From 4881873f4cc1460f63d85fa81363d56be328ccdc Mon Sep 17 00:00:00 2001 From: Martin Blumenstingl Date: Sat, 30 Nov 2019 19:53:37 +0100 Subject: dt-bindings: reset: meson8b: fix duplicate reset IDs According to the public S805 datasheet the RESET2 register uses the following bits for the PIC_DC, PSC and NAND reset lines: - PIC_DC is at bit 3 (meaning: RESET_VD_RMEM + 3) - PSC is at bit 4 (meaning: RESET_VD_RMEM + 4) - NAND is at bit 5 (meaning: RESET_VD_RMEM + 4) Update the reset IDs of these three reset lines so they don't conflict with PIC_DC and map to the actual hardware reset lines. Fixes: 79795e20a184eb ("dt-bindings: reset: Add bindings for the Meson SoC Reset Controller") Signed-off-by: Martin Blumenstingl Signed-off-by: Kevin Hilman --- include/dt-bindings/reset/amlogic,meson8b-reset.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/dt-bindings/reset/amlogic,meson8b-reset.h b/include/dt-bindings/reset/amlogic,meson8b-reset.h index c614438bcbdb..fbc524a900da 100644 --- a/include/dt-bindings/reset/amlogic,meson8b-reset.h +++ b/include/dt-bindings/reset/amlogic,meson8b-reset.h @@ -46,9 +46,9 @@ #define RESET_VD_RMEM 64 #define RESET_AUDIN 65 #define RESET_DBLK 66 -#define RESET_PIC_DC 66 -#define RESET_PSC 66 -#define RESET_NAND 66 +#define RESET_PIC_DC 67 +#define RESET_PSC 68 +#define RESET_NAND 69 #define RESET_GE2D 70 #define RESET_PARSER_REG 71 #define RESET_PARSER_FETCH 72 -- cgit v1.2.3 From 53a256a9b925b47c7e67fc1f16ca41561a7b877c Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Thu, 5 Dec 2019 12:54:49 +0100 Subject: dmaengine: Fix access to uninitialized dma_slave_caps dmaengine_desc_set_reuse() allocates a struct dma_slave_caps on the stack, populates it using dma_get_slave_caps() and then accesses one of its members. However dma_get_slave_caps() may fail and this isn't accounted for, leading to a legitimate warning of gcc-4.9 (but not newer versions): In file included from drivers/spi/spi-bcm2835.c:19:0: drivers/spi/spi-bcm2835.c: In function 'dmaengine_desc_set_reuse': >> include/linux/dmaengine.h:1370:10: warning: 'caps.descriptor_reuse' is used uninitialized in this function [-Wuninitialized] if (caps.descriptor_reuse) { Fix it, thereby also silencing the gcc-4.9 warning. The issue has been present for 4 years but surfaces only now that the first caller of dmaengine_desc_set_reuse() has been added in spi-bcm2835.c. Another user of reusable DMA descriptors has existed for a while in pxa_camera.c, but it sets the DMA_CTRL_REUSE flag directly instead of calling dmaengine_desc_set_reuse(). Nevertheless, tag this commit for stable in case there are out-of-tree users. Fixes: 272420214d26 ("dmaengine: Add DMA_CTRL_REUSE") Reported-by: kbuild test robot Signed-off-by: Lukas Wunner Cc: stable@vger.kernel.org # v4.3+ Link: https://lore.kernel.org/r/ca92998ccc054b4f2bfd60ef3adbab2913171eac.1575546234.git.lukas@wunner.de Signed-off-by: Vinod Koul --- include/linux/dmaengine.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 8fcdee1c0cf9..dad4a68fa009 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -1364,8 +1364,11 @@ static inline int dma_get_slave_caps(struct dma_chan *chan, static inline int dmaengine_desc_set_reuse(struct dma_async_tx_descriptor *tx) { struct dma_slave_caps caps; + int ret; - dma_get_slave_caps(tx->chan, &caps); + ret = dma_get_slave_caps(tx->chan, &caps); + if (ret) + return ret; if (caps.descriptor_reuse) { tx->flags |= DMA_CTRL_REUSE; -- cgit v1.2.3 From 653997eeecef95c3ead4fba1b2d27e6a5854d6cd Mon Sep 17 00:00:00 2001 From: Ran Bi Date: Wed, 11 Dec 2019 17:43:54 +0800 Subject: rtc: mt6397: fix alarm register overwrite Alarm registers high byte was reserved for other functions. This add mask in alarm registers operation functions. This also fix error condition in interrupt handler. Fixes: fc2979118f3f ("rtc: mediatek: Add MT6397 RTC driver") Signed-off-by: Ran Bi Signed-off-by: Hsin-Hsiung Wang Link: https://lore.kernel.org/r/1576057435-3561-6-git-send-email-hsin-hsiung.wang@mediatek.com Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-mt6397.c | 39 +++++++++++++++++++++++++-------------- include/linux/mfd/mt6397/rtc.h | 8 ++++++++ 2 files changed, 33 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/drivers/rtc/rtc-mt6397.c b/drivers/rtc/rtc-mt6397.c index 5249fc99fd5f..9135e2101752 100644 --- a/drivers/rtc/rtc-mt6397.c +++ b/drivers/rtc/rtc-mt6397.c @@ -47,7 +47,7 @@ static irqreturn_t mtk_rtc_irq_handler_thread(int irq, void *data) irqen = irqsta & ~RTC_IRQ_EN_AL; mutex_lock(&rtc->lock); if (regmap_write(rtc->regmap, rtc->addr_base + RTC_IRQ_EN, - irqen) < 0) + irqen) == 0) mtk_rtc_write_trigger(rtc); mutex_unlock(&rtc->lock); @@ -169,12 +169,12 @@ static int mtk_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alm) alm->pending = !!(pdn2 & RTC_PDN2_PWRON_ALARM); mutex_unlock(&rtc->lock); - tm->tm_sec = data[RTC_OFFSET_SEC]; - tm->tm_min = data[RTC_OFFSET_MIN]; - tm->tm_hour = data[RTC_OFFSET_HOUR]; - tm->tm_mday = data[RTC_OFFSET_DOM]; - tm->tm_mon = data[RTC_OFFSET_MTH]; - tm->tm_year = data[RTC_OFFSET_YEAR]; + tm->tm_sec = data[RTC_OFFSET_SEC] & RTC_AL_SEC_MASK; + tm->tm_min = data[RTC_OFFSET_MIN] & RTC_AL_MIN_MASK; + tm->tm_hour = data[RTC_OFFSET_HOUR] & RTC_AL_HOU_MASK; + tm->tm_mday = data[RTC_OFFSET_DOM] & RTC_AL_DOM_MASK; + tm->tm_mon = data[RTC_OFFSET_MTH] & RTC_AL_MTH_MASK; + tm->tm_year = data[RTC_OFFSET_YEAR] & RTC_AL_YEA_MASK; tm->tm_year += RTC_MIN_YEAR_OFFSET; tm->tm_mon--; @@ -195,14 +195,25 @@ static int mtk_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alm) tm->tm_year -= RTC_MIN_YEAR_OFFSET; tm->tm_mon++; - data[RTC_OFFSET_SEC] = tm->tm_sec; - data[RTC_OFFSET_MIN] = tm->tm_min; - data[RTC_OFFSET_HOUR] = tm->tm_hour; - data[RTC_OFFSET_DOM] = tm->tm_mday; - data[RTC_OFFSET_MTH] = tm->tm_mon; - data[RTC_OFFSET_YEAR] = tm->tm_year; - mutex_lock(&rtc->lock); + ret = regmap_bulk_read(rtc->regmap, rtc->addr_base + RTC_AL_SEC, + data, RTC_OFFSET_COUNT); + if (ret < 0) + goto exit; + + data[RTC_OFFSET_SEC] = ((data[RTC_OFFSET_SEC] & ~(RTC_AL_SEC_MASK)) | + (tm->tm_sec & RTC_AL_SEC_MASK)); + data[RTC_OFFSET_MIN] = ((data[RTC_OFFSET_MIN] & ~(RTC_AL_MIN_MASK)) | + (tm->tm_min & RTC_AL_MIN_MASK)); + data[RTC_OFFSET_HOUR] = ((data[RTC_OFFSET_HOUR] & ~(RTC_AL_HOU_MASK)) | + (tm->tm_hour & RTC_AL_HOU_MASK)); + data[RTC_OFFSET_DOM] = ((data[RTC_OFFSET_DOM] & ~(RTC_AL_DOM_MASK)) | + (tm->tm_mday & RTC_AL_DOM_MASK)); + data[RTC_OFFSET_MTH] = ((data[RTC_OFFSET_MTH] & ~(RTC_AL_MTH_MASK)) | + (tm->tm_mon & RTC_AL_MTH_MASK)); + data[RTC_OFFSET_YEAR] = ((data[RTC_OFFSET_YEAR] & ~(RTC_AL_YEA_MASK)) | + (tm->tm_year & RTC_AL_YEA_MASK)); + if (alm->enabled) { ret = regmap_bulk_write(rtc->regmap, rtc->addr_base + RTC_AL_SEC, diff --git a/include/linux/mfd/mt6397/rtc.h b/include/linux/mfd/mt6397/rtc.h index f84b9163c0ee..7dfb63b81373 100644 --- a/include/linux/mfd/mt6397/rtc.h +++ b/include/linux/mfd/mt6397/rtc.h @@ -46,6 +46,14 @@ #define RTC_AL_SEC 0x0018 +#define RTC_AL_SEC_MASK 0x003f +#define RTC_AL_MIN_MASK 0x003f +#define RTC_AL_HOU_MASK 0x001f +#define RTC_AL_DOM_MASK 0x001f +#define RTC_AL_DOW_MASK 0x0007 +#define RTC_AL_MTH_MASK 0x000f +#define RTC_AL_YEA_MASK 0x007f + #define RTC_PDN2 0x002e #define RTC_PDN2_PWRON_ALARM BIT(4) -- cgit v1.2.3 From f729a1b0f8df7091cea3729fc0e414f5326e1163 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 13 Dec 2019 14:06:58 -0800 Subject: Input: input_event - fix struct padding on sparc64 Going through all uses of timeval, I noticed that we screwed up input_event in the previous attempts to fix it: The time fields now match between kernel and user space, but all following fields are in the wrong place. Add the required padding that is implied by the glibc timeval definition to fix the layout, and use a struct initializer to avoid leaking kernel stack data. Fixes: 141e5dcaa735 ("Input: input_event - fix the CONFIG_SPARC64 mixup") Fixes: 2e746942ebac ("Input: input_event - provide override for sparc64") Signed-off-by: Arnd Bergmann Link: https://lore.kernel.org/r/20191213204936.3643476-2-arnd@arndb.de Cc: stable@vger.kernel.org Signed-off-by: Dmitry Torokhov --- drivers/input/evdev.c | 14 +++++++------- drivers/input/misc/uinput.c | 14 +++++++++----- include/uapi/linux/input.h | 1 + 3 files changed, 17 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/drivers/input/evdev.c b/drivers/input/evdev.c index d7dd6fcf2db0..f918fca9ada3 100644 --- a/drivers/input/evdev.c +++ b/drivers/input/evdev.c @@ -224,13 +224,13 @@ static void __pass_event(struct evdev_client *client, */ client->tail = (client->head - 2) & (client->bufsize - 1); - client->buffer[client->tail].input_event_sec = - event->input_event_sec; - client->buffer[client->tail].input_event_usec = - event->input_event_usec; - client->buffer[client->tail].type = EV_SYN; - client->buffer[client->tail].code = SYN_DROPPED; - client->buffer[client->tail].value = 0; + client->buffer[client->tail] = (struct input_event) { + .input_event_sec = event->input_event_sec, + .input_event_usec = event->input_event_usec, + .type = EV_SYN, + .code = SYN_DROPPED, + .value = 0, + }; client->packet_head = client->tail; } diff --git a/drivers/input/misc/uinput.c b/drivers/input/misc/uinput.c index 0bb456015d8f..f2593133e524 100644 --- a/drivers/input/misc/uinput.c +++ b/drivers/input/misc/uinput.c @@ -74,12 +74,16 @@ static int uinput_dev_event(struct input_dev *dev, struct uinput_device *udev = input_get_drvdata(dev); struct timespec64 ts; - udev->buff[udev->head].type = type; - udev->buff[udev->head].code = code; - udev->buff[udev->head].value = value; ktime_get_ts64(&ts); - udev->buff[udev->head].input_event_sec = ts.tv_sec; - udev->buff[udev->head].input_event_usec = ts.tv_nsec / NSEC_PER_USEC; + + udev->buff[udev->head] = (struct input_event) { + .input_event_sec = ts.tv_sec, + .input_event_usec = ts.tv_nsec / NSEC_PER_USEC, + .type = type, + .code = code, + .value = value, + }; + udev->head = (udev->head + 1) % UINPUT_BUFFER_SIZE; wake_up_interruptible(&udev->waitq); diff --git a/include/uapi/linux/input.h b/include/uapi/linux/input.h index f056b2a00d5c..9a61c28ed3ae 100644 --- a/include/uapi/linux/input.h +++ b/include/uapi/linux/input.h @@ -34,6 +34,7 @@ struct input_event { __kernel_ulong_t __sec; #if defined(__sparc__) && defined(__arch64__) unsigned int __usec; + unsigned int __pad; #else __kernel_ulong_t __usec; #endif -- cgit v1.2.3 From bd085ef678b2cc8c38c105673dfe8ff8f5ec0c57 Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Sun, 22 Dec 2019 10:51:09 +0800 Subject: net: add bool confirm_neigh parameter for dst_ops.update_pmtu The MTU update code is supposed to be invoked in response to real networking events that update the PMTU. In IPv6 PMTU update function __ip6_rt_update_pmtu() we called dst_confirm_neigh() to update neighbor confirmed time. But for tunnel code, it will call pmtu before xmit, like: - tnl_update_pmtu() - skb_dst_update_pmtu() - ip6_rt_update_pmtu() - __ip6_rt_update_pmtu() - dst_confirm_neigh() If the tunnel remote dst mac address changed and we still do the neigh confirm, we will not be able to update neigh cache and ping6 remote will failed. So for this ip_tunnel_xmit() case, _EVEN_ if the MTU is changed, we should not be invoking dst_confirm_neigh() as we have no evidence of successful two-way communication at this point. On the other hand it is also important to keep the neigh reachability fresh for TCP flows, so we cannot remove this dst_confirm_neigh() call. To fix the issue, we have to add a new bool parameter for dst_ops.update_pmtu to choose whether we should do neigh update or not. I will add the parameter in this patch and set all the callers to true to comply with the previous way, and fix the tunnel code one by one on later patches. v5: No change. v4: No change. v3: Do not remove dst_confirm_neigh, but add a new bool parameter in dst_ops.update_pmtu to control whether we should do neighbor confirm. Also split the big patch to small ones for each area. v2: Remove dst_confirm_neigh in __ip6_rt_update_pmtu. Suggested-by: David Miller Reviewed-by: Guillaume Nault Acked-by: David Ahern Signed-off-by: Hangbin Liu Signed-off-by: David S. Miller --- drivers/net/gtp.c | 2 +- include/net/dst.h | 2 +- include/net/dst_ops.h | 3 ++- net/bridge/br_nf_core.c | 3 ++- net/decnet/dn_route.c | 6 ++++-- net/ipv4/inet_connection_sock.c | 2 +- net/ipv4/route.c | 9 ++++++--- net/ipv4/xfrm4_policy.c | 5 +++-- net/ipv6/inet6_connection_sock.c | 2 +- net/ipv6/ip6_gre.c | 2 +- net/ipv6/route.c | 22 +++++++++++++++------- net/ipv6/xfrm6_policy.c | 5 +++-- net/netfilter/ipvs/ip_vs_xmit.c | 2 +- net/sctp/transport.c | 2 +- 14 files changed, 42 insertions(+), 25 deletions(-) (limited to 'include') diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index e5b7d6d2286e..913062017be9 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -540,7 +540,7 @@ static int gtp_build_skb_ip4(struct sk_buff *skb, struct net_device *dev, mtu = dst_mtu(&rt->dst); } - rt->dst.ops->update_pmtu(&rt->dst, NULL, skb, mtu); + rt->dst.ops->update_pmtu(&rt->dst, NULL, skb, mtu, true); if (!skb_is_gso(skb) && (iph->frag_off & htons(IP_DF)) && mtu < ntohs(iph->tot_len)) { diff --git a/include/net/dst.h b/include/net/dst.h index 8224dad2ae94..593630e0e076 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -516,7 +516,7 @@ static inline void skb_dst_update_pmtu(struct sk_buff *skb, u32 mtu) struct dst_entry *dst = skb_dst(skb); if (dst && dst->ops->update_pmtu) - dst->ops->update_pmtu(dst, NULL, skb, mtu); + dst->ops->update_pmtu(dst, NULL, skb, mtu, true); } static inline void skb_tunnel_check_pmtu(struct sk_buff *skb, diff --git a/include/net/dst_ops.h b/include/net/dst_ops.h index 5ec645f27ee3..443863c7b8da 100644 --- a/include/net/dst_ops.h +++ b/include/net/dst_ops.h @@ -27,7 +27,8 @@ struct dst_ops { struct dst_entry * (*negative_advice)(struct dst_entry *); void (*link_failure)(struct sk_buff *); void (*update_pmtu)(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb, u32 mtu); + struct sk_buff *skb, u32 mtu, + bool confirm_neigh); void (*redirect)(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb); int (*local_out)(struct net *net, struct sock *sk, struct sk_buff *skb); diff --git a/net/bridge/br_nf_core.c b/net/bridge/br_nf_core.c index 2cdfc5d6c25d..8c69f0c95a8e 100644 --- a/net/bridge/br_nf_core.c +++ b/net/bridge/br_nf_core.c @@ -22,7 +22,8 @@ #endif static void fake_update_pmtu(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb, u32 mtu) + struct sk_buff *skb, u32 mtu, + bool confirm_neigh) { } diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index aea918135ec3..08c3dc45f1a4 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -110,7 +110,8 @@ static void dn_dst_ifdown(struct dst_entry *, struct net_device *dev, int how); static struct dst_entry *dn_dst_negative_advice(struct dst_entry *); static void dn_dst_link_failure(struct sk_buff *); static void dn_dst_update_pmtu(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb , u32 mtu); + struct sk_buff *skb , u32 mtu, + bool confirm_neigh); static void dn_dst_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb); static struct neighbour *dn_dst_neigh_lookup(const struct dst_entry *dst, @@ -251,7 +252,8 @@ static int dn_dst_gc(struct dst_ops *ops) * advertise to the other end). */ static void dn_dst_update_pmtu(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb, u32 mtu) + struct sk_buff *skb, u32 mtu, + bool confirm_neigh) { struct dn_route *rt = (struct dn_route *) dst; struct neighbour *n = rt->n; diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index e4c6e8b40490..18c0d5bffe12 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -1086,7 +1086,7 @@ struct dst_entry *inet_csk_update_pmtu(struct sock *sk, u32 mtu) if (!dst) goto out; } - dst->ops->update_pmtu(dst, sk, NULL, mtu); + dst->ops->update_pmtu(dst, sk, NULL, mtu, true); dst = __sk_dst_check(sk, 0); if (!dst) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index f88c93c38f11..87e979f2b74a 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -139,7 +139,8 @@ static unsigned int ipv4_mtu(const struct dst_entry *dst); static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst); static void ipv4_link_failure(struct sk_buff *skb); static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb, u32 mtu); + struct sk_buff *skb, u32 mtu, + bool confirm_neigh); static void ip_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb); static void ipv4_dst_destroy(struct dst_entry *dst); @@ -1043,7 +1044,8 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu) } static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb, u32 mtu) + struct sk_buff *skb, u32 mtu, + bool confirm_neigh) { struct rtable *rt = (struct rtable *) dst; struct flowi4 fl4; @@ -2687,7 +2689,8 @@ static unsigned int ipv4_blackhole_mtu(const struct dst_entry *dst) } static void ipv4_rt_blackhole_update_pmtu(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb, u32 mtu) + struct sk_buff *skb, u32 mtu, + bool confirm_neigh) { } diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index 35b84b52b702..9ebd54752e03 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -100,12 +100,13 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, } static void xfrm4_update_pmtu(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb, u32 mtu) + struct sk_buff *skb, u32 mtu, + bool confirm_neigh) { struct xfrm_dst *xdst = (struct xfrm_dst *)dst; struct dst_entry *path = xdst->route; - path->ops->update_pmtu(path, sk, skb, mtu); + path->ops->update_pmtu(path, sk, skb, mtu, confirm_neigh); } static void xfrm4_redirect(struct dst_entry *dst, struct sock *sk, diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c index fe9cb8d1adca..e315526fa244 100644 --- a/net/ipv6/inet6_connection_sock.c +++ b/net/ipv6/inet6_connection_sock.c @@ -146,7 +146,7 @@ struct dst_entry *inet6_csk_update_pmtu(struct sock *sk, u32 mtu) if (IS_ERR(dst)) return NULL; - dst->ops->update_pmtu(dst, sk, NULL, mtu); + dst->ops->update_pmtu(dst, sk, NULL, mtu, true); dst = inet6_csk_route_socket(sk, &fl6); return IS_ERR(dst) ? NULL : dst; diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 9d0965252ddf..3ba69174ad6c 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -1040,7 +1040,7 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, /* TooBig packet may have updated dst->dev's mtu */ if (!t->parms.collect_md && dst && dst_mtu(dst) > dst->dev->mtu) - dst->ops->update_pmtu(dst, NULL, skb, dst->dev->mtu); + dst->ops->update_pmtu(dst, NULL, skb, dst->dev->mtu, true); err = ip6_tnl_xmit(skb, dev, dsfield, &fl6, encap_limit, &mtu, NEXTHDR_GRE); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index b59940416cb5..affb51c11a25 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -95,7 +95,8 @@ static int ip6_pkt_prohibit(struct sk_buff *skb); static int ip6_pkt_prohibit_out(struct net *net, struct sock *sk, struct sk_buff *skb); static void ip6_link_failure(struct sk_buff *skb); static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb, u32 mtu); + struct sk_buff *skb, u32 mtu, + bool confirm_neigh); static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb); static int rt6_score_route(const struct fib6_nh *nh, u32 fib6_flags, int oif, @@ -264,7 +265,8 @@ static unsigned int ip6_blackhole_mtu(const struct dst_entry *dst) } static void ip6_rt_blackhole_update_pmtu(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb, u32 mtu) + struct sk_buff *skb, u32 mtu, + bool confirm_neigh) { } @@ -2692,7 +2694,8 @@ static bool rt6_cache_allowed_for_pmtu(const struct rt6_info *rt) } static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk, - const struct ipv6hdr *iph, u32 mtu) + const struct ipv6hdr *iph, u32 mtu, + bool confirm_neigh) { const struct in6_addr *daddr, *saddr; struct rt6_info *rt6 = (struct rt6_info *)dst; @@ -2710,7 +2713,10 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk, daddr = NULL; saddr = NULL; } - dst_confirm_neigh(dst, daddr); + + if (confirm_neigh) + dst_confirm_neigh(dst, daddr); + mtu = max_t(u32, mtu, IPV6_MIN_MTU); if (mtu >= dst_mtu(dst)) return; @@ -2764,9 +2770,11 @@ out_unlock: } static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb, u32 mtu) + struct sk_buff *skb, u32 mtu, + bool confirm_neigh) { - __ip6_rt_update_pmtu(dst, sk, skb ? ipv6_hdr(skb) : NULL, mtu); + __ip6_rt_update_pmtu(dst, sk, skb ? ipv6_hdr(skb) : NULL, mtu, + confirm_neigh); } void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu, @@ -2785,7 +2793,7 @@ void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu, dst = ip6_route_output(net, NULL, &fl6); if (!dst->error) - __ip6_rt_update_pmtu(dst, NULL, iph, ntohl(mtu)); + __ip6_rt_update_pmtu(dst, NULL, iph, ntohl(mtu), true); dst_release(dst); } EXPORT_SYMBOL_GPL(ip6_update_pmtu); diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 699e0730ce8e..af7a4b8b1e9c 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -98,12 +98,13 @@ static int xfrm6_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, } static void xfrm6_update_pmtu(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb, u32 mtu) + struct sk_buff *skb, u32 mtu, + bool confirm_neigh) { struct xfrm_dst *xdst = (struct xfrm_dst *)dst; struct dst_entry *path = xdst->route; - path->ops->update_pmtu(path, sk, skb, mtu); + path->ops->update_pmtu(path, sk, skb, mtu, confirm_neigh); } static void xfrm6_redirect(struct dst_entry *dst, struct sock *sk, diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index b1e300f8881b..b00866d777fe 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -208,7 +208,7 @@ static inline void maybe_update_pmtu(int skb_af, struct sk_buff *skb, int mtu) struct rtable *ort = skb_rtable(skb); if (!skb->dev && sk && sk_fullsock(sk)) - ort->dst.ops->update_pmtu(&ort->dst, sk, NULL, mtu); + ort->dst.ops->update_pmtu(&ort->dst, sk, NULL, mtu, true); } static inline bool ensure_mtu_is_adequate(struct netns_ipvs *ipvs, int skb_af, diff --git a/net/sctp/transport.c b/net/sctp/transport.c index 7235a6032671..3bbe1a58ec87 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -263,7 +263,7 @@ bool sctp_transport_update_pmtu(struct sctp_transport *t, u32 pmtu) pf->af->from_sk(&addr, sk); pf->to_sk_daddr(&t->ipaddr, sk); - dst->ops->update_pmtu(dst, sk, NULL, pmtu); + dst->ops->update_pmtu(dst, sk, NULL, pmtu, true); pf->to_sk_daddr(&addr, sk); dst = sctp_transport_dst_check(t); -- cgit v1.2.3 From 07dc35c6e3cc3c001915d05f5bf21f80a39a0970 Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Sun, 22 Dec 2019 10:51:12 +0800 Subject: net/dst: add new function skb_dst_update_pmtu_no_confirm Add a new function skb_dst_update_pmtu_no_confirm() for callers who need update pmtu but should not do neighbor confirm. v5: No change. v4: No change. v3: Do not remove dst_confirm_neigh, but add a new bool parameter in dst_ops.update_pmtu to control whether we should do neighbor confirm. Also split the big patch to small ones for each area. v2: Remove dst_confirm_neigh in __ip6_rt_update_pmtu. Reviewed-by: Guillaume Nault Acked-by: David Ahern Signed-off-by: Hangbin Liu Signed-off-by: David S. Miller --- include/net/dst.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/net/dst.h b/include/net/dst.h index 593630e0e076..dc7cc1f1051c 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -519,6 +519,15 @@ static inline void skb_dst_update_pmtu(struct sk_buff *skb, u32 mtu) dst->ops->update_pmtu(dst, NULL, skb, mtu, true); } +/* update dst pmtu but not do neighbor confirm */ +static inline void skb_dst_update_pmtu_no_confirm(struct sk_buff *skb, u32 mtu) +{ + struct dst_entry *dst = skb_dst(skb); + + if (dst && dst->ops->update_pmtu) + dst->ops->update_pmtu(dst, NULL, skb, mtu, false); +} + static inline void skb_tunnel_check_pmtu(struct sk_buff *skb, struct dst_entry *encap_dst, int headroom) -- cgit v1.2.3 From f081042d128a0c7acbd67611def62e1b52e2d294 Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Sun, 22 Dec 2019 10:51:16 +0800 Subject: net/dst: do not confirm neighbor for vxlan and geneve pmtu update When do IPv6 tunnel PMTU update and calls __ip6_rt_update_pmtu() in the end, we should not call dst_confirm_neigh() as there is no two-way communication. So disable the neigh confirm for vxlan and geneve pmtu update. v5: No change. v4: No change. v3: Do not remove dst_confirm_neigh, but add a new bool parameter in dst_ops.update_pmtu to control whether we should do neighbor confirm. Also split the big patch to small ones for each area. v2: Remove dst_confirm_neigh in __ip6_rt_update_pmtu. Fixes: a93bf0ff4490 ("vxlan: update skb dst pmtu on tx path") Fixes: 52a589d51f10 ("geneve: update skb dst pmtu on tx path") Reviewed-by: Guillaume Nault Tested-by: Guillaume Nault Acked-by: David Ahern Signed-off-by: Hangbin Liu Signed-off-by: David S. Miller --- include/net/dst.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/dst.h b/include/net/dst.h index dc7cc1f1051c..3448cf865ede 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -535,7 +535,7 @@ static inline void skb_tunnel_check_pmtu(struct sk_buff *skb, u32 encap_mtu = dst_mtu(encap_dst); if (skb->len > encap_mtu - headroom) - skb_dst_update_pmtu(skb, encap_mtu - headroom); + skb_dst_update_pmtu_no_confirm(skb, encap_mtu - headroom); } #endif /* _NET_DST_H */ -- cgit v1.2.3 From 463f550fb47bede3a5d7d5177f363a6c3b45d50b Mon Sep 17 00:00:00 2001 From: Mathieu Desnoyers Date: Wed, 11 Dec 2019 11:17:12 -0500 Subject: rseq: Unregister rseq for clone CLONE_VM It has been reported by Google that rseq is not behaving properly with respect to clone when CLONE_VM is used without CLONE_THREAD. It keeps the prior thread's rseq TLS registered when the TLS of the thread has moved, so the kernel can corrupt the TLS of the parent. The approach of clearing the per task-struct rseq registration on clone with CLONE_THREAD flag is incomplete. It does not cover the use-case of clone with CLONE_VM set, but without CLONE_THREAD. Here is the rationale for unregistering rseq on clone with CLONE_VM flag set: 1) CLONE_THREAD requires CLONE_SIGHAND, which requires CLONE_VM to be set. Therefore, just checking for CLONE_VM covers all CLONE_THREAD uses. There is no point in checking for both CLONE_THREAD and CLONE_VM, 2) There is the possibility of an unlikely scenario where CLONE_SETTLS is used without CLONE_VM. In order to be an issue, it would require that the rseq TLS is in a shared memory area. I do not plan on adding CLONE_SETTLS to the set of clone flags which unregister RSEQ, because it would require that we also unregister RSEQ on set_thread_area(2) and arch_prctl(2) ARCH_SET_FS for completeness. So rather than doing a partial solution, it appears better to let user-space explicitly perform rseq unregistration across clone if needed in scenarios where CLONE_VM is not set. Signed-off-by: Mathieu Desnoyers Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: https://lkml.kernel.org/r/20191211161713.4490-3-mathieu.desnoyers@efficios.com Signed-off-by: Ingo Molnar --- include/linux/sched.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index 467d26046416..716ad1d8d95e 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1929,11 +1929,11 @@ static inline void rseq_migrate(struct task_struct *t) /* * If parent process has a registered restartable sequences area, the - * child inherits. Only applies when forking a process, not a thread. + * child inherits. Unregister rseq for a clone with CLONE_VM set. */ static inline void rseq_fork(struct task_struct *t, unsigned long clone_flags) { - if (clone_flags & CLONE_THREAD) { + if (clone_flags & CLONE_VM) { t->rseq = NULL; t->rseq_sig = 0; t->rseq_event_mask = 0; -- cgit v1.2.3 From 8385d756e114f2df8568e508902d5f9850817ffb Mon Sep 17 00:00:00 2001 From: Sascha Hauer Date: Fri, 13 Dec 2019 09:04:08 +0100 Subject: libata: Fix retrieving of active qcs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit ata_qc_complete_multiple() is called with a mask of the still active tags. mv_sata doesn't have this information directly and instead calculates the still active tags from the started tags (ap->qc_active) and the finished tags as (ap->qc_active ^ done_mask) Since 28361c40368 the hw_tag and tag are no longer the same and the equation is no longer valid. In ata_exec_internal_sg() ap->qc_active is initialized as 1ULL << ATA_TAG_INTERNAL, but in hardware tag 0 is started and this will be in done_mask on completion. ap->qc_active ^ done_mask becomes 0x100000000 ^ 0x1 = 0x100000001 and thus tag 0 used as the internal tag will never be reported as completed. This is fixed by introducing ata_qc_get_active() which returns the active hardware tags and calling it where appropriate. This is tested on mv_sata, but sata_fsl and sata_nv suffer from the same problem. There is another case in sata_nv that most likely needs fixing as well, but this looks a little different, so I wasn't confident enough to change that. Fixes: 28361c403683 ("libata: add extra internal command") Cc: stable@vger.kernel.org Tested-by: Pali Rohár Signed-off-by: Sascha Hauer Add missing export of ata_qc_get_active(), as per Pali. Signed-off-by: Jens Axboe --- drivers/ata/libata-core.c | 24 ++++++++++++++++++++++++ drivers/ata/sata_fsl.c | 2 +- drivers/ata/sata_mv.c | 2 +- drivers/ata/sata_nv.c | 2 +- include/linux/libata.h | 1 + 5 files changed, 28 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index e9017c570bc5..6f4ab5c5b52d 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -5328,6 +5328,30 @@ void ata_qc_complete(struct ata_queued_cmd *qc) } } +/** + * ata_qc_get_active - get bitmask of active qcs + * @ap: port in question + * + * LOCKING: + * spin_lock_irqsave(host lock) + * + * RETURNS: + * Bitmask of active qcs + */ +u64 ata_qc_get_active(struct ata_port *ap) +{ + u64 qc_active = ap->qc_active; + + /* ATA_TAG_INTERNAL is sent to hw as tag 0 */ + if (qc_active & (1ULL << ATA_TAG_INTERNAL)) { + qc_active |= (1 << 0); + qc_active &= ~(1ULL << ATA_TAG_INTERNAL); + } + + return qc_active; +} +EXPORT_SYMBOL_GPL(ata_qc_get_active); + /** * ata_qc_complete_multiple - Complete multiple qcs successfully * @ap: port in question diff --git a/drivers/ata/sata_fsl.c b/drivers/ata/sata_fsl.c index 9239615d8a04..d55ee244d693 100644 --- a/drivers/ata/sata_fsl.c +++ b/drivers/ata/sata_fsl.c @@ -1280,7 +1280,7 @@ static void sata_fsl_host_intr(struct ata_port *ap) i, ioread32(hcr_base + CC), ioread32(hcr_base + CA)); } - ata_qc_complete_multiple(ap, ap->qc_active ^ done_mask); + ata_qc_complete_multiple(ap, ata_qc_get_active(ap) ^ done_mask); return; } else if ((ap->qc_active & (1ULL << ATA_TAG_INTERNAL))) { diff --git a/drivers/ata/sata_mv.c b/drivers/ata/sata_mv.c index 277f11909fc1..d7228f8e9297 100644 --- a/drivers/ata/sata_mv.c +++ b/drivers/ata/sata_mv.c @@ -2829,7 +2829,7 @@ static void mv_process_crpb_entries(struct ata_port *ap, struct mv_port_priv *pp } if (work_done) { - ata_qc_complete_multiple(ap, ap->qc_active ^ done_mask); + ata_qc_complete_multiple(ap, ata_qc_get_active(ap) ^ done_mask); /* Update the software queue position index in hardware */ writelfl((pp->crpb_dma & EDMA_RSP_Q_BASE_LO_MASK) | diff --git a/drivers/ata/sata_nv.c b/drivers/ata/sata_nv.c index f3e62f5528bd..eb9dc14e5147 100644 --- a/drivers/ata/sata_nv.c +++ b/drivers/ata/sata_nv.c @@ -984,7 +984,7 @@ static irqreturn_t nv_adma_interrupt(int irq, void *dev_instance) check_commands = 0; check_commands &= ~(1 << pos); } - ata_qc_complete_multiple(ap, ap->qc_active ^ done_mask); + ata_qc_complete_multiple(ap, ata_qc_get_active(ap) ^ done_mask); } } diff --git a/include/linux/libata.h b/include/linux/libata.h index d3bbfddf616a..2dbde119721d 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -1175,6 +1175,7 @@ extern unsigned int ata_do_dev_read_id(struct ata_device *dev, struct ata_taskfile *tf, u16 *id); extern void ata_qc_complete(struct ata_queued_cmd *qc); extern int ata_qc_complete_multiple(struct ata_port *ap, u64 qc_active); +extern u64 ata_qc_get_active(struct ata_port *ap); extern void ata_scsi_simulate(struct ata_device *dev, struct scsi_cmnd *cmd); extern int ata_std_bios_param(struct scsi_device *sdev, struct block_device *bdev, -- cgit v1.2.3 From 84b032dbfdf1c139cd2b864e43959510646975f8 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Tue, 10 Dec 2019 10:53:44 -0800 Subject: ata: libahci_platform: Export again ahci_platform_able_phys() This reverts commit 6bb86fefa086faba7b60bb452300b76a47cde1a5 ("libahci_platform: Staticize ahci_platform_able_phys()") we are going to need ahci_platform_{enable,disable}_phys() in a subsequent commit for ahci_brcm.c in order to properly control the PHY initialization order. Also make sure the function prototypes are declared in include/linux/ahci_platform.h as a result. Cc: stable@vger.kernel.org Reviewed-by: Hans de Goede Signed-off-by: Florian Fainelli Signed-off-by: Jens Axboe --- drivers/ata/libahci_platform.c | 6 ++++-- include/linux/ahci_platform.h | 2 ++ 2 files changed, 6 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/drivers/ata/libahci_platform.c b/drivers/ata/libahci_platform.c index 8befce036af8..129556fcf6be 100644 --- a/drivers/ata/libahci_platform.c +++ b/drivers/ata/libahci_platform.c @@ -43,7 +43,7 @@ EXPORT_SYMBOL_GPL(ahci_platform_ops); * RETURNS: * 0 on success otherwise a negative error code */ -static int ahci_platform_enable_phys(struct ahci_host_priv *hpriv) +int ahci_platform_enable_phys(struct ahci_host_priv *hpriv) { int rc, i; @@ -74,6 +74,7 @@ disable_phys: } return rc; } +EXPORT_SYMBOL_GPL(ahci_platform_enable_phys); /** * ahci_platform_disable_phys - Disable PHYs @@ -81,7 +82,7 @@ disable_phys: * * This function disables all PHYs found in hpriv->phys. */ -static void ahci_platform_disable_phys(struct ahci_host_priv *hpriv) +void ahci_platform_disable_phys(struct ahci_host_priv *hpriv) { int i; @@ -90,6 +91,7 @@ static void ahci_platform_disable_phys(struct ahci_host_priv *hpriv) phy_exit(hpriv->phys[i]); } } +EXPORT_SYMBOL_GPL(ahci_platform_disable_phys); /** * ahci_platform_enable_clks - Enable platform clocks diff --git a/include/linux/ahci_platform.h b/include/linux/ahci_platform.h index 6782f0d45ebe..49e5383d4222 100644 --- a/include/linux/ahci_platform.h +++ b/include/linux/ahci_platform.h @@ -19,6 +19,8 @@ struct ahci_host_priv; struct platform_device; struct scsi_host_template; +int ahci_platform_enable_phys(struct ahci_host_priv *hpriv); +void ahci_platform_disable_phys(struct ahci_host_priv *hpriv); int ahci_platform_enable_clks(struct ahci_host_priv *hpriv); void ahci_platform_disable_clks(struct ahci_host_priv *hpriv); int ahci_platform_enable_regulators(struct ahci_host_priv *hpriv); -- cgit v1.2.3 From 7df2281a174bd0fdbb2211a26914e5440740fcde Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Mon, 23 Dec 2019 11:03:21 +0100 Subject: of: mdio: Add missing inline to of_mdiobus_child_is_phy() dummy MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit If CONFIG_OF_MDIO=n: drivers/net/phy/mdio_bus.c:23: include/linux/of_mdio.h:58:13: warning: ‘of_mdiobus_child_is_phy’ defined but not used [-Wunused-function] static bool of_mdiobus_child_is_phy(struct device_node *child) ^~~~~~~~~~~~~~~~~~~~~~~ Fix this by adding the missing "inline" keyword. Fixes: 0aa4d016c043d16a ("of: mdio: export of_mdiobus_child_is_phy") Signed-off-by: Geert Uytterhoeven Reviewed-by: Andrew Lunn Acked-by: Borislav Petkov Signed-off-by: David S. Miller --- include/linux/of_mdio.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/of_mdio.h b/include/linux/of_mdio.h index 79bc82e30c02..491a2b7e77c1 100644 --- a/include/linux/of_mdio.h +++ b/include/linux/of_mdio.h @@ -55,7 +55,7 @@ static inline int of_mdio_parse_addr(struct device *dev, } #else /* CONFIG_OF_MDIO */ -static bool of_mdiobus_child_is_phy(struct device_node *child) +static inline bool of_mdiobus_child_is_phy(struct device_node *child) { return false; } -- cgit v1.2.3 From 862dd2a946aa1417f013fb748e2aa0f4349b405b Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 27 Dec 2019 03:24:17 +0200 Subject: spi: Don't look at TX buffer for PTP system timestamping The API for PTP system timestamping (associating a SPI transaction with the system time at which it was transferred) is flawed: it assumes that the xfer->tx_buf pointer will always be present. This is, of course, not always the case. So introduce a "progress" variable that denotes how many word have been transferred. Fix the Freescale DSPI driver, the only user of the API so far, in the same patch. Fixes: b42faeee718c ("spi: Add a PTP system timestamp to the transfer structure") Fixes: d6b71dfaeeba ("spi: spi-fsl-dspi: Implement the PTP system timestamping for TCFQ mode") Signed-off-by: Vladimir Oltean Link: https://lore.kernel.org/r/20191227012417.1057-1-olteanv@gmail.com Signed-off-by: Mark Brown --- drivers/spi/spi-fsl-dspi.c | 9 ++++++--- drivers/spi/spi.c | 22 ++++++++-------------- include/linux/spi/spi.h | 4 ++-- 3 files changed, 16 insertions(+), 19 deletions(-) (limited to 'include') diff --git a/drivers/spi/spi-fsl-dspi.c b/drivers/spi/spi-fsl-dspi.c index 442cff71a0d2..9c3934efe2b1 100644 --- a/drivers/spi/spi-fsl-dspi.c +++ b/drivers/spi/spi-fsl-dspi.c @@ -185,6 +185,7 @@ struct fsl_dspi { struct spi_transfer *cur_transfer; struct spi_message *cur_msg; struct chip_data *cur_chip; + size_t progress; size_t len; const void *tx; void *rx; @@ -658,7 +659,7 @@ static int dspi_rxtx(struct fsl_dspi *dspi) u32 spi_tcr; spi_take_timestamp_post(dspi->ctlr, dspi->cur_transfer, - dspi->tx - dspi->bytes_per_word, !dspi->irq); + dspi->progress, !dspi->irq); /* Get transfer counter (in number of SPI transfers). It was * reset to 0 when transfer(s) were started. @@ -667,6 +668,7 @@ static int dspi_rxtx(struct fsl_dspi *dspi) spi_tcnt = SPI_TCR_GET_TCNT(spi_tcr); /* Update total number of bytes that were transferred */ msg->actual_length += spi_tcnt * dspi->bytes_per_word; + dspi->progress += spi_tcnt; trans_mode = dspi->devtype_data->trans_mode; if (trans_mode == DSPI_EOQ_MODE) @@ -679,7 +681,7 @@ static int dspi_rxtx(struct fsl_dspi *dspi) return 0; spi_take_timestamp_pre(dspi->ctlr, dspi->cur_transfer, - dspi->tx, !dspi->irq); + dspi->progress, !dspi->irq); if (trans_mode == DSPI_EOQ_MODE) dspi_eoq_write(dspi); @@ -768,6 +770,7 @@ static int dspi_transfer_one_message(struct spi_controller *ctlr, dspi->rx = transfer->rx_buf; dspi->rx_end = dspi->rx + transfer->len; dspi->len = transfer->len; + dspi->progress = 0; /* Validated transfer specific frame size (defaults applied) */ dspi->bits_per_word = transfer->bits_per_word; if (transfer->bits_per_word <= 8) @@ -789,7 +792,7 @@ static int dspi_transfer_one_message(struct spi_controller *ctlr, SPI_CTARE_DTCP(1)); spi_take_timestamp_pre(dspi->ctlr, dspi->cur_transfer, - dspi->tx, !dspi->irq); + dspi->progress, !dspi->irq); trans_mode = dspi->devtype_data->trans_mode; switch (trans_mode) { diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index 0d40953b463c..6b95cd957ba7 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -1499,8 +1499,7 @@ static void spi_pump_messages(struct kthread_work *work) * advances its @tx buffer pointer monotonically. * @ctlr: Pointer to the spi_controller structure of the driver * @xfer: Pointer to the transfer being timestamped - * @tx: Pointer to the current word within the xfer->tx_buf that the driver is - * preparing to transmit right now. + * @progress: How many words (not bytes) have been transferred so far * @irqs_off: If true, will disable IRQs and preemption for the duration of the * transfer, for less jitter in time measurement. Only compatible * with PIO drivers. If true, must follow up with @@ -1510,21 +1509,19 @@ static void spi_pump_messages(struct kthread_work *work) */ void spi_take_timestamp_pre(struct spi_controller *ctlr, struct spi_transfer *xfer, - const void *tx, bool irqs_off) + size_t progress, bool irqs_off) { - u8 bytes_per_word = DIV_ROUND_UP(xfer->bits_per_word, 8); - if (!xfer->ptp_sts) return; if (xfer->timestamped_pre) return; - if (tx < (xfer->tx_buf + xfer->ptp_sts_word_pre * bytes_per_word)) + if (progress < xfer->ptp_sts_word_pre) return; /* Capture the resolution of the timestamp */ - xfer->ptp_sts_word_pre = (tx - xfer->tx_buf) / bytes_per_word; + xfer->ptp_sts_word_pre = progress; xfer->timestamped_pre = true; @@ -1546,23 +1543,20 @@ EXPORT_SYMBOL_GPL(spi_take_timestamp_pre); * timestamped. * @ctlr: Pointer to the spi_controller structure of the driver * @xfer: Pointer to the transfer being timestamped - * @tx: Pointer to the current word within the xfer->tx_buf that the driver has - * just transmitted. + * @progress: How many words (not bytes) have been transferred so far * @irqs_off: If true, will re-enable IRQs and preemption for the local CPU. */ void spi_take_timestamp_post(struct spi_controller *ctlr, struct spi_transfer *xfer, - const void *tx, bool irqs_off) + size_t progress, bool irqs_off) { - u8 bytes_per_word = DIV_ROUND_UP(xfer->bits_per_word, 8); - if (!xfer->ptp_sts) return; if (xfer->timestamped_post) return; - if (tx < (xfer->tx_buf + xfer->ptp_sts_word_post * bytes_per_word)) + if (progress < xfer->ptp_sts_word_post) return; ptp_read_system_postts(xfer->ptp_sts); @@ -1573,7 +1567,7 @@ void spi_take_timestamp_post(struct spi_controller *ctlr, } /* Capture the resolution of the timestamp */ - xfer->ptp_sts_word_post = (tx - xfer->tx_buf) / bytes_per_word; + xfer->ptp_sts_word_post = progress; xfer->timestamped_post = true; } diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 98fe8663033a..3a67a7e45633 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -689,10 +689,10 @@ extern void spi_finalize_current_transfer(struct spi_controller *ctlr); /* Helper calls for driver to timestamp transfer */ void spi_take_timestamp_pre(struct spi_controller *ctlr, struct spi_transfer *xfer, - const void *tx, bool irqs_off); + size_t progress, bool irqs_off); void spi_take_timestamp_post(struct spi_controller *ctlr, struct spi_transfer *xfer, - const void *tx, bool irqs_off); + size_t progress, bool irqs_off); /* the spi driver core manages memory for the spi_controller classdev */ extern struct spi_controller *__spi_alloc_controller(struct device *host, -- cgit v1.2.3 From 85a8ce62c2eabe28b9d76ca4eecf37922402df93 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Sat, 28 Dec 2019 07:05:48 +0800 Subject: block: add bio_truncate to fix guard_bio_eod Some filesystem, such as vfat, may send bio which crosses device boundary, and the worse thing is that the IO request starting within device boundaries can contain more than one segment past EOD. Commit dce30ca9e3b6 ("fs: fix guard_bio_eod to check for real EOD errors") tries to fix this issue by returning -EIO for this situation. However, this way lets fs user code lose chance to handle -EIO, then sync_inodes_sb() may hang for ever. Also the current truncating on last segment is dangerous by updating the last bvec, given bvec table becomes not immutable any more, and fs bio users may not retrieve the truncated pages via bio_for_each_segment_all() in its .end_io callback. Fixes this issue by supporting multi-segment truncating. And the approach is simpler: - just update bio size since block layer can make correct bvec with the updated bio size. Then bvec table becomes really immutable. - zero all truncated segments for read bio Cc: Carlos Maiolino Cc: linux-fsdevel@vger.kernel.org Fixed-by: dce30ca9e3b6 ("fs: fix guard_bio_eod to check for real EOD errors") Reported-by: syzbot+2b9e54155c8c25d8d165@syzkaller.appspotmail.com Signed-off-by: Ming Lei Signed-off-by: Jens Axboe --- block/bio.c | 39 +++++++++++++++++++++++++++++++++++++++ fs/buffer.c | 25 +------------------------ include/linux/bio.h | 1 + 3 files changed, 41 insertions(+), 24 deletions(-) (limited to 'include') diff --git a/block/bio.c b/block/bio.c index a5d75f6bf4c7..006bcc52a77e 100644 --- a/block/bio.c +++ b/block/bio.c @@ -538,6 +538,45 @@ void zero_fill_bio_iter(struct bio *bio, struct bvec_iter start) } EXPORT_SYMBOL(zero_fill_bio_iter); +void bio_truncate(struct bio *bio, unsigned new_size) +{ + struct bio_vec bv; + struct bvec_iter iter; + unsigned int done = 0; + bool truncated = false; + + if (new_size >= bio->bi_iter.bi_size) + return; + + if (bio_data_dir(bio) != READ) + goto exit; + + bio_for_each_segment(bv, bio, iter) { + if (done + bv.bv_len > new_size) { + unsigned offset; + + if (!truncated) + offset = new_size - done; + else + offset = 0; + zero_user(bv.bv_page, offset, bv.bv_len - offset); + truncated = true; + } + done += bv.bv_len; + } + + exit: + /* + * Don't touch bvec table here and make it really immutable, since + * fs bio user has to retrieve all pages via bio_for_each_segment_all + * in its .end_bio() callback. + * + * It is enough to truncate bio by updating .bi_size since we can make + * correct bvec with the updated .bi_size for drivers. + */ + bio->bi_iter.bi_size = new_size; +} + /** * bio_put - release a reference to a bio * @bio: bio to release reference to diff --git a/fs/buffer.c b/fs/buffer.c index d8c7242426bb..e94a6619464c 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -3034,8 +3034,6 @@ static void end_bio_bh_io_sync(struct bio *bio) void guard_bio_eod(int op, struct bio *bio) { sector_t maxsector; - struct bio_vec *bvec = bio_last_bvec_all(bio); - unsigned truncated_bytes; struct hd_struct *part; rcu_read_lock(); @@ -3061,28 +3059,7 @@ void guard_bio_eod(int op, struct bio *bio) if (likely((bio->bi_iter.bi_size >> 9) <= maxsector)) return; - /* Uhhuh. We've got a bio that straddles the device size! */ - truncated_bytes = bio->bi_iter.bi_size - (maxsector << 9); - - /* - * The bio contains more than one segment which spans EOD, just return - * and let IO layer turn it into an EIO - */ - if (truncated_bytes > bvec->bv_len) - return; - - /* Truncate the bio.. */ - bio->bi_iter.bi_size -= truncated_bytes; - bvec->bv_len -= truncated_bytes; - - /* ..and clear the end of the buffer for reads */ - if (op == REQ_OP_READ) { - struct bio_vec bv; - - mp_bvec_last_segment(bvec, &bv); - zero_user(bv.bv_page, bv.bv_offset + bv.bv_len, - truncated_bytes); - } + bio_truncate(bio, maxsector << 9); } static int submit_bh_wbc(int op, int op_flags, struct buffer_head *bh, diff --git a/include/linux/bio.h b/include/linux/bio.h index 3cdb84cdc488..853d92ceee64 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -470,6 +470,7 @@ extern struct bio *bio_copy_user_iov(struct request_queue *, gfp_t); extern int bio_uncopy_user(struct bio *); void zero_fill_bio_iter(struct bio *bio, struct bvec_iter iter); +void bio_truncate(struct bio *bio, unsigned new_size); static inline void zero_fill_bio(struct bio *bio) { -- cgit v1.2.3 From 4f0bd808134d73184054ad09173821c84f31dd5d Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Mon, 23 Dec 2019 13:00:03 +0200 Subject: asm-generic/nds32: don't redefine cacheflush primitives The commit c296d4dc13ae ("asm-generic: fix a compilation warning") changed asm-generic/cachflush.h to use static inlines instead of macros and as a result the nds32 build with CONFIG_CPU_CACHE_ALIASING=n fails: CC init/main.o In file included from arch/nds32/include/asm/cacheflush.h:43, from include/linux/highmem.h:12, from include/linux/pagemap.h:11, from include/linux/blkdev.h:16, from include/linux/blk-cgroup.h:23, from include/linux/writeback.h:14, from init/main.c:44: include/asm-generic/cacheflush.h:50:20: error: static declaration of 'flush_icache_range' follows non-static declaration static inline void flush_icache_range(unsigned long start, unsigned long end) ^~~~~~~~~~~~~~~~~~ In file included from include/linux/highmem.h:12, from include/linux/pagemap.h:11, from include/linux/blkdev.h:16, from include/linux/blk-cgroup.h:23, from include/linux/writeback.h:14, from init/main.c:44: arch/nds32/include/asm/cacheflush.h:11:6: note: previous declaration of 'flush_icache_range' was here void flush_icache_range(unsigned long start, unsigned long end); ^~~~~~~~~~~~~~~~~~ Surround the inline functions in asm-generic/cacheflush.h by ifdef's so that architectures could override them and add the required overrides to nds32. Fixes: c296d4dc13ae ("asm-generic: fix a compilation warning") Link: https://lore.kernel.org/lkml/201912212139.yptX8CsV%25lkp@intel.com/ Reported-by: kbuild test robot Signed-off-by: Mike Rapoport Reviewed-by: Greentime Hu Signed-off-by: Arnd Bergmann --- arch/nds32/include/asm/cacheflush.h | 11 +++++++---- include/asm-generic/cacheflush.h | 33 ++++++++++++++++++++++++++++++++- 2 files changed, 39 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/arch/nds32/include/asm/cacheflush.h b/arch/nds32/include/asm/cacheflush.h index d9ac7e6408ef..caddded56e77 100644 --- a/arch/nds32/include/asm/cacheflush.h +++ b/arch/nds32/include/asm/cacheflush.h @@ -9,7 +9,11 @@ #define PG_dcache_dirty PG_arch_1 void flush_icache_range(unsigned long start, unsigned long end); +#define flush_icache_range flush_icache_range + void flush_icache_page(struct vm_area_struct *vma, struct page *page); +#define flush_icache_page flush_icache_page + #ifdef CONFIG_CPU_CACHE_ALIASING void flush_cache_mm(struct mm_struct *mm); void flush_cache_dup_mm(struct mm_struct *mm); @@ -40,12 +44,11 @@ void invalidate_kernel_vmap_range(void *addr, int size); #define flush_dcache_mmap_unlock(mapping) xa_unlock_irq(&(mapping)->i_pages) #else -#include -#undef flush_icache_range -#undef flush_icache_page -#undef flush_icache_user_range void flush_icache_user_range(struct vm_area_struct *vma, struct page *page, unsigned long addr, int len); +#define flush_icache_user_range flush_icache_user_range + +#include #endif #endif /* __NDS32_CACHEFLUSH_H__ */ diff --git a/include/asm-generic/cacheflush.h b/include/asm-generic/cacheflush.h index a950a22c4890..cac7404b2bdd 100644 --- a/include/asm-generic/cacheflush.h +++ b/include/asm-generic/cacheflush.h @@ -11,71 +11,102 @@ * The cache doesn't need to be flushed when TLB entries change when * the cache is mapped to physical memory, not virtual memory */ +#ifndef flush_cache_all static inline void flush_cache_all(void) { } +#endif +#ifndef flush_cache_mm static inline void flush_cache_mm(struct mm_struct *mm) { } +#endif +#ifndef flush_cache_dup_mm static inline void flush_cache_dup_mm(struct mm_struct *mm) { } +#endif +#ifndef flush_cache_range static inline void flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end) { } +#endif +#ifndef flush_cache_page static inline void flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, unsigned long pfn) { } +#endif +#ifndef flush_dcache_page static inline void flush_dcache_page(struct page *page) { } +#endif +#ifndef flush_dcache_mmap_lock static inline void flush_dcache_mmap_lock(struct address_space *mapping) { } +#endif +#ifndef flush_dcache_mmap_unlock static inline void flush_dcache_mmap_unlock(struct address_space *mapping) { } +#endif +#ifndef flush_icache_range static inline void flush_icache_range(unsigned long start, unsigned long end) { } +#endif +#ifndef flush_icache_page static inline void flush_icache_page(struct vm_area_struct *vma, struct page *page) { } +#endif +#ifndef flush_icache_user_range static inline void flush_icache_user_range(struct vm_area_struct *vma, struct page *page, unsigned long addr, int len) { } +#endif +#ifndef flush_cache_vmap static inline void flush_cache_vmap(unsigned long start, unsigned long end) { } +#endif +#ifndef flush_cache_vunmap static inline void flush_cache_vunmap(unsigned long start, unsigned long end) { } +#endif -#define copy_to_user_page(vma, page, vaddr, dst, src, len) \ +#ifndef copy_to_user_page +#define copy_to_user_page(vma, page, vaddr, dst, src, len) \ do { \ memcpy(dst, src, len); \ flush_icache_user_range(vma, page, vaddr, len); \ } while (0) +#endif + +#ifndef copy_from_user_page #define copy_from_user_page(vma, page, vaddr, dst, src, len) \ memcpy(dst, src, len) +#endif #endif /* __ASM_CACHEFLUSH_H */ -- cgit v1.2.3 From 1f07dcc459d5f2c639f185f6e94829a0c79f2b4c Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 30 Dec 2019 12:01:56 -0800 Subject: kernel.h: Remove unused FIELD_SIZEOF() Now that all callers of FIELD_SIZEOF() have been converted to sizeof_field(), remove the unused prior macro. Signed-off-by: Kees Cook --- include/linux/kernel.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 3adcb39fa6f5..0d9db2a14f44 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -79,15 +79,6 @@ */ #define round_down(x, y) ((x) & ~__round_mask(x, y)) -/** - * FIELD_SIZEOF - get the size of a struct's field - * @t: the target struct - * @f: the target struct's field - * Return: the size of @f in the struct definition without having a - * declared instance of @t. - */ -#define FIELD_SIZEOF(t, f) (sizeof(((t*)0)->f)) - #define typeof_member(T, m) typeof(((T*)0)->m) #define DIV_ROUND_UP __KERNEL_DIV_ROUND_UP -- cgit v1.2.3 From a33121e5487b424339636b25c35d3a180eaa5f5e Mon Sep 17 00:00:00 2001 From: Vladis Dronov Date: Fri, 27 Dec 2019 03:26:27 +0100 Subject: ptp: fix the race between the release of ptp_clock and cdev In a case when a ptp chardev (like /dev/ptp0) is open but an underlying device is removed, closing this file leads to a race. This reproduces easily in a kvm virtual machine: ts# cat openptp0.c int main() { ... fp = fopen("/dev/ptp0", "r"); ... sleep(10); } ts# uname -r 5.5.0-rc3-46cf053e ts# cat /proc/cmdline ... slub_debug=FZP ts# modprobe ptp_kvm ts# ./openptp0 & [1] 670 opened /dev/ptp0, sleeping 10s... ts# rmmod ptp_kvm ts# ls /dev/ptp* ls: cannot access '/dev/ptp*': No such file or directory ts# ...woken up [ 48.010809] general protection fault: 0000 [#1] SMP [ 48.012502] CPU: 6 PID: 658 Comm: openptp0 Not tainted 5.5.0-rc3-46cf053e #25 [ 48.014624] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), ... [ 48.016270] RIP: 0010:module_put.part.0+0x7/0x80 [ 48.017939] RSP: 0018:ffffb3850073be00 EFLAGS: 00010202 [ 48.018339] RAX: 000000006b6b6b6b RBX: 6b6b6b6b6b6b6b6b RCX: ffff89a476c00ad0 [ 48.018936] RDX: fffff65a08d3ea08 RSI: 0000000000000247 RDI: 6b6b6b6b6b6b6b6b [ 48.019470] ... ^^^ a slub poison [ 48.023854] Call Trace: [ 48.024050] __fput+0x21f/0x240 [ 48.024288] task_work_run+0x79/0x90 [ 48.024555] do_exit+0x2af/0xab0 [ 48.024799] ? vfs_write+0x16a/0x190 [ 48.025082] do_group_exit+0x35/0x90 [ 48.025387] __x64_sys_exit_group+0xf/0x10 [ 48.025737] do_syscall_64+0x3d/0x130 [ 48.026056] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 48.026479] RIP: 0033:0x7f53b12082f6 [ 48.026792] ... [ 48.030945] Modules linked in: ptp i6300esb watchdog [last unloaded: ptp_kvm] [ 48.045001] Fixing recursive fault but reboot is needed! This happens in: static void __fput(struct file *file) { ... if (file->f_op->release) file->f_op->release(inode, file); <<< cdev is kfree'd here if (unlikely(S_ISCHR(inode->i_mode) && inode->i_cdev != NULL && !(mode & FMODE_PATH))) { cdev_put(inode->i_cdev); <<< cdev fields are accessed here Namely: __fput() posix_clock_release() kref_put(&clk->kref, delete_clock) <<< the last reference delete_clock() delete_ptp_clock() kfree(ptp) <<< cdev is embedded in ptp cdev_put module_put(p->owner) <<< *p is kfree'd, bang! Here cdev is embedded in posix_clock which is embedded in ptp_clock. The race happens because ptp_clock's lifetime is controlled by two refcounts: kref and cdev.kobj in posix_clock. This is wrong. Make ptp_clock's sysfs device a parent of cdev with cdev_device_add() created especially for such cases. This way the parent device with its ptp_clock is not released until all references to the cdev are released. This adds a requirement that an initialized but not exposed struct device should be provided to posix_clock_register() by a caller instead of a simple dev_t. This approach was adopted from the commit 72139dfa2464 ("watchdog: Fix the race between the release of watchdog_core_data and cdev"). See details of the implementation in the commit 233ed09d7fda ("chardev: add helper function to register char devs with a struct device"). Link: https://lore.kernel.org/linux-fsdevel/20191125125342.6189-1-vdronov@redhat.com/T/#u Analyzed-by: Stephen Johnston Analyzed-by: Vern Lovejoy Signed-off-by: Vladis Dronov Acked-by: Richard Cochran Signed-off-by: David S. Miller --- drivers/ptp/ptp_clock.c | 31 ++++++++++++++----------------- drivers/ptp/ptp_private.h | 2 +- include/linux/posix-clock.h | 19 +++++++++++-------- kernel/time/posix-clock.c | 31 +++++++++++++------------------ 4 files changed, 39 insertions(+), 44 deletions(-) (limited to 'include') diff --git a/drivers/ptp/ptp_clock.c b/drivers/ptp/ptp_clock.c index e60eab7f8a61..61fafe0374ce 100644 --- a/drivers/ptp/ptp_clock.c +++ b/drivers/ptp/ptp_clock.c @@ -166,9 +166,9 @@ static struct posix_clock_operations ptp_clock_ops = { .read = ptp_read, }; -static void delete_ptp_clock(struct posix_clock *pc) +static void ptp_clock_release(struct device *dev) { - struct ptp_clock *ptp = container_of(pc, struct ptp_clock, clock); + struct ptp_clock *ptp = container_of(dev, struct ptp_clock, dev); mutex_destroy(&ptp->tsevq_mux); mutex_destroy(&ptp->pincfg_mux); @@ -213,7 +213,6 @@ struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info, } ptp->clock.ops = ptp_clock_ops; - ptp->clock.release = delete_ptp_clock; ptp->info = info; ptp->devid = MKDEV(major, index); ptp->index = index; @@ -236,15 +235,6 @@ struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info, if (err) goto no_pin_groups; - /* Create a new device in our class. */ - ptp->dev = device_create_with_groups(ptp_class, parent, ptp->devid, - ptp, ptp->pin_attr_groups, - "ptp%d", ptp->index); - if (IS_ERR(ptp->dev)) { - err = PTR_ERR(ptp->dev); - goto no_device; - } - /* Register a new PPS source. */ if (info->pps) { struct pps_source_info pps; @@ -260,8 +250,18 @@ struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info, } } - /* Create a posix clock. */ - err = posix_clock_register(&ptp->clock, ptp->devid); + /* Initialize a new device of our class in our clock structure. */ + device_initialize(&ptp->dev); + ptp->dev.devt = ptp->devid; + ptp->dev.class = ptp_class; + ptp->dev.parent = parent; + ptp->dev.groups = ptp->pin_attr_groups; + ptp->dev.release = ptp_clock_release; + dev_set_drvdata(&ptp->dev, ptp); + dev_set_name(&ptp->dev, "ptp%d", ptp->index); + + /* Create a posix clock and link it to the device. */ + err = posix_clock_register(&ptp->clock, &ptp->dev); if (err) { pr_err("failed to create posix clock\n"); goto no_clock; @@ -273,8 +273,6 @@ no_clock: if (ptp->pps_source) pps_unregister_source(ptp->pps_source); no_pps: - device_destroy(ptp_class, ptp->devid); -no_device: ptp_cleanup_pin_groups(ptp); no_pin_groups: if (ptp->kworker) @@ -304,7 +302,6 @@ int ptp_clock_unregister(struct ptp_clock *ptp) if (ptp->pps_source) pps_unregister_source(ptp->pps_source); - device_destroy(ptp_class, ptp->devid); ptp_cleanup_pin_groups(ptp); posix_clock_unregister(&ptp->clock); diff --git a/drivers/ptp/ptp_private.h b/drivers/ptp/ptp_private.h index 9171d42468fd..6b97155148f1 100644 --- a/drivers/ptp/ptp_private.h +++ b/drivers/ptp/ptp_private.h @@ -28,7 +28,7 @@ struct timestamp_event_queue { struct ptp_clock { struct posix_clock clock; - struct device *dev; + struct device dev; struct ptp_clock_info *info; dev_t devid; int index; /* index into clocks.map */ diff --git a/include/linux/posix-clock.h b/include/linux/posix-clock.h index fe6cfdcfbc26..468328b1e1dd 100644 --- a/include/linux/posix-clock.h +++ b/include/linux/posix-clock.h @@ -69,29 +69,32 @@ struct posix_clock_operations { * * @ops: Functional interface to the clock * @cdev: Character device instance for this clock - * @kref: Reference count. + * @dev: Pointer to the clock's device. * @rwsem: Protects the 'zombie' field from concurrent access. * @zombie: If 'zombie' is true, then the hardware has disappeared. - * @release: A function to free the structure when the reference count reaches - * zero. May be NULL if structure is statically allocated. * * Drivers should embed their struct posix_clock within a private * structure, obtaining a reference to it during callbacks using * container_of(). + * + * Drivers should supply an initialized but not exposed struct device + * to posix_clock_register(). It is used to manage lifetime of the + * driver's private structure. It's 'release' field should be set to + * a release function for this private structure. */ struct posix_clock { struct posix_clock_operations ops; struct cdev cdev; - struct kref kref; + struct device *dev; struct rw_semaphore rwsem; bool zombie; - void (*release)(struct posix_clock *clk); }; /** * posix_clock_register() - register a new clock - * @clk: Pointer to the clock. Caller must provide 'ops' and 'release' - * @devid: Allocated device id + * @clk: Pointer to the clock. Caller must provide 'ops' field + * @dev: Pointer to the initialized device. Caller must provide + * 'release' field * * A clock driver calls this function to register itself with the * clock device subsystem. If 'clk' points to dynamically allocated @@ -100,7 +103,7 @@ struct posix_clock { * * Returns zero on success, non-zero otherwise. */ -int posix_clock_register(struct posix_clock *clk, dev_t devid); +int posix_clock_register(struct posix_clock *clk, struct device *dev); /** * posix_clock_unregister() - unregister a clock diff --git a/kernel/time/posix-clock.c b/kernel/time/posix-clock.c index ec960bb939fd..200fb2d3be99 100644 --- a/kernel/time/posix-clock.c +++ b/kernel/time/posix-clock.c @@ -14,8 +14,6 @@ #include "posix-timers.h" -static void delete_clock(struct kref *kref); - /* * Returns NULL if the posix_clock instance attached to 'fp' is old and stale. */ @@ -125,7 +123,7 @@ static int posix_clock_open(struct inode *inode, struct file *fp) err = 0; if (!err) { - kref_get(&clk->kref); + get_device(clk->dev); fp->private_data = clk; } out: @@ -141,7 +139,7 @@ static int posix_clock_release(struct inode *inode, struct file *fp) if (clk->ops.release) err = clk->ops.release(clk); - kref_put(&clk->kref, delete_clock); + put_device(clk->dev); fp->private_data = NULL; @@ -161,38 +159,35 @@ static const struct file_operations posix_clock_file_operations = { #endif }; -int posix_clock_register(struct posix_clock *clk, dev_t devid) +int posix_clock_register(struct posix_clock *clk, struct device *dev) { int err; - kref_init(&clk->kref); init_rwsem(&clk->rwsem); cdev_init(&clk->cdev, &posix_clock_file_operations); + err = cdev_device_add(&clk->cdev, dev); + if (err) { + pr_err("%s unable to add device %d:%d\n", + dev_name(dev), MAJOR(dev->devt), MINOR(dev->devt)); + return err; + } clk->cdev.owner = clk->ops.owner; - err = cdev_add(&clk->cdev, devid, 1); + clk->dev = dev; - return err; + return 0; } EXPORT_SYMBOL_GPL(posix_clock_register); -static void delete_clock(struct kref *kref) -{ - struct posix_clock *clk = container_of(kref, struct posix_clock, kref); - - if (clk->release) - clk->release(clk); -} - void posix_clock_unregister(struct posix_clock *clk) { - cdev_del(&clk->cdev); + cdev_device_del(&clk->cdev, clk->dev); down_write(&clk->rwsem); clk->zombie = true; up_write(&clk->rwsem); - kref_put(&clk->kref, delete_clock); + put_device(clk->dev); } EXPORT_SYMBOL_GPL(posix_clock_unregister); -- cgit v1.2.3 From a5b72a083da197b493c7ed1e5730d62d3199f7d6 Mon Sep 17 00:00:00 2001 From: Davide Caratti Date: Sat, 28 Dec 2019 16:36:58 +0100 Subject: net/sched: add delete_empty() to filters and use it in cls_flower Revert "net/sched: cls_u32: fix refcount leak in the error path of u32_change()", and fix the u32 refcount leak in a more generic way that preserves the semantic of rule dumping. On tc filters that don't support lockless insertion/removal, there is no need to guard against concurrent insertion when a removal is in progress. Therefore, for most of them we can avoid a full walk() when deleting, and just decrease the refcount, like it was done on older Linux kernels. This fixes situations where walk() was wrongly detecting a non-empty filter, like it happened with cls_u32 in the error path of change(), thus leading to failures in the following tdc selftests: 6aa7: (filter, u32) Add/Replace u32 with source match and invalid indev 6658: (filter, u32) Add/Replace u32 with custom hash table and invalid handle 74c2: (filter, u32) Add/Replace u32 filter with invalid hash table id On cls_flower, and on (future) lockless filters, this check is necessary: move all the check_empty() logic in a callback so that each filter can have its own implementation. For cls_flower, it's sufficient to check if no IDRs have been allocated. This reverts commit 275c44aa194b7159d1191817b20e076f55f0e620. Changes since v1: - document the need for delete_empty() when TCF_PROTO_OPS_DOIT_UNLOCKED is used, thanks to Vlad Buslov - implement delete_empty() without doing fl_walk(), thanks to Vlad Buslov - squash revert and new fix in a single patch, to be nice with bisect tests that run tdc on u32 filter, thanks to Dave Miller Fixes: 275c44aa194b ("net/sched: cls_u32: fix refcount leak in the error path of u32_change()") Fixes: 6676d5e416ee ("net: sched: set dedicated tcf_walker flag when tp is empty") Suggested-by: Jamal Hadi Salim Suggested-by: Vlad Buslov Signed-off-by: Davide Caratti Reviewed-by: Vlad Buslov Tested-by: Jamal Hadi Salim Acked-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- include/net/sch_generic.h | 5 +++++ net/sched/cls_api.c | 31 +++++-------------------------- net/sched/cls_flower.c | 12 ++++++++++++ net/sched/cls_u32.c | 25 ------------------------- 4 files changed, 22 insertions(+), 51 deletions(-) (limited to 'include') diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 144f264ea394..fceddf89592a 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -308,6 +308,7 @@ struct tcf_proto_ops { int (*delete)(struct tcf_proto *tp, void *arg, bool *last, bool rtnl_held, struct netlink_ext_ack *); + bool (*delete_empty)(struct tcf_proto *tp); void (*walk)(struct tcf_proto *tp, struct tcf_walker *arg, bool rtnl_held); int (*reoffload)(struct tcf_proto *tp, bool add, @@ -336,6 +337,10 @@ struct tcf_proto_ops { int flags; }; +/* Classifiers setting TCF_PROTO_OPS_DOIT_UNLOCKED in tcf_proto_ops->flags + * are expected to implement tcf_proto_ops->delete_empty(), otherwise race + * conditions can occur when filters are inserted/deleted simultaneously. + */ enum tcf_proto_ops_flags { TCF_PROTO_OPS_DOIT_UNLOCKED = 1, }; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 6a0eacafdb19..76e0d122616a 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -308,33 +308,12 @@ static void tcf_proto_put(struct tcf_proto *tp, bool rtnl_held, tcf_proto_destroy(tp, rtnl_held, true, extack); } -static int walker_check_empty(struct tcf_proto *tp, void *fh, - struct tcf_walker *arg) +static bool tcf_proto_check_delete(struct tcf_proto *tp) { - if (fh) { - arg->nonempty = true; - return -1; - } - return 0; -} - -static bool tcf_proto_is_empty(struct tcf_proto *tp, bool rtnl_held) -{ - struct tcf_walker walker = { .fn = walker_check_empty, }; - - if (tp->ops->walk) { - tp->ops->walk(tp, &walker, rtnl_held); - return !walker.nonempty; - } - return true; -} + if (tp->ops->delete_empty) + return tp->ops->delete_empty(tp); -static bool tcf_proto_check_delete(struct tcf_proto *tp, bool rtnl_held) -{ - spin_lock(&tp->lock); - if (tcf_proto_is_empty(tp, rtnl_held)) - tp->deleting = true; - spin_unlock(&tp->lock); + tp->deleting = true; return tp->deleting; } @@ -1751,7 +1730,7 @@ static void tcf_chain_tp_delete_empty(struct tcf_chain *chain, * concurrently. * Mark tp for deletion if it is empty. */ - if (!tp_iter || !tcf_proto_check_delete(tp, rtnl_held)) { + if (!tp_iter || !tcf_proto_check_delete(tp)) { mutex_unlock(&chain->filter_chain_lock); return; } diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 0d125de54285..b0f42e62dd76 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -2773,6 +2773,17 @@ static void fl_bind_class(void *fh, u32 classid, unsigned long cl) f->res.class = cl; } +static bool fl_delete_empty(struct tcf_proto *tp) +{ + struct cls_fl_head *head = fl_head_dereference(tp); + + spin_lock(&tp->lock); + tp->deleting = idr_is_empty(&head->handle_idr); + spin_unlock(&tp->lock); + + return tp->deleting; +} + static struct tcf_proto_ops cls_fl_ops __read_mostly = { .kind = "flower", .classify = fl_classify, @@ -2782,6 +2793,7 @@ static struct tcf_proto_ops cls_fl_ops __read_mostly = { .put = fl_put, .change = fl_change, .delete = fl_delete, + .delete_empty = fl_delete_empty, .walk = fl_walk, .reoffload = fl_reoffload, .hw_add = fl_hw_add, diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index 66c6bcec16cb..a0e6fac613de 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -1108,33 +1108,10 @@ erridr: return err; } -static bool u32_hnode_empty(struct tc_u_hnode *ht, bool *non_root_ht) -{ - int i; - - if (!ht) - return true; - if (!ht->is_root) { - *non_root_ht = true; - return false; - } - if (*non_root_ht) - return false; - if (ht->refcnt < 2) - return true; - - for (i = 0; i <= ht->divisor; i++) { - if (rtnl_dereference(ht->ht[i])) - return false; - } - return true; -} - static void u32_walk(struct tcf_proto *tp, struct tcf_walker *arg, bool rtnl_held) { struct tc_u_common *tp_c = tp->data; - bool non_root_ht = false; struct tc_u_hnode *ht; struct tc_u_knode *n; unsigned int h; @@ -1147,8 +1124,6 @@ static void u32_walk(struct tcf_proto *tp, struct tcf_walker *arg, ht = rtnl_dereference(ht->next)) { if (ht->prio != tp->prio) continue; - if (u32_hnode_empty(ht, &non_root_ht)) - return; if (arg->count >= arg->skip) { if (arg->fn(tp, ht, arg) < 0) { arg->stop = 1; -- cgit v1.2.3 From e7153bf70c3496bac00e7e4f395bb8d8394ac0ea Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Sat, 7 Dec 2019 19:34:18 +0100 Subject: can: can_dropped_invalid_skb(): ensure an initialized headroom in outgoing CAN sk_buffs KMSAN sysbot detected a read access to an untinitialized value in the headroom of an outgoing CAN related sk_buff. When using CAN sockets this area is filled appropriately - but when using a packet socket this initialization is missing. The problematic read access occurs in the CAN receive path which can only be triggered when the sk_buff is sent through a (virtual) CAN interface. So we check in the sending path whether we need to perform the missing initializations. Fixes: d3b58c47d330d ("can: replace timestamp as unique skb attribute") Reported-by: syzbot+b02ff0707a97e4e79ebb@syzkaller.appspotmail.com Signed-off-by: Oliver Hartkopp Tested-by: Oliver Hartkopp Cc: linux-stable # >= v4.1 Signed-off-by: Marc Kleine-Budde --- include/linux/can/dev.h | 34 ++++++++++++++++++++++++++++++++++ 1 file changed, 34 insertions(+) (limited to 'include') diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index 9b3c720a31b1..5e3d45525bd3 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -18,6 +18,7 @@ #include #include #include +#include #include /* @@ -91,6 +92,36 @@ struct can_priv { #define get_can_dlc(i) (min_t(__u8, (i), CAN_MAX_DLC)) #define get_canfd_dlc(i) (min_t(__u8, (i), CANFD_MAX_DLC)) +/* Check for outgoing skbs that have not been created by the CAN subsystem */ +static inline bool can_skb_headroom_valid(struct net_device *dev, + struct sk_buff *skb) +{ + /* af_packet creates a headroom of HH_DATA_MOD bytes which is fine */ + if (WARN_ON_ONCE(skb_headroom(skb) < sizeof(struct can_skb_priv))) + return false; + + /* af_packet does not apply CAN skb specific settings */ + if (skb->ip_summed == CHECKSUM_NONE) { + /* init headroom */ + can_skb_prv(skb)->ifindex = dev->ifindex; + can_skb_prv(skb)->skbcnt = 0; + + skb->ip_summed = CHECKSUM_UNNECESSARY; + + /* preform proper loopback on capable devices */ + if (dev->flags & IFF_ECHO) + skb->pkt_type = PACKET_LOOPBACK; + else + skb->pkt_type = PACKET_HOST; + + skb_reset_mac_header(skb); + skb_reset_network_header(skb); + skb_reset_transport_header(skb); + } + + return true; +} + /* Drop a given socketbuffer if it does not contain a valid CAN frame. */ static inline bool can_dropped_invalid_skb(struct net_device *dev, struct sk_buff *skb) @@ -108,6 +139,9 @@ static inline bool can_dropped_invalid_skb(struct net_device *dev, } else goto inval_skb; + if (!can_skb_headroom_valid(dev, skb)) + goto inval_skb; + return false; inval_skb: -- cgit v1.2.3 From 74f1a299107b9e1a563831a4ba85f769ab577164 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Wed, 1 Jan 2020 20:05:03 +0100 Subject: Revert "fs: remove ksys_dup()" This reverts commit 8243186f0cc7 ("fs: remove ksys_dup()") and the subsequent fix for it in commit 2d3145f8d280 ("early init: fix error handling when opening /dev/console"). Trying to use filp_open() and f_dupfd() instead of pseudo-syscalls caused more trouble than what is worth it: it requires accessing vfs internals and it turns out there were other bugs in it too. In particular, the file reference counting was wrong - because unlike the original "open+2*dup" sequence it used "filp_open+3*f_dupfd" and thus had an extra leaked file reference. That in turn then caused odd problems with Androidx86 long after boot becaue of how the extra reference to the console kept the session active even after all file descriptors had been closed. Reported-by: youling 257 Cc: Arvind Sankar Cc: Al Viro Signed-off-by: Dominik Brodowski Signed-off-by: Linus Torvalds --- fs/file.c | 7 ++++++- include/linux/syscalls.h | 1 + init/main.c | 26 ++++++-------------------- 3 files changed, 13 insertions(+), 21 deletions(-) (limited to 'include') diff --git a/fs/file.c b/fs/file.c index 2f4fcf985079..3da91a112bab 100644 --- a/fs/file.c +++ b/fs/file.c @@ -960,7 +960,7 @@ SYSCALL_DEFINE2(dup2, unsigned int, oldfd, unsigned int, newfd) return ksys_dup3(oldfd, newfd, 0); } -SYSCALL_DEFINE1(dup, unsigned int, fildes) +int ksys_dup(unsigned int fildes) { int ret = -EBADF; struct file *file = fget_raw(fildes); @@ -975,6 +975,11 @@ SYSCALL_DEFINE1(dup, unsigned int, fildes) return ret; } +SYSCALL_DEFINE1(dup, unsigned int, fildes) +{ + return ksys_dup(fildes); +} + int f_dupfd(unsigned int from, struct file *file, unsigned flags) { int err; diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 2960dedcfde8..5262b7a76d39 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -1232,6 +1232,7 @@ asmlinkage long sys_ni_syscall(void); */ int ksys_umount(char __user *name, int flags); +int ksys_dup(unsigned int fildes); int ksys_chroot(const char __user *filename); ssize_t ksys_write(unsigned int fd, const char __user *buf, size_t count); int ksys_chdir(const char __user *filename); diff --git a/init/main.c b/init/main.c index 1ecfd43ed464..2cd736059416 100644 --- a/init/main.c +++ b/init/main.c @@ -93,7 +93,6 @@ #include #include #include -#include #include #include @@ -1158,26 +1157,13 @@ static int __ref kernel_init(void *unused) void console_on_rootfs(void) { - struct file *file; - unsigned int i; - - /* Open /dev/console in kernelspace, this should never fail */ - file = filp_open("/dev/console", O_RDWR, 0); - if (IS_ERR(file)) - goto err_out; - - /* create stdin/stdout/stderr, this should never fail */ - for (i = 0; i < 3; i++) { - if (f_dupfd(i, file, 0) != i) - goto err_out; - } - - return; + /* Open the /dev/console as stdin, this should never fail */ + if (ksys_open((const char __user *) "/dev/console", O_RDWR, 0) < 0) + pr_err("Warning: unable to open an initial console.\n"); -err_out: - /* no panic -- this might not be fatal */ - pr_err("Warning: unable to open an initial console.\n"); - return; + /* create stdout/stderr */ + (void) ksys_dup(0); + (void) ksys_dup(0); } static noinline void __init kernel_init_freeable(void) -- cgit v1.2.3 From bf44f488e168368cae4139b4b33c3d0aaa11679c Mon Sep 17 00:00:00 2001 From: "Joel Fernandes (Google)" Date: Thu, 2 Jan 2020 14:46:25 -0500 Subject: tracing: Change offset type to s32 in preempt/irq tracepoints Discussion in the below link reported that symbols in modules can appear to be before _stext on ARM architecture, causing wrapping with the offsets of this tracepoint. Change the offset type to s32 to fix this. Link: http://lore.kernel.org/r/20191127154428.191095-1-antonio.borneo@st.com Link: http://lkml.kernel.org/r/20200102194625.226436-1-joel@joelfernandes.org Cc: Bjorn Helgaas Cc: David Sterba Cc: Ingo Molnar Cc: Mike Rapoport Cc: "Rafael J. Wysocki" Cc: Sakari Ailus Cc: Antonio Borneo Cc: stable@vger.kernel.org Fixes: d59158162e032 ("tracing: Add support for preempt and irq enable/disable events") Signed-off-by: Joel Fernandes (Google) Signed-off-by: Steven Rostedt (VMware) --- include/trace/events/preemptirq.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/trace/events/preemptirq.h b/include/trace/events/preemptirq.h index 95fba0471e5b..3f249e150c0c 100644 --- a/include/trace/events/preemptirq.h +++ b/include/trace/events/preemptirq.h @@ -18,13 +18,13 @@ DECLARE_EVENT_CLASS(preemptirq_template, TP_ARGS(ip, parent_ip), TP_STRUCT__entry( - __field(u32, caller_offs) - __field(u32, parent_offs) + __field(s32, caller_offs) + __field(s32, parent_offs) ), TP_fast_assign( - __entry->caller_offs = (u32)(ip - (unsigned long)_stext); - __entry->parent_offs = (u32)(parent_ip - (unsigned long)_stext); + __entry->caller_offs = (s32)(ip - (unsigned long)_stext); + __entry->parent_offs = (s32)(parent_ip - (unsigned long)_stext); ), TP_printk("caller=%pS parent=%pS", -- cgit v1.2.3 From feee6b2989165631b17ac6d4ccdbf6759254e85a Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Sat, 4 Jan 2020 12:59:33 -0800 Subject: mm/memory_hotplug: shrink zones when offlining memory We currently try to shrink a single zone when removing memory. We use the zone of the first page of the memory we are removing. If that memmap was never initialized (e.g., memory was never onlined), we will read garbage and can trigger kernel BUGs (due to a stale pointer): BUG: unable to handle page fault for address: 000000000000353d #PF: supervisor write access in kernel mode #PF: error_code(0x0002) - not-present page PGD 0 P4D 0 Oops: 0002 [#1] SMP PTI CPU: 1 PID: 7 Comm: kworker/u8:0 Not tainted 5.3.0-rc5-next-20190820+ #317 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.1-0-ga5cab58e9a3f-prebuilt.qemu.4 Workqueue: kacpi_hotplug acpi_hotplug_work_fn RIP: 0010:clear_zone_contiguous+0x5/0x10 Code: 48 89 c6 48 89 c3 e8 2a fe ff ff 48 85 c0 75 cf 5b 5d c3 c6 85 fd 05 00 00 01 5b 5d c3 0f 1f 840 RSP: 0018:ffffad2400043c98 EFLAGS: 00010246 RAX: 0000000000000000 RBX: 0000000200000000 RCX: 0000000000000000 RDX: 0000000000200000 RSI: 0000000000140000 RDI: 0000000000002f40 RBP: 0000000140000000 R08: 0000000000000000 R09: 0000000000000001 R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000140000 R13: 0000000000140000 R14: 0000000000002f40 R15: ffff9e3e7aff3680 FS: 0000000000000000(0000) GS:ffff9e3e7bb00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000000000000353d CR3: 0000000058610000 CR4: 00000000000006e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: __remove_pages+0x4b/0x640 arch_remove_memory+0x63/0x8d try_remove_memory+0xdb/0x130 __remove_memory+0xa/0x11 acpi_memory_device_remove+0x70/0x100 acpi_bus_trim+0x55/0x90 acpi_device_hotplug+0x227/0x3a0 acpi_hotplug_work_fn+0x1a/0x30 process_one_work+0x221/0x550 worker_thread+0x50/0x3b0 kthread+0x105/0x140 ret_from_fork+0x3a/0x50 Modules linked in: CR2: 000000000000353d Instead, shrink the zones when offlining memory or when onlining failed. Introduce and use remove_pfn_range_from_zone(() for that. We now properly shrink the zones, even if we have DIMMs whereby - Some memory blocks fall into no zone (never onlined) - Some memory blocks fall into multiple zones (offlined+re-onlined) - Multiple memory blocks that fall into different zones Drop the zone parameter (with a potential dubious value) from __remove_pages() and __remove_section(). Link: http://lkml.kernel.org/r/20191006085646.5768-6-david@redhat.com Fixes: f1dd2cd13c4b ("mm, memory_hotplug: do not associate hotadded memory to zones until online") [visible after d0dc12e86b319] Signed-off-by: David Hildenbrand Reviewed-by: Oscar Salvador Cc: Michal Hocko Cc: "Matthew Wilcox (Oracle)" Cc: "Aneesh Kumar K.V" Cc: Pavel Tatashin Cc: Greg Kroah-Hartman Cc: Dan Williams Cc: Logan Gunthorpe Cc: [5.0+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arm64/mm/mmu.c | 4 +--- arch/ia64/mm/init.c | 4 +--- arch/powerpc/mm/mem.c | 3 +-- arch/s390/mm/init.c | 4 +--- arch/sh/mm/init.c | 4 +--- arch/x86/mm/init_32.c | 4 +--- arch/x86/mm/init_64.c | 4 +--- include/linux/memory_hotplug.h | 7 +++++-- mm/memory_hotplug.c | 31 ++++++++++++++++--------------- mm/memremap.c | 2 +- 10 files changed, 29 insertions(+), 38 deletions(-) (limited to 'include') diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 5a3b15a14a7f..40797cbfba2d 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -1070,7 +1070,6 @@ void arch_remove_memory(int nid, u64 start, u64 size, { unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; - struct zone *zone; /* * FIXME: Cleanup page tables (also in arch_add_memory() in case @@ -1079,7 +1078,6 @@ void arch_remove_memory(int nid, u64 start, u64 size, * unplug. ARCH_ENABLE_MEMORY_HOTREMOVE must not be * unlocked yet. */ - zone = page_zone(pfn_to_page(start_pfn)); - __remove_pages(zone, start_pfn, nr_pages, altmap); + __remove_pages(start_pfn, nr_pages, altmap); } #endif diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c index 58fd67068bac..b01d68a2d5d9 100644 --- a/arch/ia64/mm/init.c +++ b/arch/ia64/mm/init.c @@ -689,9 +689,7 @@ void arch_remove_memory(int nid, u64 start, u64 size, { unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; - struct zone *zone; - zone = page_zone(pfn_to_page(start_pfn)); - __remove_pages(zone, start_pfn, nr_pages, altmap); + __remove_pages(start_pfn, nr_pages, altmap); } #endif diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 617c2777926f..f5535eae637f 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -151,10 +151,9 @@ void __ref arch_remove_memory(int nid, u64 start, u64 size, { unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; - struct page *page = pfn_to_page(start_pfn) + vmem_altmap_offset(altmap); int ret; - __remove_pages(page_zone(page), start_pfn, nr_pages, altmap); + __remove_pages(start_pfn, nr_pages, altmap); /* Remove htab bolted mappings for this section of memory */ start = (unsigned long)__va(start); diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c index f0ce22220565..ac44bd76db4b 100644 --- a/arch/s390/mm/init.c +++ b/arch/s390/mm/init.c @@ -292,10 +292,8 @@ void arch_remove_memory(int nid, u64 start, u64 size, { unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; - struct zone *zone; - zone = page_zone(pfn_to_page(start_pfn)); - __remove_pages(zone, start_pfn, nr_pages, altmap); + __remove_pages(start_pfn, nr_pages, altmap); vmem_remove_mapping(start, size); } #endif /* CONFIG_MEMORY_HOTPLUG */ diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c index dfdbaa50946e..d1b1ff2be17a 100644 --- a/arch/sh/mm/init.c +++ b/arch/sh/mm/init.c @@ -434,9 +434,7 @@ void arch_remove_memory(int nid, u64 start, u64 size, { unsigned long start_pfn = PFN_DOWN(start); unsigned long nr_pages = size >> PAGE_SHIFT; - struct zone *zone; - zone = page_zone(pfn_to_page(start_pfn)); - __remove_pages(zone, start_pfn, nr_pages, altmap); + __remove_pages(start_pfn, nr_pages, altmap); } #endif /* CONFIG_MEMORY_HOTPLUG */ diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index 930edeb41ec3..0a74407ef92e 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -865,10 +865,8 @@ void arch_remove_memory(int nid, u64 start, u64 size, { unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; - struct zone *zone; - zone = page_zone(pfn_to_page(start_pfn)); - __remove_pages(zone, start_pfn, nr_pages, altmap); + __remove_pages(start_pfn, nr_pages, altmap); } #endif diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index dcb9bc961b39..bcfede46fe02 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -1212,10 +1212,8 @@ void __ref arch_remove_memory(int nid, u64 start, u64 size, { unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; - struct page *page = pfn_to_page(start_pfn) + vmem_altmap_offset(altmap); - struct zone *zone = page_zone(page); - __remove_pages(zone, start_pfn, nr_pages, altmap); + __remove_pages(start_pfn, nr_pages, altmap); kernel_physical_mapping_remove(start, start + size); } #endif /* CONFIG_MEMORY_HOTPLUG */ diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 3a08ecdfca11..ba0dca6aac6e 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -122,8 +122,8 @@ static inline bool movable_node_is_enabled(void) extern void arch_remove_memory(int nid, u64 start, u64 size, struct vmem_altmap *altmap); -extern void __remove_pages(struct zone *zone, unsigned long start_pfn, - unsigned long nr_pages, struct vmem_altmap *altmap); +extern void __remove_pages(unsigned long start_pfn, unsigned long nr_pages, + struct vmem_altmap *altmap); /* reasonably generic interface to expand the physical pages */ extern int __add_pages(int nid, unsigned long start_pfn, unsigned long nr_pages, @@ -342,6 +342,9 @@ extern int add_memory(int nid, u64 start, u64 size); extern int add_memory_resource(int nid, struct resource *resource); extern void move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn, unsigned long nr_pages, struct vmem_altmap *altmap); +extern void remove_pfn_range_from_zone(struct zone *zone, + unsigned long start_pfn, + unsigned long nr_pages); extern bool is_memblock_offlined(struct memory_block *mem); extern int sparse_add_section(int nid, unsigned long pfn, unsigned long nr_pages, struct vmem_altmap *altmap); diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 55ac23ef11c1..a91a072f2b2c 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -483,8 +483,9 @@ static void update_pgdat_span(struct pglist_data *pgdat) pgdat->node_spanned_pages = node_end_pfn - node_start_pfn; } -static void __remove_zone(struct zone *zone, unsigned long start_pfn, - unsigned long nr_pages) +void __ref remove_pfn_range_from_zone(struct zone *zone, + unsigned long start_pfn, + unsigned long nr_pages) { struct pglist_data *pgdat = zone->zone_pgdat; unsigned long flags; @@ -499,28 +500,30 @@ static void __remove_zone(struct zone *zone, unsigned long start_pfn, return; #endif + clear_zone_contiguous(zone); + pgdat_resize_lock(zone->zone_pgdat, &flags); shrink_zone_span(zone, start_pfn, start_pfn + nr_pages); update_pgdat_span(pgdat); pgdat_resize_unlock(zone->zone_pgdat, &flags); + + set_zone_contiguous(zone); } -static void __remove_section(struct zone *zone, unsigned long pfn, - unsigned long nr_pages, unsigned long map_offset, - struct vmem_altmap *altmap) +static void __remove_section(unsigned long pfn, unsigned long nr_pages, + unsigned long map_offset, + struct vmem_altmap *altmap) { struct mem_section *ms = __nr_to_section(pfn_to_section_nr(pfn)); if (WARN_ON_ONCE(!valid_section(ms))) return; - __remove_zone(zone, pfn, nr_pages); sparse_remove_section(ms, pfn, nr_pages, map_offset, altmap); } /** - * __remove_pages() - remove sections of pages from a zone - * @zone: zone from which pages need to be removed + * __remove_pages() - remove sections of pages * @pfn: starting pageframe (must be aligned to start of a section) * @nr_pages: number of pages to remove (must be multiple of section size) * @altmap: alternative device page map or %NULL if default memmap is used @@ -530,16 +533,14 @@ static void __remove_section(struct zone *zone, unsigned long pfn, * sure that pages are marked reserved and zones are adjust properly by * calling offline_pages(). */ -void __remove_pages(struct zone *zone, unsigned long pfn, - unsigned long nr_pages, struct vmem_altmap *altmap) +void __remove_pages(unsigned long pfn, unsigned long nr_pages, + struct vmem_altmap *altmap) { unsigned long map_offset = 0; unsigned long nr, start_sec, end_sec; map_offset = vmem_altmap_offset(altmap); - clear_zone_contiguous(zone); - if (check_pfn_span(pfn, nr_pages, "remove")) return; @@ -551,13 +552,11 @@ void __remove_pages(struct zone *zone, unsigned long pfn, cond_resched(); pfns = min(nr_pages, PAGES_PER_SECTION - (pfn & ~PAGE_SECTION_MASK)); - __remove_section(zone, pfn, pfns, map_offset, altmap); + __remove_section(pfn, pfns, map_offset, altmap); pfn += pfns; nr_pages -= pfns; map_offset = 0; } - - set_zone_contiguous(zone); } int set_online_page_callback(online_page_callback_t callback) @@ -869,6 +868,7 @@ failed_addition: (unsigned long long) pfn << PAGE_SHIFT, (((unsigned long long) pfn + nr_pages) << PAGE_SHIFT) - 1); memory_notify(MEM_CANCEL_ONLINE, &arg); + remove_pfn_range_from_zone(zone, pfn, nr_pages); mem_hotplug_done(); return ret; } @@ -1628,6 +1628,7 @@ static int __ref __offline_pages(unsigned long start_pfn, writeback_set_ratelimit(); memory_notify(MEM_OFFLINE, &arg); + remove_pfn_range_from_zone(zone, start_pfn, nr_pages); mem_hotplug_done(); return 0; diff --git a/mm/memremap.c b/mm/memremap.c index 03ccbdfeb697..c51c6bd2fe34 100644 --- a/mm/memremap.c +++ b/mm/memremap.c @@ -120,7 +120,7 @@ void memunmap_pages(struct dev_pagemap *pgmap) mem_hotplug_begin(); if (pgmap->type == MEMORY_DEVICE_PRIVATE) { - __remove_pages(page_zone(first_page), PHYS_PFN(res->start), + __remove_pages(PHYS_PFN(res->start), PHYS_PFN(resource_size(res)), NULL); } else { arch_remove_memory(nid, res->start, resource_size(res), -- cgit v1.2.3 From a69b83e1ae7f6c5ff2cc310870c1708405d86be2 Mon Sep 17 00:00:00 2001 From: Andrey Konovalov Date: Sat, 4 Jan 2020 12:59:39 -0800 Subject: kcov: fix struct layout for kcov_remote_arg Make the layout of kcov_remote_arg the same for 32-bit and 64-bit code. This makes it more convenient to write userspace apps that can be compiled into 32-bit or 64-bit binaries and still work with the same 64-bit kernel. Also use proper __u32 types in uapi headers instead of unsigned ints. Link: http://lkml.kernel.org/r/9e91020876029cfefc9211ff747685eba9536426.1575638983.git.andreyknvl@google.com Fixes: eec028c9386ed1a ("kcov: remote coverage support") Signed-off-by: Andrey Konovalov Acked-by: Marco Elver Cc: Greg Kroah-Hartman Cc: Alan Stern Cc: Felipe Balbi Cc: Chunfeng Yun Cc: "Jacky . Cao @ sony . com" Cc: Dmitry Vyukov Cc: Alexander Potapenko Cc: Marco Elver Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/dev-tools/kcov.rst | 10 +++++----- include/uapi/linux/kcov.h | 10 +++++----- 2 files changed, 10 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/Documentation/dev-tools/kcov.rst b/Documentation/dev-tools/kcov.rst index 36890b026e77..1c4e1825d769 100644 --- a/Documentation/dev-tools/kcov.rst +++ b/Documentation/dev-tools/kcov.rst @@ -251,11 +251,11 @@ selectively from different subsystems. .. code-block:: c struct kcov_remote_arg { - unsigned trace_mode; - unsigned area_size; - unsigned num_handles; - uint64_t common_handle; - uint64_t handles[0]; + __u32 trace_mode; + __u32 area_size; + __u32 num_handles; + __aligned_u64 common_handle; + __aligned_u64 handles[0]; }; #define KCOV_INIT_TRACE _IOR('c', 1, unsigned long) diff --git a/include/uapi/linux/kcov.h b/include/uapi/linux/kcov.h index 409d3ad1e6e2..1d0350e44ae3 100644 --- a/include/uapi/linux/kcov.h +++ b/include/uapi/linux/kcov.h @@ -9,11 +9,11 @@ * and the comment before kcov_remote_start() for usage details. */ struct kcov_remote_arg { - unsigned int trace_mode; /* KCOV_TRACE_PC or KCOV_TRACE_CMP */ - unsigned int area_size; /* Length of coverage buffer in words */ - unsigned int num_handles; /* Size of handles array */ - __u64 common_handle; - __u64 handles[0]; + __u32 trace_mode; /* KCOV_TRACE_PC or KCOV_TRACE_CMP */ + __u32 area_size; /* Length of coverage buffer in words */ + __u32 num_handles; /* Size of handles array */ + __aligned_u64 common_handle; + __aligned_u64 handles[0]; }; #define KCOV_REMOTE_MAX_HANDLES 0x100 -- cgit v1.2.3 From 57415790f405534e5578d0106d806630c325dcb3 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 3 Jan 2020 21:09:35 -0700 Subject: block: remove unused mp_bvec_last_segment After commit 85a8ce62c2ea ("block: add bio_truncate to fix guard_bio_eod") this function is unused, remove it. Reviewed-by: Ming Lei Signed-off-by: Jens Axboe --- include/linux/bvec.h | 22 ---------------------- 1 file changed, 22 deletions(-) (limited to 'include') diff --git a/include/linux/bvec.h b/include/linux/bvec.h index 679a42253170..a81c13ac1972 100644 --- a/include/linux/bvec.h +++ b/include/linux/bvec.h @@ -153,26 +153,4 @@ static inline void bvec_advance(const struct bio_vec *bvec, } } -/* - * Get the last single-page segment from the multi-page bvec and store it - * in @seg - */ -static inline void mp_bvec_last_segment(const struct bio_vec *bvec, - struct bio_vec *seg) -{ - unsigned total = bvec->bv_offset + bvec->bv_len; - unsigned last_page = (total - 1) / PAGE_SIZE; - - seg->bv_page = bvec->bv_page + last_page; - - /* the whole segment is inside the last page */ - if (bvec->bv_offset >= last_page * PAGE_SIZE) { - seg->bv_offset = bvec->bv_offset % PAGE_SIZE; - seg->bv_len = bvec->bv_len; - } else { - seg->bv_offset = 0; - seg->bv_len = total - last_page * PAGE_SIZE; - } -} - #endif /* __LINUX_BVEC_ITER_H */ -- cgit v1.2.3 From fb46f1b7806977e9135a83eb347e5d82e68233a2 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Fri, 3 Jan 2020 18:10:04 +0100 Subject: netfilter: flowtable: add nf_flowtable_time_stamp This patch adds nf_flowtable_time_stamp and updates the existing code to use it. This patch is also implicitly fixing up hardware statistic fetching via nf_flow_offload_stats() where casting to u32 is missing. Use nf_flow_timeout_delta() to fix this. Fixes: c29f74e0df7a ("netfilter: nf_flow_table: hardware offload support") Signed-off-by: Pablo Neira Ayuso Acked-by: wenxu --- include/net/netfilter/nf_flow_table.h | 6 ++++++ net/netfilter/nf_flow_table_core.c | 7 +------ net/netfilter/nf_flow_table_ip.c | 4 ++-- net/netfilter/nf_flow_table_offload.c | 4 ++-- 4 files changed, 11 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h index f0897b3c97fb..415b8f49d150 100644 --- a/include/net/netfilter/nf_flow_table.h +++ b/include/net/netfilter/nf_flow_table.h @@ -106,6 +106,12 @@ struct flow_offload { }; #define NF_FLOW_TIMEOUT (30 * HZ) +#define nf_flowtable_time_stamp (u32)jiffies + +static inline __s32 nf_flow_timeout_delta(unsigned int timeout) +{ + return (__s32)(timeout - nf_flowtable_time_stamp); +} struct nf_flow_route { struct { diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index 9889d52eda82..e33a73cb1f42 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -134,11 +134,6 @@ static void flow_offload_fixup_tcp(struct ip_ct_tcp *tcp) #define NF_FLOWTABLE_TCP_PICKUP_TIMEOUT (120 * HZ) #define NF_FLOWTABLE_UDP_PICKUP_TIMEOUT (30 * HZ) -static inline __s32 nf_flow_timeout_delta(unsigned int timeout) -{ - return (__s32)(timeout - (u32)jiffies); -} - static void flow_offload_fixup_ct_timeout(struct nf_conn *ct) { const struct nf_conntrack_l4proto *l4proto; @@ -232,7 +227,7 @@ int flow_offload_add(struct nf_flowtable *flow_table, struct flow_offload *flow) { int err; - flow->timeout = (u32)jiffies + NF_FLOW_TIMEOUT; + flow->timeout = nf_flowtable_time_stamp + NF_FLOW_TIMEOUT; err = rhashtable_insert_fast(&flow_table->rhashtable, &flow->tuplehash[0].node, diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c index b9e7dd6e60ce..7ea2ddc2aa93 100644 --- a/net/netfilter/nf_flow_table_ip.c +++ b/net/netfilter/nf_flow_table_ip.c @@ -280,7 +280,7 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb, if (nf_flow_nat_ip(flow, skb, thoff, dir) < 0) return NF_DROP; - flow->timeout = (u32)jiffies + NF_FLOW_TIMEOUT; + flow->timeout = nf_flowtable_time_stamp + NF_FLOW_TIMEOUT; iph = ip_hdr(skb); ip_decrease_ttl(iph); skb->tstamp = 0; @@ -509,7 +509,7 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb, if (nf_flow_nat_ipv6(flow, skb, dir) < 0) return NF_DROP; - flow->timeout = (u32)jiffies + NF_FLOW_TIMEOUT; + flow->timeout = nf_flowtable_time_stamp + NF_FLOW_TIMEOUT; ip6h = ipv6_hdr(skb); ip6h->hop_limit--; skb->tstamp = 0; diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c index 6c162c954c4f..d06969af1085 100644 --- a/net/netfilter/nf_flow_table_offload.c +++ b/net/netfilter/nf_flow_table_offload.c @@ -781,9 +781,9 @@ void nf_flow_offload_stats(struct nf_flowtable *flowtable, struct flow_offload *flow) { struct flow_offload_work *offload; - s64 delta; + __s32 delta; - delta = flow->timeout - jiffies; + delta = nf_flow_timeout_delta(flow->timeout); if ((delta >= (9 * NF_FLOW_TIMEOUT) / 10) || flow->flags & FLOW_OFFLOAD_HW_DYING) return; -- cgit v1.2.3 From 5adcb8b18611c69577fd0f35337ab8d2573712fa Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sat, 4 Jan 2020 16:21:06 +0100 Subject: net: ethernet: sxgbe: Rename Samsung to lowercase Fix up inconsistent usage of upper and lowercase letters in "Samsung" name. "SAMSUNG" is not an abbreviation but a regular trademarked name. Therefore it should be written with lowercase letters starting with capital letter. Although advertisement materials usually use uppercase "SAMSUNG", the lowercase version is used in all legal aspects (e.g. on Wikipedia and in privacy/legal statements on https://www.samsung.com/semiconductor/privacy-global/). Signed-off-by: Krzysztof Kozlowski Signed-off-by: David S. Miller --- drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c | 2 +- include/linux/sxgbe_platform.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c index c56fcbb37066..52ed111d98f4 100644 --- a/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c +++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c @@ -2296,7 +2296,7 @@ __setup("sxgbeeth=", sxgbe_cmdline_opt); -MODULE_DESCRIPTION("SAMSUNG 10G/2.5G/1G Ethernet PLATFORM driver"); +MODULE_DESCRIPTION("Samsung 10G/2.5G/1G Ethernet PLATFORM driver"); MODULE_PARM_DESC(debug, "Message Level (-1: default, 0: no output, 16: all)"); MODULE_PARM_DESC(eee_timer, "EEE-LPI Default LS timer value"); diff --git a/include/linux/sxgbe_platform.h b/include/linux/sxgbe_platform.h index 85ec745767bd..966146f7267a 100644 --- a/include/linux/sxgbe_platform.h +++ b/include/linux/sxgbe_platform.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* - * 10G controller driver for Samsung EXYNOS SoCs + * 10G controller driver for Samsung Exynos SoCs * * Copyright (C) 2013 Samsung Electronics Co., Ltd. * http://www.samsung.com -- cgit v1.2.3 From 96cc4b69581db68efc9749ef32e9cf8e0160c509 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 6 Jan 2020 12:30:48 -0800 Subject: macvlan: do not assume mac_header is set in macvlan_broadcast() Use of eth_hdr() in tx path is error prone. Many drivers call skb_reset_mac_header() before using it, but others do not. Commit 6d1ccff62780 ("net: reset mac header in dev_start_xmit()") attempted to fix this generically, but commit d346a3fae3ff ("packet: introduce PACKET_QDISC_BYPASS socket option") brought back the macvlan bug. Lets add a new helper, so that tx paths no longer have to call skb_reset_mac_header() only to get a pointer to skb->data. Hopefully we will be able to revert 6d1ccff62780 ("net: reset mac header in dev_start_xmit()") and save few cycles in transmit fast path. BUG: KASAN: use-after-free in __get_unaligned_cpu32 include/linux/unaligned/packed_struct.h:19 [inline] BUG: KASAN: use-after-free in mc_hash drivers/net/macvlan.c:251 [inline] BUG: KASAN: use-after-free in macvlan_broadcast+0x547/0x620 drivers/net/macvlan.c:277 Read of size 4 at addr ffff8880a4932401 by task syz-executor947/9579 CPU: 0 PID: 9579 Comm: syz-executor947 Not tainted 5.5.0-rc4-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x197/0x210 lib/dump_stack.c:118 print_address_description.constprop.0.cold+0xd4/0x30b mm/kasan/report.c:374 __kasan_report.cold+0x1b/0x41 mm/kasan/report.c:506 kasan_report+0x12/0x20 mm/kasan/common.c:639 __asan_report_load_n_noabort+0xf/0x20 mm/kasan/generic_report.c:145 __get_unaligned_cpu32 include/linux/unaligned/packed_struct.h:19 [inline] mc_hash drivers/net/macvlan.c:251 [inline] macvlan_broadcast+0x547/0x620 drivers/net/macvlan.c:277 macvlan_queue_xmit drivers/net/macvlan.c:520 [inline] macvlan_start_xmit+0x402/0x77f drivers/net/macvlan.c:559 __netdev_start_xmit include/linux/netdevice.h:4447 [inline] netdev_start_xmit include/linux/netdevice.h:4461 [inline] dev_direct_xmit+0x419/0x630 net/core/dev.c:4079 packet_direct_xmit+0x1a9/0x250 net/packet/af_packet.c:240 packet_snd net/packet/af_packet.c:2966 [inline] packet_sendmsg+0x260d/0x6220 net/packet/af_packet.c:2991 sock_sendmsg_nosec net/socket.c:639 [inline] sock_sendmsg+0xd7/0x130 net/socket.c:659 __sys_sendto+0x262/0x380 net/socket.c:1985 __do_sys_sendto net/socket.c:1997 [inline] __se_sys_sendto net/socket.c:1993 [inline] __x64_sys_sendto+0xe1/0x1a0 net/socket.c:1993 do_syscall_64+0xfa/0x790 arch/x86/entry/common.c:294 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x442639 Code: 18 89 d0 c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 5b 10 fc ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007ffc13549e08 EFLAGS: 00000246 ORIG_RAX: 000000000000002c RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 0000000000442639 RDX: 000000000000000e RSI: 0000000020000080 RDI: 0000000000000003 RBP: 0000000000000004 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: 0000000000403bb0 R14: 0000000000000000 R15: 0000000000000000 Allocated by task 9389: save_stack+0x23/0x90 mm/kasan/common.c:72 set_track mm/kasan/common.c:80 [inline] __kasan_kmalloc mm/kasan/common.c:513 [inline] __kasan_kmalloc.constprop.0+0xcf/0xe0 mm/kasan/common.c:486 kasan_kmalloc+0x9/0x10 mm/kasan/common.c:527 __do_kmalloc mm/slab.c:3656 [inline] __kmalloc+0x163/0x770 mm/slab.c:3665 kmalloc include/linux/slab.h:561 [inline] tomoyo_realpath_from_path+0xc5/0x660 security/tomoyo/realpath.c:252 tomoyo_get_realpath security/tomoyo/file.c:151 [inline] tomoyo_path_perm+0x230/0x430 security/tomoyo/file.c:822 tomoyo_inode_getattr+0x1d/0x30 security/tomoyo/tomoyo.c:129 security_inode_getattr+0xf2/0x150 security/security.c:1222 vfs_getattr+0x25/0x70 fs/stat.c:115 vfs_statx_fd+0x71/0xc0 fs/stat.c:145 vfs_fstat include/linux/fs.h:3265 [inline] __do_sys_newfstat+0x9b/0x120 fs/stat.c:378 __se_sys_newfstat fs/stat.c:375 [inline] __x64_sys_newfstat+0x54/0x80 fs/stat.c:375 do_syscall_64+0xfa/0x790 arch/x86/entry/common.c:294 entry_SYSCALL_64_after_hwframe+0x49/0xbe Freed by task 9389: save_stack+0x23/0x90 mm/kasan/common.c:72 set_track mm/kasan/common.c:80 [inline] kasan_set_free_info mm/kasan/common.c:335 [inline] __kasan_slab_free+0x102/0x150 mm/kasan/common.c:474 kasan_slab_free+0xe/0x10 mm/kasan/common.c:483 __cache_free mm/slab.c:3426 [inline] kfree+0x10a/0x2c0 mm/slab.c:3757 tomoyo_realpath_from_path+0x1a7/0x660 security/tomoyo/realpath.c:289 tomoyo_get_realpath security/tomoyo/file.c:151 [inline] tomoyo_path_perm+0x230/0x430 security/tomoyo/file.c:822 tomoyo_inode_getattr+0x1d/0x30 security/tomoyo/tomoyo.c:129 security_inode_getattr+0xf2/0x150 security/security.c:1222 vfs_getattr+0x25/0x70 fs/stat.c:115 vfs_statx_fd+0x71/0xc0 fs/stat.c:145 vfs_fstat include/linux/fs.h:3265 [inline] __do_sys_newfstat+0x9b/0x120 fs/stat.c:378 __se_sys_newfstat fs/stat.c:375 [inline] __x64_sys_newfstat+0x54/0x80 fs/stat.c:375 do_syscall_64+0xfa/0x790 arch/x86/entry/common.c:294 entry_SYSCALL_64_after_hwframe+0x49/0xbe The buggy address belongs to the object at ffff8880a4932000 which belongs to the cache kmalloc-4k of size 4096 The buggy address is located 1025 bytes inside of 4096-byte region [ffff8880a4932000, ffff8880a4933000) The buggy address belongs to the page: page:ffffea0002924c80 refcount:1 mapcount:0 mapping:ffff8880aa402000 index:0x0 compound_mapcount: 0 raw: 00fffe0000010200 ffffea0002846208 ffffea00028f3888 ffff8880aa402000 raw: 0000000000000000 ffff8880a4932000 0000000100000001 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff8880a4932300: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff8880a4932380: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb >ffff8880a4932400: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff8880a4932480: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff8880a4932500: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb Fixes: b863ceb7ddce ("[NET]: Add macvlan driver") Signed-off-by: Eric Dumazet Reported-by: syzbot Signed-off-by: David S. Miller --- drivers/net/macvlan.c | 2 +- include/linux/if_ether.h | 8 ++++++++ 2 files changed, 9 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index 05631d97eeb4..747c0542a53c 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -259,7 +259,7 @@ static void macvlan_broadcast(struct sk_buff *skb, struct net_device *src, enum macvlan_mode mode) { - const struct ethhdr *eth = eth_hdr(skb); + const struct ethhdr *eth = skb_eth_hdr(skb); const struct macvlan_dev *vlan; struct sk_buff *nskb; unsigned int i; diff --git a/include/linux/if_ether.h b/include/linux/if_ether.h index 76cf11e905e1..8a9792a6427a 100644 --- a/include/linux/if_ether.h +++ b/include/linux/if_ether.h @@ -24,6 +24,14 @@ static inline struct ethhdr *eth_hdr(const struct sk_buff *skb) return (struct ethhdr *)skb_mac_header(skb); } +/* Prefer this version in TX path, instead of + * skb_reset_mac_header() + eth_hdr() + */ +static inline struct ethhdr *skb_eth_hdr(const struct sk_buff *skb) +{ + return (struct ethhdr *)skb->data; +} + static inline struct ethhdr *inner_eth_hdr(const struct sk_buff *skb) { return (struct ethhdr *)skb_inner_mac_header(skb); -- cgit v1.2.3 From 44f45994f438b4f4e0ba977b173980268983c60f Mon Sep 17 00:00:00 2001 From: Amir Mahdi Ghorbanian Date: Thu, 2 Jan 2020 12:10:08 -0500 Subject: mtd: onenand: omap2: Fix errors in style Correct mispelling, spacing, and coding style flaws caught by checkpatch.pl script in the Omap2 Onenand driver . Signed-off-by: Amir Mahdi Ghorbanian Signed-off-by: Miquel Raynal --- drivers/mtd/nand/onenand/omap2.c | 11 ++++++----- drivers/mtd/nand/onenand/onenand_base.c | 14 +++++++------- include/linux/mtd/flashchip.h | 2 +- 3 files changed, 14 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/drivers/mtd/nand/onenand/omap2.c b/drivers/mtd/nand/onenand/omap2.c index edf94ee54ec7..8cb2294bc837 100644 --- a/drivers/mtd/nand/onenand/omap2.c +++ b/drivers/mtd/nand/onenand/omap2.c @@ -148,13 +148,13 @@ static int omap2_onenand_wait(struct mtd_info *mtd, int state) unsigned long timeout; u32 syscfg; - if (state == FL_RESETING || state == FL_PREPARING_ERASE || + if (state == FL_RESETTING || state == FL_PREPARING_ERASE || state == FL_VERIFYING_ERASE) { int i = 21; unsigned int intr_flags = ONENAND_INT_MASTER; switch (state) { - case FL_RESETING: + case FL_RESETTING: intr_flags |= ONENAND_INT_RESET; break; case FL_PREPARING_ERASE: @@ -375,7 +375,7 @@ static int omap2_onenand_read_bufferram(struct mtd_info *mtd, int area, * context fallback to PIO mode. */ if (!virt_addr_valid(buf) || bram_offset & 3 || (size_t)buf & 3 || - count < 384 || in_interrupt() || oops_in_progress ) + count < 384 || in_interrupt() || oops_in_progress) goto out_copy; xtra = count & 3; @@ -422,7 +422,7 @@ static int omap2_onenand_write_bufferram(struct mtd_info *mtd, int area, * context fallback to PIO mode. */ if (!virt_addr_valid(buf) || bram_offset & 3 || (size_t)buf & 3 || - count < 384 || in_interrupt() || oops_in_progress ) + count < 384 || in_interrupt() || oops_in_progress) goto out_copy; dma_src = dma_map_single(dev, buf, count, DMA_TO_DEVICE); @@ -528,7 +528,8 @@ static int omap2_onenand_probe(struct platform_device *pdev) c->gpmc_cs, c->phys_base, c->onenand.base, c->dma_chan ? "DMA" : "PIO"); - if ((r = onenand_scan(&c->mtd, 1)) < 0) + r = onenand_scan(&c->mtd, 1); + if (r < 0) goto err_release_dma; freq = omap2_onenand_get_freq(c->onenand.version_id); diff --git a/drivers/mtd/nand/onenand/onenand_base.c b/drivers/mtd/nand/onenand/onenand_base.c index 77bd32a683e1..85640ee11c86 100644 --- a/drivers/mtd/nand/onenand/onenand_base.c +++ b/drivers/mtd/nand/onenand/onenand_base.c @@ -2853,7 +2853,7 @@ static int onenand_otp_write_oob_nolock(struct mtd_info *mtd, loff_t to, /* Exit OTP access mode */ this->command(mtd, ONENAND_CMD_RESET, 0, 0); - this->wait(mtd, FL_RESETING); + this->wait(mtd, FL_RESETTING); status = this->read_word(this->base + ONENAND_REG_CTRL_STATUS); status &= 0x60; @@ -2924,7 +2924,7 @@ static int do_otp_read(struct mtd_info *mtd, loff_t from, size_t len, /* Exit OTP access mode */ this->command(mtd, ONENAND_CMD_RESET, 0, 0); - this->wait(mtd, FL_RESETING); + this->wait(mtd, FL_RESETTING); return ret; } @@ -2968,7 +2968,7 @@ static int do_otp_write(struct mtd_info *mtd, loff_t to, size_t len, /* Exit OTP access mode */ this->command(mtd, ONENAND_CMD_RESET, 0, 0); - this->wait(mtd, FL_RESETING); + this->wait(mtd, FL_RESETTING); return ret; } @@ -3008,7 +3008,7 @@ static int do_otp_lock(struct mtd_info *mtd, loff_t from, size_t len, /* Exit OTP access mode */ this->command(mtd, ONENAND_CMD_RESET, 0, 0); - this->wait(mtd, FL_RESETING); + this->wait(mtd, FL_RESETTING); } else { ops.mode = MTD_OPS_PLACE_OOB; ops.ooblen = len; @@ -3413,7 +3413,7 @@ static int flexonenand_get_boundary(struct mtd_info *mtd) this->boundary[die] = bdry & FLEXONENAND_PI_MASK; this->command(mtd, ONENAND_CMD_RESET, 0, 0); - this->wait(mtd, FL_RESETING); + this->wait(mtd, FL_RESETTING); printk(KERN_INFO "Die %d boundary: %d%s\n", die, this->boundary[die], locked ? "(Locked)" : "(Unlocked)"); @@ -3635,7 +3635,7 @@ static int flexonenand_set_boundary(struct mtd_info *mtd, int die, ret = this->wait(mtd, FL_WRITING); out: this->write_word(ONENAND_CMD_RESET, this->base + ONENAND_REG_COMMAND); - this->wait(mtd, FL_RESETING); + this->wait(mtd, FL_RESETTING); if (!ret) /* Recalculate device size on boundary change*/ flexonenand_get_size(mtd); @@ -3671,7 +3671,7 @@ static int onenand_chip_probe(struct mtd_info *mtd) /* Reset OneNAND to read default register values */ this->write_word(ONENAND_CMD_RESET, this->base + ONENAND_BOOTRAM); /* Wait reset */ - this->wait(mtd, FL_RESETING); + this->wait(mtd, FL_RESETTING); /* Restore system configuration 1 */ this->write_word(syscfg, this->base + ONENAND_REG_SYS_CFG1); diff --git a/include/linux/mtd/flashchip.h b/include/linux/mtd/flashchip.h index ecc88a41792a..c04f690871ca 100644 --- a/include/linux/mtd/flashchip.h +++ b/include/linux/mtd/flashchip.h @@ -40,7 +40,7 @@ typedef enum { FL_READING, FL_CACHEDPRG, /* These 4 come from onenand_state_t, which has been unified here */ - FL_RESETING, + FL_RESETTING, FL_OTPING, FL_PREPARING_ERASE, FL_VERIFYING_ERASE, -- cgit v1.2.3 From b0efcae5e12b341e569f971ccd193e31f1d0ffa8 Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Thu, 9 Jan 2020 11:08:20 -0800 Subject: devlink: correct misspelling of snapshot The function to obtain a unique snapshot id was mistakenly typo'd as devlink_region_shapshot_id_get. Fix this typo by renaming the function and all of its users. Signed-off-by: Jacob Keller Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/crdump.c | 2 +- drivers/net/netdevsim/dev.c | 2 +- include/net/devlink.h | 2 +- net/core/devlink.c | 6 +++--- 4 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/mellanox/mlx4/crdump.c b/drivers/net/ethernet/mellanox/mlx4/crdump.c index eaf08f7ad128..64ed725aec28 100644 --- a/drivers/net/ethernet/mellanox/mlx4/crdump.c +++ b/drivers/net/ethernet/mellanox/mlx4/crdump.c @@ -182,7 +182,7 @@ int mlx4_crdump_collect(struct mlx4_dev *dev) crdump_enable_crspace_access(dev, cr_space); /* Get the available snapshot ID for the dumps */ - id = devlink_region_shapshot_id_get(devlink); + id = devlink_region_snapshot_id_get(devlink); /* Try to capture dumps */ mlx4_crdump_collect_crspace(dev, cr_space, id); diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c index 059711edfc61..4b39aba2e9c4 100644 --- a/drivers/net/netdevsim/dev.c +++ b/drivers/net/netdevsim/dev.c @@ -53,7 +53,7 @@ static ssize_t nsim_dev_take_snapshot_write(struct file *file, get_random_bytes(dummy_data, NSIM_DEV_DUMMY_REGION_SIZE); - id = devlink_region_shapshot_id_get(priv_to_devlink(nsim_dev)); + id = devlink_region_snapshot_id_get(priv_to_devlink(nsim_dev)); err = devlink_region_snapshot_create(nsim_dev->dummy_region, dummy_data, id, kfree); if (err) { diff --git a/include/net/devlink.h b/include/net/devlink.h index 47f87b2fcf63..38b4acb93f74 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -938,7 +938,7 @@ struct devlink_region *devlink_region_create(struct devlink *devlink, u32 region_max_snapshots, u64 region_size); void devlink_region_destroy(struct devlink_region *region); -u32 devlink_region_shapshot_id_get(struct devlink *devlink); +u32 devlink_region_snapshot_id_get(struct devlink *devlink); int devlink_region_snapshot_create(struct devlink_region *region, u8 *data, u32 snapshot_id, devlink_snapshot_data_dest_t *data_destructor); diff --git a/net/core/devlink.c b/net/core/devlink.c index b8d698a2bf57..f76219bf0c21 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -7563,7 +7563,7 @@ void devlink_region_destroy(struct devlink_region *region) EXPORT_SYMBOL_GPL(devlink_region_destroy); /** - * devlink_region_shapshot_id_get - get snapshot ID + * devlink_region_snapshot_id_get - get snapshot ID * * This callback should be called when adding a new snapshot, * Driver should use the same id for multiple snapshots taken @@ -7571,7 +7571,7 @@ EXPORT_SYMBOL_GPL(devlink_region_destroy); * * @devlink: devlink */ -u32 devlink_region_shapshot_id_get(struct devlink *devlink) +u32 devlink_region_snapshot_id_get(struct devlink *devlink) { u32 id; @@ -7581,7 +7581,7 @@ u32 devlink_region_shapshot_id_get(struct devlink *devlink) return id; } -EXPORT_SYMBOL_GPL(devlink_region_shapshot_id_get); +EXPORT_SYMBOL_GPL(devlink_region_snapshot_id_get); /** * devlink_region_snapshot_create - create a new snapshot -- cgit v1.2.3 From 13cf4cf030183dd9a8731f3fe32456e83b6c7b68 Mon Sep 17 00:00:00 2001 From: Yash Shah Date: Tue, 7 Jan 2020 22:09:06 -0800 Subject: riscv: move sifive_l2_cache.h to include/soc The commit 9209fb51896f ("riscv: move sifive_l2_cache.c to drivers/soc") moves the sifive L2 cache driver to driver/soc. It did not move the header file along with the driver. Therefore this patch moves the header file to driver/soc Signed-off-by: Yash Shah Reviewed-by: Anup Patel [paul.walmsley@sifive.com: updated to fix the include guard] Fixes: 9209fb51896f ("riscv: move sifive_l2_cache.c to drivers/soc") Signed-off-by: Paul Walmsley --- arch/riscv/include/asm/sifive_l2_cache.h | 16 ---------------- drivers/edac/sifive_edac.c | 2 +- drivers/soc/sifive/sifive_l2_cache.c | 2 +- include/soc/sifive/sifive_l2_cache.h | 16 ++++++++++++++++ 4 files changed, 18 insertions(+), 18 deletions(-) delete mode 100644 arch/riscv/include/asm/sifive_l2_cache.h create mode 100644 include/soc/sifive/sifive_l2_cache.h (limited to 'include') diff --git a/arch/riscv/include/asm/sifive_l2_cache.h b/arch/riscv/include/asm/sifive_l2_cache.h deleted file mode 100644 index 04f6748fc50b..000000000000 --- a/arch/riscv/include/asm/sifive_l2_cache.h +++ /dev/null @@ -1,16 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * SiFive L2 Cache Controller header file - * - */ - -#ifndef _ASM_RISCV_SIFIVE_L2_CACHE_H -#define _ASM_RISCV_SIFIVE_L2_CACHE_H - -extern int register_sifive_l2_error_notifier(struct notifier_block *nb); -extern int unregister_sifive_l2_error_notifier(struct notifier_block *nb); - -#define SIFIVE_L2_ERR_TYPE_CE 0 -#define SIFIVE_L2_ERR_TYPE_UE 1 - -#endif /* _ASM_RISCV_SIFIVE_L2_CACHE_H */ diff --git a/drivers/edac/sifive_edac.c b/drivers/edac/sifive_edac.c index 413cdb4a591d..c0cc72a3b2be 100644 --- a/drivers/edac/sifive_edac.c +++ b/drivers/edac/sifive_edac.c @@ -10,7 +10,7 @@ #include #include #include "edac_module.h" -#include +#include #define DRVNAME "sifive_edac" diff --git a/drivers/soc/sifive/sifive_l2_cache.c b/drivers/soc/sifive/sifive_l2_cache.c index a9ffff3277c7..a5069394cd61 100644 --- a/drivers/soc/sifive/sifive_l2_cache.c +++ b/drivers/soc/sifive/sifive_l2_cache.c @@ -9,7 +9,7 @@ #include #include #include -#include +#include #define SIFIVE_L2_DIRECCFIX_LOW 0x100 #define SIFIVE_L2_DIRECCFIX_HIGH 0x104 diff --git a/include/soc/sifive/sifive_l2_cache.h b/include/soc/sifive/sifive_l2_cache.h new file mode 100644 index 000000000000..92ade10ed67e --- /dev/null +++ b/include/soc/sifive/sifive_l2_cache.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * SiFive L2 Cache Controller header file + * + */ + +#ifndef __SOC_SIFIVE_L2_CACHE_H +#define __SOC_SIFIVE_L2_CACHE_H + +extern int register_sifive_l2_error_notifier(struct notifier_block *nb); +extern int unregister_sifive_l2_error_notifier(struct notifier_block *nb); + +#define SIFIVE_L2_ERR_TYPE_CE 0 +#define SIFIVE_L2_ERR_TYPE_UE 1 + +#endif /* __SOC_SIFIVE_L2_CACHE_H */ -- cgit v1.2.3 From 4a87e2a25dc27131c3cce5e94421622193305638 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Mon, 13 Jan 2020 16:29:16 -0800 Subject: mm: memcg/slab: fix percpu slab vmstats flushing Currently slab percpu vmstats are flushed twice: during the memcg offlining and just before freeing the memcg structure. Each time percpu counters are summed, added to the atomic counterparts and propagated up by the cgroup tree. The second flushing is required due to how recursive vmstats are implemented: counters are batched in percpu variables on a local level, and once a percpu value is crossing some predefined threshold, it spills over to atomic values on the local and each ascendant levels. It means that without flushing some numbers cached in percpu variables will be dropped on floor each time a cgroup is destroyed. And with uptime the error on upper levels might become noticeable. The first flushing aims to make counters on ancestor levels more precise. Dying cgroups may resume in the dying state for a long time. After kmem_cache reparenting which is performed during the offlining slab counters of the dying cgroup don't have any chances to be updated, because any slab operations will be performed on the parent level. It means that the inaccuracy caused by percpu batching will not decrease up to the final destruction of the cgroup. By the original idea flushing slab counters during the offlining should minimize the visible inaccuracy of slab counters on the parent level. The problem is that percpu counters are not zeroed after the first flushing. So every cached percpu value is summed twice. It creates a small error (up to 32 pages per cpu, but usually less) which accumulates on parent cgroup level. After creating and destroying of thousands of child cgroups, slab counter on parent level can be way off the real value. For now, let's just stop flushing slab counters on memcg offlining. It can't be done correctly without scheduling a work on each cpu: reading and zeroing it during css offlining can race with an asynchronous update, which doesn't expect values to be changed underneath. With this change, slab counters on parent level will become eventually consistent. Once all dying children are gone, values are correct. And if not, the error is capped by 32 * NR_CPUS pages per dying cgroup. It's not perfect, as slab are reparented, so any updates after the reparenting will happen on the parent level. It means that if a slab page was allocated, a counter on child level was bumped, then the page was reparented and freed, the annihilation of positive and negative counter values will not happen until the child cgroup is released. It makes slab counters different from others, and it might want us to implement flushing in a correct form again. But it's also a question of performance: scheduling a work on each cpu isn't free, and it's an open question if the benefit of having more accurate counters is worth it. We might also consider flushing all counters on offlining, not only slab counters. So let's fix the main problem now: make the slab counters eventually consistent, so at least the error won't grow with uptime (or more precisely the number of created and destroyed cgroups). And think about the accuracy of counters separately. Link: http://lkml.kernel.org/r/20191220042728.1045881-1-guro@fb.com Fixes: bee07b33db78 ("mm: memcontrol: flush percpu slab vmstats on kmem offlining") Signed-off-by: Roman Gushchin Acked-by: Johannes Weiner Acked-by: Michal Hocko Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 5 ++--- mm/memcontrol.c | 37 +++++++++---------------------------- 2 files changed, 11 insertions(+), 31 deletions(-) (limited to 'include') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 89d8ff06c9ce..5334ad8fc7bd 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -215,9 +215,8 @@ enum node_stat_item { NR_INACTIVE_FILE, /* " " " " " */ NR_ACTIVE_FILE, /* " " " " " */ NR_UNEVICTABLE, /* " " " " " */ - NR_SLAB_RECLAIMABLE, /* Please do not reorder this item */ - NR_SLAB_UNRECLAIMABLE, /* and this one without looking at - * memcg_flush_percpu_vmstats() first. */ + NR_SLAB_RECLAIMABLE, + NR_SLAB_UNRECLAIMABLE, NR_ISOLATED_ANON, /* Temporary isolated pages from anon lru */ NR_ISOLATED_FILE, /* Temporary isolated pages from file lru */ WORKINGSET_NODES, diff --git a/mm/memcontrol.c b/mm/memcontrol.c index c5b5f74cfd4d..6c83cf4ed970 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3287,49 +3287,34 @@ static u64 mem_cgroup_read_u64(struct cgroup_subsys_state *css, } } -static void memcg_flush_percpu_vmstats(struct mem_cgroup *memcg, bool slab_only) +static void memcg_flush_percpu_vmstats(struct mem_cgroup *memcg) { - unsigned long stat[MEMCG_NR_STAT]; + unsigned long stat[MEMCG_NR_STAT] = {0}; struct mem_cgroup *mi; int node, cpu, i; - int min_idx, max_idx; - - if (slab_only) { - min_idx = NR_SLAB_RECLAIMABLE; - max_idx = NR_SLAB_UNRECLAIMABLE; - } else { - min_idx = 0; - max_idx = MEMCG_NR_STAT; - } - - for (i = min_idx; i < max_idx; i++) - stat[i] = 0; for_each_online_cpu(cpu) - for (i = min_idx; i < max_idx; i++) + for (i = 0; i < MEMCG_NR_STAT; i++) stat[i] += per_cpu(memcg->vmstats_percpu->stat[i], cpu); for (mi = memcg; mi; mi = parent_mem_cgroup(mi)) - for (i = min_idx; i < max_idx; i++) + for (i = 0; i < MEMCG_NR_STAT; i++) atomic_long_add(stat[i], &mi->vmstats[i]); - if (!slab_only) - max_idx = NR_VM_NODE_STAT_ITEMS; - for_each_node(node) { struct mem_cgroup_per_node *pn = memcg->nodeinfo[node]; struct mem_cgroup_per_node *pi; - for (i = min_idx; i < max_idx; i++) + for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) stat[i] = 0; for_each_online_cpu(cpu) - for (i = min_idx; i < max_idx; i++) + for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) stat[i] += per_cpu( pn->lruvec_stat_cpu->count[i], cpu); for (pi = pn; pi; pi = parent_nodeinfo(pi, node)) - for (i = min_idx; i < max_idx; i++) + for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) atomic_long_add(stat[i], &pi->lruvec_stat[i]); } } @@ -3403,13 +3388,9 @@ static void memcg_offline_kmem(struct mem_cgroup *memcg) parent = root_mem_cgroup; /* - * Deactivate and reparent kmem_caches. Then flush percpu - * slab statistics to have precise values at the parent and - * all ancestor levels. It's required to keep slab stats - * accurate after the reparenting of kmem_caches. + * Deactivate and reparent kmem_caches. */ memcg_deactivate_kmem_caches(memcg, parent); - memcg_flush_percpu_vmstats(memcg, true); kmemcg_id = memcg->kmemcg_id; BUG_ON(kmemcg_id < 0); @@ -4913,7 +4894,7 @@ static void mem_cgroup_free(struct mem_cgroup *memcg) * Flush percpu vmstats and vmevents to guarantee the value correctness * on parent's and all ancestor levels. */ - memcg_flush_percpu_vmstats(memcg, false); + memcg_flush_percpu_vmstats(memcg); memcg_flush_percpu_vmevents(memcg); __mem_cgroup_free(memcg); } -- cgit v1.2.3 From 8e57f8acbbd121ecfb0c9dc13b8b030f86c6bd3b Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Mon, 13 Jan 2020 16:29:20 -0800 Subject: mm, debug_pagealloc: don't rely on static keys too early Commit 96a2b03f281d ("mm, debug_pagelloc: use static keys to enable debugging") has introduced a static key to reduce overhead when debug_pagealloc is compiled in but not enabled. It relied on the assumption that jump_label_init() is called before parse_early_param() as in start_kernel(), so when the "debug_pagealloc=on" option is parsed, it is safe to enable the static key. However, it turns out multiple architectures call parse_early_param() earlier from their setup_arch(). x86 also calls jump_label_init() even earlier, so no issue was found while testing the commit, but same is not true for e.g. ppc64 and s390 where the kernel would not boot with debug_pagealloc=on as found by our QA. To fix this without tricky changes to init code of multiple architectures, this patch partially reverts the static key conversion from 96a2b03f281d. Init-time and non-fastpath calls (such as in arch code) of debug_pagealloc_enabled() will again test a simple bool variable. Fastpath mm code is converted to a new debug_pagealloc_enabled_static() variant that relies on the static key, which is enabled in a well-defined point in mm_init() where it's guaranteed that jump_label_init() has been called, regardless of architecture. [sfr@canb.auug.org.au: export _debug_pagealloc_enabled_early] Link: http://lkml.kernel.org/r/20200106164944.063ac07b@canb.auug.org.au Link: http://lkml.kernel.org/r/20191219130612.23171-1-vbabka@suse.cz Fixes: 96a2b03f281d ("mm, debug_pagelloc: use static keys to enable debugging") Signed-off-by: Vlastimil Babka Signed-off-by: Stephen Rothwell Cc: Joonsoo Kim Cc: "Kirill A. Shutemov" Cc: Michal Hocko Cc: Vlastimil Babka Cc: Matthew Wilcox Cc: Mel Gorman Cc: Peter Zijlstra Cc: Borislav Petkov Cc: Qian Cai Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 18 +++++++++++++++--- init/main.c | 1 + mm/page_alloc.c | 37 +++++++++++++------------------------ mm/slab.c | 4 ++-- mm/slub.c | 2 +- mm/vmalloc.c | 4 ++-- 6 files changed, 34 insertions(+), 32 deletions(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index 80a9162b406c..cfaa8feecfe8 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2658,13 +2658,25 @@ static inline bool want_init_on_free(void) !page_poisoning_enabled(); } -#ifdef CONFIG_DEBUG_PAGEALLOC_ENABLE_DEFAULT -DECLARE_STATIC_KEY_TRUE(_debug_pagealloc_enabled); +#ifdef CONFIG_DEBUG_PAGEALLOC +extern void init_debug_pagealloc(void); #else -DECLARE_STATIC_KEY_FALSE(_debug_pagealloc_enabled); +static inline void init_debug_pagealloc(void) {} #endif +extern bool _debug_pagealloc_enabled_early; +DECLARE_STATIC_KEY_FALSE(_debug_pagealloc_enabled); static inline bool debug_pagealloc_enabled(void) +{ + return IS_ENABLED(CONFIG_DEBUG_PAGEALLOC) && + _debug_pagealloc_enabled_early; +} + +/* + * For use in fast paths after init_debug_pagealloc() has run, or when a + * false negative result is not harmful when called too early. + */ +static inline bool debug_pagealloc_enabled_static(void) { if (!IS_ENABLED(CONFIG_DEBUG_PAGEALLOC)) return false; diff --git a/init/main.c b/init/main.c index 2cd736059416..da1bc0b60a7d 100644 --- a/init/main.c +++ b/init/main.c @@ -553,6 +553,7 @@ static void __init mm_init(void) * bigger than MAX_ORDER unless SPARSEMEM. */ page_ext_init_flatmem(); + init_debug_pagealloc(); report_meminit(); mem_init(); kmem_cache_init(); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 409be5ec7e2c..d047bf7d8fd4 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -694,34 +694,27 @@ void prep_compound_page(struct page *page, unsigned int order) #ifdef CONFIG_DEBUG_PAGEALLOC unsigned int _debug_guardpage_minorder; -#ifdef CONFIG_DEBUG_PAGEALLOC_ENABLE_DEFAULT -DEFINE_STATIC_KEY_TRUE(_debug_pagealloc_enabled); -#else +bool _debug_pagealloc_enabled_early __read_mostly + = IS_ENABLED(CONFIG_DEBUG_PAGEALLOC_ENABLE_DEFAULT); +EXPORT_SYMBOL(_debug_pagealloc_enabled_early); DEFINE_STATIC_KEY_FALSE(_debug_pagealloc_enabled); -#endif EXPORT_SYMBOL(_debug_pagealloc_enabled); DEFINE_STATIC_KEY_FALSE(_debug_guardpage_enabled); static int __init early_debug_pagealloc(char *buf) { - bool enable = false; - - if (kstrtobool(buf, &enable)) - return -EINVAL; - - if (enable) - static_branch_enable(&_debug_pagealloc_enabled); - - return 0; + return kstrtobool(buf, &_debug_pagealloc_enabled_early); } early_param("debug_pagealloc", early_debug_pagealloc); -static void init_debug_guardpage(void) +void init_debug_pagealloc(void) { if (!debug_pagealloc_enabled()) return; + static_branch_enable(&_debug_pagealloc_enabled); + if (!debug_guardpage_minorder()) return; @@ -1186,7 +1179,7 @@ static __always_inline bool free_pages_prepare(struct page *page, */ arch_free_page(page, order); - if (debug_pagealloc_enabled()) + if (debug_pagealloc_enabled_static()) kernel_map_pages(page, 1 << order, 0); kasan_free_nondeferred_pages(page, order); @@ -1207,7 +1200,7 @@ static bool free_pcp_prepare(struct page *page) static bool bulkfree_pcp_prepare(struct page *page) { - if (debug_pagealloc_enabled()) + if (debug_pagealloc_enabled_static()) return free_pages_check(page); else return false; @@ -1221,7 +1214,7 @@ static bool bulkfree_pcp_prepare(struct page *page) */ static bool free_pcp_prepare(struct page *page) { - if (debug_pagealloc_enabled()) + if (debug_pagealloc_enabled_static()) return free_pages_prepare(page, 0, true); else return free_pages_prepare(page, 0, false); @@ -1973,10 +1966,6 @@ void __init page_alloc_init_late(void) for_each_populated_zone(zone) set_zone_contiguous(zone); - -#ifdef CONFIG_DEBUG_PAGEALLOC - init_debug_guardpage(); -#endif } #ifdef CONFIG_CMA @@ -2106,7 +2095,7 @@ static inline bool free_pages_prezeroed(void) */ static inline bool check_pcp_refill(struct page *page) { - if (debug_pagealloc_enabled()) + if (debug_pagealloc_enabled_static()) return check_new_page(page); else return false; @@ -2128,7 +2117,7 @@ static inline bool check_pcp_refill(struct page *page) } static inline bool check_new_pcp(struct page *page) { - if (debug_pagealloc_enabled()) + if (debug_pagealloc_enabled_static()) return check_new_page(page); else return false; @@ -2155,7 +2144,7 @@ inline void post_alloc_hook(struct page *page, unsigned int order, set_page_refcounted(page); arch_alloc_page(page, order); - if (debug_pagealloc_enabled()) + if (debug_pagealloc_enabled_static()) kernel_map_pages(page, 1 << order, 1); kasan_alloc_pages(page, order); kernel_poison_pages(page, 1 << order, 1); diff --git a/mm/slab.c b/mm/slab.c index f1e1840af533..a89633603b2d 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -1416,7 +1416,7 @@ static void kmem_rcu_free(struct rcu_head *head) #if DEBUG static bool is_debug_pagealloc_cache(struct kmem_cache *cachep) { - if (debug_pagealloc_enabled() && OFF_SLAB(cachep) && + if (debug_pagealloc_enabled_static() && OFF_SLAB(cachep) && (cachep->size % PAGE_SIZE) == 0) return true; @@ -2008,7 +2008,7 @@ int __kmem_cache_create(struct kmem_cache *cachep, slab_flags_t flags) * to check size >= 256. It guarantees that all necessary small * sized slab is initialized in current slab initialization sequence. */ - if (debug_pagealloc_enabled() && (flags & SLAB_POISON) && + if (debug_pagealloc_enabled_static() && (flags & SLAB_POISON) && size >= 256 && cachep->object_size > cache_line_size()) { if (size < PAGE_SIZE || size % PAGE_SIZE == 0) { size_t tmp_size = ALIGN(size, PAGE_SIZE); diff --git a/mm/slub.c b/mm/slub.c index d11389710b12..8eafccf75940 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -288,7 +288,7 @@ static inline void *get_freepointer_safe(struct kmem_cache *s, void *object) unsigned long freepointer_addr; void *p; - if (!debug_pagealloc_enabled()) + if (!debug_pagealloc_enabled_static()) return get_freepointer(s, object); freepointer_addr = (unsigned long)object + s->offset; diff --git a/mm/vmalloc.c b/mm/vmalloc.c index e9681dc4aa75..b29ad17edcf5 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -1383,7 +1383,7 @@ static void free_unmap_vmap_area(struct vmap_area *va) { flush_cache_vunmap(va->va_start, va->va_end); unmap_vmap_area(va); - if (debug_pagealloc_enabled()) + if (debug_pagealloc_enabled_static()) flush_tlb_kernel_range(va->va_start, va->va_end); free_vmap_area_noflush(va); @@ -1681,7 +1681,7 @@ static void vb_free(const void *addr, unsigned long size) vunmap_page_range((unsigned long)addr, (unsigned long)addr + size); - if (debug_pagealloc_enabled()) + if (debug_pagealloc_enabled_static()) flush_tlb_kernel_range((unsigned long)addr, (unsigned long)addr + size); -- cgit v1.2.3 From 554913f600b45d73de12ad58c1ac7baa0f22a703 Mon Sep 17 00:00:00 2001 From: Yang Shi Date: Mon, 13 Jan 2020 16:29:36 -0800 Subject: mm: khugepaged: add trace status description for SCAN_PAGE_HAS_PRIVATE Commit 99cb0dbd47a1 ("mm,thp: add read-only THP support for (non-shmem) FS") introduced a new khugepaged scan result: SCAN_PAGE_HAS_PRIVATE, but the corresponding description for trace events were not added. Link: http://lkml.kernel.org/r/1574793844-2914-1-git-send-email-yang.shi@linux.alibaba.com Fixes: 99cb0dbd47a1 ("mm,thp: add read-only THP support for (non-shmem) FS") Signed-off-by: Yang Shi Cc: Song Liu Cc: Kirill A. Shutemov Cc: Anshuman Khandual Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/trace/events/huge_memory.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/trace/events/huge_memory.h b/include/trace/events/huge_memory.h index dd4db334bd63..d82a0f4e824d 100644 --- a/include/trace/events/huge_memory.h +++ b/include/trace/events/huge_memory.h @@ -31,7 +31,8 @@ EM( SCAN_ALLOC_HUGE_PAGE_FAIL, "alloc_huge_page_failed") \ EM( SCAN_CGROUP_CHARGE_FAIL, "ccgroup_charge_failed") \ EM( SCAN_EXCEED_SWAP_PTE, "exceed_swap_pte") \ - EMe(SCAN_TRUNCATED, "truncated") \ + EM( SCAN_TRUNCATED, "truncated") \ + EMe(SCAN_PAGE_HAS_PRIVATE, "page_has_private") \ #undef EM #undef EMe -- cgit v1.2.3 From 40a708bd622b78582ae3d280de29b09b50bd04c0 Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 14 Jan 2020 16:16:25 +0000 Subject: afs: Fix use-after-loss-of-ref afs_lookup() has a tracepoint to indicate the outcome of d_splice_alias(), passing it the inode to retrieve the fid from. However, the function gave up its ref on that inode when it called d_splice_alias(), which may have failed and dropped the inode. Fix this by caching the fid. Fixes: 80548b03991f ("afs: Add more tracepoints") Reported-by: Al Viro Signed-off-by: David Howells Signed-off-by: Linus Torvalds --- fs/afs/dir.c | 12 +++++++----- include/trace/events/afs.h | 12 +++--------- 2 files changed, 10 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/fs/afs/dir.c b/fs/afs/dir.c index 497f979018c2..813db1708494 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -908,6 +908,7 @@ static struct dentry *afs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { struct afs_vnode *dvnode = AFS_FS_I(dir); + struct afs_fid fid = {}; struct inode *inode; struct dentry *d; struct key *key; @@ -957,15 +958,16 @@ static struct dentry *afs_lookup(struct inode *dir, struct dentry *dentry, dentry->d_fsdata = (void *)(unsigned long)dvnode->status.data_version; } + + if (!IS_ERR_OR_NULL(inode)) + fid = AFS_FS_I(inode)->fid; + d = d_splice_alias(inode, dentry); if (!IS_ERR_OR_NULL(d)) { d->d_fsdata = dentry->d_fsdata; - trace_afs_lookup(dvnode, &d->d_name, - inode ? AFS_FS_I(inode) : NULL); + trace_afs_lookup(dvnode, &d->d_name, &fid); } else { - trace_afs_lookup(dvnode, &dentry->d_name, - IS_ERR_OR_NULL(inode) ? NULL - : AFS_FS_I(inode)); + trace_afs_lookup(dvnode, &dentry->d_name, &fid); } return d; } diff --git a/include/trace/events/afs.h b/include/trace/events/afs.h index d5ec4fac82ae..564ba1b5cf57 100644 --- a/include/trace/events/afs.h +++ b/include/trace/events/afs.h @@ -915,9 +915,9 @@ TRACE_EVENT(afs_call_state, TRACE_EVENT(afs_lookup, TP_PROTO(struct afs_vnode *dvnode, const struct qstr *name, - struct afs_vnode *vnode), + struct afs_fid *fid), - TP_ARGS(dvnode, name, vnode), + TP_ARGS(dvnode, name, fid), TP_STRUCT__entry( __field_struct(struct afs_fid, dfid ) @@ -928,13 +928,7 @@ TRACE_EVENT(afs_lookup, TP_fast_assign( int __len = min_t(int, name->len, 23); __entry->dfid = dvnode->fid; - if (vnode) { - __entry->fid = vnode->fid; - } else { - __entry->fid.vid = 0; - __entry->fid.vnode = 0; - __entry->fid.unique = 0; - } + __entry->fid = *fid; memcpy(__entry->name, name->name, __len); __entry->name[__len] = 0; ), -- cgit v1.2.3 From c64cd6e34ea340adbb2a0a2f99cc884b96dcdca5 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 10 Jan 2020 17:17:19 -0500 Subject: reimplement path_mountpoint() with less magic ... and get rid of a bunch of bugs in it. Background: the reason for path_mountpoint() is that umount() really doesn't want attempts to revalidate the root of what it's trying to umount. The thing we want to avoid actually happen from complete_walk(); solution was to do something parallel to normal path_lookupat() and it both went overboard and got the boilerplate subtly (and not so subtly) wrong. A better solution is to do pretty much what the normal path_lookupat() does, but instead of complete_walk() do unlazy_walk(). All it takes to avoid that ->d_weak_revalidate() call... mountpoint_last() goes away, along with everything it got wrong, and so does the magic around LOOKUP_NO_REVAL. Another source of bugs is that when we traverse mounts at the final location (and we need to do that - umount . expects to get whatever's overmounting ., if any, out of the lookup) we really ought to take care of ->d_manage() - as it is, manual umount of autofs automount in progress can lead to unpleasant surprises for the daemon. Easily solved by using handle_lookup_down() instead of follow_mount(). Tested-by: Ian Kent Signed-off-by: Al Viro --- fs/namei.c | 89 +++++++-------------------------------------------- fs/nfs/nfstrace.h | 2 -- include/linux/namei.h | 1 - 3 files changed, 12 insertions(+), 80 deletions(-) (limited to 'include') diff --git a/fs/namei.c b/fs/namei.c index d6c91d1e88cb..204677c37751 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -1649,17 +1649,15 @@ again: if (IS_ERR(dentry)) return dentry; if (unlikely(!d_in_lookup(dentry))) { - if (!(flags & LOOKUP_NO_REVAL)) { - int error = d_revalidate(dentry, flags); - if (unlikely(error <= 0)) { - if (!error) { - d_invalidate(dentry); - dput(dentry); - goto again; - } + int error = d_revalidate(dentry, flags); + if (unlikely(error <= 0)) { + if (!error) { + d_invalidate(dentry); dput(dentry); - dentry = ERR_PTR(error); + goto again; } + dput(dentry); + dentry = ERR_PTR(error); } } else { old = inode->i_op->lookup(inode, dentry, flags); @@ -2617,72 +2615,6 @@ int user_path_at_empty(int dfd, const char __user *name, unsigned flags, } EXPORT_SYMBOL(user_path_at_empty); -/** - * mountpoint_last - look up last component for umount - * @nd: pathwalk nameidata - currently pointing at parent directory of "last" - * - * This is a special lookup_last function just for umount. In this case, we - * need to resolve the path without doing any revalidation. - * - * The nameidata should be the result of doing a LOOKUP_PARENT pathwalk. Since - * mountpoints are always pinned in the dcache, their ancestors are too. Thus, - * in almost all cases, this lookup will be served out of the dcache. The only - * cases where it won't are if nd->last refers to a symlink or the path is - * bogus and it doesn't exist. - * - * Returns: - * -error: if there was an error during lookup. This includes -ENOENT if the - * lookup found a negative dentry. - * - * 0: if we successfully resolved nd->last and found it to not to be a - * symlink that needs to be followed. - * - * 1: if we successfully resolved nd->last and found it to be a symlink - * that needs to be followed. - */ -static int -mountpoint_last(struct nameidata *nd) -{ - int error = 0; - struct dentry *dir = nd->path.dentry; - struct path path; - - /* If we're in rcuwalk, drop out of it to handle last component */ - if (nd->flags & LOOKUP_RCU) { - if (unlazy_walk(nd)) - return -ECHILD; - } - - nd->flags &= ~LOOKUP_PARENT; - - if (unlikely(nd->last_type != LAST_NORM)) { - error = handle_dots(nd, nd->last_type); - if (error) - return error; - path.dentry = dget(nd->path.dentry); - } else { - path.dentry = d_lookup(dir, &nd->last); - if (!path.dentry) { - /* - * No cached dentry. Mounted dentries are pinned in the - * cache, so that means that this dentry is probably - * a symlink or the path doesn't actually point - * to a mounted dentry. - */ - path.dentry = lookup_slow(&nd->last, dir, - nd->flags | LOOKUP_NO_REVAL); - if (IS_ERR(path.dentry)) - return PTR_ERR(path.dentry); - } - } - if (d_flags_negative(smp_load_acquire(&path.dentry->d_flags))) { - dput(path.dentry); - return -ENOENT; - } - path.mnt = nd->path.mnt; - return step_into(nd, &path, 0, d_backing_inode(path.dentry), 0); -} - /** * path_mountpoint - look up a path to be umounted * @nd: lookup context @@ -2699,14 +2631,17 @@ path_mountpoint(struct nameidata *nd, unsigned flags, struct path *path) int err; while (!(err = link_path_walk(s, nd)) && - (err = mountpoint_last(nd)) > 0) { + (err = lookup_last(nd)) > 0) { s = trailing_symlink(nd); } + if (!err && (nd->flags & LOOKUP_RCU)) + err = unlazy_walk(nd); + if (!err) + err = handle_lookup_down(nd); if (!err) { *path = nd->path; nd->path.mnt = NULL; nd->path.dentry = NULL; - follow_mount(path); } terminate_walk(nd); return err; diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h index f64a33d2a1d1..2a82dcce5fc1 100644 --- a/fs/nfs/nfstrace.h +++ b/fs/nfs/nfstrace.h @@ -206,7 +206,6 @@ TRACE_DEFINE_ENUM(LOOKUP_AUTOMOUNT); TRACE_DEFINE_ENUM(LOOKUP_PARENT); TRACE_DEFINE_ENUM(LOOKUP_REVAL); TRACE_DEFINE_ENUM(LOOKUP_RCU); -TRACE_DEFINE_ENUM(LOOKUP_NO_REVAL); TRACE_DEFINE_ENUM(LOOKUP_OPEN); TRACE_DEFINE_ENUM(LOOKUP_CREATE); TRACE_DEFINE_ENUM(LOOKUP_EXCL); @@ -224,7 +223,6 @@ TRACE_DEFINE_ENUM(LOOKUP_DOWN); { LOOKUP_PARENT, "PARENT" }, \ { LOOKUP_REVAL, "REVAL" }, \ { LOOKUP_RCU, "RCU" }, \ - { LOOKUP_NO_REVAL, "NO_REVAL" }, \ { LOOKUP_OPEN, "OPEN" }, \ { LOOKUP_CREATE, "CREATE" }, \ { LOOKUP_EXCL, "EXCL" }, \ diff --git a/include/linux/namei.h b/include/linux/namei.h index 7fe7b87a3ded..07bfb0874033 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -34,7 +34,6 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT, LAST_BIND}; /* internal use only */ #define LOOKUP_PARENT 0x0010 -#define LOOKUP_NO_REVAL 0x0080 #define LOOKUP_JUMPED 0x1000 #define LOOKUP_ROOT 0x2000 #define LOOKUP_ROOT_GRABBED 0x0008 -- cgit v1.2.3 From 26ec17a1dc5ecdd8d91aba63ead6f8b5ad5dea0d Mon Sep 17 00:00:00 2001 From: Orr Mazor Date: Sun, 22 Dec 2019 14:55:31 +0000 Subject: cfg80211: Fix radar event during another phy CAC In case a radar event of CAC_FINISHED or RADAR_DETECTED happens during another phy is during CAC we might need to cancel that CAC. If we got a radar in a channel that another phy is now doing CAC on then the CAC should be canceled there. If, for example, 2 phys doing CAC on the same channels, or on comptable channels, once on of them will finish his CAC the other might need to cancel his CAC, since it is no longer relevant. To fix that the commit adds an callback and implement it in mac80211 to end CAC. This commit also adds a call to said callback if after a radar event we see the CAC is no longer relevant Signed-off-by: Orr Mazor Reviewed-by: Sergey Matyukevich Link: https://lore.kernel.org/r/20191222145449.15792-1-Orr.Mazor@tandemg.com [slightly reformat/reword commit message] Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 5 +++++ net/mac80211/cfg.c | 23 +++++++++++++++++++++++ net/wireless/rdev-ops.h | 10 ++++++++++ net/wireless/reg.c | 23 ++++++++++++++++++++++- net/wireless/trace.h | 5 +++++ 5 files changed, 65 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 059524b87c4c..f22bd6c838a3 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -3548,6 +3548,9 @@ struct cfg80211_update_owe_info { * * @start_radar_detection: Start radar detection in the driver. * + * @end_cac: End running CAC, probably because a related CAC + * was finished on another phy. + * * @update_ft_ies: Provide updated Fast BSS Transition information to the * driver. If the SME is in the driver/firmware, this information can be * used in building Authentication and Reassociation Request frames. @@ -3874,6 +3877,8 @@ struct cfg80211_ops { struct net_device *dev, struct cfg80211_chan_def *chandef, u32 cac_time_ms); + void (*end_cac)(struct wiphy *wiphy, + struct net_device *dev); int (*update_ft_ies)(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_update_ft_ies_params *ftie); int (*crit_proto_start)(struct wiphy *wiphy, diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 4fb7f1f12109..000c742d0527 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -2954,6 +2954,28 @@ static int ieee80211_start_radar_detection(struct wiphy *wiphy, return err; } +static void ieee80211_end_cac(struct wiphy *wiphy, + struct net_device *dev) +{ + struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + struct ieee80211_local *local = sdata->local; + + mutex_lock(&local->mtx); + list_for_each_entry(sdata, &local->interfaces, list) { + /* it might be waiting for the local->mtx, but then + * by the time it gets it, sdata->wdev.cac_started + * will no longer be true + */ + cancel_delayed_work(&sdata->dfs_cac_timer_work); + + if (sdata->wdev.cac_started) { + ieee80211_vif_release_channel(sdata); + sdata->wdev.cac_started = false; + } + } + mutex_unlock(&local->mtx); +} + static struct cfg80211_beacon_data * cfg80211_beacon_dup(struct cfg80211_beacon_data *beacon) { @@ -4023,6 +4045,7 @@ const struct cfg80211_ops mac80211_config_ops = { #endif .get_channel = ieee80211_cfg_get_channel, .start_radar_detection = ieee80211_start_radar_detection, + .end_cac = ieee80211_end_cac, .channel_switch = ieee80211_channel_switch, .set_qos_map = ieee80211_set_qos_map, .set_ap_chanwidth = ieee80211_set_ap_chanwidth, diff --git a/net/wireless/rdev-ops.h b/net/wireless/rdev-ops.h index e853a4fe6f97..663c0d3127a4 100644 --- a/net/wireless/rdev-ops.h +++ b/net/wireless/rdev-ops.h @@ -1167,6 +1167,16 @@ rdev_start_radar_detection(struct cfg80211_registered_device *rdev, return ret; } +static inline void +rdev_end_cac(struct cfg80211_registered_device *rdev, + struct net_device *dev) +{ + trace_rdev_end_cac(&rdev->wiphy, dev); + if (rdev->ops->end_cac) + rdev->ops->end_cac(&rdev->wiphy, dev); + trace_rdev_return_void(&rdev->wiphy); +} + static inline int rdev_set_mcast_rate(struct cfg80211_registered_device *rdev, struct net_device *dev, diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 3c2070040277..fff9a74891fc 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -3892,6 +3892,25 @@ bool regulatory_pre_cac_allowed(struct wiphy *wiphy) } EXPORT_SYMBOL(regulatory_pre_cac_allowed); +static void cfg80211_check_and_end_cac(struct cfg80211_registered_device *rdev) +{ + struct wireless_dev *wdev; + /* If we finished CAC or received radar, we should end any + * CAC running on the same channels. + * the check !cfg80211_chandef_dfs_usable contain 2 options: + * either all channels are available - those the CAC_FINISHED + * event has effected another wdev state, or there is a channel + * in unavailable state in wdev chandef - those the RADAR_DETECTED + * event has effected another wdev state. + * In both cases we should end the CAC on the wdev. + */ + list_for_each_entry(wdev, &rdev->wiphy.wdev_list, list) { + if (wdev->cac_started && + !cfg80211_chandef_dfs_usable(&rdev->wiphy, &wdev->chandef)) + rdev_end_cac(rdev, wdev->netdev); + } +} + void regulatory_propagate_dfs_state(struct wiphy *wiphy, struct cfg80211_chan_def *chandef, enum nl80211_dfs_state dfs_state, @@ -3918,8 +3937,10 @@ void regulatory_propagate_dfs_state(struct wiphy *wiphy, cfg80211_set_dfs_state(&rdev->wiphy, chandef, dfs_state); if (event == NL80211_RADAR_DETECTED || - event == NL80211_RADAR_CAC_FINISHED) + event == NL80211_RADAR_CAC_FINISHED) { cfg80211_sched_dfs_chan_update(rdev); + cfg80211_check_and_end_cac(rdev); + } nl80211_radar_notify(rdev, chandef, event, NULL, GFP_KERNEL); } diff --git a/net/wireless/trace.h b/net/wireless/trace.h index d98ad2b3143b..8677d7ab7d69 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -646,6 +646,11 @@ DEFINE_EVENT(wiphy_netdev_evt, rdev_flush_pmksa, TP_ARGS(wiphy, netdev) ); +DEFINE_EVENT(wiphy_netdev_evt, rdev_end_cac, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev), + TP_ARGS(wiphy, netdev) +); + DECLARE_EVENT_CLASS(station_add_change, TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, u8 *mac, struct station_parameters *params), -- cgit v1.2.3 From 0af2ffc93a4b50948f9dad2786b7f1bd253bf0b9 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Wed, 15 Jan 2020 21:47:33 +0100 Subject: bpf: Fix incorrect verifier simulation of ARSH under ALU32 Anatoly has been fuzzing with kBdysch harness and reported a hang in one of the outcomes: 0: R1=ctx(id=0,off=0,imm=0) R10=fp0 0: (85) call bpf_get_socket_cookie#46 1: R0_w=invP(id=0) R10=fp0 1: (57) r0 &= 808464432 2: R0_w=invP(id=0,umax_value=808464432,var_off=(0x0; 0x30303030)) R10=fp0 2: (14) w0 -= 810299440 3: R0_w=invP(id=0,umax_value=4294967295,var_off=(0xcf800000; 0x3077fff0)) R10=fp0 3: (c4) w0 s>>= 1 4: R0_w=invP(id=0,umin_value=1740636160,umax_value=2147221496,var_off=(0x67c00000; 0x183bfff8)) R10=fp0 4: (76) if w0 s>= 0x30303030 goto pc+216 221: R0_w=invP(id=0,umin_value=1740636160,umax_value=2147221496,var_off=(0x67c00000; 0x183bfff8)) R10=fp0 221: (95) exit processed 6 insns (limit 1000000) [...] Taking a closer look, the program was xlated as follows: # ./bpftool p d x i 12 0: (85) call bpf_get_socket_cookie#7800896 1: (bf) r6 = r0 2: (57) r6 &= 808464432 3: (14) w6 -= 810299440 4: (c4) w6 s>>= 1 5: (76) if w6 s>= 0x30303030 goto pc+216 6: (05) goto pc-1 7: (05) goto pc-1 8: (05) goto pc-1 [...] 220: (05) goto pc-1 221: (05) goto pc-1 222: (95) exit Meaning, the visible effect is very similar to f54c7898ed1c ("bpf: Fix precision tracking for unbounded scalars"), that is, the fall-through branch in the instruction 5 is considered to be never taken given the conclusion from the min/max bounds tracking in w6, and therefore the dead-code sanitation rewrites it as goto pc-1. However, real-life input disagrees with verification analysis since a soft-lockup was observed. The bug sits in the analysis of the ARSH. The definition is that we shift the target register value right by K bits through shifting in copies of its sign bit. In adjust_scalar_min_max_vals(), we do first coerce the register into 32 bit mode, same happens after simulating the operation. However, for the case of simulating the actual ARSH, we don't take the mode into account and act as if it's always 64 bit, but location of sign bit is different: dst_reg->smin_value >>= umin_val; dst_reg->smax_value >>= umin_val; dst_reg->var_off = tnum_arshift(dst_reg->var_off, umin_val); Consider an unknown R0 where bpf_get_socket_cookie() (or others) would for example return 0xffff. With the above ARSH simulation, we'd see the following results: [...] 1: R1=ctx(id=0,off=0,imm=0) R2_w=invP65535 R10=fp0 1: (85) call bpf_get_socket_cookie#46 2: R0_w=invP(id=0) R10=fp0 2: (57) r0 &= 808464432 -> R0_runtime = 0x3030 3: R0_w=invP(id=0,umax_value=808464432,var_off=(0x0; 0x30303030)) R10=fp0 3: (14) w0 -= 810299440 -> R0_runtime = 0xcfb40000 4: R0_w=invP(id=0,umax_value=4294967295,var_off=(0xcf800000; 0x3077fff0)) R10=fp0 (0xffffffff) 4: (c4) w0 s>>= 1 -> R0_runtime = 0xe7da0000 5: R0_w=invP(id=0,umin_value=1740636160,umax_value=2147221496,var_off=(0x67c00000; 0x183bfff8)) R10=fp0 (0x67c00000) (0x7ffbfff8) [...] In insn 3, we have a runtime value of 0xcfb40000, which is '1100 1111 1011 0100 0000 0000 0000 0000', the result after the shift has 0xe7da0000 that is '1110 0111 1101 1010 0000 0000 0000 0000', where the sign bit is correctly retained in 32 bit mode. In insn4, the umax was 0xffffffff, and changed into 0x7ffbfff8 after the shift, that is, '0111 1111 1111 1011 1111 1111 1111 1000' and means here that the simulation didn't retain the sign bit. With above logic, the updates happen on the 64 bit min/max bounds and given we coerced the register, the sign bits of the bounds are cleared as well, meaning, we need to force the simulation into s32 space for 32 bit alu mode. Verification after the fix below. We're first analyzing the fall-through branch on 32 bit signed >= test eventually leading to rejection of the program in this specific case: 0: R1=ctx(id=0,off=0,imm=0) R10=fp0 0: (b7) r2 = 808464432 1: R1=ctx(id=0,off=0,imm=0) R2_w=invP808464432 R10=fp0 1: (85) call bpf_get_socket_cookie#46 2: R0_w=invP(id=0) R10=fp0 2: (bf) r6 = r0 3: R0_w=invP(id=0) R6_w=invP(id=0) R10=fp0 3: (57) r6 &= 808464432 4: R0_w=invP(id=0) R6_w=invP(id=0,umax_value=808464432,var_off=(0x0; 0x30303030)) R10=fp0 4: (14) w6 -= 810299440 5: R0_w=invP(id=0) R6_w=invP(id=0,umax_value=4294967295,var_off=(0xcf800000; 0x3077fff0)) R10=fp0 5: (c4) w6 s>>= 1 6: R0_w=invP(id=0) R6_w=invP(id=0,umin_value=3888119808,umax_value=4294705144,var_off=(0xe7c00000; 0x183bfff8)) R10=fp0 (0x67c00000) (0xfffbfff8) 6: (76) if w6 s>= 0x30303030 goto pc+216 7: R0_w=invP(id=0) R6_w=invP(id=0,umin_value=3888119808,umax_value=4294705144,var_off=(0xe7c00000; 0x183bfff8)) R10=fp0 7: (30) r0 = *(u8 *)skb[808464432] BPF_LD_[ABS|IND] uses reserved fields processed 8 insns (limit 1000000) [...] Fixes: 9cbe1f5a32dc ("bpf/verifier: improve register value range tracking with ARSH") Reported-by: Anatoly Trosinenko Signed-off-by: Daniel Borkmann Acked-by: Yonghong Song Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200115204733.16648-1-daniel@iogearbox.net --- include/linux/tnum.h | 2 +- kernel/bpf/tnum.c | 9 +++++++-- kernel/bpf/verifier.c | 13 ++++++++++--- 3 files changed, 18 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/tnum.h b/include/linux/tnum.h index c17af77f3fae..ea627d1ab7e3 100644 --- a/include/linux/tnum.h +++ b/include/linux/tnum.h @@ -30,7 +30,7 @@ struct tnum tnum_lshift(struct tnum a, u8 shift); /* Shift (rsh) a tnum right (by a fixed shift) */ struct tnum tnum_rshift(struct tnum a, u8 shift); /* Shift (arsh) a tnum right (by a fixed min_shift) */ -struct tnum tnum_arshift(struct tnum a, u8 min_shift); +struct tnum tnum_arshift(struct tnum a, u8 min_shift, u8 insn_bitness); /* Add two tnums, return @a + @b */ struct tnum tnum_add(struct tnum a, struct tnum b); /* Subtract two tnums, return @a - @b */ diff --git a/kernel/bpf/tnum.c b/kernel/bpf/tnum.c index ca52b9642943..d4f335a9a899 100644 --- a/kernel/bpf/tnum.c +++ b/kernel/bpf/tnum.c @@ -44,14 +44,19 @@ struct tnum tnum_rshift(struct tnum a, u8 shift) return TNUM(a.value >> shift, a.mask >> shift); } -struct tnum tnum_arshift(struct tnum a, u8 min_shift) +struct tnum tnum_arshift(struct tnum a, u8 min_shift, u8 insn_bitness) { /* if a.value is negative, arithmetic shifting by minimum shift * will have larger negative offset compared to more shifting. * If a.value is nonnegative, arithmetic shifting by minimum shift * will have larger positive offset compare to more shifting. */ - return TNUM((s64)a.value >> min_shift, (s64)a.mask >> min_shift); + if (insn_bitness == 32) + return TNUM((u32)(((s32)a.value) >> min_shift), + (u32)(((s32)a.mask) >> min_shift)); + else + return TNUM((s64)a.value >> min_shift, + (s64)a.mask >> min_shift); } struct tnum tnum_add(struct tnum a, struct tnum b) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index ce85e7041f0c..7d530ce8719d 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -5049,9 +5049,16 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, /* Upon reaching here, src_known is true and * umax_val is equal to umin_val. */ - dst_reg->smin_value >>= umin_val; - dst_reg->smax_value >>= umin_val; - dst_reg->var_off = tnum_arshift(dst_reg->var_off, umin_val); + if (insn_bitness == 32) { + dst_reg->smin_value = (u32)(((s32)dst_reg->smin_value) >> umin_val); + dst_reg->smax_value = (u32)(((s32)dst_reg->smax_value) >> umin_val); + } else { + dst_reg->smin_value >>= umin_val; + dst_reg->smax_value >>= umin_val; + } + + dst_reg->var_off = tnum_arshift(dst_reg->var_off, umin_val, + insn_bitness); /* blow away the dst_reg umin_value/umax_value and rely on * dst_reg var_off to refine the result. -- cgit v1.2.3 From 5a64967a2f3bbc01cc708ee43c7b0893089c61c4 Mon Sep 17 00:00:00 2001 From: Wayne Lin Date: Mon, 13 Jan 2020 17:36:49 +0800 Subject: drm/dp_mst: Have DP_Tx send one msg at a time [Why] Noticed this while testing MST with the 4 ports MST hub from StarTech.com. Sometimes can't light up monitors normally and get the error message as 'sideband msg build failed'. Look into aux transactions, found out that source sometimes will send out another down request before receiving the down reply of the previous down request. On the other hand, in drm_dp_get_one_sb_msg(), current code doesn't handle the interleaved replies case. Hence, source can't build up message completely and can't light up monitors. [How] For good compatibility, enforce source to send out one down request at a time. Add a flag, is_waiting_for_dwn_reply, to determine if the source can send out a down request immediately or not. - Check the flag before calling process_single_down_tx_qlock to send out a msg - Set the flag when successfully send out a down request - Clear the flag when successfully build up a down reply - Clear the flag when find erros during sending out a down request - Clear the flag when find errors during building up a down reply - Clear the flag when timeout occurs during waiting for a down reply - Use drm_dp_mst_kick_tx() to try to send another down request in queue at the end of drm_dp_mst_wait_tx_reply() (attempt to send out messages in queue when errors occur) Cc: Lyude Paul Signed-off-by: Wayne Lin Signed-off-by: Lyude Paul Link: https://patchwork.freedesktop.org/patch/msgid/20200113093649.11755-1-Wayne.Lin@amd.com --- drivers/gpu/drm/drm_dp_mst_topology.c | 14 ++++++++++++-- include/drm/drm_dp_mst_helper.h | 6 ++++++ 2 files changed, 18 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c index 03874ee2a033..5a61a5596912 100644 --- a/drivers/gpu/drm/drm_dp_mst_topology.c +++ b/drivers/gpu/drm/drm_dp_mst_topology.c @@ -1190,6 +1190,8 @@ static int drm_dp_mst_wait_tx_reply(struct drm_dp_mst_branch *mstb, txmsg->state == DRM_DP_SIDEBAND_TX_SENT) { mstb->tx_slots[txmsg->seqno] = NULL; } + mgr->is_waiting_for_dwn_reply = false; + } out: if (unlikely(ret == -EIO) && drm_debug_enabled(DRM_UT_DP)) { @@ -1199,6 +1201,7 @@ out: } mutex_unlock(&mgr->qlock); + drm_dp_mst_kick_tx(mgr); return ret; } @@ -2741,9 +2744,11 @@ static void process_single_down_tx_qlock(struct drm_dp_mst_topology_mgr *mgr) ret = process_single_tx_qlock(mgr, txmsg, false); if (ret == 1) { /* txmsg is sent it should be in the slots now */ + mgr->is_waiting_for_dwn_reply = true; list_del(&txmsg->next); } else if (ret) { DRM_DEBUG_KMS("failed to send msg in q %d\n", ret); + mgr->is_waiting_for_dwn_reply = false; list_del(&txmsg->next); if (txmsg->seqno != -1) txmsg->dst->tx_slots[txmsg->seqno] = NULL; @@ -2783,7 +2788,8 @@ static void drm_dp_queue_down_tx(struct drm_dp_mst_topology_mgr *mgr, drm_dp_mst_dump_sideband_msg_tx(&p, txmsg); } - if (list_is_singular(&mgr->tx_msg_downq)) + if (list_is_singular(&mgr->tx_msg_downq) && + !mgr->is_waiting_for_dwn_reply) process_single_down_tx_qlock(mgr); mutex_unlock(&mgr->qlock); } @@ -3701,6 +3707,7 @@ static int drm_dp_mst_handle_down_rep(struct drm_dp_mst_topology_mgr *mgr) mutex_lock(&mgr->qlock); txmsg->state = DRM_DP_SIDEBAND_TX_RX; mstb->tx_slots[slot] = NULL; + mgr->is_waiting_for_dwn_reply = false; mutex_unlock(&mgr->qlock); wake_up_all(&mgr->tx_waitq); @@ -3710,6 +3717,9 @@ static int drm_dp_mst_handle_down_rep(struct drm_dp_mst_topology_mgr *mgr) no_msg: drm_dp_mst_topology_put_mstb(mstb); clear_down_rep_recv: + mutex_lock(&mgr->qlock); + mgr->is_waiting_for_dwn_reply = false; + mutex_unlock(&mgr->qlock); memset(&mgr->down_rep_recv, 0, sizeof(struct drm_dp_sideband_msg_rx)); return 0; @@ -4520,7 +4530,7 @@ static void drm_dp_tx_work(struct work_struct *work) struct drm_dp_mst_topology_mgr *mgr = container_of(work, struct drm_dp_mst_topology_mgr, tx_work); mutex_lock(&mgr->qlock); - if (!list_empty(&mgr->tx_msg_downq)) + if (!list_empty(&mgr->tx_msg_downq) && !mgr->is_waiting_for_dwn_reply) process_single_down_tx_qlock(mgr); mutex_unlock(&mgr->qlock); } diff --git a/include/drm/drm_dp_mst_helper.h b/include/drm/drm_dp_mst_helper.h index d5fc90b30487..c1bda7030e2d 100644 --- a/include/drm/drm_dp_mst_helper.h +++ b/include/drm/drm_dp_mst_helper.h @@ -605,6 +605,12 @@ struct drm_dp_mst_topology_mgr { * &drm_dp_sideband_msg_tx.state once they are queued */ struct mutex qlock; + + /** + * @is_waiting_for_dwn_reply: indicate whether is waiting for down reply + */ + bool is_waiting_for_dwn_reply; + /** * @tx_msg_downq: List of pending down replies. */ -- cgit v1.2.3 From 4da6a196f93b1af7612340e8c1ad8ce71e18f955 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Sat, 11 Jan 2020 06:11:59 +0000 Subject: bpf: Sockmap/tls, during free we may call tcp_bpf_unhash() in loop When a sockmap is free'd and a socket in the map is enabled with tls we tear down the bpf context on the socket, the psock struct and state, and then call tcp_update_ulp(). The tcp_update_ulp() call is to inform the tls stack it needs to update its saved sock ops so that when the tls socket is later destroyed it doesn't try to call the now destroyed psock hooks. This is about keeping stacked ULPs in good shape so they always have the right set of stacked ops. However, recently unhash() hook was removed from TLS side. But, the sockmap/bpf side is not doing any extra work to update the unhash op when is torn down instead expecting TLS side to manage it. So both TLS and sockmap believe the other side is managing the op and instead no one updates the hook so it continues to point at tcp_bpf_unhash(). When unhash hook is called we call tcp_bpf_unhash() which detects the psock has already been destroyed and calls sk->sk_prot_unhash() which calls tcp_bpf_unhash() yet again and so on looping and hanging the core. To fix have sockmap tear down logic fixup the stale pointer. Fixes: 5d92e631b8be ("net/tls: partially revert fix transition through disconnect with close") Reported-by: syzbot+83979935eb6304f8cd46@syzkaller.appspotmail.com Signed-off-by: John Fastabend Signed-off-by: Daniel Borkmann Reviewed-by: Jakub Sitnicki Acked-by: Song Liu Cc: stable@vger.kernel.org Link: https://lore.kernel.org/bpf/20200111061206.8028-2-john.fastabend@gmail.com --- include/linux/skmsg.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index ef7031f8a304..b6afe01f8592 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -358,6 +358,7 @@ static inline void sk_psock_update_proto(struct sock *sk, static inline void sk_psock_restore_proto(struct sock *sk, struct sk_psock *psock) { + sk->sk_prot->unhash = psock->saved_unhash; sk->sk_write_space = psock->saved_write_space; if (psock->sk_proto) { -- cgit v1.2.3 From 33bfe20dd7117dd81fd896a53f743a233e1ad64f Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Sat, 11 Jan 2020 06:12:01 +0000 Subject: bpf: Sockmap/tls, push write_space updates through ulp updates When sockmap sock with TLS enabled is removed we cleanup bpf/psock state and call tcp_update_ulp() to push updates to TLS ULP on top. However, we don't push the write_space callback up and instead simply overwrite the op with the psock stored previous op. This may or may not be correct so to ensure we don't overwrite the TLS write space hook pass this field to the ULP and have it fixup the ctx. This completes a previous fix that pushed the ops through to the ULP but at the time missed doing this for write_space, presumably because write_space TLS hook was added around the same time. Fixes: 95fa145479fbc ("bpf: sockmap/tls, close can race with map free") Signed-off-by: John Fastabend Signed-off-by: Daniel Borkmann Reviewed-by: Jakub Sitnicki Acked-by: Jonathan Lemon Cc: stable@vger.kernel.org Link: https://lore.kernel.org/bpf/20200111061206.8028-4-john.fastabend@gmail.com --- include/linux/skmsg.h | 12 ++++++++---- include/net/tcp.h | 6 ++++-- net/ipv4/tcp_ulp.c | 6 ++++-- net/tls/tls_main.c | 10 +++++++--- 4 files changed, 23 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index b6afe01f8592..14d61bba0b79 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -359,17 +359,21 @@ static inline void sk_psock_restore_proto(struct sock *sk, struct sk_psock *psock) { sk->sk_prot->unhash = psock->saved_unhash; - sk->sk_write_space = psock->saved_write_space; if (psock->sk_proto) { struct inet_connection_sock *icsk = inet_csk(sk); bool has_ulp = !!icsk->icsk_ulp_data; - if (has_ulp) - tcp_update_ulp(sk, psock->sk_proto); - else + if (has_ulp) { + tcp_update_ulp(sk, psock->sk_proto, + psock->saved_write_space); + } else { sk->sk_prot = psock->sk_proto; + sk->sk_write_space = psock->saved_write_space; + } psock->sk_proto = NULL; + } else { + sk->sk_write_space = psock->saved_write_space; } } diff --git a/include/net/tcp.h b/include/net/tcp.h index e460ea7f767b..e6f48384dc71 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -2147,7 +2147,8 @@ struct tcp_ulp_ops { /* initialize ulp */ int (*init)(struct sock *sk); /* update ulp */ - void (*update)(struct sock *sk, struct proto *p); + void (*update)(struct sock *sk, struct proto *p, + void (*write_space)(struct sock *sk)); /* cleanup ulp */ void (*release)(struct sock *sk); /* diagnostic */ @@ -2162,7 +2163,8 @@ void tcp_unregister_ulp(struct tcp_ulp_ops *type); int tcp_set_ulp(struct sock *sk, const char *name); void tcp_get_available_ulp(char *buf, size_t len); void tcp_cleanup_ulp(struct sock *sk); -void tcp_update_ulp(struct sock *sk, struct proto *p); +void tcp_update_ulp(struct sock *sk, struct proto *p, + void (*write_space)(struct sock *sk)); #define MODULE_ALIAS_TCP_ULP(name) \ __MODULE_INFO(alias, alias_userspace, name); \ diff --git a/net/ipv4/tcp_ulp.c b/net/ipv4/tcp_ulp.c index 12ab5db2b71c..38d3ad141161 100644 --- a/net/ipv4/tcp_ulp.c +++ b/net/ipv4/tcp_ulp.c @@ -99,17 +99,19 @@ void tcp_get_available_ulp(char *buf, size_t maxlen) rcu_read_unlock(); } -void tcp_update_ulp(struct sock *sk, struct proto *proto) +void tcp_update_ulp(struct sock *sk, struct proto *proto, + void (*write_space)(struct sock *sk)) { struct inet_connection_sock *icsk = inet_csk(sk); if (!icsk->icsk_ulp_ops) { + sk->sk_write_space = write_space; sk->sk_prot = proto; return; } if (icsk->icsk_ulp_ops->update) - icsk->icsk_ulp_ops->update(sk, proto); + icsk->icsk_ulp_ops->update(sk, proto, write_space); } void tcp_cleanup_ulp(struct sock *sk) diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index dac24c7aa7d4..94774c0e5ff3 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -732,15 +732,19 @@ out: return rc; } -static void tls_update(struct sock *sk, struct proto *p) +static void tls_update(struct sock *sk, struct proto *p, + void (*write_space)(struct sock *sk)) { struct tls_context *ctx; ctx = tls_get_ctx(sk); - if (likely(ctx)) + if (likely(ctx)) { + ctx->sk_write_space = write_space; ctx->sk_proto = p; - else + } else { sk->sk_prot = p; + sk->sk_write_space = write_space; + } } static int tls_get_info(const struct sock *sk, struct sk_buff *skb) -- cgit v1.2.3 From ad6bf88a6c19a39fb3b0045d78ea880325dfcf15 Mon Sep 17 00:00:00 2001 From: Mikulas Patocka Date: Wed, 15 Jan 2020 08:35:25 -0500 Subject: block: fix an integer overflow in logical block size Logical block size has type unsigned short. That means that it can be at most 32768. However, there are architectures that can run with 64k pages (for example arm64) and on these architectures, it may be possible to create block devices with 64k block size. For exmaple (run this on an architecture with 64k pages): Mount will fail with this error because it tries to read the superblock using 2-sector access: device-mapper: writecache: I/O is not aligned, sector 2, size 1024, block size 65536 EXT4-fs (dm-0): unable to read superblock This patch changes the logical block size from unsigned short to unsigned int to avoid the overflow. Cc: stable@vger.kernel.org Reviewed-by: Martin K. Petersen Reviewed-by: Ming Lei Signed-off-by: Mikulas Patocka Signed-off-by: Jens Axboe --- block/blk-settings.c | 2 +- drivers/md/dm-snap-persistent.c | 2 +- drivers/md/raid0.c | 2 +- include/linux/blkdev.h | 8 ++++---- 4 files changed, 7 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/block/blk-settings.c b/block/blk-settings.c index 5f6dcc7a47bd..c8eda2e7b91e 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -328,7 +328,7 @@ EXPORT_SYMBOL(blk_queue_max_segment_size); * storage device can address. The default of 512 covers most * hardware. **/ -void blk_queue_logical_block_size(struct request_queue *q, unsigned short size) +void blk_queue_logical_block_size(struct request_queue *q, unsigned int size) { q->limits.logical_block_size = size; diff --git a/drivers/md/dm-snap-persistent.c b/drivers/md/dm-snap-persistent.c index 3c50c4e4da8f..963d3774c93e 100644 --- a/drivers/md/dm-snap-persistent.c +++ b/drivers/md/dm-snap-persistent.c @@ -17,7 +17,7 @@ #include #define DM_MSG_PREFIX "persistent snapshot" -#define DM_CHUNK_SIZE_DEFAULT_SECTORS 32 /* 16KB */ +#define DM_CHUNK_SIZE_DEFAULT_SECTORS 32U /* 16KB */ #define DM_PREFETCH_CHUNKS 12 diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index b7c20979bd19..322386ff5d22 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -87,7 +87,7 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf) char b[BDEVNAME_SIZE]; char b2[BDEVNAME_SIZE]; struct r0conf *conf = kzalloc(sizeof(*conf), GFP_KERNEL); - unsigned short blksize = 512; + unsigned blksize = 512; *private_conf = ERR_PTR(-ENOMEM); if (!conf) diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 47eb22a3b7f9..4c636c42ad68 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -328,6 +328,7 @@ struct queue_limits { unsigned int max_sectors; unsigned int max_segment_size; unsigned int physical_block_size; + unsigned int logical_block_size; unsigned int alignment_offset; unsigned int io_min; unsigned int io_opt; @@ -338,7 +339,6 @@ struct queue_limits { unsigned int discard_granularity; unsigned int discard_alignment; - unsigned short logical_block_size; unsigned short max_segments; unsigned short max_integrity_segments; unsigned short max_discard_segments; @@ -1077,7 +1077,7 @@ extern void blk_queue_max_write_same_sectors(struct request_queue *q, unsigned int max_write_same_sectors); extern void blk_queue_max_write_zeroes_sectors(struct request_queue *q, unsigned int max_write_same_sectors); -extern void blk_queue_logical_block_size(struct request_queue *, unsigned short); +extern void blk_queue_logical_block_size(struct request_queue *, unsigned int); extern void blk_queue_physical_block_size(struct request_queue *, unsigned int); extern void blk_queue_alignment_offset(struct request_queue *q, unsigned int alignment); @@ -1291,7 +1291,7 @@ static inline unsigned int queue_max_segment_size(const struct request_queue *q) return q->limits.max_segment_size; } -static inline unsigned short queue_logical_block_size(const struct request_queue *q) +static inline unsigned queue_logical_block_size(const struct request_queue *q) { int retval = 512; @@ -1301,7 +1301,7 @@ static inline unsigned short queue_logical_block_size(const struct request_queue return retval; } -static inline unsigned short bdev_logical_block_size(struct block_device *bdev) +static inline unsigned int bdev_logical_block_size(struct block_device *bdev) { return queue_logical_block_size(bdev_get_queue(bdev)); } -- cgit v1.2.3