From f5b98461cb8167ba362ad9f74c41d126b7becea7 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Fri, 6 Jan 2017 19:32:01 +0100 Subject: random: use chacha20 for get_random_int/long Now that our crng uses chacha20, we can rely on its speedy characteristics for replacing MD5, while simultaneously achieving a higher security guarantee. Before the idea was to use these functions if you wanted random integers that aren't stupidly insecure but aren't necessarily secure either, a vague gray zone, that hopefully was "good enough" for its users. With chacha20, we can strengthen this claim, since either we're using an rdrand-like instruction, or we're using the same crng as /dev/urandom. And it's faster than what was before. We could have chosen to replace this with a SipHash-derived function, which might be slightly faster, but at the cost of having yet another RNG construction in the kernel. By moving to chacha20, we have a single RNG to analyze and verify, and we also already get good performance improvements on all platforms. Implementation-wise, rather than use a generic buffer for both get_random_int/long and memcpy based on the size needs, we use a specific buffer for 32-bit reads and for 64-bit reads. This way, we're guaranteed to always have aligned accesses on all platforms. While slightly more verbose in C, the assembly this generates is a lot simpler than otherwise. Finally, on 32-bit platforms where longs and ints are the same size, we simply alias get_random_int to get_random_long. Signed-off-by: Jason A. Donenfeld Suggested-by: Theodore Ts'o Cc: Theodore Ts'o Cc: Hannes Frederic Sowa Cc: Andy Lutomirski Signed-off-by: Theodore Ts'o --- include/linux/random.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/random.h b/include/linux/random.h index 7bd2403e4fef..16ab429735a7 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -37,7 +37,6 @@ extern void get_random_bytes(void *buf, int nbytes); extern int add_random_ready_callback(struct random_ready_callback *rdy); extern void del_random_ready_callback(struct random_ready_callback *rdy); extern void get_random_bytes_arch(void *buf, int nbytes); -extern int random_int_secret_init(void); #ifndef MODULE extern const struct file_operations random_fops, urandom_fops; -- cgit v1.2.3 From c440408cf6901eeb2c09563397e24a9097907078 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Sun, 22 Jan 2017 16:34:08 +0100 Subject: random: convert get_random_int/long into get_random_u32/u64 Many times, when a user wants a random number, he wants a random number of a guaranteed size. So, thinking of get_random_int and get_random_long in terms of get_random_u32 and get_random_u64 makes it much easier to achieve this. It also makes the code simpler. On 32-bit platforms, get_random_int and get_random_long are both aliased to get_random_u32. On 64-bit platforms, int->u32 and long->u64. Signed-off-by: Jason A. Donenfeld Cc: Greg Kroah-Hartman Cc: Theodore Ts'o Signed-off-by: Theodore Ts'o --- drivers/char/random.c | 55 +++++++++++++++++++++++++------------------------- include/linux/random.h | 17 ++++++++++++++-- 2 files changed, 42 insertions(+), 30 deletions(-) (limited to 'include/linux') diff --git a/drivers/char/random.c b/drivers/char/random.c index b800e5479b7d..066ae125f2c8 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -2018,8 +2018,8 @@ struct ctl_table random_table[] = { struct batched_entropy { union { - unsigned long entropy_long[CHACHA20_BLOCK_SIZE / sizeof(unsigned long)]; - unsigned int entropy_int[CHACHA20_BLOCK_SIZE / sizeof(unsigned int)]; + u64 entropy_u64[CHACHA20_BLOCK_SIZE / sizeof(u64)]; + u32 entropy_u32[CHACHA20_BLOCK_SIZE / sizeof(u32)]; }; unsigned int position; }; @@ -2029,52 +2029,51 @@ struct batched_entropy { * number is either as good as RDRAND or as good as /dev/urandom, with the * goal of being quite fast and not depleting entropy. */ -static DEFINE_PER_CPU(struct batched_entropy, batched_entropy_long); -unsigned long get_random_long(void) +static DEFINE_PER_CPU(struct batched_entropy, batched_entropy_u64); +u64 get_random_u64(void) { - unsigned long ret; + u64 ret; struct batched_entropy *batch; - if (arch_get_random_long(&ret)) +#if BITS_PER_LONG == 64 + if (arch_get_random_long((unsigned long *)&ret)) return ret; +#else + if (arch_get_random_long((unsigned long *)&ret) && + arch_get_random_long((unsigned long *)&ret + 1)) + return ret; +#endif - batch = &get_cpu_var(batched_entropy_long); - if (batch->position % ARRAY_SIZE(batch->entropy_long) == 0) { - extract_crng((u8 *)batch->entropy_long); + batch = &get_cpu_var(batched_entropy_u64); + if (batch->position % ARRAY_SIZE(batch->entropy_u64) == 0) { + extract_crng((u8 *)batch->entropy_u64); batch->position = 0; } - ret = batch->entropy_long[batch->position++]; - put_cpu_var(batched_entropy_long); + ret = batch->entropy_u64[batch->position++]; + put_cpu_var(batched_entropy_u64); return ret; } -EXPORT_SYMBOL(get_random_long); +EXPORT_SYMBOL(get_random_u64); -#if BITS_PER_LONG == 32 -unsigned int get_random_int(void) -{ - return get_random_long(); -} -#else -static DEFINE_PER_CPU(struct batched_entropy, batched_entropy_int); -unsigned int get_random_int(void) +static DEFINE_PER_CPU(struct batched_entropy, batched_entropy_u32); +u32 get_random_u32(void) { - unsigned int ret; + u32 ret; struct batched_entropy *batch; if (arch_get_random_int(&ret)) return ret; - batch = &get_cpu_var(batched_entropy_int); - if (batch->position % ARRAY_SIZE(batch->entropy_int) == 0) { - extract_crng((u8 *)batch->entropy_int); + batch = &get_cpu_var(batched_entropy_u32); + if (batch->position % ARRAY_SIZE(batch->entropy_u32) == 0) { + extract_crng((u8 *)batch->entropy_u32); batch->position = 0; } - ret = batch->entropy_int[batch->position++]; - put_cpu_var(batched_entropy_int); + ret = batch->entropy_u32[batch->position++]; + put_cpu_var(batched_entropy_u32); return ret; } -#endif -EXPORT_SYMBOL(get_random_int); +EXPORT_SYMBOL(get_random_u32); /** * randomize_page - Generate a random, page aligned address diff --git a/include/linux/random.h b/include/linux/random.h index 16ab429735a7..ed5c3838780d 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -42,8 +42,21 @@ extern void get_random_bytes_arch(void *buf, int nbytes); extern const struct file_operations random_fops, urandom_fops; #endif -unsigned int get_random_int(void); -unsigned long get_random_long(void); +u32 get_random_u32(void); +u64 get_random_u64(void); +static inline unsigned int get_random_int(void) +{ + return get_random_u32(); +} +static inline unsigned long get_random_long(void) +{ +#if BITS_PER_LONG == 64 + return get_random_u64(); +#else + return get_random_u32(); +#endif +} + unsigned long randomize_page(unsigned long start, unsigned long range); u32 prandom_u32(void); -- cgit v1.2.3 From cd8d860dcce906cd477be7d0648ba6f56a52eaa6 Mon Sep 17 00:00:00 2001 From: Boris Ostrovsky Date: Tue, 28 Feb 2017 11:32:22 -0500 Subject: jump_label: Fix anonymous union initialization Pre-4.6 gcc do not allow direct static initialization of members of anonymous structs/unions. After commit 3821fd35b58d ("jump_label: Reduce the size of struct static_key") STATIC_KEY_INIT_{TRUE|FALSE} definitions cannot be compiled with those older compilers. Placing initializers inside curved brackets works around this problem. Link: http://lkml.kernel.org/r/1488299542-30765-1-git-send-email-boris.ostrovsky@oracle.com Fixes: 3821fd35b58d ("jump_label: Reduce the size of struct static_key") Reviewed-by: Jason Baron Compiled-by: Chris Mason Signed-off-by: Boris Ostrovsky Signed-off-by: Steven Rostedt (VMware) --- include/linux/jump_label.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h index 680c98b2f41c..a7f90117cf7d 100644 --- a/include/linux/jump_label.h +++ b/include/linux/jump_label.h @@ -166,10 +166,10 @@ extern void static_key_disable(struct static_key *key); */ #define STATIC_KEY_INIT_TRUE \ { .enabled = { 1 }, \ - .entries = (void *)JUMP_TYPE_TRUE } + { .entries = (void *)JUMP_TYPE_TRUE } } #define STATIC_KEY_INIT_FALSE \ { .enabled = { 0 }, \ - .entries = (void *)JUMP_TYPE_FALSE } + { .entries = (void *)JUMP_TYPE_FALSE } } #else /* !HAVE_JUMP_LABEL */ -- cgit v1.2.3 From b17ef2ed624aa7c1f68ed11acd16ecbf80fe01d7 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Thu, 2 Mar 2017 17:28:45 -0500 Subject: jump_label: Add comment about initialization order for anonymous unions Commit 3821fd35b58d ("jump_label: Reduce the size of struct static_key") broke old compilers that could not handle static initialization of anonymous unions. Boris fixed it with a patch that added brackets around the static initializer. But this creates a dependency between those initializers and the structure's order of its fields. Document this dependency in case new fields are added to struct static_key in the future. Noted-by: Boris Ostrovsky Suggested-by: Chris Mason Signed-off-by: Steven Rostedt (VMware) --- include/linux/jump_label.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h index a7f90117cf7d..28e04a33535a 100644 --- a/include/linux/jump_label.h +++ b/include/linux/jump_label.h @@ -90,6 +90,13 @@ extern bool static_key_initialized; struct static_key { atomic_t enabled; /* + * Note: + * To make anonymous unions work with old compilers, the static + * initialization of them requires brackets. This creates a dependency + * on the order of the struct with the initializers. If any fields + * are added, STATIC_KEY_INIT_TRUE and STATIC_KEY_INIT_FALSE may need + * to be modified. + * * bit 0 => 1 if key is initially true * 0 if initially false * bit 1 => 1 if points to struct static_key_mod -- cgit v1.2.3 From 4dfc050571523ac2bc02cbf948dd47621f7dd83f Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 21 Feb 2017 11:32:47 +0000 Subject: KVM: arm/arm64: vgic-v3: Don't pretend to support IRQ/FIQ bypass Our GICv3 emulation always presents ICC_SRE_EL1 with DIB/DFB set to zero, which implies that there is a way to bypass the GIC and inject raw IRQ/FIQ by driving the CPU pins. Of course, we don't allow that when the GIC is configured, but we fail to indicate that to the guest. The obvious fix is to set these bits (and never let them being changed again). Reported-by: Peter Maydell Acked-by: Christoffer Dall Reviewed-by: Eric Auger Signed-off-by: Marc Zyngier --- include/linux/irqchip/arm-gic-v3.h | 2 ++ virt/kvm/arm/vgic/vgic-v3.c | 5 ++++- 2 files changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 672cfef72fc8..97cbca19430d 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -373,6 +373,8 @@ #define ICC_IGRPEN0_EL1_MASK (1 << ICC_IGRPEN0_EL1_SHIFT) #define ICC_IGRPEN1_EL1_SHIFT 0 #define ICC_IGRPEN1_EL1_MASK (1 << ICC_IGRPEN1_EL1_SHIFT) +#define ICC_SRE_EL1_DIB (1U << 2) +#define ICC_SRE_EL1_DFB (1U << 1) #define ICC_SRE_EL1_SRE (1U << 0) /* diff --git a/virt/kvm/arm/vgic/vgic-v3.c b/virt/kvm/arm/vgic/vgic-v3.c index edc6ee2dc852..be0f4c3e0142 100644 --- a/virt/kvm/arm/vgic/vgic-v3.c +++ b/virt/kvm/arm/vgic/vgic-v3.c @@ -229,10 +229,13 @@ void vgic_v3_enable(struct kvm_vcpu *vcpu) /* * If we are emulating a GICv3, we do it in an non-GICv2-compatible * way, so we force SRE to 1 to demonstrate this to the guest. + * Also, we don't support any form of IRQ/FIQ bypass. * This goes with the spec allowing the value to be RAO/WI. */ if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) { - vgic_v3->vgic_sre = ICC_SRE_EL1_SRE; + vgic_v3->vgic_sre = (ICC_SRE_EL1_DIB | + ICC_SRE_EL1_DFB | + ICC_SRE_EL1_SRE); vcpu->arch.vgic_cpu.pendbaser = INITIAL_PENDBASER_VALUE; } else { vgic_v3->vgic_sre = 0; -- cgit v1.2.3 From b3e228473e6cec7cf83b4025b4570c8066ab2dd8 Mon Sep 17 00:00:00 2001 From: Mian Yousaf Kaukab Date: Thu, 2 Mar 2017 16:11:47 +0100 Subject: irqdomain: Add empty irq_domain_check_msi_remap Fix following build error for s390: drivers/vfio/vfio_iommu_type1.c: In function 'vfio_iommu_type1_attach_group': drivers/vfio/vfio_iommu_type1.c:1290:25: error: implicit declaration of function 'irq_domain_check_msi_remap' Acked-by: Marc Zyngier Reviewed-by: Eric Auger Signed-off-by: Mian Yousaf Kaukab Signed-off-by: Marc Zyngier --- include/linux/irqdomain.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index 188eced6813e..9f3616085423 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -524,6 +524,10 @@ static inline struct irq_domain *irq_find_matching_fwnode( { return NULL; } +static inline bool irq_domain_check_msi_remap(void) +{ + return false; +} #endif /* !CONFIG_IRQ_DOMAIN */ #endif /* _LINUX_IRQDOMAIN_H */ -- cgit v1.2.3 From 040757f738e13caaa9c5078bca79aa97e11dde88 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sun, 5 Mar 2017 15:03:22 -0600 Subject: ucount: Remove the atomicity from ucount->count Always increment/decrement ucount->count under the ucounts_lock. The increments are there already and moving the decrements there means the locking logic of the code is simpler. This simplification in the locking logic fixes a race between put_ucounts and get_ucounts that could result in a use-after-free because the count could go zero then be found by get_ucounts and then be freed by put_ucounts. A bug presumably this one was found by a combination of syzkaller and KASAN. JongWhan Kim reported the syzkaller failure and Dmitry Vyukov spotted the race in the code. Cc: stable@vger.kernel.org Fixes: f6b2db1a3e8d ("userns: Make the count of user namespaces per user") Reported-by: JongHwan Kim Reported-by: Dmitry Vyukov Reviewed-by: Andrei Vagin Signed-off-by: "Eric W. Biederman" --- include/linux/user_namespace.h | 2 +- kernel/ucount.c | 18 +++++++++++------- 2 files changed, 12 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h index be765234c0a2..32354b4b4b2b 100644 --- a/include/linux/user_namespace.h +++ b/include/linux/user_namespace.h @@ -72,7 +72,7 @@ struct ucounts { struct hlist_node node; struct user_namespace *ns; kuid_t uid; - atomic_t count; + int count; atomic_t ucount[UCOUNT_COUNTS]; }; diff --git a/kernel/ucount.c b/kernel/ucount.c index 62630a40ab3a..b4eeee03934f 100644 --- a/kernel/ucount.c +++ b/kernel/ucount.c @@ -144,7 +144,7 @@ static struct ucounts *get_ucounts(struct user_namespace *ns, kuid_t uid) new->ns = ns; new->uid = uid; - atomic_set(&new->count, 0); + new->count = 0; spin_lock_irq(&ucounts_lock); ucounts = find_ucounts(ns, uid, hashent); @@ -155,8 +155,10 @@ static struct ucounts *get_ucounts(struct user_namespace *ns, kuid_t uid) ucounts = new; } } - if (!atomic_add_unless(&ucounts->count, 1, INT_MAX)) + if (ucounts->count == INT_MAX) ucounts = NULL; + else + ucounts->count += 1; spin_unlock_irq(&ucounts_lock); return ucounts; } @@ -165,13 +167,15 @@ static void put_ucounts(struct ucounts *ucounts) { unsigned long flags; - if (atomic_dec_and_test(&ucounts->count)) { - spin_lock_irqsave(&ucounts_lock, flags); + spin_lock_irqsave(&ucounts_lock, flags); + ucounts->count -= 1; + if (!ucounts->count) hlist_del_init(&ucounts->node); - spin_unlock_irqrestore(&ucounts_lock, flags); + else + ucounts = NULL; + spin_unlock_irqrestore(&ucounts_lock, flags); - kfree(ucounts); - } + kfree(ucounts); } static inline bool atomic_inc_below(atomic_t *v, int u) -- cgit v1.2.3 From 7cc5e38f2f0b0b58a22a4c18a56348dd99a71270 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Sun, 12 Feb 2017 17:11:07 +0100 Subject: libceph: osd_request_timeout option osd_request_timeout specifies how many seconds to wait for a response from OSDs before returning -ETIMEDOUT from an OSD request. 