From patchwork Wed Nov 16 16:56:54 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Oliver Upton X-Patchwork-Id: 13045589 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 6465BC433FE for ; Wed, 16 Nov 2022 16:57:23 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S231437AbiKPQ5U (ORCPT ); Wed, 16 Nov 2022 11:57:20 -0500 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:42752 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S238998AbiKPQ5O (ORCPT ); Wed, 16 Nov 2022 11:57:14 -0500 Received: from out2.migadu.com (out2.migadu.com [188.165.223.204]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 8D985B21; Wed, 16 Nov 2022 08:57:13 -0800 (PST) X-Report-Abuse: Please report any abuse attempt to abuse@migadu.com and include these headers. DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linux.dev; s=key1; t=1668617832; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=KOTqOJazrNlg6uf0of0H9oY+uUV+g1nfwPZCAYMKJ64=; b=WMRi/CC4iw4j1vxt5iLaz3Gbv/Sah9GKivsYmN6GjhPfPEiFyZT3R/jgn2Tr7YxQZCIaQZ liPtIscA4LFP8VtIPJU1zhUHW/x7aDXbd54UQmemFS3LV/fXXkrctOqmmYKF4dPZkI/OLf SDOZDpWi/LJ2juG4txA2WgrXC5V2/ZQ= From: Oliver Upton To: Marc Zyngier , James Morse , Alexandru Elisei , Suzuki K Poulose , Oliver Upton , Catalin Marinas , Will Deacon Cc: linux-arm-kernel@lists.infradead.org, kvmarm@lists.cs.columbia.edu, kvm@vger.kernel.org, kvmarm@lists.linux.dev, linux-kernel@vger.kernel.org Subject: [PATCH v3 1/2] KVM: arm64: Take a pointer to walker data in kvm_dereference_pteref() Date: Wed, 16 Nov 2022 16:56:54 +0000 Message-Id: <20221116165655.2649475-2-oliver.upton@linux.dev> In-Reply-To: <20221116165655.2649475-1-oliver.upton@linux.dev> References: <20221116165655.2649475-1-oliver.upton@linux.dev> MIME-Version: 1.0 X-Migadu-Flow: FLOW_OUT Precedence: bulk List-ID: X-Mailing-List: kvm@vger.kernel.org Rather than passing through the state of the KVM_PGTABLE_WALK_SHARED flag, just take a pointer to the whole walker structure instead. Move around struct kvm_pgtable and the RCU indirection such that the associated ifdeffery remains in one place while ensuring the walker + flags definitions precede their use. No functional change intended. Signed-off-by: Oliver Upton --- arch/arm64/include/asm/kvm_pgtable.h | 144 ++++++++++++++------------- arch/arm64/kvm/hyp/pgtable.c | 6 +- 2 files changed, 76 insertions(+), 74 deletions(-) diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h index a874ce0ce7b5..f23af693e3c5 100644 --- a/arch/arm64/include/asm/kvm_pgtable.h +++ b/arch/arm64/include/asm/kvm_pgtable.h @@ -37,54 +37,6 @@ static inline u64 kvm_get_parange(u64 mmfr0) typedef u64 kvm_pte_t; -/* - * RCU cannot be used in a non-kernel context such as the hyp. As such, page - * table walkers used in hyp do not call into RCU and instead use other - * synchronization mechanisms (such as a spinlock). - */ -#if defined(__KVM_NVHE_HYPERVISOR__) || defined(__KVM_VHE_HYPERVISOR__) - -typedef kvm_pte_t *kvm_pteref_t; - -static inline kvm_pte_t *kvm_dereference_pteref(kvm_pteref_t pteref, bool shared) -{ - return pteref; -} - -static inline void kvm_pgtable_walk_begin(void) {} -static inline void kvm_pgtable_walk_end(void) {} - -static inline bool kvm_pgtable_walk_lock_held(void) -{ - return true; -} - -#else - -typedef kvm_pte_t __rcu *kvm_pteref_t; - -static inline kvm_pte_t *kvm_dereference_pteref(kvm_pteref_t pteref, bool shared) -{ - return rcu_dereference_check(pteref, !shared); -} - -static inline void kvm_pgtable_walk_begin(void) -{ - rcu_read_lock(); -} - -static inline void kvm_pgtable_walk_end(void) -{ - rcu_read_unlock(); -} - -static inline bool kvm_pgtable_walk_lock_held(void) -{ - return rcu_read_lock_held(); -} - -#endif - #define KVM_PTE_VALID BIT(0) #define KVM_PTE_ADDR_MASK GENMASK(47, PAGE_SHIFT) @@ -212,29 +164,6 @@ enum kvm_pgtable_prot { typedef bool (*kvm_pgtable_force_pte_cb_t)(u64 addr, u64 end, enum kvm_pgtable_prot prot); -/** - * struct kvm_pgtable - KVM page-table. - * @ia_bits: Maximum input address size, in bits. - * @start_level: Level at which the page-table walk starts. - * @pgd: Pointer to the first top-level entry of the page-table. - * @mm_ops: Memory management callbacks. - * @mmu: Stage-2 KVM MMU struct. Unused for stage-1 page-tables. - * @flags: Stage-2 page-table flags. - * @force_pte_cb: Function that returns true if page level mappings must - * be used instead of block mappings. - */ -struct kvm_pgtable { - u32 ia_bits; - u32 start_level; - kvm_pteref_t pgd; - struct kvm_pgtable_mm_ops *mm_ops; - - /* Stage-2 only */ - struct kvm_s2_mmu *mmu; - enum kvm_pgtable_stage2_flags flags; - kvm_pgtable_force_pte_cb_t force_pte_cb; -}; - /** * enum kvm_pgtable_walk_flags - Flags to control a depth-first page-table walk. * @KVM_PGTABLE_WALK_LEAF: Visit leaf entries, including invalid @@ -285,6 +214,79 @@ struct kvm_pgtable_walker { const enum kvm_pgtable_walk_flags flags; }; +/* + * RCU cannot be used in a non-kernel context such as the hyp. As such, page + * table walkers used in hyp do not call into RCU and instead use other + * synchronization mechanisms (such as a spinlock). + */ +#if defined(__KVM_NVHE_HYPERVISOR__) || defined(__KVM_VHE_HYPERVISOR__) + +typedef kvm_pte_t *kvm_pteref_t; + +static inline kvm_pte_t *kvm_dereference_pteref(struct kvm_pgtable_walker *walker, + kvm_pteref_t pteref) +{ + return pteref; +} + +static inline void kvm_pgtable_walk_begin(void) {} +static inline void kvm_pgtable_walk_end(void) {} + +static inline bool kvm_pgtable_walk_lock_held(void) +{ + return true; +} + +#else + +typedef kvm_pte_t __rcu *kvm_pteref_t; + +static inline kvm_pte_t *kvm_dereference_pteref(struct kvm_pgtable_walker *walker, + kvm_pteref_t pteref) +{ + return rcu_dereference_check(pteref, !(walker->flags & KVM_PGTABLE_WALK_SHARED)); +} + +static inline void kvm_pgtable_walk_begin(void) +{ + rcu_read_lock(); +} + +static inline void kvm_pgtable_walk_end(void) +{ + rcu_read_unlock(); +} + +static inline bool kvm_pgtable_walk_lock_held(void) +{ + return rcu_read_lock_held(); +} + +#endif + +/** + * struct kvm_pgtable - KVM page-table. + * @ia_bits: Maximum input address size, in bits. + * @start_level: Level at which the page-table walk starts. + * @pgd: Pointer to the first top-level entry of the page-table. + * @mm_ops: Memory management callbacks. + * @mmu: Stage-2 KVM MMU struct. Unused for stage-1 page-tables. + * @flags: Stage-2 page-table flags. + * @force_pte_cb: Function that returns true if page level mappings must + * be used instead of block mappings. + */ +struct kvm_pgtable { + u32 ia_bits; + u32 start_level; + kvm_pteref_t pgd; + struct kvm_pgtable_mm_ops *mm_ops; + + /* Stage-2 only */ + struct kvm_s2_mmu *mmu; + enum kvm_pgtable_stage2_flags flags; + kvm_pgtable_force_pte_cb_t force_pte_cb; +}; + /** * kvm_pgtable_hyp_init() - Initialise a hypervisor stage-1 page-table. * @pgt: Uninitialised page-table structure to initialise. diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c index 5bca9610d040..b5b91a882836 100644 --- a/arch/arm64/kvm/hyp/pgtable.c +++ b/arch/arm64/kvm/hyp/pgtable.c @@ -188,7 +188,7 @@ static inline int __kvm_pgtable_visit(struct kvm_pgtable_walk_data *data, kvm_pteref_t pteref, u32 level) { enum kvm_pgtable_walk_flags flags = data->walker->flags; - kvm_pte_t *ptep = kvm_dereference_pteref(pteref, flags & KVM_PGTABLE_WALK_SHARED); + kvm_pte_t *ptep = kvm_dereference_pteref(data->walker, pteref); struct kvm_pgtable_visit_ctx ctx = { .ptep = ptep, .old = READ_ONCE(*ptep), @@ -558,7 +558,7 @@ void kvm_pgtable_hyp_destroy(struct kvm_pgtable *pgt) }; WARN_ON(kvm_pgtable_walk(pgt, 0, BIT(pgt->ia_bits), &walker)); - pgt->mm_ops->put_page(kvm_dereference_pteref(pgt->pgd, false)); + pgt->mm_ops->put_page(kvm_dereference_pteref(&walker, pgt->pgd)); pgt->pgd = NULL; } @@ -1241,7 +1241,7 @@ void kvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt) WARN_ON(kvm_pgtable_walk(pgt, 0, BIT(pgt->ia_bits), &walker)); pgd_sz = kvm_pgd_pages(pgt->ia_bits, pgt->start_level) * PAGE_SIZE; - pgt->mm_ops->free_pages_exact(kvm_dereference_pteref(pgt->pgd, false), pgd_sz); + pgt->mm_ops->free_pages_exact(kvm_dereference_pteref(&walker, pgt->pgd), pgd_sz); pgt->pgd = NULL; } From patchwork Wed Nov 16 16:56:55 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Oliver Upton X-Patchwork-Id: 13045590 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 5D271C43217 for ; Wed, 16 Nov 2022 16:57:25 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S233361AbiKPQ5X (ORCPT ); Wed, 16 Nov 2022 11:57:23 -0500 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:42814 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S229703AbiKPQ5R (ORCPT ); Wed, 16 Nov 2022 11:57:17 -0500 Received: from out2.migadu.com (out2.migadu.com [IPv6:2001:41d0:2:aacc::]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 9E3373BA; Wed, 16 Nov 2022 08:57:16 -0800 (PST) X-Report-Abuse: Please report any abuse attempt to abuse@migadu.com and include these headers. DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linux.dev; s=key1; t=1668617835; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=PJOu0pfrq2jAQIo6Bks9pUoZjM76RoOURl952XiuGoE=; b=PLFCEsIpQHYPkHrDRzIwl8KiYXr9h6qIjwmBInUzR+YMr4Lv9YkHUQZRZ7HacgHYkgFyp3 PrwMAStUr2lAu7NBIGYF321EzC0G0p/LHqYPzNPnKwy+VWYDYEFecPyf3Tj3Bz+NdM95IP 7tnXy3Nj6aI+1ptdxnUCt+9M9WO0hlM= From: Oliver Upton To: Marc Zyngier , James Morse , Alexandru Elisei , Suzuki K Poulose , Oliver Upton , Catalin Marinas , Will Deacon Cc: linux-arm-kernel@lists.infradead.org, kvmarm@lists.cs.columbia.edu, kvm@vger.kernel.org, kvmarm@lists.linux.dev, Marek Szyprowski , linux-kernel@vger.kernel.org Subject: [PATCH v3 2/2] KVM: arm64: Don't acquire RCU read lock for exclusive table walks Date: Wed, 16 Nov 2022 16:56:55 +0000 Message-Id: <20221116165655.2649475-3-oliver.upton@linux.dev> In-Reply-To: <20221116165655.2649475-1-oliver.upton@linux.dev> References: <20221116165655.2649475-1-oliver.upton@linux.dev> MIME-Version: 1.0 X-Migadu-Flow: FLOW_OUT Precedence: bulk List-ID: X-Mailing-List: kvm@vger.kernel.org Marek reported a BUG resulting from the recent parallel faults changes, as the hyp stage-1 map walker attempted to allocate table memory while holding the RCU read lock: BUG: sleeping function called from invalid context at include/linux/sched/mm.h:274 in_atomic(): 0, irqs_disabled(): 0, non_block: 0, pid: 1, name: swapper/0 preempt_count: 0, expected: 0 RCU nest depth: 1, expected: 0 2 locks held by swapper/0/1: #0: ffff80000a8a44d0 (kvm_hyp_pgd_mutex){+.