- Linux-stable-mirror - lists.linaro.org

[PATCH v4.14] KVM: PPC: Book3S HV: Fix handling of large pages in radix page fault handler

by Paul Mackerras

commit c3856aeb29402e94ad9b3879030165cc6a4fdc56 upstream. This fixes several bugs in the radix page fault handler relating to the way large pages in the memory backing the guest were handled. First, the check for large pages only checked for explicit huge pages and missed transparent huge pages. Then the check that the addresses (host virtual vs. guest physical) had appropriate alignment was wrong, meaning that the code never put a large page in the partition scoped radix tree; it was always demoted to a small page. Fixing this exposed bugs in kvmppc_create_pte(). We were never invalidating a 2MB PTE, which meant that if a page was initially faulted in without write permission and the guest then attempted to store to it, we would never update the PTE to have write permission. If we find a valid 2MB PTE in the PMD, we need to clear it and do a TLB invalidation before installing either the new 2MB PTE or a pointer to a page table page. This also corrects an assumption that get_user_pages_fast would set the _PAGE_DIRTY bit if we are writing, which is not true. Instead we mark the page dirty explicitly with set_page_dirty_lock(). This also means we don't need the dirty bit set on the host PTE when providing write access on a read fault. [paulus(a)ozlabs.org - use mark_pages_dirty instead of kvmppc_update_dirty_map] Signed-off-by: Paul Mackerras <paulus(a)ozlabs.org> --- arch/powerpc/kvm/book3s_64_mmu_radix.c | 72 ++++++++++++++++++++++------------ 1 file changed, 46 insertions(+), 26 deletions(-) diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c index c5d7435455f1..27a41695fcfd 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_radix.c +++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c @@ -19,6 +19,9 @@ #include <asm/pgalloc.h> #include <asm/pte-walk.h> +static void mark_pages_dirty(struct kvm *kvm, struct kvm_memory_slot *memslot, + unsigned long gfn, unsigned int order); + /* * Supported radix tree geometry. * Like p9, we support either 5 or 9 bits at the first (lowest) level, @@ -195,6 +198,12 @@ static void kvmppc_pte_free(pte_t *ptep) kmem_cache_free(kvm_pte_cache, ptep); } +/* Like pmd_huge() and pmd_large(), but works regardless of config options */ +static inline int pmd_is_leaf(pmd_t pmd) +{ + return !!(pmd_val(pmd) & _PAGE_PTE); +} + static int kvmppc_create_pte(struct kvm *kvm, pte_t pte, unsigned long gpa, unsigned int level, unsigned long mmu_seq) { @@ -219,7 +228,7 @@ static int kvmppc_create_pte(struct kvm *kvm, pte_t pte, unsigned long gpa, else new_pmd = pmd_alloc_one(kvm->mm, gpa); - if (level == 0 && !(pmd && pmd_present(*pmd))) + if (level == 0 && !(pmd && pmd_present(*pmd) && !pmd_is_leaf(*pmd))) new_ptep = kvmppc_pte_alloc(); /* Check if we might have been invalidated; let the guest retry if so */ @@ -244,12 +253,30 @@ static int kvmppc_create_pte(struct kvm *kvm, pte_t pte, unsigned long gpa, new_pmd = NULL; } pmd = pmd_offset(pud, gpa); - if (pmd_large(*pmd)) { - /* Someone else has instantiated a large page here; retry */ - ret = -EAGAIN; - goto out_unlock; - } - if (level == 1 && !pmd_none(*pmd)) { + if (pmd_is_leaf(*pmd)) { + unsigned long lgpa = gpa & PMD_MASK; + + /* + * If we raced with another CPU which has just put + * a 2MB pte in after we saw a pte page, try again. + */ + if (level == 0 && !new_ptep) { + ret = -EAGAIN; + goto out_unlock; + } + /* Valid 2MB page here already, remove it */ + old = kvmppc_radix_update_pte(kvm, pmdp_ptep(pmd), + ~0UL, 0, lgpa, PMD_SHIFT); + kvmppc_radix_tlbie_page(kvm, lgpa, PMD_SHIFT); + if (old & _PAGE_DIRTY) { + unsigned long gfn = lgpa >> PAGE_SHIFT; + struct kvm_memory_slot *memslot; + memslot = gfn_to_memslot(kvm, gfn); + if (memslot) + mark_pages_dirty(kvm, memslot, gfn, + PMD_SHIFT - PAGE_SHIFT); + } + } else if (level == 1 && !pmd_none(*pmd)) { /* * There's a page table page here, but we wanted * to install a large page. Tell the caller and let @@ -412,28 +439,24 @@ int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, } else { page = pages[0]; pfn = page_to_pfn(page); - if (PageHuge(page)) { - page = compound_head(page); - pte_size <<= compound_order(page); + if (PageCompound(page)) { + pte_size <<= compound_order(compound_head(page)); /* See if we can insert a 2MB large-page PTE here */ if (pte_size >= PMD_SIZE && - (gpa & PMD_MASK & PAGE_MASK) == - (hva & PMD_MASK & PAGE_MASK)) { + (gpa & (PMD_SIZE - PAGE_SIZE)) == + (hva & (PMD_SIZE - PAGE_SIZE))) { level = 1; pfn &= ~((PMD_SIZE >> PAGE_SHIFT) - 1); } } /* See if we can provide write access */ if (writing) { - /* - * We assume gup_fast has set dirty on the host PTE. - */ pgflags |= _PAGE_WRITE; } else { local_irq_save(flags); ptep = find_current_mm_pte(current->mm->pgd, hva, NULL, NULL); - if (ptep && pte_write(*ptep) && pte_dirty(*ptep)) + if (ptep && pte_write(*ptep)) pgflags |= _PAGE_WRITE; local_irq_restore(flags); } @@ -459,18 +482,15 @@ int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, pte = pfn_pte(pfn, __pgprot(pgflags)); ret = kvmppc_create_pte(kvm, pte, gpa, level, mmu_seq); } - if (ret == 0 || ret == -EAGAIN) - ret = RESUME_GUEST; if (page) { - /* - * We drop pages[0] here, not page because page might - * have been set to the head page of a compound, but - * we have to drop the reference on the correct tail - * page to match the get inside gup() - */ - put_page(pages[0]); + if (!ret && (pgflags & _PAGE_WRITE)) + set_page_dirty_lock(page); + put_page(page); } + + if (ret == 0 || ret == -EAGAIN) + ret = RESUME_GUEST; return ret; } @@ -676,7 +696,7 @@ void kvmppc_free_radix(struct kvm *kvm) continue; pmd = pmd_offset(pud, 0); for (im = 0; im < PTRS_PER_PMD; ++im, ++pmd) { - if (pmd_huge(*pmd)) { + if (pmd_is_leaf(*pmd)) { pmd_clear(pmd); continue; } -- 2.11.0

7 years, 8 months

2
1
0 0

[PATCH v2 04/13] soc: rockchip: power-domain: Fix wrong value when power up pd

by Elaine Zhang

From: Finley Xiao <finley.xiao(a)rock-chips.com> Solve the pd could only ever turn off but never turn them on again, If the pd registers have the writemask bits. Fix up the code error for commit: commit 79bb17ce8edb3141339b5882e372d0ec7346217c Author: Elaine Zhang <zhangqing(a)rock-chips.com> Date: Fri Dec 23 11:47:52 2016 +0800 soc: rockchip: power-domain: Support domain control in hiword-registers New Rockchips SoCs may have their power-domain control in registers using a writemask-based access scheme (upper 16bit being the write mask). So add a DOMAIN_M type and handle this case accordingly. Signed-off-by: Elaine Zhang <zhangqing(a)rock-chips.com> Signed-off-by: Heiko Stuebner <heiko(a)sntech.de> Signed-off-by: Finley Xiao <finley.xiao(a)rock-chips.com> Signed-off-by: Elaine Zhang <zhangqing(a)rock-chips.com> --- drivers/soc/rockchip/pm_domains.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/soc/rockchip/pm_domains.c b/drivers/soc/rockchip/pm_domains.c index ebd7c41898c0..01d4ba26a054 100644 --- a/drivers/soc/rockchip/pm_domains.c +++ b/drivers/soc/rockchip/pm_domains.c @@ -264,7 +264,7 @@ static void rockchip_do_pmu_set_power_domain(struct rockchip_pm_domain *pd, return; else if (pd->info->pwr_w_mask) regmap_write(pmu->regmap, pmu->info->pwr_offset, - on ? pd->info->pwr_mask : + on ? pd->info->pwr_w_mask : (pd->info->pwr_mask | pd->info->pwr_w_mask)); else regmap_update_bits(pmu->regmap, pmu->info->pwr_offset, -- 1.9.1

7 years, 8 months

2
1
0 0

[PATCH v4.14 1/4] KVM: PPC: Book3S HV: Fix trap number return from __kvmppc_vcore_entry

by Paul Mackerras

commit a8b48a4dccea77e29462e59f1dbf0d5aa1ff167c upstream. This fixes a bug where the trap number that is returned by __kvmppc_vcore_entry gets corrupted. The effect of the corruption is that IPIs get ignored on POWER9 systems when the IPI is sent via a doorbell interrupt to a CPU which is executing in a KVM guest. The effect of the IPI being ignored is often that another CPU locks up inside smp_call_function_many() (and if that CPU is holding a spinlock, other CPUs then lock up inside raw_spin_lock()). The trap number is currently held in register r12 for most of the assembly-language part of the guest exit path. In that path, we call kvmppc_subcore_exit_guest(), which is a C function, without restoring r12 afterwards. Depending on the kernel config and the compiler, it may modify r12 or it may not, so some config/compiler combinations see the bug and others don't. To fix this, we arrange for the trap number to be stored on the stack from the point where kvmhv_commence_exit is called until the end of the function, then the trap number is loaded and returned in r12 as before. Cc: stable(a)vger.kernel.org # v4.8+ Fixes: fd7bacbca47a ("KVM: PPC: Book3S HV: Fix TB corruption in guest exit path on HMI interrupt") Signed-off-by: Paul Mackerras <paulus(a)ozlabs.org> --- arch/powerpc/kvm/book3s_hv_rmhandlers.S | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index 2b3194b9608f..663a398449b7 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -308,7 +308,6 @@ kvm_novcpu_exit: stw r12, STACK_SLOT_TRAP(r1) bl kvmhv_commence_exit nop - lwz r12, STACK_SLOT_TRAP(r1) b kvmhv_switch_to_host /* @@ -1136,6 +1135,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) secondary_too_late: li r12, 0 + stw r12, STACK_SLOT_TRAP(r1) cmpdi r4, 0 beq 11f stw r12, VCPU_TRAP(r4) @@ -1445,12 +1445,12 @@ mc_cont: 1: #endif /* CONFIG_KVM_XICS */ + stw r12, STACK_SLOT_TRAP(r1) mr r3, r12 /* Increment exit count, poke other threads to exit */ bl kvmhv_commence_exit nop ld r9, HSTATE_KVM_VCPU(r13) - lwz r12, VCPU_TRAP(r9) /* Stop others sending VCPU interrupts to this physical CPU */ li r0, -1 @@ -1816,6 +1816,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_POWER9_DD1) * POWER7/POWER8 guest -> host partition switch code. * We don't have to lock against tlbies but we do * have to coordinate the hardware threads. + * Here STACK_SLOT_TRAP(r1) contains the trap number. */ kvmhv_switch_to_host: /* Secondary threads wait for primary to do partition switch */ @@ -1868,11 +1869,11 @@ BEGIN_FTR_SECTION END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) /* If HMI, call kvmppc_realmode_hmi_handler() */ + lwz r12, STACK_SLOT_TRAP(r1) cmpwi r12, BOOK3S_INTERRUPT_HMI bne 27f bl kvmppc_realmode_hmi_handler nop - li r12, BOOK3S_INTERRUPT_HMI /* * At this point kvmppc_realmode_hmi_handler would have resync-ed * the TB. Hence it is not required to subtract guest timebase @@ -1950,6 +1951,7 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_RADIX) li r0, KVM_GUEST_MODE_NONE stb r0, HSTATE_IN_GUEST(r13) + lwz r12, STACK_SLOT_TRAP(r1) /* return trap # in r12 */ ld r0, SFS+PPC_LR_STKOFF(r1) addi r1, r1, SFS mtlr r0 -- 2.11.0

