From 533555e5cbb6aa2d77598917871ae5b579fe724b Mon Sep 17 00:00:00 2001 From: Wei Yongjun Date: Sat, 27 Oct 2018 06:12:06 +0000 Subject: xfrm: Fix error return code in xfrm_output_one() xfrm_output_one() does not return a error code when there is no dst_entry attached to the skb, it is still possible crash with a NULL pointer dereference in xfrm_output_resume(). Fix it by return error code -EHOSTUNREACH. Fixes: 9e1437937807 ("xfrm: Fix NULL pointer dereference when skb_dst_force clears the dst_entry.") Signed-off-by: Wei Yongjun Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_output.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index 4ae87c5ce2e3..fef6b2da3c5d 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -102,6 +102,7 @@ static int xfrm_output_one(struct sk_buff *skb, int err) skb_dst_force(skb); if (!skb_dst(skb)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTERROR); + err = -EHOSTUNREACH; goto error_nolock; } -- cgit v1.2.3 From ca92e173ab34a4f7fc4128bd372bd96f1af6f507 Mon Sep 17 00:00:00 2001 From: Benjamin Poirier Date: Mon, 5 Nov 2018 17:00:53 +0900 Subject: xfrm: Fix bucket count reported to userspace sadhcnt is reported by `ip -s xfrm state count` as "buckets count", not the hash mask. Fixes: 28d8909bc790 ("[XFRM]: Export SAD info.") Signed-off-by: Benjamin Poirier Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_state.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index b669262682c9..12cdb350c456 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -788,7 +788,7 @@ void xfrm_sad_getinfo(struct net *net, struct xfrmk_sadinfo *si) { spin_lock_bh(&net->xfrm.xfrm_state_lock); si->sadcnt = net->xfrm.state_num; - si->sadhcnt = net->xfrm.state_hmask; + si->sadhcnt = net->xfrm.state_hmask + 1; si->sadhmcnt = xfrm_state_hashmax; spin_unlock_bh(&net->xfrm.xfrm_state_lock); } -- cgit v1.2.3 From 5f8208f557065163f9a8089ea2ea7888f9d96922 Mon Sep 17 00:00:00 2001 From: Corentin Labbe Date: Mon, 9 Jul 2018 19:51:54 +0000 Subject: ARM: dts: sun8i: a83t: bananapi-m3: increase vcc-pd voltage to 3.3V Since commit d7c5f6863550 ("ARM: dts: sun8i: a83t: bananapi-m3: Add AXP813 regulator nodes") my BPIM3 no longer works at gigabit speed. With the default setting, dldo3 is regulated at 2.9v which seems sufficient for the PHY but the aforementioned commit drops it to 2.5V which is insufficient. Note that this behaviour is random for all BPIM3. Some work with 2.5V, but some don't. Finnaly, someone from Bananapi confirmed that this regulator must be set to 3.3V. Fixes: d7c5f6863550 ("ARM: dts: sun8i: a83t: bananapi-m3: Add AXP813 regulator nodes") Signed-off-by: Corentin Labbe [wens@csie.org: Reworked commit message] Signed-off-by: Chen-Yu Tsai --- arch/arm/boot/dts/sun8i-a83t-bananapi-m3.dts | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm/boot/dts/sun8i-a83t-bananapi-m3.dts b/arch/arm/boot/dts/sun8i-a83t-bananapi-m3.dts index 742d2946b08b..583a5a01642f 100644 --- a/arch/arm/boot/dts/sun8i-a83t-bananapi-m3.dts +++ b/arch/arm/boot/dts/sun8i-a83t-bananapi-m3.dts @@ -314,8 +314,8 @@ ®_dldo3 { regulator-always-on; - regulator-min-microvolt = <2500000>; - regulator-max-microvolt = <2500000>; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; regulator-name = "vcc-pd"; }; -- cgit v1.2.3 From 5db0b0a298d26c007e06a96d7e60849b4829a57c Mon Sep 17 00:00:00 2001 From: Craig Tatlor Date: Mon, 12 Nov 2018 20:25:53 +0000 Subject: pinctrl: sdm660: Set tile property for pingroups This was missed when tiles support was added in a revison and causes the driver to fail to load. Fixes: 9cf0c526bc58 ("pinctrl: qcom: Add sdm660 pinctrl driver") Signed-off-by: Craig Tatlor Reviewed-by: Bjorn Andersson Signed-off-by: Linus Walleij --- drivers/pinctrl/qcom/pinctrl-sdm660.c | 28 +++++++++++++++------------- 1 file changed, 15 insertions(+), 13 deletions(-) diff --git a/drivers/pinctrl/qcom/pinctrl-sdm660.c b/drivers/pinctrl/qcom/pinctrl-sdm660.c index 6838b38555a1..1bfb0ae6b387 100644 --- a/drivers/pinctrl/qcom/pinctrl-sdm660.c +++ b/drivers/pinctrl/qcom/pinctrl-sdm660.c @@ -33,7 +33,7 @@ enum { } -#define PINGROUP(id, base, f1, f2, f3, f4, f5, f6, f7, f8, f9) \ +#define PINGROUP(id, _tile, f1, f2, f3, f4, f5, f6, f7, f8, f9) \ { \ .name = "gpio" #id, \ .pins = gpio##id##_pins, \ @@ -51,11 +51,12 @@ enum { msm_mux_##f9 \ }, \ .nfuncs = 10, \ - .ctl_reg = base + REG_SIZE * id, \ - .io_reg = base + 0x4 + REG_SIZE * id, \ - .intr_cfg_reg = base + 0x8 + REG_SIZE * id, \ - .intr_status_reg = base + 0xc + REG_SIZE * id, \ - .intr_target_reg = base + 0x8 + REG_SIZE * id, \ + .ctl_reg = REG_SIZE * id, \ + .io_reg = 0x4 + REG_SIZE * id, \ + .intr_cfg_reg = 0x8 + REG_SIZE * id, \ + .intr_status_reg = 0xc + REG_SIZE * id, \ + .intr_target_reg = 0x8 + REG_SIZE * id, \ + .tile = _tile, \ .mux_bit = 2, \ .pull_bit = 0, \ .drv_bit = 6, \ @@ -82,6 +83,7 @@ enum { .intr_cfg_reg = 0, \ .intr_status_reg = 0, \ .intr_target_reg = 0, \ + .tile = NORTH, \ .mux_bit = -1, \ .pull_bit = pull, \ .drv_bit = drv, \ @@ -1397,13 +1399,13 @@ static const struct msm_pingroup sdm660_groups[] = { PINGROUP(111, SOUTH, _, _, _, _, _, _, _, _, _), PINGROUP(112, SOUTH, _, _, _, _, _, _, _, _, _), PINGROUP(113, SOUTH, _, _, _, _, _, _, _, _, _), - SDC_QDSD_PINGROUP(sdc1_clk, 0x99a000, 13, 6), - SDC_QDSD_PINGROUP(sdc1_cmd, 0x99a000, 11, 3), - SDC_QDSD_PINGROUP(sdc1_data, 0x99a000, 9, 0), - SDC_QDSD_PINGROUP(sdc2_clk, 0x99b000, 14, 6), - SDC_QDSD_PINGROUP(sdc2_cmd, 0x99b000, 11, 3), - SDC_QDSD_PINGROUP(sdc2_data, 0x99b000, 9, 0), - SDC_QDSD_PINGROUP(sdc1_rclk, 0x99a000, 15, 0), + SDC_QDSD_PINGROUP(sdc1_clk, 0x9a000, 13, 6), + SDC_QDSD_PINGROUP(sdc1_cmd, 0x9a000, 11, 3), + SDC_QDSD_PINGROUP(sdc1_data, 0x9a000, 9, 0), + SDC_QDSD_PINGROUP(sdc2_clk, 0x9b000, 14, 6), + SDC_QDSD_PINGROUP(sdc2_cmd, 0x9b000, 11, 3), + SDC_QDSD_PINGROUP(sdc2_data, 0x9b000, 9, 0), + SDC_QDSD_PINGROUP(sdc1_rclk, 0x9a000, 15, 0), }; static const struct msm_pinctrl_soc_data sdm660_pinctrl = { -- cgit v1.2.3 From 614b1868a125a0ba24be08f3a7fa832ddcde6bca Mon Sep 17 00:00:00 2001 From: Jerome Brunet Date: Tue, 13 Nov 2018 11:55:36 +0100 Subject: pinctrl: meson: fix pull enable register calculation We just changed the code so we apply bias disable on the correct register but forgot to align the register calculation. The result is that we apply the change on the correct register, but possibly at the incorrect offset/bit This went undetected because offsets tends to be the same between REG_PULL and REG_PULLEN for a given pin the EE controller. This is not true for the AO controller. Fixes: e39f9dd8206a ("pinctrl: meson: fix pinconf bias disable") Signed-off-by: Jerome Brunet Acked-by: Neil Armstrong Signed-off-by: Linus Walleij --- drivers/pinctrl/meson/pinctrl-meson.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/pinctrl/meson/pinctrl-meson.c b/drivers/pinctrl/meson/pinctrl-meson.c index 53d449076dee..ea87d739f534 100644 --- a/drivers/pinctrl/meson/pinctrl-meson.c +++ b/drivers/pinctrl/meson/pinctrl-meson.c @@ -191,7 +191,8 @@ static int meson_pinconf_set(struct pinctrl_dev *pcdev, unsigned int pin, case PIN_CONFIG_BIAS_DISABLE: dev_dbg(pc->dev, "pin %u: disable bias\n", pin); - meson_calc_reg_and_bit(bank, pin, REG_PULL, ®, &bit); + meson_calc_reg_and_bit(bank, pin, REG_PULLEN, ®, + &bit); ret = regmap_update_bits(pc->reg_pullen, reg, BIT(bit), 0); if (ret) -- cgit v1.2.3 From 91ff20f34e94424e586f57f4f593beae16504f86 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Wed, 14 Nov 2018 16:01:34 +0200 Subject: ovl: fix missing override creds in link of a metacopy upper Theodore Ts'o reported a v4.19 regression with docker-dropbox: https://marc.info/?l=linux-fsdevel&m=154070089431116&w=2 "I was rebuilding my dropbox Docker container, and it failed in 4.19 with the following error: ... dpkg: error: error creating new backup file \ '/var/lib/dpkg/status-old': Invalid cross-device link" The problem did not reproduce with metacopy feature disabled. The error was caused by insufficient credentials to set "trusted.overlay.redirect" xattr on link of a metacopy file. Reproducer: echo Y > /sys/module/overlay/parameters/redirect_dir echo Y > /sys/module/overlay/parameters/metacopy cd /tmp mkdir l u w m chmod 777 l u touch l/foo ln l/foo l/link chmod 666 l/foo mount -t overlay none -olowerdir=l,upperdir=u,workdir=w m su fsgqa ln m/foo m/bar [ 21.455823] overlayfs: failed to set redirect (-1) ln: failed to create hard link 'm/bar' => 'm/foo':\ Invalid cross-device link Reported-by: Theodore Y. Ts'o Reported-by: Maciej Zięba Fixes: 4120fe64dce4 ("ovl: Set redirect on upper inode when it is linked") Cc: # v4.19 Signed-off-by: Amir Goldstein Acked-by: Vivek Goyal Signed-off-by: Miklos Szeredi --- fs/overlayfs/dir.c | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c index c6289147c787..82c129bfe58d 100644 --- a/fs/overlayfs/dir.c +++ b/fs/overlayfs/dir.c @@ -651,6 +651,18 @@ static int ovl_symlink(struct inode *dir, struct dentry *dentry, return ovl_create_object(dentry, S_IFLNK, 0, link); } +static int ovl_set_link_redirect(struct dentry *dentry) +{ + const struct cred *old_cred; + int err; + + old_cred = ovl_override_creds(dentry->d_sb); + err = ovl_set_redirect(dentry, false); + revert_creds(old_cred); + + return err; +} + static int ovl_link(struct dentry *old, struct inode *newdir, struct dentry *new) { @@ -670,7 +682,7 @@ static int ovl_link(struct dentry *old, struct inode *newdir, goto out_drop_write; if (ovl_is_metacopy_dentry(old)) { - err = ovl_set_redirect(old, false); + err = ovl_set_link_redirect(old); if (err) goto out_drop_write; } -- cgit v1.2.3 From 155b8a0492a90a4c6e22f046a3568b92a6bc48da Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Mon, 5 Nov 2018 07:50:10 +0200 Subject: ovl: fix decode of dir file handle with multi lower layers When decoding a lower file handle, we first call ovl_check_origin_fh() with connected=false to get any real lower dentry for overlay inode cache lookup. If the real dentry is a disconnected dir dentry, ovl_check_origin_fh() is called again with connected=true to get a connected real dentry and find the lower layer the real dentry belongs to. If the first call returned a connected real dentry, we use it to lookup an overlay connected dentry, but the first ovl_check_origin_fh() call with connected=false did not check that the found dentry is under the root of the layer (see ovl_acceptable()), it only checked that the found dentry super block matches the uuid of the lower file handle. In case there are multiple lower layers on the same fs and the found dentry is not from the top most lower layer, using the layer index returned from the first ovl_check_origin_fh() is wrong and we end up failing to decode the file handle. Fix this by always calling ovl_check_origin_fh() with connected=true if we got a directory dentry in the first call. Fixes: 8b58924ad55c ("ovl: lookup in inode cache first when decoding...") Cc: # v4.17 Signed-off-by: Amir Goldstein Signed-off-by: Miklos Szeredi --- fs/overlayfs/export.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/fs/overlayfs/export.c b/fs/overlayfs/export.c index 8fa37cd7818a..54e5d17d7f3e 100644 --- a/fs/overlayfs/export.c +++ b/fs/overlayfs/export.c @@ -754,9 +754,8 @@ static struct dentry *ovl_lower_fh_to_d(struct super_block *sb, goto out; } - /* Otherwise, get a connected non-upper dir or disconnected non-dir */ - if (d_is_dir(origin.dentry) && - (origin.dentry->d_flags & DCACHE_DISCONNECTED)) { + /* Find origin.dentry again with ovl_acceptable() layer check */ + if (d_is_dir(origin.dentry)) { dput(origin.dentry); origin.dentry = NULL; err = ovl_check_origin_fh(ofs, fh, true, NULL, &stack); @@ -769,6 +768,7 @@ static struct dentry *ovl_lower_fh_to_d(struct super_block *sb, goto out_err; } + /* Get a connected non-upper dir or disconnected non-dir */ dentry = ovl_get_dentry(sb, NULL, &origin, index); out: -- cgit v1.2.3 From 0152eee6fc3b84298bb6a79961961734e8afa5b8 Mon Sep 17 00:00:00 2001 From: Steffen Klassert Date: Thu, 22 Nov 2018 07:26:24 +0100 Subject: xfrm: Fix NULL pointer dereference in xfrm_input when skb_dst_force clears the dst_entry. Since commit 222d7dbd258d ("net: prevent dst uses after free") skb_dst_force() might clear the dst_entry attached to the skb. The xfrm code doesn't expect this to happen, so we crash with a NULL pointer dereference in this case. Fix it by checking skb_dst(skb) for NULL after skb_dst_force() and drop the packet in case the dst_entry was cleared. We also move the skb_dst_force() to a codepath that is not used when the transformation was offloaded, because in this case we don't have a dst_entry attached to the skb. The output and forwarding path was already fixed by commit 9e1437937807 ("xfrm: Fix NULL pointer dereference when skb_dst_force clears the dst_entry.") Fixes: 222d7dbd258d ("net: prevent dst uses after free") Reported-by: Jean-Philippe Menil Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_input.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index 684c0bc01e2c..d5635908587f 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -346,6 +346,12 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) skb->sp->xvec[skb->sp->len++] = x; + skb_dst_force(skb); + if (!skb_dst(skb)) { + XFRM_INC_STATS(net, LINUX_MIB_XFRMINERROR); + goto drop; + } + lock: spin_lock(&x->lock); @@ -385,7 +391,6 @@ lock: XFRM_SKB_CB(skb)->seq.input.low = seq; XFRM_SKB_CB(skb)->seq.input.hi = seq_hi; - skb_dst_force(skb); dev_hold(skb->dev); if (crypto_done) -- cgit v1.2.3 From 4fc4bb796b0c75067fd65292dfd874869ff7c9dc Mon Sep 17 00:00:00 2001 From: Myungho Jung Date: Wed, 21 Nov 2018 15:18:30 -0800 Subject: fuse: Add bad inode check in fuse_destroy_inode() make_bad_inode() sets inode->i_mode to S_IFREG if I/O error is detected in fuse_do_getattr()/fuse_do_setattr(). If the inode is not a regular file, write_files and queued_writes in fuse_inode are not initialized and have NULL or invalid pointers written by other members in a union. So, list_empty() returns false in fuse_destroy_inode(). Add is_bad_inode() to check if make_bad_inode() was called. Reported-by: syzbot+b9c89b84423073226299@syzkaller.appspotmail.com Fixes: ab2257e9941b ("fuse: reduce size of struct fuse_inode") Signed-off-by: Myungho Jung Signed-off-by: Miklos Szeredi --- fs/fuse/inode.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 0b94b23b02d4..073865371f9b 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -115,7 +115,7 @@ static void fuse_i_callback(struct rcu_head *head) static void fuse_destroy_inode(struct inode *inode) { struct fuse_inode *fi = get_fuse_inode(inode); - if (S_ISREG(inode->i_mode)) { + if (S_ISREG(inode->i_mode) && !is_bad_inode(inode)) { WARN_ON(!list_empty(&fi->write_files)); WARN_ON(!list_empty(&fi->queued_writes)); } -- cgit v1.2.3 From 4a135e538962cb00a9667c82e7d2b9e4d7cd7177 Mon Sep 17 00:00:00 2001 From: Mathias Krause Date: Wed, 21 Nov 2018 21:09:23 +0100 Subject: xfrm_user: fix freeing of xfrm states on acquire Commit 565f0fa902b6 ("xfrm: use a dedicated slab cache for struct xfrm_state") moved xfrm state objects to use their own slab cache. However, it missed to adapt xfrm_user to use this new cache when freeing xfrm states. Fix this by introducing and make use of a new helper for freeing xfrm_state objects. Fixes: 565f0fa902b6 ("xfrm: use a dedicated slab cache for struct xfrm_state") Reported-by: Pan Bian Cc: # v4.18+ Signed-off-by: Mathias Krause Acked-by: Herbert Xu Signed-off-by: Steffen Klassert --- include/net/xfrm.h | 1 + net/xfrm/xfrm_state.c | 8 +++++++- net/xfrm/xfrm_user.c | 4 ++-- 3 files changed, 10 insertions(+), 3 deletions(-) diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 0eb390c205af..da588def3c61 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -1552,6 +1552,7 @@ int xfrm_state_walk(struct net *net, struct xfrm_state_walk *walk, int (*func)(struct xfrm_state *, int, void*), void *); void xfrm_state_walk_done(struct xfrm_state_walk *walk, struct net *net); struct xfrm_state *xfrm_state_alloc(struct net *net); +void xfrm_state_free(struct xfrm_state *x); struct xfrm_state *xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr, const struct flowi *fl, diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 12cdb350c456..cc0203efb584 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -426,6 +426,12 @@ static void xfrm_put_mode(struct xfrm_mode *mode) module_put(mode->owner); } +void xfrm_state_free(struct xfrm_state *x) +{ + kmem_cache_free(xfrm_state_cache, x); +} +EXPORT_SYMBOL(xfrm_state_free); + static void xfrm_state_gc_destroy(struct xfrm_state *x) { tasklet_hrtimer_cancel(&x->mtimer); @@ -452,7 +458,7 @@ static void xfrm_state_gc_destroy(struct xfrm_state *x) } xfrm_dev_state_free(x); security_xfrm_state_free(x); - kmem_cache_free(xfrm_state_cache, x); + xfrm_state_free(x); } static void xfrm_state_gc_task(struct work_struct *work) diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index ca7a207b81a9..683080172655 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -2288,13 +2288,13 @@ static int xfrm_add_acquire(struct sk_buff *skb, struct nlmsghdr *nlh, } - kfree(x); + xfrm_state_free(x); kfree(xp); return 0; free_state: - kfree(x); + xfrm_state_free(x); nomem: return err; } -- cgit v1.2.3 From 6c05946e349d92f527d98644fbc9c41f06312c00 Mon Sep 17 00:00:00 2001 From: Ryder Lee Date: Mon, 12 Nov 2018 09:28:06 +0800 Subject: arm64: dts: mt7622: fix no more console output on rfb1 No default serial console on boot. Fix this by using a 'stdout-path' property that points to the device. Fixes: c0d9f9ad4f76 ("arm64: dts: mt7622: add earlycon to mt7622-rfb1 board") Signed-off-by: Ryder Lee Tested-by: Kevin Hilman [mb: Fix commit message] Signed-off-by: Matthias Brugger --- arch/arm64/boot/dts/mediatek/mt7622-rfb1.dts | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/mediatek/mt7622-rfb1.dts b/arch/arm64/boot/dts/mediatek/mt7622-rfb1.dts index dcad0869b84c..3f783348c66a 100644 --- a/arch/arm64/boot/dts/mediatek/mt7622-rfb1.dts +++ b/arch/arm64/boot/dts/mediatek/mt7622-rfb1.dts @@ -17,8 +17,13 @@ model = "MediaTek MT7622 RFB1 board"; compatible = "mediatek,mt7622-rfb1", "mediatek,mt7622"; + aliases { + serial0 = &uart0; + }; + chosen { - bootargs = "earlycon=uart8250,mmio32,0x11002000 console=ttyS0,115200n1 swiotlb=512"; + stdout-path = "serial0:115200n8"; + bootargs = "earlycon=uart8250,mmio32,0x11002000 swiotlb=512"; }; cpus { -- cgit v1.2.3 From 396defa8523372645d6d5a8b7f4b5403b119e360 Mon Sep 17 00:00:00 2001 From: Ryder Lee Date: Mon, 12 Nov 2018 09:28:07 +0800 Subject: arm64: dts: mt7622: fix no more console output on BPI-R64 board Fix this by using a 'stdout-path' property that points to the device. Fixes: 0b6286dd96c0 ("arm64: dts: mt7622: add bananapi BPI-R64 board") Signed-off-by: Ryder Lee Signed-off-by: Matthias Brugger --- arch/arm64/boot/dts/mediatek/mt7622-bananapi-bpi-r64.dts | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/mediatek/mt7622-bananapi-bpi-r64.dts b/arch/arm64/boot/dts/mediatek/mt7622-bananapi-bpi-r64.dts index 5d6005c9b097..710c5c3d87d3 100644 --- a/arch/arm64/boot/dts/mediatek/mt7622-bananapi-bpi-r64.dts +++ b/arch/arm64/boot/dts/mediatek/mt7622-bananapi-bpi-r64.dts @@ -16,8 +16,13 @@ model = "Bananapi BPI-R64"; compatible = "bananapi,bpi-r64", "mediatek,mt7622"; + aliases { + serial0 = &uart0; + }; + chosen { - bootargs = "earlycon=uart8250,mmio32,0x11002000 console=ttyS0,115200n1 swiotlb=512"; + stdout-path = "serial0:115200n8"; + bootargs = "earlycon=uart8250,mmio32,0x11002000 swiotlb=512"; }; cpus { -- cgit v1.2.3 From ce68cc6fad893eb33b69ef7ec186233a51696236 Mon Sep 17 00:00:00 2001 From: Ryder Lee Date: Mon, 12 Nov 2018 09:28:08 +0800 Subject: arm64: dts: mt7622: Drop the general purpose timer node MediaTeks general purpose timer register into system in early phase during kernel boot, but the clock sources aren't probed at this point. The system has the ARM architecture timer, so we don't need the GPT timer from mediatek. Drop the DT node for it. Fixes: 9cc7f0de9e67 ("arm64: dts: mt7622: add timer, CCI-400 and PMU nodes") Signed-off-by: Ryder Lee [mb: fix commit message] Signed-off-by: Matthias Brugger --- arch/arm64/boot/dts/mediatek/mt7622.dtsi | 10 ---------- 1 file changed, 10 deletions(-) diff --git a/arch/arm64/boot/dts/mediatek/mt7622.dtsi b/arch/arm64/boot/dts/mediatek/mt7622.dtsi index fe0c875f1d95..14a1028ca3a6 100644 --- a/arch/arm64/boot/dts/mediatek/mt7622.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt7622.dtsi @@ -227,16 +227,6 @@ #reset-cells = <1>; }; - timer: timer@10004000 { - compatible = "mediatek,mt7622-timer", - "mediatek,mt6577-timer"; - reg = <0 0x10004000 0 0x80>; - interrupts = ; - clocks = <&infracfg CLK_INFRA_APXGPT_PD>, - <&topckgen CLK_TOP_RTC>; - clock-names = "system-clk", "rtc-clk"; - }; - scpsys: scpsys@10006000 { compatible = "mediatek,mt7622-scpsys", "syscon"; -- cgit v1.2.3 From 5564597d51c8ff5b88d95c76255e18b13b760879 Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Tue, 27 Nov 2018 09:01:54 +1100 Subject: powerpc: Fix COFF zImage booting on old powermacs Commit 6975a783d7b4 ("powerpc/boot: Allow building the zImage wrapper as a relocatable ET_DYN", 2011-04-12) changed the procedure descriptor at the start of crt0.S to have a hard-coded start address of 0x500000 rather than a reference to _zimage_start, presumably because having a reference to a symbol introduced a relocation which is awkward to handle in a position-independent executable. Unfortunately, what is at 0x500000 in the COFF image is not the first instruction, but the procedure descriptor itself, that is, a word containing 0x500000, which is not a valid instruction. Hence, booting a COFF zImage results in a "DEFAULT CATCH!, code=FFF00700" message from Open Firmware. This fixes the problem by (a) putting the procedure descriptor in the data section and (b) adding a branch to _zimage_start as the first instruction in the program. Fixes: 6975a783d7b4 ("powerpc/boot: Allow building the zImage wrapper as a relocatable ET_DYN") Signed-off-by: Paul Mackerras Signed-off-by: Michael Ellerman --- arch/powerpc/boot/crt0.S | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/arch/powerpc/boot/crt0.S b/arch/powerpc/boot/crt0.S index 32dfe6d083f3..9b9d17437373 100644 --- a/arch/powerpc/boot/crt0.S +++ b/arch/powerpc/boot/crt0.S @@ -15,7 +15,7 @@ RELA = 7 RELACOUNT = 0x6ffffff9 - .text + .data /* A procedure descriptor used when booting this as a COFF file. * When making COFF, this comes first in the link and we're * linked at 0x500000. @@ -23,6 +23,8 @@ RELACOUNT = 0x6ffffff9 .globl _zimage_start_opd _zimage_start_opd: .long 0x500000, 0, 0, 0 + .text + b _zimage_start #ifdef __powerpc64__ .balign 8 -- cgit v1.2.3 From 462951cd32e1496dc64b00051dfb777efc8ae5d8 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Mon, 26 Nov 2018 12:59:16 +1100 Subject: powerpc/mm: Fix linux page tables build with some configs For some configs the build fails with: arch/powerpc/mm/dump_linuxpagetables.c: In function 'populate_markers': arch/powerpc/mm/dump_linuxpagetables.c:306:39: error: 'PKMAP_BASE' undeclared (first use in this function) arch/powerpc/mm/dump_linuxpagetables.c:314:50: error: 'LAST_PKMAP' undeclared (first use in this function) These come from highmem.h, including that fixes the build. Signed-off-by: Michael Ellerman --- arch/powerpc/mm/dump_linuxpagetables.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/powerpc/mm/dump_linuxpagetables.c b/arch/powerpc/mm/dump_linuxpagetables.c index 2b74f8adf4d0..6aa41669ac1a 100644 --- a/arch/powerpc/mm/dump_linuxpagetables.c +++ b/arch/powerpc/mm/dump_linuxpagetables.c @@ -19,6 +19,7 @@ #include #include #include +#include #include #include #include -- cgit v1.2.3 From 78e7b15e17ac175e7eed9e21c6f92d03d3b0a6fa Mon Sep 17 00:00:00 2001 From: Radu Rendec Date: Tue, 27 Nov 2018 22:20:48 -0500 Subject: powerpc/msi: Fix NULL pointer access in teardown code The arch_teardown_msi_irqs() function assumes that controller ops pointers were already checked in arch_setup_msi_irqs(), but this assumption is wrong: arch_teardown_msi_irqs() can be called even when arch_setup_msi_irqs() returns an error (-ENOSYS). This can happen in the following scenario: - msi_capability_init() calls pci_msi_setup_msi_irqs() - pci_msi_setup_msi_irqs() returns -ENOSYS - msi_capability_init() notices the error and calls free_msi_irqs() - free_msi_irqs() calls pci_msi_teardown_msi_irqs() This is easier to see when CONFIG_PCI_MSI_IRQ_DOMAIN is not set and pci_msi_setup_msi_irqs() and pci_msi_teardown_msi_irqs() are just aliases to arch_setup_msi_irqs() and arch_teardown_msi_irqs(). The call to free_msi_irqs() upon pci_msi_setup_msi_irqs() failure seems legit, as it does additional cleanup; e.g. list_del(&entry->list) and kfree(entry) inside free_msi_irqs() do happen (MSI descriptors are allocated before pci_msi_setup_msi_irqs() is called and need to be cleaned up if that fails). Fixes: 6b2fd7efeb88 ("PCI/MSI/PPC: Remove arch_msi_check_device()") Cc: stable@vger.kernel.org # v3.18+ Signed-off-by: Radu Rendec Signed-off-by: Michael Ellerman --- arch/powerpc/kernel/msi.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/arch/powerpc/kernel/msi.c b/arch/powerpc/kernel/msi.c index dab616a33b8d..f2197654be07 100644 --- a/arch/powerpc/kernel/msi.c +++ b/arch/powerpc/kernel/msi.c @@ -34,5 +34,10 @@ void arch_teardown_msi_irqs(struct pci_dev *dev) { struct pci_controller *phb = pci_bus_to_host(dev->bus); - phb->controller_ops.teardown_msi_irqs(dev); + /* + * We can be called even when arch_setup_msi_irqs() returns -ENOSYS, + * so check the pointer again. + */ + if (phb->controller_ops.teardown_msi_irqs) + phb->controller_ops.teardown_msi_irqs(dev); } -- cgit v1.2.3 From 4050207485e47e00353e87f2fe2166083e282688 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Mon, 26 Nov 2018 11:52:18 +0100 Subject: HID: ite: Add USB id match for another ITE based keyboard rfkill key quirk The 258a:6a88 keyboard-dock shipped with the Prowise PT301 tablet is likely another ITE based design. The controller die is directly bonded to the PCB with a blob of black glue on top so there are no markings and the 258a vendor-id used is unknown anywhere. But the keyboard has the exact same hotkeys mapped to Fn+F1 - F10 as the other ITE8595 keyboard I have *and* it has the same quirky behavior wrt the rfkill hotkey. Either way as said this keyboard has the same quirk for its rfkill / airplane mode hotkey as the ITE 8595 chip, it only sends a single release event when pressed and released, it never sends a press event. This commit adds the 258a:6a88 USB id to the hid-ite id-table, fixing the rfkill key not working on this keyboard. Signed-off-by: Hans de Goede Signed-off-by: Benjamin Tissoires --- drivers/hid/hid-ids.h | 3 +++ drivers/hid/hid-ite.c | 1 + 2 files changed, 4 insertions(+) diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index ed35c9a9a110..94df9cdf6ec6 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -17,6 +17,9 @@ #ifndef HID_IDS_H_FILE #define HID_IDS_H_FILE +#define USB_VENDOR_ID_258A 0x258a +#define USB_DEVICE_ID_258A_6A88 0x6a88 + #define USB_VENDOR_ID_3M 0x0596 #define USB_DEVICE_ID_3M1968 0x0500 #define USB_DEVICE_ID_3M2256 0x0502 diff --git a/drivers/hid/hid-ite.c b/drivers/hid/hid-ite.c index 1882a4ab0f29..98b059d79bc8 100644 --- a/drivers/hid/hid-ite.c +++ b/drivers/hid/hid-ite.c @@ -42,6 +42,7 @@ static int ite_event(struct hid_device *hdev, struct hid_field *field, static const struct hid_device_id ite_devices[] = { { HID_USB_DEVICE(USB_VENDOR_ID_ITE, USB_DEVICE_ID_ITE8595) }, + { HID_USB_DEVICE(USB_VENDOR_ID_258A, USB_DEVICE_ID_258A_6A88) }, { } }; MODULE_DEVICE_TABLE(hid, ite_devices); -- cgit v1.2.3 From bf3d6afbb234156749b640b6c50f714967a85964 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Fri, 30 Nov 2018 14:54:09 +1100 Subject: powerpc: Look for "stdout-path" when setting up legacy consoles Commit 78e5dfea84dc ("powerpc: dts: replace 'linux,stdout-path' with 'stdout-path'") broke the default console on a number of embedded PowerPC systems, because it failed to also update the code in arch/powerpc/kernel/legacy_serial.c to look for that property in addition to the old one. This fixes it. Fixes: 78e5dfea84dc ("powerpc: dts: replace 'linux,stdout-path' with 'stdout-path'") Cc: stable@vger.kernel.org # v4.17+ Signed-off-by: Benjamin Herrenschmidt Reviewed-by: Rob Herring Signed-off-by: Michael Ellerman --- arch/powerpc/kernel/legacy_serial.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/arch/powerpc/kernel/legacy_serial.c b/arch/powerpc/kernel/legacy_serial.c index 33b34a58fc62..5b9dce17f0c9 100644 --- a/arch/powerpc/kernel/legacy_serial.c +++ b/arch/powerpc/kernel/legacy_serial.c @@ -372,6 +372,8 @@ void __init find_legacy_serial_ports(void) /* Now find out if one of these is out firmware console */ path = of_get_property(of_chosen, "linux,stdout-path", NULL); + if (path == NULL) + path = of_get_property(of_chosen, "stdout-path", NULL); if (path != NULL) { stdout = of_find_node_by_path(path); if (stdout) @@ -595,8 +597,10 @@ static int __init check_legacy_serial_console(void) /* We are getting a weird phandle from OF ... */ /* ... So use the full path instead */ name = of_get_property(of_chosen, "linux,stdout-path", NULL); + if (name == NULL) + name = of_get_property(of_chosen, "stdout-path", NULL); if (name == NULL) { - DBG(" no linux,stdout-path !\n"); + DBG(" no stdout-path !\n"); return -ENODEV; } prom_stdout = of_find_node_by_path(name); -- cgit v1.2.3 From a73d4e1490913b76b292f91553b7ba08a65caa3f Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Thu, 29 Nov 2018 17:41:54 -0500 Subject: ieee802154: hwsim: fix off-by-one in parse nested This patch fixes a off-by-one mistake in nla_parse_nested() functions of mac802154_hwsim driver. I had to enabled stack protector so I was able to reproduce it. Reference: https://github.com/linux-wpan/wpan-tools/issues/17 Signed-off-by: Alexander Aring Signed-off-by: Stefan Schmidt --- drivers/net/ieee802154/mac802154_hwsim.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ieee802154/mac802154_hwsim.c b/drivers/net/ieee802154/mac802154_hwsim.c index 51b5198d5943..b6743f03dce0 100644 --- a/drivers/net/ieee802154/mac802154_hwsim.c +++ b/drivers/net/ieee802154/mac802154_hwsim.c @@ -492,7 +492,7 @@ static int hwsim_del_edge_nl(struct sk_buff *msg, struct genl_info *info) !info->attrs[MAC802154_HWSIM_ATTR_RADIO_EDGE]) return -EINVAL; - if (nla_parse_nested(edge_attrs, MAC802154_HWSIM_EDGE_ATTR_MAX + 1, + if (nla_parse_nested(edge_attrs, MAC802154_HWSIM_EDGE_ATTR_MAX, info->attrs[MAC802154_HWSIM_ATTR_RADIO_EDGE], hwsim_edge_policy, NULL)) return -EINVAL; @@ -542,7 +542,7 @@ static int hwsim_set_edge_lqi(struct sk_buff *msg, struct genl_info *info) !info->attrs[MAC802154_HWSIM_ATTR_RADIO_EDGE]) return -EINVAL; - if (nla_parse_nested(edge_attrs, MAC802154_HWSIM_EDGE_ATTR_MAX + 1, + if (nla_parse_nested(edge_attrs, MAC802154_HWSIM_EDGE_ATTR_MAX, info->attrs[MAC802154_HWSIM_ATTR_RADIO_EDGE], hwsim_edge_policy, NULL)) return -EINVAL; -- cgit v1.2.3 From a0071bc455da7b830b9517058933a83eb6cc902a Mon Sep 17 00:00:00 2001 From: Nicolas Boichat Date: Mon, 26 Nov 2018 12:07:37 +0800 Subject: drm/mediatek: Only try to attach bridge if there is one Even if dsi->bridge is NULL, we still try to call drm_bridge_attach, and print out an error message, before creating the connector. When no bridge is provided, let's skip these 2 steps and directly create the connector. Signed-off-by: Nicolas Boichat Signed-off-by: CK Hu Reviewed-by: Andrzej Hajda --- drivers/gpu/drm/mediatek/mtk_dsi.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/mediatek/mtk_dsi.c b/drivers/gpu/drm/mediatek/mtk_dsi.c index 66df1b177959..27b507eb4a99 100644 --- a/drivers/gpu/drm/mediatek/mtk_dsi.c +++ b/drivers/gpu/drm/mediatek/mtk_dsi.c @@ -818,10 +818,13 @@ static int mtk_dsi_create_conn_enc(struct drm_device *drm, struct mtk_dsi *dsi) dsi->encoder.possible_crtcs = 1; /* If there's a bridge, attach to it and let it create the connector */ - ret = drm_bridge_attach(&dsi->encoder, dsi->bridge, NULL); - if (ret) { - DRM_ERROR("Failed to attach bridge to drm\n"); - + if (dsi->bridge) { + ret = drm_bridge_attach(&dsi->encoder, dsi->bridge, NULL); + if (ret) { + DRM_ERROR("Failed to attach bridge to drm\n"); + goto err_encoder_cleanup; + } + } else { /* Otherwise create our own connector and attach to a panel */ ret = mtk_dsi_create_connector(drm, dsi); if (ret) -- cgit v1.2.3 From a40fa231bb64b33e2cd54cf8ef44a9f89875fa11 Mon Sep 17 00:00:00 2001 From: Tina Zhang Date: Mon, 3 Dec 2018 16:29:23 +0800 Subject: drm/i915/gvt: Fix tiled memory decoding bug on BDW Commit b244ffa15c8b ("drm/i915/gvt: Fix drm_format_mod value for vGPU plane") introduced a regression issue to the tiled memory decoding on BDW. This patch can fix this issue. Here is the issue detail: https://github.com/intel/gvt-linux/issues/61 v1->v2: - Refine the commit message. (Zhenyu) Fixes: b244ffa15c8b("drm/i915/gvt: Fix drm_format_mod value for vGPU plane") Signed-off-by: Tina Zhang Cc: stable@vger.kernel.org # v4.19+ Cc: Zhenyu Wang Signed-off-by: Zhenyu Wang --- drivers/gpu/drm/i915/gvt/fb_decoder.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/gvt/fb_decoder.c b/drivers/gpu/drm/i915/gvt/fb_decoder.c index 481896fb712a..85e6736f0a32 100644 --- a/drivers/gpu/drm/i915/gvt/fb_decoder.c +++ b/drivers/gpu/drm/i915/gvt/fb_decoder.c @@ -235,7 +235,7 @@ int intel_vgpu_decode_primary_plane(struct intel_vgpu *vgpu, plane->bpp = skl_pixel_formats[fmt].bpp; plane->drm_format = skl_pixel_formats[fmt].drm_format; } else { - plane->tiled = !!(val & DISPPLANE_TILED); + plane->tiled = val & DISPPLANE_TILED; fmt = bdw_format_to_drm(val & DISPPLANE_PIXFORMAT_MASK); plane->bpp = bdw_pixel_formats[fmt].bpp; plane->drm_format = bdw_pixel_formats[fmt].drm_format; -- cgit v1.2.3 From a9c2d1e82fc2937baf43c0d400f0c9e87dcf035d Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Mon, 3 Dec 2018 10:14:43 +0100 Subject: fuse: fix fsync on directory Commit ab2257e9941b ("fuse: reduce size of struct fuse_inode") moved parts of fields related to writeback on regular file and to directory caching into a union. However fuse_fsync_common() called from fuse_dir_fsync() touches some writeback related fields, resulting in a crash. Move writeback related parts from fuse_fsync_common() to fuse_fysnc(). Reported-by: Brett Girton Tested-by: Brett Girton Fixes: ab2257e9941b ("fuse: reduce size of struct fuse_inode") Signed-off-by: Miklos Szeredi --- fs/fuse/dir.c | 20 +++++++++++++++++++- fs/fuse/file.c | 43 ++++++++++++++++++++++--------------------- fs/fuse/fuse_i.h | 2 +- 3 files changed, 42 insertions(+), 23 deletions(-) diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 47395b0c3b35..56931dfdcc46 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -1249,7 +1249,25 @@ static int fuse_dir_release(struct inode *inode, struct file *file) static int fuse_dir_fsync(struct file *file, loff_t start, loff_t end, int datasync) { - return fuse_fsync_common(file, start, end, datasync, 1); + struct inode *inode = file->f_mapping->host; + struct fuse_conn *fc = get_fuse_conn(inode); + int err; + + if (is_bad_inode(inode)) + return -EIO; + + if (fc->no_fsyncdir) + return 0; + + inode_lock(inode); + err = fuse_fsync_common(file, start, end, datasync, FUSE_FSYNCDIR); + if (err == -ENOSYS) { + fc->no_fsyncdir = 1; + err = 0; + } + inode_unlock(inode); + + return err; } static long fuse_dir_ioctl(struct file *file, unsigned int cmd, diff --git a/fs/fuse/file.c b/fs/fuse/file.c index b52f9baaa3e7..677c51341e96 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -441,13 +441,30 @@ static int fuse_flush(struct file *file, fl_owner_t id) } int fuse_fsync_common(struct file *file, loff_t start, loff_t end, - int datasync, int isdir) + int datasync, int opcode) { struct inode *inode = file->f_mapping->host; struct fuse_conn *fc = get_fuse_conn(inode); struct fuse_file *ff = file->private_data; FUSE_ARGS(args); struct fuse_fsync_in inarg; + + memset(&inarg, 0, sizeof(inarg)); + inarg.fh = ff->fh; + inarg.fsync_flags = datasync ? 1 : 0; + args.in.h.opcode = opcode; + args.in.h.nodeid = get_node_id(inode); + args.in.numargs = 1; + args.in.args[0].size = sizeof(inarg); + args.in.args[0].value = &inarg; + return fuse_simple_request(fc, &args); +} + +static int fuse_fsync(struct file *file, loff_t start, loff_t end, + int datasync) +{ + struct inode *inode = file->f_mapping->host; + struct fuse_conn *fc = get_fuse_conn(inode); int err; if (is_bad_inode(inode)) @@ -479,34 +496,18 @@ int fuse_fsync_common(struct file *file, loff_t start, loff_t end, if (err) goto out; - if ((!isdir && fc->no_fsync) || (isdir && fc->no_fsyncdir)) + if (fc->no_fsync) goto out; - memset(&inarg, 0, sizeof(inarg)); - inarg.fh = ff->fh; - inarg.fsync_flags = datasync ? 1 : 0; - args.in.h.opcode = isdir ? FUSE_FSYNCDIR : FUSE_FSYNC; - args.in.h.nodeid = get_node_id(inode); - args.in.numargs = 1; - args.in.args[0].size = sizeof(inarg); - args.in.args[0].value = &inarg; - err = fuse_simple_request(fc, &args); + err = fuse_fsync_common(file, start, end, datasync, FUSE_FSYNC); if (err == -ENOSYS) { - if (isdir) - fc->no_fsyncdir = 1; - else - fc->no_fsync = 1; + fc->no_fsync = 1; err = 0; } out: inode_unlock(inode); - return err; -} -static int fuse_fsync(struct file *file, loff_t start, loff_t end, - int datasync) -{ - return fuse_fsync_common(file, start, end, datasync, 0); + return err; } void fuse_read_fill(struct fuse_req *req, struct file *file, loff_t pos, diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index e9f712e81c7d..afe1f231c758 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -828,7 +828,7 @@ void fuse_release_common(struct file *file, int opcode); * Send FSYNC or FSYNCDIR request */ int fuse_fsync_common(struct file *file, loff_t start, loff_t end, - int datasync, int isdir); + int datasync, int opcode); /** * Notify poll wakeup -- cgit v1.2.3 From d233c7dd1682437ba4b430b04766aa6eef9aef67 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Mon, 3 Dec 2018 10:14:43 +0100 Subject: fuse: fix revalidation of attributes for permission check fuse_invalidate_attr() now sets fi->inval_mask instead of fi->i_time, hence we need to check the inval mask in fuse_permission() as well. Signed-off-by: Miklos Szeredi Fixes: 2f1e81965fd0 ("fuse: allow fine grained attr cache invaldation") --- fs/fuse/dir.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 56931dfdcc46..dc4e83d8ace7 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -1119,8 +1119,10 @@ static int fuse_permission(struct inode *inode, int mask) if (fc->default_permissions || ((mask & MAY_EXEC) && S_ISREG(inode->i_mode))) { struct fuse_inode *fi = get_fuse_inode(inode); + u32 perm_mask = STATX_MODE | STATX_UID | STATX_GID; - if (time_before64(fi->i_time, get_jiffies_64())) { + if (perm_mask & READ_ONCE(fi->inval_mask) || + time_before64(fi->i_time, get_jiffies_64())) { refreshed = true; err = fuse_perm_getattr(inode, mask); -- cgit v1.2.3 From e25b6783c7b1bb79103d4617336879423f86b05e Mon Sep 17 00:00:00 2001 From: Stefan Wahren Date: Mon, 3 Dec 2018 19:37:08 +0100 Subject: ARM: dts: bcm2837: Fix polarity of wifi reset GPIOs The commit b1b8f45b3130 ("ARM: dts: bcm2837: Add missing GPIOs of Expander") introduced a wifi power sequence. Unfortunately the polarity of the reset GPIOs were wrong and broke the wifi support on Raspberry Pi 3 B and later in 3 B+. This wasn't discovered before since the power sequence takes only effect in case the relevant MMC driver is compiled as a module. Fixes: b1b8f45b3130 ("ARM: dts: bcm2837: Add missing GPIOs of Expander") Cc: stable@vger.kernel.org Reported-by: Matthias Lueschner Link: https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=911443 Signed-off-by: Stefan Wahren Reviewed-by: Eric Anholt Signed-off-by: Florian Fainelli --- arch/arm/boot/dts/bcm2837-rpi-3-b-plus.dts | 2 +- arch/arm/boot/dts/bcm2837-rpi-3-b.dts | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm/boot/dts/bcm2837-rpi-3-b-plus.dts b/arch/arm/boot/dts/bcm2837-rpi-3-b-plus.dts index 4adb85e66be3..93762244be7f 100644 --- a/arch/arm/boot/dts/bcm2837-rpi-3-b-plus.dts +++ b/arch/arm/boot/dts/bcm2837-rpi-3-b-plus.dts @@ -31,7 +31,7 @@ wifi_pwrseq: wifi-pwrseq { compatible = "mmc-pwrseq-simple"; - reset-gpios = <&expgpio 1 GPIO_ACTIVE_HIGH>; + reset-gpios = <&expgpio 1 GPIO_ACTIVE_LOW>; }; }; diff --git a/arch/arm/boot/dts/bcm2837-rpi-3-b.dts b/arch/arm/boot/dts/bcm2837-rpi-3-b.dts index c318bcbc6ba7..89e6fd547c75 100644 --- a/arch/arm/boot/dts/bcm2837-rpi-3-b.dts +++ b/arch/arm/boot/dts/bcm2837-rpi-3-b.dts @@ -26,7 +26,7 @@ wifi_pwrseq: wifi-pwrseq { compatible = "mmc-pwrseq-simple"; - reset-gpios = <&expgpio 1 GPIO_ACTIVE_HIGH>; + reset-gpios = <&expgpio 1 GPIO_ACTIVE_LOW>; }; }; -- cgit v1.2.3 From 230bce5511cc001cc5b27ffc83b2da188ea43606 Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Wed, 21 Nov 2018 22:38:07 -0500 Subject: media: vsp1: Fix LIF buffer thresholds Commit de2bc45c84f7 ("media: vsp1: Update LIF buffer thresholds") updated the LIF buffer thresholds based on the VSP version, but used the wrong model mask. This resulted in all VSP instances to be treated as a Gen3 VSPD, breaking operation on all Gen2 platforms as well as on H3 ES2.0, M3-N, V3M and V3H. Fix it. Fixes: de2bc45c84f7 ("media: vsp1: Update LIF buffer thresholds") Reported-by: Colin Ian King Signed-off-by: Laurent Pinchart Reviewed-by: Kieran Bingham Signed-off-by: Mauro Carvalho Chehab --- drivers/media/platform/vsp1/vsp1_lif.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/media/platform/vsp1/vsp1_lif.c b/drivers/media/platform/vsp1/vsp1_lif.c index 0b18f0bd7419..8b0a26335d70 100644 --- a/drivers/media/platform/vsp1/vsp1_lif.c +++ b/drivers/media/platform/vsp1/vsp1_lif.c @@ -95,7 +95,7 @@ static void lif_configure_stream(struct vsp1_entity *entity, format = vsp1_entity_get_pad_format(&lif->entity, lif->entity.config, LIF_PAD_SOURCE); - switch (entity->vsp1->version & VI6_IP_VERSION_SOC_MASK) { + switch (entity->vsp1->version & VI6_IP_VERSION_MODEL_MASK) { case VI6_IP_VERSION_MODEL_VSPD_GEN2: case VI6_IP_VERSION_MODEL_VSPD_V2H: hbth = 1536; -- cgit v1.2.3 From 53e9d838275d9a2a5736d788f84814c64cbf94b0 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Mon, 26 Nov 2018 03:10:44 -0500 Subject: media: cedrus: Fix a NULL vs IS_ERR() check The devm_ioremap_resource() function doesn't return NULL pointers, it returns error pointers. Fixes: 50e761516f2b ("media: platform: Add Cedrus VPU decoder driver") Signed-off-by: Dan Carpenter Acked-by: Paul Kocialkowski Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- drivers/staging/media/sunxi/cedrus/cedrus_hw.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/staging/media/sunxi/cedrus/cedrus_hw.c b/drivers/staging/media/sunxi/cedrus/cedrus_hw.c index 32adbcbe6175..07520a2ce179 100644 --- a/drivers/staging/media/sunxi/cedrus/cedrus_hw.c +++ b/drivers/staging/media/sunxi/cedrus/cedrus_hw.c @@ -255,10 +255,10 @@ int cedrus_hw_probe(struct cedrus_dev *dev) res = platform_get_resource(dev->pdev, IORESOURCE_MEM, 0); dev->base = devm_ioremap_resource(dev->dev, res); - if (!dev->base) { + if (IS_ERR(dev->base)) { v4l2_err(&dev->v4l2_dev, "Failed to map registers\n"); - ret = -ENOMEM; + ret = PTR_ERR(dev->base); goto err_sram; } -- cgit v1.2.3 From 04990215dec43c424daff00d1f622167b8aafd1f Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Wed, 28 Nov 2018 03:37:43 -0500 Subject: media: vb2: don't call __vb2_queue_cancel if vb2_start_streaming failed vb2_start_streaming() already rolls back the buffers, so there is no need to call __vb2_queue_cancel(). Especially since __vb2_queue_cancel() does too much, such as zeroing the q->queued_count value, causing vb2 to think that no buffers have been queued. It appears that this call to __vb2_queue_cancel() is a left-over from before commit b3379c6201bb3. Fixes: b3379c6201bb3 ('vb2: only call start_streaming if sufficient buffers are queued') Signed-off-by: Hans Verkuil Cc: # for v4.16 and up Acked-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- drivers/media/common/videobuf2/videobuf2-core.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/media/common/videobuf2/videobuf2-core.c b/drivers/media/common/videobuf2/videobuf2-core.c index 975ff5669f72..e006698807fa 100644 --- a/drivers/media/common/videobuf2/videobuf2-core.c +++ b/drivers/media/common/videobuf2/videobuf2-core.c @@ -1940,10 +1940,8 @@ int vb2_core_streamon(struct vb2_queue *q, unsigned int type) if (ret) return ret; ret = vb2_start_streaming(q); - if (ret) { - __vb2_queue_cancel(q); + if (ret) return ret; - } } q->streaming = 1; -- cgit v1.2.3 From b7ff0b099089f3d4bfd4e30f581ee9d9dc4f8840 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Wed, 28 Nov 2018 03:37:44 -0500 Subject: media: vb2: skip request checks for VIDIOC_PREPARE_BUF VIDIOC_PREPARE_BUF should ignore V4L2_BUF_FLAG_REQUEST_FD since it isn't doing anything with requests. So inform vb2_queue_or_prepare_buf whether it is called from vb2_prepare_buf or vb2_qbuf and just return 0 in the first case. This was found when adding new v4l2-compliance checks. Signed-off-by: Hans Verkuil Acked-by: Sakari Ailus Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- drivers/media/common/videobuf2/videobuf2-v4l2.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/drivers/media/common/videobuf2/videobuf2-v4l2.c b/drivers/media/common/videobuf2/videobuf2-v4l2.c index a17033ab2c22..ce28bc052c3c 100644 --- a/drivers/media/common/videobuf2/videobuf2-v4l2.c +++ b/drivers/media/common/videobuf2/videobuf2-v4l2.c @@ -333,10 +333,10 @@ static int vb2_fill_vb2_v4l2_buffer(struct vb2_buffer *vb, struct v4l2_buffer *b } static int vb2_queue_or_prepare_buf(struct vb2_queue *q, struct media_device *mdev, - struct v4l2_buffer *b, - const char *opname, + struct v4l2_buffer *b, bool is_prepare, struct media_request **p_req) { + const char *opname = is_prepare ? "prepare_buf" : "qbuf"; struct media_request *req; struct vb2_v4l2_buffer *vbuf; struct vb2_buffer *vb; @@ -378,6 +378,9 @@ static int vb2_queue_or_prepare_buf(struct vb2_queue *q, struct media_device *md return ret; } + if (is_prepare) + return 0; + if (!(b->flags & V4L2_BUF_FLAG_REQUEST_FD)) { if (q->uses_requests) { dprintk(1, "%s: queue uses requests\n", opname); @@ -657,7 +660,7 @@ int vb2_prepare_buf(struct vb2_queue *q, struct media_device *mdev, if (b->flags & V4L2_BUF_FLAG_REQUEST_FD) return -EINVAL; - ret = vb2_queue_or_prepare_buf(q, mdev, b, "prepare_buf", NULL); + ret = vb2_queue_or_prepare_buf(q, mdev, b, true, NULL); return ret ? ret : vb2_core_prepare_buf(q, b->index, b); } @@ -729,7 +732,7 @@ int vb2_qbuf(struct vb2_queue *q, struct media_device *mdev, return -EBUSY; } - ret = vb2_queue_or_prepare_buf(q, mdev, b, "qbuf", &req); + ret = vb2_queue_or_prepare_buf(q, mdev, b, false, &req); if (ret) return ret; ret = vb2_core_qbuf(q, b->index, b, req); -- cgit v1.2.3 From 6093d3002eabd7c2913d97f1d1f4ce34b072acf9 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Wed, 28 Nov 2018 03:37:45 -0500 Subject: media: vb2: keep a reference to the request until dqbuf When vb2_buffer_done is called the buffer is unbound from the request and put. The media_request_object_put also 'put's the request reference. If the application has already closed the request fd, then that means that the request reference at that point goes to 0 and the whole request is released. This means that the control handler associated with the request is also freed and that causes this kernel oops: [174705.995401] BUG: sleeping function called from invalid context at kernel/locking/mutex.c:908 [174705.995411] in_atomic(): 1, irqs_disabled(): 1, pid: 28071, name: vivid-000-vid-o [174705.995416] 2 locks held by vivid-000-vid-o/28071: [174705.995420] #0: 000000001ea3a232 (&dev->mutex#3){....}, at: vivid_thread_vid_out+0x3f5/0x550 [vivid] [174705.995447] #1: 00000000e30a0d1e (&(&q->done_lock)->rlock){....}, at: vb2_buffer_done+0x92/0x1d0 [videobuf2_common] [174705.995460] Preemption disabled at: [174705.995461] [<0000000000000000>] (null) [174705.995472] CPU: 11 PID: 28071 Comm: vivid-000-vid-o Tainted: G W 4.20.0-rc1-test-no #88 [174705.995476] Hardware name: VMware, Inc. VMware Virtual Platform/440BX Desktop Reference Platform, BIOS 6.00 05/19/2017 [174705.995481] Call Trace: [174705.995500] dump_stack+0x46/0x60 [174705.995512] ___might_sleep.cold.79+0xe1/0xf1 [174705.995523] __mutex_lock+0x50/0x8f0 [174705.995531] ? find_held_lock+0x2d/0x90 [174705.995536] ? find_held_lock+0x2d/0x90 [174705.995542] ? find_held_lock+0x2d/0x90 [174705.995564] ? v4l2_ctrl_handler_free.part.13+0x44/0x1d0 [videodev] [174705.995576] v4l2_ctrl_handler_free.part.13+0x44/0x1d0 [videodev] [174705.995590] v4l2_ctrl_request_release+0x1c/0x30 [videodev] [174705.995600] media_request_clean+0x64/0xe0 [media] [174705.995609] media_request_release+0x19/0x40 [media] [174705.995617] vb2_buffer_done+0xef/0x1d0 [videobuf2_common] [174705.995630] vivid_thread_vid_out+0x2c1/0x550 [vivid] [174705.995645] ? vivid_stop_generating_vid_cap+0x1c0/0x1c0 [vivid] [174705.995653] kthread+0x113/0x130 [174705.995659] ? kthread_park+0x80/0x80 [174705.995667] ret_from_fork+0x35/0x40 The vb2_buffer_done function can be called from interrupt context, so anything that sleeps is not allowed. The solution is to increment the request refcount when the buffer is queued and decrement it when the buffer is dequeued. Releasing the request is fine if that happens from VIDIOC_DQBUF. Signed-off-by: Hans Verkuil Acked-by: Sakari Ailus Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- drivers/media/common/videobuf2/videobuf2-core.c | 38 +++++++++++++++++++++---- include/media/videobuf2-core.h | 2 ++ 2 files changed, 35 insertions(+), 5 deletions(-) diff --git a/drivers/media/common/videobuf2/videobuf2-core.c b/drivers/media/common/videobuf2/videobuf2-core.c index e006698807fa..a6dfb0860558 100644 --- a/drivers/media/common/videobuf2/videobuf2-core.c +++ b/drivers/media/common/videobuf2/videobuf2-core.c @@ -1359,8 +1359,12 @@ static void vb2_req_release(struct media_request_object *obj) { struct vb2_buffer *vb = container_of(obj, struct vb2_buffer, req_obj); - if (vb->state == VB2_BUF_STATE_IN_REQUEST) + if (vb->state == VB2_BUF_STATE_IN_REQUEST) { vb->state = VB2_BUF_STATE_DEQUEUED; + if (vb->request) + media_request_put(vb->request); + vb->request = NULL; + } } static const struct media_request_object_ops vb2_core_req_ops = { @@ -1528,6 +1532,18 @@ int vb2_core_qbuf(struct vb2_queue *q, unsigned int index, void *pb, return ret; vb->state = VB2_BUF_STATE_IN_REQUEST; + + /* + * Increment the refcount and store the request. + * The request refcount is decremented again when the + * buffer is dequeued. This is to prevent vb2_buffer_done() + * from freeing the request from interrupt context, which can + * happen if the application closed the request fd after + * queueing the request. + */ + media_request_get(req); + vb->request = req; + /* Fill buffer information for the userspace */ if (pb) { call_void_bufop(q, copy_timestamp, vb, pb); @@ -1749,10 +1765,6 @@ static void __vb2_dqbuf(struct vb2_buffer *vb) call_void_memop(vb, unmap_dmabuf, vb->planes[i].mem_priv); vb->planes[i].dbuf_mapped = 0; } - if (vb->req_obj.req) { - media_request_object_unbind(&vb->req_obj); - media_request_object_put(&vb->req_obj); - } call_void_bufop(q, init_buffer, vb); } @@ -1797,6 +1809,14 @@ int vb2_core_dqbuf(struct vb2_queue *q, unsigned int *pindex, void *pb, /* go back to dequeued state */ __vb2_dqbuf(vb); + if (WARN_ON(vb->req_obj.req)) { + media_request_object_unbind(&vb->req_obj); + media_request_object_put(&vb->req_obj); + } + if (vb->request) + media_request_put(vb->request); + vb->request = NULL; + dprintk(2, "dqbuf of buffer %d, with state %d\n", vb->index, vb->state); @@ -1903,6 +1923,14 @@ static void __vb2_queue_cancel(struct vb2_queue *q) vb->prepared = false; } __vb2_dqbuf(vb); + + if (vb->req_obj.req) { + media_request_object_unbind(&vb->req_obj); + media_request_object_put(&vb->req_obj); + } + if (vb->request) + media_request_put(vb->request); + vb->request = NULL; } } diff --git a/include/media/videobuf2-core.h b/include/media/videobuf2-core.h index e86981d615ae..4a737b2c610b 100644 --- a/include/media/videobuf2-core.h +++ b/include/media/videobuf2-core.h @@ -239,6 +239,7 @@ struct vb2_queue; * @num_planes: number of planes in the buffer * on an internal driver queue. * @timestamp: frame timestamp in ns. + * @request: the request this buffer is associated with. * @req_obj: used to bind this buffer to a request. This * request object has a refcount. */ @@ -249,6 +250,7 @@ struct vb2_buffer { unsigned int memory; unsigned int num_planes; u64 timestamp; + struct media_request *request; struct media_request_object req_obj; /* private: internal use only -- cgit v1.2.3 From dde6bdcc975983c219ffe9b8f3a2942df0b7937d Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Wed, 28 Nov 2018 03:37:46 -0500 Subject: media: vb2: don't unbind/put the object when going to state QUEUED When a buffer is returned to state QUEUED (that happens when start_streaming fails), then do not unbind and put the object from the request. Nothing has changed yet, so just keep it as is. Signed-off-by: Hans Verkuil Acked-by: Sakari Ailus Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- drivers/media/common/videobuf2/videobuf2-core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/media/common/videobuf2/videobuf2-core.c b/drivers/media/common/videobuf2/videobuf2-core.c index a6dfb0860558..8ff8722cb6b1 100644 --- a/drivers/media/common/videobuf2/videobuf2-core.c +++ b/drivers/media/common/videobuf2/videobuf2-core.c @@ -947,7 +947,7 @@ void vb2_buffer_done(struct vb2_buffer *vb, enum vb2_buffer_state state) } atomic_dec(&q->owned_by_drv_count); - if (vb->req_obj.req) { + if (state != VB2_BUF_STATE_QUEUED && vb->req_obj.req) { /* This is not supported at the moment */ WARN_ON(state == VB2_BUF_STATE_REQUEUEING); media_request_object_unbind(&vb->req_obj); -- cgit v1.2.3 From e714c92f42aeed6052a287b8ccf5a519e42bab15 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Wed, 28 Nov 2018 03:37:47 -0500 Subject: media: vivid: drop v4l2_ctrl_request_complete() from start_streaming If start_streaming() fails and all queued buffers are returned to vb2, then do not call v4l2_ctrl_request_complete(). Nothing happened to the request and the state should remain as it was before start_streaming was called. Signed-off-by: Hans Verkuil Acked-by: Sakari Ailus Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- drivers/media/platform/vivid/vivid-sdr-cap.c | 2 -- drivers/media/platform/vivid/vivid-vbi-cap.c | 2 -- drivers/media/platform/vivid/vivid-vbi-out.c | 2 -- drivers/media/platform/vivid/vivid-vid-cap.c | 2 -- drivers/media/platform/vivid/vivid-vid-out.c | 2 -- 5 files changed, 10 deletions(-) diff --git a/drivers/media/platform/vivid/vivid-sdr-cap.c b/drivers/media/platform/vivid/vivid-sdr-cap.c index dcdc80e272c2..9acc709b0740 100644 --- a/drivers/media/platform/vivid/vivid-sdr-cap.c +++ b/drivers/media/platform/vivid/vivid-sdr-cap.c @@ -276,8 +276,6 @@ static int sdr_cap_start_streaming(struct vb2_queue *vq, unsigned count) list_for_each_entry_safe(buf, tmp, &dev->sdr_cap_active, list) { list_del(&buf->list); - v4l2_ctrl_request_complete(buf->vb.vb2_buf.req_obj.req, - &dev->ctrl_hdl_sdr_cap); vb2_buffer_done(&buf->vb.vb2_buf, VB2_BUF_STATE_QUEUED); } diff --git a/drivers/media/platform/vivid/vivid-vbi-cap.c b/drivers/media/platform/vivid/vivid-vbi-cap.c index 903cebeb5ce5..d666271bdaed 100644 --- a/drivers/media/platform/vivid/vivid-vbi-cap.c +++ b/drivers/media/platform/vivid/vivid-vbi-cap.c @@ -204,8 +204,6 @@ static int vbi_cap_start_streaming(struct vb2_queue *vq, unsigned count) list_for_each_entry_safe(buf, tmp, &dev->vbi_cap_active, list) { list_del(&buf->list); - v4l2_ctrl_request_complete(buf->vb.vb2_buf.req_obj.req, - &dev->ctrl_hdl_vbi_cap); vb2_buffer_done(&buf->vb.vb2_buf, VB2_BUF_STATE_QUEUED); } diff --git a/drivers/media/platform/vivid/vivid-vbi-out.c b/drivers/media/platform/vivid/vivid-vbi-out.c index 9357c07e30d6..cd56476902a2 100644 --- a/drivers/media/platform/vivid/vivid-vbi-out.c +++ b/drivers/media/platform/vivid/vivid-vbi-out.c @@ -96,8 +96,6 @@ static int vbi_out_start_streaming(struct vb2_queue *vq, unsigned count) list_for_each_entry_safe(buf, tmp, &dev->vbi_out_active, list) { list_del(&buf->list); - v4l2_ctrl_request_complete(buf->vb.vb2_buf.req_obj.req, - &dev->ctrl_hdl_vbi_out); vb2_buffer_done(&buf->vb.vb2_buf, VB2_BUF_STATE_QUEUED); } diff --git a/drivers/media/platform/vivid/vivid-vid-cap.c b/drivers/media/platform/vivid/vivid-vid-cap.c index 9c8e8be81ce3..673772cd17d6 100644 --- a/drivers/media/platform/vivid/vivid-vid-cap.c +++ b/drivers/media/platform/vivid/vivid-vid-cap.c @@ -243,8 +243,6 @@ static int vid_cap_start_streaming(struct vb2_queue *vq, unsigned count) list_for_each_entry_safe(buf, tmp, &dev->vid_cap_active, list) { list_del(&buf->list); - v4l2_ctrl_request_complete(buf->vb.vb2_buf.req_obj.req, - &dev->ctrl_hdl_vid_cap); vb2_buffer_done(&buf->vb.vb2_buf, VB2_BUF_STATE_QUEUED); } diff --git a/drivers/media/platform/vivid/vivid-vid-out.c b/drivers/media/platform/vivid/vivid-vid-out.c index aaf13f03d5d4..628eae154ee7 100644 --- a/drivers/media/platform/vivid/vivid-vid-out.c +++ b/drivers/media/platform/vivid/vivid-vid-out.c @@ -162,8 +162,6 @@ static int vid_out_start_streaming(struct vb2_queue *vq, unsigned count) list_for_each_entry_safe(buf, tmp, &dev->vid_out_active, list) { list_del(&buf->list); - v4l2_ctrl_request_complete(buf->vb.vb2_buf.req_obj.req, - &dev->ctrl_hdl_vid_out); vb2_buffer_done(&buf->vb.vb2_buf, VB2_BUF_STATE_QUEUED); } -- cgit v1.2.3 From daa3fc4454b21ac883152d07b4778bc4f83ec716 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Wed, 28 Nov 2018 15:52:42 -0500 Subject: media: vicodec: set state resolution from raw format The state structure contains the resolution expected by the decoder and encoder. For an encoder that resolution should be taken from the OUTPUT format, and for a decoder from the CAPTURE format. If the wrong format is picked, a buffer overrun can occur if there is a mismatch between the CAPTURE and OUTPUT formats. The real fix would be to correctly implement the stateful codec specification, but that will take more time. For now just prevent the buffer overrun. Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- drivers/media/platform/vicodec/vicodec-core.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/drivers/media/platform/vicodec/vicodec-core.c b/drivers/media/platform/vicodec/vicodec-core.c index 013cdebecbc4..13fb69c58967 100644 --- a/drivers/media/platform/vicodec/vicodec-core.c +++ b/drivers/media/platform/vicodec/vicodec-core.c @@ -997,11 +997,18 @@ static int vicodec_start_streaming(struct vb2_queue *q, q_data->sequence = 0; - if (!V4L2_TYPE_IS_OUTPUT(q->type)) + if (!V4L2_TYPE_IS_OUTPUT(q->type)) { + if (!ctx->is_enc) { + state->width = q_data->width; + state->height = q_data->height; + } return 0; + } - state->width = q_data->width; - state->height = q_data->height; + if (ctx->is_enc) { + state->width = q_data->width; + state->height = q_data->height; + } state->ref_frame.width = state->ref_frame.height = 0; state->ref_frame.luma = kvmalloc(size + 2 * size / chroma_div, GFP_KERNEL); -- cgit v1.2.3 From 7bb64d55fd0e4bb09863ae1519ec8024e1279b2b Mon Sep 17 00:00:00 2001 From: Matthias Brugger Date: Tue, 16 Oct 2018 16:57:58 +0200 Subject: MAINTAINERS: mediatek: Update SoC entry Add IRC channel and URL of the wiki. Also add soc drivers folder and regex to catch more mediatek components. Signed-off-by: Matthias Brugger Signed-off-by: Olof Johansson --- MAINTAINERS | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index 6682420421c1..1306254bf078 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1738,13 +1738,17 @@ ARM/Mediatek SoC support M: Matthias Brugger L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) L: linux-mediatek@lists.infradead.org (moderated for non-subscribers) +W: https://mtk.bcnfs.org/ +C: irc://chat.freenode.net/linux-mediatek S: Maintained F: arch/arm/boot/dts/mt6* F: arch/arm/boot/dts/mt7* F: arch/arm/boot/dts/mt8* F: arch/arm/mach-mediatek/ F: arch/arm64/boot/dts/mediatek/ +F: drivers/soc/mediatek/ N: mtk +N: mt[678] K: mediatek ARM/Mediatek USB3 PHY DRIVER -- cgit v1.2.3 From 76f4e2c3b6a560cdd7a75b87df543e04d05a9e5f Mon Sep 17 00:00:00 2001 From: Lubomir Rintel Date: Sun, 2 Dec 2018 12:12:24 +0100 Subject: ARM: mmp/mmp2: fix cpu_is_mmp2() on mmp2-dt cpu_is_mmp2() was equivalent to cpu_is_pj4(), wouldn't be correct for multiplatform kernels. Fix it by also considering mmp_chip_id, as is done for cpu_is_pxa168() and cpu_is_pxa910() above. Moreover, it is only available with CONFIG_CPU_MMP2 and thus doesn't work on DT-based MMP2 machines. Enable it on CONFIG_MACH_MMP2_DT too. Note: CONFIG_CPU_MMP2 is only used for machines that use board files instead of DT. It should perhaps be renamed. I'm not doing it now, because I don't have a better idea. Signed-off-by: Lubomir Rintel Acked-by: Arnd Bergmann Cc: stable@vger.kernel.org Signed-off-by: Olof Johansson --- arch/arm/mach-mmp/cputype.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/arch/arm/mach-mmp/cputype.h b/arch/arm/mach-mmp/cputype.h index 446edaeb78a7..a96abcf521b4 100644 --- a/arch/arm/mach-mmp/cputype.h +++ b/arch/arm/mach-mmp/cputype.h @@ -44,10 +44,12 @@ static inline int cpu_is_pxa910(void) #define cpu_is_pxa910() (0) #endif -#ifdef CONFIG_CPU_MMP2 +#if defined(CONFIG_CPU_MMP2) || defined(CONFIG_MACH_MMP2_DT) static inline int cpu_is_mmp2(void) { - return (((read_cpuid_id() >> 8) & 0xff) == 0x58); + return (((read_cpuid_id() >> 8) & 0xff) == 0x58) && + (((mmp_chip_id & 0xfff) == 0x410) || + ((mmp_chip_id & 0xfff) == 0x610)); } #else #define cpu_is_mmp2() (0) -- cgit v1.2.3 From f6936d029c4a14ce873bbb423bbc518aa1b4def2 Mon Sep 17 00:00:00 2001 From: Lubomir Rintel Date: Sun, 2 Dec 2018 12:14:28 +0100 Subject: MAINTAINERS: update entry for MMP platform Move Eric Miao and Haojian Zhuang over to CREDITS, since they're AWOL for some time already. The git trees have gone away too. I'm adding myself as a reviewer. I'd like to be Cc'd on patches and will be able to test them, but I don't possess a data sheet thus there might be things I'll be unable to review. Hence the Odd-Fixes status. Signed-off-by: Lubomir Rintel Signed-off-by: Olof Johansson --- CREDITS | 8 ++++++++ MAINTAINERS | 7 ++----- 2 files changed, 10 insertions(+), 5 deletions(-) diff --git a/CREDITS b/CREDITS index c9273393fe14..7d397ee67524 100644 --- a/CREDITS +++ b/CREDITS @@ -2541,6 +2541,10 @@ S: Ormond S: Victoria 3163 S: Australia +N: Eric Miao +E: eric.y.miao@gmail.com +D: MMP support + N: Pauline Middelink E: middelin@polyware.nl D: General low-level bug fixes, /proc fixes, identd support @@ -4115,6 +4119,10 @@ S: 1507 145th Place SE #B5 S: Bellevue, Washington 98007 S: USA +N: Haojian Zhuang +E: haojian.zhuang@gmail.com +D: MMP support + N: Richard Zidlicky E: rz@linux-m68k.org, rdzidlic@geocities.com W: http://www.geocities.com/rdzidlic diff --git a/MAINTAINERS b/MAINTAINERS index 1306254bf078..f063443a3e3a 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -10002,12 +10002,9 @@ S: Odd Fixes F: drivers/media/radio/radio-miropcm20* MMP SUPPORT -M: Eric Miao -M: Haojian Zhuang +R: Lubomir Rintel L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) -T: git git://github.com/hzhuang1/linux.git -T: git git://git.linaro.org/people/ycmiao/pxa-linux.git -S: Maintained +S: Odd Fixes F: arch/arm/boot/dts/mmp* F: arch/arm/mach-mmp/ -- cgit v1.2.3 From f3b2f758ec1e6cdb13c925647cbd8ad4938b78fb Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Mon, 3 Dec 2018 13:12:48 -0600 Subject: ARM: dts: realview: Fix some more duplicate regulator nodes There's a bug in dtc in checking for duplicate node names when there's another section (e.g. "/ { };"). In this case, skeleton.dtsi provides another section. Upon removal of skeleton.dtsi, the dtb fails to build due to a duplicate node 'fixedregulator@0'. As both nodes were pretty much the same 3.3V fixed regulator, it hasn't really mattered. Fix this by renaming the nodes to something unique. In the process, drop the unit-address which shouldn't be present wtihout reg property. Signed-off-by: Rob Herring Reviewed-by: Linus Walleij Signed-off-by: Olof Johansson --- arch/arm/boot/dts/arm-realview-pb1176.dts | 4 ++-- arch/arm/boot/dts/arm-realview-pb11mp.dts | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/arm/boot/dts/arm-realview-pb1176.dts b/arch/arm/boot/dts/arm-realview-pb1176.dts index f2a1d25eb6cf..83e0fbc4a1a1 100644 --- a/arch/arm/boot/dts/arm-realview-pb1176.dts +++ b/arch/arm/boot/dts/arm-realview-pb1176.dts @@ -45,7 +45,7 @@ }; /* The voltage to the MMC card is hardwired at 3.3V */ - vmmc: fixedregulator@0 { + vmmc: regulator-vmmc { compatible = "regulator-fixed"; regulator-name = "vmmc"; regulator-min-microvolt = <3300000>; @@ -53,7 +53,7 @@ regulator-boot-on; }; - veth: fixedregulator@0 { + veth: regulator-veth { compatible = "regulator-fixed"; regulator-name = "veth"; regulator-min-microvolt = <3300000>; diff --git a/arch/arm/boot/dts/arm-realview-pb11mp.dts b/arch/arm/boot/dts/arm-realview-pb11mp.dts index 7f9cbdf33a51..2f6aa24a0b67 100644 --- a/arch/arm/boot/dts/arm-realview-pb11mp.dts +++ b/arch/arm/boot/dts/arm-realview-pb11mp.dts @@ -145,7 +145,7 @@ }; /* The voltage to the MMC card is hardwired at 3.3V */ - vmmc: fixedregulator@0 { + vmmc: regulator-vmmc { compatible = "regulator-fixed"; regulator-name = "vmmc"; regulator-min-microvolt = <3300000>; @@ -153,7 +153,7 @@ regulator-boot-on; }; - veth: fixedregulator@0 { + veth: regulator-veth { compatible = "regulator-fixed"; regulator-name = "veth"; regulator-min-microvolt = <3300000>; -- cgit v1.2.3 From 90b2620e6a8aa08c40cc78d61603e0acd853c33a Mon Sep 17 00:00:00 2001 From: Michael J. Ruhl Date: Wed, 28 Nov 2018 06:44:36 -0800 Subject: IB/hfi1: Fix a latency issue for small messages A recent performance enhancement introduced a latency issue in the HFI message path. The new algorithm removed a forced call send for PIO messages and added a forced schedule event for messages larger than the MTU. For PIO, the schedule path can introduce thrashing that can significantly impact the throughput for small messages. If a message size is within the PIO threshold, always take the send path. Fixes: 0b79b27748cb ("IB/{hfi1, qib, rdmavt}: Schedule multi RC/UC packets instead of posting") Reviewed-by: Mike Marciniszyn Signed-off-by: Michael J. Ruhl Signed-off-by: Dennis Dalessandro Signed-off-by: Doug Ledford --- drivers/infiniband/hw/hfi1/qp.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/infiniband/hw/hfi1/qp.c b/drivers/infiniband/hw/hfi1/qp.c index 6f3bc4dab858..1a016248039f 100644 --- a/drivers/infiniband/hw/hfi1/qp.c +++ b/drivers/infiniband/hw/hfi1/qp.c @@ -340,6 +340,13 @@ int hfi1_setup_wqe(struct rvt_qp *qp, struct rvt_swqe *wqe, bool *call_send) default: break; } + + /* + * System latency between send and schedule is large enough that + * forcing call_send to true for piothreshold packets is necessary. + */ + if (wqe->length <= piothreshold) + *call_send = true; return 0; } -- cgit v1.2.3 From 36d842194a57f1b21fbc6a6875f2fa2f9a7f8679 Mon Sep 17 00:00:00 2001 From: Piotr Stankiewicz Date: Wed, 28 Nov 2018 06:44:46 -0800 Subject: IB/hfi1: Fix an out-of-bounds access in get_hw_stats When running with KASAN, the following trace is produced: [ 62.535888] ================================================================== [ 62.544930] BUG: KASAN: slab-out-of-bounds in gut_hw_stats+0x122/0x230 [hfi1] [ 62.553856] Write of size 8 at addr ffff88080e8d6330 by task kworker/0:1/14 [ 62.565333] CPU: 0 PID: 14 Comm: kworker/0:1 Not tainted 4.19.0-test-build-kasan+ #8 [ 62.575087] Hardware name: Intel Corporation S2600KPR/S2600KPR, BIOS SE5C610.86B.01.01.0019.101220160604 10/12/2016 [ 62.587951] Workqueue: events work_for_cpu_fn [ 62.594050] Call Trace: [ 62.598023] dump_stack+0xc6/0x14c [ 62.603089] ? dump_stack_print_info.cold.1+0x2f/0x2f [ 62.610041] ? kmsg_dump_rewind_nolock+0x59/0x59 [ 62.616615] ? get_hw_stats+0x122/0x230 [hfi1] [ 62.622985] print_address_description+0x6c/0x23c [ 62.629744] ? get_hw_stats+0x122/0x230 [hfi1] [ 62.636108] kasan_report.cold.6+0x241/0x308 [ 62.642365] get_hw_stats+0x122/0x230 [hfi1] [ 62.648703] ? hfi1_alloc_rn+0x40/0x40 [hfi1] [ 62.655088] ? __kmalloc+0x110/0x240 [ 62.660695] ? hfi1_alloc_rn+0x40/0x40 [hfi1] [ 62.667142] setup_hw_stats+0xd8/0x430 [ib_core] [ 62.673972] ? show_hfi+0x50/0x50 [hfi1] [ 62.680026] ib_device_register_sysfs+0x165/0x180 [ib_core] [ 62.687995] ib_register_device+0x5a2/0xa10 [ib_core] [ 62.695340] ? show_hfi+0x50/0x50 [hfi1] [ 62.701421] ? ib_unregister_device+0x2e0/0x2e0 [ib_core] [ 62.709222] ? __vmalloc_node_range+0x2d0/0x380 [ 62.716131] ? rvt_driver_mr_init+0x11f/0x2d0 [rdmavt] [ 62.723735] ? vmalloc_node+0x5c/0x70 [ 62.729697] ? rvt_driver_mr_init+0x11f/0x2d0 [rdmavt] [ 62.737347] ? rvt_driver_mr_init+0x1f5/0x2d0 [rdmavt] [ 62.744998] ? __rvt_alloc_mr+0x110/0x110 [rdmavt] [ 62.752315] ? rvt_rc_error+0x140/0x140 [rdmavt] [ 62.759434] ? rvt_vma_open+0x30/0x30 [rdmavt] [ 62.766364] ? mutex_unlock+0x1d/0x40 [ 62.772445] ? kmem_cache_create_usercopy+0x15d/0x230 [ 62.780115] rvt_register_device+0x1f6/0x360 [rdmavt] [ 62.787823] ? rvt_get_port_immutable+0x180/0x180 [rdmavt] [ 62.796058] ? __get_txreq+0x400/0x400 [hfi1] [ 62.802969] ? memcpy+0x34/0x50 [ 62.808611] hfi1_register_ib_device+0xde6/0xeb0 [hfi1] [ 62.816601] ? hfi1_get_npkeys+0x10/0x10 [hfi1] [ 62.823760] ? hfi1_init+0x89f/0x9a0 [hfi1] [ 62.830469] ? hfi1_setup_eagerbufs+0xad0/0xad0 [hfi1] [ 62.838204] ? pcie_capability_clear_and_set_word+0xcd/0xe0 [ 62.846429] ? pcie_capability_read_word+0xd0/0xd0 [ 62.853791] ? hfi1_pcie_init+0x187/0x4b0 [hfi1] [ 62.860958] init_one+0x67f/0xae0 [hfi1] [ 62.867301] ? hfi1_init+0x9a0/0x9a0 [hfi1] [ 62.873876] ? wait_woken+0x130/0x130 [ 62.879860] ? read_word_at_a_time+0xe/0x20 [ 62.886329] ? strscpy+0x14b/0x280 [ 62.891998] ? hfi1_init+0x9a0/0x9a0 [hfi1] [ 62.898405] local_pci_probe+0x70/0xd0 [ 62.904295] ? pci_device_shutdown+0x90/0x90 [ 62.910833] work_for_cpu_fn+0x29/0x40 [ 62.916750] process_one_work+0x584/0x960 [ 62.922974] ? rcu_work_rcufn+0x40/0x40 [ 62.928991] ? __schedule+0x396/0xdc0 [ 62.934806] ? __sched_text_start+0x8/0x8 [ 62.941020] ? pick_next_task_fair+0x68b/0xc60 [ 62.947674] ? run_rebalance_domains+0x260/0x260 [ 62.954471] ? __list_add_valid+0x29/0xa0 [ 62.960607] ? move_linked_works+0x1c7/0x230 [ 62.967077] ? trace_event_raw_event_workqueue_execute_start+0x140/0x140 [ 62.976248] ? mutex_lock+0xa6/0x100 [ 62.982029] ? __mutex_lock_slowpath+0x10/0x10 [ 62.988795] ? __switch_to+0x37a/0x710 [ 62.994731] worker_thread+0x62e/0x9d0 [ 63.000602] ? max_active_store+0xf0/0xf0 [ 63.006828] ? __switch_to_asm+0x40/0x70 [ 63.012932] ? __switch_to_asm+0x34/0x70 [ 63.019013] ? __switch_to_asm+0x40/0x70 [ 63.025042] ? __switch_to_asm+0x34/0x70 [ 63.031030] ? __switch_to_asm+0x40/0x70 [ 63.037006] ? __schedule+0x396/0xdc0 [ 63.042660] ? kmem_cache_alloc_trace+0xf3/0x1f0 [ 63.049323] ? kthread+0x59/0x1d0 [ 63.054594] ? ret_from_fork+0x35/0x40 [ 63.060257] ? __sched_text_start+0x8/0x8 [ 63.066212] ? schedule+0xcf/0x250 [ 63.071529] ? __wake_up_common+0x110/0x350 [ 63.077794] ? __schedule+0xdc0/0xdc0 [ 63.083348] ? wait_woken+0x130/0x130 [ 63.088963] ? finish_task_switch+0x1f1/0x520 [ 63.095258] ? kasan_unpoison_shadow+0x30/0x40 [ 63.101792] ? __init_waitqueue_head+0xa0/0xd0 [ 63.108183] ? replenish_dl_entity.cold.60+0x18/0x18 [ 63.115151] ? _raw_spin_lock_irqsave+0x25/0x50 [ 63.121754] ? max_active_store+0xf0/0xf0 [ 63.127753] kthread+0x1ae/0x1d0 [ 63.132894] ? kthread_bind+0x30/0x30 [ 63.138422] ret_from_fork+0x35/0x40 [ 63.146973] Allocated by task 14: [ 63.152077] kasan_kmalloc+0xbf/0xe0 [ 63.157471] __kmalloc+0x110/0x240 [ 63.162804] init_cntrs+0x34d/0xdf0 [hfi1] [ 63.168883] hfi1_init_dd+0x29a3/0x2f90 [hfi1] [ 63.175244] init_one+0x551/0xae0 [hfi1] [ 63.181065] local_pci_probe+0x70/0xd0 [ 63.186759] work_for_cpu_fn+0x29/0x40 [ 63.192310] process_one_work+0x584/0x960 [ 63.198163] worker_thread+0x62e/0x9d0 [ 63.203843] kthread+0x1ae/0x1d0 [ 63.208874] ret_from_fork+0x35/0x40 [ 63.217203] Freed by task 1: [ 63.221844] __kasan_slab_free+0x12e/0x180 [ 63.227844] kfree+0x92/0x1a0 [ 63.232570] single_release+0x3a/0x60 [ 63.238024] __fput+0x1d9/0x480 [ 63.242911] task_work_run+0x139/0x190 [ 63.248440] exit_to_usermode_loop+0x191/0x1a0 [ 63.254814] do_syscall_64+0x301/0x330 [ 63.260283] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 63.270199] The buggy address belongs to the object at ffff88080e8d5500 which belongs to the cache kmalloc-4096 of size 4096 [ 63.287247] The buggy address is located 3632 bytes inside of 4096-byte region [ffff88080e8d5500, ffff88080e8d6500) [ 63.303564] The buggy address belongs to the page: [ 63.310447] page:ffffea00203a3400 count:1 mapcount:0 mapping:ffff88081380e840 index:0x0 compound_mapcount: 0 [ 63.323102] flags: 0x2fffff80008100(slab|head) [ 63.329775] raw: 002fffff80008100 0000000000000000 0000000100000001 ffff88081380e840 [ 63.340175] raw: 0000000000000000 0000000000070007 00000001ffffffff 0000000000000000 [ 63.350564] page dumped because: kasan: bad access detected [ 63.361974] Memory state around the buggy address: [ 63.369137] ffff88080e8d6200: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 63.379082] ffff88080e8d6280: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 63.389032] >ffff88080e8d6300: 00 00 00 00 00 00 fc fc fc fc fc fc fc fc fc fc [ 63.398944] ^ [ 63.406141] ffff88080e8d6380: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 63.416109] ffff88080e8d6400: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 63.426099] ================================================================== The trace happens because get_hw_stats() assumes there is room in the memory allocated in init_cntrs() to accommodate the driver counters. Unfortunately, that routine only allocated space for the device counters. Fix by insuring the allocation has room for the additional driver counters. Cc: # v4.14+ Fixes: b7481944b06e9 ("IB/hfi1: Show statistics counters under IB stats interface") Reviewed-by: Mike Marciniczyn Reviewed-by: Mike Ruhl Signed-off-by: Piotr Stankiewicz Signed-off-by: Dennis Dalessandro Signed-off-by: Doug Ledford --- drivers/infiniband/hw/hfi1/chip.c | 3 ++- drivers/infiniband/hw/hfi1/hfi.h | 2 ++ drivers/infiniband/hw/hfi1/verbs.c | 2 +- 3 files changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/infiniband/hw/hfi1/chip.c b/drivers/infiniband/hw/hfi1/chip.c index 9b20479dc710..7e6d70936c63 100644 --- a/drivers/infiniband/hw/hfi1/chip.c +++ b/drivers/infiniband/hw/hfi1/chip.c @@ -12500,7 +12500,8 @@ static int init_cntrs(struct hfi1_devdata *dd) } /* allocate space for the counter values */ - dd->cntrs = kcalloc(dd->ndevcntrs, sizeof(u64), GFP_KERNEL); + dd->cntrs = kcalloc(dd->ndevcntrs + num_driver_cntrs, sizeof(u64), + GFP_KERNEL); if (!dd->cntrs) goto bail; diff --git a/drivers/infiniband/hw/hfi1/hfi.h b/drivers/infiniband/hw/hfi1/hfi.h index 1401b6ea4a28..2b882347d0c2 100644 --- a/drivers/infiniband/hw/hfi1/hfi.h +++ b/drivers/infiniband/hw/hfi1/hfi.h @@ -155,6 +155,8 @@ struct hfi1_ib_stats { extern struct hfi1_ib_stats hfi1_stats; extern const struct pci_error_handlers hfi1_pci_err_handler; +extern int num_driver_cntrs; + /* * First-cut criterion for "device is active" is * two thousand dwords combined Tx, Rx traffic per diff --git a/drivers/infiniband/hw/hfi1/verbs.c b/drivers/infiniband/hw/hfi1/verbs.c index 48e11e510358..a365089a9305 100644 --- a/drivers/infiniband/hw/hfi1/verbs.c +++ b/drivers/infiniband/hw/hfi1/verbs.c @@ -1479,7 +1479,7 @@ static const char * const driver_cntr_names[] = { static DEFINE_MUTEX(cntr_names_lock); /* protects the *_cntr_names bufers */ static const char **dev_cntr_names; static const char **port_cntr_names; -static int num_driver_cntrs = ARRAY_SIZE(driver_cntr_names); +int num_driver_cntrs = ARRAY_SIZE(driver_cntr_names); static int num_dev_cntrs; static int num_port_cntrs; static int cntr_names_initialized; -- cgit v1.2.3 From 37b06e5078975bb4efe3cbd91e254112851b125f Mon Sep 17 00:00:00 2001 From: Artemy Kovalyov Date: Tue, 27 Nov 2018 08:51:25 +0200 Subject: IB/mlx5: Fix implicit ODP interrupted page fault Since any page fault may be interrupted by a MMU invalidation and implicit leaf MR may be released during this process. The check for parent value is unreliable condition for an implicit MR. Use other condition that we can rely on to determine if MR is implicit. Fixes: b4cfe447d47b ("IB/mlx5: Implement on demand paging by adding support for MMU notifiers") Signed-off-by: Artemy Kovalyov Signed-off-by: Moni Shoua Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford --- drivers/infiniband/hw/mlx5/odp.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c index 2cc3d69ab6f6..4dc6cc640ce0 100644 --- a/drivers/infiniband/hw/mlx5/odp.c +++ b/drivers/infiniband/hw/mlx5/odp.c @@ -506,14 +506,13 @@ void mlx5_ib_free_implicit_mr(struct mlx5_ib_mr *imr) static int pagefault_mr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr, u64 io_virt, size_t bcnt, u32 *bytes_mapped) { + int npages = 0, current_seq, page_shift, ret, np; + bool implicit = false; struct ib_umem_odp *odp_mr = to_ib_umem_odp(mr->umem); u64 access_mask = ODP_READ_ALLOWED_BIT; - int npages = 0, page_shift, np; u64 start_idx, page_mask; struct ib_umem_odp *odp; - int current_seq; size_t size; - int ret; if (!odp_mr->page_list) { odp = implicit_mr_get_data(mr, io_virt, bcnt); @@ -521,7 +520,7 @@ static int pagefault_mr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr, if (IS_ERR(odp)) return PTR_ERR(odp); mr = odp->private; - + implicit = true; } else { odp = odp_mr; } @@ -600,7 +599,7 @@ next_mr: out: if (ret == -EAGAIN) { - if (mr->parent || !odp->dying) { + if (implicit || !odp->dying) { unsigned long timeout = msecs_to_jiffies(MMU_NOTIFIER_TIMEOUT); -- cgit v1.2.3 From 4c05ec47384ab3627b62814e8f886e90cc38ce15 Mon Sep 17 00:00:00 2001 From: Taehee Yoo Date: Mon, 26 Nov 2018 20:03:30 +0900 Subject: netfilter: nf_tables: fix suspicious RCU usage in nft_chain_stats_replace() basechain->stats is rcu protected data which is updated from nft_chain_stats_replace(). This function is executed from the commit phase which holds the pernet nf_tables commit mutex - not the global nfnetlink subsystem mutex. Test commands to reproduce the problem are: %iptables-nft -I INPUT %iptables-nft -Z %iptables-nft -Z This patch uses RCU calls to handle basechain->stats updates to fix a splat that looks like: [89279.358755] ============================= [89279.363656] WARNING: suspicious RCU usage [89279.368458] 4.20.0-rc2+ #44 Tainted: G W L [89279.374661] ----------------------------- [89279.379542] net/netfilter/nf_tables_api.c:1404 suspicious rcu_dereference_protected() usage! [...] [89279.406556] 1 lock held by iptables-nft/5225: [89279.411728] #0: 00000000bf45a000 (&net->nft.commit_mutex){+.+.}, at: nf_tables_valid_genid+0x1f/0x70 [nf_tables] [89279.424022] stack backtrace: [89279.429236] CPU: 0 PID: 5225 Comm: iptables-nft Tainted: G W L 4.20.0-rc2+ #44 [89279.430135] Call Trace: [89279.430135] dump_stack+0xc9/0x16b [89279.430135] ? show_regs_print_info+0x5/0x5 [89279.430135] ? lockdep_rcu_suspicious+0x117/0x160 [89279.430135] nft_chain_commit_update+0x4ea/0x640 [nf_tables] [89279.430135] ? sched_clock_local+0xd4/0x140 [89279.430135] ? check_flags.part.35+0x440/0x440 [89279.430135] ? __rhashtable_remove_fast.constprop.67+0xec0/0xec0 [nf_tables] [89279.430135] ? sched_clock_cpu+0x126/0x170 [89279.430135] ? find_held_lock+0x39/0x1c0 [89279.430135] ? hlock_class+0x140/0x140 [89279.430135] ? is_bpf_text_address+0x5/0xf0 [89279.430135] ? check_flags.part.35+0x440/0x440 [89279.430135] ? __lock_is_held+0xb4/0x140 [89279.430135] nf_tables_commit+0x2555/0x39c0 [nf_tables] Fixes: f102d66b335a4 ("netfilter: nf_tables: use dedicated mutex to guard transactions") Signed-off-by: Taehee Yoo Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/nfnetlink.h | 12 ------------ net/netfilter/nf_tables_api.c | 21 +++++++++++++-------- net/netfilter/nf_tables_core.c | 2 +- 3 files changed, 14 insertions(+), 21 deletions(-) diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h index 4a520d3304a2..cf09ab37b45b 100644 --- a/include/linux/netfilter/nfnetlink.h +++ b/include/linux/netfilter/nfnetlink.h @@ -62,18 +62,6 @@ static inline bool lockdep_nfnl_is_held(__u8 subsys_id) } #endif /* CONFIG_PROVE_LOCKING */ -/* - * nfnl_dereference - fetch RCU pointer when updates are prevented by subsys mutex - * - * @p: The pointer to read, prior to dereferencing - * @ss: The nfnetlink subsystem ID - * - * Return the value of the specified RCU-protected pointer, but omit - * the READ_ONCE(), because caller holds the NFNL subsystem mutex. - */ -#define nfnl_dereference(p, ss) \ - rcu_dereference_protected(p, lockdep_nfnl_is_held(ss)) - #define MODULE_ALIAS_NFNL_SUBSYS(subsys) \ MODULE_ALIAS("nfnetlink-subsys-" __stringify(subsys)) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 2e61aab6ed73..6e548d7c9f67 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -1216,7 +1216,8 @@ static int nf_tables_fill_chain_info(struct sk_buff *skb, struct net *net, if (nla_put_string(skb, NFTA_CHAIN_TYPE, basechain->type->name)) goto nla_put_failure; - if (basechain->stats && nft_dump_stats(skb, basechain->stats)) + if (rcu_access_pointer(basechain->stats) && + nft_dump_stats(skb, rcu_dereference(basechain->stats))) goto nla_put_failure; } @@ -1392,7 +1393,8 @@ static struct nft_stats __percpu *nft_stats_alloc(const struct nlattr *attr) return newstats; } -static void nft_chain_stats_replace(struct nft_base_chain *chain, +static void nft_chain_stats_replace(struct net *net, + struct nft_base_chain *chain, struct nft_stats __percpu *newstats) { struct nft_stats __percpu *oldstats; @@ -1400,8 +1402,9 @@ static void nft_chain_stats_replace(struct nft_base_chain *chain, if (newstats == NULL) return; - if (chain->stats) { - oldstats = nfnl_dereference(chain->stats, NFNL_SUBSYS_NFTABLES); + if (rcu_access_pointer(chain->stats)) { + oldstats = rcu_dereference_protected(chain->stats, + lockdep_commit_lock_is_held(net)); rcu_assign_pointer(chain->stats, newstats); synchronize_rcu(); free_percpu(oldstats); @@ -1439,9 +1442,10 @@ static void nf_tables_chain_destroy(struct nft_ctx *ctx) struct nft_base_chain *basechain = nft_base_chain(chain); module_put(basechain->type->owner); - free_percpu(basechain->stats); - if (basechain->stats) + if (rcu_access_pointer(basechain->stats)) { static_branch_dec(&nft_counters_enabled); + free_percpu(rcu_dereference_raw(basechain->stats)); + } kfree(chain->name); kfree(basechain); } else { @@ -1590,7 +1594,7 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, kfree(basechain); return PTR_ERR(stats); } - basechain->stats = stats; + rcu_assign_pointer(basechain->stats, stats); static_branch_inc(&nft_counters_enabled); } @@ -6180,7 +6184,8 @@ static void nft_chain_commit_update(struct nft_trans *trans) return; basechain = nft_base_chain(trans->ctx.chain); - nft_chain_stats_replace(basechain, nft_trans_chain_stats(trans)); + nft_chain_stats_replace(trans->ctx.net, basechain, + nft_trans_chain_stats(trans)); switch (nft_trans_chain_policy(trans)) { case NF_DROP: diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c index 3fbce3b9c5ec..a50500232b0a 100644 --- a/net/netfilter/nf_tables_core.c +++ b/net/netfilter/nf_tables_core.c @@ -101,7 +101,7 @@ static noinline void nft_update_chain_stats(const struct nft_chain *chain, struct nft_stats *stats; base_chain = nft_base_chain(chain); - if (!base_chain->stats) + if (!rcu_access_pointer(base_chain->stats)) return; local_bh_disable(); -- cgit v1.2.3 From a44f7cb937321d4961bfc8f28912126b06e701c5 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Mon, 26 Nov 2018 14:38:13 +0100 Subject: mmc: core: use mrq->sbc when sending CMD23 for RPMB When sending out CMD23 in the blk preparation, the comment there rightfully says: * However, it is not sufficient to just send CMD23, * and avoid the final CMD12, as on an error condition * CMD12 (stop) needs to be sent anyway. This, coupled * with Auto-CMD23 enhancements provided by some * hosts, means that the complexity of dealing * with this is best left to the host. If CMD23 is * supported by card and host, we'll fill sbc in and let * the host deal with handling it correctly. Let's do this behaviour for RPMB as well, and not send CMD23 independently. Otherwise IP cores (like Renesas SDHI) may timeout because of automatic CMD23/CMD12 handling. Reported-by: Masaharu Hayakawa Signed-off-by: Wolfram Sang Tested-by: Clément Péron Reviewed-by: Avri Altman Reviewed-by: Niklas Söderlund Cc: stable@vger.kernel.org Signed-off-by: Ulf Hansson --- drivers/mmc/core/block.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c index c35b5b08bb33..111934838da2 100644 --- a/drivers/mmc/core/block.c +++ b/drivers/mmc/core/block.c @@ -472,7 +472,7 @@ out: static int __mmc_blk_ioctl_cmd(struct mmc_card *card, struct mmc_blk_data *md, struct mmc_blk_ioc_data *idata) { - struct mmc_command cmd = {}; + struct mmc_command cmd = {}, sbc = {}; struct mmc_data data = {}; struct mmc_request mrq = {}; struct scatterlist sg; @@ -550,10 +550,15 @@ static int __mmc_blk_ioctl_cmd(struct mmc_card *card, struct mmc_blk_data *md, } if (idata->rpmb) { - err = mmc_set_blockcount(card, data.blocks, - idata->ic.write_flag & (1 << 31)); - if (err) - return err; + sbc.opcode = MMC_SET_BLOCK_COUNT; + /* + * We don't do any blockcount validation because the max size + * may be increased by a future standard. We just copy the + * 'Reliable Write' bit here. + */ + sbc.arg = data.blocks | (idata->ic.write_flag & BIT(31)); + sbc.flags = MMC_RSP_R1 | MMC_CMD_AC; + mrq.sbc = &sbc; } if ((MMC_EXTRACT_INDEX_FROM_ARG(cmd.arg) == EXT_CSD_SANITIZE_START) && -- cgit v1.2.3 From ec7ba118b9407c9b4d998b8065167afae5ed04be Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Tue, 4 Dec 2018 11:31:30 +0100 Subject: Revert "ovl: relax permission checking on underlying layers" This reverts commit 007ea44892e6fa963a0876a979e34890325c64eb. The commit broke some selinux-testsuite cases, and it looks like there's no straightforward fix keeping the direction of this patch, so revert for now. The original patch was trying to fix the consistency of permission checks, and not an observed bug. So reverting should be safe. Signed-off-by: Miklos Szeredi --- fs/overlayfs/inode.c | 17 ++++------------- 1 file changed, 4 insertions(+), 13 deletions(-) diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index 6bcc9dedc342..3b7ed5d2279c 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -286,22 +286,13 @@ int ovl_permission(struct inode *inode, int mask) if (err) return err; - /* No need to do any access on underlying for special files */ - if (special_file(realinode->i_mode)) - return 0; - - /* No need to access underlying for execute */ - mask &= ~MAY_EXEC; - if ((mask & (MAY_READ | MAY_WRITE)) == 0) - return 0; - - /* Lower files get copied up, so turn write access into read */ - if (!upperinode && mask & MAY_WRITE) { + old_cred = ovl_override_creds(inode->i_sb); + if (!upperinode && + !special_file(realinode->i_mode) && mask & MAY_WRITE) { mask &= ~(MAY_WRITE | MAY_APPEND); + /* Make sure mounter can read file for copy up later */ mask |= MAY_READ; } - - old_cred = ovl_override_creds(inode->i_sb); err = inode_permission(realinode, mask); revert_creds(old_cred); -- cgit v1.2.3 From e8cde625bfe8a714a856e1366bcbb259d7346095 Mon Sep 17 00:00:00 2001 From: Aaro Koskinen Date: Tue, 20 Nov 2018 01:14:00 +0200 Subject: MMC: OMAP: fix broken MMC on OMAP15XX/OMAP5910/OMAP310 Since v2.6.22 or so there has been reports [1] about OMAP MMC being broken on OMAP15XX based hardware (OMAP5910 and OMAP310). The breakage seems to have been caused by commit 46a6730e3ff9 ("mmc-omap: Fix omap to use MMC_POWER_ON") that changed clock enabling to be done on MMC_POWER_ON. This can happen multiple times in a row, and on 15XX the hardware doesn't seem to like it and the MMC just stops responding. Fix by memorizing the power mode and do the init only when necessary. Before the patch (on Palm TE): mmc0: new SD card at address b368 mmcblk0: mmc0:b368 SDC 977 MiB mmci-omap mmci-omap.0: command timeout (CMD18) mmci-omap mmci-omap.0: command timeout (CMD13) mmci-omap mmci-omap.0: command timeout (CMD13) mmci-omap mmci-omap.0: command timeout (CMD12) [x 6] mmci-omap mmci-omap.0: command timeout (CMD13) [x 6] mmcblk0: error -110 requesting status mmci-omap mmci-omap.0: command timeout (CMD8) mmci-omap mmci-omap.0: command timeout (CMD18) mmci-omap mmci-omap.0: command timeout (CMD13) mmci-omap mmci-omap.0: command timeout (CMD13) mmci-omap mmci-omap.0: command timeout (CMD12) [x 6] mmci-omap mmci-omap.0: command timeout (CMD13) [x 6] mmcblk0: error -110 requesting status mmcblk0: recovery failed! print_req_error: I/O error, dev mmcblk0, sector 0 Buffer I/O error on dev mmcblk0, logical block 0, async page read mmcblk0: unable to read partition table After the patch: mmc0: new SD card at address b368 mmcblk0: mmc0:b368 SDC 977 MiB mmcblk0: p1 The patch is based on a fix and analysis done by Ladislav Michl. Tested on OMAP15XX/OMAP310 (Palm TE), OMAP1710 (Nokia 770) and OMAP2420 (Nokia N810). [1] https://marc.info/?t=123175197000003&r=1&w=2 Fixes: 46a6730e3ff9 ("mmc-omap: Fix omap to use MMC_POWER_ON") Reported-by: Ladislav Michl Reported-by: Andrzej Zaborowski Tested-by: Ladislav Michl Acked-by: Tony Lindgren Signed-off-by: Aaro Koskinen Cc: stable@vger.kernel.org Signed-off-by: Ulf Hansson --- drivers/mmc/host/omap.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/drivers/mmc/host/omap.c b/drivers/mmc/host/omap.c index adf32682f27a..c60a7625b1fa 100644 --- a/drivers/mmc/host/omap.c +++ b/drivers/mmc/host/omap.c @@ -104,6 +104,7 @@ struct mmc_omap_slot { unsigned int vdd; u16 saved_con; u16 bus_mode; + u16 power_mode; unsigned int fclk_freq; struct tasklet_struct cover_tasklet; @@ -1157,7 +1158,7 @@ static void mmc_omap_set_ios(struct mmc_host *mmc, struct mmc_ios *ios) struct mmc_omap_slot *slot = mmc_priv(mmc); struct mmc_omap_host *host = slot->host; int i, dsor; - int clk_enabled; + int clk_enabled, init_stream; mmc_omap_select_slot(slot, 0); @@ -1167,6 +1168,7 @@ static void mmc_omap_set_ios(struct mmc_host *mmc, struct mmc_ios *ios) slot->vdd = ios->vdd; clk_enabled = 0; + init_stream = 0; switch (ios->power_mode) { case MMC_POWER_OFF: mmc_omap_set_power(slot, 0, ios->vdd); @@ -1174,13 +1176,17 @@ static void mmc_omap_set_ios(struct mmc_host *mmc, struct mmc_ios *ios) case MMC_POWER_UP: /* Cannot touch dsor yet, just power up MMC */ mmc_omap_set_power(slot, 1, ios->vdd); + slot->power_mode = ios->power_mode; goto exit; case MMC_POWER_ON: mmc_omap_fclk_enable(host, 1); clk_enabled = 1; dsor |= 1 << 11; + if (slot->power_mode != MMC_POWER_ON) + init_stream = 1; break; } + slot->power_mode = ios->power_mode; if (slot->bus_mode != ios->bus_mode) { if (slot->pdata->set_bus_mode != NULL) @@ -1196,7 +1202,7 @@ static void mmc_omap_set_ios(struct mmc_host *mmc, struct mmc_ios *ios) for (i = 0; i < 2; i++) OMAP_MMC_WRITE(host, CON, dsor); slot->saved_con = dsor; - if (ios->power_mode == MMC_POWER_ON) { + if (init_stream) { /* worst case at 400kHz, 80 cycles makes 200 microsecs */ int usecs = 250; @@ -1234,6 +1240,7 @@ static int mmc_omap_new_slot(struct mmc_omap_host *host, int id) slot->host = host; slot->mmc = mmc; slot->id = id; + slot->power_mode = MMC_POWER_UNDEFINED; slot->pdata = &host->pdata->slots[id]; host->slots[id] = slot; -- cgit v1.2.3 From c3b9ab5db11d8098ca7674175f12ab21cdce1bbb Mon Sep 17 00:00:00 2001 From: Fabio Estevam Date: Fri, 30 Nov 2018 08:31:29 -0200 Subject: ARM: dts: imx7d-pico: Describe the Wifi clock The Wifi chip should be clocked by a 32kHz clock coming from i.MX7D CLKO2 output pin, so describe the pinmux and clock hierarchy in the device tree to allow the Wifi chip to be properly clocked. Managed to successfully test Wifi with such change. Used the standard nvram.txt file provided by TechNexion, which selects an external 32kHz clock for the Wifi chip by default. Fixes: 99a52450c707 ("ARM: dts: imx7d-pico: Add Wifi support") Suggested-by: Arend van Spriel Tested-by: Otavio Salvador Signed-off-by: Fabio Estevam Signed-off-by: Shawn Guo --- arch/arm/boot/dts/imx7d-pico.dtsi | 22 +++++++++++++++++++++- 1 file changed, 21 insertions(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/imx7d-pico.dtsi b/arch/arm/boot/dts/imx7d-pico.dtsi index 21973eb55671..f27b3849d3ff 100644 --- a/arch/arm/boot/dts/imx7d-pico.dtsi +++ b/arch/arm/boot/dts/imx7d-pico.dtsi @@ -100,6 +100,19 @@ regulator-min-microvolt = <1800000>; regulator-max-microvolt = <1800000>; }; + + usdhc2_pwrseq: usdhc2_pwrseq { + compatible = "mmc-pwrseq-simple"; + clocks = <&clks IMX7D_CLKO2_ROOT_DIV>; + clock-names = "ext_clock"; + }; +}; + +&clks { + assigned-clocks = <&clks IMX7D_CLKO2_ROOT_SRC>, + <&clks IMX7D_CLKO2_ROOT_DIV>; + assigned-clock-parents = <&clks IMX7D_CKIL>; + assigned-clock-rates = <0>, <32768>; }; &i2c4 { @@ -199,12 +212,13 @@ &usdhc2 { /* Wifi SDIO */ pinctrl-names = "default"; - pinctrl-0 = <&pinctrl_usdhc2>; + pinctrl-0 = <&pinctrl_usdhc2 &pinctrl_wifi_clk>; no-1-8-v; non-removable; keep-power-in-suspend; wakeup-source; vmmc-supply = <®_ap6212>; + mmc-pwrseq = <&usdhc2_pwrseq>; status = "okay"; }; @@ -301,6 +315,12 @@ }; &iomuxc_lpsr { + pinctrl_wifi_clk: wificlkgrp { + fsl,pins = < + MX7D_PAD_LPSR_GPIO1_IO03__CCM_CLKO2 0x7d + >; + }; + pinctrl_wdog: wdoggrp { fsl,pins = < MX7D_PAD_LPSR_GPIO1_IO00__WDOG1_WDOG_B 0x74 -- cgit v1.2.3 From dae522045094ebfa9a10cf7951a8f79b02da8e15 Mon Sep 17 00:00:00 2001 From: Baruch Siach Date: Tue, 4 Dec 2018 17:46:02 +0200 Subject: Revert "arm64: dts: marvell: add CPU Idle power state support on Armada 7K/8K" This reverts commit 8ed46368776b3bc93d74c1f8f2bfb9fd8a9ad805. This commit breaks boot on Armada 8K based systems. Reverting it makes affected systems boot again. Reported-by: Sergey Matyukevich Signed-off-by: Baruch Siach Signed-off-by: Gregory CLEMENT --- arch/arm64/boot/dts/marvell/armada-ap806-quad.dtsi | 4 ---- arch/arm64/boot/dts/marvell/armada-ap806.dtsi | 27 ---------------------- 2 files changed, 31 deletions(-) diff --git a/arch/arm64/boot/dts/marvell/armada-ap806-quad.dtsi b/arch/arm64/boot/dts/marvell/armada-ap806-quad.dtsi index 64632c873888..01ea662afba8 100644 --- a/arch/arm64/boot/dts/marvell/armada-ap806-quad.dtsi +++ b/arch/arm64/boot/dts/marvell/armada-ap806-quad.dtsi @@ -20,28 +20,24 @@ compatible = "arm,cortex-a72", "arm,armv8"; reg = <0x000>; enable-method = "psci"; - cpu-idle-states = <&CPU_SLEEP_0>; }; cpu1: cpu@1 { device_type = "cpu"; compatible = "arm,cortex-a72", "arm,armv8"; reg = <0x001>; enable-method = "psci"; - cpu-idle-states = <&CPU_SLEEP_0>; }; cpu2: cpu@100 { device_type = "cpu"; compatible = "arm,cortex-a72", "arm,armv8"; reg = <0x100>; enable-method = "psci"; - cpu-idle-states = <&CPU_SLEEP_0>; }; cpu3: cpu@101 { device_type = "cpu"; compatible = "arm,cortex-a72", "arm,armv8"; reg = <0x101>; enable-method = "psci"; - cpu-idle-states = <&CPU_SLEEP_0>; }; }; }; diff --git a/arch/arm64/boot/dts/marvell/armada-ap806.dtsi b/arch/arm64/boot/dts/marvell/armada-ap806.dtsi index 073610ac0a53..7d94c1fa592a 100644 --- a/arch/arm64/boot/dts/marvell/armada-ap806.dtsi +++ b/arch/arm64/boot/dts/marvell/armada-ap806.dtsi @@ -28,33 +28,6 @@ method = "smc"; }; - cpus { - #address-cells = <1>; - #size-cells = <0>; - - idle_states { - entry_method = "arm,pcsi"; - - CPU_SLEEP_0: cpu-sleep-0 { - compatible = "arm,idle-state"; - local-timer-stop; - arm,psci-suspend-param = <0x0010000>; - entry-latency-us = <80>; - exit-latency-us = <160>; - min-residency-us = <320>; - }; - - CLUSTER_SLEEP_0: cluster-sleep-0 { - compatible = "arm,idle-state"; - local-timer-stop; - arm,psci-suspend-param = <0x1010000>; - entry-latency-us = <500>; - exit-latency-us = <1000>; - min-residency-us = <2500>; - }; - }; - }; - ap806 { #address-cells = <2>; #size-cells = <2>; -- cgit v1.2.3 From 009367791f31afa0842854e7ea0acc9edf70ccaf Mon Sep 17 00:00:00 2001 From: Tvrtko Ursulin Date: Wed, 5 Dec 2018 11:33:23 +0000 Subject: drm/i915: Record GT workarounds in a list To enable later verification of GT workaround state at various stages of driver lifetime, we record the list of applicable ones per platforms to a list, from which they are also applied. The added data structure is a simple array of register, mask and value items, which is allocated on demand as workarounds are added to the list. This is a temporary implementation which later in the series gets fused with the existing per context workaround list handling. It is separated at this stage since the following patch fixes a bug which needs to be as easy to backport as possible. Also, since in the following patch we will be adding a new class of workarounds (per engine) which can be applied from interrupt context, we straight away make the provision for safe read-modify-write cycle. v2: * Change dev_priv to i915 along the init path. (Chris Wilson) * API rename. (Chris Wilson) v3: * Remove explicit list size tracking in favour of growing the allocation in power of two chunks. (Chris Wilson) v4: Chris Wilson: * Change wa_list_finish to early return. * Copy workarounds using the compiler for static checking. * Do not bother zeroing unused entries. * Re-order struct i915_wa_list. v5: * kmalloc_array. * Whitespace cleanup. Signed-off-by: Tvrtko Ursulin Reviewed-by: Chris Wilson Link: https://patchwork.freedesktop.org/patch/msgid/20181203133319.10174-1-tvrtko.ursulin@linux.intel.com (cherry picked from commit 25d140faaa25f728159eb8c304eae53d88a7f14e) Fixes: 59b449d5c82a ("drm/i915: Split out functions for different kinds of workarounds") Signed-off-by: Joonas Lahtinen --- drivers/gpu/drm/i915/i915_drv.c | 1 + drivers/gpu/drm/i915/i915_drv.h | 2 + drivers/gpu/drm/i915/i915_gem.c | 4 +- drivers/gpu/drm/i915/intel_workarounds.c | 482 +++++++++++++++++++++---------- drivers/gpu/drm/i915/intel_workarounds.h | 23 +- 5 files changed, 352 insertions(+), 160 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index ffdbbac4400e..47062ee979cf 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -1444,6 +1444,7 @@ static int i915_driver_init_hw(struct drm_i915_private *dev_priv) intel_uncore_sanitize(dev_priv); + intel_gt_init_workarounds(dev_priv); i915_gem_load_init_fences(dev_priv); /* On the 945G/GM, the chipset reports the MSI capability on the diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 9102571e9692..1331cde79c2e 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -67,6 +67,7 @@ #include "intel_ringbuffer.h" #include "intel_uncore.h" #include "intel_wopcm.h" +#include "intel_workarounds.h" #include "intel_uc.h" #include "i915_gem.h" @@ -1805,6 +1806,7 @@ struct drm_i915_private { int dpio_phy_iosf_port[I915_NUM_PHYS_VLV]; struct i915_workarounds workarounds; + struct i915_wa_list gt_wa_list; struct i915_frontbuffer_tracking fb_tracking; diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 0c8aa57ce83b..ba371712c560 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -5305,7 +5305,7 @@ int i915_gem_init_hw(struct drm_i915_private *dev_priv) } } - intel_gt_workarounds_apply(dev_priv); + intel_gt_apply_workarounds(dev_priv); i915_gem_init_swizzling(dev_priv); @@ -5677,6 +5677,8 @@ void i915_gem_fini(struct drm_i915_private *dev_priv) i915_gem_contexts_fini(dev_priv); mutex_unlock(&dev_priv->drm.struct_mutex); + intel_wa_list_free(&dev_priv->gt_wa_list); + intel_cleanup_gt_powersave(dev_priv); intel_uc_fini_misc(dev_priv); diff --git a/drivers/gpu/drm/i915/intel_workarounds.c b/drivers/gpu/drm/i915/intel_workarounds.c index 4bcdeaf8d98f..9ac3e086a46c 100644 --- a/drivers/gpu/drm/i915/intel_workarounds.c +++ b/drivers/gpu/drm/i915/intel_workarounds.c @@ -48,6 +48,20 @@ * - Public functions to init or apply the given workaround type. */ +static void wa_init_start(struct i915_wa_list *wal, const char *name) +{ + wal->name = name; +} + +static void wa_init_finish(struct i915_wa_list *wal) +{ + if (!wal->count) + return; + + DRM_DEBUG_DRIVER("Initialized %u %s workarounds\n", + wal->count, wal->name); +} + static void wa_add(struct drm_i915_private *i915, i915_reg_t reg, const u32 mask, const u32 val) { @@ -580,160 +594,239 @@ int intel_ctx_workarounds_emit(struct i915_request *rq) return 0; } -static void bdw_gt_workarounds_apply(struct drm_i915_private *dev_priv) +static void +wal_add(struct i915_wa_list *wal, const struct i915_wa *wa) +{ + const unsigned int grow = 1 << 4; + + GEM_BUG_ON(!is_power_of_2(grow)); + + if (IS_ALIGNED(wal->count, grow)) { /* Either uninitialized or full. */ + struct i915_wa *list; + + list = kmalloc_array(ALIGN(wal->count + 1, grow), sizeof(*wa), + GFP_KERNEL); + if (!list) { + DRM_ERROR("No space for workaround init!\n"); + return; + } + + if (wal->list) + memcpy(list, wal->list, sizeof(*wa) * wal->count); + + wal->list = list; + } + + wal->list[wal->count++] = *wa; +} + +static void +wa_masked_en(struct i915_wa_list *wal, i915_reg_t reg, u32 val) { + struct i915_wa wa = { + .reg = reg, + .mask = val, + .val = _MASKED_BIT_ENABLE(val) + }; + + wal_add(wal, &wa); } -static void chv_gt_workarounds_apply(struct drm_i915_private *dev_priv) +static void +wa_write_masked_or(struct i915_wa_list *wal, i915_reg_t reg, u32 mask, + u32 val) { + struct i915_wa wa = { + .reg = reg, + .mask = mask, + .val = val + }; + + wal_add(wal, &wa); } -static void gen9_gt_workarounds_apply(struct drm_i915_private *dev_priv) +static void +wa_write(struct i915_wa_list *wal, i915_reg_t reg, u32 val) { + wa_write_masked_or(wal, reg, ~0, val); +} + +static void +wa_write_or(struct i915_wa_list *wal, i915_reg_t reg, u32 val) +{ + wa_write_masked_or(wal, reg, val, val); +} + +static void gen9_gt_workarounds_init(struct drm_i915_private *i915) +{ + struct i915_wa_list *wal = &i915->gt_wa_list; + /* WaContextSwitchWithConcurrentTLBInvalidate:skl,bxt,kbl,glk,cfl */ - I915_WRITE(GEN9_CSFE_CHICKEN1_RCS, - _MASKED_BIT_ENABLE(GEN9_PREEMPT_GPGPU_SYNC_SWITCH_DISABLE)); + wa_masked_en(wal, + GEN9_CSFE_CHICKEN1_RCS, + GEN9_PREEMPT_GPGPU_SYNC_SWITCH_DISABLE); + /* WaEnableLbsSlaRetryTimerDecrement:skl,bxt,kbl,glk,cfl */ - I915_WRITE(BDW_SCRATCH1, I915_READ(BDW_SCRATCH1) | - GEN9_LBS_SLA_RETRY_TIMER_DECREMENT_ENABLE); + wa_write_or(wal, + BDW_SCRATCH1, + GEN9_LBS_SLA_RETRY_TIMER_DECREMENT_ENABLE); /* WaDisableKillLogic:bxt,skl,kbl */ - if (!IS_COFFEELAKE(dev_priv)) - I915_WRITE(GAM_ECOCHK, I915_READ(GAM_ECOCHK) | - ECOCHK_DIS_TLB); + if (!IS_COFFEELAKE(i915)) + wa_write_or(wal, + GAM_ECOCHK, + ECOCHK_DIS_TLB); - if (HAS_LLC(dev_priv)) { + if (HAS_LLC(i915)) { /* WaCompressedResourceSamplerPbeMediaNewHashMode:skl,kbl * * Must match Display Engine. See * WaCompressedResourceDisplayNewHashMode. */ - I915_WRITE(MMCD_MISC_CTRL, - I915_READ(MMCD_MISC_CTRL) | - MMCD_PCLA | - MMCD_HOTSPOT_EN); + wa_write_or(wal, + MMCD_MISC_CTRL, + MMCD_PCLA | MMCD_HOTSPOT_EN); } /* WaDisableHDCInvalidation:skl,bxt,kbl,cfl */ - I915_WRITE(GAM_ECOCHK, I915_READ(GAM_ECOCHK) | - BDW_DISABLE_HDC_INVALIDATION); + wa_write_or(wal, + GAM_ECOCHK, + BDW_DISABLE_HDC_INVALIDATION); /* WaProgramL3SqcReg1DefaultForPerf:bxt,glk */ - if (IS_GEN9_LP(dev_priv)) { - u32 val = I915_READ(GEN8_L3SQCREG1); - - val &= ~L3_PRIO_CREDITS_MASK; - val |= L3_GENERAL_PRIO_CREDITS(62) | L3_HIGH_PRIO_CREDITS(2); - I915_WRITE(GEN8_L3SQCREG1, val); - } + if (IS_GEN9_LP(i915)) + wa_write_masked_or(wal, + GEN8_L3SQCREG1, + L3_PRIO_CREDITS_MASK, + L3_GENERAL_PRIO_CREDITS(62) | + L3_HIGH_PRIO_CREDITS(2)); /* WaOCLCoherentLineFlush:skl,bxt,kbl,cfl */ - I915_WRITE(GEN8_L3SQCREG4, - I915_READ(GEN8_L3SQCREG4) | GEN8_LQSC_FLUSH_COHERENT_LINES); + wa_write_or(wal, + GEN8_L3SQCREG4, + GEN8_LQSC_FLUSH_COHERENT_LINES); /* WaEnablePreemptionGranularityControlByUMD:skl,bxt,kbl,cfl,[cnl] */ - I915_WRITE(GEN7_FF_SLICE_CS_CHICKEN1, - _MASKED_BIT_ENABLE(GEN9_FFSC_PERCTX_PREEMPT_CTRL)); + wa_masked_en(wal, + GEN7_FF_SLICE_CS_CHICKEN1, + GEN9_FFSC_PERCTX_PREEMPT_CTRL); } -static void skl_gt_workarounds_apply(struct drm_i915_private *dev_priv) +static void skl_gt_workarounds_init(struct drm_i915_private *i915) { - gen9_gt_workarounds_apply(dev_priv); + struct i915_wa_list *wal = &i915->gt_wa_list; + + gen9_gt_workarounds_init(i915); /* WaEnableGapsTsvCreditFix:skl */ - I915_WRITE(GEN8_GARBCNTL, - I915_READ(GEN8_GARBCNTL) | GEN9_GAPS_TSV_CREDIT_DISABLE); + wa_write_or(wal, + GEN8_GARBCNTL, + GEN9_GAPS_TSV_CREDIT_DISABLE); /* WaDisableGafsUnitClkGating:skl */ - I915_WRITE(GEN7_UCGCTL4, - I915_READ(GEN7_UCGCTL4) | GEN8_EU_GAUNIT_CLOCK_GATE_DISABLE); + wa_write_or(wal, + GEN7_UCGCTL4, + GEN8_EU_GAUNIT_CLOCK_GATE_DISABLE); /* WaInPlaceDecompressionHang:skl */ - if (IS_SKL_REVID(dev_priv, SKL_REVID_H0, REVID_FOREVER)) - I915_WRITE(GEN9_GAMT_ECO_REG_RW_IA, - I915_READ(GEN9_GAMT_ECO_REG_RW_IA) | - GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS); + if (IS_SKL_REVID(i915, SKL_REVID_H0, REVID_FOREVER)) + wa_write_or(wal, + GEN9_GAMT_ECO_REG_RW_IA, + GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS); } -static void bxt_gt_workarounds_apply(struct drm_i915_private *dev_priv) +static void bxt_gt_workarounds_init(struct drm_i915_private *i915) { - gen9_gt_workarounds_apply(dev_priv); + struct i915_wa_list *wal = &i915->gt_wa_list; + + gen9_gt_workarounds_init(i915); /* WaDisablePooledEuLoadBalancingFix:bxt */ - I915_WRITE(FF_SLICE_CS_CHICKEN2, - _MASKED_BIT_ENABLE(GEN9_POOLED_EU_LOAD_BALANCING_FIX_DISABLE)); + wa_masked_en(wal, + FF_SLICE_CS_CHICKEN2, + GEN9_POOLED_EU_LOAD_BALANCING_FIX_DISABLE); /* WaInPlaceDecompressionHang:bxt */ - I915_WRITE(GEN9_GAMT_ECO_REG_RW_IA, - I915_READ(GEN9_GAMT_ECO_REG_RW_IA) | - GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS); + wa_write_or(wal, + GEN9_GAMT_ECO_REG_RW_IA, + GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS); } -static void kbl_gt_workarounds_apply(struct drm_i915_private *dev_priv) +static void kbl_gt_workarounds_init(struct drm_i915_private *i915) { - gen9_gt_workarounds_apply(dev_priv); + struct i915_wa_list *wal = &i915->gt_wa_list; + + gen9_gt_workarounds_init(i915); /* WaEnableGapsTsvCreditFix:kbl */ - I915_WRITE(GEN8_GARBCNTL, - I915_READ(GEN8_GARBCNTL) | GEN9_GAPS_TSV_CREDIT_DISABLE); + wa_write_or(wal, + GEN8_GARBCNTL, + GEN9_GAPS_TSV_CREDIT_DISABLE); /* WaDisableDynamicCreditSharing:kbl */ - if (IS_KBL_REVID(dev_priv, 0, KBL_REVID_B0)) - I915_WRITE(GAMT_CHKN_BIT_REG, - I915_READ(GAMT_CHKN_BIT_REG) | - GAMT_CHKN_DISABLE_DYNAMIC_CREDIT_SHARING); + if (IS_KBL_REVID(i915, 0, KBL_REVID_B0)) + wa_write_or(wal, + GAMT_CHKN_BIT_REG, + GAMT_CHKN_DISABLE_DYNAMIC_CREDIT_SHARING); /* WaDisableGafsUnitClkGating:kbl */ - I915_WRITE(GEN7_UCGCTL4, - I915_READ(GEN7_UCGCTL4) | GEN8_EU_GAUNIT_CLOCK_GATE_DISABLE); + wa_write_or(wal, + GEN7_UCGCTL4, + GEN8_EU_GAUNIT_CLOCK_GATE_DISABLE); /* WaInPlaceDecompressionHang:kbl */ - I915_WRITE(GEN9_GAMT_ECO_REG_RW_IA, - I915_READ(GEN9_GAMT_ECO_REG_RW_IA) | - GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS); + wa_write_or(wal, + GEN9_GAMT_ECO_REG_RW_IA, + GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS); /* WaKBLVECSSemaphoreWaitPoll:kbl */ - if (IS_KBL_REVID(dev_priv, KBL_REVID_A0, KBL_REVID_E0)) { + if (IS_KBL_REVID(i915, KBL_REVID_A0, KBL_REVID_E0)) { struct intel_engine_cs *engine; unsigned int tmp; - for_each_engine(engine, dev_priv, tmp) { + for_each_engine(engine, i915, tmp) { if (engine->id == RCS) continue; - I915_WRITE(RING_SEMA_WAIT_POLL(engine->mmio_base), 1); + wa_write(wal, + RING_SEMA_WAIT_POLL(engine->mmio_base), + 1); } } } -static void glk_gt_workarounds_apply(struct drm_i915_private *dev_priv) +static void glk_gt_workarounds_init(struct drm_i915_private *i915) { - gen9_gt_workarounds_apply(dev_priv); + gen9_gt_workarounds_init(i915); } -static void cfl_gt_workarounds_apply(struct drm_i915_private *dev_priv) +static void cfl_gt_workarounds_init(struct drm_i915_private *i915) { - gen9_gt_workarounds_apply(dev_priv); + struct i915_wa_list *wal = &i915->gt_wa_list; + + gen9_gt_workarounds_init(i915); /* WaEnableGapsTsvCreditFix:cfl */ - I915_WRITE(GEN8_GARBCNTL, - I915_READ(GEN8_GARBCNTL) | GEN9_GAPS_TSV_CREDIT_DISABLE); + wa_write_or(wal, + GEN8_GARBCNTL, + GEN9_GAPS_TSV_CREDIT_DISABLE); /* WaDisableGafsUnitClkGating:cfl */ - I915_WRITE(GEN7_UCGCTL4, - I915_READ(GEN7_UCGCTL4) | GEN8_EU_GAUNIT_CLOCK_GATE_DISABLE); + wa_write_or(wal, + GEN7_UCGCTL4, + GEN8_EU_GAUNIT_CLOCK_GATE_DISABLE); /* WaInPlaceDecompressionHang:cfl */ - I915_WRITE(GEN9_GAMT_ECO_REG_RW_IA, - I915_READ(GEN9_GAMT_ECO_REG_RW_IA) | - GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS); + wa_write_or(wal, + GEN9_GAMT_ECO_REG_RW_IA, + GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS); } static void wa_init_mcr(struct drm_i915_private *dev_priv) { const struct sseu_dev_info *sseu = &(INTEL_INFO(dev_priv)->sseu); - u32 mcr; + struct i915_wa_list *wal = &dev_priv->gt_wa_list; u32 mcr_slice_subslice_mask; /* @@ -770,8 +863,6 @@ static void wa_init_mcr(struct drm_i915_private *dev_priv) WARN_ON((enabled_mask & disabled_mask) != enabled_mask); } - mcr = I915_READ(GEN8_MCR_SELECTOR); - if (INTEL_GEN(dev_priv) >= 11) mcr_slice_subslice_mask = GEN11_MCR_SLICE_MASK | GEN11_MCR_SUBSLICE_MASK; @@ -789,148 +880,223 @@ static void wa_init_mcr(struct drm_i915_private *dev_priv) * occasions, such as INSTDONE, where this value is dependent * on s/ss combo, the read should be done with read_subslice_reg. */ - mcr &= ~mcr_slice_subslice_mask; - mcr |= intel_calculate_mcr_s_ss_select(dev_priv); - I915_WRITE(GEN8_MCR_SELECTOR, mcr); + wa_write_masked_or(wal, + GEN8_MCR_SELECTOR, + mcr_slice_subslice_mask, + intel_calculate_mcr_s_ss_select(dev_priv)); } -static void cnl_gt_workarounds_apply(struct drm_i915_private *dev_priv) +static void cnl_gt_workarounds_init(struct drm_i915_private *i915) { - wa_init_mcr(dev_priv); + struct i915_wa_list *wal = &i915->gt_wa_list; + + wa_init_mcr(i915); /* WaDisableI2mCycleOnWRPort:cnl (pre-prod) */ - if (IS_CNL_REVID(dev_priv, CNL_REVID_B0, CNL_REVID_B0)) - I915_WRITE(GAMT_CHKN_BIT_REG, - I915_READ(GAMT_CHKN_BIT_REG) | - GAMT_CHKN_DISABLE_I2M_CYCLE_ON_WR_PORT); + if (IS_CNL_REVID(i915, CNL_REVID_B0, CNL_REVID_B0)) + wa_write_or(wal, + GAMT_CHKN_BIT_REG, + GAMT_CHKN_DISABLE_I2M_CYCLE_ON_WR_PORT); /* WaInPlaceDecompressionHang:cnl */ - I915_WRITE(GEN9_GAMT_ECO_REG_RW_IA, - I915_READ(GEN9_GAMT_ECO_REG_RW_IA) | - GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS); + wa_write_or(wal, + GEN9_GAMT_ECO_REG_RW_IA, + GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS); /* WaEnablePreemptionGranularityControlByUMD:cnl */ - I915_WRITE(GEN7_FF_SLICE_CS_CHICKEN1, - _MASKED_BIT_ENABLE(GEN9_FFSC_PERCTX_PREEMPT_CTRL)); + wa_masked_en(wal, + GEN7_FF_SLICE_CS_CHICKEN1, + GEN9_FFSC_PERCTX_PREEMPT_CTRL); } -static void icl_gt_workarounds_apply(struct drm_i915_private *dev_priv) +static void icl_gt_workarounds_init(struct drm_i915_private *i915) { - wa_init_mcr(dev_priv); + struct i915_wa_list *wal = &i915->gt_wa_list; + + wa_init_mcr(i915); /* This is not an Wa. Enable for better image quality */ - I915_WRITE(_3D_CHICKEN3, - _MASKED_BIT_ENABLE(_3D_CHICKEN3_AA_LINE_QUALITY_FIX_ENABLE)); + wa_masked_en(wal, + _3D_CHICKEN3, + _3D_CHICKEN3_AA_LINE_QUALITY_FIX_ENABLE); /* WaInPlaceDecompressionHang:icl */ - I915_WRITE(GEN9_GAMT_ECO_REG_RW_IA, I915_READ(GEN9_GAMT_ECO_REG_RW_IA) | - GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS); + wa_write_or(wal, + GEN9_GAMT_ECO_REG_RW_IA, + GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS); /* WaPipelineFlushCoherentLines:icl */ - I915_WRITE(GEN8_L3SQCREG4, I915_READ(GEN8_L3SQCREG4) | - GEN8_LQSC_FLUSH_COHERENT_LINES); + wa_write_or(wal, + GEN8_L3SQCREG4, + GEN8_LQSC_FLUSH_COHERENT_LINES); /* Wa_1405543622:icl * Formerly known as WaGAPZPriorityScheme */ - I915_WRITE(GEN8_GARBCNTL, I915_READ(GEN8_GARBCNTL) | - GEN11_ARBITRATION_PRIO_ORDER_MASK); + wa_write_or(wal, + GEN8_GARBCNTL, + GEN11_ARBITRATION_PRIO_ORDER_MASK); /* Wa_1604223664:icl * Formerly known as WaL3BankAddressHashing */ - I915_WRITE(GEN8_GARBCNTL, - (I915_READ(GEN8_GARBCNTL) & ~GEN11_HASH_CTRL_EXCL_MASK) | - GEN11_HASH_CTRL_EXCL_BIT0); - I915_WRITE(GEN11_GLBLINVL, - (I915_READ(GEN11_GLBLINVL) & ~GEN11_BANK_HASH_ADDR_EXCL_MASK) | - GEN11_BANK_HASH_ADDR_EXCL_BIT0); + wa_write_masked_or(wal, + GEN8_GARBCNTL, + GEN11_HASH_CTRL_EXCL_MASK, + GEN11_HASH_CTRL_EXCL_BIT0); + wa_write_masked_or(wal, + GEN11_GLBLINVL, + GEN11_BANK_HASH_ADDR_EXCL_MASK, + GEN11_BANK_HASH_ADDR_EXCL_BIT0); /* WaModifyGamTlbPartitioning:icl */ - I915_WRITE(GEN11_GACB_PERF_CTRL, - (I915_READ(GEN11_GACB_PERF_CTRL) & ~GEN11_HASH_CTRL_MASK) | - GEN11_HASH_CTRL_BIT0 | GEN11_HASH_CTRL_BIT4); + wa_write_masked_or(wal, + GEN11_GACB_PERF_CTRL, + GEN11_HASH_CTRL_MASK, + GEN11_HASH_CTRL_BIT0 | GEN11_HASH_CTRL_BIT4); /* Wa_1405733216:icl * Formerly known as WaDisableCleanEvicts */ - I915_WRITE(GEN8_L3SQCREG4, I915_READ(GEN8_L3SQCREG4) | - GEN11_LQSC_CLEAN_EVICT_DISABLE); + wa_write_or(wal, + GEN8_L3SQCREG4, + GEN11_LQSC_CLEAN_EVICT_DISABLE); /* Wa_1405766107:icl * Formerly known as WaCL2SFHalfMaxAlloc */ - I915_WRITE(GEN11_LSN_UNSLCVC, I915_READ(GEN11_LSN_UNSLCVC) | - GEN11_LSN_UNSLCVC_GAFS_HALF_SF_MAXALLOC | - GEN11_LSN_UNSLCVC_GAFS_HALF_CL2_MAXALLOC); + wa_write_or(wal, + GEN11_LSN_UNSLCVC, + GEN11_LSN_UNSLCVC_GAFS_HALF_SF_MAXALLOC | + GEN11_LSN_UNSLCVC_GAFS_HALF_CL2_MAXALLOC); /* Wa_220166154:icl * Formerly known as WaDisCtxReload */ - I915_WRITE(GAMW_ECO_DEV_RW_IA_REG, I915_READ(GAMW_ECO_DEV_RW_IA_REG) | - GAMW_ECO_DEV_CTX_RELOAD_DISABLE); + wa_write_or(wal, + GEN8_GAMW_ECO_DEV_RW_IA, + GAMW_ECO_DEV_CTX_RELOAD_DISABLE); /* Wa_1405779004:icl (pre-prod) */ - if (IS_ICL_REVID(dev_priv, ICL_REVID_A0, ICL_REVID_A0)) - I915_WRITE(SLICE_UNIT_LEVEL_CLKGATE, - I915_READ(SLICE_UNIT_LEVEL_CLKGATE) | - MSCUNIT_CLKGATE_DIS); + if (IS_ICL_REVID(i915, ICL_REVID_A0, ICL_REVID_A0)) + wa_write_or(wal, + SLICE_UNIT_LEVEL_CLKGATE, + MSCUNIT_CLKGATE_DIS); /* Wa_1406680159:icl */ - I915_WRITE(SUBSLICE_UNIT_LEVEL_CLKGATE, - I915_READ(SUBSLICE_UNIT_LEVEL_CLKGATE) | - GWUNIT_CLKGATE_DIS); + wa_write_or(wal, + SUBSLICE_UNIT_LEVEL_CLKGATE, + GWUNIT_CLKGATE_DIS); /* Wa_1604302699:icl */ - I915_WRITE(GEN10_L3_CHICKEN_MODE_REGISTER, - I915_READ(GEN10_L3_CHICKEN_MODE_REGISTER) | - GEN11_I2M_WRITE_DISABLE); + wa_write_or(wal, + GEN10_L3_CHICKEN_MODE_REGISTER, + GEN11_I2M_WRITE_DISABLE); /* Wa_1406838659:icl (pre-prod) */ - if (IS_ICL_REVID(dev_priv, ICL_REVID_A0, ICL_REVID_B0)) - I915_WRITE(INF_UNIT_LEVEL_CLKGATE, - I915_READ(INF_UNIT_LEVEL_CLKGATE) | - CGPSF_CLKGATE_DIS); + if (IS_ICL_REVID(i915, ICL_REVID_A0, ICL_REVID_B0)) + wa_write_or(wal, + INF_UNIT_LEVEL_CLKGATE, + CGPSF_CLKGATE_DIS); /* WaForwardProgressSoftReset:icl */ - I915_WRITE(GEN10_SCRATCH_LNCF2, - I915_READ(GEN10_SCRATCH_LNCF2) | - PMFLUSHDONE_LNICRSDROP | - PMFLUSH_GAPL3UNBLOCK | - PMFLUSHDONE_LNEBLK); + wa_write_or(wal, + GEN10_SCRATCH_LNCF2, + PMFLUSHDONE_LNICRSDROP | + PMFLUSH_GAPL3UNBLOCK | + PMFLUSHDONE_LNEBLK); /* Wa_1406463099:icl * Formerly known as WaGamTlbPendError */ - I915_WRITE(GAMT_CHKN_BIT_REG, - I915_READ(GAMT_CHKN_BIT_REG) | - GAMT_CHKN_DISABLE_L3_COH_PIPE); + wa_write_or(wal, + GAMT_CHKN_BIT_REG, + GAMT_CHKN_DISABLE_L3_COH_PIPE); } -void intel_gt_workarounds_apply(struct drm_i915_private *dev_priv) +void intel_gt_init_workarounds(struct drm_i915_private *i915) { - if (INTEL_GEN(dev_priv) < 8) + struct i915_wa_list *wal = &i915->gt_wa_list; + + wa_init_start(wal, "GT"); + + if (INTEL_GEN(i915) < 8) return; - else if (IS_BROADWELL(dev_priv)) - bdw_gt_workarounds_apply(dev_priv); - else if (IS_CHERRYVIEW(dev_priv)) - chv_gt_workarounds_apply(dev_priv); - else if (IS_SKYLAKE(dev_priv)) - skl_gt_workarounds_apply(dev_priv); - else if (IS_BROXTON(dev_priv)) - bxt_gt_workarounds_apply(dev_priv); - else if (IS_KABYLAKE(dev_priv)) - kbl_gt_workarounds_apply(dev_priv); - else if (IS_GEMINILAKE(dev_priv)) - glk_gt_workarounds_apply(dev_priv); - else if (IS_COFFEELAKE(dev_priv)) - cfl_gt_workarounds_apply(dev_priv); - else if (IS_CANNONLAKE(dev_priv)) - cnl_gt_workarounds_apply(dev_priv); - else if (IS_ICELAKE(dev_priv)) - icl_gt_workarounds_apply(dev_priv); + else if (IS_BROADWELL(i915)) + return; + else if (IS_CHERRYVIEW(i915)) + return; + else if (IS_SKYLAKE(i915)) + skl_gt_workarounds_init(i915); + else if (IS_BROXTON(i915)) + bxt_gt_workarounds_init(i915); + else if (IS_KABYLAKE(i915)) + kbl_gt_workarounds_init(i915); + else if (IS_GEMINILAKE(i915)) + glk_gt_workarounds_init(i915); + else if (IS_COFFEELAKE(i915)) + cfl_gt_workarounds_init(i915); + else if (IS_CANNONLAKE(i915)) + cnl_gt_workarounds_init(i915); + else if (IS_ICELAKE(i915)) + icl_gt_workarounds_init(i915); else - MISSING_CASE(INTEL_GEN(dev_priv)); + MISSING_CASE(INTEL_GEN(i915)); + + wa_init_finish(wal); +} + +static enum forcewake_domains +wal_get_fw_for_rmw(struct drm_i915_private *dev_priv, + const struct i915_wa_list *wal) +{ + enum forcewake_domains fw = 0; + struct i915_wa *wa; + unsigned int i; + + for (i = 0, wa = wal->list; i < wal->count; i++, wa++) + fw |= intel_uncore_forcewake_for_reg(dev_priv, + wa->reg, + FW_REG_READ | + FW_REG_WRITE); + + return fw; +} + +static void +wa_list_apply(struct drm_i915_private *dev_priv, const struct i915_wa_list *wal) +{ + enum forcewake_domains fw; + unsigned long flags; + struct i915_wa *wa; + unsigned int i; + + if (!wal->count) + return; + + fw = wal_get_fw_for_rmw(dev_priv, wal); + + spin_lock_irqsave(&dev_priv->uncore.lock, flags); + intel_uncore_forcewake_get__locked(dev_priv, fw); + + for (i = 0, wa = wal->list; i < wal->count; i++, wa++) { + u32 val = I915_READ_FW(wa->reg); + + val &= ~wa->mask; + val |= wa->val; + + I915_WRITE_FW(wa->reg, val); + } + + intel_uncore_forcewake_put__locked(dev_priv, fw); + spin_unlock_irqrestore(&dev_priv->uncore.lock, flags); + + DRM_DEBUG_DRIVER("Applied %u %s workarounds\n", wal->count, wal->name); +} + +void intel_gt_apply_workarounds(struct drm_i915_private *dev_priv) +{ + wa_list_apply(dev_priv, &dev_priv->gt_wa_list); } struct whitelist { diff --git a/drivers/gpu/drm/i915/intel_workarounds.h b/drivers/gpu/drm/i915/intel_workarounds.h index b11d0623e626..263106600fdc 100644 --- a/drivers/gpu/drm/i915/intel_workarounds.h +++ b/drivers/gpu/drm/i915/intel_workarounds.h @@ -7,10 +7,31 @@ #ifndef _I915_WORKAROUNDS_H_ #define _I915_WORKAROUNDS_H_ +#include + +struct i915_wa { + i915_reg_t reg; + u32 mask; + u32 val; +}; + +struct i915_wa_list { + const char *name; + struct i915_wa *list; + unsigned int count; +}; + +static inline void intel_wa_list_free(struct i915_wa_list *wal) +{ + kfree(wal->list); + memset(wal, 0, sizeof(*wal)); +} + int intel_ctx_workarounds_init(struct drm_i915_private *dev_priv); int intel_ctx_workarounds_emit(struct i915_request *rq); -void intel_gt_workarounds_apply(struct drm_i915_private *dev_priv); +void intel_gt_init_workarounds(struct drm_i915_private *dev_priv); +void intel_gt_apply_workarounds(struct drm_i915_private *dev_priv); void intel_whitelist_workarounds_apply(struct intel_engine_cs *engine); -- cgit v1.2.3 From 90098efacc4c3e2e4f6262a657d6b520ecfb2555 Mon Sep 17 00:00:00 2001 From: Tvrtko Ursulin Date: Wed, 5 Dec 2018 11:33:24 +0000 Subject: drm/i915: Introduce per-engine workarounds We stopped re-applying the GT workarounds after engine reset since commit 59b449d5c82a ("drm/i915: Split out functions for different kinds of workarounds"). Issue with this is that some of the GT workarounds live in the MMIO space which gets lost during engine resets. So far the registers in 0x2xxx and 0xbxxx address range have been identified to be affected. This losing of applied workarounds has obvious negative effects and can even lead to hard system hangs (see the linked Bugzilla). Rather than just restoring this re-application, because we have also observed that it is not safe to just re-write all GT workarounds after engine resets (GPU might be live and weird hardware states can happen), we introduce a new class of per-engine workarounds and move only the affected GT workarounds over. Using the framework introduced in the previous patch, we therefore after engine reset, re-apply only the workarounds living in the affected MMIO address ranges. v2: * Move Wa_1406609255:icl to engine workarounds as well. * Rename API. (Chris Wilson) * Drop redundant IS_KABYLAKE. (Chris Wilson) * Re-order engine wa/ init so latest platforms are first. (Rodrigo Vivi) Signed-off-by: Tvrtko Ursulin Bugzilla: https://bugzilla.freedesktop.org/show_bug.cgi?id=107945 Fixes: 59b449d5c82a ("drm/i915: Split out functions for different kinds of workarounds") Cc: Mika Kuoppala Cc: Ville Syrjälä Cc: Chris Wilson Cc: Jani Nikula Cc: Joonas Lahtinen Cc: Rodrigo Vivi Cc: intel-gfx@lists.freedesktop.org Acked-by: Rodrigo Vivi Reviewed-by: Chris Wilson Link: https://patchwork.freedesktop.org/patch/msgid/20181203133341.10258-1-tvrtko.ursulin@linux.intel.com (cherry picked from commit 4a15c75c42460252a63d30f03b4766a52945fb47) Signed-off-by: Joonas Lahtinen --- drivers/gpu/drm/i915/intel_engine_cs.c | 2 + drivers/gpu/drm/i915/intel_lrc.c | 4 + drivers/gpu/drm/i915/intel_ringbuffer.h | 2 + drivers/gpu/drm/i915/intel_workarounds.c | 257 +++++++++++++++++-------------- drivers/gpu/drm/i915/intel_workarounds.h | 3 + 5 files changed, 151 insertions(+), 117 deletions(-) diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c index 217ed3ee1cab..cdfa6b21cbff 100644 --- a/drivers/gpu/drm/i915/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/intel_engine_cs.c @@ -720,6 +720,8 @@ void intel_engine_cleanup_common(struct intel_engine_cs *engine) __intel_context_unpin(i915->kernel_context, engine); i915_timeline_fini(&engine->timeline); + + intel_wa_list_free(&engine->wa_list); } u64 intel_engine_get_active_head(const struct intel_engine_cs *engine) diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c index 37c94a54efcb..4acb24c90c68 100644 --- a/drivers/gpu/drm/i915/intel_lrc.c +++ b/drivers/gpu/drm/i915/intel_lrc.c @@ -1793,6 +1793,8 @@ static bool unexpected_starting_state(struct intel_engine_cs *engine) static int gen8_init_common_ring(struct intel_engine_cs *engine) { + intel_engine_apply_workarounds(engine); + intel_mocs_init_engine(engine); intel_engine_reset_breadcrumbs(engine); @@ -2491,6 +2493,8 @@ int logical_render_ring_init(struct intel_engine_cs *engine) ret); } + intel_engine_init_workarounds(engine); + return 0; err_cleanup_common: diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h index 2dfa585712c2..04c61307f4d1 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.h +++ b/drivers/gpu/drm/i915/intel_ringbuffer.h @@ -15,6 +15,7 @@ #include "i915_selftest.h" #include "i915_timeline.h" #include "intel_gpu_commands.h" +#include "intel_workarounds.h" struct drm_printer; struct i915_sched_attr; @@ -440,6 +441,7 @@ struct intel_engine_cs { struct intel_hw_status_page status_page; struct i915_ctx_workarounds wa_ctx; + struct i915_wa_list wa_list; struct i915_vma *scratch; u32 irq_keep_mask; /* always keep these interrupts */ diff --git a/drivers/gpu/drm/i915/intel_workarounds.c b/drivers/gpu/drm/i915/intel_workarounds.c index 9ac3e086a46c..6e580891db96 100644 --- a/drivers/gpu/drm/i915/intel_workarounds.c +++ b/drivers/gpu/drm/i915/intel_workarounds.c @@ -661,17 +661,6 @@ static void gen9_gt_workarounds_init(struct drm_i915_private *i915) { struct i915_wa_list *wal = &i915->gt_wa_list; - /* WaContextSwitchWithConcurrentTLBInvalidate:skl,bxt,kbl,glk,cfl */ - wa_masked_en(wal, - GEN9_CSFE_CHICKEN1_RCS, - GEN9_PREEMPT_GPGPU_SYNC_SWITCH_DISABLE); - - - /* WaEnableLbsSlaRetryTimerDecrement:skl,bxt,kbl,glk,cfl */ - wa_write_or(wal, - BDW_SCRATCH1, - GEN9_LBS_SLA_RETRY_TIMER_DECREMENT_ENABLE); - /* WaDisableKillLogic:bxt,skl,kbl */ if (!IS_COFFEELAKE(i915)) wa_write_or(wal, @@ -693,24 +682,6 @@ static void gen9_gt_workarounds_init(struct drm_i915_private *i915) wa_write_or(wal, GAM_ECOCHK, BDW_DISABLE_HDC_INVALIDATION); - - /* WaProgramL3SqcReg1DefaultForPerf:bxt,glk */ - if (IS_GEN9_LP(i915)) - wa_write_masked_or(wal, - GEN8_L3SQCREG1, - L3_PRIO_CREDITS_MASK, - L3_GENERAL_PRIO_CREDITS(62) | - L3_HIGH_PRIO_CREDITS(2)); - - /* WaOCLCoherentLineFlush:skl,bxt,kbl,cfl */ - wa_write_or(wal, - GEN8_L3SQCREG4, - GEN8_LQSC_FLUSH_COHERENT_LINES); - - /* WaEnablePreemptionGranularityControlByUMD:skl,bxt,kbl,cfl,[cnl] */ - wa_masked_en(wal, - GEN7_FF_SLICE_CS_CHICKEN1, - GEN9_FFSC_PERCTX_PREEMPT_CTRL); } static void skl_gt_workarounds_init(struct drm_i915_private *i915) @@ -719,11 +690,6 @@ static void skl_gt_workarounds_init(struct drm_i915_private *i915) gen9_gt_workarounds_init(i915); - /* WaEnableGapsTsvCreditFix:skl */ - wa_write_or(wal, - GEN8_GARBCNTL, - GEN9_GAPS_TSV_CREDIT_DISABLE); - /* WaDisableGafsUnitClkGating:skl */ wa_write_or(wal, GEN7_UCGCTL4, @@ -742,11 +708,6 @@ static void bxt_gt_workarounds_init(struct drm_i915_private *i915) gen9_gt_workarounds_init(i915); - /* WaDisablePooledEuLoadBalancingFix:bxt */ - wa_masked_en(wal, - FF_SLICE_CS_CHICKEN2, - GEN9_POOLED_EU_LOAD_BALANCING_FIX_DISABLE); - /* WaInPlaceDecompressionHang:bxt */ wa_write_or(wal, GEN9_GAMT_ECO_REG_RW_IA, @@ -759,11 +720,6 @@ static void kbl_gt_workarounds_init(struct drm_i915_private *i915) gen9_gt_workarounds_init(i915); - /* WaEnableGapsTsvCreditFix:kbl */ - wa_write_or(wal, - GEN8_GARBCNTL, - GEN9_GAPS_TSV_CREDIT_DISABLE); - /* WaDisableDynamicCreditSharing:kbl */ if (IS_KBL_REVID(i915, 0, KBL_REVID_B0)) wa_write_or(wal, @@ -779,21 +735,6 @@ static void kbl_gt_workarounds_init(struct drm_i915_private *i915) wa_write_or(wal, GEN9_GAMT_ECO_REG_RW_IA, GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS); - - /* WaKBLVECSSemaphoreWaitPoll:kbl */ - if (IS_KBL_REVID(i915, KBL_REVID_A0, KBL_REVID_E0)) { - struct intel_engine_cs *engine; - unsigned int tmp; - - for_each_engine(engine, i915, tmp) { - if (engine->id == RCS) - continue; - - wa_write(wal, - RING_SEMA_WAIT_POLL(engine->mmio_base), - 1); - } - } } static void glk_gt_workarounds_init(struct drm_i915_private *i915) @@ -807,11 +748,6 @@ static void cfl_gt_workarounds_init(struct drm_i915_private *i915) gen9_gt_workarounds_init(i915); - /* WaEnableGapsTsvCreditFix:cfl */ - wa_write_or(wal, - GEN8_GARBCNTL, - GEN9_GAPS_TSV_CREDIT_DISABLE); - /* WaDisableGafsUnitClkGating:cfl */ wa_write_or(wal, GEN7_UCGCTL4, @@ -902,11 +838,6 @@ static void cnl_gt_workarounds_init(struct drm_i915_private *i915) wa_write_or(wal, GEN9_GAMT_ECO_REG_RW_IA, GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS); - - /* WaEnablePreemptionGranularityControlByUMD:cnl */ - wa_masked_en(wal, - GEN7_FF_SLICE_CS_CHICKEN1, - GEN9_FFSC_PERCTX_PREEMPT_CTRL); } static void icl_gt_workarounds_init(struct drm_i915_private *i915) @@ -915,53 +846,17 @@ static void icl_gt_workarounds_init(struct drm_i915_private *i915) wa_init_mcr(i915); - /* This is not an Wa. Enable for better image quality */ - wa_masked_en(wal, - _3D_CHICKEN3, - _3D_CHICKEN3_AA_LINE_QUALITY_FIX_ENABLE); - /* WaInPlaceDecompressionHang:icl */ wa_write_or(wal, GEN9_GAMT_ECO_REG_RW_IA, GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS); - /* WaPipelineFlushCoherentLines:icl */ - wa_write_or(wal, - GEN8_L3SQCREG4, - GEN8_LQSC_FLUSH_COHERENT_LINES); - - /* Wa_1405543622:icl - * Formerly known as WaGAPZPriorityScheme - */ - wa_write_or(wal, - GEN8_GARBCNTL, - GEN11_ARBITRATION_PRIO_ORDER_MASK); - - /* Wa_1604223664:icl - * Formerly known as WaL3BankAddressHashing - */ - wa_write_masked_or(wal, - GEN8_GARBCNTL, - GEN11_HASH_CTRL_EXCL_MASK, - GEN11_HASH_CTRL_EXCL_BIT0); - wa_write_masked_or(wal, - GEN11_GLBLINVL, - GEN11_BANK_HASH_ADDR_EXCL_MASK, - GEN11_BANK_HASH_ADDR_EXCL_BIT0); - /* WaModifyGamTlbPartitioning:icl */ wa_write_masked_or(wal, GEN11_GACB_PERF_CTRL, GEN11_HASH_CTRL_MASK, GEN11_HASH_CTRL_BIT0 | GEN11_HASH_CTRL_BIT4); - /* Wa_1405733216:icl - * Formerly known as WaDisableCleanEvicts - */ - wa_write_or(wal, - GEN8_L3SQCREG4, - GEN11_LQSC_CLEAN_EVICT_DISABLE); - /* Wa_1405766107:icl * Formerly known as WaCL2SFHalfMaxAlloc */ @@ -988,24 +883,12 @@ static void icl_gt_workarounds_init(struct drm_i915_private *i915) SUBSLICE_UNIT_LEVEL_CLKGATE, GWUNIT_CLKGATE_DIS); - /* Wa_1604302699:icl */ - wa_write_or(wal, - GEN10_L3_CHICKEN_MODE_REGISTER, - GEN11_I2M_WRITE_DISABLE); - /* Wa_1406838659:icl (pre-prod) */ if (IS_ICL_REVID(i915, ICL_REVID_A0, ICL_REVID_B0)) wa_write_or(wal, INF_UNIT_LEVEL_CLKGATE, CGPSF_CLKGATE_DIS); - /* WaForwardProgressSoftReset:icl */ - wa_write_or(wal, - GEN10_SCRATCH_LNCF2, - PMFLUSHDONE_LNICRSDROP | - PMFLUSH_GAPL3UNBLOCK | - PMFLUSHDONE_LNEBLK); - /* Wa_1406463099:icl * Formerly known as WaGamTlbPendError */ @@ -1243,6 +1126,146 @@ void intel_whitelist_workarounds_apply(struct intel_engine_cs *engine) whitelist_apply(engine, whitelist_build(engine, &w)); } +static void rcs_engine_wa_init(struct intel_engine_cs *engine) +{ + struct drm_i915_private *i915 = engine->i915; + struct i915_wa_list *wal = &engine->wa_list; + + if (IS_ICELAKE(i915)) { + /* This is not an Wa. Enable for better image quality */ + wa_masked_en(wal, + _3D_CHICKEN3, + _3D_CHICKEN3_AA_LINE_QUALITY_FIX_ENABLE); + + /* WaPipelineFlushCoherentLines:icl */ + wa_write_or(wal, + GEN8_L3SQCREG4, + GEN8_LQSC_FLUSH_COHERENT_LINES); + + /* + * Wa_1405543622:icl + * Formerly known as WaGAPZPriorityScheme + */ + wa_write_or(wal, + GEN8_GARBCNTL, + GEN11_ARBITRATION_PRIO_ORDER_MASK); + + /* + * Wa_1604223664:icl + * Formerly known as WaL3BankAddressHashing + */ + wa_write_masked_or(wal, + GEN8_GARBCNTL, + GEN11_HASH_CTRL_EXCL_MASK, + GEN11_HASH_CTRL_EXCL_BIT0); + wa_write_masked_or(wal, + GEN11_GLBLINVL, + GEN11_BANK_HASH_ADDR_EXCL_MASK, + GEN11_BANK_HASH_ADDR_EXCL_BIT0); + + /* + * Wa_1405733216:icl + * Formerly known as WaDisableCleanEvicts + */ + wa_write_or(wal, + GEN8_L3SQCREG4, + GEN11_LQSC_CLEAN_EVICT_DISABLE); + + /* Wa_1604302699:icl */ + wa_write_or(wal, + GEN10_L3_CHICKEN_MODE_REGISTER, + GEN11_I2M_WRITE_DISABLE); + + /* WaForwardProgressSoftReset:icl */ + wa_write_or(wal, + GEN10_SCRATCH_LNCF2, + PMFLUSHDONE_LNICRSDROP | + PMFLUSH_GAPL3UNBLOCK | + PMFLUSHDONE_LNEBLK); + } + + if (IS_GEN9(i915) || IS_CANNONLAKE(i915)) { + /* WaEnablePreemptionGranularityControlByUMD:skl,bxt,kbl,cfl,cnl */ + wa_masked_en(wal, + GEN7_FF_SLICE_CS_CHICKEN1, + GEN9_FFSC_PERCTX_PREEMPT_CTRL); + } + + if (IS_SKYLAKE(i915) || IS_KABYLAKE(i915) || IS_COFFEELAKE(i915)) { + /* WaEnableGapsTsvCreditFix:skl,kbl,cfl */ + wa_write_or(wal, + GEN8_GARBCNTL, + GEN9_GAPS_TSV_CREDIT_DISABLE); + } + + if (IS_BROXTON(i915)) { + /* WaDisablePooledEuLoadBalancingFix:bxt */ + wa_masked_en(wal, + FF_SLICE_CS_CHICKEN2, + GEN9_POOLED_EU_LOAD_BALANCING_FIX_DISABLE); + } + + if (IS_GEN9(i915)) { + /* WaContextSwitchWithConcurrentTLBInvalidate:skl,bxt,kbl,glk,cfl */ + wa_masked_en(wal, + GEN9_CSFE_CHICKEN1_RCS, + GEN9_PREEMPT_GPGPU_SYNC_SWITCH_DISABLE); + + /* WaEnableLbsSlaRetryTimerDecrement:skl,bxt,kbl,glk,cfl */ + wa_write_or(wal, + BDW_SCRATCH1, + GEN9_LBS_SLA_RETRY_TIMER_DECREMENT_ENABLE); + + /* WaProgramL3SqcReg1DefaultForPerf:bxt,glk */ + if (IS_GEN9_LP(i915)) + wa_write_masked_or(wal, + GEN8_L3SQCREG1, + L3_PRIO_CREDITS_MASK, + L3_GENERAL_PRIO_CREDITS(62) | + L3_HIGH_PRIO_CREDITS(2)); + + /* WaOCLCoherentLineFlush:skl,bxt,kbl,cfl */ + wa_write_or(wal, + GEN8_L3SQCREG4, + GEN8_LQSC_FLUSH_COHERENT_LINES); + } +} + +static void xcs_engine_wa_init(struct intel_engine_cs *engine) +{ + struct drm_i915_private *i915 = engine->i915; + struct i915_wa_list *wal = &engine->wa_list; + + /* WaKBLVECSSemaphoreWaitPoll:kbl */ + if (IS_KBL_REVID(i915, KBL_REVID_A0, KBL_REVID_E0)) { + wa_write(wal, + RING_SEMA_WAIT_POLL(engine->mmio_base), + 1); + } +} + +void intel_engine_init_workarounds(struct intel_engine_cs *engine) +{ + struct i915_wa_list *wal = &engine->wa_list; + + if (GEM_WARN_ON(INTEL_GEN(engine->i915) < 8)) + return; + + wa_init_start(wal, engine->name); + + if (engine->id == RCS) + rcs_engine_wa_init(engine); + else + xcs_engine_wa_init(engine); + + wa_init_finish(wal); +} + +void intel_engine_apply_workarounds(struct intel_engine_cs *engine) +{ + wa_list_apply(engine->i915, &engine->wa_list); +} + #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST) #include "selftests/intel_workarounds.c" #endif diff --git a/drivers/gpu/drm/i915/intel_workarounds.h b/drivers/gpu/drm/i915/intel_workarounds.h index 263106600fdc..979695a53964 100644 --- a/drivers/gpu/drm/i915/intel_workarounds.h +++ b/drivers/gpu/drm/i915/intel_workarounds.h @@ -35,4 +35,7 @@ void intel_gt_apply_workarounds(struct drm_i915_private *dev_priv); void intel_whitelist_workarounds_apply(struct intel_engine_cs *engine); +void intel_engine_init_workarounds(struct intel_engine_cs *engine); +void intel_engine_apply_workarounds(struct intel_engine_cs *engine); + #endif -- cgit v1.2.3 From db2039fcfd5754d15986340152e4503737f68f8d Mon Sep 17 00:00:00 2001 From: Faiz Abbas Date: Wed, 21 Nov 2018 16:03:55 +0530 Subject: mmc: sdhci-omap: Fix DCRC error handling during tuning Commit 7d33c3581536 ("mmc: sdhci-omap: Workaround for Errata i802") disabled DCRC interrupts during tuning. This write to the interrupt enable register gets overwritten in sdhci_prepare_data() and the interrupt is not in fact disabled. Fix this by disabling the interrupt in the host->ier variable. Fixes: 7d33c3581536 ("mmc: sdhci-omap: Workaround for Errata i802") Cc: Signed-off-by: Faiz Abbas Acked-by: Adrian Hunter Signed-off-by: Ulf Hansson --- drivers/mmc/host/sdhci-omap.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/drivers/mmc/host/sdhci-omap.c b/drivers/mmc/host/sdhci-omap.c index 88347ce78f23..d264391616f9 100644 --- a/drivers/mmc/host/sdhci-omap.c +++ b/drivers/mmc/host/sdhci-omap.c @@ -288,9 +288,9 @@ static int sdhci_omap_execute_tuning(struct mmc_host *mmc, u32 opcode) struct device *dev = omap_host->dev; struct mmc_ios *ios = &mmc->ios; u32 start_window = 0, max_window = 0; + bool dcrc_was_enabled = false; u8 cur_match, prev_match = 0; u32 length = 0, max_len = 0; - u32 ier = host->ier; u32 phase_delay = 0; int ret = 0; u32 reg; @@ -317,9 +317,10 @@ static int sdhci_omap_execute_tuning(struct mmc_host *mmc, u32 opcode) * during the tuning procedure. So disable it during the * tuning procedure. */ - ier &= ~SDHCI_INT_DATA_CRC; - sdhci_writel(host, ier, SDHCI_INT_ENABLE); - sdhci_writel(host, ier, SDHCI_SIGNAL_ENABLE); + if (host->ier & SDHCI_INT_DATA_CRC) { + host->ier &= ~SDHCI_INT_DATA_CRC; + dcrc_was_enabled = true; + } while (phase_delay <= MAX_PHASE_DELAY) { sdhci_omap_set_dll(omap_host, phase_delay); @@ -366,6 +367,9 @@ tuning_error: ret: sdhci_reset(host, SDHCI_RESET_CMD | SDHCI_RESET_DATA); + /* Reenable forbidden interrupt */ + if (dcrc_was_enabled) + host->ier |= SDHCI_INT_DATA_CRC; sdhci_writel(host, host->ier, SDHCI_INT_ENABLE); sdhci_writel(host, host->ier, SDHCI_SIGNAL_ENABLE); return ret; -- cgit v1.2.3 From 9514063498cbff9a351f4bc25e1b1bfca8eccb7a Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Wed, 5 Dec 2018 06:28:20 -0500 Subject: media: mpeg2-ctrls.h: move MPEG2 state controls to non-public header The MPEG2 state controls for the cedrus stateless MPEG2 driver are not yet stable. Move them out of the public headers into media/mpeg2-ctrls.h. Eventually, once this has stabilized, they will be moved back to the public headers. Unfortunately I had to cast the control type to a u32 in two switch statements to prevent a compiler warning about a control type define not being part of the enum. Signed-off-by: Hans Verkuil Reviewed-by: Paul Kocialkowski Signed-off-by: Mauro Carvalho Chehab --- drivers/media/v4l2-core/v4l2-ctrls.c | 4 +- include/media/mpeg2-ctrls.h | 86 ++++++++++++++++++++++++++++++++++++ include/media/v4l2-ctrls.h | 6 +++ include/uapi/linux/v4l2-controls.h | 68 ---------------------------- include/uapi/linux/videodev2.h | 4 -- 5 files changed, 94 insertions(+), 74 deletions(-) create mode 100644 include/media/mpeg2-ctrls.h diff --git a/drivers/media/v4l2-core/v4l2-ctrls.c b/drivers/media/v4l2-core/v4l2-ctrls.c index 5f2b033a7a42..10b8d94edbef 100644 --- a/drivers/media/v4l2-core/v4l2-ctrls.c +++ b/drivers/media/v4l2-core/v4l2-ctrls.c @@ -1563,7 +1563,7 @@ static int std_validate(const struct v4l2_ctrl *ctrl, u32 idx, u64 offset; s64 val; - switch (ctrl->type) { + switch ((u32)ctrl->type) { case V4L2_CTRL_TYPE_INTEGER: return ROUND_TO_RANGE(ptr.p_s32[idx], u32, ctrl); case V4L2_CTRL_TYPE_INTEGER64: @@ -2232,7 +2232,7 @@ static struct v4l2_ctrl *v4l2_ctrl_new(struct v4l2_ctrl_handler *hdl, is_array = nr_of_dims > 0; /* Prefill elem_size for all types handled by std_type_ops */ - switch (type) { + switch ((u32)type) { case V4L2_CTRL_TYPE_INTEGER64: elem_size = sizeof(s64); break; diff --git a/include/media/mpeg2-ctrls.h b/include/media/mpeg2-ctrls.h new file mode 100644 index 000000000000..d21f40edc09e --- /dev/null +++ b/include/media/mpeg2-ctrls.h @@ -0,0 +1,86 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * These are the MPEG2 state controls for use with stateless MPEG-2 + * codec drivers. + * + * It turns out that these structs are not stable yet and will undergo + * more changes. So keep them private until they are stable and ready to + * become part of the official public API. + */ + +#ifndef _MPEG2_CTRLS_H_ +#define _MPEG2_CTRLS_H_ + +#define V4L2_CID_MPEG_VIDEO_MPEG2_SLICE_PARAMS (V4L2_CID_MPEG_BASE+250) +#define V4L2_CID_MPEG_VIDEO_MPEG2_QUANTIZATION (V4L2_CID_MPEG_BASE+251) + +/* enum v4l2_ctrl_type type values */ +#define V4L2_CTRL_TYPE_MPEG2_SLICE_PARAMS 0x0103 +#define V4L2_CTRL_TYPE_MPEG2_QUANTIZATION 0x0104 + +#define V4L2_MPEG2_PICTURE_CODING_TYPE_I 1 +#define V4L2_MPEG2_PICTURE_CODING_TYPE_P 2 +#define V4L2_MPEG2_PICTURE_CODING_TYPE_B 3 +#define V4L2_MPEG2_PICTURE_CODING_TYPE_D 4 + +struct v4l2_mpeg2_sequence { + /* ISO/IEC 13818-2, ITU-T Rec. H.262: Sequence header */ + __u16 horizontal_size; + __u16 vertical_size; + __u32 vbv_buffer_size; + + /* ISO/IEC 13818-2, ITU-T Rec. H.262: Sequence extension */ + __u8 profile_and_level_indication; + __u8 progressive_sequence; + __u8 chroma_format; + __u8 pad; +}; + +struct v4l2_mpeg2_picture { + /* ISO/IEC 13818-2, ITU-T Rec. H.262: Picture header */ + __u8 picture_coding_type; + + /* ISO/IEC 13818-2, ITU-T Rec. H.262: Picture coding extension */ + __u8 f_code[2][2]; + __u8 intra_dc_precision; + __u8 picture_structure; + __u8 top_field_first; + __u8 frame_pred_frame_dct; + __u8 concealment_motion_vectors; + __u8 q_scale_type; + __u8 intra_vlc_format; + __u8 alternate_scan; + __u8 repeat_first_field; + __u8 progressive_frame; + __u8 pad; +}; + +struct v4l2_ctrl_mpeg2_slice_params { + __u32 bit_size; + __u32 data_bit_offset; + + struct v4l2_mpeg2_sequence sequence; + struct v4l2_mpeg2_picture picture; + + /* ISO/IEC 13818-2, ITU-T Rec. H.262: Slice */ + __u8 quantiser_scale_code; + + __u8 backward_ref_index; + __u8 forward_ref_index; + __u8 pad; +}; + +struct v4l2_ctrl_mpeg2_quantization { + /* ISO/IEC 13818-2, ITU-T Rec. H.262: Quant matrix extension */ + __u8 load_intra_quantiser_matrix; + __u8 load_non_intra_quantiser_matrix; + __u8 load_chroma_intra_quantiser_matrix; + __u8 load_chroma_non_intra_quantiser_matrix; + + __u8 intra_quantiser_matrix[64]; + __u8 non_intra_quantiser_matrix[64]; + __u8 chroma_intra_quantiser_matrix[64]; + __u8 chroma_non_intra_quantiser_matrix[64]; +}; + +#endif diff --git a/include/media/v4l2-ctrls.h b/include/media/v4l2-ctrls.h index 83ce0593b275..d63cf227b0ab 100644 --- a/include/media/v4l2-ctrls.h +++ b/include/media/v4l2-ctrls.h @@ -22,6 +22,12 @@ #include #include +/* + * Include the mpeg2 stateless codec compound control definitions. + * This will move to the public headers once this API is fully stable. + */ +#include + /* forward references */ struct file; struct v4l2_ctrl_handler; diff --git a/include/uapi/linux/v4l2-controls.h b/include/uapi/linux/v4l2-controls.h index 998983a6e6b7..3dcfc6148f99 100644 --- a/include/uapi/linux/v4l2-controls.h +++ b/include/uapi/linux/v4l2-controls.h @@ -404,9 +404,6 @@ enum v4l2_mpeg_video_multi_slice_mode { #define V4L2_CID_MPEG_VIDEO_MV_V_SEARCH_RANGE (V4L2_CID_MPEG_BASE+228) #define V4L2_CID_MPEG_VIDEO_FORCE_KEY_FRAME (V4L2_CID_MPEG_BASE+229) -#define V4L2_CID_MPEG_VIDEO_MPEG2_SLICE_PARAMS (V4L2_CID_MPEG_BASE+250) -#define V4L2_CID_MPEG_VIDEO_MPEG2_QUANTIZATION (V4L2_CID_MPEG_BASE+251) - #define V4L2_CID_MPEG_VIDEO_H263_I_FRAME_QP (V4L2_CID_MPEG_BASE+300) #define V4L2_CID_MPEG_VIDEO_H263_P_FRAME_QP (V4L2_CID_MPEG_BASE+301) #define V4L2_CID_MPEG_VIDEO_H263_B_FRAME_QP (V4L2_CID_MPEG_BASE+302) @@ -1097,69 +1094,4 @@ enum v4l2_detect_md_mode { #define V4L2_CID_DETECT_MD_THRESHOLD_GRID (V4L2_CID_DETECT_CLASS_BASE + 3) #define V4L2_CID_DETECT_MD_REGION_GRID (V4L2_CID_DETECT_CLASS_BASE + 4) -#define V4L2_MPEG2_PICTURE_CODING_TYPE_I 1 -#define V4L2_MPEG2_PICTURE_CODING_TYPE_P 2 -#define V4L2_MPEG2_PICTURE_CODING_TYPE_B 3 -#define V4L2_MPEG2_PICTURE_CODING_TYPE_D 4 - -struct v4l2_mpeg2_sequence { - /* ISO/IEC 13818-2, ITU-T Rec. H.262: Sequence header */ - __u16 horizontal_size; - __u16 vertical_size; - __u32 vbv_buffer_size; - - /* ISO/IEC 13818-2, ITU-T Rec. H.262: Sequence extension */ - __u8 profile_and_level_indication; - __u8 progressive_sequence; - __u8 chroma_format; - __u8 pad; -}; - -struct v4l2_mpeg2_picture { - /* ISO/IEC 13818-2, ITU-T Rec. H.262: Picture header */ - __u8 picture_coding_type; - - /* ISO/IEC 13818-2, ITU-T Rec. H.262: Picture coding extension */ - __u8 f_code[2][2]; - __u8 intra_dc_precision; - __u8 picture_structure; - __u8 top_field_first; - __u8 frame_pred_frame_dct; - __u8 concealment_motion_vectors; - __u8 q_scale_type; - __u8 intra_vlc_format; - __u8 alternate_scan; - __u8 repeat_first_field; - __u8 progressive_frame; - __u8 pad; -}; - -struct v4l2_ctrl_mpeg2_slice_params { - __u32 bit_size; - __u32 data_bit_offset; - - struct v4l2_mpeg2_sequence sequence; - struct v4l2_mpeg2_picture picture; - - /* ISO/IEC 13818-2, ITU-T Rec. H.262: Slice */ - __u8 quantiser_scale_code; - - __u8 backward_ref_index; - __u8 forward_ref_index; - __u8 pad; -}; - -struct v4l2_ctrl_mpeg2_quantization { - /* ISO/IEC 13818-2, ITU-T Rec. H.262: Quant matrix extension */ - __u8 load_intra_quantiser_matrix; - __u8 load_non_intra_quantiser_matrix; - __u8 load_chroma_intra_quantiser_matrix; - __u8 load_chroma_non_intra_quantiser_matrix; - - __u8 intra_quantiser_matrix[64]; - __u8 non_intra_quantiser_matrix[64]; - __u8 chroma_intra_quantiser_matrix[64]; - __u8 chroma_non_intra_quantiser_matrix[64]; -}; - #endif diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index c8e8ff810190..2ba2ad0e23fb 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -1622,8 +1622,6 @@ struct v4l2_ext_control { __u8 __user *p_u8; __u16 __user *p_u16; __u32 __user *p_u32; - struct v4l2_ctrl_mpeg2_slice_params __user *p_mpeg2_slice_params; - struct v4l2_ctrl_mpeg2_quantization __user *p_mpeg2_quantization; void __user *ptr; }; } __attribute__ ((packed)); @@ -1669,8 +1667,6 @@ enum v4l2_ctrl_type { V4L2_CTRL_TYPE_U8 = 0x0100, V4L2_CTRL_TYPE_U16 = 0x0101, V4L2_CTRL_TYPE_U32 = 0x0102, - V4L2_CTRL_TYPE_MPEG2_SLICE_PARAMS = 0x0103, - V4L2_CTRL_TYPE_MPEG2_QUANTIZATION = 0x0104, }; /* Used in the VIDIOC_QUERYCTRL ioctl for querying controls */ -- cgit v1.2.3 From cd9fd6f12fc762246607c77673acdfb55f8096b6 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Wed, 5 Dec 2018 06:36:13 -0500 Subject: media: extended-controls.rst: add note to the MPEG2 state controls Add a note mentioning that these two controls are not part of the public API while they still stabilizing. Signed-off-by: Hans Verkuil Reviewed-by: Paul Kocialkowski Signed-off-by: Mauro Carvalho Chehab --- Documentation/media/uapi/v4l/extended-controls.rst | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/Documentation/media/uapi/v4l/extended-controls.rst b/Documentation/media/uapi/v4l/extended-controls.rst index 65a1d873196b..027358b91082 100644 --- a/Documentation/media/uapi/v4l/extended-controls.rst +++ b/Documentation/media/uapi/v4l/extended-controls.rst @@ -1505,6 +1505,11 @@ enum v4l2_mpeg_video_h264_hierarchical_coding_type - configuring a stateless hardware decoding pipeline for MPEG-2. The bitstream parameters are defined according to :ref:`mpeg2part2`. + .. note:: + + This compound control is not yet part of the public kernel API and + it is expected to change. + .. c:type:: v4l2_ctrl_mpeg2_slice_params .. cssclass:: longtable @@ -1625,6 +1630,11 @@ enum v4l2_mpeg_video_h264_hierarchical_coding_type - Specifies quantization matrices (as extracted from the bitstream) for the associated MPEG-2 slice data. + .. note:: + + This compound control is not yet part of the public kernel API and + it is expected to change. + .. c:type:: v4l2_ctrl_mpeg2_quantization .. cssclass:: longtable -- cgit v1.2.3 From 078ab3ea2c3bb69cb989d52346fefa1246055e5b Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Wed, 5 Dec 2018 12:23:54 -0500 Subject: media: Add a Kconfig option for the Request API The Request API is now merged to the kernel but the confidence on the stability of that API is not great, especially regarding the interaction with V4L2. Add a Kconfig option for the API, with a scary-looking warning. The patch itself disables request creation as well as does not advertise them as buffer flags. The driver requiring requests (cedrus) now depends on the Kconfig option as well. Signed-off-by: Sakari Ailus Acked-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- drivers/media/Kconfig | 13 +++++++++++++ drivers/media/common/videobuf2/videobuf2-v4l2.c | 2 ++ drivers/media/media-device.c | 4 ++++ drivers/staging/media/sunxi/cedrus/Kconfig | 1 + 4 files changed, 20 insertions(+) diff --git a/drivers/media/Kconfig b/drivers/media/Kconfig index 8add62a18293..102eb35fcf3f 100644 --- a/drivers/media/Kconfig +++ b/drivers/media/Kconfig @@ -110,6 +110,19 @@ config MEDIA_CONTROLLER_DVB This is currently experimental. +config MEDIA_CONTROLLER_REQUEST_API + bool "Enable Media controller Request API (EXPERIMENTAL)" + depends on MEDIA_CONTROLLER && STAGING_MEDIA + default n + ---help--- + DO NOT ENABLE THIS OPTION UNLESS YOU KNOW WHAT YOU'RE DOING. + + This option enables the Request API for the Media controller and V4L2 + interfaces. It is currently needed by a few stateless codec drivers. + + There is currently no intention to provide API or ABI stability for + this new API as of yet. + # # Video4Linux support # Only enables if one of the V4L2 types (ATV, webcam, radio) is selected diff --git a/drivers/media/common/videobuf2/videobuf2-v4l2.c b/drivers/media/common/videobuf2/videobuf2-v4l2.c index ce28bc052c3c..1d35aeabfd85 100644 --- a/drivers/media/common/videobuf2/videobuf2-v4l2.c +++ b/drivers/media/common/videobuf2/videobuf2-v4l2.c @@ -634,8 +634,10 @@ static void fill_buf_caps(struct vb2_queue *q, u32 *caps) *caps |= V4L2_BUF_CAP_SUPPORTS_USERPTR; if (q->io_modes & VB2_DMABUF) *caps |= V4L2_BUF_CAP_SUPPORTS_DMABUF; +#ifdef CONFIG_MEDIA_CONTROLLER_REQUEST_API if (q->supports_requests) *caps |= V4L2_BUF_CAP_SUPPORTS_REQUESTS; +#endif } int vb2_reqbufs(struct vb2_queue *q, struct v4l2_requestbuffers *req) diff --git a/drivers/media/media-device.c b/drivers/media/media-device.c index bed24372e61f..b8ec88612df7 100644 --- a/drivers/media/media-device.c +++ b/drivers/media/media-device.c @@ -381,10 +381,14 @@ static long media_device_get_topology(struct media_device *mdev, void *arg) static long media_device_request_alloc(struct media_device *mdev, int *alloc_fd) { +#ifdef CONFIG_MEDIA_CONTROLLER_REQUEST_API if (!mdev->ops || !mdev->ops->req_validate || !mdev->ops->req_queue) return -ENOTTY; return media_request_alloc(mdev, alloc_fd); +#else + return -ENOTTY; +#endif } static long copy_arg_from_user(void *karg, void __user *uarg, unsigned int cmd) diff --git a/drivers/staging/media/sunxi/cedrus/Kconfig b/drivers/staging/media/sunxi/cedrus/Kconfig index a7a34e89c42d..3252efa422f9 100644 --- a/drivers/staging/media/sunxi/cedrus/Kconfig +++ b/drivers/staging/media/sunxi/cedrus/Kconfig @@ -3,6 +3,7 @@ config VIDEO_SUNXI_CEDRUS depends on VIDEO_DEV && VIDEO_V4L2 && MEDIA_CONTROLLER depends on HAS_DMA depends on OF + depends on MEDIA_CONTROLLER_REQUEST_API select SUNXI_SRAM select VIDEOBUF2_DMA_CONTIG select V4L2_MEM2MEM_DEV -- cgit v1.2.3 From 1e434b703248580b7aaaf8a115d93e682f57d29f Mon Sep 17 00:00:00 2001 From: Anson Huang Date: Tue, 4 Dec 2018 03:17:45 +0000 Subject: ARM: imx: update the cpu power up timing setting on i.mx6sx The sw2iso count should cover ARM LDO ramp-up time, the MAX ARM LDO ramp-up time may be up to more than 100us on some boards, this patch sets sw2iso to 0xf (~384us) which is the reset value, and it is much more safe to cover different boards, since we have observed that some customer boards failed with current setting of 0x2. Fixes: 05136f0897b5 ("ARM: imx: support arm power off in cpuidle for i.mx6sx") Signed-off-by: Anson Huang Reviewed-by: Fabio Estevam Signed-off-by: Shawn Guo --- arch/arm/mach-imx/cpuidle-imx6sx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/mach-imx/cpuidle-imx6sx.c b/arch/arm/mach-imx/cpuidle-imx6sx.c index 243a108a940b..fd0053e47a15 100644 --- a/arch/arm/mach-imx/cpuidle-imx6sx.c +++ b/arch/arm/mach-imx/cpuidle-imx6sx.c @@ -110,7 +110,7 @@ int __init imx6sx_cpuidle_init(void) * except for power up sw2iso which need to be * larger than LDO ramp up time. */ - imx_gpc_set_arm_power_up_timing(2, 1); + imx_gpc_set_arm_power_up_timing(0xf, 1); imx_gpc_set_arm_power_down_timing(1, 1); return cpuidle_register(&imx6sx_cpuidle_driver, NULL); -- cgit v1.2.3 From e41b93a6be57e26a4a123345f826a6ac3a213551 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Mon, 3 Dec 2018 19:55:55 +1100 Subject: powerpc/boot: Fix build failures with -j 1 In commit 5e9dcb6188a4 ("powerpc/boot: Expose Kconfig symbols to wrapper") we added a dependency to serial.c on autoconf.h: $(obj)/serial.c: $(obj)/autoconf.h This works when building in-tree (ie. with KBUILD_OUTPUT unset) because the obj tree is the src tree. But when building with eg. O=build and -j 1 the build fails: gcc ... -I../arch/powerpc/boot -c -o arch/powerpc/boot/serial.o arch/powerpc/boot/serial.c gcc: error: arch/powerpc/boot/serial.c: No such file or directory Why this is only happening with -j 1 is not clear, when building with -j greater than 1 somehow we decide to look for serial.c in the src tree (../), eg: gcc -I../arch/powerpc/boot -c -o arch/powerpc/boot/serial.o ../arch/powerpc/boot/serial.c Regardless we shouldn't be specifying a dependency on serial.c in the build tree, we want to add a dependency to the version in $(srctree) so fix the rule to say that. Fixes: 5e9dcb6188a4 ("powerpc/boot: Expose Kconfig symbols to wrapper") Tested-by: Daniel Axtens Signed-off-by: Michael Ellerman --- arch/powerpc/boot/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile index 39354365f54a..ed9883169190 100644 --- a/arch/powerpc/boot/Makefile +++ b/arch/powerpc/boot/Makefile @@ -197,7 +197,7 @@ $(obj)/empty.c: $(obj)/zImage.coff.lds $(obj)/zImage.ps3.lds : $(obj)/%: $(srctree)/$(src)/%.S $(Q)cp $< $@ -$(obj)/serial.c: $(obj)/autoconf.h +$(srctree)/$(src)/serial.c: $(obj)/autoconf.h $(obj)/autoconf.h: $(obj)/%: $(objtree)/include/generated/% $(Q)cp $< $@ -- cgit v1.2.3 From f15096f12a4e9340168df5fdd9201aa8ed60d59e Mon Sep 17 00:00:00 2001 From: Fabio Estevam Date: Wed, 5 Dec 2018 09:05:30 -0200 Subject: ARM: dts: imx7d-nitrogen7: Fix the description of the Wifi clock According to bindings/regulator/fixed-regulator.txt the 'clocks' and 'clock-names' properties are not valid ones. In order to turn on the Wifi clock the correct location for describing the CLKO2 clock is via a mmc-pwrseq handle, so do it accordingly. Fixes: 56354959cfec ("ARM: dts: imx: add Boundary Devices Nitrogen7 board") Signed-off-by: Fabio Estevam Acked-by: Troy Kisky Signed-off-by: Shawn Guo --- arch/arm/boot/dts/imx7d-nitrogen7.dts | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/arch/arm/boot/dts/imx7d-nitrogen7.dts b/arch/arm/boot/dts/imx7d-nitrogen7.dts index d8aac4a2d02a..177d21fdeb28 100644 --- a/arch/arm/boot/dts/imx7d-nitrogen7.dts +++ b/arch/arm/boot/dts/imx7d-nitrogen7.dts @@ -86,13 +86,17 @@ compatible = "regulator-fixed"; regulator-min-microvolt = <3300000>; regulator-max-microvolt = <3300000>; - clocks = <&clks IMX7D_CLKO2_ROOT_DIV>; - clock-names = "slow"; regulator-name = "reg_wlan"; startup-delay-us = <70000>; gpio = <&gpio4 21 GPIO_ACTIVE_HIGH>; enable-active-high; }; + + usdhc2_pwrseq: usdhc2_pwrseq { + compatible = "mmc-pwrseq-simple"; + clocks = <&clks IMX7D_CLKO2_ROOT_DIV>; + clock-names = "ext_clock"; + }; }; &adc1 { @@ -375,6 +379,7 @@ bus-width = <4>; non-removable; vmmc-supply = <®_wlan>; + mmc-pwrseq = <&usdhc2_pwrseq>; cap-power-off-card; keep-power-in-suspend; status = "okay"; -- cgit v1.2.3 From b704441e38f645dcfba1348ca3cc1ba43d1a9f31 Mon Sep 17 00:00:00 2001 From: Alek Du Date: Thu, 6 Dec 2018 17:24:59 +0800 Subject: mmc: sdhci: fix the timeout check window for clock and reset We observed some premature timeouts on a virtualization platform, the log is like this: case 1: [159525.255629] mmc1: Internal clock never stabilised. [159525.255818] mmc1: sdhci: ============ SDHCI REGISTER DUMP =========== [159525.256049] mmc1: sdhci: Sys addr: 0x00000000 | Version: 0x00001002 ... [159525.257205] mmc1: sdhci: Wake-up: 0x00000000 | Clock: 0x0000fa03 From the clock control register dump, we are pretty sure the clock was stablized. case 2: [ 914.550127] mmc1: Reset 0x2 never completed. [ 914.550321] mmc1: sdhci: ============ SDHCI REGISTER DUMP =========== [ 914.550608] mmc1: sdhci: Sys addr: 0x00000010 | Version: 0x00001002 After checking the sdhci code, we found the timeout check actually has a little window that the CPU can be scheduled out and when it comes back, the original time set or check is not valid. Fixes: 5a436cc0af62 ("mmc: sdhci: Optimize delay loops") Cc: stable@vger.kernel.org # v4.12+ Signed-off-by: Alek Du Acked-by: Adrian Hunter Signed-off-by: Ulf Hansson --- drivers/mmc/host/sdhci.c | 18 +++++++++++++----- 1 file changed, 13 insertions(+), 5 deletions(-) diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c index 99bdae53fa2e..451b08a818a9 100644 --- a/drivers/mmc/host/sdhci.c +++ b/drivers/mmc/host/sdhci.c @@ -216,8 +216,12 @@ void sdhci_reset(struct sdhci_host *host, u8 mask) timeout = ktime_add_ms(ktime_get(), 100); /* hw clears the bit when it's done */ - while (sdhci_readb(host, SDHCI_SOFTWARE_RESET) & mask) { - if (ktime_after(ktime_get(), timeout)) { + while (1) { + bool timedout = ktime_after(ktime_get(), timeout); + + if (!(sdhci_readb(host, SDHCI_SOFTWARE_RESET) & mask)) + break; + if (timedout) { pr_err("%s: Reset 0x%x never completed.\n", mmc_hostname(host->mmc), (int)mask); sdhci_dumpregs(host); @@ -1608,9 +1612,13 @@ void sdhci_enable_clk(struct sdhci_host *host, u16 clk) /* Wait max 20 ms */ timeout = ktime_add_ms(ktime_get(), 20); - while (!((clk = sdhci_readw(host, SDHCI_CLOCK_CONTROL)) - & SDHCI_CLOCK_INT_STABLE)) { - if (ktime_after(ktime_get(), timeout)) { + while (1) { + bool timedout = ktime_after(ktime_get(), timeout); + + clk = sdhci_readw(host, SDHCI_CLOCK_CONTROL); + if (clk & SDHCI_CLOCK_INT_STABLE) + break; + if (timedout) { pr_err("%s: Internal clock never stabilised.\n", mmc_hostname(host->mmc)); sdhci_dumpregs(host); -- cgit v1.2.3 From eff3860bbfedbac6edac57fb0d7f3a60e860c1c3 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Thu, 6 Dec 2018 08:19:13 -0500 Subject: radix tree: Don't return retry entries from lookup Commit 66ee620f06f9 ("idr: Permit any valid kernel pointer to be stored") changed the radix tree lookup so that it stops when reaching the bottom of the tree. However, the condition was added in the wrong place, making it possible to return retry entries to the caller. Reorder the tests to check for the retry entry before checking whether we're at the bottom of the tree. The retry entry should never be found in the tree root, so it's safe to defer the check until the end of the loop. Add a regression test to the test-suite to be sure this doesn't come back. Fixes: 66ee620f06f9 ("idr: Permit any valid kernel pointer to be stored") Reported-by: Greg Kurz Signed-off-by: Matthew Wilcox --- lib/radix-tree.c | 4 +- tools/testing/radix-tree/Makefile | 1 + tools/testing/radix-tree/main.c | 1 + tools/testing/radix-tree/regression.h | 1 + tools/testing/radix-tree/regression4.c | 79 ++++++++++++++++++++++++++++++++++ 5 files changed, 84 insertions(+), 2 deletions(-) create mode 100644 tools/testing/radix-tree/regression4.c diff --git a/lib/radix-tree.c b/lib/radix-tree.c index 1106bb6aa01e..14d51548bea6 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -784,11 +784,11 @@ void *__radix_tree_lookup(const struct radix_tree_root *root, while (radix_tree_is_internal_node(node)) { unsigned offset; - if (node == RADIX_TREE_RETRY) - goto restart; parent = entry_to_node(node); offset = radix_tree_descend(parent, &node, index); slot = parent->slots + offset; + if (node == RADIX_TREE_RETRY) + goto restart; if (parent->shift == 0) break; } diff --git a/tools/testing/radix-tree/Makefile b/tools/testing/radix-tree/Makefile index acf1afa01c5b..397d6b612502 100644 --- a/tools/testing/radix-tree/Makefile +++ b/tools/testing/radix-tree/Makefile @@ -7,6 +7,7 @@ LDLIBS+= -lpthread -lurcu TARGETS = main idr-test multiorder xarray CORE_OFILES := xarray.o radix-tree.o idr.o linux.o test.o find_bit.o bitmap.o OFILES = main.o $(CORE_OFILES) regression1.o regression2.o regression3.o \ + regression4.o \ tag_check.o multiorder.o idr-test.o iteration_check.o benchmark.o ifndef SHIFT diff --git a/tools/testing/radix-tree/main.c b/tools/testing/radix-tree/main.c index 77a44c54998f..7a22d6e3732e 100644 --- a/tools/testing/radix-tree/main.c +++ b/tools/testing/radix-tree/main.c @@ -308,6 +308,7 @@ int main(int argc, char **argv) regression1_test(); regression2_test(); regression3_test(); + regression4_test(); iteration_test(0, 10 + 90 * long_run); iteration_test(7, 10 + 90 * long_run); single_thread_tests(long_run); diff --git a/tools/testing/radix-tree/regression.h b/tools/testing/radix-tree/regression.h index 3c8a1584e9ee..135145af18b7 100644 --- a/tools/testing/radix-tree/regression.h +++ b/tools/testing/radix-tree/regression.h @@ -5,5 +5,6 @@ void regression1_test(void); void regression2_test(void); void regression3_test(void); +void regression4_test(void); #endif diff --git a/tools/testing/radix-tree/regression4.c b/tools/testing/radix-tree/regression4.c new file mode 100644 index 000000000000..cf4e5aba6b08 --- /dev/null +++ b/tools/testing/radix-tree/regression4.c @@ -0,0 +1,79 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "regression.h" + +static pthread_barrier_t worker_barrier; +static int obj0, obj1; +static RADIX_TREE(mt_tree, GFP_KERNEL); + +static void *reader_fn(void *arg) +{ + int i; + void *entry; + + rcu_register_thread(); + pthread_barrier_wait(&worker_barrier); + + for (i = 0; i < 1000000; i++) { + rcu_read_lock(); + entry = radix_tree_lookup(&mt_tree, 0); + rcu_read_unlock(); + if (entry != &obj0) { + printf("iteration %d bad entry = %p\n", i, entry); + abort(); + } + } + + rcu_unregister_thread(); + + return NULL; +} + +static void *writer_fn(void *arg) +{ + int i; + + rcu_register_thread(); + pthread_barrier_wait(&worker_barrier); + + for (i = 0; i < 1000000; i++) { + radix_tree_insert(&mt_tree, 1, &obj1); + radix_tree_delete(&mt_tree, 1); + } + + rcu_unregister_thread(); + + return NULL; +} + +void regression4_test(void) +{ + pthread_t reader, writer; + + printv(1, "regression test 4 starting\n"); + + radix_tree_insert(&mt_tree, 0, &obj0); + pthread_barrier_init(&worker_barrier, NULL, 2); + + if (pthread_create(&reader, NULL, reader_fn, NULL) || + pthread_create(&writer, NULL, writer_fn, NULL)) { + perror("pthread_create"); + exit(1); + } + + if (pthread_join(reader, NULL) || pthread_join(writer, NULL)) { + perror("pthread_join"); + exit(1); + } + + printv(1, "regression test 4 passed\n"); +} -- cgit v1.2.3 From 55f3f7eab75c10d9b33d122670b5935ab64db50f Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Mon, 26 Nov 2018 16:08:43 -0500 Subject: XArray: Add xa_cmpxchg_irq and xa_cmpxchg_bh These convenience wrappers match the other _irq and _bh wrappers we already have. It turns out I'd already open-coded xa_cmpxchg_irq() in the shmem code, so convert that. Signed-off-by: Matthew Wilcox --- Documentation/core-api/xarray.rst | 5 +++- include/linux/xarray.h | 54 +++++++++++++++++++++++++++++++++++++++ mm/shmem.c | 4 +-- 3 files changed, 59 insertions(+), 4 deletions(-) diff --git a/Documentation/core-api/xarray.rst b/Documentation/core-api/xarray.rst index dbe96cb5558e..6a6d67acaf69 100644 --- a/Documentation/core-api/xarray.rst +++ b/Documentation/core-api/xarray.rst @@ -187,6 +187,8 @@ Takes xa_lock internally: * :c:func:`xa_erase_bh` * :c:func:`xa_erase_irq` * :c:func:`xa_cmpxchg` + * :c:func:`xa_cmpxchg_bh` + * :c:func:`xa_cmpxchg_irq` * :c:func:`xa_store_range` * :c:func:`xa_alloc` * :c:func:`xa_alloc_bh` @@ -263,7 +265,8 @@ using :c:func:`xa_lock_irqsave` in both the interrupt handler and process context, or :c:func:`xa_lock_irq` in process context and :c:func:`xa_lock` in the interrupt handler. Some of the more common patterns have helper functions such as :c:func:`xa_store_bh`, :c:func:`xa_store_irq`, -:c:func:`xa_erase_bh` and :c:func:`xa_erase_irq`. +:c:func:`xa_erase_bh`, :c:func:`xa_erase_irq`, :c:func:`xa_cmpxchg_bh` +and :c:func:`xa_cmpxchg_irq`. Sometimes you need to protect access to the XArray with a mutex because that lock sits above another mutex in the locking hierarchy. That does diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 564892e19f8c..f492e21c4aa2 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -553,6 +553,60 @@ static inline void *xa_cmpxchg(struct xarray *xa, unsigned long index, return curr; } +/** + * xa_cmpxchg_bh() - Conditionally replace an entry in the XArray. + * @xa: XArray. + * @index: Index into array. + * @old: Old value to test against. + * @entry: New value to place in array. + * @gfp: Memory allocation flags. + * + * This function is like calling xa_cmpxchg() except it disables softirqs + * while holding the array lock. + * + * Context: Any context. Takes and releases the xa_lock while + * disabling softirqs. May sleep if the @gfp flags permit. + * Return: The old value at this index or xa_err() if an error happened. + */ +static inline void *xa_cmpxchg_bh(struct xarray *xa, unsigned long index, + void *old, void *entry, gfp_t gfp) +{ + void *curr; + + xa_lock_bh(xa); + curr = __xa_cmpxchg(xa, index, old, entry, gfp); + xa_unlock_bh(xa); + + return curr; +} + +/** + * xa_cmpxchg_irq() - Conditionally replace an entry in the XArray. + * @xa: XArray. + * @index: Index into array. + * @old: Old value to test against. + * @entry: New value to place in array. + * @gfp: Memory allocation flags. + * + * This function is like calling xa_cmpxchg() except it disables interrupts + * while holding the array lock. + * + * Context: Process context. Takes and releases the xa_lock while + * disabling interrupts. May sleep if the @gfp flags permit. + * Return: The old value at this index or xa_err() if an error happened. + */ +static inline void *xa_cmpxchg_irq(struct xarray *xa, unsigned long index, + void *old, void *entry, gfp_t gfp) +{ + void *curr; + + xa_lock_irq(xa); + curr = __xa_cmpxchg(xa, index, old, entry, gfp); + xa_unlock_irq(xa); + + return curr; +} + /** * xa_insert() - Store this entry in the XArray unless another entry is * already present. diff --git a/mm/shmem.c b/mm/shmem.c index cddc72ac44d8..6adbdd349875 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -661,9 +661,7 @@ static int shmem_free_swap(struct address_space *mapping, { void *old; - xa_lock_irq(&mapping->i_pages); - old = __xa_cmpxchg(&mapping->i_pages, index, radswap, NULL, 0); - xa_unlock_irq(&mapping->i_pages); + old = xa_cmpxchg_irq(&mapping->i_pages, index, radswap, NULL, 0); if (old != radswap) return -ENOENT; free_swap_and_cache(radix_to_swp_entry(radswap)); -- cgit v1.2.3 From b7677a132a4c2ff877986c5b30f9427127b9897a Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Mon, 5 Nov 2018 13:19:54 -0500 Subject: XArray tests: Handle larger indices more elegantly xa_mk_value() only handles values up to LONG_MAX. I successfully hid that inside xa_store_index() and xa_erase_index(), but it turned out I also needed it for testing xa_alloc() on 32-bit machines. So extract xa_mk_index() from the above two functions, and convert the non-constant users of xa_mk_value() to xa_mk_index(). Signed-off-by: Matthew Wilcox --- lib/test_xarray.c | 91 +++++++++++++++++++++++++++++-------------------------- 1 file changed, 48 insertions(+), 43 deletions(-) diff --git a/lib/test_xarray.c b/lib/test_xarray.c index 0598e86af8fc..d30fd907a3dd 100644 --- a/lib/test_xarray.c +++ b/lib/test_xarray.c @@ -28,23 +28,28 @@ void xa_dump(const struct xarray *xa) { } } while (0) #endif +static void *xa_mk_index(unsigned long index) +{ + return xa_mk_value(index & LONG_MAX); +} + static void *xa_store_index(struct xarray *xa, unsigned long index, gfp_t gfp) { - return xa_store(xa, index, xa_mk_value(index & LONG_MAX), gfp); + return xa_store(xa, index, xa_mk_index(index), gfp); } static void xa_alloc_index(struct xarray *xa, unsigned long index, gfp_t gfp) { u32 id = 0; - XA_BUG_ON(xa, xa_alloc(xa, &id, UINT_MAX, xa_mk_value(index & LONG_MAX), + XA_BUG_ON(xa, xa_alloc(xa, &id, UINT_MAX, xa_mk_index(index), gfp) != 0); XA_BUG_ON(xa, id != index); } static void xa_erase_index(struct xarray *xa, unsigned long index) { - XA_BUG_ON(xa, xa_erase(xa, index) != xa_mk_value(index & LONG_MAX)); + XA_BUG_ON(xa, xa_erase(xa, index) != xa_mk_index(index)); XA_BUG_ON(xa, xa_load(xa, index) != NULL); } @@ -118,7 +123,7 @@ static noinline void check_xas_retry(struct xarray *xa) xas_set(&xas, 0); xas_for_each(&xas, entry, ULONG_MAX) { - xas_store(&xas, xa_mk_value(xas.xa_index)); + xas_store(&xas, xa_mk_index(xas.xa_index)); } xas_unlock(&xas); @@ -196,7 +201,7 @@ static noinline void check_xa_mark_1(struct xarray *xa, unsigned long index) XA_BUG_ON(xa, xa_store_index(xa, index + 2, GFP_KERNEL)); xa_set_mark(xa, index + 2, XA_MARK_1); XA_BUG_ON(xa, xa_store_index(xa, next, GFP_KERNEL)); - xa_store_order(xa, index, order, xa_mk_value(index), + xa_store_order(xa, index, order, xa_mk_index(index), GFP_KERNEL); for (i = base; i < next; i++) { XA_STATE(xas, xa, i); @@ -405,7 +410,7 @@ static noinline void check_xas_erase(struct xarray *xa) xas_set(&xas, j); do { xas_lock(&xas); - xas_store(&xas, xa_mk_value(j)); + xas_store(&xas, xa_mk_index(j)); xas_unlock(&xas); } while (xas_nomem(&xas, GFP_KERNEL)); } @@ -423,7 +428,7 @@ static noinline void check_xas_erase(struct xarray *xa) xas_set(&xas, 0); j = i; xas_for_each(&xas, entry, ULONG_MAX) { - XA_BUG_ON(xa, entry != xa_mk_value(j)); + XA_BUG_ON(xa, entry != xa_mk_index(j)); xas_store(&xas, NULL); j++; } @@ -440,17 +445,17 @@ static noinline void check_multi_store_1(struct xarray *xa, unsigned long index, unsigned long min = index & ~((1UL << order) - 1); unsigned long max = min + (1UL << order); - xa_store_order(xa, index, order, xa_mk_value(index), GFP_KERNEL); - XA_BUG_ON(xa, xa_load(xa, min) != xa_mk_value(index)); - XA_BUG_ON(xa, xa_load(xa, max - 1) != xa_mk_value(index)); + xa_store_order(xa, index, order, xa_mk_index(index), GFP_KERNEL); + XA_BUG_ON(xa, xa_load(xa, min) != xa_mk_index(index)); + XA_BUG_ON(xa, xa_load(xa, max - 1) != xa_mk_index(index)); XA_BUG_ON(xa, xa_load(xa, max) != NULL); XA_BUG_ON(xa, xa_load(xa, min - 1) != NULL); xas_lock(&xas); - XA_BUG_ON(xa, xas_store(&xas, xa_mk_value(min)) != xa_mk_value(index)); + XA_BUG_ON(xa, xas_store(&xas, xa_mk_index(min)) != xa_mk_index(index)); xas_unlock(&xas); - XA_BUG_ON(xa, xa_load(xa, min) != xa_mk_value(min)); - XA_BUG_ON(xa, xa_load(xa, max - 1) != xa_mk_value(min)); + XA_BUG_ON(xa, xa_load(xa, min) != xa_mk_index(min)); + XA_BUG_ON(xa, xa_load(xa, max - 1) != xa_mk_index(min)); XA_BUG_ON(xa, xa_load(xa, max) != NULL); XA_BUG_ON(xa, xa_load(xa, min - 1) != NULL); @@ -523,15 +528,15 @@ static noinline void check_multi_store(struct xarray *xa) for (i = 0; i < max_order; i++) { for (j = 0; j < max_order; j++) { - xa_store_order(xa, 0, i, xa_mk_value(i), GFP_KERNEL); - xa_store_order(xa, 0, j, xa_mk_value(j), GFP_KERNEL); + xa_store_order(xa, 0, i, xa_mk_index(i), GFP_KERNEL); + xa_store_order(xa, 0, j, xa_mk_index(j), GFP_KERNEL); for (k = 0; k < max_order; k++) { void *entry = xa_load(xa, (1UL << k) - 1); if ((i < k) && (j < k)) XA_BUG_ON(xa, entry != NULL); else - XA_BUG_ON(xa, entry != xa_mk_value(j)); + XA_BUG_ON(xa, entry != xa_mk_index(j)); } xa_erase(xa, 0); @@ -587,13 +592,13 @@ static noinline void check_xa_alloc(void) xa_destroy(&xa0); id = 0xfffffffeU; - XA_BUG_ON(&xa0, xa_alloc(&xa0, &id, UINT_MAX, xa_mk_value(0), + XA_BUG_ON(&xa0, xa_alloc(&xa0, &id, UINT_MAX, xa_mk_index(id), GFP_KERNEL) != 0); XA_BUG_ON(&xa0, id != 0xfffffffeU); - XA_BUG_ON(&xa0, xa_alloc(&xa0, &id, UINT_MAX, xa_mk_value(0), + XA_BUG_ON(&xa0, xa_alloc(&xa0, &id, UINT_MAX, xa_mk_index(id), GFP_KERNEL) != 0); XA_BUG_ON(&xa0, id != 0xffffffffU); - XA_BUG_ON(&xa0, xa_alloc(&xa0, &id, UINT_MAX, xa_mk_value(0), + XA_BUG_ON(&xa0, xa_alloc(&xa0, &id, UINT_MAX, xa_mk_index(id), GFP_KERNEL) != -ENOSPC); XA_BUG_ON(&xa0, id != 0xffffffffU); xa_destroy(&xa0); @@ -610,11 +615,11 @@ retry: xas_lock(&xas); xas_for_each_conflict(&xas, entry) { XA_BUG_ON(xa, !xa_is_value(entry)); - XA_BUG_ON(xa, entry < xa_mk_value(start)); - XA_BUG_ON(xa, entry > xa_mk_value(start + (1UL << order) - 1)); + XA_BUG_ON(xa, entry < xa_mk_index(start)); + XA_BUG_ON(xa, entry > xa_mk_index(start + (1UL << order) - 1)); count++; } - xas_store(&xas, xa_mk_value(start)); + xas_store(&xas, xa_mk_index(start)); xas_unlock(&xas); if (xas_nomem(&xas, GFP_KERNEL)) { count = 0; @@ -622,9 +627,9 @@ retry: } XA_BUG_ON(xa, xas_error(&xas)); XA_BUG_ON(xa, count != present); - XA_BUG_ON(xa, xa_load(xa, start) != xa_mk_value(start)); + XA_BUG_ON(xa, xa_load(xa, start) != xa_mk_index(start)); XA_BUG_ON(xa, xa_load(xa, start + (1UL << order) - 1) != - xa_mk_value(start)); + xa_mk_index(start)); xa_erase_index(xa, start); } @@ -703,7 +708,7 @@ static noinline void check_multi_find_2(struct xarray *xa) for (j = 0; j < index; j++) { XA_STATE(xas, xa, j + index); xa_store_index(xa, index - 1, GFP_KERNEL); - xa_store_order(xa, index, i, xa_mk_value(index), + xa_store_order(xa, index, i, xa_mk_index(index), GFP_KERNEL); rcu_read_lock(); xas_for_each(&xas, entry, ULONG_MAX) { @@ -778,7 +783,7 @@ static noinline void check_find_2(struct xarray *xa) j = 0; index = 0; xa_for_each(xa, entry, index, ULONG_MAX, XA_PRESENT) { - XA_BUG_ON(xa, xa_mk_value(index) != entry); + XA_BUG_ON(xa, xa_mk_index(index) != entry); XA_BUG_ON(xa, index != j++); } } @@ -829,11 +834,11 @@ static noinline void check_find_entry(struct xarray *xa) for (index = 0; index < (1UL << (order + 5)); index += (1UL << order)) { xa_store_order(xa, index, order, - xa_mk_value(index), GFP_KERNEL); + xa_mk_index(index), GFP_KERNEL); XA_BUG_ON(xa, xa_load(xa, index) != - xa_mk_value(index)); + xa_mk_index(index)); XA_BUG_ON(xa, xa_find_entry(xa, - xa_mk_value(index)) != index); + xa_mk_index(index)) != index); } XA_BUG_ON(xa, xa_find_entry(xa, xa) != -1); xa_destroy(xa); @@ -844,7 +849,7 @@ static noinline void check_find_entry(struct xarray *xa) XA_BUG_ON(xa, xa_find_entry(xa, xa) != -1); xa_store_index(xa, ULONG_MAX, GFP_KERNEL); XA_BUG_ON(xa, xa_find_entry(xa, xa) != -1); - XA_BUG_ON(xa, xa_find_entry(xa, xa_mk_value(LONG_MAX)) != -1); + XA_BUG_ON(xa, xa_find_entry(xa, xa_mk_index(ULONG_MAX)) != -1); xa_erase_index(xa, ULONG_MAX); XA_BUG_ON(xa, !xa_empty(xa)); } @@ -864,7 +869,7 @@ static noinline void check_move_small(struct xarray *xa, unsigned long idx) XA_BUG_ON(xa, xas.xa_node == XAS_RESTART); XA_BUG_ON(xa, xas.xa_index != i); if (i == 0 || i == idx) - XA_BUG_ON(xa, entry != xa_mk_value(i)); + XA_BUG_ON(xa, entry != xa_mk_index(i)); else XA_BUG_ON(xa, entry != NULL); } @@ -878,7 +883,7 @@ static noinline void check_move_small(struct xarray *xa, unsigned long idx) XA_BUG_ON(xa, xas.xa_node == XAS_RESTART); XA_BUG_ON(xa, xas.xa_index != i); if (i == 0 || i == idx) - XA_BUG_ON(xa, entry != xa_mk_value(i)); + XA_BUG_ON(xa, entry != xa_mk_index(i)); else XA_BUG_ON(xa, entry != NULL); } while (i > 0); @@ -909,7 +914,7 @@ static noinline void check_move(struct xarray *xa) do { void *entry = xas_prev(&xas); i--; - XA_BUG_ON(xa, entry != xa_mk_value(i)); + XA_BUG_ON(xa, entry != xa_mk_index(i)); XA_BUG_ON(xa, i != xas.xa_index); } while (i != 0); @@ -918,7 +923,7 @@ static noinline void check_move(struct xarray *xa) do { void *entry = xas_next(&xas); - XA_BUG_ON(xa, entry != xa_mk_value(i)); + XA_BUG_ON(xa, entry != xa_mk_index(i)); XA_BUG_ON(xa, i != xas.xa_index); i++; } while (i < (1 << 16)); @@ -934,7 +939,7 @@ static noinline void check_move(struct xarray *xa) void *entry = xas_prev(&xas); i--; if ((i < (1 << 8)) || (i >= (1 << 15))) - XA_BUG_ON(xa, entry != xa_mk_value(i)); + XA_BUG_ON(xa, entry != xa_mk_index(i)); else XA_BUG_ON(xa, entry != NULL); XA_BUG_ON(xa, i != xas.xa_index); @@ -946,7 +951,7 @@ static noinline void check_move(struct xarray *xa) do { void *entry = xas_next(&xas); if ((i < (1 << 8)) || (i >= (1 << 15))) - XA_BUG_ON(xa, entry != xa_mk_value(i)); + XA_BUG_ON(xa, entry != xa_mk_index(i)); else XA_BUG_ON(xa, entry != NULL); XA_BUG_ON(xa, i != xas.xa_index); @@ -976,7 +981,7 @@ static noinline void xa_store_many_order(struct xarray *xa, if (xas_error(&xas)) goto unlock; for (i = 0; i < (1U << order); i++) { - XA_BUG_ON(xa, xas_store(&xas, xa_mk_value(index + i))); + XA_BUG_ON(xa, xas_store(&xas, xa_mk_index(index + i))); xas_next(&xas); } unlock: @@ -1031,9 +1036,9 @@ static noinline void check_create_range_4(struct xarray *xa, if (xas_error(&xas)) goto unlock; for (i = 0; i < (1UL << order); i++) { - void *old = xas_store(&xas, xa_mk_value(base + i)); + void *old = xas_store(&xas, xa_mk_index(base + i)); if (xas.xa_index == index) - XA_BUG_ON(xa, old != xa_mk_value(base + i)); + XA_BUG_ON(xa, old != xa_mk_index(base + i)); else XA_BUG_ON(xa, old != NULL); xas_next(&xas); @@ -1085,10 +1090,10 @@ static noinline void __check_store_range(struct xarray *xa, unsigned long first, unsigned long last) { #ifdef CONFIG_XARRAY_MULTI - xa_store_range(xa, first, last, xa_mk_value(first), GFP_KERNEL); + xa_store_range(xa, first, last, xa_mk_index(first), GFP_KERNEL); - XA_BUG_ON(xa, xa_load(xa, first) != xa_mk_value(first)); - XA_BUG_ON(xa, xa_load(xa, last) != xa_mk_value(first)); + XA_BUG_ON(xa, xa_load(xa, first) != xa_mk_index(first)); + XA_BUG_ON(xa, xa_load(xa, last) != xa_mk_index(first)); XA_BUG_ON(xa, xa_load(xa, first - 1) != NULL); XA_BUG_ON(xa, xa_load(xa, last + 1) != NULL); @@ -1195,7 +1200,7 @@ static noinline void check_account(struct xarray *xa) XA_BUG_ON(xa, xas.xa_node->nr_values != 0); rcu_read_unlock(); - xa_store_order(xa, 1 << order, order, xa_mk_value(1 << order), + xa_store_order(xa, 1 << order, order, xa_mk_index(1UL << order), GFP_KERNEL); XA_BUG_ON(xa, xas.xa_node->count != xas.xa_node->nr_values * 2); -- cgit v1.2.3 From 4f145cd66a1a76136ff5a03a99e37ba082715dc6 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Thu, 29 Nov 2018 16:04:35 -0500 Subject: XArray tests: Check iterating over multiorder entries There was no bug here, but there was no test coverage for this scenario. Signed-off-by: Matthew Wilcox --- lib/test_xarray.c | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) diff --git a/lib/test_xarray.c b/lib/test_xarray.c index d30fd907a3dd..6f09c845187e 100644 --- a/lib/test_xarray.c +++ b/lib/test_xarray.c @@ -476,6 +476,32 @@ static noinline void check_multi_store_2(struct xarray *xa, unsigned long index, xas_unlock(&xas); XA_BUG_ON(xa, !xa_empty(xa)); } + +static noinline void check_multi_store_3(struct xarray *xa, unsigned long index, + unsigned int order) +{ + XA_STATE(xas, xa, 0); + void *entry; + int n = 0; + + xa_store_order(xa, index, order, xa_mk_index(index), GFP_KERNEL); + + xas_lock(&xas); + xas_for_each(&xas, entry, ULONG_MAX) { + XA_BUG_ON(xa, entry != xa_mk_index(index)); + n++; + } + XA_BUG_ON(xa, n != 1); + xas_set(&xas, index + 1); + xas_for_each(&xas, entry, ULONG_MAX) { + XA_BUG_ON(xa, entry != xa_mk_index(index)); + n++; + } + XA_BUG_ON(xa, n != 2); + xas_unlock(&xas); + + xa_destroy(xa); +} #endif static noinline void check_multi_store(struct xarray *xa) @@ -550,6 +576,11 @@ static noinline void check_multi_store(struct xarray *xa) check_multi_store_1(xa, (1UL << i) + 1, i); } check_multi_store_2(xa, 4095, 9); + + for (i = 1; i < 20; i++) { + check_multi_store_3(xa, 0, i); + check_multi_store_3(xa, 1UL << i, i); + } #endif } -- cgit v1.2.3 From 47f07f03b5ee436fe074c4fb1fb28d013c36a0d8 Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Wed, 5 Dec 2018 15:50:21 +0200 Subject: IB/mlx5: Block DEVX umem from the non applicable cases Blocks creating a DEVX UMEM with the non applicable access flags as of ODP, MW_BIND, etc. Specifically when an ODP flag is used below WARN call trace is issued. [ 2510.404131] RIP: 0010:__mlx5_ib_populate_pas+0x207/0x220 [mlx5_ib] ... [ 2510.404143] Call Trace: [ 2510.404150] ? __kmalloc_node+0x1b3/0x280 [ 2510.404156] ? _uverbs_alloc+0x63/0x90 [ib_uverbs] [ 2510.404158] ? _uverbs_alloc+0x63/0x90 [ib_uverbs] [ 2510.404162] mlx5_ib_populate_pas+0x53/0x60 [mlx5_ib] [ 2510.404167] mlx5_ib_handler_MLX5_IB_METHOD_DEVX_UMEM_REG+0x273/0x3f0 [mlx5_ib] Fixes: aeae94579caf ("IB/mlx5: Add DEVX support for memory registration") Signed-off-by: Yishai Hadas Reviewed-by: Artemy Kovalyov Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford --- drivers/infiniband/hw/mlx5/devx.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/infiniband/hw/mlx5/devx.c b/drivers/infiniband/hw/mlx5/devx.c index 61aab7c0c513..45c421c87100 100644 --- a/drivers/infiniband/hw/mlx5/devx.c +++ b/drivers/infiniband/hw/mlx5/devx.c @@ -1066,7 +1066,9 @@ static int devx_umem_get(struct mlx5_ib_dev *dev, struct ib_ucontext *ucontext, err = uverbs_get_flags32(&access, attrs, MLX5_IB_ATTR_DEVX_UMEM_REG_ACCESS, - IB_ACCESS_SUPPORTED); + IB_ACCESS_LOCAL_WRITE | + IB_ACCESS_REMOTE_WRITE | + IB_ACCESS_REMOTE_READ); if (err) return err; -- cgit v1.2.3 From bde1a7459623a66c2abec4d0a841e4b06cc88d9a Mon Sep 17 00:00:00 2001 From: Kailang Yang Date: Fri, 7 Dec 2018 15:14:59 +0800 Subject: ALSA: hda/realtek - Fixed headphone issue for ALC700 If it plugged headphone or headset into the jack, then do the reboot, it will have a chance to cause headphone no sound. It just need to run the headphone mode procedure after boot time. The issue will be fixed. It also suitable for ALC234 ALC274 and ALC294. Signed-off-by: Kailang Yang Cc: Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_realtek.c | 33 +++++++++++++++++++++++++++++++++ 1 file changed, 33 insertions(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 8d75597028ee..abc4d28dcf4f 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -7227,6 +7227,37 @@ static void alc269_fill_coef(struct hda_codec *codec) alc_update_coef_idx(codec, 0x4, 0, 1<<11); } +static void alc294_hp_init(struct hda_codec *codec) +{ + struct alc_spec *spec = codec->spec; + hda_nid_t hp_pin = spec->gen.autocfg.hp_pins[0]; + int i, val; + + if (!hp_pin) + return; + + snd_hda_codec_write(codec, hp_pin, 0, + AC_VERB_SET_AMP_GAIN_MUTE, AMP_OUT_MUTE); + + msleep(100); + + snd_hda_codec_write(codec, hp_pin, 0, + AC_VERB_SET_PIN_WIDGET_CONTROL, 0x0); + + alc_update_coef_idx(codec, 0x6f, 0x000f, 0);/* Set HP depop to manual mode */ + alc_update_coefex_idx(codec, 0x58, 0x00, 0x8000, 0x8000); /* HP depop procedure start */ + + /* Wait for depop procedure finish */ + val = alc_read_coefex_idx(codec, 0x58, 0x01); + for (i = 0; i < 20 && val & 0x0080; i++) { + msleep(50); + val = alc_read_coefex_idx(codec, 0x58, 0x01); + } + /* Set HP depop to auto mode */ + alc_update_coef_idx(codec, 0x6f, 0x000f, 0x000b); + msleep(50); +} + /* */ static int patch_alc269(struct hda_codec *codec) @@ -7352,6 +7383,7 @@ static int patch_alc269(struct hda_codec *codec) spec->codec_variant = ALC269_TYPE_ALC294; spec->gen.mixer_nid = 0; /* ALC2x4 does not have any loopback mixer path */ alc_update_coef_idx(codec, 0x6b, 0x0018, (1<<4) | (1<<3)); /* UAJ MIC Vref control by verb */ + alc294_hp_init(codec); break; case 0x10ec0300: spec->codec_variant = ALC269_TYPE_ALC300; @@ -7363,6 +7395,7 @@ static int patch_alc269(struct hda_codec *codec) spec->codec_variant = ALC269_TYPE_ALC700; spec->gen.mixer_nid = 0; /* ALC700 does not have any loopback mixer path */ alc_update_coef_idx(codec, 0x4a, 1 << 15, 0); /* Combo jack auto trigger control */ + alc294_hp_init(codec); break; } -- cgit v1.2.3 From 530aad77010b81526586dfc09130ec875cd084e4 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 5 Dec 2018 14:12:19 +0100 Subject: netfilter: seqadj: re-load tcp header pointer after possible head reallocation When adjusting sack block sequence numbers, skb_make_writable() gets called to make sure tcp options are all in the linear area, and buffer is not shared. This can cause tcp header pointer to get reallocated, so we must reaload it to avoid memory corruption. This bug pre-dates git history. Reported-by: Neel Mehta Reported-by: Shane Huntley Reported-by: Heather Adkins Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_conntrack_seqadj.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/net/netfilter/nf_conntrack_seqadj.c b/net/netfilter/nf_conntrack_seqadj.c index a975efd6b8c3..9da303461069 100644 --- a/net/netfilter/nf_conntrack_seqadj.c +++ b/net/netfilter/nf_conntrack_seqadj.c @@ -115,12 +115,12 @@ static void nf_ct_sack_block_adjust(struct sk_buff *skb, /* TCP SACK sequence number adjustment */ static unsigned int nf_ct_sack_adjust(struct sk_buff *skb, unsigned int protoff, - struct tcphdr *tcph, struct nf_conn *ct, enum ip_conntrack_info ctinfo) { - unsigned int dir, optoff, optend; + struct tcphdr *tcph = (void *)skb->data + protoff; struct nf_conn_seqadj *seqadj = nfct_seqadj(ct); + unsigned int dir, optoff, optend; optoff = protoff + sizeof(struct tcphdr); optend = protoff + tcph->doff * 4; @@ -128,6 +128,7 @@ static unsigned int nf_ct_sack_adjust(struct sk_buff *skb, if (!skb_make_writable(skb, optend)) return 0; + tcph = (void *)skb->data + protoff; dir = CTINFO2DIR(ctinfo); while (optoff < optend) { @@ -207,7 +208,7 @@ int nf_ct_seq_adjust(struct sk_buff *skb, ntohl(newack)); tcph->ack_seq = newack; - res = nf_ct_sack_adjust(skb, protoff, tcph, ct, ctinfo); + res = nf_ct_sack_adjust(skb, protoff, ct, ctinfo); out: spin_unlock_bh(&ct->lock); -- cgit v1.2.3 From a6460b03f945ee216dbf42a0d9ee78d52fd470c2 Mon Sep 17 00:00:00 2001 From: Sandipan Das Date: Thu, 6 Dec 2018 14:57:01 +0530 Subject: powerpc/bpf: Fix broken uapi for BPF_PROG_TYPE_PERF_EVENT Now that there are different variants of pt_regs for userspace and kernel, the uapi for the BPF_PROG_TYPE_PERF_EVENT program type must be changed by exporting the user_pt_regs structure instead of the pt_regs structure that is in-kernel only. Fixes: 002af9391bfb ("powerpc: Split user/kernel definitions of struct pt_regs") Signed-off-by: Sandipan Das Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/perf_event.h | 2 ++ arch/powerpc/include/uapi/asm/Kbuild | 1 - arch/powerpc/include/uapi/asm/bpf_perf_event.h | 9 +++++++++ 3 files changed, 11 insertions(+), 1 deletion(-) create mode 100644 arch/powerpc/include/uapi/asm/bpf_perf_event.h diff --git a/arch/powerpc/include/asm/perf_event.h b/arch/powerpc/include/asm/perf_event.h index 8bf1b6351716..16a49819da9a 100644 --- a/arch/powerpc/include/asm/perf_event.h +++ b/arch/powerpc/include/asm/perf_event.h @@ -26,6 +26,8 @@ #include #include +#define perf_arch_bpf_user_pt_regs(regs) ®s->user_regs + /* * Overload regs->result to specify whether we should use the MSR (result * is zero) or the SIAR (result is non zero). diff --git a/arch/powerpc/include/uapi/asm/Kbuild b/arch/powerpc/include/uapi/asm/Kbuild index a658091a19f9..3712152206f3 100644 --- a/arch/powerpc/include/uapi/asm/Kbuild +++ b/arch/powerpc/include/uapi/asm/Kbuild @@ -1,7 +1,6 @@ # UAPI Header export list include include/uapi/asm-generic/Kbuild.asm -generic-y += bpf_perf_event.h generic-y += param.h generic-y += poll.h generic-y += resource.h diff --git a/arch/powerpc/include/uapi/asm/bpf_perf_event.h b/arch/powerpc/include/uapi/asm/bpf_perf_event.h new file mode 100644 index 000000000000..b551b741653d --- /dev/null +++ b/arch/powerpc/include/uapi/asm/bpf_perf_event.h @@ -0,0 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _UAPI__ASM_BPF_PERF_EVENT_H__ +#define _UAPI__ASM_BPF_PERF_EVENT_H__ + +#include + +typedef struct user_pt_regs bpf_user_pt_regs_t; + +#endif /* _UAPI__ASM_BPF_PERF_EVENT_H__ */ -- cgit v1.2.3 From 14ebfec0712f66a4ef037fb7ac0df6a600584356 Mon Sep 17 00:00:00 2001 From: Oliver O'Halloran Date: Fri, 7 Dec 2018 02:17:08 +1100 Subject: powerpc/papr_scm: Use depend instead of select Making PAPR_SCM select LIBNVDIMM results in circular dependencies in Kconfig when another symbol depends on it. Fix this by replacing the select with a depends. Fixes: b5beae5e224f ("powerpc/pseries: Add driver for PAPR SCM regions") Reported-by: Alastair D'Silva Signed-off-by: Oliver O'Halloran Signed-off-by: Michael Ellerman --- arch/powerpc/platforms/pseries/Kconfig | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig index 2e4bd32154b5..472b784f01eb 100644 --- a/arch/powerpc/platforms/pseries/Kconfig +++ b/arch/powerpc/platforms/pseries/Kconfig @@ -140,8 +140,7 @@ config IBMEBUS Bus device driver for GX bus based adapters. config PAPR_SCM - depends on PPC_PSERIES && MEMORY_HOTPLUG - select LIBNVDIMM + depends on PPC_PSERIES && MEMORY_HOTPLUG && LIBNVDIMM tristate "Support for the PAPR Storage Class Memory interface" help Enable access to hypervisor provided storage class memory. -- cgit v1.2.3 From 59613526117b0595cb7b04835390ecd5175f9cd4 Mon Sep 17 00:00:00 2001 From: Oliver O'Halloran Date: Fri, 7 Dec 2018 02:17:09 +1100 Subject: powerpc/papr_scm: Fix resource end address Fix an off-by-one error in the memory resource range. This resource is used to determine the address range of the memory to be hot-plugged as ZONE_DEVICE memory. The current end address results in the kernel attempting to map an additional memblock and the hypervisor may reject the mapping resulting in the entire hot-plug failing. Fixes: b5beae5e224f ("powerpc/pseries: Add driver for PAPR SCM regions") Signed-off-by: Oliver O'Halloran Signed-off-by: Michael Ellerman --- arch/powerpc/platforms/pseries/papr_scm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c index ee9372b65ca5..390badd33547 100644 --- a/arch/powerpc/platforms/pseries/papr_scm.c +++ b/arch/powerpc/platforms/pseries/papr_scm.c @@ -296,7 +296,7 @@ static int papr_scm_probe(struct platform_device *pdev) /* setup the resource for the newly bound range */ p->res.start = p->bound_addr; - p->res.end = p->bound_addr + p->blocks * p->block_size; + p->res.end = p->bound_addr + p->blocks * p->block_size - 1; p->res.name = pdev->name; p->res.flags = IORESOURCE_MEM; -- cgit v1.2.3 From 478b6767ad26ab86d9ecc341027dd09a87b1f997 Mon Sep 17 00:00:00 2001 From: Chen-Yu Tsai Date: Tue, 4 Dec 2018 17:04:57 +0800 Subject: pinctrl: sunxi: a83t: Fix IRQ offset typo for PH11 Pin PH11 is used on various A83T board to detect a change in the OTG port's ID pin, as in when an OTG host cable is plugged in. The incorrect offset meant the gpiochip/irqchip was activating the wrong pin for interrupts. Fixes: 4730f33f0d82 ("pinctrl: sunxi: add allwinner A83T PIO controller support") Cc: Signed-off-by: Chen-Yu Tsai Acked-by: Maxime Ripard Signed-off-by: Linus Walleij --- drivers/pinctrl/sunxi/pinctrl-sun8i-a83t.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/pinctrl/sunxi/pinctrl-sun8i-a83t.c b/drivers/pinctrl/sunxi/pinctrl-sun8i-a83t.c index 6624499eae72..4ada80317a3b 100644 --- a/drivers/pinctrl/sunxi/pinctrl-sun8i-a83t.c +++ b/drivers/pinctrl/sunxi/pinctrl-sun8i-a83t.c @@ -568,7 +568,7 @@ static const struct sunxi_desc_pin sun8i_a83t_pins[] = { SUNXI_PIN(SUNXI_PINCTRL_PIN(H, 11), SUNXI_FUNCTION(0x0, "gpio_in"), SUNXI_FUNCTION(0x1, "gpio_out"), - SUNXI_FUNCTION_IRQ_BANK(0x6, 2, 1)), /* PH_EINT11 */ + SUNXI_FUNCTION_IRQ_BANK(0x6, 2, 11)), /* PH_EINT11 */ }; static const struct sunxi_pinctrl_desc sun8i_a83t_pinctrl_data = { -- cgit v1.2.3 From 868613f1c0ccf7b832f38b48b18cca31cdeb3d26 Mon Sep 17 00:00:00 2001 From: Nic Soudée Date: Thu, 6 Dec 2018 11:59:25 -0500 Subject: HID: quirks: fix RetroUSB.com devices SNES RetroPort and RetroPad register only 4 gamepad buttons when they should register all 8 buttons. This is described here: https://ask.fedoraproject.org/en/question/128102 This is happening because of: Commit 190d7f02ce8e ("HID: input: do not increment usages when duplicate is found") Here, I add the quirk HID_QUIRK_INCREMENT_USAGE_ON_DUPLICATE (created for backward compatibility with the change in 190d7f02ce8e) for the two products. Tested with both RetroPort and RetroPad. Cc: stable@vger.kernel.org # v4.18+ Signed-off-by: Nic Soudée Signed-off-by: Benjamin Tissoires --- drivers/hid/hid-ids.h | 4 ++++ drivers/hid/hid-quirks.c | 2 ++ 2 files changed, 6 insertions(+) diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index 94df9cdf6ec6..27519eb8ee63 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -944,6 +944,10 @@ #define USB_VENDOR_ID_REALTEK 0x0bda #define USB_DEVICE_ID_REALTEK_READER 0x0152 +#define USB_VENDOR_ID_RETROUSB 0xf000 +#define USB_DEVICE_ID_RETROUSB_SNES_RETROPAD 0x0003 +#define USB_DEVICE_ID_RETROUSB_SNES_RETROPORT 0x00f1 + #define USB_VENDOR_ID_ROCCAT 0x1e7d #define USB_DEVICE_ID_ROCCAT_ARVO 0x30d4 #define USB_DEVICE_ID_ROCCAT_ISKU 0x319c diff --git a/drivers/hid/hid-quirks.c b/drivers/hid/hid-quirks.c index c85a79986b6a..94088c0ed68a 100644 --- a/drivers/hid/hid-quirks.c +++ b/drivers/hid/hid-quirks.c @@ -137,6 +137,8 @@ static const struct hid_device_id hid_quirks[] = { { HID_USB_DEVICE(USB_VENDOR_ID_QUANTA, USB_DEVICE_ID_QUANTA_OPTICAL_TOUCH_3003), HID_QUIRK_NOGET }, { HID_USB_DEVICE(USB_VENDOR_ID_QUANTA, USB_DEVICE_ID_QUANTA_OPTICAL_TOUCH_3008), HID_QUIRK_NOGET }, { HID_USB_DEVICE(USB_VENDOR_ID_REALTEK, USB_DEVICE_ID_REALTEK_READER), HID_QUIRK_NO_INIT_REPORTS }, + { HID_USB_DEVICE(USB_VENDOR_ID_RETROUSB, USB_DEVICE_ID_RETROUSB_SNES_RETROPAD), HID_QUIRK_INCREMENT_USAGE_ON_DUPLICATE }, + { HID_USB_DEVICE(USB_VENDOR_ID_RETROUSB, USB_DEVICE_ID_RETROUSB_SNES_RETROPORT), HID_QUIRK_INCREMENT_USAGE_ON_DUPLICATE }, { HID_USB_DEVICE(USB_VENDOR_ID_SAITEK, USB_DEVICE_ID_SAITEK_RUMBLEPAD), HID_QUIRK_BADPAD }, { HID_USB_DEVICE(USB_VENDOR_ID_SEMICO, USB_DEVICE_ID_SEMICO_USB_KEYKOARD2), HID_QUIRK_NO_INIT_REPORTS }, { HID_USB_DEVICE(USB_VENDOR_ID_SEMICO, USB_DEVICE_ID_SEMICO_USB_KEYKOARD), HID_QUIRK_NO_INIT_REPORTS }, -- cgit v1.2.3 From c201e3808e0e4be9b98d192802085a9f491bd80c Mon Sep 17 00:00:00 2001 From: Peter Hutterer Date: Thu, 6 Dec 2018 09:03:36 +1000 Subject: Input: restore EV_ABS ABS_RESERVED ABS_RESERVED was added in d9ca1c990a7 and accidentally removed as part of ffe0e7cf290f5c9 when the high-resolution scrolling code was removed. Signed-off-by: Peter Hutterer Reviewed-by: Martin Kepplinger Acked-by: Benjamin Tissoires Acked-by: Dmitry Torokhov Signed-off-by: Benjamin Tissoires --- include/uapi/linux/input-event-codes.h | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/include/uapi/linux/input-event-codes.h b/include/uapi/linux/input-event-codes.h index 3eb5a4c3d60a..ae366b87426a 100644 --- a/include/uapi/linux/input-event-codes.h +++ b/include/uapi/linux/input-event-codes.h @@ -752,6 +752,15 @@ #define ABS_MISC 0x28 +/* + * 0x2e is reserved and should not be used in input drivers. + * It was used by HID as ABS_MISC+6 and userspace needs to detect if + * the next ABS_* event is correct or is just ABS_MISC + n. + * We define here ABS_RESERVED so userspace can rely on it and detect + * the situation described above. + */ +#define ABS_RESERVED 0x2e + #define ABS_MT_SLOT 0x2f /* MT slot being modified */ #define ABS_MT_TOUCH_MAJOR 0x30 /* Major axis of touching ellipse */ #define ABS_MT_TOUCH_MINOR 0x31 /* Minor axis (omit if circular) */ -- cgit v1.2.3 From 153573d8870e1c173721bdc1ced72b3ad0d85de4 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Wed, 17 Oct 2018 11:24:26 -0500 Subject: drm/amdgpu: update smu firmware images for VI variants (v2) Some new variants require updated firmware. V2: add MODULE_FIRMWARE for new firmwares Reviewed-by: Huang Rui (v1) Reviewed-by: Christian König Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c | 33 +++++++++++++++++++++++---- drivers/gpu/drm/amd/powerplay/smumgr/smumgr.c | 3 +++ 2 files changed, 31 insertions(+), 5 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c index 8816c697b205..ceadeeadfa56 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c @@ -330,7 +330,9 @@ static int amdgpu_cgs_get_firmware_info(struct cgs_device *cgs_device, case CHIP_TOPAZ: if (((adev->pdev->device == 0x6900) && (adev->pdev->revision == 0x81)) || ((adev->pdev->device == 0x6900) && (adev->pdev->revision == 0x83)) || - ((adev->pdev->device == 0x6907) && (adev->pdev->revision == 0x87))) { + ((adev->pdev->device == 0x6907) && (adev->pdev->revision == 0x87)) || + ((adev->pdev->device == 0x6900) && (adev->pdev->revision == 0xD1)) || + ((adev->pdev->device == 0x6900) && (adev->pdev->revision == 0xD3))) { info->is_kicker = true; strcpy(fw_name, "amdgpu/topaz_k_smc.bin"); } else @@ -351,7 +353,6 @@ static int amdgpu_cgs_get_firmware_info(struct cgs_device *cgs_device, if (type == CGS_UCODE_ID_SMU) { if (((adev->pdev->device == 0x67ef) && ((adev->pdev->revision == 0xe0) || - (adev->pdev->revision == 0xe2) || (adev->pdev->revision == 0xe5))) || ((adev->pdev->device == 0x67ff) && ((adev->pdev->revision == 0xcf) || @@ -359,8 +360,13 @@ static int amdgpu_cgs_get_firmware_info(struct cgs_device *cgs_device, (adev->pdev->revision == 0xff)))) { info->is_kicker = true; strcpy(fw_name, "amdgpu/polaris11_k_smc.bin"); - } else + } else if ((adev->pdev->device == 0x67ef) && + (adev->pdev->revision == 0xe2)) { + info->is_kicker = true; + strcpy(fw_name, "amdgpu/polaris11_k2_smc.bin"); + } else { strcpy(fw_name, "amdgpu/polaris11_smc.bin"); + } } else if (type == CGS_UCODE_ID_SMU_SK) { strcpy(fw_name, "amdgpu/polaris11_smc_sk.bin"); } @@ -378,14 +384,31 @@ static int amdgpu_cgs_get_firmware_info(struct cgs_device *cgs_device, (adev->pdev->revision == 0xef))) { info->is_kicker = true; strcpy(fw_name, "amdgpu/polaris10_k_smc.bin"); - } else + } else if ((adev->pdev->device == 0x67df) && + ((adev->pdev->revision == 0xe1) || + (adev->pdev->revision == 0xf7))) { + info->is_kicker = true; + strcpy(fw_name, "amdgpu/polaris10_k2_smc.bin"); + } else { strcpy(fw_name, "amdgpu/polaris10_smc.bin"); + } } else if (type == CGS_UCODE_ID_SMU_SK) { strcpy(fw_name, "amdgpu/polaris10_smc_sk.bin"); } break; case CHIP_POLARIS12: - strcpy(fw_name, "amdgpu/polaris12_smc.bin"); + if (((adev->pdev->device == 0x6987) && + ((adev->pdev->revision == 0xc0) || + (adev->pdev->revision == 0xc3))) || + ((adev->pdev->device == 0x6981) && + ((adev->pdev->revision == 0x00) || + (adev->pdev->revision == 0x01) || + (adev->pdev->revision == 0x10)))) { + info->is_kicker = true; + strcpy(fw_name, "amdgpu/polaris12_k_smc.bin"); + } else { + strcpy(fw_name, "amdgpu/polaris12_smc.bin"); + } break; case CHIP_VEGAM: strcpy(fw_name, "amdgpu/vegam_smc.bin"); diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/smumgr.c index 99d5e4f98f49..a6edd5df33b0 100644 --- a/drivers/gpu/drm/amd/powerplay/smumgr/smumgr.c +++ b/drivers/gpu/drm/amd/powerplay/smumgr/smumgr.c @@ -37,10 +37,13 @@ MODULE_FIRMWARE("amdgpu/fiji_smc.bin"); MODULE_FIRMWARE("amdgpu/polaris10_smc.bin"); MODULE_FIRMWARE("amdgpu/polaris10_smc_sk.bin"); MODULE_FIRMWARE("amdgpu/polaris10_k_smc.bin"); +MODULE_FIRMWARE("amdgpu/polaris10_k2_smc.bin"); MODULE_FIRMWARE("amdgpu/polaris11_smc.bin"); MODULE_FIRMWARE("amdgpu/polaris11_smc_sk.bin"); MODULE_FIRMWARE("amdgpu/polaris11_k_smc.bin"); +MODULE_FIRMWARE("amdgpu/polaris11_k2_smc.bin"); MODULE_FIRMWARE("amdgpu/polaris12_smc.bin"); +MODULE_FIRMWARE("amdgpu/polaris12_k_smc.bin"); MODULE_FIRMWARE("amdgpu/vegam_smc.bin"); MODULE_FIRMWARE("amdgpu/vega10_smc.bin"); MODULE_FIRMWARE("amdgpu/vega10_acg_smc.bin"); -- cgit v1.2.3 From 687cf4412a343a63928a5c9d91bdc0f522939d43 Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Fri, 9 Nov 2018 11:56:03 -0500 Subject: dm cache metadata: verify cache has blocks in blocks_are_clean_separate_dirty() Otherwise dm_bitset_cursor_begin() return -ENODATA. Other calls to dm_bitset_cursor_begin() have similar negative checks. Fixes inability to create a cache in passthrough mode (even though doing so makes no sense). Fixes: 0d963b6e65 ("dm cache metadata: fix metadata2 format's blocks_are_clean_separate_dirty") Cc: stable@vger.kernel.org Reported-by: David Teigland Signed-off-by: Mike Snitzer --- drivers/md/dm-cache-metadata.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/md/dm-cache-metadata.c b/drivers/md/dm-cache-metadata.c index 5936de71883f..6fc93834da44 100644 --- a/drivers/md/dm-cache-metadata.c +++ b/drivers/md/dm-cache-metadata.c @@ -930,6 +930,10 @@ static int blocks_are_clean_separate_dirty(struct dm_cache_metadata *cmd, bool dirty_flag; *result = true; + if (from_cblock(cmd->cache_blocks) == 0) + /* Nothing to do */ + return 0; + r = dm_bitset_cursor_begin(&cmd->dirty_info, cmd->dirty_root, from_cblock(cmd->cache_blocks), &cmd->dirty_cursor); if (r) { -- cgit v1.2.3 From 89f5fa47476eda56402e29fff3c5097f5c2a1e19 Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Mon, 3 Dec 2018 16:47:21 -0500 Subject: dm: call blk_queue_split() to impose device limits on bios Otherwise the incoming bios, of various types, won't be shaped based on the DM device's advertised limits. Depends-on: af67c31fba ("blk: remove bio_set arg from blk_queue_split()") Fixes: 744889b7cb ("block: don't deal with discard limit in blkdev_issue_discard()") Cc: stable@vger.kernel.org Signed-off-by: Mike Snitzer --- drivers/md/dm.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/md/dm.c b/drivers/md/dm.c index c510179a7f84..63a7c416b224 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1593,6 +1593,8 @@ static blk_qc_t __split_and_process_bio(struct mapped_device *md, return ret; } + blk_queue_split(md->queue, &bio); + init_clone_info(&ci, md, map, bio); if (bio->bi_opf & REQ_PREFLUSH) { -- cgit v1.2.3 From d57f9da890696af1484f4a47f7f123560197865a Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Fri, 30 Nov 2018 15:31:48 +0900 Subject: dm zoned: Fix target BIO completion handling struct bioctx includes the ref refcount_t to track the number of I/O fragments used to process a target BIO as well as ensure that the zone of the BIO is kept in the active state throughout the lifetime of the BIO. However, since decrementing of this reference count is done in the target .end_io method, the function bio_endio() must be called multiple times for read and write target BIOs, which causes problems with the value of the __bi_remaining struct bio field for chained BIOs (e.g. the clone BIO passed by dm core is large and splits into fragments by the block layer), resulting in incorrect values and inconsistencies with the BIO_CHAIN flag setting. This is turn triggers the BUG_ON() call: BUG_ON(atomic_read(&bio->__bi_remaining) <= 0); in bio_remaining_done() called from bio_endio(). Fix this ensuring that bio_endio() is called only once for any target BIO by always using internal clone BIOs for processing any read or write target BIO. This allows reference counting using the target BIO context counter to trigger the target BIO completion bio_endio() call once all data, metadata and other zone work triggered by the BIO complete. Overall, this simplifies the code too as the target .end_io becomes unnecessary and differences between read and write BIO issuing and completion processing disappear. Fixes: 3b1a94c88b79 ("dm zoned: drive-managed zoned block device target") Cc: stable@vger.kernel.org Signed-off-by: Damien Le Moal Signed-off-by: Mike Snitzer --- drivers/md/dm-zoned-target.c | 122 ++++++++++++++----------------------------- 1 file changed, 38 insertions(+), 84 deletions(-) diff --git a/drivers/md/dm-zoned-target.c b/drivers/md/dm-zoned-target.c index 981154e59461..6af5babe6837 100644 --- a/drivers/md/dm-zoned-target.c +++ b/drivers/md/dm-zoned-target.c @@ -20,7 +20,6 @@ struct dmz_bioctx { struct dm_zone *zone; struct bio *bio; refcount_t ref; - blk_status_t status; }; /* @@ -78,65 +77,66 @@ static inline void dmz_bio_endio(struct bio *bio, blk_status_t status) { struct dmz_bioctx *bioctx = dm_per_bio_data(bio, sizeof(struct dmz_bioctx)); - if (bioctx->status == BLK_STS_OK && status != BLK_STS_OK) - bioctx->status = status; - bio_endio(bio); + if (status != BLK_STS_OK && bio->bi_status == BLK_STS_OK) + bio->bi_status = status; + + if (refcount_dec_and_test(&bioctx->ref)) { + struct dm_zone *zone = bioctx->zone; + + if (zone) { + if (bio->bi_status != BLK_STS_OK && + bio_op(bio) == REQ_OP_WRITE && + dmz_is_seq(zone)) + set_bit(DMZ_SEQ_WRITE_ERR, &zone->flags); + dmz_deactivate_zone(zone); + } + bio_endio(bio); + } } /* - * Partial clone read BIO completion callback. This terminates the + * Completion callback for an internally cloned target BIO. This terminates the * target BIO when there are no more references to its context. */ -static void dmz_read_bio_end_io(struct bio *bio) +static void dmz_clone_endio(struct bio *clone) { - struct dmz_bioctx *bioctx = bio->bi_private; - blk_status_t status = bio->bi_status; + struct dmz_bioctx *bioctx = clone->bi_private; + blk_status_t status = clone->bi_status; - bio_put(bio); + bio_put(clone); dmz_bio_endio(bioctx->bio, status); } /* - * Issue a BIO to a zone. The BIO may only partially process the + * Issue a clone of a target BIO. The clone may only partially process the * original target BIO. */ -static int dmz_submit_read_bio(struct dmz_target *dmz, struct dm_zone *zone, - struct bio *bio, sector_t chunk_block, - unsigned int nr_blocks) +static int dmz_submit_bio(struct dmz_target *dmz, struct dm_zone *zone, + struct bio *bio, sector_t chunk_block, + unsigned int nr_blocks) { struct dmz_bioctx *bioctx = dm_per_bio_data(bio, sizeof(struct dmz_bioctx)); - sector_t sector; struct bio *clone; - /* BIO remap sector */ - sector = dmz_start_sect(dmz->metadata, zone) + dmz_blk2sect(chunk_block); - - /* If the read is not partial, there is no need to clone the BIO */ - if (nr_blocks == dmz_bio_blocks(bio)) { - /* Setup and submit the BIO */ - bio->bi_iter.bi_sector = sector; - refcount_inc(&bioctx->ref); - generic_make_request(bio); - return 0; - } - - /* Partial BIO: we need to clone the BIO */ clone = bio_clone_fast(bio, GFP_NOIO, &dmz->bio_set); if (!clone) return -ENOMEM; - /* Setup the clone */ - clone->bi_iter.bi_sector = sector; + bio_set_dev(clone, dmz->dev->bdev); + clone->bi_iter.bi_sector = + dmz_start_sect(dmz->metadata, zone) + dmz_blk2sect(chunk_block); clone->bi_iter.bi_size = dmz_blk2sect(nr_blocks) << SECTOR_SHIFT; - clone->bi_end_io = dmz_read_bio_end_io; + clone->bi_end_io = dmz_clone_endio; clone->bi_private = bioctx; bio_advance(bio, clone->bi_iter.bi_size); - /* Submit the clone */ refcount_inc(&bioctx->ref); generic_make_request(clone); + if (bio_op(bio) == REQ_OP_WRITE && dmz_is_seq(zone)) + zone->wp_block += nr_blocks; + return 0; } @@ -214,7 +214,7 @@ static int dmz_handle_read(struct dmz_target *dmz, struct dm_zone *zone, if (nr_blocks) { /* Valid blocks found: read them */ nr_blocks = min_t(unsigned int, nr_blocks, end_block - chunk_block); - ret = dmz_submit_read_bio(dmz, rzone, bio, chunk_block, nr_blocks); + ret = dmz_submit_bio(dmz, rzone, bio, chunk_block, nr_blocks); if (ret) return ret; chunk_block += nr_blocks; @@ -228,25 +228,6 @@ static int dmz_handle_read(struct dmz_target *dmz, struct dm_zone *zone, return 0; } -/* - * Issue a write BIO to a zone. - */ -static void dmz_submit_write_bio(struct dmz_target *dmz, struct dm_zone *zone, - struct bio *bio, sector_t chunk_block, - unsigned int nr_blocks) -{ - struct dmz_bioctx *bioctx = dm_per_bio_data(bio, sizeof(struct dmz_bioctx)); - - /* Setup and submit the BIO */ - bio_set_dev(bio, dmz->dev->bdev); - bio->bi_iter.bi_sector = dmz_start_sect(dmz->metadata, zone) + dmz_blk2sect(chunk_block); - refcount_inc(&bioctx->ref); - generic_make_request(bio); - - if (dmz_is_seq(zone)) - zone->wp_block += nr_blocks; -} - /* * Write blocks directly in a data zone, at the write pointer. * If a buffer zone is assigned, invalidate the blocks written @@ -265,7 +246,9 @@ static int dmz_handle_direct_write(struct dmz_target *dmz, return -EROFS; /* Submit write */ - dmz_submit_write_bio(dmz, zone, bio, chunk_block, nr_blocks); + ret = dmz_submit_bio(dmz, zone, bio, chunk_block, nr_blocks); + if (ret) + return ret; /* * Validate the blocks in the data zone and invalidate @@ -301,7 +284,9 @@ static int dmz_handle_buffered_write(struct dmz_target *dmz, return -EROFS; /* Submit write */ - dmz_submit_write_bio(dmz, bzone, bio, chunk_block, nr_blocks); + ret = dmz_submit_bio(dmz, bzone, bio, chunk_block, nr_blocks); + if (ret) + return ret; /* * Validate the blocks in the buffer zone @@ -600,7 +585,6 @@ static int dmz_map(struct dm_target *ti, struct bio *bio) bioctx->zone = NULL; bioctx->bio = bio; refcount_set(&bioctx->ref, 1); - bioctx->status = BLK_STS_OK; /* Set the BIO pending in the flush list */ if (!nr_sectors && bio_op(bio) == REQ_OP_WRITE) { @@ -623,35 +607,6 @@ static int dmz_map(struct dm_target *ti, struct bio *bio) return DM_MAPIO_SUBMITTED; } -/* - * Completed target BIO processing. - */ -static int dmz_end_io(struct dm_target *ti, struct bio *bio, blk_status_t *error) -{ - struct dmz_bioctx *bioctx = dm_per_bio_data(bio, sizeof(struct dmz_bioctx)); - - if (bioctx->status == BLK_STS_OK && *error) - bioctx->status = *error; - - if (!refcount_dec_and_test(&bioctx->ref)) - return DM_ENDIO_INCOMPLETE; - - /* Done */ - bio->bi_status = bioctx->status; - - if (bioctx->zone) { - struct dm_zone *zone = bioctx->zone; - - if (*error && bio_op(bio) == REQ_OP_WRITE) { - if (dmz_is_seq(zone)) - set_bit(DMZ_SEQ_WRITE_ERR, &zone->flags); - } - dmz_deactivate_zone(zone); - } - - return DM_ENDIO_DONE; -} - /* * Get zoned device information. */ @@ -946,7 +901,6 @@ static struct target_type dmz_type = { .ctr = dmz_ctr, .dtr = dmz_dtr, .map = dmz_map, - .end_io = dmz_end_io, .io_hints = dmz_io_hints, .prepare_ioctl = dmz_prepare_ioctl, .postsuspend = dmz_suspend, -- cgit v1.2.3 From 13e56ec2cc9860aa22e01ffc7a3160f35a96b728 Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Wed, 5 Dec 2018 20:40:47 -0800 Subject: selftests/bpf: use thoff instead of nhoff in BPF flow dissector We are returning thoff from the flow dissector, not the nhoff. Pass thoff along with nhoff to the bpf program (initially thoff == nhoff) and expect flow dissector amend/return thoff, not nhoff. This avoids confusion, when by the time bpf flow dissector exits, nhoff == thoff, which doesn't make much sense. Signed-off-by: Stanislav Fomichev Acked-by: Song Liu Signed-off-by: Alexei Starovoitov --- net/core/flow_dissector.c | 1 + tools/testing/selftests/bpf/bpf_flow.c | 36 ++++++++++++++++------------------ 2 files changed, 18 insertions(+), 19 deletions(-) diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 588f475019d4..ff5556d80570 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -783,6 +783,7 @@ bool __skb_flow_dissect(const struct sk_buff *skb, /* Pass parameters to the BPF program */ cb->qdisc_cb.flow_keys = &flow_keys; flow_keys.nhoff = nhoff; + flow_keys.thoff = nhoff; bpf_compute_data_pointers((struct sk_buff *)skb); result = BPF_PROG_RUN(attached, skb); diff --git a/tools/testing/selftests/bpf/bpf_flow.c b/tools/testing/selftests/bpf/bpf_flow.c index 107350a7821d..df9d32fd2055 100644 --- a/tools/testing/selftests/bpf/bpf_flow.c +++ b/tools/testing/selftests/bpf/bpf_flow.c @@ -70,18 +70,18 @@ static __always_inline void *bpf_flow_dissect_get_header(struct __sk_buff *skb, { void *data_end = (void *)(long)skb->data_end; void *data = (void *)(long)skb->data; - __u16 nhoff = skb->flow_keys->nhoff; + __u16 thoff = skb->flow_keys->thoff; __u8 *hdr; /* Verifies this variable offset does not overflow */ - if (nhoff > (USHRT_MAX - hdr_size)) + if (thoff > (USHRT_MAX - hdr_size)) return NULL; - hdr = data + nhoff; + hdr = data + thoff; if (hdr + hdr_size <= data_end) return hdr; - if (bpf_skb_load_bytes(skb, nhoff, buffer, hdr_size)) + if (bpf_skb_load_bytes(skb, thoff, buffer, hdr_size)) return NULL; return buffer; @@ -158,13 +158,13 @@ static __always_inline int parse_ip_proto(struct __sk_buff *skb, __u8 proto) /* Only inspect standard GRE packets with version 0 */ return BPF_OK; - keys->nhoff += sizeof(*gre); /* Step over GRE Flags and Proto */ + keys->thoff += sizeof(*gre); /* Step over GRE Flags and Proto */ if (GRE_IS_CSUM(gre->flags)) - keys->nhoff += 4; /* Step over chksum and Padding */ + keys->thoff += 4; /* Step over chksum and Padding */ if (GRE_IS_KEY(gre->flags)) - keys->nhoff += 4; /* Step over key */ + keys->thoff += 4; /* Step over key */ if (GRE_IS_SEQ(gre->flags)) - keys->nhoff += 4; /* Step over sequence number */ + keys->thoff += 4; /* Step over sequence number */ keys->is_encap = true; @@ -174,7 +174,7 @@ static __always_inline int parse_ip_proto(struct __sk_buff *skb, __u8 proto) if (!eth) return BPF_DROP; - keys->nhoff += sizeof(*eth); + keys->thoff += sizeof(*eth); return parse_eth_proto(skb, eth->h_proto); } else { @@ -191,7 +191,6 @@ static __always_inline int parse_ip_proto(struct __sk_buff *skb, __u8 proto) if ((__u8 *)tcp + (tcp->doff << 2) > data_end) return BPF_DROP; - keys->thoff = keys->nhoff; keys->sport = tcp->source; keys->dport = tcp->dest; return BPF_OK; @@ -201,7 +200,6 @@ static __always_inline int parse_ip_proto(struct __sk_buff *skb, __u8 proto) if (!udp) return BPF_DROP; - keys->thoff = keys->nhoff; keys->sport = udp->source; keys->dport = udp->dest; return BPF_OK; @@ -252,8 +250,8 @@ PROG(IP)(struct __sk_buff *skb) keys->ipv4_src = iph->saddr; keys->ipv4_dst = iph->daddr; - keys->nhoff += iph->ihl << 2; - if (data + keys->nhoff > data_end) + keys->thoff += iph->ihl << 2; + if (data + keys->thoff > data_end) return BPF_DROP; if (iph->frag_off & bpf_htons(IP_MF | IP_OFFSET)) { @@ -285,7 +283,7 @@ PROG(IPV6)(struct __sk_buff *skb) keys->addr_proto = ETH_P_IPV6; memcpy(&keys->ipv6_src, &ip6h->saddr, 2*sizeof(ip6h->saddr)); - keys->nhoff += sizeof(struct ipv6hdr); + keys->thoff += sizeof(struct ipv6hdr); return parse_ipv6_proto(skb, ip6h->nexthdr); } @@ -301,7 +299,7 @@ PROG(IPV6OP)(struct __sk_buff *skb) /* hlen is in 8-octets and does not include the first 8 bytes * of the header */ - skb->flow_keys->nhoff += (1 + ip6h->hdrlen) << 3; + skb->flow_keys->thoff += (1 + ip6h->hdrlen) << 3; return parse_ipv6_proto(skb, ip6h->nexthdr); } @@ -315,7 +313,7 @@ PROG(IPV6FR)(struct __sk_buff *skb) if (!fragh) return BPF_DROP; - keys->nhoff += sizeof(*fragh); + keys->thoff += sizeof(*fragh); keys->is_frag = true; if (!(fragh->frag_off & bpf_htons(IP6_OFFSET))) keys->is_first_frag = true; @@ -341,7 +339,7 @@ PROG(VLAN)(struct __sk_buff *skb) __be16 proto; /* Peek back to see if single or double-tagging */ - if (bpf_skb_load_bytes(skb, keys->nhoff - sizeof(proto), &proto, + if (bpf_skb_load_bytes(skb, keys->thoff - sizeof(proto), &proto, sizeof(proto))) return BPF_DROP; @@ -354,14 +352,14 @@ PROG(VLAN)(struct __sk_buff *skb) if (vlan->h_vlan_encapsulated_proto != bpf_htons(ETH_P_8021Q)) return BPF_DROP; - keys->nhoff += sizeof(*vlan); + keys->thoff += sizeof(*vlan); } vlan = bpf_flow_dissect_get_header(skb, sizeof(*vlan), &_vlan); if (!vlan) return BPF_DROP; - keys->nhoff += sizeof(*vlan); + keys->thoff += sizeof(*vlan); /* Only allow 8021AD + 8021Q double tagging and no triple tagging.*/ if (vlan->h_vlan_encapsulated_proto == bpf_htons(ETH_P_8021AD) || vlan->h_vlan_encapsulated_proto == bpf_htons(ETH_P_8021Q)) -- cgit v1.2.3 From ec3d837aac5dca7cb8a69c9f101690c182da79c4 Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Wed, 5 Dec 2018 20:40:48 -0800 Subject: net/flow_dissector: correctly cap nhoff and thoff in case of BPF We want to make sure that the following condition holds: 0 <= nhoff <= thoff <= skb->len BPF program can set out-of-bounds nhoff and thoff, which is dangerous, see recent commit d0c081b49137 ("flow_dissector: properly cap thoff field")'. Signed-off-by: Stanislav Fomichev Acked-by: Song Liu Signed-off-by: Alexei Starovoitov --- net/core/flow_dissector.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index ff5556d80570..af68207ee56c 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -791,9 +791,12 @@ bool __skb_flow_dissect(const struct sk_buff *skb, /* Restore state */ memcpy(cb, &cb_saved, sizeof(cb_saved)); + flow_keys.nhoff = clamp_t(u16, flow_keys.nhoff, 0, skb->len); + flow_keys.thoff = clamp_t(u16, flow_keys.thoff, + flow_keys.nhoff, skb->len); + __skb_flow_bpf_to_target(&flow_keys, flow_dissector, target_container); - key_control->thoff = min_t(u16, key_control->thoff, skb->len); rcu_read_unlock(); return result == BPF_OK; } -- cgit v1.2.3 From c64a87f9518409d0a439895f09f6149ffdd427b8 Mon Sep 17 00:00:00 2001 From: Himanshu Madhani Date: Thu, 6 Dec 2018 21:49:42 -0800 Subject: Revert "scsi: qla2xxx: Fix NVMe Target discovery" This reverts commit db186382af21e926e90df19499475f2552192b77. This commit introduced regression with FCP discovery so revert it to fix discovery for FCP luns. Signed-off-by: Himanshu Madhani Signed-off-by: Martin K. Petersen --- drivers/scsi/qla2xxx/qla_os.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index b658b9a5eb1e..d0ecc729a90a 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -4886,10 +4886,10 @@ void qla24xx_create_new_sess(struct scsi_qla_host *vha, struct qla_work_evt *e) fcport->d_id = e->u.new_sess.id; fcport->flags |= FCF_FABRIC_DEVICE; fcport->fw_login_state = DSC_LS_PLOGI_PEND; - if (e->u.new_sess.fc4_type & FS_FC4TYPE_FCP) + if (e->u.new_sess.fc4_type == FS_FC4TYPE_FCP) fcport->fc4_type = FC4_TYPE_FCP_SCSI; - if (e->u.new_sess.fc4_type & FS_FC4TYPE_NVME) { + if (e->u.new_sess.fc4_type == FS_FC4TYPE_NVME) { fcport->fc4_type = FC4_TYPE_OTHER; fcport->fc4f_nvme = FC4_TYPE_NVME; } -- cgit v1.2.3 From 9ae4f8420ed7be4b13c96600e3568c144d101a23 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Thu, 1 Nov 2018 08:25:30 +0300 Subject: scsi: bnx2fc: Fix NULL dereference in error handling If "interface" is NULL then we can't release it and trying to will only lead to an Oops. Fixes: aea71a024914 ("[SCSI] bnx2fc: Introduce interface structure for each vlan interface") Signed-off-by: Dan Carpenter Signed-off-by: Martin K. Petersen --- drivers/scsi/bnx2fc/bnx2fc_fcoe.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c index cd160f2ec75d..bcd30e2374f1 100644 --- a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c +++ b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c @@ -2364,7 +2364,7 @@ static int _bnx2fc_create(struct net_device *netdev, if (!interface) { printk(KERN_ERR PFX "bnx2fc_interface_create failed\n"); rc = -ENOMEM; - goto ifput_err; + goto netdev_err; } if (is_vlan_dev(netdev)) { -- cgit v1.2.3 From 60a89a3ce0cce515dc663bc1b45ac89202ad6c79 Mon Sep 17 00:00:00 2001 From: Martin K. Petersen Date: Tue, 4 Dec 2018 20:58:33 -0500 Subject: scsi: t10-pi: Return correct ref tag when queue has no integrity profile Commit ddd0bc756983 ("block: move ref_tag calculation func to the block layer") moved ref tag calculation from SCSI to a library function. However, this change broke returning the correct ref tag for devices operating in DIF mode since these do not have an associated block integrity profile. This in turn caused read/write failures on PI-formatted disks attached to an mpt3sas controller. Fixes: ddd0bc756983 ("block: move ref_tag calculation func to the block layer") Cc: stable@vger.kernel.org # 4.19+ Reported-by: John Garry Tested-by: Xiang Chen Signed-off-by: Martin K. Petersen --- include/linux/t10-pi.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/include/linux/t10-pi.h b/include/linux/t10-pi.h index b9626aa7e90c..3e2a80cc7b56 100644 --- a/include/linux/t10-pi.h +++ b/include/linux/t10-pi.h @@ -39,12 +39,13 @@ struct t10_pi_tuple { static inline u32 t10_pi_ref_tag(struct request *rq) { + unsigned int shift = ilog2(queue_logical_block_size(rq->q)); + #ifdef CONFIG_BLK_DEV_INTEGRITY - return blk_rq_pos(rq) >> - (rq->q->integrity.interval_exp - 9) & 0xffffffff; -#else - return -1U; + if (rq->q->integrity.interval_exp) + shift = rq->q->integrity.interval_exp; #endif + return blk_rq_pos(rq) >> (shift - SECTOR_SHIFT) & 0xffffffff; } extern const struct blk_integrity_profile t10_pi_type1_crc; -- cgit v1.2.3 From 6ba189c5c1a4bda70dc1e4826c58b0246068bb8d Mon Sep 17 00:00:00 2001 From: Hui Wang Date: Sun, 9 Dec 2018 09:16:43 +0800 Subject: ALSA: hda/realtek - Fix the mute LED regresion on Lenovo X1 Carbon Users reported a mute LED regression on Lenovo X1 Carbon, the root cause is we applied the fixup of ALC285_FIXUP_LENOVO_HEADPHONE_NOISE to this machine, then the machine can't apply the fixup of ALC269_FIXUP_THINKPAD_ACPI anymore. To fix it, we chain two fixup together. Fixes: c4cfcf6f4297 ("ALSA: hda/realtek - fix the pop noise on headphone for lenovo laptops") Cc: Signed-off-by: Hui Wang Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_realtek.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index abc4d28dcf4f..cbd78aa5fad3 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -6392,6 +6392,8 @@ static const struct hda_fixup alc269_fixups[] = { [ALC285_FIXUP_LENOVO_HEADPHONE_NOISE] = { .type = HDA_FIXUP_FUNC, .v.func = alc285_fixup_invalidate_dacs, + .chained = true, + .chain_id = ALC269_FIXUP_THINKPAD_ACPI }, [ALC295_FIXUP_HP_AUTO_MUTE] = { .type = HDA_FIXUP_FUNC, -- cgit v1.2.3 From fa9c98e4b975bb3192ed6af09d9fa282ed3cd8a0 Mon Sep 17 00:00:00 2001 From: Takashi Sakamoto Date: Sun, 9 Dec 2018 17:04:19 +0900 Subject: ALSA: fireface: fix reference to wrong register for clock configuration In an initial commit, 'SYNC_STATUS' register is referred to get clock configuration, however this is wrong, according to my local note at hand for reverse-engineering about packet dump. It should be 'CLOCK_CONFIG' register. Actually, ff400_dump_clock_config() is correctly programmed. This commit fixes the bug. Cc: # v4.12+ Fixes: 76fdb3a9e13a ('ALSA: fireface: add support for Fireface 400') Signed-off-by: Takashi Sakamoto Signed-off-by: Takashi Iwai --- sound/firewire/fireface/ff-protocol-ff400.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/firewire/fireface/ff-protocol-ff400.c b/sound/firewire/fireface/ff-protocol-ff400.c index 64c3cb0fb926..654a50319198 100644 --- a/sound/firewire/fireface/ff-protocol-ff400.c +++ b/sound/firewire/fireface/ff-protocol-ff400.c @@ -30,7 +30,7 @@ static int ff400_get_clock(struct snd_ff *ff, unsigned int *rate, int err; err = snd_fw_transaction(ff->unit, TCODE_READ_QUADLET_REQUEST, - FF400_SYNC_STATUS, ®, sizeof(reg), 0); + FF400_CLOCK_CONFIG, ®, sizeof(reg), 0); if (err < 0) return err; data = le32_to_cpu(reg); -- cgit v1.2.3 From 683ec0e04ab7e2d86d2656c71322dfb2ebf063fc Mon Sep 17 00:00:00 2001 From: Oliver O'Halloran Date: Fri, 7 Dec 2018 02:17:10 +1100 Subject: powerpc/papr_scm: Update DT properties The ibm,unit-sizes property was originally specified as an array of two u32s corresponding to the memory block size, and the number of blocks available in that region. A fairly last-minute change to the SCM DT specification was splitting that into two seperate u64 properties: ibm,block-sizes and ibm,number-of-blocks that convey the same information. No firmware / hypervisor that emitted the ibm,unit-size property ever appeared in the wild. Fixes: b5beae5e224f ("powerpc/pseries: Add driver for PAPR SCM regions") Signed-off-by: Oliver O'Halloran [mpe: Use kernel types (u32/u64)] Signed-off-by: Michael Ellerman --- arch/powerpc/platforms/pseries/papr_scm.c | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c index 390badd33547..de47e3719c8d 100644 --- a/arch/powerpc/platforms/pseries/papr_scm.c +++ b/arch/powerpc/platforms/pseries/papr_scm.c @@ -257,8 +257,9 @@ err: nvdimm_bus_unregister(p->bus); static int papr_scm_probe(struct platform_device *pdev) { - uint32_t drc_index, metadata_size, unit_cap[2]; struct device_node *dn = pdev->dev.of_node; + u32 drc_index, metadata_size; + u64 blocks, block_size; struct papr_scm_priv *p; int rc; @@ -268,8 +269,13 @@ static int papr_scm_probe(struct platform_device *pdev) return -ENODEV; } - if (of_property_read_u32_array(dn, "ibm,unit-capacity", unit_cap, 2)) { - dev_err(&pdev->dev, "%pOF: missing unit-capacity!\n", dn); + if (of_property_read_u64(dn, "ibm,block-size", &block_size)) { + dev_err(&pdev->dev, "%pOF: missing block-size!\n", dn); + return -ENODEV; + } + + if (of_property_read_u64(dn, "ibm,number-of-blocks", &blocks)) { + dev_err(&pdev->dev, "%pOF: missing number-of-blocks!\n", dn); return -ENODEV; } @@ -282,8 +288,8 @@ static int papr_scm_probe(struct platform_device *pdev) p->dn = dn; p->drc_index = drc_index; - p->block_size = unit_cap[0]; - p->blocks = unit_cap[1]; + p->block_size = block_size; + p->blocks = blocks; /* might be zero */ p->metadata_size = metadata_size; -- cgit v1.2.3 From 409dd7dc83eb54c4bc156aea890cc95bc21dc6f0 Mon Sep 17 00:00:00 2001 From: Oliver O'Halloran Date: Fri, 7 Dec 2018 02:17:11 +1100 Subject: powerpc/papr_scm: Remove endian conversions The return values of a h-call are returned in the CPU registers and written to the provided buffer by the plpar_hcall() wrapper. As a result the values written to memory are always in the native endian and should not be byte swapped. The inital implementation of the H-Call interface was done in qemu and the returned values were byte swapped unnecessarily in both the hypervisor and in the driver so this was only noticed when bringing up the PowerVM implementation. Fixes: b5beae5e224f ("powerpc/pseries: Add driver for PAPR SCM regions") Signed-off-by: Oliver O'Halloran Signed-off-by: Michael Ellerman --- arch/powerpc/platforms/pseries/papr_scm.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c index de47e3719c8d..8b5153c55da6 100644 --- a/arch/powerpc/platforms/pseries/papr_scm.c +++ b/arch/powerpc/platforms/pseries/papr_scm.c @@ -55,7 +55,7 @@ static int drc_pmem_bind(struct papr_scm_priv *p) do { rc = plpar_hcall(H_SCM_BIND_MEM, ret, p->drc_index, 0, p->blocks, BIND_ANY_ADDR, token); - token = be64_to_cpu(ret[0]); + token = ret[0]; cond_resched(); } while (rc == H_BUSY); @@ -64,7 +64,7 @@ static int drc_pmem_bind(struct papr_scm_priv *p) return -ENXIO; } - p->bound_addr = be64_to_cpu(ret[1]); + p->bound_addr = ret[1]; dev_dbg(&p->pdev->dev, "bound drc %x to %pR\n", p->drc_index, &p->res); @@ -82,7 +82,7 @@ static int drc_pmem_unbind(struct papr_scm_priv *p) do { rc = plpar_hcall(H_SCM_UNBIND_MEM, ret, p->drc_index, p->bound_addr, p->blocks, token); - token = be64_to_cpu(ret); + token = ret[0]; cond_resched(); } while (rc == H_BUSY); -- cgit v1.2.3 From b0d65a8cbcb097d2110885c3660add97b0125867 Mon Sep 17 00:00:00 2001 From: Oliver O'Halloran Date: Fri, 7 Dec 2018 02:17:12 +1100 Subject: powerpc/papr_scm: Fix DIMM device registration race When a new nvdimm device is registered with libnvdimm via nvdimm_create() it is added as a device on the nvdimm bus. The probe function for the DIMM driver is potentially quite slow so actually registering and probing the device is done in an async domain rather than immediately after device creation. This can result in a race where the region device (created 2nd) is probed first and fails to activate at boot. To fix this we use the same approach as the ACPI/NFIT driver which is to check that all the DIMM devices registered successfully. LibNVDIMM provides the nvdimm_bus_count_dimms() function which synchronises with the async domain and verifies that the dimm was successfully registered with the bus. If either of these does not occur then we bail. Fixes: b5beae5e224f ("powerpc/pseries: Add driver for PAPR SCM regions") Signed-off-by: Oliver O'Halloran Signed-off-by: Michael Ellerman --- arch/powerpc/platforms/pseries/papr_scm.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c index 8b5153c55da6..7dc6a751cb4c 100644 --- a/arch/powerpc/platforms/pseries/papr_scm.c +++ b/arch/powerpc/platforms/pseries/papr_scm.c @@ -223,6 +223,9 @@ static int papr_scm_nvdimm_init(struct papr_scm_priv *p) goto err; } + if (nvdimm_bus_check_dimm_count(p->bus, 1)) + goto err; + /* now add the region */ memset(&mapping, 0, sizeof(mapping)); -- cgit v1.2.3 From 43001c52b603cac041783cc392094ea560bd9444 Mon Sep 17 00:00:00 2001 From: Oliver O'Halloran Date: Fri, 7 Dec 2018 02:17:13 +1100 Subject: powerpc/papr_scm: Use ibm,unit-guid as the iset cookie The interleave set cookie is used to determine if a label stored in the metadata space should be applied to the current region. This is important in the case of NVDIMMs since the firmware may change the interleaving configuration of a DIMM which would invalidate the existing labels. In our case the hypervisor hides those details from us so we don't really care, but libnvdimm still requires the interleave set cookie to be non-zero. For our purposes we just need the set cookie to be unique and fixed for a given PAPR SCM region and using the unit-guid (really a UUID) is fine for this purpose. Fixes: b5beae5e224f ("powerpc/pseries: Add driver for PAPR SCM regions") Signed-off-by: Oliver O'Halloran [mpe: Use kernel types (u64)] Signed-off-by: Michael Ellerman --- arch/powerpc/platforms/pseries/papr_scm.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c index 7dc6a751cb4c..7d6457ab5d34 100644 --- a/arch/powerpc/platforms/pseries/papr_scm.c +++ b/arch/powerpc/platforms/pseries/papr_scm.c @@ -264,6 +264,8 @@ static int papr_scm_probe(struct platform_device *pdev) u32 drc_index, metadata_size; u64 blocks, block_size; struct papr_scm_priv *p; + const char *uuid_str; + u64 uuid[2]; int rc; /* check we have all the required DT properties */ @@ -282,6 +284,11 @@ static int papr_scm_probe(struct platform_device *pdev) return -ENODEV; } + if (of_property_read_string(dn, "ibm,unit-guid", &uuid_str)) { + dev_err(&pdev->dev, "%pOF: missing unit-guid!\n", dn); + return -ENODEV; + } + p = kzalloc(sizeof(*p), GFP_KERNEL); if (!p) return -ENOMEM; @@ -294,6 +301,11 @@ static int papr_scm_probe(struct platform_device *pdev) p->block_size = block_size; p->blocks = blocks; + /* We just need to ensure that set cookies are unique across */ + uuid_parse(uuid_str, (uuid_t *) uuid); + p->nd_set.cookie1 = uuid[0]; + p->nd_set.cookie2 = uuid[1]; + /* might be zero */ p->metadata_size = metadata_size; p->pdev = pdev; -- cgit v1.2.3 From 9ef34630a4614ee1cd478f9859ebea55d55f10ec Mon Sep 17 00:00:00 2001 From: Oliver O'Halloran Date: Fri, 7 Dec 2018 02:17:14 +1100 Subject: powerpc/mm: Fallback to RAM if the altmap is unusable The "altmap" is used to provide a pool of memory that is reserved for the vmemmap backing of hot-plugged memory. This is useful when adding large amount of ZONE_DEVICE memory to a system with a limited amount of normal memory. On ppc64 we use huge pages to map the vmemmap which requires the backing storage to be contigious and aligned to the hugepage size. The altmap implementation allows for the altmap provider to reserve a few PFNs at the start of the range for it's own uses and when this occurs the first chunk of the altmap is not usable for hugepage mappings. On hash there is no sane way to fall back to a normal sized page mapping so we fail the allocation. This results in memory hotplug failing with ENOMEM when the new range doesn't fall into an existing vmemmap block. This patch handles this case by falling back to using system memory rather than failing if we cannot allocate from the altmap. This fallback should only ever be used for the first vmemmap block so it should not cause excess memory consumption. Fixes: 7b73d978a5d0 ("mm: pass the vmem_altmap to vmemmap_populate") Signed-off-by: Oliver O'Halloran Signed-off-by: Michael Ellerman --- arch/powerpc/mm/init_64.c | 19 ++++++++++++++++--- 1 file changed, 16 insertions(+), 3 deletions(-) diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c index 7a9886f98b0c..a5091c034747 100644 --- a/arch/powerpc/mm/init_64.c +++ b/arch/powerpc/mm/init_64.c @@ -188,15 +188,20 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, pr_debug("vmemmap_populate %lx..%lx, node %d\n", start, end, node); for (; start < end; start += page_size) { - void *p; + void *p = NULL; int rc; if (vmemmap_populated(start, page_size)) continue; + /* + * Allocate from the altmap first if we have one. This may + * fail due to alignment issues when using 16MB hugepages, so + * fall back to system memory if the altmap allocation fail. + */ if (altmap) p = altmap_alloc_block_buf(page_size, altmap); - else + if (!p) p = vmemmap_alloc_block_buf(page_size, node); if (!p) return -ENOMEM; @@ -255,8 +260,15 @@ void __ref vmemmap_free(unsigned long start, unsigned long end, { unsigned long page_size = 1 << mmu_psize_defs[mmu_vmemmap_psize].shift; unsigned long page_order = get_order(page_size); + unsigned long alt_start = ~0, alt_end = ~0; + unsigned long base_pfn; start = _ALIGN_DOWN(start, page_size); + if (altmap) { + alt_start = altmap->base_pfn; + alt_end = altmap->base_pfn + altmap->reserve + + altmap->free + altmap->alloc + altmap->align; + } pr_debug("vmemmap_free %lx...%lx\n", start, end); @@ -280,8 +292,9 @@ void __ref vmemmap_free(unsigned long start, unsigned long end, page = pfn_to_page(addr >> PAGE_SHIFT); section_base = pfn_to_page(vmemmap_section_start(start)); nr_pages = 1 << page_order; + base_pfn = PHYS_PFN(addr); - if (altmap) { + if (base_pfn >= alt_start && base_pfn < alt_end) { vmem_altmap_free(altmap, nr_pages); } else if (PageReserved(page)) { /* allocated from bootmem */ -- cgit v1.2.3 From 51a11b14c29c6c7cc985c6ce7dd9e20f61cf7f0a Mon Sep 17 00:00:00 2001 From: Sandipan Das Date: Thu, 6 Dec 2018 14:57:01 +0530 Subject: bpf: powerpc: fix broken uapi for BPF_PROG_TYPE_PERF_EVENT Now that there are different variants of pt_regs for userspace and kernel, the uapi for the BPF_PROG_TYPE_PERF_EVENT program type must be changed by exporting the user_pt_regs structure instead of the pt_regs structure that is in-kernel only. Fixes: 002af9391bfb ("powerpc: Split user/kernel definitions of struct pt_regs") Signed-off-by: Sandipan Das Signed-off-by: Alexei Starovoitov --- arch/powerpc/include/asm/perf_event.h | 2 ++ arch/powerpc/include/uapi/asm/Kbuild | 1 - arch/powerpc/include/uapi/asm/bpf_perf_event.h | 9 +++++++++ 3 files changed, 11 insertions(+), 1 deletion(-) create mode 100644 arch/powerpc/include/uapi/asm/bpf_perf_event.h diff --git a/arch/powerpc/include/asm/perf_event.h b/arch/powerpc/include/asm/perf_event.h index 8bf1b6351716..16a49819da9a 100644 --- a/arch/powerpc/include/asm/perf_event.h +++ b/arch/powerpc/include/asm/perf_event.h @@ -26,6 +26,8 @@ #include #include +#define perf_arch_bpf_user_pt_regs(regs) ®s->user_regs + /* * Overload regs->result to specify whether we should use the MSR (result * is zero) or the SIAR (result is non zero). diff --git a/arch/powerpc/include/uapi/asm/Kbuild b/arch/powerpc/include/uapi/asm/Kbuild index a658091a19f9..3712152206f3 100644 --- a/arch/powerpc/include/uapi/asm/Kbuild +++ b/arch/powerpc/include/uapi/asm/Kbuild @@ -1,7 +1,6 @@ # UAPI Header export list include include/uapi/asm-generic/Kbuild.asm -generic-y += bpf_perf_event.h generic-y += param.h generic-y += poll.h generic-y += resource.h diff --git a/arch/powerpc/include/uapi/asm/bpf_perf_event.h b/arch/powerpc/include/uapi/asm/bpf_perf_event.h new file mode 100644 index 000000000000..b551b741653d --- /dev/null +++ b/arch/powerpc/include/uapi/asm/bpf_perf_event.h @@ -0,0 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _UAPI__ASM_BPF_PERF_EVENT_H__ +#define _UAPI__ASM_BPF_PERF_EVENT_H__ + +#include + +typedef struct user_pt_regs bpf_user_pt_regs_t; + +#endif /* _UAPI__ASM_BPF_PERF_EVENT_H__ */ -- cgit v1.2.3 From a225f1567405558fb5410e9b2b90805819df1c67 Mon Sep 17 00:00:00 2001 From: Elvira Khabirova Date: Fri, 7 Dec 2018 18:56:05 +0300 Subject: powerpc/ptrace: replace ptrace_report_syscall() with a tracehook call Arch code should use tracehook_*() helpers, as documented in include/linux/tracehook.h, ptrace_report_syscall() is not expected to be used outside that file. The patch does not look very nice, but at least it is correct and opens the way for PTRACE_GET_SYSCALL_INFO API. Co-authored-by: Dmitry V. Levin Fixes: 5521eb4bca2d ("powerpc/ptrace: Add support for PTRACE_SYSEMU") Signed-off-by: Elvira Khabirova Signed-off-by: Dmitry V. Levin [mpe: Take this as a minimal fix for 4.20, we'll rework it later] Signed-off-by: Michael Ellerman --- arch/powerpc/kernel/ptrace.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c index afb819f4ca68..714c3480c52d 100644 --- a/arch/powerpc/kernel/ptrace.c +++ b/arch/powerpc/kernel/ptrace.c @@ -3266,12 +3266,17 @@ long do_syscall_trace_enter(struct pt_regs *regs) user_exit(); if (test_thread_flag(TIF_SYSCALL_EMU)) { - ptrace_report_syscall(regs); /* + * A nonzero return code from tracehook_report_syscall_entry() + * tells us to prevent the syscall execution, but we are not + * going to execute it anyway. + * * Returning -1 will skip the syscall execution. We want to * avoid clobbering any register also, thus, not 'gotoing' * skip label. */ + if (tracehook_report_syscall_entry(regs)) + ; return -1; } -- cgit v1.2.3 From d72f70da60de1af4bfd0f0a3d0ecbc28eea07679 Mon Sep 17 00:00:00 2001 From: Takeshi Misawa Date: Sun, 9 Dec 2018 14:30:15 +0900 Subject: fuse: Fix memory leak in fuse_dev_free() When ntfs is unmounted, the following leak is reported by kmemleak. kmemleak report: unreferenced object 0xffff880052bf4400 (size 4096): comm "mount.ntfs", pid 16530, jiffies 4294861127 (age 3215.836s) hex dump (first 32 bytes): 00 44 bf 52 00 88 ff ff 00 44 bf 52 00 88 ff ff .D.R.....D.R.... 10 44 bf 52 00 88 ff ff 10 44 bf 52 00 88 ff ff .D.R.....D.R.... backtrace: [<00000000bf4a2f8d>] fuse_fill_super+0xb22/0x1da0 [fuse] [<000000004dde0f0c>] mount_bdev+0x263/0x320 [<0000000025aebc66>] mount_fs+0x82/0x2bf [<0000000042c5a6be>] vfs_kern_mount.part.33+0xbf/0x480 [<00000000ed10cd5b>] do_mount+0x3de/0x2ad0 [<00000000d59ff068>] ksys_mount+0xba/0xd0 [<000000001bda1bcc>] __x64_sys_mount+0xba/0x150 [<00000000ebe26304>] do_syscall_64+0x151/0x490 [<00000000d25f2b42>] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [<000000002e0abd2c>] 0xffffffffffffffff fuse_dev_alloc() allocate fud->pq.processing. But this hash table is not freed. Fix this by freeing fud->pq.processing. Signed-off-by: Takeshi Misawa Signed-off-by: Miklos Szeredi Fixes: be2ff42c5d6e ("fuse: Use hash table to link processing request") --- fs/fuse/inode.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 073865371f9b..568abed20eb2 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -1068,6 +1068,7 @@ void fuse_dev_free(struct fuse_dev *fud) fuse_conn_put(fc); } + kfree(fud->pq.processing); kfree(fud); } EXPORT_SYMBOL_GPL(fuse_dev_free); -- cgit v1.2.3 From d57ec3c83b5153217a70b561d4fb6ed96f2f7a25 Mon Sep 17 00:00:00 2001 From: Tore Anderson Date: Sat, 8 Dec 2018 19:05:12 +0100 Subject: USB: serial: option: add HP lt4132 The HP lt4132 is a rebranded Huawei ME906s-158 LTE modem. The interface with protocol 0x16 is "CDC ECM & NCM" according to the *.inf files included with the Windows driver. Attaching the option driver to it doesn't result in a /dev/ttyUSB* device being created, so I've excluded it. Note that it is also excluded for corresponding Huawei-branded devices, cf. commit d544db293a44 ("USB: support new huawei devices in option.c"). T: Bus=01 Lev=01 Prnt=01 Port=02 Cnt=02 Dev#= 3 Spd=480 MxCh= 0 D: Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=ff MxPS=64 #Cfgs= 3 P: Vendor=03f0 ProdID=a31d Rev=01.02 S: Manufacturer=HP Inc. S: Product=HP lt4132 LTE/HSPA+ 4G Module S: SerialNumber=0123456789ABCDEF C: #Ifs= 6 Cfg#= 1 Atr=a0 MxPwr=2mA I: If#=0x0 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=06 Prot=10 Driver=option I: If#=0x1 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=06 Prot=13 Driver=option I: If#=0x2 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=06 Prot=12 Driver=option I: If#=0x3 Alt= 0 #EPs= 1 Cls=ff(vend.) Sub=06 Prot=16 Driver=(none) I: If#=0x4 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=06 Prot=14 Driver=option I: If#=0x5 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=06 Prot=1b Driver=option T: Bus=01 Lev=01 Prnt=01 Port=02 Cnt=02 Dev#= 3 Spd=480 MxCh= 0 D: Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=ff MxPS=64 #Cfgs= 3 P: Vendor=03f0 ProdID=a31d Rev=01.02 S: Manufacturer=HP Inc. S: Product=HP lt4132 LTE/HSPA+ 4G Module S: SerialNumber=0123456789ABCDEF C: #Ifs= 7 Cfg#= 2 Atr=a0 MxPwr=2mA I: If#=0x0 Alt= 0 #EPs= 1 Cls=02(commc) Sub=06 Prot=00 Driver=cdc_ether I: If#=0x1 Alt= 0 #EPs= 2 Cls=0a(data ) Sub=06 Prot=00 Driver=cdc_ether I: If#=0x2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=06 Prot=10 Driver=option I: If#=0x3 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=06 Prot=13 Driver=option I: If#=0x4 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=06 Prot=12 Driver=option I: If#=0x5 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=06 Prot=14 Driver=option I: If#=0x6 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=06 Prot=1b Driver=option T: Bus=01 Lev=01 Prnt=01 Port=02 Cnt=02 Dev#= 3 Spd=480 MxCh= 0 D: Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=ff MxPS=64 #Cfgs= 3 P: Vendor=03f0 ProdID=a31d Rev=01.02 S: Manufacturer=HP Inc. S: Product=HP lt4132 LTE/HSPA+ 4G Module S: SerialNumber=0123456789ABCDEF C: #Ifs= 3 Cfg#= 3 Atr=a0 MxPwr=2mA I: If#=0x0 Alt= 0 #EPs= 1 Cls=02(commc) Sub=0e Prot=00 Driver=cdc_mbim I: If#=0x1 Alt= 1 #EPs= 2 Cls=0a(data ) Sub=00 Prot=02 Driver=cdc_mbim I: If#=0x2 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=06 Prot=14 Driver=option Signed-off-by: Tore Anderson Cc: stable@vger.kernel.org [ johan: drop id defines ] Signed-off-by: Johan Hovold --- drivers/usb/serial/option.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index e24ff16d4147..642624fc75ad 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -1940,7 +1940,12 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(WETELECOM_VENDOR_ID, WETELECOM_PRODUCT_WMD200, 0xff, 0xff, 0xff) }, { USB_DEVICE_AND_INTERFACE_INFO(WETELECOM_VENDOR_ID, WETELECOM_PRODUCT_6802, 0xff, 0xff, 0xff) }, { USB_DEVICE_AND_INTERFACE_INFO(WETELECOM_VENDOR_ID, WETELECOM_PRODUCT_WMD300, 0xff, 0xff, 0xff) }, - { USB_DEVICE_AND_INTERFACE_INFO(0x03f0, 0x421d, 0xff, 0xff, 0xff) }, /* HP lt2523 (Novatel E371) */ + { USB_DEVICE_AND_INTERFACE_INFO(0x03f0, 0x421d, 0xff, 0xff, 0xff) }, /* HP lt2523 (Novatel E371) */ + { USB_DEVICE_AND_INTERFACE_INFO(0x03f0, 0xa31d, 0xff, 0x06, 0x10) }, /* HP lt4132 (Huawei ME906s-158) */ + { USB_DEVICE_AND_INTERFACE_INFO(0x03f0, 0xa31d, 0xff, 0x06, 0x12) }, + { USB_DEVICE_AND_INTERFACE_INFO(0x03f0, 0xa31d, 0xff, 0x06, 0x13) }, + { USB_DEVICE_AND_INTERFACE_INFO(0x03f0, 0xa31d, 0xff, 0x06, 0x14) }, + { USB_DEVICE_AND_INTERFACE_INFO(0x03f0, 0xa31d, 0xff, 0x06, 0x1b) }, { } /* Terminating entry */ }; MODULE_DEVICE_TABLE(usb, option_ids); -- cgit v1.2.3 From d8ae458eeca9ed686e09a1b894867cb91fc4c1cb Mon Sep 17 00:00:00 2001 From: Chris Chiu Date: Fri, 7 Dec 2018 17:17:11 +0800 Subject: ALSA: hda/realtek: ALC294 mic and headset-mode fixups for ASUS X542UN The known ALC256_FIXUP_ASUS_MIC fixup can fix the headphone jack sensing and enable use of the internal microphone on this laptop X542UN. However, it's ALC294 so create a new fixup named ALC294_FIXUP_ASUS_MIC to avoid confusion. Signed-off-by: Jian-Hong Pan Signed-off-by: Daniel Drake Signed-off-by: Chris Chiu Cc: Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_realtek.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index cbd78aa5fad3..2ee830397dfe 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -5520,6 +5520,7 @@ enum { ALC285_FIXUP_LENOVO_HEADPHONE_NOISE, ALC295_FIXUP_HP_AUTO_MUTE, ALC286_FIXUP_ACER_AIO_MIC_NO_PRESENCE, + ALC294_FIXUP_ASUS_MIC, }; static const struct hda_fixup alc269_fixups[] = { @@ -6408,6 +6409,16 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC269_FIXUP_HEADSET_MIC }, + [ALC294_FIXUP_ASUS_MIC] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x13, 0x90a60160 }, /* use as internal mic */ + { 0x19, 0x04a11120 }, /* use as headset mic, without its own jack detect */ + { } + }, + .chained = true, + .chain_id = ALC269_FIXUP_HEADSET_MODE_NO_HP_MIC + }, }; static const struct snd_pci_quirk alc269_fixup_tbl[] = { @@ -7157,6 +7168,10 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = { SND_HDA_PIN_QUIRK(0x10ec0293, 0x1028, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE, ALC292_STANDARD_PINS, {0x13, 0x90a60140}), + SND_HDA_PIN_QUIRK(0x10ec0294, 0x1043, "ASUS", ALC294_FIXUP_ASUS_MIC, + {0x14, 0x90170110}, + {0x1b, 0x90a70130}, + {0x21, 0x04211020}), SND_HDA_PIN_QUIRK(0x10ec0295, 0x1028, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE, ALC295_STANDARD_PINS, {0x17, 0x21014020}, -- cgit v1.2.3 From 4e051106730dfc640a8b49db88440af304726f4d Mon Sep 17 00:00:00 2001 From: Jian-Hong Pan Date: Fri, 7 Dec 2018 17:17:12 +0800 Subject: ALSA: hda/realtek: Enable audio jacks of ASUS UX533FD with ALC294 The ASUS UX533FD with ALC294 cannot detect the headset MIC and outputs through the internal speaker and the headphone until ALC294_FIXUP_ASUS_SPK and ALC294_FIXUP_ASUS_HEADSET_MIC quirk applied. Signed-off-by: Daniel Drake Signed-off-by: Jian-Hong Pan Cc: Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_realtek.c | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 2ee830397dfe..408f3162f2f6 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -5521,6 +5521,8 @@ enum { ALC295_FIXUP_HP_AUTO_MUTE, ALC286_FIXUP_ACER_AIO_MIC_NO_PRESENCE, ALC294_FIXUP_ASUS_MIC, + ALC294_FIXUP_ASUS_HEADSET_MIC, + ALC294_FIXUP_ASUS_SPK, }; static const struct hda_fixup alc269_fixups[] = { @@ -6419,6 +6421,26 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC269_FIXUP_HEADSET_MODE_NO_HP_MIC }, + [ALC294_FIXUP_ASUS_HEADSET_MIC] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x19, 0x01a1113c }, /* use as headset mic, without its own jack detect */ + { } + }, + .chained = true, + .chain_id = ALC269_FIXUP_HEADSET_MODE_NO_HP_MIC + }, + [ALC294_FIXUP_ASUS_SPK] = { + .type = HDA_FIXUP_VERBS, + .v.verbs = (const struct hda_verb[]) { + /* Set EAPD high */ + { 0x20, AC_VERB_SET_COEF_INDEX, 0x40 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x8800 }, + { } + }, + .chained = true, + .chain_id = ALC294_FIXUP_ASUS_HEADSET_MIC + }, }; static const struct snd_pci_quirk alc269_fixup_tbl[] = { @@ -6561,6 +6583,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x12e0, "ASUS X541SA", ALC256_FIXUP_ASUS_MIC), SND_PCI_QUIRK(0x1043, 0x13b0, "ASUS Z550SA", ALC256_FIXUP_ASUS_MIC), SND_PCI_QUIRK(0x1043, 0x1427, "Asus Zenbook UX31E", ALC269VB_FIXUP_ASUS_ZENBOOK), + SND_PCI_QUIRK(0x1043, 0x14a1, "ASUS UX533FD", ALC294_FIXUP_ASUS_SPK), SND_PCI_QUIRK(0x1043, 0x1517, "Asus Zenbook UX31A", ALC269VB_FIXUP_ASUS_ZENBOOK_UX31A), SND_PCI_QUIRK(0x1043, 0x16e3, "ASUS UX50", ALC269_FIXUP_STEREO_DMIC), SND_PCI_QUIRK(0x1043, 0x1a13, "Asus G73Jw", ALC269_FIXUP_ASUS_G73JW), -- cgit v1.2.3 From 0bea4cc8383519f78f3f74caca7bdebdfb346d3b Mon Sep 17 00:00:00 2001 From: Jian-Hong Pan Date: Fri, 7 Dec 2018 17:17:13 +0800 Subject: ALSA: hda/realtek: Enable audio jacks of ASUS UX433FN/UX333FA with ALC294 The ASUS UX433FN and UX333FA with ALC294 cannot detect the headset MIC and output through the internal speaker and the headphone until ALC294_FIXUP_ASUS_SPK and ALC294_FIXUP_ASUS_HEADSET_MIC quirk applied. Signed-off-by: Daniel Drake Signed-off-by: Jian-Hong Pan Cc: Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_realtek.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 408f3162f2f6..15021c839372 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -7195,6 +7195,10 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = { {0x14, 0x90170110}, {0x1b, 0x90a70130}, {0x21, 0x04211020}), + SND_HDA_PIN_QUIRK(0x10ec0294, 0x1043, "ASUS", ALC294_FIXUP_ASUS_SPK, + {0x12, 0x90a60130}, + {0x17, 0x90170110}, + {0x21, 0x04211020}), SND_HDA_PIN_QUIRK(0x10ec0295, 0x1028, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE, ALC295_STANDARD_PINS, {0x17, 0x21014020}, -- cgit v1.2.3 From d347d0c82a99b41efc2770fc01a04066903300df Mon Sep 17 00:00:00 2001 From: Enric Balletbo i Serra Date: Mon, 10 Dec 2018 13:14:37 +0100 Subject: backlight: pwm_bl: Fix brightness levels for non-DT case. Commit '88ba95bedb79 ("backlight: pwm_bl: Compute brightness of LED linearly to human eye")' allows the possibility to compute a default brightness table when there isn't the brightness-levels property in the DT. Unfortunately the changes made broke the pwm backlight for the non-DT boards. Usually, the non-DT boards don't pass the brightness levels via platform data, instead, it sets the max_brightness in their platform data and the driver calculates the level without a table. The offending patch assumed that when there is no brightness levels table we should create one, but this is clearly wrong for the non-DT case. After this patch the code handles the DT and the non-DT case taking in consideration also if max_brightness is set or not. Fixes: 88ba95bedb79 ("backlight: pwm_bl: Compute brightness of LED linearly to human eye") Reported-by: Robert Jarzmik Signed-off-by: Enric Balletbo i Serra Tested-by: Robert Jarzmik Acked-by: Daniel Thompson Signed-off-by: Lee Jones --- drivers/video/backlight/pwm_bl.c | 41 ++++++++++++++++++++++++++++++++++------ 1 file changed, 35 insertions(+), 6 deletions(-) diff --git a/drivers/video/backlight/pwm_bl.c b/drivers/video/backlight/pwm_bl.c index 678b27063198..f9ef0673a083 100644 --- a/drivers/video/backlight/pwm_bl.c +++ b/drivers/video/backlight/pwm_bl.c @@ -562,7 +562,30 @@ static int pwm_backlight_probe(struct platform_device *pdev) goto err_alloc; } - if (!data->levels) { + if (data->levels) { + /* + * For the DT case, only when brightness levels is defined + * data->levels is filled. For the non-DT case, data->levels + * can come from platform data, however is not usual. + */ + for (i = 0; i <= data->max_brightness; i++) { + if (data->levels[i] > pb->scale) + pb->scale = data->levels[i]; + + pb->levels = data->levels; + } + } else if (!data->max_brightness) { + /* + * If no brightness levels are provided and max_brightness is + * not set, use the default brightness table. For the DT case, + * max_brightness is set to 0 when brightness levels is not + * specified. For the non-DT case, max_brightness is usually + * set to some value. + */ + + /* Get the PWM period (in nanoseconds) */ + pwm_get_state(pb->pwm, &state); + ret = pwm_backlight_brightness_default(&pdev->dev, data, state.period); if (ret < 0) { @@ -570,13 +593,19 @@ static int pwm_backlight_probe(struct platform_device *pdev) "failed to setup default brightness table\n"); goto err_alloc; } - } - for (i = 0; i <= data->max_brightness; i++) { - if (data->levels[i] > pb->scale) - pb->scale = data->levels[i]; + for (i = 0; i <= data->max_brightness; i++) { + if (data->levels[i] > pb->scale) + pb->scale = data->levels[i]; - pb->levels = data->levels; + pb->levels = data->levels; + } + } else { + /* + * That only happens for the non-DT case, where platform data + * sets the max_brightness value. + */ + pb->scale = data->max_brightness; } pb->lth_brightness = data->lth_brightness * (state.period / pb->scale); -- cgit v1.2.3 From c2a20a2731df11f9b7b7030f7ac3fc222c9ce39d Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Thu, 6 Dec 2018 20:14:11 -0800 Subject: selftests/bpf: add missing pointer dereference for map stacktrace fixup I get a segfault without it, other fixups always do dereference, and without dereference I don't understand how it can ever work. Fixes: 7c85c448e7d74 ("selftests/bpf: test_verifier, check bpf_map_lookup_elem access in bpf prog") Signed-off-by: Stanislav Fomichev Signed-off-by: Daniel Borkmann --- tools/testing/selftests/bpf/test_verifier.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index df6f751cc1e8..d23929a1985d 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -14166,7 +14166,7 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_map_type prog_type, do { prog[*fixup_map_stacktrace].imm = map_fds[12]; fixup_map_stacktrace++; - } while (fixup_map_stacktrace); + } while (*fixup_map_stacktrace); } } -- cgit v1.2.3 From 8a034aad4892baf82f8c9082f969c5ebc1143a05 Mon Sep 17 00:00:00 2001 From: Srinivas Kandagatla Date: Fri, 7 Dec 2018 14:11:49 +0530 Subject: clk: qcom: qcs404: Fix gpll0_out_main parent gpll0_out_main parent is cxo so fix it. Fixes: 652f1813c113 ("clk: qcom: gcc: Add global clock controller driver for QCS404") Signed-off-by: Srinivas Kandagatla Reviewed-by: Bjorn Andersson Signed-off-by: Vinod Koul Signed-off-by: Stephen Boyd --- drivers/clk/qcom/gcc-qcs404.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/clk/qcom/gcc-qcs404.c b/drivers/clk/qcom/gcc-qcs404.c index ef1b267cb058..64da032bb9ed 100644 --- a/drivers/clk/qcom/gcc-qcs404.c +++ b/drivers/clk/qcom/gcc-qcs404.c @@ -297,7 +297,7 @@ static struct clk_alpha_pll gpll0_out_main = { .hw.init = &(struct clk_init_data){ .name = "gpll0_out_main", .parent_names = (const char *[]) - { "gpll0_sleep_clk_src" }, + { "cxo" }, .num_parents = 1, .ops = &clk_alpha_pll_ops, }, -- cgit v1.2.3 From 4a2eb0c37b4759416996fbb4c45b932500cf06d3 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Mon, 10 Dec 2018 18:00:52 +0800 Subject: sctp: initialize sin6_flowinfo for ipv6 addrs in sctp_inet6addr_event syzbot reported a kernel-infoleak, which is caused by an uninitialized field(sin6_flowinfo) of addr->a.v6 in sctp_inet6addr_event(). The call trace is as below: BUG: KMSAN: kernel-infoleak in _copy_to_user+0x19a/0x230 lib/usercopy.c:33 CPU: 1 PID: 8164 Comm: syz-executor2 Not tainted 4.20.0-rc3+ #95 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+0x32d/0x480 lib/dump_stack.c:113 kmsan_report+0x12c/0x290 mm/kmsan/kmsan.c:683 kmsan_internal_check_memory+0x32a/0xa50 mm/kmsan/kmsan.c:743 kmsan_copy_to_user+0x78/0xd0 mm/kmsan/kmsan_hooks.c:634 _copy_to_user+0x19a/0x230 lib/usercopy.c:33 copy_to_user include/linux/uaccess.h:183 [inline] sctp_getsockopt_local_addrs net/sctp/socket.c:5998 [inline] sctp_getsockopt+0x15248/0x186f0 net/sctp/socket.c:7477 sock_common_getsockopt+0x13f/0x180 net/core/sock.c:2937 __sys_getsockopt+0x489/0x550 net/socket.c:1939 __do_sys_getsockopt net/socket.c:1950 [inline] __se_sys_getsockopt+0xe1/0x100 net/socket.c:1947 __x64_sys_getsockopt+0x62/0x80 net/socket.c:1947 do_syscall_64+0xcf/0x110 arch/x86/entry/common.c:291 entry_SYSCALL_64_after_hwframe+0x63/0xe7 sin6_flowinfo is not really used by SCTP, so it will be fixed by simply setting it to 0. The issue exists since very beginning. Thanks Alexander for the reproducer provided. Reported-by: syzbot+ad5d327e6936a2e284be@syzkaller.appspotmail.com Signed-off-by: Xin Long Acked-by: Marcelo Ricardo Leitner Acked-by: Neil Horman Signed-off-by: David S. Miller --- net/sctp/ipv6.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index fc6c5e4bffa5..7f0539db5604 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -101,6 +101,7 @@ static int sctp_inet6addr_event(struct notifier_block *this, unsigned long ev, if (addr) { addr->a.v6.sin6_family = AF_INET6; addr->a.v6.sin6_port = 0; + addr->a.v6.sin6_flowinfo = 0; addr->a.v6.sin6_addr = ifa->addr; addr->a.v6.sin6_scope_id = ifa->idev->dev->ifindex; addr->valid = 1; -- cgit v1.2.3 From 5648451e30a0d13d11796574919a359025d52cce Mon Sep 17 00:00:00 2001 From: Gustavo A. R. Silva Date: Mon, 10 Dec 2018 12:41:24 -0600 Subject: ipv4: Fix potential Spectre v1 vulnerability vr.vifi is indirectly controlled by user-space, hence leading to a potential exploitation of the Spectre variant 1 vulnerability. This issue was detected with the help of Smatch: net/ipv4/ipmr.c:1616 ipmr_ioctl() warn: potential spectre issue 'mrt->vif_table' [r] (local cap) net/ipv4/ipmr.c:1690 ipmr_compat_ioctl() warn: potential spectre issue 'mrt->vif_table' [r] (local cap) Fix this by sanitizing vr.vifi before using it to index mrt->vif_table' Notice that given that speculation windows are large, the policy is to kill the speculation on the first load and not worry if it can be completed with a dependent load/store [1]. [1] https://marc.info/?l=linux-kernel&m=152449131114778&w=2 Signed-off-by: Gustavo A. R. Silva Signed-off-by: David S. Miller --- net/ipv4/ipmr.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index a6defbec4f1b..e7a3879cedd0 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -69,6 +69,8 @@ #include #include +#include + struct ipmr_rule { struct fib_rule common; }; @@ -1612,6 +1614,7 @@ int ipmr_ioctl(struct sock *sk, int cmd, void __user *arg) return -EFAULT; if (vr.vifi >= mrt->maxvif) return -EINVAL; + vr.vifi = array_index_nospec(vr.vifi, mrt->maxvif); read_lock(&mrt_lock); vif = &mrt->vif_table[vr.vifi]; if (VIF_EXISTS(mrt, vr.vifi)) { @@ -1686,6 +1689,7 @@ int ipmr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg) return -EFAULT; if (vr.vifi >= mrt->maxvif) return -EINVAL; + vr.vifi = array_index_nospec(vr.vifi, mrt->maxvif); read_lock(&mrt_lock); vif = &mrt->vif_table[vr.vifi]; if (VIF_EXISTS(mrt, vr.vifi)) { -- cgit v1.2.3 From 2244b5887c6865b9e9cf14ee12a312b776aeeb58 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Fri, 7 Dec 2018 15:58:23 -0500 Subject: drm/amdgpu: add some additional vega10 pci ids New vega ids. Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 8de55f7f1a3a..9b28f0d38a5d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -872,7 +872,13 @@ static const struct pci_device_id pciidlist[] = { {0x1002, 0x6864, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VEGA10}, {0x1002, 0x6867, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VEGA10}, {0x1002, 0x6868, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VEGA10}, + {0x1002, 0x6869, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VEGA10}, + {0x1002, 0x686a, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VEGA10}, + {0x1002, 0x686b, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VEGA10}, {0x1002, 0x686c, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VEGA10}, + {0x1002, 0x686d, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VEGA10}, + {0x1002, 0x686e, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VEGA10}, + {0x1002, 0x686f, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VEGA10}, {0x1002, 0x687f, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VEGA10}, /* Vega 12 */ {0x1002, 0x69A0, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VEGA12}, -- cgit v1.2.3 From ec5b2020726bffc893d5bddca39502e116da1fbc Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Fri, 7 Dec 2018 16:00:27 -0500 Subject: drm/amdgpu: add some additional vega20 pci ids New vega ids. Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 9b28f0d38a5d..74b611e8a1b1 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -891,6 +891,7 @@ static const struct pci_device_id pciidlist[] = { {0x1002, 0x66A1, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VEGA20}, {0x1002, 0x66A2, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VEGA20}, {0x1002, 0x66A3, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VEGA20}, + {0x1002, 0x66A4, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VEGA20}, {0x1002, 0x66A7, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VEGA20}, {0x1002, 0x66AF, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VEGA20}, /* Raven */ -- cgit v1.2.3 From 756e16bf79f2815e7c83a04881b5545b55a99fd3 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Fri, 7 Dec 2018 16:23:19 -0500 Subject: drm/amdkfd: add new vega10 pci ids New vega10 ids. Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdkfd/kfd_device.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c index a9f18ea7e354..5edefc742863 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c @@ -337,7 +337,13 @@ static const struct kfd_deviceid supported_devices[] = { { 0x6864, &vega10_device_info }, /* Vega10 */ { 0x6867, &vega10_device_info }, /* Vega10 */ { 0x6868, &vega10_device_info }, /* Vega10 */ + { 0x6869, &vega10_device_info }, /* Vega10 */ + { 0x686A, &vega10_device_info }, /* Vega10 */ + { 0x686B, &vega10_device_info }, /* Vega10 */ { 0x686C, &vega10_vf_device_info }, /* Vega10 vf*/ + { 0x686D, &vega10_device_info }, /* Vega10 */ + { 0x686E, &vega10_device_info }, /* Vega10 */ + { 0x686F, &vega10_device_info }, /* Vega10 */ { 0x687F, &vega10_device_info }, /* Vega10 */ { 0x66a0, &vega20_device_info }, /* Vega20 */ { 0x66a1, &vega20_device_info }, /* Vega20 */ -- cgit v1.2.3 From 9bd206f89fa758f130fde09bf6f876f955ed989a Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Fri, 7 Dec 2018 16:24:33 -0500 Subject: drm/amdkfd: add new vega20 pci id New vega20 id. Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdkfd/kfd_device.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c index 5edefc742863..e4ded890b1cb 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c @@ -349,6 +349,7 @@ static const struct kfd_deviceid supported_devices[] = { { 0x66a1, &vega20_device_info }, /* Vega20 */ { 0x66a2, &vega20_device_info }, /* Vega20 */ { 0x66a3, &vega20_device_info }, /* Vega20 */ + { 0x66a4, &vega20_device_info }, /* Vega20 */ { 0x66a7, &vega20_device_info }, /* Vega20 */ { 0x66af, &vega20_device_info } /* Vega20 */ }; -- cgit v1.2.3 From d55d8be0747c96db28a1d08fc24d22ccd9b448ac Mon Sep 17 00:00:00 2001 From: Junwei Zhang Date: Fri, 7 Dec 2018 15:15:03 +0800 Subject: drm/amdgpu: update SMC firmware image for polaris10 variants Some new variants require different firmwares. Signed-off-by: Junwei Zhang Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c index ceadeeadfa56..387f1cf1dc20 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c @@ -381,7 +381,8 @@ static int amdgpu_cgs_get_firmware_info(struct cgs_device *cgs_device, (adev->pdev->revision == 0xe7) || (adev->pdev->revision == 0xef))) || ((adev->pdev->device == 0x6fdf) && - (adev->pdev->revision == 0xef))) { + ((adev->pdev->revision == 0xef) || + (adev->pdev->revision == 0xff)))) { info->is_kicker = true; strcpy(fw_name, "amdgpu/polaris10_k_smc.bin"); } else if ((adev->pdev->device == 0x67df) && -- cgit v1.2.3 From cf4197ed5796234a53beb71228198c7d1e678947 Mon Sep 17 00:00:00 2001 From: Kenneth Feng Date: Thu, 6 Dec 2018 11:56:14 +0800 Subject: drm/amdgpu/powerplay: Apply avfs cks-off voltages on VI Instead of EVV cks-off voltages, avfs cks-off voltages can avoid the overshoot voltages when switching sclk. Signed-off-by: Kenneth Feng Acked-by: Alex Deucher Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/powerplay/inc/smu7_ppsmc.h | 2 ++ drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c | 6 ++++++ 2 files changed, 8 insertions(+) diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu7_ppsmc.h b/drivers/gpu/drm/amd/powerplay/inc/smu7_ppsmc.h index 62f36ba2435b..c1a99dfe4913 100644 --- a/drivers/gpu/drm/amd/powerplay/inc/smu7_ppsmc.h +++ b/drivers/gpu/drm/amd/powerplay/inc/smu7_ppsmc.h @@ -386,6 +386,8 @@ typedef uint16_t PPSMC_Result; #define PPSMC_MSG_AgmResetPsm ((uint16_t) 0x403) #define PPSMC_MSG_ReadVftCell ((uint16_t) 0x404) +#define PPSMC_MSG_ApplyAvfsCksOffVoltage ((uint16_t) 0x415) + #define PPSMC_MSG_GFX_CU_PG_ENABLE ((uint16_t) 0x280) #define PPSMC_MSG_GFX_CU_PG_DISABLE ((uint16_t) 0x281) #define PPSMC_MSG_GetCurrPkgPwr ((uint16_t) 0x282) diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c index 872d3824337b..a1e0ac9ae248 100644 --- a/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c +++ b/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c @@ -1985,6 +1985,12 @@ int polaris10_thermal_avfs_enable(struct pp_hwmgr *hwmgr) smum_send_msg_to_smc(hwmgr, PPSMC_MSG_EnableAvfs); + /* Apply avfs cks-off voltages to avoid the overshoot + * when switching to the highest sclk frequency + */ + if (data->apply_avfs_cks_off_voltage) + smum_send_msg_to_smc(hwmgr, PPSMC_MSG_ApplyAvfsCksOffVoltage); + return 0; } -- cgit v1.2.3 From f55adad601c6a97c8c9628195453e0fb23b4a0ae Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Mon, 10 Dec 2018 08:44:42 -0700 Subject: block/bio: Do not zero user pages We don't need to zero fill the bio if not using kernel allocated pages. Fixes: f3587d76da05 ("block: Clear kernel memory before copying to user") # v4.20-rc2 Reported-by: Todd Aiken Cc: Laurence Oberman Cc: stable@vger.kernel.org Cc: Bart Van Assche Tested-by: Laurence Oberman Signed-off-by: Keith Busch Signed-off-by: Jens Axboe --- block/bio.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/block/bio.c b/block/bio.c index 4f4d9884443b..4d86e90654b2 100644 --- a/block/bio.c +++ b/block/bio.c @@ -1261,7 +1261,8 @@ struct bio *bio_copy_user_iov(struct request_queue *q, if (ret) goto cleanup; } else { - zero_fill_bio(bio); + if (bmd->is_our_pages) + zero_fill_bio(bio); iov_iter_advance(iter, bio->bi_iter.bi_size); } -- cgit v1.2.3 From aca1a80ebe3e4d49adaf6516c61a6786b1ee7dad Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Mon, 10 Dec 2018 15:25:04 -0800 Subject: selftests/bpf: use proper type when passing prog_type Use bpf_prog_type instead of bpf_map_type when passing prog_type. -Wenum-conversion might be unhappy about it: error: implicit conversion from enumeration type 'enum bpf_map_type' to different enumeration type 'enum bpf_prog_type' Signed-off-by: Stanislav Fomichev Signed-off-by: Daniel Borkmann --- tools/testing/selftests/bpf/test_verifier.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index d23929a1985d..37583267bdbc 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -13940,7 +13940,7 @@ static int create_map(uint32_t type, uint32_t size_key, return fd; } -static int create_prog_dummy1(enum bpf_map_type prog_type) +static int create_prog_dummy1(enum bpf_prog_type prog_type) { struct bpf_insn prog[] = { BPF_MOV64_IMM(BPF_REG_0, 42), @@ -13951,7 +13951,7 @@ static int create_prog_dummy1(enum bpf_map_type prog_type) ARRAY_SIZE(prog), "GPL", 0, NULL, 0); } -static int create_prog_dummy2(enum bpf_map_type prog_type, int mfd, int idx) +static int create_prog_dummy2(enum bpf_prog_type prog_type, int mfd, int idx) { struct bpf_insn prog[] = { BPF_MOV64_IMM(BPF_REG_3, idx), @@ -13966,7 +13966,7 @@ static int create_prog_dummy2(enum bpf_map_type prog_type, int mfd, int idx) ARRAY_SIZE(prog), "GPL", 0, NULL, 0); } -static int create_prog_array(enum bpf_map_type prog_type, uint32_t max_elem, +static int create_prog_array(enum bpf_prog_type prog_type, uint32_t max_elem, int p1key) { int p2key = 1; @@ -14037,7 +14037,7 @@ static int create_cgroup_storage(bool percpu) static char bpf_vlog[UINT_MAX >> 8]; -static void do_test_fixup(struct bpf_test *test, enum bpf_map_type prog_type, +static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type, struct bpf_insn *prog, int *map_fds) { int *fixup_map_hash_8b = test->fixup_map_hash_8b; -- cgit v1.2.3 From 6c5c7489089608d89b7ce310bca44812e2b0a4a5 Mon Sep 17 00:00:00 2001 From: Thomas Falcon Date: Mon, 10 Dec 2018 15:22:22 -0600 Subject: ibmvnic: Convert reset work item mutex to spin lock ibmvnic_reset can create and schedule a reset work item from an IRQ context, so do not use a mutex, which can sleep. Convert the reset work item mutex to a spin lock. Locking debugger generated the trace output below. BUG: sleeping function called from invalid context at kernel/locking/mutex.c:908 in_atomic(): 1, irqs_disabled(): 1, pid: 120, name: kworker/8:1 4 locks held by kworker/8:1/120: #0: 0000000017c05720 ((wq_completion)"events"){+.+.}, at: process_one_work+0x188/0x710 #1: 00000000ace90706 ((linkwatch_work).work){+.+.}, at: process_one_work+0x188/0x710 #2: 000000007632871f (rtnl_mutex){+.+.}, at: rtnl_lock+0x30/0x50 #3: 00000000fc36813a (&(&crq->lock)->rlock){..-.}, at: ibmvnic_tasklet+0x88/0x2010 [ibmvnic] irq event stamp: 26293 hardirqs last enabled at (26292): [] tasklet_action_common.isra.12+0x78/0x1c0 hardirqs last disabled at (26293): [] _raw_spin_lock_irqsave+0x48/0xf0 softirqs last enabled at (26288): [] dev_deactivate_queue.constprop.28+0xc8/0x160 softirqs last disabled at (26289): [] call_do_softirq+0x14/0x24 CPU: 8 PID: 120 Comm: kworker/8:1 Kdump: loaded Not tainted 4.20.0-rc6 #6 Workqueue: events linkwatch_event Call Trace: [c0000003fffa7a50] [c000000000bc83e4] dump_stack+0xe8/0x164 (unreliable) [c0000003fffa7aa0] [c00000000015ba0c] ___might_sleep+0x2dc/0x320 [c0000003fffa7b20] [c000000000be960c] __mutex_lock+0x8c/0xb40 [c0000003fffa7c30] [d000000006202ac8] ibmvnic_reset+0x78/0x330 [ibmvnic] [c0000003fffa7cc0] [d0000000062097f4] ibmvnic_tasklet+0x1054/0x2010 [ibmvnic] [c0000003fffa7e00] [c0000000001224c8] tasklet_action_common.isra.12+0xd8/0x1c0 [c0000003fffa7e60] [c000000000bf1238] __do_softirq+0x1a8/0x64c [c0000003fffa7f90] [c0000000000306e0] call_do_softirq+0x14/0x24 [c0000003f3f87980] [c00000000001ba50] do_softirq_own_stack+0x60/0xb0 [c0000003f3f879c0] [c0000000001218a8] do_softirq+0xa8/0x100 [c0000003f3f879f0] [c000000000121a74] __local_bh_enable_ip+0x174/0x180 [c0000003f3f87a60] [c000000000bf003c] _raw_spin_unlock_bh+0x5c/0x80 [c0000003f3f87a90] [c000000000a8ac78] dev_deactivate_queue.constprop.28+0xc8/0x160 [c0000003f3f87ad0] [c000000000a8c8b0] dev_deactivate_many+0xd0/0x520 [c0000003f3f87b70] [c000000000a8cd40] dev_deactivate+0x40/0x60 [c0000003f3f87ba0] [c000000000a5e0c4] linkwatch_do_dev+0x74/0xd0 [c0000003f3f87bd0] [c000000000a5e694] __linkwatch_run_queue+0x1a4/0x1f0 [c0000003f3f87c30] [c000000000a5e728] linkwatch_event+0x48/0x60 [c0000003f3f87c50] [c0000000001444e8] process_one_work+0x238/0x710 [c0000003f3f87d20] [c000000000144a48] worker_thread+0x88/0x4e0 [c0000003f3f87db0] [c00000000014e3a8] kthread+0x178/0x1c0 [c0000003f3f87e20] [c00000000000bfd0] ret_from_kernel_thread+0x5c/0x6c Signed-off-by: Thomas Falcon Signed-off-by: David S. Miller --- drivers/net/ethernet/ibm/ibmvnic.c | 16 +++++++++------- drivers/net/ethernet/ibm/ibmvnic.h | 2 +- 2 files changed, 10 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index ed50b8dee44f..ffc0cab05b0f 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -1939,8 +1939,9 @@ static int do_hard_reset(struct ibmvnic_adapter *adapter, static struct ibmvnic_rwi *get_next_rwi(struct ibmvnic_adapter *adapter) { struct ibmvnic_rwi *rwi; + unsigned long flags; - mutex_lock(&adapter->rwi_lock); + spin_lock_irqsave(&adapter->rwi_lock, flags); if (!list_empty(&adapter->rwi_list)) { rwi = list_first_entry(&adapter->rwi_list, struct ibmvnic_rwi, @@ -1950,7 +1951,7 @@ static struct ibmvnic_rwi *get_next_rwi(struct ibmvnic_adapter *adapter) rwi = NULL; } - mutex_unlock(&adapter->rwi_lock); + spin_unlock_irqrestore(&adapter->rwi_lock, flags); return rwi; } @@ -2025,6 +2026,7 @@ static int ibmvnic_reset(struct ibmvnic_adapter *adapter, struct list_head *entry, *tmp_entry; struct ibmvnic_rwi *rwi, *tmp; struct net_device *netdev = adapter->netdev; + unsigned long flags; int ret; if (adapter->state == VNIC_REMOVING || @@ -2041,13 +2043,13 @@ static int ibmvnic_reset(struct ibmvnic_adapter *adapter, goto err; } - mutex_lock(&adapter->rwi_lock); + spin_lock_irqsave(&adapter->rwi_lock, flags); list_for_each(entry, &adapter->rwi_list) { tmp = list_entry(entry, struct ibmvnic_rwi, list); if (tmp->reset_reason == reason) { netdev_dbg(netdev, "Skipping matching reset\n"); - mutex_unlock(&adapter->rwi_lock); + spin_unlock_irqrestore(&adapter->rwi_lock, flags); ret = EBUSY; goto err; } @@ -2055,7 +2057,7 @@ static int ibmvnic_reset(struct ibmvnic_adapter *adapter, rwi = kzalloc(sizeof(*rwi), GFP_KERNEL); if (!rwi) { - mutex_unlock(&adapter->rwi_lock); + spin_unlock_irqrestore(&adapter->rwi_lock, flags); ibmvnic_close(netdev); ret = ENOMEM; goto err; @@ -2069,7 +2071,7 @@ static int ibmvnic_reset(struct ibmvnic_adapter *adapter, } rwi->reset_reason = reason; list_add_tail(&rwi->list, &adapter->rwi_list); - mutex_unlock(&adapter->rwi_lock); + spin_unlock_irqrestore(&adapter->rwi_lock, flags); adapter->resetting = true; netdev_dbg(adapter->netdev, "Scheduling reset (reason %d)\n", reason); schedule_work(&adapter->ibmvnic_reset); @@ -4759,7 +4761,7 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id) INIT_WORK(&adapter->ibmvnic_reset, __ibmvnic_reset); INIT_LIST_HEAD(&adapter->rwi_list); - mutex_init(&adapter->rwi_lock); + spin_lock_init(&adapter->rwi_lock); adapter->resetting = false; adapter->mac_change_pending = false; diff --git a/drivers/net/ethernet/ibm/ibmvnic.h b/drivers/net/ethernet/ibm/ibmvnic.h index 99c4f8d331ce..f2018dbebfa5 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.h +++ b/drivers/net/ethernet/ibm/ibmvnic.h @@ -1075,7 +1075,7 @@ struct ibmvnic_adapter { struct tasklet_struct tasklet; enum vnic_state state; enum ibmvnic_reset_reason reset_reason; - struct mutex rwi_lock; + spinlock_t rwi_lock; struct list_head rwi_list; struct work_struct ibmvnic_reset; bool resetting; -- cgit v1.2.3 From 1d1bbc37f89b0559c9e913682f2489d89cfde6b8 Mon Sep 17 00:00:00 2001 From: Thomas Falcon Date: Mon, 10 Dec 2018 15:22:23 -0600 Subject: ibmvnic: Fix non-atomic memory allocation in IRQ context ibmvnic_reset allocated new reset work item objects in a non-atomic context. This can be called from a tasklet, generating the output below. Allocate work items with the GFP_ATOMIC flag instead. BUG: sleeping function called from invalid context at mm/slab.h:421 in_atomic(): 1, irqs_disabled(): 1, pid: 93, name: kworker/0:2 INFO: lockdep is turned off. irq event stamp: 66049 hardirqs last enabled at (66048): [] tasklet_action_common.isra.12+0x78/0x1c0 hardirqs last disabled at (66049): [] _raw_spin_lock_irqsave+0x48/0xf0 softirqs last enabled at (66044): [] dev_deactivate_queue.constprop.28+0xc8/0x160 softirqs last disabled at (66045): [] call_do_softirq+0x14/0x24 CPU: 0 PID: 93 Comm: kworker/0:2 Kdump: loaded Not tainted 4.20.0-rc6-00001-g1b50a8f03706 #7 Workqueue: events linkwatch_event Call Trace: [c0000003fffe7ae0] [c000000000bc83e4] dump_stack+0xe8/0x164 (unreliable) [c0000003fffe7b30] [c00000000015ba0c] ___might_sleep+0x2dc/0x320 [c0000003fffe7bb0] [c000000000391514] kmem_cache_alloc_trace+0x3e4/0x440 [c0000003fffe7c30] [d000000005b2309c] ibmvnic_reset+0x16c/0x360 [ibmvnic] [c0000003fffe7cc0] [d000000005b29834] ibmvnic_tasklet+0x1054/0x2010 [ibmvnic] [c0000003fffe7e00] [c0000000001224c8] tasklet_action_common.isra.12+0xd8/0x1c0 [c0000003fffe7e60] [c000000000bf1238] __do_softirq+0x1a8/0x64c [c0000003fffe7f90] [c0000000000306e0] call_do_softirq+0x14/0x24 [c0000003f3967980] [c00000000001ba50] do_softirq_own_stack+0x60/0xb0 [c0000003f39679c0] [c0000000001218a8] do_softirq+0xa8/0x100 [c0000003f39679f0] [c000000000121a74] __local_bh_enable_ip+0x174/0x180 [c0000003f3967a60] [c000000000bf003c] _raw_spin_unlock_bh+0x5c/0x80 [c0000003f3967a90] [c000000000a8ac78] dev_deactivate_queue.constprop.28+0xc8/0x160 [c0000003f3967ad0] [c000000000a8c8b0] dev_deactivate_many+0xd0/0x520 [c0000003f3967b70] [c000000000a8cd40] dev_deactivate+0x40/0x60 [c0000003f3967ba0] [c000000000a5e0c4] linkwatch_do_dev+0x74/0xd0 [c0000003f3967bd0] [c000000000a5e694] __linkwatch_run_queue+0x1a4/0x1f0 [c0000003f3967c30] [c000000000a5e728] linkwatch_event+0x48/0x60 [c0000003f3967c50] [c0000000001444e8] process_one_work+0x238/0x710 [c0000003f3967d20] [c000000000144a48] worker_thread+0x88/0x4e0 [c0000003f3967db0] [c00000000014e3a8] kthread+0x178/0x1c0 [c0000003f3967e20] [c00000000000bfd0] ret_from_kernel_thread+0x5c/0x6c Signed-off-by: Thomas Falcon Signed-off-by: David S. Miller --- drivers/net/ethernet/ibm/ibmvnic.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index ffc0cab05b0f..67cc6d9c8fd7 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -2055,7 +2055,7 @@ static int ibmvnic_reset(struct ibmvnic_adapter *adapter, } } - rwi = kzalloc(sizeof(*rwi), GFP_KERNEL); + rwi = kzalloc(sizeof(*rwi), GFP_ATOMIC); if (!rwi) { spin_unlock_irqrestore(&adapter->rwi_lock, flags); ibmvnic_close(netdev); -- cgit v1.2.3 From 290974d434783624c13a9530a23c45f9c5ffe018 Mon Sep 17 00:00:00 2001 From: Pieter Jansen van Vuuren Date: Mon, 10 Dec 2018 15:03:43 -0800 Subject: nfp: flower: ensure TCP flags can be placed in IPv6 frame Previously we did not ensure tcp flags have a place to be stored when using IPv6. We correct this by including IPv6 key layer when we match tcp flags and the IPv6 key layer has not been included already. Fixes: 07e1671cfca5 ("nfp: flower: refactor shared ip header in match offload") Signed-off-by: Pieter Jansen van Vuuren Reviewed-by: Jakub Kicinski Signed-off-by: David S. Miller --- .../net/ethernet/netronome/nfp/flower/offload.c | 28 +++++++++++++++++----- 1 file changed, 22 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c index 2f49eb75f3cc..67e576fe7fc0 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/offload.c +++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c @@ -345,13 +345,29 @@ nfp_flower_calculate_key_layers(struct nfp_app *app, !(tcp_flags & (TCPHDR_FIN | TCPHDR_SYN | TCPHDR_RST))) return -EOPNOTSUPP; - /* We need to store TCP flags in the IPv4 key space, thus - * we need to ensure we include a IPv4 key layer if we have - * not done so already. + /* We need to store TCP flags in the either the IPv4 or IPv6 key + * space, thus we need to ensure we include a IPv4/IPv6 key + * layer if we have not done so already. */ - if (!(key_layer & NFP_FLOWER_LAYER_IPV4)) { - key_layer |= NFP_FLOWER_LAYER_IPV4; - key_size += sizeof(struct nfp_flower_ipv4); + if (!key_basic) + return -EOPNOTSUPP; + + if (!(key_layer & NFP_FLOWER_LAYER_IPV4) && + !(key_layer & NFP_FLOWER_LAYER_IPV6)) { + switch (key_basic->n_proto) { + case cpu_to_be16(ETH_P_IP): + key_layer |= NFP_FLOWER_LAYER_IPV4; + key_size += sizeof(struct nfp_flower_ipv4); + break; + + case cpu_to_be16(ETH_P_IPV6): + key_layer |= NFP_FLOWER_LAYER_IPV6; + key_size += sizeof(struct nfp_flower_ipv6); + break; + + default: + return -EOPNOTSUPP; + } } } -- cgit v1.2.3 From 5d7ab8f0bc1410ee9d4099284ea05bf31a2e39ec Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Fri, 30 Nov 2018 09:00:31 +0100 Subject: thermal/drivers/hisi: Fix wrong platform_get_irq_byname() Without this patch, the thermal driver on hi6220 and hi3660 is broken. That is due because part of the posted patchset was merged but a small change in the DT was dropped. The hi6220 and hi3660 do not have an interrupt name in the DT, so finding interrupt by name fails. Fix this by returning back to the platform_get_irq() function call. Fixes: 2cffaeff083f (thermal/drivers/hisi: Use platform_get_irq_byname) Signed-off-by: Daniel Lezcano Signed-off-by: Eduardo Valentin --- drivers/thermal/hisi_thermal.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/thermal/hisi_thermal.c b/drivers/thermal/hisi_thermal.c index c4111a98f1a7..50f4d002e8ae 100644 --- a/drivers/thermal/hisi_thermal.c +++ b/drivers/thermal/hisi_thermal.c @@ -589,7 +589,7 @@ static int hisi_thermal_probe(struct platform_device *pdev) return ret; } - ret = platform_get_irq_byname(pdev, sensor->irq_name); + ret = platform_get_irq(pdev, 0); if (ret < 0) return ret; -- cgit v1.2.3 From 7d3a2a2bbadb4bf5856ed394ba09b8fbb7a80460 Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Fri, 30 Nov 2018 09:00:32 +0100 Subject: thermal/drivers/hisi: Fix number of sensors on hi3660 Without this patch the thermal driver is broken on hi3660. The dual sensors support patchset was partially merged, unfortunately the dual thermal zones definition is not available in the DT yet, so when the driver tries to register all the sensors that fails. By reducing to 1 the number of sensors on the hi3660, we switch back to the previous functionnality. Fixes: 8c6c36846f11 (thermal/drivers/hisi: Add the dual clusters sensors for hi3660) Signed-off-by: Daniel Lezcano Signed-off-by: Eduardo Valentin --- drivers/thermal/hisi_thermal.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/thermal/hisi_thermal.c b/drivers/thermal/hisi_thermal.c index 50f4d002e8ae..2d26ae80e202 100644 --- a/drivers/thermal/hisi_thermal.c +++ b/drivers/thermal/hisi_thermal.c @@ -424,7 +424,7 @@ static int hi3660_thermal_probe(struct hisi_thermal_data *data) struct platform_device *pdev = data->pdev; struct device *dev = &pdev->dev; - data->nr_sensors = 2; + data->nr_sensors = 1; data->sensor = devm_kzalloc(dev, sizeof(*data->sensor) * data->nr_sensors, GFP_KERNEL); -- cgit v1.2.3 From 3c9d082064b5ec5876f7e20bc50959d1915c5ab0 Mon Sep 17 00:00:00 2001 From: David HERNANDEZ SANCHEZ Date: Thu, 6 Dec 2018 13:23:32 +0000 Subject: thermal: stm32: read factory settings inside stm_thermal_prepare Calling stm_thermal_read_factory_settings before clocking internal peripheral causes bad register values and makes temperature computation wrong. Calling stm_thermal_read_factory_settings inside stm_thermal_prepare fixes this problem as internal peripheral is well clocked at this stage. Fixes: 1d693155 ("thermal: add stm32 thermal driver") Reviewed-by: Daniel Lezcano Signed-off-by: David Hernandez Sanchez Signed-off-by: Eduardo Valentin --- drivers/thermal/st/stm_thermal.