From nobody Sat Apr 27 09:56:35 2024 Delivered-To: importer@patchew.org Received-SPF: pass (zoho.com: domain of gnu.org designates 208.118.235.17 as permitted sender) client-ip=208.118.235.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Authentication-Results: mx.zohomail.com; spf=pass (zoho.com: domain of gnu.org designates 208.118.235.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org Return-Path: Received: from lists.gnu.org (lists.gnu.org [208.118.235.17]) by mx.zohomail.com with SMTPS id 1526946284664862.6869379447596; Mon, 21 May 2018 16:44:44 -0700 (PDT) Received: from localhost ([::1]:52866 helo=lists.gnu.org) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1fKuTr-0006Ds-LX for importer@patchew.org; Mon, 21 May 2018 19:44:43 -0400 Received: from eggs.gnu.org ([2001:4830:134:3::10]:57823) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1fKuOt-0002eD-4v for qemu-devel@nongnu.org; Mon, 21 May 2018 19:39:38 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1fKuOo-0005Wp-J0 for qemu-devel@nongnu.org; Mon, 21 May 2018 19:39:35 -0400 Received: from out1-smtp.messagingengine.com ([66.111.4.25]:58847) by eggs.gnu.org with esmtps (TLS1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.71) (envelope-from ) id 1fKuOo-0005Uo-EV for qemu-devel@nongnu.org; Mon, 21 May 2018 19:39:30 -0400 Received: from compute4.internal (compute4.nyi.internal [10.202.2.44]) by mailout.nyi.internal (Postfix) with ESMTP id 9F68622534; Mon, 21 May 2018 19:39:28 -0400 (EDT) Received: from mailfrontend2 ([10.202.2.163]) by compute4.internal (MEProxy); Mon, 21 May 2018 19:39:28 -0400 Received: from localhost (flamenco.cs.columbia.edu [128.59.20.216]) by mail.messagingengine.com (Postfix) with ESMTPA id 455201025C; Mon, 21 May 2018 19:39:28 -0400 (EDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=braap.org; h=cc :content-transfer-encoding:content-type:date:from:in-reply-to :message-id:mime-version:references:subject:to:x-me-sender :x-me-sender:x-sasl-enc; s=mesmtp; bh=qP6g5d8qbG8FSj8S8FVfM8WoW3 Qw3N77wq8Xu+DWeds=; b=o/9yW0k3GdTtBoUvlGhJt+1t+Jm5P0o9+XhiN2jrZm Z+OExR+Fl3JWPc3HWa9MkN0sePEvir/GkR6gT5IrxbwrwwD4LCJCGJ28gHcFFhIf kVxnLxiBRFCDPzD1ZyYJhzKUVuSkzDi9GkbbiNN/gYYdT+4tOXHqO9YOpuF5ub74 Q= DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d= messagingengine.com; h=cc:content-transfer-encoding:content-type :date:from:in-reply-to:message-id:mime-version:references :subject:to:x-me-sender:x-me-sender:x-sasl-enc; s=fm2; bh=qP6g5d 8qbG8FSj8S8FVfM8WoW3Qw3N77wq8Xu+DWeds=; b=Hc6Z1Uk0AXCEF1YpXuInX0 vMau7Ef6pXQ9B9DcvWx+PcW5m9rqOrlyQSisC5Ls3F1N9+FxKc6BVZTpN8mBHxBO 78/zQnoYYD2m3wk8nqoJ062xpHBp5H6gkTMxVQTsn7G24H98uS/Kg+TLSyFoK7ed QY41ub/cu943XPAT7j/4ug+uR/gho8XhTVqfFPNlmSfKDJxIQBn3nq7He6fKJtps 7NUZCKo3Q43GNaU0sV5bcpLlkHreIiTX4i4o76LRsPLx0uuA7P4hv+QkXg6mYbJk Y2QohtnuCTBN8/gkkMii6rjSjQavahQyZ7opYx0aOjoTRq7Fic5/7aUbS0ejSotw == X-ME-Proxy: X-ME-Proxy: X-ME-Proxy: X-ME-Proxy: X-ME-Proxy: X-ME-Proxy: X-ME-Sender: From: "Emilio G. Cota" To: qemu-devel@nongnu.org Date: Mon, 21 May 2018 19:39:11 -0400 Message-Id: <1526945967-9687-2-git-send-email-cota@braap.org> X-Mailer: git-send-email 2.7.4 In-Reply-To: <1526945967-9687-1-git-send-email-cota@braap.org> References: <1526945967-9687-1-git-send-email-cota@braap.org> MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable X-detected-operating-system: by eggs.gnu.org: GNU/Linux 2.2.x-3.x [generic] [fuzzy] X-Received-From: 66.111.4.25 Subject: [Qemu-devel] [PATCH v3 01/17] qht: require a default comparison function X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.21 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: =?UTF-8?q?Alex=20Benn=C3=A9e?= , Richard Henderson , Paolo Bonzini Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: "Qemu-devel" X-ZohoMail: RSF_0 Z_629925259 SPT_0 qht_lookup now uses the default cmp function. qht_lookup_custom is defined to retain the old behaviour, that is a cmp function is explicitly provided. qht_insert will gain use of the default cmp in the next patch. Note that we move qht_lookup_custom's @func to be the last argument, which makes the new qht_lookup as simple as possible. Instead of this (i.e. keeping @func 2nd): 0000000000010750 : 10750: 89 d1 mov %edx,%ecx 10752: 48 89 f2 mov %rsi,%rdx 10755: 48 8b 77 08 mov 0x8(%rdi),%rsi 10759: e9 22 ff ff ff jmpq 10680 1075e: 66 90 xchg %ax,%ax We get: 0000000000010740 : 10740: 48 8b 4f 08 mov 0x8(%rdi),%rcx 10744: e9 37 ff ff ff jmpq 10680 10749: 0f 1f 80 00 00 00 00 nopl 0x0(%rax) Reviewed-by: Richard Henderson Reviewed-by: Alex Benn=C3=A9e Signed-off-by: Emilio G. Cota Tested-by: Alex Benn=C3=A9e --- include/qemu/qht.h | 25 ++++++++++++++++++++----- accel/tcg/cpu-exec.c | 4 ++-- accel/tcg/translate-all.c | 16 +++++++++++++++- tests/qht-bench.c | 14 +++++++------- tests/test-qht.c | 15 ++++++++++----- util/qht.c | 14 +++++++++++--- 6 files changed, 65 insertions(+), 23 deletions(-) diff --git a/include/qemu/qht.h b/include/qemu/qht.h index 531aa95..5f03a0f 100644 --- a/include/qemu/qht.h +++ b/include/qemu/qht.h @@ -11,8 +11,11 @@ #include "qemu/thread.h" #include "qemu/qdist.h" =20 +typedef bool (*qht_cmp_func_t)(const void *a, const void *b); + struct qht { struct qht_map *map; + qht_cmp_func_t cmp; QemuMutex lock; /* serializes setters of ht->map */ unsigned int mode; }; @@ -47,10 +50,12 @@ typedef void (*qht_iter_func_t)(struct qht *ht, void *p= , uint32_t h, void *up); /** * qht_init - Initialize a QHT * @ht: QHT to be initialized + * @cmp: default comparison function. Cannot be NULL. * @n_elems: number of entries the hash table should be optimized for. * @mode: bitmask with OR'ed QHT_MODE_* */ -void qht_init(struct qht *ht, size_t n_elems, unsigned int mode); +void qht_init(struct qht *ht, qht_cmp_func_t cmp, size_t n_elems, + unsigned int mode); =20 /** * qht_destroy - destroy a previously initialized QHT @@ -78,11 +83,11 @@ void qht_destroy(struct qht *ht); bool qht_insert(struct qht *ht, void *p, uint32_t hash); =20 /** - * qht_lookup - Look up a pointer in a QHT + * qht_lookup_custom - Look up a pointer using a custom comparison functio= n. * @ht: QHT to be looked up - * @func: function to compare existing pointers against @userp * @userp: pointer to pass to @func * @hash: hash of the pointer to be looked up + * @func: function to compare existing pointers against @userp * * Needs to be called under an RCU read-critical section. * @@ -94,8 +99,18 @@ bool qht_insert(struct qht *ht, void *p, uint32_t hash); * Returns the corresponding pointer when a match is found. * Returns NULL otherwise. */ -void *qht_lookup(struct qht *ht, qht_lookup_func_t func, const void *userp, - uint32_t hash); +void *qht_lookup_custom(struct qht *ht, const void *userp, uint32_t hash, + qht_lookup_func_t func); + +/** + * qht_lookup - Look up a pointer in a QHT + * @ht: QHT to be looked up + * @userp: pointer to pass to the comparison function + * @hash: hash of the pointer to be looked up + * + * Calls qht_lookup_custom() using @ht's default comparison function. + */ +void *qht_lookup(struct qht *ht, const void *userp, uint32_t hash); =20 /** * qht_remove - remove a pointer from the hash table diff --git a/accel/tcg/cpu-exec.c b/accel/tcg/cpu-exec.c index 0b154cc..aefc682 100644 --- a/accel/tcg/cpu-exec.c +++ b/accel/tcg/cpu-exec.c @@ -296,7 +296,7 @@ struct tb_desc { uint32_t trace_vcpu_dstate; }; =20 -static bool tb_cmp(const void *p, const void *d) +static bool tb_lookup_cmp(const void *p, const void *d) { const TranslationBlock *tb =3D p; const struct tb_desc *desc =3D d; @@ -341,7 +341,7 @@ TranslationBlock *tb_htable_lookup(CPUState *cpu, targe= t_ulong pc, phys_pc =3D get_page_addr_code(desc.env, pc); desc.phys_page1 =3D phys_pc & TARGET_PAGE_MASK; h =3D tb_hash_func(phys_pc, pc, flags, cf_mask, *cpu->trace_dstate); - return qht_lookup(&tb_ctx.htable, tb_cmp, &desc, h); + return qht_lookup_custom(&tb_ctx.htable, &desc, h, tb_lookup_cmp); } =20 void tb_set_jmp_target(TranslationBlock *tb, int n, uintptr_t addr) diff --git a/accel/tcg/translate-all.c b/accel/tcg/translate-all.c index 732c919..5b7b91d 100644 --- a/accel/tcg/translate-all.c +++ b/accel/tcg/translate-all.c @@ -782,11 +782,25 @@ static inline void code_gen_alloc(size_t tb_size) qemu_mutex_init(&tb_ctx.tb_lock); } =20 +static bool tb_cmp(const void *ap, const void *bp) +{ + const TranslationBlock *a =3D ap; + const TranslationBlock *b =3D bp; + + return a->pc =3D=3D b->pc && + a->cs_base =3D=3D b->cs_base && + a->flags =3D=3D b->flags && + (tb_cflags(a) & CF_HASH_MASK) =3D=3D (tb_cflags(b) & CF_HASH_MASK)= && + a->trace_vcpu_dstate =3D=3D b->trace_vcpu_dstate && + a->page_addr[0] =3D=3D b->page_addr[0] && + a->page_addr[1] =3D=3D b->page_addr[1]; +} + static void tb_htable_init(void) { unsigned int mode =3D QHT_MODE_AUTO_RESIZE; =20 - qht_init(&tb_ctx.htable, CODE_GEN_HTABLE_SIZE, mode); + qht_init(&tb_ctx.htable, tb_cmp, CODE_GEN_HTABLE_SIZE, mode); } =20 /* Must be called before using the QEMU cpus. 'tb_size' is the size diff --git a/tests/qht-bench.c b/tests/qht-bench.c index 4cabdfd..c94ac25 100644 --- a/tests/qht-bench.c +++ b/tests/qht-bench.c @@ -93,10 +93,10 @@ static void usage_complete(int argc, char *argv[]) exit(-1); } =20 -static bool is_equal(const void *obj, const void *userp) +static bool is_equal(const void *ap, const void *bp) { - const long *a =3D obj; - const long *b =3D userp; + const long *a =3D ap; + const long *b =3D bp; =20 return *a =3D=3D *b; } @@ -150,7 +150,7 @@ static void do_rw(struct thread_info *info) =20 p =3D &keys[info->r & (lookup_range - 1)]; hash =3D h(*p); - read =3D qht_lookup(&ht, is_equal, p, hash); + read =3D qht_lookup(&ht, p, hash); if (read) { stats->rd++; } else { @@ -162,7 +162,7 @@ static void do_rw(struct thread_info *info) if (info->write_op) { bool written =3D false; =20 - if (qht_lookup(&ht, is_equal, p, hash) =3D=3D NULL) { + if (qht_lookup(&ht, p, hash) =3D=3D NULL) { written =3D qht_insert(&ht, p, hash); } if (written) { @@ -173,7 +173,7 @@ static void do_rw(struct thread_info *info) } else { bool removed =3D false; =20 - if (qht_lookup(&ht, is_equal, p, hash)) { + if (qht_lookup(&ht, p, hash)) { removed =3D qht_remove(&ht, p, hash); } if (removed) { @@ -308,7 +308,7 @@ static void htable_init(void) } =20 /* initialize the hash table */ - qht_init(&ht, qht_n_elems, qht_mode); + qht_init(&ht, is_equal, qht_n_elems, qht_mode); assert(init_size <=3D init_range); =20 pr_params(); diff --git a/tests/test-qht.c b/tests/test-qht.c index 9b7423a..b069881 100644 --- a/tests/test-qht.c +++ b/tests/test-qht.c @@ -13,10 +13,10 @@ static struct qht ht; static int32_t arr[N * 2]; =20 -static bool is_equal(const void *obj, const void *userp) +static bool is_equal(const void *ap, const void *bp) { - const int32_t *a =3D obj; - const int32_t *b =3D userp; + const int32_t *a =3D ap; + const int32_t *b =3D bp; =20 return *a =3D=3D *b; } @@ -60,7 +60,12 @@ static void check(int a, int b, bool expected) =20 val =3D i; hash =3D i; - p =3D qht_lookup(&ht, is_equal, &val, hash); + /* test both lookup variants; results should be the same */ + if (i % 2) { + p =3D qht_lookup(&ht, &val, hash); + } else { + p =3D qht_lookup_custom(&ht, &val, hash, is_equal); + } g_assert_true(!!p =3D=3D expected); } rcu_read_unlock(); @@ -102,7 +107,7 @@ static void qht_do_test(unsigned int mode, size_t init_= entries) /* under KVM we might fetch stats from an uninitialized qht */ check_n(0); =20 - qht_init(&ht, 0, mode); + qht_init(&ht, is_equal, 0, mode); =20 check_n(0); insert(0, N); diff --git a/util/qht.c b/util/qht.c index ff4d2e6..8610ce3 100644 --- a/util/qht.c +++ b/util/qht.c @@ -351,11 +351,14 @@ static struct qht_map *qht_map_create(size_t n_bucket= s) return map; } =20 -void qht_init(struct qht *ht, size_t n_elems, unsigned int mode) +void qht_init(struct qht *ht, qht_cmp_func_t cmp, size_t n_elems, + unsigned int mode) { struct qht_map *map; size_t n_buckets =3D qht_elems_to_buckets(n_elems); =20 + g_assert(cmp); + ht->cmp =3D cmp; ht->mode =3D mode; qemu_mutex_init(&ht->lock); map =3D qht_map_create(n_buckets); @@ -479,8 +482,8 @@ void *qht_lookup__slowpath(struct qht_bucket *b, qht_lo= okup_func_t func, return ret; } =20 -void *qht_lookup(struct qht *ht, qht_lookup_func_t func, const void *userp, - uint32_t hash) +void *qht_lookup_custom(struct qht *ht, const void *userp, uint32_t hash, + qht_lookup_func_t func) { struct qht_bucket *b; struct qht_map *map; @@ -502,6 +505,11 @@ void *qht_lookup(struct qht *ht, qht_lookup_func_t fun= c, const void *userp, return qht_lookup__slowpath(b, func, userp, hash); } =20 +void *qht_lookup(struct qht *ht, const void *userp, uint32_t hash) +{ + return qht_lookup_custom(ht, userp, hash, ht->cmp); +} + /* call with head->lock held */ static bool qht_insert__locked(struct qht *ht, struct qht_map *map, struct qht_bucket *head, void *p, uint32_t = hash, --=20 2.7.4 From nobody Sat Apr 27 09:56:35 2024 Delivered-To: importer@patchew.org Received-SPF: pass (zoho.com: domain of gnu.org designates 208.118.235.17 as permitted sender) client-ip=208.118.235.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Authentication-Results: mx.zohomail.com; spf=pass (zoho.com: domain of gnu.org designates 208.118.235.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org Return-Path: Received: from lists.gnu.org (lists.gnu.org [208.118.235.17]) by mx.zohomail.com with SMTPS id 15269466691942.7955927666558864; Mon, 21 May 2018 16:51:09 -0700 (PDT) Received: from localhost ([::1]:52904 helo=lists.gnu.org) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1fKua4-0002mE-7k for importer@patchew.org; Mon, 21 May 2018 19:51:08 -0400 Received: from eggs.gnu.org ([2001:4830:134:3::10]:57824) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1fKuOt-0002eE-5D for qemu-devel@nongnu.org; Mon, 21 May 2018 19:39:38 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1fKuOo-0005Wk-Ih for qemu-devel@nongnu.org; Mon, 21 May 2018 19:39:35 -0400 Received: from out1-smtp.messagingengine.com ([66.111.4.25]:37515) by eggs.gnu.org with esmtps (TLS1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.71) (envelope-from ) id 1fKuOo-0005Uw-EY for qemu-devel@nongnu.org; Mon, 21 May 2018 19:39:30 -0400 Received: from compute4.internal (compute4.nyi.internal [10.202.2.44]) by mailout.nyi.internal (Postfix) with ESMTP id D01A82255B; Mon, 21 May 2018 19:39:28 -0400 (EDT) Received: from mailfrontend1 ([10.202.2.162]) by compute4.internal (MEProxy); Mon, 21 May 2018 19:39:28 -0400 Received: from localhost (flamenco.cs.columbia.edu [128.59.20.216]) by mail.messagingengine.com (Postfix) with ESMTPA id 7EFB0E4119; Mon, 21 May 2018 19:39:28 -0400 (EDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=braap.org; h=cc :date:from:in-reply-to:message-id:references:subject:to :x-me-sender:x-me-sender:x-sasl-enc; s=mesmtp; bh=0JfffYvJT/zi+m aTtE4fKFjRujGvnAj4XAZ6tBk7m0s=; b=xAQyLgg1pw2p3+/mXP0uBwmsxQIFRX FtbrfFQApVTCJW3Ma/PFkkk5jESlMGQZWhC1vo0lcTDjDgJvLaa7CG85/QVOT4oI BUnYPS84ZZNqrfLlv2kKeI/DUOF531nFWVVRxKbrrfYMYHobUFLCPFCN7TzbiL2w IP7tjZlF1xmyM= DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d= messagingengine.com; h=cc:date:from:in-reply-to:message-id :references:subject:to:x-me-sender:x-me-sender:x-sasl-enc; s= fm2; bh=0JfffYvJT/zi+maTtE4fKFjRujGvnAj4XAZ6tBk7m0s=; b=AVpvjXYq GOd3tjYw21j1AKA64IPePRb43C6hIJQLXD7iBx4jsGBXKxZ0u3tBxazbaMfxm4E2 vjLt2R23q9UCvvAUxnxX0VKNW12U2Sya6NSQLiGKA0gnew34pRUYl8p5wWggthoA DuGwMDbdRHL7ENILigsgY27xE9qqE/e9NWt86Fv9Jil06soW26z4IT6r2Vw5hgwa zlEBFZ6GHTXSFn9fcTG8xVnZUcZGAFAihE24Jv7sKZRoTEnCxcRCF/vDtmZaB4lb 2331lByaLfgvpcPnQq81rM4n1a5iGTmWr8Vv7lyCuv3OZpVvRztfy/tUPtzaBfYj 9evCXqNN+h9jpw== X-ME-Proxy: X-ME-Proxy: X-ME-Proxy: X-ME-Proxy: X-ME-Proxy: X-ME-Proxy: X-ME-Sender: From: "Emilio G. Cota" To: qemu-devel@nongnu.org Date: Mon, 21 May 2018 19:39:12 -0400 Message-Id: <1526945967-9687-3-git-send-email-cota@braap.org> X-Mailer: git-send-email 2.7.4 In-Reply-To: <1526945967-9687-1-git-send-email-cota@braap.org> References: <1526945967-9687-1-git-send-email-cota@braap.org> X-detected-operating-system: by eggs.gnu.org: GNU/Linux 2.2.x-3.x [generic] [fuzzy] X-Received-From: 66.111.4.25 Subject: [Qemu-devel] [PATCH v3 02/17] qht: return existing entry when qht_insert fails X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.21 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: =?UTF-8?q?Alex=20Benn=C3=A9e?= , Richard Henderson , Paolo Bonzini Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: "Qemu-devel" X-ZohoMail: RSF_0 Z_629925259 SPT_0 Content-Transfer-Encoding: quoted-printable MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" The meaning of "existing" is now changed to "matches in hash and ht->cmp result". This is saner than just checking the pointer value. Suggested-by: Richard Henderson Reviewed-by: Richard Henderson Signed-off-by: Emilio G. Cota Reviewed-by: Alex Benn=C3=A9e Tested-by: Alex Benn=C3=A9e --- include/qemu/qht.h | 7 +++++-- accel/tcg/translate-all.c | 2 +- tests/qht-bench.c | 4 ++-- tests/test-qht.c | 8 +++++++- util/qht.c | 27 +++++++++++++++++---------- 5 files changed, 32 insertions(+), 16 deletions(-) diff --git a/include/qemu/qht.h b/include/qemu/qht.h index 5f03a0f..1fb9116 100644 --- a/include/qemu/qht.h +++ b/include/qemu/qht.h @@ -70,6 +70,7 @@ void qht_destroy(struct qht *ht); * @ht: QHT to insert to * @p: pointer to be inserted * @hash: hash corresponding to @p + * @existing: address where the pointer to an existing entry can be copied= to * * Attempting to insert a NULL @p is a bug. * Inserting the same pointer @p with different @hash values is a bug. @@ -78,9 +79,11 @@ void qht_destroy(struct qht *ht); * inserted into the hash table. * * Returns true on success. - * Returns false if the @p-@hash pair already exists in the hash table. + * Returns false if there is an existing entry in the table that is equiva= lent + * (i.e. ht->cmp matches and the hash is the same) to @p-@h. If @existing + * is !NULL, a pointer to this existing entry is copied to it. */ -bool qht_insert(struct qht *ht, void *p, uint32_t hash); +bool qht_insert(struct qht *ht, void *p, uint32_t hash, void **existing); =20 /** * qht_lookup_custom - Look up a pointer using a custom comparison functio= n. diff --git a/accel/tcg/translate-all.c b/accel/tcg/translate-all.c index 5b7b91d..8080eb7 100644 --- a/accel/tcg/translate-all.c +++ b/accel/tcg/translate-all.c @@ -1242,7 +1242,7 @@ static void tb_link_page(TranslationBlock *tb, tb_pag= e_addr_t phys_pc, /* add in the hash table */ h =3D tb_hash_func(phys_pc, tb->pc, tb->flags, tb->cflags & CF_HASH_MA= SK, tb->trace_vcpu_dstate); - qht_insert(&tb_ctx.htable, tb, h); + qht_insert(&tb_ctx.htable, tb, h, NULL); =20 #ifdef CONFIG_USER_ONLY if (DEBUG_TB_CHECK_GATE) { diff --git a/tests/qht-bench.c b/tests/qht-bench.c index c94ac25..f492b3a 100644 --- a/tests/qht-bench.c +++ b/tests/qht-bench.c @@ -163,7 +163,7 @@ static void do_rw(struct thread_info *info) bool written =3D false; =20 if (qht_lookup(&ht, p, hash) =3D=3D NULL) { - written =3D qht_insert(&ht, p, hash); + written =3D qht_insert(&ht, p, hash, NULL); } if (written) { stats->in++; @@ -322,7 +322,7 @@ static void htable_init(void) r =3D xorshift64star(r); p =3D &keys[r & (init_range - 1)]; hash =3D h(*p); - if (qht_insert(&ht, p, hash)) { + if (qht_insert(&ht, p, hash, NULL)) { break; } retries++; diff --git a/tests/test-qht.c b/tests/test-qht.c index b069881..dda6a06 100644 --- a/tests/test-qht.c +++ b/tests/test-qht.c @@ -27,11 +27,17 @@ static void insert(int a, int b) =20 for (i =3D a; i < b; i++) { uint32_t hash; + void *existing; + bool inserted; =20 arr[i] =3D i; hash =3D i; =20 - qht_insert(&ht, &arr[i], hash); + inserted =3D qht_insert(&ht, &arr[i], hash, NULL); + g_assert_true(inserted); + inserted =3D qht_insert(&ht, &arr[i], hash, &existing); + g_assert_false(inserted); + g_assert_true(existing =3D=3D &arr[i]); } } =20 diff --git a/util/qht.c b/util/qht.c index 8610ce3..9d030e7 100644 --- a/util/qht.c +++ b/util/qht.c @@ -511,9 +511,9 @@ void *qht_lookup(struct qht *ht, const void *userp, uin= t32_t hash) } =20 /* call with head->lock held */ -static bool qht_insert__locked(struct qht *ht, struct qht_map *map, - struct qht_bucket *head, void *p, uint32_t = hash, - bool *needs_resize) +static void *qht_insert__locked(struct qht *ht, struct qht_map *map, + struct qht_bucket *head, void *p, uint32_t= hash, + bool *needs_resize) { struct qht_bucket *b =3D head; struct qht_bucket *prev =3D NULL; @@ -523,8 +523,9 @@ static bool qht_insert__locked(struct qht *ht, struct q= ht_map *map, do { for (i =3D 0; i < QHT_BUCKET_ENTRIES; i++) { if (b->pointers[i]) { - if (unlikely(b->pointers[i] =3D=3D p)) { - return false; + if (unlikely(b->hashes[i] =3D=3D hash && + ht->cmp(b->pointers[i], p))) { + return b->pointers[i]; } } else { goto found; @@ -553,7 +554,7 @@ static bool qht_insert__locked(struct qht *ht, struct q= ht_map *map, atomic_set(&b->hashes[i], hash); atomic_set(&b->pointers[i], p); seqlock_write_end(&head->sequence); - return true; + return NULL; } =20 static __attribute__((noinline)) void qht_grow_maybe(struct qht *ht) @@ -577,25 +578,31 @@ static __attribute__((noinline)) void qht_grow_maybe(= struct qht *ht) qemu_mutex_unlock(&ht->lock); } =20 -bool qht_insert(struct qht *ht, void *p, uint32_t hash) +bool qht_insert(struct qht *ht, void *p, uint32_t hash, void **existing) { struct qht_bucket *b; struct qht_map *map; bool needs_resize =3D false; - bool ret; + void *prev; =20 /* NULL pointers are not supported */ qht_debug_assert(p); =20 b =3D qht_bucket_lock__no_stale(ht, hash, &map); - ret =3D qht_insert__locked(ht, map, b, p, hash, &needs_resize); + prev =3D qht_insert__locked(ht, map, b, p, hash, &needs_resize); qht_bucket_debug__locked(b); qemu_spin_unlock(&b->lock); =20 if (unlikely(needs_resize) && ht->mode & QHT_MODE_AUTO_RESIZE) { qht_grow_maybe(ht); } - return ret; + if (likely(prev =3D=3D NULL)) { + return true; + } + if (existing) { + *existing =3D prev; + } + return false; } =20 static inline bool qht_entry_is_last(struct qht_bucket *b, int pos) --=20 2.7.4 From nobody Sat Apr 27 09:56:35 2024 Delivered-To: importer@patchew.org Received-SPF: pass (zoho.com: domain of gnu.org designates 208.118.235.17 as permitted sender) client-ip=208.118.235.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Authentication-Results: mx.zohomail.com; spf=pass (zoho.com: domain of gnu.org designates 208.118.235.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org Return-Path: Received: from lists.gnu.org (208.118.235.17 [208.118.235.17]) by mx.zohomail.com with SMTPS id 1526946823083922.6235051581517; Mon, 21 May 2018 16:53:43 -0700 (PDT) Received: from localhost ([::1]:52913 helo=lists.gnu.org) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1fKucW-0004bs-Do for importer@patchew.org; Mon, 21 May 2018 19:53:40 -0400 Received: from eggs.gnu.org ([2001:4830:134:3::10]:57828) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1fKuOt-0002eH-6F for qemu-devel@nongnu.org; Mon, 21 May 2018 19:39:39 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1fKuOo-0005X9-Uy for qemu-devel@nongnu.org; Mon, 21 May 2018 19:39:35 -0400 Received: from out1-smtp.messagingengine.com ([66.111.4.25]:50923) by eggs.gnu.org with esmtps (TLS1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.71) (envelope-from ) id 1fKuOo-0005V1-QO for qemu-devel@nongnu.org; Mon, 21 May 2018 19:39:30 -0400 Received: from compute4.internal (compute4.nyi.internal [10.202.2.44]) by mailout.nyi.internal (Postfix) with ESMTP id 2568022564; Mon, 21 May 2018 19:39:29 -0400 (EDT) Received: from mailfrontend2 ([10.202.2.163]) by compute4.internal (MEProxy); Mon, 21 May 2018 19:39:29 -0400 Received: from localhost (flamenco.cs.columbia.edu [128.59.20.216]) by mail.messagingengine.com (Postfix) with ESMTPA id BA9861025C; Mon, 21 May 2018 19:39:28 -0400 (EDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=braap.org; h=cc :content-transfer-encoding:content-type:date:from:in-reply-to :message-id:mime-version:references:subject:to:x-me-sender :x-me-sender:x-sasl-enc; s=mesmtp; bh=flEBxI1VLRsDk/c4I2fxuzdQkU v3yxk99fRpCyTvqtM=; b=XNh6A7Di77+64ChrF3c/uYQg2kBT2iwTrvlxerR4aG zi/ePQ2iC9fFh3jiNXyJLtpGlWPWMpY6B+6Zqom/6Sb+t9Ddz1Wo3SUCE0qLSrTy gfWgl7JFbqlJZWs/iBq9gXlPkMbzQKOSbaixdykTkx/e+YJeHzHhad1Yc30ucayQ I= DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d= messagingengine.com; h=cc:content-transfer-encoding:content-type :date:from:in-reply-to:message-id:mime-version:references :subject:to:x-me-sender:x-me-sender:x-sasl-enc; s=fm2; bh=flEBxI 1VLRsDk/c4I2fxuzdQkUv3yxk99fRpCyTvqtM=; b=LHRAgSlyhlbAm9Fbc0QvJP YXx8/KAwKBKtYScYSlTqGgv75TWBlrAIcOZJsF4rFpn7cRqzHwcEIEVl1poph/1z e4q7gjvQaJO0iCaWa8s2bGmeS6t0UT/myhfsDxdSGGYI6SuL+m/i1/l1gPFhRSNC Qswv0rNQN0LhbNbwz+gm7kAIU9n0CzU3pv8+1Un/6azo+xPniJd+p6M/NyTkQn7V PLeUrytgH/7Oyv7Ce9R+4iuS4OIcPZeskOpw9HaPB7JuuNqF4GbKK+xUK9DCFr34 blhgiqopEP4PbXZuvbdq3qKDCL9Bg1BFZwm8fbWiH77NAwDp8Su/PUEL4oIXBMqw == X-ME-Proxy: X-ME-Proxy: X-ME-Proxy: X-ME-Proxy: X-ME-Proxy: X-ME-Proxy: X-ME-Sender: From: "Emilio G. Cota" To: qemu-devel@nongnu.org Date: Mon, 21 May 2018 19:39:13 -0400 Message-Id: <1526945967-9687-4-git-send-email-cota@braap.org> X-Mailer: git-send-email 2.7.4 In-Reply-To: <1526945967-9687-1-git-send-email-cota@braap.org> References: <1526945967-9687-1-git-send-email-cota@braap.org> MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable X-detected-operating-system: by eggs.gnu.org: GNU/Linux 2.2.x-3.x [generic] [fuzzy] X-Received-From: 66.111.4.25 Subject: [Qemu-devel] [PATCH v3 03/17] tcg: track TBs with per-region BST's X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.21 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: =?UTF-8?q?Alex=20Benn=C3=A9e?= , Richard Henderson , Paolo Bonzini Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: "Qemu-devel" X-ZohoMail: RSF_0 Z_629925259 SPT_0 This paves the way for enabling scalable parallel generation of TCG code. Instead of tracking TBs with a single binary search tree (BST), use a BST for each TCG region, protecting it with a lock. This is as scalable as it gets, since each TCG thread operates on a separate region. The core of this change is the introduction of struct tcg_region_tree, which contains a pointer to a GTree and an associated lock to serialize accesses to it. We then allocate an array of tcg_region_tree's, adding the appropriate padding to avoid false sharing based on qemu_dcache_linesize. Given a tc_ptr, we first find the corresponding region_tree. This is done by special-casing the first and last regions first, since they might be of size !=3D region.size; otherwise we just divide the offset by region.stride. I was worried about this division (several dozen cycles of latency), but profiling shows that this is not a fast path. Note that region.stride is not required to be a power of two; it is only required to be a multiple of the host's page size. Note that with this design we can also provide consistent snapshots about all region trees at once; for instance, tcg_tb_foreach acquires/releases all region_tree locks before/after iterating over them. For this reason we now drop tb_lock in dump_exec_info(). As an alternative I considered implementing a concurrent BST, but this can be tricky to get right, offers no consistent snapshots of the BST, and performance and scalability-wise I don't think it could ever beat having separate GTrees, given that our workload is insert-mostly (all concurrent BST designs I've seen focus, understandably, on making lookups fast, which comes at the expense of convoluted, non-wait-free insertions/removals). Reviewed-by: Richard Henderson Reviewed-by: Alex Benn=C3=A9e Signed-off-by: Emilio G. Cota Tested-by: Alex Benn=C3=A9e --- include/exec/exec-all.h | 1 - include/exec/tb-context.h | 1 - tcg/tcg.h | 6 ++ accel/tcg/cpu-exec.c | 2 +- accel/tcg/translate-all.c | 101 ++++-------------------- tcg/tcg.c | 191 ++++++++++++++++++++++++++++++++++++++++++= ++++ 6 files changed, 213 insertions(+), 89 deletions(-) diff --git a/include/exec/exec-all.h b/include/exec/exec-all.h index bd68328..6207b4d 100644 --- a/include/exec/exec-all.h +++ b/include/exec/exec-all.h @@ -404,7 +404,6 @@ static inline uint32_t curr_cflags(void) | (use_icount ? CF_USE_ICOUNT : 0); } =20 -void tb_remove(TranslationBlock *tb); void tb_flush(CPUState *cpu); void tb_phys_invalidate(TranslationBlock *tb, tb_page_addr_t page_addr); TranslationBlock *tb_htable_lookup(CPUState *cpu, target_ulong pc, diff --git a/include/exec/tb-context.h b/include/exec/tb-context.h index 1d41202..d8472c8 100644 --- a/include/exec/tb-context.h +++ b/include/exec/tb-context.h @@ -31,7 +31,6 @@ typedef struct TBContext TBContext; =20 struct TBContext { =20 - GTree *tb_tree; struct qht htable; /* any access to the tbs or the page table must use this lock */ QemuMutex tb_lock; diff --git a/tcg/tcg.h b/tcg/tcg.h index 08f8bbf..afe8492 100644 --- a/tcg/tcg.h +++ b/tcg/tcg.h @@ -866,6 +866,12 @@ void tcg_region_reset_all(void); size_t tcg_code_size(void); size_t tcg_code_capacity(void); =20 +void tcg_tb_insert(TranslationBlock *tb); +void tcg_tb_remove(TranslationBlock *tb); +TranslationBlock *tcg_tb_lookup(uintptr_t tc_ptr); +void tcg_tb_foreach(GTraverseFunc func, gpointer user_data); +size_t tcg_nb_tbs(void); + /* user-mode: Called with tb_lock held. */ static inline void *tcg_malloc(int size) { diff --git a/accel/tcg/cpu-exec.c b/accel/tcg/cpu-exec.c index aefc682..7b934a6 100644 --- a/accel/tcg/cpu-exec.c +++ b/accel/tcg/cpu-exec.c @@ -225,7 +225,7 @@ static void cpu_exec_nocache(CPUState *cpu, int max_cyc= les, =20 tb_lock(); tb_phys_invalidate(tb, -1); - tb_remove(tb); + tcg_tb_remove(tb); tb_unlock(); } #endif diff --git a/accel/tcg/translate-all.c b/accel/tcg/translate-all.c index 8080eb7..e9341f3 100644 --- a/accel/tcg/translate-all.c +++ b/accel/tcg/translate-all.c @@ -205,8 +205,6 @@ void tb_lock_reset(void) } } =20 -static TranslationBlock *tb_find_pc(uintptr_t tc_ptr); - void cpu_gen_init(void) { tcg_context_init(&tcg_init_ctx); @@ -375,13 +373,13 @@ bool cpu_restore_state(CPUState *cpu, uintptr_t host_= pc, bool will_exit) =20 if (check_offset < tcg_init_ctx.code_gen_buffer_size) { tb_lock(); - tb =3D tb_find_pc(host_pc); + tb =3D tcg_tb_lookup(host_pc); if (tb) { cpu_restore_state_from_tb(cpu, tb, host_pc, will_exit); if (tb->cflags & CF_NOCACHE) { /* one-shot translation, invalidate it immediately */ tb_phys_invalidate(tb, -1); - tb_remove(tb); + tcg_tb_remove(tb); } r =3D true; } @@ -728,48 +726,6 @@ static inline void *alloc_code_gen_buffer(void) } #endif /* USE_STATIC_CODE_GEN_BUFFER, WIN32, POSIX */ =20 -/* compare a pointer @ptr and a tb_tc @s */ -static int ptr_cmp_tb_tc(const void *ptr, const struct tb_tc *s) -{ - if (ptr >=3D s->ptr + s->size) { - return 1; - } else if (ptr < s->ptr) { - return -1; - } - return 0; -} - -static gint tb_tc_cmp(gconstpointer ap, gconstpointer bp) -{ - const struct tb_tc *a =3D ap; - const struct tb_tc *b =3D bp; - - /* - * When both sizes are set, we know this isn't a lookup. - * This is the most likely case: every TB must be inserted; lookups - * are a lot less frequent. - */ - if (likely(a->size && b->size)) { - if (a->ptr > b->ptr) { - return 1; - } else if (a->ptr < b->ptr) { - return -1; - } - /* a->ptr =3D=3D b->ptr should happen only on deletions */ - g_assert(a->size =3D=3D b->size); - return 0; - } - /* - * All lookups have either .size field set to 0. - * From the glib sources we see that @ap is always the lookup key. How= ever - * the docs provide no guarantee, so we just mark this case as likely. - */ - if (likely(a->size =3D=3D 0)) { - return ptr_cmp_tb_tc(a->ptr, b); - } - return ptr_cmp_tb_tc(b->ptr, a); -} - static inline void code_gen_alloc(size_t tb_size) { tcg_ctx->code_gen_buffer_size =3D size_code_gen_buffer(tb_size); @@ -778,7 +734,6 @@ static inline void code_gen_alloc(size_t tb_size) fprintf(stderr, "Could not allocate dynamic translator buffer\n"); exit(1); } - tb_ctx.tb_tree =3D g_tree_new(tb_tc_cmp); qemu_mutex_init(&tb_ctx.tb_lock); } =20 @@ -839,14 +794,6 @@ static TranslationBlock *tb_alloc(target_ulong pc) return tb; } =20 -/* Called with tb_lock held. */ -void tb_remove(TranslationBlock *tb) -{ - assert_tb_locked(); - - g_tree_remove(tb_ctx.tb_tree, &tb->tc); -} - static inline void invalidate_page_bitmap(PageDesc *p) { #ifdef CONFIG_SOFTMMU @@ -911,10 +858,10 @@ static void do_tb_flush(CPUState *cpu, run_on_cpu_dat= a tb_flush_count) } =20 if (DEBUG_TB_FLUSH_GATE) { - size_t nb_tbs =3D g_tree_nnodes(tb_ctx.tb_tree); + size_t nb_tbs =3D tcg_nb_tbs(); size_t host_size =3D 0; =20 - g_tree_foreach(tb_ctx.tb_tree, tb_host_size_iter, &host_size); + tcg_tb_foreach(tb_host_size_iter, &host_size); printf("qemu: flush code_size=3D%zu nb_tbs=3D%zu avg_tb_size=3D%zu= \n", tcg_code_size(), nb_tbs, nb_tbs > 0 ? host_size / nb_tbs : = 0); } @@ -923,10 +870,6 @@ static void do_tb_flush(CPUState *cpu, run_on_cpu_data= tb_flush_count) cpu_tb_jmp_cache_clear(cpu); } =20 - /* Increment the refcount first so that destroy acts as a reset */ - g_tree_ref(tb_ctx.tb_tree); - g_tree_destroy(tb_ctx.tb_tree); - qht_reset_size(&tb_ctx.htable, CODE_GEN_HTABLE_SIZE); page_flush_tb(); =20 @@ -1406,7 +1349,7 @@ TranslationBlock *tb_gen_code(CPUState *cpu, * through the physical hash table and physical page list. */ tb_link_page(tb, phys_pc, phys_page2); - g_tree_insert(tb_ctx.tb_tree, &tb->tc, tb); + tcg_tb_insert(tb); return tb; } =20 @@ -1510,7 +1453,7 @@ void tb_invalidate_phys_page_range(tb_page_addr_t sta= rt, tb_page_addr_t end, current_tb =3D NULL; if (cpu->mem_io_pc) { /* now we have a real cpu fault */ - current_tb =3D tb_find_pc(cpu->mem_io_pc); + current_tb =3D tcg_tb_lookup(cpu->mem_io_pc); } } if (current_tb =3D=3D tb && @@ -1627,7 +1570,7 @@ static bool tb_invalidate_phys_page(tb_page_addr_t ad= dr, uintptr_t pc) tb =3D p->first_tb; #ifdef TARGET_HAS_PRECISE_SMC if (tb && pc !=3D 0) { - current_tb =3D tb_find_pc(pc); + current_tb =3D tcg_tb_lookup(pc); } if (cpu !=3D NULL) { env =3D cpu->env_ptr; @@ -1670,18 +1613,6 @@ static bool tb_invalidate_phys_page(tb_page_addr_t a= ddr, uintptr_t pc) } #endif =20 -/* - * Find the TB 'tb' such that - * tb->tc.ptr <=3D tc_ptr < tb->tc.ptr + tb->tc.size - * Return NULL if not found. - */ -static TranslationBlock *tb_find_pc(uintptr_t tc_ptr) -{ - struct tb_tc s =3D { .ptr =3D (void *)tc_ptr }; - - return g_tree_lookup(tb_ctx.tb_tree, &s); -} - #if !defined(CONFIG_USER_ONLY) void tb_invalidate_phys_addr(AddressSpace *as, hwaddr addr) { @@ -1709,7 +1640,7 @@ void tb_check_watchpoint(CPUState *cpu) { TranslationBlock *tb; =20 - tb =3D tb_find_pc(cpu->mem_io_pc); + tb =3D tcg_tb_lookup(cpu->mem_io_pc); if (tb) { /* We can use retranslation to find the PC. */ cpu_restore_state_from_tb(cpu, tb, cpu->mem_io_pc, true); @@ -1743,7 +1674,7 @@ void cpu_io_recompile(CPUState *cpu, uintptr_t retadd= r) uint32_t n; =20 tb_lock(); - tb =3D tb_find_pc(retaddr); + tb =3D tcg_tb_lookup(retaddr); if (!tb) { cpu_abort(cpu, "cpu_io_recompile: could not find TB for pc=3D%p", (void *)retaddr); @@ -1782,7 +1713,7 @@ void cpu_io_recompile(CPUState *cpu, uintptr_t retadd= r) * cpu_exec_nocache() */ tb_phys_invalidate(tb->orig_tb, -1); } - tb_remove(tb); + tcg_tb_remove(tb); } =20 /* TODO: If env->pc !=3D tb->pc (i.e. the faulting instruction was not @@ -1853,6 +1784,7 @@ static void print_qht_statistics(FILE *f, fprintf_fun= ction cpu_fprintf, } =20 struct tb_tree_stats { + size_t nb_tbs; size_t host_size; size_t target_size; size_t max_target_size; @@ -1866,6 +1798,7 @@ static gboolean tb_tree_stats_iter(gpointer key, gpoi= nter value, gpointer data) const TranslationBlock *tb =3D value; struct tb_tree_stats *tst =3D data; =20 + tst->nb_tbs++; tst->host_size +=3D tb->tc.size; tst->target_size +=3D tb->size; if (tb->size > tst->max_target_size) { @@ -1889,10 +1822,8 @@ void dump_exec_info(FILE *f, fprintf_function cpu_fp= rintf) struct qht_stats hst; size_t nb_tbs; =20 - tb_lock(); - - nb_tbs =3D g_tree_nnodes(tb_ctx.tb_tree); - g_tree_foreach(tb_ctx.tb_tree, tb_tree_stats_iter, &tst); + tcg_tb_foreach(tb_tree_stats_iter, &tst); + nb_tbs =3D tst.nb_tbs; /* XXX: avoid using doubles ? */ cpu_fprintf(f, "Translation buffer state:\n"); /* @@ -1927,8 +1858,6 @@ void dump_exec_info(FILE *f, fprintf_function cpu_fpr= intf) cpu_fprintf(f, "TB invalidate count %d\n", tb_ctx.tb_phys_invalidate_c= ount); cpu_fprintf(f, "TLB flush count %zu\n", tlb_flush_count()); tcg_dump_info(f, cpu_fprintf); - - tb_unlock(); } =20 void dump_opcount_info(FILE *f, fprintf_function cpu_fprintf) @@ -2196,7 +2125,7 @@ int page_unprotect(target_ulong address, uintptr_t pc) * set the page to PAGE_WRITE and did the TB invalidate for us. */ #ifdef TARGET_HAS_PRECISE_SMC - TranslationBlock *current_tb =3D tb_find_pc(pc); + TranslationBlock *current_tb =3D tcg_tb_lookup(pc); if (current_tb) { current_tb_invalidated =3D tb_cflags(current_tb) & CF_INVA= LID; } diff --git a/tcg/tcg.c b/tcg/tcg.c index 6eeebe0..62e3391 100644 --- a/tcg/tcg.c +++ b/tcg/tcg.c @@ -135,6 +135,12 @@ static TCGContext **tcg_ctxs; static unsigned int n_tcg_ctxs; TCGv_env cpu_env =3D 0; =20 +struct tcg_region_tree { + QemuMutex lock; + GTree *tree; + /* padding to avoid false sharing is computed at run-time */ +}; + /* * We divide code_gen_buffer into equally-sized "regions" that TCG threads * dynamically allocate from as demand dictates. Given appropriate region @@ -158,6 +164,13 @@ struct tcg_region_state { }; =20 static struct tcg_region_state region; +/* + * This is an array of struct tcg_region_tree's, with padding. + * We use void * to simplify the computation of region_trees[i]; each + * struct is found every tree_size bytes. + */ +static void *region_trees; +static size_t tree_size; static TCGRegSet tcg_target_available_regs[TCG_TYPE_COUNT]; static TCGRegSet tcg_target_call_clobber_regs; =20 @@ -295,6 +308,180 @@ TCGLabel *gen_new_label(void) =20 #include "tcg-target.inc.c" =20 +/* compare a pointer @ptr and a tb_tc @s */ +static int ptr_cmp_tb_tc(const void *ptr, const struct tb_tc *s) +{ + if (ptr >=3D s->ptr + s->size) { + return 1; + } else if (ptr < s->ptr) { + return -1; + } + return 0; +} + +static gint tb_tc_cmp(gconstpointer ap, gconstpointer bp) +{ + const struct tb_tc *a =3D ap; + const struct tb_tc *b =3D bp; + + /* + * When both sizes are set, we know this isn't a lookup. + * This is the most likely case: every TB must be inserted; lookups + * are a lot less frequent. + */ + if (likely(a->size && b->size)) { + if (a->ptr > b->ptr) { + return 1; + } else if (a->ptr < b->ptr) { + return -1; + } + /* a->ptr =3D=3D b->ptr should happen only on deletions */ + g_assert(a->size =3D=3D b->size); + return 0; + } + /* + * All lookups have either .size field set to 0. + * From the glib sources we see that @ap is always the lookup key. How= ever + * the docs provide no guarantee, so we just mark this case as likely. + */ + if (likely(a->size =3D=3D 0)) { + return ptr_cmp_tb_tc(a->ptr, b); + } + return ptr_cmp_tb_tc(b->ptr, a); +} + +static void tcg_region_trees_init(void) +{ + size_t i; + + tree_size =3D ROUND_UP(sizeof(struct tcg_region_tree), qemu_dcache_lin= esize); + region_trees =3D qemu_memalign(qemu_dcache_linesize, region.n * tree_s= ize); + for (i =3D 0; i < region.n; i++) { + struct tcg_region_tree *rt =3D region_trees + i * tree_size; + + qemu_mutex_init(&rt->lock); + rt->tree =3D g_tree_new(tb_tc_cmp); + } +} + +static struct tcg_region_tree *tc_ptr_to_region_tree(void *p) +{ + size_t region_idx; + + if (p < region.start_aligned) { + region_idx =3D 0; + } else { + ptrdiff_t offset =3D p - region.start_aligned; + + if (offset > region.stride * (region.n - 1)) { + region_idx =3D region.n - 1; + } else { + region_idx =3D offset / region.stride; + } + } + return region_trees + region_idx * tree_size; +} + +void tcg_tb_insert(TranslationBlock *tb) +{ + struct tcg_region_tree *rt =3D tc_ptr_to_region_tree(tb->tc.ptr); + + qemu_mutex_lock(&rt->lock); + g_tree_insert(rt->tree, &tb->tc, tb); + qemu_mutex_unlock(&rt->lock); +} + +void tcg_tb_remove(TranslationBlock *tb) +{ + struct tcg_region_tree *rt =3D tc_ptr_to_region_tree(tb->tc.ptr); + + qemu_mutex_lock(&rt->lock); + g_tree_remove(rt->tree, &tb->tc); + qemu_mutex_unlock(&rt->lock); +} + +/* + * Find the TB 'tb' such that + * tb->tc.ptr <=3D tc_ptr < tb->tc.ptr + tb->tc.size + * Return NULL if not found. + */ +TranslationBlock *tcg_tb_lookup(uintptr_t tc_ptr) +{ + struct tcg_region_tree *rt =3D tc_ptr_to_region_tree((void *)tc_ptr); + TranslationBlock *tb; + struct tb_tc s =3D { .ptr =3D (void *)tc_ptr }; + + qemu_mutex_lock(&rt->lock); + tb =3D g_tree_lookup(rt->tree, &s); + qemu_mutex_unlock(&rt->lock); + return tb; +} + +static void tcg_region_tree_lock_all(void) +{ + size_t i; + + for (i =3D 0; i < region.n; i++) { + struct tcg_region_tree *rt =3D region_trees + i * tree_size; + + qemu_mutex_lock(&rt->lock); + } +} + +static void tcg_region_tree_unlock_all(void) +{ + size_t i; + + for (i =3D 0; i < region.n; i++) { + struct tcg_region_tree *rt =3D region_trees + i * tree_size; + + qemu_mutex_unlock(&rt->lock); + } +} + +void tcg_tb_foreach(GTraverseFunc func, gpointer user_data) +{ + size_t i; + + tcg_region_tree_lock_all(); + for (i =3D 0; i < region.n; i++) { + struct tcg_region_tree *rt =3D region_trees + i * tree_size; + + g_tree_foreach(rt->tree, func, user_data); + } + tcg_region_tree_unlock_all(); +} + +size_t tcg_nb_tbs(void) +{ + size_t nb_tbs =3D 0; + size_t i; + + tcg_region_tree_lock_all(); + for (i =3D 0; i < region.n; i++) { + struct tcg_region_tree *rt =3D region_trees + i * tree_size; + + nb_tbs +=3D g_tree_nnodes(rt->tree); + } + tcg_region_tree_unlock_all(); + return nb_tbs; +} + +static void tcg_region_tree_reset_all(void) +{ + size_t i; + + tcg_region_tree_lock_all(); + for (i =3D 0; i < region.n; i++) { + struct tcg_region_tree *rt =3D region_trees + i * tree_size; + + /* Increment the refcount first so that destroy acts as a reset */ + g_tree_ref(rt->tree); + g_tree_destroy(rt->tree); + } + tcg_region_tree_unlock_all(); +} + static void tcg_region_bounds(size_t curr_region, void **pstart, void **pe= nd) { void *start, *end; @@ -380,6 +567,8 @@ void tcg_region_reset_all(void) g_assert(!err); } qemu_mutex_unlock(®ion.lock); + + tcg_region_tree_reset_all(); } =20 #ifdef CONFIG_USER_ONLY @@ -496,6 +685,8 @@ void tcg_region_init(void) g_assert(!rc); } =20 + tcg_region_trees_init(); + /* In user-mode we support only one ctx, so do the initial allocation = now */ #ifdef CONFIG_USER_ONLY { --=20 2.7.4 From nobody Sat Apr 27 09:56:35 2024 Delivered-To: importer@patchew.org Received-SPF: pass (zoho.com: domain of gnu.org designates 208.118.235.17 as permitted sender) client-ip=208.118.235.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Authentication-Results: mx.zohomail.com; spf=pass (zoho.com: domain of gnu.org designates 208.118.235.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org Return-Path: Received: from lists.gnu.org (lists.gnu.org [208.118.235.17]) by mx.zohomail.com with SMTPS id 1526946277885699.0576692659766; Mon, 21 May 2018 16:44:37 -0700 (PDT) Received: from localhost ([::1]:52864 helo=lists.gnu.org) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1fKuTl-00069D-2U for importer@patchew.org; Mon, 21 May 2018 19:44:37 -0400 Received: from eggs.gnu.org ([2001:4830:134:3::10]:57829) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1fKuOt-0002eI-6C for qemu-devel@nongnu.org; Mon, 21 May 2018 19:39:37 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1fKuOo-0005X1-OH for qemu-devel@nongnu.org; Mon, 21 May 2018 19:39:35 -0400 Received: from out1-smtp.messagingengine.com ([66.111.4.25]:60447) by eggs.gnu.org with esmtps (TLS1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.71) (envelope-from ) id 1fKuOo-0005V4-Kn for qemu-devel@nongnu.org; Mon, 21 May 2018 19:39:30 -0400 Received: from compute4.internal (compute4.nyi.internal [10.202.2.44]) by mailout.nyi.internal (Postfix) with ESMTP id 41104225C3; Mon, 21 May 2018 19:39:29 -0400 (EDT) Received: from mailfrontend1 ([10.202.2.162]) by compute4.internal (MEProxy); Mon, 21 May 2018 19:39:29 -0400 Received: from localhost (flamenco.cs.columbia.edu [128.59.20.216]) by mail.messagingengine.com (Postfix) with ESMTPA id EE84BE4119; Mon, 21 May 2018 19:39:28 -0400 (EDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=braap.org; h=cc :content-transfer-encoding:content-type:date:from:in-reply-to :message-id:mime-version:references:subject:to:x-me-sender :x-me-sender:x-sasl-enc; s=mesmtp; bh=uf7kGqloxbXDCj9Xz3Q2iklfQH YJpyKHpQBl5VGQ0FI=; b=EfKeUHW6ZsH70HGop7Xulssuavid+feTIl09jghIJX 7W+pONwc3mYXWcnrk4kTatbwfLV3O0g7saK8RsEESAafplPV2QQEWKBQRuF+yjJP qhcRAqlcDhZ42uaoPf0YX0Ivl6bGKj4H8EKPbtyT/bJGP3hiHktW++F6SAYVrF52 8= DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d= messagingengine.com; h=cc:content-transfer-encoding:content-type :date:from:in-reply-to:message-id:mime-version:references :subject:to:x-me-sender:x-me-sender:x-sasl-enc; s=fm2; bh=uf7kGq loxbXDCj9Xz3Q2iklfQHYJpyKHpQBl5VGQ0FI=; b=m7do21Nu6X7LkwTrRSS/Nw YFyGhtPM2eT9NJgQzfiNFgsh84S1pERHF45G/d4unkOUpnJ51bqSOfGqykNbIYcl E3XFM4K5KrShMMlgF6Unu2XIP62bArZSBo3bFwIl0c8NMYwemdb3WDGhjSUPoUWz ltwT0u2JmVTHRq5asPduGQd/NFSTs1zVpZEXup1HPlzLkPkkawEzmytxGOd+629c fhOaXZlFLsCZ03u07yiSZPvqgX9LHewyfmrvkGCc0STQfxKLhGsS1OsN9fhPOUYn TF8ZfD9BZG6ggpfcgM0pGnk4CrEu5lHtw1jSEemBbJahrgYroWPAFhB4G+UgAQDA == X-ME-Proxy: X-ME-Proxy: X-ME-Proxy: X-ME-Proxy: X-ME-Proxy: X-ME-Proxy: X-ME-Sender: From: "Emilio G. Cota" To: qemu-devel@nongnu.org Date: Mon, 21 May 2018 19:39:14 -0400 Message-Id: <1526945967-9687-5-git-send-email-cota@braap.org> X-Mailer: git-send-email 2.7.4 In-Reply-To: <1526945967-9687-1-git-send-email-cota@braap.org> References: <1526945967-9687-1-git-send-email-cota@braap.org> MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable X-detected-operating-system: by eggs.gnu.org: GNU/Linux 2.2.x-3.x [generic] [fuzzy] X-Received-From: 66.111.4.25 Subject: [Qemu-devel] [PATCH v3 04/17] tcg: move tb_ctx.tb_phys_invalidate_count to tcg_ctx X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.21 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: =?UTF-8?q?Alex=20Benn=C3=A9e?= , Richard Henderson , Paolo Bonzini Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: "Qemu-devel" X-ZohoMail: RSF_0 Z_629925259 SPT_0 Thereby making it per-TCGContext. Once we remove tb_lock, this will avoid an atomic increment every time a TB is invalidated. Reviewed-by: Richard Henderson Reviewed-by: Alex Benn=C3=A9e Signed-off-by: Emilio G. Cota Tested-by: Alex Benn=C3=A9e --- include/exec/tb-context.h | 1 - tcg/tcg.h | 3 +++ accel/tcg/translate-all.c | 5 +++-- tcg/tcg.c | 14 ++++++++++++++ 4 files changed, 20 insertions(+), 3 deletions(-) diff --git a/include/exec/tb-context.h b/include/exec/tb-context.h index d8472c8..8c9b49c 100644 --- a/include/exec/tb-context.h +++ b/include/exec/tb-context.h @@ -37,7 +37,6 @@ struct TBContext { =20 /* statistics */ unsigned tb_flush_count; - int tb_phys_invalidate_count; }; =20 extern TBContext tb_ctx; diff --git a/tcg/tcg.h b/tcg/tcg.h index afe8492..ec8027b 100644 --- a/tcg/tcg.h +++ b/tcg/tcg.h @@ -695,6 +695,8 @@ struct TCGContext { /* Threshold to flush the translated code buffer. */ void *code_gen_highwater; =20 + size_t tb_phys_invalidate_count; + /* Track which vCPU triggers events */ CPUState *cpu; /* *_trans */ =20 @@ -868,6 +870,7 @@ size_t tcg_code_capacity(void); =20 void tcg_tb_insert(TranslationBlock *tb); void tcg_tb_remove(TranslationBlock *tb); +size_t tcg_tb_phys_invalidate_count(void); TranslationBlock *tcg_tb_lookup(uintptr_t tc_ptr); void tcg_tb_foreach(GTraverseFunc func, gpointer user_data); size_t tcg_nb_tbs(void); diff --git a/accel/tcg/translate-all.c b/accel/tcg/translate-all.c index e9341f3..8caf28d 100644 --- a/accel/tcg/translate-all.c +++ b/accel/tcg/translate-all.c @@ -1069,7 +1069,8 @@ void tb_phys_invalidate(TranslationBlock *tb, tb_page= _addr_t page_addr) /* suppress any remaining jumps to this TB */ tb_jmp_unlink(tb); =20 - tb_ctx.tb_phys_invalidate_count++; + atomic_set(&tcg_ctx->tb_phys_invalidate_count, + tcg_ctx->tb_phys_invalidate_count + 1); } =20 #ifdef CONFIG_SOFTMMU @@ -1855,7 +1856,7 @@ void dump_exec_info(FILE *f, fprintf_function cpu_fpr= intf) cpu_fprintf(f, "\nStatistics:\n"); cpu_fprintf(f, "TB flush count %u\n", atomic_read(&tb_ctx.tb_flush_count)); - cpu_fprintf(f, "TB invalidate count %d\n", tb_ctx.tb_phys_invalidate_c= ount); + cpu_fprintf(f, "TB invalidate count %zu\n", tcg_tb_phys_invalidate_cou= nt()); cpu_fprintf(f, "TLB flush count %zu\n", tlb_flush_count()); tcg_dump_info(f, cpu_fprintf); } diff --git a/tcg/tcg.c b/tcg/tcg.c index 62e3391..1d1dfd7 100644 --- a/tcg/tcg.c +++ b/tcg/tcg.c @@ -791,6 +791,20 @@ size_t tcg_code_capacity(void) return capacity; } =20 +size_t tcg_tb_phys_invalidate_count(void) +{ + unsigned int n_ctxs =3D atomic_read(&n_tcg_ctxs); + unsigned int i; + size_t total =3D 0; + + for (i =3D 0; i < n_ctxs; i++) { + const TCGContext *s =3D atomic_read(&tcg_ctxs[i]); + + total +=3D atomic_read(&s->tb_phys_invalidate_count); + } + return total; +} + /* pool based memory allocation */ void *tcg_malloc_internal(TCGContext *s, int size) { --=20 2.7.4 From nobody Sat Apr 27 09:56:35 2024 Delivered-To: importer@patchew.org Received-SPF: pass (zoho.com: domain of gnu.org designates 208.118.235.17 as permitted sender) client-ip=208.118.235.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Authentication-Results: mx.zohomail.com; spf=pass (zoho.com: domain of gnu.org designates 208.118.235.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org Return-Path: Received: from lists.gnu.org (lists.gnu.org [208.118.235.17]) by mx.zohomail.com with SMTPS id 15269464817601010.8470139337529; Mon, 21 May 2018 16:48:01 -0700 (PDT) Received: from localhost ([::1]:52885 helo=lists.gnu.org) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1fKuWx-0000Eg-R1 for importer@patchew.org; Mon, 21 May 2018 19:47:55 -0400 Received: from eggs.gnu.org ([2001:4830:134:3::10]:57831) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1fKuOt-0002eJ-6c for qemu-devel@nongnu.org; Mon, 21 May 2018 19:39:38 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1fKuOq-0005Xv-Dy for qemu-devel@nongnu.org; Mon, 21 May 2018 19:39:35 -0400 Received: from out1-smtp.messagingengine.com ([66.111.4.25]:41361) by eggs.gnu.org with esmtps (TLS1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.71) (envelope-from ) id 1fKuOq-0005Vw-2g for qemu-devel@nongnu.org; Mon, 21 May 2018 19:39:32 -0400 Received: from compute4.internal (compute4.nyi.internal [10.202.2.44]) by mailout.nyi.internal (Postfix) with ESMTP id 84F262267A; Mon, 21 May 2018 19:39:29 -0400 (EDT) Received: from mailfrontend2 ([10.202.2.163]) by compute4.internal (MEProxy); Mon, 21 May 2018 19:39:29 -0400 Received: from localhost (flamenco.cs.columbia.edu [128.59.20.216]) by mail.messagingengine.com (Postfix) with ESMTPA id 2E86710260; Mon, 21 May 2018 19:39:29 -0400 (EDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=braap.org; h=cc :date:from:in-reply-to:message-id:references:subject:to :x-me-sender:x-me-sender:x-sasl-enc; s=mesmtp; bh=GIF5upE4NKBOQ2 prOoUTl5/1NRqZOuk4yg+Dk4SU4aM=; b=JQcrkLzbFvvRJRRflWl+fyEYRdRh8M 8VAF7E86BGoGBYiWNOf2leOb3WgHLvBoQJjrbLC8WMgDf3Vegc3TQSM2Mjj0ULir kQv5p6u7XMw8nHcTswdq+uVMonL8PuY6UR+Dixb5UadKX89i5FMW8hqMDHZb0DLi 1wYCcTy2Hi1LY= DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d= messagingengine.com; h=cc:date:from:in-reply-to:message-id :references:subject:to:x-me-sender:x-me-sender:x-sasl-enc; s= fm2; bh=GIF5upE4NKBOQ2prOoUTl5/1NRqZOuk4yg+Dk4SU4aM=; b=KGZE2lRO Af4Mwcrpfr3vA3CLtpbs1OjYohTkXmaBHBbhItoEV7W43FhvfAi0ciOsNXuJ1FmF 2dPG44enMax6mYL+6EdxvzajPQU0IgoVbRX7eKvApy9b90SsRVB4egnWJDa1aIeY UTYXncTx/1q+lueHG+pjVvMUNtWzAsQcM6WD7Xa0vW/BeplPY+vHKFEhe2ikbVk3 Z/4E4scKt5hoBgE2vHopwtk2QY5QAcQWfmU2ygF/DGBU0z3nBh/iqztjgNtyRaSt vToe0/NEp+bR9StJfxvHg1cNv7myine+yb95Y6h9I5hHA+3wFeXYGmvY42L844dj p7RZWA0NaSY10w== X-ME-Proxy: X-ME-Proxy: X-ME-Proxy: X-ME-Proxy: X-ME-Proxy: X-ME-Proxy: X-ME-Sender: From: "Emilio G. Cota" To: qemu-devel@nongnu.org Date: Mon, 21 May 2018 19:39:15 -0400 Message-Id: <1526945967-9687-6-git-send-email-cota@braap.org> X-Mailer: git-send-email 2.7.4 In-Reply-To: <1526945967-9687-1-git-send-email-cota@braap.org> References: <1526945967-9687-1-git-send-email-cota@braap.org> X-detected-operating-system: by eggs.gnu.org: GNU/Linux 2.2.x-3.x [generic] [fuzzy] X-Received-From: 66.111.4.25 Subject: [Qemu-devel] [PATCH v3 05/17] translate-all: iterate over TBs in a page with PAGE_FOR_EACH_TB X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.21 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: =?UTF-8?q?Alex=20Benn=C3=A9e?= , Richard Henderson , Paolo Bonzini Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: "Qemu-devel" X-ZohoMail: RSF_0 Z_629925259 SPT_0 Content-Transfer-Encoding: quoted-printable MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" This commit does several things, but to avoid churn I merged them all into the same commit. To wit: - Use uintptr_t instead of TranslationBlock * for the list of TBs in a page. Just like we did in (c37e6d7e "tcg: Use uintptr_t type for jmp_list_{next|first} fields of TB"), the rationale is the same: these are tagged pointers, not pointers. So use a more appropriate type. - Only check the least significant bit of the tagged pointers. Masking with 3/~3 is unnecessary and confusing. - Introduce the TB_FOR_EACH_TAGGED macro, and use it to define PAGE_FOR_EACH_TB, which improves readability. Note that TB_FOR_EACH_TAGGED will gain another user in a subsequent patch. - Update tb_page_remove to use PAGE_FOR_EACH_TB. In case there is a bug and we attempt to remove a TB that is not in the list, instead of segfaulting (since the list is NULL-terminated) we will reach g_assert_not_reached(). Reviewed-by: Richard Henderson Signed-off-by: Emilio G. Cota Tested-by: Alex Benn=C3=A9e --- include/exec/exec-all.h | 2 +- accel/tcg/translate-all.c | 62 ++++++++++++++++++++++---------------------= ---- 2 files changed, 30 insertions(+), 34 deletions(-) diff --git a/include/exec/exec-all.h b/include/exec/exec-all.h index 6207b4d..b2d8c8e 100644 --- a/include/exec/exec-all.h +++ b/include/exec/exec-all.h @@ -359,7 +359,7 @@ struct TranslationBlock { struct TranslationBlock *orig_tb; /* first and second physical page containing code. The lower bit of the pointer tells the index in page_next[] */ - struct TranslationBlock *page_next[2]; + uintptr_t page_next[2]; tb_page_addr_t page_addr[2]; =20 /* The following data are used to directly call another TB from diff --git a/accel/tcg/translate-all.c b/accel/tcg/translate-all.c index 8caf28d..7302d05 100644 --- a/accel/tcg/translate-all.c +++ b/accel/tcg/translate-all.c @@ -103,7 +103,7 @@ =20 typedef struct PageDesc { /* list of TBs intersecting this ram page */ - TranslationBlock *first_tb; + uintptr_t first_tb; #ifdef CONFIG_SOFTMMU /* in order to optimize self modifying code, we count the number of lookups we do to a given page to use a bitmap */ @@ -114,6 +114,15 @@ typedef struct PageDesc { #endif } PageDesc; =20 +/* list iterators for lists of tagged pointers in TranslationBlock */ +#define TB_FOR_EACH_TAGGED(head, tb, n, field) \ + for (n =3D (head) & 1, tb =3D (TranslationBlock *)((head) & ~1); = \ + tb; tb =3D (TranslationBlock *)tb->field[n], n =3D (uintptr_t)tb = & 1, \ + tb =3D (TranslationBlock *)((uintptr_t)tb & ~1)) + +#define PAGE_FOR_EACH_TB(pagedesc, tb, n) \ + TB_FOR_EACH_TAGGED((pagedesc)->first_tb, tb, n, page_next) + /* In system mode we want L1_MAP to be based on ram offsets, while in user mode we want it to be based on virtual addresses. */ #if !defined(CONFIG_USER_ONLY) @@ -815,7 +824,7 @@ static void page_flush_tb_1(int level, void **lp) PageDesc *pd =3D *lp; =20 for (i =3D 0; i < V_L2_SIZE; ++i) { - pd[i].first_tb =3D NULL; + pd[i].first_tb =3D (uintptr_t)NULL; invalidate_page_bitmap(pd + i); } } else { @@ -943,21 +952,21 @@ static void tb_page_check(void) =20 #endif /* CONFIG_USER_ONLY */ =20 -static inline void tb_page_remove(TranslationBlock **ptb, TranslationBlock= *tb) +static inline void tb_page_remove(PageDesc *pd, TranslationBlock *tb) { TranslationBlock *tb1; + uintptr_t *pprev; unsigned int n1; =20 - for (;;) { - tb1 =3D *ptb; - n1 =3D (uintptr_t)tb1 & 3; - tb1 =3D (TranslationBlock *)((uintptr_t)tb1 & ~3); + pprev =3D &pd->first_tb; + PAGE_FOR_EACH_TB(pd, tb1, n1) { if (tb1 =3D=3D tb) { - *ptb =3D tb1->page_next[n1]; - break; + *pprev =3D tb1->page_next[n1]; + return; } - ptb =3D &tb1->page_next[n1]; + pprev =3D &tb1->page_next[n1]; } + g_assert_not_reached(); } =20 /* remove the TB from a list of TBs jumping to the n-th jump target of the= TB */ @@ -1045,12 +1054,12 @@ void tb_phys_invalidate(TranslationBlock *tb, tb_pa= ge_addr_t page_addr) /* remove the TB from the page list */ if (tb->page_addr[0] !=3D page_addr) { p =3D page_find(tb->page_addr[0] >> TARGET_PAGE_BITS); - tb_page_remove(&p->first_tb, tb); + tb_page_remove(p, tb); invalidate_page_bitmap(p); } if (tb->page_addr[1] !=3D -1 && tb->page_addr[1] !=3D page_addr) { p =3D page_find(tb->page_addr[1] >> TARGET_PAGE_BITS); - tb_page_remove(&p->first_tb, tb); + tb_page_remove(p, tb); invalidate_page_bitmap(p); } =20 @@ -1081,10 +1090,7 @@ static void build_page_bitmap(PageDesc *p) =20 p->code_bitmap =3D bitmap_new(TARGET_PAGE_SIZE); =20 - tb =3D p->first_tb; - while (tb !=3D NULL) { - n =3D (uintptr_t)tb & 3; - tb =3D (TranslationBlock *)((uintptr_t)tb & ~3); + PAGE_FOR_EACH_TB(p, tb, n) { /* NOTE: this is subtle as a TB may span two physical pages */ if (n =3D=3D 0) { /* NOTE: tb_end may be after the end of the page, but @@ -1099,7 +1105,6 @@ static void build_page_bitmap(PageDesc *p) tb_end =3D ((tb->pc + tb->size) & ~TARGET_PAGE_MASK); } bitmap_set(p->code_bitmap, tb_start, tb_end - tb_start); - tb =3D tb->page_next[n]; } } #endif @@ -1122,9 +1127,9 @@ static inline void tb_alloc_page(TranslationBlock *tb, p =3D page_find_alloc(page_addr >> TARGET_PAGE_BITS, 1); tb->page_next[n] =3D p->first_tb; #ifndef CONFIG_USER_ONLY - page_already_protected =3D p->first_tb !=3D NULL; + page_already_protected =3D p->first_tb !=3D (uintptr_t)NULL; #endif - p->first_tb =3D (TranslationBlock *)((uintptr_t)tb | n); + p->first_tb =3D (uintptr_t)tb | n; invalidate_page_bitmap(p); =20 #if defined(CONFIG_USER_ONLY) @@ -1401,7 +1406,7 @@ void tb_invalidate_phys_range(tb_page_addr_t start, t= b_page_addr_t end) void tb_invalidate_phys_page_range(tb_page_addr_t start, tb_page_addr_t en= d, int is_cpu_write_access) { - TranslationBlock *tb, *tb_next; + TranslationBlock *tb; tb_page_addr_t tb_start, tb_end; PageDesc *p; int n; @@ -1432,11 +1437,7 @@ void tb_invalidate_phys_page_range(tb_page_addr_t st= art, tb_page_addr_t end, /* we remove all the TBs in the range [start, end[ */ /* XXX: see if in some cases it could be faster to invalidate all the code */ - tb =3D p->first_tb; - while (tb !=3D NULL) { - n =3D (uintptr_t)tb & 3; - tb =3D (TranslationBlock *)((uintptr_t)tb & ~3); - tb_next =3D tb->page_next[n]; + PAGE_FOR_EACH_TB(p, tb, n) { /* NOTE: this is subtle as a TB may span two physical pages */ if (n =3D=3D 0) { /* NOTE: tb_end may be after the end of the page, but @@ -1474,7 +1475,6 @@ void tb_invalidate_phys_page_range(tb_page_addr_t sta= rt, tb_page_addr_t end, #endif /* TARGET_HAS_PRECISE_SMC */ tb_phys_invalidate(tb, -1); } - tb =3D tb_next; } #if !defined(CONFIG_USER_ONLY) /* if no code remaining, no need to continue to use slow writes */ @@ -1568,18 +1568,15 @@ static bool tb_invalidate_phys_page(tb_page_addr_t = addr, uintptr_t pc) } =20 tb_lock(); - tb =3D p->first_tb; #ifdef TARGET_HAS_PRECISE_SMC - if (tb && pc !=3D 0) { + if (p->first_tb && pc !=3D 0) { current_tb =3D tcg_tb_lookup(pc); } if (cpu !=3D NULL) { env =3D cpu->env_ptr; } #endif - while (tb !=3D NULL) { - n =3D (uintptr_t)tb & 3; - tb =3D (TranslationBlock *)((uintptr_t)tb & ~3); + PAGE_FOR_EACH_TB(p, tb, n) { #ifdef TARGET_HAS_PRECISE_SMC if (current_tb =3D=3D tb && (current_tb->cflags & CF_COUNT_MASK) !=3D 1) { @@ -1596,9 +1593,8 @@ static bool tb_invalidate_phys_page(tb_page_addr_t ad= dr, uintptr_t pc) } #endif /* TARGET_HAS_PRECISE_SMC */ tb_phys_invalidate(tb, addr); - tb =3D tb->page_next[n]; } - p->first_tb =3D NULL; + p->first_tb =3D (uintptr_t)NULL; #ifdef TARGET_HAS_PRECISE_SMC if (current_tb_modified) { /* Force execution of one insn next time. */ --=20 2.7.4 From nobody Sat Apr 27 09:56:35 2024 Delivered-To: importer@patchew.org Received-SPF: pass (zoho.com: domain of gnu.org designates 208.118.235.17 as permitted sender) client-ip=208.118.235.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Authentication-Results: mx.zohomail.com; spf=pass (zoho.com: domain of gnu.org designates 208.118.235.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org Return-Path: Received: from lists.gnu.org (lists.gnu.org [208.118.235.17]) by mx.zohomail.com with SMTPS id 1526946120088610.6240604638818; Mon, 21 May 2018 16:42:00 -0700 (PDT) Received: from localhost ([::1]:52854 helo=lists.gnu.org) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1fKuR3-0003xO-VY for importer@patchew.org; Mon, 21 May 2018 19:41:50 -0400 Received: from eggs.gnu.org ([2001:4830:134:3::10]:57825) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1fKuOt-0002eF-5r for qemu-devel@nongnu.org; Mon, 21 May 2018 19:39:37 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1fKuOq-0005Xc-6P for qemu-devel@nongnu.org; Mon, 21 May 2018 19:39:35 -0400 Received: from out1-smtp.messagingengine.com ([66.111.4.25]:34215) by eggs.gnu.org with esmtps (TLS1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.71) (envelope-from ) id 1fKuOp-0005Vx-V5 for qemu-devel@nongnu.org; Mon, 21 May 2018 19:39:32 -0400 Received: from compute4.internal (compute4.nyi.internal [10.202.2.44]) by mailout.nyi.internal (Postfix) with ESMTP id A9DF222696; Mon, 21 May 2018 19:39:29 -0400 (EDT) Received: from mailfrontend1 ([10.202.2.162]) by compute4.internal (MEProxy); Mon, 21 May 2018 19:39:29 -0400 Received: from localhost (flamenco.cs.columbia.edu [128.59.20.216]) by mail.messagingengine.com (Postfix) with ESMTPA id 62CF7E4119; Mon, 21 May 2018 19:39:29 -0400 (EDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=braap.org; h=cc :content-transfer-encoding:content-type:date:from:in-reply-to :message-id:mime-version:references:subject:to:x-me-sender :x-me-sender:x-sasl-enc; s=mesmtp; bh=Rx+DSmF0MKj1+mWEbdHcLpYnJR Dd3HOT+JC8Jplq3O8=; b=nZpbzOoJI4GBeauvKkG9ci9PjhBxPbzj9uT7m2QrFA kx0/M+wallMVpl6hRAAjsssIMN2fZtT5pBWeAOrv/Qq+cltku1W61Wf3sZcsGP0w jICMYjqbLhi4ApMGTGN4TVNXOPi2zD7RYfCxCtTFzPrnt6CC1bRv0ckgLWinz/CH Q= DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d= messagingengine.com; h=cc:content-transfer-encoding:content-type :date:from:in-reply-to:message-id:mime-version:references :subject:to:x-me-sender:x-me-sender:x-sasl-enc; s=fm2; bh=Rx+DSm F0MKj1+mWEbdHcLpYnJRDd3HOT+JC8Jplq3O8=; b=M4fhZ+9VrywhFC2+H+b5ba lUKhDiNX60qujWQNutNwXR/11buNHrsHk5zH6Z7FL4DL0uTC2IRwR7Ax9BCV1RhJ yXkWw2GZBCy5tuUpMvJZzHrtE07xT/36GMua0I8rlv1i8fqmlZ284P/cKhESAkBf n0nvUlpkv7sM6NdYtGDjuev1/w3GURQ2YvXbtfdgnx9iGVafCYeUxX8PQyKv6zps qcd+torITRSYZvbjJYAGuOUCxu1qlT1p7JnD7iqrEp9BeU/N5zAmg5sTrlj5YbBY ArWTRXO2FZpIIFUC62aTzug4oO2F6nuMhdBY63+NkCP8sp+qZEZGxzgRYcZoxZaA == X-ME-Proxy: X-ME-Proxy: X-ME-Proxy: X-ME-Proxy: X-ME-Proxy: X-ME-Proxy: X-ME-Sender: From: "Emilio G. Cota" To: qemu-devel@nongnu.org Date: Mon, 21 May 2018 19:39:16 -0400 Message-Id: <1526945967-9687-7-git-send-email-cota@braap.org> X-Mailer: git-send-email 2.7.4 In-Reply-To: <1526945967-9687-1-git-send-email-cota@braap.org> References: <1526945967-9687-1-git-send-email-cota@braap.org> MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable X-detected-operating-system: by eggs.gnu.org: GNU/Linux 2.2.x-3.x [generic] [fuzzy] X-Received-From: 66.111.4.25 Subject: [Qemu-devel] [PATCH v3 06/17] translate-all: make l1_map lockless X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.21 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: =?UTF-8?q?Alex=20Benn=C3=A9e?= , Richard Henderson , Paolo Bonzini Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: "Qemu-devel" X-ZohoMail: RSF_0 Z_629925259 SPT_0 Groundwork for supporting parallel TCG generation. We never remove entries from the radix tree, so we can use cmpxchg to implement lockless insertions. Reviewed-by: Richard Henderson Reviewed-by: Alex Benn=C3=A9e Signed-off-by: Emilio G. Cota Tested-by: Alex Benn=C3=A9e --- docs/devel/multi-thread-tcg.txt | 4 ++-- accel/tcg/translate-all.c | 24 ++++++++++++++---------- 2 files changed, 16 insertions(+), 12 deletions(-) diff --git a/docs/devel/multi-thread-tcg.txt b/docs/devel/multi-thread-tcg.= txt index a99b456..faf8918 100644 --- a/docs/devel/multi-thread-tcg.txt +++ b/docs/devel/multi-thread-tcg.txt @@ -134,8 +134,8 @@ tb_set_jmp_target() code. Modification to the linked li= sts that allow searching for linked pages are done under the protect of the tb_lock(). =20 -The global page table is protected by the tb_lock() in system-mode and -mmap_lock() in linux-user mode. +The global page table is a lockless radix tree; cmpxchg is used +to atomically insert new elements. =20 The lookup caches are updated atomically and the lookup hash uses QHT which is designed for concurrent safe lookup. diff --git a/accel/tcg/translate-all.c b/accel/tcg/translate-all.c index 7302d05..38e712d 100644 --- a/accel/tcg/translate-all.c +++ b/accel/tcg/translate-all.c @@ -469,20 +469,12 @@ static void page_init(void) #endif } =20 -/* If alloc=3D1: - * Called with tb_lock held for system emulation. - * Called with mmap_lock held for user-mode emulation. - */ static PageDesc *page_find_alloc(tb_page_addr_t index, int alloc) { PageDesc *pd; void **lp; int i; =20 - if (alloc) { - assert_memory_lock(); - } - /* Level 1. Always allocated. */ lp =3D l1_map + ((index >> v_l1_shift) & (v_l1_size - 1)); =20 @@ -491,11 +483,17 @@ static PageDesc *page_find_alloc(tb_page_addr_t index= , int alloc) void **p =3D atomic_rcu_read(lp); =20 if (p =3D=3D NULL) { + void *existing; + if (!alloc) { return NULL; } p =3D g_new0(void *, V_L2_SIZE); - atomic_rcu_set(lp, p); + existing =3D atomic_cmpxchg(lp, NULL, p); + if (unlikely(existing)) { + g_free(p); + p =3D existing; + } } =20 lp =3D p + ((index >> (i * V_L2_BITS)) & (V_L2_SIZE - 1)); @@ -503,11 +501,17 @@ static PageDesc *page_find_alloc(tb_page_addr_t index= , int alloc) =20 pd =3D atomic_rcu_read(lp); if (pd =3D=3D NULL) { + void *existing; + if (!alloc) { return NULL; } pd =3D g_new0(PageDesc, V_L2_SIZE); - atomic_rcu_set(lp, pd); + existing =3D atomic_cmpxchg(lp, NULL, pd); + if (unlikely(existing)) { + g_free(pd); + pd =3D existing; + } } =20 return pd + (index & (V_L2_SIZE - 1)); --=20 2.7.4 From nobody Sat Apr 27 09:56:35 2024 Delivered-To: importer@patchew.org Received-SPF: pass (zoho.com: domain of gnu.org designates 208.118.235.17 as permitted sender) client-ip=208.118.235.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Authentication-Results: mx.zohomail.com; spf=pass (zoho.com: domain of gnu.org designates 208.118.235.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org Return-Path: Received: from lists.gnu.org (lists.gnu.org [208.118.235.17]) by mx.zohomail.com with SMTPS id 1526946111821148.59845683632545; Mon, 21 May 2018 16:41:51 -0700 (PDT) Received: from localhost ([::1]:52852 helo=lists.gnu.org) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1fKuR1-0003wq-7y for importer@patchew.org; Mon, 21 May 2018 19:41:47 -0400 Received: from eggs.gnu.org ([2001:4830:134:3::10]:57826) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1fKuOt-0002eG-5s for qemu-devel@nongnu.org; Mon, 21 May 2018 19:39:37 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1fKuOq-0005YC-I5 for qemu-devel@nongnu.org; Mon, 21 May 2018 19:39:35 -0400 Received: from out1-smtp.messagingengine.com ([66.111.4.25]:45545) by eggs.gnu.org with esmtps (TLS1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.71) (envelope-from ) id 1fKuOq-0005Wf-9d for qemu-devel@nongnu.org; Mon, 21 May 2018 19:39:32 -0400 Received: from compute4.internal (compute4.nyi.internal [10.202.2.44]) by mailout.nyi.internal (Postfix) with ESMTP id DDF1E226B8; Mon, 21 May 2018 19:39:29 -0400 (EDT) Received: from mailfrontend2 ([10.202.2.163]) by compute4.internal (MEProxy); Mon, 21 May 2018 19:39:29 -0400 Received: from localhost (flamenco.cs.columbia.edu [128.59.20.216]) by mail.messagingengine.com (Postfix) with ESMTPA id 91A7210260; Mon, 21 May 2018 19:39:29 -0400 (EDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=braap.org; h=cc :content-transfer-encoding:content-type:date:from:in-reply-to :message-id:mime-version:references:subject:to:x-me-sender :x-me-sender:x-sasl-enc; s=mesmtp; bh=pbGU7ptkSthPb/pFhAGR/HDx6F C3rYPkBcdpBdNr3wE=; b=iashl0JhKp+graaZTFPpYLa3Pclyh/7/2eo5tBu9dL 9wGVVo5jEcwDK1T7bAblXguoUduEzcEmWi5U22rEPWX4a9YL+eYRv5BoWNGtsoLR EqWY4JD3IpJluURAH5S4matzQxWt99p+WScypcOPqJx4OVA24wx5gaMDVShX2CzO I= DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d= messagingengine.com; h=cc:content-transfer-encoding:content-type :date:from:in-reply-to:message-id:mime-version:references :subject:to:x-me-sender:x-me-sender:x-sasl-enc; s=fm2; bh=pbGU7p tkSthPb/pFhAGR/HDx6FC3rYPkBcdpBdNr3wE=; b=cUKOkXqp7kSvDXqMME1cpb XVvj3M6cVDtJoQ/hFzB1e7e45FrDsSIpaY/uhJ0yXX4qWrrqg30dWuI+ciUEbcFc q1/O9Z3fiGkUeNu8XTRCGl2XLtinjCkEwnGRlKp0UdjsCCJ2Ko4ELVwmCdVg5sLd RmN6XPrLFXNXMyLCB6OBL3fU+n4Zr+vWEKJGeTJWY2p7lPfQuWL9DAu0AwVIQwiz 0mirqjP0cFWwpiZ7TaNODi1OxGjZNUDFBrrqSkxJBUG/7Kl7UcUPacS07rf2S4j2 vbEAxkdI9z8kwFOyM6uLEdFwJ60rVYpQ6mopt6SbWoJHUjv2yXeN0ghqaHPyKRpQ == X-ME-Proxy: X-ME-Proxy: X-ME-Proxy: X-ME-Proxy: X-ME-Proxy: X-ME-Proxy: X-ME-Sender: From: "Emilio G. Cota" To: qemu-devel@nongnu.org Date: Mon, 21 May 2018 19:39:17 -0400 Message-Id: <1526945967-9687-8-git-send-email-cota@braap.org> X-Mailer: git-send-email 2.7.4 In-Reply-To: <1526945967-9687-1-git-send-email-cota@braap.org> References: <1526945967-9687-1-git-send-email-cota@braap.org> MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable X-detected-operating-system: by eggs.gnu.org: GNU/Linux 2.2.x-3.x [generic] [fuzzy] X-Received-From: 66.111.4.25 Subject: [Qemu-devel] [PATCH v3 07/17] translate-all: remove hole in PageDesc X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.21 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: =?UTF-8?q?Alex=20Benn=C3=A9e?= , Richard Henderson , Paolo Bonzini Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: "Qemu-devel" X-ZohoMail: RSF_0 Z_629925259 SPT_0 Groundwork for supporting parallel TCG generation. Move the hole to the end of the struct, so that a u32 field can be added there without bloating the struct. Reviewed-by: Richard Henderson Reviewed-by: Alex Benn=C3=A9e Signed-off-by: Emilio G. Cota Tested-by: Alex Benn=C3=A9e --- accel/tcg/translate-all.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/accel/tcg/translate-all.c b/accel/tcg/translate-all.c index 38e712d..07674e4 100644 --- a/accel/tcg/translate-all.c +++ b/accel/tcg/translate-all.c @@ -107,8 +107,8 @@ typedef struct PageDesc { #ifdef CONFIG_SOFTMMU /* in order to optimize self modifying code, we count the number of lookups we do to a given page to use a bitmap */ - unsigned int code_write_count; unsigned long *code_bitmap; + unsigned int code_write_count; #else unsigned long flags; #endif --=20 2.7.4 From nobody Sat Apr 27 09:56:35 2024 Delivered-To: importer@patchew.org Received-SPF: pass (zoho.com: domain of gnu.org designates 208.118.235.17 as permitted sender) client-ip=208.118.235.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Authentication-Results: mx.zohomail.com; spf=pass (zoho.com: domain of gnu.org designates 208.118.235.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org Return-Path: Received: from lists.gnu.org (208.118.235.17 [208.118.235.17]) by mx.zohomail.com with SMTPS id 1526946477263153.29715752618688; Mon, 21 May 2018 16:47:57 -0700 (PDT) Received: from localhost ([::1]:52884 helo=lists.gnu.org) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1fKuWq-0000AL-H4 for importer@patchew.org; Mon, 21 May 2018 19:47:48 -0400 Received: from eggs.gnu.org ([2001:4830:134:3::10]:57832) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1fKuOt-0002eK-6s for qemu-devel@nongnu.org; Mon, 21 May 2018 19:39:38 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1fKuOq-0005Y3-Fl for qemu-devel@nongnu.org; Mon, 21 May 2018 19:39:35 -0400 Received: from out1-smtp.messagingengine.com ([66.111.4.25]:57707) by eggs.gnu.org with esmtps (TLS1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.71) (envelope-from ) id 1fKuOq-0005We-6T for qemu-devel@nongnu.org; Mon, 21 May 2018 19:39:32 -0400 Received: from compute4.internal (compute4.nyi.internal [10.202.2.44]) by mailout.nyi.internal (Postfix) with ESMTP id 185CE2275A; Mon, 21 May 2018 19:39:30 -0400 (EDT) Received: from mailfrontend1 ([10.202.2.162]) by compute4.internal (MEProxy); Mon, 21 May 2018 19:39:30 -0400 Received: from localhost (flamenco.cs.columbia.edu [128.59.20.216]) by mail.messagingengine.com (Postfix) with ESMTPA id C435FE4119; Mon, 21 May 2018 19:39:29 -0400 (EDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=braap.org; h=cc :content-transfer-encoding:content-type:date:from:in-reply-to :message-id:mime-version:references:subject:to:x-me-sender :x-me-sender:x-sasl-enc; s=mesmtp; bh=Etwbtw+LlWQSFKjTg6m2HuY7A8 be0eVQhFpRAWTR0Vs=; b=gG0nE42PrZiOStfFknQzlZyK2+xgDZFIwoe4WDVLUd VgzdD2JOMGXVJ11nkpBKusLH5fmSd930ZYlqKVG1n5gPIglRTOvG+RSoiSryny2X Kz50i3Wm8gFqowgw/XsnmNrwEHbD/7D2PvuEgBzRDI/FcFSoZFY9wR5gQ0lMzzAt Y= DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d= messagingengine.com; h=cc:content-transfer-encoding:content-type :date:from:in-reply-to:message-id:mime-version:references :subject:to:x-me-sender:x-me-sender:x-sasl-enc; s=fm2; bh=Etwbtw +LlWQSFKjTg6m2HuY7A8be0eVQhFpRAWTR0Vs=; b=AM7psYUeJTVRvmiB0amLai xNX0omNIBLFRpX5L6ID28yHB7YXo3HUhkNbn/YGP8+kRA7mjHkYxi7ixv7jNAKkH dmZf3WObE2y44ivPLqUTpyVf+YRjFsNEMx+DhYmA6byN+CWit4TBkto5PrKWdGL3 guy4dkPkgQkWB1f65dasDxXUwRY8fBPewwjjgKejlLX3FZYUTcgUkR0LeK6Ki8i0 vZGac3tJmlJJMVk7B23etHFo+uRlHjSOsGajoDlnshHSNUYLMAsI5ot/2+KydqzJ AJJ3fHXF2frYap7TrdDpH84rEuMFxhoOyXeVrahdFwsrkyKNOkVPX4qsey8/MZvA == X-ME-Proxy: X-ME-Proxy: X-ME-Proxy: X-ME-Proxy: X-ME-Proxy: X-ME-Proxy: X-ME-Sender: From: "Emilio G. Cota" To: qemu-devel@nongnu.org Date: Mon, 21 May 2018 19:39:18 -0400 Message-Id: <1526945967-9687-9-git-send-email-cota@braap.org> X-Mailer: git-send-email 2.7.4 In-Reply-To: <1526945967-9687-1-git-send-email-cota@braap.org> References: <1526945967-9687-1-git-send-email-cota@braap.org> MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable X-detected-operating-system: by eggs.gnu.org: GNU/Linux 2.2.x-3.x [generic] [fuzzy] X-Received-From: 66.111.4.25 Subject: [Qemu-devel] [PATCH v3 08/17] translate-all: work page-by-page in tb_invalidate_phys_range_1 X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.21 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: =?UTF-8?q?Alex=20Benn=C3=A9e?= , Richard Henderson , Paolo Bonzini Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: "Qemu-devel" X-ZohoMail: RSF_0 Z_629925259 SPT_0 So that we pass a same-page range to tb_invalidate_phys_page_range, instead of always passing an end address that could be on a different page. As discussed with Peter Maydell on the list [1], tb_invalidate_phys_page_ra= nge doesn't actually do much with 'end', which explains why we have never hit a bug despite going against what the comment on top of tb_invalidate_phys_page_range requires: > * Invalidate all TBs which intersect with the target physical address ran= ge > * [start;end[. NOTE: start and end must refer to the *same* physical page. The appended honours the comment, which avoids confusion. While at it, rework the loop into a for loop, which is less error prone (e.g. "continue" won't result in an infinite loop). [1] https://lists.gnu.org/archive/html/qemu-devel/2017-07/msg09165.html Reviewed-by: Richard Henderson Reviewed-by: Alex Benn=C3=A9e Signed-off-by: Emilio G. Cota Tested-by: Alex Benn=C3=A9e --- accel/tcg/translate-all.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/accel/tcg/translate-all.c b/accel/tcg/translate-all.c index 07674e4..8622f25 100644 --- a/accel/tcg/translate-all.c +++ b/accel/tcg/translate-all.c @@ -1375,10 +1375,14 @@ TranslationBlock *tb_gen_code(CPUState *cpu, */ static void tb_invalidate_phys_range_1(tb_page_addr_t start, tb_page_addr_= t end) { - while (start < end) { - tb_invalidate_phys_page_range(start, end, 0); - start &=3D TARGET_PAGE_MASK; - start +=3D TARGET_PAGE_SIZE; + tb_page_addr_t next; + + for (next =3D (start & TARGET_PAGE_MASK) + TARGET_PAGE_SIZE; + start < end; + start =3D next, next +=3D TARGET_PAGE_SIZE) { + tb_page_addr_t bound =3D MIN(next, end); + + tb_invalidate_phys_page_range(start, bound, 0); } } =20 --=20 2.7.4 From nobody Sat Apr 27 09:56:35 2024 Delivered-To: importer@patchew.org Received-SPF: pass (zoho.com: domain of gnu.org designates 208.118.235.17 as permitted sender) client-ip=208.118.235.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Authentication-Results: mx.zohomail.com; spf=pass (zoho.com: domain of gnu.org designates 208.118.235.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org Return-Path: Received: from lists.gnu.org (lists.gnu.org [208.118.235.17]) by mx.zohomail.com with SMTPS id 1526946283808777.3749740484491; Mon, 21 May 2018 16:44:43 -0700 (PDT) Received: from localhost ([::1]:52865 helo=lists.gnu.org) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1fKuTq-0006DF-UW for importer@patchew.org; Mon, 21 May 2018 19:44:42 -0400 Received: from eggs.gnu.org ([2001:4830:134:3::10]:57868) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1fKuOu-0002eV-RR for qemu-devel@nongnu.org; Mon, 21 May 2018 19:39:38 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1fKuOr-0005Yo-BM for qemu-devel@nongnu.org; Mon, 21 May 2018 19:39:36 -0400 Received: from out1-smtp.messagingengine.com ([66.111.4.25]:43055) by eggs.gnu.org with esmtps (TLS1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.71) (envelope-from ) id 1fKuOq-0005XY-FL for qemu-devel@nongnu.org; Mon, 21 May 2018 19:39:32 -0400 Received: from compute4.internal (compute4.nyi.internal [10.202.2.44]) by mailout.nyi.internal (Postfix) with ESMTP id 4F9BB2275B; Mon, 21 May 2018 19:39:30 -0400 (EDT) Received: from mailfrontend2 ([10.202.2.163]) by compute4.internal (MEProxy); Mon, 21 May 2018 19:39:30 -0400 Received: from localhost (flamenco.cs.columbia.edu [128.59.20.216]) by mail.messagingengine.com (Postfix) with ESMTPA id EFEE41025C; Mon, 21 May 2018 19:39:29 -0400 (EDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=braap.org; h=cc :content-transfer-encoding:content-type:date:from:in-reply-to :message-id:mime-version:references:subject:to:x-me-sender :x-me-sender:x-sasl-enc; s=mesmtp; bh=G/0YFEj3OIFNVHpQSZRHTuwu3F 231h5hMKlShQBMUE4=; b=1hIwWkxZNZDEHtU4wbMFgVshaDlRb2f5VmzuF13pjm EVd7ajqf/1ZyX78BnLudhLghqTHcxPl0W7xZx1F0IFxCoa5FZjAgsWNEcHa9ozBv IqQNsWPHtB401U0BpUzdI2yvf1Xtxe5tD9fTcskMi5Qm7sgis69q2eR8EU5OVnn4 w= DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d= messagingengine.com; h=cc:content-transfer-encoding:content-type :date:from:in-reply-to:message-id:mime-version:references :subject:to:x-me-sender:x-me-sender:x-sasl-enc; s=fm2; bh=G/0YFE j3OIFNVHpQSZRHTuwu3F231h5hMKlShQBMUE4=; b=HHQCbd5+rO53D7/KVGR8Fa 8BR40xAdiukPvYKJHaQHSTESP7V+9o0Xg2b1QuyfJ9e7bzivhdi+LR0Q8aj+CnLI pnhF8yArRP6ggc272jjP+kMAyBG/Th0yv6OQMM8uU+zCXqC22SDRuRM5MDBF3Iga +aEKjr4fWlAaSU2UX+/q9ARV6oMgyMXD3J5Er6b1zOmMjryXTf6QCit9MaE/rgt7 JNMBByMDKJRBeiN1Pt6BuUWbJlkapN4JeJgKdKLnkh5yW9XsKv71sB0MHJH7vDxT BhPota5soh6DPhKrN5aoM0gmXfTEPbu08waC5Uklm9ppMNk5ez4kINQQKACYGn5Q == X-ME-Proxy: X-ME-Proxy: X-ME-Proxy: X-ME-Proxy: X-ME-Proxy: X-ME-Proxy: X-ME-Sender: From: "Emilio G. Cota" To: qemu-devel@nongnu.org Date: Mon, 21 May 2018 19:39:19 -0400 Message-Id: <1526945967-9687-10-git-send-email-cota@braap.org> X-Mailer: git-send-email 2.7.4 In-Reply-To: <1526945967-9687-1-git-send-email-cota@braap.org> References: <1526945967-9687-1-git-send-email-cota@braap.org> MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable X-detected-operating-system: by eggs.gnu.org: GNU/Linux 2.2.x-3.x [generic] [fuzzy] X-Received-From: 66.111.4.25 Subject: [Qemu-devel] [PATCH v3 09/17] translate-all: move tb_invalidate_phys_page_range up in the file X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.21 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: =?UTF-8?q?Alex=20Benn=C3=A9e?= , Richard Henderson , Paolo Bonzini Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: "Qemu-devel" X-ZohoMail: RSF_0 Z_629925259 SPT_0 This greatly simplifies next commit's diff. Reviewed-by: Richard Henderson Reviewed-by: Alex Benn=C3=A9e Signed-off-by: Emilio G. Cota Tested-by: Alex Benn=C3=A9e --- accel/tcg/translate-all.c | 77 ++++++++++++++++++++++++-------------------= ---- 1 file changed, 39 insertions(+), 38 deletions(-) diff --git a/accel/tcg/translate-all.c b/accel/tcg/translate-all.c index 8622f25..bd08bce 100644 --- a/accel/tcg/translate-all.c +++ b/accel/tcg/translate-all.c @@ -1365,44 +1365,6 @@ TranslationBlock *tb_gen_code(CPUState *cpu, =20 /* * Invalidate all TBs which intersect with the target physical address ran= ge - * [start;end[. NOTE: start and end may refer to *different* physical page= s. - * 'is_cpu_write_access' should be true if called from a real cpu write - * access: the virtual CPU will exit the current TB if code is modified in= side - * this TB. - * - * Called with mmap_lock held for user-mode emulation, grabs tb_lock - * Called with tb_lock held for system-mode emulation - */ -static void tb_invalidate_phys_range_1(tb_page_addr_t start, tb_page_addr_= t end) -{ - tb_page_addr_t next; - - for (next =3D (start & TARGET_PAGE_MASK) + TARGET_PAGE_SIZE; - start < end; - start =3D next, next +=3D TARGET_PAGE_SIZE) { - tb_page_addr_t bound =3D MIN(next, end); - - tb_invalidate_phys_page_range(start, bound, 0); - } -} - -#ifdef CONFIG_SOFTMMU -void tb_invalidate_phys_range(tb_page_addr_t start, tb_page_addr_t end) -{ - assert_tb_locked(); - tb_invalidate_phys_range_1(start, end); -} -#else -void tb_invalidate_phys_range(tb_page_addr_t start, tb_page_addr_t end) -{ - assert_memory_lock(); - tb_lock(); - tb_invalidate_phys_range_1(start, end); - tb_unlock(); -} -#endif -/* - * Invalidate all TBs which intersect with the target physical address ran= ge * [start;end[. NOTE: start and end must refer to the *same* physical page. * 'is_cpu_write_access' should be true if called from a real cpu write * access: the virtual CPU will exit the current TB if code is modified in= side @@ -1500,6 +1462,45 @@ void tb_invalidate_phys_page_range(tb_page_addr_t st= art, tb_page_addr_t end, #endif } =20 +/* + * Invalidate all TBs which intersect with the target physical address ran= ge + * [start;end[. NOTE: start and end may refer to *different* physical page= s. + * 'is_cpu_write_access' should be true if called from a real cpu write + * access: the virtual CPU will exit the current TB if code is modified in= side + * this TB. + * + * Called with mmap_lock held for user-mode emulation, grabs tb_lock + * Called with tb_lock held for system-mode emulation + */ +static void tb_invalidate_phys_range_1(tb_page_addr_t start, tb_page_addr_= t end) +{ + tb_page_addr_t next; + + for (next =3D (start & TARGET_PAGE_MASK) + TARGET_PAGE_SIZE; + start < end; + start =3D next, next +=3D TARGET_PAGE_SIZE) { + tb_page_addr_t bound =3D MIN(next, end); + + tb_invalidate_phys_page_range(start, bound, 0); + } +} + +#ifdef CONFIG_SOFTMMU +void tb_invalidate_phys_range(tb_page_addr_t start, tb_page_addr_t end) +{ + assert_tb_locked(); + tb_invalidate_phys_range_1(start, end); +} +#else +void tb_invalidate_phys_range(tb_page_addr_t start, tb_page_addr_t end) +{ + assert_memory_lock(); + tb_lock(); + tb_invalidate_phys_range_1(start, end); + tb_unlock(); +} +#endif + #ifdef CONFIG_SOFTMMU /* len must be <=3D 8 and start must be a multiple of len. * Called via softmmu_template.h when code areas are written to with --=20 2.7.4 From nobody Sat Apr 27 09:56:35 2024 Delivered-To: importer@patchew.org Received-SPF: temperror (zoho.com: Error in retrieving data from DNS) client-ip=208.118.235.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Authentication-Results: mx.zohomail.com; spf=temperror (zoho.com: Error in retrieving data from DNS) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org Return-Path: Received: from lists.gnu.org (208.118.235.17 [208.118.235.17]) by mx.zohomail.com with SMTPS id 1526946820306659.9060419378523; Mon, 21 May 2018 16:53:40 -0700 (PDT) Received: from localhost ([::1]:52911 helo=lists.gnu.org) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1fKucO-0004Xy-41 for importer@patchew.org; Mon, 21 May 2018 19:53:32 -0400 Received: from eggs.gnu.org ([2001:4830:134:3::10]:57946) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1fKuOx-0002gZ-A7 for qemu-devel@nongnu.org; Mon, 21 May 2018 19:39:43 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1fKuOr-0005ZG-CQ for qemu-devel@nongnu.org; Mon, 21 May 2018 19:39:39 -0400 Received: from out1-smtp.messagingengine.com ([66.111.4.25]:39575) by eggs.gnu.org with esmtps (TLS1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.71) (envelope-from ) id 1fKuOq-0005Xg-FS for qemu-devel@nongnu.org; Mon, 21 May 2018 19:39:32 -0400 Received: from compute4.internal (compute4.nyi.internal [10.202.2.44]) by mailout.nyi.internal (Postfix) with ESMTP id 8E2DE2275E; Mon, 21 May 2018 19:39:30 -0400 (EDT) Received: from mailfrontend1 ([10.202.2.162]) by compute4.internal (MEProxy); Mon, 21 May 2018 19:39:30 -0400 Received: from localhost (flamenco.cs.columbia.edu [128.59.20.216]) by mail.messagingengine.com (Postfix) with ESMTPA id 30B85E4119; Mon, 21 May 2018 19:39:30 -0400 (EDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=braap.org; h=cc :date:from:in-reply-to:message-id:references:subject:to :x-me-sender:x-me-sender:x-sasl-enc; s=mesmtp; bh=oxDCE/O0JYKxr4 I19Ul2zkpeah/+Vu0r7R1wcgtp9hM=; b=y8R92n1LoMCk35Uj8eilUOsCc+ZSlP AoNac10IEkINdwi4+RKWdM30+gDbBV7bNgw+iNtZqRFwGVp3yDlm6XGfiB9hGVI+ cEz12X3cPwtb1zCm2rb8bqRnrSeZqZjtVRjBBXYVYT91Jiz2VotGu/iOBUGm20UH T0KAr+7Fyi9/Q= DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d= messagingengine.com; h=cc:date:from:in-reply-to:message-id :references:subject:to:x-me-sender:x-me-sender:x-sasl-enc; s= fm2; bh=oxDCE/O0JYKxr4I19Ul2zkpeah/+Vu0r7R1wcgtp9hM=; b=V0zjxaPh WlpvXAHzAnU8eHS0+EuTlf/i2jdwh1kwmna8su+bdbw0bu6OjqDARoOXcdJyHdVz hTCe9OXX9DzRkYT86X0up0pjrTxPi925o2k3yxCIO/8b0Nbjgq1xnf8xCemjWf8E gjfsK9S7jlmrILlicIn+LTcODUlBUNvQbi5g7saYW1Lg6Elzg/w28Szf0N5eE9/g Ynpbb0D02N7APAFSmRucNBHweD/954v7ByBU2hnWUIOBijnkbVupSkRpSgA3pa9Q 6v5nEy6qefZn2ZWSfDEqlMLePcser9saNq0QkEBgYBt4vw1eIKy7LE61RNMw9vSC wmzyjyUGaUOoQg== X-ME-Proxy: X-ME-Proxy: X-ME-Proxy: X-ME-Proxy: X-ME-Proxy: X-ME-Proxy: X-ME-Sender: From: "Emilio G. Cota" To: qemu-devel@nongnu.org Date: Mon, 21 May 2018 19:39:20 -0400 Message-Id: <1526945967-9687-11-git-send-email-cota@braap.org> X-Mailer: git-send-email 2.7.4 In-Reply-To: <1526945967-9687-1-git-send-email-cota@braap.org> References: <1526945967-9687-1-git-send-email-cota@braap.org> X-detected-operating-system: by eggs.gnu.org: GNU/Linux 2.2.x-3.x [generic] [fuzzy] X-Received-From: 66.111.4.25 Subject: [Qemu-devel] [PATCH v3 10/17] translate-all: use per-page locking in !user-mode X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.21 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: =?UTF-8?q?Alex=20Benn=C3=A9e?= , Richard Henderson , Paolo Bonzini Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: "Qemu-devel" X-ZohoMail: RSF_6 Z_629925259 SPT_0 Content-Transfer-Encoding: quoted-printable MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Groundwork for supporting parallel TCG generation. Instead of using a global lock (tb_lock) to protect changes to pages, use fine-grained, per-page locks in !user-mode. User-mode stays with mmap_lock. Sometimes changes need to happen atomically on more than one page (e.g. when a TB that spans across two pages is added/invalidated, or when a range of pages is invalidated). We therefore introduce struct page_collection, which helps us keep track of a set of pages that have been locked in the appropriate locking order (i.e. by ascending page index). This commit first introduces the structs and the function helpers, to then convert the calling code to use per-page locking. Note that tb_lock is not removed yet. While at it, rename tb_alloc_page to tb_page_add, which pairs with tb_page_remove. Signed-off-by: Emilio G. Cota Tested-by: Alex Benn=C3=A9e --- accel/tcg/translate-all.h | 3 + include/exec/exec-all.h | 3 +- accel/tcg/translate-all.c | 444 +++++++++++++++++++++++++++++++++++++++++-= ---- 3 files changed, 409 insertions(+), 41 deletions(-) diff --git a/accel/tcg/translate-all.h b/accel/tcg/translate-all.h index ba8e4d6..6d1d258 100644 --- a/accel/tcg/translate-all.h +++ b/accel/tcg/translate-all.h @@ -23,6 +23,9 @@ =20 =20 /* translate-all.c */ +struct page_collection *page_collection_lock(tb_page_addr_t start, + tb_page_addr_t end); +void page_collection_unlock(struct page_collection *set); void tb_invalidate_phys_page_fast(tb_page_addr_t start, int len); void tb_invalidate_phys_page_range(tb_page_addr_t start, tb_page_addr_t en= d, int is_cpu_write_access); diff --git a/include/exec/exec-all.h b/include/exec/exec-all.h index b2d8c8e..3fad93b 100644 --- a/include/exec/exec-all.h +++ b/include/exec/exec-all.h @@ -358,7 +358,8 @@ struct TranslationBlock { /* original tb when cflags has CF_NOCACHE */ struct TranslationBlock *orig_tb; /* first and second physical page containing code. The lower bit - of the pointer tells the index in page_next[] */ + of the pointer tells the index in page_next[]. + The list is protected by the TB's page('s) lock(s) */ uintptr_t page_next[2]; tb_page_addr_t page_addr[2]; =20 diff --git a/accel/tcg/translate-all.c b/accel/tcg/translate-all.c index bd08bce..14c2c23 100644 --- a/accel/tcg/translate-all.c +++ b/accel/tcg/translate-all.c @@ -112,8 +112,55 @@ typedef struct PageDesc { #else unsigned long flags; #endif +#ifndef CONFIG_USER_ONLY + QemuSpin lock; +#endif } PageDesc; =20 +/** + * struct page_entry - page descriptor entry + * @pd: pointer to the &struct PageDesc of the page this entry represe= nts + * @index: page index of the page + * @locked: whether the page is locked + * + * This struct helps us keep track of the locked state of a page, without + * bloating &struct PageDesc. + * + * A page lock protects accesses to all fields of &struct PageDesc. + * + * See also: &struct page_collection. + */ +struct page_entry { + PageDesc *pd; + tb_page_addr_t index; + bool locked; +}; + +/** + * struct page_collection - tracks a set of pages (i.e. &struct page_entry= 's) + * @tree: Binary search tree (BST) of the pages, with key =3D=3D page in= dex + * @max: Pointer to the page in @tree with the highest page index + * + * To avoid deadlock we lock pages in ascending order of page index. + * When operating on a set of pages, we need to keep track of them so that + * we can lock them in order and also unlock them later. For this we colle= ct + * pages (i.e. &struct page_entry's) in a binary search @tree. Given that = the + * @tree implementation we use does not provide an O(1) operation to obtai= n the + * highest-ranked element, we use @max to keep track of the inserted page + * with the highest index. This is valuable because if a page is not in + * the tree and its index is higher than @max's, then we can lock it + * without breaking the locking order rule. + * + * Note on naming: 'struct page_set' would be shorter, but we already have= a few + * page_set_*() helpers, so page_collection is used instead to avoid confu= sion. + * + * See also: page_collection_lock(). + */ +struct page_collection { + GTree *tree; + struct page_entry *max; +}; + /* list iterators for lists of tagged pointers in TranslationBlock */ #define TB_FOR_EACH_TAGGED(head, tb, n, field) \ for (n =3D (head) & 1, tb =3D (TranslationBlock *)((head) & ~1); = \ @@ -507,6 +554,15 @@ static PageDesc *page_find_alloc(tb_page_addr_t index,= int alloc) return NULL; } pd =3D g_new0(PageDesc, V_L2_SIZE); +#ifndef CONFIG_USER_ONLY + { + int i; + + for (i =3D 0; i < V_L2_SIZE; i++) { + qemu_spin_init(&pd[i].lock); + } + } +#endif existing =3D atomic_cmpxchg(lp, NULL, pd); if (unlikely(existing)) { g_free(pd); @@ -522,6 +578,253 @@ static inline PageDesc *page_find(tb_page_addr_t inde= x) return page_find_alloc(index, 0); } =20 +static void page_lock_pair(PageDesc **ret_p1, tb_page_addr_t phys1, + PageDesc **ret_p2, tb_page_addr_t phys2, int al= loc); + +/* In user-mode page locks aren't used; mmap_lock is enough */ +#ifdef CONFIG_USER_ONLY +static inline void page_lock(PageDesc *pd) +{ } + +static inline void page_unlock(PageDesc *pd) +{ } + +static inline void page_lock_tb(const TranslationBlock *tb) +{ } + +static inline void page_unlock_tb(const TranslationBlock *tb) +{ } + +struct page_collection * +page_collection_lock(tb_page_addr_t start, tb_page_addr_t end) +{ + return NULL; +} + +void page_collection_unlock(struct page_collection *set) +{ } +#else /* !CONFIG_USER_ONLY */ + +static inline void page_lock(PageDesc *pd) +{ + qemu_spin_lock(&pd->lock); +} + +static inline void page_unlock(PageDesc *pd) +{ + qemu_spin_unlock(&pd->lock); +} + +/* lock the page(s) of a TB in the correct acquisition order */ +static inline void page_lock_tb(const TranslationBlock *tb) +{ + page_lock_pair(NULL, tb->page_addr[0], NULL, tb->page_addr[1], 0); +} + +static inline void page_unlock_tb(const TranslationBlock *tb) +{ + page_unlock(page_find(tb->page_addr[0] >> TARGET_PAGE_BITS)); + if (unlikely(tb->page_addr[1] !=3D -1)) { + page_unlock(page_find(tb->page_addr[1] >> TARGET_PAGE_BITS)); + } +} + +static inline struct page_entry * +page_entry_new(PageDesc *pd, tb_page_addr_t index) +{ + struct page_entry *pe =3D g_malloc(sizeof(*pe)); + + pe->index =3D index; + pe->pd =3D pd; + pe->locked =3D false; + return pe; +} + +static void page_entry_destroy(gpointer p) +{ + struct page_entry *pe =3D p; + + g_assert(pe->locked); + page_unlock(pe->pd); + g_free(pe); +} + +/* returns false on success */ +static bool page_entry_trylock(struct page_entry *pe) +{ + bool busy; + + busy =3D qemu_spin_trylock(&pe->pd->lock); + if (!busy) { + g_assert(!pe->locked); + pe->locked =3D true; + } + return busy; +} + +static void do_page_entry_lock(struct page_entry *pe) +{ + page_lock(pe->pd); + g_assert(!pe->locked); + pe->locked =3D true; +} + +static gboolean page_entry_lock(gpointer key, gpointer value, gpointer dat= a) +{ + struct page_entry *pe =3D value; + + do_page_entry_lock(pe); + return FALSE; +} + +static gboolean page_entry_unlock(gpointer key, gpointer value, gpointer d= ata) +{ + struct page_entry *pe =3D value; + + if (pe->locked) { + pe->locked =3D false; + page_unlock(pe->pd); + } + return FALSE; +} + +/* + * Trylock a page, and if successful, add the page to a collection. + * Returns true ("busy") if the page could not be locked; false otherwise. + */ +static bool page_trylock_add(struct page_collection *set, tb_page_addr_t a= ddr) +{ + tb_page_addr_t index =3D addr >> TARGET_PAGE_BITS; + struct page_entry *pe; + PageDesc *pd; + + pe =3D g_tree_lookup(set->tree, &index); + if (pe) { + return false; + } + + pd =3D page_find(index); + if (pd =3D=3D NULL) { + return false; + } + + pe =3D page_entry_new(pd, index); + g_tree_insert(set->tree, &pe->index, pe); + + /* + * If this is either (1) the first insertion or (2) a page whose index + * is higher than any other so far, just lock the page and move on. + */ + if (set->max =3D=3D NULL || pe->index > set->max->index) { + set->max =3D pe; + do_page_entry_lock(pe); + return false; + } + /* + * Try to acquire out-of-order lock; if busy, return busy so that we a= cquire + * locks in order. + */ + return page_entry_trylock(pe); +} + +static gint tb_page_addr_cmp(gconstpointer ap, gconstpointer bp, gpointer = udata) +{ + tb_page_addr_t a =3D *(const tb_page_addr_t *)ap; + tb_page_addr_t b =3D *(const tb_page_addr_t *)bp; + + if (a =3D=3D b) { + return 0; + } else if (a < b) { + return -1; + } + return 1; +} + +/* + * Lock a range of pages ([@start,@end[) as well as the pages of all + * intersecting TBs. + * Locking order: acquire locks in ascending order of page index. + */ +struct page_collection * +page_collection_lock(tb_page_addr_t start, tb_page_addr_t end) +{ + struct page_collection *set =3D g_malloc(sizeof(*set)); + tb_page_addr_t index; + PageDesc *pd; + + start >>=3D TARGET_PAGE_BITS; + end >>=3D TARGET_PAGE_BITS; + g_assert(start <=3D end); + + set->tree =3D g_tree_new_full(tb_page_addr_cmp, NULL, NULL, + page_entry_destroy); + set->max =3D NULL; + + retry: + g_tree_foreach(set->tree, page_entry_lock, NULL); + + for (index =3D start; index <=3D end; index++) { + TranslationBlock *tb; + int n; + + pd =3D page_find(index); + if (pd =3D=3D NULL) { + continue; + } + if (page_trylock_add(set, index << TARGET_PAGE_BITS)) { + g_tree_foreach(set->tree, page_entry_unlock, NULL); + goto retry; + } + PAGE_FOR_EACH_TB(pd, tb, n) { + if (page_trylock_add(set, tb->page_addr[0]) || + (tb->page_addr[1] !=3D -1 && + page_trylock_add(set, tb->page_addr[1]))) { + /* drop all locks, and reacquire in order */ + g_tree_foreach(set->tree, page_entry_unlock, NULL); + goto retry; + } + } + } + return set; +} + +void page_collection_unlock(struct page_collection *set) +{ + /* entries are unlocked and freed via page_entry_destroy */ + g_tree_destroy(set->tree); + g_free(set); +} + +#endif /* !CONFIG_USER_ONLY */ + +static void page_lock_pair(PageDesc **ret_p1, tb_page_addr_t phys1, + PageDesc **ret_p2, tb_page_addr_t phys2, int al= loc) +{ + PageDesc *p1, *p2; + + assert_memory_lock(); + g_assert(phys1 !=3D -1 && phys1 !=3D phys2); + p1 =3D page_find_alloc(phys1 >> TARGET_PAGE_BITS, alloc); + if (ret_p1) { + *ret_p1 =3D p1; + } + if (likely(phys2 =3D=3D -1)) { + page_lock(p1); + return; + } + p2 =3D page_find_alloc(phys2 >> TARGET_PAGE_BITS, alloc); + if (ret_p2) { + *ret_p2 =3D p2; + } + if (phys1 < phys2) { + page_lock(p1); + page_lock(p2); + } else { + page_lock(p2); + page_lock(p1); + } +} + #if defined(CONFIG_USER_ONLY) /* Currently it is not recommended to allocate big chunks of data in user mode. It will change when a dedicated libc will be used. */ @@ -807,6 +1110,7 @@ static TranslationBlock *tb_alloc(target_ulong pc) return tb; } =20 +/* call with @p->lock held */ static inline void invalidate_page_bitmap(PageDesc *p) { #ifdef CONFIG_SOFTMMU @@ -828,8 +1132,10 @@ static void page_flush_tb_1(int level, void **lp) PageDesc *pd =3D *lp; =20 for (i =3D 0; i < V_L2_SIZE; ++i) { + page_lock(&pd[i]); pd[i].first_tb =3D (uintptr_t)NULL; invalidate_page_bitmap(pd + i); + page_unlock(&pd[i]); } } else { void **pp =3D *lp; @@ -956,6 +1262,7 @@ static void tb_page_check(void) =20 #endif /* CONFIG_USER_ONLY */ =20 +/* call with @pd->lock held */ static inline void tb_page_remove(PageDesc *pd, TranslationBlock *tb) { TranslationBlock *tb1; @@ -1032,11 +1339,8 @@ static inline void tb_jmp_unlink(TranslationBlock *t= b) } } =20 -/* invalidate one TB - * - * Called with tb_lock held. - */ -void tb_phys_invalidate(TranslationBlock *tb, tb_page_addr_t page_addr) +/* If @rm_from_page_list is set, call with the TB's pages' locks held */ +static void do_tb_phys_invalidate(TranslationBlock *tb, bool rm_from_page_= list) { CPUState *cpu; PageDesc *p; @@ -1056,15 +1360,15 @@ void tb_phys_invalidate(TranslationBlock *tb, tb_pa= ge_addr_t page_addr) } =20 /* remove the TB from the page list */ - if (tb->page_addr[0] !=3D page_addr) { + if (rm_from_page_list) { p =3D page_find(tb->page_addr[0] >> TARGET_PAGE_BITS); tb_page_remove(p, tb); invalidate_page_bitmap(p); - } - if (tb->page_addr[1] !=3D -1 && tb->page_addr[1] !=3D page_addr) { - p =3D page_find(tb->page_addr[1] >> TARGET_PAGE_BITS); - tb_page_remove(p, tb); - invalidate_page_bitmap(p); + if (tb->page_addr[1] !=3D -1) { + p =3D page_find(tb->page_addr[1] >> TARGET_PAGE_BITS); + tb_page_remove(p, tb); + invalidate_page_bitmap(p); + } } =20 /* remove the TB from the hash list */ @@ -1086,7 +1390,28 @@ void tb_phys_invalidate(TranslationBlock *tb, tb_pag= e_addr_t page_addr) tcg_ctx->tb_phys_invalidate_count + 1); } =20 +static void tb_phys_invalidate__locked(TranslationBlock *tb) +{ + do_tb_phys_invalidate(tb, true); +} + +/* invalidate one TB + * + * Called with tb_lock held. + */ +void tb_phys_invalidate(TranslationBlock *tb, tb_page_addr_t page_addr) +{ + if (page_addr =3D=3D -1) { + page_lock_tb(tb); + do_tb_phys_invalidate(tb, true); + page_unlock_tb(tb); + } else { + do_tb_phys_invalidate(tb, false); + } +} + #ifdef CONFIG_SOFTMMU +/* call with @p->lock held */ static void build_page_bitmap(PageDesc *p) { int n, tb_start, tb_end; @@ -1116,11 +1441,11 @@ static void build_page_bitmap(PageDesc *p) /* add the tb in the target page and protect it if necessary * * Called with mmap_lock held for user-mode emulation. + * Called with @p->lock held. */ -static inline void tb_alloc_page(TranslationBlock *tb, - unsigned int n, tb_page_addr_t page_addr) +static inline void tb_page_add(PageDesc *p, TranslationBlock *tb, + unsigned int n, tb_page_addr_t page_addr) { - PageDesc *p; #ifndef CONFIG_USER_ONLY bool page_already_protected; #endif @@ -1128,7 +1453,6 @@ static inline void tb_alloc_page(TranslationBlock *tb, assert_memory_lock(); =20 tb->page_addr[n] =3D page_addr; - p =3D page_find_alloc(page_addr >> TARGET_PAGE_BITS, 1); tb->page_next[n] =3D p->first_tb; #ifndef CONFIG_USER_ONLY page_already_protected =3D p->first_tb !=3D (uintptr_t)NULL; @@ -1180,18 +1504,28 @@ static inline void tb_alloc_page(TranslationBlock *= tb, static void tb_link_page(TranslationBlock *tb, tb_page_addr_t phys_pc, tb_page_addr_t phys_page2) { + PageDesc *p; + PageDesc *p2 =3D NULL; uint32_t h; =20 assert_memory_lock(); =20 - /* add in the page list */ - tb_alloc_page(tb, 0, phys_pc & TARGET_PAGE_MASK); - if (phys_page2 !=3D -1) { - tb_alloc_page(tb, 1, phys_page2); + /* + * Add the TB to the page list, acquiring first the pages's locks. + */ + page_lock_pair(&p, phys_pc, &p2, phys_page2, 1); + tb_page_add(p, tb, 0, phys_pc & TARGET_PAGE_MASK); + if (p2) { + tb_page_add(p2, tb, 1, phys_page2); } else { tb->page_addr[1] =3D -1; } =20 + if (p2) { + page_unlock(p2); + } + page_unlock(p); + /* add in the hash table */ h =3D tb_hash_func(phys_pc, tb->pc, tb->flags, tb->cflags & CF_HASH_MA= SK, tb->trace_vcpu_dstate); @@ -1364,21 +1698,17 @@ TranslationBlock *tb_gen_code(CPUState *cpu, } =20 /* - * Invalidate all TBs which intersect with the target physical address ran= ge - * [start;end[. NOTE: start and end must refer to the *same* physical page. - * 'is_cpu_write_access' should be true if called from a real cpu write - * access: the virtual CPU will exit the current TB if code is modified in= side - * this TB. - * - * Called with tb_lock/mmap_lock held for user-mode emulation - * Called with tb_lock held for system-mode emulation + * Call with all @pages locked. + * @p must be non-NULL. */ -void tb_invalidate_phys_page_range(tb_page_addr_t start, tb_page_addr_t en= d, - int is_cpu_write_access) +static void +tb_invalidate_phys_page_range__locked(struct page_collection *pages, + PageDesc *p, tb_page_addr_t start, + tb_page_addr_t end, + int is_cpu_write_access) { TranslationBlock *tb; tb_page_addr_t tb_start, tb_end; - PageDesc *p; int n; #ifdef TARGET_HAS_PRECISE_SMC CPUState *cpu =3D current_cpu; @@ -1394,10 +1724,6 @@ void tb_invalidate_phys_page_range(tb_page_addr_t st= art, tb_page_addr_t end, assert_memory_lock(); assert_tb_locked(); =20 - p =3D page_find(start >> TARGET_PAGE_BITS); - if (!p) { - return; - } #if defined(TARGET_HAS_PRECISE_SMC) if (cpu !=3D NULL) { env =3D cpu->env_ptr; @@ -1443,7 +1769,7 @@ void tb_invalidate_phys_page_range(tb_page_addr_t sta= rt, tb_page_addr_t end, ¤t_flags); } #endif /* TARGET_HAS_PRECISE_SMC */ - tb_phys_invalidate(tb, -1); + tb_phys_invalidate__locked(tb); } } #if !defined(CONFIG_USER_ONLY) @@ -1455,6 +1781,7 @@ void tb_invalidate_phys_page_range(tb_page_addr_t sta= rt, tb_page_addr_t end, #endif #ifdef TARGET_HAS_PRECISE_SMC if (current_tb_modified) { + page_collection_unlock(pages); /* Force execution of one insn next time. */ cpu->cflags_next_tb =3D 1 | curr_cflags(); cpu_loop_exit_noexc(cpu); @@ -1464,6 +1791,35 @@ void tb_invalidate_phys_page_range(tb_page_addr_t st= art, tb_page_addr_t end, =20 /* * Invalidate all TBs which intersect with the target physical address ran= ge + * [start;end[. NOTE: start and end must refer to the *same* physical page. + * 'is_cpu_write_access' should be true if called from a real cpu write + * access: the virtual CPU will exit the current TB if code is modified in= side + * this TB. + * + * Called with tb_lock/mmap_lock held for user-mode emulation + * Called with tb_lock held for system-mode emulation + */ +void tb_invalidate_phys_page_range(tb_page_addr_t start, tb_page_addr_t en= d, + int is_cpu_write_access) +{ + struct page_collection *pages; + PageDesc *p; + + assert_memory_lock(); + assert_tb_locked(); + + p =3D page_find(start >> TARGET_PAGE_BITS); + if (p =3D=3D NULL) { + return; + } + pages =3D page_collection_lock(start, end); + tb_invalidate_phys_page_range__locked(pages, p, start, end, + is_cpu_write_access); + page_collection_unlock(pages); +} + +/* + * Invalidate all TBs which intersect with the target physical address ran= ge * [start;end[. NOTE: start and end may refer to *different* physical page= s. * 'is_cpu_write_access' should be true if called from a real cpu write * access: the virtual CPU will exit the current TB if code is modified in= side @@ -1474,15 +1830,22 @@ void tb_invalidate_phys_page_range(tb_page_addr_t s= tart, tb_page_addr_t end, */ static void tb_invalidate_phys_range_1(tb_page_addr_t start, tb_page_addr_= t end) { + struct page_collection *pages; tb_page_addr_t next; =20 + pages =3D page_collection_lock(start, end); for (next =3D (start & TARGET_PAGE_MASK) + TARGET_PAGE_SIZE; start < end; start =3D next, next +=3D TARGET_PAGE_SIZE) { + PageDesc *pd =3D page_find(start >> TARGET_PAGE_BITS); tb_page_addr_t bound =3D MIN(next, end); =20 - tb_invalidate_phys_page_range(start, bound, 0); + if (pd =3D=3D NULL) { + continue; + } + tb_invalidate_phys_page_range__locked(pages, pd, start, bound, 0); } + page_collection_unlock(pages); } =20 #ifdef CONFIG_SOFTMMU @@ -1508,6 +1871,7 @@ void tb_invalidate_phys_range(tb_page_addr_t start, t= b_page_addr_t end) */ void tb_invalidate_phys_page_fast(tb_page_addr_t start, int len) { + struct page_collection *pages; PageDesc *p; =20 #if 0 @@ -1525,11 +1889,10 @@ void tb_invalidate_phys_page_fast(tb_page_addr_t st= art, int len) if (!p) { return; } + + pages =3D page_collection_lock(start, start + len); if (!p->code_bitmap && ++p->code_write_count >=3D SMC_BITMAP_USE_THRESHOLD) { - /* build code bitmap. FIXME: writes should be protected by - * tb_lock, reads by tb_lock or RCU. - */ build_page_bitmap(p); } if (p->code_bitmap) { @@ -1543,8 +1906,9 @@ void tb_invalidate_phys_page_fast(tb_page_addr_t star= t, int len) } } else { do_invalidate: - tb_invalidate_phys_page_range(start, start + len, 1); + tb_invalidate_phys_page_range__locked(pages, p, start, start + len= , 1); } + page_collection_unlock(pages); } #else /* Called with mmap_lock held. If pc is not 0 then it indicates the --=20 2.7.4 From nobody Sat Apr 27 09:56:35 2024 Delivered-To: importer@patchew.org Received-SPF: pass (zoho.com: domain of gnu.org designates 208.118.235.17 as permitted sender) client-ip=208.118.235.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Authentication-Results: mx.zohomail.com; spf=pass (zoho.com: domain of gnu.org designates 208.118.235.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org Return-Path: Received: from lists.gnu.org (208.118.235.17 [208.118.235.17]) by mx.zohomail.com with SMTPS id 1526946820601687.4084581437148; Mon, 21 May 2018 16:53:40 -0700 (PDT) Received: from localhost ([::1]:52912 helo=lists.gnu.org) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1fKucN-0004YG-Vj for importer@patchew.org; Mon, 21 May 2018 19:53:32 -0400 Received: from eggs.gnu.org ([2001:4830:134:3::10]:57897) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1fKuOv-0002f7-I1 for qemu-devel@nongnu.org; Mon, 21 May 2018 19:39:39 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1fKuOr-0005Z2-BT for qemu-devel@nongnu.org; Mon, 21 May 2018 19:39:37 -0400 Received: from out1-smtp.messagingengine.com ([66.111.4.25]:45731) by eggs.gnu.org with esmtps (TLS1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.71) (envelope-from ) id 1fKuOq-0005Xa-Fd for qemu-devel@nongnu.org; Mon, 21 May 2018 19:39:32 -0400 Received: from compute4.internal (compute4.nyi.internal [10.202.2.44]) by mailout.nyi.internal (Postfix) with ESMTP id B37D5226D3; Mon, 21 May 2018 19:39:30 -0400 (EDT) Received: from mailfrontend2 ([10.202.2.163]) by compute4.internal (MEProxy); Mon, 21 May 2018 19:39:30 -0400 Received: from localhost (flamenco.cs.columbia.edu [128.59.20.216]) by mail.messagingengine.com (Postfix) with ESMTPA id 5B92A10262; Mon, 21 May 2018 19:39:30 -0400 (EDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=braap.org; h=cc :content-transfer-encoding:content-type:date:from:in-reply-to :message-id:mime-version:references:subject:to:x-me-sender :x-me-sender:x-sasl-enc; s=mesmtp; bh=Irc+n7VRz2Yx2T9Ozc0T9B+Ojo a8Kqkft45iuNaCDCc=; b=qTxcZ8fxJEJ1ZxzXFMsN7ry8eGECQbXAoUXjt8t2rb 7290IxNNwbxIuNweNPLl838tg2QdZJuWSia9e9ccK321dfhwaHrS0m85OBm4JKzY aPRlfyucstRh7igh0ZZ/ksNVS1Dol/kIREgIVmhtM1/qZJSRy8Ig/VEm6BIvH0rl I= DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d= messagingengine.com; h=cc:content-transfer-encoding:content-type :date:from:in-reply-to:message-id:mime-version:references :subject:to:x-me-sender:x-me-sender:x-sasl-enc; s=fm2; bh=Irc+n7 VRz2Yx2T9Ozc0T9B+Ojoa8Kqkft45iuNaCDCc=; b=VNzy8Tldr8q9lYyI8WwP4C y2tjN90TKmFndVj0e6Cw2V9ui9S8WBGzKMAjaDCz5sfi+t+GrKB/Jf+0Izu50tp3 YutgWhhl/qyAEwdfG78A2XAdxROGbkRY4wpPYMh9fPIjHBRn/kuK/1mzlSLyOmw3 4Z9DiScfdBvQt6qQ+2VkNeL2muZUF3QFapodcneTBWTPBo4o3kT331cWY9w8+0kL 3e1hKL3+MzbTlntL1fyDzDr8R40cZeq1yzEp9CNHy+3b9O2x8XYJkVWQ9ovSMJvE Plh4ExetnzKmBQYTZqTY0eVkn4dLAo3tB5bSdfd7XJavGUx1LdhPKmYebq0Kdj4A == X-ME-Proxy: X-ME-Proxy: X-ME-Proxy: X-ME-Proxy: X-ME-Proxy: X-ME-Proxy: X-ME-Sender: From: "Emilio G. Cota" To: qemu-devel@nongnu.org Date: Mon, 21 May 2018 19:39:21 -0400 Message-Id: <1526945967-9687-12-git-send-email-cota@braap.org> X-Mailer: git-send-email 2.7.4 In-Reply-To: <1526945967-9687-1-git-send-email-cota@braap.org> References: <1526945967-9687-1-git-send-email-cota@braap.org> MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable X-detected-operating-system: by eggs.gnu.org: GNU/Linux 2.2.x-3.x [generic] [fuzzy] X-Received-From: 66.111.4.25 Subject: [Qemu-devel] [PATCH v3 11/17] translate-all: add page_locked assertions X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.21 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: =?UTF-8?q?Alex=20Benn=C3=A9e?= , Richard Henderson , Paolo Bonzini Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: "Qemu-devel" X-ZohoMail: RSF_0 Z_629925259 SPT_0 This is only compiled under CONFIG_DEBUG_TCG to avoid bloating the binary. In user-mode, assert_page_locked is equivalent to assert_mmap_lock. Note: There are some tb_lock assertions left that will be removed by later patches. Suggested-by: Alex Benn=C3=A9e Signed-off-by: Emilio G. Cota Tested-by: Alex Benn=C3=A9e --- accel/tcg/translate-all.c | 81 +++++++++++++++++++++++++++++++++++++++++++= ++-- 1 file changed, 78 insertions(+), 3 deletions(-) diff --git a/accel/tcg/translate-all.c b/accel/tcg/translate-all.c index 14c2c23..8286203 100644 --- a/accel/tcg/translate-all.c +++ b/accel/tcg/translate-all.c @@ -583,6 +583,9 @@ static void page_lock_pair(PageDesc **ret_p1, tb_page_a= ddr_t phys1, =20 /* In user-mode page locks aren't used; mmap_lock is enough */ #ifdef CONFIG_USER_ONLY + +#define assert_page_locked(pd) tcg_debug_assert(have_mmap_lock()) + static inline void page_lock(PageDesc *pd) { } =20 @@ -605,14 +608,80 @@ void page_collection_unlock(struct page_collection *s= et) { } #else /* !CONFIG_USER_ONLY */ =20 +#ifdef CONFIG_DEBUG_TCG + +static __thread GHashTable *ht_pages_locked_debug; + +static void ht_pages_locked_debug_init(void) +{ + if (ht_pages_locked_debug) { + return; + } + ht_pages_locked_debug =3D g_hash_table_new(NULL, NULL); +} + +static bool page_is_locked(const PageDesc *pd) +{ + PageDesc *found; + + ht_pages_locked_debug_init(); + found =3D g_hash_table_lookup(ht_pages_locked_debug, pd); + return !!found; +} + +static void page_lock__debug(PageDesc *pd) +{ + ht_pages_locked_debug_init(); + g_assert(!page_is_locked(pd)); + g_hash_table_insert(ht_pages_locked_debug, pd, pd); +} + +static void page_unlock__debug(const PageDesc *pd) +{ + bool removed; + + ht_pages_locked_debug_init(); + g_assert(page_is_locked(pd)); + removed =3D g_hash_table_remove(ht_pages_locked_debug, pd); + g_assert(removed); +} + +static void +do_assert_page_locked(const PageDesc *pd, const char *file, int line) +{ + if (unlikely(!page_is_locked(pd))) { + error_report("assert_page_lock: PageDesc %p not locked @ %s:%d", + pd, file, line); + abort(); + } +} + +#define assert_page_locked(pd) do_assert_page_locked(pd, __FILE__, __LINE_= _) + +#else /* !CONFIG_DEBUG_TCG */ + +#define assert_page_locked(pd) + +static inline void page_lock__debug(const PageDesc *pd) +{ +} + +static inline void page_unlock__debug(const PageDesc *pd) +{ +} + +#endif /* CONFIG_DEBUG_TCG */ + static inline void page_lock(PageDesc *pd) { + page_lock__debug(pd); qemu_spin_lock(&pd->lock); } =20 static inline void page_unlock(PageDesc *pd) { qemu_spin_unlock(&pd->lock); + page_unlock__debug(pd); } =20 /* lock the page(s) of a TB in the correct acquisition order */ @@ -775,6 +844,7 @@ page_collection_lock(tb_page_addr_t start, tb_page_addr= _t end) g_tree_foreach(set->tree, page_entry_unlock, NULL); goto retry; } + assert_page_locked(pd); PAGE_FOR_EACH_TB(pd, tb, n) { if (page_trylock_add(set, tb->page_addr[0]) || (tb->page_addr[1] !=3D -1 && @@ -1113,6 +1183,7 @@ static TranslationBlock *tb_alloc(target_ulong pc) /* call with @p->lock held */ static inline void invalidate_page_bitmap(PageDesc *p) { + assert_page_locked(p); #ifdef CONFIG_SOFTMMU g_free(p->code_bitmap); p->code_bitmap =3D NULL; @@ -1269,6 +1340,7 @@ static inline void tb_page_remove(PageDesc *pd, Trans= lationBlock *tb) uintptr_t *pprev; unsigned int n1; =20 + assert_page_locked(pd); pprev =3D &pd->first_tb; PAGE_FOR_EACH_TB(pd, tb1, n1) { if (tb1 =3D=3D tb) { @@ -1417,6 +1489,7 @@ static void build_page_bitmap(PageDesc *p) int n, tb_start, tb_end; TranslationBlock *tb; =20 + assert_page_locked(p); p->code_bitmap =3D bitmap_new(TARGET_PAGE_SIZE); =20 PAGE_FOR_EACH_TB(p, tb, n) { @@ -1450,7 +1523,7 @@ static inline void tb_page_add(PageDesc *p, Translati= onBlock *tb, bool page_already_protected; #endif =20 - assert_memory_lock(); + assert_page_locked(p); =20 tb->page_addr[n] =3D page_addr; tb->page_next[n] =3D p->first_tb; @@ -1721,8 +1794,7 @@ tb_invalidate_phys_page_range__locked(struct page_col= lection *pages, uint32_t current_flags =3D 0; #endif /* TARGET_HAS_PRECISE_SMC */ =20 - assert_memory_lock(); - assert_tb_locked(); + assert_page_locked(p); =20 #if defined(TARGET_HAS_PRECISE_SMC) if (cpu !=3D NULL) { @@ -1734,6 +1806,7 @@ tb_invalidate_phys_page_range__locked(struct page_col= lection *pages, /* XXX: see if in some cases it could be faster to invalidate all the code */ PAGE_FOR_EACH_TB(p, tb, n) { + assert_page_locked(p); /* NOTE: this is subtle as a TB may span two physical pages */ if (n =3D=3D 0) { /* NOTE: tb_end may be after the end of the page, but @@ -1891,6 +1964,7 @@ void tb_invalidate_phys_page_fast(tb_page_addr_t star= t, int len) } =20 pages =3D page_collection_lock(start, start + len); + assert_page_locked(p); if (!p->code_bitmap && ++p->code_write_count >=3D SMC_BITMAP_USE_THRESHOLD) { build_page_bitmap(p); @@ -1949,6 +2023,7 @@ static bool tb_invalidate_phys_page(tb_page_addr_t ad= dr, uintptr_t pc) env =3D cpu->env_ptr; } #endif + assert_page_locked(p); PAGE_FOR_EACH_TB(p, tb, n) { #ifdef TARGET_HAS_PRECISE_SMC if (current_tb =3D=3D tb && --=20 2.7.4 From nobody Sat Apr 27 09:56:35 2024 Delivered-To: importer@patchew.org Received-SPF: pass (zoho.com: domain of gnu.org designates 208.118.235.17 as permitted sender) client-ip=208.118.235.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Authentication-Results: mx.zohomail.com; spf=pass (zoho.com: domain of gnu.org designates 208.118.235.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org Return-Path: Received: from lists.gnu.org (lists.gnu.org [208.118.235.17]) by mx.zohomail.com with SMTPS id 1526946120491647.4716159596912; Mon, 21 May 2018 16:42:00 -0700 (PDT) Received: from localhost ([::1]:52853 helo=lists.gnu.org) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1fKuR1-0003xC-R0 for importer@patchew.org; Mon, 21 May 2018 19:41:47 -0400 Received: from eggs.gnu.org ([2001:4830:134:3::10]:57833) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1fKuOt-0002eL-6j for qemu-devel@nongnu.org; Mon, 21 May 2018 19:39:37 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1fKuOr-0005YZ-9f for qemu-devel@nongnu.org; Mon, 21 May 2018 19:39:35 -0400 Received: from out1-smtp.messagingengine.com ([66.111.4.25]:40953) by eggs.gnu.org with esmtps (TLS1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.71) (envelope-from ) id 1fKuOq-0005XX-FP for qemu-devel@nongnu.org; Mon, 21 May 2018 19:39:32 -0400 Received: from compute4.internal (compute4.nyi.internal [10.202.2.44]) by mailout.nyi.internal (Postfix) with ESMTP id D319122759; Mon, 21 May 2018 19:39:30 -0400 (EDT) Received: from mailfrontend1 ([10.202.2.162]) by compute4.internal (MEProxy); Mon, 21 May 2018 19:39:30 -0400 Received: from localhost (flamenco.cs.columbia.edu [128.59.20.216]) by mail.messagingengine.com (Postfix) with ESMTPA id 919ADE4F0A; Mon, 21 May 2018 19:39:30 -0400 (EDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=braap.org; h=cc :date:from:in-reply-to:message-id:references:subject:to :x-me-sender:x-me-sender:x-sasl-enc; s=mesmtp; bh=nIDCtJ0u26J/zd SaAd+Q34P3H++c5AT5WVMGkrFWiQk=; b=viMhIgWTK5TASWxK1r1xvNgiNEdsSe ybWSdWuBLDO5qE/YiaVUUAJGbvG5gBeRYzPLSSOSXGiYWDF7EEuBq+4eO9Ru2NRA orojgzpHPvJm9u1XvgHZ+UmvIoEGILYuHUeGTmNMF+41tz0zMOGPxmS8JxCI1Lyl X8nvAJiWSsVKE= DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d= messagingengine.com; h=cc:date:from:in-reply-to:message-id :references:subject:to:x-me-sender:x-me-sender:x-sasl-enc; s= fm2; bh=nIDCtJ0u26J/zdSaAd+Q34P3H++c5AT5WVMGkrFWiQk=; b=RCfdASJU Z0/B2NRUMFUiXE/TgqMXKZN0I3wLnl7Fi4w+3z8AJdd6bQHYt27nv285sClBlDe9 yHrIKuHtMmfgIrJi6pjrFKIlzgzxmwuOBE5hZWzK1qwVGO65zF8kZ/LBvBZKGJMG NymWIgSiuF8RY9/OPb149g1AXzidVxtsV+glMxB8R8n0iOzXhHUoA4+ceBNhAv3M jEVl0RYlF9bfTrZiNPTZqdWmJCEdGGQByddJgDbqo6QyrgoEDsofj0QDm6iDSY5q 4M2kv+wrOwslpVGMsRmRFkX+YbSbjIklkNwteYezT8fXDOkzKYjZbFRxxv/3xWGk zAxA47pk9/BJaw== X-ME-Proxy: X-ME-Proxy: X-ME-Proxy: X-ME-Proxy: X-ME-Proxy: X-ME-Proxy: X-ME-Sender: From: "Emilio G. Cota" To: qemu-devel@nongnu.org Date: Mon, 21 May 2018 19:39:22 -0400 Message-Id: <1526945967-9687-13-git-send-email-cota@braap.org> X-Mailer: git-send-email 2.7.4 In-Reply-To: <1526945967-9687-1-git-send-email-cota@braap.org> References: <1526945967-9687-1-git-send-email-cota@braap.org> X-detected-operating-system: by eggs.gnu.org: GNU/Linux 2.2.x-3.x [generic] [fuzzy] X-Received-From: 66.111.4.25 Subject: [Qemu-devel] [PATCH v3 12/17] translate-all: introduce assert_no_pages_locked X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.21 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: =?UTF-8?q?Alex=20Benn=C3=A9e?= , Richard Henderson , Paolo Bonzini Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: "Qemu-devel" X-ZohoMail: RSF_0 Z_629925259 SPT_0 Content-Transfer-Encoding: quoted-printable MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" The appended adds assertions to make sure we do not longjmp with page locks held. Note that user-mode has nothing to check, since page_locks are !user-mode only. Signed-off-by: Emilio G. Cota Tested-by: Alex Benn=C3=A9e --- include/exec/exec-all.h | 8 ++++++++ accel/tcg/cpu-exec.c | 1 + accel/tcg/translate-all.c | 7 +++++++ 3 files changed, 16 insertions(+) diff --git a/include/exec/exec-all.h b/include/exec/exec-all.h index 3fad93b..66902f7 100644 --- a/include/exec/exec-all.h +++ b/include/exec/exec-all.h @@ -434,6 +434,14 @@ void tb_lock(void); void tb_unlock(void); void tb_lock_reset(void); =20 +#if !defined(CONFIG_USER_ONLY) && defined(CONFIG_DEBUG_TCG) +void assert_no_pages_locked(void); +#else +static inline void assert_no_pages_locked(void) +{ +} +#endif + #if !defined(CONFIG_USER_ONLY) =20 struct MemoryRegion *iotlb_to_region(CPUState *cpu, diff --git a/accel/tcg/cpu-exec.c b/accel/tcg/cpu-exec.c index 7b934a6..ad1f0c4 100644 --- a/accel/tcg/cpu-exec.c +++ b/accel/tcg/cpu-exec.c @@ -274,6 +274,7 @@ void cpu_exec_step_atomic(CPUState *cpu) tcg_debug_assert(!have_mmap_lock()); #endif tb_lock_reset(); + assert_no_pages_locked(); } =20 if (in_exclusive_region) { diff --git a/accel/tcg/translate-all.c b/accel/tcg/translate-all.c index 8286203..f3a0ecb 100644 --- a/accel/tcg/translate-all.c +++ b/accel/tcg/translate-all.c @@ -658,6 +658,12 @@ do_assert_page_locked(const PageDesc *pd, const char *= file, int line) =20 #define assert_page_locked(pd) do_assert_page_locked(pd, __FILE__, __LINE_= _) =20 +void assert_no_pages_locked(void) +{ + ht_pages_locked_debug_init(); + g_assert(g_hash_table_size(ht_pages_locked_debug) =3D=3D 0); +} + #else /* !CONFIG_DEBUG_TCG */ =20 #define assert_page_locked(pd) @@ -828,6 +834,7 @@ page_collection_lock(tb_page_addr_t start, tb_page_addr= _t end) set->tree =3D g_tree_new_full(tb_page_addr_cmp, NULL, NULL, page_entry_destroy); set->max =3D NULL; + assert_no_pages_locked(); =20 retry: g_tree_foreach(set->tree, page_entry_lock, NULL); --=20 2.7.4 From nobody Sat Apr 27 09:56:35 2024 Delivered-To: importer@patchew.org Received-SPF: pass (zoho.com: domain of gnu.org designates 208.118.235.17 as permitted sender) client-ip=208.118.235.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Authentication-Results: mx.zohomail.com; spf=pass (zoho.com: domain of gnu.org designates 208.118.235.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org Return-Path: Received: from lists.gnu.org (lists.gnu.org [208.118.235.17]) by mx.zohomail.com with SMTPS id 15269466644711019.6850246315864; Mon, 21 May 2018 16:51:04 -0700 (PDT) Received: from localhost ([::1]:52900 helo=lists.gnu.org) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1fKuZz-0002ge-J1 for importer@patchew.org; Mon, 21 May 2018 19:51:03 -0400 Received: from eggs.gnu.org ([2001:4830:134:3::10]:57893) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1fKuOv-0002ep-CR for qemu-devel@nongnu.org; Mon, 21 May 2018 19:39:39 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1fKuOr-0005Yc-9J for qemu-devel@nongnu.org; Mon, 21 May 2018 19:39:37 -0400 Received: from out1-smtp.messagingengine.com ([66.111.4.25]:41495) by eggs.gnu.org with esmtps (TLS1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.71) (envelope-from ) id 1fKuOq-0005XZ-Eq for qemu-devel@nongnu.org; Mon, 21 May 2018 19:39:32 -0400 Received: from compute4.internal (compute4.nyi.internal [10.202.2.44]) by mailout.nyi.internal (Postfix) with ESMTP id 1A3D722760; Mon, 21 May 2018 19:39:31 -0400 (EDT) Received: from mailfrontend2 ([10.202.2.163]) by compute4.internal (MEProxy); Mon, 21 May 2018 19:39:31 -0400 Received: from localhost (flamenco.cs.columbia.edu [128.59.20.216]) by mail.messagingengine.com (Postfix) with ESMTPA id BDF1810263; Mon, 21 May 2018 19:39:30 -0400 (EDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=braap.org; h=cc :date:from:in-reply-to:message-id:references:subject:to :x-me-sender:x-me-sender:x-sasl-enc; s=mesmtp; bh=QV03rr4cA+d4p6 sh04IZpghRgOCJmyNAv313m6oCaPg=; b=WepMp4k9n086rv80s71uJ5Sop4t84K GCCBm7jOdniQV7hHxrUVuVL+AW4I6nwy/xw5qtBQEPjBinxRbaxKJnxLj1iuqfZq GiADyD0GI5UH07q7f84F8gf644qg8yEd3KL6fHDWaU/VvFdyRbsH23AwlzC15Bxh A9sf9Pm6+ll1Y= DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d= messagingengine.com; h=cc:date:from:in-reply-to:message-id :references:subject:to:x-me-sender:x-me-sender:x-sasl-enc; s= fm2; bh=QV03rr4cA+d4p6sh04IZpghRgOCJmyNAv313m6oCaPg=; b=dPsGtmin mTAsjmZgRCmQxyt8aVlS/KwQiVYgpuKhTi972t2YCy9M42L5xmpoqCtSTMkw8S/8 MhhOBbJYGesZ4SQkkmvKThd8paC006tsnjOuoNbi/p8kCz05BAT0lB8ZOx3gSDTA C50eRLcjA4p3154B5EEnndL27ZbYnLRmjEOBbnKxGpcLKszfp1LbwY4lGhPZk25r LjdcIHGybqiKoU6Jg3B5f8tqEDktYEeIqfHXN7c8i8vJ7Eg1FIgRCeckdxk6GT2O /L5vb70OQUbF2nrSdXTWfjAMfsiapgFk703RLAgw78h4YRbnh8OtegZpYC+WOx/s y/5qDGvozSDtVA== X-ME-Proxy: X-ME-Proxy: X-ME-Proxy: X-ME-Proxy: X-ME-Proxy: X-ME-Proxy: X-ME-Sender: From: "Emilio G. Cota" To: qemu-devel@nongnu.org Date: Mon, 21 May 2018 19:39:23 -0400 Message-Id: <1526945967-9687-14-git-send-email-cota@braap.org> X-Mailer: git-send-email 2.7.4 In-Reply-To: <1526945967-9687-1-git-send-email-cota@braap.org> References: <1526945967-9687-1-git-send-email-cota@braap.org> X-detected-operating-system: by eggs.gnu.org: GNU/Linux 2.2.x-3.x [generic] [fuzzy] X-Received-From: 66.111.4.25 Subject: [Qemu-devel] [PATCH v3 13/17] translate-all: discard TB when tb_link_page returns an existing matching TB X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.21 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: =?UTF-8?q?Alex=20Benn=C3=A9e?= , Richard Henderson , Paolo Bonzini Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: "Qemu-devel" X-ZohoMail: RSF_0 Z_629925259 SPT_0 Content-Transfer-Encoding: quoted-printable MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Use the recently-gained QHT feature of returning the matching TB if it already exists. This allows us to get rid of the lookup we perform right after acquiring tb_lock. Suggested-by: Richard Henderson Reviewed-by: Richard Henderson Signed-off-by: Emilio G. Cota Tested-by: Alex Benn=C3=A9e --- docs/devel/multi-thread-tcg.txt | 3 +++ accel/tcg/cpu-exec.c | 14 ++---------- accel/tcg/translate-all.c | 50 +++++++++++++++++++++++++++++++++----= ---- 3 files changed, 46 insertions(+), 21 deletions(-) diff --git a/docs/devel/multi-thread-tcg.txt b/docs/devel/multi-thread-tcg.= txt index faf8918..faf09c6 100644 --- a/docs/devel/multi-thread-tcg.txt +++ b/docs/devel/multi-thread-tcg.txt @@ -140,6 +140,9 @@ to atomically insert new elements. The lookup caches are updated atomically and the lookup hash uses QHT which is designed for concurrent safe lookup. =20 +Parallel code generation is supported. QHT is used at insertion time +as the synchronization point across threads, thereby ensuring that we only +keep track of a single TranslationBlock for each guest code block. =20 Memory maps and TLBs -------------------- diff --git a/accel/tcg/cpu-exec.c b/accel/tcg/cpu-exec.c index ad1f0c4..b45d10f 100644 --- a/accel/tcg/cpu-exec.c +++ b/accel/tcg/cpu-exec.c @@ -246,10 +246,7 @@ void cpu_exec_step_atomic(CPUState *cpu) if (tb =3D=3D NULL) { mmap_lock(); tb_lock(); - tb =3D tb_htable_lookup(cpu, pc, cs_base, flags, cf_mask); - if (likely(tb =3D=3D NULL)) { - tb =3D tb_gen_code(cpu, pc, cs_base, flags, cflags); - } + tb =3D tb_gen_code(cpu, pc, cs_base, flags, cflags); tb_unlock(); mmap_unlock(); } @@ -399,14 +396,7 @@ static inline TranslationBlock *tb_find(CPUState *cpu, tb_lock(); acquired_tb_lock =3D true; =20 - /* There's a chance that our desired tb has been translated while - * taking the locks so we check again inside the lock. - */ - tb =3D tb_htable_lookup(cpu, pc, cs_base, flags, cf_mask); - if (likely(tb =3D=3D NULL)) { - /* if no translated code available, then translate it now */ - tb =3D tb_gen_code(cpu, pc, cs_base, flags, cf_mask); - } + tb =3D tb_gen_code(cpu, pc, cs_base, flags, cf_mask); =20 mmap_unlock(); /* We add the TB in the virtual pc hash table for the fast lookup = */ diff --git a/accel/tcg/translate-all.c b/accel/tcg/translate-all.c index f3a0ecb..f24dcb8 100644 --- a/accel/tcg/translate-all.c +++ b/accel/tcg/translate-all.c @@ -1580,18 +1580,30 @@ static inline void tb_page_add(PageDesc *p, Transla= tionBlock *tb, * (-1) to indicate that only one page contains the TB. * * Called with mmap_lock held for user-mode emulation. + * + * Returns a pointer @tb, or a pointer to an existing TB that matches @tb. + * Note that in !user-mode, another thread might have already added a TB + * for the same block of guest code that @tb corresponds to. In that case, + * the caller should discard the original @tb, and use instead the returne= d TB. */ -static void tb_link_page(TranslationBlock *tb, tb_page_addr_t phys_pc, - tb_page_addr_t phys_page2) +static TranslationBlock * +tb_link_page(TranslationBlock *tb, tb_page_addr_t phys_pc, + tb_page_addr_t phys_page2) { PageDesc *p; PageDesc *p2 =3D NULL; + void *existing_tb =3D NULL; uint32_t h; =20 assert_memory_lock(); =20 /* * Add the TB to the page list, acquiring first the pages's locks. + * We keep the locks held until after inserting the TB in the hash tab= le, + * so that if the insertion fails we know for sure that the TBs are st= ill + * in the page descriptors. + * Note that inserting into the hash table first isn't an option, since + * we can only insert TBs that are fully initialized. */ page_lock_pair(&p, phys_pc, &p2, phys_page2, 1); tb_page_add(p, tb, 0, phys_pc & TARGET_PAGE_MASK); @@ -1601,21 +1613,33 @@ static void tb_link_page(TranslationBlock *tb, tb_p= age_addr_t phys_pc, tb->page_addr[1] =3D -1; } =20 + /* add in the hash table */ + h =3D tb_hash_func(phys_pc, tb->pc, tb->flags, tb->cflags & CF_HASH_MA= SK, + tb->trace_vcpu_dstate); + qht_insert(&tb_ctx.htable, tb, h, &existing_tb); + + /* remove TB from the page(s) if we couldn't insert it */ + if (unlikely(existing_tb)) { + tb_page_remove(p, tb); + invalidate_page_bitmap(p); + if (p2) { + tb_page_remove(p2, tb); + invalidate_page_bitmap(p2); + } + tb =3D existing_tb; + } + if (p2) { page_unlock(p2); } page_unlock(p); =20 - /* add in the hash table */ - h =3D tb_hash_func(phys_pc, tb->pc, tb->flags, tb->cflags & CF_HASH_MA= SK, - tb->trace_vcpu_dstate); - qht_insert(&tb_ctx.htable, tb, h, NULL); - #ifdef CONFIG_USER_ONLY if (DEBUG_TB_CHECK_GATE) { tb_page_check(); } #endif + return tb; } =20 /* Called with mmap_lock held for user mode emulation. */ @@ -1624,7 +1648,7 @@ TranslationBlock *tb_gen_code(CPUState *cpu, uint32_t flags, int cflags) { CPUArchState *env =3D cpu->env_ptr; - TranslationBlock *tb; + TranslationBlock *tb, *existing_tb; tb_page_addr_t phys_pc, phys_page2; target_ulong virt_page2; tcg_insn_unit *gen_code_buf; @@ -1772,7 +1796,15 @@ TranslationBlock *tb_gen_code(CPUState *cpu, * memory barrier is required before tb_link_page() makes the TB visib= le * through the physical hash table and physical page list. */ - tb_link_page(tb, phys_pc, phys_page2); + existing_tb =3D tb_link_page(tb, phys_pc, phys_page2); + /* if the TB already exists, discard what we just translated */ + if (unlikely(existing_tb !=3D tb)) { + uintptr_t orig_aligned =3D (uintptr_t)gen_code_buf; + + orig_aligned -=3D ROUND_UP(sizeof(*tb), qemu_icache_linesize); + atomic_set(&tcg_ctx->code_gen_ptr, orig_aligned); + return existing_tb; + } tcg_tb_insert(tb); return tb; } --=20 2.7.4 From nobody Sat Apr 27 09:56:35 2024 Delivered-To: importer@patchew.org Received-SPF: pass (zoho.com: domain of gnu.org designates 208.118.235.17 as permitted sender) client-ip=208.118.235.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Authentication-Results: mx.zohomail.com; spf=pass (zoho.com: domain of gnu.org designates 208.118.235.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org Return-Path: Received: from lists.gnu.org (lists.gnu.org [208.118.235.17]) by mx.zohomail.com with SMTPS id 1526946916677919.2084201163269; Mon, 21 May 2018 16:55:16 -0700 (PDT) Received: from localhost ([::1]:52923 helo=lists.gnu.org) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1fKue3-0005ru-Of for importer@patchew.org; Mon, 21 May 2018 19:55:15 -0400 Received: from eggs.gnu.org ([2001:4830:134:3::10]:57948) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1fKuOx-0002h0-HC for qemu-devel@nongnu.org; Mon, 21 May 2018 19:39:43 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1fKuOr-0005Yl-AB for qemu-devel@nongnu.org; Mon, 21 May 2018 19:39:39 -0400 Received: from out1-smtp.messagingengine.com ([66.111.4.25]:45485) by eggs.gnu.org with esmtps (TLS1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.71) (envelope-from ) id 1fKuOq-0005Xd-E9 for qemu-devel@nongnu.org; Mon, 21 May 2018 19:39:32 -0400 Received: from compute4.internal (compute4.nyi.internal [10.202.2.44]) by mailout.nyi.internal (Postfix) with ESMTP id 5711922761; Mon, 21 May 2018 19:39:31 -0400 (EDT) Received: from mailfrontend1 ([10.202.2.162]) by compute4.internal (MEProxy); Mon, 21 May 2018 19:39:31 -0400 Received: from localhost (flamenco.cs.columbia.edu [128.59.20.216]) by mail.messagingengine.com (Postfix) with ESMTPA id EE94FE4F0C; Mon, 21 May 2018 19:39:30 -0400 (EDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=braap.org; h=cc :content-transfer-encoding:content-type:date:from:in-reply-to :message-id:mime-version:references:subject:to:x-me-sender :x-me-sender:x-sasl-enc; s=mesmtp; bh=Ck/G9ahCOrHXpM0PjEUd9Ypkrb OtErj3Ur6A9bl0C64=; b=yFZZxgjn0DnO1YRWZN5SyuDikK37Ts0jKDevd+qrZ0 vnNkd/D/BGbRfy8///E8ywhWajSUoowO7x4ppExkM5jMgn784R3b+2IYGSMwkSy9 sp2ruixVHzo+ZrCu77sH+oAvIP6dhdxVzYCMIgUir4T7oLX/+AXqs4i+1hzW8fHw Y= DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d= messagingengine.com; h=cc:content-transfer-encoding:content-type :date:from:in-reply-to:message-id:mime-version:references :subject:to:x-me-sender:x-me-sender:x-sasl-enc; s=fm2; bh=Ck/G9a hCOrHXpM0PjEUd9YpkrbOtErj3Ur6A9bl0C64=; b=EvAlH/m2E/9JfUzmnr7Yco 8BylAA4MqBXrRTCInrvEJcgdtKlHHCkTudS1ZSuwQYaTPu/4LUS1Rxfm0NWuOslC ofTRAyMtyaucFRFhx9eD5qQtxD2kxScL/5jOi0D7nL/+Fm3x0fVUIxzB5veiLGTD HuxdJ3vXz7kNsvgerIbsEEfNYcF/5VUdTJkJYFf5iAPPy5U0DiPbtD0Dh2wrU282 u2Lux34jOxTyI19qQWSv7iHPY+ho+WOKIp3yE3B4bc6Vhh3MIlRCsz1/PDLFPJBt OaxzrgsDfEtfvtoz/qp0ZHlqI4r1gbDK9fRolQ16IgMKoMRb6zNTXL3yTk6dDSfA == X-ME-Proxy: X-ME-Proxy: X-ME-Proxy: X-ME-Proxy: X-ME-Proxy: X-ME-Proxy: X-ME-Sender: From: "Emilio G. Cota" To: qemu-devel@nongnu.org Date: Mon, 21 May 2018 19:39:24 -0400 Message-Id: <1526945967-9687-15-git-send-email-cota@braap.org> X-Mailer: git-send-email 2.7.4 In-Reply-To: <1526945967-9687-1-git-send-email-cota@braap.org> References: <1526945967-9687-1-git-send-email-cota@braap.org> MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable X-detected-operating-system: by eggs.gnu.org: GNU/Linux 2.2.x-3.x [generic] [fuzzy] X-Received-From: 66.111.4.25 Subject: [Qemu-devel] [PATCH v3 14/17] translate-all: protect TB jumps with a per-destination-TB lock X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.21 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: =?UTF-8?q?Alex=20Benn=C3=A9e?= , Richard Henderson , Paolo Bonzini Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: "Qemu-devel" X-ZohoMail: RSF_0 Z_629925259 SPT_0 This applies to both user-mode and !user-mode emulation. Instead of relying on a global lock, protect the list of incoming jumps with tb->jmp_lock. This lock also protects tb->cflags, so update all tb->cflags readers outside tb->jmp_lock to use atomic reads via tb_cflags(). In order to find the destination TB (and therefore its jmp_lock) from the origin TB, we introduce tb->jmp_dest[]. I considered not using a linked list of jumps, which simplifies code and makes the struct smaller. However, it unnecessarily increases memory usage, which results in a performance decrease. See for instance these numbers booting+shutting down debian-arm: Time (s) Rel. err (%) Abs. err (s) Rel. slowdown (= %) Tested-by: Alex Benn=C3=A9e ---------------------------------------------------------------------------= --- before 20.88 0.74 0.154512 = 0. after 20.81 0.38 0.079078 -0.335249= 04 GTree 21.02 0.28 0.058856 0.670498= 08 GHashTable + xxhash 21.63 1.08 0.233604 3.59195= 40 Using a hash table or a binary tree to keep track of the jumps doesn't really pay off, not only due to the increased memory usage, but also because most TBs have only 0 or 1 jumps to them. The maximum number of jumps when booting debian-arm that I measured is 35, but as we can see in the histogram below a TB with that many incoming jumps is extremely rare; the average TB has 0.80 incoming jumps. n_jumps: 379208; avg jumps/tb: 0.801099 dist: [0.0,1.0)|=E2=96=84=E2=96=88=E2=96=81=E2=96=81=E2=96=81=E2=96=81=E2= =96=81=E2=96=81=E2=96=81=E2=96=81=E2=96=81=E2=96=81=E2=96=81 =E2=96=81=E2= =96=81=E2=96=81=E2=96=81=E2=96=81=E2=96=81 =E2=96=81=E2=96=81=E2=96=81 =E2= =96=81=E2=96=81=E2=96=81 =E2=96=81|[34.0,35.0] Signed-off-by: Emilio G. Cota --- docs/devel/multi-thread-tcg.txt | 6 +- include/exec/exec-all.h | 35 +++++++----- accel/tcg/cpu-exec.c | 41 +++++++++----- accel/tcg/translate-all.c | 118 ++++++++++++++++++++++++------------= ---- 4 files changed, 124 insertions(+), 76 deletions(-) diff --git a/docs/devel/multi-thread-tcg.txt b/docs/devel/multi-thread-tcg.= txt index faf09c6..df83445 100644 --- a/docs/devel/multi-thread-tcg.txt +++ b/docs/devel/multi-thread-tcg.txt @@ -131,8 +131,10 @@ DESIGN REQUIREMENT: Safely handle invalidation of TBs =20 The direct jump themselves are updated atomically by the TCG tb_set_jmp_target() code. Modification to the linked lists that allow -searching for linked pages are done under the protect of the -tb_lock(). +searching for linked pages are done under the protection of tb->jmp_lock, +where tb is the destination block of a jump. Each origin block keeps a +pointer to its destinations so that the appropriate lock can be acquired b= efore +iterating over a jump list. =20 The global page table is a lockless radix tree; cmpxchg is used to atomically insert new elements. diff --git a/include/exec/exec-all.h b/include/exec/exec-all.h index 66902f7..daac968 100644 --- a/include/exec/exec-all.h +++ b/include/exec/exec-all.h @@ -344,7 +344,7 @@ struct TranslationBlock { #define CF_LAST_IO 0x00008000 /* Last insn may be an IO access. */ #define CF_NOCACHE 0x00010000 /* To be freed after execution */ #define CF_USE_ICOUNT 0x00020000 -#define CF_INVALID 0x00040000 /* TB is stale. Setters need tb_lock */ +#define CF_INVALID 0x00040000 /* TB is stale. Set with @jmp_lock held = */ #define CF_PARALLEL 0x00080000 /* Generate code for a parallel context = */ /* cflags' mask for hashing/comparison */ #define CF_HASH_MASK \ @@ -363,6 +363,9 @@ struct TranslationBlock { uintptr_t page_next[2]; tb_page_addr_t page_addr[2]; =20 + /* jmp_lock placed here to fill a 4-byte hole. Its documentation is be= low */ + QemuSpin jmp_lock; + /* The following data are used to directly call another TB from * the code of this one. This can be done either by emitting direct or * indirect native jump instructions. These jumps are reset so that th= e TB @@ -374,20 +377,26 @@ struct TranslationBlock { #define TB_JMP_RESET_OFFSET_INVALID 0xffff /* indicates no jump generated = */ uintptr_t jmp_target_arg[2]; /* target address or offset */ =20 - /* Each TB has an associated circular list of TBs jumping to this one. - * jmp_list_first points to the first TB jumping to this one. - * jmp_list_next is used to point to the next TB in a list. - * Since each TB can have two jumps, it can participate in two lists. - * jmp_list_first and jmp_list_next are 4-byte aligned pointers to a - * TranslationBlock structure, but the two least significant bits of - * them are used to encode which data field of the pointed TB should - * be used to traverse the list further from that TB: - * 0 =3D> jmp_list_next[0], 1 =3D> jmp_list_next[1], 2 =3D> jmp_list_f= irst. - * In other words, 0/1 tells which jump is used in the pointed TB, - * and 2 means that this is a pointer back to the target TB of this li= st. + /* + * Each TB has a NULL-terminated list (jmp_list_head) of incoming jump= s. + * Each TB can have two outgoing jumps, and therefore can participate + * in two lists. The list entries are kept in jmp_list_next[2]. The le= ast + * significant bit (LSB) of the pointers in these lists is used to enc= ode + * which of the two list entries is to be used in the pointed TB. + * + * List traversals are protected by jmp_lock. The destination TB of ea= ch + * outgoing jump is kept in jmp_dest[] so that the appropriate jmp_lock + * can be acquired from any origin TB. + * + * jmp_dest[] are tagged pointers as well. The LSB is set when the TB = is + * being invalidated, so that no further outgoing jumps from it can be= set. + * + * jmp_lock also protects the CF_INVALID cflag; a jump must not be cha= ined + * to a destination TB that has CF_INVALID set. */ + uintptr_t jmp_list_head; uintptr_t jmp_list_next[2]; - uintptr_t jmp_list_first; + uintptr_t jmp_dest[2]; }; =20 extern bool parallel_cpus; diff --git a/accel/tcg/cpu-exec.c b/accel/tcg/cpu-exec.c index b45d10f..c9db99d 100644 --- a/accel/tcg/cpu-exec.c +++ b/accel/tcg/cpu-exec.c @@ -353,28 +353,43 @@ void tb_set_jmp_target(TranslationBlock *tb, int n, u= intptr_t addr) } } =20 -/* Called with tb_lock held. */ static inline void tb_add_jump(TranslationBlock *tb, int n, TranslationBlock *tb_next) { + uintptr_t old; + assert(n < ARRAY_SIZE(tb->jmp_list_next)); - if (tb->jmp_list_next[n]) { - /* Another thread has already done this while we were - * outside of the lock; nothing to do in this case */ - return; + qemu_spin_lock(&tb_next->jmp_lock); + + /* make sure the destination TB is valid */ + if (tb_next->cflags & CF_INVALID) { + goto out_unlock_next; + } + /* Atomically claim the jump destination slot only if it was NULL */ + old =3D atomic_cmpxchg(&tb->jmp_dest[n], (uintptr_t)NULL, (uintptr_t)t= b_next); + if (old) { + goto out_unlock_next; } + + /* patch the native jump address */ + tb_set_jmp_target(tb, n, (uintptr_t)tb_next->tc.ptr); + + /* add in TB jmp list */ + tb->jmp_list_next[n] =3D tb_next->jmp_list_head; + tb_next->jmp_list_head =3D (uintptr_t)tb | n; + + qemu_spin_unlock(&tb_next->jmp_lock); + qemu_log_mask_and_addr(CPU_LOG_EXEC, tb->pc, "Linking TBs %p [" TARGET_FMT_lx "] index %d -> %p [" TARGET_FMT_lx "]\n", tb->tc.ptr, tb->pc, n, tb_next->tc.ptr, tb_next->pc); + return; =20 - /* patch the native jump address */ - tb_set_jmp_target(tb, n, (uintptr_t)tb_next->tc.ptr); - - /* add in TB jmp circular list */ - tb->jmp_list_next[n] =3D tb_next->jmp_list_first; - tb_next->jmp_list_first =3D (uintptr_t)tb | n; + out_unlock_next: + qemu_spin_unlock(&tb_next->jmp_lock); + return; } =20 static inline TranslationBlock *tb_find(CPUState *cpu, @@ -417,9 +432,7 @@ static inline TranslationBlock *tb_find(CPUState *cpu, tb_lock(); acquired_tb_lock =3D true; } - if (!(tb->cflags & CF_INVALID)) { - tb_add_jump(last_tb, tb_exit, tb); - } + tb_add_jump(last_tb, tb_exit, tb); } if (acquired_tb_lock) { tb_unlock(); diff --git a/accel/tcg/translate-all.c b/accel/tcg/translate-all.c index f24dcb8..031060f 100644 --- a/accel/tcg/translate-all.c +++ b/accel/tcg/translate-all.c @@ -170,6 +170,9 @@ struct page_collection { #define PAGE_FOR_EACH_TB(pagedesc, tb, n) \ TB_FOR_EACH_TAGGED((pagedesc)->first_tb, tb, n, page_next) =20 +#define TB_FOR_EACH_JMP(head_tb, tb, n) \ + TB_FOR_EACH_TAGGED((head_tb)->jmp_list_head, tb, n, jmp_list_next) + /* In system mode we want L1_MAP to be based on ram offsets, while in user mode we want it to be based on virtual addresses. */ #if !defined(CONFIG_USER_ONLY) @@ -389,7 +392,7 @@ static int cpu_restore_state_from_tb(CPUState *cpu, Tra= nslationBlock *tb, return -1; =20 found: - if (reset_icount && (tb->cflags & CF_USE_ICOUNT)) { + if (reset_icount && (tb_cflags(tb) & CF_USE_ICOUNT)) { assert(use_icount); /* Reset the cycle counter to the start of the block and shift if to the number of actually executed instructions */ @@ -432,7 +435,7 @@ bool cpu_restore_state(CPUState *cpu, uintptr_t host_pc= , bool will_exit) tb =3D tcg_tb_lookup(host_pc); if (tb) { cpu_restore_state_from_tb(cpu, tb, host_pc, will_exit); - if (tb->cflags & CF_NOCACHE) { + if (tb_cflags(tb) & CF_NOCACHE) { /* one-shot translation, invalidate it immediately */ tb_phys_invalidate(tb, -1); tcg_tb_remove(tb); @@ -1359,34 +1362,53 @@ static inline void tb_page_remove(PageDesc *pd, Tra= nslationBlock *tb) g_assert_not_reached(); } =20 -/* remove the TB from a list of TBs jumping to the n-th jump target of the= TB */ -static inline void tb_remove_from_jmp_list(TranslationBlock *tb, int n) +/* remove @orig from its @n_orig-th jump list */ +static inline void tb_remove_from_jmp_list(TranslationBlock *orig, int n_o= rig) { - TranslationBlock *tb1; - uintptr_t *ptb, ntb; - unsigned int n1; + uintptr_t ptr, ptr_locked; + TranslationBlock *dest; + TranslationBlock *tb; + uintptr_t *pprev; + int n; =20 - ptb =3D &tb->jmp_list_next[n]; - if (*ptb) { - /* find tb(n) in circular list */ - for (;;) { - ntb =3D *ptb; - n1 =3D ntb & 3; - tb1 =3D (TranslationBlock *)(ntb & ~3); - if (n1 =3D=3D n && tb1 =3D=3D tb) { - break; - } - if (n1 =3D=3D 2) { - ptb =3D &tb1->jmp_list_first; - } else { - ptb =3D &tb1->jmp_list_next[n1]; - } - } - /* now we can suppress tb(n) from the list */ - *ptb =3D tb->jmp_list_next[n]; + /* mark the LSB of jmp_dest[] so that no further jumps can be inserted= */ + ptr =3D atomic_or_fetch(&orig->jmp_dest[n_orig], 1); + dest =3D (TranslationBlock *)(ptr & ~1); + if (dest =3D=3D NULL) { + return; + } =20 - tb->jmp_list_next[n] =3D (uintptr_t)NULL; + qemu_spin_lock(&dest->jmp_lock); + /* + * While acquiring the lock, the jump might have been removed if the + * destination TB was invalidated; check again. + */ + ptr_locked =3D atomic_read(&orig->jmp_dest[n_orig]); + if (ptr_locked !=3D ptr) { + qemu_spin_unlock(&dest->jmp_lock); + /* + * The only possibility is that the jump was unlinked via + * tb_jump_unlink(dest). Seeing here another destination would be = a bug, + * because we set the LSB above. + */ + g_assert(ptr_locked =3D=3D 1 && dest->cflags & CF_INVALID); + return; } + /* + * We first acquired the lock, and since the destination pointer match= es, + * we know for sure that @orig is in the jmp list. + */ + pprev =3D &dest->jmp_list_head; + TB_FOR_EACH_JMP(dest, tb, n) { + if (tb =3D=3D orig && n =3D=3D n_orig) { + *pprev =3D tb->jmp_list_next[n]; + /* no need to set orig->jmp_dest[n]; setting the LSB was enoug= h */ + qemu_spin_unlock(&dest->jmp_lock); + return; + } + pprev =3D &tb->jmp_list_next[n]; + } + g_assert_not_reached(); } =20 /* reset the jump entry 'n' of a TB so that it is not chained to @@ -1398,24 +1420,21 @@ static inline void tb_reset_jump(TranslationBlock *= tb, int n) } =20 /* remove any jumps to the TB */ -static inline void tb_jmp_unlink(TranslationBlock *tb) +static inline void tb_jmp_unlink(TranslationBlock *dest) { - TranslationBlock *tb1; - uintptr_t *ptb, ntb; - unsigned int n1; + TranslationBlock *tb; + int n; =20 - ptb =3D &tb->jmp_list_first; - for (;;) { - ntb =3D *ptb; - n1 =3D ntb & 3; - tb1 =3D (TranslationBlock *)(ntb & ~3); - if (n1 =3D=3D 2) { - break; - } - tb_reset_jump(tb1, n1); - *ptb =3D tb1->jmp_list_next[n1]; - tb1->jmp_list_next[n1] =3D (uintptr_t)NULL; + qemu_spin_lock(&dest->jmp_lock); + + TB_FOR_EACH_JMP(dest, tb, n) { + tb_reset_jump(tb, n); + atomic_and(&tb->jmp_dest[n], (uintptr_t)NULL | 1); + /* No need to clear the list entry; setting the dest ptr is enough= */ } + dest->jmp_list_head =3D (uintptr_t)NULL; + + qemu_spin_unlock(&dest->jmp_lock); } =20 /* If @rm_from_page_list is set, call with the TB's pages' locks held */ @@ -1428,11 +1447,14 @@ static void do_tb_phys_invalidate(TranslationBlock = *tb, bool rm_from_page_list) =20 assert_tb_locked(); =20 + /* make sure no further incoming jumps will be chained to this TB */ + qemu_spin_lock(&tb->jmp_lock); atomic_set(&tb->cflags, tb->cflags | CF_INVALID); + qemu_spin_unlock(&tb->jmp_lock); =20 /* remove the TB from the hash list */ phys_pc =3D tb->page_addr[0] + (tb->pc & ~TARGET_PAGE_MASK); - h =3D tb_hash_func(phys_pc, tb->pc, tb->flags, tb->cflags & CF_HASH_MA= SK, + h =3D tb_hash_func(phys_pc, tb->pc, tb->flags, tb_cflags(tb) & CF_HASH= _MASK, tb->trace_vcpu_dstate); if (!qht_remove(&tb_ctx.htable, tb, h)) { return; @@ -1772,10 +1794,12 @@ TranslationBlock *tb_gen_code(CPUState *cpu, CODE_GEN_ALIGN)); =20 /* init jump list */ - assert(((uintptr_t)tb & 3) =3D=3D 0); - tb->jmp_list_first =3D (uintptr_t)tb | 2; + qemu_spin_init(&tb->jmp_lock); + tb->jmp_list_head =3D (uintptr_t)NULL; tb->jmp_list_next[0] =3D (uintptr_t)NULL; tb->jmp_list_next[1] =3D (uintptr_t)NULL; + tb->jmp_dest[0] =3D (uintptr_t)NULL; + tb->jmp_dest[1] =3D (uintptr_t)NULL; =20 /* init original jump addresses wich has been set during tcg_gen_code(= ) */ if (tb->jmp_reset_offset[0] !=3D TB_JMP_RESET_OFFSET_INVALID) { @@ -1867,7 +1891,7 @@ tb_invalidate_phys_page_range__locked(struct page_col= lection *pages, } } if (current_tb =3D=3D tb && - (current_tb->cflags & CF_COUNT_MASK) !=3D 1) { + (tb_cflags(current_tb) & CF_COUNT_MASK) !=3D 1) { /* If we are modifying the current TB, we must stop its execution. We could be more precise by checking that the modification is after the current PC, but it @@ -2066,7 +2090,7 @@ static bool tb_invalidate_phys_page(tb_page_addr_t ad= dr, uintptr_t pc) PAGE_FOR_EACH_TB(p, tb, n) { #ifdef TARGET_HAS_PRECISE_SMC if (current_tb =3D=3D tb && - (current_tb->cflags & CF_COUNT_MASK) !=3D 1) { + (tb_cflags(current_tb) & CF_COUNT_MASK) !=3D 1) { /* If we are modifying the current TB, we must stop its execution. We could be more precise by checking that the modification is after the current PC, but it @@ -2191,7 +2215,7 @@ void cpu_io_recompile(CPUState *cpu, uintptr_t retadd= r) /* Generate a new TB executing the I/O insn. */ cpu->cflags_next_tb =3D curr_cflags() | CF_LAST_IO | n; =20 - if (tb->cflags & CF_NOCACHE) { + if (tb_cflags(tb) & CF_NOCACHE) { if (tb->orig_tb) { /* Invalidate original TB if this TB was generated in * cpu_exec_nocache() */ --=20 2.7.4 From nobody Sat Apr 27 09:56:35 2024 Delivered-To: importer@patchew.org Received-SPF: pass (zoho.com: domain of gnu.org designates 208.118.235.17 as permitted sender) client-ip=208.118.235.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Authentication-Results: mx.zohomail.com; spf=pass (zoho.com: domain of gnu.org designates 208.118.235.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org Return-Path: Received: from lists.gnu.org (lists.gnu.org [208.118.235.17]) by mx.zohomail.com with SMTPS id 1526946483936838.5684272582764; Mon, 21 May 2018 16:48:03 -0700 (PDT) Received: from localhost ([::1]:52886 helo=lists.gnu.org) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1fKuX0-0000HH-PH for importer@patchew.org; Mon, 21 May 2018 19:47:58 -0400 Received: from eggs.gnu.org ([2001:4830:134:3::10]:57885) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1fKuOv-0002eX-6R for qemu-devel@nongnu.org; Mon, 21 May 2018 19:39:38 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1fKuOr-0005Yv-An for qemu-devel@nongnu.org; Mon, 21 May 2018 19:39:37 -0400 Received: from out1-smtp.messagingengine.com ([66.111.4.25]:56391) by eggs.gnu.org with esmtps (TLS1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.71) (envelope-from ) id 1fKuOq-0005XW-Fh for qemu-devel@nongnu.org; Mon, 21 May 2018 19:39:32 -0400 Received: from compute4.internal (compute4.nyi.internal [10.202.2.44]) by mailout.nyi.internal (Postfix) with ESMTP id 7DDE022762; Mon, 21 May 2018 19:39:31 -0400 (EDT) Received: from mailfrontend2 ([10.202.2.163]) by compute4.internal (MEProxy); Mon, 21 May 2018 19:39:31 -0400 Received: from localhost (flamenco.cs.columbia.edu [128.59.20.216]) by mail.messagingengine.com (Postfix) with ESMTPA id 2A8341026B; Mon, 21 May 2018 19:39:31 -0400 (EDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=braap.org; h=cc :content-transfer-encoding:content-type:date:from:in-reply-to :message-id:mime-version:references:subject:to:x-me-sender :x-me-sender:x-sasl-enc; s=mesmtp; bh=2vds9sjw6XdB5/OtLSvpjNQTHg dqpTFlnQgqSdby+ME=; b=n5i53tCA7hS5SNUBRFgeeVpNU4w4VLP2oLjC/rIX5p 3NfosPh5ItqARKZZcoz8vG1mE7CkunrEJUBLffC/XO8UcHsh2a/JhWOHqFb1nA+j ZMHJxd/zGBJrDC2W2ZFw65Y5EgxkBU9dxrCJOfW/K/cVWuiFCFeSvrTvUgYfkGnm Y= DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d= messagingengine.com; h=cc:content-transfer-encoding:content-type :date:from:in-reply-to:message-id:mime-version:references :subject:to:x-me-sender:x-me-sender:x-sasl-enc; s=fm2; bh=2vds9s jw6XdB5/OtLSvpjNQTHgdqpTFlnQgqSdby+ME=; b=hsgCWALNJaXUn0usyi4tjm IHvYQVtTp1oBAIskuyK53jhyrbNjLzMgJmjJIvO6yDnXpRm1bUtAj5elwCAN6u4B TTh5XnjLJ0xGd6QiL7H2TR3aBz0BuOQ1bGvrpDzNZCVR5bB4BVl2B1AFp5ZZ/VSv maBy2SV/6WugtqCCc/fwUS4f5zZNXdIgnCjgibv1yPsWfKNjAJEpE8+QpT6INr5m Et1CO6QGiaz0Y/EgtPWc0vD77fkHGTyNu8V4mKAADJK3F/erJsiHa7tcaomiIhqk AmzxH9sP8O4+3Nr5Ag+XW0zaXhchp12izVTL6fqfxZvlyYUBkvRguyjC4xkhCojw == X-ME-Proxy: X-ME-Proxy: X-ME-Proxy: X-ME-Proxy: X-ME-Proxy: X-ME-Proxy: X-ME-Sender: From: "Emilio G. Cota" To: qemu-devel@nongnu.org Date: Mon, 21 May 2018 19:39:25 -0400 Message-Id: <1526945967-9687-16-git-send-email-cota@braap.org> X-Mailer: git-send-email 2.7.4 In-Reply-To: <1526945967-9687-1-git-send-email-cota@braap.org> References: <1526945967-9687-1-git-send-email-cota@braap.org> MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable X-detected-operating-system: by eggs.gnu.org: GNU/Linux 2.2.x-3.x [generic] [fuzzy] X-Received-From: 66.111.4.25 Subject: [Qemu-devel] [PATCH v3 15/17] cputlb: remove tb_lock from tlb_flush functions X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.21 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: =?UTF-8?q?Alex=20Benn=C3=A9e?= , Richard Henderson , Paolo Bonzini Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: "Qemu-devel" X-ZohoMail: RSF_0 Z_629925259 SPT_0 The acquisition of tb_lock was added when the async tlb_flush was introduced in e3b9ca810 ("cputlb: introduce tlb_flush_* async work.") tb_lock was there to allow us to do memset() on the tb_jmp_cache's. However, since f3ced3c5928 ("tcg: consistently access cpu->tb_jmp_cache atomically") all accesses to tb_jmp_cache are atomic, so tb_lock is not needed here. Get rid of it. Reviewed-by: Alex Benn=C3=A9e Reviewed-by: Richard Henderson Signed-off-by: Emilio G. Cota Tested-by: Alex Benn=C3=A9e --- accel/tcg/cputlb.c | 8 -------- 1 file changed, 8 deletions(-) diff --git a/accel/tcg/cputlb.c b/accel/tcg/cputlb.c index 0543903..f5c3a09 100644 --- a/accel/tcg/cputlb.c +++ b/accel/tcg/cputlb.c @@ -125,8 +125,6 @@ static void tlb_flush_nocheck(CPUState *cpu) atomic_set(&env->tlb_flush_count, env->tlb_flush_count + 1); tlb_debug("(count: %zu)\n", tlb_flush_count()); =20 - tb_lock(); - memset(env->tlb_table, -1, sizeof(env->tlb_table)); memset(env->tlb_v_table, -1, sizeof(env->tlb_v_table)); cpu_tb_jmp_cache_clear(cpu); @@ -135,8 +133,6 @@ static void tlb_flush_nocheck(CPUState *cpu) env->tlb_flush_addr =3D -1; env->tlb_flush_mask =3D 0; =20 - tb_unlock(); - atomic_mb_set(&cpu->pending_tlb_flush, 0); } =20 @@ -180,8 +176,6 @@ static void tlb_flush_by_mmuidx_async_work(CPUState *cp= u, run_on_cpu_data data) =20 assert_cpu_is_self(cpu); =20 - tb_lock(); - tlb_debug("start: mmu_idx:0x%04lx\n", mmu_idx_bitmask); =20 for (mmu_idx =3D 0; mmu_idx < NB_MMU_MODES; mmu_idx++) { @@ -197,8 +191,6 @@ static void tlb_flush_by_mmuidx_async_work(CPUState *cp= u, run_on_cpu_data data) cpu_tb_jmp_cache_clear(cpu); =20 tlb_debug("done\n"); - - tb_unlock(); } =20 void tlb_flush_by_mmuidx(CPUState *cpu, uint16_t idxmap) --=20 2.7.4 From nobody Sat Apr 27 09:56:35 2024 Delivered-To: importer@patchew.org Received-SPF: pass (zoho.com: domain of gnu.org designates 208.118.235.17 as permitted sender) client-ip=208.118.235.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Authentication-Results: mx.zohomail.com; spf=pass (zoho.com: domain of gnu.org designates 208.118.235.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org Return-Path: Received: from lists.gnu.org (lists.gnu.org [208.118.235.17]) by mx.zohomail.com with SMTPS id 15269466665631007.1363726581594; Mon, 21 May 2018 16:51:06 -0700 (PDT) Received: from localhost ([::1]:52903 helo=lists.gnu.org) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1fKua1-0002l5-Oc for importer@patchew.org; Mon, 21 May 2018 19:51:05 -0400 Received: from eggs.gnu.org ([2001:4830:134:3::10]:57864) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1fKuOu-0002eT-Pf for qemu-devel@nongnu.org; Mon, 21 May 2018 19:39:38 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1fKuOr-0005Z8-C2 for qemu-devel@nongnu.org; Mon, 21 May 2018 19:39:36 -0400 Received: from out1-smtp.messagingengine.com ([66.111.4.25]:60043) by eggs.gnu.org with esmtps (TLS1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.71) (envelope-from ) id 1fKuOq-0005Xz-M7 for qemu-devel@nongnu.org; Mon, 21 May 2018 19:39:33 -0400 Received: from compute4.internal (compute4.nyi.internal [10.202.2.44]) by mailout.nyi.internal (Postfix) with ESMTP id 43B7922767; Mon, 21 May 2018 19:39:32 -0400 (EDT) Received: from mailfrontend1 ([10.202.2.162]) by compute4.internal (MEProxy); Mon, 21 May 2018 19:39:32 -0400 Received: from localhost (flamenco.cs.columbia.edu [128.59.20.216]) by mail.messagingengine.com (Postfix) with ESMTPA id 60CA4E4FAF; Mon, 21 May 2018 19:39:31 -0400 (EDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=braap.org; h=cc :date:from:in-reply-to:message-id:references:subject:to :x-me-sender:x-me-sender:x-sasl-enc; s=mesmtp; bh=V7+RUCtKTwxWLn S+kpCVcS9lOwCuf0zodJOo9yVgkNQ=; b=orlSX3or0P7831ZMnI5wjjDK7gwLoN k4/KLM/KQ+NCz+FP5PVgj9Y7eS9WlEYJ669ESLKYGZQf3NnuNnKVA7kbM6RJ46gx Shhh15EjbEAov/WCl37LoHX6gRyPGuOEbwW4HN9zMqBMg0ytCQmm1Wow/Pwv9Ywj GwCP2AeO7TWNk= DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d= messagingengine.com; h=cc:date:from:in-reply-to:message-id :references:subject:to:x-me-sender:x-me-sender:x-sasl-enc; s= fm2; bh=V7+RUCtKTwxWLnS+kpCVcS9lOwCuf0zodJOo9yVgkNQ=; b=J/yFmKjR vrG9DQGTAyDUTNts1e/g6SmsUhjTcIfwOhHCLcNBpaK+RjZagbREPHvqwBFQF7Hw bMYZnmtU/VxY8mrFsQ4dmYmdMgSGFJyVnFOPrroTJUgK16uCdlONBwrkX6/Y1tPh 23RaulD7Sx+QsS1ycvHJRJzWPaOmjQws3KqkkdH/jaVEKJyGaNx+CXJDLMLqaNEX 6WfAdZ/TeHY+08oMRzWAYZenbsbGBsQrMk2ciTeyVAerpN4pEkG3iqvyoJ+NYqmp qO5enA85J9DpWOOlg5MvXgo/Khn49fSkQCKMZMyweoouaNNkehszl5Kcfr0l7sOE slz9qs3Cf/jWzw== X-ME-Proxy: X-ME-Proxy: X-ME-Proxy: X-ME-Proxy: X-ME-Proxy: X-ME-Proxy: X-ME-Sender: From: "Emilio G. Cota" To: qemu-devel@nongnu.org Date: Mon, 21 May 2018 19:39:26 -0400 Message-Id: <1526945967-9687-17-git-send-email-cota@braap.org> X-Mailer: git-send-email 2.7.4 In-Reply-To: <1526945967-9687-1-git-send-email-cota@braap.org> References: <1526945967-9687-1-git-send-email-cota@braap.org> X-detected-operating-system: by eggs.gnu.org: GNU/Linux 2.2.x-3.x [generic] [fuzzy] X-Received-From: 66.111.4.25 Subject: [Qemu-devel] [PATCH v3 16/17] translate-all: remove tb_lock mention from cpu_restore_state_from_tb X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.21 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: =?UTF-8?q?Alex=20Benn=C3=A9e?= , Richard Henderson , Paolo Bonzini Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: "Qemu-devel" X-ZohoMail: RSF_0 Z_629925259 SPT_0 Content-Transfer-Encoding: quoted-printable MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" tb_lock was needed when the function did retranslation. However, since fca8a500d519 ("tcg: Save insn data and use it in cpu_restore_state_from_tb") we don't do retranslation. Get rid of the comment. Reviewed-by: Richard Henderson Signed-off-by: Emilio G. Cota Tested-by: Alex Benn=C3=A9e --- accel/tcg/translate-all.c | 1 - 1 file changed, 1 deletion(-) diff --git a/accel/tcg/translate-all.c b/accel/tcg/translate-all.c index 031060f..6cc7b94 100644 --- a/accel/tcg/translate-all.c +++ b/accel/tcg/translate-all.c @@ -355,7 +355,6 @@ static int encode_search(TranslationBlock *tb, uint8_t = *block) } =20 /* The cpu state corresponding to 'searched_pc' is restored. - * Called with tb_lock held. * When reset_icount is true, current TB will be interrupted and * icount should be recalculated. */ --=20 2.7.4 From nobody Sat Apr 27 09:56:35 2024 Delivered-To: importer@patchew.org Received-SPF: pass (zoho.com: domain of gnu.org designates 208.118.235.17 as permitted sender) client-ip=208.118.235.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Authentication-Results: mx.zohomail.com; spf=pass (zoho.com: domain of gnu.org designates 208.118.235.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org Return-Path: Received: from lists.gnu.org (lists.gnu.org [208.118.235.17]) by mx.zohomail.com with SMTPS id 1526946354243940.6503596981763; Mon, 21 May 2018 16:45:54 -0700 (PDT) Received: from localhost ([::1]:52873 helo=lists.gnu.org) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1fKuUz-0007FX-5i for importer@patchew.org; Mon, 21 May 2018 19:45:53 -0400 Received: from eggs.gnu.org ([2001:4830:134:3::10]:57954) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1fKuOy-0002hx-8N for qemu-devel@nongnu.org; Mon, 21 May 2018 19:39:43 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1fKuOr-0005ZL-D2 for qemu-devel@nongnu.org; Mon, 21 May 2018 19:39:40 -0400 Received: from out1-smtp.messagingengine.com ([66.111.4.25]:42089) by eggs.gnu.org with esmtps (TLS1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.71) (envelope-from ) id 1fKuOq-0005Y9-W6 for qemu-devel@nongnu.org; Mon, 21 May 2018 19:39:33 -0400 Received: from compute4.internal (compute4.nyi.internal [10.202.2.44]) by mailout.nyi.internal (Postfix) with ESMTP id 64EE52276A; Mon, 21 May 2018 19:39:32 -0400 (EDT) Received: from mailfrontend2 ([10.202.2.163]) by compute4.internal (MEProxy); Mon, 21 May 2018 19:39:32 -0400 Received: from localhost (flamenco.cs.columbia.edu [128.59.20.216]) by mail.messagingengine.com (Postfix) with ESMTPA id 92E551026C; Mon, 21 May 2018 19:39:31 -0400 (EDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=braap.org; h=cc :content-transfer-encoding:content-type:date:from:in-reply-to :message-id:mime-version:references:subject:to:x-me-sender :x-me-sender:x-sasl-enc; s=mesmtp; bh=KjstdaU+Tw9ieLOKQIfgAuoIsb GRR2NpgQWaG/qfX/c=; b=eb22P/CNfgSsg9+jRK0Mx4VzTiqM2YfO4xPIXg48ID 5pCsk+CraokKVm9nIh5JjehwbHTaxS34Oga7VVXM5pRv7V6EHgpP8qPCNrMiFNlX m7CCO3GzPhOL1Lh022ogvZPuyo2CHjJld0F/TIwkec9GUyODkLMOujw12Pf/5VHP U= DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d= messagingengine.com; h=cc:content-transfer-encoding:content-type :date:from:in-reply-to:message-id:mime-version:references :subject:to:x-me-sender:x-me-sender:x-sasl-enc; s=fm2; bh=Kjstda U+Tw9ieLOKQIfgAuoIsbGRR2NpgQWaG/qfX/c=; b=Rs9se3FHc9WQJ8k4EkUGfY 6jXKJwus26D/tATRglD3h3DikL/BgiGN2X4celn1nJS1dUbSsPmPMOGPegIKG9Bj 0AAevfABMolvIPrAq2lBbP2YTRDq1D6tsmorxYMCUv3S8qxFfYQ9ErHeofWcHpHk LhbUNpWAhuZOrT8UWoUGdTr4T1heujM1Cffy6fnGGdocSaPY7LuFNBTEqcbZeJNR F1X4lOmguFslAdXWXxe2rW53nemsIWeFARsOmIf4h07EcgqAQr+k+nV5+mLNgAAa sEBvrLDhBHi1yb7thtNQowROzHD0WliADInh4ZuqohYhhA1gA3jYiYYjHcqfiFvA == X-ME-Proxy: X-ME-Proxy: X-ME-Proxy: X-ME-Proxy: X-ME-Proxy: X-ME-Proxy: X-ME-Sender: From: "Emilio G. Cota" To: qemu-devel@nongnu.org Date: Mon, 21 May 2018 19:39:27 -0400 Message-Id: <1526945967-9687-18-git-send-email-cota@braap.org> X-Mailer: git-send-email 2.7.4 In-Reply-To: <1526945967-9687-1-git-send-email-cota@braap.org> References: <1526945967-9687-1-git-send-email-cota@braap.org> MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable X-detected-operating-system: by eggs.gnu.org: GNU/Linux 2.2.x-3.x [generic] [fuzzy] X-Received-From: 66.111.4.25 Subject: [Qemu-devel] [PATCH v3 17/17] tcg: remove tb_lock X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.21 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: =?UTF-8?q?Alex=20Benn=C3=A9e?= , Richard Henderson , Paolo Bonzini Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: "Qemu-devel" X-ZohoMail: RSF_0 Z_629925259 SPT_0 Use mmap_lock in user-mode to protect TCG state and the page descriptors. In !user-mode, each vCPU has its own TCG state, so no locks needed. Per-page locks are used to protect the page descriptors. Per-TB locks are used in both modes to protect TB jumps. Some notes: - tb_lock is removed from notdirty_mem_write by passing a locked page_collection to tb_invalidate_phys_page_fast. - tcg_tb_lookup/remove/insert/etc have their own internal lock(s), so there is no need to further serialize access to them. - do_tb_flush is run in a safe async context, meaning no other vCPU threads are running. Therefore acquiring mmap_lock there is just to please tools such as thread sanitizer. - Not visible in the diff, but tb_invalidate_phys_page already has an assert_memory_lock. - cpu_io_recompile is !user-only, so no mmap_lock there. - Added mmap_unlock()'s before all siglongjmp's that could be called in user-mode while mmap_lock is held. + Added an assert for !have_mmap_lock() after returning from the longjmp in cpu_exec, just like we do in cpu_exec_step_atomic. Performance numbers before/after: Host: AMD Opteron(tm) Processor 6376 ubuntu 17.04 ppc64 bootup+shutdown time 700 +-+--+----+------+------------+-----------+------------*--+-+ | + + + + + *B | | before ***B*** ** * | |tb lock removal ###D### *** | 600 +-+ *** +-+ | ** # | | *B* #D | | *** * ## | 500 +-+ *** ### +-+ | * *** ### | | *B* # ## | | ** * #D# | 400 +-+ ** ## +-+ | ** ### | | ** ## | | ** # ## | 300 +-+ * B* #D# +-+ | B *** ### | | * ** #### | | * *** ### | 200 +-+ B *B #D# +-+ | #B* * ## # | | #* ## | | + D##D# + + + + | 100 +-+--+----+------+------------+-----------+------------+--+-+ 1 8 16 Guest CPUs 48 64 png: https://imgur.com/HwmBHXe debian jessie aarch64 bootup+shutdown time 90 +-+--+-----+-----+------------+------------+------------+--+-+ | + + + + + + | | before ***B*** B | 80 +tb lock removal ###D### **D +-+ | **### | | **## | 70 +-+ ** # +-+ | ** ## | | ** # | 60 +-+ *B ## +-+ | ** ## | | *** #D | 50 +-+ *** ## +-+ | * ** ### | | **B* ### | 40 +-+ **** # ## +-+ | **** #D# | | ***B** ### | 30 +-+ B***B** #### +-+ | B * * # ### | | B ###D# | 20 +-+ D ##D## +-+ | D# | | + + + + + + | 10 +-+--+-----+-----+------------+------------+------------+--+-+ 1 8 16 Guest CPUs 48 64 png: https://imgur.com/iGpGFtv The gains are high for 4-8 CPUs. Beyond that point, however, unrelated lock contention significantly hurts scalability. Reviewed-by: Alex Benn=C3=A9e Signed-off-by: Emilio G. Cota Tested-by: Alex Benn=C3=A9e --- docs/devel/multi-thread-tcg.txt | 11 ++-- accel/tcg/translate-all.h | 3 +- include/exec/cpu-common.h | 2 +- include/exec/exec-all.h | 4 -- include/exec/memory-internal.h | 6 +- include/exec/tb-context.h | 2 - tcg/tcg.h | 4 +- accel/tcg/cpu-exec.c | 34 +++-------- accel/tcg/translate-all.c | 132 ++++++++++++------------------------= ---- exec.c | 25 +++----- linux-user/main.c | 3 - 11 files changed, 74 insertions(+), 152 deletions(-) diff --git a/docs/devel/multi-thread-tcg.txt b/docs/devel/multi-thread-tcg.= txt index df83445..06530be 100644 --- a/docs/devel/multi-thread-tcg.txt +++ b/docs/devel/multi-thread-tcg.txt @@ -61,6 +61,7 @@ have their block-to-block jumps patched. Global TCG State ---------------- =20 +### User-mode emulation We need to protect the entire code generation cycle including any post generation patching of the translated code. This also implies a shared translation buffer which contains code running on all cores. Any @@ -75,9 +76,11 @@ patching. =20 (Current solution) =20 -Mainly as part of the linux-user work all code generation is -serialised with a tb_lock(). For the SoftMMU tb_lock() also takes the -place of mmap_lock() in linux-user. +Code generation is serialised with mmap_lock(). + +### !User-mode emulation +Each vCPU has its own TCG context and associated TCG region, thereby +requiring no locking. =20 Translation Blocks ------------------ @@ -195,7 +198,7 @@ work as "safe work" and exiting the cpu run loop. This = ensure by the time execution restarts all flush operations have completed. =20 TLB flag updates are all done atomically and are also protected by the -tb_lock() which is used by the functions that update the TLB in bulk. +corresponding page lock. =20 (Known limitation) =20 diff --git a/accel/tcg/translate-all.h b/accel/tcg/translate-all.h index 6d1d258..e6cb963 100644 --- a/accel/tcg/translate-all.h +++ b/accel/tcg/translate-all.h @@ -26,7 +26,8 @@ struct page_collection *page_collection_lock(tb_page_addr_t start, tb_page_addr_t end); void page_collection_unlock(struct page_collection *set); -void tb_invalidate_phys_page_fast(tb_page_addr_t start, int len); +void tb_invalidate_phys_page_fast(struct page_collection *pages, + tb_page_addr_t start, int len); void tb_invalidate_phys_page_range(tb_page_addr_t start, tb_page_addr_t en= d, int is_cpu_write_access); void tb_invalidate_phys_range(tb_page_addr_t start, tb_page_addr_t end); diff --git a/include/exec/cpu-common.h b/include/exec/cpu-common.h index 24d335f..46b3be5 100644 --- a/include/exec/cpu-common.h +++ b/include/exec/cpu-common.h @@ -23,7 +23,7 @@ typedef struct CPUListState { FILE *file; } CPUListState; =20 -/* The CPU list lock nests outside tb_lock/tb_unlock. */ +/* The CPU list lock nests outside page_(un)lock or mmap_(un)lock */ void qemu_init_cpu_list(void); void cpu_list_lock(void); void cpu_list_unlock(void); diff --git a/include/exec/exec-all.h b/include/exec/exec-all.h index daac968..9ad159a 100644 --- a/include/exec/exec-all.h +++ b/include/exec/exec-all.h @@ -439,10 +439,6 @@ extern uintptr_t tci_tb_ptr; smaller than 4 bytes, so we don't worry about special-casing this. */ #define GETPC_ADJ 2 =20 -void tb_lock(void); -void tb_unlock(void); -void tb_lock_reset(void); - #if !defined(CONFIG_USER_ONLY) && defined(CONFIG_DEBUG_TCG) void assert_no_pages_locked(void); #else diff --git a/include/exec/memory-internal.h b/include/exec/memory-internal.h index 58399b9..93a1ec2 100644 --- a/include/exec/memory-internal.h +++ b/include/exec/memory-internal.h @@ -48,6 +48,8 @@ void mtree_print_dispatch(fprintf_function mon, void *f, struct AddressSpaceDispatch *d, MemoryRegion *root); =20 +struct page_collection; + /* Opaque struct for passing info from memory_notdirty_write_prepare() * to memory_notdirty_write_complete(). Callers should treat all fields * as private, with the exception of @active. @@ -59,10 +61,10 @@ void mtree_print_dispatch(fprintf_function mon, void *f, */ typedef struct { CPUState *cpu; + struct page_collection *pages; ram_addr_t ram_addr; vaddr mem_vaddr; unsigned size; - bool locked; bool active; } NotDirtyInfo; =20 @@ -90,7 +92,7 @@ typedef struct { * * This must only be called if we are using TCG; it will assert otherwise. * - * We may take a lock in the prepare call, so callers must ensure that + * We may take locks in the prepare call, so callers must ensure that * they don't exit (via longjump or otherwise) without calling complete. * * This call must only be made inside an RCU critical section. diff --git a/include/exec/tb-context.h b/include/exec/tb-context.h index 8c9b49c..feb585e 100644 --- a/include/exec/tb-context.h +++ b/include/exec/tb-context.h @@ -32,8 +32,6 @@ typedef struct TBContext TBContext; struct TBContext { =20 struct qht htable; - /* any access to the tbs or the page table must use this lock */ - QemuMutex tb_lock; =20 /* statistics */ unsigned tb_flush_count; diff --git a/tcg/tcg.h b/tcg/tcg.h index ec8027b..2fccd20 100644 --- a/tcg/tcg.h +++ b/tcg/tcg.h @@ -857,7 +857,7 @@ static inline bool tcg_op_buf_full(void) =20 /* pool based memory allocation */ =20 -/* user-mode: tb_lock must be held for tcg_malloc_internal. */ +/* user-mode: mmap_lock must be held for tcg_malloc_internal. */ void *tcg_malloc_internal(TCGContext *s, int size); void tcg_pool_reset(TCGContext *s); TranslationBlock *tcg_tb_alloc(TCGContext *s); @@ -875,7 +875,7 @@ TranslationBlock *tcg_tb_lookup(uintptr_t tc_ptr); void tcg_tb_foreach(GTraverseFunc func, gpointer user_data); size_t tcg_nb_tbs(void); =20 -/* user-mode: Called with tb_lock held. */ +/* user-mode: Called with mmap_lock held. */ static inline void *tcg_malloc(int size) { TCGContext *s =3D tcg_ctx; diff --git a/accel/tcg/cpu-exec.c b/accel/tcg/cpu-exec.c index c9db99d..f86d9cb 100644 --- a/accel/tcg/cpu-exec.c +++ b/accel/tcg/cpu-exec.c @@ -213,20 +213,20 @@ static void cpu_exec_nocache(CPUState *cpu, int max_c= ycles, We only end up here when an existing TB is too long. */ cflags |=3D MIN(max_cycles, CF_COUNT_MASK); =20 - tb_lock(); + mmap_lock(); tb =3D tb_gen_code(cpu, orig_tb->pc, orig_tb->cs_base, orig_tb->flags, cflags); tb->orig_tb =3D orig_tb; - tb_unlock(); + mmap_unlock(); =20 /* execute the generated code */ trace_exec_tb_nocache(tb, tb->pc); cpu_tb_exec(cpu, tb); =20 - tb_lock(); + mmap_lock(); tb_phys_invalidate(tb, -1); + mmap_unlock(); tcg_tb_remove(tb); - tb_unlock(); } #endif =20 @@ -245,9 +245,7 @@ void cpu_exec_step_atomic(CPUState *cpu) tb =3D tb_lookup__cpu_state(cpu, &pc, &cs_base, &flags, cf_mask); if (tb =3D=3D NULL) { mmap_lock(); - tb_lock(); tb =3D tb_gen_code(cpu, pc, cs_base, flags, cflags); - tb_unlock(); mmap_unlock(); } =20 @@ -262,15 +260,13 @@ void cpu_exec_step_atomic(CPUState *cpu) cpu_tb_exec(cpu, tb); cc->cpu_exec_exit(cpu); } else { - /* We may have exited due to another problem here, so we need - * to reset any tb_locks we may have taken but didn't release. + /* * The mmap_lock is dropped by tb_gen_code if it runs out of * memory. */ #ifndef CONFIG_SOFTMMU tcg_debug_assert(!have_mmap_lock()); #endif - tb_lock_reset(); assert_no_pages_locked(); } =20 @@ -399,20 +395,11 @@ static inline TranslationBlock *tb_find(CPUState *cpu, TranslationBlock *tb; target_ulong cs_base, pc; uint32_t flags; - bool acquired_tb_lock =3D false; =20 tb =3D tb_lookup__cpu_state(cpu, &pc, &cs_base, &flags, cf_mask); if (tb =3D=3D NULL) { - /* mmap_lock is needed by tb_gen_code, and mmap_lock must be - * taken outside tb_lock. As system emulation is currently - * single threaded the locks are NOPs. - */ mmap_lock(); - tb_lock(); - acquired_tb_lock =3D true; - tb =3D tb_gen_code(cpu, pc, cs_base, flags, cf_mask); - mmap_unlock(); /* We add the TB in the virtual pc hash table for the fast lookup = */ atomic_set(&cpu->tb_jmp_cache[tb_jmp_cache_hash_func(pc)], tb); @@ -428,15 +415,8 @@ static inline TranslationBlock *tb_find(CPUState *cpu, #endif /* See if we can patch the calling TB. */ if (last_tb && !qemu_loglevel_mask(CPU_LOG_TB_NOCHAIN)) { - if (!acquired_tb_lock) { - tb_lock(); - acquired_tb_lock =3D true; - } tb_add_jump(last_tb, tb_exit, tb); } - if (acquired_tb_lock) { - tb_unlock(); - } return tb; } =20 @@ -711,7 +691,9 @@ int cpu_exec(CPUState *cpu) g_assert(cpu =3D=3D current_cpu); g_assert(cc =3D=3D CPU_GET_CLASS(cpu)); #endif /* buggy compiler */ - tb_lock_reset(); +#ifndef CONFIG_SOFTMMU + tcg_debug_assert(!have_mmap_lock()); +#endif if (qemu_mutex_iothread_locked()) { qemu_mutex_unlock_iothread(); } diff --git a/accel/tcg/translate-all.c b/accel/tcg/translate-all.c index 6cc7b94..9d76ec0 100644 --- a/accel/tcg/translate-all.c +++ b/accel/tcg/translate-all.c @@ -88,13 +88,13 @@ #endif =20 /* Access to the various translations structures need to be serialised via= locks - * for consistency. This is automatic for SoftMMU based system - * emulation due to its single threaded nature. In user-mode emulation - * access to the memory related structures are protected with the - * mmap_lock. + * for consistency. + * In user-mode emulation access to the memory related structures are prot= ected + * with mmap_lock. + * In !user-mode we use per-page locks. */ #ifdef CONFIG_SOFTMMU -#define assert_memory_lock() tcg_debug_assert(have_tb_lock) +#define assert_memory_lock() #else #define assert_memory_lock() tcg_debug_assert(have_mmap_lock()) #endif @@ -216,9 +216,6 @@ __thread TCGContext *tcg_ctx; TBContext tb_ctx; bool parallel_cpus; =20 -/* translation block context */ -static __thread int have_tb_lock; - static void page_table_config_init(void) { uint32_t v_l1_bits; @@ -239,31 +236,6 @@ static void page_table_config_init(void) assert(v_l2_levels >=3D 0); } =20 -#define assert_tb_locked() tcg_debug_assert(have_tb_lock) -#define assert_tb_unlocked() tcg_debug_assert(!have_tb_lock) - -void tb_lock(void) -{ - assert_tb_unlocked(); - qemu_mutex_lock(&tb_ctx.tb_lock); - have_tb_lock++; -} - -void tb_unlock(void) -{ - assert_tb_locked(); - have_tb_lock--; - qemu_mutex_unlock(&tb_ctx.tb_lock); -} - -void tb_lock_reset(void) -{ - if (have_tb_lock) { - qemu_mutex_unlock(&tb_ctx.tb_lock); - have_tb_lock =3D 0; - } -} - void cpu_gen_init(void) { tcg_context_init(&tcg_init_ctx); @@ -420,8 +392,7 @@ bool cpu_restore_state(CPUState *cpu, uintptr_t host_pc= , bool will_exit) * - fault during translation (instruction fetch) * - fault from helper (not using GETPC() macro) * - * Either way we need return early to avoid blowing up on a - * recursive tb_lock() as we can't resolve it here. + * Either way we need return early as we can't resolve it here. * * We are using unsigned arithmetic so if host_pc < * tcg_init_ctx.code_gen_buffer check_offset will wrap to way @@ -430,7 +401,6 @@ bool cpu_restore_state(CPUState *cpu, uintptr_t host_pc= , bool will_exit) check_offset =3D host_pc - (uintptr_t) tcg_init_ctx.code_gen_buffer; =20 if (check_offset < tcg_init_ctx.code_gen_buffer_size) { - tb_lock(); tb =3D tcg_tb_lookup(host_pc); if (tb) { cpu_restore_state_from_tb(cpu, tb, host_pc, will_exit); @@ -441,7 +411,6 @@ bool cpu_restore_state(CPUState *cpu, uintptr_t host_pc= , bool will_exit) } r =3D true; } - tb_unlock(); } =20 return r; @@ -1129,7 +1098,6 @@ static inline void code_gen_alloc(size_t tb_size) fprintf(stderr, "Could not allocate dynamic translator buffer\n"); exit(1); } - qemu_mutex_init(&tb_ctx.tb_lock); } =20 static bool tb_cmp(const void *ap, const void *bp) @@ -1173,14 +1141,12 @@ void tcg_exec_init(unsigned long tb_size) /* * Allocate a new translation block. Flush the translation buffer if * too many translation blocks or too much generated code. - * - * Called with tb_lock held. */ static TranslationBlock *tb_alloc(target_ulong pc) { TranslationBlock *tb; =20 - assert_tb_locked(); + assert_memory_lock(); =20 tb =3D tcg_tb_alloc(tcg_ctx); if (unlikely(tb =3D=3D NULL)) { @@ -1247,8 +1213,7 @@ static gboolean tb_host_size_iter(gpointer key, gpoin= ter value, gpointer data) /* flush all the translation blocks */ static void do_tb_flush(CPUState *cpu, run_on_cpu_data tb_flush_count) { - tb_lock(); - + mmap_lock(); /* If it is already been done on request of another CPU, * just retry. */ @@ -1278,7 +1243,7 @@ static void do_tb_flush(CPUState *cpu, run_on_cpu_dat= a tb_flush_count) atomic_mb_set(&tb_ctx.tb_flush_count, tb_ctx.tb_flush_count + 1); =20 done: - tb_unlock(); + mmap_unlock(); } =20 void tb_flush(CPUState *cpu) @@ -1312,7 +1277,7 @@ do_tb_invalidate_check(struct qht *ht, void *p, uint3= 2_t hash, void *userp) =20 /* verify that all the pages have correct rights for code * - * Called with tb_lock held. + * Called with mmap_lock held. */ static void tb_invalidate_check(target_ulong address) { @@ -1342,7 +1307,10 @@ static void tb_page_check(void) =20 #endif /* CONFIG_USER_ONLY */ =20 -/* call with @pd->lock held */ +/* + * user-mode: call with mmap_lock held + * !user-mode: call with @pd->lock held + */ static inline void tb_page_remove(PageDesc *pd, TranslationBlock *tb) { TranslationBlock *tb1; @@ -1436,7 +1404,11 @@ static inline void tb_jmp_unlink(TranslationBlock *d= est) qemu_spin_unlock(&dest->jmp_lock); } =20 -/* If @rm_from_page_list is set, call with the TB's pages' locks held */ +/* + * In user-mode, call with mmap_lock held. + * In !user-mode, if @rm_from_page_list is set, call with the TB's pages' + * locks held. + */ static void do_tb_phys_invalidate(TranslationBlock *tb, bool rm_from_page_= list) { CPUState *cpu; @@ -1444,7 +1416,7 @@ static void do_tb_phys_invalidate(TranslationBlock *t= b, bool rm_from_page_list) uint32_t h; tb_page_addr_t phys_pc; =20 - assert_tb_locked(); + assert_memory_lock(); =20 /* make sure no further incoming jumps will be chained to this TB */ qemu_spin_lock(&tb->jmp_lock); @@ -1497,7 +1469,7 @@ static void tb_phys_invalidate__locked(TranslationBlo= ck *tb) =20 /* invalidate one TB * - * Called with tb_lock held. + * Called with mmap_lock held in user-mode. */ void tb_phys_invalidate(TranslationBlock *tb, tb_page_addr_t page_addr) { @@ -1542,7 +1514,7 @@ static void build_page_bitmap(PageDesc *p) /* add the tb in the target page and protect it if necessary * * Called with mmap_lock held for user-mode emulation. - * Called with @p->lock held. + * Called with @p->lock held in !user-mode. */ static inline void tb_page_add(PageDesc *p, TranslationBlock *tb, unsigned int n, tb_page_addr_t page_addr) @@ -1814,10 +1786,9 @@ TranslationBlock *tb_gen_code(CPUState *cpu, if ((pc & TARGET_PAGE_MASK) !=3D virt_page2) { phys_page2 =3D get_page_addr_code(env, virt_page2); } - /* As long as consistency of the TB stuff is provided by tb_lock in us= er - * mode and is implicit in single-threaded softmmu emulation, no expli= cit - * memory barrier is required before tb_link_page() makes the TB visib= le - * through the physical hash table and physical page list. + /* + * No explicit memory barrier is required -- tb_link_page() makes the + * TB visible in a consistent state. */ existing_tb =3D tb_link_page(tb, phys_pc, phys_page2); /* if the TB already exists, discard what we just translated */ @@ -1833,8 +1804,9 @@ TranslationBlock *tb_gen_code(CPUState *cpu, } =20 /* - * Call with all @pages locked. * @p must be non-NULL. + * user-mode: call with mmap_lock held. + * !user-mode: call with all @pages locked. */ static void tb_invalidate_phys_page_range__locked(struct page_collection *pages, @@ -1919,6 +1891,7 @@ tb_invalidate_phys_page_range__locked(struct page_col= lection *pages, page_collection_unlock(pages); /* Force execution of one insn next time. */ cpu->cflags_next_tb =3D 1 | curr_cflags(); + mmap_unlock(); cpu_loop_exit_noexc(cpu); } #endif @@ -1931,8 +1904,7 @@ tb_invalidate_phys_page_range__locked(struct page_col= lection *pages, * access: the virtual CPU will exit the current TB if code is modified in= side * this TB. * - * Called with tb_lock/mmap_lock held for user-mode emulation - * Called with tb_lock held for system-mode emulation + * Called with mmap_lock held for user-mode emulation */ void tb_invalidate_phys_page_range(tb_page_addr_t start, tb_page_addr_t en= d, int is_cpu_write_access) @@ -1941,7 +1913,6 @@ void tb_invalidate_phys_page_range(tb_page_addr_t sta= rt, tb_page_addr_t end, PageDesc *p; =20 assert_memory_lock(); - assert_tb_locked(); =20 p =3D page_find(start >> TARGET_PAGE_BITS); if (p =3D=3D NULL) { @@ -1960,14 +1931,15 @@ void tb_invalidate_phys_page_range(tb_page_addr_t s= tart, tb_page_addr_t end, * access: the virtual CPU will exit the current TB if code is modified in= side * this TB. * - * Called with mmap_lock held for user-mode emulation, grabs tb_lock - * Called with tb_lock held for system-mode emulation + * Called with mmap_lock held for user-mode emulation. */ -static void tb_invalidate_phys_range_1(tb_page_addr_t start, tb_page_addr_= t end) +void tb_invalidate_phys_range(tb_page_addr_t start, tb_page_addr_t end) { struct page_collection *pages; tb_page_addr_t next; =20 + assert_memory_lock(); + pages =3D page_collection_lock(start, end); for (next =3D (start & TARGET_PAGE_MASK) + TARGET_PAGE_SIZE; start < end; @@ -1984,29 +1956,15 @@ static void tb_invalidate_phys_range_1(tb_page_addr= _t start, tb_page_addr_t end) } =20 #ifdef CONFIG_SOFTMMU -void tb_invalidate_phys_range(tb_page_addr_t start, tb_page_addr_t end) -{ - assert_tb_locked(); - tb_invalidate_phys_range_1(start, end); -} -#else -void tb_invalidate_phys_range(tb_page_addr_t start, tb_page_addr_t end) -{ - assert_memory_lock(); - tb_lock(); - tb_invalidate_phys_range_1(start, end); - tb_unlock(); -} -#endif - -#ifdef CONFIG_SOFTMMU /* len must be <=3D 8 and start must be a multiple of len. * Called via softmmu_template.h when code areas are written to with * iothread mutex not held. + * + * Call with all @pages in the range [@start, @start + len[ locked. */ -void tb_invalidate_phys_page_fast(tb_page_addr_t start, int len) +void tb_invalidate_phys_page_fast(struct page_collection *pages, + tb_page_addr_t start, int len) { - struct page_collection *pages; PageDesc *p; =20 #if 0 @@ -2025,7 +1983,6 @@ void tb_invalidate_phys_page_fast(tb_page_addr_t star= t, int len) return; } =20 - pages =3D page_collection_lock(start, start + len); assert_page_locked(p); if (!p->code_bitmap && ++p->code_write_count >=3D SMC_BITMAP_USE_THRESHOLD) { @@ -2044,7 +2001,6 @@ void tb_invalidate_phys_page_fast(tb_page_addr_t star= t, int len) do_invalidate: tb_invalidate_phys_page_range__locked(pages, p, start, start + len= , 1); } - page_collection_unlock(pages); } #else /* Called with mmap_lock held. If pc is not 0 then it indicates the @@ -2076,7 +2032,6 @@ static bool tb_invalidate_phys_page(tb_page_addr_t ad= dr, uintptr_t pc) return false; } =20 - tb_lock(); #ifdef TARGET_HAS_PRECISE_SMC if (p->first_tb && pc !=3D 0) { current_tb =3D tcg_tb_lookup(pc); @@ -2109,12 +2064,9 @@ static bool tb_invalidate_phys_page(tb_page_addr_t a= ddr, uintptr_t pc) if (current_tb_modified) { /* Force execution of one insn next time. */ cpu->cflags_next_tb =3D 1 | curr_cflags(); - /* tb_lock will be reset after cpu_loop_exit_noexc longjmps - * back into the cpu_exec loop. */ return true; } #endif - tb_unlock(); =20 return false; } @@ -2135,18 +2087,18 @@ void tb_invalidate_phys_addr(AddressSpace *as, hwad= dr addr) return; } ram_addr =3D memory_region_get_ram_addr(mr) + addr; - tb_lock(); tb_invalidate_phys_page_range(ram_addr, ram_addr + 1, 0); - tb_unlock(); rcu_read_unlock(); } #endif /* !defined(CONFIG_USER_ONLY) */ =20 -/* Called with tb_lock held. */ +/* user-mode: call with mmap_lock held */ void tb_check_watchpoint(CPUState *cpu) { TranslationBlock *tb; =20 + assert_memory_lock(); + tb =3D tcg_tb_lookup(cpu->mem_io_pc); if (tb) { /* We can use retranslation to find the PC. */ @@ -2180,7 +2132,6 @@ void cpu_io_recompile(CPUState *cpu, uintptr_t retadd= r) TranslationBlock *tb; uint32_t n; =20 - tb_lock(); tb =3D tcg_tb_lookup(retaddr); if (!tb) { cpu_abort(cpu, "cpu_io_recompile: could not find TB for pc=3D%p", @@ -2228,9 +2179,6 @@ void cpu_io_recompile(CPUState *cpu, uintptr_t retadd= r) * repeating the fault, which is horribly inefficient. * Better would be to execute just this insn uncached, or generate a * second new TB. - * - * cpu_loop_exit_noexc will longjmp back to cpu_exec where the - * tb_lock gets reset. */ cpu_loop_exit_noexc(cpu); } diff --git a/exec.c b/exec.c index ffa1099..afc37e0 100644 --- a/exec.c +++ b/exec.c @@ -884,9 +884,7 @@ const char *parse_cpu_model(const char *cpu_model) static void breakpoint_invalidate(CPUState *cpu, target_ulong pc) { mmap_lock(); - tb_lock(); tb_invalidate_phys_page_range(pc, pc + 1, 0); - tb_unlock(); mmap_unlock(); } #else @@ -2481,21 +2479,20 @@ void memory_notdirty_write_prepare(NotDirtyInfo *nd= i, ndi->ram_addr =3D ram_addr; ndi->mem_vaddr =3D mem_vaddr; ndi->size =3D size; - ndi->locked =3D false; + ndi->pages =3D NULL; =20 assert(tcg_enabled()); if (!cpu_physical_memory_get_dirty_flag(ram_addr, DIRTY_MEMORY_CODE)) { - ndi->locked =3D true; - tb_lock(); - tb_invalidate_phys_page_fast(ram_addr, size); + ndi->pages =3D page_collection_lock(ram_addr, ram_addr + size); + tb_invalidate_phys_page_fast(ndi->pages, ram_addr, size); } } =20 /* Called within RCU critical section. */ void memory_notdirty_write_complete(NotDirtyInfo *ndi) { - if (ndi->locked) { - tb_unlock(); + if (ndi->pages) { + page_collection_unlock(ndi->pages); } =20 /* Set both VGA and migration bits for simplicity and to remove @@ -2596,18 +2593,16 @@ static void check_watchpoint(int offset, int len, M= emTxAttrs attrs, int flags) } cpu->watchpoint_hit =3D wp; =20 - /* Both tb_lock and iothread_mutex will be reset when - * cpu_loop_exit or cpu_loop_exit_noexc longjmp - * back into the cpu_exec main loop. - */ - tb_lock(); + mmap_lock(); tb_check_watchpoint(cpu); if (wp->flags & BP_STOP_BEFORE_ACCESS) { cpu->exception_index =3D EXCP_DEBUG; + mmap_unlock(); cpu_loop_exit(cpu); } else { /* Force execution of one insn next time. */ cpu->cflags_next_tb =3D 1 | curr_cflags(); + mmap_unlock(); cpu_loop_exit_noexc(cpu); } } @@ -3024,9 +3019,9 @@ static void invalidate_and_set_dirty(MemoryRegion *mr= , hwaddr addr, } if (dirty_log_mask & (1 << DIRTY_MEMORY_CODE)) { assert(tcg_enabled()); - tb_lock(); + mmap_lock(); tb_invalidate_phys_range(addr, addr + length); - tb_unlock(); + mmap_unlock(); dirty_log_mask &=3D ~(1 << DIRTY_MEMORY_CODE); } cpu_physical_memory_set_dirty_range(addr, length, dirty_log_mask); diff --git a/linux-user/main.c b/linux-user/main.c index 3234754..ae68b2e 100644 --- a/linux-user/main.c +++ b/linux-user/main.c @@ -120,7 +120,6 @@ void fork_start(void) { start_exclusive(); mmap_fork_start(); - qemu_mutex_lock(&tb_ctx.tb_lock); cpu_list_lock(); } =20 @@ -136,14 +135,12 @@ void fork_end(int child) QTAILQ_REMOVE(&cpus, cpu, node); } } - qemu_mutex_init(&tb_ctx.tb_lock); qemu_init_cpu_list(); gdbserver_fork(thread_cpu); /* qemu_init_cpu_list() takes care of reinitializing the * exclusive state, so we don't need to end_exclusive() here. */ } else { - qemu_mutex_unlock(&tb_ctx.tb_lock); cpu_list_unlock(); end_exclusive(); } --=20 2.7.4