7 years, 8 months

2
8
0 0

[PATCH] ext4: update mtime in ext4_punch_hole even if no blocks are released

by Lukas Czerner

Currently in ext4_punch_hole we're going to skip the mtime update if there are no actual blocks to release. However we've actually modified the file by zeroing the partial block so the mtime should be updated. Moreover the sync and datasync handling is skipped as well, which is also wrong. Fix it. Signed-off-by: Lukas Czerner <lczerner(a)redhat.com> Reported-by: Joe Habermann <joe.habermann(a)quantum.com> Cc: <stable(a)vger.kernel.org> --- fs/ext4/inode.c | 36 ++++++++++++++++++------------------ 1 file changed, 18 insertions(+), 18 deletions(-) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 1e50c5e..6b4c5c0 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -4298,28 +4298,28 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length) EXT4_BLOCK_SIZE_BITS(sb); stop_block = (offset + length) >> EXT4_BLOCK_SIZE_BITS(sb); - /* If there are no blocks to remove, return now */ - if (first_block >= stop_block) - goto out_stop; + /* If there are blocks to remove, do it */ + if (stop_block > first_block) { - down_write(&EXT4_I(inode)->i_data_sem); - ext4_discard_preallocations(inode); + down_write(&EXT4_I(inode)->i_data_sem); + ext4_discard_preallocations(inode); - ret = ext4_es_remove_extent(inode, first_block, - stop_block - first_block); - if (ret) { - up_write(&EXT4_I(inode)->i_data_sem); - goto out_stop; - } + ret = ext4_es_remove_extent(inode, first_block, + stop_block - first_block); + if (ret) { + up_write(&EXT4_I(inode)->i_data_sem); + goto out_stop; + } - if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) - ret = ext4_ext_remove_space(inode, first_block, - stop_block - 1); - else - ret = ext4_ind_remove_space(handle, inode, first_block, - stop_block); + if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) + ret = ext4_ext_remove_space(inode, first_block, + stop_block - 1); + else + ret = ext4_ind_remove_space(handle, inode, first_block, + stop_block); - up_write(&EXT4_I(inode)->i_data_sem); + up_write(&EXT4_I(inode)->i_data_sem); + } if (IS_SYNC(inode)) ext4_handle_sync(handle); -- 2.7.5

7 years, 8 months

2
1
0 0

[PATCH] ext4: Fix hole length detection in ext4_ind_map_blocks()

by Jan Kara

When ext4_ind_map_blocks() computes a length of a hole, it doesn't count with the fact that mapped offset may be somewhere in the middle of the completely empty subtree. In such case it will return too large length of the hole which then results in lseek(SEEK_DATA) to end up returning an incorrect offset beyond the end of the hole. Fix the problem by correctly taking offset within a subtree into account when computing a length of a hole. Fixes: facab4d9711e7aa3532cb82643803e8f1b9518e8 CC: stable(a)vger.kernel.org Reported-by: Jeff Mahoney <jeffm(a)suse.com> Signed-off-by: Jan Kara <jack(a)suse.cz> --- fs/ext4/indirect.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) I'll submit corresponding fstest shortly. diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c index c32802c956d5..bf7fa1507e81 100644 --- a/fs/ext4/indirect.c +++ b/fs/ext4/indirect.c @@ -561,10 +561,16 @@ int ext4_ind_map_blocks(handle_t *handle, struct inode *inode, unsigned epb = inode->i_sb->s_blocksize / sizeof(u32); int i; - /* Count number blocks in a subtree under 'partial' */ - count = 1; - for (i = 0; partial + i != chain + depth - 1; i++) - count *= epb; + /* + * Count number blocks in a subtree under 'partial'. At each + * level we count number of complete empty subtrees beyond + * current offset and then descend into the subtree only + * partially beyond current offset. + */ + count = 0; + for (i = partial - chain + 1; i < depth; i++) + count = count * epb + (epb - offsets[i] - 1); + count++; /* Fill in size of a hole we found */ map->m_pblk = 0; map->m_len = min_t(unsigned int, map->m_len, count); -- 2.13.6

7 years, 8 months

2
1
0 0

[BUGFIX PATCH v3 0/4] arm: kprobes: Fix to prohibit probing on unsafe functions

by Masami Hiramatsu

Hi, This is the 3rd version of bugfix series for kprobes on arm. This series fixes 4 different issues which I found. - Fix to use smp_processor_id() after disabling preemption. - Prohibit probing on optimized_callback() for avoiding recursive probe. - Prohibit kprobes on do_undefinstr() by same reason. - Prohibit kprobes on get_user() by same reason. >From v2, I included another 2 bugfixes (1/4 and 2/4) which are not merged yet, and added "Cc: stable(a)vger.kernel.org", since there are obvious bugs. Thanks, --- Masami Hiramatsu (4): arm: kprobes: Fix to use get_kprobe_ctlblk after irq-disabed arm: kprobes: Prohibit probing on optimized_callback arm: kprobes: Prohibit kprobes on do_undefinstr arm: kprobes: Prohibit kprobes on get_user functions arch/arm/include/asm/assembler.h | 10 ++++++++++ arch/arm/kernel/traps.c | 5 ++++- arch/arm/lib/getuser.S | 10 ++++++++++ arch/arm/probes/kprobes/opt-arm.c | 4 +++- 4 files changed, 27 insertions(+), 2 deletions(-) -- Masami Hiramatsu (Linaro) <mhiramat(a)kernel.org>

7 years, 8 months

4
11
0 0

[PATCH 4.4 00/50] 4.4.130-stable review

by Greg Kroah-Hartman

This is the start of the stable review cycle for the 4.4.130 release. There are 50 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know. Responses should be made by Sun Apr 29 13:56:42 UTC 2018. Anything received after that time might be too late. The whole patch series can be found in one patch at: https://www.kernel.org/pub/linux/kernel/v4.x/stable-review/patch-4.4.130-rc… or in the git tree and branch at: git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git linux-4.4.y and the diffstat can be found below. thanks, greg k-h ------------- Pseudo-Shortlog of commits: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Linux 4.4.130-rc1 Heiko Carstens <heiko.carstens(a)de.ibm.com> s390/uprobes: implement arch_uretprobe_is_alive() Sebastian Ott <sebott(a)linux.ibm.com> s390/cio: update chpid descriptor after resource accessibility event Dan Carpenter <dan.carpenter(a)oracle.com> cdrom: information leak in cdrom_ioctl_media_changed() Martin K. Petersen <martin.petersen(a)oracle.com> scsi: mptsas: Disable WRITE SAME Eric Dumazet <edumazet(a)google.com> ipv6: add RTA_TABLE and RTA_PREFSRC to rtm_ipv6_policy Eric Dumazet <edumazet(a)google.com> net: af_packet: fix race in PACKET_{R|T}X_RING Eric Dumazet <edumazet(a)google.com> tcp: md5: reject TCP_MD5SIG or TCP_MD5SIG_EXT on established sockets Wolfgang Bumiller <w.bumiller(a)proxmox.com> net: fix deadlock while clearing neighbor proxy table Eric Dumazet <edumazet(a)google.com> tipc: add policy for TIPC_NLA_NET_ADDR Cong Wang <xiyou.wangcong(a)gmail.com> llc: fix NULL pointer deref for SOCK_ZAPPED Cong Wang <xiyou.wangcong(a)gmail.com> llc: hold llc_sap before release_sock() Xin Long <lucien.xin(a)gmail.com> sctp: do not check port in sctp_inet6_cmp_addr Toshiaki Makita <makita.toshiaki(a)lab.ntt.co.jp> vlan: Fix reading memory beyond skb->tail in skb_vlan_tagged_multi Guillaume Nault <g.nault(a)alphalink.fr> pppoe: check sockaddr length in pppoe_connect() Willem de Bruijn <willemb(a)google.com> packet: fix bitfield update race Xin Long <lucien.xin(a)gmail.com> team: fix netconsole setup over team Paolo Abeni <pabeni(a)redhat.com> team: avoid adding twice the same option to the event list Jann Horn <jannh(a)google.com> tcp: don't read out-of-bounds opsize Cong Wang <xiyou.wangcong(a)gmail.com> llc: delete timers synchronously in llc_sk_free() Eric Dumazet <edumazet(a)google.com> net: validate attribute sizes in neigh_dump_table() Guillaume Nault <g.nault(a)alphalink.fr> l2tp: check sockaddr length in pppol2tp_connect() Eric Biggers <ebiggers(a)google.com> KEYS: DNS: limit the length of option strings Xin Long <lucien.xin(a)gmail.com> bonding: do not set slave_dev npinfo before slave_enable_netpoll in bond_enslave Martin Schwidefsky <schwidefsky(a)de.ibm.com> s390: correct module section names for expoline code revert Martin Schwidefsky <schwidefsky(a)de.ibm.com> s390: correct nospec auto detection init order Martin Schwidefsky <schwidefsky(a)de.ibm.com> s390: add sysfs attributes for spectre Martin Schwidefsky <schwidefsky(a)de.ibm.com> s390: report spectre mitigation via syslog Martin Schwidefsky <schwidefsky(a)de.ibm.com> s390: add automatic detection of the spectre defense Martin Schwidefsky <schwidefsky(a)de.ibm.com> s390: move nobp parameter functions to nospec-branch.c Martin Schwidefsky <schwidefsky(a)de.ibm.com> s390/entry.S: fix spurious zeroing of r0 Martin Schwidefsky <schwidefsky(a)de.ibm.com> s390: do not bypass BPENTER for interrupt system calls Martin Schwidefsky <schwidefsky(a)de.ibm.com> s390: Replace IS_ENABLED(EXPOLINE_*) with IS_ENABLED(CONFIG_EXPOLINE_*) Martin Schwidefsky <schwidefsky(a)de.ibm.com> s390: introduce execute-trampolines for branches Martin Schwidefsky <schwidefsky(a)de.ibm.com> s390: run user space and KVM guests with modified branch prediction Martin Schwidefsky <schwidefsky(a)de.ibm.com> s390: add options to change branch prediction behaviour for the kernel Martin Schwidefsky <schwidefsky(a)de.ibm.com> s390/alternative: use a copy of the facility bit mask Martin Schwidefsky <schwidefsky(a)de.ibm.com> s390: add optimized array_index_mask_nospec Martin Schwidefsky <schwidefsky(a)de.ibm.com> s390: scrub registers on kernel entry and KVM exit Martin Schwidefsky <schwidefsky(a)de.ibm.com> KVM: s390: wire up bpb feature Martin Schwidefsky <schwidefsky(a)de.ibm.com> s390: enable CPU alternatives unconditionally Martin Schwidefsky <schwidefsky(a)de.ibm.com> s390: introduce CPU alternatives Karthikeyan Periyasamy <periyasa(a)codeaurora.org> Revert "ath10k: send (re)assoc peer command when NSS changed" Sahitya Tummala <stummala(a)codeaurora.org> jbd2: fix use after free in kjournald2() Felix Fietkau <nbd(a)nbd.name> ath9k_hw: check if the chip failed to wake up Dmitry Torokhov <dmitry.torokhov(a)gmail.com> Input: drv260x - fix initializing overdrive voltage Grant Grundler <grundler(a)chromium.org> r8152: add Linksys USB3GIGV1 id Chen Feng <puck.chen(a)hisilicon.com> staging: ion : Donnot wakeup kswapd in ion system alloc Jiri Olsa <jolsa(a)kernel.org> perf: Return proper values for user stack errors Xiaoming Gao <gxm.linux.kernel(a)gmail.com> x86/tsc: Prevent 32bit truncation in calc_hpet_ref() Steve French <smfrench(a)gmail.com> cifs: do not allow creating sockets except with SMB1 posix exensions ------------- Diffstat: Documentation/kernel-parameters.txt | 3 + Makefile | 4 +- arch/s390/Kconfig | 47 +++++ arch/s390/Makefile | 10 ++ arch/s390/include/asm/alternative.h | 149 +++++++++++++++ arch/s390/include/asm/barrier.h | 24 +++ arch/s390/include/asm/facility.h | 18 ++ arch/s390/include/asm/kvm_host.h | 3 +- arch/s390/include/asm/lowcore.h | 7 +- arch/s390/include/asm/nospec-branch.h | 17 ++ arch/s390/include/asm/processor.h | 4 + arch/s390/include/asm/thread_info.h | 4 + arch/s390/include/uapi/asm/kvm.h | 3 + arch/s390/kernel/Makefile | 5 +- arch/s390/kernel/alternative.c | 112 ++++++++++++ arch/s390/kernel/early.c | 5 + arch/s390/kernel/entry.S | 250 +++++++++++++++++++++++--- arch/s390/kernel/ipl.c | 1 + arch/s390/kernel/module.c | 65 ++++++- arch/s390/kernel/nospec-branch.c | 169 +++++++++++++++++ arch/s390/kernel/processor.c | 18 ++ arch/s390/kernel/setup.c | 14 +- arch/s390/kernel/smp.c | 7 +- arch/s390/kernel/uprobes.c | 9 + arch/s390/kernel/vmlinux.lds.S | 37 ++++ arch/s390/kvm/kvm-s390.c | 13 +- arch/x86/kernel/tsc.c | 2 +- drivers/cdrom/cdrom.c | 2 +- drivers/input/misc/drv260x.c | 2 +- drivers/message/fusion/mptsas.c | 1 + drivers/net/bonding/bond_main.c | 3 +- drivers/net/ppp/pppoe.c | 4 + drivers/net/team/team.c | 38 +++- drivers/net/usb/cdc_ether.c | 10 ++ drivers/net/usb/r8152.c | 2 + drivers/net/wireless/ath/ath10k/mac.c | 5 +- drivers/net/wireless/ath/ath9k/hw.c | 4 + drivers/s390/char/Makefile | 2 + drivers/s390/cio/chsc.c | 14 +- drivers/staging/android/ion/ion_system_heap.c | 2 +- fs/cifs/dir.c | 9 +- fs/jbd2/journal.c | 2 +- include/linux/if_vlan.h | 7 +- include/net/llc_conn.h | 1 + include/uapi/linux/kvm.h | 1 + kernel/events/core.c | 4 +- net/core/dev.c | 2 +- net/core/neighbour.c | 40 +++-- net/dns_resolver/dns_key.c | 13 +- net/ipv4/tcp.c | 6 +- net/ipv4/tcp_input.c | 7 +- net/ipv6/route.c | 2 + net/l2tp/l2tp_ppp.c | 7 + net/llc/af_llc.c | 14 +- net/llc/llc_c_ac.c | 9 +- net/llc/llc_conn.c | 22 ++- net/packet/af_packet.c | 88 ++++++--- net/packet/internal.h | 10 +- net/sctp/ipv6.c | 60 +++---- net/tipc/net.c | 3 +- 60 files changed, 1228 insertions(+), 168 deletions(-)

7 years, 8 months

7
58
0 0

[PATCH] [stable 4.9] arm64: Add work around for Arm Cortex-A55 Erratum 1024718

by Suzuki K Poulose

commit ece1397cbc89c51914fae1aec729539cfd8bd62b upstream Some variants of the Arm Cortex-55 cores (r0p0, r0p1, r1p0) suffer from an erratum 1024718, which causes incorrect updates when DBM/AP bits in a page table entry is modified without a break-before-make sequence. The work around is to disable the hardware DBM feature on the affected cores. The hardware Access Flag management features is not affected. The hardware DBM feature is a non-conflicting capability, i.e, the kernel could handle cores using the feature and those without having the features running at the same time. So this work around is detected at early boot time, rather than delaying it until the CPUs are brought up into the kernel with MMU turned on. This also avoids other complexities with late CPUs turning online, with or without the hardware DBM features. Cc: stable(a)vger.kernel.org # v4.9 Cc: Catalin Marinas <catalin.marinas(a)arm.com> Cc: Mark Rutland <mark.rutland(a)arm.com> Cc: Will Deacon <will.deacon(a)arm.com> Signed-off-by: Suzuki K Poulose <suzuki.poulose(a)arm.com> --- Note: The upstream commit is on top of a reworked capability infrastructure for arm64 heterogeneous systems, which allows delaying the CPU model checks. This backport is based on the original version of the patch [0], which checks the affected CPU models during the early boot. [0] https://lkml.kernel.org/r/20180116102323.3470-1-suzuki.poulose@arm.com --- Documentation/arm64/silicon-errata.txt | 1 + arch/arm64/Kconfig | 14 ++++++++++++ arch/arm64/include/asm/assembler.h | 40 ++++++++++++++++++++++++++++++++++ arch/arm64/include/asm/cputype.h | 5 +++++ arch/arm64/mm/proc.S | 5 +++++ 5 files changed, 65 insertions(+) diff --git a/Documentation/arm64/silicon-errata.txt b/Documentation/arm64/silicon-errata.txt index d11af52..ac9489f 100644 --- a/Documentation/arm64/silicon-errata.txt +++ b/Documentation/arm64/silicon-errata.txt @@ -54,6 +54,7 @@ stable kernels. | ARM | Cortex-A57 | #852523 | N/A | | ARM | Cortex-A57 | #834220 | ARM64_ERRATUM_834220 | | ARM | Cortex-A72 | #853709 | N/A | +| ARM | Cortex-A55 | #1024718 | ARM64_ERRATUM_1024718 | | ARM | MMU-500 | #841119,#826419 | N/A | | | | | | | Cavium | ThunderX ITS | #22375, #24313 | CAVIUM_ERRATUM_22375 | diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 90e58bb..d0df361 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -427,6 +427,20 @@ config ARM64_ERRATUM_843419 If unsure, say Y. +config ARM64_ERRATUM_1024718 + bool "Cortex-A55: 1024718: Update of DBM/AP bits without break before make might result in incorrect update" + default y + help + This option adds work around for Arm Cortex-A55 Erratum 1024718. + + Affected Cortex-A55 cores (r0p0, r0p1, r1p0) could cause incorrect + update of the hardware dirty bit when the DBM/AP bits are updated + without a break-before-make. The work around is to disable the usage + of hardware DBM locally on the affected cores. CPUs not affected by + erratum will continue to use the feature. + + If unsure, say Y. + config CAVIUM_ERRATUM_22375 bool "Cavium erratum 22375, 24313" default y diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h index e60375c..bfcfec3 100644 --- a/arch/arm64/include/asm/assembler.h +++ b/arch/arm64/include/asm/assembler.h @@ -25,6 +25,7 @@ #include <asm/asm-offsets.h> #include <asm/cpufeature.h> +#include <asm/cputype.h> #include <asm/page.h> #include <asm/pgtable-hwdef.h> #include <asm/ptrace.h> @@ -435,4 +436,43 @@ alternative_endif and \phys, \pte, #(((1 << (48 - PAGE_SHIFT)) - 1) << PAGE_SHIFT) .endm +/* + * Check the MIDR_EL1 of the current CPU for a given model and a range of + * variant/revision. See asm/cputype.h for the macros used below. + * + * model: MIDR_CPU_MODEL of CPU + * rv_min: Minimum of MIDR_CPU_VAR_REV() + * rv_max: Maximum of MIDR_CPU_VAR_REV() + * res: Result register. + * tmp1, tmp2, tmp3: Temporary registers + * + * Corrupts: res, tmp1, tmp2, tmp3 + * Returns: 0, if the CPU id doesn't match. Non-zero otherwise + */ + .macro cpu_midr_match model, rv_min, rv_max, res, tmp1, tmp2, tmp3 + mrs \res, midr_el1 + mov_q \tmp1, (MIDR_REVISION_MASK | MIDR_VARIANT_MASK) + mov_q \tmp2, MIDR_CPU_MODEL_MASK + and \tmp3, \res, \tmp2 // Extract model + and \tmp1, \res, \tmp1 // rev & variant + mov_q \tmp2, \model + cmp \tmp3, \tmp2 + cset \res, eq + cbz \res, .Ldone\@ // Model matches ? + + .if (\rv_min != 0) // Skip min check if rv_min == 0 + mov_q \tmp3, \rv_min + cmp \tmp1, \tmp3 + cset \res, ge + .endif // \rv_min != 0 + /* Skip rv_max check if rv_min == rv_max && rv_min != 0 */ + .if ((\rv_min != \rv_max) || \rv_min == 0) + mov_q \tmp2, \rv_max + cmp \tmp1, \tmp2 + cset \tmp2, le + and \res, \res, \tmp2 + .endif +.Ldone\@: + .endm + #endif /* __ASM_ASSEMBLER_H */ diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index 9ee3038..39d1db6 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -56,6 +56,9 @@ (0xf << MIDR_ARCHITECTURE_SHIFT) | \ ((partnum) << MIDR_PARTNUM_SHIFT)) +#define MIDR_CPU_VAR_REV(var, rev) \ + (((var) << MIDR_VARIANT_SHIFT) | (rev)) + #define MIDR_CPU_MODEL_MASK (MIDR_IMPLEMENTOR_MASK | MIDR_PARTNUM_MASK | \ MIDR_ARCHITECTURE_MASK) @@ -74,6 +77,7 @@ #define ARM_CPU_PART_AEM_V8 0xD0F #define ARM_CPU_PART_FOUNDATION 0xD00 +#define ARM_CPU_PART_CORTEX_A55 0xD05 #define ARM_CPU_PART_CORTEX_A57 0xD07 #define ARM_CPU_PART_CORTEX_A72 0xD08 #define ARM_CPU_PART_CORTEX_A53 0xD03 @@ -89,6 +93,7 @@ #define BRCM_CPU_PART_VULCAN 0x516 #define MIDR_CORTEX_A53 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A53) +#define MIDR_CORTEX_A55 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A55) #define MIDR_CORTEX_A57 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A57) #define MIDR_CORTEX_A72 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A72) #define MIDR_CORTEX_A73 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A73) diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index 619da1c..66cce21 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -425,6 +425,11 @@ ENTRY(__cpu_setup) cbz x9, 2f cmp x9, #2 b.lt 1f +#ifdef CONFIG_ARM64_ERRATUM_1024718 + /* Disable hardware DBM on Cortex-A55 r0p0, r0p1 & r1p0 */ + cpu_midr_match MIDR_CORTEX_A55, MIDR_CPU_VAR_REV(0, 0), MIDR_CPU_VAR_REV(1, 0), x1, x2, x3, x4 + cbnz x1, 1f +#endif orr x10, x10, #TCR_HD // hardware Dirty flag update 1: orr x10, x10, #TCR_HA // hardware Access flag update 2: -- 2.7.4

7 years, 8 months

3
3
0 0

FAILED: patch "[PATCH] drm/i915: Adjust eDP's logical vco in a reliable place." failed to apply to 4.14-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.14-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 9d219554d9bf59875b4e571a0392d620e8954879 Mon Sep 17 00:00:00 2001 From: Rodrigo Vivi <rodrigo.vivi(a)intel.com> Date: Wed, 2 May 2018 10:52:55 -0700 Subject: [PATCH] drm/i915: Adjust eDP's logical vco in a reliable place. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit On intel_dp_compute_config() we were calculating the needed vco for eDP on gen9 and we stashing it in intel_atomic_state.cdclk.logical.vco However few moments later on intel_modeset_checks() we fully replace entire intel_atomic_state.cdclk.logical with dev_priv->cdclk.logical fully overwriting the logical desired vco for eDP on gen9. So, with wrong VCO value we end up with wrong desired cdclk, but also it will raise a lot of WARNs: On gen9, when we read CDCLK_CTL to verify if we configured properly the desired frequency the CD Frequency Select bits [27:26] == 10b can mean 337.5 or 308.57 MHz depending on the VCO. So if we have wrong VCO value stashed we will believe the frequency selection didn't stick and start to raise WARNs of cdclk mismatch. [ 42.857519] [drm:intel_dump_cdclk_state [i915]] Changing CDCLK to 308571 kHz, VCO 8640000 kHz, ref 24000 kHz, bypass 24000 kHz, voltage level 0 [ 42.897269] cdclk state doesn't match! [ 42.901052] WARNING: CPU: 5 PID: 1116 at drivers/gpu/drm/i915/intel_cdclk.c:2084 intel_set_cdclk+0x5d/0x110 [i915] [ 42.938004] RIP: 0010:intel_set_cdclk+0x5d/0x110 [i915] [ 43.155253] WARNING: CPU: 5 PID: 1116 at drivers/gpu/drm/i915/intel_cdclk.c:2084 intel_set_cdclk+0x5d/0x110 [i915] [ 43.170277] [drm:intel_dump_cdclk_state [i915]] [hw state] 337500 kHz, VCO 8100000 kHz, ref 24000 kHz, bypass 24000 kHz, voltage level 0 [ 43.182566] [drm:intel_dump_cdclk_state [i915]] [sw state] 308571 kHz, VCO 8640000 kHz, ref 24000 kHz, bypass 24000 kHz, voltage level 0 v2: Move the entire eDP's vco logical adjustment to inside the skl_modeset_calc_cdclk as suggested by Ville. Cc: Ville Syrjälä <ville.syrjala(a)linux.intel.com> Signed-off-by: Rodrigo Vivi <rodrigo.vivi(a)intel.com> Reviewed-by: Ville Syrjälä <ville.syrjala(a)linux.intel.com> Fixes: bb0f4aab0e76 ("drm/i915: Track full cdclk state for the logical and actual cdclk frequencies") Cc: <stable(a)vger.kernel.org> # v4.12+ Link: https://patchwork.freedesktop.org/patch/msgid/20180502175255.5344-1-rodrigo… (cherry picked from commit 3297234a05ab1e90091b0574db4c397ef0e90d5f) Signed-off-by: Joonas Lahtinen <joonas.lahtinen(a)linux.intel.com> diff --git a/drivers/gpu/drm/i915/intel_cdclk.c b/drivers/gpu/drm/i915/intel_cdclk.c index 32d24c69da3c..704ddb4d3ca7 100644 --- a/drivers/gpu/drm/i915/intel_cdclk.c +++ b/drivers/gpu/drm/i915/intel_cdclk.c @@ -2302,9 +2302,44 @@ static int bdw_modeset_calc_cdclk(struct drm_atomic_state *state) return 0; } +static int skl_dpll0_vco(struct intel_atomic_state *intel_state) +{ + struct drm_i915_private *dev_priv = to_i915(intel_state->base.dev); + struct intel_crtc *crtc; + struct intel_crtc_state *crtc_state; + int vco, i; + + vco = intel_state->cdclk.logical.vco; + if (!vco) + vco = dev_priv->skl_preferred_vco_freq; + + for_each_new_intel_crtc_in_state(intel_state, crtc, crtc_state, i) { + if (!crtc_state->base.enable) + continue; + + if (!intel_crtc_has_type(crtc_state, INTEL_OUTPUT_EDP)) + continue; + + /* + * DPLL0 VCO may need to be adjusted to get the correct + * clock for eDP. This will affect cdclk as well. + */ + switch (crtc_state->port_clock / 2) { + case 108000: + case 216000: + vco = 8640000; + break; + default: + vco = 8100000; + break; + } + } + + return vco; +} + static int skl_modeset_calc_cdclk(struct drm_atomic_state *state) { - struct drm_i915_private *dev_priv = to_i915(state->dev); struct intel_atomic_state *intel_state = to_intel_atomic_state(state); int min_cdclk, cdclk, vco; @@ -2312,9 +2347,7 @@ static int skl_modeset_calc_cdclk(struct drm_atomic_state *state) if (min_cdclk < 0) return min_cdclk; - vco = intel_state->cdclk.logical.vco; - if (!vco) - vco = dev_priv->skl_preferred_vco_freq; + vco = skl_dpll0_vco(intel_state); /* * FIXME should also account for plane ratio diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c index 9a4a51e79fa1..b7b4cfdeb974 100644 --- a/drivers/gpu/drm/i915/intel_dp.c +++ b/drivers/gpu/drm/i915/intel_dp.c @@ -1881,26 +1881,6 @@ intel_dp_compute_config(struct intel_encoder *encoder, reduce_m_n); } - /* - * DPLL0 VCO may need to be adjusted to get the correct - * clock for eDP. This will affect cdclk as well. - */ - if (intel_dp_is_edp(intel_dp) && IS_GEN9_BC(dev_priv)) { - int vco; - - switch (pipe_config->port_clock / 2) { - case 108000: - case 216000: - vco = 8640000; - break; - default: - vco = 8100000; - break; - } - - to_intel_atomic_state(pipe_config->base.state)->cdclk.logical.vco = vco; - } - if (!HAS_DDI(dev_priv)) intel_dp_set_clock(encoder, pipe_config);