+.}-{3:3}, at: __create_hyp_mappings+0x80/0xc4 #1: ffff80000a927720 (rcu_read_lock){....}-{1:2}, at: kvm_pgtable_walk+0x0/0x1f4 CPU: 2 PID: 1 Comm: swapper/0 Not tainted 6.1.0-rc3+ #5918 Hardware name: Raspberry Pi 3 Model B (DT) Call trace: dump_backtrace.part.0+0xe4/0xf0 show_stack+0x18/0x40 dump_stack_lvl+0x8c/0xb8 dump_stack+0x18/0x34 __might_resched+0x178/0x220 __might_sleep+0x48/0xa0 prepare_alloc_pages+0x178/0x1a0 __alloc_pages+0x9c/0x109c alloc_page_interleave+0x1c/0xc4 alloc_pages+0xec/0x160 get_zeroed_page+0x1c/0x44 kvm_hyp_zalloc_page+0x14/0x20 hyp_map_walker+0xd4/0x134 kvm_pgtable_visitor_cb.isra.0+0x38/0x5c __kvm_pgtable_walk+0x1a4/0x220 kvm_pgtable_walk+0x104/0x1f4 kvm_pgtable_hyp_map+0x80/0xc4 __create_hyp_mappings+0x9c/0xc4 kvm_mmu_init+0x144/0x1cc kvm_arch_init+0xe4/0xef4 kvm_init+0x3c/0x3d0 arm_init+0x20/0x30 do_one_initcall+0x74/0x400 kernel_init_freeable+0x2e0/0x350 kernel_init+0x24/0x130 ret_from_fork+0x10/0x20 Since the hyp stage-1 table walkers are serialized by kvm_hyp_pgd_mutex, RCU protection really doesn't add anything. Don't acquire the RCU read lock for an exclusive walk. While at it, add a warning which codifies the lack of support for shared walks in the hypervisor code. Reported-by: Marek Szyprowski Signed-off-by: Oliver Upton --- arch/arm64/include/asm/kvm_pgtable.h | 22 ++++++++++++++++------ arch/arm64/kvm/hyp/pgtable.c | 4 ++-- 2 files changed, 18 insertions(+), 8 deletions(-) diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h index f23af693e3c5..a07fc5e35a8c 100644 --- a/arch/arm64/include/asm/kvm_pgtable.h +++ b/arch/arm64/include/asm/kvm_pgtable.h @@ -229,8 +229,16 @@ static inline kvm_pte_t *kvm_dereference_pteref(struct kvm_pgtable_walker *walke return pteref; } -static inline void kvm_pgtable_walk_begin(void) {} -static inline void kvm_pgtable_walk_end(void) {} +static inline void kvm_pgtable_walk_begin(struct kvm_pgtable_walker *walker) +{ + /* + * Due to the lack of RCU (or a similar protection scheme), only + * non-shared table walkers are allowed in the hypervisor. + */ + WARN_ON(walker->flags & KVM_PGTABLE_WALK_SHARED); +} + +static inline void kvm_pgtable_walk_end(struct kvm_pgtable_walker *walker) {} static inline bool kvm_pgtable_walk_lock_held(void) { @@ -247,14 +255,16 @@ static inline kvm_pte_t *kvm_dereference_pteref(struct kvm_pgtable_walker *walke return rcu_dereference_check(pteref, !(walker->flags & KVM_PGTABLE_WALK_SHARED)); } -static inline void kvm_pgtable_walk_begin(void) +static inline void kvm_pgtable_walk_begin(struct kvm_pgtable_walker *walker) { - rcu_read_lock(); + if (walker->flags & KVM_PGTABLE_WALK_SHARED) + rcu_read_lock(); } -static inline void kvm_pgtable_walk_end(void) +static inline void kvm_pgtable_walk_end(struct kvm_pgtable_walker *walker) { - rcu_read_unlock(); + if (walker->flags & KVM_PGTABLE_WALK_SHARED) + rcu_read_unlock(); } static inline bool kvm_pgtable_walk_lock_held(void) diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c index b5b91a882836..d6f3753cb87e 100644 --- a/arch/arm64/kvm/hyp/pgtable.c +++ b/arch/arm64/kvm/hyp/pgtable.c @@ -289,9 +289,9 @@ int kvm_pgtable_walk(struct kvm_pgtable *pgt, u64 addr, u64 size, }; int r; - kvm_pgtable_walk_begin(); + kvm_pgtable_walk_begin(walker); r = _kvm_pgtable_walk(pgt, &walk_data); - kvm_pgtable_walk_end(); + kvm_pgtable_walk_end(walker); return r; }