From ef7d9593390a050c50eba5fc02d2cb65a1104434 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Mon, 11 Sep 2023 08:39:04 -0700 Subject: xfs: remove CPU hotplug infrastructure There are no users of the cpu hotplug hooks in xfs now, so remove it. This reverts f1653c2e2831e ("xfs: introduce CPU hotplug infrastructure"). Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- include/linux/cpuhotplug.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 06dda85f0424..068f7738be22 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -90,7 +90,6 @@ enum cpuhp_state { CPUHP_FS_BUFF_DEAD, CPUHP_PRINTK_DEAD, CPUHP_MM_MEMCQ_DEAD, - CPUHP_XFS_DEAD, CPUHP_PERCPU_CNT_DEAD, CPUHP_RADIX_DEAD, CPUHP_PAGE_ALLOC, -- cgit v1.2.3 From 49f776724e64c27dd861e7ac8da9d42f01d9d172 Mon Sep 17 00:00:00 2001 From: Smita Koralahalli Date: Wed, 23 Aug 2023 23:43:04 +0000 Subject: PCI/AER: Export pcie_aer_is_native() Export and move the declaration of pcie_aer_is_native() to a common header file to be reused by cxl/pci module. Signed-off-by: Smita Koralahalli Acked-by: Bjorn Helgaas Reviewed-by: Kuppuswamy Sathyanarayanan Reviewed-by: Robert Richter Reviewed-by: Jonathan Cameron Reviewed-by: Dave Jiang Link: https://lore.kernel.org/r/20230823234305.27333-3-Smita.KoralahalliChannabasappa@amd.com Signed-off-by: Dan Williams --- drivers/pci/pcie/aer.c | 1 + drivers/pci/pcie/portdrv.h | 2 -- include/linux/aer.h | 2 ++ 3 files changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c index e85ff946e8c8..9c8fd69ae5ad 100644 --- a/drivers/pci/pcie/aer.c +++ b/drivers/pci/pcie/aer.c @@ -229,6 +229,7 @@ int pcie_aer_is_native(struct pci_dev *dev) return pcie_ports_native || host->native_aer; } +EXPORT_SYMBOL_NS_GPL(pcie_aer_is_native, CXL); static int pci_enable_pcie_error_reporting(struct pci_dev *dev) { diff --git a/drivers/pci/pcie/portdrv.h b/drivers/pci/pcie/portdrv.h index 58a2b1a1cae4..1f3803bde7ee 100644 --- a/drivers/pci/pcie/portdrv.h +++ b/drivers/pci/pcie/portdrv.h @@ -29,10 +29,8 @@ extern bool pcie_ports_dpc_native; #ifdef CONFIG_PCIEAER int pcie_aer_init(void); -int pcie_aer_is_native(struct pci_dev *dev); #else static inline int pcie_aer_init(void) { return 0; } -static inline int pcie_aer_is_native(struct pci_dev *dev) { return 0; } #endif #ifdef CONFIG_HOTPLUG_PCI_PCIE diff --git a/include/linux/aer.h b/include/linux/aer.h index 2dd175f5debd..29cc10220952 100644 --- a/include/linux/aer.h +++ b/include/linux/aer.h @@ -42,11 +42,13 @@ struct aer_capability_regs { #if defined(CONFIG_PCIEAER) int pci_aer_clear_nonfatal_status(struct pci_dev *dev); +int pcie_aer_is_native(struct pci_dev *dev); #else static inline int pci_aer_clear_nonfatal_status(struct pci_dev *dev) { return -EINVAL; } +static inline int pcie_aer_is_native(struct pci_dev *dev) { return 0; } #endif void cper_print_aer(struct pci_dev *dev, int aer_severity, -- cgit v1.2.3 From 373beef00f7d781a000b12c31fb17a5a9c25969c Mon Sep 17 00:00:00 2001 From: Jean-Philippe Brucker Date: Mon, 11 Sep 2023 15:52:57 +0100 Subject: KVM: arm64: nvhe: Ignore SVE hint in SMCCC function ID When SVE is enabled, the host may set bit 16 in SMCCC function IDs, a hint that indicates an unused SVE state. At the moment NVHE doesn't account for this bit when inspecting the function ID, and rejects most calls. Clear the hint bit before comparing function IDs. About version compatibility: the host's PSCI driver initially probes the firmware for a SMCCC version number. If the firmware implements a protocol recent enough (1.3), subsequent SMCCC calls have the hint bit set. Since the hint bit was reserved in earlier versions of the protocol, clearing it is fine regardless of the version in use. When a new hint is added to the protocol in the future, it will be added to ARM_SMCCC_CALL_HINTS and NVHE will handle it straight away. This patch only clears known hints and leaves reserved bits as is, because future SMCCC versions could use reserved bits as modifiers for the function ID, rather than hints. Fixes: cfa7ff959a78 ("arm64: smccc: Support SMCCC v1.3 SVE register saving hint") Reported-by: Ben Horgan Signed-off-by: Jean-Philippe Brucker Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230911145254.934414-4-jean-philippe@linaro.org --- arch/arm64/include/asm/kvm_hyp.h | 2 +- arch/arm64/kvm/hyp/include/nvhe/ffa.h | 2 +- arch/arm64/kvm/hyp/nvhe/ffa.c | 3 +-- arch/arm64/kvm/hyp/nvhe/hyp-init.S | 1 + arch/arm64/kvm/hyp/nvhe/hyp-main.c | 8 ++++++-- arch/arm64/kvm/hyp/nvhe/psci-relay.c | 3 +-- include/linux/arm-smccc.h | 2 ++ 7 files changed, 13 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h index b7238c72a04c..66efd67ea7e8 100644 --- a/arch/arm64/include/asm/kvm_hyp.h +++ b/arch/arm64/include/asm/kvm_hyp.h @@ -118,7 +118,7 @@ void deactivate_traps_vhe_put(struct kvm_vcpu *vcpu); u64 __guest_enter(struct kvm_vcpu *vcpu); -bool kvm_host_psci_handler(struct kvm_cpu_context *host_ctxt); +bool kvm_host_psci_handler(struct kvm_cpu_context *host_ctxt, u32 func_id); #ifdef __KVM_NVHE_HYPERVISOR__ void __noreturn __hyp_do_panic(struct kvm_cpu_context *host_ctxt, u64 spsr, diff --git a/arch/arm64/kvm/hyp/include/nvhe/ffa.h b/arch/arm64/kvm/hyp/include/nvhe/ffa.h index 1becb10ecd80..d9fd5e6c7d3c 100644 --- a/arch/arm64/kvm/hyp/include/nvhe/ffa.h +++ b/arch/arm64/kvm/hyp/include/nvhe/ffa.h @@ -12,6 +12,6 @@ #define FFA_MAX_FUNC_NUM 0x7F int hyp_ffa_init(void *pages); -bool kvm_host_ffa_handler(struct kvm_cpu_context *host_ctxt); +bool kvm_host_ffa_handler(struct kvm_cpu_context *host_ctxt, u32 func_id); #endif /* __KVM_HYP_FFA_H */ diff --git a/arch/arm64/kvm/hyp/nvhe/ffa.c b/arch/arm64/kvm/hyp/nvhe/ffa.c index ab4f5d160c58..6e4dba9eadef 100644 --- a/arch/arm64/kvm/hyp/nvhe/ffa.c +++ b/arch/arm64/kvm/hyp/nvhe/ffa.c @@ -634,9 +634,8 @@ out_handled: return true; } -bool kvm_host_ffa_handler(struct kvm_cpu_context *host_ctxt) +bool kvm_host_ffa_handler(struct kvm_cpu_context *host_ctxt, u32 func_id) { - DECLARE_REG(u64, func_id, host_ctxt, 0); struct arm_smccc_res res; /* diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-init.S b/arch/arm64/kvm/hyp/nvhe/hyp-init.S index 90fade1b032e..1cc06e6797bd 100644 --- a/arch/arm64/kvm/hyp/nvhe/hyp-init.S +++ b/arch/arm64/kvm/hyp/nvhe/hyp-init.S @@ -57,6 +57,7 @@ __do_hyp_init: cmp x0, #HVC_STUB_HCALL_NR b.lo __kvm_handle_stub_hvc + bic x0, x0, #ARM_SMCCC_CALL_HINTS mov x3, #KVM_HOST_SMCCC_FUNC(__kvm_hyp_init) cmp x0, x3 b.eq 1f diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c index 857d9bc04fd4..2385fd03ed87 100644 --- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c +++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c @@ -368,6 +368,7 @@ static void handle_host_hcall(struct kvm_cpu_context *host_ctxt) if (static_branch_unlikely(&kvm_protected_mode_initialized)) hcall_min = __KVM_HOST_SMCCC_FUNC___pkvm_prot_finalize; + id &= ~ARM_SMCCC_CALL_HINTS; id -= KVM_HOST_SMCCC_ID(0); if (unlikely(id < hcall_min || id >= ARRAY_SIZE(host_hcall))) @@ -392,11 +393,14 @@ static void default_host_smc_handler(struct kvm_cpu_context *host_ctxt) static void handle_host_smc(struct kvm_cpu_context *host_ctxt) { + DECLARE_REG(u64, func_id, host_ctxt, 0); bool handled; - handled = kvm_host_psci_handler(host_ctxt); + func_id &= ~ARM_SMCCC_CALL_HINTS; + + handled = kvm_host_psci_handler(host_ctxt, func_id); if (!handled) - handled = kvm_host_ffa_handler(host_ctxt); + handled = kvm_host_ffa_handler(host_ctxt, func_id); if (!handled) default_host_smc_handler(host_ctxt); diff --git a/arch/arm64/kvm/hyp/nvhe/psci-relay.c b/arch/arm64/kvm/hyp/nvhe/psci-relay.c index 24543d2a3490..d57bcb6ab94d 100644 --- a/arch/arm64/kvm/hyp/nvhe/psci-relay.c +++ b/arch/arm64/kvm/hyp/nvhe/psci-relay.c @@ -273,9 +273,8 @@ static unsigned long psci_1_0_handler(u64 func_id, struct kvm_cpu_context *host_ } } -bool kvm_host_psci_handler(struct kvm_cpu_context *host_ctxt) +bool kvm_host_psci_handler(struct kvm_cpu_context *host_ctxt, u32 func_id) { - DECLARE_REG(u64, func_id, host_ctxt, 0); unsigned long ret; switch (kvm_host_psci_config.version) { diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h index 7c67c17321d4..083f85653716 100644 --- a/include/linux/arm-smccc.h +++ b/include/linux/arm-smccc.h @@ -67,6 +67,8 @@ #define ARM_SMCCC_VERSION_1_3 0x10003 #define ARM_SMCCC_1_3_SVE_HINT 0x10000 +#define ARM_SMCCC_CALL_HINTS ARM_SMCCC_1_3_SVE_HINT + #define ARM_SMCCC_VERSION_FUNC_ID \ ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ -- cgit v1.2.3 From d57125b55a292a8e74a1fb17182576a3b2b2e795 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Mon, 18 Sep 2023 10:44:08 +0200 Subject: Revert "ceph: make members in struct ceph_mds_request_args_ext a union" This reverts commit 3af5ae22030cb59fab4fba35f5a2b62f47e14df9. ceph_mds_request_args_ext was already (and remains to be) a union. An additional anonymous union inside is bogus: union ceph_mds_request_args_ext { union { union ceph_mds_request_args old; struct { ... } __attribute__ ((packed)) setattr_ext; }; } Signed-off-by: Ilya Dryomov Reviewed-by: Xiubo Li --- include/linux/ceph/ceph_fs.h | 24 +++++++++++------------- 1 file changed, 11 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h index 5f2301ee88bc..f3b3593254b9 100644 --- a/include/linux/ceph/ceph_fs.h +++ b/include/linux/ceph/ceph_fs.h @@ -467,19 +467,17 @@ union ceph_mds_request_args { } __attribute__ ((packed)); union ceph_mds_request_args_ext { - union { - union ceph_mds_request_args old; - struct { - __le32 mode; - __le32 uid; - __le32 gid; - struct ceph_timespec mtime; - struct ceph_timespec atime; - __le64 size, old_size; /* old_size needed by truncate */ - __le32 mask; /* CEPH_SETATTR_* */ - struct ceph_timespec btime; - } __attribute__ ((packed)) setattr_ext; - }; + union ceph_mds_request_args old; + struct { + __le32 mode; + __le32 uid; + __le32 gid; + struct ceph_timespec mtime; + struct ceph_timespec atime; + __le64 size, old_size; /* old_size needed by truncate */ + __le32 mask; /* CEPH_SETATTR_* */ + struct ceph_timespec btime; + } __attribute__ ((packed)) setattr_ext; }; #define CEPH_MDS_FLAG_REPLAY 1 /* this is a replayed op */ -- cgit v1.2.3 From 9ea9cb00a82b53ec39630eac718776d37e41b35a Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Thu, 14 Sep 2023 11:21:39 -0400 Subject: mm: memcontrol: fix GFP_NOFS recursion in memory.high enforcement Breno and Josef report a deadlock scenario from cgroup reclaim re-entering the filesystem: [ 361.546690] ====================================================== [ 361.559210] WARNING: possible circular locking dependency detected [ 361.571703] 6.5.0-0_fbk700_debug_rc0_kbuilder_13159_gbf787a128001 #1 Tainted: G S E [ 361.589704] ------------------------------------------------------ [ 361.602277] find/9315 is trying to acquire lock: [ 361.611625] ffff88837ba140c0 (&delayed_node->mutex){+.+.}-{4:4}, at: __btrfs_release_delayed_node+0x68/0x4f0 [ 361.631437] [ 361.631437] but task is already holding lock: [ 361.643243] ffff8881765b8678 (btrfs-tree-01){++++}-{4:4}, at: btrfs_tree_read_lock+0x1e/0x40 [ 362.904457] mutex_lock_nested+0x1c/0x30 [ 362.912414] __btrfs_release_delayed_node+0x68/0x4f0 [ 362.922460] btrfs_evict_inode+0x301/0x770 [ 362.982726] evict+0x17c/0x380 [ 362.988944] prune_icache_sb+0x100/0x1d0 [ 363.005559] super_cache_scan+0x1f8/0x260 [ 363.013695] do_shrink_slab+0x2a2/0x540 [ 363.021489] shrink_slab_memcg+0x237/0x3d0 [ 363.050606] shrink_slab+0xa7/0x240 [ 363.083382] shrink_node_memcgs+0x262/0x3b0 [ 363.091870] shrink_node+0x1a4/0x720 [ 363.099150] shrink_zones+0x1f6/0x5d0 [ 363.148798] do_try_to_free_pages+0x19b/0x5e0 [ 363.157633] try_to_free_mem_cgroup_pages+0x266/0x370 [ 363.190575] reclaim_high+0x16f/0x1f0 [ 363.208409] mem_cgroup_handle_over_high+0x10b/0x270 [ 363.246678] try_charge_memcg+0xaf2/0xc70 [ 363.304151] charge_memcg+0xf0/0x350 [ 363.320070] __mem_cgroup_charge+0x28/0x40 [ 363.328371] __filemap_add_folio+0x870/0xd50 [ 363.371303] filemap_add_folio+0xdd/0x310 [ 363.399696] __filemap_get_folio+0x2fc/0x7d0 [ 363.419086] pagecache_get_page+0xe/0x30 [ 363.427048] alloc_extent_buffer+0x1cd/0x6a0 [ 363.435704] read_tree_block+0x43/0xc0 [ 363.443316] read_block_for_search+0x361/0x510 [ 363.466690] btrfs_search_slot+0xc8c/0x1520 This is caused by the mem_cgroup_handle_over_high() not respecting the gfp_mask of the allocation context. We used to only call this function on resume to userspace, where no locks were held. But c9afe31ec443 ("memcg: synchronously enforce memory.high for large overcharges") added a call from the allocation context without considering the gfp. Link: https://lkml.kernel.org/r/20230914152139.100822-1-hannes@cmpxchg.org Fixes: c9afe31ec443 ("memcg: synchronously enforce memory.high for large overcharges") Signed-off-by: Johannes Weiner Reported-by: Breno Leitao Reported-by: Josef Bacik Acked-by: Shakeel Butt Acked-by: Michal Hocko Cc: Roman Gushchin Cc: Muchun Song Cc: [5.17+] Signed-off-by: Andrew Morton --- include/linux/memcontrol.h | 4 ++-- include/linux/resume_user_mode.h | 2 +- mm/memcontrol.c | 6 +++--- 3 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index ab94ad4597d0..e4e24da16d2c 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -920,7 +920,7 @@ unsigned long mem_cgroup_get_zone_lru_size(struct lruvec *lruvec, return READ_ONCE(mz->lru_zone_size[zone_idx][lru]); } -void mem_cgroup_handle_over_high(void); +void mem_cgroup_handle_over_high(gfp_t gfp_mask); unsigned long mem_cgroup_get_max(struct mem_cgroup *memcg); @@ -1458,7 +1458,7 @@ static inline void mem_cgroup_unlock_pages(void) rcu_read_unlock(); } -static inline void mem_cgroup_handle_over_high(void) +static inline void mem_cgroup_handle_over_high(gfp_t gfp_mask) { } diff --git a/include/linux/resume_user_mode.h b/include/linux/resume_user_mode.h index 285189454449..f8f3e958e9cf 100644 --- a/include/linux/resume_user_mode.h +++ b/include/linux/resume_user_mode.h @@ -55,7 +55,7 @@ static inline void resume_user_mode_work(struct pt_regs *regs) } #endif - mem_cgroup_handle_over_high(); + mem_cgroup_handle_over_high(GFP_KERNEL); blkcg_maybe_throttle_current(); rseq_handle_notify_resume(NULL, regs); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index a4d3282493b6..d13dde2f8b56 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2555,7 +2555,7 @@ static unsigned long calculate_high_delay(struct mem_cgroup *memcg, * Scheduled by try_charge() to be executed from the userland return path * and reclaims memory over the high limit. */ -void mem_cgroup_handle_over_high(void) +void mem_cgroup_handle_over_high(gfp_t gfp_mask) { unsigned long penalty_jiffies; unsigned long pflags; @@ -2583,7 +2583,7 @@ retry_reclaim: */ nr_reclaimed = reclaim_high(memcg, in_retry ? SWAP_CLUSTER_MAX : nr_pages, - GFP_KERNEL); + gfp_mask); /* * memory.high is breached and reclaim is unable to keep up. Throttle @@ -2819,7 +2819,7 @@ done_restock: if (current->memcg_nr_pages_over_high > MEMCG_CHARGE_BATCH && !(current->flags & PF_MEMALLOC) && gfpflags_allow_blocking(gfp_mask)) { - mem_cgroup_handle_over_high(); + mem_cgroup_handle_over_high(gfp_mask); } return 0; } -- cgit v1.2.3 From b724a6418f1f853bcb39c8923bf14a50c7bdbd07 Mon Sep 17 00:00:00 2001 From: Leon Hwang Date: Sun, 17 Sep 2023 23:38:46 +0800 Subject: bpf: Fix tr dereferencing Fix 'tr' dereferencing bug when CONFIG_BPF_JIT is turned off. When CONFIG_BPF_JIT is turned off, 'bpf_trampoline_get()' returns NULL, which is same as the cases when CONFIG_BPF_JIT is turned on. Closes: https://lore.kernel.org/r/202309131936.5Nc8eUD0-lkp@intel.com/ Fixes: f7b12b6fea00 ("bpf: verifier: refactor check_attach_btf_id()") Reported-by: kernel test robot Reported-by: Dan Carpenter Signed-off-by: Leon Hwang Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20230917153846.88732-1-hffilwlqm@gmail.com --- include/linux/bpf.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 024e8b28c34b..49f8b691496c 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1307,7 +1307,7 @@ static inline int bpf_trampoline_unlink_prog(struct bpf_tramp_link *link, static inline struct bpf_trampoline *bpf_trampoline_get(u64 key, struct bpf_attach_target_info *tgt_info) { - return ERR_PTR(-EOPNOTSUPP); + return NULL; } static inline void bpf_trampoline_put(struct bpf_trampoline *tr) {} #define DEFINE_BPF_DISPATCHER(name) -- cgit v1.2.3 From 2a86f1b56a30e242caf7ee1268af68f4f49ce847 Mon Sep 17 00:00:00 2001 From: Huacai Chen Date: Wed, 20 Sep 2023 14:26:29 +0800 Subject: kasan: Cleanup the __HAVE_ARCH_SHADOW_MAP usage As Linus suggested, __HAVE_ARCH_XYZ is "stupid" and "having historical uses of it doesn't make it good". So migrate __HAVE_ARCH_SHADOW_MAP to separate macros named after the respective functions. Suggested-by: Linus Torvalds Reviewed-by: WANG Xuerui Reviewed-by: Andrey Konovalov Signed-off-by: Huacai Chen --- arch/loongarch/include/asm/kasan.h | 10 ++++++++-- include/linux/kasan.h | 2 +- mm/kasan/kasan.h | 8 +++----- 3 files changed, 12 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/arch/loongarch/include/asm/kasan.h b/arch/loongarch/include/asm/kasan.h index deeff8158f45..a12ecab37da7 100644 --- a/arch/loongarch/include/asm/kasan.h +++ b/arch/loongarch/include/asm/kasan.h @@ -10,8 +10,6 @@ #include #include -#define __HAVE_ARCH_SHADOW_MAP - #define KASAN_SHADOW_SCALE_SHIFT 3 #define KASAN_SHADOW_OFFSET _AC(CONFIG_KASAN_SHADOW_OFFSET, UL) @@ -68,6 +66,7 @@ static __always_inline bool kasan_arch_is_ready(void) return !kasan_early_stage; } +#define kasan_mem_to_shadow kasan_mem_to_shadow static inline void *kasan_mem_to_shadow(const void *addr) { if (!kasan_arch_is_ready()) { @@ -97,6 +96,7 @@ static inline void *kasan_mem_to_shadow(const void *addr) } } +#define kasan_shadow_to_mem kasan_shadow_to_mem static inline const void *kasan_shadow_to_mem(const void *shadow_addr) { unsigned long addr = (unsigned long)shadow_addr; @@ -119,6 +119,12 @@ static inline const void *kasan_shadow_to_mem(const void *shadow_addr) } } +#define addr_has_metadata addr_has_metadata +static __always_inline bool addr_has_metadata(const void *addr) +{ + return (kasan_mem_to_shadow((void *)addr) != NULL); +} + void kasan_init(void); asmlinkage void kasan_early_init(void); diff --git a/include/linux/kasan.h b/include/linux/kasan.h index 3df5499f7936..842623d708c2 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -54,7 +54,7 @@ extern p4d_t kasan_early_shadow_p4d[MAX_PTRS_PER_P4D]; int kasan_populate_early_shadow(const void *shadow_start, const void *shadow_end); -#ifndef __HAVE_ARCH_SHADOW_MAP +#ifndef kasan_mem_to_shadow static inline void *kasan_mem_to_shadow(const void *addr) { return (void *)((unsigned long)addr >> KASAN_SHADOW_SCALE_SHIFT) diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h index f70e3d7a602e..d37831b8511c 100644 --- a/mm/kasan/kasan.h +++ b/mm/kasan/kasan.h @@ -291,7 +291,7 @@ struct kasan_stack_ring { #if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) -#ifndef __HAVE_ARCH_SHADOW_MAP +#ifndef kasan_shadow_to_mem static inline const void *kasan_shadow_to_mem(const void *shadow_addr) { return (void *)(((unsigned long)shadow_addr - KASAN_SHADOW_OFFSET) @@ -299,15 +299,13 @@ static inline const void *kasan_shadow_to_mem(const void *shadow_addr) } #endif +#ifndef addr_has_metadata static __always_inline bool addr_has_metadata(const void *addr) { -#ifdef __HAVE_ARCH_SHADOW_MAP - return (kasan_mem_to_shadow((void *)addr) != NULL); -#else return (kasan_reset_tag(addr) >= kasan_shadow_to_mem((void *)KASAN_SHADOW_START)); -#endif } +#endif /** * kasan_check_range - Check memory region, and report if invalid access. -- cgit v1.2.3 From 6d2779ecaeb56f92d7105c56772346c71c88c278 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Tue, 19 Sep 2023 18:14:29 +0100 Subject: locking/atomic: scripts: fix fallback ifdeffery Since commit: 9257959a6e5b4fca ("locking/atomic: scripts: restructure fallback ifdeffery") The ordering fallbacks for atomic*_read_acquire() and atomic*_set_release() erroneously fall back to the implictly relaxed atomic*_read() and atomic*_set() variants respectively, without any additional barriers. This loses the ACQUIRE and RELEASE ordering semantics, which can result in a wide variety of problems, even on strongly-ordered architectures where the implementation of atomic*_read() and/or atomic*_set() allows the compiler to reorder those relative to other accesses. In practice this has been observed to break bit spinlocks on arm64, resulting in dentry cache corruption. The fallback logic was intended to allow ACQUIRE/RELEASE/RELAXED ops to be defined in terms of FULL ops, but where an op had RELAXED ordering by default, this unintentionally permitted the ACQUIRE/RELEASE ops to be defined in terms of the implicitly RELAXED default. This patch corrects the logic to avoid falling back to implicitly RELAXED ops, resulting in the same behaviour as prior to commit 9257959a6e5b4fca. I've verified the resulting assembly on arm64 by generating outlined wrappers of the atomics. Prior to this patch the compiler generates sequences using relaxed load (LDR) and store (STR) instructions, e.g. | : | ldr x0, [x0] | ret | | : | str x1, [x0] | ret With this patch applied the compiler generates sequences using the intended load-acquire (LDAR) and store-release (STLR) instructions, e.g. | : | ldar x0, [x0] | ret | | : | stlr x1, [x0] | ret To make sure that there were no other victims of the ifdeffery rewrite, I generated outlined copies of all of the {atomic,atomic64,atomic_long} atomic operations before and after commit 9257959a6e5b4fca. A diff of the generated assembly on arm64 shows that only the read_acquire() and set_release() operations were changed, and only lost their intended ordering: | [mark@lakrids:~/src/linux]% diff -u \ | <(aarch64-linux-gnu-objdump -d before-9257959a6e5b4fca.o) | <(aarch64-linux-gnu-objdump -d after-9257959a6e5b4fca.o) | --- /proc/self/fd/11 2023-09-19 16:51:51.114779415 +0100 | +++ /proc/self/fd/16 2023-09-19 16:51:51.114779415 +0100 | @@ -1,5 +1,5 @@ | | -before-9257959a6e5b4fca.o: file format elf64-littleaarch64 | +after-9257959a6e5b4fca.o: file format elf64-littleaarch64 | | | Disassembly of section .text: | @@ -9,7 +9,7 @@ | 4: d65f03c0 ret | | 0000000000000008 : | - 8: 88dffc00 ldar w0, [x0] | + 8: b9400000 ldr w0, [x0] | c: d65f03c0 ret | | 0000000000000010 : | @@ -17,7 +17,7 @@ | 14: d65f03c0 ret | | 0000000000000018 : | - 18: 889ffc01 stlr w1, [x0] | + 18: b9000001 str w1, [x0] | 1c: d65f03c0 ret | | 0000000000000020 : | @@ -1230,7 +1230,7 @@ | 1070: d65f03c0 ret | | 0000000000001074 : | - 1074: c8dffc00 ldar x0, [x0] | + 1074: f9400000 ldr x0, [x0] | 1078: d65f03c0 ret | | 000000000000107c : | @@ -1238,7 +1238,7 @@ | 1080: d65f03c0 ret | | 0000000000001084 : | - 1084: c89ffc01 stlr x1, [x0] | + 1084: f9000001 str x1, [x0] | 1088: d65f03c0 ret | | 000000000000108c : | @@ -2427,7 +2427,7 @@ | 207c: d65f03c0 ret | | 0000000000002080 : | - 2080: c8dffc00 ldar x0, [x0] | + 2080: f9400000 ldr x0, [x0] | 2084: d65f03c0 ret | | 0000000000002088 : | @@ -2435,7 +2435,7 @@ | 208c: d65f03c0 ret | | 0000000000002090 : | - 2090: c89ffc01 stlr x1, [x0] | + 2090: f9000001 str x1, [x0] | 2094: d65f03c0 ret | | 0000000000002098 : I've build tested this with a variety of configs for alpha, arm, arm64, csky, i386, m68k, microblaze, mips, nios2, openrisc, powerpc, riscv, s390, sh, sparc, x86_64, and xtensa, for which I've seen no issues. I was unable to build test for ia64 and parisc due to existing build breakage in v6.6-rc2. Fixes: 9257959a6e5b4fca ("locking/atomic: scripts: restructure fallback ifdeffery") Reported-by: Ming Lei Reported-by: Darrick J. Wong Signed-off-by: Mark Rutland Signed-off-by: Peter Zijlstra (Intel) Tested-by: Baokun Li Link: https://lkml.kernel.org/r/20230919171430.2697727-1-mark.rutland@arm.com --- include/linux/atomic/atomic-arch-fallback.h | 10 +--------- scripts/atomic/gen-atomic-fallback.sh | 2 +- 2 files changed, 2 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/atomic/atomic-arch-fallback.h b/include/linux/atomic/atomic-arch-fallback.h index 18f5744dfb5d..b83ef19da13d 100644 --- a/include/linux/atomic/atomic-arch-fallback.h +++ b/include/linux/atomic/atomic-arch-fallback.h @@ -459,8 +459,6 @@ raw_atomic_read_acquire(const atomic_t *v) { #if defined(arch_atomic_read_acquire) return arch_atomic_read_acquire(v); -#elif defined(arch_atomic_read) - return arch_atomic_read(v); #else int ret; @@ -508,8 +506,6 @@ raw_atomic_set_release(atomic_t *v, int i) { #if defined(arch_atomic_set_release) arch_atomic_set_release(v, i); -#elif defined(arch_atomic_set) - arch_atomic_set(v, i); #else if (__native_word(atomic_t)) { smp_store_release(&(v)->counter, i); @@ -2575,8 +2571,6 @@ raw_atomic64_read_acquire(const atomic64_t *v) { #if defined(arch_atomic64_read_acquire) return arch_atomic64_read_acquire(v); -#elif defined(arch_atomic64_read) - return arch_atomic64_read(v); #else s64 ret; @@ -2624,8 +2618,6 @@ raw_atomic64_set_release(atomic64_t *v, s64 i) { #if defined(arch_atomic64_set_release) arch_atomic64_set_release(v, i); -#elif defined(arch_atomic64_set) - arch_atomic64_set(v, i); #else if (__native_word(atomic64_t)) { smp_store_release(&(v)->counter, i); @@ -4657,4 +4649,4 @@ raw_atomic64_dec_if_positive(atomic64_t *v) } #endif /* _LINUX_ATOMIC_FALLBACK_H */ -// 202b45c7db600ce36198eb1f1fc2c2d5268ace2d +// 2fdd6702823fa842f9cea57a002e6e4476ae780c diff --git a/scripts/atomic/gen-atomic-fallback.sh b/scripts/atomic/gen-atomic-fallback.sh index c0c8a85d7c81..a45154cefa48 100755 --- a/scripts/atomic/gen-atomic-fallback.sh +++ b/scripts/atomic/gen-atomic-fallback.sh @@ -102,7 +102,7 @@ gen_proto_order_variant() fi # Allow ACQUIRE/RELEASE/RELAXED ops to be defined in terms of FULL ops - if [ ! -z "${order}" ]; then + if [ ! -z "${order}" ] && ! meta_is_implicitly_relaxed "${meta}"; then printf "#elif defined(arch_${basename})\n" printf "\t${retstmt}arch_${basename}(${args});\n" fi -- cgit v1.2.3 From 41b43b6c6e30a832c790b010a06772e793bca193 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Wed, 20 Sep 2023 12:46:27 +0200 Subject: locking/seqlock: Do the lockdep annotation before locking in do_write_seqcount_begin_nested() It was brought up by Tetsuo that the following sequence: write_seqlock_irqsave() printk_deferred_enter() could lead to a deadlock if the lockdep annotation within write_seqlock_irqsave() triggers. The problem is that the sequence counter is incremented before the lockdep annotation is performed. The lockdep splat would then attempt to invoke printk() but the reader side, of the same seqcount, could have a tty_port::lock acquired waiting for the sequence number to become even again. The other lockdep annotations come before the actual locking because "we want to see the locking error before it happens". There is no reason why seqcount should be different here. Do the lockdep annotation first then perform the locking operation (the sequence increment). Fixes: 1ca7d67cf5d5a ("seqcount: Add lockdep functionality to seqcount/seqlock structures") Reported-by: Tetsuo Handa Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20230920104627._DTHgPyA@linutronix.de Closes: https://lore.kernel.org/20230621130641.-5iueY1I@linutronix.de --- include/linux/seqlock.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h index 987a59d977c5..e9bd2f65d7f4 100644 --- a/include/linux/seqlock.h +++ b/include/linux/seqlock.h @@ -512,8 +512,8 @@ do { \ static inline void do_write_seqcount_begin_nested(seqcount_t *s, int subclass) { - do_raw_write_seqcount_begin(s); seqcount_acquire(&s->dep_map, subclass, 0, _RET_IP_); + do_raw_write_seqcount_begin(s); } /** -- cgit v1.2.3 From 753a4d531bc518633ea88ac0ed02b25a16823d51 Mon Sep 17 00:00:00 2001 From: Matthias Schiffer Date: Fri, 22 Sep 2023 22:55:16 +0200 Subject: ata: libata-sata: increase PMP SRST timeout to 10s On certain SATA controllers, softreset fails after wakeup from S2RAM with the message "softreset failed (1st FIS failed)", sometimes resulting in drives not being detected again. With the increased timeout, this issue is avoided. Instead, "softreset failed (device not ready)" is now logged 1-2 times; this later failure seems to cause fewer problems however, and the drives are detected reliably once they've spun up and the probe is retried. The issue was observed with the primary SATA controller of the QNAP TS-453B, which is an "Intel Corporation Celeron/Pentium Silver Processor SATA Controller [8086:31e3] (rev 06)" integrated in the Celeron J4125 CPU, and the following drives: - Seagate IronWolf ST12000VN0008 - Seagate IronWolf ST8000NE0004 The SATA controller seems to be more relevant to this issue than the drives, as the same drives are always detected reliably on the secondary SATA controller on the same board (an ASMedia 106x) without any "softreset failed" errors even without the increased timeout. Fixes: e7d3ef13d52a ("libata: change drive ready wait after hard reset to 5s") Cc: stable@vger.kernel.org Signed-off-by: Matthias Schiffer Signed-off-by: Damien Le Moal --- include/linux/libata.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index bf4913f4d7ac..84aca8c44fa3 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -259,7 +259,7 @@ enum { * advised to wait only for the following duration before * doing SRST. */ - ATA_TMOUT_PMP_SRST_WAIT = 5000, + ATA_TMOUT_PMP_SRST_WAIT = 10000, /* When the LPM policy is set to ATA_LPM_MAX_POWER, there might * be a spurious PHY event, so ignore the first PHY event that -- cgit v1.2.3 From 2d5780bbef8dbe6375d481cbea212606a80e4453 Mon Sep 17 00:00:00 2001 From: Petr Tesarik Date: Tue, 26 Sep 2023 20:55:56 +0200 Subject: swiotlb: fix the check whether a device has used software IO TLB When CONFIG_SWIOTLB_DYNAMIC=y, devices which do not use the software IO TLB can avoid swiotlb lookup. A flag is added by commit 1395706a1490 ("swiotlb: search the software IO TLB only if the device makes use of it"), the flag is correctly set, but it is then never checked. Add the actual check here. Note that this code is an alternative to the default pool check, not an additional check, because: 1. swiotlb_find_pool() also searches the default pool; 2. if dma_uses_io_tlb is false, the default swiotlb pool is not used. Tested in a KVM guest against a QEMU RAM-backed SATA disk over virtio and *not* using software IO TLB, this patch increases IOPS by approx 2% for 4-way parallel I/O. The write memory barrier in swiotlb_dyn_alloc() is not needed, because a newly allocated pool must always be observed by swiotlb_find_slots() before an address from that pool is passed to is_swiotlb_buffer(). Correctness was verified using the following litmus test: C swiotlb-new-pool (* * Result: Never * * Check that a newly allocated pool is always visible when the * corresponding swiotlb buffer is visible. *) { mem_pools = default; } P0(int **mem_pools, int *pool) { /* add_mem_pool() */ WRITE_ONCE(*pool, 999); rcu_assign_pointer(*mem_pools, pool); } P1(int **mem_pools, int *flag, int *buf) { /* swiotlb_find_slots() */ int *r0; int r1; rcu_read_lock(); r0 = READ_ONCE(*mem_pools); r1 = READ_ONCE(*r0); rcu_read_unlock(); if (r1) { WRITE_ONCE(*flag, 1); smp_mb(); } /* device driver (presumed) */ WRITE_ONCE(*buf, r1); } P2(int **mem_pools, int *flag, int *buf) { /* device driver (presumed) */ int r0 = READ_ONCE(*buf); /* is_swiotlb_buffer() */ int r1; int *r2; int r3; smp_rmb(); r1 = READ_ONCE(*flag); if (r1) { /* swiotlb_find_pool() */ rcu_read_lock(); r2 = READ_ONCE(*mem_pools); r3 = READ_ONCE(*r2); rcu_read_unlock(); } } exists (2:r0<>0 /\ 2:r3=0) (* Not found. *) Fixes: 1395706a1490 ("swiotlb: search the software IO TLB only if the device makes use of it") Reported-by: Jonathan Corbet Closes: https://lore.kernel.org/linux-iommu/87a5uz3ob8.fsf@meer.lwn.net/ Signed-off-by: Petr Tesarik Reviewed-by: Catalin Marinas Signed-off-by: Christoph Hellwig --- include/linux/swiotlb.h | 23 ++++++++++++++++------- kernel/dma/swiotlb.c | 26 ++++++++++++++++++++------ 2 files changed, 36 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index b4536626f8ff..ecde0312dd52 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -172,14 +172,23 @@ static inline bool is_swiotlb_buffer(struct device *dev, phys_addr_t paddr) if (!mem) return false; - if (IS_ENABLED(CONFIG_SWIOTLB_DYNAMIC)) { - /* Pairs with smp_wmb() in swiotlb_find_slots() and - * swiotlb_dyn_alloc(), which modify the RCU lists. - */ - smp_rmb(); - return swiotlb_find_pool(dev, paddr); - } +#ifdef CONFIG_SWIOTLB_DYNAMIC + /* + * All SWIOTLB buffer addresses must have been returned by + * swiotlb_tbl_map_single() and passed to a device driver. + * If a SWIOTLB address is checked on another CPU, then it was + * presumably loaded by the device driver from an unspecified private + * data structure. Make sure that this load is ordered before reading + * dev->dma_uses_io_tlb here and mem->pools in swiotlb_find_pool(). + * + * This barrier pairs with smp_mb() in swiotlb_find_slots(). + */ + smp_rmb(); + return READ_ONCE(dev->dma_uses_io_tlb) && + swiotlb_find_pool(dev, paddr); +#else return paddr >= mem->defpool.start && paddr < mem->defpool.end; +#endif } static inline bool is_swiotlb_force_bounce(struct device *dev) diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index 85dd94323b98..01637677736f 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -728,9 +728,6 @@ static void swiotlb_dyn_alloc(struct work_struct *work) } add_mem_pool(mem, pool); - - /* Pairs with smp_rmb() in is_swiotlb_buffer(). */ - smp_wmb(); } /** @@ -1151,9 +1148,26 @@ static int swiotlb_find_slots(struct device *dev, phys_addr_t orig_addr, spin_unlock_irqrestore(&dev->dma_io_tlb_lock, flags); found: - dev->dma_uses_io_tlb = true; - /* Pairs with smp_rmb() in is_swiotlb_buffer() */ - smp_wmb(); + WRITE_ONCE(dev->dma_uses_io_tlb, true); + + /* + * The general barrier orders reads and writes against a presumed store + * of the SWIOTLB buffer address by a device driver (to a driver private + * data structure). It serves two purposes. + * + * First, the store to dev->dma_uses_io_tlb must be ordered before the + * presumed store. This guarantees that the returned buffer address + * cannot be passed to another CPU before updating dev->dma_uses_io_tlb. + * + * Second, the load from mem->pools must be ordered before the same + * presumed store. This guarantees that the returned buffer address + * cannot be observed by another CPU before an update of the RCU list + * that was made by swiotlb_dyn_alloc() on a third CPU (cf. multicopy + * atomicity). + * + * See also the comment in is_swiotlb_buffer(). + */ + smp_mb(); *retpool = pool; return index; -- cgit v1.2.3 From 1a6a464774947920dcedcf7409be62495c7cedd0 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Tue, 12 Sep 2023 12:44:06 +0200 Subject: timers: Tag (hr)timer softirq as hotplug safe Specific stress involving frequent CPU-hotplug operations, such as running rcutorture for example, may trigger the following message: NOHZ tick-stop error: local softirq work is pending, handler #02!!!" This happens in the CPU-down hotplug process, after CPUHP_AP_SMPBOOT_THREADS whose teardown callback parks ksoftirqd, and before the target CPU shuts down through CPUHP_AP_IDLE_DEAD. In this fragile intermediate state, softirqs waiting for threaded handling may be forever ignored and eventually reported by the idle task as in the above example. However some vectors are known to be safe as long as the corresponding subsystems have teardown callbacks handling the migration of their events. The above error message reports pending timers softirq although this vector can be considered as hotplug safe because the CPUHP_TIMERS_PREPARE teardown callback performs the necessary migration of timers after the death of the CPU. Hrtimers also have a similar hotplug handling. Therefore this error message, as far as (hr-)timers are concerned, can be considered spurious and the relevant softirq vectors can be marked as hotplug safe. Fixes: 0345691b24c0 ("tick/rcu: Stop allowing RCU_SOFTIRQ in idle") Signed-off-by: Frederic Weisbecker Signed-off-by: Thomas Gleixner Reviewed-by: Joel Fernandes (Google) Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230912104406.312185-6-frederic@kernel.org --- include/linux/interrupt.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index a92bce40b04b..4a1dc88ddbff 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -569,8 +569,12 @@ enum * 2) rcu_report_dead() reports the final quiescent states. * * _ IRQ_POLL: irq_poll_cpu_dead() migrates the queue + * + * _ (HR)TIMER_SOFTIRQ: (hr)timers_dead_cpu() migrates the queue */ -#define SOFTIRQ_HOTPLUG_SAFE_MASK (BIT(RCU_SOFTIRQ) | BIT(IRQ_POLL_SOFTIRQ)) +#define SOFTIRQ_HOTPLUG_SAFE_MASK (BIT(TIMER_SOFTIRQ) | BIT(IRQ_POLL_SOFTIRQ) |\ + BIT(HRTIMER_SOFTIRQ) | BIT(RCU_SOFTIRQ)) + /* map softirq index to softirq name. update 'softirq_to_name' in * kernel/softirq.c when adding a new softirq. -- cgit v1.2.3 From fb99ef17865035a6657786d4b2af11a27ba23f9b Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Fri, 25 Aug 2023 15:41:14 +0900 Subject: ata: libata-scsi: link ata port and scsi device There is no direct device ancestry defined between an ata_device and its scsi device which prevents the power management code from correctly ordering suspend and resume operations. Create such ancestry with the ata device as the parent to ensure that the scsi device (child) is suspended before the ata device and that resume handles the ata device before the scsi device. The parent-child (supplier-consumer) relationship is established between the ata_port (parent) and the scsi device (child) with the function device_add_link(). The parent used is not the ata_device as the PM operations are defined per port and the status of all devices connected through that port is controlled from the port operations. The device link is established with the new function ata_scsi_slave_alloc(), and this function is used to define the ->slave_alloc callback of the scsi host template of all ata drivers. Fixes: a19a93e4c6a9 ("scsi: core: pm: Rely on the device driver core for async power management") Cc: stable@vger.kernel.org Signed-off-by: Damien Le Moal Reviewed-by: Hannes Reinecke Reviewed-by: Niklas Cassel Tested-by: Geert Uytterhoeven Reviewed-by: Martin K. Petersen Reviewed-by: John Garry --- drivers/ata/libata-scsi.c | 45 ++++++++++++++++++++++++++++++++++++++++----- include/linux/libata.h | 2 ++ 2 files changed, 42 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index fb73c145b49a..8b43290ca2cd 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -1089,6 +1089,42 @@ int ata_scsi_dev_config(struct scsi_device *sdev, struct ata_device *dev) return 0; } +/** + * ata_scsi_slave_alloc - Early setup of SCSI device + * @sdev: SCSI device to examine + * + * This is called from scsi_alloc_sdev() when the scsi device + * associated with an ATA device is scanned on a port. + * + * LOCKING: + * Defined by SCSI layer. We don't really care. + */ + +int ata_scsi_slave_alloc(struct scsi_device *sdev) +{ + struct ata_port *ap = ata_shost_to_port(sdev->host); + struct device_link *link; + + ata_scsi_sdev_config(sdev); + + /* + * Create a link from the ata_port device to the scsi device to ensure + * that PM does suspend/resume in the correct order: the scsi device is + * consumer (child) and the ata port the supplier (parent). + */ + link = device_link_add(&sdev->sdev_gendev, &ap->tdev, + DL_FLAG_STATELESS | + DL_FLAG_PM_RUNTIME | DL_FLAG_RPM_ACTIVE); + if (!link) { + ata_port_err(ap, "Failed to create link to scsi device %s\n", + dev_name(&sdev->sdev_gendev)); + return -ENODEV; + } + + return 0; +} +EXPORT_SYMBOL_GPL(ata_scsi_slave_alloc); + /** * ata_scsi_slave_config - Set SCSI device attributes * @sdev: SCSI device to examine @@ -1105,14 +1141,11 @@ int ata_scsi_slave_config(struct scsi_device *sdev) { struct ata_port *ap = ata_shost_to_port(sdev->host); struct ata_device *dev = __ata_scsi_find_dev(ap, sdev); - int rc = 0; - - ata_scsi_sdev_config(sdev); if (dev) - rc = ata_scsi_dev_config(sdev, dev); + return ata_scsi_dev_config(sdev, dev); - return rc; + return 0; } EXPORT_SYMBOL_GPL(ata_scsi_slave_config); @@ -1136,6 +1169,8 @@ void ata_scsi_slave_destroy(struct scsi_device *sdev) unsigned long flags; struct ata_device *dev; + device_link_remove(&sdev->sdev_gendev, &ap->tdev); + spin_lock_irqsave(ap->lock, flags); dev = __ata_scsi_find_dev(ap, sdev); if (dev && dev->sdev) { diff --git a/include/linux/libata.h b/include/linux/libata.h index 84aca8c44fa3..3ce1ab408114 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -1148,6 +1148,7 @@ extern int ata_std_bios_param(struct scsi_device *sdev, struct block_device *bdev, sector_t capacity, int geom[]); extern void ata_scsi_unlock_native_capacity(struct scsi_device *sdev); +extern int ata_scsi_slave_alloc(struct scsi_device *sdev); extern int ata_scsi_slave_config(struct scsi_device *sdev); extern void ata_scsi_slave_destroy(struct scsi_device *sdev); extern int ata_scsi_change_queue_depth(struct scsi_device *sdev, @@ -1396,6 +1397,7 @@ extern const struct attribute_group *ata_common_sdev_groups[]; .this_id = ATA_SHT_THIS_ID, \ .emulated = ATA_SHT_EMULATED, \ .proc_name = drv_name, \ + .slave_alloc = ata_scsi_slave_alloc, \ .slave_destroy = ata_scsi_slave_destroy, \ .bios_param = ata_std_bios_param, \ .unlock_native_capacity = ata_scsi_unlock_native_capacity,\ -- cgit v1.2.3 From aa3998dbeb3abce63653b7f6d4542e7dcd022590 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Sat, 26 Aug 2023 09:43:39 +0900 Subject: ata: libata-scsi: Disable scsi device manage_system_start_stop The introduction of a device link to create a consumer/supplier relationship between the scsi device of an ATA device and the ATA port of that ATA device fixes the ordering of system suspend and resume operations. For suspend, the scsi device is suspended first and the ata port after it. This is fine as this allows the synchronize cache and START STOP UNIT commands issued by the scsi disk driver to be executed before the ata port is disabled. For resume operations, the ata port is resumed first, followed by the scsi device. This allows having the request queue of the scsi device to be unfrozen after the ata port resume is scheduled in EH, thus avoiding to see new requests prematurely issued to the ATA device. Since libata sets manage_system_start_stop to 1, the scsi disk resume operation also results in issuing a START STOP UNIT command to the device being resumed so that the device exits standby power mode. However, restoring the ATA device to the active power mode must be synchronized with libata EH processing of the port resume operation to avoid either 1) seeing the start stop unit command being received too early when the port is not yet resumed and ready to accept commands, or after the port resume process issues commands such as IDENTIFY to revalidate the device. In this last case, the risk is that the device revalidation fails with timeout errors as the drive is still spun down. Commit 0a8589055936 ("ata,scsi: do not issue START STOP UNIT on resume") disabled issuing the START STOP UNIT command to avoid issues with it. But this is incorrect as transitioning a device to the active power mode from the standby power mode set on suspend requires a media access command. The IDENTIFY, READ LOG and SET FEATURES commands executed in libata EH context triggered by the ata port resume operation may thus fail. Fix these synchronization issues is by handling a device power mode transitions for system suspend and resume directly in libata EH context, without relying on the scsi disk driver management triggered with the manage_system_start_stop flag. To do this, the following libata helper functions are introduced: 1) ata_dev_power_set_standby(): This function issues a STANDBY IMMEDIATE command to transitiom a device to the standby power mode. For HDDs, this spins down the disks. This function applies only to ATA and ZAC devices and does nothing otherwise. This function also does nothing for devices that have the ATA_FLAG_NO_POWEROFF_SPINDOWN or ATA_FLAG_NO_HIBERNATE_SPINDOWN flag set. For suspend, call ata_dev_power_set_standby() in ata_eh_handle_port_suspend() before the port is disabled and frozen. ata_eh_unload() is also modified to transition all enabled devices to the standby power mode when the system is shutdown or devices removed. 2) ata_dev_power_set_active() and This function applies to ATA or ZAC devices and issues a VERIFY command for 1 sector at LBA 0 to transition the device to the active power mode. For HDDs, since this function will complete only once the disk spin up. Its execution uses the same timeouts as for reset, to give the drive enough time to complete spinup without triggering a command timeout. For resume, call ata_dev_power_set_active() in ata_eh_revalidate_and_attach() after the port has been enabled and before any other command is issued to the device. With these changes, the manage_system_start_stop and no_start_on_resume scsi device flags do not need to be set in ata_scsi_dev_config(). The flag manage_runtime_start_stop is still set to allow the sd driver to spinup/spindown a disk through the sd runtime operations. Fixes: 0a8589055936 ("ata,scsi: do not issue START STOP UNIT on resume") Cc: stable@vger.kernel.org Signed-off-by: Damien Le Moal Reviewed-by: Hannes Reinecke Tested-by: Geert Uytterhoeven Reviewed-by: Martin K. Petersen --- drivers/ata/libata-core.c | 90 +++++++++++++++++++++++++++++++++++++++++++++++ drivers/ata/libata-eh.c | 46 +++++++++++++++++++++++- drivers/ata/libata-scsi.c | 16 ++++----- drivers/ata/libata.h | 2 ++ include/linux/libata.h | 6 ++-- 5 files changed, 148 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 8e35afe5e560..a0bc01606b30 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -1972,6 +1972,96 @@ retry: return rc; } +/** + * ata_dev_power_set_standby - Set a device power mode to standby + * @dev: target device + * + * Issue a STANDBY IMMEDIATE command to set a device power mode to standby. + * For an HDD device, this spins down the disks. + * + * LOCKING: + * Kernel thread context (may sleep). + */ +void ata_dev_power_set_standby(struct ata_device *dev) +{ + unsigned long ap_flags = dev->link->ap->flags; + struct ata_taskfile tf; + unsigned int err_mask; + + /* Issue STANDBY IMMEDIATE command only if supported by the device */ + if (dev->class != ATA_DEV_ATA && dev->class != ATA_DEV_ZAC) + return; + + /* + * Some odd clown BIOSes issue spindown on power off (ACPI S4 or S5) + * causing some drives to spin up and down again. For these, do nothing + * if we are being called on shutdown. + */ + if ((ap_flags & ATA_FLAG_NO_POWEROFF_SPINDOWN) && + system_state == SYSTEM_POWER_OFF) + return; + + if ((ap_flags & ATA_FLAG_NO_HIBERNATE_SPINDOWN) && + system_entering_hibernation()) + return; + + ata_tf_init(dev, &tf); + tf.flags |= ATA_TFLAG_DEVICE | ATA_TFLAG_ISADDR; + tf.protocol = ATA_PROT_NODATA; + tf.command = ATA_CMD_STANDBYNOW1; + + ata_dev_notice(dev, "Entering standby power mode\n"); + + err_mask = ata_exec_internal(dev, &tf, NULL, DMA_NONE, NULL, 0, 0); + if (err_mask) + ata_dev_err(dev, "STANDBY IMMEDIATE failed (err_mask=0x%x)\n", + err_mask); +} + +/** + * ata_dev_power_set_active - Set a device power mode to active + * @dev: target device + * + * Issue a VERIFY command to enter to ensure that the device is in the + * active power mode. For a spun-down HDD (standby or idle power mode), + * the VERIFY command will complete after the disk spins up. + * + * LOCKING: + * Kernel thread context (may sleep). + */ +void ata_dev_power_set_active(struct ata_device *dev) +{ + struct ata_taskfile tf; + unsigned int err_mask; + + /* + * Issue READ VERIFY SECTORS command for 1 sector at lba=0 only + * if supported by the device. + */ + if (dev->class != ATA_DEV_ATA && dev->class != ATA_DEV_ZAC) + return; + + ata_tf_init(dev, &tf); + tf.flags |= ATA_TFLAG_DEVICE | ATA_TFLAG_ISADDR; + tf.protocol = ATA_PROT_NODATA; + tf.command = ATA_CMD_VERIFY; + tf.nsect = 1; + if (dev->flags & ATA_DFLAG_LBA) { + tf.flags |= ATA_TFLAG_LBA; + tf.device |= ATA_LBA; + } else { + /* CHS */ + tf.lbal = 0x1; /* sect */ + } + + ata_dev_notice(dev, "Entering active power mode\n"); + + err_mask = ata_exec_internal(dev, &tf, NULL, DMA_NONE, NULL, 0, 0); + if (err_mask) + ata_dev_err(dev, "VERIFY failed (err_mask=0x%x)\n", + err_mask); +} + /** * ata_read_log_page - read a specific log page * @dev: target device diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c index 4cf4f57e57b8..b1b2c276371e 100644 --- a/drivers/ata/libata-eh.c +++ b/drivers/ata/libata-eh.c @@ -147,6 +147,8 @@ ata_eh_cmd_timeout_table[ATA_EH_CMD_TIMEOUT_TABLE_SIZE] = { .timeouts = ata_eh_other_timeouts, }, { .commands = CMDS(ATA_CMD_FLUSH, ATA_CMD_FLUSH_EXT), .timeouts = ata_eh_flush_timeouts }, + { .commands = CMDS(ATA_CMD_VERIFY), + .timeouts = ata_eh_reset_timeouts }, }; #undef CMDS @@ -498,7 +500,19 @@ static void ata_eh_unload(struct ata_port *ap) struct ata_device *dev; unsigned long flags; - /* Restore SControl IPM and SPD for the next driver and + /* + * Unless we are restarting, transition all enabled devices to + * standby power mode. + */ + if (system_state != SYSTEM_RESTART) { + ata_for_each_link(link, ap, PMP_FIRST) { + ata_for_each_dev(dev, link, ENABLED) + ata_dev_power_set_standby(dev); + } + } + + /* + * Restore SControl IPM and SPD for the next driver and * disable attached devices. */ ata_for_each_link(link, ap, PMP_FIRST) { @@ -684,6 +698,10 @@ void ata_scsi_port_error_handler(struct Scsi_Host *host, struct ata_port *ap) ehc->saved_xfer_mode[devno] = dev->xfer_mode; if (ata_ncq_enabled(dev)) ehc->saved_ncq_enabled |= 1 << devno; + + /* If we are resuming, wake up the device */ + if (ap->pflags & ATA_PFLAG_RESUMING) + ehc->i.dev_action[devno] |= ATA_EH_SET_ACTIVE; } } @@ -743,6 +761,8 @@ void ata_scsi_port_error_handler(struct Scsi_Host *host, struct ata_port *ap) /* clean up */ spin_lock_irqsave(ap->lock, flags); + ap->pflags &= ~ATA_PFLAG_RESUMING; + if (ap->pflags & ATA_PFLAG_LOADING) ap->pflags &= ~ATA_PFLAG_LOADING; else if ((ap->pflags & ATA_PFLAG_SCSI_HOTPLUG) && @@ -1218,6 +1238,13 @@ void ata_eh_detach_dev(struct ata_device *dev) struct ata_eh_context *ehc = &link->eh_context; unsigned long flags; + /* + * If the device is still enabled, transition it to standby power mode + * (i.e. spin down HDDs). + */ + if (ata_dev_enabled(dev)) + ata_dev_power_set_standby(dev); + ata_dev_disable(dev); spin_lock_irqsave(ap->lock, flags); @@ -3016,6 +3043,15 @@ static int ata_eh_revalidate_and_attach(struct ata_link *link, if (ehc->i.flags & ATA_EHI_DID_RESET) readid_flags |= ATA_READID_POSTRESET; + /* + * When resuming, before executing any command, make sure to + * transition the device to the active power mode. + */ + if ((action & ATA_EH_SET_ACTIVE) && ata_dev_enabled(dev)) { + ata_dev_power_set_active(dev); + ata_eh_done(link, dev, ATA_EH_SET_ACTIVE); + } + if ((action & ATA_EH_REVALIDATE) && ata_dev_enabled(dev)) { WARN_ON(dev->class == ATA_DEV_PMP); @@ -3989,6 +4025,7 @@ static void ata_eh_handle_port_suspend(struct ata_port *ap) unsigned long flags; int rc = 0; struct ata_device *dev; + struct ata_link *link; /* are we suspending? */ spin_lock_irqsave(ap->lock, flags); @@ -4001,6 +4038,12 @@ static void ata_eh_handle_port_suspend(struct ata_port *ap) WARN_ON(ap->pflags & ATA_PFLAG_SUSPENDED); + /* Set all devices attached to the port in standby mode */ + ata_for_each_link(link, ap, HOST_FIRST) { + ata_for_each_dev(dev, link, ENABLED) + ata_dev_power_set_standby(dev); + } + /* * If we have a ZPODD attached, check its zero * power ready status before the port is frozen. @@ -4083,6 +4126,7 @@ static void ata_eh_handle_port_resume(struct ata_port *ap) /* update the flags */ spin_lock_irqsave(ap->lock, flags); ap->pflags &= ~(ATA_PFLAG_PM_PENDING | ATA_PFLAG_SUSPENDED); + ap->pflags |= ATA_PFLAG_RESUMING; spin_unlock_irqrestore(ap->lock, flags); } #endif /* CONFIG_PM */ diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index 73428ad0c8d2..a0e58d22d222 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -1050,15 +1050,13 @@ int ata_scsi_dev_config(struct scsi_device *sdev, struct ata_device *dev) } } else { sdev->sector_size = ata_id_logical_sector_size(dev->id); + /* - * Stop the drive on suspend but do not issue START STOP UNIT - * on resume as this is not necessary and may fail: the device - * will be woken up by ata_port_pm_resume() with a port reset - * and device revalidation. + * Ask the sd driver to issue START STOP UNIT on runtime suspend + * and resume only. For system level suspend/resume, devices + * power state is handled directly by libata EH. */ - sdev->manage_system_start_stop = true; sdev->manage_runtime_start_stop = true; - sdev->no_start_on_resume = 1; } /* @@ -1231,7 +1229,7 @@ static unsigned int ata_scsi_start_stop_xlat(struct ata_queued_cmd *qc) } if (cdb[4] & 0x1) { - tf->nsect = 1; /* 1 sector, lba=0 */ + tf->nsect = 1; /* 1 sector, lba=0 */ if (qc->dev->flags & ATA_DFLAG_LBA) { tf->flags |= ATA_TFLAG_LBA; @@ -1247,7 +1245,7 @@ static unsigned int ata_scsi_start_stop_xlat(struct ata_queued_cmd *qc) tf->lbah = 0x0; /* cyl high */ } - tf->command = ATA_CMD_VERIFY; /* READ VERIFY */ + tf->command = ATA_CMD_VERIFY; /* READ VERIFY */ } else { /* Some odd clown BIOSen issue spindown on power off (ACPI S4 * or S5) causing some drives to spin up and down again. @@ -1257,7 +1255,7 @@ static unsigned int ata_scsi_start_stop_xlat(struct ata_queued_cmd *qc) goto skip; if ((qc->ap->flags & ATA_FLAG_NO_HIBERNATE_SPINDOWN) && - system_entering_hibernation()) + system_entering_hibernation()) goto skip; /* Issue ATA STANDBY IMMEDIATE command */ diff --git a/drivers/ata/libata.h b/drivers/ata/libata.h index 6e7d352803bd..820299bd9d06 100644 --- a/drivers/ata/libata.h +++ b/drivers/ata/libata.h @@ -60,6 +60,8 @@ extern int ata_dev_reread_id(struct ata_device *dev, unsigned int readid_flags); extern int ata_dev_revalidate(struct ata_device *dev, unsigned int new_class, unsigned int readid_flags); extern int ata_dev_configure(struct ata_device *dev); +extern void ata_dev_power_set_standby(struct ata_device *dev); +extern void ata_dev_power_set_active(struct ata_device *dev); extern int sata_down_spd_limit(struct ata_link *link, u32 spd_limit); extern int ata_down_xfermask_limit(struct ata_device *dev, unsigned int sel); extern unsigned int ata_dev_set_feature(struct ata_device *dev, diff --git a/include/linux/libata.h b/include/linux/libata.h index 3ce1ab408114..2a7d2af0ed80 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -192,6 +192,7 @@ enum { ATA_PFLAG_UNLOADING = (1 << 9), /* driver is being unloaded */ ATA_PFLAG_UNLOADED = (1 << 10), /* driver is unloaded */ + ATA_PFLAG_RESUMING = (1 << 16), /* port is being resumed */ ATA_PFLAG_SUSPENDED = (1 << 17), /* port is suspended (power) */ ATA_PFLAG_PM_PENDING = (1 << 18), /* PM operation pending */ ATA_PFLAG_INIT_GTM_VALID = (1 << 19), /* initial gtm data valid */ @@ -318,9 +319,10 @@ enum { ATA_EH_ENABLE_LINK = (1 << 3), ATA_EH_PARK = (1 << 5), /* unload heads and stop I/O */ ATA_EH_GET_SUCCESS_SENSE = (1 << 6), /* Get sense data for successful cmd */ + ATA_EH_SET_ACTIVE = (1 << 7), /* Set a device to active power mode */ ATA_EH_PERDEV_MASK = ATA_EH_REVALIDATE | ATA_EH_PARK | - ATA_EH_GET_SUCCESS_SENSE, + ATA_EH_GET_SUCCESS_SENSE | ATA_EH_SET_ACTIVE, ATA_EH_ALL_ACTIONS = ATA_EH_REVALIDATE | ATA_EH_RESET | ATA_EH_ENABLE_LINK, @@ -357,7 +359,7 @@ enum { /* This should match the actual table size of * ata_eh_cmd_timeout_table in libata-eh.c. */ - ATA_EH_CMD_TIMEOUT_TABLE_SIZE = 7, + ATA_EH_CMD_TIMEOUT_TABLE_SIZE = 8, /* Horkage types. May be set by libata or controller on drives (some horkage may be drive/controller pair dependent */ -- cgit v1.2.3 From ce60f27bb62dfeb1bf827350520f34abc84e0933 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Wed, 20 Sep 2023 05:09:58 +0100 Subject: mm: abstract moving to the next PFN In order to fix the L1TF vulnerability, x86 can invert the PTE bits for PROT_NONE VMAs, which means we cannot move from one PTE to the next by adding 1 to the PFN field of the PTE. This results in the BUG reported at [1]. Abstract advancing the PTE to the next PFN through a pte_next_pfn() function/macro. Link: https://lkml.kernel.org/r/20230920040958.866520-1-willy@infradead.org Fixes: bcc6cc832573 ("mm: add default definition of set_ptes()") Signed-off-by: Matthew Wilcox (Oracle) Reported-by: syzbot+55cc72f8cc3a549119df@syzkaller.appspotmail.com Closes: https://lkml.kernel.org/r/000000000000d099fa0604f03351@google.com [1] Reviewed-by: Yin Fengwei Cc: Dave Hansen Cc: David Hildenbrand Cc: Thomas Gleixner Signed-off-by: Andrew Morton --- arch/x86/include/asm/pgtable.h | 8 ++++++++ include/linux/pgtable.h | 10 +++++++++- 2 files changed, 17 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index d6ad98ca1288..e02b179ec659 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -955,6 +955,14 @@ static inline int pte_same(pte_t a, pte_t b) return a.pte == b.pte; } +static inline pte_t pte_next_pfn(pte_t pte) +{ + if (__pte_needs_invert(pte_val(pte))) + return __pte(pte_val(pte) - (1UL << PFN_PTE_SHIFT)); + return __pte(pte_val(pte) + (1UL << PFN_PTE_SHIFT)); +} +#define pte_next_pfn pte_next_pfn + static inline int pte_present(pte_t a) { return pte_flags(a) & (_PAGE_PRESENT | _PAGE_PROTNONE); diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index 1fba072b3dac..af7639c3b0a3 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -206,6 +206,14 @@ static inline int pmd_young(pmd_t pmd) #endif #ifndef set_ptes + +#ifndef pte_next_pfn +static inline pte_t pte_next_pfn(pte_t pte) +{ + return __pte(pte_val(pte) + (1UL << PFN_PTE_SHIFT)); +} +#endif + /** * set_ptes - Map consecutive pages to a contiguous range of addresses. * @mm: Address space to map the pages into. @@ -231,7 +239,7 @@ static inline void set_ptes(struct mm_struct *mm, unsigned long addr, if (--nr == 0) break; ptep++; - pte = __pte(pte_val(pte) + (1UL << PFN_PTE_SHIFT)); + pte = pte_next_pfn(pte); } arch_leave_lazy_mmu_mode(); } -- cgit v1.2.3 From 5c590804b6b0ff933ed4e5cee5d76de3a5048d9f Mon Sep 17 00:00:00 2001 From: "Liam R. Howlett" Date: Thu, 21 Sep 2023 14:12:35 -0400 Subject: maple_tree: add mas_is_active() to detect in-tree walks Patch series "maple_tree: Fix mas_prev() state regression". Pedro Falcato retported an mprotect regression [1] which was bisected back to the iterator changes for maple tree. Root cause analysis showed the mas_prev() running off the end of the VMA space (previous from 0) followed by mas_find(), would skip the first value. This patchset introduces maple state underflow/overflow so the sequence of calls on the maple state will return what the user expects. Users who encounter this bug may see mprotect(), userfaultfd_register(), and mlock() fail on VMAs mapped with address 0. This patch (of 2): Instead of constantly checking each possibility of the maple state, create a fast path that will skip over checking unlikely states. Link: https://lkml.kernel.org/r/20230921181236.509072-1-Liam.Howlett@oracle.com Link: https://lkml.kernel.org/r/20230921181236.509072-2-Liam.Howlett@oracle.com Signed-off-by: Liam R. Howlett Cc: Pedro Falcato Cc: Signed-off-by: Andrew Morton --- include/linux/maple_tree.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/maple_tree.h b/include/linux/maple_tree.h index e41c70ac7744..f66f5f78f8cf 100644 --- a/include/linux/maple_tree.h +++ b/include/linux/maple_tree.h @@ -511,6 +511,15 @@ static inline bool mas_is_paused(const struct ma_state *mas) return mas->node == MAS_PAUSE; } +/* Check if the mas is pointing to a node or not */ +static inline bool mas_is_active(struct ma_state *mas) +{ + if ((unsigned long)mas->node >= MAPLE_RESERVED_RANGE) + return true; + + return false; +} + /** * mas_reset() - Reset a Maple Tree operation state. * @mas: Maple Tree operation state. -- cgit v1.2.3 From a8091f039c1ebf5cb0d5261e3613f18eb2a5d8b7 Mon Sep 17 00:00:00 2001 From: "Liam R. Howlett" Date: Thu, 21 Sep 2023 14:12:36 -0400 Subject: maple_tree: add MAS_UNDERFLOW and MAS_OVERFLOW states When updating the maple tree iterator to avoid rewalks, an issue was introduced when shifting beyond the limits. This can be seen by trying to go to the previous address of 0, which would set the maple node to MAS_NONE and keep the range as the last entry. Subsequent calls to mas_find() would then search upwards from mas->last and skip the value at mas->index/mas->last. This showed up as a bug in mprotect which skips the actual VMA at the current range after attempting to go to the previous VMA from 0. Since MAS_NONE may already be set when searching for a value that isn't contained within a node, changing the handling of MAS_NONE in mas_find() would make the code more complicated and error prone. Furthermore, there was no way to tell which limit was hit, and thus which action to take (next or the entry at the current range). This solution is to add two states to track what happened with the previous iterator action. This allows for the expected behaviour of the next command to return the correct item (either the item at the range requested, or the next/previous). Tests are also added and updated accordingly. Link: https://lkml.kernel.org/r/20230921181236.509072-3-Liam.Howlett@oracle.com Link: https://gist.github.com/heatd/85d2971fae1501b55b6ea401fbbe485b Link: https://lore.kernel.org/linux-mm/20230921181236.509072-1-Liam.Howlett@oracle.com/ Fixes: 39193685d585 ("maple_tree: try harder to keep active node with mas_prev()") Signed-off-by: Liam R. Howlett Reported-by: Pedro Falcato Closes: https://gist.github.com/heatd/85d2971fae1501b55b6ea401fbbe485b Closes: https://bugs.archlinux.org/task/79656 Cc: Signed-off-by: Andrew Morton --- include/linux/maple_tree.h | 2 + lib/maple_tree.c | 221 +++++++++++++++++++++++++++++++++------------ lib/test_maple_tree.c | 87 +++++++++++++++--- 3 files changed, 237 insertions(+), 73 deletions(-) (limited to 'include/linux') diff --git a/include/linux/maple_tree.h b/include/linux/maple_tree.h index f66f5f78f8cf..d01e850b570f 100644 --- a/include/linux/maple_tree.h +++ b/include/linux/maple_tree.h @@ -428,6 +428,8 @@ struct ma_wr_state { #define MAS_ROOT ((struct maple_enode *)5UL) #define MAS_NONE ((struct maple_enode *)9UL) #define MAS_PAUSE ((struct maple_enode *)17UL) +#define MAS_OVERFLOW ((struct maple_enode *)33UL) +#define MAS_UNDERFLOW ((struct maple_enode *)65UL) #define MA_ERROR(err) \ ((struct maple_enode *)(((unsigned long)err << 2) | 2UL)) diff --git a/lib/maple_tree.c b/lib/maple_tree.c index ee1ff0c59fd7..0e00a84e8e8f 100644 --- a/lib/maple_tree.c +++ b/lib/maple_tree.c @@ -256,6 +256,22 @@ bool mas_is_err(struct ma_state *mas) return xa_is_err(mas->node); } +static __always_inline bool mas_is_overflow(struct ma_state *mas) +{ + if (unlikely(mas->node == MAS_OVERFLOW)) + return true; + + return false; +} + +static __always_inline bool mas_is_underflow(struct ma_state *mas) +{ + if (unlikely(mas->node == MAS_UNDERFLOW)) + return true; + + return false; +} + static inline bool mas_searchable(struct ma_state *mas) { if (mas_is_none(mas)) @@ -4415,10 +4431,13 @@ no_entry: * * @mas: The maple state * @max: The minimum starting range + * @empty: Can be empty + * @set_underflow: Set the @mas->node to underflow state on limit. * * Return: The entry in the previous slot which is possibly NULL */ -static void *mas_prev_slot(struct ma_state *mas, unsigned long min, bool empty) +static void *mas_prev_slot(struct ma_state *mas, unsigned long min, bool empty, + bool set_underflow) { void *entry; void __rcu **slots; @@ -4435,7 +4454,6 @@ retry: if (unlikely(mas_rewalk_if_dead(mas, node, save_point))) goto retry; -again: if (mas->min <= min) { pivot = mas_safe_min(mas, pivots, mas->offset); @@ -4443,9 +4461,10 @@ again: goto retry; if (pivot <= min) - return NULL; + goto underflow; } +again: if (likely(mas->offset)) { mas->offset--; mas->last = mas->index - 1; @@ -4457,7 +4476,7 @@ again: } if (mas_is_none(mas)) - return NULL; + goto underflow; mas->last = mas->max; node = mas_mn(mas); @@ -4474,10 +4493,19 @@ again: if (likely(entry)) return entry; - if (!empty) + if (!empty) { + if (mas->index <= min) + goto underflow; + goto again; + } return entry; + +underflow: + if (set_underflow) + mas->node = MAS_UNDERFLOW; + return NULL; } /* @@ -4567,10 +4595,13 @@ no_entry: * @mas: The maple state * @max: The maximum starting range * @empty: Can be empty + * @set_overflow: Should @mas->node be set to overflow when the limit is + * reached. * * Return: The entry in the next slot which is possibly NULL */ -static void *mas_next_slot(struct ma_state *mas, unsigned long max, bool empty) +static void *mas_next_slot(struct ma_state *mas, unsigned long max, bool empty, + bool set_overflow) { void __rcu **slots; unsigned long *pivots; @@ -4589,22 +4620,22 @@ retry: if (unlikely(mas_rewalk_if_dead(mas, node, save_point))) goto retry; -again: if (mas->max >= max) { if (likely(mas->offset < data_end)) pivot = pivots[mas->offset]; else - return NULL; /* must be mas->max */ + goto overflow; if (unlikely(mas_rewalk_if_dead(mas, node, save_point))) goto retry; if (pivot >= max) - return NULL; + goto overflow; } if (likely(mas->offset < data_end)) { mas->index = pivots[mas->offset] + 1; +again: mas->offset++; if (likely(mas->offset < data_end)) mas->last = pivots[mas->offset]; @@ -4616,8 +4647,11 @@ again: goto retry; } - if (mas_is_none(mas)) + if (WARN_ON_ONCE(mas_is_none(mas))) { + mas->node = MAS_OVERFLOW; return NULL; + goto overflow; + } mas->offset = 0; mas->index = mas->min; @@ -4636,12 +4670,20 @@ again: return entry; if (!empty) { - if (!mas->offset) - data_end = 2; + if (mas->last >= max) + goto overflow; + + mas->index = mas->last + 1; + /* Node cannot end on NULL, so it's safe to short-cut here */ goto again; } return entry; + +overflow: + if (set_overflow) + mas->node = MAS_OVERFLOW; + return NULL; } /* @@ -4651,17 +4693,20 @@ again: * * Set the @mas->node to the next entry and the range_start to * the beginning value for the entry. Does not check beyond @limit. - * Sets @mas->index and @mas->last to the limit if it is hit. + * Sets @mas->index and @mas->last to the range, Does not update @mas->index and + * @mas->last on overflow. * Restarts on dead nodes. * * Return: the next entry or %NULL. */ static inline void *mas_next_entry(struct ma_state *mas, unsigned long limit) { - if (mas->last >= limit) + if (mas->last >= limit) { + mas->node = MAS_OVERFLOW; return NULL; + } - return mas_next_slot(mas, limit, false); + return mas_next_slot(mas, limit, false, true); } /* @@ -4837,7 +4882,7 @@ void *mas_walk(struct ma_state *mas) { void *entry; - if (mas_is_none(mas) || mas_is_paused(mas) || mas_is_ptr(mas)) + if (!mas_is_active(mas) || !mas_is_start(mas)) mas->node = MAS_START; retry: entry = mas_state_walk(mas); @@ -5294,14 +5339,22 @@ static inline void mte_destroy_walk(struct maple_enode *enode, static void mas_wr_store_setup(struct ma_wr_state *wr_mas) { - if (mas_is_start(wr_mas->mas)) - return; + if (!mas_is_active(wr_mas->mas)) { + if (mas_is_start(wr_mas->mas)) + return; - if (unlikely(mas_is_paused(wr_mas->mas))) - goto reset; + if (unlikely(mas_is_paused(wr_mas->mas))) + goto reset; - if (unlikely(mas_is_none(wr_mas->mas))) - goto reset; + if (unlikely(mas_is_none(wr_mas->mas))) + goto reset; + + if (unlikely(mas_is_overflow(wr_mas->mas))) + goto reset; + + if (unlikely(mas_is_underflow(wr_mas->mas))) + goto reset; + } /* * A less strict version of mas_is_span_wr() where we allow spanning @@ -5595,8 +5648,25 @@ static inline bool mas_next_setup(struct ma_state *mas, unsigned long max, { bool was_none = mas_is_none(mas); - if (mas_is_none(mas) || mas_is_paused(mas)) + if (unlikely(mas->last >= max)) { + mas->node = MAS_OVERFLOW; + return true; + } + + if (mas_is_active(mas)) + return false; + + if (mas_is_none(mas) || mas_is_paused(mas)) { + mas->node = MAS_START; + } else if (mas_is_overflow(mas)) { + /* Overflowed before, but the max changed */ mas->node = MAS_START; + } else if (mas_is_underflow(mas)) { + mas->node = MAS_START; + *entry = mas_walk(mas); + if (*entry) + return true; + } if (mas_is_start(mas)) *entry = mas_walk(mas); /* Retries on dead nodes handled by mas_walk */ @@ -5615,6 +5685,7 @@ static inline bool mas_next_setup(struct ma_state *mas, unsigned long max, if (mas_is_none(mas)) return true; + return false; } @@ -5637,7 +5708,7 @@ void *mas_next(struct ma_state *mas, unsigned long max) return entry; /* Retries on dead nodes handled by mas_next_slot */ - return mas_next_slot(mas, max, false); + return mas_next_slot(mas, max, false, true); } EXPORT_SYMBOL_GPL(mas_next); @@ -5660,7 +5731,7 @@ void *mas_next_range(struct ma_state *mas, unsigned long max) return entry; /* Retries on dead nodes handled by mas_next_slot */ - return mas_next_slot(mas, max, true); + return mas_next_slot(mas, max, true, true); } EXPORT_SYMBOL_GPL(mas_next_range); @@ -5691,18 +5762,31 @@ EXPORT_SYMBOL_GPL(mt_next); static inline bool mas_prev_setup(struct ma_state *mas, unsigned long min, void **entry) { - if (mas->index <= min) - goto none; + if (unlikely(mas->index <= min)) { + mas->node = MAS_UNDERFLOW; + return true; + } - if (mas_is_none(mas) || mas_is_paused(mas)) + if (mas_is_active(mas)) + return false; + + if (mas_is_overflow(mas)) { mas->node = MAS_START; + *entry = mas_walk(mas); + if (*entry) + return true; + } - if (mas_is_start(mas)) { - mas_walk(mas); - if (!mas->index) - goto none; + if (mas_is_none(mas) || mas_is_paused(mas)) { + mas->node = MAS_START; + } else if (mas_is_underflow(mas)) { + /* underflowed before but the min changed */ + mas->node = MAS_START; } + if (mas_is_start(mas)) + mas_walk(mas); + if (unlikely(mas_is_ptr(mas))) { if (!mas->index) goto none; @@ -5747,7 +5831,7 @@ void *mas_prev(struct ma_state *mas, unsigned long min) if (mas_prev_setup(mas, min, &entry)) return entry; - return mas_prev_slot(mas, min, false); + return mas_prev_slot(mas, min, false, true); } EXPORT_SYMBOL_GPL(mas_prev); @@ -5770,7 +5854,7 @@ void *mas_prev_range(struct ma_state *mas, unsigned long min) if (mas_prev_setup(mas, min, &entry)) return entry; - return mas_prev_slot(mas, min, true); + return mas_prev_slot(mas, min, true, true); } EXPORT_SYMBOL_GPL(mas_prev_range); @@ -5828,24 +5912,35 @@ EXPORT_SYMBOL_GPL(mas_pause); static inline bool mas_find_setup(struct ma_state *mas, unsigned long max, void **entry) { - *entry = NULL; + if (mas_is_active(mas)) { + if (mas->last < max) + return false; - if (unlikely(mas_is_none(mas))) { + return true; + } + + if (mas_is_paused(mas)) { if (unlikely(mas->last >= max)) return true; - mas->index = mas->last; + mas->index = ++mas->last; mas->node = MAS_START; - } else if (unlikely(mas_is_paused(mas))) { + } else if (mas_is_none(mas)) { if (unlikely(mas->last >= max)) return true; + mas->index = mas->last; mas->node = MAS_START; - mas->index = ++mas->last; - } else if (unlikely(mas_is_ptr(mas))) - goto ptr_out_of_range; + } else if (mas_is_overflow(mas) || mas_is_underflow(mas)) { + if (mas->index > max) { + mas->node = MAS_OVERFLOW; + return true; + } + + mas->node = MAS_START; + } - if (unlikely(mas_is_start(mas))) { + if (mas_is_start(mas)) { /* First run or continue */ if (mas->index > max) return true; @@ -5895,7 +5990,7 @@ void *mas_find(struct ma_state *mas, unsigned long max) return entry; /* Retries on dead nodes handled by mas_next_slot */ - return mas_next_slot(mas, max, false); + return mas_next_slot(mas, max, false, false); } EXPORT_SYMBOL_GPL(mas_find); @@ -5913,13 +6008,13 @@ EXPORT_SYMBOL_GPL(mas_find); */ void *mas_find_range(struct ma_state *mas, unsigned long max) { - void *entry; + void *entry = NULL; if (mas_find_setup(mas, max, &entry)) return entry; /* Retries on dead nodes handled by mas_next_slot */ - return mas_next_slot(mas, max, true); + return mas_next_slot(mas, max, true, false); } EXPORT_SYMBOL_GPL(mas_find_range); @@ -5934,26 +6029,36 @@ EXPORT_SYMBOL_GPL(mas_find_range); static inline bool mas_find_rev_setup(struct ma_state *mas, unsigned long min, void **entry) { - *entry = NULL; - - if (unlikely(mas_is_none(mas))) { - if (mas->index <= min) - goto none; + if (mas_is_active(mas)) { + if (mas->index > min) + return false; - mas->last = mas->index; - mas->node = MAS_START; + return true; } - if (unlikely(mas_is_paused(mas))) { + if (mas_is_paused(mas)) { if (unlikely(mas->index <= min)) { mas->node = MAS_NONE; return true; } mas->node = MAS_START; mas->last = --mas->index; + } else if (mas_is_none(mas)) { + if (mas->index <= min) + goto none; + + mas->last = mas->index; + mas->node = MAS_START; + } else if (mas_is_underflow(mas) || mas_is_overflow(mas)) { + if (mas->last <= min) { + mas->node = MAS_UNDERFLOW; + return true; + } + + mas->node = MAS_START; } - if (unlikely(mas_is_start(mas))) { + if (mas_is_start(mas)) { /* First run or continue */ if (mas->index < min) return true; @@ -6004,13 +6109,13 @@ none: */ void *mas_find_rev(struct ma_state *mas, unsigned long min) { - void *entry; + void *entry = NULL; if (mas_find_rev_setup(mas, min, &entry)) return entry; /* Retries on dead nodes handled by mas_prev_slot */ - return mas_prev_slot(mas, min, false); + return mas_prev_slot(mas, min, false, false); } EXPORT_SYMBOL_GPL(mas_find_rev); @@ -6030,13 +6135,13 @@ EXPORT_SYMBOL_GPL(mas_find_rev); */ void *mas_find_range_rev(struct ma_state *mas, unsigned long min) { - void *entry; + void *entry = NULL; if (mas_find_rev_setup(mas, min, &entry)) return entry; /* Retries on dead nodes handled by mas_prev_slot */ - return mas_prev_slot(mas, min, true); + return mas_prev_slot(mas, min, true, false); } EXPORT_SYMBOL_GPL(mas_find_range_rev); diff --git a/lib/test_maple_tree.c b/lib/test_maple_tree.c index 0674aebd4423..06959165e2f9 100644 --- a/lib/test_maple_tree.c +++ b/lib/test_maple_tree.c @@ -2166,7 +2166,7 @@ static noinline void __init next_prev_test(struct maple_tree *mt) MT_BUG_ON(mt, val != NULL); MT_BUG_ON(mt, mas.index != 0); MT_BUG_ON(mt, mas.last != 5); - MT_BUG_ON(mt, mas.node != MAS_NONE); + MT_BUG_ON(mt, mas.node != MAS_UNDERFLOW); mas.index = 0; mas.last = 5; @@ -2917,6 +2917,7 @@ static noinline void __init check_empty_area_fill(struct maple_tree *mt) * exists MAS_NONE active range * exists active active range * DNE active active set to last range + * ERANGE active MAS_OVERFLOW last range * * Function ENTRY Start Result index & last * mas_prev() @@ -2945,6 +2946,7 @@ static noinline void __init check_empty_area_fill(struct maple_tree *mt) * any MAS_ROOT MAS_NONE 0 * exists active active range * DNE active active last range + * ERANGE active MAS_UNDERFLOW last range * * Function ENTRY Start Result index & last * mas_find() @@ -2955,7 +2957,7 @@ static noinline void __init check_empty_area_fill(struct maple_tree *mt) * DNE MAS_START MAS_NONE 0 * DNE MAS_PAUSE MAS_NONE 0 * DNE MAS_ROOT MAS_NONE 0 - * DNE MAS_NONE MAS_NONE 0 + * DNE MAS_NONE MAS_NONE 1 * if index == 0 * exists MAS_START MAS_ROOT 0 * exists MAS_PAUSE MAS_ROOT 0 @@ -2967,7 +2969,7 @@ static noinline void __init check_empty_area_fill(struct maple_tree *mt) * DNE MAS_START active set to max * exists MAS_PAUSE active range * DNE MAS_PAUSE active set to max - * exists MAS_NONE active range + * exists MAS_NONE active range (start at last) * exists active active range * DNE active active last range (max < last) * @@ -2992,7 +2994,7 @@ static noinline void __init check_empty_area_fill(struct maple_tree *mt) * DNE MAS_START active set to min * exists MAS_PAUSE active range * DNE MAS_PAUSE active set to min - * exists MAS_NONE active range + * exists MAS_NONE active range (start at index) * exists active active range * DNE active active last range (min > index) * @@ -3039,10 +3041,10 @@ static noinline void __init check_state_handling(struct maple_tree *mt) mtree_store_range(mt, 0, 0, ptr, GFP_KERNEL); mas_lock(&mas); - /* prev: Start -> none */ + /* prev: Start -> underflow*/ entry = mas_prev(&mas, 0); MT_BUG_ON(mt, entry != NULL); - MT_BUG_ON(mt, mas.node != MAS_NONE); + MT_BUG_ON(mt, mas.node != MAS_UNDERFLOW); /* prev: Start -> root */ mas_set(&mas, 10); @@ -3069,7 +3071,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt) MT_BUG_ON(mt, entry != NULL); MT_BUG_ON(mt, mas.node != MAS_NONE); - /* next: start -> none */ + /* next: start -> none*/ mas_set(&mas, 10); entry = mas_next(&mas, ULONG_MAX); MT_BUG_ON(mt, mas.index != 1); @@ -3268,25 +3270,46 @@ static noinline void __init check_state_handling(struct maple_tree *mt) MT_BUG_ON(mt, mas.last != 0x2500); MT_BUG_ON(mt, !mas_active(mas)); - /* next:active -> active out of range*/ + /* next:active -> active beyond data */ entry = mas_next(&mas, 0x2999); MT_BUG_ON(mt, entry != NULL); MT_BUG_ON(mt, mas.index != 0x2501); MT_BUG_ON(mt, mas.last != 0x2fff); MT_BUG_ON(mt, !mas_active(mas)); - /* Continue after out of range*/ + /* Continue after last range ends after max */ entry = mas_next(&mas, ULONG_MAX); MT_BUG_ON(mt, entry != ptr3); MT_BUG_ON(mt, mas.index != 0x3000); MT_BUG_ON(mt, mas.last != 0x3500); MT_BUG_ON(mt, !mas_active(mas)); - /* next:active -> active out of range*/ + /* next:active -> active continued */ + entry = mas_next(&mas, ULONG_MAX); + MT_BUG_ON(mt, entry != NULL); + MT_BUG_ON(mt, mas.index != 0x3501); + MT_BUG_ON(mt, mas.last != ULONG_MAX); + MT_BUG_ON(mt, !mas_active(mas)); + + /* next:active -> overflow */ entry = mas_next(&mas, ULONG_MAX); MT_BUG_ON(mt, entry != NULL); MT_BUG_ON(mt, mas.index != 0x3501); MT_BUG_ON(mt, mas.last != ULONG_MAX); + MT_BUG_ON(mt, mas.node != MAS_OVERFLOW); + + /* next:overflow -> overflow */ + entry = mas_next(&mas, ULONG_MAX); + MT_BUG_ON(mt, entry != NULL); + MT_BUG_ON(mt, mas.index != 0x3501); + MT_BUG_ON(mt, mas.last != ULONG_MAX); + MT_BUG_ON(mt, mas.node != MAS_OVERFLOW); + + /* prev:overflow -> active */ + entry = mas_prev(&mas, 0); + MT_BUG_ON(mt, entry != ptr3); + MT_BUG_ON(mt, mas.index != 0x3000); + MT_BUG_ON(mt, mas.last != 0x3500); MT_BUG_ON(mt, !mas_active(mas)); /* next: none -> active, skip value at location */ @@ -3307,11 +3330,46 @@ static noinline void __init check_state_handling(struct maple_tree *mt) MT_BUG_ON(mt, mas.last != 0x1500); MT_BUG_ON(mt, !mas_active(mas)); - /* prev:active -> active out of range*/ + /* prev:active -> active spanning end range */ + entry = mas_prev(&mas, 0x0100); + MT_BUG_ON(mt, entry != NULL); + MT_BUG_ON(mt, mas.index != 0); + MT_BUG_ON(mt, mas.last != 0x0FFF); + MT_BUG_ON(mt, !mas_active(mas)); + + /* prev:active -> underflow */ + entry = mas_prev(&mas, 0); + MT_BUG_ON(mt, entry != NULL); + MT_BUG_ON(mt, mas.index != 0); + MT_BUG_ON(mt, mas.last != 0x0FFF); + MT_BUG_ON(mt, mas.node != MAS_UNDERFLOW); + + /* prev:underflow -> underflow */ entry = mas_prev(&mas, 0); MT_BUG_ON(mt, entry != NULL); MT_BUG_ON(mt, mas.index != 0); MT_BUG_ON(mt, mas.last != 0x0FFF); + MT_BUG_ON(mt, mas.node != MAS_UNDERFLOW); + + /* next:underflow -> active */ + entry = mas_next(&mas, ULONG_MAX); + MT_BUG_ON(mt, entry != ptr); + MT_BUG_ON(mt, mas.index != 0x1000); + MT_BUG_ON(mt, mas.last != 0x1500); + MT_BUG_ON(mt, !mas_active(mas)); + + /* prev:first value -> underflow */ + entry = mas_prev(&mas, 0x1000); + MT_BUG_ON(mt, entry != NULL); + MT_BUG_ON(mt, mas.index != 0x1000); + MT_BUG_ON(mt, mas.last != 0x1500); + MT_BUG_ON(mt, mas.node != MAS_UNDERFLOW); + + /* find:underflow -> first value */ + entry = mas_find(&mas, ULONG_MAX); + MT_BUG_ON(mt, entry != ptr); + MT_BUG_ON(mt, mas.index != 0x1000); + MT_BUG_ON(mt, mas.last != 0x1500); MT_BUG_ON(mt, !mas_active(mas)); /* prev: pause ->active */ @@ -3325,14 +3383,14 @@ static noinline void __init check_state_handling(struct maple_tree *mt) MT_BUG_ON(mt, mas.last != 0x2500); MT_BUG_ON(mt, !mas_active(mas)); - /* prev:active -> active out of range*/ + /* prev:active -> active spanning min */ entry = mas_prev(&mas, 0x1600); MT_BUG_ON(mt, entry != NULL); MT_BUG_ON(mt, mas.index != 0x1501); MT_BUG_ON(mt, mas.last != 0x1FFF); MT_BUG_ON(mt, !mas_active(mas)); - /* prev: active ->active, continue*/ + /* prev: active ->active, continue */ entry = mas_prev(&mas, 0); MT_BUG_ON(mt, entry != ptr); MT_BUG_ON(mt, mas.index != 0x1000); @@ -3379,7 +3437,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt) MT_BUG_ON(mt, mas.last != 0x2FFF); MT_BUG_ON(mt, !mas_active(mas)); - /* find: none ->active */ + /* find: overflow ->active */ entry = mas_find(&mas, 0x5000); MT_BUG_ON(mt, entry != ptr3); MT_BUG_ON(mt, mas.index != 0x3000); @@ -3778,7 +3836,6 @@ static int __init maple_tree_seed(void) check_empty_area_fill(&tree); mtree_destroy(&tree); - mt_init_flags(&tree, MT_FLAGS_ALLOC_RANGE); check_state_handling(&tree); mtree_destroy(&tree); -- cgit v1.2.3 From 935d4f0c6dc8b3533e6e39346de7389a84490178 Mon Sep 17 00:00:00 2001 From: Ryan Roberts Date: Fri, 22 Sep 2023 12:58:03 +0100 Subject: mm: hugetlb: add huge page size param to set_huge_pte_at() Patch series "Fix set_huge_pte_at() panic on arm64", v2. This series fixes a bug in arm64's implementation of set_huge_pte_at(), which can result in an unprivileged user causing a kernel panic. The problem was triggered when running the new uffd poison mm selftest for HUGETLB memory. This test (and the uffd poison feature) was merged for v6.5-rc7. Ideally, I'd like to get this fix in for v6.6 and I've cc'ed stable (correctly this time) to get it backported to v6.5, where the issue first showed up. Description of Bug ================== arm64's huge pte implementation supports multiple huge page sizes, some of which are implemented in the page table with multiple contiguous entries. So set_huge_pte_at() needs to work out how big the logical pte is, so that it can also work out how many physical ptes (or pmds) need to be written. It previously did this by grabbing the folio out of the pte and querying its size. However, there are cases when the pte being set is actually a swap entry. But this also used to work fine, because for huge ptes, we only ever saw migration entries and hwpoison entries. And both of these types of swap entries have a PFN embedded, so the code would grab that and everything still worked out. But over time, more calls to set_huge_pte_at() have been added that set swap entry types that do not embed a PFN. And this causes the code to go bang. The triggering case is for the uffd poison test, commit 99aa77215ad0 ("selftests/mm: add uffd unit test for UFFDIO_POISON"), which causes a PTE_MARKER_POISONED swap entry to be set, coutesey of commit 8a13897fb0da ("mm: userfaultfd: support UFFDIO_POISON for hugetlbfs") - added in v6.5-rc7. Although review shows that there are other call sites that set PTE_MARKER_UFFD_WP (which also has no PFN), these don't trigger on arm64 because arm64 doesn't support UFFD WP. If CONFIG_DEBUG_VM is enabled, we do at least get a BUG(), but otherwise, it will dereference a bad pointer in page_folio(): static inline struct folio *hugetlb_swap_entry_to_folio(swp_entry_t entry) { VM_BUG_ON(!is_migration_entry(entry) && !is_hwpoison_entry(entry)); return page_folio(pfn_to_page(swp_offset_pfn(entry))); } Fix === The simplest fix would have been to revert the dodgy cleanup commit 18f3962953e4 ("mm: hugetlb: kill set_huge_swap_pte_at()"), but since things have moved on, this would have required an audit of all the new set_huge_pte_at() call sites to see if they should be converted to set_huge_swap_pte_at(). As per the original intent of the change, it would also leave us open to future bugs when people invariably get it wrong and call the wrong helper. So instead, I've added a huge page size parameter to set_huge_pte_at(). This means that the arm64 code has the size in all cases. It's a bigger change, due to needing to touch the arches that implement the function, but it is entirely mechanical, so in my view, low risk. I've compile-tested all touched arches; arm64, parisc, powerpc, riscv, s390, sparc (and additionally x86_64). I've additionally booted and run mm selftests against arm64, where I observe the uffd poison test is fixed, and there are no other regressions. This patch (of 2): In order to fix a bug, arm64 needs to be told the size of the huge page for which the pte is being set in set_huge_pte_at(). Provide for this by adding an `unsigned long sz` parameter to the function. This follows the same pattern as huge_pte_clear(). This commit makes the required interface modifications to the core mm as well as all arches that implement this function (arm64, parisc, powerpc, riscv, s390, sparc). The actual arm64 bug will be fixed in a separate commit. No behavioral changes intended. Link: https://lkml.kernel.org/r/20230922115804.2043771-1-ryan.roberts@arm.com Link: https://lkml.kernel.org/r/20230922115804.2043771-2-ryan.roberts@arm.com Fixes: 8a13897fb0da ("mm: userfaultfd: support UFFDIO_POISON for hugetlbfs") Signed-off-by: Ryan Roberts Reviewed-by: Christophe Leroy [powerpc 8xx] Reviewed-by: Lorenzo Stoakes [vmalloc change] Cc: Alexandre Ghiti Cc: Albert Ou Cc: Alexander Gordeev Cc: Anshuman Khandual Cc: Arnd Bergmann Cc: Axel Rasmussen Cc: Catalin Marinas Cc: Christian Borntraeger Cc: Christoph Hellwig Cc: David S. Miller Cc: Gerald Schaefer Cc: Heiko Carstens Cc: Helge Deller Cc: "James E.J. Bottomley" Cc: Mike Kravetz Cc: Muchun Song Cc: Nicholas Piggin Cc: Palmer Dabbelt Cc: Paul Walmsley Cc: Peter Xu Cc: Qi Zheng Cc: Ryan Roberts Cc: SeongJae Park Cc: Sven Schnelle Cc: Uladzislau Rezki (Sony) Cc: Vasily Gorbik Cc: Will Deacon Cc: [6.5+] Signed-off-by: Andrew Morton --- arch/arm64/include/asm/hugetlb.h | 2 +- arch/arm64/mm/hugetlbpage.c | 6 ++-- arch/parisc/include/asm/hugetlb.h | 2 +- arch/parisc/mm/hugetlbpage.c | 2 +- arch/powerpc/include/asm/nohash/32/hugetlb-8xx.h | 3 +- arch/powerpc/mm/book3s64/hugetlbpage.c | 5 ++- arch/powerpc/mm/book3s64/radix_hugetlbpage.c | 3 +- arch/powerpc/mm/nohash/8xx.c | 3 +- arch/powerpc/mm/pgtable.c | 3 +- arch/riscv/include/asm/hugetlb.h | 3 +- arch/riscv/mm/hugetlbpage.c | 3 +- arch/s390/include/asm/hugetlb.h | 6 ++-- arch/s390/mm/hugetlbpage.c | 8 ++++- arch/sparc/include/asm/hugetlb.h | 6 ++-- arch/sparc/mm/hugetlbpage.c | 8 ++++- include/asm-generic/hugetlb.h | 2 +- include/linux/hugetlb.h | 6 ++-- mm/damon/vaddr.c | 3 +- mm/hugetlb.c | 43 +++++++++++++----------- mm/migrate.c | 7 ++-- mm/rmap.c | 23 ++++++++++--- mm/vmalloc.c | 2 +- 22 files changed, 100 insertions(+), 49 deletions(-) (limited to 'include/linux') diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h index f43a38ac1779..2ddc33d93b13 100644 --- a/arch/arm64/include/asm/hugetlb.h +++ b/arch/arm64/include/asm/hugetlb.h @@ -28,7 +28,7 @@ pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags_t flags); #define arch_make_huge_pte arch_make_huge_pte #define __HAVE_ARCH_HUGE_SET_HUGE_PTE_AT extern void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, - pte_t *ptep, pte_t pte); + pte_t *ptep, pte_t pte, unsigned long sz); #define __HAVE_ARCH_HUGE_PTEP_SET_ACCESS_FLAGS extern int huge_ptep_set_access_flags(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c index 9c52718ea750..a7f8c8db3425 100644 --- a/arch/arm64/mm/hugetlbpage.c +++ b/arch/arm64/mm/hugetlbpage.c @@ -249,7 +249,7 @@ static inline struct folio *hugetlb_swap_entry_to_folio(swp_entry_t entry) } void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, - pte_t *ptep, pte_t pte) + pte_t *ptep, pte_t pte, unsigned long sz) { size_t pgsize; int i; @@ -571,5 +571,7 @@ pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t old_pte, pte_t pte) { - set_huge_pte_at(vma->vm_mm, addr, ptep, pte); + unsigned long psize = huge_page_size(hstate_vma(vma)); + + set_huge_pte_at(vma->vm_mm, addr, ptep, pte, psize); } diff --git a/arch/parisc/include/asm/hugetlb.h b/arch/parisc/include/asm/hugetlb.h index f7f078c2872c..72daacc472a0 100644 --- a/arch/parisc/include/asm/hugetlb.h +++ b/arch/parisc/include/asm/hugetlb.h @@ -6,7 +6,7 @@ #define __HAVE_ARCH_HUGE_SET_HUGE_PTE_AT void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, - pte_t *ptep, pte_t pte); + pte_t *ptep, pte_t pte, unsigned long sz); #define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, diff --git a/arch/parisc/mm/hugetlbpage.c b/arch/parisc/mm/hugetlbpage.c index a8a1a7c1e16e..a9f7e21f6656 100644 --- a/arch/parisc/mm/hugetlbpage.c +++ b/arch/parisc/mm/hugetlbpage.c @@ -140,7 +140,7 @@ static void __set_huge_pte_at(struct mm_struct *mm, unsigned long addr, } void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, - pte_t *ptep, pte_t entry) + pte_t *ptep, pte_t entry, unsigned long sz) { __set_huge_pte_at(mm, addr, ptep, entry); } diff --git a/arch/powerpc/include/asm/nohash/32/hugetlb-8xx.h b/arch/powerpc/include/asm/nohash/32/hugetlb-8xx.h index de092b04ee1a..92df40c6cc6b 100644 --- a/arch/powerpc/include/asm/nohash/32/hugetlb-8xx.h +++ b/arch/powerpc/include/asm/nohash/32/hugetlb-8xx.h @@ -46,7 +46,8 @@ static inline int check_and_get_huge_psize(int shift) } #define __HAVE_ARCH_HUGE_SET_HUGE_PTE_AT -void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte); +void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, + pte_t pte, unsigned long sz); #define __HAVE_ARCH_HUGE_PTE_CLEAR static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr, diff --git a/arch/powerpc/mm/book3s64/hugetlbpage.c b/arch/powerpc/mm/book3s64/hugetlbpage.c index 3bc0eb21b2a0..5a2e512e96db 100644 --- a/arch/powerpc/mm/book3s64/hugetlbpage.c +++ b/arch/powerpc/mm/book3s64/hugetlbpage.c @@ -143,11 +143,14 @@ pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma, void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t old_pte, pte_t pte) { + unsigned long psize; if (radix_enabled()) return radix__huge_ptep_modify_prot_commit(vma, addr, ptep, old_pte, pte); - set_huge_pte_at(vma->vm_mm, addr, ptep, pte); + + psize = huge_page_size(hstate_vma(vma)); + set_huge_pte_at(vma->vm_mm, addr, ptep, pte, psize); } void __init hugetlbpage_init_defaultsize(void) diff --git a/arch/powerpc/mm/book3s64/radix_hugetlbpage.c b/arch/powerpc/mm/book3s64/radix_hugetlbpage.c index 17075c78d4bc..35fd2a95be24 100644 --- a/arch/powerpc/mm/book3s64/radix_hugetlbpage.c +++ b/arch/powerpc/mm/book3s64/radix_hugetlbpage.c @@ -47,6 +47,7 @@ void radix__huge_ptep_modify_prot_commit(struct vm_area_struct *vma, pte_t old_pte, pte_t pte) { struct mm_struct *mm = vma->vm_mm; + unsigned long psize = huge_page_size(hstate_vma(vma)); /* * POWER9 NMMU must flush the TLB after clearing the PTE before @@ -58,5 +59,5 @@ void radix__huge_ptep_modify_prot_commit(struct vm_area_struct *vma, atomic_read(&mm->context.copros) > 0) radix__flush_hugetlb_page(vma, addr); - set_huge_pte_at(vma->vm_mm, addr, ptep, pte); + set_huge_pte_at(vma->vm_mm, addr, ptep, pte, psize); } diff --git a/arch/powerpc/mm/nohash/8xx.c b/arch/powerpc/mm/nohash/8xx.c index dbbfe897455d..a642a7929892 100644 --- a/arch/powerpc/mm/nohash/8xx.c +++ b/arch/powerpc/mm/nohash/8xx.c @@ -91,7 +91,8 @@ static int __ref __early_map_kernel_hugepage(unsigned long va, phys_addr_t pa, if (new && WARN_ON(pte_present(*ptep) && pgprot_val(prot))) return -EINVAL; - set_huge_pte_at(&init_mm, va, ptep, pte_mkhuge(pfn_pte(pa >> PAGE_SHIFT, prot))); + set_huge_pte_at(&init_mm, va, ptep, + pte_mkhuge(pfn_pte(pa >> PAGE_SHIFT, prot)), psize); return 0; } diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c index 3f86fd217690..3ba9fe411604 100644 --- a/arch/powerpc/mm/pgtable.c +++ b/arch/powerpc/mm/pgtable.c @@ -288,7 +288,8 @@ int huge_ptep_set_access_flags(struct vm_area_struct *vma, } #if defined(CONFIG_PPC_8xx) -void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte) +void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, + pte_t pte, unsigned long sz) { pmd_t *pmd = pmd_off(mm, addr); pte_basic_t val; diff --git a/arch/riscv/include/asm/hugetlb.h b/arch/riscv/include/asm/hugetlb.h index 34e24f078cc1..4c5b0e929890 100644 --- a/arch/riscv/include/asm/hugetlb.h +++ b/arch/riscv/include/asm/hugetlb.h @@ -18,7 +18,8 @@ void huge_pte_clear(struct mm_struct *mm, unsigned long addr, #define __HAVE_ARCH_HUGE_SET_HUGE_PTE_AT void set_huge_pte_at(struct mm_struct *mm, - unsigned long addr, pte_t *ptep, pte_t pte); + unsigned long addr, pte_t *ptep, pte_t pte, + unsigned long sz); #define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR pte_t huge_ptep_get_and_clear(struct mm_struct *mm, diff --git a/arch/riscv/mm/hugetlbpage.c b/arch/riscv/mm/hugetlbpage.c index 96225a8533ad..e4a2ace92dbe 100644 --- a/arch/riscv/mm/hugetlbpage.c +++ b/arch/riscv/mm/hugetlbpage.c @@ -180,7 +180,8 @@ pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags_t flags) void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, - pte_t pte) + pte_t pte, + unsigned long sz) { int i, pte_num; diff --git a/arch/s390/include/asm/hugetlb.h b/arch/s390/include/asm/hugetlb.h index f07267875a19..deb198a61039 100644 --- a/arch/s390/include/asm/hugetlb.h +++ b/arch/s390/include/asm/hugetlb.h @@ -16,6 +16,8 @@ #define hugepages_supported() (MACHINE_HAS_EDAT1) void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pte, unsigned long sz); +void __set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte); pte_t huge_ptep_get(pte_t *ptep); pte_t huge_ptep_get_and_clear(struct mm_struct *mm, @@ -65,7 +67,7 @@ static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma, int changed = !pte_same(huge_ptep_get(ptep), pte); if (changed) { huge_ptep_get_and_clear(vma->vm_mm, addr, ptep); - set_huge_pte_at(vma->vm_mm, addr, ptep, pte); + __set_huge_pte_at(vma->vm_mm, addr, ptep, pte); } return changed; } @@ -74,7 +76,7 @@ static inline void huge_ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { pte_t pte = huge_ptep_get_and_clear(mm, addr, ptep); - set_huge_pte_at(mm, addr, ptep, pte_wrprotect(pte)); + __set_huge_pte_at(mm, addr, ptep, pte_wrprotect(pte)); } static inline pte_t mk_huge_pte(struct page *page, pgprot_t pgprot) diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c index c718f2a0de94..297a6d897d5a 100644 --- a/arch/s390/mm/hugetlbpage.c +++ b/arch/s390/mm/hugetlbpage.c @@ -142,7 +142,7 @@ static void clear_huge_pte_skeys(struct mm_struct *mm, unsigned long rste) __storage_key_init_range(paddr, paddr + size - 1); } -void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, +void __set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte) { unsigned long rste; @@ -163,6 +163,12 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, set_pte(ptep, __pte(rste)); } +void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pte, unsigned long sz) +{ + __set_huge_pte_at(mm, addr, ptep, pte); +} + pte_t huge_ptep_get(pte_t *ptep) { return __rste_to_pte(pte_val(*ptep)); diff --git a/arch/sparc/include/asm/hugetlb.h b/arch/sparc/include/asm/hugetlb.h index 0a26cca24232..c714ca6a05aa 100644 --- a/arch/sparc/include/asm/hugetlb.h +++ b/arch/sparc/include/asm/hugetlb.h @@ -14,6 +14,8 @@ extern struct pud_huge_patch_entry __pud_huge_patch, __pud_huge_patch_end; #define __HAVE_ARCH_HUGE_SET_HUGE_PTE_AT void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pte, unsigned long sz); +void __set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte); #define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR @@ -32,7 +34,7 @@ static inline void huge_ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { pte_t old_pte = *ptep; - set_huge_pte_at(mm, addr, ptep, pte_wrprotect(old_pte)); + __set_huge_pte_at(mm, addr, ptep, pte_wrprotect(old_pte)); } #define __HAVE_ARCH_HUGE_PTEP_SET_ACCESS_FLAGS @@ -42,7 +44,7 @@ static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma, { int changed = !pte_same(*ptep, pte); if (changed) { - set_huge_pte_at(vma->vm_mm, addr, ptep, pte); + __set_huge_pte_at(vma->vm_mm, addr, ptep, pte); flush_tlb_page(vma, addr); } return changed; diff --git a/arch/sparc/mm/hugetlbpage.c b/arch/sparc/mm/hugetlbpage.c index d7018823206c..b432500c13a5 100644 --- a/arch/sparc/mm/hugetlbpage.c +++ b/arch/sparc/mm/hugetlbpage.c @@ -328,7 +328,7 @@ pte_t *huge_pte_offset(struct mm_struct *mm, return pte_offset_huge(pmd, addr); } -void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, +void __set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t entry) { unsigned int nptes, orig_shift, shift; @@ -364,6 +364,12 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, orig_shift); } +void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t entry, unsigned long sz) +{ + __set_huge_pte_at(mm, addr, ptep, entry); +} + pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { diff --git a/include/asm-generic/hugetlb.h b/include/asm-generic/hugetlb.h index 4da02798a00b..6dcf4d576970 100644 --- a/include/asm-generic/hugetlb.h +++ b/include/asm-generic/hugetlb.h @@ -76,7 +76,7 @@ static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb, #ifndef __HAVE_ARCH_HUGE_SET_HUGE_PTE_AT static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, - pte_t *ptep, pte_t pte) + pte_t *ptep, pte_t pte, unsigned long sz) { set_pte_at(mm, addr, ptep, pte); } diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 5b2626063f4f..a30686e649f7 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -984,7 +984,9 @@ static inline void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t old_pte, pte_t pte) { - set_huge_pte_at(vma->vm_mm, addr, ptep, pte); + unsigned long psize = huge_page_size(hstate_vma(vma)); + + set_huge_pte_at(vma->vm_mm, addr, ptep, pte, psize); } #endif @@ -1173,7 +1175,7 @@ static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma, } static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, - pte_t *ptep, pte_t pte) + pte_t *ptep, pte_t pte, unsigned long sz) { } diff --git a/mm/damon/vaddr.c b/mm/damon/vaddr.c index 4c81a9dbd044..cf8a9fc5c9d1 100644 --- a/mm/damon/vaddr.c +++ b/mm/damon/vaddr.c @@ -341,13 +341,14 @@ static void damon_hugetlb_mkold(pte_t *pte, struct mm_struct *mm, bool referenced = false; pte_t entry = huge_ptep_get(pte); struct folio *folio = pfn_folio(pte_pfn(entry)); + unsigned long psize = huge_page_size(hstate_vma(vma)); folio_get(folio); if (pte_young(entry)) { referenced = true; entry = pte_mkold(entry); - set_huge_pte_at(mm, addr, pte, entry); + set_huge_pte_at(mm, addr, pte, entry, psize); } #ifdef CONFIG_MMU_NOTIFIER diff --git a/mm/hugetlb.c b/mm/hugetlb.c index ba6d39b71cb1..52d26072dfda 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -4980,7 +4980,7 @@ static bool is_hugetlb_entry_hwpoisoned(pte_t pte) static void hugetlb_install_folio(struct vm_area_struct *vma, pte_t *ptep, unsigned long addr, - struct folio *new_folio, pte_t old) + struct folio *new_folio, pte_t old, unsigned long sz) { pte_t newpte = make_huge_pte(vma, &new_folio->page, 1); @@ -4988,7 +4988,7 @@ hugetlb_install_folio(struct vm_area_struct *vma, pte_t *ptep, unsigned long add hugepage_add_new_anon_rmap(new_folio, vma, addr); if (userfaultfd_wp(vma) && huge_pte_uffd_wp(old)) newpte = huge_pte_mkuffd_wp(newpte); - set_huge_pte_at(vma->vm_mm, addr, ptep, newpte); + set_huge_pte_at(vma->vm_mm, addr, ptep, newpte, sz); hugetlb_count_add(pages_per_huge_page(hstate_vma(vma)), vma->vm_mm); folio_set_hugetlb_migratable(new_folio); } @@ -5065,7 +5065,7 @@ again: } else if (unlikely(is_hugetlb_entry_hwpoisoned(entry))) { if (!userfaultfd_wp(dst_vma)) entry = huge_pte_clear_uffd_wp(entry); - set_huge_pte_at(dst, addr, dst_pte, entry); + set_huge_pte_at(dst, addr, dst_pte, entry, sz); } else if (unlikely(is_hugetlb_entry_migration(entry))) { swp_entry_t swp_entry = pte_to_swp_entry(entry); bool uffd_wp = pte_swp_uffd_wp(entry); @@ -5080,18 +5080,18 @@ again: entry = swp_entry_to_pte(swp_entry); if (userfaultfd_wp(src_vma) && uffd_wp) entry = pte_swp_mkuffd_wp(entry); - set_huge_pte_at(src, addr, src_pte, entry); + set_huge_pte_at(src, addr, src_pte, entry, sz); } if (!userfaultfd_wp(dst_vma)) entry = huge_pte_clear_uffd_wp(entry); - set_huge_pte_at(dst, addr, dst_pte, entry); + set_huge_pte_at(dst, addr, dst_pte, entry, sz); } else if (unlikely(is_pte_marker(entry))) { pte_marker marker = copy_pte_marker( pte_to_swp_entry(entry), dst_vma); if (marker) set_huge_pte_at(dst, addr, dst_pte, - make_pte_marker(marker)); + make_pte_marker(marker), sz); } else { entry = huge_ptep_get(src_pte); pte_folio = page_folio(pte_page(entry)); @@ -5145,7 +5145,7 @@ again: goto again; } hugetlb_install_folio(dst_vma, dst_pte, addr, - new_folio, src_pte_old); + new_folio, src_pte_old, sz); spin_unlock(src_ptl); spin_unlock(dst_ptl); continue; @@ -5166,7 +5166,7 @@ again: if (!userfaultfd_wp(dst_vma)) entry = huge_pte_clear_uffd_wp(entry); - set_huge_pte_at(dst, addr, dst_pte, entry); + set_huge_pte_at(dst, addr, dst_pte, entry, sz); hugetlb_count_add(npages, dst); } spin_unlock(src_ptl); @@ -5184,7 +5184,8 @@ again: } static void move_huge_pte(struct vm_area_struct *vma, unsigned long old_addr, - unsigned long new_addr, pte_t *src_pte, pte_t *dst_pte) + unsigned long new_addr, pte_t *src_pte, pte_t *dst_pte, + unsigned long sz) { struct hstate *h = hstate_vma(vma); struct mm_struct *mm = vma->vm_mm; @@ -5202,7 +5203,7 @@ static void move_huge_pte(struct vm_area_struct *vma, unsigned long old_addr, spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); pte = huge_ptep_get_and_clear(mm, old_addr, src_pte); - set_huge_pte_at(mm, new_addr, dst_pte, pte); + set_huge_pte_at(mm, new_addr, dst_pte, pte, sz); if (src_ptl != dst_ptl) spin_unlock(src_ptl); @@ -5259,7 +5260,7 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma, if (!dst_pte) break; - move_huge_pte(vma, old_addr, new_addr, src_pte, dst_pte); + move_huge_pte(vma, old_addr, new_addr, src_pte, dst_pte, sz); } if (shared_pmd) @@ -5337,7 +5338,8 @@ static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct if (pte_swp_uffd_wp_any(pte) && !(zap_flags & ZAP_FLAG_DROP_MARKER)) set_huge_pte_at(mm, address, ptep, - make_pte_marker(PTE_MARKER_UFFD_WP)); + make_pte_marker(PTE_MARKER_UFFD_WP), + sz); else huge_pte_clear(mm, address, ptep, sz); spin_unlock(ptl); @@ -5371,7 +5373,8 @@ static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct if (huge_pte_uffd_wp(pte) && !(zap_flags & ZAP_FLAG_DROP_MARKER)) set_huge_pte_at(mm, address, ptep, - make_pte_marker(PTE_MARKER_UFFD_WP)); + make_pte_marker(PTE_MARKER_UFFD_WP), + sz); hugetlb_count_sub(pages_per_huge_page(h), mm); page_remove_rmap(page, vma, true); @@ -5676,7 +5679,7 @@ retry_avoidcopy: hugepage_add_new_anon_rmap(new_folio, vma, haddr); if (huge_pte_uffd_wp(pte)) newpte = huge_pte_mkuffd_wp(newpte); - set_huge_pte_at(mm, haddr, ptep, newpte); + set_huge_pte_at(mm, haddr, ptep, newpte, huge_page_size(h)); folio_set_hugetlb_migratable(new_folio); /* Make the old page be freed below */ new_folio = old_folio; @@ -5972,7 +5975,7 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm, */ if (unlikely(pte_marker_uffd_wp(old_pte))) new_pte = huge_pte_mkuffd_wp(new_pte); - set_huge_pte_at(mm, haddr, ptep, new_pte); + set_huge_pte_at(mm, haddr, ptep, new_pte, huge_page_size(h)); hugetlb_count_add(pages_per_huge_page(h), mm); if ((flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED)) { @@ -6261,7 +6264,8 @@ int hugetlb_mfill_atomic_pte(pte_t *dst_pte, } _dst_pte = make_pte_marker(PTE_MARKER_POISONED); - set_huge_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte); + set_huge_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte, + huge_page_size(h)); /* No need to invalidate - it was non-present before */ update_mmu_cache(dst_vma, dst_addr, dst_pte); @@ -6412,7 +6416,7 @@ int hugetlb_mfill_atomic_pte(pte_t *dst_pte, if (wp_enabled) _dst_pte = huge_pte_mkuffd_wp(_dst_pte); - set_huge_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte); + set_huge_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte, huge_page_size(h)); hugetlb_count_add(pages_per_huge_page(h), dst_mm); @@ -6598,7 +6602,7 @@ long hugetlb_change_protection(struct vm_area_struct *vma, else if (uffd_wp_resolve) newpte = pte_swp_clear_uffd_wp(newpte); if (!pte_same(pte, newpte)) - set_huge_pte_at(mm, address, ptep, newpte); + set_huge_pte_at(mm, address, ptep, newpte, psize); } else if (unlikely(is_pte_marker(pte))) { /* No other markers apply for now. */ WARN_ON_ONCE(!pte_marker_uffd_wp(pte)); @@ -6623,7 +6627,8 @@ long hugetlb_change_protection(struct vm_area_struct *vma, if (unlikely(uffd_wp)) /* Safe to modify directly (none->non-present). */ set_huge_pte_at(mm, address, ptep, - make_pte_marker(PTE_MARKER_UFFD_WP)); + make_pte_marker(PTE_MARKER_UFFD_WP), + psize); } spin_unlock(ptl); } diff --git a/mm/migrate.c b/mm/migrate.c index b7fa020003f3..2053b54556ca 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -243,7 +243,9 @@ static bool remove_migration_pte(struct folio *folio, #ifdef CONFIG_HUGETLB_PAGE if (folio_test_hugetlb(folio)) { - unsigned int shift = huge_page_shift(hstate_vma(vma)); + struct hstate *h = hstate_vma(vma); + unsigned int shift = huge_page_shift(h); + unsigned long psize = huge_page_size(h); pte = arch_make_huge_pte(pte, shift, vma->vm_flags); if (folio_test_anon(folio)) @@ -251,7 +253,8 @@ static bool remove_migration_pte(struct folio *folio, rmap_flags); else page_dup_file_rmap(new, true); - set_huge_pte_at(vma->vm_mm, pvmw.address, pvmw.pte, pte); + set_huge_pte_at(vma->vm_mm, pvmw.address, pvmw.pte, pte, + psize); } else #endif { diff --git a/mm/rmap.c b/mm/rmap.c index ec7f8e6c9e48..9f795b93cf40 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1480,6 +1480,7 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma, struct mmu_notifier_range range; enum ttu_flags flags = (enum ttu_flags)(long)arg; unsigned long pfn; + unsigned long hsz = 0; /* * When racing against e.g. zap_pte_range() on another cpu, @@ -1511,6 +1512,9 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma, */ adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end); + + /* We need the huge page size for set_huge_pte_at() */ + hsz = huge_page_size(hstate_vma(vma)); } mmu_notifier_invalidate_range_start(&range); @@ -1628,7 +1632,8 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma, pteval = swp_entry_to_pte(make_hwpoison_entry(subpage)); if (folio_test_hugetlb(folio)) { hugetlb_count_sub(folio_nr_pages(folio), mm); - set_huge_pte_at(mm, address, pvmw.pte, pteval); + set_huge_pte_at(mm, address, pvmw.pte, pteval, + hsz); } else { dec_mm_counter(mm, mm_counter(&folio->page)); set_pte_at(mm, address, pvmw.pte, pteval); @@ -1820,6 +1825,7 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma, struct mmu_notifier_range range; enum ttu_flags flags = (enum ttu_flags)(long)arg; unsigned long pfn; + unsigned long hsz = 0; /* * When racing against e.g. zap_pte_range() on another cpu, @@ -1855,6 +1861,9 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma, */ adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end); + + /* We need the huge page size for set_huge_pte_at() */ + hsz = huge_page_size(hstate_vma(vma)); } mmu_notifier_invalidate_range_start(&range); @@ -2020,7 +2029,8 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma, pteval = swp_entry_to_pte(make_hwpoison_entry(subpage)); if (folio_test_hugetlb(folio)) { hugetlb_count_sub(folio_nr_pages(folio), mm); - set_huge_pte_at(mm, address, pvmw.pte, pteval); + set_huge_pte_at(mm, address, pvmw.pte, pteval, + hsz); } else { dec_mm_counter(mm, mm_counter(&folio->page)); set_pte_at(mm, address, pvmw.pte, pteval); @@ -2044,7 +2054,8 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma, if (arch_unmap_one(mm, vma, address, pteval) < 0) { if (folio_test_hugetlb(folio)) - set_huge_pte_at(mm, address, pvmw.pte, pteval); + set_huge_pte_at(mm, address, pvmw.pte, + pteval, hsz); else set_pte_at(mm, address, pvmw.pte, pteval); ret = false; @@ -2058,7 +2069,8 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma, if (anon_exclusive && page_try_share_anon_rmap(subpage)) { if (folio_test_hugetlb(folio)) - set_huge_pte_at(mm, address, pvmw.pte, pteval); + set_huge_pte_at(mm, address, pvmw.pte, + pteval, hsz); else set_pte_at(mm, address, pvmw.pte, pteval); ret = false; @@ -2090,7 +2102,8 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma, if (pte_uffd_wp(pteval)) swp_pte = pte_swp_mkuffd_wp(swp_pte); if (folio_test_hugetlb(folio)) - set_huge_pte_at(mm, address, pvmw.pte, swp_pte); + set_huge_pte_at(mm, address, pvmw.pte, swp_pte, + hsz); else set_pte_at(mm, address, pvmw.pte, swp_pte); trace_set_migration_pte(address, pte_val(swp_pte), diff --git a/mm/vmalloc.c b/mm/vmalloc.c index ef8599d394fd..a3fedb3ee0db 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -111,7 +111,7 @@ static int vmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, pte_t entry = pfn_pte(pfn, prot); entry = arch_make_huge_pte(entry, ilog2(size), 0); - set_huge_pte_at(&init_mm, addr, pte, entry); + set_huge_pte_at(&init_mm, addr, pte, entry, size); pfn += PFN_DOWN(size); continue; } -- cgit v1.2.3 From 8e56b063c86569e51eed1c5681ce6361fa97fc7a Mon Sep 17 00:00:00 2001 From: Xin Long Date: Tue, 3 Oct 2023 13:17:53 -0400 Subject: netfilter: handle the connecting collision properly in nf_conntrack_proto_sctp In Scenario A and B below, as the delayed INIT_ACK always changes the peer vtag, SCTP ct with the incorrect vtag may cause packet loss. Scenario A: INIT_ACK is delayed until the peer receives its own INIT_ACK 192.168.1.2 > 192.168.1.1: [INIT] [init tag: 1328086772] 192.168.1.1 > 192.168.1.2: [INIT] [init tag: 1414468151] 192.168.1.2 > 192.168.1.1: [INIT ACK] [init tag: 1328086772] 192.168.1.1 > 192.168.1.2: [INIT ACK] [init tag: 1650211246] * 192.168.1.2 > 192.168.1.1: [COOKIE ECHO] 192.168.1.1 > 192.168.1.2: [COOKIE ECHO] 192.168.1.2 > 192.168.1.1: [COOKIE ACK] Scenario B: INIT_ACK is delayed until the peer completes its own handshake 192.168.1.2 > 192.168.1.1: sctp (1) [INIT] [init tag: 3922216408] 192.168.1.1 > 192.168.1.2: sctp (1) [INIT] [init tag: 144230885] 192.168.1.2 > 192.168.1.1: sctp (1) [INIT ACK] [init tag: 3922216408] 192.168.1.1 > 192.168.1.2: sctp (1) [COOKIE ECHO] 192.168.1.2 > 192.168.1.1: sctp (1) [COOKIE ACK] 192.168.1.1 > 192.168.1.2: sctp (1) [INIT ACK] [init tag: 3914796021] * This patch fixes it as below: In SCTP_CID_INIT processing: - clear ct->proto.sctp.init[!dir] if ct->proto.sctp.init[dir] && ct->proto.sctp.init[!dir]. (Scenario E) - set ct->proto.sctp.init[dir]. In SCTP_CID_INIT_ACK processing: - drop it if !ct->proto.sctp.init[!dir] && ct->proto.sctp.vtag[!dir] && ct->proto.sctp.vtag[!dir] != ih->init_tag. (Scenario B, Scenario C) - drop it if ct->proto.sctp.init[dir] && ct->proto.sctp.init[!dir] && ct->proto.sctp.vtag[!dir] != ih->init_tag. (Scenario A) In SCTP_CID_COOKIE_ACK processing: - clear ct->proto.sctp.init[dir] and ct->proto.sctp.init[!dir]. (Scenario D) Also, it's important to allow the ct state to move forward with cookie_echo and cookie_ack from the opposite dir for the collision scenarios. There are also other Scenarios where it should allow the packet through, addressed by the processing above: Scenario C: new CT is created by INIT_ACK. Scenario D: start INIT on the existing ESTABLISHED ct. Scenario E: start INIT after the old collision on the existing ESTABLISHED ct. 192.168.1.2 > 192.168.1.1: sctp (1) [INIT] [init tag: 3922216408] 192.168.1.1 > 192.168.1.2: sctp (1) [INIT] [init tag: 144230885] (both side are stopped, then start new connection again in hours) 192.168.1.2 > 192.168.1.1: sctp (1) [INIT] [init tag: 242308742] Fixes: 9fb9cbb1082d ("[NETFILTER]: Add nf_conntrack subsystem.") Signed-off-by: Xin Long Signed-off-by: Florian Westphal --- include/linux/netfilter/nf_conntrack_sctp.h | 1 + net/netfilter/nf_conntrack_proto_sctp.c | 43 ++++++++++++++++++++++------- 2 files changed, 34 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/nf_conntrack_sctp.h b/include/linux/netfilter/nf_conntrack_sctp.h index 625f491b95de..fb31312825ae 100644 --- a/include/linux/netfilter/nf_conntrack_sctp.h +++ b/include/linux/netfilter/nf_conntrack_sctp.h @@ -9,6 +9,7 @@ struct ip_ct_sctp { enum sctp_conntrack state; __be32 vtag[IP_CT_DIR_MAX]; + u8 init[IP_CT_DIR_MAX]; u8 last_dir; u8 flags; }; diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index b6bcc8f2f46b..c6bd533983c1 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -112,7 +112,7 @@ static const u8 sctp_conntracks[2][11][SCTP_CONNTRACK_MAX] = { /* shutdown_ack */ {sSA, sCL, sCW, sCE, sES, sSA, sSA, sSA, sSA}, /* error */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL},/* Can't have Stale cookie*/ /* cookie_echo */ {sCL, sCL, sCE, sCE, sES, sSS, sSR, sSA, sCL},/* 5.2.4 - Big TODO */ -/* cookie_ack */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL},/* Can't come in orig dir */ +/* cookie_ack */ {sCL, sCL, sCW, sES, sES, sSS, sSR, sSA, sCL},/* Can't come in orig dir */ /* shutdown_comp*/ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sCL, sCL}, /* heartbeat */ {sHS, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS}, /* heartbeat_ack*/ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS}, @@ -126,7 +126,7 @@ static const u8 sctp_conntracks[2][11][SCTP_CONNTRACK_MAX] = { /* shutdown */ {sIV, sCL, sCW, sCE, sSR, sSS, sSR, sSA, sIV}, /* shutdown_ack */ {sIV, sCL, sCW, sCE, sES, sSA, sSA, sSA, sIV}, /* error */ {sIV, sCL, sCW, sCL, sES, sSS, sSR, sSA, sIV}, -/* cookie_echo */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sIV},/* Can't come in reply dir */ +/* cookie_echo */ {sIV, sCL, sCE, sCE, sES, sSS, sSR, sSA, sIV},/* Can't come in reply dir */ /* cookie_ack */ {sIV, sCL, sCW, sES, sES, sSS, sSR, sSA, sIV}, /* shutdown_comp*/ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sCL, sIV}, /* heartbeat */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS}, @@ -412,6 +412,9 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct, /* (D) vtag must be same as init_vtag as found in INIT_ACK */ if (sh->vtag != ct->proto.sctp.vtag[dir]) goto out_unlock; + } else if (sch->type == SCTP_CID_COOKIE_ACK) { + ct->proto.sctp.init[dir] = 0; + ct->proto.sctp.init[!dir] = 0; } else if (sch->type == SCTP_CID_HEARTBEAT) { if (ct->proto.sctp.vtag[dir] == 0) { pr_debug("Setting %d vtag %x for dir %d\n", sch->type, sh->vtag, dir); @@ -461,16 +464,18 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct, } /* If it is an INIT or an INIT ACK note down the vtag */ - if (sch->type == SCTP_CID_INIT || - sch->type == SCTP_CID_INIT_ACK) { - struct sctp_inithdr _inithdr, *ih; + if (sch->type == SCTP_CID_INIT) { + struct sctp_inithdr _ih, *ih; - ih = skb_header_pointer(skb, offset + sizeof(_sch), - sizeof(_inithdr), &_inithdr); - if (ih == NULL) + ih = skb_header_pointer(skb, offset + sizeof(_sch), sizeof(*ih), &_ih); + if (!ih) goto out_unlock; - pr_debug("Setting vtag %x for dir %d\n", - ih->init_tag, !dir); + + if (ct->proto.sctp.init[dir] && ct->proto.sctp.init[!dir]) + ct->proto.sctp.init[!dir] = 0; + ct->proto.sctp.init[dir] = 1; + + pr_debug("Setting vtag %x for dir %d\n", ih->init_tag, !dir); ct->proto.sctp.vtag[!dir] = ih->init_tag; /* don't renew timeout on init retransmit so @@ -481,6 +486,24 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct, old_state == SCTP_CONNTRACK_CLOSED && nf_ct_is_confirmed(ct)) ignore = true; + } else if (sch->type == SCTP_CID_INIT_ACK) { + struct sctp_inithdr _ih, *ih; + __be32 vtag; + + ih = skb_header_pointer(skb, offset + sizeof(_sch), sizeof(*ih), &_ih); + if (!ih) + goto out_unlock; + + vtag = ct->proto.sctp.vtag[!dir]; + if (!ct->proto.sctp.init[!dir] && vtag && vtag != ih->init_tag) + goto out_unlock; + /* collision */ + if (ct->proto.sctp.init[dir] && ct->proto.sctp.init[!dir] && + vtag != ih->init_tag) + goto out_unlock; + + pr_debug("Setting vtag %x for dir %d\n", ih->init_tag, !dir); + ct->proto.sctp.vtag[!dir] = ih->init_tag; } ct->proto.sctp.state = new_state; -- cgit v1.2.3