7 years, 8 months

1
0
0 0

FAILED: patch "[PATCH] mm: treat indirectly reclaimable memory as free in overcommit" failed to apply to 4.14-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.14-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From d79f7aa496fc94d763f67b833a1f36f4c171176f Mon Sep 17 00:00:00 2001 From: Roman Gushchin <guro(a)fb.com> Date: Tue, 10 Apr 2018 16:27:47 -0700 Subject: [PATCH] mm: treat indirectly reclaimable memory as free in overcommit logic Indirectly reclaimable memory can consume a significant part of total memory and it's actually reclaimable (it will be released under actual memory pressure). So, the overcommit logic should treat it as free. Otherwise, it's possible to cause random system-wide memory allocation failures by consuming a significant amount of memory by indirectly reclaimable memory, e.g. dentry external names. If overcommit policy GUESS is used, it might be used for denial of service attack under some conditions. The following program illustrates the approach. It causes the kernel to allocate an unreclaimable kmalloc-256 chunk for each stat() call, so that at some point the overcommit logic may start blocking large allocation system-wide. int main() { char buf[256]; unsigned long i; struct stat statbuf; buf[0] = '/'; for (i = 1; i < sizeof(buf); i++) buf[i] = '_'; for (i = 0; 1; i++) { sprintf(&buf[248], "%8lu", i); stat(buf, &statbuf); } return 0; } This patch in combination with related indirectly reclaimable memory patches closes this issue. Link: http://lkml.kernel.org/r/20180313130041.8078-1-guro@fb.com Signed-off-by: Roman Gushchin <guro(a)fb.com> Reviewed-by: Andrew Morton <akpm(a)linux-foundation.org> Cc: Alexander Viro <viro(a)zeniv.linux.org.uk> Cc: Michal Hocko <mhocko(a)suse.com> Cc: Johannes Weiner <hannes(a)cmpxchg.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> diff --git a/mm/util.c b/mm/util.c index 029fc2f3b395..73676f0f1b43 100644 --- a/mm/util.c +++ b/mm/util.c @@ -667,6 +667,13 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin) */ free += global_node_page_state(NR_SLAB_RECLAIMABLE); + /* + * Part of the kernel memory, which can be released + * under memory pressure. + */ + free += global_node_page_state( + NR_INDIRECTLY_RECLAIMABLE_BYTES) >> PAGE_SHIFT; + /* * Leave reserved pages. The pages are not for anonymous pages. */

7 years, 8 months

1
0
0 0

[PATCH] nvme/pci: Sync controller reset for AER slot_reset

by Keith Busch

AER handling expects a successful return from slot_reset means the driver made the device functional again. The nvme driver had been using an asynchronous reset to recover the device, so the device may still be initializing after control is returned to the AER handler. This creates problems for subsequent event handling, causing the initializion to fail. This patch fixes that by syncing the controller reset before returning to the AER driver, and reporting the true state of the reset. Link: https://bugzilla.kernel.org/show_bug.cgi?id=199657 Reported-by: Alex Gagniuc <mr.nuke.me(a)gmail.com> Cc: Sinan Kaya <okaya(a)codeaurora.org> Cc: Bjorn Helgaas <bhelgaas(a)google.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Keith Busch <keith.busch(a)intel.com> --- drivers/nvme/host/pci.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index b542dce45927..2e221796257a 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -2681,8 +2681,15 @@ static pci_ers_result_t nvme_slot_reset(struct pci_dev *pdev) dev_info(dev->ctrl.device, "restart after slot reset\n"); pci_restore_state(pdev); - nvme_reset_ctrl(&dev->ctrl); - return PCI_ERS_RESULT_RECOVERED; + nvme_reset_ctrl_sync(&dev->ctrl); + + switch (dev->ctrl.state) { + case NVME_CTRL_LIVE: + case NVME_CTRL_ADMIN_ONLY: + return PCI_ERS_RESULT_RECOVERED; + default: + return PCI_ERS_RESULT_DISCONNECT; + } } static void nvme_error_resume(struct pci_dev *pdev) -- 2.14.3

7 years, 8 months

6
8
0 0

[PATCH 1/1] doc: fix sysfs ABI documentation

by kys＠linuxonhyperv.com

From: Stephen Hemminger <stephen(a)networkplumber.org> In 4.9 kernel, the sysfs files for Hyper-V VMBus changed name but the documentation files were not updated. The current sysfs file names are /sys/bus/vmbus/devices/<UUID>/... See commit 9a56e5d6a0ba ("Drivers: hv: make VMBus bus ids persistent") and commit f6b2db084b65 ("vmbus: make sysfs names consistent with PCI") Reported-by: Michael Kelley <mikelley(a)microsoft.com> Signed-off-by: Stephen Hemminger <sthemmin(a)microsoft.com> Cc: stable(a)vger.kernel.org Signed-off-by: K. Y. Srinivasan <kys(a)microsoft.com> --- Documentation/ABI/stable/sysfs-bus-vmbus | 40 ++++++++++++++++---------------- 1 file changed, 20 insertions(+), 20 deletions(-) diff --git a/Documentation/ABI/stable/sysfs-bus-vmbus b/Documentation/ABI/stable/sysfs-bus-vmbus index 0c9d9dcd2151..3eaffbb2d468 100644 --- a/Documentation/ABI/stable/sysfs-bus-vmbus +++ b/Documentation/ABI/stable/sysfs-bus-vmbus @@ -1,25 +1,25 @@ -What: /sys/bus/vmbus/devices/vmbus_*/id +What: /sys/bus/vmbus/devices/<UUID>/id Date: Jul 2009 KernelVersion: 2.6.31 Contact: K. Y. Srinivasan <kys(a)microsoft.com> Description: The VMBus child_relid of the device's primary channel Users: tools/hv/lsvmbus -What: /sys/bus/vmbus/devices/vmbus_*/class_id +What: /sys/bus/vmbus/devices/<UUID>/class_id Date: Jul 2009 KernelVersion: 2.6.31 Contact: K. Y. Srinivasan <kys(a)microsoft.com> Description: The VMBus interface type GUID of the device Users: tools/hv/lsvmbus -What: /sys/bus/vmbus/devices/vmbus_*/device_id +What: /sys/bus/vmbus/devices/<UUID>/device_id Date: Jul 2009 KernelVersion: 2.6.31 Contact: K. Y. Srinivasan <kys(a)microsoft.com> Description: The VMBus interface instance GUID of the device Users: tools/hv/lsvmbus -What: /sys/bus/vmbus/devices/vmbus_*/channel_vp_mapping +What: /sys/bus/vmbus/devices/<UUID>/channel_vp_mapping Date: Jul 2015 KernelVersion: 4.2.0 Contact: K. Y. Srinivasan <kys(a)microsoft.com> @@ -28,112 +28,112 @@ Description: The mapping of which primary/sub channels are bound to which Format: <channel's child_relid:the bound cpu's number> Users: tools/hv/lsvmbus -What: /sys/bus/vmbus/devices/vmbus_*/device +What: /sys/bus/vmbus/devices/<UUID>/device Date: Dec. 2015 KernelVersion: 4.5 Contact: K. Y. Srinivasan <kys(a)microsoft.com> Description: The 16 bit device ID of the device Users: tools/hv/lsvmbus and user level RDMA libraries -What: /sys/bus/vmbus/devices/vmbus_*/vendor +What: /sys/bus/vmbus/devices/<UUID>/vendor Date: Dec. 2015 KernelVersion: 4.5 Contact: K. Y. Srinivasan <kys(a)microsoft.com> Description: The 16 bit vendor ID of the device Users: tools/hv/lsvmbus and user level RDMA libraries -What: /sys/bus/vmbus/devices/vmbus_*/channels/NN +What: /sys/bus/vmbus/devices/<UUID>/channels/<N> Date: September. 2017 KernelVersion: 4.14 Contact: Stephen Hemminger <sthemmin(a)microsoft.com> Description: Directory for per-channel information NN is the VMBUS relid associtated with the channel. -What: /sys/bus/vmbus/devices/vmbus_*/channels/NN/cpu +What: /sys/bus/vmbus/devices/<UUID>/channels/<N>/cpu Date: September. 2017 KernelVersion: 4.14 Contact: Stephen Hemminger <sthemmin(a)microsoft.com> Description: VCPU (sub)channel is affinitized to Users: tools/hv/lsvmbus and other debugging tools -What: /sys/bus/vmbus/devices/vmbus_*/channels/NN/cpu +What: /sys/bus/vmbus/devices/<UUID>/channels/<N>/cpu Date: September. 2017 KernelVersion: 4.14 Contact: Stephen Hemminger <sthemmin(a)microsoft.com> Description: VCPU (sub)channel is affinitized to Users: tools/hv/lsvmbus and other debugging tools -What: /sys/bus/vmbus/devices/vmbus_*/channels/NN/in_mask +What: /sys/bus/vmbus/devices/<UUID>/channels/<N>/in_mask Date: September. 2017 KernelVersion: 4.14 Contact: Stephen Hemminger <sthemmin(a)microsoft.com> Description: Host to guest channel interrupt mask Users: Debugging tools -What: /sys/bus/vmbus/devices/vmbus_*/channels/NN/latency +What: /sys/bus/vmbus/devices/<UUID>/channels/<N>/latency Date: September. 2017 KernelVersion: 4.14 Contact: Stephen Hemminger <sthemmin(a)microsoft.com> Description: Channel signaling latency Users: Debugging tools -What: /sys/bus/vmbus/devices/vmbus_*/channels/NN/out_mask +What: /sys/bus/vmbus/devices/<UUID>/channels/<N>/out_mask Date: September. 2017 KernelVersion: 4.14 Contact: Stephen Hemminger <sthemmin(a)microsoft.com> Description: Guest to host channel interrupt mask Users: Debugging tools -What: /sys/bus/vmbus/devices/vmbus_*/channels/NN/pending +What: /sys/bus/vmbus/devices/<UUID>/channels/<N>/pending Date: September. 2017 KernelVersion: 4.14 Contact: Stephen Hemminger <sthemmin(a)microsoft.com> Description: Channel interrupt pending state Users: Debugging tools -What: /sys/bus/vmbus/devices/vmbus_*/channels/NN/read_avail +What: /sys/bus/vmbus/devices/<UUID>/channels/<N>/read_avail Date: September. 2017 KernelVersion: 4.14 Contact: Stephen Hemminger <sthemmin(a)microsoft.com> Description: Bytes available to read Users: Debugging tools -What: /sys/bus/vmbus/devices/vmbus_*/channels/NN/write_avail +What: /sys/bus/vmbus/devices/<UUID>/channels/<N>/write_avail Date: September. 2017 KernelVersion: 4.14 Contact: Stephen Hemminger <sthemmin(a)microsoft.com> Description: Bytes available to write Users: Debugging tools -What: /sys/bus/vmbus/devices/vmbus_*/channels/NN/events +What: /sys/bus/vmbus/devices/<UUID>/channels/<N>/events Date: September. 2017 KernelVersion: 4.14 Contact: Stephen Hemminger <sthemmin(a)microsoft.com> Description: Number of times we have signaled the host Users: Debugging tools -What: /sys/bus/vmbus/devices/vmbus_*/channels/NN/interrupts +What: /sys/bus/vmbus/devices/<UUID>/channels/<N>/interrupts Date: September. 2017 KernelVersion: 4.14 Contact: Stephen Hemminger <sthemmin(a)microsoft.com> Description: Number of times we have taken an interrupt (incoming) Users: Debugging tools -What: /sys/bus/vmbus/devices/vmbus_*/channels/NN/subchannel_id +What: /sys/bus/vmbus/devices/<UUID>/channels/<N>/subchannel_id Date: January. 2018 KernelVersion: 4.16 Contact: Stephen Hemminger <sthemmin(a)microsoft.com> Description: Subchannel ID associated with VMBUS channel Users: Debugging tools and userspace drivers -What: /sys/bus/vmbus/devices/vmbus_*/channels/NN/monitor_id +What: /sys/bus/vmbus/devices/<UUID>/channels/<N>/monitor_id Date: January. 2018 KernelVersion: 4.16 Contact: Stephen Hemminger <sthemmin(a)microsoft.com> Description: Monitor bit associated with channel Users: Debugging tools and userspace drivers -What: /sys/bus/vmbus/devices/vmbus_*/channels/NN/ring +What: /sys/bus/vmbus/devices/<UUID>/channels/<N>/ring Date: January. 2018 KernelVersion: 4.16 Contact: Stephen Hemminger <sthemmin(a)microsoft.com> -- 2.15.1

7 years, 8 months

1
0
0 0

[PATCH v2 03/12] arm: dts: mt7623: fix invalid memory node being generated

by sean.wang＠mediatek.com

From: Sean Wang <sean.wang(a)mediatek.com> Below two wrong nodes in existing DTS files would cause a fail boot since in fact the address 0 is not the correct place the memory device locates at. memory { device_type = "memory"; reg = <0x0 0x0 0x0 0x0>; }; memory@80000000 { reg = <0x0 0x80000000 0x0 0x40000000>; }; In order to avoid having a memory node starting at address 0, we can't include file skeleton64.dtsi and instead need to explicitly manually define a few of properties the DTS relies on such as #address-cells and #size-cells in root node and device_type in the node memory@80000000. Cc: stable(a)vger.kernel.org Fixes: 31ac0d69a1d4 ("ARM: dts: mediatek: add MT7623 basic support") Signed-off-by: Sean Wang <sean.wang(a)mediatek.com> Cc: Rob Herring <robh+dt(a)kernel.org> --- arch/arm/boot/dts/mt7623.dtsi | 3 ++- arch/arm/boot/dts/mt7623n-bananapi-bpi-r2.dts | 1 + arch/arm/boot/dts/mt7623n-rfb.dtsi | 1 + 3 files changed, 4 insertions(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/mt7623.dtsi b/arch/arm/boot/dts/mt7623.dtsi index fec4715..406a9f3 100644 --- a/arch/arm/boot/dts/mt7623.dtsi +++ b/arch/arm/boot/dts/mt7623.dtsi @@ -15,11 +15,12 @@ #include <dt-bindings/phy/phy.h> #include <dt-bindings/reset/mt2701-resets.h> #include <dt-bindings/thermal/thermal.h> -#include "skeleton64.dtsi" / { compatible = "mediatek,mt7623"; interrupt-parent = <&sysirq>; + #address-cells = <2>; + #size-cells = <2>; cpu_opp_table: opp-table { compatible = "operating-points-v2"; diff --git a/arch/arm/boot/dts/mt7623n-bananapi-bpi-r2.dts b/arch/arm/boot/dts/mt7623n-bananapi-bpi-r2.dts index bbf56f8..5938e4c 100644 --- a/arch/arm/boot/dts/mt7623n-bananapi-bpi-r2.dts +++ b/arch/arm/boot/dts/mt7623n-bananapi-bpi-r2.dts @@ -109,6 +109,7 @@ }; memory@80000000 { + device_type = "memory"; reg = <0 0x80000000 0 0x40000000>; }; }; diff --git a/arch/arm/boot/dts/mt7623n-rfb.dtsi b/arch/arm/boot/dts/mt7623n-rfb.dtsi index a199ae7..343e8ef 100644 --- a/arch/arm/boot/dts/mt7623n-rfb.dtsi +++ b/arch/arm/boot/dts/mt7623n-rfb.dtsi @@ -40,6 +40,7 @@ }; memory@80000000 { + device_type = "memory"; reg = <0 0x80000000 0 0x40000000>; }; -- 2.7.4

7 years, 8 months

3
2
0 0

patch "xhci: Fix use-after-free in xhci_free_virt_device" causes kernel crashes on 4.16.8 on unplug

by Jacob Saunders

On Linux kernel 4.16.8 (using Arch Linux) if I eject a USB 3.0 device from my system (unplug or "udisksctl power-off --block-device /dev/sde), it freezes instantly with a null pointer error in XHCI. I've been unable to successfully capture a kernel log of the error (and my cameras did not return usable results) and the screen begins scrolling near-immediately with hung processors in a VT. I have done a git bisection (between 4.16.7 and 4.16.7) narrowing it down to the following commit: commit f5331826b0b7a5f2db56a9020ddbb8ce16acdfc0 Author: Mathias Nyman <mathias.nyman(a)linux.intel.com> Date: Thu May 3 17:30:07 2018 +0300 xhci: Fix use-after-free in xhci_free_virt_device commit 44a182b9d17765514fa2b1cc911e4e65134eef93 upstream. KASAN found a use-after-free in xhci_free_virt_device+0x33b/0x38e where xhci_free_virt_device() sets slot id to 0 if udev exists: if (dev->udev && dev->udev->slot_id) dev->udev->slot_id = 0; dev->udev will be true even if udev is freed because dev->udev is not set to NULL. set dev->udev pointer to NULL in xhci_free_dev() The original patch went to stable so this fix needs to be applied there as well. Fixes: a400efe455f7 ("xhci: zero usb device slot_id member when disabling and freeing a xhci slot") Cc: <stable(a)vger.kernel.org> Reported-by: Guenter Roeck <linux(a)roeck-us.net> Reviewed-by: Guenter Roeck <linux(a)roeck-us.net> Tested-by: Guenter Roeck <linux(a)roeck-us.net> Signed-off-by: Mathias Nyman <mathias.nyman(a)linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> :040000 040000 356ecdc13bf252535bd51b8558a8173dae546f19 d28f201228652e87e51ba48f5a0ad4539cca5c29 M drivers Can I be CC'd on future responses to this? I am not subscribed to the list. Jacob Saunders

7 years, 8 months

2
1
0 0

[patch 10/13] mm, oom: fix concurrent munlock and oom reaper unmap, v3

by akpm＠linux-foundation.org

From: David Rientjes <rientjes(a)google.com> Subject: mm, oom: fix concurrent munlock and oom reaper unmap, v3 Since exit_mmap() is done without the protection of mm->mmap_sem, it is possible for the oom reaper to concurrently operate on an mm until MMF_OOM_SKIP is set. This allows munlock_vma_pages_all() to concurrently run while the oom reaper is operating on a vma. Since munlock_vma_pages_range() depends on clearing VM_LOCKED from vm_flags before actually doing the munlock to determine if any other vmas are locking the same memory, the check for VM_LOCKED in the oom reaper is racy. This is especially noticeable on architectures such as powerpc where clearing a huge pmd requires serialize_against_pte_lookup(). If the pmd is zapped by the oom reaper during follow_page_mask() after the check for pmd_none() is bypassed, this ends up deferencing a NULL ptl or a kernel oops. Fix this by manually freeing all possible memory from the mm before doing the munlock and then setting MMF_OOM_SKIP. The oom reaper can not run on the mm anymore so the munlock is safe to do in exit_mmap(). It also matches the logic that the oom reaper currently uses for determining when to set MMF_OOM_SKIP itself, so there's no new risk of excessive oom killing. This issue fixes CVE-2018-1000200. Link: http://lkml.kernel.org/r/alpine.DEB.2.21.1804241526320.238665@chino.kir.cor… Fixes: 212925802454 ("mm: oom: let oom_reap_task and exit_mmap run concurrently") Signed-off-by: David Rientjes <rientjes(a)google.com> Suggested-by: Tetsuo Handa <penguin-kernel(a)I-love.SAKURA.ne.jp> Acked-by: Michal Hocko <mhocko(a)suse.com> Cc: Andrea Arcangeli <aarcange(a)redhat.com> Cc: <stable(a)vger.kernel.org> [4.14+] Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- include/linux/oom.h | 2 + mm/mmap.c | 44 +++++++++++++--------- mm/oom_kill.c | 81 ++++++++++++++++++++++-------------------- 3 files changed, 71 insertions(+), 56 deletions(-) diff -puN include/linux/oom.h~mm-oom-fix-concurrent-munlock-and-oom-reaper-unmap include/linux/oom.h --- a/include/linux/oom.h~mm-oom-fix-concurrent-munlock-and-oom-reaper-unmap +++ a/include/linux/oom.h @@ -95,6 +95,8 @@ static inline int check_stable_address_s return 0; } +void __oom_reap_task_mm(struct mm_struct *mm); + extern unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg, const nodemask_t *nodemask, unsigned long totalpages); diff -puN mm/mmap.c~mm-oom-fix-concurrent-munlock-and-oom-reaper-unmap mm/mmap.c --- a/mm/mmap.c~mm-oom-fix-concurrent-munlock-and-oom-reaper-unmap +++ a/mm/mmap.c @@ -3024,6 +3024,32 @@ void exit_mmap(struct mm_struct *mm) /* mm's last user has gone, and its about to be pulled down */ mmu_notifier_release(mm); + if (unlikely(mm_is_oom_victim(mm))) { + /* + * Manually reap the mm to free as much memory as possible. + * Then, as the oom reaper does, set MMF_OOM_SKIP to disregard + * this mm from further consideration. Taking mm->mmap_sem for + * write after setting MMF_OOM_SKIP will guarantee that the oom + * reaper will not run on this mm again after mmap_sem is + * dropped. + * + * Nothing can be holding mm->mmap_sem here and the above call + * to mmu_notifier_release(mm) ensures mmu notifier callbacks in + * __oom_reap_task_mm() will not block. + * + * This needs to be done before calling munlock_vma_pages_all(), + * which clears VM_LOCKED, otherwise the oom reaper cannot + * reliably test it. + */ + mutex_lock(&oom_lock); + __oom_reap_task_mm(mm); + mutex_unlock(&oom_lock); + + set_bit(MMF_OOM_SKIP, &mm->flags); + down_write(&mm->mmap_sem); + up_write(&mm->mmap_sem); + } + if (mm->locked_vm) { vma = mm->mmap; while (vma) { @@ -3045,24 +3071,6 @@ void exit_mmap(struct mm_struct *mm) /* update_hiwater_rss(mm) here? but nobody should be looking */ /* Use -1 here to ensure all VMAs in the mm are unmapped */ unmap_vmas(&tlb, vma, 0, -1); - - if (unlikely(mm_is_oom_victim(mm))) { - /* - * Wait for oom_reap_task() to stop working on this - * mm. Because MMF_OOM_SKIP is already set before - * calling down_read(), oom_reap_task() will not run - * on this "mm" post up_write(). - * - * mm_is_oom_victim() cannot be set from under us - * either because victim->mm is already set to NULL - * under task_lock before calling mmput and oom_mm is - * set not NULL by the OOM killer only if victim->mm - * is found not NULL while holding the task_lock. - */ - set_bit(MMF_OOM_SKIP, &mm->flags); - down_write(&mm->mmap_sem); - up_write(&mm->mmap_sem); - } free_pgtables(&tlb, vma, FIRST_USER_ADDRESS, USER_PGTABLES_CEILING); tlb_finish_mmu(&tlb, 0, -1); diff -puN mm/oom_kill.c~mm-oom-fix-concurrent-munlock-and-oom-reaper-unmap mm/oom_kill.c --- a/mm/oom_kill.c~mm-oom-fix-concurrent-munlock-and-oom-reaper-unmap +++ a/mm/oom_kill.c @@ -469,7 +469,6 @@ bool process_shares_mm(struct task_struc return false; } - #ifdef CONFIG_MMU /* * OOM Reaper kernel thread which tries to reap the memory used by the OOM @@ -480,16 +479,54 @@ static DECLARE_WAIT_QUEUE_HEAD(oom_reape static struct task_struct *oom_reaper_list; static DEFINE_SPINLOCK(oom_reaper_lock); -static bool __oom_reap_task_mm(struct task_struct *tsk, struct mm_struct *mm) +void __oom_reap_task_mm(struct mm_struct *mm) { - struct mmu_gather tlb; struct vm_area_struct *vma; + + /* + * Tell all users of get_user/copy_from_user etc... that the content + * is no longer stable. No barriers really needed because unmapping + * should imply barriers already and the reader would hit a page fault + * if it stumbled over a reaped memory. + */ + set_bit(MMF_UNSTABLE, &mm->flags); + + for (vma = mm->mmap ; vma; vma = vma->vm_next) { + if (!can_madv_dontneed_vma(vma)) + continue; + + /* + * Only anonymous pages have a good chance to be dropped + * without additional steps which we cannot afford as we + * are OOM already. + * + * We do not even care about fs backed pages because all + * which are reclaimable have already been reclaimed and + * we do not want to block exit_mmap by keeping mm ref + * count elevated without a good reason. + */ + if (vma_is_anonymous(vma) || !(vma->vm_flags & VM_SHARED)) { + const unsigned long start = vma->vm_start; + const unsigned long end = vma->vm_end; + struct mmu_gather tlb; + + tlb_gather_mmu(&tlb, mm, start, end); + mmu_notifier_invalidate_range_start(mm, start, end); + unmap_page_range(&tlb, vma, start, end, NULL); + mmu_notifier_invalidate_range_end(mm, start, end); + tlb_finish_mmu(&tlb, start, end); + } + } +} + +static bool oom_reap_task_mm(struct task_struct *tsk, struct mm_struct *mm) +{ bool ret = true; /* * We have to make sure to not race with the victim exit path * and cause premature new oom victim selection: - * __oom_reap_task_mm exit_mm + * oom_reap_task_mm exit_mm * mmget_not_zero * mmput * atomic_dec_and_test @@ -534,39 +571,8 @@ static bool __oom_reap_task_mm(struct ta trace_start_task_reaping(tsk->pid); - /* - * Tell all users of get_user/copy_from_user etc... that the content - * is no longer stable. No barriers really needed because unmapping - * should imply barriers already and the reader would hit a page fault - * if it stumbled over a reaped memory. - */ - set_bit(MMF_UNSTABLE, &mm->flags); - - for (vma = mm->mmap ; vma; vma = vma->vm_next) { - if (!can_madv_dontneed_vma(vma)) - continue; + __oom_reap_task_mm(mm); - /* - * Only anonymous pages have a good chance to be dropped - * without additional steps which we cannot afford as we - * are OOM already. - * - * We do not even care about fs backed pages because all - * which are reclaimable have already been reclaimed and - * we do not want to block exit_mmap by keeping mm ref - * count elevated without a good reason. - */ - if (vma_is_anonymous(vma) || !(vma->vm_flags & VM_SHARED)) { - const unsigned long start = vma->vm_start; - const unsigned long end = vma->vm_end; - - tlb_gather_mmu(&tlb, mm, start, end); - mmu_notifier_invalidate_range_start(mm, start, end); - unmap_page_range(&tlb, vma, start, end, NULL); - mmu_notifier_invalidate_range_end(mm, start, end); - tlb_finish_mmu(&tlb, start, end); - } - } pr_info("oom_reaper: reaped process %d (%s), now anon-rss:%lukB, file-rss:%lukB, shmem-rss:%lukB\n", task_pid_nr(tsk), tsk->comm, K(get_mm_counter(mm, MM_ANONPAGES)), @@ -587,14 +593,13 @@ static void oom_reap_task(struct task_st struct mm_struct *mm = tsk->signal->oom_mm; /* Retry the down_read_trylock(mmap_sem) a few times */ - while (attempts++ < MAX_OOM_REAP_RETRIES && !__oom_reap_task_mm(tsk, mm)) + while (attempts++ < MAX_OOM_REAP_RETRIES && !oom_reap_task_mm(tsk, mm)) schedule_timeout_idle(HZ/10); if (attempts <= MAX_OOM_REAP_RETRIES || test_bit(MMF_OOM_SKIP, &mm->flags)) goto done; - pr_info("oom_reaper: unable to reap pid:%d (%s)\n", task_pid_nr(tsk), tsk->comm); debug_show_all_locks(); _

7 years, 8 months

1
0
0 0

[patch 06/13] mm: sections are not offlined during memory hotremove

by akpm＠linux-foundation.org

From: Pavel Tatashin <pasha.tatashin(a)oracle.com> Subject: mm: sections are not offlined during memory hotremove Memory hotplug and hotremove operate with per-block granularity. If the machine has a large amount of memory (more than 64G), the size of a memory block can span multiple sections. By mistake, during hotremove we set only the first section to offline state. The bug was discovered because kernel selftest started to fail: https://lkml.kernel.org/r/20180423011247.GK5563@yexl-desktop After commit, "mm/memory_hotplug: optimize probe routine". But, the bug is older than this commit. In this optimization we also added a check for sections to be in a proper state during hotplug operation. Link: http://lkml.kernel.org/r/20180427145257.15222-1-pasha.tatashin@oracle.com Fixes: 2d070eab2e82 ("mm: consider zone which is not fully populated to have holes") Signed-off-by: Pavel Tatashin <pasha.tatashin(a)oracle.com> Acked-by: Michal Hocko <mhocko(a)suse.com> Reviewed-by: Andrew Morton <akpm(a)linux-foundation.org> Cc: Vlastimil Babka <vbabka(a)suse.cz> Cc: Steven Sistare <steven.sistare(a)oracle.com> Cc: Daniel Jordan <daniel.m.jordan(a)oracle.com> Cc: "Kirill A. Shutemov" <kirill.shutemov(a)linux.intel.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/sparse.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff -puN mm/sparse.c~mm-sections-are-not-offlined-during-memory-hotremove mm/sparse.c --- a/mm/sparse.c~mm-sections-are-not-offlined-during-memory-hotremove +++ a/mm/sparse.c @@ -629,7 +629,7 @@ void offline_mem_sections(unsigned long unsigned long pfn; for (pfn = start_pfn; pfn < end_pfn; pfn += PAGES_PER_SECTION) { - unsigned long section_nr = pfn_to_section_nr(start_pfn); + unsigned long section_nr = pfn_to_section_nr(pfn); struct mem_section *ms; /* _

7 years, 8 months

1
0
0 0

[patch 05/13] z3fold: fix reclaim lock-ups

by akpm＠linux-foundation.org

From: Vitaly Wool <vitalywool(a)gmail.com> Subject: z3fold: fix reclaim lock-ups Do not try to optimize in-page object layout while the page is under reclaim. This fixes lock-ups on reclaim and improves reclaim performance at the same time. [akpm(a)linux-foundation.org: coding-style fixes] Link: http://lkml.kernel.org/r/20180430125800.444cae9706489f412ad12621@gmail.com Signed-off-by: Vitaly Wool <vitaly.vul(a)sony.com> Reported-by: Guenter Roeck <linux(a)roeck-us.net> Tested-by: Guenter Roeck <linux(a)roeck-us.net> Cc: <Oleksiy.Avramchenko(a)sony.com> Cc: Matthew Wilcox <mawilcox(a)microsoft.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/z3fold.c | 42 ++++++++++++++++++++++++++++++------------ 1 file changed, 30 insertions(+), 12 deletions(-) diff -puN mm/z3fold.c~z3fold-fix-reclaim-lock-ups mm/z3fold.c --- a/mm/z3fold.c~z3fold-fix-reclaim-lock-ups +++ a/mm/z3fold.c @@ -144,7 +144,8 @@ enum z3fold_page_flags { PAGE_HEADLESS = 0, MIDDLE_CHUNK_MAPPED, NEEDS_COMPACTING, - PAGE_STALE + PAGE_STALE, + UNDER_RECLAIM }; /***************** @@ -173,6 +174,7 @@ static struct z3fold_header *init_z3fold clear_bit(MIDDLE_CHUNK_MAPPED, &page->private); clear_bit(NEEDS_COMPACTING, &page->private); clear_bit(PAGE_STALE, &page->private); + clear_bit(UNDER_RECLAIM, &page->private); spin_lock_init(&zhdr->page_lock); kref_init(&zhdr->refcount); @@ -756,6 +758,10 @@ static void z3fold_free(struct z3fold_po atomic64_dec(&pool->pages_nr); return; } + if (test_bit(UNDER_RECLAIM, &page->private)) { + z3fold_page_unlock(zhdr); + return; + } if (test_and_set_bit(NEEDS_COMPACTING, &page->private)) { z3fold_page_unlock(zhdr); return; @@ -840,6 +846,8 @@ static int z3fold_reclaim_page(struct z3 kref_get(&zhdr->refcount); list_del_init(&zhdr->buddy); zhdr->cpu = -1; + set_bit(UNDER_RECLAIM, &page->private); + break; } list_del_init(&page->lru); @@ -887,25 +895,35 @@ static int z3fold_reclaim_page(struct z3 goto next; } next: - spin_lock(&pool->lock); if (test_bit(PAGE_HEADLESS, &page->private)) { if (ret == 0) { - spin_unlock(&pool->lock); free_z3fold_page(page); return 0; } - } else if (kref_put(&zhdr->refcount, release_z3fold_page)) { - atomic64_dec(&pool->pages_nr); + spin_lock(&pool->lock); + list_add(&page->lru, &pool->lru); + spin_unlock(&pool->lock); + } else { + z3fold_page_lock(zhdr); + clear_bit(UNDER_RECLAIM, &page->private); + if (kref_put(&zhdr->refcount, + release_z3fold_page_locked)) { + atomic64_dec(&pool->pages_nr); + return 0; + } + /* + * if we are here, the page is still not completely + * free. Take the global pool lock then to be able + * to add it back to the lru list + */ + spin_lock(&pool->lock); + list_add(&page->lru, &pool->lru); spin_unlock(&pool->lock); - return 0; + z3fold_page_unlock(zhdr); } - /* - * Add to the beginning of LRU. - * Pool lock has to be kept here to ensure the page has - * not already been released - */ - list_add(&page->lru, &pool->lru); + /* We started off locked to we need to lock the pool back */ + spin_lock(&pool->lock); } spin_unlock(&pool->lock); return -EAGAIN; _

7 years, 8 months

1
0
0 0

Re: [PATCH] drm/i915/oa: Disable OA on Haswell

by Chris Wilson

Quoting Lionel Landwerlin (2018-05-11 18:41:28) > On 11/05/18 16:51, Chris Wilson wrote: > > But I can't even startup a gdm on that machine with drm-tip. So maybe > there is some much more broken... > > Don't leave us in suspense... > > > https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=890614 > > > Not our bug :) You would not believe how relieved I am that someone else has bugs in their code. -Chris

7 years, 8 months

1
0
0 0

[GIT PULL] tracing: Fix regex_match_front() to not over compare the test string

by Steven Rostedt

Linus, Working on some new updates to trace filtering, I noticed that the regex_match_front() test was updated to be limited to the size of the pattern instead of the full test string. But as the test string is not guaranteed to be nul terminated, it still needs to consider the size of the test string. Please pull the latest trace-v4.17-rc4 tree, which can be found at: git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace.git trace-v4.17-rc4 Tag SHA1: cb82e07247fa5f1a91940a2928fb260256727a14 Head SHA1: dc432c3d7f9bceb3de6f5b44fb9c657c9810ed6d Steven Rostedt (VMware) (1): tracing: Fix regex_match_front() to not over compare the test string ---- kernel/trace/trace_events_filter.c | 3 +++ 1 file changed, 3 insertions(+) --------------------------- commit dc432c3d7f9bceb3de6f5b44fb9c657c9810ed6d Author: Steven Rostedt (VMware) <rostedt(a)goodmis.org> Date: Wed May 9 11:59:32 2018 -0400 tracing: Fix regex_match_front() to not over compare the test string The regex match function regex_match_front() in the tracing filter logic, was fixed to test just the pattern length from testing the entire test string. That is, it went from strncmp(str, r->pattern, len) to strcmp(str, r->pattern, r->len). The issue is that str is not guaranteed to be nul terminated, and if r->len is greater than the length of str, it can access more memory than is allocated. The solution is to add a simple test if (len < r->len) return 0. Cc: stable(a)vger.kernel.org Fixes: 285caad415f45 ("tracing/filters: Fix MATCH_FRONT_ONLY filter matching") Signed-off-by: Steven Rostedt (VMware) <rostedt(a)goodmis.org> diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index 1f951b3df60c..7d306b74230f 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -762,6 +762,9 @@ static int regex_match_full(char *str, struct regex *r, int len) static int regex_match_front(char *str, struct regex *r, int len) { + if (len < r->len) + return 0; + if (strncmp(str, r->pattern, r->len) == 0) return 1; return 0;

7 years, 8 months

1
0
0 0

FAILED: patch "[PATCH] test_firmware: fix setting old custom fw path back on exit, " failed to apply to 4.16-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.16-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From e538409257d0217a9bc715686100a5328db75a15 Mon Sep 17 00:00:00 2001 From: Ben Hutchings <ben.hutchings(a)codethink.co.uk> Date: Wed, 4 Apr 2018 22:38:49 +0200 Subject: [PATCH] test_firmware: fix setting old custom fw path back on exit, second try Commit 65c79230576 tried to clear the custom firmware path on exit by writing a single space to the firmware_class.path parameter. This doesn't work because nothing strips this space from the value stored and fw_get_filesystem_firmware() only ignores zero-length paths. Instead, write a null byte. Fixes: 0a8adf58475 ("test: add firmware_class loader test") Fixes: 65c79230576 ("test_firmware: fix setting old custom fw path back on exit") Signed-off-by: Ben Hutchings <ben.hutchings(a)codethink.co.uk> Acked-by: Luis R. Rodriguez <mcgrof(a)kernel.org> Cc: stable <stable(a)vger.kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> diff --git a/tools/testing/selftests/firmware/fw_lib.sh b/tools/testing/selftests/firmware/fw_lib.sh index 9ea31b57d71a..962d7f4ac627 100755 --- a/tools/testing/selftests/firmware/fw_lib.sh +++ b/tools/testing/selftests/firmware/fw_lib.sh @@ -154,11 +154,13 @@ test_finish() if [ "$HAS_FW_LOADER_USER_HELPER" = "yes" ]; then echo "$OLD_TIMEOUT" >/sys/class/firmware/timeout fi - if [ "$OLD_FWPATH" = "" ]; then - OLD_FWPATH=" " - fi if [ "$TEST_REQS_FW_SET_CUSTOM_PATH" = "yes" ]; then - echo -n "$OLD_FWPATH" >/sys/module/firmware_class/parameters/path + if [ "$OLD_FWPATH" = "" ]; then + # A zero-length write won't work; write a null byte + printf '\000' >/sys/module/firmware_class/parameters/path + else + echo -n "$OLD_FWPATH" >/sys/module/firmware_class/parameters/path + fi fi if [ -f $FW ]; then rm -f "$FW"

7 years, 8 months

3
3
0 0

[PATCH 4/4] KVM: arm/arm64: VGIC/ITS save/restore: protect kvm_read_guest() calls

by Andre Przywara

kvm_read_guest() will eventually look up in kvm_memslots(), which requires either to hold the kvm->slots_lock or to be inside a kvm->srcu critical section. In contrast to x86 and s390 we don't take the SRCU lock on every guest exit, so we have to do it individually for each kvm_read_guest() call. Use the newly introduced wrapper for that. Cc: Stable <stable(a)vger.kernel.org> # 4.12+ Reported-by: Jan Glauber <jan.glauber(a)caviumnetworks.com> Signed-off-by: Andre Przywara <andre.przywara(a)arm.com> --- virt/kvm/arm/vgic/vgic-its.c | 4 ++-- virt/kvm/arm/vgic/vgic-v3.c | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/virt/kvm/arm/vgic/vgic-its.c b/virt/kvm/arm/vgic/vgic-its.c index 7cb060e01a76..4ed79c939fb4 100644 --- a/virt/kvm/arm/vgic/vgic-its.c +++ b/virt/kvm/arm/vgic/vgic-its.c @@ -1897,7 +1897,7 @@ static int scan_its_table(struct vgic_its *its, gpa_t base, int size, int esz, int next_offset; size_t byte_offset; - ret = kvm_read_guest(kvm, gpa, entry, esz); + ret = kvm_read_guest_lock(kvm, gpa, entry, esz); if (ret) return ret; @@ -2267,7 +2267,7 @@ static int vgic_its_restore_cte(struct vgic_its *its, gpa_t gpa, int esz) int ret; BUG_ON(esz > sizeof(val)); - ret = kvm_read_guest(kvm, gpa, &val, esz); + ret = kvm_read_guest_lock(kvm, gpa, &val, esz); if (ret) return ret; val = le64_to_cpu(val); diff --git a/virt/kvm/arm/vgic/vgic-v3.c b/virt/kvm/arm/vgic/vgic-v3.c index c7423f3768e5..bdcf8e7a6161 100644 --- a/virt/kvm/arm/vgic/vgic-v3.c +++ b/virt/kvm/arm/vgic/vgic-v3.c @@ -344,7 +344,7 @@ int vgic_v3_lpi_sync_pending_status(struct kvm *kvm, struct vgic_irq *irq) bit_nr = irq->intid % BITS_PER_BYTE; ptr = pendbase + byte_offset; - ret = kvm_read_guest(kvm, ptr, &val, 1); + ret = kvm_read_guest_lock(kvm, ptr, &val, 1); if (ret) return ret; @@ -397,7 +397,7 @@ int vgic_v3_save_pending_tables(struct kvm *kvm) ptr = pendbase + byte_offset; if (byte_offset != last_byte_offset) { - ret = kvm_read_guest(kvm, ptr, &val, 1); + ret = kvm_read_guest_lock(kvm, ptr, &val, 1); if (ret) return ret; last_byte_offset = byte_offset; -- 2.14.1

7 years, 8 months

1
0
0 0

[PATCH 3/4] KVM: arm/arm64: VGIC/ITS: protect kvm_read_guest() calls with SRCU lock

by Andre Przywara

kvm_read_guest() will eventually look up in kvm_memslots(), which requires either to hold the kvm->slots_lock or to be inside a kvm->srcu critical section. In contrast to x86 and s390 we don't take the SRCU lock on every guest exit, so we have to do it individually for each kvm_read_guest() call. Provide a wrapper which does that and use that everywhere. Note that ending the SRCU critical section before returning from the kvm_read_guest() wrapper is safe, because the data has been *copied*, so we don't need to rely on valid references to the memslot anymore. Cc: Stable <stable(a)vger.kernel.org> # 4.8+ Reported-by: Jan Glauber <jan.glauber(a)caviumnetworks.com> Signed-off-by: Andre Przywara <andre.przywara(a)arm.com> --- arch/arm/include/asm/kvm_mmu.h | 16 ++++++++++++++++ arch/arm64/include/asm/kvm_mmu.h | 16 ++++++++++++++++ virt/kvm/arm/vgic/vgic-its.c | 15 ++++++++------- 3 files changed, 40 insertions(+), 7 deletions(-) diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h index 707a1f06dc5d..f675162663f0 100644 --- a/arch/arm/include/asm/kvm_mmu.h +++ b/arch/arm/include/asm/kvm_mmu.h @@ -309,6 +309,22 @@ static inline unsigned int kvm_get_vmid_bits(void) return 8; } +/* + * We are not in the kvm->srcu critical section most of the time, so we take + * the SRCU read lock here. Since we copy the data from the user page, we + * can immediately drop the lock again. + */ +static inline int kvm_read_guest_lock(struct kvm *kvm, + gpa_t gpa, void *data, unsigned long len) +{ + int srcu_idx = srcu_read_lock(&kvm->srcu); + int ret = kvm_read_guest(kvm, gpa, data, len); + + srcu_read_unlock(&kvm->srcu, srcu_idx); + + return ret; +} + static inline void *kvm_get_hyp_vector(void) { return kvm_ksym_ref(__kvm_hyp_vector); diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h index 082110993647..6128992c2ded 100644 --- a/arch/arm64/include/asm/kvm_mmu.h +++ b/arch/arm64/include/asm/kvm_mmu.h @@ -360,6 +360,22 @@ static inline unsigned int kvm_get_vmid_bits(void) return (cpuid_feature_extract_unsigned_field(reg, ID_AA64MMFR1_VMIDBITS_SHIFT) == 2) ? 16 : 8; } +/* + * We are not in the kvm->srcu critical section most of the time, so we take + * the SRCU read lock here. Since we copy the data from the user page, we + * can immediately drop the lock again. + */ +static inline int kvm_read_guest_lock(struct kvm *kvm, + gpa_t gpa, void *data, unsigned long len) +{ + int srcu_idx = srcu_read_lock(&kvm->srcu); + int ret = kvm_read_guest(kvm, gpa, data, len); + + srcu_read_unlock(&kvm->srcu, srcu_idx); + + return ret; +} + #ifdef CONFIG_KVM_INDIRECT_VECTORS /* * EL2 vectors can be mapped and rerouted in a number of ways, diff --git a/virt/kvm/arm/vgic/vgic-its.c b/virt/kvm/arm/vgic/vgic-its.c index 51a80b600632..7cb060e01a76 100644 --- a/virt/kvm/arm/vgic/vgic-its.c +++ b/virt/kvm/arm/vgic/vgic-its.c @@ -281,8 +281,8 @@ static int update_lpi_config(struct kvm *kvm, struct vgic_irq *irq, int ret; unsigned long flags; - ret = kvm_read_guest(kvm, propbase + irq->intid - GIC_LPI_OFFSET, - &prop, 1); + ret = kvm_read_guest_lock(kvm, propbase + irq->intid - GIC_LPI_OFFSET, + &prop, 1); if (ret) return ret; @@ -444,8 +444,9 @@ static int its_sync_lpi_pending_table(struct kvm_vcpu *vcpu) * this very same byte in the last iteration. Reuse that. */ if (byte_offset != last_byte_offset) { - ret = kvm_read_guest(vcpu->kvm, pendbase + byte_offset, - &pendmask, 1); + ret = kvm_read_guest_lock(vcpu->kvm, + pendbase + byte_offset, + &pendmask, 1); if (ret) { kfree(intids); return ret; @@ -789,7 +790,7 @@ static bool vgic_its_check_id(struct vgic_its *its, u64 baser, u32 id, return false; /* Each 1st level entry is represented by a 64-bit value. */ - if (kvm_read_guest(its->dev->kvm, + if (kvm_read_guest_lock(its->dev->kvm, BASER_ADDRESS(baser) + index * sizeof(indirect_ptr), &indirect_ptr, sizeof(indirect_ptr))) return false; @@ -1370,8 +1371,8 @@ static void vgic_its_process_commands(struct kvm *kvm, struct vgic_its *its) cbaser = CBASER_ADDRESS(its->cbaser); while (its->cwriter != its->creadr) { - int ret = kvm_read_guest(kvm, cbaser + its->creadr, - cmd_buf, ITS_CMD_SIZE); + int ret = kvm_read_guest_lock(kvm, cbaser + its->creadr, + cmd_buf, ITS_CMD_SIZE); /* * If kvm_read_guest() fails, this could be due to the guest * programming a bogus value in CBASER or something else going -- 2.14.1

7 years, 8 months

1
0
0 0

[PATCH 2/4] KVM: arm/arm64: VGIC/ITS: Promote irq_lock() in update_affinity

by Andre Przywara

Apparently the development of update_affinity() overlapped with the promotion of irq_lock to be _irqsave, so the patch didn't convert this lock over. This will make lockdep complain. Fix this by disabling IRQs around the lock. Cc: stable(a)vger.kernel.org Fixes: 08c9fd042117 ("KVM: arm/arm64: vITS: Add a helper to update the affinity of an LPI") Reported-by: Jan Glauber <jan.glauber(a)caviumnetworks.com> Signed-off-by: Andre Przywara <andre.przywara(a)arm.com> --- virt/kvm/arm/vgic/vgic-its.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/virt/kvm/arm/vgic/vgic-its.c b/virt/kvm/arm/vgic/vgic-its.c index 41abf92f2699..51a80b600632 100644 --- a/virt/kvm/arm/vgic/vgic-its.c +++ b/virt/kvm/arm/vgic/vgic-its.c @@ -350,10 +350,11 @@ static int vgic_copy_lpi_list(struct kvm_vcpu *vcpu, u32 **intid_ptr) static int update_affinity(struct vgic_irq *irq, struct kvm_vcpu *vcpu) { int ret = 0; + unsigned long flags; - spin_lock(&irq->irq_lock); + spin_lock_irqsave(&irq->irq_lock, flags); irq->target_vcpu = vcpu; - spin_unlock(&irq->irq_lock); + spin_unlock_irqrestore(&irq->irq_lock, flags); if (irq->hw) { struct its_vlpi_map map; -- 2.14.1

7 years, 8 months

1
0
0 0

[PATCH 1/4] KVM: arm/arm64: Properly protect VGIC locks from IRQs

by Andre Przywara

As Jan reported [1], lockdep complains about the VGIC not being bullet proof. This seems to be due to two issues: - When commit 006df0f34930 ("KVM: arm/arm64: Support calling vgic_update_irq_pending from irq context") promoted irq_lock and ap_list_lock to _irqsave, we forgot two instances of irq_lock. lockdeps seems to pick those up. - If a lock is _irqsave, any other locks we take inside them should be _irqsafe as well. So the lpi_list_lock needs to be promoted also. This fixes both issues by simply making the remaining instances of those locks _irqsave. One irq_lock is addressed in a separate patch, to simplify backporting. Cc: stable(a)vger.kernel.org Fixes: 006df0f34930 ("KVM: arm/arm64: Support calling vgic_update_irq_pending from irq context") Reported-by: Jan Glauber <jan.glauber(a)caviumnetworks.com> Signed-off-by: Andre Przywara <andre.przywara(a)arm.com> [1] http://lists.infradead.org/pipermail/linux-arm-kernel/2018-May/575718.html --- virt/kvm/arm/vgic/vgic-debug.c | 5 +++-- virt/kvm/arm/vgic/vgic-its.c | 10 ++++++---- virt/kvm/arm/vgic/vgic.c | 22 ++++++++++++++-------- 3 files changed, 23 insertions(+), 14 deletions(-) diff --git a/virt/kvm/arm/vgic/vgic-debug.c b/virt/kvm/arm/vgic/vgic-debug.c index 10b38178cff2..4ffc0b5e6105 100644 --- a/virt/kvm/arm/vgic/vgic-debug.c +++ b/virt/kvm/arm/vgic/vgic-debug.c @@ -211,6 +211,7 @@ static int vgic_debug_show(struct seq_file *s, void *v) struct vgic_state_iter *iter = (struct vgic_state_iter *)v; struct vgic_irq *irq; struct kvm_vcpu *vcpu = NULL; + unsigned long flags; if (iter->dist_id == 0) { print_dist_state(s, &kvm->arch.vgic); @@ -227,9 +228,9 @@ static int vgic_debug_show(struct seq_file *s, void *v) irq = &kvm->arch.vgic.spis[iter->intid - VGIC_NR_PRIVATE_IRQS]; } - spin_lock(&irq->irq_lock); + spin_lock_irqsave(&irq->irq_lock, flags); print_irq_state(s, irq, vcpu); - spin_unlock(&irq->irq_lock); + spin_unlock_irqrestore(&irq->irq_lock, flags); return 0; } diff --git a/virt/kvm/arm/vgic/vgic-its.c b/virt/kvm/arm/vgic/vgic-its.c index a8f07243aa9f..41abf92f2699 100644 --- a/virt/kvm/arm/vgic/vgic-its.c +++ b/virt/kvm/arm/vgic/vgic-its.c @@ -52,6 +52,7 @@ static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid, { struct vgic_dist *dist = &kvm->arch.vgic; struct vgic_irq *irq = vgic_get_irq(kvm, NULL, intid), *oldirq; + unsigned long flags; int ret; /* In this case there is no put, since we keep the reference. */ @@ -71,7 +72,7 @@ static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid, irq->intid = intid; irq->target_vcpu = vcpu; - spin_lock(&dist->lpi_list_lock); + spin_lock_irqsave(&dist->lpi_list_lock, flags); /* * There could be a race with another vgic_add_lpi(), so we need to @@ -99,7 +100,7 @@ static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid, dist->lpi_list_count++; out_unlock: - spin_unlock(&dist->lpi_list_lock); + spin_unlock_irqrestore(&dist->lpi_list_lock, flags); /* * We "cache" the configuration table entries in our struct vgic_irq's. @@ -315,6 +316,7 @@ static int vgic_copy_lpi_list(struct kvm_vcpu *vcpu, u32 **intid_ptr) { struct vgic_dist *dist = &vcpu->kvm->arch.vgic; struct vgic_irq *irq; + unsigned long flags; u32 *intids; int irq_count, i = 0; @@ -330,7 +332,7 @@ static int vgic_copy_lpi_list(struct kvm_vcpu *vcpu, u32 **intid_ptr) if (!intids) return -ENOMEM; - spin_lock(&dist->lpi_list_lock); + spin_lock_irqsave(&dist->lpi_list_lock, flags); list_for_each_entry(irq, &dist->lpi_list_head, lpi_list) { if (i == irq_count) break; @@ -339,7 +341,7 @@ static int vgic_copy_lpi_list(struct kvm_vcpu *vcpu, u32 **intid_ptr) continue; intids[i++] = irq->intid; } - spin_unlock(&dist->lpi_list_lock); + spin_unlock_irqrestore(&dist->lpi_list_lock, flags); *intid_ptr = intids; return i; diff --git a/virt/kvm/arm/vgic/vgic.c b/virt/kvm/arm/vgic/vgic.c index 27219313a406..1dfb5b2f1b12 100644 --- a/virt/kvm/arm/vgic/vgic.c +++ b/virt/kvm/arm/vgic/vgic.c @@ -43,9 +43,13 @@ struct vgic_global kvm_vgic_global_state __ro_after_init = { * kvm->lock (mutex) * its->cmd_lock (mutex) * its->its_lock (mutex) - * vgic_cpu->ap_list_lock - * kvm->lpi_list_lock - * vgic_irq->irq_lock + * vgic_cpu->ap_list_lock must be taken with IRQs disabled + * kvm->lpi_list_lock must be taken with IRQs disabled + * vgic_irq->irq_lock must be taken with IRQs disabled + * + * As the ap_list_lock might be taken from the timer interrupt handler, + * we have to disable IRQs before taking this lock and everything lower + * than it. * * If you need to take multiple locks, always take the upper lock first, * then the lower ones, e.g. first take the its_lock, then the irq_lock. @@ -72,8 +76,9 @@ static struct vgic_irq *vgic_get_lpi(struct kvm *kvm, u32 intid) { struct vgic_dist *dist = &kvm->arch.vgic; struct vgic_irq *irq = NULL; + unsigned long flags; - spin_lock(&dist->lpi_list_lock); + spin_lock_irqsave(&dist->lpi_list_lock, flags); list_for_each_entry(irq, &dist->lpi_list_head, lpi_list) { if (irq->intid != intid) @@ -89,7 +94,7 @@ static struct vgic_irq *vgic_get_lpi(struct kvm *kvm, u32 intid) irq = NULL; out_unlock: - spin_unlock(&dist->lpi_list_lock); + spin_unlock_irqrestore(&dist->lpi_list_lock, flags); return irq; } @@ -134,19 +139,20 @@ static void vgic_irq_release(struct kref *ref) void vgic_put_irq(struct kvm *kvm, struct vgic_irq *irq) { struct vgic_dist *dist = &kvm->arch.vgic; + unsigned long flags; if (irq->intid < VGIC_MIN_LPI) return; - spin_lock(&dist->lpi_list_lock); + spin_lock_irqsave(&dist->lpi_list_lock, flags); if (!kref_put(&irq->refcount, vgic_irq_release)) { - spin_unlock(&dist->lpi_list_lock); + spin_unlock_irqrestore(&dist->lpi_list_lock, flags); return; }; list_del(&irq->lpi_list); dist->lpi_list_count--; - spin_unlock(&dist->lpi_list_lock); + spin_unlock_irqrestore(&dist->lpi_list_lock, flags); kfree(irq); } -- 2.14.1

7 years, 8 months

1
0
0 0

[PATCH] [stable 4.14] arm64: Add work around for Arm Cortex-A55 Erratum 1024718

by Suzuki K Poulose

commit ece1397cbc89c51914fae1aec729539cfd8bd62b upstream Some variants of the Arm Cortex-55 cores (r0p0, r0p1, r1p0) suffer from an erratum 1024718, which causes incorrect updates when DBM/AP bits in a page table entry is modified without a break-before-make sequence. The work around is to disable the hardware DBM feature on the affected cores. The hardware Access Flag management features is not affected. The hardware DBM feature is a non-conflicting capability, i.e, the kernel could handle cores using the feature and those without having the features running at the same time. So this work around is detected at early boot time, rather than delaying it until the CPUs are brought up into the kernel with MMU turned on. This also avoids other complexities with late CPUs turning online, with or without the hardware DBM features. Cc: stable(a)vger.kernel.org # v4.14 Cc: Catalin Marinas <catalin.marinas(a)arm.com> Cc: Mark Rutland <mark.rutland(a)arm.com> Cc: Will Deacon <will.deacon(a)arm.com> Signed-off-by: Suzuki K Poulose <suzuki.poulose(a)arm.com> --- Note: The upstream commit is on top of a reworked capability infrastructure for arm64 heterogeneous systems, which allows delaying the CPU model checks. This backport is based on the original version of the patch [0], which checks the affected CPU models during the early boot. [0] https://lkml.kernel.org/r/20180116102323.3470-1-suzuki.poulose@arm.com --- Documentation/arm64/silicon-errata.txt | 1 + arch/arm64/Kconfig | 14 ++++++++++++ arch/arm64/include/asm/assembler.h | 40 ++++++++++++++++++++++++++++++++++ arch/arm64/include/asm/cputype.h | 2 ++ arch/arm64/mm/proc.S | 5 +++++ 5 files changed, 62 insertions(+) diff --git a/Documentation/arm64/silicon-errata.txt b/Documentation/arm64/silicon-errata.txt index f3d0d31..e4fe6ad 100644 --- a/Documentation/arm64/silicon-errata.txt +++ b/Documentation/arm64/silicon-errata.txt @@ -55,6 +55,7 @@ stable kernels. | ARM | Cortex-A57 | #834220 | ARM64_ERRATUM_834220 | | ARM | Cortex-A72 | #853709 | N/A | | ARM | Cortex-A73 | #858921 | ARM64_ERRATUM_858921 | +| ARM | Cortex-A55 | #1024718 | ARM64_ERRATUM_1024718 | | ARM | MMU-500 | #841119,#826419 | N/A | | | | | | | Cavium | ThunderX ITS | #22375, #24313 | CAVIUM_ERRATUM_22375 | diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index c2abb4e..2d5f7ac 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -443,6 +443,20 @@ config ARM64_ERRATUM_843419 If unsure, say Y. +config ARM64_ERRATUM_1024718 + bool "Cortex-A55: 1024718: Update of DBM/AP bits without break before make might result in incorrect update" + default y + help + This option adds work around for Arm Cortex-A55 Erratum 1024718. + + Affected Cortex-A55 cores (r0p0, r0p1, r1p0) could cause incorrect + update of the hardware dirty bit when the DBM/AP bits are updated + without a break-before-make. The work around is to disable the usage + of hardware DBM locally on the affected cores. CPUs not affected by + erratum will continue to use the feature. + + If unsure, say Y. + config CAVIUM_ERRATUM_22375 bool "Cavium erratum 22375, 24313" default y diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h index 463619d..25b2a41 100644 --- a/arch/arm64/include/asm/assembler.h +++ b/arch/arm64/include/asm/assembler.h @@ -25,6 +25,7 @@ #include <asm/asm-offsets.h> #include <asm/cpufeature.h> +#include <asm/cputype.h> #include <asm/page.h> #include <asm/pgtable-hwdef.h> #include <asm/ptrace.h> @@ -495,4 +496,43 @@ alternative_endif and \phys, \pte, #(((1 << (48 - PAGE_SHIFT)) - 1) << PAGE_SHIFT) .endm +/* + * Check the MIDR_EL1 of the current CPU for a given model and a range of + * variant/revision. See asm/cputype.h for the macros used below. + * + * model: MIDR_CPU_MODEL of CPU + * rv_min: Minimum of MIDR_CPU_VAR_REV() + * rv_max: Maximum of MIDR_CPU_VAR_REV() + * res: Result register. + * tmp1, tmp2, tmp3: Temporary registers + * + * Corrupts: res, tmp1, tmp2, tmp3 + * Returns: 0, if the CPU id doesn't match. Non-zero otherwise + */ + .macro cpu_midr_match model, rv_min, rv_max, res, tmp1, tmp2, tmp3 + mrs \res, midr_el1 + mov_q \tmp1, (MIDR_REVISION_MASK | MIDR_VARIANT_MASK) + mov_q \tmp2, MIDR_CPU_MODEL_MASK + and \tmp3, \res, \tmp2 // Extract model + and \tmp1, \res, \tmp1 // rev & variant + mov_q \tmp2, \model + cmp \tmp3, \tmp2 + cset \res, eq + cbz \res, .Ldone\@ // Model matches ? + + .if (\rv_min != 0) // Skip min check if rv_min == 0 + mov_q \tmp3, \rv_min + cmp \tmp1, \tmp3 + cset \res, ge + .endif // \rv_min != 0 + /* Skip rv_max check if rv_min == rv_max && rv_min != 0 */ + .if ((\rv_min != \rv_max) || \rv_min == 0) + mov_q \tmp2, \rv_max + cmp \tmp1, \tmp2 + cset \tmp2, le + and \res, \res, \tmp2 + .endif +.Ldone\@: + .endm + #endif /* __ASM_ASSEMBLER_H */ diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index be7bd19..30da091 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -78,6 +78,7 @@ #define ARM_CPU_PART_AEM_V8 0xD0F #define ARM_CPU_PART_FOUNDATION 0xD00 +#define ARM_CPU_PART_CORTEX_A55 0xD05 #define ARM_CPU_PART_CORTEX_A57 0xD07 #define ARM_CPU_PART_CORTEX_A72 0xD08 #define ARM_CPU_PART_CORTEX_A53 0xD03 @@ -98,6 +99,7 @@ #define QCOM_CPU_PART_KRYO 0x200 #define MIDR_CORTEX_A53 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A53) +#define MIDR_CORTEX_A55 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A55) #define MIDR_CORTEX_A57 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A57) #define MIDR_CORTEX_A72 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A72) #define MIDR_CORTEX_A73 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A73) diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index 139320a..e338165 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -438,6 +438,11 @@ ENTRY(__cpu_setup) cbz x9, 2f cmp x9, #2 b.lt 1f +#ifdef CONFIG_ARM64_ERRATUM_1024718 + /* Disable hardware DBM on Cortex-A55 r0p0, r0p1 & r1p0 */ + cpu_midr_match MIDR_CORTEX_A55, MIDR_CPU_VAR_REV(0, 0), MIDR_CPU_VAR_REV(1, 0), x1, x2, x3, x4 + cbnz x1, 1f +#endif orr x10, x10, #TCR_HD // hardware Dirty flag update 1: orr x10, x10, #TCR_HA // hardware Access flag update 2: -- 2.7.4

7 years, 8 months

2
1
0 0

2026

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror