- Linux-stable-mirror - lists.linaro.org

[PATCH v4.14] net: dsa: Discard frames from unused ports

by Andrew Lunn

[ Upstream commit fc5f33768cca7144f8d793205b229d46740d183b ] The Marvell switches under some conditions will pass a frame to the host with the port being the CPU port. Such frames are invalid, and should be dropped. Not dropping them can result in a crash when incrementing the receive statistics for an invalid port. This has been reworked for 4.14, which does not have the central dsa_master_find_slave() function, so each tag driver needs to check. Reported-by: Chris Healy <cphealy(a)gmail.com> Fixes: 91da11f870f0 ("net: Distributed Switch Architecture protocol support") Signed-off-by: Andrew Lunn <andrew(a)lunn.ch> Reviewed-by: Florian Fainelli <f.fainelli(a)gmail.com> Signed-off-by: David S. Miller <davem(a)davemloft.net> --- net/dsa/tag_brcm.c | 3 +++ net/dsa/tag_dsa.c | 3 +++ net/dsa/tag_edsa.c | 3 +++ net/dsa/tag_ksz.c | 3 +++ net/dsa/tag_lan9303.c | 3 +++ net/dsa/tag_mtk.c | 3 +++ net/dsa/tag_qca.c | 3 +++ net/dsa/tag_trailer.c | 3 +++ 8 files changed, 24 insertions(+) diff --git a/net/dsa/tag_brcm.c b/net/dsa/tag_brcm.c index dbb016434ace..de92fc1fc3be 100644 --- a/net/dsa/tag_brcm.c +++ b/net/dsa/tag_brcm.c @@ -121,6 +121,9 @@ static struct sk_buff *brcm_tag_rcv(struct sk_buff *skb, struct net_device *dev, if (source_port >= ds->num_ports || !ds->ports[source_port].netdev) return NULL; + if (unlikely(ds->cpu_port_mask & BIT(source_port))) + return NULL; + /* Remove Broadcom tag and update checksum */ skb_pull_rcsum(skb, BRCM_TAG_LEN); diff --git a/net/dsa/tag_dsa.c b/net/dsa/tag_dsa.c index fbf9ca954773..b3008a9bacf3 100644 --- a/net/dsa/tag_dsa.c +++ b/net/dsa/tag_dsa.c @@ -107,6 +107,9 @@ static struct sk_buff *dsa_rcv(struct sk_buff *skb, struct net_device *dev, if (source_port >= ds->num_ports || !ds->ports[source_port].netdev) return NULL; + if (unlikely(ds->cpu_port_mask & BIT(source_port))) + return NULL; + /* * Convert the DSA header to an 802.1q header if the 'tagged' * bit in the DSA header is set. If the 'tagged' bit is clear, diff --git a/net/dsa/tag_edsa.c b/net/dsa/tag_edsa.c index 76367ba1b2e2..c86b6d90576d 100644 --- a/net/dsa/tag_edsa.c +++ b/net/dsa/tag_edsa.c @@ -120,6 +120,9 @@ static struct sk_buff *edsa_rcv(struct sk_buff *skb, struct net_device *dev, if (source_port >= ds->num_ports || !ds->ports[source_port].netdev) return NULL; + if (unlikely(ds->cpu_port_mask & BIT(source_port))) + return NULL; + /* * If the 'tagged' bit is set, convert the DSA tag to a 802.1q * tag and delete the ethertype part. If the 'tagged' bit is diff --git a/net/dsa/tag_ksz.c b/net/dsa/tag_ksz.c index 010ca0a336c4..6c894692b9cd 100644 --- a/net/dsa/tag_ksz.c +++ b/net/dsa/tag_ksz.c @@ -92,6 +92,9 @@ static struct sk_buff *ksz_rcv(struct sk_buff *skb, struct net_device *dev, if (source_port >= ds->num_ports || !ds->ports[source_port].netdev) return NULL; + if (unlikely(ds->cpu_port_mask & BIT(source_port))) + return NULL; + pskb_trim_rcsum(skb, skb->len - KSZ_EGRESS_TAG_LEN); skb->dev = ds->ports[source_port].netdev; diff --git a/net/dsa/tag_lan9303.c b/net/dsa/tag_lan9303.c index 0b9826105e42..2d1603009e16 100644 --- a/net/dsa/tag_lan9303.c +++ b/net/dsa/tag_lan9303.c @@ -108,6 +108,9 @@ static struct sk_buff *lan9303_rcv(struct sk_buff *skb, struct net_device *dev, return NULL; } + if (unlikely(ds->cpu_port_mask & BIT(source_port))) + return NULL; + if (!ds->ports[source_port].netdev) { dev_warn_ratelimited(&dev->dev, "Dropping packet due to invalid netdev or device\n"); return NULL; diff --git a/net/dsa/tag_mtk.c b/net/dsa/tag_mtk.c index ec8ee5f43255..5c471854412d 100644 --- a/net/dsa/tag_mtk.c +++ b/net/dsa/tag_mtk.c @@ -81,6 +81,9 @@ static struct sk_buff *mtk_tag_rcv(struct sk_buff *skb, struct net_device *dev, if (!ds->ports[port].netdev) return NULL; + if (unlikely(ds->cpu_port_mask & BIT(port))) + return NULL; + skb->dev = ds->ports[port].netdev; return skb; diff --git a/net/dsa/tag_qca.c b/net/dsa/tag_qca.c index 1d4c70711c0f..b8c05f1cf47d 100644 --- a/net/dsa/tag_qca.c +++ b/net/dsa/tag_qca.c @@ -104,6 +104,9 @@ static struct sk_buff *qca_tag_rcv(struct sk_buff *skb, struct net_device *dev, if (!ds->ports[port].netdev) return NULL; + if (unlikely(ds->cpu_port_mask & BIT(port))) + return NULL; + /* Update skb & forward the frame accordingly */ skb->dev = ds->ports[port].netdev; diff --git a/net/dsa/tag_trailer.c b/net/dsa/tag_trailer.c index d2fd4923aa3e..fcc9aa72877d 100644 --- a/net/dsa/tag_trailer.c +++ b/net/dsa/tag_trailer.c @@ -76,6 +76,9 @@ static struct sk_buff *trailer_rcv(struct sk_buff *skb, struct net_device *dev, if (source_port >= ds->num_ports || !ds->ports[source_port].netdev) return NULL; + if (unlikely(ds->cpu_port_mask & BIT(source_port))) + return NULL; + pskb_trim_rcsum(skb, skb->len - 4); skb->dev = ds->ports[source_port].netdev; -- 2.17.0

7 years, 2 months

3
2
0 0

FAILED: patch "[PATCH] writeback: safer lock nesting" failed to apply to 4.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.4-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 2e898e4c0a3897ccd434adac5abb8330194f527b Mon Sep 17 00:00:00 2001 From: Greg Thelen <gthelen(a)google.com> Date: Fri, 20 Apr 2018 14:55:42 -0700 Subject: [PATCH] writeback: safer lock nesting lock_page_memcg()/unlock_page_memcg() use spin_lock_irqsave/restore() if the page's memcg is undergoing move accounting, which occurs when a process leaves its memcg for a new one that has memory.move_charge_at_immigrate set. unlocked_inode_to_wb_begin,end() use spin_lock_irq/spin_unlock_irq() if the given inode is switching writeback domains. Switches occur when enough writes are issued from a new domain. This existing pattern is thus suspicious: lock_page_memcg(page); unlocked_inode_to_wb_begin(inode, &locked); ... unlocked_inode_to_wb_end(inode, locked); unlock_page_memcg(page); If both inode switch and process memcg migration are both in-flight then unlocked_inode_to_wb_end() will unconditionally enable interrupts while still holding the lock_page_memcg() irq spinlock. This suggests the possibility of deadlock if an interrupt occurs before unlock_page_memcg(). truncate __cancel_dirty_page lock_page_memcg unlocked_inode_to_wb_begin unlocked_inode_to_wb_end <interrupts mistakenly enabled> <interrupt> end_page_writeback test_clear_page_writeback lock_page_memcg <deadlock> unlock_page_memcg Due to configuration limitations this deadlock is not currently possible because we don't mix cgroup writeback (a cgroupv2 feature) and memory.move_charge_at_immigrate (a cgroupv1 feature). If the kernel is hacked to always claim inode switching and memcg moving_account, then this script triggers lockup in less than a minute: cd /mnt/cgroup/memory mkdir a b echo 1 > a/memory.move_charge_at_immigrate echo 1 > b/memory.move_charge_at_immigrate ( echo $BASHPID > a/cgroup.procs while true; do dd if=/dev/zero of=/mnt/big bs=1M count=256 done ) & while true; do sync done & sleep 1h & SLEEP=$! while true; do echo $SLEEP > a/cgroup.procs echo $SLEEP > b/cgroup.procs done The deadlock does not seem possible, so it's debatable if there's any reason to modify the kernel. I suggest we should to prevent future surprises. And Wang Long said "this deadlock occurs three times in our environment", so there's more reason to apply this, even to stable. Stable 4.4 has minor conflicts applying this patch. For a clean 4.4 patch see "[PATCH for-4.4] writeback: safer lock nesting" https://lkml.org/lkml/2018/4/11/146 Wang Long said "this deadlock occurs three times in our environment" [gthelen(a)google.com: v4] Link: http://lkml.kernel.org/r/20180411084653.254724-1-gthelen@google.com [akpm(a)linux-foundation.org: comment tweaks, struct initialization simplification] Change-Id: Ibb773e8045852978f6207074491d262f1b3fb613 Link: http://lkml.kernel.org/r/20180410005908.167976-1-gthelen@google.com Fixes: 682aa8e1a6a1 ("writeback: implement unlocked_inode_to_wb transaction and use it for stat updates") Signed-off-by: Greg Thelen <gthelen(a)google.com> Reported-by: Wang Long <wanglong19(a)meituan.com> Acked-by: Wang Long <wanglong19(a)meituan.com> Acked-by: Michal Hocko <mhocko(a)suse.com> Reviewed-by: Andrew Morton <akpm(a)linux-foundation.org> Cc: Johannes Weiner <hannes(a)cmpxchg.org> Cc: Tejun Heo <tj(a)kernel.org> Cc: Nicholas Piggin <npiggin(a)gmail.com> Cc: <stable(a)vger.kernel.org> [v4.2+] Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 4b12ba70a895..47d7c151fcba 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -745,11 +745,12 @@ int inode_congested(struct inode *inode, int cong_bits) */ if (inode && inode_to_wb_is_valid(inode)) { struct bdi_writeback *wb; - bool locked, congested; + struct wb_lock_cookie lock_cookie = {}; + bool congested; - wb = unlocked_inode_to_wb_begin(inode, &locked); + wb = unlocked_inode_to_wb_begin(inode, &lock_cookie); congested = wb_congested(wb, cong_bits); - unlocked_inode_to_wb_end(inode, locked); + unlocked_inode_to_wb_end(inode, &lock_cookie); return congested; } diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h index bfe86b54f6c1..0bd432a4d7bd 100644 --- a/include/linux/backing-dev-defs.h +++ b/include/linux/backing-dev-defs.h @@ -223,6 +223,11 @@ static inline void set_bdi_congested(struct backing_dev_info *bdi, int sync) set_wb_congested(bdi->wb.congested, sync); } +struct wb_lock_cookie { + bool locked; + unsigned long flags; +}; + #ifdef CONFIG_CGROUP_WRITEBACK /** diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index f6be4b0b6c18..72ca0f3d39f3 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -347,7 +347,7 @@ static inline struct bdi_writeback *inode_to_wb(const struct inode *inode) /** * unlocked_inode_to_wb_begin - begin unlocked inode wb access transaction * @inode: target inode - * @lockedp: temp bool output param, to be passed to the end function + * @cookie: output param, to be passed to the end function * * The caller wants to access the wb associated with @inode but isn't * holding inode->i_lock, the i_pages lock or wb->list_lock. This @@ -355,12 +355,12 @@ static inline struct bdi_writeback *inode_to_wb(const struct inode *inode) * association doesn't change until the transaction is finished with * unlocked_inode_to_wb_end(). * - * The caller must call unlocked_inode_to_wb_end() with *@lockdep - * afterwards and can't sleep during transaction. IRQ may or may not be - * disabled on return. + * The caller must call unlocked_inode_to_wb_end() with *@cookie afterwards and + * can't sleep during the transaction. IRQs may or may not be disabled on + * return. */ static inline struct bdi_writeback * -unlocked_inode_to_wb_begin(struct inode *inode, bool *lockedp) +unlocked_inode_to_wb_begin(struct inode *inode, struct wb_lock_cookie *cookie) { rcu_read_lock(); @@ -368,10 +368,10 @@ unlocked_inode_to_wb_begin(struct inode *inode, bool *lockedp) * Paired with store_release in inode_switch_wb_work_fn() and * ensures that we see the new wb if we see cleared I_WB_SWITCH. */ - *lockedp = smp_load_acquire(&inode->i_state) & I_WB_SWITCH; + cookie->locked = smp_load_acquire(&inode->i_state) & I_WB_SWITCH; - if (unlikely(*lockedp)) - xa_lock_irq(&inode->i_mapping->i_pages); + if (unlikely(cookie->locked)) + xa_lock_irqsave(&inode->i_mapping->i_pages, cookie->flags); /* * Protected by either !I_WB_SWITCH + rcu_read_lock() or the i_pages @@ -383,12 +383,13 @@ unlocked_inode_to_wb_begin(struct inode *inode, bool *lockedp) /** * unlocked_inode_to_wb_end - end inode wb access transaction * @inode: target inode - * @locked: *@lockedp from unlocked_inode_to_wb_begin() + * @cookie: @cookie from unlocked_inode_to_wb_begin() */ -static inline void unlocked_inode_to_wb_end(struct inode *inode, bool locked) +static inline void unlocked_inode_to_wb_end(struct inode *inode, + struct wb_lock_cookie *cookie) { - if (unlikely(locked)) - xa_unlock_irq(&inode->i_mapping->i_pages); + if (unlikely(cookie->locked)) + xa_unlock_irqrestore(&inode->i_mapping->i_pages, cookie->flags); rcu_read_unlock(); } @@ -435,12 +436,13 @@ static inline struct bdi_writeback *inode_to_wb(struct inode *inode) } static inline struct bdi_writeback * -unlocked_inode_to_wb_begin(struct inode *inode, bool *lockedp) +unlocked_inode_to_wb_begin(struct inode *inode, struct wb_lock_cookie *cookie) { return inode_to_wb(inode); } -static inline void unlocked_inode_to_wb_end(struct inode *inode, bool locked) +static inline void unlocked_inode_to_wb_end(struct inode *inode, + struct wb_lock_cookie *cookie) { } diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 5c1a3279e63f..337c6afb3345 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -2502,13 +2502,13 @@ void account_page_redirty(struct page *page) if (mapping && mapping_cap_account_dirty(mapping)) { struct inode *inode = mapping->host; struct bdi_writeback *wb; - bool locked; + struct wb_lock_cookie cookie = {}; - wb = unlocked_inode_to_wb_begin(inode, &locked); + wb = unlocked_inode_to_wb_begin(inode, &cookie); current->nr_dirtied--; dec_node_page_state(page, NR_DIRTIED); dec_wb_stat(wb, WB_DIRTIED); - unlocked_inode_to_wb_end(inode, locked); + unlocked_inode_to_wb_end(inode, &cookie); } } EXPORT_SYMBOL(account_page_redirty); @@ -2614,15 +2614,15 @@ void __cancel_dirty_page(struct page *page) if (mapping_cap_account_dirty(mapping)) { struct inode *inode = mapping->host; struct bdi_writeback *wb; - bool locked; + struct wb_lock_cookie cookie = {}; lock_page_memcg(page); - wb = unlocked_inode_to_wb_begin(inode, &locked); + wb = unlocked_inode_to_wb_begin(inode, &cookie); if (TestClearPageDirty(page)) account_page_cleaned(page, mapping, wb); - unlocked_inode_to_wb_end(inode, locked); + unlocked_inode_to_wb_end(inode, &cookie); unlock_page_memcg(page); } else { ClearPageDirty(page); @@ -2654,7 +2654,7 @@ int clear_page_dirty_for_io(struct page *page) if (mapping && mapping_cap_account_dirty(mapping)) { struct inode *inode = mapping->host; struct bdi_writeback *wb; - bool locked; + struct wb_lock_cookie cookie = {}; /* * Yes, Virginia, this is indeed insane. @@ -2691,14 +2691,14 @@ int clear_page_dirty_for_io(struct page *page) * always locked coming in here, so we get the desired * exclusion. */ - wb = unlocked_inode_to_wb_begin(inode, &locked); + wb = unlocked_inode_to_wb_begin(inode, &cookie); if (TestClearPageDirty(page)) { dec_lruvec_page_state(page, NR_FILE_DIRTY); dec_zone_page_state(page, NR_ZONE_WRITE_PENDING); dec_wb_stat(wb, WB_RECLAIMABLE); ret = 1; } - unlocked_inode_to_wb_end(inode, locked); + unlocked_inode_to_wb_end(inode, &cookie); return ret; } return TestClearPageDirty(page);

7 years, 2 months

1
0
0 0

FAILED: patch "[PATCH] writeback: safer lock nesting" failed to apply to 4.9-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.9-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 2e898e4c0a3897ccd434adac5abb8330194f527b Mon Sep 17 00:00:00 2001 From: Greg Thelen <gthelen(a)google.com> Date: Fri, 20 Apr 2018 14:55:42 -0700 Subject: [PATCH] writeback: safer lock nesting lock_page_memcg()/unlock_page_memcg() use spin_lock_irqsave/restore() if the page's memcg is undergoing move accounting, which occurs when a process leaves its memcg for a new one that has memory.move_charge_at_immigrate set. unlocked_inode_to_wb_begin,end() use spin_lock_irq/spin_unlock_irq() if the given inode is switching writeback domains. Switches occur when enough writes are issued from a new domain. This existing pattern is thus suspicious: lock_page_memcg(page); unlocked_inode_to_wb_begin(inode, &locked); ... unlocked_inode_to_wb_end(inode, locked); unlock_page_memcg(page); If both inode switch and process memcg migration are both in-flight then unlocked_inode_to_wb_end() will unconditionally enable interrupts while still holding the lock_page_memcg() irq spinlock. This suggests the possibility of deadlock if an interrupt occurs before unlock_page_memcg(). truncate __cancel_dirty_page lock_page_memcg unlocked_inode_to_wb_begin unlocked_inode_to_wb_end <interrupts mistakenly enabled> <interrupt> end_page_writeback test_clear_page_writeback lock_page_memcg <deadlock> unlock_page_memcg Due to configuration limitations this deadlock is not currently possible because we don't mix cgroup writeback (a cgroupv2 feature) and memory.move_charge_at_immigrate (a cgroupv1 feature). If the kernel is hacked to always claim inode switching and memcg moving_account, then this script triggers lockup in less than a minute: cd /mnt/cgroup/memory mkdir a b echo 1 > a/memory.move_charge_at_immigrate echo 1 > b/memory.move_charge_at_immigrate ( echo $BASHPID > a/cgroup.procs while true; do dd if=/dev/zero of=/mnt/big bs=1M count=256 done ) & while true; do sync done & sleep 1h & SLEEP=$! while true; do echo $SLEEP > a/cgroup.procs echo $SLEEP > b/cgroup.procs done The deadlock does not seem possible, so it's debatable if there's any reason to modify the kernel. I suggest we should to prevent future surprises. And Wang Long said "this deadlock occurs three times in our environment", so there's more reason to apply this, even to stable. Stable 4.4 has minor conflicts applying this patch. For a clean 4.4 patch see "[PATCH for-4.4] writeback: safer lock nesting" https://lkml.org/lkml/2018/4/11/146 Wang Long said "this deadlock occurs three times in our environment" [gthelen(a)google.com: v4] Link: http://lkml.kernel.org/r/20180411084653.254724-1-gthelen@google.com [akpm(a)linux-foundation.org: comment tweaks, struct initialization simplification] Change-Id: Ibb773e8045852978f6207074491d262f1b3fb613 Link: http://lkml.kernel.org/r/20180410005908.167976-1-gthelen@google.com Fixes: 682aa8e1a6a1 ("writeback: implement unlocked_inode_to_wb transaction and use it for stat updates") Signed-off-by: Greg Thelen <gthelen(a)google.com> Reported-by: Wang Long <wanglong19(a)meituan.com> Acked-by: Wang Long <wanglong19(a)meituan.com> Acked-by: Michal Hocko <mhocko(a)suse.com> Reviewed-by: Andrew Morton <akpm(a)linux-foundation.org> Cc: Johannes Weiner <hannes(a)cmpxchg.org> Cc: Tejun Heo <tj(a)kernel.org> Cc: Nicholas Piggin <npiggin(a)gmail.com> Cc: <stable(a)vger.kernel.org> [v4.2+] Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 4b12ba70a895..47d7c151fcba 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -745,11 +745,12 @@ int inode_congested(struct inode *inode, int cong_bits) */ if (inode && inode_to_wb_is_valid(inode)) { struct bdi_writeback *wb; - bool locked, congested; + struct wb_lock_cookie lock_cookie = {}; + bool congested; - wb = unlocked_inode_to_wb_begin(inode, &locked); + wb = unlocked_inode_to_wb_begin(inode, &lock_cookie); congested = wb_congested(wb, cong_bits); - unlocked_inode_to_wb_end(inode, locked); + unlocked_inode_to_wb_end(inode, &lock_cookie); return congested; } diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h index bfe86b54f6c1..0bd432a4d7bd 100644 --- a/include/linux/backing-dev-defs.h +++ b/include/linux/backing-dev-defs.h @@ -223,6 +223,11 @@ static inline void set_bdi_congested(struct backing_dev_info *bdi, int sync) set_wb_congested(bdi->wb.congested, sync); } +struct wb_lock_cookie { + bool locked; + unsigned long flags; +}; + #ifdef CONFIG_CGROUP_WRITEBACK /** diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index f6be4b0b6c18..72ca0f3d39f3 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -347,7 +347,7 @@ static inline struct bdi_writeback *inode_to_wb(const struct inode *inode) /** * unlocked_inode_to_wb_begin - begin unlocked inode wb access transaction * @inode: target inode - * @lockedp: temp bool output param, to be passed to the end function + * @cookie: output param, to be passed to the end function * * The caller wants to access the wb associated with @inode but isn't * holding inode->i_lock, the i_pages lock or wb->list_lock. This @@ -355,12 +355,12 @@ static inline struct bdi_writeback *inode_to_wb(const struct inode *inode) * association doesn't change until the transaction is finished with * unlocked_inode_to_wb_end(). * - * The caller must call unlocked_inode_to_wb_end() with *@lockdep - * afterwards and can't sleep during transaction. IRQ may or may not be - * disabled on return. + * The caller must call unlocked_inode_to_wb_end() with *@cookie afterwards and + * can't sleep during the transaction. IRQs may or may not be disabled on + * return. */ static inline struct bdi_writeback * -unlocked_inode_to_wb_begin(struct inode *inode, bool *lockedp) +unlocked_inode_to_wb_begin(struct inode *inode, struct wb_lock_cookie *cookie) { rcu_read_lock(); @@ -368,10 +368,10 @@ unlocked_inode_to_wb_begin(struct inode *inode, bool *lockedp) * Paired with store_release in inode_switch_wb_work_fn() and * ensures that we see the new wb if we see cleared I_WB_SWITCH. */ - *lockedp = smp_load_acquire(&inode->i_state) & I_WB_SWITCH; + cookie->locked = smp_load_acquire(&inode->i_state) & I_WB_SWITCH; - if (unlikely(*lockedp)) - xa_lock_irq(&inode->i_mapping->i_pages); + if (unlikely(cookie->locked)) + xa_lock_irqsave(&inode->i_mapping->i_pages, cookie->flags); /* * Protected by either !I_WB_SWITCH + rcu_read_lock() or the i_pages @@ -383,12 +383,13 @@ unlocked_inode_to_wb_begin(struct inode *inode, bool *lockedp) /** * unlocked_inode_to_wb_end - end inode wb access transaction * @inode: target inode - * @locked: *@lockedp from unlocked_inode_to_wb_begin() + * @cookie: @cookie from unlocked_inode_to_wb_begin() */ -static inline void unlocked_inode_to_wb_end(struct inode *inode, bool locked) +static inline void unlocked_inode_to_wb_end(struct inode *inode, + struct wb_lock_cookie *cookie) { - if (unlikely(locked)) - xa_unlock_irq(&inode->i_mapping->i_pages); + if (unlikely(cookie->locked)) + xa_unlock_irqrestore(&inode->i_mapping->i_pages, cookie->flags); rcu_read_unlock(); } @@ -435,12 +436,13 @@ static inline struct bdi_writeback *inode_to_wb(struct inode *inode) } static inline struct bdi_writeback * -unlocked_inode_to_wb_begin(struct inode *inode, bool *lockedp) +unlocked_inode_to_wb_begin(struct inode *inode, struct wb_lock_cookie *cookie) { return inode_to_wb(inode); } -static inline void unlocked_inode_to_wb_end(struct inode *inode, bool locked) +static inline void unlocked_inode_to_wb_end(struct inode *inode, + struct wb_lock_cookie *cookie) { } diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 5c1a3279e63f..337c6afb3345 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -2502,13 +2502,13 @@ void account_page_redirty(struct page *page) if (mapping && mapping_cap_account_dirty(mapping)) { struct inode *inode = mapping->host; struct bdi_writeback *wb; - bool locked; + struct wb_lock_cookie cookie = {}; - wb = unlocked_inode_to_wb_begin(inode, &locked); + wb = unlocked_inode_to_wb_begin(inode, &cookie); current->nr_dirtied--; dec_node_page_state(page, NR_DIRTIED); dec_wb_stat(wb, WB_DIRTIED); - unlocked_inode_to_wb_end(inode, locked); + unlocked_inode_to_wb_end(inode, &cookie); } } EXPORT_SYMBOL(account_page_redirty); @@ -2614,15 +2614,15 @@ void __cancel_dirty_page(struct page *page) if (mapping_cap_account_dirty(mapping)) { struct inode *inode = mapping->host; struct bdi_writeback *wb; - bool locked; + struct wb_lock_cookie cookie = {}; lock_page_memcg(page); - wb = unlocked_inode_to_wb_begin(inode, &locked); + wb = unlocked_inode_to_wb_begin(inode, &cookie); if (TestClearPageDirty(page)) account_page_cleaned(page, mapping, wb); - unlocked_inode_to_wb_end(inode, locked); + unlocked_inode_to_wb_end(inode, &cookie); unlock_page_memcg(page); } else { ClearPageDirty(page); @@ -2654,7 +2654,7 @@ int clear_page_dirty_for_io(struct page *page) if (mapping && mapping_cap_account_dirty(mapping)) { struct inode *inode = mapping->host; struct bdi_writeback *wb; - bool locked; + struct wb_lock_cookie cookie = {}; /* * Yes, Virginia, this is indeed insane. @@ -2691,14 +2691,14 @@ int clear_page_dirty_for_io(struct page *page) * always locked coming in here, so we get the desired * exclusion. */ - wb = unlocked_inode_to_wb_begin(inode, &locked); + wb = unlocked_inode_to_wb_begin(inode, &cookie); if (TestClearPageDirty(page)) { dec_lruvec_page_state(page, NR_FILE_DIRTY); dec_zone_page_state(page, NR_ZONE_WRITE_PENDING); dec_wb_stat(wb, WB_RECLAIMABLE); ret = 1; } - unlocked_inode_to_wb_end(inode, locked); + unlocked_inode_to_wb_end(inode, &cookie); return ret; } return TestClearPageDirty(page);

7 years, 2 months

1
0
0 0

FAILED: patch "[PATCH] writeback: safer lock nesting" failed to apply to 4.14-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.14-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 2e898e4c0a3897ccd434adac5abb8330194f527b Mon Sep 17 00:00:00 2001 From: Greg Thelen <gthelen(a)google.com> Date: Fri, 20 Apr 2018 14:55:42 -0700 Subject: [PATCH] writeback: safer lock nesting lock_page_memcg()/unlock_page_memcg() use spin_lock_irqsave/restore() if the page's memcg is undergoing move accounting, which occurs when a process leaves its memcg for a new one that has memory.move_charge_at_immigrate set. unlocked_inode_to_wb_begin,end() use spin_lock_irq/spin_unlock_irq() if the given inode is switching writeback domains. Switches occur when enough writes are issued from a new domain. This existing pattern is thus suspicious: lock_page_memcg(page); unlocked_inode_to_wb_begin(inode, &locked); ... unlocked_inode_to_wb_end(inode, locked); unlock_page_memcg(page); If both inode switch and process memcg migration are both in-flight then unlocked_inode_to_wb_end() will unconditionally enable interrupts while still holding the lock_page_memcg() irq spinlock. This suggests the possibility of deadlock if an interrupt occurs before unlock_page_memcg(). truncate __cancel_dirty_page lock_page_memcg unlocked_inode_to_wb_begin unlocked_inode_to_wb_end <interrupts mistakenly enabled> <interrupt> end_page_writeback test_clear_page_writeback lock_page_memcg <deadlock> unlock_page_memcg Due to configuration limitations this deadlock is not currently possible because we don't mix cgroup writeback (a cgroupv2 feature) and memory.move_charge_at_immigrate (a cgroupv1 feature). If the kernel is hacked to always claim inode switching and memcg moving_account, then this script triggers lockup in less than a minute: cd /mnt/cgroup/memory mkdir a b echo 1 > a/memory.move_charge_at_immigrate echo 1 > b/memory.move_charge_at_immigrate ( echo $BASHPID > a/cgroup.procs while true; do dd if=/dev/zero of=/mnt/big bs=1M count=256 done ) & while true; do sync done & sleep 1h & SLEEP=$! while true; do echo $SLEEP > a/cgroup.procs echo $SLEEP > b/cgroup.procs done The deadlock does not seem possible, so it's debatable if there's any reason to modify the kernel. I suggest we should to prevent future surprises. And Wang Long said "this deadlock occurs three times in our environment", so there's more reason to apply this, even to stable. Stable 4.4 has minor conflicts applying this patch. For a clean 4.4 patch see "[PATCH for-4.4] writeback: safer lock nesting" https://lkml.org/lkml/2018/4/11/146 Wang Long said "this deadlock occurs three times in our environment" [gthelen(a)google.com: v4] Link: http://lkml.kernel.org/r/20180411084653.254724-1-gthelen@google.com [akpm(a)linux-foundation.org: comment tweaks, struct initialization simplification] Change-Id: Ibb773e8045852978f6207074491d262f1b3fb613 Link: http://lkml.kernel.org/r/20180410005908.167976-1-gthelen@google.com Fixes: 682aa8e1a6a1 ("writeback: implement unlocked_inode_to_wb transaction and use it for stat updates") Signed-off-by: Greg Thelen <gthelen(a)google.com> Reported-by: Wang Long <wanglong19(a)meituan.com> Acked-by: Wang Long <wanglong19(a)meituan.com> Acked-by: Michal Hocko <mhocko(a)suse.com> Reviewed-by: Andrew Morton <akpm(a)linux-foundation.org> Cc: Johannes Weiner <hannes(a)cmpxchg.org> Cc: Tejun Heo <tj(a)kernel.org> Cc: Nicholas Piggin <npiggin(a)gmail.com> Cc: <stable(a)vger.kernel.org> [v4.2+] Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 4b12ba70a895..47d7c151fcba 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -745,11 +745,12 @@ int inode_congested(struct inode *inode, int cong_bits) */ if (inode && inode_to_wb_is_valid(inode)) { struct bdi_writeback *wb; - bool locked, congested; + struct wb_lock_cookie lock_cookie = {}; + bool congested; - wb = unlocked_inode_to_wb_begin(inode, &locked); + wb = unlocked_inode_to_wb_begin(inode, &lock_cookie); congested = wb_congested(wb, cong_bits); - unlocked_inode_to_wb_end(inode, locked); + unlocked_inode_to_wb_end(inode, &lock_cookie); return congested; } diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h index bfe86b54f6c1..0bd432a4d7bd 100644 --- a/include/linux/backing-dev-defs.h +++ b/include/linux/backing-dev-defs.h @@ -223,6 +223,11 @@ static inline void set_bdi_congested(struct backing_dev_info *bdi, int sync) set_wb_congested(bdi->wb.congested, sync); } +struct wb_lock_cookie { + bool locked; + unsigned long flags; +}; + #ifdef CONFIG_CGROUP_WRITEBACK /** diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index f6be4b0b6c18..72ca0f3d39f3 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -347,7 +347,7 @@ static inline struct bdi_writeback *inode_to_wb(const struct inode *inode) /** * unlocked_inode_to_wb_begin - begin unlocked inode wb access transaction * @inode: target inode - * @lockedp: temp bool output param, to be passed to the end function + * @cookie: output param, to be passed to the end function * * The caller wants to access the wb associated with @inode but isn't * holding inode->i_lock, the i_pages lock or wb->list_lock. This @@ -355,12 +355,12 @@ static inline struct bdi_writeback *inode_to_wb(const struct inode *inode) * association doesn't change until the transaction is finished with * unlocked_inode_to_wb_end(). * - * The caller must call unlocked_inode_to_wb_end() with *@lockdep - * afterwards and can't sleep during transaction. IRQ may or may not be - * disabled on return. + * The caller must call unlocked_inode_to_wb_end() with *@cookie afterwards and + * can't sleep during the transaction. IRQs may or may not be disabled on + * return. */ static inline struct bdi_writeback * -unlocked_inode_to_wb_begin(struct inode *inode, bool *lockedp) +unlocked_inode_to_wb_begin(struct inode *inode, struct wb_lock_cookie *cookie) { rcu_read_lock(); @@ -368,10 +368,10 @@ unlocked_inode_to_wb_begin(struct inode *inode, bool *lockedp) * Paired with store_release in inode_switch_wb_work_fn() and * ensures that we see the new wb if we see cleared I_WB_SWITCH. */ - *lockedp = smp_load_acquire(&inode->i_state) & I_WB_SWITCH; + cookie->locked = smp_load_acquire(&inode->i_state) & I_WB_SWITCH; - if (unlikely(*lockedp)) - xa_lock_irq(&inode->i_mapping->i_pages); + if (unlikely(cookie->locked)) + xa_lock_irqsave(&inode->i_mapping->i_pages, cookie->flags); /* * Protected by either !I_WB_SWITCH + rcu_read_lock() or the i_pages @@ -383,12 +383,13 @@ unlocked_inode_to_wb_begin(struct inode *inode, bool *lockedp) /** * unlocked_inode_to_wb_end - end inode wb access transaction * @inode: target inode - * @locked: *@lockedp from unlocked_inode_to_wb_begin() + * @cookie: @cookie from unlocked_inode_to_wb_begin() */ -static inline void unlocked_inode_to_wb_end(struct inode *inode, bool locked) +static inline void unlocked_inode_to_wb_end(struct inode *inode, + struct wb_lock_cookie *cookie) { - if (unlikely(locked)) - xa_unlock_irq(&inode->i_mapping->i_pages); + if (unlikely(cookie->locked)) + xa_unlock_irqrestore(&inode->i_mapping->i_pages, cookie->flags); rcu_read_unlock(); } @@ -435,12 +436,13 @@ static inline struct bdi_writeback *inode_to_wb(struct inode *inode) } static inline struct bdi_writeback * -unlocked_inode_to_wb_begin(struct inode *inode, bool *lockedp) +unlocked_inode_to_wb_begin(struct inode *inode, struct wb_lock_cookie *cookie) { return inode_to_wb(inode); } -static inline void unlocked_inode_to_wb_end(struct inode *inode, bool locked) +static inline void unlocked_inode_to_wb_end(struct inode *inode, + struct wb_lock_cookie *cookie) { } diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 5c1a3279e63f..337c6afb3345 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -2502,13 +2502,13 @@ void account_page_redirty(struct page *page) if (mapping && mapping_cap_account_dirty(mapping)) { struct inode *inode = mapping->host; struct bdi_writeback *wb; - bool locked; + struct wb_lock_cookie cookie = {}; - wb = unlocked_inode_to_wb_begin(inode, &locked); + wb = unlocked_inode_to_wb_begin(inode, &cookie); current->nr_dirtied--; dec_node_page_state(page, NR_DIRTIED); dec_wb_stat(wb, WB_DIRTIED); - unlocked_inode_to_wb_end(inode, locked); + unlocked_inode_to_wb_end(inode, &cookie); } } EXPORT_SYMBOL(account_page_redirty); @@ -2614,15 +2614,15 @@ void __cancel_dirty_page(struct page *page) if (mapping_cap_account_dirty(mapping)) { struct inode *inode = mapping->host; struct bdi_writeback *wb; - bool locked; + struct wb_lock_cookie cookie = {}; lock_page_memcg(page); - wb = unlocked_inode_to_wb_begin(inode, &locked); + wb = unlocked_inode_to_wb_begin(inode, &cookie); if (TestClearPageDirty(page)) account_page_cleaned(page, mapping, wb); - unlocked_inode_to_wb_end(inode, locked); + unlocked_inode_to_wb_end(inode, &cookie); unlock_page_memcg(page); } else { ClearPageDirty(page); @@ -2654,7 +2654,7 @@ int clear_page_dirty_for_io(struct page *page) if (mapping && mapping_cap_account_dirty(mapping)) { struct inode *inode = mapping->host; struct bdi_writeback *wb; - bool locked; + struct wb_lock_cookie cookie = {}; /* * Yes, Virginia, this is indeed insane. @@ -2691,14 +2691,14 @@ int clear_page_dirty_for_io(struct page *page) * always locked coming in here, so we get the desired * exclusion. */ - wb = unlocked_inode_to_wb_begin(inode, &locked); + wb = unlocked_inode_to_wb_begin(inode, &cookie); if (TestClearPageDirty(page)) { dec_lruvec_page_state(page, NR_FILE_DIRTY); dec_zone_page_state(page, NR_ZONE_WRITE_PENDING); dec_wb_stat(wb, WB_RECLAIMABLE); ret = 1; } - unlocked_inode_to_wb_end(inode, locked); + unlocked_inode_to_wb_end(inode, &cookie); return ret; } return TestClearPageDirty(page);

7 years, 2 months

1
0
0 0

FAILED: patch "[PATCH] writeback: safer lock nesting" failed to apply to 4.16-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.16-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 2e898e4c0a3897ccd434adac5abb8330194f527b Mon Sep 17 00:00:00 2001 From: Greg Thelen <gthelen(a)google.com> Date: Fri, 20 Apr 2018 14:55:42 -0700 Subject: [PATCH] writeback: safer lock nesting lock_page_memcg()/unlock_page_memcg() use spin_lock_irqsave/restore() if the page's memcg is undergoing move accounting, which occurs when a process leaves its memcg for a new one that has memory.move_charge_at_immigrate set. unlocked_inode_to_wb_begin,end() use spin_lock_irq/spin_unlock_irq() if the given inode is switching writeback domains. Switches occur when enough writes are issued from a new domain. This existing pattern is thus suspicious: lock_page_memcg(page); unlocked_inode_to_wb_begin(inode, &locked); ... unlocked_inode_to_wb_end(inode, locked); unlock_page_memcg(page); If both inode switch and process memcg migration are both in-flight then unlocked_inode_to_wb_end() will unconditionally enable interrupts while still holding the lock_page_memcg() irq spinlock. This suggests the possibility of deadlock if an interrupt occurs before unlock_page_memcg(). truncate __cancel_dirty_page lock_page_memcg unlocked_inode_to_wb_begin unlocked_inode_to_wb_end <interrupts mistakenly enabled> <interrupt> end_page_writeback test_clear_page_writeback lock_page_memcg <deadlock> unlock_page_memcg Due to configuration limitations this deadlock is not currently possible because we don't mix cgroup writeback (a cgroupv2 feature) and memory.move_charge_at_immigrate (a cgroupv1 feature). If the kernel is hacked to always claim inode switching and memcg moving_account, then this script triggers lockup in less than a minute: cd /mnt/cgroup/memory mkdir a b echo 1 > a/memory.move_charge_at_immigrate echo 1 > b/memory.move_charge_at_immigrate ( echo $BASHPID > a/cgroup.procs while true; do dd if=/dev/zero of=/mnt/big bs=1M count=256 done ) & while true; do sync done & sleep 1h & SLEEP=$! while true; do echo $SLEEP > a/cgroup.procs echo $SLEEP > b/cgroup.procs done The deadlock does not seem possible, so it's debatable if there's any reason to modify the kernel. I suggest we should to prevent future surprises. And Wang Long said "this deadlock occurs three times in our environment", so there's more reason to apply this, even to stable. Stable 4.4 has minor conflicts applying this patch. For a clean 4.4 patch see "[PATCH for-4.4] writeback: safer lock nesting" https://lkml.org/lkml/2018/4/11/146 Wang Long said "this deadlock occurs three times in our environment" [gthelen(a)google.com: v4] Link: http://lkml.kernel.org/r/20180411084653.254724-1-gthelen@google.com [akpm(a)linux-foundation.org: comment tweaks, struct initialization simplification] Change-Id: Ibb773e8045852978f6207074491d262f1b3fb613 Link: http://lkml.kernel.org/r/20180410005908.167976-1-gthelen@google.com Fixes: 682aa8e1a6a1 ("writeback: implement unlocked_inode_to_wb transaction and use it for stat updates") Signed-off-by: Greg Thelen <gthelen(a)google.com> Reported-by: Wang Long <wanglong19(a)meituan.com> Acked-by: Wang Long <wanglong19(a)meituan.com> Acked-by: Michal Hocko <mhocko(a)suse.com> Reviewed-by: Andrew Morton <akpm(a)linux-foundation.org> Cc: Johannes Weiner <hannes(a)cmpxchg.org> Cc: Tejun Heo <tj(a)kernel.org> Cc: Nicholas Piggin <npiggin(a)gmail.com> Cc: <stable(a)vger.kernel.org> [v4.2+] Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 4b12ba70a895..47d7c151fcba 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -745,11 +745,12 @@ int inode_congested(struct inode *inode, int cong_bits) */ if (inode && inode_to_wb_is_valid(inode)) { struct bdi_writeback *wb; - bool locked, congested; + struct wb_lock_cookie lock_cookie = {}; + bool congested; - wb = unlocked_inode_to_wb_begin(inode, &locked); + wb = unlocked_inode_to_wb_begin(inode, &lock_cookie); congested = wb_congested(wb, cong_bits); - unlocked_inode_to_wb_end(inode, locked); + unlocked_inode_to_wb_end(inode, &lock_cookie); return congested; } diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h index bfe86b54f6c1..0bd432a4d7bd 100644 --- a/include/linux/backing-dev-defs.h +++ b/include/linux/backing-dev-defs.h @@ -223,6 +223,11 @@ static inline void set_bdi_congested(struct backing_dev_info *bdi, int sync) set_wb_congested(bdi->wb.congested, sync); } +struct wb_lock_cookie { + bool locked; + unsigned long flags; +}; + #ifdef CONFIG_CGROUP_WRITEBACK /** diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index f6be4b0b6c18..72ca0f3d39f3 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -347,7 +347,7 @@ static inline struct bdi_writeback *inode_to_wb(const struct inode *inode) /** * unlocked_inode_to_wb_begin - begin unlocked inode wb access transaction * @inode: target inode - * @lockedp: temp bool output param, to be passed to the end function + * @cookie: output param, to be passed to the end function * * The caller wants to access the wb associated with @inode but isn't * holding inode->i_lock, the i_pages lock or wb->list_lock. This @@ -355,12 +355,12 @@ static inline struct bdi_writeback *inode_to_wb(const struct inode *inode) * association doesn't change until the transaction is finished with * unlocked_inode_to_wb_end(). * - * The caller must call unlocked_inode_to_wb_end() with *@lockdep - * afterwards and can't sleep during transaction. IRQ may or may not be - * disabled on return. + * The caller must call unlocked_inode_to_wb_end() with *@cookie afterwards and + * can't sleep during the transaction. IRQs may or may not be disabled on + * return. */ static inline struct bdi_writeback * -unlocked_inode_to_wb_begin(struct inode *inode, bool *lockedp) +unlocked_inode_to_wb_begin(struct inode *inode, struct wb_lock_cookie *cookie) { rcu_read_lock(); @@ -368,10 +368,10 @@ unlocked_inode_to_wb_begin(struct inode *inode, bool *lockedp) * Paired with store_release in inode_switch_wb_work_fn() and * ensures that we see the new wb if we see cleared I_WB_SWITCH. */ - *lockedp = smp_load_acquire(&inode->i_state) & I_WB_SWITCH; + cookie->locked = smp_load_acquire(&inode->i_state) & I_WB_SWITCH; - if (unlikely(*lockedp)) - xa_lock_irq(&inode->i_mapping->i_pages); + if (unlikely(cookie->locked)) + xa_lock_irqsave(&inode->i_mapping->i_pages, cookie->flags); /* * Protected by either !I_WB_SWITCH + rcu_read_lock() or the i_pages @@ -383,12 +383,13 @@ unlocked_inode_to_wb_begin(struct inode *inode, bool *lockedp) /** * unlocked_inode_to_wb_end - end inode wb access transaction * @inode: target inode - * @locked: *@lockedp from unlocked_inode_to_wb_begin() + * @cookie: @cookie from unlocked_inode_to_wb_begin() */ -static inline void unlocked_inode_to_wb_end(struct inode *inode, bool locked) +static inline void unlocked_inode_to_wb_end(struct inode *inode, + struct wb_lock_cookie *cookie) { - if (unlikely(locked)) - xa_unlock_irq(&inode->i_mapping->i_pages); + if (unlikely(cookie->locked)) + xa_unlock_irqrestore(&inode->i_mapping->i_pages, cookie->flags); rcu_read_unlock(); } @@ -435,12 +436,13 @@ static inline struct bdi_writeback *inode_to_wb(struct inode *inode) } static inline struct bdi_writeback * -unlocked_inode_to_wb_begin(struct inode *inode, bool *lockedp) +unlocked_inode_to_wb_begin(struct inode *inode, struct wb_lock_cookie *cookie) { return inode_to_wb(inode); } -static inline void unlocked_inode_to_wb_end(struct inode *inode, bool locked) +static inline void unlocked_inode_to_wb_end(struct inode *inode, + struct wb_lock_cookie *cookie) { } diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 5c1a3279e63f..337c6afb3345 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -2502,13 +2502,13 @@ void account_page_redirty(struct page *page) if (mapping && mapping_cap_account_dirty(mapping)) { struct inode *inode = mapping->host; struct bdi_writeback *wb; - bool locked; + struct wb_lock_cookie cookie = {}; - wb = unlocked_inode_to_wb_begin(inode, &locked); + wb = unlocked_inode_to_wb_begin(inode, &cookie); current->nr_dirtied--; dec_node_page_state(page, NR_DIRTIED); dec_wb_stat(wb, WB_DIRTIED); - unlocked_inode_to_wb_end(inode, locked); + unlocked_inode_to_wb_end(inode, &cookie); } } EXPORT_SYMBOL(account_page_redirty); @@ -2614,15 +2614,15 @@ void __cancel_dirty_page(struct page *page) if (mapping_cap_account_dirty(mapping)) { struct inode *inode = mapping->host; struct bdi_writeback *wb; - bool locked; + struct wb_lock_cookie cookie = {}; lock_page_memcg(page); - wb = unlocked_inode_to_wb_begin(inode, &locked); + wb = unlocked_inode_to_wb_begin(inode, &cookie); if (TestClearPageDirty(page)) account_page_cleaned(page, mapping, wb); - unlocked_inode_to_wb_end(inode, locked); + unlocked_inode_to_wb_end(inode, &cookie); unlock_page_memcg(page); } else { ClearPageDirty(page); @@ -2654,7 +2654,7 @@ int clear_page_dirty_for_io(struct page *page) if (mapping && mapping_cap_account_dirty(mapping)) { struct inode *inode = mapping->host; struct bdi_writeback *wb; - bool locked; + struct wb_lock_cookie cookie = {}; /* * Yes, Virginia, this is indeed insane. @@ -2691,14 +2691,14 @@ int clear_page_dirty_for_io(struct page *page) * always locked coming in here, so we get the desired * exclusion. */ - wb = unlocked_inode_to_wb_begin(inode, &locked); + wb = unlocked_inode_to_wb_begin(inode, &cookie); if (TestClearPageDirty(page)) { dec_lruvec_page_state(page, NR_FILE_DIRTY); dec_zone_page_state(page, NR_ZONE_WRITE_PENDING); dec_wb_stat(wb, WB_RECLAIMABLE); ret = 1; } - unlocked_inode_to_wb_end(inode, locked); + unlocked_inode_to_wb_end(inode, &cookie); return ret; } return TestClearPageDirty(page);

7 years, 2 months

1
0
0 0

FAILED: patch "[PATCH] mm/filemap.c: fix NULL pointer in page_cache_tree_insert()" failed to apply to 3.18-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 3.18-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From abc1be13fd113ddef5e2d807a466286b864caed3 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox <mawilcox(a)microsoft.com> Date: Fri, 20 Apr 2018 14:56:20 -0700 Subject: [PATCH] mm/filemap.c: fix NULL pointer in page_cache_tree_insert() f2fs specifies the __GFP_ZERO flag for allocating some of its pages. Unfortunately, the page cache also uses the mapping's GFP flags for allocating radix tree nodes. It always masked off the __GFP_HIGHMEM flag, and masks off __GFP_ZERO in some paths, but not all. That causes radix tree nodes to be allocated with a NULL list_head, which causes backtraces like: __list_del_entry+0x30/0xd0 list_lru_del+0xac/0x1ac page_cache_tree_insert+0xd8/0x110 The __GFP_DMA and __GFP_DMA32 flags would also be able to sneak through if they are ever used. Fix them all by using GFP_RECLAIM_MASK at the innermost location, and remove it from earlier in the callchain. Link: http://lkml.kernel.org/r/20180411060320.14458-2-willy@infradead.org Fixes: 449dd6984d0e ("mm: keep page cache radix tree nodes in check") Signed-off-by: Matthew Wilcox <mawilcox(a)microsoft.com> Reported-by: Chris Fries <cfries(a)google.com> Debugged-by: Minchan Kim <minchan(a)kernel.org> Acked-by: Johannes Weiner <hannes(a)cmpxchg.org> Acked-by: Michal Hocko <mhocko(a)suse.com> Reviewed-by: Jan Kara <jack(a)suse.cz> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> diff --git a/mm/filemap.c b/mm/filemap.c index 9276bdb2343c..0604cb02e6f3 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -786,7 +786,7 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask) VM_BUG_ON_PAGE(!PageLocked(new), new); VM_BUG_ON_PAGE(new->mapping, new); - error = radix_tree_preload(gfp_mask & ~__GFP_HIGHMEM); + error = radix_tree_preload(gfp_mask & GFP_RECLAIM_MASK); if (!error) { struct address_space *mapping = old->mapping; void (*freepage)(struct page *); @@ -842,7 +842,7 @@ static int __add_to_page_cache_locked(struct page *page, return error; } - error = radix_tree_maybe_preload(gfp_mask & ~__GFP_HIGHMEM); + error = radix_tree_maybe_preload(gfp_mask & GFP_RECLAIM_MASK); if (error) { if (!huge) mem_cgroup_cancel_charge(page, memcg, false); @@ -1585,8 +1585,7 @@ struct page *pagecache_get_page(struct address_space *mapping, pgoff_t offset, if (fgp_flags & FGP_ACCESSED) __SetPageReferenced(page); - err = add_to_page_cache_lru(page, mapping, offset, - gfp_mask & GFP_RECLAIM_MASK); + err = add_to_page_cache_lru(page, mapping, offset, gfp_mask); if (unlikely(err)) { put_page(page); page = NULL; @@ -2387,7 +2386,7 @@ static int page_cache_read(struct file *file, pgoff_t offset, gfp_t gfp_mask) if (!page) return -ENOMEM; - ret = add_to_page_cache_lru(page, mapping, offset, gfp_mask & GFP_KERNEL); + ret = add_to_page_cache_lru(page, mapping, offset, gfp_mask); if (ret == 0) ret = mapping->a_ops->readpage(file, page); else if (ret == -EEXIST)

7 years, 2 months

1
0
0 0

FAILED: patch "[PATCH] rapidio: fix rio_dma_transfer error handling" failed to apply to 4.14-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.14-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From c5157b76869ba98c3a99a1982396437464e131a6 Mon Sep 17 00:00:00 2001 From: Ioan Nicu <ioan.nicu.ext(a)nokia.com> Date: Fri, 20 Apr 2018 14:55:49 -0700 Subject: [PATCH] rapidio: fix rio_dma_transfer error handling Some of the mport_dma_req structure members were initialized late inside the do_dma_request() function, just before submitting the request to the dma engine. But we have some error branches before that. In case of such an error, the code would return on the error path and trigger the calling of dma_req_free() with a req structure which is not completely initialized. This causes a NULL pointer dereference in dma_req_free(). This patch fixes these error branches by making sure that all necessary mport_dma_req structure members are initialized in rio_dma_transfer() immediately after the request structure gets allocated. Link: http://lkml.kernel.org/r/20180412150605.GA31409@nokia.com Fixes: bbd876adb8c72 ("rapidio: use a reference count for struct mport_dma_req") Signed-off-by: Ioan Nicu <ioan.nicu.ext(a)nokia.com> Tested-by: Alexander Sverdlin <alexander.sverdlin(a)nokia.com> Acked-by: Alexandre Bounine <alex.bou9(a)gmail.com> Cc: Barry Wood <barry.wood(a)idt.com> Cc: Matt Porter <mporter(a)kernel.crashing.org> Cc: Christophe JAILLET <christophe.jaillet(a)wanadoo.fr> Cc: Logan Gunthorpe <logang(a)deltatee.com> Cc: Chris Wilson <chris(a)chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin(a)intel.com> Cc: Frank Kunz <frank.kunz(a)nokia.com> Cc: <stable(a)vger.kernel.org> [4.6+] Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> diff --git a/drivers/rapidio/devices/rio_mport_cdev.c b/drivers/rapidio/devices/rio_mport_cdev.c index 9d27016c899e..0434ab7b6497 100644 --- a/drivers/rapidio/devices/rio_mport_cdev.c +++ b/drivers/rapidio/devices/rio_mport_cdev.c @@ -740,10 +740,7 @@ static int do_dma_request(struct mport_dma_req *req, tx->callback = dma_xfer_callback; tx->callback_param = req; - req->dmach = chan; - req->sync = sync; req->status = DMA_IN_PROGRESS; - init_completion(&req->req_comp); kref_get(&req->refcount); cookie = dmaengine_submit(tx); @@ -831,13 +828,20 @@ rio_dma_transfer(struct file *filp, u32 transfer_mode, if (!req) return -ENOMEM; - kref_init(&req->refcount); - ret = get_dma_channel(priv); if (ret) { kfree(req); return ret; } + chan = priv->dmach; + + kref_init(&req->refcount); + init_completion(&req->req_comp); + req->dir = dir; + req->filp = filp; + req->priv = priv; + req->dmach = chan; + req->sync = sync; /* * If parameter loc_addr != NULL, we are transferring data from/to @@ -925,11 +929,6 @@ rio_dma_transfer(struct file *filp, u32 transfer_mode, xfer->offset, xfer->length); } - req->dir = dir; - req->filp = filp; - req->priv = priv; - chan = priv->dmach; - nents = dma_map_sg(chan->device->dev, req->sgt.sgl, req->sgt.nents, dir); if (nents == 0) {

7 years, 2 months

1
0
0 0

FAILED: patch "[PATCH] rapidio: fix rio_dma_transfer error handling" failed to apply to 4.16-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.16-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From c5157b76869ba98c3a99a1982396437464e131a6 Mon Sep 17 00:00:00 2001 From: Ioan Nicu <ioan.nicu.ext(a)nokia.com> Date: Fri, 20 Apr 2018 14:55:49 -0700 Subject: [PATCH] rapidio: fix rio_dma_transfer error handling Some of the mport_dma_req structure members were initialized late inside the do_dma_request() function, just before submitting the request to the dma engine. But we have some error branches before that. In case of such an error, the code would return on the error path and trigger the calling of dma_req_free() with a req structure which is not completely initialized. This causes a NULL pointer dereference in dma_req_free(). This patch fixes these error branches by making sure that all necessary mport_dma_req structure members are initialized in rio_dma_transfer() immediately after the request structure gets allocated. Link: http://lkml.kernel.org/r/20180412150605.GA31409@nokia.com Fixes: bbd876adb8c72 ("rapidio: use a reference count for struct mport_dma_req") Signed-off-by: Ioan Nicu <ioan.nicu.ext(a)nokia.com> Tested-by: Alexander Sverdlin <alexander.sverdlin(a)nokia.com> Acked-by: Alexandre Bounine <alex.bou9(a)gmail.com> Cc: Barry Wood <barry.wood(a)idt.com> Cc: Matt Porter <mporter(a)kernel.crashing.org> Cc: Christophe JAILLET <christophe.jaillet(a)wanadoo.fr> Cc: Logan Gunthorpe <logang(a)deltatee.com> Cc: Chris Wilson <chris(a)chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin(a)intel.com> Cc: Frank Kunz <frank.kunz(a)nokia.com> Cc: <stable(a)vger.kernel.org> [4.6+] Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> diff --git a/drivers/rapidio/devices/rio_mport_cdev.c b/drivers/rapidio/devices/rio_mport_cdev.c index 9d27016c899e..0434ab7b6497 100644 --- a/drivers/rapidio/devices/rio_mport_cdev.c +++ b/drivers/rapidio/devices/rio_mport_cdev.c @@ -740,10 +740,7 @@ static int do_dma_request(struct mport_dma_req *req, tx->callback = dma_xfer_callback; tx->callback_param = req; - req->dmach = chan; - req->sync = sync; req->status = DMA_IN_PROGRESS; - init_completion(&req->req_comp); kref_get(&req->refcount); cookie = dmaengine_submit(tx); @@ -831,13 +828,20 @@ rio_dma_transfer(struct file *filp, u32 transfer_mode, if (!req) return -ENOMEM; - kref_init(&req->refcount); - ret = get_dma_channel(priv); if (ret) { kfree(req); return ret; } + chan = priv->dmach; + + kref_init(&req->refcount); + init_completion(&req->req_comp); + req->dir = dir; + req->filp = filp; + req->priv = priv; + req->dmach = chan; + req->sync = sync; /* * If parameter loc_addr != NULL, we are transferring data from/to @@ -925,11 +929,6 @@ rio_dma_transfer(struct file *filp, u32 transfer_mode, xfer->offset, xfer->length); } - req->dir = dir; - req->filp = filp; - req->priv = priv; - chan = priv->dmach; - nents = dma_map_sg(chan->device->dev, req->sgt.sgl, req->sgt.nents, dir); if (nents == 0) {

7 years, 2 months

1
0
0 0

FAILED: patch "[PATCH] drm/i915: Correctly handle limited range YCbCr data on" failed to apply to 4.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.4-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 5deae9191130db6b617c94fb261804597cf9b508 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= <ville.syrjala(a)linux.intel.com> Date: Wed, 14 Feb 2018 21:23:23 +0200 Subject: [PATCH] drm/i915: Correctly handle limited range YCbCr data on VLV/CHV MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Turns out the VLV/CHV fixed function sprite CSC expects full range data as input. We've been feeding it limited range data to it all along. To expand the data out to full range we'll use the color correction registers (brightness, contrast, and saturation). On CHV pipe B we were actually doing the right thing already because we progammed the custom CSC matrix to do expect limited range input. Now that well pre-expand the data out with the color correction unit, we need to change the CSC matrix to operate with full range input instead. This should make the sprite output of the other pipes match the sprite output of pipe B reasonably well. Looking at the resulting pipe CRCs, there can be a slight difference in the output, but as I don't know the formula used by the fixed function CSC of the other pipes, I don't think it's worth the effort to try to match the output exactly. It might not even be possible due to difference in internal precision etc. One slight caveat here is that the color correction registers are single bufferred, so we should really be updating them during vblank, but we still don't have a mechanism for that, so just toss in another FIXME. v2: Rebase v3: s/bri/brightness/ s/con/contrast/ (Shashank) v4: Clarify the constants and math (Shashank) Cc: Harry Wentland <harry.wentland(a)amd.com> Cc: Daniel Vetter <daniel(a)ffwll.ch> Cc: Daniel Stone <daniel(a)fooishbar.org> Cc: Russell King - ARM Linux <linux(a)armlinux.org.uk> Cc: Ilia Mirkin <imirkin(a)alum.mit.edu> Cc: Hans Verkuil <hverkuil(a)xs4all.nl> Cc: Shashank Sharma <shashank.sharma(a)intel.com> Cc: Uma Shankar <uma.shankar(a)intel.com> Cc: Jyri Sarha <jsarha(a)ti.com> Cc: "Tang, Jun" <jun.tang(a)intel.com> Reported-by: "Tang, Jun" <jun.tang(a)intel.com> Cc: stable(a)vger.kernel.org Fixes: 7f1f3851feb0 ("drm/i915: sprite support for ValleyView v4") Reviewed-by: Shashank Sharma <shashank.sharma(a)intel.com> Signed-off-by: Ville Syrjälä <ville.syrjala(a)linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20180214192327.3250-5-ville.s… diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index e9c79b560823..aaed94f074f5 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -6278,6 +6278,12 @@ enum { #define _SPATILEOFF (VLV_DISPLAY_BASE + 0x721a4) #define _SPACONSTALPHA (VLV_DISPLAY_BASE + 0x721a8) #define SP_CONST_ALPHA_ENABLE (1<<31) +#define _SPACLRC0 (VLV_DISPLAY_BASE + 0x721d0) +#define SP_CONTRAST(x) ((x) << 18) /* u3.6 */ +#define SP_BRIGHTNESS(x) ((x) & 0xff) /* s8 */ +#define _SPACLRC1 (VLV_DISPLAY_BASE + 0x721d4) +#define SP_SH_SIN(x) (((x) & 0x7ff) << 16) /* s4.7 */ +#define SP_SH_COS(x) (x) /* u3.7 */ #define _SPAGAMC (VLV_DISPLAY_BASE + 0x721f4) #define _SPBCNTR (VLV_DISPLAY_BASE + 0x72280) @@ -6291,6 +6297,8 @@ enum { #define _SPBKEYMAXVAL (VLV_DISPLAY_BASE + 0x722a0) #define _SPBTILEOFF (VLV_DISPLAY_BASE + 0x722a4) #define _SPBCONSTALPHA (VLV_DISPLAY_BASE + 0x722a8) +#define _SPBCLRC0 (VLV_DISPLAY_BASE + 0x722d0) +#define _SPBCLRC1 (VLV_DISPLAY_BASE + 0x722d4) #define _SPBGAMC (VLV_DISPLAY_BASE + 0x722f4) #define _MMIO_VLV_SPR(pipe, plane_id, reg_a, reg_b) \ @@ -6307,6 +6315,8 @@ enum { #define SPKEYMAXVAL(pipe, plane_id) _MMIO_VLV_SPR((pipe), (plane_id), _SPAKEYMAXVAL, _SPBKEYMAXVAL) #define SPTILEOFF(pipe, plane_id) _MMIO_VLV_SPR((pipe), (plane_id), _SPATILEOFF, _SPBTILEOFF) #define SPCONSTALPHA(pipe, plane_id) _MMIO_VLV_SPR((pipe), (plane_id), _SPACONSTALPHA, _SPBCONSTALPHA) +#define SPCLRC0(pipe, plane_id) _MMIO_VLV_SPR((pipe), (plane_id), _SPACLRC0, _SPBCLRC0) +#define SPCLRC1(pipe, plane_id) _MMIO_VLV_SPR((pipe), (plane_id), _SPACLRC1, _SPBCLRC1) #define SPGAMC(pipe, plane_id) _MMIO_VLV_SPR((pipe), (plane_id), _SPAGAMC, _SPBGAMC) /* diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c index 3be22c0fcfb5..9b7171f20549 100644 --- a/drivers/gpu/drm/i915/intel_sprite.c +++ b/drivers/gpu/drm/i915/intel_sprite.c @@ -346,44 +346,87 @@ skl_plane_get_hw_state(struct intel_plane *plane) } static void -chv_update_csc(struct intel_plane *plane, uint32_t format) +chv_update_csc(const struct intel_plane_state *plane_state) { + struct intel_plane *plane = to_intel_plane(plane_state->base.plane); struct drm_i915_private *dev_priv = to_i915(plane->base.dev); + const struct drm_framebuffer *fb = plane_state->base.fb; enum plane_id plane_id = plane->id; /* Seems RGB data bypasses the CSC always */ - if (!format_is_yuv(format)) + if (!format_is_yuv(fb->format->format)) return; /* - * BT.601 limited range YCbCr -> full range RGB + * BT.601 full range YCbCr -> full range RGB * - * |r| | 6537 4769 0| |cr | - * |g| = |-3330 4769 -1605| x |y-64| - * |b| | 0 4769 8263| |cb | + * |r| | 5743 4096 0| |cr| + * |g| = |-2925 4096 -1410| x |y | + * |b| | 0 4096 7258| |cb| * - * Cb and Cr apparently come in as signed already, so no - * need for any offset. For Y we need to remove the offset. + * Cb and Cr apparently come in as signed already, + * and we get full range data in on account of CLRC0/1 */ - I915_WRITE_FW(SPCSCYGOFF(plane_id), SPCSC_OOFF(0) | SPCSC_IOFF(-64)); + I915_WRITE_FW(SPCSCYGOFF(plane_id), SPCSC_OOFF(0) | SPCSC_IOFF(0)); I915_WRITE_FW(SPCSCCBOFF(plane_id), SPCSC_OOFF(0) | SPCSC_IOFF(0)); I915_WRITE_FW(SPCSCCROFF(plane_id), SPCSC_OOFF(0) | SPCSC_IOFF(0)); - I915_WRITE_FW(SPCSCC01(plane_id), SPCSC_C1(4769) | SPCSC_C0(6537)); - I915_WRITE_FW(SPCSCC23(plane_id), SPCSC_C1(-3330) | SPCSC_C0(0)); - I915_WRITE_FW(SPCSCC45(plane_id), SPCSC_C1(-1605) | SPCSC_C0(4769)); - I915_WRITE_FW(SPCSCC67(plane_id), SPCSC_C1(4769) | SPCSC_C0(0)); - I915_WRITE_FW(SPCSCC8(plane_id), SPCSC_C0(8263)); + I915_WRITE_FW(SPCSCC01(plane_id), SPCSC_C1(4096) | SPCSC_C0(5743)); + I915_WRITE_FW(SPCSCC23(plane_id), SPCSC_C1(-2925) | SPCSC_C0(0)); + I915_WRITE_FW(SPCSCC45(plane_id), SPCSC_C1(-1410) | SPCSC_C0(4096)); + I915_WRITE_FW(SPCSCC67(plane_id), SPCSC_C1(4096) | SPCSC_C0(0)); + I915_WRITE_FW(SPCSCC8(plane_id), SPCSC_C0(7258)); - I915_WRITE_FW(SPCSCYGICLAMP(plane_id), SPCSC_IMAX(940) | SPCSC_IMIN(64)); - I915_WRITE_FW(SPCSCCBICLAMP(plane_id), SPCSC_IMAX(448) | SPCSC_IMIN(-448)); - I915_WRITE_FW(SPCSCCRICLAMP(plane_id), SPCSC_IMAX(448) | SPCSC_IMIN(-448)); + I915_WRITE_FW(SPCSCYGICLAMP(plane_id), SPCSC_IMAX(1023) | SPCSC_IMIN(0)); + I915_WRITE_FW(SPCSCCBICLAMP(plane_id), SPCSC_IMAX(512) | SPCSC_IMIN(-512)); + I915_WRITE_FW(SPCSCCRICLAMP(plane_id), SPCSC_IMAX(512) | SPCSC_IMIN(-512)); I915_WRITE_FW(SPCSCYGOCLAMP(plane_id), SPCSC_OMAX(1023) | SPCSC_OMIN(0)); I915_WRITE_FW(SPCSCCBOCLAMP(plane_id), SPCSC_OMAX(1023) | SPCSC_OMIN(0)); I915_WRITE_FW(SPCSCCROCLAMP(plane_id), SPCSC_OMAX(1023) | SPCSC_OMIN(0)); } +#define SIN_0 0 +#define COS_0 1 + +static void +vlv_update_clrc(const struct intel_plane_state *plane_state) +{ + struct intel_plane *plane = to_intel_plane(plane_state->base.plane); + struct drm_i915_private *dev_priv = to_i915(plane->base.dev); + const struct drm_framebuffer *fb = plane_state->base.fb; + enum pipe pipe = plane->pipe; + enum plane_id plane_id = plane->id; + int contrast, brightness, sh_scale, sh_sin, sh_cos; + + if (format_is_yuv(fb->format->format)) { + /* + * Expand limited range to full range: + * Contrast is applied first and is used to expand Y range. + * Brightness is applied second and is used to remove the + * offset from Y. Saturation/hue is used to expand CbCr range. + */ + contrast = DIV_ROUND_CLOSEST(255 << 6, 235 - 16); + brightness = -DIV_ROUND_CLOSEST(16 * 255, 235 - 16); + sh_scale = DIV_ROUND_CLOSEST(128 << 7, 240 - 128); + sh_sin = SIN_0 * sh_scale; + sh_cos = COS_0 * sh_scale; + } else { + /* Pass-through everything. */ + contrast = 1 << 6; + brightness = 0; + sh_scale = 1 << 7; + sh_sin = SIN_0 * sh_scale; + sh_cos = COS_0 * sh_scale; + } + + /* FIXME these register are single buffered :( */ + I915_WRITE_FW(SPCLRC0(pipe, plane_id), + SP_CONTRAST(contrast) | SP_BRIGHTNESS(brightness)); + I915_WRITE_FW(SPCLRC1(pipe, plane_id), + SP_SH_SIN(sh_sin) | SP_SH_COS(sh_cos)); +} + static u32 vlv_sprite_ctl(const struct intel_crtc_state *crtc_state, const struct intel_plane_state *plane_state) { @@ -477,8 +520,10 @@ vlv_update_plane(struct intel_plane *plane, spin_lock_irqsave(&dev_priv->uncore.lock, irqflags); + vlv_update_clrc(plane_state); + if (IS_CHERRYVIEW(dev_priv) && pipe == PIPE_B) - chv_update_csc(plane, fb->format->format); + chv_update_csc(plane_state); if (key->flags) { I915_WRITE_FW(SPKEYMINVAL(pipe, plane_id), key->min_value);

7 years, 2 months

1
0
0 0

FAILED: patch "[PATCH] drm/i915: Correctly handle limited range YCbCr data on" failed to apply to 4.9-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.9-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 5deae9191130db6b617c94fb261804597cf9b508 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= <ville.syrjala(a)linux.intel.com> Date: Wed, 14 Feb 2018 21:23:23 +0200 Subject: [PATCH] drm/i915: Correctly handle limited range YCbCr data on VLV/CHV MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Turns out the VLV/CHV fixed function sprite CSC expects full range data as input. We've been feeding it limited range data to it all along. To expand the data out to full range we'll use the color correction registers (brightness, contrast, and saturation). On CHV pipe B we were actually doing the right thing already because we progammed the custom CSC matrix to do expect limited range input. Now that well pre-expand the data out with the color correction unit, we need to change the CSC matrix to operate with full range input instead. This should make the sprite output of the other pipes match the sprite output of pipe B reasonably well. Looking at the resulting pipe CRCs, there can be a slight difference in the output, but as I don't know the formula used by the fixed function CSC of the other pipes, I don't think it's worth the effort to try to match the output exactly. It might not even be possible due to difference in internal precision etc. One slight caveat here is that the color correction registers are single bufferred, so we should really be updating them during vblank, but we still don't have a mechanism for that, so just toss in another FIXME. v2: Rebase v3: s/bri/brightness/ s/con/contrast/ (Shashank) v4: Clarify the constants and math (Shashank) Cc: Harry Wentland <harry.wentland(a)amd.com> Cc: Daniel Vetter <daniel(a)ffwll.ch> Cc: Daniel Stone <daniel(a)fooishbar.org> Cc: Russell King - ARM Linux <linux(a)armlinux.org.uk> Cc: Ilia Mirkin <imirkin(a)alum.mit.edu> Cc: Hans Verkuil <hverkuil(a)xs4all.nl> Cc: Shashank Sharma <shashank.sharma(a)intel.com> Cc: Uma Shankar <uma.shankar(a)intel.com> Cc: Jyri Sarha <jsarha(a)ti.com> Cc: "Tang, Jun" <jun.tang(a)intel.com> Reported-by: "Tang, Jun" <jun.tang(a)intel.com> Cc: stable(a)vger.kernel.org Fixes: 7f1f3851feb0 ("drm/i915: sprite support for ValleyView v4") Reviewed-by: Shashank Sharma <shashank.sharma(a)intel.com> Signed-off-by: Ville Syrjälä <ville.syrjala(a)linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20180214192327.3250-5-ville.s… diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index e9c79b560823..aaed94f074f5 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -6278,6 +6278,12 @@ enum { #define _SPATILEOFF (VLV_DISPLAY_BASE + 0x721a4) #define _SPACONSTALPHA (VLV_DISPLAY_BASE + 0x721a8) #define SP_CONST_ALPHA_ENABLE (1<<31) +#define _SPACLRC0 (VLV_DISPLAY_BASE + 0x721d0) +#define SP_CONTRAST(x) ((x) << 18) /* u3.6 */ +#define SP_BRIGHTNESS(x) ((x) & 0xff) /* s8 */ +#define _SPACLRC1 (VLV_DISPLAY_BASE + 0x721d4) +#define SP_SH_SIN(x) (((x) & 0x7ff) << 16) /* s4.7 */ +#define SP_SH_COS(x) (x) /* u3.7 */ #define _SPAGAMC (VLV_DISPLAY_BASE + 0x721f4) #define _SPBCNTR (VLV_DISPLAY_BASE + 0x72280) @@ -6291,6 +6297,8 @@ enum { #define _SPBKEYMAXVAL (VLV_DISPLAY_BASE + 0x722a0) #define _SPBTILEOFF (VLV_DISPLAY_BASE + 0x722a4) #define _SPBCONSTALPHA (VLV_DISPLAY_BASE + 0x722a8) +#define _SPBCLRC0 (VLV_DISPLAY_BASE + 0x722d0) +#define _SPBCLRC1 (VLV_DISPLAY_BASE + 0x722d4) #define _SPBGAMC (VLV_DISPLAY_BASE + 0x722f4) #define _MMIO_VLV_SPR(pipe, plane_id, reg_a, reg_b) \ @@ -6307,6 +6315,8 @@ enum { #define SPKEYMAXVAL(pipe, plane_id) _MMIO_VLV_SPR((pipe), (plane_id), _SPAKEYMAXVAL, _SPBKEYMAXVAL) #define SPTILEOFF(pipe, plane_id) _MMIO_VLV_SPR((pipe), (plane_id), _SPATILEOFF, _SPBTILEOFF) #define SPCONSTALPHA(pipe, plane_id) _MMIO_VLV_SPR((pipe), (plane_id), _SPACONSTALPHA, _SPBCONSTALPHA) +#define SPCLRC0(pipe, plane_id) _MMIO_VLV_SPR((pipe), (plane_id), _SPACLRC0, _SPBCLRC0) +#define SPCLRC1(pipe, plane_id) _MMIO_VLV_SPR((pipe), (plane_id), _SPACLRC1, _SPBCLRC1) #define SPGAMC(pipe, plane_id) _MMIO_VLV_SPR((pipe), (plane_id), _SPAGAMC, _SPBGAMC) /* diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c index 3be22c0fcfb5..9b7171f20549 100644 --- a/drivers/gpu/drm/i915/intel_sprite.c +++ b/drivers/gpu/drm/i915/intel_sprite.c @@ -346,44 +346,87 @@ skl_plane_get_hw_state(struct intel_plane *plane) } static void -chv_update_csc(struct intel_plane *plane, uint32_t format) +chv_update_csc(const struct intel_plane_state *plane_state) { + struct intel_plane *plane = to_intel_plane(plane_state->base.plane); struct drm_i915_private *dev_priv = to_i915(plane->base.dev); + const struct drm_framebuffer *fb = plane_state->base.fb; enum plane_id plane_id = plane->id; /* Seems RGB data bypasses the CSC always */ - if (!format_is_yuv(format)) + if (!format_is_yuv(fb->format->format)) return; /* - * BT.601 limited range YCbCr -> full range RGB + * BT.601 full range YCbCr -> full range RGB * - * |r| | 6537 4769 0| |cr | - * |g| = |-3330 4769 -1605| x |y-64| - * |b| | 0 4769 8263| |cb | + * |r| | 5743 4096 0| |cr| + * |g| = |-2925 4096 -1410| x |y | + * |b| | 0 4096 7258| |cb| * - * Cb and Cr apparently come in as signed already, so no - * need for any offset. For Y we need to remove the offset. + * Cb and Cr apparently come in as signed already, + * and we get full range data in on account of CLRC0/1 */ - I915_WRITE_FW(SPCSCYGOFF(plane_id), SPCSC_OOFF(0) | SPCSC_IOFF(-64)); + I915_WRITE_FW(SPCSCYGOFF(plane_id), SPCSC_OOFF(0) | SPCSC_IOFF(0)); I915_WRITE_FW(SPCSCCBOFF(plane_id), SPCSC_OOFF(0) | SPCSC_IOFF(0)); I915_WRITE_FW(SPCSCCROFF(plane_id), SPCSC_OOFF(0) | SPCSC_IOFF(0)); - I915_WRITE_FW(SPCSCC01(plane_id), SPCSC_C1(4769) | SPCSC_C0(6537)); - I915_WRITE_FW(SPCSCC23(plane_id), SPCSC_C1(-3330) | SPCSC_C0(0)); - I915_WRITE_FW(SPCSCC45(plane_id), SPCSC_C1(-1605) | SPCSC_C0(4769)); - I915_WRITE_FW(SPCSCC67(plane_id), SPCSC_C1(4769) | SPCSC_C0(0)); - I915_WRITE_FW(SPCSCC8(plane_id), SPCSC_C0(8263)); + I915_WRITE_FW(SPCSCC01(plane_id), SPCSC_C1(4096) | SPCSC_C0(5743)); + I915_WRITE_FW(SPCSCC23(plane_id), SPCSC_C1(-2925) | SPCSC_C0(0)); + I915_WRITE_FW(SPCSCC45(plane_id), SPCSC_C1(-1410) | SPCSC_C0(4096)); + I915_WRITE_FW(SPCSCC67(plane_id), SPCSC_C1(4096) | SPCSC_C0(0)); + I915_WRITE_FW(SPCSCC8(plane_id), SPCSC_C0(7258)); - I915_WRITE_FW(SPCSCYGICLAMP(plane_id), SPCSC_IMAX(940) | SPCSC_IMIN(64)); - I915_WRITE_FW(SPCSCCBICLAMP(plane_id), SPCSC_IMAX(448) | SPCSC_IMIN(-448)); - I915_WRITE_FW(SPCSCCRICLAMP(plane_id), SPCSC_IMAX(448) | SPCSC_IMIN(-448)); + I915_WRITE_FW(SPCSCYGICLAMP(plane_id), SPCSC_IMAX(1023) | SPCSC_IMIN(0)); + I915_WRITE_FW(SPCSCCBICLAMP(plane_id), SPCSC_IMAX(512) | SPCSC_IMIN(-512)); + I915_WRITE_FW(SPCSCCRICLAMP(plane_id), SPCSC_IMAX(512) | SPCSC_IMIN(-512)); I915_WRITE_FW(SPCSCYGOCLAMP(plane_id), SPCSC_OMAX(1023) | SPCSC_OMIN(0)); I915_WRITE_FW(SPCSCCBOCLAMP(plane_id), SPCSC_OMAX(1023) | SPCSC_OMIN(0)); I915_WRITE_FW(SPCSCCROCLAMP(plane_id), SPCSC_OMAX(1023) | SPCSC_OMIN(0)); } +#define SIN_0 0 +#define COS_0 1 + +static void +vlv_update_clrc(const struct intel_plane_state *plane_state) +{ + struct intel_plane *plane = to_intel_plane(plane_state->base.plane); + struct drm_i915_private *dev_priv = to_i915(plane->base.dev); + const struct drm_framebuffer *fb = plane_state->base.fb; + enum pipe pipe = plane->pipe; + enum plane_id plane_id = plane->id; + int contrast, brightness, sh_scale, sh_sin, sh_cos; + + if (format_is_yuv(fb->format->format)) { + /* + * Expand limited range to full range: + * Contrast is applied first and is used to expand Y range. + * Brightness is applied second and is used to remove the + * offset from Y. Saturation/hue is used to expand CbCr range. + */ + contrast = DIV_ROUND_CLOSEST(255 << 6, 235 - 16); + brightness = -DIV_ROUND_CLOSEST(16 * 255, 235 - 16); + sh_scale = DIV_ROUND_CLOSEST(128 << 7, 240 - 128); + sh_sin = SIN_0 * sh_scale; + sh_cos = COS_0 * sh_scale; + } else { + /* Pass-through everything. */ + contrast = 1 << 6; + brightness = 0; + sh_scale = 1 << 7; + sh_sin = SIN_0 * sh_scale; + sh_cos = COS_0 * sh_scale; + } + + /* FIXME these register are single buffered :( */ + I915_WRITE_FW(SPCLRC0(pipe, plane_id), + SP_CONTRAST(contrast) | SP_BRIGHTNESS(brightness)); + I915_WRITE_FW(SPCLRC1(pipe, plane_id), + SP_SH_SIN(sh_sin) | SP_SH_COS(sh_cos)); +} + static u32 vlv_sprite_ctl(const struct intel_crtc_state *crtc_state, const struct intel_plane_state *plane_state) { @@ -477,8 +520,10 @@ vlv_update_plane(struct intel_plane *plane, spin_lock_irqsave(&dev_priv->uncore.lock, irqflags); + vlv_update_clrc(plane_state); + if (IS_CHERRYVIEW(dev_priv) && pipe == PIPE_B) - chv_update_csc(plane, fb->format->format); + chv_update_csc(plane_state); if (key->flags) { I915_WRITE_FW(SPKEYMINVAL(pipe, plane_id), key->min_value);

7 years, 2 months

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror