From 579b9239c1f38665b21e8d0e6ee83ecc96dbd6bb Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Wed, 23 Jan 2019 11:51:38 +0530 Subject: powerpc/radix: Fix kernel crash with mremap() With support for split pmd lock, we use pmd page pmd_huge_pte pointer to store the deposited page table. In those config when we move page tables we need to make sure we move the deposited page table to the correct pmd page. Otherwise this can result in crash when we withdraw of deposited page table because we can find the pmd_huge_pte NULL. eg: __split_huge_pmd+0x1070/0x1940 __split_huge_pmd+0xe34/0x1940 (unreliable) vma_adjust_trans_huge+0x110/0x1c0 __vma_adjust+0x2b4/0x9b0 __split_vma+0x1b8/0x280 __do_munmap+0x13c/0x550 sys_mremap+0x220/0x7e0 system_call+0x5c/0x70 Fixes: 675d995297d4 ("powerpc/book3s64: Enable split pmd ptlock.") Cc: stable@vger.kernel.org # v4.18+ Signed-off-by: Aneesh Kumar K.V Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/book3s/64/pgtable.h | 22 +++++++--------------- arch/powerpc/mm/pgtable-book3s64.c | 22 ++++++++++++++++++++++ 2 files changed, 29 insertions(+), 15 deletions(-) (limited to 'arch/powerpc') diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index 2e6ada28da64..c9bfe526ca9d 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -1258,21 +1258,13 @@ extern pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, #define pmd_move_must_withdraw pmd_move_must_withdraw struct spinlock; -static inline int pmd_move_must_withdraw(struct spinlock *new_pmd_ptl, - struct spinlock *old_pmd_ptl, - struct vm_area_struct *vma) -{ - if (radix_enabled()) - return false; - /* - * Archs like ppc64 use pgtable to store per pmd - * specific information. So when we switch the pmd, - * we should also withdraw and deposit the pgtable - */ - return true; -} - - +extern int pmd_move_must_withdraw(struct spinlock *new_pmd_ptl, + struct spinlock *old_pmd_ptl, + struct vm_area_struct *vma); +/* + * Hash translation mode use the deposited table to store hash pte + * slot information. + */ #define arch_needs_pgtable_deposit arch_needs_pgtable_deposit static inline bool arch_needs_pgtable_deposit(void) { diff --git a/arch/powerpc/mm/pgtable-book3s64.c b/arch/powerpc/mm/pgtable-book3s64.c index f3c31f5e1026..ecd31569a120 100644 --- a/arch/powerpc/mm/pgtable-book3s64.c +++ b/arch/powerpc/mm/pgtable-book3s64.c @@ -400,3 +400,25 @@ void arch_report_meminfo(struct seq_file *m) atomic_long_read(&direct_pages_count[MMU_PAGE_1G]) << 20); } #endif /* CONFIG_PROC_FS */ + +/* + * For hash translation mode, we use the deposited table to store hash slot + * information and they are stored at PTRS_PER_PMD offset from related pmd + * location. Hence a pmd move requires deposit and withdraw. + * + * For radix translation with split pmd ptl, we store the deposited table in the + * pmd page. Hence if we have different pmd page we need to withdraw during pmd + * move. + * + * With hash we use deposited table always irrespective of anon or not. + * With radix we use deposited table only for anonymous mapping. + */ +int pmd_move_must_withdraw(struct spinlock *new_pmd_ptl, + struct spinlock *old_pmd_ptl, + struct vm_area_struct *vma) +{ + if (radix_enabled()) + return (new_pmd_ptl != old_pmd_ptl) && vma_is_anonymous(vma); + + return true; +} -- cgit From 5a3840a470c41ec0b85cd36ca80370330656b163 Mon Sep 17 00:00:00 2001 From: Oliver O'Halloran Date: Thu, 31 Jan 2019 12:53:47 +1100 Subject: powerpc/papr_scm: Use the correct bind address When binding an SCM volume to a physical address the hypervisor has the option to return early with a continue token with the expectation that the guest will resume the bind operation until it completes. A quirk of this interface is that the bind address will only be returned by the first bind h-call and the subsequent calls will return 0xFFFF_FFFF_FFFF_FFFF for the bind address. We currently do not save the address returned by the first h-call. As a result we will use the junk address as the base of the bound region if the hypervisor decides to split the bind across multiple h-calls. This bug was found when testing with very large SCM volumes where the bind process would take more time than they hypervisor's internal h-call time limit would allow. This patch fixes the issue by saving the bind address from the first call. Cc: stable@vger.kernel.org Fixes: b5beae5e224f ("powerpc/pseries: Add driver for PAPR SCM regions") Signed-off-by: Oliver O'Halloran Signed-off-by: Michael Ellerman --- arch/powerpc/platforms/pseries/papr_scm.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'arch/powerpc') diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c index 7d6457ab5d34..bba281b1fe1b 100644 --- a/arch/powerpc/platforms/pseries/papr_scm.c +++ b/arch/powerpc/platforms/pseries/papr_scm.c @@ -43,6 +43,7 @@ static int drc_pmem_bind(struct papr_scm_priv *p) { unsigned long ret[PLPAR_HCALL_BUFSIZE]; uint64_t rc, token; + uint64_t saved = 0; /* * When the hypervisor cannot map all the requested memory in a single @@ -56,6 +57,8 @@ static int drc_pmem_bind(struct papr_scm_priv *p) rc = plpar_hcall(H_SCM_BIND_MEM, ret, p->drc_index, 0, p->blocks, BIND_ANY_ADDR, token); token = ret[0]; + if (!saved) + saved = ret[1]; cond_resched(); } while (rc == H_BUSY); @@ -64,7 +67,7 @@ static int drc_pmem_bind(struct papr_scm_priv *p) return -ENXIO; } - p->bound_addr = ret[1]; + p->bound_addr = saved; dev_dbg(&p->pdev->dev, "bound drc %x to %pR\n", p->drc_index, &p->res); -- cgit From a58007621be33e9f7c7bed5d5ff8ecb914e1044a Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Thu, 14 Feb 2019 15:00:36 +1100 Subject: powerpc/64s: Fix possible corruption on big endian due to pgd/pud_present() In v4.20 we changed our pgd/pud_present() to check for _PAGE_PRESENT rather than just checking that the value is non-zero, e.g.: static inline int pgd_present(pgd_t pgd) { - return !pgd_none(pgd); + return (pgd_raw(pgd) & cpu_to_be64(_PAGE_PRESENT)); } Unfortunately this is broken on big endian, as the result of the bitwise & is truncated to int, which is always zero because _PAGE_PRESENT is 0x8000000000000000ul. This means pgd_present() and pud_present() are always false at compile time, and the compiler elides the subsequent code. Remarkably with that bug present we are still able to boot and run with few noticeable effects. However under some work loads we are able to trigger a warning in the ext4 code: WARNING: CPU: 11 PID: 29593 at fs/ext4/inode.c:3927 .ext4_set_page_dirty+0x70/0xb0 CPU: 11 PID: 29593 Comm: debugedit Not tainted 4.20.0-rc1 #1 ... NIP .ext4_set_page_dirty+0x70/0xb0 LR .set_page_dirty+0xa0/0x150 Call Trace: .set_page_dirty+0xa0/0x150 .unmap_page_range+0xbf0/0xe10 .unmap_vmas+0x84/0x130 .unmap_region+0xe8/0x190 .__do_munmap+0x2f0/0x510 .__vm_munmap+0x80/0x110 .__se_sys_munmap+0x14/0x30 system_call+0x5c/0x70 The fix is simple, we need to convert the result of the bitwise & to an int before returning it. Thanks to Erhard, Jan Kara and Aneesh for help with debugging. Fixes: da7ad366b497 ("powerpc/mm/book3s: Update pmd_present to look at _PAGE_PRESENT bit") Cc: stable@vger.kernel.org # v4.20+ Reported-by: Erhard F. Reviewed-by: Aneesh Kumar K.V Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/book3s/64/pgtable.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/powerpc') diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index c9bfe526ca9d..d8c8d7c9df15 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -904,7 +904,7 @@ static inline int pud_none(pud_t pud) static inline int pud_present(pud_t pud) { - return (pud_raw(pud) & cpu_to_be64(_PAGE_PRESENT)); + return !!(pud_raw(pud) & cpu_to_be64(_PAGE_PRESENT)); } extern struct page *pud_page(pud_t pud); @@ -951,7 +951,7 @@ static inline int pgd_none(pgd_t pgd) static inline int pgd_present(pgd_t pgd) { - return (pgd_raw(pgd) & cpu_to_be64(_PAGE_PRESENT)); + return !!(pgd_raw(pgd) & cpu_to_be64(_PAGE_PRESENT)); } static inline pte_t pgd_pte(pgd_t pgd) -- cgit From 8f5b27347e88b171c755562f0090ce40e514fc00 Mon Sep 17 00:00:00 2001 From: Alexey Kardashevskiy Date: Mon, 18 Feb 2019 16:58:01 +1100 Subject: powerpc/powernv/sriov: Register IOMMU groups for VFs The compound IOMMU group rework moved iommu_register_group() together in pnv_pci_ioda_setup_iommu_api() (which is a part of ppc_md.pcibios_fixup). As the result, pnv_ioda_setup_bus_iommu_group() does not create groups any more, it only adds devices to groups. This works fine for boot time devices. However IOMMU groups for SRIOV's VFs were added by pnv_ioda_setup_bus_iommu_group() so this got broken: pnv_tce_iommu_bus_notifier() expects a group to be registered for VF and it is not. This adds missing group registration and adds a NULL pointer check into the bus notifier so we won't crash if there is no group, although it is not expected to happen now because of the change above. Example oops seen prior to this patch: $ echo 1 > /sys/bus/pci/devices/0000\:01\:00.0/sriov_numvfs Unable to handle kernel paging request for data at address 0x00000030 Faulting instruction address: 0xc0000000004a6018 Oops: Kernel access of bad area, sig: 11 [#1] LE SMP NR_CPUS=2048 NUMA PowerNV CPU: 46 PID: 7006 Comm: bash Not tainted 4.15-ish NIP: c0000000004a6018 LR: c0000000004a6014 CTR: 0000000000000000 REGS: c000008fc876b400 TRAP: 0300 Not tainted (4.15-ish) MSR: 900000000280b033 CFAR: c000000000d0be20 DAR: 0000000000000030 DSISR: 40000000 SOFTE: 1 ... NIP sysfs_do_create_link_sd.isra.0+0x68/0x150 LR sysfs_do_create_link_sd.isra.0+0x64/0x150 Call Trace: pci_dev_type+0x0/0x30 (unreliable) iommu_group_add_device+0x8c/0x600 iommu_add_device+0xe8/0x180 pnv_tce_iommu_bus_notifier+0xb0/0xf0 notifier_call_chain+0x9c/0x110 blocking_notifier_call_chain+0x64/0xa0 device_add+0x524/0x7d0 pci_device_add+0x248/0x450 pci_iov_add_virtfn+0x294/0x3e0 pci_enable_sriov+0x43c/0x580 mlx5_core_sriov_configure+0x15c/0x2f0 [mlx5_core] sriov_numvfs_store+0x180/0x240 dev_attr_store+0x3c/0x60 sysfs_kf_write+0x64/0x90 kernfs_fop_write+0x1ac/0x240 __vfs_write+0x3c/0x70 vfs_write+0xd8/0x220 SyS_write+0x6c/0x110 system_call+0x58/0x6c Fixes: 0bd971676e68 ("powerpc/powernv/npu: Add compound IOMMU groups") Signed-off-by: Alexey Kardashevskiy Reported-by: Santwana Samantray Signed-off-by: Michael Ellerman --- arch/powerpc/platforms/powernv/pci-ioda.c | 2 ++ arch/powerpc/platforms/powernv/pci.c | 2 ++ 2 files changed, 4 insertions(+) (limited to 'arch/powerpc') diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 7db3119f8a5b..145373f0e5dc 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -1593,6 +1593,8 @@ static void pnv_ioda_setup_vf_PE(struct pci_dev *pdev, u16 num_vfs) pnv_pci_ioda2_setup_dma_pe(phb, pe); #ifdef CONFIG_IOMMU_API + iommu_register_group(&pe->table_group, + pe->phb->hose->global_number, pe->pe_number); pnv_ioda_setup_bus_iommu_group(pe, &pe->table_group, NULL); #endif } diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c index 45fb70b4bfa7..ef9448a907c6 100644 --- a/arch/powerpc/platforms/powernv/pci.c +++ b/arch/powerpc/platforms/powernv/pci.c @@ -1147,6 +1147,8 @@ static int pnv_tce_iommu_bus_notifier(struct notifier_block *nb, return 0; pe = &phb->ioda.pe_array[pdn->pe_number]; + if (!pe->table_group.group) + return 0; iommu_add_device(&pe->table_group, dev); return 0; case BUS_NOTIFY_DEL_DEVICE: -- cgit