0 (default) means no limit. osd_request_timeout is osdkeepalive-precise -- in-flight requests are swept through every osdkeepalive seconds. With ack vs commit behaviour gone, abort_request() is really simple. This is based on a patch from Artur Molchanov . Tested-by: Artur Molchanov Signed-off-by: Ilya Dryomov Reviewed-by: Sage Weil --- include/linux/ceph/libceph.h | 2 ++ include/linux/ceph/osd_client.h | 1 + net/ceph/ceph_common.c | 15 +++++++++++++++ net/ceph/osd_client.c | 36 +++++++++++++++++++++++++++++++++++- 4 files changed, 53 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index 1816c5e26581..88cd5dc8e238 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -48,6 +48,7 @@ struct ceph_options { unsigned long mount_timeout; /* jiffies */ unsigned long osd_idle_ttl; /* jiffies */ unsigned long osd_keepalive_timeout; /* jiffies */ + unsigned long osd_request_timeout; /* jiffies */ /* * any type that can't be simply compared or doesn't need need @@ -68,6 +69,7 @@ struct ceph_options { #define CEPH_MOUNT_TIMEOUT_DEFAULT msecs_to_jiffies(60 * 1000) #define CEPH_OSD_KEEPALIVE_DEFAULT msecs_to_jiffies(5 * 1000) #define CEPH_OSD_IDLE_TTL_DEFAULT msecs_to_jiffies(60 * 1000) +#define CEPH_OSD_REQUEST_TIMEOUT_DEFAULT 0 /* no timeout */ #define CEPH_MONC_HUNT_INTERVAL msecs_to_jiffies(3 * 1000) #define CEPH_MONC_PING_INTERVAL msecs_to_jiffies(10 * 1000) diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 2ea0c282f3dc..c125b5d9e13c 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -189,6 +189,7 @@ struct ceph_osd_request { /* internal */ unsigned long r_stamp; /* jiffies, send or check time */ + unsigned long r_start_stamp; /* jiffies */ int r_attempts; struct ceph_eversion r_replay_version; /* aka reassert_version */ u32 r_last_force_resend; diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c index 464e88599b9d..108533859a53 100644 --- a/net/ceph/ceph_common.c +++ b/net/ceph/ceph_common.c @@ -230,6 +230,7 @@ enum { Opt_osdkeepalivetimeout, Opt_mount_timeout, Opt_osd_idle_ttl, + Opt_osd_request_timeout, Opt_last_int, /* int args above */ Opt_fsid, @@ -256,6 +257,7 @@ static match_table_t opt_tokens = { {Opt_osdkeepalivetimeout, "osdkeepalive=%d"}, {Opt_mount_timeout, "mount_timeout=%d"}, {Opt_osd_idle_ttl, "osd_idle_ttl=%d"}, + {Opt_osd_request_timeout, "osd_request_timeout=%d"}, /* int args above */ {Opt_fsid, "fsid=%s"}, {Opt_name, "name=%s"}, @@ -361,6 +363,7 @@ ceph_parse_options(char *options, const char *dev_name, opt->osd_keepalive_timeout = CEPH_OSD_KEEPALIVE_DEFAULT; opt->mount_timeout = CEPH_MOUNT_TIMEOUT_DEFAULT; opt->osd_idle_ttl = CEPH_OSD_IDLE_TTL_DEFAULT; + opt->osd_request_timeout = CEPH_OSD_REQUEST_TIMEOUT_DEFAULT; /* get mon ip(s) */ /* ip1[:port1][,ip2[:port2]...] */ @@ -473,6 +476,15 @@ ceph_parse_options(char *options, const char *dev_name, } opt->mount_timeout = msecs_to_jiffies(intval * 1000); break; + case Opt_osd_request_timeout: + /* 0 is "wait forever" (i.e. infinite timeout) */ + if (intval < 0 || intval > INT_MAX / 1000) { + pr_err("osd_request_timeout out of range\n"); + err = -EINVAL; + goto out; + } + opt->osd_request_timeout = msecs_to_jiffies(intval * 1000); + break; case Opt_share: opt->flags &= ~CEPH_OPT_NOSHARE; @@ -557,6 +569,9 @@ int ceph_print_client_options(struct seq_file *m, struct ceph_client *client) if (opt->osd_keepalive_timeout != CEPH_OSD_KEEPALIVE_DEFAULT) seq_printf(m, "osdkeepalivetimeout=%d,", jiffies_to_msecs(opt->osd_keepalive_timeout) / 1000); + if (opt->osd_request_timeout != CEPH_OSD_REQUEST_TIMEOUT_DEFAULT) + seq_printf(m, "osd_request_timeout=%d,", + jiffies_to_msecs(opt->osd_request_timeout) / 1000); /* drop redundant comma */ if (m->count != pos) diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index b65bbf9f45eb..e15ea9e4c495 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -1709,6 +1709,8 @@ static void account_request(struct ceph_osd_request *req) req->r_flags |= CEPH_OSD_FLAG_ONDISK; atomic_inc(&req->r_osdc->num_requests); + + req->r_start_stamp = jiffies; } static void submit_request(struct ceph_osd_request *req, bool wrlocked) @@ -1789,6 +1791,14 @@ static void cancel_request(struct ceph_osd_request *req) ceph_osdc_put_request(req); } +static void abort_request(struct ceph_osd_request *req, int err) +{ + dout("%s req %p tid %llu err %d\n", __func__, req, req->r_tid, err); + + cancel_map_check(req); + complete_request(req, err); +} + static void check_pool_dne(struct ceph_osd_request *req) { struct ceph_osd_client *osdc = req->r_osdc; @@ -2487,6 +2497,7 @@ static void handle_timeout(struct work_struct *work) container_of(work, struct ceph_osd_client, timeout_work.work); struct ceph_options *opts = osdc->client->options; unsigned long cutoff = jiffies - opts->osd_keepalive_timeout; + unsigned long expiry_cutoff = jiffies - opts->osd_request_timeout; LIST_HEAD(slow_osds); struct rb_node *n, *p; @@ -2502,15 +2513,23 @@ static void handle_timeout(struct work_struct *work) struct ceph_osd *osd = rb_entry(n, struct ceph_osd, o_node); bool found = false; - for (p = rb_first(&osd->o_requests); p; p = rb_next(p)) { + for (p = rb_first(&osd->o_requests); p; ) { struct ceph_osd_request *req = rb_entry(p, struct ceph_osd_request, r_node); + p = rb_next(p); /* abort_request() */ + if (time_before(req->r_stamp, cutoff)) { dout(" req %p tid %llu on osd%d is laggy\n", req, req->r_tid, osd->o_osd); found = true; } + if (opts->osd_request_timeout && + time_before(req->r_start_stamp, expiry_cutoff)) { + pr_err_ratelimited("tid %llu on osd%d timeout\n", + req->r_tid, osd->o_osd); + abort_request(req, -ETIMEDOUT); + } } for (p = rb_first(&osd->o_linger_requests); p; p = rb_next(p)) { struct ceph_osd_linger_request *lreq = @@ -2530,6 +2549,21 @@ static void handle_timeout(struct work_struct *work) list_move_tail(&osd->o_keepalive_item, &slow_osds); } + if (opts->osd_request_timeout) { + for (p = rb_first(&osdc->homeless_osd.o_requests); p; ) { + struct ceph_osd_request *req = + rb_entry(p, struct ceph_osd_request, r_node); + + p = rb_next(p); /* abort_request() */ + + if (time_before(req->r_start_stamp, expiry_cutoff)) { + pr_err_ratelimited("tid %llu on osd%d timeout\n", + req->r_tid, osdc->homeless_osd.o_osd); + abort_request(req, -ETIMEDOUT); + } + } + } + if (atomic_read(&osdc->num_homeless) || !list_empty(&slow_osds)) maybe_request_map(osdc); -- cgit v1.2.3 From c01228db4ba965986511a5b28c478bddd7e2726e Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 8 Mar 2017 17:48:34 +0100 Subject: Revert "scsi, block: fix duplicate bdi name registration crashes" This reverts commit 0dba1314d4f81115dce711292ec7981d17231064. It causes leaking of device numbers for SCSI when SCSI registers multiple gendisks for one request_queue in succession. It can be easily reproduced using Omar's script [1] on kernel with CONFIG_DEBUG_TEST_DRIVER_REMOVE. Furthermore the protection provided by this commit is not needed anymore as the problem it was fixing got also fixed by commit 165a5e22fafb "block: Move bdi_unregister() to del_gendisk()". [1]: http://marc.info/?l=linux-block&m=148554717109098&w=2 Signed-off-by: Jan Kara Acked-by: Dan Williams Tested-by: Omar Sandoval Signed-off-by: Jens Axboe --- block/blk-core.c | 2 -- block/genhd.c | 21 --------------------- drivers/scsi/sd.c | 41 ++++++++--------------------------------- include/linux/blkdev.h | 1 - include/linux/genhd.h | 8 -------- 5 files changed, 8 insertions(+), 65 deletions(-) (limited to 'include/linux') diff --git a/block/blk-core.c b/block/blk-core.c index 1086dac8724c..a76895c9776d 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -578,8 +578,6 @@ void blk_cleanup_queue(struct request_queue *q) q->queue_lock = &q->__queue_lock; spin_unlock_irq(lock); - put_disk_devt(q->disk_devt); - /* @q is and will stay empty, shutdown and put */ blk_put_queue(q); } diff --git a/block/genhd.c b/block/genhd.c index 94f323842b52..a9c516a8b37d 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -572,20 +572,6 @@ exit: disk_part_iter_exit(&piter); } -void put_disk_devt(struct disk_devt *disk_devt) -{ - if (disk_devt && atomic_dec_and_test(&disk_devt->count)) - disk_devt->release(disk_devt); -} -EXPORT_SYMBOL(put_disk_devt); - -void get_disk_devt(struct disk_devt *disk_devt) -{ - if (disk_devt) - atomic_inc(&disk_devt->count); -} -EXPORT_SYMBOL(get_disk_devt); - /** * device_add_disk - add partitioning information to kernel list * @parent: parent device for the disk @@ -626,13 +612,6 @@ void device_add_disk(struct device *parent, struct gendisk *disk) disk_alloc_events(disk); - /* - * Take a reference on the devt and assign it to queue since it - * must not be reallocated while the bdi is registered - */ - disk->queue->disk_devt = disk->disk_devt; - get_disk_devt(disk->disk_devt); - /* Register BDI before referencing it from bdev */ bdi = disk->queue->backing_dev_info; bdi_register_owner(bdi, disk_to_dev(disk)); diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index c7839f6c35cc..d277e8620e3e 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -3075,23 +3075,6 @@ static void sd_probe_async(void *data, async_cookie_t cookie) put_device(&sdkp->dev); } -struct sd_devt { - int idx; - struct disk_devt disk_devt; -}; - -static void sd_devt_release(struct disk_devt *disk_devt) -{ - struct sd_devt *sd_devt = container_of(disk_devt, struct sd_devt, - disk_devt); - - spin_lock(&sd_index_lock); - ida_remove(&sd_index_ida, sd_devt->idx); - spin_unlock(&sd_index_lock); - - kfree(sd_devt); -} - /** * sd_probe - called during driver initialization and whenever a * new scsi device is attached to the system. It is called once @@ -3113,7 +3096,6 @@ static void sd_devt_release(struct disk_devt *disk_devt) static int sd_probe(struct device *dev) { struct scsi_device *sdp = to_scsi_device(dev); - struct sd_devt *sd_devt; struct scsi_disk *sdkp; struct gendisk *gd; int index; @@ -3139,13 +3121,9 @@ static int sd_probe(struct device *dev) if (!sdkp) goto out; - sd_devt = kzalloc(sizeof(*sd_devt), GFP_KERNEL); - if (!sd_devt) - goto out_free; - gd = alloc_disk(SD_MINORS); if (!gd) - goto out_free_devt; + goto out_free; do { if (!ida_pre_get(&sd_index_ida, GFP_KERNEL)) @@ -3161,11 +3139,6 @@ static int sd_probe(struct device *dev) goto out_put; } - atomic_set(&sd_devt->disk_devt.count, 1); - sd_devt->disk_devt.release = sd_devt_release; - sd_devt->idx = index; - gd->disk_devt = &sd_devt->disk_devt; - error = sd_format_disk_name("sd", index, gd->disk_name, DISK_NAME_LEN); if (error) { sdev_printk(KERN_WARNING, sdp, "SCSI disk (sd) name length exceeded.\n"); @@ -3205,12 +3178,11 @@ static int sd_probe(struct device *dev) return 0; out_free_index: - put_disk_devt(&sd_devt->disk_devt); - sd_devt = NULL; + spin_lock(&sd_index_lock); + ida_remove(&sd_index_ida, index); + spin_unlock(&sd_index_lock); out_put: put_disk(gd); - out_free_devt: - kfree(sd_devt); out_free: kfree(sdkp); out: @@ -3271,7 +3243,10 @@ static void scsi_disk_release(struct device *dev) struct scsi_disk *sdkp = to_scsi_disk(dev); struct gendisk *disk = sdkp->disk; - put_disk_devt(disk->disk_devt); + spin_lock(&sd_index_lock); + ida_remove(&sd_index_ida, sdkp->index); + spin_unlock(&sd_index_lock); + disk->private_data = NULL; put_disk(disk); put_device(&sdkp->device->sdev_gendev); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 796016e63c1d..5a7da607ca04 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -435,7 +435,6 @@ struct request_queue { struct delayed_work delay_work; struct backing_dev_info *backing_dev_info; - struct disk_devt *disk_devt; /* * The queue owner gets to use this for whatever they like. diff --git a/include/linux/genhd.h b/include/linux/genhd.h index a999d281a2f1..76f39754e7b0 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -167,13 +167,6 @@ struct blk_integrity { }; #endif /* CONFIG_BLK_DEV_INTEGRITY */ -struct disk_devt { - atomic_t count; - void (*release)(struct disk_devt *disk_devt); -}; - -void put_disk_devt(struct disk_devt *disk_devt); -void get_disk_devt(struct disk_devt *disk_devt); struct gendisk { /* major, first_minor and minors are input parameters only, @@ -183,7 +176,6 @@ struct gendisk { int first_minor; int minors; /* maximum number of minors, =1 for * disks that can't be partitioned. */ - struct disk_devt *disk_devt; char disk_name[DISK_NAME_LEN]; /* name of major driver */ char *(*devnode)(struct gendisk *gd, umode_t *mode); -- cgit v1.2.3 From bd0f9b356d00aa241ced36fb075a07041c28d3b8 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 7 Mar 2017 15:33:14 -0800 Subject: sched/headers: fix up header file dependency on The scheduler header file split and cleanups ended up exposing a few nasty header file dependencies, and in particular it showed how we in ended up depending on "signal_pending()", which now comes from . That's a very subtle and annoying dependency, which already caused a semantic merge conflict (see commit e58bc927835a "Pull overlayfs updates from Miklos Szeredi", which added that fixup in the merge commit). It turns out that we can avoid this dependency _and_ improve code generation by moving the guts of the fairly nasty helper #define __wait_event_interruptible_locked() to out-of-line code. The code that includes the signal_pending() check is all in the slow-path where we actually go to sleep waiting for the event anyway, so using a helper function is the right thing to do. Using a helper function is also what we already did for the non-locked versions, see the "__wait_event*()" macros and the "prepare_to_wait*()" set of helper functions. We might want to try to unify all these macro games, we have a _lot_ of subtly different wait-event loops. But this is the minimal patch to fix the annoying header dependency. Acked-by: Ingo Molnar Signed-off-by: Linus Torvalds --- include/linux/wait.h | 31 ++++++++++--------------------- kernel/sched/wait.c | 39 +++++++++++++++++++++++++++++++++++++++ 2 files changed, 49 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/wait.h b/include/linux/wait.h index aacb1282d19a..db076ca7f11d 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -620,30 +620,19 @@ do { \ __ret; \ }) +extern int do_wait_intr(wait_queue_head_t *, wait_queue_t *); +extern int do_wait_intr_irq(wait_queue_head_t *, wait_queue_t *); -#define __wait_event_interruptible_locked(wq, condition, exclusive, irq) \ +#define __wait_event_interruptible_locked(wq, condition, exclusive, fn) \ ({ \ - int __ret = 0; \ + int __ret; \ DEFINE_WAIT(__wait); \ if (exclusive) \ __wait.flags |= WQ_FLAG_EXCLUSIVE; \ do { \ - if (likely(list_empty(&__wait.task_list))) \ - __add_wait_queue_tail(&(wq), &__wait); \ - set_current_state(TASK_INTERRUPTIBLE); \ - if (signal_pending(current)) { \ - __ret = -ERESTARTSYS; \ + __ret = fn(&(wq), &__wait); \ + if (__ret) \ break; \ - } \ - if (irq) \ - spin_unlock_irq(&(wq).lock); \ - else \ - spin_unlock(&(wq).lock); \ - schedule(); \ - if (irq) \ - spin_lock_irq(&(wq).lock); \ - else \ - spin_lock(&(wq).lock); \ } while (!