[v5,06/13] xen/spinlock: add explicit non-recursive locking functions

Message ID	20240314072029.16937-7-jgross@suse.com (mailing list archive)
State	Superseded
Headers	show Return-Path: <xen-devel-bounces@lists.xenproject.org> Errors-To: xen-devel-bounces@lists.xenproject.org Precedence: list Sender: "Xen-devel" <xen-devel-bounces@lists.xenproject.org> From: Juergen Gross <jgross@suse.com> To: xen-devel@lists.xenproject.org Cc: Juergen Gross <jgross@suse.com>, Stefano Stabellini <sstabellini@kernel.org>, Julien Grall <julien@xen.org>, Bertrand Marquis <bertrand.marquis@arm.com>, Michal Orzel <michal.orzel@amd.com>, Volodymyr Babchuk <Volodymyr_Babchuk@epam.com>, Andrew Cooper <andrew.cooper3@citrix.com>, George Dunlap <george.dunlap@citrix.com>, Jan Beulich <jbeulich@suse.com>, Wei Liu <wl@xen.org>, =?utf-8?q?Roger_Pau_Monn=C3=A9?= <roger.pau@citrix.com>, Tamas K Lengyel <tamas@tklengyel.com>, Lukasz Hawrylko <lukasz@hawrylko.pl>, "Daniel P. Smith" <dpsmith@apertussolutions.com>, =?utf-8?q?Mateusz_M=C3=B3?= =?utf-8?q?wka?= <mateusz.mowka@intel.com> Subject: [PATCH v5 06/13] xen/spinlock: add explicit non-recursive locking functions Date: Thu, 14 Mar 2024 08:20:22 +0100 Message-Id: <20240314072029.16937-7-jgross@suse.com> In-Reply-To: <20240314072029.16937-1-jgross@suse.com> References: <20240314072029.16937-1-jgross@suse.com> MIME-Version: 1.0 Content-Transfer-Encoding: 8bit
Series	xen/spinlock: make recursive spinlocks a dedicated type \| expand [v5,00/13] xen/spinlock: make recursive spinlocks a dedicated type [v5,01/13] xen/spinlock: remove misra rule 21.1 violations [v5,02/13] xen/spinlock: introduce new type for recursive spinlocks [v5,03/13] xen/spinlock: rename recursive lock functions [v5,04/13] xen/spinlock: add rspin_[un]lock_irq[save\|restore]() [v5,05/13] xen/spinlock: make struct lock_profile rspinlock_t aware [v5,06/13] xen/spinlock: add explicit non-recursive locking functions [v5,07/13] xen/spinlock: add another function level [v5,08/13] xen/spinlock: add missing rspin_is_locked() and rspin_barrier() [v5,09/13] xen/spinlock: split recursive spinlocks from normal ones [v5,10/13] xen/spinlock: let all is_locked and trylock variants return bool [v5,11/13] xen/spinlock: support higher number of cpus [v5,12/13] xen/rwlock: raise the number of possible cpus [v5,13/13] xen: allow up to 16383 cpus

diff --git a/xen/arch/arm/mm.c b/xen/arch/arm/mm.c index b15a18a494..def939172c 100644 --- a/xen/arch/arm/mm.c +++ b/xen/arch/arm/mm.c @@ -105,7 +105,7 @@ void share_xen_page_with_guest(struct page_info *page, struct domain *d, if ( page_get_owner(page) == d ) return; - spin_lock(&d->page_alloc_lock); + nrspin_lock(&d->page_alloc_lock); /* * The incremented type count pins as writable or read-only. @@ -136,7 +136,7 @@ void share_xen_page_with_guest(struct page_info *page, struct domain *d, page_list_add_tail(page, &d->xenpage_list); } - spin_unlock(&d->page_alloc_lock); + nrspin_unlock(&d->page_alloc_lock); } int xenmem_add_to_physmap_one( diff --git a/xen/arch/x86/domain.c b/xen/arch/x86/domain.c index a11c55f921..33a2830d9d 100644 --- a/xen/arch/x86/domain.c +++ b/xen/arch/x86/domain.c @@ -212,7 +212,7 @@ void dump_pageframe_info(struct domain *d) { unsigned