08:10:31 -0800 Subject: [PATCH 223/325] klist: fix starting point removed bug in klist iterators commit 00cd29b799e3449f0c68b1cc77cd4a5f95b42d17 upstream. The starting node for a klist iteration is often passed in from somewhere way above the klist infrastructure, meaning there's no guarantee the node is still on the list. We've seen this in SCSI where we use bus_find_device() to iterate through a list of devices. In the face of heavy hotplug activity, the last device returned by bus_find_device() can be removed before the next call. This leads to Dec 3 13:22:02 localhost kernel: WARNING: CPU: 2 PID: 28073 at include/linux/kref.h:47 klist_iter_init_node+0x3d/0x50() Dec 3 13:22:02 localhost kernel: Modules linked in: scsi_debug x86_pkg_temp_thermal kvm_intel kvm irqbypass crc32c_intel joydev iTCO_wdt dcdbas ipmi_devintf acpi_power_meter iTCO_vendor_support ipmi_si imsghandler pcspkr wmi acpi_cpufreq tpm_tis tpm shpchp lpc_ich mfd_core nfsd nfs_acl lockd grace sunrpc tg3 ptp pps_core Dec 3 13:22:02 localhost kernel: CPU: 2 PID: 28073 Comm: cat Not tainted 4.4.0-rc1+ #2 Dec 3 13:22:02 localhost kernel: Hardware name: Dell Inc. PowerEdge R320/08VT7V, BIOS 2.0.22 11/19/2013 Dec 3 13:22:02 localhost kernel: ffffffff81a20e77 ffff880613acfd18 ffffffff81321eef 0000000000000000 Dec 3 13:22:02 localhost kernel: ffff880613acfd50 ffffffff8107ca52 ffff88061176b198 0000000000000000 Dec 3 13:22:02 localhost kernel: ffffffff814542b0 ffff880610cfb100 ffff88061176b198 ffff880613acfd60 Dec 3 13:22:02 localhost kernel: Call Trace: Dec 3 13:22:02 localhost kernel: [] dump_stack+0x44/0x55 Dec 3 13:22:02 localhost kernel: [] warn_slowpath_common+0x82/0xc0 Dec 3 13:22:02 localhost kernel: [] ? proc_scsi_show+0x20/0x20 Dec 3 13:22:02 localhost kernel: [] warn_slowpath_null+0x1a/0x20 Dec 3 13:22:02 localhost kernel: [] klist_iter_init_node+0x3d/0x50 Dec 3 13:22:02 localhost kernel: [] bus_find_device+0x51/0xb0 Dec 3 13:22:02 localhost kernel: [] scsi_seq_next+0x2d/0x40 [...] And an eventual crash. It can actually occur in any hotplug system which has a device finder and a starting device. We can fix this globally by making sure the starting node for klist_iter_init_node() is actually a member of the list before using it (and by starting from the beginning if it isn't). Reported-by: Ewan D. Milne Tested-by: Ewan D. Milne Signed-off-by: James Bottomley Signed-off-by: Greg Kroah-Hartman --- lib/klist.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/lib/klist.c b/lib/klist.c index d74cf7a29afd..0507fa5d84c5 100644 --- a/lib/klist.c +++ b/lib/klist.c @@ -282,9 +282,9 @@ void klist_iter_init_node(struct klist *k, struct klist_iter *i, struct klist_node *n) { i->i_klist = k; - i->i_cur = n; - if (n) - kref_get(&n->n_ref); + i->i_cur = NULL; + if (n && kref_get_unless_zero(&n->n_ref)) + i->i_cur = n; } EXPORT_SYMBOL_GPL(klist_iter_init_node); From 954bb20f70ed1ab93406c6e01e1cd54d866c977e Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Thu, 7 Jan 2016 16:34:05 -0600 Subject: [PATCH 224/325] scsi: add Synology to 1024 sector blacklist commit 9055082fb100cc66e20c048251d05159f5f2cfba upstream. Another iscsi target that cannot handle large IOs, but does not tell us a limit. The Synology iSCSI targets report: Block limits VPD page (SBC): Write same no zero (WSNZ): 0 Maximum compare and write length: 0 blocks Optimal transfer length granularity: 0 blocks Maximum transfer length: 0 blocks Optimal transfer length: 0 blocks Maximum prefetch length: 0 blocks Maximum unmap LBA count: 0 Maximum unmap block descriptor count: 0 Optimal unmap granularity: 0 Unmap granularity alignment valid: 0 Unmap granularity alignment: 0 Maximum write same length: 0x0 blocks and the size of the command it can handle seems to depend on how much memory it can allocate at the time. This results in IO errors when handling large IOs. This patch just has us use the old 1024 default sectors for this target by adding it to the scsi blacklist. We do not have good contacs with this vendors, so I have not been able to try and fix on their side. I have posted this a long while back, but it was not merged. This version just fixes it up for merge/patch failures in the original version. Reported-by: Ancoron Luciferis Reported-by: Michael Meyers Signed-off-by: Mike Christie Signed-off-by: Martin K. Petersen Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/scsi_devinfo.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/scsi/scsi_devinfo.c b/drivers/scsi/scsi_devinfo.c index 2c1160c7ec92..47b9d13f97b8 100644 --- a/drivers/scsi/scsi_devinfo.c +++ b/drivers/scsi/scsi_devinfo.c @@ -227,6 +227,7 @@ static struct { {"Promise", "VTrak E610f", NULL, BLIST_SPARSELUN | BLIST_NO_RSOC}, {"Promise", "", NULL, BLIST_SPARSELUN}, {"QNAP", "iSCSI Storage", NULL, BLIST_MAX_1024}, + {"SYNOLOGY", "iSCSI Storage", NULL, BLIST_MAX_1024}, {"QUANTUM", "XP34301", "1071", BLIST_NOTQ}, {"REGAL", "CDC-4X", NULL, BLIST_MAX5LUN | BLIST_SINGLELUN}, {"SanDisk", "ImageMate CF-SD1", NULL, BLIST_FORCELUN}, From dcec7af70910c48cba1e7b42383b9696356afc33 Mon Sep 17 00:00:00 2001 From: Nicholas Bellinger Date: Tue, 19 Jan 2016 16:15:27 -0800 Subject: [PATCH 225/325] iscsi-target: Fix potential dead-lock during node acl delete commit 26a99c19f810b2593410899a5b304b21b47428a6 upstream. This patch is a iscsi-target specific bug-fix for a dead-lock that can occur during explicit struct se_node_acl->acl_group se_session deletion via configfs rmdir(2), when iscsi-target time2retain timer is still active. It changes iscsi-target to obtain se_portal_group->session_lock internally using spin_in_locked() to check for the specific se_node_acl configfs shutdown rmdir(2) case. Note this patch is intended for stable, and the subsequent v4.5-rc patch converts target_core_tpg.c to use proper se_sess->sess_kref reference counting for both se_node_acl deletion + se_node_acl->queue_depth se_session restart. Reported-by:: Sagi Grimberg Cc: Christoph Hellwig Cc: Hannes Reinecke Cc: Andy Grover Cc: Mike Christie Signed-off-by: Nicholas Bellinger Signed-off-by: Greg Kroah-Hartman --- drivers/target/iscsi/iscsi_target_configfs.c | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) diff --git a/drivers/target/iscsi/iscsi_target_configfs.c b/drivers/target/iscsi/iscsi_target_configfs.c index 255204cc43e6..b4bfd706ac94 100644 --- a/drivers/target/iscsi/iscsi_target_configfs.c +++ b/drivers/target/iscsi/iscsi_target_configfs.c @@ -1593,7 +1593,8 @@ static int lio_tpg_check_prot_fabric_only( } /* - * Called with spin_lock_bh(struct se_portal_group->session_lock) held.. + * Called with spin_lock_irq(struct se_portal_group->session_lock) held + * or not held. * * Also, this function calls iscsit_inc_session_usage_count() on the * struct iscsi_session in question. @@ -1601,19 +1602,32 @@ static int lio_tpg_check_prot_fabric_only( static int lio_tpg_shutdown_session(struct se_session *se_sess) { struct iscsi_session *sess = se_sess->fabric_sess_ptr; + struct se_portal_group *se_tpg = se_sess->se_tpg; + bool local_lock = false; + + if (!spin_is_locked(&se_tpg->session_lock)) { + spin_lock_irq(&se_tpg->session_lock); + local_lock = true; + } spin_lock(&sess->conn_lock); if (atomic_read(&sess->session_fall_back_to_erl0) || atomic_read(&sess->session_logout) || (sess->time2retain_timer_flags & ISCSI_TF_EXPIRED)) { spin_unlock(&sess->conn_lock); + if (local_lock) + spin_unlock_irq(&sess->conn_lock); return 0; } atomic_set(&sess->session_reinstatement, 1); spin_unlock(&sess->conn_lock); iscsit_stop_time2retain_timer(sess); + spin_unlock_irq(&se_tpg->session_lock); + iscsit_stop_session(sess, 1, 1); + if (!local_lock) + spin_lock_irq(&se_tpg->session_lock); return 1; } From d763177d00d72af0efc0f13745b8c26c832845bf Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Wed, 20 Jan 2016 11:26:01 -0500 Subject: [PATCH 226/325] SCSI: fix crashes in sd and sr runtime PM commit 13b4389143413a1f18127c07f72c74cad5b563e8 upstream. Runtime suspend during driver probe and removal can cause problems. The driver's runtime_suspend or runtime_resume callbacks may invoked before the driver has finished binding to the device or after the driver has unbound from the device. This problem shows up with the sd and sr drivers, and can cause disk or CD/DVD drives to become unusable as a result. The fix is simple. The drivers store a pointer to the scsi_disk or scsi_cd structure as their private device data when probing is finished, so we simply have to be sure to clear the private data during removal and test it during runtime suspend/resume. This fixes . Signed-off-by: Alan Stern Reported-by: Paul Menzel Reported-by: Erich Schubert Reported-by: Alexandre Rossi Tested-by: Paul Menzel Tested-by: Erich Schubert Signed-off-by: James Bottomley Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/sd.c | 7 +++++-- drivers/scsi/sr.c | 4 ++++ 2 files changed, 9 insertions(+), 2 deletions(-) diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 4e08d1cd704d..84fa4c46eaa6 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -3268,8 +3268,8 @@ static int sd_suspend_common(struct device *dev, bool ignore_stop_errors) struct scsi_disk *sdkp = dev_get_drvdata(dev); int ret = 0; - if (!sdkp) - return 0; /* this can happen */ + if (!sdkp) /* E.g.: runtime suspend following sd_remove() */ + return 0; if (sdkp->WCE && sdkp->media_present) { sd_printk(KERN_NOTICE, sdkp, "Synchronizing SCSI cache\n"); @@ -3308,6 +3308,9 @@ static int sd_resume(struct device *dev) { struct scsi_disk *sdkp = dev_get_drvdata(dev); + if (!sdkp) /* E.g.: runtime resume at the start of sd_probe() */ + return 0; + if (!sdkp->device->manage_start_stop) return 0; diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c index 8bd54a64efd6..64c867405ad4 100644 --- a/drivers/scsi/sr.c +++ b/drivers/scsi/sr.c @@ -144,6 +144,9 @@ static int sr_runtime_suspend(struct device *dev) { struct scsi_cd *cd = dev_get_drvdata(dev); + if (!cd) /* E.g.: runtime suspend following sr_remove() */ + return 0; + if (cd->media_present) return -EBUSY; else @@ -985,6 +988,7 @@ static int sr_remove(struct device *dev) scsi_autopm_get_device(cd->device); del_gendisk(cd->disk); + dev_set_drvdata(dev, NULL); mutex_lock(&sr_ref_mutex); kref_put(&cd->kref, sr_kref_release); From 4c654fc9357b70803c1878ec729ef61a8be0af52 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Tue, 2 Feb 2016 16:57:35 -0800 Subject: [PATCH 227/325] drivers/scsi/sg.c: mark VMA as VM_IO to prevent migration commit 461c7fa126794157484dca48e88effa4963e3af3 upstream. Reduced testcase: #include #include #include #include #define SIZE 0x2000 int main() { int fd; void *p; fd = open("/dev/sg0", O_RDWR); p = mmap(NULL, SIZE, PROT_EXEC, MAP_PRIVATE | MAP_LOCKED, fd, 0); mbind(p, SIZE, 0, NULL, 0, MPOL_MF_MOVE); return 0; } We shouldn't try to migrate pages in sg VMA as we don't have a way to update Sg_scatter_hold::pages accordingly from mm core. Let's mark the VMA as VM_IO to indicate to mm core that the VMA is not migratable. Signed-off-by: Kirill A. Shutemov Reported-by: Dmitry Vyukov Acked-by: Vlastimil Babka Cc: Doug Gilbert Cc: David Rientjes Cc: Naoya Horiguchi Cc: "Kirill A. Shutemov" Cc: Shiraz Hashim Cc: Hugh Dickins Cc: Sasha Levin Cc: syzkaller Cc: Kostya Serebryany Cc: Alexander Potapenko Cc: James Bottomley Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/sg.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index 503ab8b46c0b..5e820674432c 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -1261,7 +1261,7 @@ sg_mmap(struct file *filp, struct vm_area_struct *vma) } sfp->mmap_called = 1; - vma->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP; + vma->vm_flags |= VM_IO | VM_DONTEXPAND | VM_DONTDUMP; vma->vm_private_data = sfp; vma->vm_ops = &sg_mmap_vm_ops; return 0; From 32c55052aa3364bd4a0d0c2b5f53ed9b95ae8d05 Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Fri, 22 Jan 2016 15:42:41 +0100 Subject: [PATCH 228/325] scsi_dh_rdac: always retry MODE SELECT on command lock violation commit d2d06d4fe0f2cc2df9b17fefec96e6e1a1271d91 upstream. If MODE SELECT returns with sense '05/91/36' (command lock violation) it should always be retried without counting the number of retries. During an HBA upgrade or similar circumstances one might see a flood of MODE SELECT command from various HBAs, which will easily trigger the sense code and exceed the retry count. Signed-off-by: Hannes Reinecke Reviewed-by: Johannes Thumshirn Signed-off-by: Martin K. Petersen Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/device_handler/scsi_dh_rdac.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/scsi/device_handler/scsi_dh_rdac.c b/drivers/scsi/device_handler/scsi_dh_rdac.c index 361358134315..93880ed6291c 100644 --- a/drivers/scsi/device_handler/scsi_dh_rdac.c +++ b/drivers/scsi/device_handler/scsi_dh_rdac.c @@ -562,7 +562,7 @@ static int mode_select_handle_sense(struct scsi_device *sdev, /* * Command Lock contention */ - err = SCSI_DH_RETRY; + err = SCSI_DH_IMM_RETRY; break; default: break; @@ -612,6 +612,8 @@ retry: err = mode_select_handle_sense(sdev, h->sense); if (err == SCSI_DH_RETRY && retry_cnt--) goto retry; + if (err == SCSI_DH_IMM_RETRY) + goto retry; } if (err == SCSI_DH_OK) { h->state = RDAC_STATE_ACTIVE; From 900ae746c1e954c5dd2b926d9e30863c9852396c Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Wed, 27 Jan 2016 16:19:13 +0200 Subject: [PATCH 229/325] SCSI: Add Marvell Console to VPD blacklist commit 82c43310508eb19eb41fe7862e89afeb74030b84 upstream. I have a Marvell 88SE9230 SATA Controller that has some sort of integrated console SCSI device attached to one of the ports. ata14: SATA link up 1.5 Gbps (SStatus 113 SControl 300) ata14.00: ATAPI: MARVELL VIRTUALL, 1.09, max UDMA/66 ata14.00: configured for UDMA/66 scsi 13:0:0:0: Processor Marvell Console 1.01 PQ: 0 ANSI: 5 Sending it VPD INQUIRY command seem to always fail with following error: ata14.00: exception Emask 0x0 SAct 0x0 SErr 0x0 action 0x6 ata14.00: irq_stat 0x40000001 ata14.00: cmd a0/01:00:00:00:01/00:00:00:00:00/a0 tag 2 dma 16640 in Inquiry 12 01 00 00 ff 00res 00/00:00:00:00:00/00:00:00:00:00/00 Emask 0x3 (HSM violation) ata14: hard resetting link This has been minor annoyance (only error printed on dmesg) until commit 09e2b0b14690 ("scsi: rescan VPD attributes") added call to scsi_attach_vpd() in scsi_rescan_device(). The commit causes the system to splat out following errors continuously without ever reaching the UI: ata14.00: configured for UDMA/66 ata14: EH complete ata14.00: exception Emask 0x0 SAct 0x0 SErr 0x0 action 0x6 ata14.00: irq_stat 0x40000001 ata14.00: cmd a0/01:00:00:00:01/00:00:00:00:00/a0 tag 6 dma 16640 in Inquiry 12 01 00 00 ff 00res 00/00:00:00:00:00/00:00:00:00:00/00 Emask 0x3 (HSM violation) ata14: hard resetting link ata14: SATA link up 1.5 Gbps (SStatus 113 SControl 300) ata14.00: configured for UDMA/66 ata14: EH complete ata14.00: exception Emask 0x0 SAct 0x0 SErr 0x0 action 0x6 ata14.00: irq_stat 0x40000001 ata14.00: cmd a0/01:00:00:00:01/00:00:00:00:00/a0 tag 7 dma 16640 in Inquiry 12 01 00 00 ff 00res 00/00:00:00:00:00/00:00:00:00:00/00 Emask 0x3 (HSM violation) Without in-depth understanding of SCSI layer and the Marvell controller, I suspect this happens because when the link goes down (because of an error) we schedule scsi_rescan_device() which again fails to read VPD data... ad infinitum. Since VPD data cannot be read from the device anyway we prevent the SCSI layer from even trying by blacklisting the device. This gets away the error and the system starts up normally. [mkp: Widened the match to all revisions of this device] Signed-off-by: Mika Westerberg Reported-by: Kirill A. Shutemov Reported-by: Alexander Duyck Signed-off-by: Martin K. Petersen Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/scsi_devinfo.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/scsi/scsi_devinfo.c b/drivers/scsi/scsi_devinfo.c index 47b9d13f97b8..da2e068ee47d 100644 --- a/drivers/scsi/scsi_devinfo.c +++ b/drivers/scsi/scsi_devinfo.c @@ -205,6 +205,7 @@ static struct { {"Intel", "Multi-Flex", NULL, BLIST_NO_RSOC}, {"iRiver", "iFP Mass Driver", NULL, BLIST_NOT_LOCKABLE | BLIST_INQUIRY_36}, {"LASOUND", "CDX7405", "3.10", BLIST_MAX5LUN | BLIST_SINGLELUN}, + {"Marvell", "Console", NULL, BLIST_SKIP_VPD_PAGES}, {"MATSHITA", "PD-1", NULL, BLIST_FORCELUN | BLIST_SINGLELUN}, {"MATSHITA", "DMC-LC5", NULL, BLIST_NOT_LOCKABLE | BLIST_INQUIRY_36}, {"MATSHITA", "DMC-LC40", NULL, BLIST_NOT_LOCKABLE | BLIST_INQUIRY_36}, From a258a959fcf31230ae660f5b0a537b8d7fc0b675 Mon Sep 17 00:00:00 2001 From: James Bottomley Date: Wed, 10 Feb 2016 08:03:26 -0800 Subject: [PATCH 230/325] scsi: fix soft lockup in scsi_remove_target() on module removal commit 90a88d6ef88edcfc4f644dddc7eef4ea41bccf8b upstream. This softlockup is currently happening: [ 444.088002] NMI watchdog: BUG: soft lockup - CPU#1 stuck for 22s! [kworker/1:1:29] [ 444.088002] Modules linked in: lpfc(-) qla2x00tgt(O) qla2xxx_scst(O) scst_vdisk(O) scsi_transport_fc libcrc32c scst(O) dlm configfs nfsd lockd grace nfs_acl auth_rpcgss sunrpc ed d snd_pcm_oss snd_mixer_oss snd_seq snd_seq_device dm_mod iTCO_wdt snd_hda_codec_realtek snd_hda_codec_generic gpio_ich iTCO_vendor_support ppdev snd_hda_intel snd_hda_codec snd_hda _core snd_hwdep tg3 snd_pcm snd_timer libphy lpc_ich parport_pc ptp acpi_cpufreq snd pps_core fjes parport i2c_i801 ehci_pci tpm_tis tpm sr_mod cdrom soundcore floppy hwmon sg 8250_ fintek pcspkr i915 drm_kms_helper uhci_hcd ehci_hcd drm fb_sys_fops sysimgblt sysfillrect syscopyarea i2c_algo_bit usbcore button video usb_common fan ata_generic ata_piix libata th ermal [ 444.088002] CPU: 1 PID: 29 Comm: kworker/1:1 Tainted: G O 4.4.0-rc5-2.g1e923a3-default #1 [ 444.088002] Hardware name: FUJITSU SIEMENS ESPRIMO E /D2164-A1, BIOS 5.00 R1.10.2164.A1 05/08/2006 [ 444.088002] Workqueue: fc_wq_4 fc_rport_final_delete [scsi_transport_fc] [ 444.088002] task: f6266ec0 ti: f6268000 task.ti: f6268000 [ 444.088002] EIP: 0060:[] EFLAGS: 00000286 CPU: 1 [ 444.088002] EIP is at _raw_spin_unlock_irqrestore+0x14/0x20 [ 444.088002] EAX: 00000286 EBX: f20d3800 ECX: 00000002 EDX: 00000286 [ 444.088002] ESI: f50ba800 EDI: f2146848 EBP: f6269ec8 ESP: f6269ec8 [ 444.088002] DS: 007b ES: 007b FS: 00d8 GS: 00e0 SS: 0068 [ 444.088002] CR0: 8005003b CR2: 08f96600 CR3: 363ae000 CR4: 000006d0 [ 444.088002] Stack: [ 444.088002] f6269eec c066b0f7 00000286 f2146848 f50ba808 f50ba800 f50ba800 f2146a90 [ 444.088002] f2146848 f6269f08 f8f0a4ed f3141000 f2146800 f2146a90 f619fa00 00000040 [ 444.088002] f6269f40 c026cb25 00000001 166c6392 00000061 f6757140 f6136340 00000004 [ 444.088002] Call Trace: [ 444.088002] [] scsi_remove_target+0x167/0x1c0 [ 444.088002] [] fc_rport_final_delete+0x9d/0x1e0 [scsi_transport_fc] [ 444.088002] [] process_one_work+0x155/0x3e0 [ 444.088002] [] worker_thread+0x37/0x490 [ 444.088002] [] kthread+0x9b/0xb0 [ 444.088002] [] ret_from_kernel_thread+0x21/0x40 What appears to be happening is that something has pinned the target so it can't go into STARGET_DEL via final release and the loop in scsi_remove_target spins endlessly until that happens. The fix for this soft lockup is to not keep looping over a device that we've called remove on but which hasn't gone into DEL state. This patch will retain a simplistic memory of the last target and not keep looping over it. Reported-by: Sebastian Herbszt Tested-by: Sebastian Herbszt Fixes: 40998193560dab6c3ce8d25f4fa58a23e252ef38 Signed-off-by: James Bottomley Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/scsi_sysfs.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c index 21930c9ac9cd..c8115b4fe474 100644 --- a/drivers/scsi/scsi_sysfs.c +++ b/drivers/scsi/scsi_sysfs.c @@ -1192,16 +1192,18 @@ static void __scsi_remove_target(struct scsi_target *starget) void scsi_remove_target(struct device *dev) { struct Scsi_Host *shost = dev_to_shost(dev->parent); - struct scsi_target *starget; + struct scsi_target *starget, *last_target = NULL; unsigned long flags; restart: spin_lock_irqsave(shost->host_lock, flags); list_for_each_entry(starget, &shost->__targets, siblings) { - if (starget->state == STARGET_DEL) + if (starget->state == STARGET_DEL || + starget == last_target) continue; if (starget->dev.parent == dev || &starget->dev == dev) { kref_get(&starget->reap_ref); + last_target = starget; spin_unlock_irqrestore(shost->host_lock, flags); __scsi_remove_target(starget); scsi_target_reap(starget); From dc275a6eb9d0ebe7711d8ced07509dc5168163b3 Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Fri, 27 Nov 2015 14:55:56 +0100 Subject: [PATCH 231/325] iio: adis_buffer: Fix out-of-bounds memory access commit d590faf9e8f8509a0a0aa79c38e87fcc6b913248 upstream. The SPI tx and rx buffers are both supposed to be scan_bytes amount of bytes large and a common allocation is used to allocate both buffers. This puts the beginning of the tx buffer scan_bytes bytes after the rx buffer. The initialization of the tx buffer pointer is done adding scan_bytes to the beginning of the rx buffer, but since the rx buffer is of type __be16 this will actually add two times as much and the tx buffer ends up pointing after the allocated buffer. Fix this by using scan_count, which is scan_bytes / 2, instead of scan_bytes when initializing the tx buffer pointer. Fixes: aacff892cbd5 ("staging:iio:adis: Preallocate transfer message") Signed-off-by: Lars-Peter Clausen Signed-off-by: Jonathan Cameron Signed-off-by: Greg Kroah-Hartman --- drivers/iio/imu/adis_buffer.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iio/imu/adis_buffer.c b/drivers/iio/imu/adis_buffer.c index cb32b593f1c5..36607d52fee0 100644 --- a/drivers/iio/imu/adis_buffer.c +++ b/drivers/iio/imu/adis_buffer.c @@ -43,7 +43,7 @@ int adis_update_scan_mode(struct iio_dev *indio_dev, return -ENOMEM; rx = adis->buffer; - tx = rx + indio_dev->scan_bytes; + tx = rx + scan_count; spi_message_init(&adis->msg); From e9b0f0e411d00b900a72891435c8997fb8eeb32b Mon Sep 17 00:00:00 2001 From: Jonathan Cameron Date: Fri, 1 Jan 2016 18:05:34 +0000 Subject: [PATCH 232/325] iio:adc:ti_am335x_adc Fix buffered mode by identifying as software buffer. commit 9d0be85d4e2cfa2519ae16efe7ff4a7150c43c0b upstream. Whilst this part has a hardware buffer, the identifcation that IIO cares about is the userspace facing end. It this case we push individual elements from the hardware fifo into the software interface (specifically a kfifo) rather than providing direct reads through to a hardware buffer (as we still do in the sca3000 for example). Technically the original specification as a hardware buffer could be considered wrong, but it didn't matter until the patch listed below. Result is that any attempt to enable the buffer will return -EINVAL Fixes: 225d59adf1c8 ("iio: Specify supported modes for buffers") Signed-off-by: Jonathan Cameron Signed-off-by: Greg Kroah-Hartman --- drivers/iio/adc/ti_am335x_adc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iio/adc/ti_am335x_adc.c b/drivers/iio/adc/ti_am335x_adc.c index 942320e32753..c1e05532d437 100644 --- a/drivers/iio/adc/ti_am335x_adc.c +++ b/drivers/iio/adc/ti_am335x_adc.c @@ -289,7 +289,7 @@ static int tiadc_iio_buffered_hardware_setup(struct iio_dev *indio_dev, goto error_kfifo_free; indio_dev->setup_ops = setup_ops; - indio_dev->modes |= INDIO_BUFFER_HARDWARE; + indio_dev->modes |= INDIO_BUFFER_SOFTWARE; return 0; From f865d8c326dd50649d3ee3129b93e6abb6929fae Mon Sep 17 00:00:00 2001 From: Markus Elfring Date: Sat, 19 Dec 2015 14:14:54 +0100 Subject: [PATCH 233/325] iio-light: Use a signed return type for ltr501_match_samp_freq() commit c08ae18560aaed50fed306a2e11f36ce70130f65 upstream. The return type "unsigned int" was used by the ltr501_match_samp_freq() function despite of the aspect that it will eventually return a negative error code. Improve this implementation detail by deletion of the type modifier then. This issue was detected by using the Coccinelle software. Signed-off-by: Markus Elfring Acked-by: Peter Meerwald-Stadler Signed-off-by: Jonathan Cameron Signed-off-by: Greg Kroah-Hartman --- drivers/iio/light/ltr501.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iio/light/ltr501.c b/drivers/iio/light/ltr501.c index 809a961b9a7f..6bf89d8f3741 100644 --- a/drivers/iio/light/ltr501.c +++ b/drivers/iio/light/ltr501.c @@ -180,7 +180,7 @@ static const struct ltr501_samp_table ltr501_ps_samp_table[] = { {500000, 2000000} }; -static unsigned int ltr501_match_samp_freq(const struct ltr501_samp_table *tab, +static int ltr501_match_samp_freq(const struct ltr501_samp_table *tab, int len, int val, int val2) { int i, freq; From dfa6e741d472a464ee85dc2e0a44176a1496f832 Mon Sep 17 00:00:00 2001 From: Vegard Nossum Date: Sat, 2 Jan 2016 14:04:40 +0100 Subject: [PATCH 234/325] iio: add HAS_IOMEM dependency to VF610_ADC commit 005ce0713006a76d2b0c924ce0e2629e5d8510c3 upstream. Ran into this on UML: drivers/built-in.o: In function `vf610_adc_probe': drivers/iio/adc/vf610_adc.c:744: undefined reference to `devm_ioremap_resource' devm_ioremap_resource() is defined only when HAS_IOMEM is selected. Signed-off-by: Vegard Nossum Signed-off-by: Jonathan Cameron Signed-off-by: Greg Kroah-Hartman --- drivers/iio/adc/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/iio/adc/Kconfig b/drivers/iio/adc/Kconfig index 7868c744fd4b..1e7aded53117 100644 --- a/drivers/iio/adc/Kconfig +++ b/drivers/iio/adc/Kconfig @@ -372,6 +372,7 @@ config TWL6030_GPADC config VF610_ADC tristate "Freescale vf610 ADC driver" depends on OF + depends on HAS_IOMEM select IIO_BUFFER select IIO_TRIGGERED_BUFFER help From 1c1d4f2d76293cdcef7f77f7b92863c4bf3479d9 Mon Sep 17 00:00:00 2001 From: Vegard Nossum Date: Sat, 2 Jan 2016 14:04:39 +0100 Subject: [PATCH 235/325] iio: add IIO_TRIGGER dependency to STK8BA50 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 01cc5235604d61018712c11a14d74230f6a38bf4 upstream. Ran into this on UML: drivers/iio/accel/stk8ba50.c: In function ‘stk8ba50_data_rdy_trigger_set_state’: drivers/iio/accel/stk8ba50.c:163:9: error: implicit declaration of function ‘iio_trigger_get_drvdata’ [-Werror=implicit-function-declaration] iio_trigger_get_drvdata() is defined only when IIO_TRIGGER is selected. Signed-off-by: Vegard Nossum Signed-off-by: Jonathan Cameron Signed-off-by: Greg Kroah-Hartman --- drivers/iio/accel/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/iio/accel/Kconfig b/drivers/iio/accel/Kconfig index 969428dd6329..16cc5c691a55 100644 --- a/drivers/iio/accel/Kconfig +++ b/drivers/iio/accel/Kconfig @@ -173,6 +173,7 @@ config STK8312 config STK8BA50 tristate "Sensortek STK8BA50 3-Axis Accelerometer Driver" depends on I2C + depends on IIO_TRIGGER help Say yes here to get support for the Sensortek STK8BA50 3-axis accelerometer. From 377d1f59388fb7711b977458be7cb432f8dbbf9b Mon Sep 17 00:00:00 2001 From: Yong Li Date: Wed, 6 Jan 2016 09:09:43 +0800 Subject: [PATCH 236/325] iio: dac: mcp4725: set iio name property in sysfs commit 97a249e98a72d6b79fb7350a8dd56b147e9d5bdb upstream. Without this change, the name entity for mcp4725 is missing in /sys/bus/iio/devices/iio\:device*/name With this change, name is reported correctly Signed-off-by: Yong Li Signed-off-by: Jonathan Cameron Signed-off-by: Greg Kroah-Hartman --- drivers/iio/dac/mcp4725.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/iio/dac/mcp4725.c b/drivers/iio/dac/mcp4725.c index 43d14588448d..b4dde8315210 100644 --- a/drivers/iio/dac/mcp4725.c +++ b/drivers/iio/dac/mcp4725.c @@ -300,6 +300,7 @@ static int mcp4725_probe(struct i2c_client *client, data->client = client; indio_dev->dev.parent = &client->dev; + indio_dev->name = id->name; indio_dev->info = &mcp4725_info; indio_dev->channels = &mcp4725_channel; indio_dev->num_channels = 1; From 909e9c55196df318c7f3096826c8dc307cc2fd4b Mon Sep 17 00:00:00 2001 From: Gabriele Mazzotta Date: Tue, 12 Jan 2016 16:21:39 +0100 Subject: [PATCH 237/325] iio: light: acpi-als: Report data as processed commit fa34e6dd44d7c02c8a8468ce4a52a7506f907bef upstream. As per the ACPI specification (Revision 5.0) [1], the data coming from the sensor represent the ambient light illuminance reading expressed in lux. So use IIO_CHAN_INFO_PROCESSED to signify that the data are pre-processed. However, to keep backward ABI compatibility, the IIO_CHAN_INFO_RAW bit is not removed. [1] http://www.acpi.info/DOWNLOADS/ACPIspec50.pdf This issue has also been responsible for at least one userspace bug report hence marking what is a small semantic fix really for stable. [2] https://github.com/hadess/iio-sensor-proxy/issues/46 Signed-off-by: Gabriele Mazzotta Signed-off-by: Jonathan Cameron Signed-off-by: Greg Kroah-Hartman --- drivers/iio/light/acpi-als.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/iio/light/acpi-als.c b/drivers/iio/light/acpi-als.c index 60537ec0c923..53201d99a16c 100644 --- a/drivers/iio/light/acpi-als.c +++ b/drivers/iio/light/acpi-als.c @@ -54,7 +54,9 @@ static const struct iio_chan_spec acpi_als_channels[] = { .realbits = 32, .storagebits = 32, }, - .info_mask_separate = BIT(IIO_CHAN_INFO_RAW), + /* _RAW is here for backward ABI compatibility */ + .info_mask_separate = BIT(IIO_CHAN_INFO_RAW) | + BIT(IIO_CHAN_INFO_PROCESSED), }, }; @@ -152,7 +154,7 @@ static int acpi_als_read_raw(struct iio_dev *indio_dev, s32 temp_val; int ret; - if (mask != IIO_CHAN_INFO_RAW) + if ((mask != IIO_CHAN_INFO_PROCESSED) && (mask != IIO_CHAN_INFO_RAW)) return -EINVAL; /* we support only illumination (_ALI) so far. */ From e16eb4bb193c3b0faf1ca78cf05a6623de5cb633 Mon Sep 17 00:00:00 2001 From: Akinobu Mita Date: Thu, 21 Jan 2016 01:07:31 +0900 Subject: [PATCH 238/325] iio: pressure: mpl115: fix temperature offset sign commit 431386e783a3a6c8b7707bee32d18c353b8688b2 upstream. According to the datasheet, the resolusion of temperature sensor is -5.35 counts/C. Temperature ADC is 472 counts at 25C. (https://www.sparkfun.com/datasheets/Sensors/Pressure/MPL115A1.pdf NOTE: This is older revision, but this information is removed from the latest datasheet from nxp somehow) Temp [C] = (Tadc - 472) / -5.35 + 25 = (Tadc - 605.750000) * -0.186915888 So the correct offset is -605.750000. Signed-off-by: Akinobu Mita Acked-by: Peter Meerwald-Stadler Signed-off-by: Jonathan Cameron Signed-off-by: Greg Kroah-Hartman --- drivers/iio/pressure/mpl115.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iio/pressure/mpl115.c b/drivers/iio/pressure/mpl115.c index f5ecd6e19f5d..a0d7deeac62f 100644 --- a/drivers/iio/pressure/mpl115.c +++ b/drivers/iio/pressure/mpl115.c @@ -117,7 +117,7 @@ static int mpl115_read_raw(struct iio_dev *indio_dev, *val = ret >> 6; return IIO_VAL_INT; case IIO_CHAN_INFO_OFFSET: - *val = 605; + *val = -605; *val2 = 750000; return IIO_VAL_INT_PLUS_MICRO; case IIO_CHAN_INFO_SCALE: From 224f259d9393ca342dd565321db48ec4a79a695f Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Tue, 26 Jan 2016 12:25:21 +0300 Subject: [PATCH 239/325] iio: inkern: fix a NULL dereference on error commit d81dac3c1c5295c61b15293074ac2bd3254e1875 upstream. In twl4030_bci_probe() there are some failure paths where we call iio_channel_release() with a NULL pointer. (Apparently, that driver can opperate without a valid channel pointer). Let's fix it by adding a NULL check in iio_channel_release(). Fixes: 2202e1fc5a29 ('drivers: power: twl4030_charger: fix link problems when building as module') Signed-off-by: Dan Carpenter Signed-off-by: Jonathan Cameron Signed-off-by: Greg Kroah-Hartman --- drivers/iio/inkern.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/iio/inkern.c b/drivers/iio/inkern.c index c8bad3cf891d..217e9306aa0f 100644 --- a/drivers/iio/inkern.c +++ b/drivers/iio/inkern.c @@ -351,6 +351,8 @@ EXPORT_SYMBOL_GPL(iio_channel_get); void iio_channel_release(struct iio_channel *channel) { + if (!channel) + return; iio_device_put(channel->indio_dev); kfree(channel); } From 88413fceab844abec9e8007aaeec35c4bfc3f3fc Mon Sep 17 00:00:00 2001 From: Jamie Bainbridge Date: Sat, 7 Nov 2015 22:13:49 +1000 Subject: [PATCH 240/325] cifs: Ratelimit kernel log messages commit ec7147a99e33a9e4abad6fc6e1b40d15df045d53 upstream. Under some conditions, CIFS can repeatedly call the cifs_dbg() logging wrapper. If done rapidly enough, the console framebuffer can softlockup or "rcu_sched self-detected stall". Apply the built-in log ratelimiters to prevent such hangs. Signed-off-by: Jamie Bainbridge Signed-off-by: Steve French Signed-off-by: Greg Kroah-Hartman --- fs/cifs/cifs_debug.c | 2 +- fs/cifs/cifs_debug.h | 9 ++++----- 2 files changed, 5 insertions(+), 6 deletions(-) diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c index 7febcf2475c5..50b268483302 100644 --- a/fs/cifs/cifs_debug.c +++ b/fs/cifs/cifs_debug.c @@ -50,7 +50,7 @@ void cifs_vfs_err(const char *fmt, ...) vaf.fmt = fmt; vaf.va = &args; - pr_err("CIFS VFS: %pV", &vaf); + pr_err_ratelimited("CIFS VFS: %pV", &vaf); va_end(args); } diff --git a/fs/cifs/cifs_debug.h b/fs/cifs/cifs_debug.h index f40fbaca1b2a..66cf0f9fff89 100644 --- a/fs/cifs/cifs_debug.h +++ b/fs/cifs/cifs_debug.h @@ -51,14 +51,13 @@ __printf(1, 2) void cifs_vfs_err(const char *fmt, ...); /* information message: e.g., configuration, major event */ #define cifs_dbg(type, fmt, ...) \ do { \ - if (type == FYI) { \ - if (cifsFYI & CIFS_INFO) { \ - pr_debug("%s: " fmt, __FILE__, ##__VA_ARGS__); \ - } \ + if (type == FYI && cifsFYI & CIFS_INFO) { \ + pr_debug_ratelimited("%s: " \ + fmt, __FILE__, ##__VA_ARGS__); \ } else if (type == VFS) { \ cifs_vfs_err(fmt, ##__VA_ARGS__); \ } else if (type == NOISY && type != 0) { \ - pr_debug(fmt, ##__VA_ARGS__); \ + pr_debug_ratelimited(fmt, ##__VA_ARGS__); \ } \ } while (0) From 5d80673404e691093d66fc5b02c8bc2ac1692d77 Mon Sep 17 00:00:00 2001 From: Rabin Vincent Date: Wed, 23 Dec 2015 07:32:41 +0100 Subject: [PATCH 241/325] cifs: fix race between call_async() and reconnect() commit 820962dc700598ffe8cd21b967e30e7520c34748 upstream. cifs_call_async() queues the MID to the pending list and calls smb_send_rqst(). If smb_send_rqst() performs a partial send, it sets the tcpStatus to CifsNeedReconnect and returns an error code to cifs_call_async(). In this case, cifs_call_async() removes the MID from the list and returns to the caller. However, cifs_call_async() releases the server mutex _before_ removing the MID. This means that a cifs_reconnect() can race with this function and manage to remove the MID from the list and delete the entry before cifs_call_async() calls cifs_delete_mid(). This leads to various crashes due to the use after free in cifs_delete_mid(). Task1 Task2 cifs_call_async(): - rc = -EAGAIN - mutex_unlock(srv_mutex) cifs_reconnect(): - mutex_lock(srv_mutex) - mutex_unlock(srv_mutex) - list_delete(mid) - mid->callback() cifs_writev_callback(): - mutex_lock(srv_mutex) - delete(mid) - mutex_unlock(srv_mutex) - cifs_delete_mid(mid) <---- use after free Fix this by removing the MID in cifs_call_async() before releasing the srv_mutex. Also hold the srv_mutex in cifs_reconnect() until the MIDs are moved out of the pending list. Signed-off-by: Rabin Vincent Acked-by: Shirish Pargaonkar Signed-off-by: Steve French Signed-off-by: Greg Kroah-Hartman --- fs/cifs/connect.c | 2 +- fs/cifs/transport.c | 6 ++++-- 2 files changed, 5 insertions(+), 3 deletions(-) diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index ecb0803bdb0e..3c194ff0d2f0 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -368,7 +368,6 @@ cifs_reconnect(struct TCP_Server_Info *server) server->session_key.response = NULL; server->session_key.len = 0; server->lstrp = jiffies; - mutex_unlock(&server->srv_mutex); /* mark submitted MIDs for retry and issue callback */ INIT_LIST_HEAD(&retry_list); @@ -381,6 +380,7 @@ cifs_reconnect(struct TCP_Server_Info *server) list_move(&mid_entry->qhead, &retry_list); } spin_unlock(&GlobalMid_Lock); + mutex_unlock(&server->srv_mutex); cifs_dbg(FYI, "%s: issuing mid callbacks\n", __func__); list_for_each_safe(tmp, tmp2, &retry_list) { diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index 2a24c524fb9a..87abe8ed074c 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -576,14 +576,16 @@ cifs_call_async(struct TCP_Server_Info *server, struct smb_rqst *rqst, cifs_in_send_dec(server); cifs_save_when_sent(mid); - if (rc < 0) + if (rc < 0) { server->sequence_number -= 2; + cifs_delete_mid(mid); + } + mutex_unlock(&server->srv_mutex); if (rc == 0) return 0; - cifs_delete_mid(mid); add_credits_and_wake_if(server, credits, optype); return rc; } From 7e30995b26ccc952e30bbc2563fc5728c50c9e12 Mon Sep 17 00:00:00 2001 From: Vasily Averin Date: Thu, 14 Jan 2016 13:41:14 +0300 Subject: [PATCH 242/325] cifs_dbg() outputs an uninitialized buffer in cifs_readdir() commit 01b9b0b28626db4a47d7f48744d70abca9914ef1 upstream. In some cases tmp_bug can be not filled in cifs_filldir and stay uninitialized, therefore its printk with "%s" modifier can leak content of kernelspace memory. If old content of this buffer does not contain '\0' access bejond end of allocated object can crash the host. Signed-off-by: Vasily Averin Signed-off-by: Steve French Signed-off-by: Greg Kroah-Hartman --- fs/cifs/readdir.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c index 0557c45e9c33..b30a4a6d98a0 100644 --- a/fs/cifs/readdir.c +++ b/fs/cifs/readdir.c @@ -847,6 +847,7 @@ int cifs_readdir(struct file *file, struct dir_context *ctx) * if buggy server returns . and .. late do we want to * check for that here? */ + *tmp_buf = 0; rc = cifs_filldir(current_entry, file, ctx, tmp_buf, max_len); if (rc) { From dadfe92207503548d60a2d4c6c467702ead17148 Mon Sep 17 00:00:00 2001 From: Anton Protopopov Date: Wed, 10 Feb 2016 12:50:21 -0500 Subject: [PATCH 243/325] cifs: fix erroneous return value commit 4b550af519854421dfec9f7732cdddeb057134b2 upstream. The setup_ntlmv2_rsp() function may return positive value ENOMEM instead of -ENOMEM in case of kmalloc failure. Signed-off-by: Anton Protopopov Signed-off-by: Steve French Signed-off-by: Greg Kroah-Hartman --- fs/cifs/cifsencrypt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c index afa09fce8151..e682b36a210f 100644 --- a/fs/cifs/cifsencrypt.c +++ b/fs/cifs/cifsencrypt.c @@ -714,7 +714,7 @@ setup_ntlmv2_rsp(struct cifs_ses *ses, const struct nls_table *nls_cp) ses->auth_key.response = kmalloc(baselen + tilen, GFP_KERNEL); if (!ses->auth_key.response) { - rc = ENOMEM; + rc = -ENOMEM; ses->auth_key.len = 0; goto setup_ntlmv2_rsp_ret; } From 1873e6f486061eb93dc82a85fa8030857833d485 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 29 Dec 2015 18:55:19 -0500 Subject: [PATCH 244/325] NFS: Fix attribute cache revalidation commit ade14a7df796d4e86bd9d181193c883a57b13db0 upstream. If a NFSv4 client uses the cache_consistency_bitmask in order to request only information about the change attribute, timestamps and size, then it has not revalidated all attributes, and hence the attribute timeout timestamp should not be updated. Reported-by: Donald Buczek Signed-off-by: Trond Myklebust Signed-off-by: Greg Kroah-Hartman --- fs/nfs/inode.c | 54 ++++++++++++++++++++++++++++++++++++-------------- 1 file changed, 39 insertions(+), 15 deletions(-) diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index c7e8b87da5b2..3e2071a177fd 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -1641,6 +1641,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) unsigned long invalid = 0; unsigned long now = jiffies; unsigned long save_cache_validity; + bool cache_revalidated = true; dfprintk(VFS, "NFS: %s(%s/%lu fh_crc=0x%08x ct=%d info=0x%x)\n", __func__, inode->i_sb->s_id, inode->i_ino, @@ -1702,22 +1703,28 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) nfs_force_lookup_revalidate(inode); inode->i_version = fattr->change_attr; } - } else + } else { nfsi->cache_validity |= save_cache_validity; + cache_revalidated = false; + } if (fattr->valid & NFS_ATTR_FATTR_MTIME) { memcpy(&inode->i_mtime, &fattr->mtime, sizeof(inode->i_mtime)); - } else if (server->caps & NFS_CAP_MTIME) + } else if (server->caps & NFS_CAP_MTIME) { nfsi->cache_validity |= save_cache_validity & (NFS_INO_INVALID_ATTR | NFS_INO_REVAL_FORCED); + cache_revalidated = false; + } if (fattr->valid & NFS_ATTR_FATTR_CTIME) { memcpy(&inode->i_ctime, &fattr->ctime, sizeof(inode->i_ctime)); - } else if (server->caps & NFS_CAP_CTIME) + } else if (server->caps & NFS_CAP_CTIME) { nfsi->cache_validity |= save_cache_validity & (NFS_INO_INVALID_ATTR | NFS_INO_REVAL_FORCED); + cache_revalidated = false; + } /* Check if our cached file size is stale */ if (fattr->valid & NFS_ATTR_FATTR_SIZE) { @@ -1737,19 +1744,23 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) (long long)cur_isize, (long long)new_isize); } - } else + } else { nfsi->cache_validity |= save_cache_validity & (NFS_INO_INVALID_ATTR | NFS_INO_REVAL_PAGECACHE | NFS_INO_REVAL_FORCED); + cache_revalidated = false; + } if (fattr->valid & NFS_ATTR_FATTR_ATIME) memcpy(&inode->i_atime, &fattr->atime, sizeof(inode->i_atime)); - else if (server->caps & NFS_CAP_ATIME) + else if (server->caps & NFS_CAP_ATIME) { nfsi->cache_validity |= save_cache_validity & (NFS_INO_INVALID_ATIME | NFS_INO_REVAL_FORCED); + cache_revalidated = false; + } if (fattr->valid & NFS_ATTR_FATTR_MODE) { if ((inode->i_mode & S_IALLUGO) != (fattr->mode & S_IALLUGO)) { @@ -1758,36 +1769,42 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) inode->i_mode = newmode; invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL; } - } else if (server->caps & NFS_CAP_MODE) + } else if (server->caps & NFS_CAP_MODE) { nfsi->cache_validity |= save_cache_validity & (NFS_INO_INVALID_ATTR | NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL | NFS_INO_REVAL_FORCED); + cache_revalidated = false; + } if (fattr->valid & NFS_ATTR_FATTR_OWNER) { if (!uid_eq(inode->i_uid, fattr->uid)) { invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL; inode->i_uid = fattr->uid; } - } else if (server->caps & NFS_CAP_OWNER) + } else if (server->caps & NFS_CAP_OWNER) { nfsi->cache_validity |= save_cache_validity & (NFS_INO_INVALID_ATTR | NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL | NFS_INO_REVAL_FORCED); + cache_revalidated = false; + } if (fattr->valid & NFS_ATTR_FATTR_GROUP) { if (!gid_eq(inode->i_gid, fattr->gid)) { invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL; inode->i_gid = fattr->gid; } - } else if (server->caps & NFS_CAP_OWNER_GROUP) + } else if (server->caps & NFS_CAP_OWNER_GROUP) { nfsi->cache_validity |= save_cache_validity & (NFS_INO_INVALID_ATTR | NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL | NFS_INO_REVAL_FORCED); + cache_revalidated = false; + } if (fattr->valid & NFS_ATTR_FATTR_NLINK) { if (inode->i_nlink != fattr->nlink) { @@ -1796,19 +1813,22 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) invalid |= NFS_INO_INVALID_DATA; set_nlink(inode, fattr->nlink); } - } else if (server->caps & NFS_CAP_NLINK) + } else if (server->caps & NFS_CAP_NLINK) { nfsi->cache_validity |= save_cache_validity & (NFS_INO_INVALID_ATTR | NFS_INO_REVAL_FORCED); + cache_revalidated = false; + } if (fattr->valid & NFS_ATTR_FATTR_SPACE_USED) { /* * report the blocks in 512byte units */ inode->i_blocks = nfs_calc_block_size(fattr->du.nfs3.used); - } - if (fattr->valid & NFS_ATTR_FATTR_BLOCKS_USED) + } else if (fattr->valid & NFS_ATTR_FATTR_BLOCKS_USED) inode->i_blocks = fattr->du.nfs2.blocks; + else + cache_revalidated = false; /* Update attrtimeo value if we're out of the unstable period */ if (invalid & NFS_INO_INVALID_ATTR) { @@ -1818,9 +1838,13 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) /* Set barrier to be more recent than all outstanding updates */ nfsi->attr_gencount = nfs_inc_attr_generation_counter(); } else { - if (!time_in_range_open(now, nfsi->attrtimeo_timestamp, nfsi->attrtimeo_timestamp + nfsi->attrtimeo)) { - if ((nfsi->attrtimeo <<= 1) > NFS_MAXATTRTIMEO(inode)) - nfsi->attrtimeo = NFS_MAXATTRTIMEO(inode); + if (cache_revalidated) { + if (!time_in_range_open(now, nfsi->attrtimeo_timestamp, + nfsi->attrtimeo_timestamp + nfsi->attrtimeo)) { + nfsi->attrtimeo <<= 1; + if (nfsi->attrtimeo > NFS_MAXATTRTIMEO(inode)) + nfsi->attrtimeo = NFS_MAXATTRTIMEO(inode); + } nfsi->attrtimeo_timestamp = now; } /* Set the barrier to be more recent than this fattr */ @@ -1829,7 +1853,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) } /* Don't declare attrcache up to date if there were no attrs! */ - if (fattr->valid != 0) + if (cache_revalidated) invalid &= ~NFS_INO_INVALID_ATTR; /* Don't invalidate the data if we were to blame */ From c8841e15d6ded83aac4da7caf70a20d3c58bf6fe Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 30 Dec 2015 10:57:01 -0500 Subject: [PATCH 245/325] pNFS/flexfiles: Fix an Oopsable typo in ff_mirror_match_fh() commit 86fb449b07b8215443a30782dca5755d5b8b0577 upstream. Jeff reports seeing an Oops in ff_layout_alloc_lseg. Turns out copy+paste has played cruel tricks on a nested loop. Reported-by: Jeff Layton Signed-off-by: Trond Myklebust Signed-off-by: Greg Kroah-Hartman --- fs/nfs/flexfilelayout/flexfilelayout.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c index 03516c80855a..405f46ba490e 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.c +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -145,7 +145,7 @@ static bool ff_mirror_match_fh(const struct nfs4_ff_layout_mirror *m1, return false; for (i = 0; i < m1->fh_versions_cnt; i++) { bool found_fh = false; - for (j = 0; j < m2->fh_versions_cnt; i++) { + for (j = 0; j < m2->fh_versions_cnt; j++) { if (nfs_compare_fh(&m1->fh_versions[i], &m2->fh_versions[j]) == 0) { found_fh = true; From d65eb5b3dfb1159ea69c6ce170f83a0a90548ac6 Mon Sep 17 00:00:00 2001 From: Andrew Elble Date: Wed, 2 Dec 2015 09:20:57 -0500 Subject: [PATCH 246/325] nfs: Fix race in __update_open_stateid() commit 361cad3c89070aeb37560860ea8bfc092d545adc upstream. We've seen this in a packet capture - I've intermixed what I think was going on. The fix here is to grab the so_lock sooner. 1964379 -> #1 open (for write) reply seqid=1 1964393 -> #2 open (for read) reply seqid=2 __nfs4_close(), state->n_wronly-- nfs4_state_set_mode_locked(), changes state->state = [R] state->flags is [RW] state->state is [R], state->n_wronly == 0, state->n_rdonly == 1 1964398 -> #3 open (for write) call -> because close is already running 1964399 -> downgrade (to read) call seqid=2 (close of #1) 1964402 -> #3 open (for write) reply seqid=3 __update_open_stateid() nfs_set_open_stateid_locked(), changes state->flags state->flags is [RW] state->state is [R], state->n_wronly == 0, state->n_rdonly == 1 new sequence number is exposed now via nfs4_stateid_copy() next step would be update_open_stateflags(), pending so_lock 1964403 -> downgrade reply seqid=2, fails with OLD_STATEID (close of #1) nfs4_close_prepare() gets so_lock and recalcs flags -> send close 1964405 -> downgrade (to read) call seqid=3 (close of #1 retry) __update_open_stateid() gets so_lock * update_open_stateflags() updates state->n_wronly. nfs4_state_set_mode_locked() updates state->state state->flags is [RW] state->state is [RW], state->n_wronly == 1, state->n_rdonly == 1 * should have suppressed the preceding nfs4_close_prepare() from sending open_downgrade 1964406 -> write call 1964408 -> downgrade (to read) reply seqid=4 (close of #1 retry) nfs_clear_open_stateid_locked() state->flags is [R] state->state is [RW], state->n_wronly == 1, state->n_rdonly == 1 1964409 -> write reply (fails, openmode) Signed-off-by: Andrew Elble Signed-off-by: Trond Myklebust Signed-off-by: Greg Kroah-Hartman --- fs/nfs/nfs4proc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 343b0f1f15b1..f496ed721d27 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -1385,6 +1385,7 @@ static void __update_open_stateid(struct nfs4_state *state, nfs4_stateid *open_s * Protect the call to nfs4_state_set_mode_locked and * serialise the stateid update */ + spin_lock(&state->owner->so_lock); write_seqlock(&state->seqlock); if (deleg_stateid != NULL) { nfs4_stateid_copy(&state->stateid, deleg_stateid); @@ -1393,7 +1394,6 @@ static void __update_open_stateid(struct nfs4_state *state, nfs4_stateid *open_s if (open_stateid != NULL) nfs_set_open_stateid_locked(state, open_stateid, fmode); write_sequnlock(&state->seqlock); - spin_lock(&state->owner->so_lock); update_open_stateflags(state, fmode); spin_unlock(&state->owner->so_lock); } From 66b8812e87f3fcf9d52b107a8d3102cd3f77ae1e Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 21 Jan 2016 15:39:40 -0500 Subject: [PATCH 247/325] pNFS/flexfiles: Fix an XDR encoding bug in layoutreturn commit 082fa37d1351a41afc491d44a1d095cb8d919aa2 upstream. We must not skip encoding the statistics, or the server will see an XDR encoding error. Signed-off-by: Trond Myklebust Signed-off-by: Greg Kroah-Hartman --- fs/nfs/flexfilelayout/flexfilelayout.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c index 405f46ba490e..2a2e2d8ddee5 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.c +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -1859,11 +1859,9 @@ ff_layout_encode_layoutreturn(struct pnfs_layout_hdr *lo, start = xdr_reserve_space(xdr, 4); BUG_ON(!start); - if (ff_layout_encode_ioerr(flo, xdr, args)) - goto out; - + ff_layout_encode_ioerr(flo, xdr, args); ff_layout_encode_iostats(flo, xdr, args); -out: + *start = cpu_to_be32((xdr->p - start - 1) * 4); dprintk("%s: Return\n", __func__); } From aef22a3d69452aa516f6738774f7b19372034fdc Mon Sep 17 00:00:00 2001 From: Vegard Nossum Date: Fri, 11 Dec 2015 15:54:16 +0100 Subject: [PATCH 248/325] udf: limit the maximum number of indirect extents in a row commit b0918d9f476a8434b055e362b83fa4fd1d462c3f upstream. udf_next_aext() just follows extent pointers while extents are marked as indirect. This can loop forever for corrupted filesystem. Limit number the of indirect extents we are willing to follow in a row. [JK: Updated changelog, limit, style] Signed-off-by: Vegard Nossum Cc: Jan Kara Cc: Quentin Casasnovas Cc: Andrew Morton Signed-off-by: Jan Kara Signed-off-by: Greg Kroah-Hartman --- fs/udf/inode.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/fs/udf/inode.c b/fs/udf/inode.c index 8d0b3ade0ff0..566df9b5a6cb 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -2047,14 +2047,29 @@ void udf_write_aext(struct inode *inode, struct extent_position *epos, epos->offset += adsize; } +/* + * Only 1 indirect extent in a row really makes sense but allow upto 16 in case + * someone does some weird stuff. + */ +#define UDF_MAX_INDIR_EXTS 16 + int8_t udf_next_aext(struct inode *inode, struct extent_position *epos, struct kernel_lb_addr *eloc, uint32_t *elen, int inc) { int8_t etype; + unsigned int indirections = 0; while ((etype = udf_current_aext(inode, epos, eloc, elen, inc)) == (EXT_NEXT_EXTENT_ALLOCDECS >> 30)) { int block; + + if (++indirections > UDF_MAX_INDIR_EXTS) { + udf_err(inode->i_sb, + "too many indirect extents in inode %lu\n", + inode->i_ino); + return -1; + } + epos->block = *eloc; epos->offset = sizeof(struct allocExtDesc); brelse(epos->bh); From eec1445767ccbb320255ad8bfc2e64c929ee21cc Mon Sep 17 00:00:00 2001 From: Andrew Gabbasov Date: Thu, 24 Dec 2015 10:25:32 -0600 Subject: [PATCH 249/325] udf: Prevent buffer overrun with multi-byte characters commit ad402b265ecf6fa22d04043b41444cdfcdf4f52d upstream. udf_CS0toUTF8 function stops the conversion when the output buffer length reaches UDF_NAME_LEN-2, which is correct maximum name length, but, when checking, it leaves the space for a single byte only, while multi-bytes output characters can take more space, causing buffer overflow. Similar error exists in udf_CS0toNLS function, that restricts the output length to UDF_NAME_LEN, while actual maximum allowed length is UDF_NAME_LEN-2. In these cases the output can override not only the current buffer length field, causing corruption of the name buffer itself, but also following allocation structures, causing kernel crash. Adjust the output length checks in both functions to prevent buffer overruns in case of multi-bytes UTF8 or NLS characters. Signed-off-by: Andrew Gabbasov Signed-off-by: Jan Kara Signed-off-by: Greg Kroah-Hartman --- fs/udf/unicode.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/fs/udf/unicode.c b/fs/udf/unicode.c index ab478e62baae..95a224b26048 100644 --- a/fs/udf/unicode.c +++ b/fs/udf/unicode.c @@ -128,11 +128,15 @@ int udf_CS0toUTF8(struct ustr *utf_o, const struct ustr *ocu_i) if (c < 0x80U) utf_o->u_name[utf_o->u_len++] = (uint8_t)c; else if (c < 0x800U) { + if (utf_o->u_len > (UDF_NAME_LEN - 4)) + break; utf_o->u_name[utf_o->u_len++] = (uint8_t)(0xc0 | (c >> 6)); utf_o->u_name[utf_o->u_len++] = (uint8_t)(0x80 | (c & 0x3f)); } else { + if (utf_o->u_len > (UDF_NAME_LEN - 5)) + break; utf_o->u_name[utf_o->u_len++] = (uint8_t)(0xe0 | (c >> 12)); utf_o->u_name[utf_o->u_len++] = @@ -277,7 +281,7 @@ static int udf_CS0toNLS(struct nls_table *nls, struct ustr *utf_o, c = (c << 8) | ocu[i++]; len = nls->uni2char(c, &utf_o->u_name[utf_o->u_len], - UDF_NAME_LEN - utf_o->u_len); + UDF_NAME_LEN - 2 - utf_o->u_len); /* Valid character? */ if (len >= 0) utf_o->u_len += len; From d0452554b9a114d40f7f86248c2935d0ba7ddd22 Mon Sep 17 00:00:00 2001 From: Andrew Gabbasov Date: Thu, 24 Dec 2015 10:25:33 -0600 Subject: [PATCH 250/325] udf: Check output buffer length when converting name to CS0 commit bb00c898ad1ce40c4bb422a8207ae562e9aea7ae upstream. If a name contains at least some characters with Unicode values exceeding single byte, the CS0 output should have 2 bytes per character. And if other input characters have single byte Unicode values, then the single input byte is converted to 2 output bytes, and the length of output becomes larger than the length of input. And if the input name is long enough, the output length may exceed the allocated buffer length. All this means that conversion from UTF8 or NLS to CS0 requires checking of output length in order to stop when it exceeds the given output buffer size. [JK: Make code return -ENAMETOOLONG instead of silently truncating the name] Signed-off-by: Andrew Gabbasov Signed-off-by: Jan Kara Signed-off-by: Greg Kroah-Hartman --- fs/udf/unicode.c | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) diff --git a/fs/udf/unicode.c b/fs/udf/unicode.c index 95a224b26048..e788a05aab83 100644 --- a/fs/udf/unicode.c +++ b/fs/udf/unicode.c @@ -177,17 +177,22 @@ int udf_CS0toUTF8(struct ustr *utf_o, const struct ustr *ocu_i) static int udf_UTF8toCS0(dstring *ocu, struct ustr *utf, int length) { unsigned c, i, max_val, utf_char; - int utf_cnt, u_len; + int utf_cnt, u_len, u_ch; memset(ocu, 0, sizeof(dstring) * length); ocu[0] = 8; max_val = 0xffU; + u_ch = 1; try_again: u_len = 0U; utf_char = 0U; utf_cnt = 0U; for (i = 0U; i < utf->u_len; i++) { + /* Name didn't fit? */ + if (u_len + 1 + u_ch >= length) + return 0; + c = (uint8_t)utf->u_name[i]; /* Complete a multi-byte UTF-8 character */ @@ -229,6 +234,7 @@ try_again: if (max_val == 0xffU) { max_val = 0xffffU; ocu[0] = (uint8_t)0x10U; + u_ch = 2; goto try_again; } goto error_out; @@ -299,15 +305,19 @@ static int udf_NLStoCS0(struct nls_table *nls, dstring *ocu, struct ustr *uni, int len; unsigned i, max_val; uint16_t uni_char; - int u_len; + int u_len, u_ch; memset(ocu, 0, sizeof(dstring) * length); ocu[0] = 8; max_val = 0xffU; + u_ch = 1; try_again: u_len = 0U; for (i = 0U; i < uni->u_len; i++) { + /* Name didn't fit? */ + if (u_len + 1 + u_ch >= length) + return 0; len = nls->char2uni(&uni->u_name[i], uni->u_len - i, &uni_char); if (!len) continue; @@ -320,6 +330,7 @@ try_again: if (uni_char > max_val) { max_val = 0xffffU; ocu[0] = (uint8_t)0x10U; + u_ch = 2; goto try_again; } From 782126b225221e5a2b30b1824b2326abba53eab9 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 6 Jan 2016 08:57:06 -0500 Subject: [PATCH 251/325] SUNRPC: Fixup socket wait for memory commit 13331a551ab4df87f7a027d2cab392da96aba1de upstream. We're seeing hangs in the NFS client code, with loops of the form: RPC: 30317 xmit incomplete (267368 left of 524448) RPC: 30317 call_status (status -11) RPC: 30317 call_transmit (status 0) RPC: 30317 xprt_prepare_transmit RPC: 30317 xprt_transmit(524448) RPC: xs_tcp_send_request(267368) = -11 RPC: 30317 xmit incomplete (267368 left of 524448) RPC: 30317 call_status (status -11) RPC: 30317 call_transmit (status 0) RPC: 30317 xprt_prepare_transmit RPC: 30317 xprt_transmit(524448) Turns out commit ceb5d58b2170 ("net: fix sock_wake_async() rcu protection") moved SOCKWQ_ASYNC_NOSPACE out of sock->flags and into sk->sk_wq->flags, however it never tried to fix up the code in net/sunrpc. The new idiom is to use the flags in the RCU protected struct socket_wq. While we're at it, clear out the now redundant places where we set/clear SOCKWQ_ASYNC_NOSPACE and SOCK_NOSPACE. In principle, sk_stream_wait_memory() is supposed to set these for us, so we only need to clear them in the particular case of our ->write_space() callback. Fixes: ceb5d58b2170 ("net: fix sock_wake_async() rcu protection") Cc: Eric Dumazet Signed-off-by: Trond Myklebust Signed-off-by: Greg Kroah-Hartman --- net/sunrpc/xprtsock.c | 49 +++++++++++++++++++------------------------ 1 file changed, 21 insertions(+), 28 deletions(-) diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 2ffaf6a79499..027c9ef8a263 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -398,7 +398,6 @@ static int xs_sendpages(struct socket *sock, struct sockaddr *addr, int addrlen, if (unlikely(!sock)) return -ENOTSOCK; - clear_bit(SOCKWQ_ASYNC_NOSPACE, &sock->flags); if (base != 0) { addr = NULL; addrlen = 0; @@ -442,7 +441,6 @@ static void xs_nospace_callback(struct rpc_task *task) struct sock_xprt *transport = container_of(task->tk_rqstp->rq_xprt, struct sock_xprt, xprt); transport->inet->sk_write_pending--; - clear_bit(SOCKWQ_ASYNC_NOSPACE, &transport->sock->flags); } /** @@ -467,20 +465,11 @@ static int xs_nospace(struct rpc_task *task) /* Don't race with disconnect */ if (xprt_connected(xprt)) { - if (test_bit(SOCKWQ_ASYNC_NOSPACE, &transport->sock->flags)) { - /* - * Notify TCP that we're limited by the application - * window size - */ - set_bit(SOCK_NOSPACE, &transport->sock->flags); - sk->sk_write_pending++; - /* ...and wait for more buffer space */ - xprt_wait_for_buffer_space(task, xs_nospace_callback); - } - } else { - clear_bit(SOCKWQ_ASYNC_NOSPACE, &transport->sock->flags); + /* wait for more buffer space */ + sk->sk_write_pending++; + xprt_wait_for_buffer_space(task, xs_nospace_callback); + } else ret = -ENOTCONN; - } spin_unlock_bh(&xprt->transport_lock); @@ -616,9 +605,6 @@ process_status: case -EAGAIN: status = xs_nospace(task); break; - default: - dprintk("RPC: sendmsg returned unrecognized error %d\n", - -status); case -ENETUNREACH: case -ENOBUFS: case -EPIPE: @@ -626,7 +612,10 @@ process_status: case -EPERM: /* When the server has died, an ICMP port unreachable message * prompts ECONNREFUSED. */ - clear_bit(SOCKWQ_ASYNC_NOSPACE, &transport->sock->flags); + break; + default: + dprintk("RPC: sendmsg returned unrecognized error %d\n", + -status); } return status; @@ -706,16 +695,16 @@ static int xs_tcp_send_request(struct rpc_task *task) case -EAGAIN: status = xs_nospace(task); break; - default: - dprintk("RPC: sendmsg returned unrecognized error %d\n", - -status); case -ECONNRESET: case -ECONNREFUSED: case -ENOTCONN: case -EADDRINUSE: case -ENOBUFS: case -EPIPE: - clear_bit(SOCKWQ_ASYNC_NOSPACE, &transport->sock->flags); + break; + default: + dprintk("RPC: sendmsg returned unrecognized error %d\n", + -status); } return status; @@ -1609,19 +1598,23 @@ static void xs_tcp_state_change(struct sock *sk) static void xs_write_space(struct sock *sk) { - struct socket *sock; + struct socket_wq *wq; struct rpc_xprt *xprt; - if (unlikely(!(sock = sk->sk_socket))) + if (!sk->sk_socket) return; - clear_bit(SOCK_NOSPACE, &sock->flags); + clear_bit(SOCK_NOSPACE, &sk->sk_socket->flags); if (unlikely(!(xprt = xprt_from_sock(sk)))) return; - if (test_and_clear_bit(SOCKWQ_ASYNC_NOSPACE, &sock->flags) == 0) - return; + rcu_read_lock(); + wq = rcu_dereference(sk->sk_wq); + if (!wq || test_and_clear_bit(SOCKWQ_ASYNC_NOSPACE, &wq->flags) == 0) + goto out; xprt_write_space(xprt); +out: + rcu_read_unlock(); } /** From 64f10cf83a6cb819d8192e679a9916519d3edf4a Mon Sep 17 00:00:00 2001 From: Gavin Shan Date: Wed, 2 Dec 2015 16:25:32 +1100 Subject: [PATCH 252/325] powerpc/eeh: Fix PE location code commit 7e56f627768da4e6480986b5145dc3422bc448a5 upstream. In eeh_pe_loc_get(), the PE location code is retrieved from the "ibm,loc-code" property of the device node for the bridge of the PE's primary bus. It's not correct because the property indicates the parent PE's location code. This reads the correct PE location code from "ibm,io-base-loc-code" or "ibm,slot-location-code" property of PE parent bus's device node. Fixes: 357b2f3dd9b7 ("powerpc/eeh: Dump PE location code") Signed-off-by: Gavin Shan Tested-by: Russell Currey Signed-off-by: Michael Ellerman Signed-off-by: Greg Kroah-Hartman --- arch/powerpc/kernel/eeh_pe.c | 35 ++++++++++++++++------------------- 1 file changed, 16 insertions(+), 19 deletions(-) diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c index 8654cb166c19..ca9e5371930e 100644 --- a/arch/powerpc/kernel/eeh_pe.c +++ b/arch/powerpc/kernel/eeh_pe.c @@ -883,32 +883,29 @@ void eeh_pe_restore_bars(struct eeh_pe *pe) const char *eeh_pe_loc_get(struct eeh_pe *pe) { struct pci_bus *bus = eeh_pe_bus_get(pe); - struct device_node *dn = pci_bus_to_OF_node(bus); + struct device_node *dn; const char *loc = NULL; - if (!dn) - goto out; + while (bus) { + dn = pci_bus_to_OF_node(bus); + if (!dn) { + bus = bus->parent; + continue; + } - /* PHB PE or root PE ? */ - if (pci_is_root_bus(bus)) { - loc = of_get_property(dn, "ibm,loc-code", NULL); - if (!loc) + if (pci_is_root_bus(bus)) loc = of_get_property(dn, "ibm,io-base-loc-code", NULL); - if (loc) - goto out; + else + loc = of_get_property(dn, "ibm,slot-location-code", + NULL); - /* Check the root port */ - dn = dn->child; - if (!dn) - goto out; + if (loc) + return loc; + + bus = bus->parent; } - loc = of_get_property(dn, "ibm,loc-code", NULL); - if (!loc) - loc = of_get_property(dn, "ibm,slot-location-code", NULL); - -out: - return loc ? loc : "N/A"; + return "N/A"; } /** From 5ecdf58c1945c40b6dcaf9764c119ecc607e8a06 Mon Sep 17 00:00:00 2001 From: Gavin Shan Date: Tue, 9 Feb 2016 15:50:21 +1100 Subject: [PATCH 253/325] powerpc/eeh: Fix stale cached primary bus commit 05ba75f848647135f063199dc0e9f40fee769724 upstream. When PE is created, its primary bus is cached to pe->bus. At later point, the cached primary bus is returned from eeh_pe_bus_get(). However, we could get stale cached primary bus and run into kernel crash in one case: full hotplug as part of fenced PHB error recovery releases all PCI busses under the PHB at unplugging time and recreate them at plugging time. pe->bus is still dereferencing the PCI bus that was released. This adds another PE flag (EEH_PE_PRI_BUS) to represent the validity of pe->bus. pe->bus is updated when its first child EEH device is online and the flag is set. Before unplugging in full hotplug for error recovery, the flag is cleared. Fixes: 8cdb2833 ("powerpc/eeh: Trace PCI bus from PE") Reported-by: Andrew Donnellan Reported-by: Pradipta Ghosh Signed-off-by: Gavin Shan Tested-by: Andrew Donnellan Signed-off-by: Michael Ellerman Signed-off-by: Greg Kroah-Hartman --- arch/powerpc/include/asm/eeh.h | 1 + arch/powerpc/kernel/eeh_driver.c | 3 +++ arch/powerpc/kernel/eeh_pe.c | 2 +- arch/powerpc/platforms/powernv/eeh-powernv.c | 5 ++++- 4 files changed, 9 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h index c5eb86f3d452..867c39b45df6 100644 --- a/arch/powerpc/include/asm/eeh.h +++ b/arch/powerpc/include/asm/eeh.h @@ -81,6 +81,7 @@ struct pci_dn; #define EEH_PE_KEEP (1 << 8) /* Keep PE on hotplug */ #define EEH_PE_CFG_RESTRICTED (1 << 9) /* Block config on error */ #define EEH_PE_REMOVED (1 << 10) /* Removed permanently */ +#define EEH_PE_PRI_BUS (1 << 11) /* Cached primary bus */ struct eeh_pe { int type; /* PE type: PHB/Bus/Device */ diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index 8d14feb40f12..f69ecaa7ce33 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -564,6 +564,7 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus) */ eeh_pe_state_mark(pe, EEH_PE_KEEP); if (bus) { + eeh_pe_state_clear(pe, EEH_PE_PRI_BUS); pci_lock_rescan_remove(); pcibios_remove_pci_devices(bus); pci_unlock_rescan_remove(); @@ -803,6 +804,7 @@ perm_error: * the their PCI config any more. */ if (frozen_bus) { + eeh_pe_state_clear(pe, EEH_PE_PRI_BUS); eeh_pe_dev_mode_mark(pe, EEH_DEV_REMOVED); pci_lock_rescan_remove(); @@ -886,6 +888,7 @@ static void eeh_handle_special_event(void) continue; /* Notify all devices to be down */ + eeh_pe_state_clear(pe, EEH_PE_PRI_BUS); bus = eeh_pe_bus_get(phb_pe); eeh_pe_dev_traverse(pe, eeh_report_failure, NULL); diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c index ca9e5371930e..98f81800e00c 100644 --- a/arch/powerpc/kernel/eeh_pe.c +++ b/arch/powerpc/kernel/eeh_pe.c @@ -928,7 +928,7 @@ struct pci_bus *eeh_pe_bus_get(struct eeh_pe *pe) bus = pe->phb->bus; } else if (pe->type & EEH_PE_BUS || pe->type & EEH_PE_DEVICE) { - if (pe->bus) { + if (pe->state & EEH_PE_PRI_BUS) { bus = pe->bus; goto out; } diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c index e1c90725522a..2ba602591a20 100644 --- a/arch/powerpc/platforms/powernv/eeh-powernv.c +++ b/arch/powerpc/platforms/powernv/eeh-powernv.c @@ -444,9 +444,12 @@ static void *pnv_eeh_probe(struct pci_dn *pdn, void *data) * PCI devices of the PE are expected to be removed prior * to PE reset. */ - if (!edev->pe->bus) + if (!(edev->pe->state & EEH_PE_PRI_BUS)) { edev->pe->bus = pci_find_bus(hose->global_number, pdn->busno); + if (edev->pe->bus) + edev->pe->state |= EEH_PE_PRI_BUS; + } /* * Enable EEH explicitly so that we will do EEH check From b5311270caba5392a83ed918e11a16e71b3b1e44 Mon Sep 17 00:00:00 2001 From: Gavin Shan Date: Tue, 9 Feb 2016 15:50:22 +1100 Subject: [PATCH 254/325] powerpc/powernv: Fix stale PE primary bus commit 1bc74f1ccd457832dc515fc1febe6655985fdcd2 upstream. When PCI bus is unplugged during full hotplug for EEH recovery, the platform PE instance (struct pnv_ioda_pe) isn't released and it dereferences the stale PCI bus that has been released. It leads to kernel crash when referring to the stale PCI bus. This fixes the issue by correcting the PE's primary bus when it's oneline at plugging time, in pnv_pci_dma_bus_setup() which is to be called by pcibios_fixup_bus(). Reported-by: Andrew Donnellan Reported-by: Pradipta Ghosh Signed-off-by: Gavin Shan Tested-by: Andrew Donnellan Signed-off-by: Michael Ellerman Signed-off-by: Greg Kroah-Hartman --- arch/powerpc/platforms/powernv/pci-ioda.c | 1 + arch/powerpc/platforms/powernv/pci.c | 20 ++++++++++++++++++++ arch/powerpc/platforms/powernv/pci.h | 1 + 3 files changed, 22 insertions(+) diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 414fd1a00fda..e40d0714679e 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -3034,6 +3034,7 @@ static void pnv_pci_ioda_shutdown(struct pci_controller *hose) static const struct pci_controller_ops pnv_pci_ioda_controller_ops = { .dma_dev_setup = pnv_pci_dma_dev_setup, + .dma_bus_setup = pnv_pci_dma_bus_setup, #ifdef CONFIG_PCI_MSI .setup_msi_irqs = pnv_setup_msi_irqs, .teardown_msi_irqs = pnv_teardown_msi_irqs, diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c index f2dd77234240..c97c76f9ad84 100644 --- a/arch/powerpc/platforms/powernv/pci.c +++ b/arch/powerpc/platforms/powernv/pci.c @@ -762,6 +762,26 @@ void pnv_pci_dma_dev_setup(struct pci_dev *pdev) phb->dma_dev_setup(phb, pdev); } +void pnv_pci_dma_bus_setup(struct pci_bus *bus) +{ + struct pci_controller *hose = bus->sysdata; + struct pnv_phb *phb = hose->private_data; + struct pnv_ioda_pe *pe; + + list_for_each_entry(pe, &phb->ioda.pe_list, list) { + if (!(pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL))) + continue; + + if (!pe->pbus) + continue; + + if (bus->number == ((pe->rid >> 8) & 0xFF)) { + pe->pbus = bus; + break; + } + } +} + void pnv_pci_shutdown(void) { struct pci_controller *hose; diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h index c8ff50e90766..36a99feab7d8 100644 --- a/arch/powerpc/platforms/powernv/pci.h +++ b/arch/powerpc/platforms/powernv/pci.h @@ -235,6 +235,7 @@ extern void pnv_pci_reset_secondary_bus(struct pci_dev *dev); extern int pnv_eeh_phb_reset(struct pci_controller *hose, int option); extern void pnv_pci_dma_dev_setup(struct pci_dev *pdev); +extern void pnv_pci_dma_bus_setup(struct pci_bus *bus); extern int pnv_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type); extern void pnv_teardown_msi_irqs(struct pci_dev *pdev); From 602acfedc981eb887289f11f1a7565e6f48c710d Mon Sep 17 00:00:00 2001 From: Alexey Kardashevskiy Date: Wed, 17 Feb 2016 18:26:31 +1100 Subject: [PATCH 255/325] powerpc/ioda: Set "read" permission when "write" is set commit 6ecad912a0073c768db1491c27ca55ad2d0ee68f upstream. Quite often drivers set only "write" permission assuming that this includes "read" permission as well and this works on plenty of platforms. However IODA2 is strict about this and produces an EEH when "read" permission is not set and reading happens. This adds a workaround in the IODA code to always add the "read" bit when the "write" bit is set. Fixes: 10b35b2b7485 ("powerpc/powernv: Do not set "read" flag if direction==DMA_NONE") Cc: Benjamin Herrenschmidt Signed-off-by: Alexey Kardashevskiy Tested-by: Douglas Miller Signed-off-by: Michael Ellerman Signed-off-by: Greg Kroah-Hartman --- arch/powerpc/platforms/powernv/pci.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c index c97c76f9ad84..ad8c3f4a5e0b 100644 --- a/arch/powerpc/platforms/powernv/pci.c +++ b/arch/powerpc/platforms/powernv/pci.c @@ -601,6 +601,9 @@ int pnv_tce_build(struct iommu_table *tbl, long index, long npages, u64 rpn = __pa(uaddr) >> tbl->it_page_shift; long i; + if (proto_tce & TCE_PCI_WRITE) + proto_tce |= TCE_PCI_READ; + for (i = 0; i < npages; i++) { unsigned long newtce = proto_tce | ((rpn + i) << tbl->it_page_shift); @@ -622,6 +625,9 @@ int pnv_tce_xchg(struct iommu_table *tbl, long index, BUG_ON(*hpa & ~IOMMU_PAGE_MASK(tbl)); + if (newtce & TCE_PCI_WRITE) + newtce |= TCE_PCI_READ; + oldtce = xchg(pnv_tce(tbl, idx), cpu_to_be64(newtce)); *hpa = be64_to_cpu(oldtce) & ~(TCE_PCI_READ | TCE_PCI_WRITE); *direction = iommu_tce_direction(oldtce); From 242813b9a1b6d44845fbc73fe0f6db13f2401828 Mon Sep 17 00:00:00 2001 From: Thomas Petazzoni Date: Fri, 4 Dec 2015 14:29:02 +0100 Subject: [PATCH 256/325] ARM: mvebu: remove duplicated regulator definition in Armada 388 GP commit 079ae0c121fd23287f4ad2be9e9f8a13f63cae73 upstream. The Armada 388 GP Device Tree file describes two times a regulator named 'reg_usb2_1_vbus', with the exact same description. This has been wrong since Armada 388 GP support was introduced. Fixes: 928413bd859c0 ("ARM: mvebu: Add Armada 388 General Purpose Development Board support") Signed-off-by: Thomas Petazzoni Signed-off-by: Gregory CLEMENT Signed-off-by: Greg Kroah-Hartman --- arch/arm/boot/dts/armada-388-gp.dts | 10 ---------- 1 file changed, 10 deletions(-) diff --git a/arch/arm/boot/dts/armada-388-gp.dts b/arch/arm/boot/dts/armada-388-gp.dts index a633be3defda..cd316021d6ce 100644 --- a/arch/arm/boot/dts/armada-388-gp.dts +++ b/arch/arm/boot/dts/armada-388-gp.dts @@ -303,16 +303,6 @@ gpio = <&expander0 4 GPIO_ACTIVE_HIGH>; }; - reg_usb2_1_vbus: v5-vbus1 { - compatible = "regulator-fixed"; - regulator-name = "v5.0-vbus1"; - regulator-min-microvolt = <5000000>; - regulator-max-microvolt = <5000000>; - enable-active-high; - regulator-always-on; - gpio = <&expander0 4 GPIO_ACTIVE_HIGH>; - }; - reg_sata0: pwr-sata0 { compatible = "regulator-fixed"; regulator-name = "pwr_en_sata0"; From a68f555363f5e43d0da4a6d025e23db74e2b4f1f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Mika=20Penttil=C3=A4?= Date: Tue, 26 Jan 2016 15:47:25 +0000 Subject: [PATCH 257/325] arm64: mm: avoid calling apply_to_page_range on empty range MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 57adec866c0440976c96a4b8f5b59fb411b1cacb upstream. Calling apply_to_page_range with an empty range results in a BUG_ON from the core code. This can be triggered by trying to load the st_drv module with CONFIG_DEBUG_SET_MODULE_RONX enabled: kernel BUG at mm/memory.c:1874! Internal error: Oops - BUG: 0 [#1] PREEMPT SMP Modules linked in: CPU: 3 PID: 1764 Comm: insmod Not tainted 4.5.0-rc1+ #2 Hardware name: ARM Juno development board (r0) (DT) task: ffffffc9763b8000 ti: ffffffc975af8000 task.ti: ffffffc975af8000 PC is at apply_to_page_range+0x2cc/0x2d0 LR is at change_memory_common+0x80/0x108 This patch fixes the issue by making change_memory_common (called by the set_memory_* functions) a NOP when numpages == 0, therefore avoiding the erroneous call to apply_to_page_range and bringing us into line with x86 and s390. Reviewed-by: Laura Abbott Acked-by: David Rientjes Signed-off-by: Mika Penttilä Signed-off-by: Will Deacon Signed-off-by: Greg Kroah-Hartman --- arch/arm64/mm/pageattr.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/arm64/mm/pageattr.c b/arch/arm64/mm/pageattr.c index 3571c7309c5e..cf6240741134 100644 --- a/arch/arm64/mm/pageattr.c +++ b/arch/arm64/mm/pageattr.c @@ -57,6 +57,9 @@ static int change_memory_common(unsigned long addr, int numpages, if (end < MODULES_VADDR || end >= MODULES_END) return -EINVAL; + if (!numpages) + return 0; + data.set_mask = set_mask; data.clear_mask = clear_mask; From 9fe0b68c4949517720546aa3717d05b491e4ee09 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Wed, 10 Feb 2016 09:25:17 +0100 Subject: [PATCH 258/325] ARM: 8519/1: ICST: try other dividends than 1 commit e972c37459c813190461dabfeaac228e00aae259 upstream. Since the dawn of time the ICST code has only supported divide by one or hang in an eternal loop. Luckily we were always dividing by one because the reference frequency for the systems using the ICSTs is 24MHz and the [min,max] values for the PLL input if [10,320] MHz for ICST307 and [6,200] for ICST525, so the loop will always terminate immediately without assigning any divisor for the reference frequency. But for the code to make sense, let's insert the missing i++ Reported-by: David Binderman Signed-off-by: Linus Walleij Signed-off-by: Russell King Signed-off-by: Greg Kroah-Hartman --- arch/arm/common/icst.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm/common/icst.c b/arch/arm/common/icst.c index 2dc6da70ae59..3b3e58b7ba74 100644 --- a/arch/arm/common/icst.c +++ b/arch/arm/common/icst.c @@ -58,6 +58,7 @@ icst_hz_to_vco(const struct icst_params *p, unsigned long freq) if (f > p->vco_min && f <= p->vco_max) break; + i++; } while (i < 8); if (i >= 8) From 53d991bbbc513ac4ac67ad7c422b13841920353f Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Mon, 8 Feb 2016 09:14:37 +0100 Subject: [PATCH 259/325] ARM: 8517/1: ICST: avoid arithmetic overflow in icst_hz() commit 5070fb14a0154f075c8b418e5bc58a620ae85a45 upstream. When trying to set the ICST 307 clock to 25174000 Hz I ran into this arithmetic error: the icst_hz_to_vco() correctly figure out DIVIDE=2, RDW=100 and VDW=99 yielding a frequency of 25174000 Hz out of the VCO. (I replicated the icst_hz() function in a spreadsheet to verify this.) However, when I called icst_hz() on these VCO settings it would instead return 4122709 Hz. This causes an error in the common clock driver for ICST as the common clock framework will call .round_rate() on the clock which will utilize icst_hz_to_vco() followed by icst_hz() suggesting the erroneous frequency, and then the clock gets set to this. The error did not manifest in the old clock framework since this high frequency was only used by the CLCD, which calls clk_set_rate() without first calling clk_round_rate() and since the old clock framework would not call clk_round_rate() before setting the frequency, the correct values propagated into the VCO. After some experimenting I figured out that it was due to a simple arithmetic overflow: the divisor for 24Mhz reference frequency as reference becomes 24000000*2*(99+8)=0x132212400 and the "1" in bit 32 overflows and is lost. But introducing an explicit 64-by-32 bit do_div() and casting the divisor into (u64) we get the right frequency back, and the right frequency gets set. Tested on the ARM Versatile. Cc: linux-clk@vger.kernel.org Cc: Pawel Moll Signed-off-by: Linus Walleij Signed-off-by: Russell King Signed-off-by: Greg Kroah-Hartman --- arch/arm/common/icst.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/arch/arm/common/icst.c b/arch/arm/common/icst.c index 3b3e58b7ba74..d7ed252708c5 100644 --- a/arch/arm/common/icst.c +++ b/arch/arm/common/icst.c @@ -16,7 +16,7 @@ */ #include #include - +#include #include /* @@ -29,7 +29,11 @@ EXPORT_SYMBOL(icst525_s2div); unsigned long icst_hz(const struct icst_params *p, struct icst_vco vco) { - return p->ref * 2 * (vco.v + 8) / ((vco.r + 2) * p->s2div[vco.s]); + u64 dividend = p->ref * 2 * (u64)(vco.v + 8); + u32 divisor = (vco.r + 2) * p->s2div[vco.s]; + + do_div(dividend, divisor); + return (unsigned long)dividend; } EXPORT_SYMBOL(icst_hz); From 323f7cd28b7fd6b1c0cd9f003aa8482c10ff9d7d Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Mon, 1 Feb 2016 14:18:57 +0100 Subject: [PATCH 260/325] ARM: nomadik: fix up SD/MMC DT settings commit 418d5516568b3fdbc4e7b53677dd78aed8514565 upstream. The DTSI file for the Nomadik does not properly specify how the PL180 levelshifter is connected: the Nomadik actually needs all the five st,sig-dir-* flags set to properly control all lines out. Further this board supports full power cycling of the card, and since this variant has no hardware clock gating, it needs a ridiculously low frequency setting to keep up with the ever overflowing FIFO. The pin configuration set-up is a bit of a mystery, because of course these pins are a mix of inputs and outputs. However the reference implementation sets all pins to "output" with unspecified initial value, so let's do that here as well. Signed-off-by: Linus Walleij Acked-by: Ulf Hansson Signed-off-by: Olof Johansson Signed-off-by: Greg Kroah-Hartman --- arch/arm/boot/dts/ste-nomadik-stn8815.dtsi | 37 ++++++++++++---------- 1 file changed, 20 insertions(+), 17 deletions(-) diff --git a/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi b/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi index d0c743853318..27a333eb8987 100644 --- a/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi +++ b/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi @@ -127,22 +127,14 @@ }; mmcsd_default_mode: mmcsd_default { mmcsd_default_cfg1 { - /* MCCLK */ - pins = "GPIO8_B10"; - ste,output = <0>; - }; - mmcsd_default_cfg2 { - /* MCCMDDIR, MCDAT0DIR, MCDAT31DIR, MCDATDIR2 */ - pins = "GPIO10_C11", "GPIO15_A12", - "GPIO16_C13", "GPIO23_D15"; - ste,output = <1>; - }; - mmcsd_default_cfg3 { - /* MCCMD, MCDAT3-0, MCMSFBCLK */ - pins = "GPIO9_A10", "GPIO11_B11", - "GPIO12_A11", "GPIO13_C12", - "GPIO14_B12", "GPIO24_C15"; - ste,input = <1>; + /* + * MCCLK, MCCMDDIR, MCDAT0DIR, MCDAT31DIR, MCDATDIR2 + * MCCMD, MCDAT3-0, MCMSFBCLK + */ + pins = "GPIO8_B10", "GPIO9_A10", "GPIO10_C11", "GPIO11_B11", + "GPIO12_A11", "GPIO13_C12", "GPIO14_B12", "GPIO15_A12", + "GPIO16_C13", "GPIO23_D15", "GPIO24_C15"; + ste,output = <2>; }; }; }; @@ -802,10 +794,21 @@ clock-names = "mclk", "apb_pclk"; interrupt-parent = <&vica>; interrupts = <22>; - max-frequency = <48000000>; + max-frequency = <400000>; bus-width = <4>; cap-mmc-highspeed; cap-sd-highspeed; + full-pwr-cycle; + /* + * The STw4811 circuit used with the Nomadik strictly + * requires that all of these signal direction pins be + * routed and used for its 4-bit levelshifter. + */ + st,sig-dir-dat0; + st,sig-dir-dat2; + st,sig-dir-dat31; + st,sig-dir-cmd; + st,sig-pin-fbclk; pinctrl-names = "default"; pinctrl-0 = <&mmcsd_default_mux>, <&mmcsd_default_mode>; vmmc-supply = <&vmmc_regulator>; From 671a5bc6f54d080b9453dc70a638c41ea23838d8 Mon Sep 17 00:00:00 2001 From: Adam Ford Date: Thu, 21 Jan 2016 11:03:20 -0600 Subject: [PATCH 261/325] ARM: dts: Fix wl12xx missing clocks that cause hangs commit 0ea24daae053a9ba65d2f3eb20523002c1a8af38 upstream. The tcxo-clock-frequency binding is listed as optional, but without it the wl12xx used on the torpedo + wireless may hang. Scanning also appears broken without this patch. Signed-off-by: Adam Ford Fixes: 687c27676151 ("ARM: dts: Add minimal support for LogicPD Torpedo DM3730 devkit") Signed-off-by: Tony Lindgren Signed-off-by: Greg Kroah-Hartman --- arch/arm/boot/dts/logicpd-torpedo-som.dtsi | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm/boot/dts/logicpd-torpedo-som.dtsi b/arch/arm/boot/dts/logicpd-torpedo-som.dtsi index 36387b11451d..80f6c786a37e 100644 --- a/arch/arm/boot/dts/logicpd-torpedo-som.dtsi +++ b/arch/arm/boot/dts/logicpd-torpedo-som.dtsi @@ -122,6 +122,7 @@ interrupt-parent = <&gpio5>; interrupts = <24 IRQ_TYPE_LEVEL_HIGH>; /* gpio 152 */ ref-clock-frequency = <26000000>; + tcxo-clock-frequency = <26000000>; }; }; From 41a94b382396f3b33d6426ca8d0ddab237ad8b8a Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Mon, 11 Jan 2016 14:35:24 -0800 Subject: [PATCH 262/325] ARM: dts: Fix omap5 PMIC control lines for RTC writes commit af756bbccff85504ce05c63a50f80b9d7823c500 upstream. The palmas PMIC has two control lines that need to be muxed properly for things to work. The sys_nirq pin is used for interrupts, and msecure pin is used for enabling writes to some PMIC registers. Without these pins configured properly things can fail in mysterious ways. For example, we can't update the RTC registers on palmas PMIC unless the msecure pin is configured. And this is probably the reason why we had RTC missing from the omap5 dts file. According to "OMAP5430 ES2.0 Data Manual [Public] VErsion A (Rev. F)" swps052f.pdf, mux mode 1 is for sys_drm_msecure so in theory there's should be no need to configure it as a GPIO pin. However, it seems there are some reliability issues using the msecure mux mode. And the TI trees configure the msecure pin as GPIO out high instead. As the PMIC only cares that the msecure line is high to allow access to the RTC registers, let's use a GPIO hog as suggested by Nishanth Menon . Also the use of the internal pull was considered but supposedly that may not be capable of keeping the line high in a noisy environment. If we ever see high security omap5 products in the mainline tree, those need to skip the msecure pin muxing and ignore setting the GPIO hog. Chances are the related pin mux registers are locked in that case and the msecure pin is managed by whatever software may be running in the ARM TrustZone. Who knows what the original intention of the msecure pin was. Maybe it was supposed to prevent the system time to be set back for some game demo modes to time out? Anyways, it seems that later PMICs like tps659037 have recycled this pin for "powerhold" and devices like beagle-x15 do not need changes to the msecure pin configuration. To avoid further confusion with TWL variant PMICs, beagle-x15 does not have a back-up battery for RTC palmas. Instead the mcp79410 RTC is used with rtc-ds1307 driver. There is a "powerhold" jumper j5 holes near the palmas PMIC, and shorting it seems to power up beagle-x15 automatically. It is unknown if it also has other side effects to the beagle-x15 power up sequence. Signed-off-by: Tony Lindgren Signed-off-by: Greg Kroah-Hartman --- arch/arm/boot/dts/omap5-board-common.dtsi | 25 +++++++++++++++++++++++ 1 file changed, 25 insertions(+) diff --git a/arch/arm/boot/dts/omap5-board-common.dtsi b/arch/arm/boot/dts/omap5-board-common.dtsi index 5cf76a1c5c75..7de5a7754f1e 100644 --- a/arch/arm/boot/dts/omap5-board-common.dtsi +++ b/arch/arm/boot/dts/omap5-board-common.dtsi @@ -130,6 +130,16 @@ }; }; +&gpio8 { + /* TI trees use GPIO instead of msecure, see also muxing */ + p234 { + gpio-hog; + gpios = <10 GPIO_ACTIVE_HIGH>; + output-high; + line-name = "gpio8_234/msecure"; + }; +}; + &omap5_pmx_core { pinctrl-names = "default"; pinctrl-0 = < @@ -213,6 +223,13 @@ >; }; + /* TI trees use GPIO mode; msecure mode does not work reliably? */ + palmas_msecure_pins: palmas_msecure_pins { + pinctrl-single,pins = < + OMAP5_IOPAD(0x180, PIN_OUTPUT | MUX_MODE6) /* gpio8_234 */ + >; + }; + usbhost_pins: pinmux_usbhost_pins { pinctrl-single,pins = < 0x84 (PIN_INPUT | MUX_MODE0) /* usbb2_hsic_strobe */ @@ -278,6 +295,12 @@ &usbhost_wkup_pins >; + palmas_sys_nirq_pins: pinmux_palmas_sys_nirq_pins { + pinctrl-single,pins = < + OMAP5_IOPAD(0x068, PIN_INPUT_PULLUP | MUX_MODE0) /* sys_nirq1 */ + >; + }; + usbhost_wkup_pins: pinmux_usbhost_wkup_pins { pinctrl-single,pins = < 0x1A (PIN_OUTPUT | MUX_MODE0) /* fref_clk1_out, USB hub clk */ @@ -345,6 +368,8 @@ interrupt-controller; #interrupt-cells = <2>; ti,system-power-controller; + pinctrl-names = "default"; + pinctrl-0 = <&palmas_sys_nirq_pins &palmas_msecure_pins>; extcon_usb3: palmas_usb { compatible = "ti,palmas-usb-vid"; From a482d944816941a8ad987975585ee064dc023325 Mon Sep 17 00:00:00 2001 From: "H. Nikolaus Schaller" Date: Tue, 5 Jan 2016 13:01:37 +0100 Subject: [PATCH 263/325] ARM: dts: omap5-board-common: enable rtc and charging of backup battery commit c08659d431b40ad5beb97d7dde49ad9796cb812c upstream. tested on OMP5432 EVM Signed-off-by: H. Nikolaus Schaller Signed-off-by: Tony Lindgren Signed-off-by: Greg Kroah-Hartman --- arch/arm/boot/dts/omap5-board-common.dtsi | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/arch/arm/boot/dts/omap5-board-common.dtsi b/arch/arm/boot/dts/omap5-board-common.dtsi index 7de5a7754f1e..41e80e7f20be 100644 --- a/arch/arm/boot/dts/omap5-board-common.dtsi +++ b/arch/arm/boot/dts/omap5-board-common.dtsi @@ -383,6 +383,14 @@ #clock-cells = <0>; }; + rtc { + compatible = "ti,palmas-rtc"; + interrupt-parent = <&palmas>; + interrupts = <8 IRQ_TYPE_NONE>; + ti,backup-battery-chargeable; + ti,backup-battery-charge-high-current; + }; + palmas_pmic { compatible = "ti,palmas-pmic"; interrupt-parent = <&palmas>; From 5542d00c46536d09c594c2f604f3d684c62c3f29 Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Fri, 15 Jan 2016 09:30:18 +0100 Subject: [PATCH 264/325] ARM: dts: at91: sama5d4 xplained: properly mux phy interrupt commit f505dba762ae826bb68978a85ee5c8ced7dea8d7 upstream. No interrupt were received from the phy because PIOE 1 may not be properly muxed. It prevented proper link detection, especially since commit 321beec5047a ("net: phy: Use interrupts when available in NOLINK state") disables polling. Signed-off-by: Alexandre Belloni Signed-off-by: Nicolas Ferre Signed-off-by: Greg Kroah-Hartman --- arch/arm/boot/dts/at91-sama5d4_xplained.dts | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/arch/arm/boot/dts/at91-sama5d4_xplained.dts b/arch/arm/boot/dts/at91-sama5d4_xplained.dts index 131614f28e75..8cf9999cb0cd 100644 --- a/arch/arm/boot/dts/at91-sama5d4_xplained.dts +++ b/arch/arm/boot/dts/at91-sama5d4_xplained.dts @@ -86,6 +86,8 @@ macb0: ethernet@f8020000 { phy-mode = "rmii"; status = "okay"; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_macb0_rmii &pinctrl_macb0_phy_irq>; phy0: ethernet-phy@1 { interrupt-parent = <&pioE>; @@ -152,6 +154,10 @@ atmel,pins = ; }; + pinctrl_macb0_phy_irq: macb0_phy_irq_0 { + atmel,pins = + ; + }; }; }; }; From 080fc28fe4759d0d8a64b8980e4e6220a590221e Mon Sep 17 00:00:00 2001 From: Mohamed Jamsheeth Hajanajubudeen Date: Fri, 11 Dec 2015 17:06:26 +0530 Subject: [PATCH 265/325] ARM: dts: at91: sama5d4: fix instance id of DBGU commit 929e883f2bfdf68d4bd3aec43912e956417005c7 upstream. Change instance id of DBGU to 45. Signed-off-by: Mohamed Jamsheeth Hajanajubudeen Fixes: 7c661394c56c ("ARM: at91: dt: add device tree file for SAMA5D4 SoC") Signed-off-by: Nicolas Ferre Signed-off-by: Greg Kroah-Hartman --- arch/arm/boot/dts/sama5d4.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/sama5d4.dtsi b/arch/arm/boot/dts/sama5d4.dtsi index 2193637b9cd2..3daf8d5d7878 100644 --- a/arch/arm/boot/dts/sama5d4.dtsi +++ b/arch/arm/boot/dts/sama5d4.dtsi @@ -1342,7 +1342,7 @@ dbgu: serial@fc069000 { compatible = "atmel,at91sam9260-dbgu", "atmel,at91sam9260-usart"; reg = <0xfc069000 0x200>; - interrupts = <2 IRQ_TYPE_LEVEL_HIGH 7>; + interrupts = <45 IRQ_TYPE_LEVEL_HIGH 7>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_dbgu>; clocks = <&dbgu_clk>; From 3b18631fbcea811634fadacb5a7358170d9e3414 Mon Sep 17 00:00:00 2001 From: Nicolas Ferre Date: Wed, 27 Jan 2016 11:03:02 +0100 Subject: [PATCH 266/325] ARM: dts: at91: sama5d4 xplained: fix phy0 IRQ type commit e873cc022ce5e2c04bbc53b5874494b657e29d3f upstream. For phy0 KSZ8081, the type of GPIO IRQ should be "level low" instead of "edge falling". Signed-off-by: Nicolas Ferre Fixes: 38153a017896 ("ARM: at91/dt: sama5d4: add dts for sama5d4 xplained board") Signed-off-by: Greg Kroah-Hartman --- arch/arm/boot/dts/at91-sama5d4_xplained.dts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/at91-sama5d4_xplained.dts b/arch/arm/boot/dts/at91-sama5d4_xplained.dts index 8cf9999cb0cd..569026e8f96c 100644 --- a/arch/arm/boot/dts/at91-sama5d4_xplained.dts +++ b/arch/arm/boot/dts/at91-sama5d4_xplained.dts @@ -91,7 +91,7 @@ phy0: ethernet-phy@1 { interrupt-parent = <&pioE>; - interrupts = <1 IRQ_TYPE_EDGE_FALLING>; + interrupts = <1 IRQ_TYPE_LEVEL_LOW>; reg = <1>; }; }; From 6ec8b7c5bbdd539878fb23f6040a2c041c43247c Mon Sep 17 00:00:00 2001 From: Wenyou Yang Date: Wed, 27 Jan 2016 13:16:24 +0800 Subject: [PATCH 267/325] ARM: dts: at91: sama5d4ek: add phy address and IRQ for macb0 commit aae6b18f5c95b9dc78de66d1e27e8afeee2763b7 upstream. On SAMA5D4EK board, the Ethernet doesn't work after resuming from the suspend state. Signed-off-by: Wenyou Yang [nicolas.ferre@atmel.com: adapt to newer kernel] Fixes: 38153a017896 ("ARM: at91/dt: sama5d4: add dts for sama5d4 xplained board") Signed-off-by: Nicolas Ferre Signed-off-by: Greg Kroah-Hartman --- arch/arm/boot/dts/at91-sama5d4ek.dts | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/arch/arm/boot/dts/at91-sama5d4ek.dts b/arch/arm/boot/dts/at91-sama5d4ek.dts index 2d4a33100af6..4e98cda97403 100644 --- a/arch/arm/boot/dts/at91-sama5d4ek.dts +++ b/arch/arm/boot/dts/at91-sama5d4ek.dts @@ -160,8 +160,15 @@ }; macb0: ethernet@f8020000 { + pinctrl-0 = <&pinctrl_macb0_rmii &pinctrl_macb0_phy_irq>; phy-mode = "rmii"; status = "okay"; + + ethernet-phy@1 { + reg = <0x1>; + interrupt-parent = <&pioE>; + interrupts = <1 IRQ_TYPE_LEVEL_LOW>; + }; }; mmc1: mmc@fc000000 { @@ -193,6 +200,10 @@ pinctrl@fc06a000 { board { + pinctrl_macb0_phy_irq: macb0_phy_irq { + atmel,pins = + ; + }; pinctrl_mmc0_cd: mmc0_cd { atmel,pins = ; From ec776d670e2d1f6034fac2f1a28ff972776bba52 Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Thu, 14 Jan 2016 12:20:47 -0800 Subject: [PATCH 268/325] ARM: OMAP2+: Fix wait_dll_lock_timed for rodata commit d9db59103305eb5ec2a86369f32063e9921b6ac5 upstream. We don't want to be writing to .text so it can be set rodata. Fix error "Unable to handle kernel paging request at virtual address c012396c" in wait_dll_lock_timed if CONFIG_DEBUG_RODATA is selected. As these counters are for debugging only and unused, we can just remove them. Cc: Kees Cook Cc: Laura Abbott Cc: Nishanth Menon Cc: Richard Woodruff Cc: Russell King Cc: Tero Kristo Acked-by: Nicolas Pitre Fixes: 1e6b48116a95 ("ARM: mm: allow non-text sections to be non-executable") Signed-off-by: Tony Lindgren Signed-off-by: Greg Kroah-Hartman --- arch/arm/mach-omap2/sleep34xx.S | 22 ---------------------- 1 file changed, 22 deletions(-) diff --git a/arch/arm/mach-omap2/sleep34xx.S b/arch/arm/mach-omap2/sleep34xx.S index eafd120b53f1..787cfda7a9b3 100644 --- a/arch/arm/mach-omap2/sleep34xx.S +++ b/arch/arm/mach-omap2/sleep34xx.S @@ -289,12 +289,6 @@ wait_sdrc_ready: bic r5, r5, #0x40 str r5, [r4] -/* - * PC-relative stores lead to undefined behaviour in Thumb-2: use a r7 as a - * base instead. - * Be careful not to clobber r7 when maintaing this code. - */ - is_dll_in_lock_mode: /* Is dll in lock mode? */ ldr r4, sdrc_dlla_ctrl @@ -302,11 +296,7 @@ is_dll_in_lock_mode: tst r5, #0x4 bne exit_nonoff_modes @ Return if locked /* wait till dll locks */ - adr r7, kick_counter wait_dll_lock_timed: - ldr r4, wait_dll_lock_counter - add r4, r4, #1 - str r4, [r7, #wait_dll_lock_counter - kick_counter] ldr r4, sdrc_dlla_status /* Wait 20uS for lock */ mov r6, #8 @@ -330,9 +320,6 @@ kick_dll: orr r6, r6, #(1<<3) @ enable dll str r6, [r4] dsb - ldr r4, kick_counter - add r4, r4, #1 - str r4, [r7] @ kick_counter b wait_dll_lock_timed exit_nonoff_modes: @@ -360,15 +347,6 @@ sdrc_dlla_status: .word SDRC_DLLA_STATUS_V sdrc_dlla_ctrl: .word SDRC_DLLA_CTRL_V - /* - * When exporting to userspace while the counters are in SRAM, - * these 2 words need to be at the end to facilitate retrival! - */ -kick_counter: - .word 0 -wait_dll_lock_counter: - .word 0 - ENTRY(omap3_do_wfi_sz) .word . - omap3_do_wfi From 98b3f17a7235cb49755c6bd17fc428381261105c Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Thu, 14 Jan 2016 12:20:47 -0800 Subject: [PATCH 269/325] ARM: OMAP2+: Fix l2_inv_api_params for rodata commit 0a0b13275558c32bbf6241464a7244b1ffd5afb3 upstream. We don't want to write to .text, so let's move l2_inv_api_params to .data and access it via a pointer. Cc: Kees Cook Cc: Laura Abbott Cc: Nishanth Menon Cc: Richard Woodruff Cc: Russell King Cc: Tero Kristo Acked-by: Nicolas Pitre Fixes: 1e6b48116a95 ("ARM: mm: allow non-text sections to be non-executable") Signed-off-by: Tony Lindgren Signed-off-by: Greg Kroah-Hartman --- arch/arm/mach-omap2/sleep34xx.S | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/arch/arm/mach-omap2/sleep34xx.S b/arch/arm/mach-omap2/sleep34xx.S index 787cfda7a9b3..920b22828280 100644 --- a/arch/arm/mach-omap2/sleep34xx.S +++ b/arch/arm/mach-omap2/sleep34xx.S @@ -427,12 +427,14 @@ skipl2dis: and r1, #0x700 cmp r1, #0x300 beq l2_inv_gp + adr r0, l2_inv_api_params_offset + ldr r3, [r0] + add r3, r3, r0 @ r3 points to dummy parameters mov r0, #40 @ set service ID for PPA mov r12, r0 @ copy secure Service ID in r12 mov r1, #0 @ set task id for ROM code in r1 mov r2, #4 @ set some flags in r2, r6 mov r6, #0xff - adr r3, l2_inv_api_params @ r3 points to dummy parameters dsb @ data write barrier dmb @ data memory barrier smc #1 @ call SMI monitor (smi #1) @@ -466,8 +468,8 @@ skipl2dis: b logic_l1_restore .align -l2_inv_api_params: - .word 0x1, 0x00 +l2_inv_api_params_offset: + .long l2_inv_api_params - . l2_inv_gp: /* Execute smi to invalidate L2 cache */ mov r12, #0x1 @ set up to invalidate L2 @@ -516,6 +518,10 @@ control_mem_rta: l2dis_3630: .word 0 + .data +l2_inv_api_params: + .word 0x1, 0x00 + /* * Internal functions */ From 31a50ee1ad3e0cc51a75fb052115fcf5a804ab35 Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Thu, 14 Jan 2016 12:20:47 -0800 Subject: [PATCH 270/325] ARM: OMAP2+: Fix l2dis_3630 for rodata commit eeaf9646aca89d097861caa24d9818434e48810e upstream. We don't want to write to .text section. Let's move l2dis_3630 to .data and access it via a pointer. For calculating the offset, let's optimize out the add and do it in ldr/str as suggested by Nicolas Pitre . Cc: Kees Cook Cc: Laura Abbott Cc: Nishanth Menon Cc: Richard Woodruff Cc: Russell King Cc: Tero Kristo Acked-by: Nicolas Pitre Fixes: 1e6b48116a95 ("ARM: mm: allow non-text sections to be non-executable") Signed-off-by: Tony Lindgren Signed-off-by: Greg Kroah-Hartman --- arch/arm/mach-omap2/sleep34xx.S | 17 +++++++++++++---- 1 file changed, 13 insertions(+), 4 deletions(-) diff --git a/arch/arm/mach-omap2/sleep34xx.S b/arch/arm/mach-omap2/sleep34xx.S index 920b22828280..73f7aa5dfc93 100644 --- a/arch/arm/mach-omap2/sleep34xx.S +++ b/arch/arm/mach-omap2/sleep34xx.S @@ -86,8 +86,9 @@ ENTRY(enable_omap3630_toggle_l2_on_restore) stmfd sp!, {lr} @ save registers on stack /* Setup so that we will disable and enable l2 */ mov r1, #0x1 - adrl r2, l2dis_3630 @ may be too distant for plain adr - str r1, [r2] + adrl r3, l2dis_3630_offset @ may be too distant for plain adr + ldr r2, [r3] @ value for offset + str r1, [r2, r3] @ write to l2dis_3630 ldmfd sp!, {pc} @ restore regs and return ENDPROC(enable_omap3630_toggle_l2_on_restore) @@ -415,7 +416,9 @@ ENTRY(omap3_restore) cmp r2, #0x0 @ Check if target power state was OFF or RET bne logic_l1_restore - ldr r0, l2dis_3630 + adr r1, l2dis_3630_offset @ address for offset + ldr r0, [r1] @ value for offset + ldr r0, [r1, r0] @ value at l2dis_3630 cmp r0, #0x1 @ should we disable L2 on 3630? bne skipl2dis mrc p15, 0, r0, c1, c0, 1 @@ -486,7 +489,9 @@ l2_inv_gp: mov r12, #0x2 smc #0 @ Call SMI monitor (smieq) logic_l1_restore: - ldr r1, l2dis_3630 + adr r0, l2dis_3630_offset @ adress for offset + ldr r1, [r0] @ value for offset + ldr r1, [r0, r1] @ value at l2dis_3630 cmp r1, #0x1 @ Test if L2 re-enable needed on 3630 bne skipl2reen mrc p15, 0, r1, c1, c0, 1 @@ -515,6 +520,10 @@ control_stat: .word CONTROL_STAT control_mem_rta: .word CONTROL_MEM_RTA_CTRL +l2dis_3630_offset: + .long l2dis_3630 - . + + .data l2dis_3630: .word 0 From 82de5956e9f4102e7b29d6718abaf0d156cdbc2a Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Thu, 14 Jan 2016 12:20:47 -0800 Subject: [PATCH 271/325] ARM: OMAP2+: Fix save_secure_ram_context for rodata commit a5311d4d13df80bd71a9e47f9ecaf327f478fab1 upstream. We don't want to write to .text and we can move save_secure_ram_context into .data as it all gets copied into SRAM anyways. Cc: Kees Cook Cc: Laura Abbott Cc: Nishanth Menon Cc: Richard Woodruff Cc: Russell King Cc: Sergei Shtylyov Cc: Tero Kristo Acked-by: Nicolas Pitre Fixes: 1e6b48116a95 ("ARM: mm: allow non-text sections to be non-executable") Signed-off-by: Tony Lindgren Signed-off-by: Greg Kroah-Hartman --- arch/arm/mach-omap2/sleep34xx.S | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/arch/arm/mach-omap2/sleep34xx.S b/arch/arm/mach-omap2/sleep34xx.S index 73f7aa5dfc93..1b9f0520dea9 100644 --- a/arch/arm/mach-omap2/sleep34xx.S +++ b/arch/arm/mach-omap2/sleep34xx.S @@ -92,8 +92,12 @@ ENTRY(enable_omap3630_toggle_l2_on_restore) ldmfd sp!, {pc} @ restore regs and return ENDPROC(enable_omap3630_toggle_l2_on_restore) - .text -/* Function to call rom code to save secure ram context */ +/* + * Function to call rom code to save secure ram context. This gets + * relocated to SRAM, so it can be all in .data section. Otherwise + * we need to initialize api_params separately. + */ + .data .align 3 ENTRY(save_secure_ram_context) stmfd sp!, {r4 - r11, lr} @ save registers on stack @@ -127,6 +131,8 @@ ENDPROC(save_secure_ram_context) ENTRY(save_secure_ram_context_sz) .word . - save_secure_ram_context + .text + /* * ====================== * == Idle entry point == From a6e01f0c81d54678cdd50892462d12b672320e5e Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Thu, 14 Jan 2016 12:20:48 -0800 Subject: [PATCH 272/325] ARM: OMAP2+: Fix ppa_zero_params and ppa_por_params for rodata commit 4da597d16602d14405b71a18d45e1c59f28f0fd2 upstream. We don't want to write to .text so let's move ppa_zero_params and ppa_por_params to .data and access them via pointers. Note that I have not been able to test as we I don't have a HS omap4 to test with. The code has been changed in similar way as for omap3 though. Cc: Kees Cook Cc: Laura Abbott Cc: Nishanth Menon Cc: Richard Woodruff Cc: Russell King Cc: Tero Kristo Acked-by: Nicolas Pitre Fixes: 1e6b48116a95 ("ARM: mm: allow non-text sections to be non-executable") Signed-off-by: Tony Lindgren Signed-off-by: Greg Kroah-Hartman --- arch/arm/mach-omap2/sleep44xx.S | 25 +++++++++++++++++-------- 1 file changed, 17 insertions(+), 8 deletions(-) diff --git a/arch/arm/mach-omap2/sleep44xx.S b/arch/arm/mach-omap2/sleep44xx.S index 9b09d85d811a..c7a3b4aab4b5 100644 --- a/arch/arm/mach-omap2/sleep44xx.S +++ b/arch/arm/mach-omap2/sleep44xx.S @@ -29,12 +29,6 @@ dsb .endm -ppa_zero_params: - .word 0x0 - -ppa_por_params: - .word 1, 0 - #ifdef CONFIG_ARCH_OMAP4 /* @@ -266,7 +260,9 @@ ENTRY(omap4_cpu_resume) beq skip_ns_smp_enable ppa_actrl_retry: mov r0, #OMAP4_PPA_CPU_ACTRL_SMP_INDEX - adr r3, ppa_zero_params @ Pointer to parameters + adr r1, ppa_zero_params_offset + ldr r3, [r1] + add r3, r3, r1 @ Pointer to ppa_zero_params mov r1, #0x0 @ Process ID mov r2, #0x4 @ Flag mov r6, #0xff @@ -303,7 +299,9 @@ skip_ns_smp_enable: ldr r0, =OMAP4_PPA_L2_POR_INDEX ldr r1, =OMAP44XX_SAR_RAM_BASE ldr r4, [r1, #L2X0_PREFETCH_CTRL_OFFSET] - adr r3, ppa_por_params + adr r1, ppa_por_params_offset + ldr r3, [r1] + add r3, r3, r1 @ Pointer to ppa_por_params str r4, [r3, #0x04] mov r1, #0x0 @ Process ID mov r2, #0x4 @ Flag @@ -328,6 +326,8 @@ skip_l2en: #endif b cpu_resume @ Jump to generic resume +ppa_por_params_offset: + .long ppa_por_params - . ENDPROC(omap4_cpu_resume) #endif /* CONFIG_ARCH_OMAP4 */ @@ -380,4 +380,13 @@ ENTRY(omap_do_wfi) nop ldmfd sp!, {pc} +ppa_zero_params_offset: + .long ppa_zero_params - . ENDPROC(omap_do_wfi) + + .data +ppa_zero_params: + .word 0 + +ppa_por_params: + .word 1, 0 From 593337c55ac30807f38ca924e716edfdc4e6a916 Mon Sep 17 00:00:00 2001 From: Marek Szyprowski Date: Tue, 16 Feb 2016 15:14:44 +0100 Subject: [PATCH 273/325] arm64: dma-mapping: fix handling of devices registered before arch_initcall commit 722ec35f7faefcc34d12616eca7976a848870f9d upstream. This patch ensures that devices, which got registered before arch_initcall will be handled correctly by IOMMU-based DMA-mapping code. Fixes: 13b8629f6511 ("arm64: Add IOMMU dma_ops") Acked-by: Robin Murphy Signed-off-by: Marek Szyprowski Signed-off-by: Will Deacon Signed-off-by: Greg Kroah-Hartman --- arch/arm64/mm/dma-mapping.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c index 7963aa4b5d28..354144e33218 100644 --- a/arch/arm64/mm/dma-mapping.c +++ b/arch/arm64/mm/dma-mapping.c @@ -933,6 +933,10 @@ static int __init __iommu_dma_init(void) ret = register_iommu_dma_ops_notifier(&platform_bus_type); if (!ret) ret = register_iommu_dma_ops_notifier(&amba_bustype); + + /* handle devices queued before this arch_initcall */ + if (!ret) + __iommu_attach_notifier(NULL, BUS_NOTIFY_ADD_DEVICE, NULL); return ret; } arch_initcall(__iommu_dma_init); From b3e336de65ebdd5ed85ba1f03216091a28583e7e Mon Sep 17 00:00:00 2001 From: Andre Przywara Date: Wed, 3 Feb 2016 16:56:51 +0000 Subject: [PATCH 274/325] KVM: arm/arm64: Fix reference to uninitialised VGIC commit b3aff6ccbb1d25e506b60ccd9c559013903f3464 upstream. Commit 4b4b4512da2a ("arm/arm64: KVM: Rework the arch timer to use level-triggered semantics") brought the virtual architected timer closer to the VGIC. There is one occasion were we don't properly check for the VGIC actually having been initialized before, but instead go on to check the active state of some IRQ number. If userland hasn't instantiated a virtual GIC, we end up with a kernel NULL pointer dereference: ========= Unable to handle kernel NULL pointer dereference at virtual address 00000000 pgd = ffffffc9745c5000 [00000000] *pgd=00000009f631e003, *pud=00000009f631e003, *pmd=0000000000000000 Internal error: Oops: 96000006 [#2] PREEMPT SMP Modules linked in: CPU: 0 PID: 2144 Comm: kvm_simplest-ar Tainted: G D 4.5.0-rc2+ #1300 Hardware name: ARM Juno development board (r1) (DT) task: ffffffc976da8000 ti: ffffffc976e28000 task.ti: ffffffc976e28000 PC is at vgic_bitmap_get_irq_val+0x78/0x90 LR is at kvm_vgic_map_is_active+0xac/0xc8 pc : [] lr : [] pstate: 20000145 .... ========= Fix this by bailing out early of kvm_timer_flush_hwstate() if we don't have a VGIC at all. Reported-by: Cosmin Gorgovan Acked-by: Marc Zyngier Signed-off-by: Andre Przywara Signed-off-by: Marc Zyngier Signed-off-by: Greg Kroah-Hartman --- virt/kvm/arm/arch_timer.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/virt/kvm/arm/arch_timer.c b/virt/kvm/arm/arch_timer.c index 69bca185c471..ea6064696fe4 100644 --- a/virt/kvm/arm/arch_timer.c +++ b/virt/kvm/arm/arch_timer.c @@ -143,7 +143,7 @@ static void kvm_timer_update_irq(struct kvm_vcpu *vcpu, bool new_level) * Check if there was a change in the timer state (should we raise or lower * the line level to the GIC). */ -static void kvm_timer_update_state(struct kvm_vcpu *vcpu) +static int kvm_timer_update_state(struct kvm_vcpu *vcpu) { struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu; @@ -154,10 +154,12 @@ static void kvm_timer_update_state(struct kvm_vcpu *vcpu) * until we call this function from kvm_timer_flush_hwstate. */ if (!vgic_initialized(vcpu->kvm)) - return; + return -ENODEV; if (kvm_timer_should_fire(vcpu) != timer->irq.level) kvm_timer_update_irq(vcpu, !timer->irq.level); + + return 0; } /* @@ -218,7 +220,8 @@ void kvm_timer_flush_hwstate(struct kvm_vcpu *vcpu) bool phys_active; int ret; - kvm_timer_update_state(vcpu); + if (kvm_timer_update_state(vcpu)) + return; /* * If we enter the guest with the virtual input level to the VGIC From 921fa9b77380b0c3df67c424c2a68db5214ab461 Mon Sep 17 00:00:00 2001 From: Thomas Huth Date: Fri, 20 Nov 2015 09:11:45 +0100 Subject: [PATCH 275/325] KVM: PPC: Fix emulation of H_SET_DABR/X on POWER8 commit 760a7364f27d974d100118d88190e574626e18a6 upstream. In the old DABR register, the BT (Breakpoint Translation) bit is bit number 61. In the new DAWRX register, the WT (Watchpoint Translation) bit is bit number 59. So to move the DABR-BT bit into the position of the DAWRX-WT bit, it has to be shifted by two, not only by one. This fixes hardware watchpoints in gdb of older guests that only use the H_SET_DABR/X interface instead of the new H_SET_MODE interface. Signed-off-by: Thomas Huth Reviewed-by: Laurent Vivier Reviewed-by: David Gibson Signed-off-by: Paul Mackerras Signed-off-by: Greg Kroah-Hartman --- arch/powerpc/kvm/book3s_hv_rmhandlers.S | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index 3c6badcd53ef..e57cc383e5da 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -2153,7 +2153,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) /* Emulate H_SET_DABR/X on P8 for the sake of compat mode guests */ 2: rlwimi r5, r4, 5, DAWRX_DR | DAWRX_DW - rlwimi r5, r4, 1, DAWRX_WT + rlwimi r5, r4, 2, DAWRX_WT clrrdi r4, r4, 3 std r4, VCPU_DAWR(r3) std r5, VCPU_DAWRX(r3) From b58731d6263a323e602191257628d93c2274cefa Mon Sep 17 00:00:00 2001 From: Greg Kurz Date: Wed, 13 Jan 2016 18:28:17 +0100 Subject: [PATCH 276/325] KVM: PPC: Fix ONE_REG AltiVec support commit b4d7f161feb3015d6306e1d35b565c888ff70c9d upstream. The get and set operations got exchanged by mistake when moving the code from book3s.c to powerpc.c. Fixes: 3840edc8033ad5b86deee309c1c321ca54257452 Signed-off-by: Greg Kurz Signed-off-by: Paul Mackerras Signed-off-by: Greg Kroah-Hartman --- arch/powerpc/kvm/powerpc.c | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 6fd2405c7f4a..a3b182dcb823 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -919,21 +919,17 @@ int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg) r = -ENXIO; break; } - vcpu->arch.vr.vr[reg->id - KVM_REG_PPC_VR0] = val.vval; + val.vval = vcpu->arch.vr.vr[reg->id - KVM_REG_PPC_VR0]; break; case KVM_REG_PPC_VSCR: if (!cpu_has_feature(CPU_FTR_ALTIVEC)) { r = -ENXIO; break; } - vcpu->arch.vr.vscr.u[3] = set_reg_val(reg->id, val); + val = get_reg_val(reg->id, vcpu->arch.vr.vscr.u[3]); break; case KVM_REG_PPC_VRSAVE: - if (!cpu_has_feature(CPU_FTR_ALTIVEC)) { - r = -ENXIO; - break; - } - vcpu->arch.vrsave = set_reg_val(reg->id, val); + val = get_reg_val(reg->id, vcpu->arch.vrsave); break; #endif /* CONFIG_ALTIVEC */ default: @@ -974,17 +970,21 @@ int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg) r = -ENXIO; break; } - val.vval = vcpu->arch.vr.vr[reg->id - KVM_REG_PPC_VR0]; + vcpu->arch.vr.vr[reg->id - KVM_REG_PPC_VR0] = val.vval; break; case KVM_REG_PPC_VSCR: if (!cpu_has_feature(CPU_FTR_ALTIVEC)) { r = -ENXIO; break; } - val = get_reg_val(reg->id, vcpu->arch.vr.vscr.u[3]); + vcpu->arch.vr.vscr.u[3] = set_reg_val(reg->id, val); break; case KVM_REG_PPC_VRSAVE: - val = get_reg_val(reg->id, vcpu->arch.vrsave); + if (!cpu_has_feature(CPU_FTR_ALTIVEC)) { + r = -ENXIO; + break; + } + vcpu->arch.vrsave = set_reg_val(reg->id, val); break; #endif /* CONFIG_ALTIVEC */ default: From a6a3f3ddf6a663ab3d141f0e13f457b084a8c409 Mon Sep 17 00:00:00 2001 From: Ravi Bangoria Date: Mon, 7 Dec 2015 12:25:02 +0530 Subject: [PATCH 277/325] perf kvm record/report: 'unprocessable sample' error while recording/reporting guest data commit 3caeaa562733c4836e61086ec07666635006a787 upstream. While recording guest samples in host using perf kvm record, it will populate unprocessable sample error, though samples will be recorded properly. While generating report using perf kvm report, no samples will be processed and same error will populate. We have seen this behaviour with upstream perf(4.4-rc3) on x86 and ppc64 hardware. Reason behind this failure is, when it tries to fetch machine from rb_tree of machines, it fails. As a part of tracing a bug, we figured out that this code was incorrectly refactored in commit 54245fdc3576 ("perf session: Remove wrappers to machines__find"). This patch will change the functionality such that if it can't fetch machine in first trial, it will create one node of machine and add that to rb_tree. So next time when it tries to fetch same machine from rb_tree, it won't fail. Actually it was the case before refactoring of code in aforementioned commit. This patch is generated from acme perf/core branch. Below I've mention an example that demonstrate the behaviour before and after applying patch. Before applying patch: [Note: One needs to run guest before recording data in host] ravi@ravi-bangoria:~$ ./perf kvm record -a Warning: 5903 unprocessable samples recorded. Do you have a KVM guest running and not using 'perf kvm'? [ perf record: Captured and wrote 1.409 MB perf.data.guest (285 samples) ] ravi@ravi-bangoria:~$ ./perf kvm report --stdio Warning: 5903 unprocessable samples recorded. Do you have a KVM guest running and not using 'perf kvm'? # To display the perf.data header info, please use --header/--header-only options. # # Total Lost Samples: 0 # # Samples: 285 of event 'cycles' # Event count (approx.): 88715406 # # Overhead Command Shared Object Symbol # ........ ....... ............. ...... # # (For a higher level overview, try: perf report --sort comm,dso) # After applying patch: ravi@ravi-bangoria:~$ ./perf kvm record -a [ perf record: Captured and wrote 1.188 MB perf.data.guest (17 samples) ] ravi@ravi-bangoria:~$ ./perf kvm report --stdio # To display the perf.data header info, please use --header/--header-only options. # # Total Lost Samples: 0 # # Samples: 17 of event 'cycles' # Event count (approx.): 700746 # # Overhead Command Shared Object Symbol # ........ ....... ................ ...................... # 34.19% :5758 [unknown] [g] 0xffffffff818682ab 22.79% :5758 [unknown] [g] 0xffffffff812dc7f8 22.79% :5758 [unknown] [g] 0xffffffff818650d0 14.83% :5758 [unknown] [g] 0xffffffff8161a1b6 2.49% :5758 [unknown] [g] 0xffffffff818692bf 0.48% :5758 [unknown] [g] 0xffffffff81869253 0.05% :5758 [unknown] [g] 0xffffffff81869250 Signed-off-by: Ravi Bangoria Cc: Naveen N. Rao Fixes: 54245fdc3576 ("perf session: Remove wrappers to machines__find") Link: http://lkml.kernel.org/r/1449471302-11283-1-git-send-email-ravi.bangoria@linux.vnet.ibm.com Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Greg Kroah-Hartman --- tools/perf/util/session.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index c35ffdd360fe..468de95bc8bb 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -972,7 +972,7 @@ static struct machine *machines__find_for_cpumode(struct machines *machines, machine = machines__find(machines, pid); if (!machine) - machine = machines__find(machines, DEFAULT_GUEST_KERNEL_ID); + machine = machines__findnew(machines, DEFAULT_GUEST_KERNEL_ID); return machine; } From bd55913cf20804d2c3d4d83e79d9867963af2ff1 Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Fri, 15 Jan 2016 16:54:03 -0800 Subject: [PATCH 278/325] mm: soft-offline: check return value in second __get_any_page() call commit d96b339f453997f2f08c52da3f41423be48c978f upstream. I saw the following BUG_ON triggered in a testcase where a process calls madvise(MADV_SOFT_OFFLINE) on thps, along with a background process that calls migratepages command repeatedly (doing ping-pong among different NUMA nodes) for the first process: Soft offlining page 0x60000 at 0x700000600000 __get_any_page: 0x60000 free buddy page page:ffffea0001800000 count:0 mapcount:-127 mapping: (null) index:0x1 flags: 0x1fffc0000000000() page dumped because: VM_BUG_ON_PAGE(atomic_read(&page->_count) == 0) ------------[ cut here ]------------ kernel BUG at /src/linux-dev/include/linux/mm.h:342! invalid opcode: 0000 [#1] SMP DEBUG_PAGEALLOC Modules linked in: cfg80211 rfkill crc32c_intel serio_raw virtio_balloon i2c_piix4 virtio_blk virtio_net ata_generic pata_acpi CPU: 3 PID: 3035 Comm: test_alloc_gene Tainted: G O 4.4.0-rc8-v4.4-rc8-160107-1501-00000-rc8+ #74 Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011 task: ffff88007c63d5c0 ti: ffff88007c210000 task.ti: ffff88007c210000 RIP: 0010:[] [] put_page+0x5c/0x60 RSP: 0018:ffff88007c213e00 EFLAGS: 00010246 Call Trace: put_hwpoison_page+0x4e/0x80 soft_offline_page+0x501/0x520 SyS_madvise+0x6bc/0x6f0 entry_SYSCALL_64_fastpath+0x12/0x6a Code: 8b fc ff ff 5b 5d c3 48 89 df e8 b0 fa ff ff 48 89 df 31 f6 e8 c6 7d ff ff 5b 5d c3 48 c7 c6 08 54 a2 81 48 89 df e8 a4 c5 01 00 <0f> 0b 66 90 66 66 66 66 90 55 48 89 e5 41 55 41 54 53 48 8b 47 RIP [] put_page+0x5c/0x60 RSP The root cause resides in get_any_page() which retries to get a refcount of the page to be soft-offlined. This function calls put_hwpoison_page(), expecting that the target page is putback to LRU list. But it can be also freed to buddy. So the second check need to care about such case. Fixes: af8fae7c0886 ("mm/memory-failure.c: clean up soft_offline_page()") Signed-off-by: Naoya Horiguchi Cc: Sasha Levin Cc: Aneesh Kumar K.V Cc: Vlastimil Babka Cc: Jerome Marchand Cc: Andrea Arcangeli Cc: Hugh Dickins Cc: Dave Hansen Cc: Mel Gorman Cc: Rik van Riel Cc: Steve Capper Cc: Johannes Weiner Cc: Michal Hocko Cc: Christoph Lameter Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- mm/memory-failure.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 8424b64711ac..750b7893ee3a 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1572,7 +1572,7 @@ static int get_any_page(struct page *page, unsigned long pfn, int flags) * Did it turn free? */ ret = __get_any_page(page, pfn, 0); - if (!PageLRU(page)) { + if (ret == 1 && !PageLRU(page)) { /* Drop page reference which is from __get_any_page() */ put_hwpoison_page(page); pr_info("soft_offline: %#lx: unknown non LRU page type %lx\n", From 6e8ea2f2258caf0d2a876b36c15a93788a7cde93 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Tue, 5 Jan 2016 18:37:23 -0800 Subject: [PATCH 279/325] libnvdimm: fix namespace object confusion in is_uuid_busy() commit e07ecd76d4db7bda1e9495395b2110a3fe28845a upstream. When btt devices were re-worked to be child devices of regions this routine was overlooked. It mistakenly attempts to_nd_namespace_pmem() or to_nd_namespace_blk() conversions on btt and pfn devices. By luck to date we have happened to be hitting valid memory leading to a uuid miscompare, but a recent change to struct nd_namespace_common causes: BUG: unable to handle kernel NULL pointer dereference at 0000000000000001 IP: [] memcmp+0xc/0x40 [..] Call Trace: [] is_uuid_busy+0xc1/0x2a0 [libnvdimm] [] ? to_nd_blk_region+0x50/0x50 [libnvdimm] [] device_for_each_child+0x50/0x90 Signed-off-by: Dan Williams Signed-off-by: Greg Kroah-Hartman --- drivers/nvdimm/namespace_devs.c | 53 +++++++++++++++++++++++++++++++ drivers/nvdimm/region_devs.c | 56 --------------------------------- 2 files changed, 53 insertions(+), 56 deletions(-) diff --git a/drivers/nvdimm/namespace_devs.c b/drivers/nvdimm/namespace_devs.c index 0955b2cb10fe..62120c38d56b 100644 --- a/drivers/nvdimm/namespace_devs.c +++ b/drivers/nvdimm/namespace_devs.c @@ -77,6 +77,59 @@ static bool is_namespace_io(struct device *dev) return dev ? dev->type == &namespace_io_device_type : false; } +static int is_uuid_busy(struct device *dev, void *data) +{ + u8 *uuid1 = data, *uuid2 = NULL; + + if (is_namespace_pmem(dev)) { + struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev); + + uuid2 = nspm->uuid; + } else if (is_namespace_blk(dev)) { + struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev); + + uuid2 = nsblk->uuid; + } else if (is_nd_btt(dev)) { + struct nd_btt *nd_btt = to_nd_btt(dev); + + uuid2 = nd_btt->uuid; + } else if (is_nd_pfn(dev)) { + struct nd_pfn *nd_pfn = to_nd_pfn(dev); + + uuid2 = nd_pfn->uuid; + } + + if (uuid2 && memcmp(uuid1, uuid2, NSLABEL_UUID_LEN) == 0) + return -EBUSY; + + return 0; +} + +static int is_namespace_uuid_busy(struct device *dev, void *data) +{ + if (is_nd_pmem(dev) || is_nd_blk(dev)) + return device_for_each_child(dev, data, is_uuid_busy); + return 0; +} + +/** + * nd_is_uuid_unique - verify that no other namespace has @uuid + * @dev: any device on a nvdimm_bus + * @uuid: uuid to check + */ +bool nd_is_uuid_unique(struct device *dev, u8 *uuid) +{ + struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(dev); + + if (!nvdimm_bus) + return false; + WARN_ON_ONCE(!is_nvdimm_bus_locked(&nvdimm_bus->dev)); + if (device_for_each_child(&nvdimm_bus->dev, uuid, + is_namespace_uuid_busy) != 0) + return false; + return true; +} + bool pmem_should_map_pages(struct device *dev) { struct nd_region *nd_region = to_nd_region(dev->parent); diff --git a/drivers/nvdimm/region_devs.c b/drivers/nvdimm/region_devs.c index 529f3f02e7b2..9521696c9385 100644 --- a/drivers/nvdimm/region_devs.c +++ b/drivers/nvdimm/region_devs.c @@ -134,62 +134,6 @@ int nd_region_to_nstype(struct nd_region *nd_region) } EXPORT_SYMBOL(nd_region_to_nstype); -static int is_uuid_busy(struct device *dev, void *data) -{ - struct nd_region *nd_region = to_nd_region(dev->parent); - u8 *uuid = data; - - switch (nd_region_to_nstype(nd_region)) { - case ND_DEVICE_NAMESPACE_PMEM: { - struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev); - - if (!nspm->uuid) - break; - if (memcmp(uuid, nspm->uuid, NSLABEL_UUID_LEN) == 0) - return -EBUSY; - break; - } - case ND_DEVICE_NAMESPACE_BLK: { - struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev); - - if (!nsblk->uuid) - break; - if (memcmp(uuid, nsblk->uuid, NSLABEL_UUID_LEN) == 0) - return -EBUSY; - break; - } - default: - break; - } - - return 0; -} - -static int is_namespace_uuid_busy(struct device *dev, void *data) -{ - if (is_nd_pmem(dev) || is_nd_blk(dev)) - return device_for_each_child(dev, data, is_uuid_busy); - return 0; -} - -/** - * nd_is_uuid_unique - verify that no other namespace has @uuid - * @dev: any device on a nvdimm_bus - * @uuid: uuid to check - */ -bool nd_is_uuid_unique(struct device *dev, u8 *uuid) -{ - struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(dev); - - if (!nvdimm_bus) - return false; - WARN_ON_ONCE(!is_nvdimm_bus_locked(&nvdimm_bus->dev)); - if (device_for_each_child(&nvdimm_bus->dev, uuid, - is_namespace_uuid_busy) != 0) - return false; - return true; -} - static ssize_t size_show(struct device *dev, struct device_attribute *attr, char *buf) { From 918a2c388ed7828fa4b6ccb5cacd9e422f30938c Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Thu, 21 Jan 2016 16:40:27 -0800 Subject: [PATCH 280/325] mm: fix mlock accouting commit 7162a1e87b3e380133dadc7909081bb70d0a7041 upstream. Tetsuo Handa reported underflow of NR_MLOCK on munlock. Testcase: #include #include #include #define BASE ((void *)0x400000000000) #define SIZE (1UL << 21) int main(int argc, char *argv[]) { void *addr; system("grep Mlocked /proc/meminfo"); addr = mmap(BASE, SIZE, PROT_READ | PROT_WRITE, MAP_ANONYMOUS | MAP_PRIVATE | MAP_LOCKED | MAP_FIXED, -1, 0); if (addr == MAP_FAILED) printf("mmap() failed\n"), exit(1); munmap(addr, SIZE); system("grep Mlocked /proc/meminfo"); return 0; } It happens on munlock_vma_page() due to unfortunate choice of nr_pages data type: __mod_zone_page_state(zone, NR_MLOCK, -nr_pages); For unsigned int nr_pages, implicitly casted to long in __mod_zone_page_state(), it becomes something around UINT_MAX. munlock_vma_page() usually called for THP as small pages go though pagevec. Let's make nr_pages signed int. Similar fixes in 6cdb18ad98a4 ("mm/vmstat: fix overflow in mod_zone_page_state()") used `long' type, but `int' here is OK for a count of the number of sub-pages in a huge page. Fixes: ff6a6da60b89 ("mm: accelerate munlock() treatment of THP pages") Signed-off-by: Kirill A. Shutemov Reported-by: Tetsuo Handa Tested-by: Tetsuo Handa Cc: Michel Lespinasse Acked-by: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- mm/mlock.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/mlock.c b/mm/mlock.c index 339d9e0949b6..d6006b146fea 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -172,7 +172,7 @@ static void __munlock_isolation_failed(struct page *page) */ unsigned int munlock_vma_page(struct page *page) { - unsigned int nr_pages; + int nr_pages; struct zone *zone = page_zone(page); /* For try_to_munlock() and to serialize with page migration */ From 413aab16bc7b9b58fb1a52010eb3af3d227d7007 Mon Sep 17 00:00:00 2001 From: Konstantin Khlebnikov Date: Fri, 5 Feb 2016 15:36:50 -0800 Subject: [PATCH 281/325] mm: replace vma_lock_anon_vma with anon_vma_lock_read/write commit 12352d3cae2cebe18805a91fab34b534d7444231 upstream. Sequence vma_lock_anon_vma() - vma_unlock_anon_vma() isn't safe if anon_vma appeared between lock and unlock. We have to check anon_vma first or call anon_vma_prepare() to be sure that it's here. There are only few users of these legacy helpers. Let's get rid of them. This patch fixes anon_vma lock imbalance in validate_mm(). Write lock isn't required here, read lock is enough. And reorders expand_downwards/expand_upwards: security_mmap_addr() and wrapping-around check don't have to be under anon vma lock. Link: https://lkml.kernel.org/r/CACT4Y+Y908EjM2z=706dv4rV6dWtxTLK9nFg9_7DhRMLppBo2g@mail.gmail.com Signed-off-by: Konstantin Khlebnikov Reported-by: Dmitry Vyukov Acked-by: Kirill A. Shutemov Cc: Andrea Arcangeli Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- include/linux/rmap.h | 14 ----------- mm/mmap.c | 55 ++++++++++++++++++++------------------------ 2 files changed, 25 insertions(+), 44 deletions(-) diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 29446aeef36e..ddda2ac3446e 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -108,20 +108,6 @@ static inline void put_anon_vma(struct anon_vma *anon_vma) __put_anon_vma(anon_vma); } -static inline void vma_lock_anon_vma(struct vm_area_struct *vma) -{ - struct anon_vma *anon_vma = vma->anon_vma; - if (anon_vma) - down_write(&anon_vma->root->rwsem); -} - -static inline void vma_unlock_anon_vma(struct vm_area_struct *vma) -{ - struct anon_vma *anon_vma = vma->anon_vma; - if (anon_vma) - up_write(&anon_vma->root->rwsem); -} - static inline void anon_vma_lock_write(struct anon_vma *anon_vma) { down_write(&anon_vma->root->rwsem); diff --git a/mm/mmap.c b/mm/mmap.c index 2ce04a649f6b..d8cb37af53ac 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -441,12 +441,16 @@ static void validate_mm(struct mm_struct *mm) struct vm_area_struct *vma = mm->mmap; while (vma) { + struct anon_vma *anon_vma = vma->anon_vma; struct anon_vma_chain *avc; - vma_lock_anon_vma(vma); - list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) - anon_vma_interval_tree_verify(avc); - vma_unlock_anon_vma(vma); + if (anon_vma) { + anon_vma_lock_read(anon_vma); + list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) + anon_vma_interval_tree_verify(avc); + anon_vma_unlock_read(anon_vma); + } + highest_address = vma->vm_end; vma = vma->vm_next; i++; @@ -2147,32 +2151,27 @@ static int acct_stack_growth(struct vm_area_struct *vma, unsigned long size, uns int expand_upwards(struct vm_area_struct *vma, unsigned long address) { struct mm_struct *mm = vma->vm_mm; - int error; + int error = 0; if (!(vma->vm_flags & VM_GROWSUP)) return -EFAULT; - /* - * We must make sure the anon_vma is allocated - * so that the anon_vma locking is not a noop. - */ + /* Guard against wrapping around to address 0. */ + if (address < PAGE_ALIGN(address+4)) + address = PAGE_ALIGN(address+4); + else + return -ENOMEM; + + /* We must make sure the anon_vma is allocated. */ if (unlikely(anon_vma_prepare(vma))) return -ENOMEM; - vma_lock_anon_vma(vma); /* * vma->vm_start/vm_end cannot change under us because the caller * is required to hold the mmap_sem in read mode. We need the * anon_vma lock to serialize against concurrent expand_stacks. - * Also guard against wrapping around to address 0. */ - if (address < PAGE_ALIGN(address+4)) - address = PAGE_ALIGN(address+4); - else { - vma_unlock_anon_vma(vma); - return -ENOMEM; - } - error = 0; + anon_vma_lock_write(vma->anon_vma); /* Somebody else might have raced and expanded it already */ if (address > vma->vm_end) { @@ -2190,7 +2189,7 @@ int expand_upwards(struct vm_area_struct *vma, unsigned long address) * updates, but we only hold a shared mmap_sem * lock here, so we need to protect against * concurrent vma expansions. - * vma_lock_anon_vma() doesn't help here, as + * anon_vma_lock_write() doesn't help here, as * we don't guarantee that all growable vmas * in a mm share the same root anon vma. * So, we reuse mm->page_table_lock to guard @@ -2214,7 +2213,7 @@ int expand_upwards(struct vm_area_struct *vma, unsigned long address) } } } - vma_unlock_anon_vma(vma); + anon_vma_unlock_write(vma->anon_vma); khugepaged_enter_vma_merge(vma, vma->vm_flags); validate_mm(mm); return error; @@ -2230,25 +2229,21 @@ int expand_downwards(struct vm_area_struct *vma, struct mm_struct *mm = vma->vm_mm; int error; - /* - * We must make sure the anon_vma is allocated - * so that the anon_vma locking is not a noop. - */ - if (unlikely(anon_vma_prepare(vma))) - return -ENOMEM; - address &= PAGE_MASK; error = security_mmap_addr(address); if (error) return error; - vma_lock_anon_vma(vma); + /* We must make sure the anon_vma is allocated. */ + if (unlikely(anon_vma_prepare(vma))) + return -ENOMEM; /* * vma->vm_start/vm_end cannot change under us because the caller * is required to hold the mmap_sem in read mode. We need the * anon_vma lock to serialize against concurrent expand_stacks. */ + anon_vma_lock_write(vma->anon_vma); /* Somebody else might have raced and expanded it already */ if (address < vma->vm_start) { @@ -2266,7 +2261,7 @@ int expand_downwards(struct vm_area_struct *vma, * updates, but we only hold a shared mmap_sem * lock here, so we need to protect against * concurrent vma expansions. - * vma_lock_anon_vma() doesn't help here, as + * anon_vma_lock_write() doesn't help here, as * we don't guarantee that all growable vmas * in a mm share the same root anon vma. * So, we reuse mm->page_table_lock to guard @@ -2288,7 +2283,7 @@ int expand_downwards(struct vm_area_struct *vma, } } } - vma_unlock_anon_vma(vma); + anon_vma_unlock_write(vma->anon_vma); khugepaged_enter_vma_merge(vma, vma->vm_flags); validate_mm(mm); return error; From d1f8217a9a6e9b84df4cf6a0d3c99c7bbe1430a7 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Wed, 17 Feb 2016 13:11:15 -0800 Subject: [PATCH 282/325] mm: fix regression in remap_file_pages() emulation commit 48f7df329474b49d83d0dffec1b6186647f11976 upstream. Grazvydas Ignotas has reported a regression in remap_file_pages() emulation. Testcase: #define _GNU_SOURCE #include #include #include #include #define SIZE (4096 * 3) int main(int argc, char **argv) { unsigned long *p; long i; p = mmap(NULL, SIZE, PROT_READ | PROT_WRITE, MAP_SHARED | MAP_ANONYMOUS, -1, 0); if (p == MAP_FAILED) { perror("mmap"); return -1; } for (i = 0; i < SIZE / 4096; i++) p[i * 4096 / sizeof(*p)] = i; if (remap_file_pages(p, 4096, 0, 1, 0)) { perror("remap_file_pages"); return -1; } if (remap_file_pages(p, 4096 * 2, 0, 1, 0)) { perror("remap_file_pages"); return -1; } assert(p[0] == 1); munmap(p, SIZE); return 0; } The second remap_file_pages() fails with -EINVAL. The reason is that remap_file_pages() emulation assumes that the target vma covers whole area we want to over map. That assumption is broken by first remap_file_pages() call: it split the area into two vma. The solution is to check next adjacent vmas, if they map the same file with the same flags. Fixes: c8d78c1823f4 ("mm: replace remap_file_pages() syscall with emulation") Signed-off-by: Kirill A. Shutemov Reported-by: Grazvydas Ignotas Tested-by: Grazvydas Ignotas Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- mm/mmap.c | 34 +++++++++++++++++++++++++++++----- 1 file changed, 29 insertions(+), 5 deletions(-) diff --git a/mm/mmap.c b/mm/mmap.c index d8cb37af53ac..455772a05e54 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2668,12 +2668,29 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size, if (!vma || !(vma->vm_flags & VM_SHARED)) goto out; - if (start < vma->vm_start || start + size > vma->vm_end) + if (start < vma->vm_start) goto out; - if (pgoff == linear_page_index(vma, start)) { - ret = 0; - goto out; + if (start + size > vma->vm_end) { + struct vm_area_struct *next; + + for (next = vma->vm_next; next; next = next->vm_next) { + /* hole between vmas ? */ + if (next->vm_start != next->vm_prev->vm_end) + goto out; + + if (next->vm_file != vma->vm_file) + goto out; + + if (next->vm_flags != vma->vm_flags) + goto out; + + if (start + size <= next->vm_end) + break; + } + + if (!next) + goto out; } prot |= vma->vm_flags & VM_READ ? PROT_READ : 0; @@ -2683,9 +2700,16 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size, flags &= MAP_NONBLOCK; flags |= MAP_SHARED | MAP_FIXED | MAP_POPULATE; if (vma->vm_flags & VM_LOCKED) { + struct vm_area_struct *tmp; flags |= MAP_LOCKED; + /* drop PG_Mlocked flag for over-mapped range */ - munlock_vma_pages_range(vma, start, start + size); + for (tmp = vma; tmp->vm_start >= start + size; + tmp = tmp->vm_next) { + munlock_vma_pages_range(tmp, + max(tmp->vm_start, start), + min(tmp->vm_end, start + size)); + } } file = get_file(vma->vm_file); From 1d70d30a5fa2139325e413aaf4ce44675d3133ce Mon Sep 17 00:00:00 2001 From: Benjamin Tissoires Date: Mon, 11 Jan 2016 17:35:38 -0800 Subject: [PATCH 283/325] Input: elantech - mark protocols v2 and v3 as semi-mt commit 6544a1df11c48c8413071aac3316792e4678fbfb upstream. When using a protocol v2 or v3 hardware, elantech uses the function elantech_report_semi_mt_data() to report data. This devices are rather creepy because if num_finger is 3, (x2,y2) is (0,0). Yes, only one valid touch is reported. Anyway, userspace (libinput) is now confused by these (0,0) touches, and detect them as palm, and rejects them. Commit 3c0213d17a09 ("Input: elantech - fix semi-mt protocol for v3 HW") was sufficient enough for xf86-input-synaptics and libinput before it has palm rejection. Now we need to actually tell libinput that this device is a semi-mt one and it should not rely on the actual values of the 2 touches. Signed-off-by: Benjamin Tissoires Signed-off-by: Dmitry Torokhov Signed-off-by: Greg Kroah-Hartman --- drivers/input/mouse/elantech.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/input/mouse/elantech.c b/drivers/input/mouse/elantech.c index 537ebb0e193a..78f93cf68840 100644 --- a/drivers/input/mouse/elantech.c +++ b/drivers/input/mouse/elantech.c @@ -1222,7 +1222,7 @@ static int elantech_set_input_params(struct psmouse *psmouse) input_set_abs_params(dev, ABS_TOOL_WIDTH, ETP_WMIN_V2, ETP_WMAX_V2, 0, 0); } - input_mt_init_slots(dev, 2, 0); + input_mt_init_slots(dev, 2, INPUT_MT_SEMI_MT); input_set_abs_params(dev, ABS_MT_POSITION_X, x_min, x_max, 0, 0); input_set_abs_params(dev, ABS_MT_POSITION_Y, y_min, y_max, 0, 0); break; From 5c73252f746d4973294b7ae7eead944f4a5210f8 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Aur=C3=A9lien=20Francillon?= Date: Sat, 2 Jan 2016 20:39:54 -0800 Subject: [PATCH 284/325] Input: i8042 - add Fujitsu Lifebook U745 to the nomux list MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit dd0d0d4de582a6a61c032332c91f4f4cb2bab569 upstream. Without i8042.nomux=1 the Elantech touch pad is not working at all on a Fujitsu Lifebook U745. This patch does not seem necessary for all U745 (maybe because of different BIOS versions?). However, it was verified that the patch does not break those (see opensuse bug 883192: https://bugzilla.opensuse.org/show_bug.cgi?id=883192). Signed-off-by: Aurélien Francillon Signed-off-by: Dmitry Torokhov Signed-off-by: Greg Kroah-Hartman --- drivers/input/serio/i8042-x86ia64io.h | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/input/serio/i8042-x86ia64io.h b/drivers/input/serio/i8042-x86ia64io.h index c11556563ef0..68f5f4a0f1e7 100644 --- a/drivers/input/serio/i8042-x86ia64io.h +++ b/drivers/input/serio/i8042-x86ia64io.h @@ -257,6 +257,13 @@ static const struct dmi_system_id __initconst i8042_dmi_nomux_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "LifeBook S6230"), }, }, + { + /* Fujitsu Lifebook U745 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), + DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK U745"), + }, + }, { /* Fujitsu T70H */ .matches = { From 726ecfc321994ec6ab044c1e3e5886408de991ac Mon Sep 17 00:00:00 2001 From: James Bottomley Date: Wed, 20 Jan 2016 14:58:29 -0800 Subject: [PATCH 285/325] string_helpers: fix precision loss for some inputs commit 564b026fbd0d28e9f70fb3831293d2922bb7855b upstream. It was noticed that we lose precision in the final calculation for some inputs. The most egregious example is size=3000 blk_size=1900 in units of 10 should yield 5.70 MB but in fact yields 3.00 MB (oops). This is because the current algorithm doesn't correctly account for all the remainders in the logarithms. Fix this by doing a correct calculation in the remainders based on napier's algorithm. Additionally, now we have the correct result, we have to account for arithmetic rounding because we're printing 3 digits of precision. This means that if the fourth digit is five or greater, we have to round up, so add a section to ensure correct rounding. Finally account for all possible inputs correctly, including zero for block size. Fixes: b9f28d863594c429e1df35a0474d2663ca28b307 Signed-off-by: James Bottomley Reported-by: Vitaly Kuznetsov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- lib/string_helpers.c | 69 +++++++++++++++++++++++++++++--------------- 1 file changed, 46 insertions(+), 23 deletions(-) diff --git a/lib/string_helpers.c b/lib/string_helpers.c index 5939f63d90cd..5c88204b6f1f 100644 --- a/lib/string_helpers.c +++ b/lib/string_helpers.c @@ -43,50 +43,73 @@ void string_get_size(u64 size, u64 blk_size, const enum string_size_units units, [STRING_UNITS_10] = 1000, [STRING_UNITS_2] = 1024, }; - int i, j; - u32 remainder = 0, sf_cap, exp; + static const unsigned int rounding[] = { 500, 50, 5 }; + int i = 0, j; + u32 remainder = 0, sf_cap; char tmp[8]; const char *unit; tmp[0] = '\0'; - i = 0; - if (!size) + + if (blk_size == 0) + size = 0; + if (size == 0) goto out; - while (blk_size >= divisor[units]) { - remainder = do_div(blk_size, divisor[units]); - i++; - } - - exp = divisor[units] / (u32)blk_size; - /* - * size must be strictly greater than exp here to ensure that remainder - * is greater than divisor[units] coming out of the if below. + /* This is Napier's algorithm. Reduce the original block size to + * + * coefficient * divisor[units]^i + * + * we do the reduction so both coefficients are just under 32 bits so + * that multiplying them together won't overflow 64 bits and we keep + * as much precision as possible in the numbers. + * + * Note: it's safe to throw away the remainders here because all the + * precision is in the coefficients. */ - if (size > exp) { - remainder = do_div(size, divisor[units]); - remainder *= blk_size; + while (blk_size >> 32) { + do_div(blk_size, divisor[units]); i++; - } else { - remainder *= size; } - size *= blk_size; - size += remainder / divisor[units]; - remainder %= divisor[units]; + while (size >> 32) { + do_div(size, divisor[units]); + i++; + } + /* now perform the actual multiplication keeping i as the sum of the + * two logarithms */ + size *= blk_size; + + /* and logarithmically reduce it until it's just under the divisor */ while (size >= divisor[units]) { remainder = do_div(size, divisor[units]); i++; } + /* work out in j how many digits of precision we need from the + * remainder */ sf_cap = size; for (j = 0; sf_cap*10 < 1000; j++) sf_cap *= 10; - if (j) { + if (units == STRING_UNITS_2) { + /* express the remainder as a decimal. It's currently the + * numerator of a fraction whose denominator is + * divisor[units], which is 1 << 10 for STRING_UNITS_2 */ remainder *= 1000; - remainder /= divisor[units]; + remainder >>= 10; + } + + /* add a 5 to the digit below what will be printed to ensure + * an arithmetical round up and carry it through to size */ + remainder += rounding[j]; + if (remainder >= 1000) { + remainder -= 1000; + size += 1; + } + + if (j) { snprintf(tmp, sizeof(tmp), ".%03u", remainder); tmp[j+1] = '\0'; } From b864f4e50c56a5bd0ab1603b86164cab66337906 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Sat, 16 Jan 2016 10:04:49 -0800 Subject: [PATCH 286/325] Input: vmmouse - fix absolute device registration commit d4f1b06d685d11ebdaccf11c0db1cb3c78736862 upstream. We should set device's capabilities first, and then register it, otherwise various handlers already present in the kernel will not be able to connect to the device. Reported-by: Lauri Kasanen Signed-off-by: Dmitry Torokhov Signed-off-by: Greg Kroah-Hartman --- drivers/input/mouse/vmmouse.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/drivers/input/mouse/vmmouse.c b/drivers/input/mouse/vmmouse.c index e272f06258ce..a3f0f5a47490 100644 --- a/drivers/input/mouse/vmmouse.c +++ b/drivers/input/mouse/vmmouse.c @@ -458,8 +458,6 @@ int vmmouse_init(struct psmouse *psmouse) priv->abs_dev = abs_dev; psmouse->private = priv; - input_set_capability(rel_dev, EV_REL, REL_WHEEL); - /* Set up and register absolute device */ snprintf(priv->phys, sizeof(priv->phys), "%s/input1", psmouse->ps2dev.serio->phys); @@ -475,10 +473,6 @@ int vmmouse_init(struct psmouse *psmouse) abs_dev->id.version = psmouse->model; abs_dev->dev.parent = &psmouse->ps2dev.serio->dev; - error = input_register_device(priv->abs_dev); - if (error) - goto init_fail; - /* Set absolute device capabilities */ input_set_capability(abs_dev, EV_KEY, BTN_LEFT); input_set_capability(abs_dev, EV_KEY, BTN_RIGHT); @@ -488,6 +482,13 @@ int vmmouse_init(struct psmouse *psmouse) input_set_abs_params(abs_dev, ABS_X, 0, VMMOUSE_MAX_X, 0, 0); input_set_abs_params(abs_dev, ABS_Y, 0, VMMOUSE_MAX_Y, 0, 0); + error = input_register_device(priv->abs_dev); + if (error) + goto init_fail; + + /* Add wheel capability to the relative device */ + input_set_capability(rel_dev, EV_REL, REL_WHEEL); + psmouse->protocol_handler = vmmouse_process_byte; psmouse->disconnect = vmmouse_disconnect; psmouse->reconnect = vmmouse_reconnect; From c65a7b684133887e9211cd901bb689c48a6c18d8 Mon Sep 17 00:00:00 2001 From: Jeremy McNicoll Date: Thu, 14 Jan 2016 21:33:06 -0800 Subject: [PATCH 287/325] iommu/vt-d: Don't skip PCI devices when disabling IOTLB commit da972fb13bc5a1baad450c11f9182e4cd0a091f6 upstream. Fix a simple typo when disabling IOTLB on PCI(e) devices. Fixes: b16d0cb9e2fc ("iommu/vt-d: Always enable PASID/PRI PCI capabilities before ATS") Signed-off-by: Jeremy McNicoll Reviewed-by: Alex Williamson Signed-off-by: Joerg Roedel Signed-off-by: Greg Kroah-Hartman --- drivers/iommu/intel-iommu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index ac7387686ddc..986a53e3eb96 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -1489,7 +1489,7 @@ static void iommu_disable_dev_iotlb(struct device_domain_info *info) { struct pci_dev *pdev; - if (dev_is_pci(info->dev)) + if (!dev_is_pci(info->dev)) return; pdev = to_pci_dev(info->dev); From d63a009a9bd9f0503a0d817b6ae97f5b06de22e3 Mon Sep 17 00:00:00 2001 From: Baoquan He Date: Wed, 20 Jan 2016 22:01:19 +0800 Subject: [PATCH 288/325] iommu/amd: Correct the wrong setting of alias DTE in do_attach commit 9b1a12d29109234d2b9718d04d4d404b7da4e794 upstream. In below commit alias DTE is set when its peripheral is setting DTE. However there's a code bug here to wrongly set the alias DTE, correct it in this patch. commit e25bfb56ea7f046b71414e02f80f620deb5c6362 Author: Joerg Roedel Date: Tue Oct 20 17:33:38 2015 +0200 iommu/amd: Set alias DTE in do_attach/do_detach Signed-off-by: Baoquan He Tested-by: Mark Hounschell Signed-off-by: Joerg Roedel Signed-off-by: Greg Kroah-Hartman --- drivers/iommu/amd_iommu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index 8b2be1e7714f..fc836f523afa 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -1905,7 +1905,7 @@ static void do_attach(struct iommu_dev_data *dev_data, /* Update device table */ set_dte_entry(dev_data->devid, domain, ats); if (alias != dev_data->devid) - set_dte_entry(dev_data->devid, domain, ats); + set_dte_entry(alias, domain, ats); device_flush_dte(dev_data); } From 7c6471cb94adcb2d7027d6981e87e87ccd05b06e Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Tue, 12 Jan 2016 19:18:06 +0000 Subject: [PATCH 289/325] iommu/vt-d: Fix mm refcounting to hold mm_count not mm_users MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit e57e58bd390a6843db58560bf7b8341665d2e058 upstream. Holding mm_users works OK for graphics, which was the first user of SVM with VT-d. However, it works less well for other devices, where we actually do a mmap() from the file descriptor to which the SVM PASID state is tied. In this case on process exit we end up with a recursive reference count: - The MM remains alive until the file is closed and the driver's release() call ends up unbinding the PASID. - The VMA corresponding to the mmap() remains intact until the MM is destroyed. - Thus the file isn't closed, even when exit_files() runs, because the VMA is still holding a reference to it. And the MM remains alive… To address this issue, we *stop* holding mm_users while the PASID is bound. We already hold mm_count by virtue of the MMU notifier, and that can be made to be sufficient. It means that for a period during process exit, the fun part of mmput() has happened and exit_mmap() has been called so the MM is basically defunct. But the PGD still exists and the PASID is still bound to it. During this period, we have to be very careful — exit_mmap() doesn't use mm->mmap_sem because it doesn't expect anyone else to be touching the MM (quite reasonably, since mm_users is zero). So we also need to fix the fault handler to just report failure if mm_users is already zero, and to temporarily bump mm_users while handling any faults. Additionally, exit_mmap() calls mmu_notifier_release() *before* it tears down the page tables, which is too early for us to flush the IOTLB for this PASID. And __mmu_notifier_release() removes every notifier from the list, so when exit_mmap() finally *does* tear down the mappings and clear the page tables, we don't get notified. So we work around this by clearing the PASID table entry in our MMU notifier release() callback. That way, the hardware *can't* get any pages back from the page tables before they get cleared. Hardware designers have confirmed that the resulting 'PASID not present' faults should be handled just as gracefully as 'page not present' faults, the important criterion being that they don't perturb the operation for any *other* PASID in the system. Signed-off-by: David Woodhouse Signed-off-by: Greg Kroah-Hartman --- drivers/iommu/intel-svm.c | 33 +++++++++++++++++++++++++++------ 1 file changed, 27 insertions(+), 6 deletions(-) diff --git a/drivers/iommu/intel-svm.c b/drivers/iommu/intel-svm.c index 50464833d0b8..97a818992d6d 100644 --- a/drivers/iommu/intel-svm.c +++ b/drivers/iommu/intel-svm.c @@ -249,12 +249,30 @@ static void intel_flush_pasid_dev(struct intel_svm *svm, struct intel_svm_dev *s static void intel_mm_release(struct mmu_notifier *mn, struct mm_struct *mm) { struct intel_svm *svm = container_of(mn, struct intel_svm, notifier); + struct intel_svm_dev *sdev; + /* This might end up being called from exit_mmap(), *before* the page + * tables are cleared. And __mmu_notifier_release() will delete us from + * the list of notifiers so that our invalidate_range() callback doesn't + * get called when the page tables are cleared. So we need to protect + * against hardware accessing those page tables. + * + * We do it by clearing the entry in the PASID table and then flushing + * the IOTLB and the PASID table caches. This might upset hardware; + * perhaps we'll want to point the PASID to a dummy PGD (like the zero + * page) so that we end up taking a fault that the hardware really + * *has* to handle gracefully without affecting other processes. + */ svm->iommu->pasid_table[svm->pasid].val = 0; + wmb(); + + rcu_read_lock(); + list_for_each_entry_rcu(sdev, &svm->devs, list) { + intel_flush_pasid_dev(svm, sdev, svm->pasid); + intel_flush_svm_range_dev(svm, sdev, 0, -1, 0, !svm->mm); + } + rcu_read_unlock(); - /* There's no need to do any flush because we can't get here if there - * are any devices left anyway. */ - WARN_ON(!list_empty(&svm->devs)); } static const struct mmu_notifier_ops intel_mmuops = { @@ -379,7 +397,6 @@ int intel_svm_bind_mm(struct device *dev, int *pasid, int flags, struct svm_dev_ goto out; } iommu->pasid_table[svm->pasid].val = (u64)__pa(mm->pgd) | 1; - mm = NULL; } else iommu->pasid_table[svm->pasid].val = (u64)__pa(init_mm.pgd) | 1 | (1ULL << 11); wmb(); @@ -442,11 +459,11 @@ int intel_svm_unbind_mm(struct device *dev, int pasid) kfree_rcu(sdev, rcu); if (list_empty(&svm->devs)) { - mmu_notifier_unregister(&svm->notifier, svm->mm); idr_remove(&svm->iommu->pasid_idr, svm->pasid); if (svm->mm) - mmput(svm->mm); + mmu_notifier_unregister(&svm->notifier, svm->mm); + /* We mandate that no page faults may be outstanding * for the PASID when intel_svm_unbind_mm() is called. * If that is not obeyed, subtle errors will happen. @@ -551,6 +568,9 @@ static irqreturn_t prq_event_thread(int irq, void *d) * any faults on kernel addresses. */ if (!svm->mm) goto bad_req; + /* If the mm is already defunct, don't handle faults. */ + if (!atomic_inc_not_zero(&svm->mm->mm_users)) + goto bad_req; down_read(&svm->mm->mmap_sem); vma = find_extend_vma(svm->mm, address); if (!vma || address < vma->vm_start) @@ -567,6 +587,7 @@ static irqreturn_t prq_event_thread(int irq, void *d) result = QI_RESP_SUCCESS; invalid: up_read(&svm->mm->mmap_sem); + mmput(svm->mm); bad_req: /* Accounting for major/minor faults? */ rcu_read_lock(); From db3ac35cbd310b3ce2e668f82eb6d0c77cc10b15 Mon Sep 17 00:00:00 2001 From: CQ Tang Date: Wed, 13 Jan 2016 21:15:03 +0000 Subject: [PATCH 290/325] iommu/vt-d: Fix 64-bit accesses to 32-bit DMAR_GSTS_REG commit fda3bec12d0979aae3f02ee645913d66fbc8a26e upstream. This is a 32-bit register. Apparently harmless on real hardware, but causing justified warnings in simulation. Signed-off-by: CQ Tang Signed-off-by: David Woodhouse Signed-off-by: Greg Kroah-Hartman --- drivers/iommu/dmar.c | 2 +- drivers/iommu/intel_irq_remapping.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c index 80e3c176008e..55a19e49205b 100644 --- a/drivers/iommu/dmar.c +++ b/drivers/iommu/dmar.c @@ -1347,7 +1347,7 @@ void dmar_disable_qi(struct intel_iommu *iommu) raw_spin_lock_irqsave(&iommu->register_lock, flags); - sts = dmar_readq(iommu->reg + DMAR_GSTS_REG); + sts = readl(iommu->reg + DMAR_GSTS_REG); if (!(sts & DMA_GSTS_QIES)) goto end; diff --git a/drivers/iommu/intel_irq_remapping.c b/drivers/iommu/intel_irq_remapping.c index 1fae1881648c..e9b241b1c9dd 100644 --- a/drivers/iommu/intel_irq_remapping.c +++ b/drivers/iommu/intel_irq_remapping.c @@ -629,7 +629,7 @@ static void iommu_disable_irq_remapping(struct intel_iommu *iommu) raw_spin_lock_irqsave(&iommu->register_lock, flags); - sts = dmar_readq(iommu->reg + DMAR_GSTS_REG); + sts = readl(iommu->reg + DMAR_GSTS_REG); if (!(sts & DMA_GSTS_IRES)) goto end; From 2231e5748746cd57df389521397e1c7f91882077 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Mon, 15 Feb 2016 12:42:38 +0000 Subject: [PATCH 291/325] iommu/vt-d: Clear PPR bit to ensure we get more page request interrupts commit 46924008273ed03bd11dbb32136e3da4cfe056e1 upstream. According to the VT-d specification we need to clear the PPR bit in the Page Request Status register when handling page requests, or the hardware won't generate any more interrupts. This wasn't actually necessary on SKL/KBL (which may well be the subject of a hardware erratum, although it's harmless enough). But other implementations do appear to get it right, and we only ever get one interrupt unless we clear the PPR bit. Reported-by: CQ Tang Signed-off-by: David Woodhouse Signed-off-by: Greg Kroah-Hartman --- drivers/iommu/intel-svm.c | 4 ++++ include/linux/intel-iommu.h | 3 +++ 2 files changed, 7 insertions(+) diff --git a/drivers/iommu/intel-svm.c b/drivers/iommu/intel-svm.c index 97a818992d6d..d9939fa9b588 100644 --- a/drivers/iommu/intel-svm.c +++ b/drivers/iommu/intel-svm.c @@ -524,6 +524,10 @@ static irqreturn_t prq_event_thread(int irq, void *d) struct intel_svm *svm = NULL; int head, tail, handled = 0; + /* Clear PPR bit before reading head/tail registers, to + * ensure that we get a new interrupt if needed. */ + writel(DMA_PRS_PPR, iommu->reg + DMAR_PRS_REG); + tail = dmar_readq(iommu->reg + DMAR_PQT_REG) & PRQ_RING_MASK; head = dmar_readq(iommu->reg + DMAR_PQH_REG) & PRQ_RING_MASK; while (head != tail) { diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 821273ca4873..2d9b650047a5 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -235,6 +235,9 @@ static inline void dmar_writeq(void __iomem *addr, u64 val) /* low 64 bit */ #define dma_frcd_page_addr(d) (d & (((u64)-1) << PAGE_SHIFT)) +/* PRS_REG */ +#define DMA_PRS_PPR ((u32)1) + #define IOMMU_WAIT_OP(iommu, offset, op, cond, sts) \ do { \ cycles_t start_time = get_cycles(); \ From d15298509b86f06d63135770ac8433295a18375f Mon Sep 17 00:00:00 2001 From: Mathias Nyman Date: Tue, 26 Jan 2016 17:50:04 +0200 Subject: [PATCH 292/325] Revert "xhci: don't finish a TD if we get a short-transfer event mid TD" commit a6835090716a85f2297668ba593bd00e1051e662 upstream. This reverts commit e210c422b6fd ("xhci: don't finish a TD if we get a short transfer event mid TD") Turns out that most host controllers do not follow the xHCI specs and never send the second event for the last TRB in the TD if there was a short event mid-TD. Returning the URB directly after the first short-transfer event is far better than never returning the URB. (class drivers usually timeout after 30sec). For the hosts that do send the second event we will go back to treating it as misplaced event and print an error message for it. The origial patch was sent to stable kernels and needs to be reverted from there as well Signed-off-by: Mathias Nyman Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci-ring.c | 10 ---------- 1 file changed, 10 deletions(-) diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index eeaa6c6bd540..db0f0831b94f 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -2192,10 +2192,6 @@ static int process_bulk_intr_td(struct xhci_hcd *xhci, struct xhci_td *td, } /* Fast path - was this the last TRB in the TD for this URB? */ } else if (event_trb == td->last_trb) { - if (td->urb_length_set && trb_comp_code == COMP_SHORT_TX) - return finish_td(xhci, td, event_trb, event, ep, - status, false); - if (EVENT_TRB_LEN(le32_to_cpu(event->transfer_len)) != 0) { td->urb->actual_length = td->urb->transfer_buffer_length - @@ -2247,12 +2243,6 @@ static int process_bulk_intr_td(struct xhci_hcd *xhci, struct xhci_td *td, td->urb->actual_length += TRB_LEN(le32_to_cpu(cur_trb->generic.field[2])) - EVENT_TRB_LEN(le32_to_cpu(event->transfer_len)); - - if (trb_comp_code == COMP_SHORT_TX) { - xhci_dbg(xhci, "mid bulk/intr SP, wait for last TRB event\n"); - td->urb_length_set = true; - return 0; - } } return finish_td(xhci, td, event_trb, event, ep, status, false); From 71e5a4a747b0eadbff4835cf41493187bcbbd886 Mon Sep 17 00:00:00 2001 From: Mathias Nyman Date: Tue, 26 Jan 2016 17:50:12 +0200 Subject: [PATCH 293/325] xhci: Fix list corruption in urb dequeue at host removal commit 5c82171167adb8e4ac77b91a42cd49fb211a81a0 upstream. xhci driver frees data for all devices, both usb2 and and usb3 the first time usb_remove_hcd() is called, including td_list and and xhci_ring structures. When usb_remove_hcd() is called a second time for the second xhci bus it will try to dequeue all pending urbs, and touches td_list which is already freed for that endpoint. Reported-by: Joe Lawrence Tested-by: Joe Lawrence Signed-off-by: Mathias Nyman Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index dca0a4692f08..776d59c32bc5 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -1549,7 +1549,9 @@ int xhci_urb_dequeue(struct usb_hcd *hcd, struct urb *urb, int status) xhci_dbg_trace(xhci, trace_xhci_dbg_cancel_urb, "HW died, freeing TD."); urb_priv = urb->hcpriv; - for (i = urb_priv->td_cnt; i < urb_priv->length; i++) { + for (i = urb_priv->td_cnt; + i < urb_priv->length && xhci->devs[urb->dev->slot_id]; + i++) { td = urb_priv->td[i]; if (!list_empty(&td->td_list)) list_del_init(&td->td_list); From 275adaf191c617409452bc569ad8f423e74678c7 Mon Sep 17 00:00:00 2001 From: Sudip Mukherjee Date: Thu, 14 Jan 2016 15:16:47 -0800 Subject: [PATCH 294/325] m32r: fix m32104ut_defconfig build fail commit 601f1db653217f205ffa5fb33514b4e1711e56d1 upstream. The build of m32104ut_defconfig for m32r arch was failing for long long time with the error: ERROR: "memory_start" [fs/udf/udf.ko] undefined! ERROR: "memory_end" [fs/udf/udf.ko] undefined! ERROR: "memory_end" [drivers/scsi/sg.ko] undefined! ERROR: "memory_start" [drivers/scsi/sg.ko] undefined! ERROR: "memory_end" [drivers/i2c/i2c-dev.ko] undefined! ERROR: "memory_start" [drivers/i2c/i2c-dev.ko] undefined! As done in other architectures export the symbols to fix the error. Reported-by: Fengguang Wu Signed-off-by: Sudip Mukherjee Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- arch/m32r/kernel/setup.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/m32r/kernel/setup.c b/arch/m32r/kernel/setup.c index 0392112a5d70..a5ecef7188ba 100644 --- a/arch/m32r/kernel/setup.c +++ b/arch/m32r/kernel/setup.c @@ -81,7 +81,10 @@ static struct resource code_resource = { }; unsigned long memory_start; +EXPORT_SYMBOL(memory_start); + unsigned long memory_end; +EXPORT_SYMBOL(memory_end); void __init setup_arch(char **); int get_cpuinfo(char *); From dad5038f3fe2ac41078eed8abba9b7f5ce2fa05c Mon Sep 17 00:00:00 2001 From: Laura Abbott Date: Thu, 14 Jan 2016 15:16:50 -0800 Subject: [PATCH 295/325] dma-debug: switch check from _text to _stext commit ea535e418c01837d07b6c94e817540f50bfdadb0 upstream. In include/asm-generic/sections.h: /* * Usage guidelines: * _text, _data: architecture specific, don't use them in * arch-independent code * [_stext, _etext]: contains .text.* sections, may also contain * .rodata.* * and/or .init.* sections _text is not guaranteed across architectures. Architectures such as ARM may reuse parts which are not actually text and erroneously trigger a bug. Switch to using _stext which is guaranteed to contain text sections. Came out of https://lkml.kernel.org/g/<567B1176.4000106@redhat.com> Signed-off-by: Laura Abbott Reviewed-by: Kees Cook Cc: Russell King Cc: Arnd Bergmann Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- lib/dma-debug.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/lib/dma-debug.c b/lib/dma-debug.c index d34bd24c2c84..4a1515f4b452 100644 --- a/lib/dma-debug.c +++ b/lib/dma-debug.c @@ -1181,7 +1181,7 @@ static inline bool overlap(void *addr, unsigned long len, void *start, void *end static void check_for_illegal_area(struct device *dev, void *addr, unsigned long len) { - if (overlap(addr, len, _text, _etext) || + if (overlap(addr, len, _stext, _etext) || overlap(addr, len, __start_rodata, __end_rodata)) err_printk(dev, NULL, "DMA-API: device driver maps memory from kernel text or rodata [addr=%p] [len=%lu]\n", addr, len); } From b105aa33af0d487fc349212edecac04ef35a2622 Mon Sep 17 00:00:00 2001 From: Sergey Senozhatsky Date: Thu, 14 Jan 2016 15:16:53 -0800 Subject: [PATCH 296/325] scripts/bloat-o-meter: fix python3 syntax error commit 72214a24a7677d4c7501eecc9517ed681b5f2db2 upstream. In Python3+ print is a function so the old syntax is not correct anymore: $ ./scripts/bloat-o-meter vmlinux.o vmlinux.o.old File "./scripts/bloat-o-meter", line 61 print "add/remove: %s/%s grow/shrink: %s/%s up/down: %s/%s (%s)" % \ ^ SyntaxError: invalid syntax Fix by calling print as a function. Tested on python 2.7.11, 3.5.1 Signed-off-by: Sergey Senozhatsky Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- scripts/bloat-o-meter | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/scripts/bloat-o-meter b/scripts/bloat-o-meter index 23e78dcd12bf..38b64f487315 100755 --- a/scripts/bloat-o-meter +++ b/scripts/bloat-o-meter @@ -58,8 +58,8 @@ for name in common: delta.sort() delta.reverse() -print "add/remove: %s/%s grow/shrink: %s/%s up/down: %s/%s (%s)" % \ - (add, remove, grow, shrink, up, -down, up-down) -print "%-40s %7s %7s %+7s" % ("function", "old", "new", "delta") +print("add/remove: %s/%s grow/shrink: %s/%s up/down: %s/%s (%s)" % \ + (add, remove, grow, shrink, up, -down, up-down)) +print("%-40s %7s %7s %+7s" % ("function", "old", "new", "delta")) for d, n in delta: - if d: print "%-40s %7s %7s %+7d" % (n, old.get(n,"-"), new.get(n,"-"), d) + if d: print("%-40s %7s %7s %+7d" % (n, old.get(n,"-"), new.get(n,"-"), d)) From db33368ca32dd307cdcc191361de34f3937f513a Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Fri, 15 Jan 2016 16:57:37 -0800 Subject: [PATCH 297/325] fs/hugetlbfs/inode.c: fix bugs in hugetlb_vmtruncate_list() commit 9aacdd354d197ad64685941b36d28ea20ab88757 upstream. Hillf Danton noticed bugs in the hugetlb_vmtruncate_list routine. The argument end is of type pgoff_t. It was being converted to a vaddr offset and passed to unmap_hugepage_range. However, end was also being used as an argument to the vma_interval_tree_foreach controlling loop. In addition, the conversion of end to vaddr offset was incorrect. hugetlb_vmtruncate_list is called as part of a file truncate or fallocate hole punch operation. When truncating a hugetlbfs file, this bug could prevent some pages from being unmapped. This is possible if there are multiple vmas mapping the file, and there is a sufficiently sized hole between the mappings. The size of the hole between two vmas (A,B) must be such that the starting virtual address of B is greater than (ending virtual address of A << PAGE_SHIFT). In this case, the pages in B would not be unmapped. If pages are not properly unmapped during truncate, the following BUG is hit: kernel BUG at fs/hugetlbfs/inode.c:428! In the fallocate hole punch case, this bug could prevent pages from being unmapped as in the truncate case. However, for hole punch the result is that unmapped pages will not be removed during the operation. For hole punch, it is also possible that more pages than desired will be unmapped. This unnecessary unmapping will cause page faults to reestablish the mappings on subsequent page access. Fixes: 1bfad99ab (" hugetlbfs: hugetlb_vmtruncate_list() needs to take a range")Reported-by: Hillf Danton Signed-off-by: Mike Kravetz Cc: Hugh Dickins Cc: Naoya Horiguchi Cc: Davidlohr Bueso Cc: Dave Hansen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- fs/hugetlbfs/inode.c | 19 +++++++++++-------- 1 file changed, 11 insertions(+), 8 deletions(-) diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index de4bdfac0cec..595ebdb41846 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -463,6 +463,7 @@ hugetlb_vmdelete_list(struct rb_root *root, pgoff_t start, pgoff_t end) */ vma_interval_tree_foreach(vma, root, start, end ? end : ULONG_MAX) { unsigned long v_offset; + unsigned long v_end; /* * Can the expression below overflow on 32-bit arches? @@ -475,15 +476,17 @@ hugetlb_vmdelete_list(struct rb_root *root, pgoff_t start, pgoff_t end) else v_offset = 0; - if (end) { - end = ((end - start) << PAGE_SHIFT) + - vma->vm_start + v_offset; - if (end > vma->vm_end) - end = vma->vm_end; - } else - end = vma->vm_end; + if (!end) + v_end = vma->vm_end; + else { + v_end = ((end - vma->vm_pgoff) << PAGE_SHIFT) + + vma->vm_start; + if (v_end > vma->vm_end) + v_end = vma->vm_end; + } - unmap_hugepage_range(vma, vma->vm_start + v_offset, end, NULL); + unmap_hugepage_range(vma, vma->vm_start + v_offset, v_end, + NULL); } } From 4b20545910cbc96cede009adb89e19f7d2aa8f52 Mon Sep 17 00:00:00 2001 From: Michael Holzheu Date: Tue, 2 Feb 2016 16:57:26 -0800 Subject: [PATCH 298/325] numa: fix /proc//numa_maps for hugetlbfs on s390 commit 5c2ff95e41c9290d16556cd02e35b25d81be8fe0 upstream. When working with hugetlbfs ptes (which are actually pmds) is not valid to directly use pte functions like pte_present() because the hardware bit layout of pmds and ptes can be different. This is the case on s390. Therefore we have to convert the hugetlbfs ptes first into a valid pte encoding with huge_ptep_get(). Currently the /proc//numa_maps code uses hugetlbfs ptes without huge_ptep_get(). On s390 this leads to the following two problems: 1) The pte_present() function returns false (instead of true) for PROT_NONE hugetlb ptes. Therefore PROT_NONE vmas are missing completely in the "numa_maps" output. 2) The pte_dirty() function always returns false for all hugetlb ptes. Therefore these pages are reported as "mapped=xxx" instead of "dirty=xxx". Therefore use huge_ptep_get() to correctly convert the hugetlb ptes. Signed-off-by: Michael Holzheu Reviewed-by: Gerald Schaefer Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- fs/proc/task_mmu.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 187b3b5f242e..09cd3edde08a 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -1473,18 +1473,19 @@ static int gather_pte_stats(pmd_t *pmd, unsigned long addr, static int gather_hugetlb_stats(pte_t *pte, unsigned long hmask, unsigned long addr, unsigned long end, struct mm_walk *walk) { + pte_t huge_pte = huge_ptep_get(pte); struct numa_maps *md; struct page *page; - if (!pte_present(*pte)) + if (!pte_present(huge_pte)) return 0; - page = pte_page(*pte); + page = pte_page(huge_pte); if (!page) return 0; md = walk->private; - gather_stats(page, md, pte_dirty(*pte), 1); + gather_stats(page, md, pte_dirty(huge_pte), 1); return 0; } From ececa3ebe27f61db28161bc8c6ef2e1612dbafbe Mon Sep 17 00:00:00 2001 From: Martijn Coenen Date: Fri, 15 Jan 2016 16:57:49 -0800 Subject: [PATCH 299/325] memcg: only free spare array when readers are done commit 6611d8d76132f86faa501de9451a89bf23fb2371 upstream. A spare array holding mem cgroup threshold events is kept around to make sure we can always safely deregister an event and have an array to store the new set of events in. In the scenario where we're going from 1 to 0 registered events, the pointer to the primary array containing 1 event is copied to the spare slot, and then the spare slot is freed because no events are left. However, it is freed before calling synchronize_rcu(), which means readers may still be accessing threshold->primary after it is freed. Fixed by only freeing after synchronize_rcu(). Signed-off-by: Martijn Coenen Cc: Johannes Weiner Acked-by: Michal Hocko Cc: Vladimir Davydov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- mm/memcontrol.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index fc10620967c7..ee6acd279953 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3522,16 +3522,17 @@ static void __mem_cgroup_usage_unregister_event(struct mem_cgroup *memcg, swap_buffers: /* Swap primary and spare array */ thresholds->spare = thresholds->primary; - /* If all events are unregistered, free the spare array */ - if (!new) { - kfree(thresholds->spare); - thresholds->spare = NULL; - } rcu_assign_pointer(thresholds->primary, new); /* To be sure that nobody uses thresholds */ synchronize_rcu(); + + /* If all events are unregistered, free the spare array */ + if (!new) { + kfree(thresholds->spare); + thresholds->spare = NULL; + } unlock: mutex_unlock(&memcg->thresholds_lock); } From 262139f0244b3ade149b785dc820118c4265cdb1 Mon Sep 17 00:00:00 2001 From: Rich Felker Date: Fri, 22 Jan 2016 15:11:05 -0800 Subject: [PATCH 300/325] MAINTAINERS: return arch/sh to maintained state, with new maintainers commit 114bf37e04d839b555b3dc460b5e6ce156f49cf0 upstream. Add Yoshinori Sato and Rich Felker as maintainers for arch/sh (SUPERH). Signed-off-by: Rich Felker Signed-off-by: Yoshinori Sato Acked-by: D. Jeff Dionne Acked-by: Rob Landley Acked-by: Peter Zijlstra (Intel) Acked-by: Simon Horman Acked-by: Geert Uytterhoeven Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- MAINTAINERS | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index 233f83464814..d826f1b9eb02 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -10289,9 +10289,11 @@ S: Maintained F: drivers/net/ethernet/dlink/sundance.c SUPERH +M: Yoshinori Sato +M: Rich Felker L: linux-sh@vger.kernel.org Q: http://patchwork.kernel.org/project/linux-sh/list/ -S: Orphan +S: Maintained F: Documentation/sh/ F: arch/sh/ F: drivers/sh/ From f4595e0081495b677a98c780e9ec1ab68ce89488 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Tue, 2 Feb 2016 16:57:52 -0800 Subject: [PATCH 301/325] radix-tree: fix race in gang lookup commit 46437f9a554fbe3e110580ca08ab703b59f2f95a upstream. If the indirect_ptr bit is set on a slot, that indicates we need to redo the lookup. Introduce a new function radix_tree_iter_retry() which forces the loop to retry the lookup by setting 'slot' to NULL and turning the iterator back to point at the problematic entry. This is a pretty rare problem to hit at the moment; the lookup has to race with a grow of the radix tree from a height of 0. The consequences of hitting this race are that gang lookup could return a pointer to a radix_tree_node instead of a pointer to whatever the user had inserted in the tree. Fixes: cebbd29e1c2f ("radix-tree: rewrite gang lookup using iterator") Signed-off-by: Matthew Wilcox Cc: Hugh Dickins Cc: Ohad Ben-Cohen Cc: Konstantin Khlebnikov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- include/linux/radix-tree.h | 16 ++++++++++++++++ lib/radix-tree.c | 12 ++++++++++-- 2 files changed, 26 insertions(+), 2 deletions(-) diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 33170dbd9db4..1a2b2276ffb3 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -369,6 +369,22 @@ radix_tree_iter_init(struct radix_tree_iter *iter, unsigned long start) void **radix_tree_next_chunk(struct radix_tree_root *root, struct radix_tree_iter *iter, unsigned flags); +/** + * radix_tree_iter_retry - retry this chunk of the iteration + * @iter: iterator state + * + * If we iterate over a tree protected only by the RCU lock, a race + * against deletion or creation may result in seeing a slot for which + * radix_tree_deref_retry() returns true. If so, call this function + * and continue the iteration. + */ +static inline __must_check +void **radix_tree_iter_retry(struct radix_tree_iter *iter) +{ + iter->next_index = iter->index; + return NULL; +} + /** * radix_tree_chunk_size - get current chunk size * diff --git a/lib/radix-tree.c b/lib/radix-tree.c index fcf5d98574ce..6b79e9026e24 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -1019,9 +1019,13 @@ radix_tree_gang_lookup(struct radix_tree_root *root, void **results, return 0; radix_tree_for_each_slot(slot, root, &iter, first_index) { - results[ret] = indirect_to_ptr(rcu_dereference_raw(*slot)); + results[ret] = rcu_dereference_raw(*slot); if (!results[ret]) continue; + if (radix_tree_is_indirect_ptr(results[ret])) { + slot = radix_tree_iter_retry(&iter); + continue; + } if (++ret == max_items) break; } @@ -1098,9 +1102,13 @@ radix_tree_gang_lookup_tag(struct radix_tree_root *root, void **results, return 0; radix_tree_for_each_tagged(slot, root, &iter, first_index, tag) { - results[ret] = indirect_to_ptr(rcu_dereference_raw(*slot)); + results[ret] = rcu_dereference_raw(*slot); if (!results[ret]) continue; + if (radix_tree_is_indirect_ptr(results[ret])) { + slot = radix_tree_iter_retry(&iter); + continue; + } if (++ret == max_items) break; } From 077b6173a8c89d666a06203f42267ff8b6d02d73 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Tue, 2 Feb 2016 16:57:55 -0800 Subject: [PATCH 302/325] drivers/hwspinlock: fix race between radix tree insertion and lookup commit c6400ba7e13a41539342f1b6e1f9e78419cb0148 upstream. of_hwspin_lock_get_id() is protected by the RCU lock, which means that insertions can occur simultaneously with the lookup. If the radix tree transitions from a height of 0, we can see a slot with the indirect_ptr bit set, which will cause us to at least read random memory, and could cause other havoc. Fix this by using the newly introduced radix_tree_iter_retry(). Signed-off-by: Matthew Wilcox Cc: Hugh Dickins Cc: Ohad Ben-Cohen Cc: Konstantin Khlebnikov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- drivers/hwspinlock/hwspinlock_core.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/hwspinlock/hwspinlock_core.c b/drivers/hwspinlock/hwspinlock_core.c index 52f708bcf77f..d50c701b19d6 100644 --- a/drivers/hwspinlock/hwspinlock_core.c +++ b/drivers/hwspinlock/hwspinlock_core.c @@ -313,6 +313,10 @@ int of_hwspin_lock_get_id(struct device_node *np, int index) hwlock = radix_tree_deref_slot(slot); if (unlikely(!hwlock)) continue; + if (radix_tree_is_indirect_ptr(hwlock)) { + slot = radix_tree_iter_retry(&iter); + continue; + } if (hwlock->bank->dev->of_node == args.np) { ret = 0; From 55e0d9869f1d3a6bbd5d1e864c0e866fe1247f97 Mon Sep 17 00:00:00 2001 From: Konstantin Khlebnikov Date: Fri, 5 Feb 2016 15:37:01 -0800 Subject: [PATCH 303/325] radix-tree: fix oops after radix_tree_iter_retry commit 732042821cfa106b3c20b9780e4c60fee9d68900 upstream. Helper radix_tree_iter_retry() resets next_index to the current index. In following radix_tree_next_slot current chunk size becomes zero. This isn't checked and it tries to dereference null pointer in slot. Tagged iterator is fine because retry happens only at slot 0 where tag bitmask in iter->tags is filled with single bit. Fixes: 46437f9a554f ("radix-tree: fix race in gang lookup") Signed-off-by: Konstantin Khlebnikov Cc: Matthew Wilcox Cc: Hugh Dickins Cc: Ohad Ben-Cohen Cc: Jeremiah Mahler Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- include/linux/radix-tree.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 1a2b2276ffb3..5d5174b59802 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -391,7 +391,7 @@ void **radix_tree_iter_retry(struct radix_tree_iter *iter) * @iter: pointer to radix tree iterator * Returns: current chunk size */ -static __always_inline unsigned +static __always_inline long radix_tree_chunk_size(struct radix_tree_iter *iter) { return iter->next_index - iter->index; @@ -425,9 +425,9 @@ radix_tree_next_slot(void **slot, struct radix_tree_iter *iter, unsigned flags) return slot + offset + 1; } } else { - unsigned size = radix_tree_chunk_size(iter) - 1; + long size = radix_tree_chunk_size(iter); - while (size--) { + while (--size > 0) { slot++; iter->index++; if (likely(*slot)) From e31e4672559674b0950885465a42968a86865d42 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 5 Feb 2016 15:36:16 -0800 Subject: [PATCH 304/325] dump_stack: avoid potential deadlocks commit d7ce36924344ace0dbdc855b1206cacc46b36d45 upstream. Some servers experienced fatal deadlocks because of a combination of bugs, leading to multiple cpus calling dump_stack(). The checksumming bug was fixed in commit 34ae6a1aa054 ("ipv6: update skb->csum when CE mark is propagated"). The second problem is a faulty locking in dump_stack() CPU1 runs in process context and calls dump_stack(), grabs dump_lock. CPU2 receives a TCP packet under softirq, grabs socket spinlock, and call dump_stack() from netdev_rx_csum_fault(). dump_stack() spins on atomic_cmpxchg(&dump_lock, -1, 2), since dump_lock is owned by CPU1 While dumping its stack, CPU1 is interrupted by a softirq, and happens to process a packet for the TCP socket locked by CPU2. CPU1 spins forever in spin_lock() : deadlock Stack trace on CPU1 looked like : NMI backtrace for cpu 1 RIP: _raw_spin_lock+0x25/0x30 ... Call Trace: tcp_v6_rcv+0x243/0x620 ip6_input_finish+0x11f/0x330 ip6_input+0x38/0x40 ip6_rcv_finish+0x3c/0x90 ipv6_rcv+0x2a9/0x500 process_backlog+0x461/0xaa0 net_rx_action+0x147/0x430 __do_softirq+0x167/0x2d0 call_softirq+0x1c/0x30 do_softirq+0x3f/0x80 irq_exit+0x6e/0xc0 smp_call_function_single_interrupt+0x35/0x40 call_function_single_interrupt+0x6a/0x70 printk+0x4d/0x4f printk_address+0x31/0x33 print_trace_address+0x33/0x3c print_context_stack+0x7f/0x119 dump_trace+0x26b/0x28e show_trace_log_lvl+0x4f/0x5c show_stack_log_lvl+0x104/0x113 show_stack+0x42/0x44 dump_stack+0x46/0x58 netdev_rx_csum_fault+0x38/0x3c __skb_checksum_complete_head+0x6e/0x80 __skb_checksum_complete+0x11/0x20 tcp_rcv_established+0x2bd5/0x2fd0 tcp_v6_do_rcv+0x13c/0x620 sk_backlog_rcv+0x15/0x30 release_sock+0xd2/0x150 tcp_recvmsg+0x1c1/0xfc0 inet_recvmsg+0x7d/0x90 sock_recvmsg+0xaf/0xe0 ___sys_recvmsg+0x111/0x3b0 SyS_recvmsg+0x5c/0xb0 system_call_fastpath+0x16/0x1b Fixes: b58d977432c8 ("dump_stack: serialize the output from dump_stack()") Signed-off-by: Eric Dumazet Cc: Alex Thorlton Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- lib/dump_stack.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/lib/dump_stack.c b/lib/dump_stack.c index 6745c6230db3..c30d07e99dba 100644 --- a/lib/dump_stack.c +++ b/lib/dump_stack.c @@ -25,6 +25,7 @@ static atomic_t dump_lock = ATOMIC_INIT(-1); asmlinkage __visible void dump_stack(void) { + unsigned long flags; int was_locked; int old; int cpu; @@ -33,9 +34,8 @@ asmlinkage __visible void dump_stack(void) * Permit this cpu to perform nested stack dumps while serialising * against other CPUs */ - preempt_disable(); - retry: + local_irq_save(flags); cpu = smp_processor_id(); old = atomic_cmpxchg(&dump_lock, -1, cpu); if (old == -1) { @@ -43,6 +43,7 @@ retry: } else if (old == cpu) { was_locked = 1; } else { + local_irq_restore(flags); cpu_relax(); goto retry; } @@ -52,7 +53,7 @@ retry: if (!was_locked) atomic_set(&dump_lock, -1); - preempt_enable(); + local_irq_restore(flags); } #else asmlinkage __visible void dump_stack(void) From edfde263bd8a70a0b93b11996fd2a77526ff3b80 Mon Sep 17 00:00:00 2001 From: Vineet Gupta Date: Thu, 11 Feb 2016 16:13:09 -0800 Subject: [PATCH 305/325] mm,thp: khugepaged: call pte flush at the time of collapse commit 6a6ac72fd6ea32594b316513e1826c3f6db4cc93 upstream. This showed up on ARC when running LMBench bw_mem tests as Overlapping TLB Machine Check Exception triggered due to STLB entry (2M pages) overlapping some NTLB entry (regular 8K page). bw_mem 2m touches a large chunk of vaddr creating NTLB entries. In the interim khugepaged kicks in, collapsing the contiguous ptes into a single pmd. pmdp_collapse_flush()->flush_pmd_tlb_range() is called to flush out NTLB entries for the ptes. This for ARC (by design) can only shootdown STLB entries (for pmd). The stray NTLB entries cause the overlap with the subsequent STLB entry for collapsed page. So make pmdp_collapse_flush() call pte flush interface not pmd flush. Note that originally all thp flush call sites in generic code called flush_tlb_range() leaving it to architecture to implement the flush for pte and/or pmd. Commit 12ebc1581ad11454 changed this by calling a new opt-in API flush_pmd_tlb_range() which made the semantics more explicit but failed to distinguish the pte vs pmd flush in generic code, which is what this patch fixes. Note that ARC can fixed w/o touching the generic pmdp_collapse_flush() by defining a ARC version, but that defeats the purpose of generic version, plus sementically this is the right thing to do. Fixes STAR 9000961194: LMBench on AXS103 triggering duplicate TLB exceptions with super pages Fixes: 12ebc1581ad11454 ("mm,thp: introduce flush_pmd_tlb_range") Signed-off-by: Vineet Gupta Reviewed-by: Aneesh Kumar K.V Acked-by: Kirill A. Shutemov Cc: Andrea Arcangeli Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- mm/pgtable-generic.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c index 7d3db0247983..1ba58213ad65 100644 --- a/mm/pgtable-generic.c +++ b/mm/pgtable-generic.c @@ -210,7 +210,9 @@ pmd_t pmdp_collapse_flush(struct vm_area_struct *vma, unsigned long address, VM_BUG_ON(address & ~HPAGE_PMD_MASK); VM_BUG_ON(pmd_trans_huge(*pmdp)); pmd = pmdp_huge_get_and_clear(vma->vm_mm, address, pmdp); - flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE); + + /* collapse entails shooting down ptes not pmd */ + flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE); return pmd; } #endif From fe90acff279808bf69425a1118639273a656c981 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Tue, 26 Jan 2016 12:24:25 +0300 Subject: [PATCH 306/325] intel_scu_ipcutil: underflow in scu_reg_access() commit b1d353ad3d5835b16724653b33c05124e1b5acf1 upstream. "count" is controlled by the user and it can be negative. Let's prevent that by making it unsigned. You have to have CAP_SYS_RAWIO to call this function so the bug is not as serious as it could be. Fixes: 5369c02d951a ('intel_scu_ipc: Utility driver for intel scu ipc') Signed-off-by: Dan Carpenter Signed-off-by: Darren Hart Signed-off-by: Greg Kroah-Hartman --- drivers/platform/x86/intel_scu_ipcutil.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/platform/x86/intel_scu_ipcutil.c b/drivers/platform/x86/intel_scu_ipcutil.c index 02bc5a6343c3..aa454241489c 100644 --- a/drivers/platform/x86/intel_scu_ipcutil.c +++ b/drivers/platform/x86/intel_scu_ipcutil.c @@ -49,7 +49,7 @@ struct scu_ipc_data { static int scu_reg_access(u32 cmd, struct scu_ipc_data *data) { - int count = data->count; + unsigned int count = data->count; if (count == 0 || count == 3 || count > 4) return -EINVAL; From 15db15e2f10ae12d021c9a2e9edd8a03b9238551 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Wed, 17 Feb 2016 13:11:35 -0800 Subject: [PATCH 307/325] ipc/shm: handle removed segments gracefully in shm_mmap() commit 1ac0b6dec656f3f78d1c3dd216fad84cb4d0a01e upstream. remap_file_pages(2) emulation can reach file which represents removed IPC ID as long as a memory segment is mapped. It breaks expectations of IPC subsystem. Test case (rewritten to be more human readable, originally autogenerated by syzkaller[1]): #define _GNU_SOURCE #include #include #include #include #define PAGE_SIZE 4096 int main() { int id; void *p; id = shmget(IPC_PRIVATE, 3 * PAGE_SIZE, 0); p = shmat(id, NULL, 0); shmctl(id, IPC_RMID, NULL); remap_file_pages(p, 3 * PAGE_SIZE, 0, 7, 0); return 0; } The patch changes shm_mmap() and code around shm_lock() to propagate locking error back to caller of shm_mmap(). [1] http://github.com/google/syzkaller Signed-off-by: Kirill A. Shutemov Reported-by: Dmitry Vyukov Cc: Davidlohr Bueso Cc: Manfred Spraul Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- ipc/shm.c | 55 ++++++++++++++++++++++++++++++++++++++++++++----------- 1 file changed, 44 insertions(+), 11 deletions(-) diff --git a/ipc/shm.c b/ipc/shm.c index 41787276e141..3174634ca4e5 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -156,11 +156,12 @@ static inline struct shmid_kernel *shm_lock(struct ipc_namespace *ns, int id) struct kern_ipc_perm *ipcp = ipc_lock(&shm_ids(ns), id); /* - * We raced in the idr lookup or with shm_destroy(). Either way, the - * ID is busted. + * Callers of shm_lock() must validate the status of the returned ipc + * object pointer (as returned by ipc_lock()), and error out as + * appropriate. */ - WARN_ON(IS_ERR(ipcp)); - + if (IS_ERR(ipcp)) + return (void *)ipcp; return container_of(ipcp, struct shmid_kernel, shm_perm); } @@ -186,18 +187,33 @@ static inline void shm_rmid(struct ipc_namespace *ns, struct shmid_kernel *s) } -/* This is called by fork, once for every shm attach. */ -static void shm_open(struct vm_area_struct *vma) +static int __shm_open(struct vm_area_struct *vma) { struct file *file = vma->vm_file; struct shm_file_data *sfd = shm_file_data(file); struct shmid_kernel *shp; shp = shm_lock(sfd->ns, sfd->id); + + if (IS_ERR(shp)) + return PTR_ERR(shp); + shp->shm_atim = get_seconds(); shp->shm_lprid = task_tgid_vnr(current); shp->shm_nattch++; shm_unlock(shp); + return 0; +} + +/* This is called by fork, once for every shm attach. */ +static void shm_open(struct vm_area_struct *vma) +{ + int err = __shm_open(vma); + /* + * We raced in the idr lookup or with shm_destroy(). + * Either way, the ID is busted. + */ + WARN_ON_ONCE(err); } /* @@ -260,6 +276,14 @@ static void shm_close(struct vm_area_struct *vma) down_write(&shm_ids(ns).rwsem); /* remove from the list of attaches of the shm segment */ shp = shm_lock(ns, sfd->id); + + /* + * We raced in the idr lookup or with shm_destroy(). + * Either way, the ID is busted. + */ + if (WARN_ON_ONCE(IS_ERR(shp))) + goto done; /* no-op */ + shp->shm_lprid = task_tgid_vnr(current); shp->shm_dtim = get_seconds(); shp->shm_nattch--; @@ -267,6 +291,7 @@ static void shm_close(struct vm_area_struct *vma) shm_destroy(ns, shp); else shm_unlock(shp); +done: up_write(&shm_ids(ns).rwsem); } @@ -388,17 +413,25 @@ static int shm_mmap(struct file *file, struct vm_area_struct *vma) struct shm_file_data *sfd = shm_file_data(file); int ret; - ret = sfd->file->f_op->mmap(sfd->file, vma); - if (ret != 0) + /* + * In case of remap_file_pages() emulation, the file can represent + * removed IPC ID: propogate shm_lock() error to caller. + */ + ret =__shm_open(vma); + if (ret) return ret; + + ret = sfd->file->f_op->mmap(sfd->file, vma); + if (ret) { + shm_close(vma); + return ret; + } sfd->vm_ops = vma->vm_ops; #ifdef CONFIG_MMU WARN_ON(!sfd->vm_ops->fault); #endif vma->vm_ops = &shm_vm_ops; - shm_open(vma); - - return ret; + return 0; } static int shm_release(struct inode *ino, struct file *file) From 30066dcdf98a1474d71b3ce8a05f81e14a61a3bd Mon Sep 17 00:00:00 2001 From: Toshi Kani Date: Wed, 17 Feb 2016 13:11:29 -0800 Subject: [PATCH 308/325] devm_memremap_release(): fix memremap'd addr handling commit 9273a8bbf58a15051e53a777389a502420ddc60e upstream. The pmem driver calls devm_memremap() to map a persistent memory range. When the pmem driver is unloaded, this memremap'd range is not released so the kernel will leak a vma. Fix devm_memremap_release() to handle a given memremap'd address properly. Signed-off-by: Toshi Kani Acked-by: Dan Williams Cc: Christoph Hellwig Cc: Ross Zwisler Cc: Matthew Wilcox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- kernel/memremap.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/memremap.c b/kernel/memremap.c index 7658d32c5c78..7a4e473cea4d 100644 --- a/kernel/memremap.c +++ b/kernel/memremap.c @@ -111,7 +111,7 @@ EXPORT_SYMBOL(memunmap); static void devm_memremap_release(struct device *dev, void *res) { - memunmap(res); + memunmap(*(void **)res); } static int devm_memremap_match(struct device *dev, void *res, void *match_data) From acaf84251f8d49d0e7ee41d654f987dbd441f991 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sat, 19 Dec 2015 20:07:38 +0000 Subject: [PATCH 309/325] futex: Drop refcount if requeue_pi() acquired the rtmutex commit fb75a4282d0d9a3c7c44d940582c2d226cf3acfb upstream. If the proxy lock in the requeue loop acquires the rtmutex for a waiter then it acquired also refcount on the pi_state related to the futex, but the waiter side does not drop the reference count. Add the missing free_pi_state() call. Signed-off-by: Thomas Gleixner Cc: Peter Zijlstra Cc: Darren Hart Cc: Davidlohr Bueso Cc: Bhuvanesh_Surachari@mentor.com Cc: Andy Lowe Link: http://lkml.kernel.org/r/20151219200607.178132067@linutronix.de Signed-off-by: Thomas Gleixner Signed-off-by: Greg Kroah-Hartman --- kernel/futex.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/kernel/futex.c b/kernel/futex.c index 495a1d06915b..461c72b2dac2 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -2755,6 +2755,11 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, if (q.pi_state && (q.pi_state->owner != current)) { spin_lock(q.lock_ptr); ret = fixup_pi_state_owner(uaddr2, &q, current); + /* + * Drop the reference to the pi state which + * the requeue_pi() code acquired for us. + */ + free_pi_state(q.pi_state); spin_unlock(q.lock_ptr); } } else { From 85a7ed329aca5efd0eb70789db145a1e989c7a53 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Tue, 10 Nov 2015 17:08:41 +0100 Subject: [PATCH 310/325] ovl: allow zero size xattr commit 97daf8b97ad6f913a34c82515be64dc9ac08d63e upstream. When ovl_copy_xattr() encountered a zero size xattr no more xattrs were copied and the function returned success. This is clearly not the desired behavior. Signed-off-by: Miklos Szeredi Signed-off-by: Greg Kroah-Hartman --- fs/overlayfs/copy_up.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c index 0a8983492d91..927cb5668dc7 100644 --- a/fs/overlayfs/copy_up.c +++ b/fs/overlayfs/copy_up.c @@ -54,7 +54,7 @@ int ovl_copy_xattr(struct dentry *old, struct dentry *new) for (name = buf; name < (buf + list_size); name += strlen(name) + 1) { size = vfs_getxattr(old, name, value, XATTR_SIZE_MAX); - if (size <= 0) { + if (size < 0) { error = size; goto out_free_value; } From fa932190a5f332e1936ab0223c7c5d79b5596a9c Mon Sep 17 00:00:00 2001 From: Vito Caputo Date: Sat, 24 Oct 2015 07:19:46 -0500 Subject: [PATCH 311/325] ovl: use a minimal buffer in ovl_copy_xattr commit e4ad29fa0d224d05e08b2858e65f112fd8edd4fe upstream. Rather than always allocating the high-order XATTR_SIZE_MAX buffer which is costly and prone to failure, only allocate what is needed and realloc if necessary. Fixes https://github.com/coreos/bugs/issues/489 Signed-off-by: Miklos Szeredi Signed-off-by: Greg Kroah-Hartman --- fs/overlayfs/copy_up.c | 39 +++++++++++++++++++++++++-------------- 1 file changed, 25 insertions(+), 14 deletions(-) diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c index 927cb5668dc7..eff6319d5037 100644 --- a/fs/overlayfs/copy_up.c +++ b/fs/overlayfs/copy_up.c @@ -22,9 +22,9 @@ int ovl_copy_xattr(struct dentry *old, struct dentry *new) { - ssize_t list_size, size; - char *buf, *name, *value; - int error; + ssize_t list_size, size, value_size = 0; + char *buf, *name, *value = NULL; + int uninitialized_var(error); if (!old->d_inode->i_op->getxattr || !new->d_inode->i_op->getxattr) @@ -41,29 +41,40 @@ int ovl_copy_xattr(struct dentry *old, struct dentry *new) if (!buf) return -ENOMEM; - error = -ENOMEM; - value = kmalloc(XATTR_SIZE_MAX, GFP_KERNEL); - if (!value) - goto out; - list_size = vfs_listxattr(old, buf, list_size); if (list_size <= 0) { error = list_size; - goto out_free_value; + goto out; } for (name = buf; name < (buf + list_size); name += strlen(name) + 1) { - size = vfs_getxattr(old, name, value, XATTR_SIZE_MAX); +retry: + size = vfs_getxattr(old, name, value, value_size); + if (size == -ERANGE) + size = vfs_getxattr(old, name, NULL, 0); + if (size < 0) { error = size; - goto out_free_value; + break; } + + if (size > value_size) { + void *new; + + new = krealloc(value, size, GFP_KERNEL); + if (!new) { + error = -ENOMEM; + break; + } + value = new; + value_size = size; + goto retry; + } + error = vfs_setxattr(new, name, value, size, 0); if (error) - goto out_free_value; + break; } - -out_free_value: kfree(value); out: kfree(buf); From 367e439dbc238907963ddf2758200b55087cab04 Mon Sep 17 00:00:00 2001 From: Konstantin Khlebnikov Date: Mon, 16 Nov 2015 18:44:11 +0300 Subject: [PATCH 312/325] ovl: check dentry positiveness in ovl_cleanup_whiteouts() commit 84889d49335627bc770b32787c1ef9ebad1da232 upstream. This patch fixes kernel crash at removing directory which contains whiteouts from lower layers. Cache of directory content passed as "list" contains entries from all layers, including whiteouts from lower layers. So, lookup in upper dir (moved into work at this stage) will return negative entry. Plus this cache is filled long before and we can race with external removal. Example: mkdir -p lower0/dir lower1/dir upper work overlay touch lower0/dir/a lower0/dir/b mknod lower1/dir/a c 0 0 mount -t overlay none overlay -o lowerdir=lower1:lower0,upperdir=upper,workdir=work rm -fr overlay/dir Signed-off-by: Konstantin Khlebnikov Signed-off-by: Miklos Szeredi Signed-off-by: Greg Kroah-Hartman --- fs/overlayfs/readdir.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c index 70e9af551600..adcb1398c481 100644 --- a/fs/overlayfs/readdir.c +++ b/fs/overlayfs/readdir.c @@ -571,7 +571,8 @@ void ovl_cleanup_whiteouts(struct dentry *upper, struct list_head *list) (int) PTR_ERR(dentry)); continue; } - ovl_cleanup(upper->d_inode, dentry); + if (dentry->d_inode) + ovl_cleanup(upper->d_inode, dentry); dput(dentry); } mutex_unlock(&upper->d_inode->i_mutex); From 7193e802960f884e0ae6c40711c4e3c70fa3b070 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Wed, 9 Dec 2015 16:11:59 +0100 Subject: [PATCH 313/325] ovl: root: copy attr commit ed06e069775ad9236087594a1c1667367e983fb5 upstream. We copy i_uid and i_gid of underlying inode into overlayfs inode. Except for the root inode. Fix this omission. Signed-off-by: Miklos Szeredi Signed-off-by: Greg Kroah-Hartman --- fs/overlayfs/super.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index e38ee0fed24a..ff826652feae 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -1053,6 +1053,9 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) root_dentry->d_fsdata = oe; + ovl_copyattr(ovl_dentry_real(root_dentry)->d_inode, + root_dentry->d_inode); + sb->s_magic = OVERLAYFS_SUPER_MAGIC; sb->s_op = &ovl_super_operations; sb->s_root = root_dentry; From 8373f6590f6b371bff2c5f2c0581548eb0192014 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Fri, 11 Dec 2015 16:30:49 +0100 Subject: [PATCH 314/325] ovl: setattr: check permissions before copy-up commit cf9a6784f7c1b5ee2b9159a1246e327c331c5697 upstream. Without this copy-up of a file can be forced, even without actually being allowed to do anything on the file. [Arnd Bergmann] include for PAGE_CACHE_SIZE (used by MAX_LFS_FILESIZE definition). Signed-off-by: Miklos Szeredi Signed-off-by: Greg Kroah-Hartman --- fs/overlayfs/inode.c | 13 +++++++++++++ fs/overlayfs/super.c | 2 ++ 2 files changed, 15 insertions(+) diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index 4060ffde8722..b29036aa8d7c 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -42,6 +42,19 @@ int ovl_setattr(struct dentry *dentry, struct iattr *attr) int err; struct dentry *upperdentry; + /* + * Check for permissions before trying to copy-up. This is redundant + * since it will be rechecked later by ->setattr() on upper dentry. But + * without this, copy-up can be triggered by just about anybody. + * + * We don't initialize inode->size, which just means that + * inode_newsize_ok() will always check against MAX_LFS_FILESIZE and not + * check for a swapfile (which this won't be anyway). + */ + err = inode_change_ok(dentry->d_inode, attr); + if (err) + return err; + err = ovl_want_write(dentry); if (err) goto out; diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index ff826652feae..f42c9407fbad 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -9,6 +9,7 @@ #include #include +#include #include #include #include @@ -910,6 +911,7 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) } sb->s_stack_depth = 0; + sb->s_maxbytes = MAX_LFS_FILESIZE; if (ufs->config.upperdir) { if (!ufs->config.workdir) { pr_err("overlayfs: missing 'workdir'\n"); From 888959f2fd5042609f1beefe663ced4dea4dc109 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Mon, 4 Jan 2016 16:13:21 +1100 Subject: [PATCH 315/325] libxfs: pack the agfl header structure so XFS_AGFL_SIZE is correct commit 96f859d52bcb1c6ea6f3388d39862bf7143e2f30 upstream. Because struct xfs_agfl is 36 bytes long and has a 64-bit integer inside it, gcc will quietly round the structure size up to the nearest 64 bits -- in this case, 40 bytes. This results in the XFS_AGFL_SIZE macro returning incorrect results for v5 filesystems on 64-bit machines (118 items instead of 119). As a result, a 32-bit xfs_repair will see garbage in AGFL item 119 and complain. Therefore, tell gcc not to pad the structure so that the AGFL size calculation is correct. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner Signed-off-by: Dave Chinner Signed-off-by: Greg Kroah-Hartman --- fs/xfs/libxfs/xfs_format.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h index 8774498ce0ff..e2536bb1c760 100644 --- a/fs/xfs/libxfs/xfs_format.h +++ b/fs/xfs/libxfs/xfs_format.h @@ -786,7 +786,7 @@ typedef struct xfs_agfl { __be64 agfl_lsn; __be32 agfl_crc; __be32 agfl_bno[]; /* actually XFS_AGFL_SIZE(mp) */ -} xfs_agfl_t; +} __attribute__((packed)) xfs_agfl_t; #define XFS_AGFL_CRC_OFF offsetof(struct xfs_agfl, agfl_crc) From 7530e6fdd9f207a6ebcf669490656def4f7cf73e Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Tue, 12 Jan 2016 07:03:44 +1100 Subject: [PATCH 316/325] xfs: inode recovery readahead can race with inode buffer creation commit b79f4a1c68bb99152d0785ee4ea3ab4396cdacc6 upstream. When we do inode readahead in log recovery, we do can do the readahead before we've replayed the icreate transaction that stamps the buffer with inode cores. The inode readahead verifier catches this and marks the buffer as !done to indicate that it doesn't yet contain valid inodes. In adding buffer error notification (i.e. setting b_error = -EIO at the same time as as we clear the done flag) to such a readahead verifier failure, we can then get subsequent inode recovery failing with this error: XFS (dm-0): metadata I/O error: block 0xa00060 ("xlog_recover_do..(read#2)") error 5 numblks 32 This occurs when readahead completion races with icreate item replay such as: inode readahead find buffer lock buffer submit RA io .... icreate recovery xfs_trans_get_buffer find buffer lock buffer ..... fails verifier clear XBF_DONE set bp->b_error = -EIO release and unlock buffer icreate initialises buffer marks buffer as done adds buffer to delayed write queue releases buffer At this point, we have an initialised inode buffer that is up to date but has an -EIO state registered against it. When we finally get to recovering an inode in that buffer: inode item recovery xfs_trans_read_buffer find buffer lock buffer sees XBF_DONE is set, returns buffer sees bp->b_error is set fail log recovery! Essentially, we need xfs_trans_get_buf_map() to clear the error status of the buffer when doing a lookup. This function returns uninitialised buffers, so the buffer returned can not be in an error state and none of the code that uses this function expects b_error to be set on return. Indeed, there is an ASSERT(!bp->b_error); in the transaction case in xfs_trans_get_buf_map() that would have caught this if log recovery used transactions.... This patch firstly changes the inode readahead failure to set -EIO on the buffer, and secondly changes xfs_buf_get_map() to never return a buffer with an error state set so this first change doesn't cause unexpected log recovery failures. Signed-off-by: Dave Chinner Reviewed-by: Brian Foster Signed-off-by: Dave Chinner Signed-off-by: Greg Kroah-Hartman --- fs/xfs/libxfs/xfs_inode_buf.c | 12 +++++++----- fs/xfs/xfs_buf.c | 7 +++++++ 2 files changed, 14 insertions(+), 5 deletions(-) diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c index 268c00f4f83a..65485cfc4ade 100644 --- a/fs/xfs/libxfs/xfs_inode_buf.c +++ b/fs/xfs/libxfs/xfs_inode_buf.c @@ -62,11 +62,12 @@ xfs_inobp_check( * has not had the inode cores stamped into it. Hence for readahead, the buffer * may be potentially invalid. * - * If the readahead buffer is invalid, we don't want to mark it with an error, - * but we do want to clear the DONE status of the buffer so that a followup read - * will re-read it from disk. This will ensure that we don't get an unnecessary - * warnings during log recovery and we don't get unnecssary panics on debug - * kernels. + * If the readahead buffer is invalid, we need to mark it with an error and + * clear the DONE status of the buffer so that a followup read will re-read it + * from disk. We don't report the error otherwise to avoid warnings during log + * recovery and we don't get unnecssary panics on debug kernels. We use EIO here + * because all we want to do is say readahead failed; there is no-one to report + * the error to, so this will distinguish it from a non-ra verifier failure. */ static void xfs_inode_buf_verify( @@ -93,6 +94,7 @@ xfs_inode_buf_verify( XFS_RANDOM_ITOBP_INOTOBP))) { if (readahead) { bp->b_flags &= ~XBF_DONE; + xfs_buf_ioerror(bp, -EIO); return; } diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index 3243cdf97f33..2f022aa1275a 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -604,6 +604,13 @@ found: } } + /* + * Clear b_error if this is a lookup from a caller that doesn't expect + * valid data to be found in the buffer. + */ + if (!(flags & XBF_READ)) + xfs_buf_ioerror(bp, 0); + XFS_STATS_INC(target->bt_mount, xb_get); trace_xfs_buf_get(bp, flags, _RET_IP_); return bp; From 16f14a28f660d0a3bdb169ebd17e0181c03d4778 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Tue, 19 Jan 2016 08:21:46 +1100 Subject: [PATCH 317/325] Revert "xfs: clear PF_NOFREEZE for xfsaild kthread" commit 3e85286e75224fa3f08bdad20e78c8327742634e upstream. This reverts commit 24ba16bb3d499c49974669cd8429c3e4138ab102 as it prevents machines from suspending. This regression occurs when the xfsaild is idle on entry to suspend, and so there s no activity to wake it from it's idle sleep and hence see that it is supposed to freeze. Hence the freezer times out waiting for it and suspend is cancelled. There is no obvious fix for this short of freezing the filesystem properly, so revert this change for now. Signed-off-by: Dave Chinner Acked-by: Jiri Kosina Reviewed-by: Brian Foster Signed-off-by: Dave Chinner Signed-off-by: Greg Kroah-Hartman --- fs/xfs/xfs_trans_ail.c | 1 - 1 file changed, 1 deletion(-) diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c index aa67339b9537..4f18fd92ca13 100644 --- a/fs/xfs/xfs_trans_ail.c +++ b/fs/xfs/xfs_trans_ail.c @@ -497,7 +497,6 @@ xfsaild( long tout = 0; /* milliseconds */ current->flags |= PF_MEMALLOC; - set_freezable(); while (!kthread_should_stop()) { if (tout && tout <= 20) From f86701c4f3cd59bac9363846e62fd26ecb2437c2 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Tue, 19 Jan 2016 08:28:10 +1100 Subject: [PATCH 318/325] xfs: log mount failures don't wait for buffers to be released commit 85bec5460ad8e05e0a8d70fb0f6750eb719ad092 upstream. Recently I've been seeing xfs/051 fail on 1k block size filesystems. Trying to trace the events during the test lead to the problem going away, indicating that it was a race condition that lead to this ASSERT failure: XFS: Assertion failed: atomic_read(&pag->pag_ref) == 0, file: fs/xfs/xfs_mount.c, line: 156 ..... [] xfs_free_perag+0x87/0xb0 [] xfs_mountfs+0x4d9/0x900 [] xfs_fs_fill_super+0x3bf/0x4d0 [] mount_bdev+0x180/0x1b0 [] xfs_fs_mount+0x15/0x20 [] mount_fs+0x38/0x170 [] vfs_kern_mount+0x67/0x120 [] do_mount+0x218/0xd60 [] SyS_mount+0x8b/0xd0 When I finally caught it with tracing enabled, I saw that AG 2 had an elevated reference count and a buffer was responsible for it. I tracked down the specific buffer, and found that it was missing the final reference count release that would put it back on the LRU and hence be found by xfs_wait_buftarg() calls in the log mount failure handling. The last four traces for the buffer before the assert were (trimmed for relevance) kworker/0:1-5259 xfs_buf_iodone: hold 2 lock 0 flags ASYNC kworker/0:1-5259 xfs_buf_ioerror: hold 2 lock 0 error -5 mount-7163 xfs_buf_lock_done: hold 2 lock 0 flags ASYNC mount-7163 xfs_buf_unlock: hold 2 lock 1 flags ASYNC This is an async write that is completing, so there's nobody waiting for it directly. Hence we call xfs_buf_relse() once all the processing is complete. That does: static inline void xfs_buf_relse(xfs_buf_t *bp) { xfs_buf_unlock(bp); xfs_buf_rele(bp); } Now, it's clear that mount is waiting on the buffer lock, and that it has been released by xfs_buf_relse() and gained by mount. This is expected, because at this point the mount process is in xfs_buf_delwri_submit() waiting for all the IO it submitted to complete. The mount process, however, is waiting on the lock for the buffer because it is in xfs_buf_delwri_submit(). This waits for IO completion, but it doesn't wait for the buffer reference owned by the IO to go away. The mount process collects all the completions, fails the log recovery, and the higher level code then calls xfs_wait_buftarg() to free all the remaining buffers in the filesystem. The issue is that on unlocking the buffer, the scheduler has decided that the mount process has higher priority than the the kworker thread that is running the IO completion, and so immediately switched contexts to the mount process from the semaphore unlock code, hence preventing the kworker thread from finishing the IO completion and releasing the IO reference to the buffer. Hence by the time that xfs_wait_buftarg() is run, the buffer still has an active reference and so isn't on the LRU list that the function walks to free the remaining buffers. Hence we miss that buffer and continue onwards to tear down the mount structures, at which time we get find a stray reference count on the perag structure. On a non-debug kernel, this will be ignored and the structure torn down and freed. Hence when the kworker thread is then rescheduled and the buffer released and freed, it will access a freed perag structure. The problem here is that when the log mount fails, we still need to quiesce the log to ensure that the IO workqueues have returned to idle before we run xfs_wait_buftarg(). By synchronising the workqueues, we ensure that all IO completions are fully processed, not just to the point where buffers have been unlocked. This ensures we don't end up in the situation above. Signed-off-by: Dave Chinner Reviewed-by: Brian Foster Signed-off-by: Dave Chinner Signed-off-by: Greg Kroah-Hartman --- fs/xfs/xfs_buf.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index 2f022aa1275a..39090fc56f09 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -1527,6 +1527,16 @@ xfs_wait_buftarg( LIST_HEAD(dispose); int loop = 0; + /* + * We need to flush the buffer workqueue to ensure that all IO + * completion processing is 100% done. Just waiting on buffer locks is + * not sufficient for async IO as the reference count held over IO is + * not released until after the buffer lock is dropped. Hence we need to + * ensure here that all reference counts have been dropped before we + * start walking the LRU list. + */ + drain_workqueue(btp->bt_mount->m_buf_workqueue); + /* loop until there is nothing left on the lru list. */ while (list_lru_count(&btp->bt_lru)) { list_lru_walk(&btp->bt_lru, xfs_buftarg_wait_rele, From e5e99792b6474b38ef2dea33cbcd1dde5fd70330 Mon Sep 17 00:00:00 2001 From: Mateusz Guzik Date: Wed, 20 Jan 2016 15:01:02 -0800 Subject: [PATCH 319/325] prctl: take mmap sem for writing to protect against others commit ddf1d398e517e660207e2c807f76a90df543a217 upstream. An unprivileged user can trigger an oops on a kernel with CONFIG_CHECKPOINT_RESTORE. proc_pid_cmdline_read takes mmap_sem for reading and obtains args + env start/end values. These get sanity checked as follows: BUG_ON(arg_start > arg_end); BUG_ON(env_start > env_end); These can be changed by prctl_set_mm. Turns out also takes the semaphore for reading, effectively rendering it useless. This results in: kernel BUG at fs/proc/base.c:240! invalid opcode: 0000 [#1] SMP Modules linked in: virtio_net CPU: 0 PID: 925 Comm: a.out Not tainted 4.4.0-rc8-next-20160105dupa+ #71 Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011 task: ffff880077a68000 ti: ffff8800784d0000 task.ti: ffff8800784d0000 RIP: proc_pid_cmdline_read+0x520/0x530 RSP: 0018:ffff8800784d3db8 EFLAGS: 00010206 RAX: ffff880077c5b6b0 RBX: ffff8800784d3f18 RCX: 0000000000000000 RDX: 0000000000000002 RSI: 00007f78e8857000 RDI: 0000000000000246 RBP: ffff8800784d3e40 R08: 0000000000000008 R09: 0000000000000001 R10: 0000000000000000 R11: 0000000000000001 R12: 0000000000000050 R13: 00007f78e8857800 R14: ffff88006fcef000 R15: ffff880077c5b600 FS: 00007f78e884a740(0000) GS:ffff88007b200000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b CR2: 00007f78e8361770 CR3: 00000000790a5000 CR4: 00000000000006f0 Call Trace: __vfs_read+0x37/0x100 vfs_read+0x82/0x130 SyS_read+0x58/0xd0 entry_SYSCALL_64_fastpath+0x12/0x76 Code: 4c 8b 7d a8 eb e9 48 8b 9d 78 ff ff ff 4c 8b 7d 90 48 8b 03 48 39 45 a8 0f 87 f0 fe ff ff e9 d1 fe ff ff 4c 8b 7d 90 eb c6 0f 0b <0f> 0b 0f 0b 66 66 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 RIP proc_pid_cmdline_read+0x520/0x530 ---[ end trace 97882617ae9c6818 ]--- Turns out there are instances where the code just reads aformentioned values without locking whatsoever - namely environ_read and get_cmdline. Interestingly these functions look quite resilient against bogus values, but I don't believe this should be relied upon. The first patch gets rid of the oops bug by grabbing mmap_sem for writing. The second patch is optional and puts locking around aformentioned consumers for safety. Consumers of other fields don't seem to benefit from similar treatment and are left untouched. This patch (of 2): The code was taking the semaphore for reading, which does not protect against readers nor concurrent modifications. The problem could cause a sanity checks to fail in procfs's cmdline reader, resulting in an OOPS. Note that some functions perform an unlocked read of various mm fields, but they seem to be fine despite possible modificaton. Signed-off-by: Mateusz Guzik Acked-by: Cyrill Gorcunov Cc: Alexey Dobriyan Cc: Jarod Wilson Cc: Jan Stancek Cc: Al Viro Cc: Anshuman Khandual Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- kernel/sys.c | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) diff --git a/kernel/sys.c b/kernel/sys.c index 6af9212ab5aa..78947de6f969 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -1853,11 +1853,13 @@ static int prctl_set_mm_map(int opt, const void __user *addr, unsigned long data user_auxv[AT_VECTOR_SIZE - 1] = AT_NULL; } - if (prctl_map.exe_fd != (u32)-1) + if (prctl_map.exe_fd != (u32)-1) { error = prctl_set_mm_exe_file(mm, prctl_map.exe_fd); - down_read(&mm->mmap_sem); - if (error) - goto out; + if (error) + return error; + } + + down_write(&mm->mmap_sem); /* * We don't validate if these members are pointing to @@ -1894,10 +1896,8 @@ static int prctl_set_mm_map(int opt, const void __user *addr, unsigned long data if (prctl_map.auxv_size) memcpy(mm->saved_auxv, user_auxv, sizeof(user_auxv)); - error = 0; -out: - up_read(&mm->mmap_sem); - return error; + up_write(&mm->mmap_sem); + return 0; } #endif /* CONFIG_CHECKPOINT_RESTORE */ @@ -1963,7 +1963,7 @@ static int prctl_set_mm(int opt, unsigned long addr, error = -EINVAL; - down_read(&mm->mmap_sem); + down_write(&mm->mmap_sem); vma = find_vma(mm, addr); prctl_map.start_code = mm->start_code; @@ -2056,7 +2056,7 @@ static int prctl_set_mm(int opt, unsigned long addr, error = 0; out: - up_read(&mm->mmap_sem); + up_write(&mm->mmap_sem); return error; } From 565f222968d300657ad40d2fad91e4ccf3148d89 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 14 Jan 2016 16:54:46 +0000 Subject: [PATCH 320/325] timerfd: Handle relative timers with CONFIG_TIME_LOW_RES proper commit b62526ed11a1fe3861ab98d40b7fdab8981d788a upstream. Helge reported that a relative timer can return a remaining time larger than the programmed relative time on parisc and other architectures which have CONFIG_TIME_LOW_RES set. This happens because we add a jiffie to the resulting expiry time to prevent short timeouts. Use the new function hrtimer_expires_remaining_adjusted() to calculate the remaining time. It takes that extra added time into account for relative timers. Reported-and-tested-by: Helge Deller Signed-off-by: Thomas Gleixner Cc: Peter Zijlstra Cc: John Stultz Cc: linux-m68k@lists.linux-m68k.org Cc: dhowells@redhat.com Link: http://lkml.kernel.org/r/20160114164159.354500742@linutronix.de Signed-off-by: Thomas Gleixner Signed-off-by: Greg Kroah-Hartman --- fs/timerfd.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/timerfd.c b/fs/timerfd.c index b94fa6c3c6eb..053818dd6c18 100644 --- a/fs/timerfd.c +++ b/fs/timerfd.c @@ -153,7 +153,7 @@ static ktime_t timerfd_get_remaining(struct timerfd_ctx *ctx) if (isalarm(ctx)) remaining = alarm_expires_remaining(&ctx->t.alarm); else - remaining = hrtimer_expires_remaining(&ctx->t.tmr); + remaining = hrtimer_expires_remaining_adjusted(&ctx->t.tmr); return remaining.tv64 < 0 ? ktime_set(0, 0): remaining; } From 1c94da3e7480e3370945aad2b784343da9eb664f Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 14 Jan 2016 16:54:47 +0000 Subject: [PATCH 321/325] posix-timers: Handle relative timers with CONFIG_TIME_LOW_RES proper commit 572c39172684c3711e4a03c9a7380067e2b0661c upstream. As Helge reported for timerfd we have the same issue in posix timers. We return remaining time larger than the programmed relative time to user space in case of CONFIG_TIME_LOW_RES=y. Use the proper function to adjust the extra time added in hrtimer_start_range_ns(). Signed-off-by: Thomas Gleixner Cc: Peter Zijlstra Cc: Helge Deller Cc: John Stultz Cc: linux-m68k@lists.linux-m68k.org Cc: dhowells@redhat.com Link: http://lkml.kernel.org/r/20160114164159.450510905@linutronix.de Signed-off-by: Thomas Gleixner Signed-off-by: Greg Kroah-Hartman --- kernel/time/posix-timers.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index 31d11ac9fa47..f2826c35e918 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -760,7 +760,7 @@ common_timer_get(struct k_itimer *timr, struct itimerspec *cur_setting) (timr->it_sigev_notify & ~SIGEV_THREAD_ID) == SIGEV_NONE)) timr->it_overrun += (unsigned int) hrtimer_forward(timer, now, iv); - remaining = ktime_sub(hrtimer_get_expires(timer), now); + remaining = __hrtimer_expires_remaining_adjusted(timer, now); /* Return 0 only, when the timer is expired and not pending */ if (remaining.tv64 <= 0) { /* From 82e730baa9f7ba55cebe9365efde3e9f008d4376 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 14 Jan 2016 16:54:48 +0000 Subject: [PATCH 322/325] itimers: Handle relative timers with CONFIG_TIME_LOW_RES proper commit 51cbb5242a41700a3f250ecfb48dcfb7e4375ea4 upstream. As Helge reported for timerfd we have the same issue in itimers. We return remaining time larger than the programmed relative time to user space in case of CONFIG_TIME_LOW_RES=y. Use the proper function to adjust the extra time added in hrtimer_start_range_ns(). Signed-off-by: Thomas Gleixner Cc: Peter Zijlstra Cc: Helge Deller Cc: John Stultz Cc: linux-m68k@lists.linux-m68k.org Cc: dhowells@redhat.com Link: http://lkml.kernel.org/r/20160114164159.528222587@linutronix.de Signed-off-by: Thomas Gleixner Signed-off-by: Greg Kroah-Hartman --- kernel/time/itimer.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/time/itimer.c b/kernel/time/itimer.c index 8d262b467573..1d5c7204ddc9 100644 --- a/kernel/time/itimer.c +++ b/kernel/time/itimer.c @@ -26,7 +26,7 @@ */ static struct timeval itimer_get_remtime(struct hrtimer *timer) { - ktime_t rem = hrtimer_get_remaining(timer); + ktime_t rem = __hrtimer_get_remaining(timer, true); /* * Racy but safe: if the itimer expires after the above From a24d9a2fee9857a162ab18c9ad72aa6571ff4715 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Wed, 3 Feb 2016 16:55:26 +1030 Subject: [PATCH 323/325] module: wrapper for symbol name. commit 2e7bac536106236104e9e339531ff0fcdb7b8147 upstream. This trivial wrapper adds clarity and makes the following patch smaller. Signed-off-by: Rusty Russell Signed-off-by: Greg Kroah-Hartman --- kernel/module.c | 26 +++++++++++++++----------- 1 file changed, 15 insertions(+), 11 deletions(-) diff --git a/kernel/module.c b/kernel/module.c index 38c7bd5583ff..56d138cdaadb 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -3646,6 +3646,11 @@ static inline int is_arm_mapping_symbol(const char *str) && (str[2] == '\0' || str[2] == '.'); } +static const char *symname(struct module *mod, unsigned int symnum) +{ + return mod->strtab + mod->symtab[symnum].st_name; +} + static const char *get_ksymbol(struct module *mod, unsigned long addr, unsigned long *size, @@ -3668,15 +3673,15 @@ static const char *get_ksymbol(struct module *mod, /* We ignore unnamed symbols: they're uninformative * and inserted at a whim. */ + if (*symname(mod, i) == '\0' + || is_arm_mapping_symbol(symname(mod, i))) + continue; + if (mod->symtab[i].st_value <= addr - && mod->symtab[i].st_value > mod->symtab[best].st_value - && *(mod->strtab + mod->symtab[i].st_name) != '\0' - && !is_arm_mapping_symbol(mod->strtab + mod->symtab[i].st_name)) + && mod->symtab[i].st_value > mod->symtab[best].st_value) best = i; if (mod->symtab[i].st_value > addr - && mod->symtab[i].st_value < nextval - && *(mod->strtab + mod->symtab[i].st_name) != '\0' - && !is_arm_mapping_symbol(mod->strtab + mod->symtab[i].st_name)) + && mod->symtab[i].st_value < nextval) nextval = mod->symtab[i].st_value; } @@ -3687,7 +3692,7 @@ static const char *get_ksymbol(struct module *mod, *size = nextval - mod->symtab[best].st_value; if (offset) *offset = addr - mod->symtab[best].st_value; - return mod->strtab + mod->symtab[best].st_name; + return symname(mod, best); } /* For kallsyms to ask for address resolution. NULL means not found. Careful @@ -3782,8 +3787,7 @@ int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type, if (symnum < mod->num_symtab) { *value = mod->symtab[symnum].st_value; *type = mod->symtab[symnum].st_info; - strlcpy(name, mod->strtab + mod->symtab[symnum].st_name, - KSYM_NAME_LEN); + strlcpy(name, symname(mod, symnum), KSYM_NAME_LEN); strlcpy(module_name, mod->name, MODULE_NAME_LEN); *exported = is_exported(name, *value, mod); preempt_enable(); @@ -3800,7 +3804,7 @@ static unsigned long mod_find_symname(struct module *mod, const char *name) unsigned int i; for (i = 0; i < mod->num_symtab; i++) - if (strcmp(name, mod->strtab+mod->symtab[i].st_name) == 0 && + if (strcmp(name, symname(mod, i)) == 0 && mod->symtab[i].st_info != 'U') return mod->symtab[i].st_value; return 0; @@ -3844,7 +3848,7 @@ int module_kallsyms_on_each_symbol(int (*fn)(void *, const char *, if (mod->state == MODULE_STATE_UNFORMED) continue; for (i = 0; i < mod->num_symtab; i++) { - ret = fn(data, mod->strtab + mod->symtab[i].st_name, + ret = fn(data, symname(mod, i), mod, mod->symtab[i].st_value); if (ret != 0) return ret; From e2f712dc927e3b9a981ecd86a64d944d0b140322 Mon Sep 17 00:00:00 2001 From: "Luis R. Rodriguez" Date: Wed, 3 Feb 2016 16:55:26 +1030 Subject: [PATCH 324/325] modules: fix modparam async_probe request commit 4355efbd80482a961cae849281a8ef866e53d55c upstream. Commit f2411da746985 ("driver-core: add driver module asynchronous probe support") added async probe support, in two forms: * in-kernel driver specification annotation * generic async_probe module parameter (modprobe foo async_probe) To support the generic kernel parameter parse_args() was extended via commit ecc8617053e0 ("module: add extra argument for parse_params() callback") however commit failed to f2411da746985 failed to add the required argument. This causes a crash then whenever async_probe generic module parameter is used. This was overlooked when the form in which in-kernel async probe support was reworked a bit... Fix this as originally intended. Cc: Hannes Reinecke Cc: Dmitry Torokhov Signed-off-by: Luis R. Rodriguez Signed-off-by: Rusty Russell [minimized] Signed-off-by: Greg Kroah-Hartman --- kernel/module.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/module.c b/kernel/module.c index 56d138cdaadb..14833e6d5e37 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -3515,7 +3515,7 @@ static int load_module(struct load_info *info, const char __user *uargs, /* Module is ready to execute: parsing args may do that. */ after_dashes = parse_args(mod->name, mod->args, mod->kp, mod->num_kp, - -32768, 32767, NULL, + -32768, 32767, mod, unknown_module_param_cb); if (IS_ERR(after_dashes)) { err = PTR_ERR(after_dashes); From 2134d97aa3a7ce38bb51f933f2e20cafde371085 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 25 Feb 2016 12:01:36 -0800 Subject: [PATCH 325/325] Linux 4.4.3 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index e7a2958eb771..802be10c40c5 100644 --- a/Makefile +++ b/Makefile @@ -1,6 +1,6 @@ VERSION = 4 PATCHLEVEL = 4 -SUBLEVEL = 2 +SUBLEVEL = 3 EXTRAVERSION = NAME = Blurry Fish Butt