(condition)); \ __remove_wait_queue(&(wq), &__wait); \ __set_current_state(TASK_RUNNING); \ @@ -676,7 +665,7 @@ do { \ */ #define wait_event_interruptible_locked(wq, condition) \ ((condition) \ - ? 0 : __wait_event_interruptible_locked(wq, condition, 0, 0)) + ? 0 : __wait_event_interruptible_locked(wq, condition, 0, do_wait_intr)) /** * wait_event_interruptible_locked_irq - sleep until a condition gets true @@ -703,7 +692,7 @@ do { \ */ #define wait_event_interruptible_locked_irq(wq, condition) \ ((condition) \ - ? 0 : __wait_event_interruptible_locked(wq, condition, 0, 1)) + ? 0 : __wait_event_interruptible_locked(wq, condition, 0, do_wait_intr_irq)) /** * wait_event_interruptible_exclusive_locked - sleep exclusively until a condition gets true @@ -734,7 +723,7 @@ do { \ */ #define wait_event_interruptible_exclusive_locked(wq, condition) \ ((condition) \ - ? 0 : __wait_event_interruptible_locked(wq, condition, 1, 0)) + ? 0 : __wait_event_interruptible_locked(wq, condition, 1, do_wait_intr)) /** * wait_event_interruptible_exclusive_locked_irq - sleep until a condition gets true @@ -765,7 +754,7 @@ do { \ */ #define wait_event_interruptible_exclusive_locked_irq(wq, condition) \ ((condition) \ - ? 0 : __wait_event_interruptible_locked(wq, condition, 1, 1)) + ? 0 : __wait_event_interruptible_locked(wq, condition, 1, do_wait_intr_irq)) #define __wait_event_killable(wq, condition) \ diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c index 4d2ea6f25568..b8c84c6dee64 100644 --- a/kernel/sched/wait.c +++ b/kernel/sched/wait.c @@ -242,6 +242,45 @@ long prepare_to_wait_event(wait_queue_head_t *q, wait_queue_t *wait, int state) } EXPORT_SYMBOL(prepare_to_wait_event); +/* + * Note! These two wait functions are entered with the + * wait-queue lock held (and interrupts off in the _irq + * case), so there is no race with testing the wakeup + * condition in the caller before they add the wait + * entry to the wake queue. + */ +int do_wait_intr(wait_queue_head_t *wq, wait_queue_t *wait) +{ + if (likely(list_empty(&wait->task_list))) + __add_wait_queue_tail(wq, wait); + + set_current_state(TASK_INTERRUPTIBLE); + if (signal_pending(current)) + return -ERESTARTSYS; + + spin_unlock(&wq->lock); + schedule(); + spin_lock(&wq->lock); + return 0; +} +EXPORT_SYMBOL(do_wait_intr); + +int do_wait_intr_irq(wait_queue_head_t *wq, wait_queue_t *wait) +{ + if (likely(list_empty(&wait->task_list))) + __add_wait_queue_tail(wq, wait); + + set_current_state(TASK_INTERRUPTIBLE); + if (signal_pending(current)) + return -ERESTARTSYS; + + spin_unlock_irq(&wq->lock); + schedule(); + spin_lock_irq(&wq->lock); + return 0; +} +EXPORT_SYMBOL(do_wait_intr_irq); + /** * finish_wait - clean up after waiting in a queue * @q: waitqueue waited on -- cgit v1.2.3 From 505a60e225606fbd3d2eadc31ff793d939ba66f1 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Thu, 9 Mar 2017 17:24:03 +0300 Subject: asm-generic: introduce 5level-fixup.h We are going to switch core MM to 5-level paging abstraction. This is preparation step which adds As with 4level-fixup.h, the new header allows quickly make all architectures compatible with 5-level paging in core MM. In long run we would like to switch architectures to properly folded p4d level by using , but it requires more changes to arch-specific code. Signed-off-by: Kirill A. Shutemov Acked-by: Michal Hocko Signed-off-by: Linus Torvalds --- include/asm-generic/4level-fixup.h | 3 ++- include/asm-generic/5level-fixup.h | 41 ++++++++++++++++++++++++++++++++++++++ include/linux/mm.h | 3 +++ 3 files changed, 46 insertions(+), 1 deletion(-) create mode 100644 include/asm-generic/5level-fixup.h (limited to 'include/linux') diff --git a/include/asm-generic/4level-fixup.h b/include/asm-generic/4level-fixup.h index 5bdab6bffd23..928fd66b1271 100644 --- a/include/asm-generic/4level-fixup.h +++ b/include/asm-generic/4level-fixup.h @@ -15,7 +15,6 @@ ((unlikely(pgd_none(*(pud))) && __pmd_alloc(mm, pud, address))? \ NULL: pmd_offset(pud, address)) -#define pud_alloc(mm, pgd, address) (pgd) #define pud_offset(pgd, start) (pgd) #define pud_none(pud) 0 #define pud_bad(pud) 0 @@ -35,4 +34,6 @@ #undef pud_addr_end #define pud_addr_end(addr, end) (end) +#include + #endif diff --git a/include/asm-generic/5level-fixup.h b/include/asm-generic/5level-fixup.h new file mode 100644 index 000000000000..b5ca82dc4175 --- /dev/null +++ b/include/asm-generic/5level-fixup.h @@ -0,0 +1,41 @@ +#ifndef _5LEVEL_FIXUP_H +#define _5LEVEL_FIXUP_H + +#define __ARCH_HAS_5LEVEL_HACK +#define __PAGETABLE_P4D_FOLDED + +#define P4D_SHIFT PGDIR_SHIFT +#define P4D_SIZE PGDIR_SIZE +#define P4D_MASK PGDIR_MASK +#define PTRS_PER_P4D 1 + +#define p4d_t pgd_t + +#define pud_alloc(mm, p4d, address) \ + ((unlikely(pgd_none(*(p4d))) && __pud_alloc(mm, p4d, address)) ? \ + NULL : pud_offset(p4d, address)) + +#define p4d_alloc(mm, pgd, address) (pgd) +#define p4d_offset(pgd, start) (pgd) +#define p4d_none(p4d) 0 +#define p4d_bad(p4d) 0 +#define p4d_present(p4d) 1 +#define p4d_ERROR(p4d) do { } while (0) +#define p4d_clear(p4d) pgd_clear(p4d) +#define p4d_val(p4d) pgd_val(p4d) +#define p4d_populate(mm, p4d, pud) pgd_populate(mm, p4d, pud) +#define p4d_page(p4d) pgd_page(p4d) +#define p4d_page_vaddr(p4d) pgd_page_vaddr(p4d) + +#define __p4d(x) __pgd(x) +#define set_p4d(p4dp, p4d) set_pgd(p4dp, p4d) + +#undef p4d_free_tlb +#define p4d_free_tlb(tlb, x, addr) do { } while (0) +#define p4d_free(mm, x) do { } while (0) +#define __p4d_free_tlb(tlb, x, addr) do { } while (0) + +#undef p4d_addr_end +#define p4d_addr_end(addr, end) (end) + +#endif diff --git a/include/linux/mm.h b/include/linux/mm.h index 0d65dd72c0f4..be1fe264eb37 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1619,11 +1619,14 @@ int __pte_alloc_kernel(pmd_t *pmd, unsigned long address); * Remove it when 4level-fixup.h has been removed. */ #if defined(CONFIG_MMU) && !defined(__ARCH_HAS_4LEVEL_HACK) + +#ifndef __ARCH_HAS_5LEVEL_HACK static inline pud_t *pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address) { return (unlikely(pgd_none(*pgd)) && __pud_alloc(mm, pgd, address))? NULL: pud_offset(pgd, address); } +#endif /* !__ARCH_HAS_5LEVEL_HACK */ static inline pmd_t *pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address) { -- cgit v1.2.3 From c2febafc67734a62196c1b9dfba926412d4077ba Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Thu, 9 Mar 2017 17:24:07 +0300 Subject: mm: convert generic code to 5-level paging Convert all non-architecture-specific code to 5-level paging. It's mostly mechanical adding handling one more page table level in places where we deal with pud_t. Signed-off-by: Kirill A. Shutemov Acked-by: Michal Hocko Signed-off-by: Linus Torvalds --- drivers/misc/sgi-gru/grufault.c | 9 +- fs/userfaultfd.c | 6 +- include/asm-generic/pgtable.h | 48 +++++++++- include/linux/hugetlb.h | 5 +- include/linux/kasan.h | 1 + include/linux/mm.h | 31 ++++-- lib/ioremap.c | 39 +++++++- mm/gup.c | 46 +++++++-- mm/huge_memory.c | 7 +- mm/hugetlb.c | 29 +++--- mm/kasan/kasan_init.c | 44 ++++++++- mm/memory.c | 207 +++++++++++++++++++++++++++++++++------- mm/mlock.c | 1 + mm/mprotect.c | 26 ++++- mm/mremap.c | 13 ++- mm/page_vma_mapped.c | 6 +- mm/pagewalk.c | 32 ++++++- mm/pgtable-generic.c | 6 ++ mm/rmap.c | 7 +- mm/sparse-vmemmap.c | 22 ++++- mm/swapfile.c | 26 ++++- mm/userfaultfd.c | 23 +++-- mm/vmalloc.c | 81 ++++++++++++---- 23 files changed, 595 insertions(+), 120 deletions(-) (limited to 'include/linux') diff --git a/drivers/misc/sgi-gru/grufault.c b/drivers/misc/sgi-gru/grufault.c index 6fb773dbcd0c..93be82fc338a 100644 --- a/drivers/misc/sgi-gru/grufault.c +++ b/drivers/misc/sgi-gru/grufault.c @@ -219,15 +219,20 @@ static int atomic_pte_lookup(struct vm_area_struct *vma, unsigned long vaddr, int write, unsigned long *paddr, int *pageshift) { pgd_t *pgdp; - pmd_t *pmdp; + p4d_t *p4dp; pud_t *pudp; + pmd_t *pmdp; pte_t pte; pgdp = pgd_offset(vma->vm_mm, vaddr); if (unlikely(pgd_none(*pgdp))) goto err; - pudp = pud_offset(pgdp, vaddr); + p4dp = p4d_offset(pgdp, vaddr); + if (unlikely(p4d_none(*p4dp))) + goto err; + + pudp = pud_offset(p4dp, vaddr); if (unlikely(pud_none(*pudp))) goto err; diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 973607df579d..02ce3944d0f5 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -267,6 +267,7 @@ static inline bool userfaultfd_must_wait(struct userfaultfd_ctx *ctx, { struct mm_struct *mm = ctx->mm; pgd_t *pgd; + p4d_t *p4d; pud_t *pud; pmd_t *pmd, _pmd; pte_t *pte; @@ -277,7 +278,10 @@ static inline bool userfaultfd_must_wait(struct userfaultfd_ctx *ctx, pgd = pgd_offset(mm, address); if (!pgd_present(*pgd)) goto out; - pud = pud_offset(pgd, address); + p4d = p4d_offset(pgd, address); + if (!p4d_present(*p4d)) + goto out; + pud = pud_offset(p4d, address); if (!pud_present(*pud)) goto out; pmd = pmd_offset(pud, address); diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h index f4ca23b158b3..1fad160f35de 100644 --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -10,9 +10,9 @@ #include #include -#if 4 - defined(__PAGETABLE_PUD_FOLDED) - defined(__PAGETABLE_PMD_FOLDED) != \ - CONFIG_PGTABLE_LEVELS -#error CONFIG_PGTABLE_LEVELS is not consistent with __PAGETABLE_{PUD,PMD}_FOLDED +#if 5 - defined(__PAGETABLE_P4D_FOLDED) - defined(__PAGETABLE_PUD_FOLDED) - \ + defined(__PAGETABLE_PMD_FOLDED) != CONFIG_PGTABLE_LEVELS +#error CONFIG_PGTABLE_LEVELS is not consistent with __PAGETABLE_{P4D,PUD,PMD}_FOLDED #endif /* @@ -424,6 +424,13 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot) (__boundary - 1 < (end) - 1)? __boundary: (end); \ }) +#ifndef p4d_addr_end +#define p4d_addr_end(addr, end) \ +({ unsigned long __boundary = ((addr) + P4D_SIZE) & P4D_MASK; \ + (__boundary - 1 < (end) - 1)? __boundary: (end); \ +}) +#endif + #ifndef pud_addr_end #define pud_addr_end(addr, end) \ ({ unsigned long __boundary = ((addr) + PUD_SIZE) & PUD_MASK; \ @@ -444,6 +451,7 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot) * Do the tests inline, but report and clear the bad entry in mm/memory.c. */ void pgd_clear_bad(pgd_t *); +void p4d_clear_bad(p4d_t *); void pud_clear_bad(pud_t *); void pmd_clear_bad(pmd_t *); @@ -458,6 +466,17 @@ static inline int pgd_none_or_clear_bad(pgd_t *pgd) return 0; } +static inline int p4d_none_or_clear_bad(p4d_t *p4d) +{ + if (p4d_none(*p4d)) + return 1; + if (unlikely(p4d_bad(*p4d))) { + p4d_clear_bad(p4d); + return 1; + } + return 0; +} + static inline int pud_none_or_clear_bad(pud_t *pud) { if (pud_none(*pud)) @@ -844,11 +863,30 @@ static inline int pmd_protnone(pmd_t pmd) #endif /* CONFIG_MMU */ #ifdef CONFIG_HAVE_ARCH_HUGE_VMAP + +#ifndef __PAGETABLE_P4D_FOLDED +int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot); +int p4d_clear_huge(p4d_t *p4d); +#else +static inline int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot) +{ + return 0; +} +static inline int p4d_clear_huge(p4d_t *p4d) +{ + return 0; +} +#endif /* !__PAGETABLE_P4D_FOLDED */ + int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot); int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot); int pud_clear_huge(pud_t *pud); int pmd_clear_huge(pmd_t *pmd); #else /* !CONFIG_HAVE_ARCH_HUGE_VMAP */ +static inline int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot) +{ + return 0; +} static inline int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot) { return 0; @@ -857,6 +895,10 @@ static inline int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot) { return 0; } +static inline int p4d_clear_huge(p4d_t *p4d) +{ + return 0; +} static inline int pud_clear_huge(pud_t *pud) { return 0; diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 503099d8aada..b857fc8cc2ec 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -122,7 +122,7 @@ struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address, struct page *follow_huge_pud(struct mm_struct *mm, unsigned long address, pud_t *pud, int flags); int pmd_huge(pmd_t pmd); -int pud_huge(pud_t pmd); +int pud_huge(pud_t pud); unsigned long hugetlb_change_protection(struct vm_area_struct *vma, unsigned long address, unsigned long end, pgprot_t newprot); @@ -197,6 +197,9 @@ static inline void __unmap_hugepage_range(struct mmu_gather *tlb, #ifndef pgd_huge #define pgd_huge(x) 0 #endif +#ifndef p4d_huge +#define p4d_huge(x) 0 +#endif #ifndef pgd_write static inline int pgd_write(pgd_t pgd) diff --git a/include/linux/kasan.h b/include/linux/kasan.h index ceb3fe78a0d3..1c823bef4c15 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -18,6 +18,7 @@ extern unsigned char kasan_zero_page[PAGE_SIZE]; extern pte_t kasan_zero_pte[PTRS_PER_PTE]; extern pmd_t kasan_zero_pmd[PTRS_PER_PMD]; extern pud_t kasan_zero_pud[PTRS_PER_PUD]; +extern p4d_t kasan_zero_p4d[PTRS_PER_P4D]; void kasan_populate_zero_shadow(const void *shadow_start, const void *shadow_end); diff --git a/include/linux/mm.h b/include/linux/mm.h index be1fe264eb37..5f01c88f0800 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1560,14 +1560,24 @@ static inline pte_t *get_locked_pte(struct mm_struct *mm, unsigned long addr, return ptep; } +#ifdef __PAGETABLE_P4D_FOLDED +static inline int __p4d_alloc(struct mm_struct *mm, pgd_t *pgd, + unsigned long address) +{ + return 0; +} +#else +int __p4d_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address); +#endif + #ifdef __PAGETABLE_PUD_FOLDED -static inline int __pud_alloc(struct mm_struct *mm, pgd_t *pgd, +static inline int __pud_alloc(struct mm_struct *mm, p4d_t *p4d, unsigned long address) { return 0; } #else -int __pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address); +int __pud_alloc(struct mm_struct *mm, p4d_t *p4d, unsigned long address); #endif #if defined(__PAGETABLE_PMD_FOLDED) || !defined(CONFIG_MMU) @@ -1621,10 +1631,18 @@ int __pte_alloc_kernel(pmd_t *pmd, unsigned long address); #if defined(CONFIG_MMU) && !defined(__ARCH_HAS_4LEVEL_HACK) #ifndef __ARCH_HAS_5LEVEL_HACK -static inline pud_t *pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address) +static inline p4d_t *p4d_alloc(struct mm_struct *mm, pgd_t *pgd, + unsigned long address) +{ + return (unlikely(pgd_none(*pgd)) && __p4d_alloc(mm, pgd, address)) ? + NULL : p4d_offset(pgd, address); +} + +static inline pud_t *pud_alloc(struct mm_struct *mm, p4d_t *p4d, + unsigned long address) { - return (unlikely(pgd_none(*pgd)) && __pud_alloc(mm, pgd, address))? - NULL: pud_offset(pgd, address); + return (unlikely(p4d_none(*p4d)) && __pud_alloc(mm, p4d, address)) ? + NULL : pud_offset(p4d, address); } #endif /* !__ARCH_HAS_5LEVEL_HACK */ @@ -2388,7 +2406,8 @@ void sparse_mem_maps_populate_node(struct page **map_map, struct page *sparse_mem_map_populate(unsigned long pnum, int nid); pgd_t *vmemmap_pgd_populate(unsigned long addr, int node); -pud_t *vmemmap_pud_populate(pgd_t *pgd, unsigned long addr, int node); +p4d_t *vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node); +pud_t *vmemmap_pud_populate(p4d_t *p4d, unsigned long addr, int node); pmd_t *vmemmap_pmd_populate(pud_t *pud, unsigned long addr, int node); pte_t *vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node); void *vmemmap_alloc_block(unsigned long size, int node); diff --git a/lib/ioremap.c b/lib/ioremap.c index a3e14ce92a56..4bb30206b942 100644 --- a/lib/ioremap.c +++ b/lib/ioremap.c @@ -14,6 +14,7 @@ #include #ifdef CONFIG_HAVE_ARCH_HUGE_VMAP +static int __read_mostly ioremap_p4d_capable; static int __read_mostly ioremap_pud_capable; static int __read_mostly ioremap_pmd_capable; static int __read_mostly ioremap_huge_disabled; @@ -35,6 +36,11 @@ void __init ioremap_huge_init(void) } } +static inline int ioremap_p4d_enabled(void) +{ + return ioremap_p4d_capable; +} + static inline int ioremap_pud_enabled(void) { return ioremap_pud_capable; @@ -46,6 +52,7 @@ static inline int ioremap_pmd_enabled(void) } #else /* !CONFIG_HAVE_ARCH_HUGE_VMAP */ +static inline int ioremap_p4d_enabled(void) { return 0; } static inline int ioremap_pud_enabled(void) { return 0; } static inline int ioremap_pmd_enabled(void) { return 0; } #endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */ @@ -94,14 +101,14 @@ static inline int ioremap_pmd_range(pud_t *pud, unsigned long addr, return 0; } -static inline int ioremap_pud_range(pgd_t *pgd, unsigned long addr, +static inline int ioremap_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end, phys_addr_t phys_addr, pgprot_t prot) { pud_t *pud; unsigned long next; phys_addr -= addr; - pud = pud_alloc(&init_mm, pgd, addr); + pud = pud_alloc(&init_mm, p4d, addr); if (!pud) return -ENOMEM; do { @@ -120,6 +127,32 @@ static inline int ioremap_pud_range(pgd_t *pgd, unsigned long addr, return 0; } +static inline int ioremap_p4d_range(pgd_t *pgd, unsigned long addr, + unsigned long end, phys_addr_t phys_addr, pgprot_t prot) +{ + p4d_t *p4d; + unsigned long next; + + phys_addr -= addr; + p4d = p4d_alloc(&init_mm, pgd, addr); + if (!p4d) + return -ENOMEM; + do { + next = p4d_addr_end(addr, end); + + if (ioremap_p4d_enabled() && + ((next - addr) == P4D_SIZE) && + IS_ALIGNED(phys_addr + addr, P4D_SIZE)) { + if (p4d_set_huge(p4d, phys_addr + addr, prot)) + continue; + } + + if (ioremap_pud_range(p4d, addr, next, phys_addr + addr, prot)) + return -ENOMEM; + } while (p4d++, addr = next, addr != end); + return 0; +} + int ioremap_page_range(unsigned long addr, unsigned long end, phys_addr_t phys_addr, pgprot_t prot) { @@ -135,7 +168,7 @@ int ioremap_page_range(unsigned long addr, pgd = pgd_offset_k(addr); do { next = pgd_addr_end(addr, end); - err = ioremap_pud_range(pgd, addr, next, phys_addr+addr, prot); + err = ioremap_p4d_range(pgd, addr, next, phys_addr+addr, prot); if (err) break; } while (pgd++, addr = next, addr != end); diff --git a/mm/gup.c b/mm/gup.c index 9c047e951aa3..c74bad1bf6e8 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -226,6 +226,7 @@ struct page *follow_page_mask(struct vm_area_struct *vma, unsigned int *page_mask) { pgd_t *pgd; + p4d_t *p4d; pud_t *pud; pmd_t *pmd; spinlock_t *ptl; @@ -243,8 +244,13 @@ struct page *follow_page_mask(struct vm_area_struct *vma, pgd = pgd_offset(mm, address); if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd))) return no_page_table(vma, flags); - - pud = pud_offset(pgd, address); + p4d = p4d_offset(pgd, address); + if (p4d_none(*p4d)) + return no_page_table(vma, flags); + BUILD_BUG_ON(p4d_huge(*p4d)); + if (unlikely(p4d_bad(*p4d))) + return no_page_table(vma, flags); + pud = pud_offset(p4d, address); if (pud_none(*pud)) return no_page_table(vma, flags); if (pud_huge(*pud) && vma->vm_flags & VM_HUGETLB) { @@ -325,6 +331,7 @@ static int get_gate_page(struct mm_struct *mm, unsigned long address, struct page **page) { pgd_t *pgd; + p4d_t *p4d; pud_t *pud; pmd_t *pmd; pte_t *pte; @@ -338,7 +345,9 @@ static int get_gate_page(struct mm_struct *mm, unsigned long address, else pgd = pgd_offset_gate(mm, address); BUG_ON(pgd_none(*pgd)); - pud = pud_offset(pgd, address); + p4d = p4d_offset(pgd, address); + BUG_ON(p4d_none(*p4d)); + pud = pud_offset(p4d, address); BUG_ON(pud_none(*pud)); pmd = pmd_offset(pud, address); if (pmd_none(*pmd)) @@ -1400,13 +1409,13 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end, return 1; } -static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end, +static int gup_pud_range(p4d_t p4d, unsigned long addr, unsigned long end, int write, struct page **pages, int *nr) { unsigned long next; pud_t *pudp; - pudp = pud_offset(&pgd, addr); + pudp = pud_offset(&p4d, addr); do { pud_t pud = READ_ONCE(*pudp); @@ -1428,6 +1437,31 @@ static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end, return 1; } +static int gup_p4d_range(pgd_t pgd, unsigned long addr, unsigned long end, + int write, struct page **pages, int *nr) +{ + unsigned long next; + p4d_t *p4dp; + + p4dp = p4d_offset(&pgd, addr); + do { + p4d_t p4d = READ_ONCE(*p4dp); + + next = p4d_addr_end(addr, end); + if (p4d_none(p4d)) + return 0; + BUILD_BUG_ON(p4d_huge(p4d)); + if (unlikely(is_hugepd(__hugepd(p4d_val(p4d))))) { + if (!gup_huge_pd(__hugepd(p4d_val(p4d)), addr, + P4D_SHIFT, next, write, pages, nr)) + return 0; + } else if (!gup_p4d_range(p4d, addr, next, write, pages, nr)) + return 0; + } while (p4dp++, addr = next, addr != end); + + return 1; +} + /* * Like get_user_pages_fast() except it's IRQ-safe in that it won't fall back to * the regular GUP. It will only return non-negative values. @@ -1478,7 +1512,7 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write, if (!gup_huge_pd(__hugepd(pgd_val(pgd)), addr, PGDIR_SHIFT, next, write, pages, &nr)) break; - } else if (!gup_pud_range(pgd, addr, next, write, pages, &nr)) + } else if (!gup_p4d_range(pgd, addr, next, write, pages, &nr)) break; } while (pgdp++, addr = next, addr != end); local_irq_restore(flags); diff --git a/mm/huge_memory.c b/mm/huge_memory.c index d36b2af4d1bf..e4766de25709 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2048,6 +2048,7 @@ void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address, bool freeze, struct page *page) { pgd_t *pgd; + p4d_t *p4d; pud_t *pud; pmd_t *pmd; @@ -2055,7 +2056,11 @@ void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address, if (!pgd_present(*pgd)) return; - pud = pud_offset(pgd, address); + p4d = p4d_offset(pgd, address); + if (!p4d_present(*p4d)) + return; + + pud = pud_offset(p4d, address); if (!pud_present(*pud)) return; diff --git a/mm/hugetlb.c b/mm/hugetlb.c index a7aa811b7d14..3d0aab9ee80d 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -4555,7 +4555,8 @@ out: int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep) { pgd_t *pgd = pgd_offset(mm, *addr); - pud_t *pud = pud_offset(pgd, *addr); + p4d_t *p4d = p4d_offset(pgd, *addr); + pud_t *pud = pud_offset(p4d, *addr); BUG_ON(page_count(virt_to_page(ptep)) == 0); if (page_count(virt_to_page(ptep)) == 1) @@ -4586,11 +4587,13 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz) { pgd_t *pgd; + p4d_t *p4d; pud_t *pud; pte_t *pte = NULL; pgd = pgd_offset(mm, addr); - pud = pud_alloc(mm, pgd, addr); + p4d = p4d_offset(pgd, addr); + pud = pud_alloc(mm, p4d, addr); if (pud) { if (sz == PUD_SIZE) { pte = (pte_t *)pud; @@ -4610,18 +4613,22 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr) { pgd_t *pgd; + p4d_t *p4d; pud_t *pud; - pmd_t *pmd = NULL; + pmd_t *pmd; pgd = pgd_offset(mm, addr); - if (pgd_present(*pgd)) { - pud = pud_offset(pgd, addr); - if (pud_present(*pud)) { - if (pud_huge(*pud)) - return (pte_t *)pud; - pmd = pmd_offset(pud, addr); - } - } + if (!pgd_present(*pgd)) + return NULL; + p4d = p4d_offset(pgd, addr); + if (!p4d_present(*p4d)) + return NULL; + pud = pud_offset(p4d, addr); + if (!pud_present(*pud)) + return NULL; + if (pud_huge(*pud)) + return (pte_t *)pud; + pmd = pmd_offset(pud, addr); return (pte_t *) pmd; } diff --git a/mm/kasan/kasan_init.c b/mm/kasan/kasan_init.c index 31238dad85fb..b96a5f773d88 100644 --- a/mm/kasan/kasan_init.c +++ b/mm/kasan/kasan_init.c @@ -30,6 +30,9 @@ */ unsigned char kasan_zero_page[PAGE_SIZE] __page_aligned_bss; +#if CONFIG_PGTABLE_LEVELS > 4 +p4d_t kasan_zero_p4d[PTRS_PER_P4D] __page_aligned_bss; +#endif #if CONFIG_PGTABLE_LEVELS > 3 pud_t kasan_zero_pud[PTRS_PER_PUD] __page_aligned_bss; #endif @@ -82,10 +85,10 @@ static void __init zero_pmd_populate(pud_t *pud, unsigned long addr, } while (pmd++, addr = next, addr != end); } -static void __init zero_pud_populate(pgd_t *pgd, unsigned long addr, +static void __init zero_pud_populate(p4d_t *p4d, unsigned long addr, unsigned long end) { - pud_t *pud = pud_offset(pgd, addr); + pud_t *pud = pud_offset(p4d, addr); unsigned long next; do { @@ -107,6 +110,23 @@ static void __init zero_pud_populate(pgd_t *pgd, unsigned long addr, } while (pud++, addr = next, addr != end); } +static void __init zero_p4d_populate(pgd_t *pgd, unsigned long addr, + unsigned long end) +{ + p4d_t *p4d = p4d_offset(pgd, addr); + unsigned long next; + + do { + next = p4d_addr_end(addr, end); + + if (p4d_none(*p4d)) { + p4d_populate(&init_mm, p4d, + early_alloc(PAGE_SIZE, NUMA_NO_NODE)); + } + zero_pud_populate(p4d, addr, next); + } while (p4d++, addr = next, addr != end); +} + /** * kasan_populate_zero_shadow - populate shadow memory region with * kasan_zero_page @@ -125,6 +145,7 @@ void __init kasan_populate_zero_shadow(const void *shadow_start, next = pgd_addr_end(addr, end); if (IS_ALIGNED(addr, PGDIR_SIZE) && end - addr >= PGDIR_SIZE) { + p4d_t *p4d; pud_t *pud; pmd_t *pmd; @@ -135,9 +156,22 @@ void __init kasan_populate_zero_shadow(const void *shadow_start, * 3,2 - level page tables where we don't have * puds,pmds, so pgd_populate(), pud_populate() * is noops. + * + * The ifndef is required to avoid build breakage. + * + * With 5level-fixup.h, pgd_populate() is not nop and + * we reference kasan_zero_p4d. It's not defined + * unless 5-level paging enabled. + * + * The ifndef can be dropped once all KASAN-enabled + * architectures will switch to pgtable-nop4d.h. */ - pgd_populate(&init_mm, pgd, lm_alias(kasan_zero_pud)); - pud = pud_offset(pgd, addr); +#ifndef __ARCH_HAS_5LEVEL_HACK + pgd_populate(&init_mm, pgd, lm_alias(kasan_zero_p4d)); +#endif + p4d = p4d_offset(pgd, addr); + p4d_populate(&init_mm, p4d, lm_alias(kasan_zero_pud)); + pud = pud_offset(p4d, addr); pud_populate(&init_mm, pud, lm_alias(kasan_zero_pmd)); pmd = pmd_offset(pud, addr); pmd_populate_kernel(&init_mm, pmd, lm_alias(kasan_zero_pte)); @@ -148,6 +182,6 @@ void __init kasan_populate_zero_shadow(const void *shadow_start, pgd_populate(&init_mm, pgd, early_alloc(PAGE_SIZE, NUMA_NO_NODE)); } - zero_pud_populate(pgd, addr, next); + zero_p4d_populate(pgd, addr, next); } while (pgd++, addr = next, addr != end); } diff --git a/mm/memory.c b/mm/memory.c index a97a4cec2e1f..7f1c2163b3ce 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -445,7 +445,7 @@ static inline void free_pmd_range(struct mmu_gather *tlb, pud_t *pud, mm_dec_nr_pmds(tlb->mm); } -static inline void free_pud_range(struct mmu_gather *tlb, pgd_t *pgd, +static inline void free_pud_range(struct mmu_gather *tlb, p4d_t *p4d, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling) { @@ -454,7 +454,7 @@ static inline void free_pud_range(struct mmu_gather *tlb, pgd_t *pgd, unsigned long start; start = addr; - pud = pud_offset(pgd, addr); + pud = pud_offset(p4d, addr); do { next = pud_addr_end(addr, end); if (pud_none_or_clear_bad(pud)) @@ -462,6 +462,39 @@ static inline void free_pud_range(struct mmu_gather *tlb, pgd_t *pgd, free_pmd_range(tlb, pud, addr, next, floor, ceiling); } while (pud++, addr = next, addr != end); + start &= P4D_MASK; + if (start < floor) + return; + if (ceiling) { + ceiling &= P4D_MASK; + if (!ceiling) + return; + } + if (end - 1 > ceiling - 1) + return; + + pud = pud_offset(p4d, start); + p4d_clear(p4d); + pud_free_tlb(tlb, pud, start); +} + +static inline void free_p4d_range(struct mmu_gather *tlb, pgd_t *pgd, + unsigned long addr, unsigned long end, + unsigned long floor, unsigned long ceiling) +{ + p4d_t *p4d; + unsigned long next; + unsigned long start; + + start = addr; + p4d = p4d_offset(pgd, addr); + do { + next = p4d_addr_end(addr, end); + if (p4d_none_or_clear_bad(p4d)) + continue; + free_pud_range(tlb, p4d, addr, next, floor, ceiling); + } while (p4d++, addr = next, addr != end); + start &= PGDIR_MASK; if (start < floor) return; @@ -473,9 +506,9 @@ static inline void free_pud_range(struct mmu_gather *tlb, pgd_t *pgd, if (end - 1 > ceiling - 1) return; - pud = pud_offset(pgd, start); + p4d = p4d_offset(pgd, start); pgd_clear(pgd); - pud_free_tlb(tlb, pud, start); + p4d_free_tlb(tlb, p4d, start); } /* @@ -539,7 +572,7 @@ void free_pgd_range(struct mmu_gather *tlb, next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) continue; - free_pud_range(tlb, pgd, addr, next, floor, ceiling); + free_p4d_range(tlb, pgd, addr, next, floor, ceiling); } while (pgd++, addr = next, addr != end); } @@ -658,7 +691,8 @@ static void print_bad_pte(struct vm_area_struct *vma, unsigned long addr, pte_t pte, struct page *page) { pgd_t *pgd = pgd_offset(vma->vm_mm, addr); - pud_t *pud = pud_offset(pgd, addr); + p4d_t *p4d = p4d_offset(pgd, addr); + pud_t *pud = pud_offset(p4d, addr); pmd_t *pmd = pmd_offset(pud, addr); struct address_space *mapping; pgoff_t index; @@ -1023,16 +1057,16 @@ static inline int copy_pmd_range(struct mm_struct *dst_mm, struct mm_struct *src } static inline int copy_pud_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, - pgd_t *dst_pgd, pgd_t *src_pgd, struct vm_area_struct *vma, + p4d_t *dst_p4d, p4d_t *src_p4d, struct vm_area_struct *vma, unsigned long addr, unsigned long end) { pud_t *src_pud, *dst_pud; unsigned long next; - dst_pud = pud_alloc(dst_mm, dst_pgd, addr); + dst_pud = pud_alloc(dst_mm, dst_p4d, addr); if (!dst_pud) return -ENOMEM; - src_pud = pud_offset(src_pgd, addr); + src_pud = pud_offset(src_p4d, addr); do { next = pud_addr_end(addr, end); if (pud_trans_huge(*src_pud) || pud_devmap(*src_pud)) { @@ -1056,6 +1090,28 @@ static inline int copy_pud_range(struct mm_struct *dst_mm, struct mm_struct *src return 0; } +static inline int copy_p4d_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, + pgd_t *dst_pgd, pgd_t *src_pgd, struct vm_area_struct *vma, + unsigned long addr, unsigned long end) +{ + p4d_t *src_p4d, *dst_p4d; + unsigned long next; + + dst_p4d = p4d_alloc(dst_mm, dst_pgd, addr); + if (!dst_p4d) + return -ENOMEM; + src_p4d = p4d_offset(src_pgd, addr); + do { + next = p4d_addr_end(addr, end); + if (p4d_none_or_clear_bad(src_p4d)) + continue; + if (copy_pud_range(dst_mm, src_mm, dst_p4d, src_p4d, + vma, addr, next)) + return -ENOMEM; + } while (dst_p4d++, src_p4d++, addr = next, addr != end); + return 0; +} + int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, struct vm_area_struct *vma) { @@ -1111,7 +1167,7 @@ int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(src_pgd)) continue; - if (unlikely(copy_pud_range(dst_mm, src_mm, dst_pgd, src_pgd, + if (unlikely(copy_p4d_range(dst_mm, src_mm, dst_pgd, src_pgd, vma, addr, next))) { ret = -ENOMEM; break; @@ -1267,14 +1323,14 @@ next: } static inline unsigned long zap_pud_range(struct mmu_gather *tlb, - struct vm_area_struct *vma, pgd_t *pgd, + struct vm_area_struct *vma, p4d_t *p4d, unsigned long addr, unsigned long end, struct zap_details *details) { pud_t *pud; unsigned long next; - pud = pud_offset(pgd, addr); + pud = pud_offset(p4d, addr); do { next = pud_addr_end(addr, end); if (pud_trans_huge(*pud) || pud_devmap(*pud)) { @@ -1295,6 +1351,25 @@ next: return addr; } +static inline unsigned long zap_p4d_range(struct mmu_gather *tlb, + struct vm_area_struct *vma, pgd_t *pgd, + unsigned long addr, unsigned long end, + struct zap_details *details) +{ + p4d_t *p4d; + unsigned long next; + + p4d = p4d_offset(pgd, addr); + do { + next = p4d_addr_end(addr, end); + if (p4d_none_or_clear_bad(p4d)) + continue; + next = zap_pud_range(tlb, vma, p4d, addr, next, details); + } while (p4d++, addr = next, addr != end); + + return addr; +} + void unmap_page_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long addr, unsigned long end, @@ -1310,7 +1385,7 @@ void unmap_page_range(struct mmu_gather *tlb, next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) continue; - next = zap_pud_range(tlb, vma, pgd, addr, next, details); + next = zap_p4d_range(tlb, vma, pgd, addr, next, details); } while (pgd++, addr = next, addr != end); tlb_end_vma(tlb, vma); } @@ -1465,16 +1540,24 @@ EXPORT_SYMBOL_GPL(zap_vma_ptes); pte_t *__get_locked_pte(struct mm_struct *mm, unsigned long addr, spinlock_t **ptl) { - pgd_t *pgd = pgd_offset(mm, addr); - pud_t *pud = pud_alloc(mm, pgd, addr); - if (pud) { - pmd_t *pmd = pmd_alloc(mm, pud, addr); - if (pmd) { - VM_BUG_ON(pmd_trans_huge(*pmd)); - return pte_alloc_map_lock(mm, pmd, addr, ptl); - } - } - return NULL; + pgd_t *pgd; + p4d_t *p4d; + pud_t *pud; + pmd_t *pmd; + + pgd = pgd_offset(mm, addr); + p4d = p4d_alloc(mm, pgd, addr); + if (!p4d) + return NULL; + pud = pud_alloc(mm, p4d, addr); + if (!pud) + return NULL; + pmd = pmd_alloc(mm, pud, addr); + if (!pmd) + return NULL; + + VM_BUG_ON(pmd_trans_huge(*pmd)); + return pte_alloc_map_lock(mm, pmd, addr, ptl); } /* @@ -1740,7 +1823,7 @@ static inline int remap_pmd_range(struct mm_struct *mm, pud_t *pud, return 0; } -static inline int remap_pud_range(struct mm_struct *mm, pgd_t *pgd, +static inline int remap_pud_range(struct mm_struct *mm, p4d_t *p4d, unsigned long addr, unsigned long end, unsigned long pfn, pgprot_t prot) { @@ -1748,7 +1831,7 @@ static inline int remap_pud_range(struct mm_struct *mm, pgd_t *pgd, unsigned long next; pfn -= addr >> PAGE_SHIFT; - pud = pud_alloc(mm, pgd, addr); + pud = pud_alloc(mm, p4d, addr); if (!pud) return -ENOMEM; do { @@ -1760,6 +1843,26 @@ static inline int remap_pud_range(struct mm_struct *mm, pgd_t *pgd, return 0; } +static inline int remap_p4d_range(struct mm_struct *mm, pgd_t *pgd, + unsigned long addr, unsigned long end, + unsigned long pfn, pgprot_t prot) +{ + p4d_t *p4d; + unsigned long next; + + pfn -= addr >> PAGE_SHIFT; + p4d = p4d_alloc(mm, pgd, addr); + if (!p4d) + return -ENOMEM; + do { + next = p4d_addr_end(addr, end); + if (remap_pud_range(mm, p4d, addr, next, + pfn + (addr >> PAGE_SHIFT), prot)) + return -ENOMEM; + } while (p4d++, addr = next, addr != end); + return 0; +} + /** * remap_pfn_range - remap kernel memory to userspace * @vma: user vma to map to @@ -1816,7 +1919,7 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr, flush_cache_range(vma, addr, end); do { next = pgd_addr_end(addr, end); - err = remap_pud_range(mm, pgd, addr, next, + err = remap_p4d_range(mm, pgd, addr, next, pfn + (addr >> PAGE_SHIFT), prot); if (err) break; @@ -1932,7 +2035,7 @@ static int apply_to_pmd_range(struct mm_struct *mm, pud_t *pud, return err; } -static int apply_to_pud_range(struct mm_struct *mm, pgd_t *pgd, +static int apply_to_pud_range(struct mm_struct *mm, p4d_t *p4d, unsigned long addr, unsigned long end, pte_fn_t fn, void *data) { @@ -1940,7 +2043,7 @@ static int apply_to_pud_range(struct mm_struct *mm, pgd_t *pgd, unsigned long next; int err; - pud = pud_alloc(mm, pgd, addr); + pud = pud_alloc(mm, p4d, addr); if (!pud) return -ENOMEM; do { @@ -1952,6 +2055,26 @@ static int apply_to_pud_range(struct mm_struct *mm, pgd_t *pgd, return err; } +static int apply_to_p4d_range(struct mm_struct *mm, pgd_t *pgd, + unsigned long addr, unsigned long end, + pte_fn_t fn, void *data) +{ + p4d_t *p4d; + unsigned long next; + int err; + + p4d = p4d_alloc(mm, pgd, addr); + if (!p4d) + return -ENOMEM; + do { + next = p4d_addr_end(addr, end); + err = apply_to_pud_range(mm, p4d, addr, next, fn, data); + if (err) + break; + } while (p4d++, addr = next, addr != end); + return err; +} + /* * Scan a region of virtual memory, filling in page tables as necessary * and calling a provided function on each leaf page table. @@ -1970,7 +2093,7 @@ int apply_to_page_range(struct mm_struct *mm, unsigned long addr, pgd = pgd_offset(mm, addr); do { next = pgd_addr_end(addr, end); - err = apply_to_pud_range(mm, pgd, addr, next, fn, data); + err = apply_to_p4d_range(mm, pgd, addr, next, fn, data); if (err) break; } while (pgd++, addr = next, addr != end); @@ -3653,11 +3776,15 @@ static int __handle_mm_fault(struct vm_area_struct *vma, unsigned long address, }; struct mm_struct *mm = vma->vm_mm; pgd_t *pgd; + p4d_t *p4d; int ret; pgd = pgd_offset(mm, address); + p4d = p4d_alloc(mm, pgd, address); + if (!p4d) + return VM_FAULT_OOM; - vmf.pud = pud_alloc(mm, pgd, address); + vmf.pud = pud_alloc(mm, p4d, address); if (!vmf.pud) return VM_FAULT_OOM; if (pud_none(*vmf.pud) && transparent_hugepage_enabled(vma)) { @@ -3784,7 +3911,7 @@ EXPORT_SYMBOL_GPL(handle_mm_fault); * Allocate page upper directory. * We've already handled the fast-path in-line. */ -int __pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address) +int __pud_alloc(struct mm_struct *mm, p4d_t *p4d, unsigned long address) { pud_t *new = pud_alloc_one(mm, address); if (!new) @@ -3793,10 +3920,17 @@ int __pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address) smp_wmb(); /* See comment in __pte_alloc */ spin_lock(&mm->page_table_lock); - if (pgd_present(*pgd)) /* Another has populated it */ +#ifndef __ARCH_HAS_5LEVEL_HACK + if (p4d_present(*p4d)) /* Another has populated it */ + pud_free(mm, new); + else + p4d_populate(mm, p4d, new); +#else + if (pgd_present(*p4d)) /* Another has populated it */ pud_free(mm, new); else - pgd_populate(mm, pgd, new); + pgd_populate(mm, p4d, new); +#endif /* __ARCH_HAS_5LEVEL_HACK */ spin_unlock(&mm->page_table_lock); return 0; } @@ -3839,6 +3973,7 @@ static int __follow_pte_pmd(struct mm_struct *mm, unsigned long address, pte_t **ptepp, pmd_t **pmdpp, spinlock_t **ptlp) { pgd_t *pgd; + p4d_t *p4d; pud_t *pud; pmd_t *pmd; pte_t *ptep; @@ -3847,7 +3982,11 @@ static int __follow_pte_pmd(struct mm_struct *mm, unsigned long address, if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd))) goto out; - pud = pud_offset(pgd, address); + p4d = p4d_offset(pgd, address); + if (p4d_none(*p4d) || unlikely(p4d_bad(*p4d))) + goto out; + + pud = pud_offset(p4d, address); if (pud_none(*pud) || unlikely(pud_bad(*pud))) goto out; diff --git a/mm/mlock.c b/mm/mlock.c index 1050511f8b2b..945edac46810 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -380,6 +380,7 @@ static unsigned long __munlock_pagevec_fill(struct pagevec *pvec, pte = get_locked_pte(vma->vm_mm, start, &ptl); /* Make sure we do not cross the page table boundary */ end = pgd_addr_end(start, end); + end = p4d_addr_end(start, end); end = pud_addr_end(start, end); end = pmd_addr_end(start, end); diff --git a/mm/mprotect.c b/mm/mprotect.c index 848e946b08e5..8edd0d576254 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -193,14 +193,14 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma, } static inline unsigned long change_pud_range(struct vm_area_struct *vma, - pgd_t *pgd, unsigned long addr, unsigned long end, + p4d_t *p4d, unsigned long addr, unsigned long end, pgprot_t newprot, int dirty_accountable, int prot_numa) { pud_t *pud; unsigned long next; unsigned long pages = 0; - pud = pud_offset(pgd, addr); + pud = pud_offset(p4d, addr); do { next = pud_addr_end(addr, end); if (pud_none_or_clear_bad(pud)) @@ -212,6 +212,26 @@ static inline unsigned long change_pud_range(struct vm_area_struct *vma, return pages; } +static inline unsigned long change_p4d_range(struct vm_area_struct *vma, + pgd_t *pgd, unsigned long addr, unsigned long end, + pgprot_t newprot, int dirty_accountable, int prot_numa) +{ + p4d_t *p4d; + unsigned long next; + unsigned long pages = 0; + + p4d = p4d_offset(pgd, addr); + do { + next = p4d_addr_end(addr, end); + if (p4d_none_or_clear_bad(p4d)) + continue; + pages += change_pud_range(vma, p4d, addr, next, newprot, + dirty_accountable, prot_numa); + } while (p4d++, addr = next, addr != end); + + return pages; +} + static unsigned long change_protection_range(struct vm_area_struct *vma, unsigned long addr, unsigned long end, pgprot_t newprot, int dirty_accountable, int prot_numa) @@ -230,7 +250,7 @@ static unsigned long change_protection_range(struct vm_area_struct *vma, next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) continue; - pages += change_pud_range(vma, pgd, addr, next, newprot, + pages += change_p4d_range(vma, pgd, addr, next, newprot, dirty_accountable, prot_numa); } while (pgd++, addr = next, addr != end); diff --git a/mm/mremap.c b/mm/mremap.c index 8233b0105c82..cd8a1b199ef9 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -32,6 +32,7 @@ static pmd_t *get_old_pmd(struct mm_struct *mm, unsigned long addr) { pgd_t *pgd; + p4d_t *p4d; pud_t *pud; pmd_t *pmd; @@ -39,7 +40,11 @@ static pmd_t *get_old_pmd(struct mm_struct *mm, unsigned long addr) if (pgd_none_or_clear_bad(pgd)) return NULL; - pud = pud_offset(pgd, addr); + p4d = p4d_offset(pgd, addr); + if (p4d_none_or_clear_bad(p4d)) + return NULL; + + pud = pud_offset(p4d, addr); if (pud_none_or_clear_bad(pud)) return NULL; @@ -54,11 +59,15 @@ static pmd_t *alloc_new_pmd(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr) { pgd_t *pgd; + p4d_t *p4d; pud_t *pud; pmd_t *pmd; pgd = pgd_offset(mm, addr); - pud = pud_alloc(mm, pgd, addr); + p4d = p4d_alloc(mm, pgd, addr); + if (!p4d) + return NULL; + pud = pud_alloc(mm, p4d, addr); if (!pud) return NULL; diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c index a23001a22c15..c4c9def8ffea 100644 --- a/mm/page_vma_mapped.c +++ b/mm/page_vma_mapped.c @@ -104,6 +104,7 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw) struct mm_struct *mm = pvmw->vma->vm_mm; struct page *page = pvmw->page; pgd_t *pgd; + p4d_t *p4d; pud_t *pud; /* The only possible pmd mapping has been handled on last iteration */ @@ -133,7 +134,10 @@ restart: pgd = pgd_offset(mm, pvmw->address); if (!pgd_present(*pgd)) return false; - pud = pud_offset(pgd, pvmw->address); + p4d = p4d_offset(pgd, pvmw->address); + if (!p4d_present(*p4d)) + return false; + pud = pud_offset(p4d, pvmw->address); if (!pud_present(*pud)) return false; pvmw->pmd = pmd_offset(pud, pvmw->address); diff --git a/mm/pagewalk.c b/mm/pagewalk.c index 03761577ae86..60f7856e508f 100644 --- a/mm/pagewalk.c +++ b/mm/pagewalk.c @@ -69,14 +69,14 @@ again: return err; } -static int walk_pud_range(pgd_t *pgd, unsigned long addr, unsigned long end, +static int walk_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end, struct mm_walk *walk) { pud_t *pud; unsigned long next; int err = 0; - pud = pud_offset(pgd, addr); + pud = pud_offset(p4d, addr); do { again: next = pud_addr_end(addr, end); @@ -113,6 +113,32 @@ static int walk_pud_range(pgd_t *pgd, unsigned long addr, unsigned long end, return err; } +static int walk_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end, + struct mm_walk *walk) +{ + p4d_t *p4d; + unsigned long next; + int err = 0; + + p4d = p4d_offset(pgd, addr); + do { + next = p4d_addr_end(addr, end); + if (p4d_none_or_clear_bad(p4d)) { + if (walk->pte_hole) + err = walk->pte_hole(addr, next, walk); + if (err) + break; + continue; + } + if (walk->pmd_entry || walk->pte_entry) + err = walk_pud_range(p4d, addr, next, walk); + if (err) + break; + } while (p4d++, addr = next, addr != end); + + return err; +} + static int walk_pgd_range(unsigned long addr, unsigned long end, struct mm_walk *walk) { @@ -131,7 +157,7 @@ static int walk_pgd_range(unsigned long addr, unsigned long end, continue; } if (walk->pmd_entry || walk->pte_entry) - err = walk_pud_range(pgd, addr, next, walk); + err = walk_p4d_range(pgd, addr, next, walk); if (err) break; } while (pgd++, addr = next, addr != end); diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c index 4ed5908c65b0..c99d9512a45b 100644 --- a/mm/pgtable-generic.c +++ b/mm/pgtable-generic.c @@ -22,6 +22,12 @@ void pgd_clear_bad(pgd_t *pgd) pgd_clear(pgd); } +void p4d_clear_bad(p4d_t *p4d) +{ + p4d_ERROR(*p4d); + p4d_clear(p4d); +} + void pud_clear_bad(pud_t *pud) { pud_ERROR(*pud); diff --git a/mm/rmap.c b/mm/rmap.c index 2da487d6cea8..2984403a2424 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -684,6 +684,7 @@ unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma) pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address) { pgd_t *pgd; + p4d_t *p4d; pud_t *pud; pmd_t *pmd = NULL; pmd_t pmde; @@ -692,7 +693,11 @@ pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address) if (!pgd_present(*pgd)) goto out; - pud = pud_offset(pgd, address); + p4d = p4d_offset(pgd, address); + if (!p4d_present(*p4d)) + goto out; + + pud = pud_offset(p4d, address); if (!pud_present(*pud)) goto out; diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c index 574c67b663fe..a56c3989f773 100644 --- a/mm/sparse-vmemmap.c +++ b/mm/sparse-vmemmap.c @@ -196,9 +196,9 @@ pmd_t * __meminit vmemmap_pmd_populate(pud_t *pud, unsigned long addr, int node) return pmd; } -pud_t * __meminit vmemmap_pud_populate(pgd_t *pgd, unsigned long addr, int node) +pud_t * __meminit vmemmap_pud_populate(p4d_t *p4d, unsigned long addr, int node) { - pud_t *pud = pud_offset(pgd, addr); + pud_t *pud = pud_offset(p4d, addr); if (pud_none(*pud)) { void *p = vmemmap_alloc_block(PAGE_SIZE, node); if (!p) @@ -208,6 +208,18 @@ pud_t * __meminit vmemmap_pud_populate(pgd_t *pgd, unsigned long addr, int node) return pud; } +p4d_t * __meminit vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node) +{ + p4d_t *p4d = p4d_offset(pgd, addr); + if (p4d_none(*p4d)) { + void *p = vmemmap_alloc_block(PAGE_SIZE, node); + if (!p) + return NULL; + p4d_populate(&init_mm, p4d, p); + } + return p4d; +} + pgd_t * __meminit vmemmap_pgd_populate(unsigned long addr, int node) { pgd_t *pgd = pgd_offset_k(addr); @@ -225,6 +237,7 @@ int __meminit vmemmap_populate_basepages(unsigned long start, { unsigned long addr = start; pgd_t *pgd; + p4d_t *p4d; pud_t *pud; pmd_t *pmd; pte_t *pte; @@ -233,7 +246,10 @@ int __meminit vmemmap_populate_basepages(unsigned long start, pgd = vmemmap_pgd_populate(addr, node); if (!pgd) return -ENOMEM; - pud = vmemmap_pud_populate(pgd, addr, node); + p4d = vmemmap_p4d_populate(pgd, addr, node); + if (!p4d) + return -ENOMEM; + pud = vmemmap_pud_populate(p4d, addr, node); if (!pud) return -ENOMEM; pmd = vmemmap_pmd_populate(pud, addr, node); diff --git a/mm/swapfile.c b/mm/swapfile.c index 521ef9b6064f..178130880b90 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -1517,7 +1517,7 @@ static inline int unuse_pmd_range(struct vm_area_struct *vma, pud_t *pud, return 0; } -static inline int unuse_pud_range(struct vm_area_struct *vma, pgd_t *pgd, +static inline int unuse_pud_range(struct vm_area_struct *vma, p4d_t *p4d, unsigned long addr, unsigned long end, swp_entry_t entry, struct page *page) { @@ -1525,7 +1525,7 @@ static inline int unuse_pud_range(struct vm_area_struct *vma, pgd_t *pgd, unsigned long next; int ret; - pud = pud_offset(pgd, addr); + pud = pud_offset(p4d, addr); do { next = pud_addr_end(addr, end); if (pud_none_or_clear_bad(pud)) @@ -1537,6 +1537,26 @@ static inline int unuse_pud_range(struct vm_area_struct *vma, pgd_t *pgd, return 0; } +static inline int unuse_p4d_range(struct vm_area_struct *vma, pgd_t *pgd, + unsigned long addr, unsigned long end, + swp_entry_t entry, struct page *page) +{ + p4d_t *p4d; + unsigned long next; + int ret; + + p4d = p4d_offset(pgd, addr); + do { + next = p4d_addr_end(addr, end); + if (p4d_none_or_clear_bad(p4d)) + continue; + ret = unuse_pud_range(vma, p4d, addr, next, entry, page); + if (ret) + return ret; + } while (p4d++, addr = next, addr != end); + return 0; +} + static int unuse_vma(struct vm_area_struct *vma, swp_entry_t entry, struct page *page) { @@ -1560,7 +1580,7 @@ static int unuse_vma(struct vm_area_struct *vma, next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) continue; - ret = unuse_pud_range(vma, pgd, addr, next, entry, page); + ret = unuse_p4d_range(vma, pgd, addr, next, entry, page); if (ret) return ret; } while (pgd++, addr = next, addr != end); diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 479e631d43c2..8bcb501bce60 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -128,19 +128,22 @@ out_unlock: static pmd_t *mm_alloc_pmd(struct mm_struct *mm, unsigned long address) { pgd_t *pgd; + p4d_t *p4d; pud_t *pud; - pmd_t *pmd = NULL; pgd = pgd_offset(mm, address); - pud = pud_alloc(mm, pgd, address); - if (pud) - /* - * Note that we didn't run this because the pmd was - * missing, the *pmd may be already established and in - * turn it may also be a trans_huge_pmd. - */ - pmd = pmd_alloc(mm, pud, address); - return pmd; + p4d = p4d_alloc(mm, pgd, address); + if (!p4d) + return NULL; + pud = pud_alloc(mm, p4d, address); + if (!pud) + return NULL; + /* + * Note that we didn't run this because the pmd was + * missing, the *pmd may be already established and in + * turn it may also be a trans_huge_pmd. + */ + return pmd_alloc(mm, pud, address); } #ifdef CONFIG_HUGETLB_PAGE diff --git a/mm/vmalloc.c b/mm/vmalloc.c index b4024d688f38..0dd80222b20b 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -86,12 +86,12 @@ static void vunmap_pmd_range(pud_t *pud, unsigned long addr, unsigned long end) } while (pmd++, addr = next, addr != end); } -static void vunmap_pud_range(pgd_t *pgd, unsigned long addr, unsigned long end) +static void vunmap_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end) { pud_t *pud; unsigned long next; - pud = pud_offset(pgd, addr); + pud = pud_offset(p4d, addr); do { next = pud_addr_end(addr, end); if (pud_clear_huge(pud)) @@ -102,6 +102,22 @@ static void vunmap_pud_range(pgd_t *pgd, unsigned long addr, unsigned long end) } while (pud++, addr = next, addr != end); } +static void vunmap_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end) +{ + p4d_t *p4d; + unsigned long next; + + p4d = p4d_offset(pgd, addr); + do { + next = p4d_addr_end(addr, end); + if (p4d_clear_huge(p4d)) + continue; + if (p4d_none_or_clear_bad(p4d)) + continue; + vunmap_pud_range(p4d, addr, next); + } while (p4d++, addr = next, addr != end); +} + static void vunmap_page_range(unsigned long addr, unsigned long end) { pgd_t *pgd; @@ -113,7 +129,7 @@ static void vunmap_page_range(unsigned long addr, unsigned long end) next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) continue; - vunmap_pud_range(pgd, addr, next); + vunmap_p4d_range(pgd, addr, next); } while (pgd++, addr = next, addr != end); } @@ -160,13 +176,13 @@ static int vmap_pmd_range(pud_t *pud, unsigned long addr, return 0; } -static int vmap_pud_range(pgd_t *pgd, unsigned long addr, +static int vmap_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, int *nr) { pud_t *pud; unsigned long next; - pud = pud_alloc(&init_mm, pgd, addr); + pud = pud_alloc(&init_mm, p4d, addr); if (!pud) return -ENOMEM; do { @@ -177,6 +193,23 @@ static int vmap_pud_range(pgd_t *pgd, unsigned long addr, return 0; } +static int vmap_p4d_range(pgd_t *pgd, unsigned long addr, + unsigned long end, pgprot_t prot, struct page **pages, int *nr) +{ + p4d_t *p4d; + unsigned long next; + + p4d = p4d_alloc(&init_mm, pgd, addr); + if (!p4d) + return -ENOMEM; + do { + next = p4d_addr_end(addr, end); + if (vmap_pud_range(p4d, addr, next, prot, pages, nr)) + return -ENOMEM; + } while (p4d++, addr = next, addr != end); + return 0; +} + /* * Set up page tables in kva (addr, end). The ptes shall have prot "prot", and * will have pfns corresponding to the "pages" array. @@ -196,7 +229,7 @@ static int vmap_page_range_noflush(unsigned long start, unsigned long end, pgd = pgd_offset_k(addr); do { next = pgd_addr_end(addr, end); - err = vmap_pud_range(pgd, addr, next, prot, pages, &nr); + err = vmap_p4d_range(pgd, addr, next, prot, pages, &nr); if (err) return err; } while (pgd++, addr = next, addr != end); @@ -237,6 +270,10 @@ struct page *vmalloc_to_page(const void *vmalloc_addr) unsigned long addr = (unsigned long) vmalloc_addr; struct page *page = NULL; pgd_t *pgd = pgd_offset_k(addr); + p4d_t *p4d; + pud_t *pud; + pmd_t *pmd; + pte_t *ptep, pte; /* * XXX we might need to change this if we add VIRTUAL_BUG_ON for @@ -244,21 +281,23 @@ struct page *vmalloc_to_page(const void *vmalloc_addr) */ VIRTUAL_BUG_ON(!is_vmalloc_or_module_addr(vmalloc_addr)); - if (!pgd_none(*pgd)) { - pud_t *pud = pud_offset(pgd, addr); - if (!pud_none(*pud)) { - pmd_t *pmd = pmd_offset(pud, addr); - if (!pmd_none(*pmd)) { - pte_t *ptep, pte; - - ptep = pte_offset_map(pmd, addr); - pte = *ptep; - if (pte_present(pte)) - page = pte_page(pte); - pte_unmap(ptep); - } - } - } + if (pgd_none(*pgd)) + return NULL; + p4d = p4d_offset(pgd, addr); + if (p4d_none(*p4d)) + return NULL; + pud = pud_offset(p4d, addr); + if (pud_none(*pud)) + return NULL; + pmd = pmd_offset(pud, addr); + if (pmd_none(*pmd)) + return NULL; + + ptep = pte_offset_map(pmd, addr); + pte = *ptep; + if (pte_present(pte)) + page = pte_page(pte); + pte_unmap(ptep); return page; } EXPORT_SYMBOL(vmalloc_to_page); -- cgit v1.2.3 From 8a1115ff6b6d90cf1066ec3a0c4e51276553eebe Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Thu, 9 Mar 2017 16:16:31 -0800 Subject: scripts/spelling.txt: add "disble(d)" pattern and fix typo instances Fix typos and add the following to the scripts/spelling.txt: disble||disable disbled||disabled I kept the TSL2563_INT_DISBLED in /drivers/iio/light/tsl2563.c untouched. The macro is not referenced at all, but this commit is touching only comment blocks just in case. Link: http://lkml.kernel.org/r/1481573103-11329-20-git-send-email-yamada.masahiro@socionext.com Signed-off-by: Masahiro Yamada Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/dev-tools/kcov.rst | 2 +- arch/cris/arch-v32/drivers/cryptocop.c | 2 +- arch/x86/kernel/ftrace.c | 2 +- drivers/crypto/ux500/cryp/cryp.c | 2 +- drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c | 2 +- drivers/hv/channel.c | 2 +- drivers/isdn/hisax/st5481_b.c | 2 +- drivers/mtd/spi-nor/spi-nor.c | 2 +- drivers/net/ethernet/qlogic/qlge/qlge.h | 2 +- drivers/scsi/aic7xxx/aic79xx_core.c | 2 +- drivers/usb/gadget/legacy/inode.c | 3 +-- drivers/usb/host/xhci.c | 4 ++-- include/linux/regulator/machine.h | 2 +- kernel/cgroup/cgroup.c | 2 +- kernel/events/core.c | 2 +- scripts/spelling.txt | 2 ++ sound/soc/amd/acp-pcm-dma.c | 2 +- 17 files changed, 19 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/Documentation/dev-tools/kcov.rst b/Documentation/dev-tools/kcov.rst index 2c41b713841f..44886c91e112 100644 --- a/Documentation/dev-tools/kcov.rst +++ b/Documentation/dev-tools/kcov.rst @@ -10,7 +10,7 @@ Note that kcov does not aim to collect as much coverage as possible. It aims to collect more or less stable coverage that is function of syscall inputs. To achieve this goal it does not collect coverage in soft/hard interrupts and instrumentation of some inherently non-deterministic parts of kernel is -disbled (e.g. scheduler, locking). +disabled (e.g. scheduler, locking). Usage ----- diff --git a/arch/cris/arch-v32/drivers/cryptocop.c b/arch/cris/arch-v32/drivers/cryptocop.c index ae6903d7fdbe..14970f11bbf2 100644 --- a/arch/cris/arch-v32/drivers/cryptocop.c +++ b/arch/cris/arch-v32/drivers/cryptocop.c @@ -2086,7 +2086,7 @@ static void cryptocop_job_queue_close(void) dma_in_cfg.en = regk_dma_no; REG_WR(dma, IN_DMA_INST, rw_cfg, dma_in_cfg); - /* Disble the cryptocop. */ + /* Disable the cryptocop. */ rw_cfg = REG_RD(strcop, regi_strcop, rw_cfg); rw_cfg.en = 0; REG_WR(strcop, regi_strcop, rw_cfg, rw_cfg); diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 8639bb2ae058..8f3d9cf26ff9 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -535,7 +535,7 @@ static void run_sync(void) { int enable_irqs = irqs_disabled(); - /* We may be called with interrupts disbled (on bootup). */ + /* We may be called with interrupts disabled (on bootup). */ if (enable_irqs) local_irq_enable(); on_each_cpu(do_sync_core, NULL, 1); diff --git a/drivers/crypto/ux500/cryp/cryp.c b/drivers/crypto/ux500/cryp/cryp.c index 43a0c8a26ab0..00a16ab601cb 100644 --- a/drivers/crypto/ux500/cryp/cryp.c +++ b/drivers/crypto/ux500/cryp/cryp.c @@ -82,7 +82,7 @@ void cryp_activity(struct cryp_device_data *device_data, void cryp_flush_inoutfifo(struct cryp_device_data *device_data) { /* - * We always need to disble the hardware before trying to flush the + * We always need to disable the hardware before trying to flush the * FIFO. This is something that isn't written in the design * specification, but we have been informed by the hardware designers * that this must be done. diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c index 31375bdde6f1..011800f621c6 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c @@ -788,7 +788,7 @@ static int sdma_v3_0_start(struct amdgpu_device *adev) } } - /* disble sdma engine before programing it */ + /* disable sdma engine before programing it */ sdma_v3_0_ctx_switch_enable(adev, false); sdma_v3_0_enable(adev, false); diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c index 81a80c82f1bd..bd0d1988feb2 100644 --- a/drivers/hv/channel.c +++ b/drivers/hv/channel.c @@ -543,7 +543,7 @@ static int vmbus_close_internal(struct vmbus_channel *channel) /* * In case a device driver's probe() fails (e.g., * util_probe() -> vmbus_open() returns -ENOMEM) and the device is - * rescinded later (e.g., we dynamically disble an Integrated Service + * rescinded later (e.g., we dynamically disable an Integrated Service * in Hyper-V Manager), the driver's remove() invokes vmbus_close(): * here we should skip most of the below cleanup work. */ diff --git a/drivers/isdn/hisax/st5481_b.c b/drivers/isdn/hisax/st5481_b.c index 409849165838..f64a36007800 100644 --- a/drivers/isdn/hisax/st5481_b.c +++ b/drivers/isdn/hisax/st5481_b.c @@ -239,7 +239,7 @@ static void st5481B_mode(struct st5481_bcs *bcs, int mode) } } } else { - // Disble B channel interrupts + // Disable B channel interrupts st5481_usb_device_ctrl_msg(adapter, FFMSK_B1+(bcs->channel * 2), 0, NULL, NULL); // Disable B channel FIFOs diff --git a/drivers/mtd/spi-nor/spi-nor.c b/drivers/mtd/spi-nor/spi-nor.c index 1ae872bfc3ba..747645c74134 100644 --- a/drivers/mtd/spi-nor/spi-nor.c +++ b/drivers/mtd/spi-nor/spi-nor.c @@ -186,7 +186,7 @@ static inline int write_enable(struct spi_nor *nor) } /* - * Send write disble instruction to the chip. + * Send write disable instruction to the chip. */ static inline int write_disable(struct spi_nor *nor) { diff --git a/drivers/net/ethernet/qlogic/qlge/qlge.h b/drivers/net/ethernet/qlogic/qlge/qlge.h index 6d31f92ef2b6..90b3b46f85cc 100644 --- a/drivers/net/ethernet/qlogic/qlge/qlge.h +++ b/drivers/net/ethernet/qlogic/qlge/qlge.h @@ -1163,7 +1163,7 @@ struct ib_mac_iocb_rsp { u8 opcode; /* 0x20 */ u8 flags1; #define IB_MAC_IOCB_RSP_OI 0x01 /* Overide intr delay */ -#define IB_MAC_IOCB_RSP_I 0x02 /* Disble Intr Generation */ +#define IB_MAC_IOCB_RSP_I 0x02 /* Disable Intr Generation */ #define IB_MAC_CSUM_ERR_MASK 0x1c /* A mask to use for csum errs */ #define IB_MAC_IOCB_RSP_TE 0x04 /* Checksum error */ #define IB_MAC_IOCB_RSP_NU 0x08 /* No checksum rcvd */ diff --git a/drivers/scsi/aic7xxx/aic79xx_core.c b/drivers/scsi/aic7xxx/aic79xx_core.c index 109e2c99e6c1..95d8f25cbcca 100644 --- a/drivers/scsi/aic7xxx/aic79xx_core.c +++ b/drivers/scsi/aic7xxx/aic79xx_core.c @@ -6278,7 +6278,7 @@ ahd_reset(struct ahd_softc *ahd, int reinit) * does not disable its parity logic prior to * the start of the reset. This may cause a * parity error to be detected and thus a - * spurious SERR or PERR assertion. Disble + * spurious SERR or PERR assertion. Disable * PERR and SERR responses during the CHIPRST. */ mod_cmd = cmd & ~(PCIM_CMD_PERRESPEN|PCIM_CMD_SERRESPEN); diff --git a/drivers/usb/gadget/legacy/inode.c b/drivers/usb/gadget/legacy/inode.c index a2615d64d07c..79a2d8fba6b6 100644 --- a/drivers/usb/gadget/legacy/inode.c +++ b/drivers/usb/gadget/legacy/inode.c @@ -84,8 +84,7 @@ static int ep_open(struct inode *, struct file *); /* /dev/gadget/$CHIP represents ep0 and the whole device */ enum ep0_state { - /* DISBLED is the initial state. - */ + /* DISABLED is the initial state. */ STATE_DEV_DISABLED = 0, /* Only one open() of /dev/gadget/$CHIP; only one file tracks diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index 6d6c46000e56..50aee8b7718b 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -868,7 +868,7 @@ static void xhci_disable_port_wake_on_bits(struct xhci_hcd *xhci) spin_lock_irqsave(&xhci->lock, flags); - /* disble usb3 ports Wake bits*/ + /* disable usb3 ports Wake bits */ port_index = xhci->num_usb3_ports; port_array = xhci->usb3_ports; while (port_index--) { @@ -879,7 +879,7 @@ static void xhci_disable_port_wake_on_bits(struct xhci_hcd *xhci) writel(t2, port_array[port_index]); } - /* disble usb2 ports Wake bits*/ + /* disable usb2 ports Wake bits */ port_index = xhci->num_usb2_ports; port_array = xhci->usb2_ports; while (port_index--) { diff --git a/include/linux/regulator/machine.h b/include/linux/regulator/machine.h index ad3e5158e586..c9f795e9a2ee 100644 --- a/include/linux/regulator/machine.h +++ b/include/linux/regulator/machine.h @@ -65,7 +65,7 @@ struct regulator_state { int uV; /* suspend voltage */ unsigned int mode; /* suspend regulator operating mode */ int enabled; /* is regulator enabled in this suspend state */ - int disabled; /* is the regulator disbled in this suspend state */ + int disabled; /* is the regulator disabled in this suspend state */ }; /** diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 0125589c7428..48851327a15e 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -2669,7 +2669,7 @@ static bool css_visible(struct cgroup_subsys_state *css) * * Returns 0 on success, -errno on failure. On failure, csses which have * been processed already aren't cleaned up. The caller is responsible for - * cleaning up with cgroup_apply_control_disble(). + * cleaning up with cgroup_apply_control_disable(). */ static int cgroup_apply_control_enable(struct cgroup *cgrp) { diff --git a/kernel/events/core.c b/kernel/events/core.c index 6f41548f2e32..a17ed56c8ce1 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -998,7 +998,7 @@ list_update_cgroup_event(struct perf_event *event, */ #define PERF_CPU_HRTIMER (1000 / HZ) /* - * function must be called with interrupts disbled + * function must be called with interrupts disabled */ static enum hrtimer_restart perf_mux_hrtimer_handler(struct hrtimer *hr) { diff --git a/scripts/spelling.txt b/scripts/spelling.txt index 0458b037c8a1..6dae4df472f6 100644 --- a/scripts/spelling.txt +++ b/scripts/spelling.txt @@ -372,6 +372,8 @@ disassocation||disassociation disapear||disappear disapeared||disappeared disappared||disappeared +disble||disable +disbled||disabled disconnet||disconnect discontinous||discontinuous dispertion||dispersion diff --git a/sound/soc/amd/acp-pcm-dma.c b/sound/soc/amd/acp-pcm-dma.c index ec1067a679da..08b1399d1da2 100644 --- a/sound/soc/amd/acp-pcm-dma.c +++ b/sound/soc/amd/acp-pcm-dma.c @@ -89,7 +89,7 @@ static void acp_reg_write(u32 val, void __iomem *acp_mmio, u32 reg) writel(val, acp_mmio + (reg * 4)); } -/* Configure a given dma channel parameters - enable/disble, +/* Configure a given dma channel parameters - enable/disable, * number of descriptors, priority */ static void config_acp_dma_channel(void __iomem *acp_mmio, u8 ch_num, -- cgit v1.2.3 From dd0db88d8094a6d9d4d1fc5fcd56ab619f54ccf8 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Thu, 9 Mar 2017 16:16:49 -0800 Subject: userfaultfd: non-cooperative: rollback userfaultfd_exit Patch series "userfaultfd non-cooperative further update for 4.11 merge window". Unfortunately I noticed one relevant bug in userfaultfd_exit while doing more testing. I've been doing testing before and this was also tested by kbuild bot and exercised by the selftest, but this bug never reproduced before. I dropped userfaultfd_exit as result. I dropped it because of implementation difficulty in receiving signals in __mmput and because I think -ENOSPC as result from the background UFFDIO_COPY should be enough already. Before I decided to remove userfaultfd_exit, I noticed userfaultfd_exit wasn't exercised by the selftest and when I tried to exercise it, after moving it to a more correct place in __mmput where it would make more sense and where the vma list is stable, it resulted in the event_wait_completion in D state. So then I added the second patch to be sure even if we call userfaultfd_event_wait_completion too late during task exit(), we won't risk to generate tasks in D state. The same check exists in handle_userfault() for the same reason, except it makes a difference there, while here is just a robustness check and it's run under WARN_ON_ONCE. While looking at the userfaultfd_event_wait_completion() function I looked back at its callers too while at it and I think it's not ok to stop executing dup_fctx on the fcs list because we relay on userfaultfd_event_wait_completion to execute userfaultfd_ctx_put(fctx->orig) which is paired against userfaultfd_ctx_get(fctx->orig) in dup_userfault just before list_add(fcs). This change only takes care of fctx->orig but this area also needs further review looking for similar problems in fctx->new. The only patch that is urgent is the first because it's an use after free during a SMP race condition that affects all processes if CONFIG_USERFAULTFD=y. Very hard to reproduce though and probably impossible without SLUB poisoning enabled. This patch (of 3): I once reproduced this oops with the userfaultfd selftest, it's not easily reproducible and it requires SLUB poisoning to reproduce. general protection fault: 0000 [#1] SMP Modules linked in: CPU: 2 PID: 18421 Comm: userfaultfd Tainted: G ------------ T 3.10.0+ #15 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.10.1-0-g8891697-prebuilt.qemu-project.org 04/01/2014 task: ffff8801f83b9440 ti: ffff8801f833c000 task.ti: ffff8801f833c000 RIP: 0010:[] [] userfaultfd_exit+0x29/0xa0 RSP: 0018:ffff8801f833fe80 EFLAGS: 00010202 RAX: ffff8801f833ffd8 RBX: 6b6b6b6b6b6b6b6b RCX: ffff8801f83b9440 RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff8800baf18600 RBP: ffff8801f833fee8 R08: 0000000000000000 R09: 0000000000000001 R10: 0000000000000000 R11: ffffffff8127ceb3 R12: 0000000000000000 R13: ffff8800baf186b0 R14: ffff8801f83b99f8 R15: 00007faed746c700 FS: 0000000000000000(0000) GS:ffff88023fc80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b CR2: 00007faf0966f028 CR3: 0000000001bc6000 CR4: 00000000000006e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Call Trace: do_exit+0x297/0xd10 SyS_exit+0x17/0x20 tracesys+0xdd/0xe2 Code: 00 00 66 66 66 66 90 55 48 89 e5 41 54 53 48 83 ec 58 48 8b 1f 48 85 db 75 11 eb 73 66 0f 1f 44 00 00 48 8b 5b 10 48 85 db 74 64 <4c> 8b a3 b8 00 00 00 4d 85 e4 74 eb 41 f6 84 24 2c 01 00 00 80 RIP [] userfaultfd_exit+0x29/0xa0 RSP ---[ end trace 9fecd6dcb442846a ]--- In the debugger I located the "mm" pointer in the stack and walking mm->mmap->vm_next through the end shows the vma->vm_next list is fully consistent and it is null terminated list as expected. So this has to be an SMP race condition where userfaultfd_exit was running while the vma list was being modified by another CPU. When userfaultfd_exit() run one of the ->vm_next pointers pointed to SLAB_POISON (RBX is the vma pointer and is 0x6b6b..). The reason is that it's not running in __mmput but while there are still other threads running and it's not holding the mmap_sem (it can't as it has to wait the even to be received by the manager). So this is an use after free that was happening for all processes. One more implementation problem aside from the race condition: userfaultfd_exit has really to check a flag in mm->flags before walking the vma or it's going to slowdown the exit() path for regular tasks. One more implementation problem: at that point signals can't be delivered so it would also create a task in D state if the manager doesn't read the event. The major design issue: it overall looks superfluous as the manager can check for -ENOSPC in the background transfer: if (mmget_not_zero(ctx->mm)) { [..] } else { return -ENOSPC; } It's safer to roll it back and re-introduce it later if at all. [rppt@linux.vnet.ibm.com: documentation fixup after removal of UFFD_EVENT_EXIT] Link: http://lkml.kernel.org/r/1488345437-4364-1-git-send-email-rppt@linux.vnet.ibm.com Link: http://lkml.kernel.org/r/20170224181957.19736-2-aarcange@redhat.com Signed-off-by: Andrea Arcangeli Signed-off-by: Mike Rapoport Acked-by: Mike Rapoport Cc: "Dr. David Alan Gilbert" Cc: Mike Kravetz Cc: Pavel Emelyanov Cc: Hillf Danton Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/vm/userfaultfd.txt | 4 ---- fs/userfaultfd.c | 28 ---------------------------- include/linux/userfaultfd_k.h | 6 ------ include/uapi/linux/userfaultfd.h | 5 +---- kernel/exit.c | 1 - 5 files changed, 1 insertion(+), 43 deletions(-) (limited to 'include/linux') diff --git a/Documentation/vm/userfaultfd.txt b/Documentation/vm/userfaultfd.txt index 0e5543a920e5..bb2f945f87ab 100644 --- a/Documentation/vm/userfaultfd.txt +++ b/Documentation/vm/userfaultfd.txt @@ -172,10 +172,6 @@ the same read(2) protocol as for the page fault notifications. The manager has to explicitly enable these events by setting appropriate bits in uffdio_api.features passed to UFFDIO_API ioctl: -UFFD_FEATURE_EVENT_EXIT - enable notification about exit() of the -non-cooperative process. When the monitored process exits, the uffd -manager will get UFFD_EVENT_EXIT. - UFFD_FEATURE_EVENT_FORK - enable userfaultfd hooks for fork(). When this feature is enabled, the userfaultfd context of the parent process is duplicated into the newly created process. The manager receives diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index f62199b90fd0..16d0cc600fa9 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -775,34 +775,6 @@ void userfaultfd_unmap_complete(struct mm_struct *mm, struct list_head *uf) } } -void userfaultfd_exit(struct mm_struct *mm) -{ - struct vm_area_struct *vma = mm->mmap; - - /* - * We can do the vma walk without locking because the caller - * (exit_mm) knows it now has exclusive access - */ - while (vma) { - struct userfaultfd_ctx *ctx = vma->vm_userfaultfd_ctx.ctx; - - if (ctx && (ctx->features & UFFD_FEATURE_EVENT_EXIT)) { - struct userfaultfd_wait_queue ewq; - - userfaultfd_ctx_get(ctx); - - msg_init(&ewq.msg); - ewq.msg.event = UFFD_EVENT_EXIT; - - userfaultfd_event_wait_completion(ctx, &ewq); - - ctx->features &= ~UFFD_FEATURE_EVENT_EXIT; - } - - vma = vma->vm_next; - } -} - static int userfaultfd_release(struct inode *inode, struct file *file) { struct userfaultfd_ctx *ctx = file->private_data; diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index 0468548acebf..f2b79bf4c895 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -72,8 +72,6 @@ extern int userfaultfd_unmap_prep(struct vm_area_struct *vma, extern void userfaultfd_unmap_complete(struct mm_struct *mm, struct list_head *uf); -extern void userfaultfd_exit(struct mm_struct *mm); - #else /* CONFIG_USERFAULTFD */ /* mm helpers */ @@ -139,10 +137,6 @@ static inline void userfaultfd_unmap_complete(struct mm_struct *mm, { } -static inline void userfaultfd_exit(struct mm_struct *mm) -{ -} - #endif /* CONFIG_USERFAULTFD */ #endif /* _LINUX_USERFAULTFD_K_H */ diff --git a/include/uapi/linux/userfaultfd.h b/include/uapi/linux/userfaultfd.h index c055947c5c98..3b059530dac9 100644 --- a/include/uapi/linux/userfaultfd.h +++ b/include/uapi/linux/userfaultfd.h @@ -18,8 +18,7 @@ * means the userland is reading). */ #define UFFD_API ((__u64)0xAA) -#define UFFD_API_FEATURES (UFFD_FEATURE_EVENT_EXIT | \ - UFFD_FEATURE_EVENT_FORK | \ +#define UFFD_API_FEATURES (UFFD_FEATURE_EVENT_FORK | \ UFFD_FEATURE_EVENT_REMAP | \ UFFD_FEATURE_EVENT_REMOVE | \ UFFD_FEATURE_EVENT_UNMAP | \ @@ -113,7 +112,6 @@ struct uffd_msg { #define UFFD_EVENT_REMAP 0x14 #define UFFD_EVENT_REMOVE 0x15 #define UFFD_EVENT_UNMAP 0x16 -#define UFFD_EVENT_EXIT 0x17 /* flags for UFFD_EVENT_PAGEFAULT */ #define UFFD_PAGEFAULT_FLAG_WRITE (1<<0) /* If this was a write fault */ @@ -163,7 +161,6 @@ struct uffdio_api { #define UFFD_FEATURE_MISSING_HUGETLBFS (1<<4) #define UFFD_FEATURE_MISSING_SHMEM (1<<5) #define UFFD_FEATURE_EVENT_UNMAP (1<<6) -#define UFFD_FEATURE_EVENT_EXIT (1<<7) __u64 features; __u64 ioctls; diff --git a/kernel/exit.c b/kernel/exit.c index e126ebf2400c..516acdb0e0ec 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -554,7 +554,6 @@ static void exit_mm(void) enter_lazy_tlb(mm, current); task_unlock(current); mm_update_next_owner(mm); - userfaultfd_exit(mm); mmput(mm); if (test_thread_flag(TIF_MEMDIE)) exit_oom_victim(); -- cgit v1.2.3 From cbfd0c1001bedb4b051cf4a1f5df24f1500381bc Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 9 Mar 2017 16:16:57 -0800 Subject: include/linux/fs.h: fix unsigned enum warning with gcc-4.2 With arm-linux-gcc-4.2, almost every file we build in the kernel ends up with this warning: include/linux/fs.h:2648: warning: comparison of unsigned expression < 0 is always false Later versions don't have this problem, but it's easy enough to work around. Link: http://lkml.kernel.org/r/20161216105634.235457-12-arnd@arndb.de Signed-off-by: Arnd Bergmann Cc: Russell King Cc: Brendan Gregg Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index aad3fd0ff5f8..7251f7bb45e8 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2678,7 +2678,7 @@ static const char * const kernel_read_file_str[] = { static inline const char *kernel_read_file_id_str(enum kernel_read_file_id id) { - if (id < 0 || id >= READING_MAX_ID) + if ((unsigned)id >= READING_MAX_ID) return kernel_read_file_str[READING_UNKNOWN]; return kernel_read_file_str[id]; -- cgit v1.2.3 From ce9311cf95ad8baf044a014738d76973d93b739a Mon Sep 17 00:00:00 2001 From: Yisheng Xie Date: Thu, 9 Mar 2017 16:17:00 -0800 Subject: mm/vmstats: add thp_split_pud event for clarity We added support for PUD-sized transparent hugepages, however we count the event "thp split pud" into thp_split_pmd event. To separate the event count of thp split pud from pmd, add a new event named thp_split_pud. Link: http://lkml.kernel.org/r/1488282380-5076-1-git-send-email-xieyisheng1@huawei.com Signed-off-by: Yisheng Xie Cc: Vlastimil Babka Cc: Johannes Weiner Cc: Michal Hocko Cc: Joonsoo Kim Cc: Sebastian Siewior Cc: Hugh Dickins Cc: Christoph Lameter Cc: Kirill A. Shutemov Cc: Aneesh Kumar K.V Cc: Mel Gorman Cc: Andrea Arcangeli Cc: Ebru Akagunduz Cc: David Rientjes Cc: Hanjun Guo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vm_event_item.h | 3 +++ mm/huge_memory.c | 2 +- mm/vmstat.c | 3 +++ 3 files changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index 6aa1b6cb5828..a80b7b59cf33 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -79,6 +79,9 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, THP_SPLIT_PAGE_FAILED, THP_DEFERRED_SPLIT_PAGE, THP_SPLIT_PMD, +#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD + THP_SPLIT_PUD, +#endif THP_ZERO_PAGE_ALLOC, THP_ZERO_PAGE_ALLOC_FAILED, #endif diff --git a/mm/huge_memory.c b/mm/huge_memory.c index d36b2af4d1bf..8f037e256c54 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1828,7 +1828,7 @@ static void __split_huge_pud_locked(struct vm_area_struct *vma, pud_t *pud, VM_BUG_ON_VMA(vma->vm_end < haddr + HPAGE_PUD_SIZE, vma); VM_BUG_ON(!pud_trans_huge(*pud) && !pud_devmap(*pud)); - count_vm_event(THP_SPLIT_PMD); + count_vm_event(THP_SPLIT_PUD); pudp_huge_clear_flush_notify(vma, haddr, pud); } diff --git a/mm/vmstat.c b/mm/vmstat.c index 69f9aff39a2e..b1947f0cbee2 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1065,6 +1065,9 @@ const char * const vmstat_text[] = { "thp_split_page_failed", "thp_deferred_split_page", "thp_split_pmd", +#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD + "thp_split_pud", +#endif "thp_zero_page_alloc", "thp_zero_page_alloc_failed", #endif -- cgit v1.2.3 From 70ccb92fdd90b35bb6f9200093d4ffd6cb38156b Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Thu, 9 Mar 2017 16:17:11 -0800 Subject: userfaultfd: non-cooperative: userfaultfd_remove revalidate vma in MADV_DONTNEED userfaultfd_remove() has to be execute before zapping the pagetables or UFFDIO_COPY could keep filling pages after zap_page_range returned, which would result in non zero data after a MADV_DONTNEED. However userfaultfd_remove() may have to release the mmap_sem. This was handled correctly in MADV_REMOVE, but MADV_DONTNEED accessed a potentially stale vma (the very vma passed to zap_page_range(vma, ...)). The fix consists in revalidating the vma in case userfaultfd_remove() had to release the mmap_sem. This also optimizes away an unnecessary down_read/up_read in the MADV_REMOVE case if UFFD_EVENT_FORK had to be delivered. It all remains zero runtime cost in case CONFIG_USERFAULTFD=n as userfaultfd_remove() will be defined as "true" at build time. Link: http://lkml.kernel.org/r/20170302173738.18994-3-aarcange@redhat.com Signed-off-by: Andrea Arcangeli Acked-by: Mike Rapoport Cc: "Dr. David Alan Gilbert" Cc: Mike Kravetz Cc: Pavel Emelyanov Cc: Hillf Danton Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/userfaultfd.c | 9 +++------ include/linux/userfaultfd_k.h | 7 +++---- mm/madvise.c | 44 ++++++++++++++++++++++++++++++++++++++++--- 3 files changed, 47 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 2407249998c3..9fd5e51ffb31 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -695,8 +695,7 @@ void mremap_userfaultfd_complete(struct vm_userfaultfd_ctx *vm_ctx, userfaultfd_event_wait_completion(ctx, &ewq); } -void userfaultfd_remove(struct vm_area_struct *vma, - struct vm_area_struct **prev, +bool userfaultfd_remove(struct vm_area_struct *vma, unsigned long start, unsigned long end) { struct mm_struct *mm = vma->vm_mm; @@ -705,13 +704,11 @@ void userfaultfd_remove(struct vm_area_struct *vma, ctx = vma->vm_userfaultfd_ctx.ctx; if (!ctx || !(ctx->features & UFFD_FEATURE_EVENT_REMOVE)) - return; + return true; userfaultfd_ctx_get(ctx); up_read(&mm->mmap_sem); - *prev = NULL; /* We wait for ACK w/o the mmap semaphore */ - msg_init(&ewq.msg); ewq.msg.event = UFFD_EVENT_REMOVE; @@ -720,7 +717,7 @@ void userfaultfd_remove(struct vm_area_struct *vma, userfaultfd_event_wait_completion(ctx, &ewq); - down_read(&mm->mmap_sem); + return false; } static bool has_unmap_ctx(struct userfaultfd_ctx *ctx, struct list_head *unmaps, diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index f2b79bf4c895..48a3483dccb1 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -61,8 +61,7 @@ extern void mremap_userfaultfd_complete(struct vm_userfaultfd_ctx *, unsigned long from, unsigned long to, unsigned long len); -extern void userfaultfd_remove(struct vm_area_struct *vma, - struct vm_area_struct **prev, +extern bool userfaultfd_remove(struct vm_area_struct *vma, unsigned long start, unsigned long end); @@ -118,11 +117,11 @@ static inline void mremap_userfaultfd_complete(struct vm_userfaultfd_ctx *ctx, { } -static inline void userfaultfd_remove(struct vm_area_struct *vma, - struct vm_area_struct **prev, +static inline bool userfaultfd_remove(struct vm_area_struct *vma, unsigned long start, unsigned long end) { + return true; } static inline int userfaultfd_unmap_prep(struct vm_area_struct *vma, diff --git a/mm/madvise.c b/mm/madvise.c index dc5927c812d3..7a2abf0127ae 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -513,7 +513,43 @@ static long madvise_dontneed(struct vm_area_struct *vma, if (!can_madv_dontneed_vma(vma)) return -EINVAL; - userfaultfd_remove(vma, prev, start, end); + if (!userfaultfd_remove(vma, start, end)) { + *prev = NULL; /* mmap_sem has been dropped, prev is stale */ + + down_read(¤t->mm->mmap_sem); + vma = find_vma(current->mm, start); + if (!vma) + return -ENOMEM; + if (start < vma->vm_start) { + /* + * This "vma" under revalidation is the one + * with the lowest vma->vm_start where start + * is also < vma->vm_end. If start < + * vma->vm_start it means an hole materialized + * in the user address space within the + * virtual range passed to MADV_DONTNEED. + */ + return -ENOMEM; + } + if (!can_madv_dontneed_vma(vma)) + return -EINVAL; + if (end > vma->vm_end) { + /* + * Don't fail if end > vma->vm_end. If the old + * vma was splitted while the mmap_sem was + * released the effect of the concurrent + * operation may not cause MADV_DONTNEED to + * have an undefined result. There may be an + * adjacent next vma that we'll walk + * next. userfaultfd_remove() will generate an + * UFFD_EVENT_REMOVE repetition on the + * end-vma->vm_end range, but the manager can + * handle a repetition fine. + */ + end = vma->vm_end; + } + VM_WARN_ON(start >= end); + } zap_page_range(vma, start, end - start); return 0; } @@ -554,8 +590,10 @@ static long madvise_remove(struct vm_area_struct *vma, * mmap_sem. */ get_file(f); - userfaultfd_remove(vma, prev, start, end); - up_read(¤t->mm->mmap_sem); + if (userfaultfd_remove(vma, start, end)) { + /* mmap_sem was not released by userfaultfd_remove() */ + up_read(¤t->mm->mmap_sem); + } error = vfs_fallocate(f, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, offset, end - start); -- cgit v1.2.3 From 40c50c1fecdf012a3bf055ec813f0ef2eda2749c Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 10 Mar 2017 13:17:18 +0100 Subject: kexec, x86/purgatory: Unbreak it and clean it up The purgatory code defines global variables which are referenced via a symbol lookup in the kexec code (core and arch). A recent commit addressing sparse warnings made these static and thereby broke kexec_file. Why did this happen? Simply because the whole machinery is undocumented and lacks any form of forward declarations. The variable names are unspecific and lack a prefix, so adding forward declarations creates shadow variables in the core code. Aside of that the code relies on magic constants and duplicate struct definitions with no way to ensure that these things stay in sync. The section placement of the purgatory variables happened by chance and not by design. Unbreak kexec and cleanup the mess: - Add proper forward declarations and document the usage - Use common struct definition - Use the proper common defines instead of magic constants - Add a purgatory_ prefix to have a proper name space - Use ARRAY_SIZE() instead of a homebrewn reimplementation - Add proper sections to the purgatory variables [ From Mike ] Fixes: 72042a8c7b01 ("x86/purgatory: Make functions and variables static") Reported-by: Mike Galbraith < Signed-off-by: Thomas Gleixner Cc: Nicholas Mc Guire Cc: Borislav Petkov Cc: Vivek Goyal Cc: "Tobin C. Harding" Link: http://lkml.kernel.org/r/alpine.DEB.2.20.1703101315140.3681@nanos Signed-off-by: Thomas Gleixner --- arch/powerpc/purgatory/trampoline.S | 12 ++++++------ arch/x86/include/asm/purgatory.h | 20 ++++++++++++++++++++ arch/x86/kernel/machine_kexec_64.c | 9 ++++++--- arch/x86/purgatory/purgatory.c | 35 +++++++++++++++++------------------ arch/x86/purgatory/purgatory.h | 8 -------- arch/x86/purgatory/setup-x86_64.S | 2 +- arch/x86/purgatory/sha256.h | 1 - include/linux/purgatory.h | 23 +++++++++++++++++++++++ kernel/kexec_file.c | 8 ++++---- kernel/kexec_internal.h | 6 +----- 10 files changed, 78 insertions(+), 46 deletions(-) create mode 100644 arch/x86/include/asm/purgatory.h delete mode 100644 arch/x86/purgatory/purgatory.h create mode 100644 include/linux/purgatory.h (limited to 'include/linux') diff --git a/arch/powerpc/purgatory/trampoline.S b/arch/powerpc/purgatory/trampoline.S index f9760ccf4032..3696ea6c4826 100644 --- a/arch/powerpc/purgatory/trampoline.S +++ b/arch/powerpc/purgatory/trampoline.S @@ -116,13 +116,13 @@ dt_offset: .data .balign 8 -.globl sha256_digest -sha256_digest: +.globl purgatory_sha256_digest +purgatory_sha256_digest: .skip 32 - .size sha256_digest, . - sha256_digest + .size purgatory_sha256_digest, . - purgatory_sha256_digest .balign 8 -.globl sha_regions -sha_regions: +.globl purgatory_sha_regions +purgatory_sha_regions: .skip 8 * 2 * 16 - .size sha_regions, . - sha_regions + .size purgatory_sha_regions, . - purgatory_sha_regions diff --git a/arch/x86/include/asm/purgatory.h b/arch/x86/include/asm/purgatory.h new file mode 100644 index 000000000000..d7da2729903d --- /dev/null +++ b/arch/x86/include/asm/purgatory.h @@ -0,0 +1,20 @@ +#ifndef _ASM_X86_PURGATORY_H +#define _ASM_X86_PURGATORY_H + +#ifndef __ASSEMBLY__ +#include + +extern void purgatory(void); +/* + * These forward declarations serve two purposes: + * + * 1) Make sparse happy when checking arch/purgatory + * 2) Document that these are required to be global so the symbol + * lookup in kexec works + */ +extern unsigned long purgatory_backup_dest; +extern unsigned long purgatory_backup_src; +extern unsigned long purgatory_backup_sz; +#endif /* __ASSEMBLY__ */ + +#endif /* _ASM_PURGATORY_H */ diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index 307b1f4543de..857cdbd02867 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -194,19 +194,22 @@ static int arch_update_purgatory(struct kimage *image) /* Setup copying of backup region */ if (image->type == KEXEC_TYPE_CRASH) { - ret = kexec_purgatory_get_set_symbol(image, "backup_dest", + ret = kexec_purgatory_get_set_symbol(image, + "purgatory_backup_dest", &image->arch.backup_load_addr, sizeof(image->arch.backup_load_addr), 0); if (ret) return ret; - ret = kexec_purgatory_get_set_symbol(image, "backup_src", + ret = kexec_purgatory_get_set_symbol(image, + "purgatory_backup_src", &image->arch.backup_src_start, sizeof(image->arch.backup_src_start), 0); if (ret) return ret; - ret = kexec_purgatory_get_set_symbol(image, "backup_sz", + ret = kexec_purgatory_get_set_symbol(image, + "purgatory_backup_sz", &image->arch.backup_src_sz, sizeof(image->arch.backup_src_sz), 0); if (ret) diff --git a/arch/x86/purgatory/purgatory.c b/arch/x86/purgatory/purgatory.c index b6d5c8946e66..470edad96bb9 100644 --- a/arch/x86/purgatory/purgatory.c +++ b/arch/x86/purgatory/purgatory.c @@ -10,22 +10,19 @@ * Version 2. See the file COPYING for more details. */ +#include +#include + #include "sha256.h" -#include "purgatory.h" #include "../boot/string.h" -struct sha_region { - unsigned long start; - unsigned long len; -}; - -static unsigned long backup_dest; -static unsigned long backup_src; -static unsigned long backup_sz; +unsigned long purgatory_backup_dest __section(.kexec-purgatory); +unsigned long purgatory_backup_src __section(.kexec-purgatory); +unsigned long purgatory_backup_sz __section(.kexec-purgatory); -static u8 sha256_digest[SHA256_DIGEST_SIZE] = { 0 }; +u8 purgatory_sha256_digest[SHA256_DIGEST_SIZE] __section(.kexec-purgatory); -struct sha_region sha_regions[16] = {}; +struct kexec_sha_region purgatory_sha_regions[KEXEC_SEGMENT_MAX] __section(.kexec-purgatory); /* * On x86, second kernel requries first 640K of memory to boot. Copy @@ -34,26 +31,28 @@ struct sha_region sha_regions[16] = {}; */ static int copy_backup_region(void) { - if (backup_dest) - memcpy((void *)backup_dest, (void *)backup_src, backup_sz); - + if (purgatory_backup_dest) { + memcpy((void *)purgatory_backup_dest, + (void *)purgatory_backup_src, purgatory_backup_sz); + } return 0; } static int verify_sha256_digest(void) { - struct sha_region *ptr, *end; + struct kexec_sha_region *ptr, *end; u8 digest[SHA256_DIGEST_SIZE]; struct sha256_state sctx; sha256_init(&sctx); - end = &sha_regions[sizeof(sha_regions)/sizeof(sha_regions[0])]; - for (ptr = sha_regions; ptr < end; ptr++) + end = purgatory_sha_regions + ARRAY_SIZE(purgatory_sha_regions); + + for (ptr = purgatory_sha_regions; ptr < end; ptr++) sha256_update(&sctx, (uint8_t *)(ptr->start), ptr->len); sha256_final(&sctx, digest); - if (memcmp(digest, sha256_digest, sizeof(digest))) + if (memcmp(digest, purgatory_sha256_digest, sizeof(digest))) return 1; return 0; diff --git a/arch/x86/purgatory/purgatory.h b/arch/x86/purgatory/purgatory.h deleted file mode 100644 index e2e365a6c192..000000000000 --- a/arch/x86/purgatory/purgatory.h +++ /dev/null @@ -1,8 +0,0 @@ -#ifndef PURGATORY_H -#define PURGATORY_H - -#ifndef __ASSEMBLY__ -extern void purgatory(void); -#endif /* __ASSEMBLY__ */ - -#endif /* PURGATORY_H */ diff --git a/arch/x86/purgatory/setup-x86_64.S b/arch/x86/purgatory/setup-x86_64.S index f90e9dfa90bb..dfae9b9e60b5 100644 --- a/arch/x86/purgatory/setup-x86_64.S +++ b/arch/x86/purgatory/setup-x86_64.S @@ -9,7 +9,7 @@ * This source code is licensed under the GNU General Public License, * Version 2. See the file COPYING for more details. */ -#include "purgatory.h" +#include .text .globl purgatory_start diff --git a/arch/x86/purgatory/sha256.h b/arch/x86/purgatory/sha256.h index bd15a4127735..2867d9825a57 100644 --- a/arch/x86/purgatory/sha256.h +++ b/arch/x86/purgatory/sha256.h @@ -10,7 +10,6 @@ #ifndef SHA256_H #define SHA256_H - #include #include diff --git a/include/linux/purgatory.h b/include/linux/purgatory.h new file mode 100644 index 000000000000..d60d4e278609 --- /dev/null +++ b/include/linux/purgatory.h @@ -0,0 +1,23 @@ +#ifndef _LINUX_PURGATORY_H +#define _LINUX_PURGATORY_H + +#include +#include +#include + +struct kexec_sha_region { + unsigned long start; + unsigned long len; +}; + +/* + * These forward declarations serve two purposes: + * + * 1) Make sparse happy when checking arch/purgatory + * 2) Document that these are required to be global so the symbol + * lookup in kexec works + */ +extern struct kexec_sha_region purgatory_sha_regions[KEXEC_SEGMENT_MAX]; +extern u8 purgatory_sha256_digest[SHA256_DIGEST_SIZE]; + +#endif diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c index b56a558e406d..b118735fea9d 100644 --- a/kernel/kexec_file.c +++ b/kernel/kexec_file.c @@ -614,13 +614,13 @@ static int kexec_calculate_store_digests(struct kimage *image) ret = crypto_shash_final(desc, digest); if (ret) goto out_free_digest; - ret = kexec_purgatory_get_set_symbol(image, "sha_regions", - sha_regions, sha_region_sz, 0); + ret = kexec_purgatory_get_set_symbol(image, "purgatory_sha_regions", + sha_regions, sha_region_sz, 0); if (ret) goto out_free_digest; - ret = kexec_purgatory_get_set_symbol(image, "sha256_digest", - digest, SHA256_DIGEST_SIZE, 0); + ret = kexec_purgatory_get_set_symbol(image, "purgatory_sha256_digest", + digest, SHA256_DIGEST_SIZE, 0); if (ret) goto out_free_digest; } diff --git a/kernel/kexec_internal.h b/kernel/kexec_internal.h index 4cef7e4706b0..799a8a452187 100644 --- a/kernel/kexec_internal.h +++ b/kernel/kexec_internal.h @@ -15,11 +15,7 @@ int kimage_is_destination_range(struct kimage *image, extern struct mutex kexec_mutex; #ifdef CONFIG_KEXEC_FILE -struct kexec_sha_region { - unsigned long start; - unsigned long len; -}; - +#include void kimage_file_post_load_cleanup(struct kimage *image); #else /* CONFIG_KEXEC_FILE */ static inline void kimage_file_post_load_cleanup(struct kimage *image) { } -- cgit v1.2.3