long total[MASK_EXTR(PGT_type_mask, PGT_type_mask) + 1] = {}; - spin_lock(&d->page_alloc_lock); + nrspin_lock(&d->page_alloc_lock); page_list_for_each ( page, &d->page_list ) { unsigned int index = MASK_EXTR(page->u.inuse.type_info, @@ -231,13 +231,13 @@ void dump_pageframe_info(struct domain *d) _p(mfn_x(page_to_mfn(page))), page->count_info, page->u.inuse.type_info); } - spin_unlock(&d->page_alloc_lock); + nrspin_unlock(&d->page_alloc_lock); } if ( is_hvm_domain(d) ) p2m_pod_dump_data(d); - spin_lock(&d->page_alloc_lock); + nrspin_lock(&d->page_alloc_lock); page_list_for_each ( page, &d->xenpage_list ) { @@ -253,7 +253,7 @@ void dump_pageframe_info(struct domain *d) page->count_info, page->u.inuse.type_info); } - spin_unlock(&d->page_alloc_lock); + nrspin_unlock(&d->page_alloc_lock); } void update_guest_memory_policy(struct vcpu *v, @@ -2448,10 +2448,10 @@ int domain_relinquish_resources(struct domain *d) d->arch.auto_unmask = 0; } - spin_lock(&d->page_alloc_lock); + nrspin_lock(&d->page_alloc_lock); page_list_splice(&d->arch.relmem_list, &d->page_list); INIT_PAGE_LIST_HEAD(&d->arch.relmem_list); - spin_unlock(&d->page_alloc_lock); + nrspin_unlock(&d->page_alloc_lock); PROGRESS(xen): diff --git a/xen/arch/x86/mm.c b/xen/arch/x86/mm.c index 62f5b811bb..b4d125db39 100644 --- a/xen/arch/x86/mm.c +++ b/xen/arch/x86/mm.c @@ -482,7 +482,7 @@ void share_xen_page_with_guest(struct page_info *page, struct domain *d, set_gpfn_from_mfn(mfn_x(page_to_mfn(page)), INVALID_M2P_ENTRY); - spin_lock(&d->page_alloc_lock); + nrspin_lock(&d->page_alloc_lock); /* The incremented type count pins as writable or read-only. */ page->u.inuse.type_info = @@ -502,7 +502,7 @@ void share_xen_page_with_guest(struct page_info *page, struct domain *d, page_list_add_tail(page, &d->xenpage_list); } - spin_unlock(&d->page_alloc_lock); + nrspin_unlock(&d->page_alloc_lock); } void make_cr3(struct vcpu *v, mfn_t mfn) @@ -3597,11 +3597,11 @@ long do_mmuext_op( { bool drop_ref; - spin_lock(&pg_owner->page_alloc_lock); + nrspin_lock(&pg_owner->page_alloc_lock); drop_ref = (pg_owner->is_dying && test_and_clear_bit(_PGT_pinned, &page->u.inuse.type_info)); - spin_unlock(&pg_owner->page_alloc_lock); + nrspin_unlock(&pg_owner->page_alloc_lock); if ( drop_ref ) { pin_drop: @@ -4424,7 +4424,7 @@ int steal_page( * that it might be upon return from alloc_domheap_pages with * MEMF_no_owner set. */ - spin_lock(&d->page_alloc_lock); + nrspin_lock(&d->page_alloc_lock); BUG_ON(page->u.inuse.type_info & (PGT_count_mask | PGT_locked | PGT_pinned)); @@ -4436,7 +4436,7 @@ int steal_page( if ( !(memflags & MEMF_no_refcount) && !domain_adjust_tot_pages(d, -1) ) drop_dom_ref = true; - spin_unlock(&d->page_alloc_lock); + nrspin_unlock(&d->page_alloc_lock); if ( unlikely(drop_dom_ref) ) put_domain(d); diff --git a/xen/arch/x86/mm/mem_sharing.c b/xen/arch/x86/mm/mem_sharing.c index f58576c702..da28266ef0 100644 --- a/xen/arch/x86/mm/mem_sharing.c +++ b/xen/arch/x86/mm/mem_sharing.c @@ -740,11 +740,11 @@ static int page_make_private(struct domain *d, struct page_info *page) if ( !get_page(page, dom_cow) ) return -EINVAL; - spin_lock(&d->page_alloc_lock); + nrspin_lock(&d->page_alloc_lock); if ( d->is_dying ) { - spin_unlock(&d->page_alloc_lock); + nrspin_unlock(&d->page_alloc_lock); put_page(page); return -EBUSY; } @@ -752,7 +752,7 @@ static int page_make_private(struct domain *d, struct page_info *page) expected_type = (PGT_shared_page | PGT_validated | PGT_locked | 2); if ( page->u.inuse.type_info != expected_type ) { - spin_unlock(&d->page_alloc_lock); + nrspin_unlock(&d->page_alloc_lock); put_page(page); return -EEXIST; } @@ -769,7 +769,7 @@ static int page_make_private(struct domain *d, struct page_info *page) if ( domain_adjust_tot_pages(d, 1) == 1 ) get_knownalive_domain(d); page_list_add_tail(page, &d->page_list); - spin_unlock(&d->page_alloc_lock); + nrspin_unlock(&d->page_alloc_lock); put_page(page); diff --git a/xen/arch/x86/mm/p2m-pod.c b/xen/arch/x86/mm/p2m-pod.c index 65d31e5523..515a8c98a5 100644 --- a/xen/arch/x86/mm/p2m-pod.c +++ b/xen/arch/x86/mm/p2m-pod.c @@ -27,7 +27,7 @@ static always_inline void lock_page_alloc(struct p2m_domain *p2m) { page_alloc_mm_pre_lock(p2m->domain); - spin_lock(&(p2m->domain->page_alloc_lock)); + nrspin_lock(&(p2m->domain->page_alloc_lock)); page_alloc_mm_post_lock(p2m->domain, p2m->domain->arch.page_alloc_unlock_level); } @@ -35,7 +35,7 @@ static always_inline void lock_page_alloc(struct p2m_domain *p2m) static inline void unlock_page_alloc(struct p2m_domain *p2m) { page_alloc_mm_unlock(p2m->domain->arch.page_alloc_unlock_level); - spin_unlock(&(p2m->domain->page_alloc_lock)); + nrspin_unlock(&(p2m->domain->page_alloc_lock)); } /* diff --git a/xen/arch/x86/mm/p2m.c b/xen/arch/x86/mm/p2m.c index ca24cd4a67..6bdff9aee9 100644 --- a/xen/arch/x86/mm/p2m.c +++ b/xen/arch/x86/mm/p2m.c @@ -2228,7 +2228,7 @@ void audit_p2m(struct domain *d, /* Audit part two: walk the domain's page allocation list, checking * the m2p entries. */ - spin_lock(&d->page_alloc_lock); + nrspin_lock(&d->page_alloc_lock); page_list_for_each ( page, &d->page_list ) { mfn = mfn_x(page_to_mfn(page)); @@ -2280,7 +2280,7 @@ void audit_p2m(struct domain *d, P2M_PRINTK("OK: mfn=%#lx, gfn=%#lx, p2mfn=%#lx\n", mfn, gfn, mfn_x(p2mfn)); } - spin_unlock(&d->page_alloc_lock); + nrspin_unlock(&d->page_alloc_lock); pod_unlock(p2m); p2m_unlock(p2m); diff --git a/xen/arch/x86/tboot.c b/xen/arch/x86/tboot.c index 4c254b4e34..ba0700d2d5 100644 --- a/xen/arch/x86/tboot.c +++ b/xen/arch/x86/tboot.c @@ -205,14 +205,14 @@ static void tboot_gen_domain_integrity(const uint8_t key[TB_KEY_SIZE], continue; printk("MACing Domain %u\n", d->domain_id); - spin_lock(&d->page_alloc_lock); + nrspin_lock(&d->page_alloc_lock); page_list_for_each(page, &d->page_list) { void *pg = __map_domain_page(page); vmac_update(pg, PAGE_SIZE, &ctx); unmap_domain_page(pg); } - spin_unlock(&d->page_alloc_lock); + nrspin_unlock(&d->page_alloc_lock); if ( is_iommu_enabled(d) && is_vtd ) { diff --git a/xen/common/domctl.c b/xen/common/domctl.c index f5a71ee5f7..cb62b18a9d 100644 --- a/xen/common/domctl.c +++ b/xen/common/domctl.c @@ -621,14 +621,14 @@ long do_domctl(XEN_GUEST_HANDLE_PARAM(xen_domctl_t) u_domctl) { uint64_t new_max = op->u.max_mem.max_memkb >> (PAGE_SHIFT - 10); - spin_lock(&d->page_alloc_lock); + nrspin_lock(&d->page_alloc_lock); /* * NB. We removed a check that new_max >= current tot_pages; this means * that the domain will now be allowed to "ratchet" down to new_max. In * the meantime, while tot > max, all new allocations are disallowed. */ d->max_pages = min(new_max, (uint64_t)(typeof(d->max_pages))-1); - spin_unlock(&d->page_alloc_lock); + nrspin_unlock(&d->page_alloc_lock); break; } diff --git a/xen/common/grant_table.c b/xen/common/grant_table.c index 7708930882..e98e9da520 100644 --- a/xen/common/grant_table.c +++ b/xen/common/grant_table.c @@ -2376,7 +2376,7 @@ gnttab_transfer( mfn = page_to_mfn(page); } - spin_lock(&e->page_alloc_lock); + nrspin_lock(&e->page_alloc_lock); /* * Check that 'e' will accept the page and has reservation @@ -2387,7 +2387,7 @@ gnttab_transfer( unlikely(domain_tot_pages(e) >= e->max_pages) || unlikely(!(e->tot_pages + 1)) ) { - spin_unlock(&e->page_alloc_lock); + nrspin_unlock(&e->page_alloc_lock); if ( e->is_dying ) gdprintk(XENLOG_INFO, "Transferee d%d is dying\n", @@ -2411,7 +2411,7 @@ gnttab_transfer( * safely drop the lock and re-aquire it later to add page to the * pagelist. */ - spin_unlock(&e->page_alloc_lock); + nrspin_unlock(&e->page_alloc_lock); okay = gnttab_prepare_for_transfer(e, d, gop.ref); /* @@ -2427,9 +2427,9 @@ gnttab_transfer( * Need to grab this again to safely free our "reserved" * page in the page total */ - spin_lock(&e->page_alloc_lock); + nrspin_lock(&e->page_alloc_lock); drop_dom_ref = !domain_adjust_tot_pages(e, -1); - spin_unlock(&e->page_alloc_lock); + nrspin_unlock(&e->page_alloc_lock); if ( okay /* i.e. e->is_dying due to the surrounding if() */ ) gdprintk(XENLOG_INFO, "Transferee d%d is now dying\n", diff --git a/xen/common/memory.c b/xen/common/memory.c index b3b05c2ec0..b4593f5f45 100644 --- a/xen/common/memory.c +++ b/xen/common/memory.c @@ -770,10 +770,10 @@ static long memory_exchange(XEN_GUEST_HANDLE_PARAM(xen_memory_exchange_t) arg) (1UL << in_chunk_order)) - (j * (1UL << exch.out.extent_order))); - spin_lock(&d->page_alloc_lock); + nrspin_lock(&d->page_alloc_lock); drop_dom_ref = (dec_count && !domain_adjust_tot_pages(d, -dec_count)); - spin_unlock(&d->page_alloc_lock); + nrspin_unlock(&d->page_alloc_lock); if ( drop_dom_ref ) put_domain(d); diff --git a/xen/common/numa.c b/xen/common/numa.c index 6374ba1721..28a09766fa 100644 --- a/xen/common/numa.c +++ b/xen/common/numa.c @@ -719,13 +719,13 @@ static void cf_check dump_numa(unsigned char key) memset(page_num_node, 0, sizeof(page_num_node)); - spin_lock(&d->page_alloc_lock); + nrspin_lock(&d->page_alloc_lock); page_list_for_each ( page, &d->page_list ) { i = page_to_nid(page); page_num_node[i]++; } - spin_unlock(&d->page_alloc_lock); + nrspin_unlock(&d->page_alloc_lock); for_each_online_node ( i ) printk(" Node %u: %u\n", i, page_num_node[i]); diff --git a/xen/common/page_alloc.c b/xen/common/page_alloc.c index b4e0ef3a4c..20238015ed 100644 --- a/xen/common/page_alloc.c +++ b/xen/common/page_alloc.c @@ -514,7 +514,7 @@ int domain_set_outstanding_pages(struct domain *d, unsigned long pages) * must always take the global heap_lock rather than only in the much * rarer case that d->outstanding_pages is non-zero */ - spin_lock(&d->page_alloc_lock); + nrspin_lock(&d->page_alloc_lock); spin_lock(&heap_lock); /* pages==0 means "unset" the claim. */ @@ -560,7 +560,7 @@ int domain_set_outstanding_pages(struct domain *d, unsigned long pages) out: spin_unlock(&heap_lock); - spin_unlock(&d->page_alloc_lock); + nrspin_unlock(&d->page_alloc_lock); return ret; } @@ -2346,7 +2346,7 @@ int assign_pages( int rc = 0; unsigned int i; - spin_lock(&d->page_alloc_lock); + nrspin_lock(&d->page_alloc_lock); if ( unlikely(d->is_dying) ) { @@ -2428,7 +2428,7 @@ int assign_pages( } out: - spin_unlock(&d->page_alloc_lock); + nrspin_unlock(&d->page_alloc_lock); return rc; } @@ -2907,9 +2907,9 @@ mfn_t acquire_reserved_page(struct domain *d, unsigned int memflags) ASSERT_ALLOC_CONTEXT(); /* Acquire a page from reserved page list(resv_page_list). */ - spin_lock(&d->page_alloc_lock); + nrspin_lock(&d->page_alloc_lock); page = page_list_remove_head(&d->resv_page_list); - spin_unlock(&d->page_alloc_lock); + nrspin_unlock(&d->page_alloc_lock); if ( unlikely(!page) ) return INVALID_MFN; @@ -2928,9 +2928,9 @@ mfn_t acquire_reserved_page(struct domain *d, unsigned int memflags) */ unprepare_staticmem_pages(page, 1, false); fail: - spin_lock(&d->page_alloc_lock); + nrspin_lock(&d->page_alloc_lock); page_list_add_tail(page, &d->resv_page_list); - spin_unlock(&d->page_alloc_lock); + nrspin_unlock(&d->page_alloc_lock); return INVALID_MFN; } #endif diff --git a/xen/drivers/char/console.c b/xen/drivers/char/console.c index ccd5f8cc14..22f50fc617 100644 --- a/xen/drivers/char/console.c +++ b/xen/drivers/char/console.c @@ -368,9 +368,9 @@ long read_console_ring(struct xen_sysctl_readconsole *op) if ( op->clear ) { - spin_lock_irq(&console_lock); + nrspin_lock_irq(&console_lock); conringc = p - c > conring_size ? p - conring_size : c; - spin_unlock_irq(&console_lock); + nrspin_unlock_irq(&console_lock); } op->count = sofar; @@ -638,7 +638,7 @@ static long guest_console_write(XEN_GUEST_HANDLE_PARAM(char) buffer, if ( is_hardware_domain(cd) ) { /* Use direct console output as it could be interactive */ - spin_lock_irq(&console_lock); + nrspin_lock_irq(&console_lock); console_serial_puts(kbuf, kcount); video_puts(kbuf, kcount); @@ -659,7 +659,7 @@ static long guest_console_write(XEN_GUEST_HANDLE_PARAM(char) buffer, tasklet_schedule(&notify_dom0_con_ring_tasklet); } - spin_unlock_irq(&console_lock); + nrspin_unlock_irq(&console_lock); } else { @@ -1026,9 +1026,9 @@ void __init console_init_preirq(void) pv_console_set_rx_handler(serial_rx); /* HELLO WORLD --- start-of-day banner text. */ - spin_lock(&console_lock); + nrspin_lock(&console_lock); __putstr(xen_banner()); - spin_unlock(&console_lock); + nrspin_unlock(&console_lock); printk("Xen version %d.%d%s (%s@%s) (%s) %s %s\n", xen_major_version(), xen_minor_version(), xen_extra_version(), xen_compile_by(), xen_compile_domain(), xen_compiler(), @@ -1065,13 +1065,13 @@ void __init console_init_ring(void) } opt_conring_size = PAGE_SIZE << order; - spin_lock_irqsave(&console_lock, flags); + nrspin_lock_irqsave(&console_lock, flags); for ( i = conringc ; i != conringp; i++ ) ring[i & (opt_conring_size - 1)] = conring[i & (conring_size - 1)]; conring = ring; smp_wmb(); /* Allow users of console_force_unlock() to see larger buffer. */ conring_size = opt_conring_size; - spin_unlock_irqrestore(&console_lock, flags); + nrspin_unlock_irqrestore(&console_lock, flags); printk("Allocated console ring of %u KiB.\n", opt_conring_size >> 10); } diff --git a/xen/include/xen/spinlock.h b/xen/include/xen/spinlock.h index 49c5115f52..f912fa968c 100644 --- a/xen/include/xen/spinlock.h +++ b/xen/include/xen/spinlock.h @@ -102,6 +102,9 @@ struct lock_profile_qhead { }; #define LOCK_PROFILE_(lockname) { .name = #lockname, .ptr.lock = &(lockname), } +#define RLOCK_PROFILE_(lockname) { .name = #lockname, \ + .ptr.rlock = &(lockname), \ + .is_rlock = true, } #define LOCK_PROFILE_PTR_(name) \ static struct lock_profile * const lock_profile__##name \ __used_section(".lockprofile.data") = \ @@ -118,10 +121,10 @@ struct lock_profile_qhead { LOCK_PROFILE_PTR_(l) #define DEFINE_RSPINLOCK(l) \ rspinlock_t l = SPIN_LOCK_UNLOCKED_(NULL); \ - static struct lock_profile lock_profile_data__##l = LOCK_PROFILE_(l); \ + static struct lock_profile lock_profile_data__##l = RLOCK_PROFILE_(l); \ LOCK_PROFILE_PTR_(l) -#define spin_lock_init_prof__(s, l, locktype) \ +#define spin_lock_init_prof__(s, l, lockptr, locktype, isr) \ do { \ struct lock_profile *prof; \ prof = xzalloc(struct lock_profile); \ @@ -134,13 +137,16 @@ struct lock_profile_qhead { break; \ } \ prof->name = #l; \ - prof->ptr.lock = &(s)->l; \ + prof->ptr.lockptr = &(s)->l; \ + prof->is_rlock = isr; \ prof->next = (s)->profile_head.elem_q; \ (s)->profile_head.elem_q = prof; \ } while( 0 ) -#define spin_lock_init_prof(s, l) spin_lock_init_prof__(s, l, spinlock_t) -#define rspin_lock_init_prof(s, l) spin_lock_init_prof__(s, l, rspinlock_t) +#define spin_lock_init_prof(s, l) \ + spin_lock_init_prof__(s, l, lock, spinlock_t, false) +#define rspin_lock_init_prof(s, l) \ + spin_lock_init_prof__(s, l, rlock, rspinlock_t, true) void _lock_profile_register_struct( int32_t type, struct lock_profile_qhead *qhead, int32_t idx); @@ -274,7 +280,10 @@ static always_inline void spin_lock_if(bool condition, spinlock_t *l) * reentered recursively on the same CPU. All critical regions that may form * part of a recursively-nested set must be protected by these forms. If there * are any critical regions that cannot form part of such a set, they can use - * standard spin_[un]lock(). + * nrspin_[un]lock(). + * The nrspin_[un]lock() forms act the same way as normal spin_[un]lock() + * calls, but operate on rspinlock_t locks. nrspin_lock() and rspin_lock() + * calls are blocking to each other for a specific lock even on the same cpu. */ bool _rspin_trylock(rspinlock_t *lock); void _rspin_lock(rspinlock_t *lock); @@ -298,4 +307,12 @@ static always_inline void rspin_lock(rspinlock_t *lock) #define rspin_unlock(l) _rspin_unlock(l) #define rspin_unlock_irqrestore(l, f) _rspin_unlock_irqrestore(l, f) +#define nrspin_trylock(l) spin_trylock(l) +#define nrspin_lock(l) spin_lock(l) +#define nrspin_unlock(l) spin_unlock(l) +#define nrspin_lock_irq(l) spin_lock_irq(l) +#define nrspin_unlock_irq(l) spin_unlock_irq(l) +#define nrspin_lock_irqsave(l, f) spin_lock_irqsave(l, f) +#define nrspin_unlock_irqrestore(l, f) spin_unlock_irqrestore(l, f) + #endif /* __SPINLOCK_H__ */

[v5,06/13] xen/spinlock: add explicit non-recursive locking functions

Commit Message

Patch