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/thermal/st/stm_thermal.c b/drivers/thermal/st/stm_thermal.c index 47623da0f91b..daa1257809a6 100644 --- a/drivers/thermal/st/stm_thermal.c +++ b/drivers/thermal/st/stm_thermal.c @@ -532,6 +532,10 @@ static int stm_thermal_prepare(struct stm_thermal_sensor *sensor) if (ret) return ret; + ret = stm_thermal_read_factory_settings(sensor); + if (ret) + goto thermal_unprepare; + ret = stm_thermal_calibration(sensor); if (ret) goto thermal_unprepare; @@ -636,10 +640,6 @@ static int stm_thermal_probe(struct platform_device *pdev) /* Populate sensor */ sensor->base = base; - ret = stm_thermal_read_factory_settings(sensor); - if (ret) - return ret; - sensor->clk = devm_clk_get(&pdev->dev, "pclk"); if (IS_ERR(sensor->clk)) { dev_err(&pdev->dev, "%s: failed to fetch PCLK clock\n", -- cgit v1.2.3 From 99c47fcd4daa2b9a1348872ba49226dcdc58cb40 Mon Sep 17 00:00:00 2001 From: David HERNANDEZ SANCHEZ Date: Thu, 6 Dec 2018 13:23:32 +0000 Subject: thermal: stm32: Fix stm_thermal_read_factory_settings Adding brackets allows to multiply the register value, masked by TS1_RAMP_COEFF_MASK, by an ADJUST value properly and not to multiply ADJUST by register value and then mask the whole. Fixes: 1d693155 ("thermal: add stm32 thermal driver") Reviewed-by: Daniel Lezcano Signed-off-by: David Hernandez Sanchez Signed-off-by: Eduardo Valentin --- drivers/thermal/st/stm_thermal.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/thermal/st/stm_thermal.c b/drivers/thermal/st/stm_thermal.c index daa1257809a6..bbd73c5a4a4e 100644 --- a/drivers/thermal/st/stm_thermal.c +++ b/drivers/thermal/st/stm_thermal.c @@ -241,8 +241,8 @@ static int stm_thermal_read_factory_settings(struct stm_thermal_sensor *sensor) sensor->t0 = TS1_T0_VAL1; /* Retrieve fmt0 and put it on Hz */ - sensor->fmt0 = ADJUST * readl_relaxed(sensor->base + DTS_T0VALR1_OFFSET) - & TS1_FMT0_MASK; + sensor->fmt0 = ADJUST * (readl_relaxed(sensor->base + + DTS_T0VALR1_OFFSET) & TS1_FMT0_MASK); /* Retrieve ramp coefficient */ sensor->ramp_coeff = readl_relaxed(sensor->base + DTS_RAMPVALR_OFFSET) & -- cgit v1.2.3 From 4ac0a807da6f79d5f2a65f991030aee503fece3a Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Fri, 23 Nov 2018 13:11:51 +0100 Subject: drm/nouveau/drm/nouveau: tegra: Call nouveau_drm_device_init() As part of commit cfea88a4d866 ("drm/nouveau: Start using new drm_dev initialization helpers"), the initialization of the Nouveau DRM device was reworked and along the way the platform driver initialization was left incomplete. Add a call to nouveau_drm_device_init() to make sure all of the structures are properly initialized. Signed-off-by: Thierry Reding Reviewed-by: Lyude Paul Tested-by: Marcel Ziswiler Signed-off-by: Ben Skeggs --- drivers/gpu/drm/nouveau/nouveau_drm.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c index 2b2baf6e0e0d..d2928d43f29a 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drm.c +++ b/drivers/gpu/drm/nouveau/nouveau_drm.c @@ -1171,10 +1171,16 @@ nouveau_platform_device_create(const struct nvkm_device_tegra_func *func, goto err_free; } + err = nouveau_drm_device_init(drm); + if (err) + goto err_put; + platform_set_drvdata(pdev, drm); return drm; +err_put: + drm_dev_put(drm); err_free: nvkm_device_del(pdevice); -- cgit v1.2.3 From 8e41cae64b08fe2e86a9ffb88b295c6b4b3a3322 Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Tue, 11 Dec 2018 11:13:39 +0800 Subject: ieee802154: ca8210: fix possible u8 overflow in ca8210_rx_done gcc warning this: drivers/net/ieee802154/ca8210.c:730:10: warning: comparison is always false due to limited range of data type [-Wtype-limits] 'len' is u8 type, we get it from buf[1] adding 2, which can overflow. This patch change the type of 'len' to unsigned int to avoid this,also fix the gcc warning. Fixes: ded845a781a5 ("ieee802154: Add CA8210 IEEE 802.15.4 device driver") Signed-off-by: YueHaibing Signed-off-by: Stefan Schmidt --- drivers/net/ieee802154/ca8210.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ieee802154/ca8210.c b/drivers/net/ieee802154/ca8210.c index 0ff5a403a8dc..b2ff903a9cb6 100644 --- a/drivers/net/ieee802154/ca8210.c +++ b/drivers/net/ieee802154/ca8210.c @@ -721,7 +721,7 @@ static void ca8210_mlme_reset_worker(struct work_struct *work) static void ca8210_rx_done(struct cas_control *cas_ctl) { u8 *buf; - u8 len; + unsigned int len; struct work_priv_container *mlme_reset_wpc; struct ca8210_priv *priv = cas_ctl->priv; @@ -730,7 +730,7 @@ static void ca8210_rx_done(struct cas_control *cas_ctl) if (len > CA8210_SPI_BUF_SIZE) { dev_crit( &priv->spi->dev, - "Received packet len (%d) erroneously long\n", + "Received packet len (%u) erroneously long\n", len ); goto finish; -- cgit v1.2.3 From 3238c359acee4ab57f15abb5a82b8ab38a661ee7 Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Mon, 10 Dec 2018 19:33:31 +0000 Subject: arm64: dma-mapping: Fix FORCE_CONTIGUOUS buffer clearing We need to invalidate the caches *before* clearing the buffer via the non-cacheable alias, else in the worst case __dma_flush_area() may write back dirty lines over the top of our nice new zeros. Fixes: dd65a941f6ba ("arm64: dma-mapping: clear buffers allocated with FORCE_CONTIGUOUS flag") Cc: # 4.18.x- Acked-by: Will Deacon Signed-off-by: Robin Murphy Signed-off-by: Catalin Marinas --- arch/arm64/mm/dma-mapping.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c index a3ac26284845..a53704406099 100644 --- a/arch/arm64/mm/dma-mapping.c +++ b/arch/arm64/mm/dma-mapping.c @@ -429,9 +429,9 @@ static void *__iommu_alloc_attrs(struct device *dev, size_t size, prot, __builtin_return_address(0)); if (addr) { - memset(addr, 0, size); if (!coherent) __dma_flush_area(page_to_virt(page), iosize); + memset(addr, 0, size); } else { iommu_dma_unmap_page(dev, *handle, iosize, 0, attrs); dma_release_from_contiguous(dev, page, -- cgit v1.2.3 From 5e3c420dcca53766dec57d5bf4df8eecdb953c03 Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Mon, 10 Dec 2018 10:18:19 -0800 Subject: uio_hv_generic: set callbacks on open This fixes the problem where uio application was unable to use multple queues on restart. The root cause is that the callbacks are cleared on disconnect. Change to setting up callbacks everytime in open. Fixes: cdfa835c6e5e ("uio_hv_generic: defer opening vmbus until first use") Reported-by: Mohammed Gamal Signed-off-by: Stephen Hemminger Signed-off-by: Greg Kroah-Hartman --- drivers/uio/uio_hv_generic.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/drivers/uio/uio_hv_generic.c b/drivers/uio/uio_hv_generic.c index c2493d011225..3c5169eb23f5 100644 --- a/drivers/uio/uio_hv_generic.c +++ b/drivers/uio/uio_hv_generic.c @@ -204,9 +204,11 @@ hv_uio_open(struct uio_info *info, struct inode *inode) if (atomic_inc_return(&pdata->refcnt) != 1) return 0; + vmbus_set_chn_rescind_callback(dev->channel, hv_uio_rescind); + vmbus_set_sc_create_callback(dev->channel, hv_uio_new_channel); + ret = vmbus_connect_ring(dev->channel, hv_uio_channel_cb, dev->channel); - if (ret == 0) dev->channel->inbound.ring_buffer->interrupt_mask = 1; else @@ -334,9 +336,6 @@ hv_uio_probe(struct hv_device *dev, goto fail_close; } - vmbus_set_chn_rescind_callback(channel, hv_uio_rescind); - vmbus_set_sc_create_callback(channel, hv_uio_new_channel); - ret = sysfs_create_bin_file(&channel->kobj, &ring_buffer_bin_attr); if (ret) dev_notice(&dev->device, -- cgit v1.2.3 From 63238173b2faf3d6b85a416f1c69af6c7be2413f Mon Sep 17 00:00:00 2001 From: Brian Norris Date: Wed, 5 Dec 2018 10:16:57 -0800 Subject: Revert "drm/rockchip: Allow driver to be shutdown on reboot/kexec" This reverts commit 7f3ef5dedb146e3d5063b6845781ad1bb59b92b5. It causes new warnings [1] on shutdown when running the Google Kevin or Scarlet (RK3399) boards under Chrome OS. Presumably our usage of DRM is different than what Marc and Heiko test. We're looking at a different approach (e.g., [2]) to replace this, but IMO the revert should be taken first, as it already propagated to -stable. [1] Report here: http://lkml.kernel.org/lkml/20181205030127.GA200921@google.com WARNING: CPU: 4 PID: 2035 at drivers/gpu/drm/drm_mode_config.c:477 drm_mode_config_cleanup+0x1c4/0x294 ... Call trace: drm_mode_config_cleanup+0x1c4/0x294 rockchip_drm_unbind+0x4c/0x8c component_master_del+0x88/0xb8 rockchip_drm_platform_remove+0x2c/0x44 rockchip_drm_platform_shutdown+0x20/0x2c platform_drv_shutdown+0x2c/0x38 device_shutdown+0x164/0x1b8 kernel_restart_prepare+0x40/0x48 kernel_restart+0x20/0x68 ... Memory manager not clean during takedown. WARNING: CPU: 4 PID: 2035 at drivers/gpu/drm/drm_mm.c:950 drm_mm_takedown+0x34/0x44 ... drm_mm_takedown+0x34/0x44 rockchip_drm_unbind+0x64/0x8c component_master_del+0x88/0xb8 rockchip_drm_platform_remove+0x2c/0x44 rockchip_drm_platform_shutdown+0x20/0x2c platform_drv_shutdown+0x2c/0x38 device_shutdown+0x164/0x1b8 kernel_restart_prepare+0x40/0x48 kernel_restart+0x20/0x68 ... [2] https://patchwork.kernel.org/patch/10556151/ https://www.spinics.net/lists/linux-rockchip/msg21342.html [PATCH] drm/rockchip: shutdown drm subsystem on shutdown Fixes: 7f3ef5dedb14 ("drm/rockchip: Allow driver to be shutdown on reboot/kexec") Cc: Jeffy Chen Cc: Robin Murphy Cc: Vicente Bergas Cc: Marc Zyngier Cc: Heiko Stuebner Cc: stable@vger.kernel.org Signed-off-by: Brian Norris Signed-off-by: Heiko Stuebner Link: https://patchwork.freedesktop.org/patch/msgid/20181205181657.177703-1-briannorris@chromium.org --- drivers/gpu/drm/rockchip/rockchip_drm_drv.c | 6 ------ 1 file changed, 6 deletions(-) diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_drv.c b/drivers/gpu/drm/rockchip/rockchip_drm_drv.c index 941f35233b1f..5864cb452c5c 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_drv.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_drv.c @@ -448,11 +448,6 @@ static int rockchip_drm_platform_remove(struct platform_device *pdev) return 0; } -static void rockchip_drm_platform_shutdown(struct platform_device *pdev) -{ - rockchip_drm_platform_remove(pdev); -} - static const struct of_device_id rockchip_drm_dt_ids[] = { { .compatible = "rockchip,display-subsystem", }, { /* sentinel */ }, @@ -462,7 +457,6 @@ MODULE_DEVICE_TABLE(of, rockchip_drm_dt_ids); static struct platform_driver rockchip_drm_platform_driver = { .probe = rockchip_drm_platform_probe, .remove = rockchip_drm_platform_remove, - .shutdown = rockchip_drm_platform_shutdown, .driver = { .name = "rockchip-drm", .of_match_table = rockchip_drm_dt_ids, -- cgit v1.2.3 From c554206077428af56cc2e0314b86b41cd030458c Mon Sep 17 00:00:00 2001 From: Andrey Grodzovsky Date: Thu, 6 Dec 2018 15:51:37 -0500 Subject: drm/amdgpu: Fix DEBUG_LOCKS_WARN_ON(depth <= 0) in amdgpu_ctx.lock If CS is submitted using guilty ctx, we terminate amdgpu_cs_parser_init before locking ctx->lock, latter in amdgpu_cs_parser_fini we still are trying to release the lock just becase parser->ctx != NULL. Signed-off-by: Andrey Grodzovsky Reviewed-by: Christian König Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index 663043c8f0f5..0acc8dee2cb8 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -124,14 +124,14 @@ static int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, union drm_amdgpu_cs goto free_chunk; } + mutex_lock(&p->ctx->lock); + /* skip guilty context job */ if (atomic_read(&p->ctx->guilty) == 1) { ret = -ECANCELED; goto free_chunk; } - mutex_lock(&p->ctx->lock); - /* get chunks */ chunk_array_user = u64_to_user_ptr(cs->in.chunks); if (copy_from_user(chunk_array, chunk_array_user, -- cgit v1.2.3 From 6f9718fe41c3a47e4362bddf145e2db6ad7d8e87 Mon Sep 17 00:00:00 2001 From: Luis Henriques Date: Mon, 10 Dec 2018 10:23:12 +0000 Subject: ceph: make 'nocopyfrom' a default mount option Since we found a problem with the 'copy-from' operation after objects have been truncated, offloading object copies to OSDs should be discouraged until the issue is fixed. Thus, this patch adds the 'nocopyfrom' mount option to the default mount options which effectily means that remote copies won't be done in copy_file_range unless they are explicitly enabled at mount time. [ Adjust ceph_show_options() accordingly. ] Link: https://tracker.ceph.com/issues/37378 Signed-off-by: Luis Henriques Reviewed-by: Ilya Dryomov Signed-off-by: Ilya Dryomov --- fs/ceph/super.c | 4 ++-- fs/ceph/super.h | 4 +++- 2 files changed, 5 insertions(+), 3 deletions(-) diff --git a/fs/ceph/super.c b/fs/ceph/super.c index b5ecd6f50360..4e9a7cc488da 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -563,8 +563,8 @@ static int ceph_show_options(struct seq_file *m, struct dentry *root) seq_puts(m, ",noacl"); #endif - if (fsopt->flags & CEPH_MOUNT_OPT_NOCOPYFROM) - seq_puts(m, ",nocopyfrom"); + if ((fsopt->flags & CEPH_MOUNT_OPT_NOCOPYFROM) == 0) + seq_puts(m, ",copyfrom"); if (fsopt->mds_namespace) seq_show_option(m, "mds_namespace", fsopt->mds_namespace); diff --git a/fs/ceph/super.h b/fs/ceph/super.h index c005a5400f2e..79a265ba9200 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -42,7 +42,9 @@ #define CEPH_MOUNT_OPT_NOQUOTADF (1<<13) /* no root dir quota in statfs */ #define CEPH_MOUNT_OPT_NOCOPYFROM (1<<14) /* don't use RADOS 'copy-from' op */ -#define CEPH_MOUNT_OPT_DEFAULT CEPH_MOUNT_OPT_DCACHE +#define CEPH_MOUNT_OPT_DEFAULT \ + (CEPH_MOUNT_OPT_DCACHE | \ + CEPH_MOUNT_OPT_NOCOPYFROM) #define ceph_set_mount_opt(fsc, opt) \ (fsc)->mount_options->flags |= CEPH_MOUNT_OPT_##opt; -- cgit v1.2.3 From cb4f131e1f2ca5dd7e2f905e4cb9fb4c5c9dcffd Mon Sep 17 00:00:00 2001 From: Sasha Levin Date: Tue, 11 Dec 2018 12:09:49 -0500 Subject: MAINTAINERS: Patch monkey for the Hyper-V code Now the Hyper-V code has it's own monkey on a tree! Make it easier to manage patch flow to upper level maintainers. Acked-by: Haiyang Zhang Acked-by: K. Y. Srinivasan Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman --- MAINTAINERS | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index 8119141a926f..553b1ed1d01f 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -6901,8 +6901,10 @@ Hyper-V CORE AND DRIVERS M: "K. Y. Srinivasan" M: Haiyang Zhang M: Stephen Hemminger +M: Sasha Levin +T: git git://git.kernel.org/pub/scm/linux/kernel/git/hyperv/linux.git L: devel@linuxdriverproject.org -S: Maintained +S: Supported F: Documentation/networking/netvsc.txt F: arch/x86/include/asm/mshyperv.h F: arch/x86/include/asm/trace/hyperv.h -- cgit v1.2.3 From a538e3ff9dabcdf6c3f477a373c629213d1c3066 Mon Sep 17 00:00:00 2001 From: Jeff Moyer Date: Tue, 11 Dec 2018 12:37:49 -0500 Subject: aio: fix spectre gadget in lookup_ioctx Matthew pointed out that the ioctx_table is susceptible to spectre v1, because the index can be controlled by an attacker. The below patch should mitigate the attack for all of the aio system calls. Cc: stable@vger.kernel.org Reported-by: Matthew Wilcox Reported-by: Dan Carpenter Signed-off-by: Jeff Moyer Signed-off-by: Jens Axboe --- fs/aio.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/aio.c b/fs/aio.c index 301e6314183b..20c07664314a 100644 --- a/fs/aio.c +++ b/fs/aio.c @@ -45,6 +45,7 @@ #include #include +#include #include "internal.h" @@ -1038,6 +1039,7 @@ static struct kioctx *lookup_ioctx(unsigned long ctx_id) if (!table || id >= table->nr) goto out; + id = array_index_nospec(id, table->nr); ctx = rcu_dereference(table->table[id]); if (ctx && ctx->user_id == ctx_id) { if (percpu_ref_tryget_live(&ctx->users)) -- cgit v1.2.3 From b61c19209c2c35ea2a2fe502d484703686eba98c Mon Sep 17 00:00:00 2001 From: Steven Rostedt (VMware) Date: Sat, 8 Dec 2018 21:10:04 -0500 Subject: tracing: Fix memory leak in create_filter() The create_filter() calls create_filter_start() which allocates a "parse_error" descriptor, but fails to call create_filter_finish() that frees it. The op_stack and inverts in predicate_parse() were also not freed. Found by kmemleak detector. Cc: stable@vger.kernel.org Fixes: 80765597bc587 ("tracing: Rewrite filter logic to be simpler and faster") Reviewed-by: Tom Zanussi Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace_events_filter.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index 84a65173b1e9..5574e862de8d 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -570,11 +570,13 @@ predicate_parse(const char *str, int nr_parens, int nr_preds, } } + kfree(op_stack); + kfree(inverts); return prog; out_free: kfree(op_stack); - kfree(prog_stack); kfree(inverts); + kfree(prog_stack); return ERR_PTR(ret); } @@ -1718,6 +1720,7 @@ static int create_filter(struct trace_event_call *call, err = process_preds(call, filter_string, *filterp, pe); if (err && set_str) append_filter_err(pe, *filterp); + create_filter_finish(pe); return err; } -- cgit v1.2.3 From 3cec638b3d793b7cacdec5b8072364b41caeb0e1 Mon Sep 17 00:00:00 2001 From: Steven Rostedt (VMware) Date: Sun, 9 Dec 2018 21:17:30 -0500 Subject: tracing: Fix memory leak in set_trigger_filter() When create_event_filter() fails in set_trigger_filter(), the filter may still be allocated and needs to be freed. The caller expects the data->filter to be updated with the new filter, even if the new filter failed (we could add an error message by setting set_str parameter of create_event_filter(), but that's another update). But because the error would just exit, filter was left hanging and nothing could free it. Found by kmemleak detector. Cc: stable@vger.kernel.org Fixes: bac5fb97a173a ("tracing: Add and use generic set_trigger_filter() implementation") Reviewed-by: Tom Zanussi Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace_events_trigger.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c index 2152d1e530cb..cd12ecb66eb9 100644 --- a/kernel/trace/trace_events_trigger.c +++ b/kernel/trace/trace_events_trigger.c @@ -732,8 +732,10 @@ int set_trigger_filter(char *filter_str, /* The filter is for the 'trigger' event, not the triggered event */ ret = create_event_filter(file->event_call, filter_str, false, &filter); - if (ret) - goto out; + /* + * If create_event_filter() fails, filter still needs to be freed. + * Which the calling code will do with data->filter. + */ assign: tmp = rcu_access_pointer(data->filter); -- cgit v1.2.3 From 2840f84f74035e5a535959d5f17269c69fa6edc5 Mon Sep 17 00:00:00 2001 From: Steven Rostedt (VMware) Date: Mon, 10 Dec 2018 23:58:01 -0500 Subject: tracing: Fix memory leak of instance function hash filters The following commands will cause a memory leak: # cd /sys/kernel/tracing # mkdir instances/foo # echo schedule > instance/foo/set_ftrace_filter # rmdir instances/foo The reason is that the hashes that hold the filters to set_ftrace_filter and set_ftrace_notrace are not freed if they contain any data on the instance and the instance is removed. Found by kmemleak detector. Cc: stable@vger.kernel.org Fixes: 591dffdade9f ("ftrace: Allow for function tracing instance to filter functions") Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/ftrace.c | 1 + 1 file changed, 1 insertion(+) diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 77734451cb05..e23eb9fc77aa 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -5460,6 +5460,7 @@ void ftrace_destroy_filter_files(struct ftrace_ops *ops) if (ops->flags & FTRACE_OPS_FL_ENABLED) ftrace_shutdown(ops, 0); ops->flags |= FTRACE_OPS_FL_DELETED; + ftrace_free_filter(ops); mutex_unlock(&ftrace_lock); } -- cgit v1.2.3 From f6c367585d0d851349d3a9e607c43e5bea993fa1 Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Tue, 11 Dec 2018 13:31:40 -0500 Subject: dm thin: send event about thin-pool state change _after_ making it Sending a DM event before a thin-pool state change is about to happen is a bug. It wasn't realized until it became clear that userspace response to the event raced with the actual state change that the event was meant to notify about. Fix this by first updating internal thin-pool state to reflect what the DM event is being issued about. This fixes a long-standing racey/buggy userspace device-mapper-test-suite 'resize_io' test that would get an event but not find the state it was looking for -- so it would just go on to hang because no other events caused the test to reevaluate the thin-pool's state. Cc: stable@vger.kernel.org Signed-off-by: Mike Snitzer --- drivers/md/dm-thin.c | 68 +++++++++++++++++++++++++++------------------------- 1 file changed, 35 insertions(+), 33 deletions(-) diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index 0bd8d498b3b9..53f8d03f76f7 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -195,7 +195,7 @@ static void throttle_unlock(struct throttle *t) struct dm_thin_new_mapping; /* - * The pool runs in 4 modes. Ordered in degraded order for comparisons. + * The pool runs in various modes. Ordered in degraded order for comparisons. */ enum pool_mode { PM_WRITE, /* metadata may be changed */ @@ -282,9 +282,38 @@ struct pool { mempool_t mapping_pool; }; -static enum pool_mode get_pool_mode(struct pool *pool); static void metadata_operation_failed(struct pool *pool, const char *op, int r); +static enum pool_mode get_pool_mode(struct pool *pool) +{ + return pool->pf.mode; +} + +static void notify_of_pool_mode_change(struct pool *pool) +{ + const char *descs[] = { + "write", + "out-of-data-space", + "read-only", + "read-only", + "fail" + }; + const char *extra_desc = NULL; + enum pool_mode mode = get_pool_mode(pool); + + if (mode == PM_OUT_OF_DATA_SPACE) { + if (!pool->pf.error_if_no_space) + extra_desc = " (queue IO)"; + else + extra_desc = " (error IO)"; + } + + dm_table_event(pool->ti->table); + DMINFO("%s: switching pool to %s%s mode", + dm_device_name(pool->pool_md), + descs[(int)mode], extra_desc ? : ""); +} + /* * Target context for a pool. */ @@ -2351,8 +2380,6 @@ static void do_waker(struct work_struct *ws) queue_delayed_work(pool->wq, &pool->waker, COMMIT_PERIOD); } -static void notify_of_pool_mode_change_to_oods(struct pool *pool); - /* * We're holding onto IO to allow userland time to react. After the * timeout either the pool will have been resized (and thus back in @@ -2365,7 +2392,7 @@ static void do_no_space_timeout(struct work_struct *ws) if (get_pool_mode(pool) == PM_OUT_OF_DATA_SPACE && !pool->pf.error_if_no_space) { pool->pf.error_if_no_space = true; - notify_of_pool_mode_change_to_oods(pool); + notify_of_pool_mode_change(pool); error_retry_list_with_code(pool, BLK_STS_NOSPC); } } @@ -2433,26 +2460,6 @@ static void noflush_work(struct thin_c *tc, void (*fn)(struct work_struct *)) /*----------------------------------------------------------------*/ -static enum pool_mode get_pool_mode(struct pool *pool) -{ - return pool->pf.mode; -} - -static void notify_of_pool_mode_change(struct pool *pool, const char *new_mode) -{ - dm_table_event(pool->ti->table); - DMINFO("%s: switching pool to %s mode", - dm_device_name(pool->pool_md), new_mode); -} - -static void notify_of_pool_mode_change_to_oods(struct pool *pool) -{ - if (!pool->pf.error_if_no_space) - notify_of_pool_mode_change(pool, "out-of-data-space (queue IO)"); - else - notify_of_pool_mode_change(pool, "out-of-data-space (error IO)"); -} - static bool passdown_enabled(struct pool_c *pt) { return pt->adjusted_pf.discard_passdown; @@ -2501,8 +2508,6 @@ static void set_pool_mode(struct pool *pool, enum pool_mode new_mode) switch (new_mode) { case PM_FAIL: - if (old_mode != new_mode) - notify_of_pool_mode_change(pool, "failure"); dm_pool_metadata_read_only(pool->pmd); pool->process_bio = process_bio_fail; pool->process_discard = process_bio_fail; @@ -2516,8 +2521,6 @@ static void set_pool_mode(struct pool *pool, enum pool_mode new_mode) case PM_OUT_OF_METADATA_SPACE: case PM_READ_ONLY: - if (!is_read_only_pool_mode(old_mode)) - notify_of_pool_mode_change(pool, "read-only"); dm_pool_metadata_read_only(pool->pmd); pool->process_bio = process_bio_read_only; pool->process_discard = process_bio_success; @@ -2538,8 +2541,6 @@ static void set_pool_mode(struct pool *pool, enum pool_mode new_mode) * alarming rate. Adjust your low water mark if you're * frequently seeing this mode. */ - if (old_mode != new_mode) - notify_of_pool_mode_change_to_oods(pool); pool->out_of_data_space = true; pool->process_bio = process_bio_read_only; pool->process_discard = process_discard_bio; @@ -2552,8 +2553,6 @@ static void set_pool_mode(struct pool *pool, enum pool_mode new_mode) break; case PM_WRITE: - if (old_mode != new_mode) - notify_of_pool_mode_change(pool, "write"); if (old_mode == PM_OUT_OF_DATA_SPACE) cancel_delayed_work_sync(&pool->no_space_timeout); pool->out_of_data_space = false; @@ -2573,6 +2572,9 @@ static void set_pool_mode(struct pool *pool, enum pool_mode new_mode) * doesn't cause an unexpected mode transition on resume. */ pt->adjusted_pf.mode = new_mode; + + if (old_mode != new_mode) + notify_of_pool_mode_change(pool); } static void abort_transaction(struct pool *pool) -- cgit v1.2.3 From 2e64ff154ce6ce9a8dc0f9556463916efa6ff460 Mon Sep 17 00:00:00 2001 From: Chad Austin Date: Mon, 10 Dec 2018 10:54:52 -0800 Subject: fuse: continue to send FUSE_RELEASEDIR when FUSE_OPEN returns ENOSYS When FUSE_OPEN returns ENOSYS, the no_open bit is set on the connection. Because the FUSE_RELEASE and FUSE_RELEASEDIR paths share code, this incorrectly caused the FUSE_RELEASEDIR request to be dropped and never sent to userspace. Pass an isdir bool to distinguish between FUSE_RELEASE and FUSE_RELEASEDIR inside of fuse_file_put. Fixes: 7678ac50615d ("fuse: support clients that don't implement 'open'") Cc: # v3.14 Signed-off-by: Chad Austin Signed-off-by: Miklos Szeredi --- fs/fuse/dir.c | 2 +- fs/fuse/file.c | 21 +++++++++++---------- fs/fuse/fuse_i.h | 2 +- 3 files changed, 13 insertions(+), 12 deletions(-) diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index dc4e83d8ace7..e909678afa2d 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -1243,7 +1243,7 @@ static int fuse_dir_open(struct inode *inode, struct file *file) static int fuse_dir_release(struct inode *inode, struct file *file) { - fuse_release_common(file, FUSE_RELEASEDIR); + fuse_release_common(file, true); return 0; } diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 677c51341e96..ffaffe18352a 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -89,12 +89,12 @@ static void fuse_release_end(struct fuse_conn *fc, struct fuse_req *req) iput(req->misc.release.inode); } -static void fuse_file_put(struct fuse_file *ff, bool sync) +static void fuse_file_put(struct fuse_file *ff, bool sync, bool isdir) { if (refcount_dec_and_test(&ff->count)) { struct fuse_req *req = ff->reserved_req; - if (ff->fc->no_open) { + if (ff->fc->no_open && !isdir) { /* * Drop the release request when client does not * implement 'open' @@ -247,10 +247,11 @@ static void fuse_prepare_release(struct fuse_file *ff, int flags, int opcode) req->in.args[0].value = inarg; } -void fuse_release_common(struct file *file, int opcode) +void fuse_release_common(struct file *file, bool isdir) { struct fuse_file *ff = file->private_data; struct fuse_req *req = ff->reserved_req; + int opcode = isdir ? FUSE_RELEASEDIR : FUSE_RELEASE; fuse_prepare_release(ff, file->f_flags, opcode); @@ -272,7 +273,7 @@ void fuse_release_common(struct file *file, int opcode) * synchronous RELEASE is allowed (and desirable) in this case * because the server can be trusted not to screw up. */ - fuse_file_put(ff, ff->fc->destroy_req != NULL); + fuse_file_put(ff, ff->fc->destroy_req != NULL, isdir); } static int fuse_open(struct inode *inode, struct file *file) @@ -288,7 +289,7 @@ static int fuse_release(struct inode *inode, struct file *file) if (fc->writeback_cache) write_inode_now(inode, 1); - fuse_release_common(file, FUSE_RELEASE); + fuse_release_common(file, false); /* return value is ignored by VFS */ return 0; @@ -302,7 +303,7 @@ void fuse_sync_release(struct fuse_file *ff, int flags) * iput(NULL) is a no-op and since the refcount is 1 and everything's * synchronous, we are fine with not doing igrab() here" */ - fuse_file_put(ff, true); + fuse_file_put(ff, true, false); } EXPORT_SYMBOL_GPL(fuse_sync_release); @@ -808,7 +809,7 @@ static void fuse_readpages_end(struct fuse_conn *fc, struct fuse_req *req) put_page(page); } if (req->ff) - fuse_file_put(req->ff, false); + fuse_file_put(req->ff, false, false); } static void fuse_send_readpages(struct fuse_req *req, struct file *file) @@ -1461,7 +1462,7 @@ static void fuse_writepage_free(struct fuse_conn *fc, struct fuse_req *req) __free_page(req->pages[i]); if (req->ff) - fuse_file_put(req->ff, false); + fuse_file_put(req->ff, false, false); } static void fuse_writepage_finish(struct fuse_conn *fc, struct fuse_req *req) @@ -1620,7 +1621,7 @@ int fuse_write_inode(struct inode *inode, struct writeback_control *wbc) ff = __fuse_write_file_get(fc, fi); err = fuse_flush_times(inode, ff); if (ff) - fuse_file_put(ff, 0); + fuse_file_put(ff, false, false); return err; } @@ -1941,7 +1942,7 @@ static int fuse_writepages(struct address_space *mapping, err = 0; } if (data.ff) - fuse_file_put(data.ff, false); + fuse_file_put(data.ff, false, false); kfree(data.orig_pages); out: diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index afe1f231c758..2f2c92e6f8cb 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -822,7 +822,7 @@ void fuse_sync_release(struct fuse_file *ff, int flags); /** * Send RELEASE or RELEASEDIR request */ -void fuse_release_common(struct file *file, int opcode); +void fuse_release_common(struct file *file, bool isdir); /** * Send FSYNC or FSYNCDIR request -- cgit v1.2.3 From 927b6b2d69b4cc900fa50d7e46d8f1fa91c91b3a Mon Sep 17 00:00:00 2001 From: Shin'ichiro Kawasaki Date: Tue, 11 Dec 2018 21:08:26 +0900 Subject: block: Fix null_blk_zoned creation failure with small number of zones null_blk_zoned creation fails if the number of zones specified is equal to or is smaller than 64 due to a memory allocation failure in blk_alloc_zones(). With such a small number of zones, the required memory size for all zones descriptors fits in a single page, and the page order for alloc_pages_node() is zero. Allow this value in blk_alloc_zones() for the allocation to succeed. Fixes: bf5054569653 "block: Introduce blk_revalidate_disk_zones()" Reviewed-by: Damien Le Moal Signed-off-by: Shin'ichiro Kawasaki Signed-off-by: Jens Axboe --- block/blk-zoned.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/block/blk-zoned.c b/block/blk-zoned.c index 13ba2011a306..a327bef07642 100644 --- a/block/blk-zoned.c +++ b/block/blk-zoned.c @@ -378,7 +378,7 @@ static struct blk_zone *blk_alloc_zones(int node, unsigned int *nr_zones) struct page *page; int order; - for (order = get_order(size); order > 0; order--) { + for (order = get_order(size); order >= 0; order--) { page = alloc_pages_node(node, GFP_NOIO | __GFP_ZERO, order); if (page) { *nr_zones = min_t(unsigned int, *nr_zones, -- cgit v1.2.3 From 2bd61abead58c82714a1f6fa6beb0fd0df6a6d13 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Thu, 6 Dec 2018 15:50:38 -0800 Subject: selftests/seccomp: Remove SIGSTOP si_pid check Commit f149b3155744 ("signal: Never allocate siginfo for SIGKILL or SIGSTOP") means that the seccomp selftest cannot check si_pid under SIGSTOP anymore. Since it's believed[1] there are no other userspace things depending on the old behavior, this removes the behavioral check in the selftest, since it's more a "extra" sanity check (which turns out, maybe, not to have been useful to test). [1] https://lkml.kernel.org/r/CAGXu5jJaZAOzP1qFz66tYrtbuywqb+UN2SOA1VLHpCCOiYvYeg@mail.gmail.com Reported-by: Tycho Andersen Suggested-by: Eric W. Biederman Signed-off-by: Kees Cook Signed-off-by: Shuah Khan --- tools/testing/selftests/seccomp/seccomp_bpf.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c index e1473234968d..c9a2abf8be1b 100644 --- a/tools/testing/selftests/seccomp/seccomp_bpf.c +++ b/tools/testing/selftests/seccomp/seccomp_bpf.c @@ -2731,9 +2731,14 @@ TEST(syscall_restart) ASSERT_EQ(child_pid, waitpid(child_pid, &status, 0)); ASSERT_EQ(true, WIFSTOPPED(status)); ASSERT_EQ(SIGSTOP, WSTOPSIG(status)); - /* Verify signal delivery came from parent now. */ ASSERT_EQ(0, ptrace(PTRACE_GETSIGINFO, child_pid, NULL, &info)); - EXPECT_EQ(getpid(), info.si_pid); + /* + * There is no siginfo on SIGSTOP any more, so we can't verify + * signal delivery came from parent now (getpid() == info.si_pid). + * https://lkml.kernel.org/r/CAGXu5jJaZAOzP1qFz66tYrtbuywqb+UN2SOA1VLHpCCOiYvYeg@mail.gmail.com + * At least verify the SIGSTOP via PTRACE_GETSIGINFO. + */ + EXPECT_EQ(SIGSTOP, info.si_signo); /* Restart nanosleep with SIGCONT, which triggers restart_syscall. */ ASSERT_EQ(0, kill(child_pid, SIGCONT)); -- cgit v1.2.3 From fdadd04931c2d7cd294dc5b2b342863f94be53a3 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 11 Dec 2018 12:14:12 +0100 Subject: bpf: fix bpf_jit_limit knob for PAGE_SIZE >= 64K Michael and Sandipan report: Commit ede95a63b5 introduced a bpf_jit_limit tuneable to limit BPF JIT allocations. At compile time it defaults to PAGE_SIZE * 40000, and is adjusted again at init time if MODULES_VADDR is defined. For ppc64 kernels, MODULES_VADDR isn't defined, so we're stuck with the compile-time default at boot-time, which is 0x9c400000 when using 64K page size. This overflows the signed 32-bit bpf_jit_limit value: root@ubuntu:/tmp# cat /proc/sys/net/core/bpf_jit_limit -1673527296 and can cause various unexpected failures throughout the network stack. In one case `strace dhclient eth0` reported: setsockopt(5, SOL_SOCKET, SO_ATTACH_FILTER, {len=11, filter=0x105dd27f8}, 16) = -1 ENOTSUPP (Unknown error 524) and similar failures can be seen with tools like tcpdump. This doesn't always reproduce however, and I'm not sure why. The more consistent failure I've seen is an Ubuntu 18.04 KVM guest booted on a POWER9 host would time out on systemd/netplan configuring a virtio-net NIC with no noticeable errors in the logs. Given this and also given that in near future some architectures like arm64 will have a custom area for BPF JIT image allocations we should get rid of the BPF_JIT_LIMIT_DEFAULT fallback / default entirely. For 4.21, we have an overridable bpf_jit_alloc_exec(), bpf_jit_free_exec() so therefore add another overridable bpf_jit_alloc_exec_limit() helper function which returns the possible size of the memory area for deriving the default heuristic in bpf_jit_charge_init(). Like bpf_jit_alloc_exec() and bpf_jit_free_exec(), the new bpf_jit_alloc_exec_limit() assumes that module_alloc() is the default JIT memory provider, and therefore in case archs implement their custom module_alloc() we use MODULES_{END,_VADDR} for limits and otherwise for vmalloc_exec() cases like on ppc64 we use VMALLOC_{END,_START}. Additionally, for archs supporting large page sizes, we should change the sysctl to be handled as long to not run into sysctl restrictions in future. Fixes: ede95a63b5e8 ("bpf: add bpf_jit_limit knob to restrict unpriv allocations") Reported-by: Sandipan Das Reported-by: Michael Roth Signed-off-by: Daniel Borkmann Tested-by: Michael Roth Signed-off-by: Alexei Starovoitov --- include/linux/filter.h | 2 +- kernel/bpf/core.c | 21 +++++++++++++++------ net/core/sysctl_net_core.c | 20 +++++++++++++++++--- 3 files changed, 33 insertions(+), 10 deletions(-) diff --git a/include/linux/filter.h b/include/linux/filter.h index 795ff0b869bb..a8b9d90a8042 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -861,7 +861,7 @@ bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk, extern int bpf_jit_enable; extern int bpf_jit_harden; extern int bpf_jit_kallsyms; -extern int bpf_jit_limit; +extern long bpf_jit_limit; typedef void (*bpf_jit_fill_hole_t)(void *area, unsigned int size); diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index b1a3545d0ec8..b2890c268cb3 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -365,13 +365,11 @@ void bpf_prog_kallsyms_del_all(struct bpf_prog *fp) } #ifdef CONFIG_BPF_JIT -# define BPF_JIT_LIMIT_DEFAULT (PAGE_SIZE * 40000) - /* All BPF JIT sysctl knobs here. */ int bpf_jit_enable __read_mostly = IS_BUILTIN(CONFIG_BPF_JIT_ALWAYS_ON); int bpf_jit_harden __read_mostly; int bpf_jit_kallsyms __read_mostly; -int bpf_jit_limit __read_mostly = BPF_JIT_LIMIT_DEFAULT; +long bpf_jit_limit __read_mostly; static __always_inline void bpf_get_prog_addr_region(const struct bpf_prog *prog, @@ -580,16 +578,27 @@ int bpf_get_kallsym(unsigned int symnum, unsigned long *value, char *type, static atomic_long_t bpf_jit_current; +/* Can be overridden by an arch's JIT compiler if it has a custom, + * dedicated BPF backend memory area, or if neither of the two + * below apply. + */ +u64 __weak bpf_jit_alloc_exec_limit(void) +{ #if defined(MODULES_VADDR) + return MODULES_END - MODULES_VADDR; +#else + return VMALLOC_END - VMALLOC_START; +#endif +} + static int __init bpf_jit_charge_init(void) { /* Only used as heuristic here to derive limit. */ - bpf_jit_limit = min_t(u64, round_up((MODULES_END - MODULES_VADDR) >> 2, - PAGE_SIZE), INT_MAX); + bpf_jit_limit = min_t(u64, round_up(bpf_jit_alloc_exec_limit() >> 2, + PAGE_SIZE), LONG_MAX); return 0; } pure_initcall(bpf_jit_charge_init); -#endif static int bpf_jit_charge_modmem(u32 pages) { diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 37b4667128a3..d67ec17f2cc8 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -28,6 +28,8 @@ static int two __maybe_unused = 2; static int min_sndbuf = SOCK_MIN_SNDBUF; static int min_rcvbuf = SOCK_MIN_RCVBUF; static int max_skb_frags = MAX_SKB_FRAGS; +static long long_one __maybe_unused = 1; +static long long_max __maybe_unused = LONG_MAX; static int net_msg_warn; /* Unused, but still a sysctl */ @@ -289,6 +291,17 @@ proc_dointvec_minmax_bpf_restricted(struct ctl_table *table, int write, return proc_dointvec_minmax(table, write, buffer, lenp, ppos); } + +static int +proc_dolongvec_minmax_bpf_restricted(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + return proc_doulongvec_minmax(table, write, buffer, lenp, ppos); +} #endif static struct ctl_table net_core_table[] = { @@ -398,10 +411,11 @@ static struct ctl_table net_core_table[] = { { .procname = "bpf_jit_limit", .data = &bpf_jit_limit, - .maxlen = sizeof(int), + .maxlen = sizeof(long), .mode = 0600, - .proc_handler = proc_dointvec_minmax_bpf_restricted, - .extra1 = &one, + .proc_handler = proc_dolongvec_minmax_bpf_restricted, + .extra1 = &long_one, + .extra2 = &long_max, }, #endif { -- cgit v1.2.3 From ee28b30cbbe0b490f52ba222c9d392b99581545e Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Sun, 9 Dec 2018 22:05:11 +0100 Subject: r8169: fix crash if CONFIG_DEBUG_SHIRQ is enabled If CONFIG_DEBUG_SHIRQ is enabled __free_irq() intentionally fires a spurious interrupt. This interrupt causes a crash because tp->dev->phydev is NULL at that time. Fixes: 38caff5a445b ("r8169: handle all interrupt events in the hard irq handler") Signed-off-by: Heiner Kallweit Signed-off-by: David S. Miller --- drivers/net/ethernet/realtek/r8169.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c index 1fd01688d37b..209566f8097b 100644 --- a/drivers/net/ethernet/realtek/r8169.c +++ b/drivers/net/ethernet/realtek/r8169.c @@ -6469,7 +6469,7 @@ static irqreturn_t rtl8169_interrupt(int irq, void *dev_instance) goto out; } - if (status & LinkChg) + if (status & LinkChg && tp->dev->phydev) phy_mac_interrupt(tp->dev->phydev); if (unlikely(status & RxFIFOOver && -- cgit v1.2.3 From 970a5ee41c72df46e3b0f307528c7d8ef7734a2e Mon Sep 17 00:00:00 2001 From: Ben Skeggs Date: Wed, 12 Dec 2018 16:51:17 +1000 Subject: drm/nouveau/kms/nv50-: also flush fb writes when rewinding push buffer Should hopefully fix a regression some people have been seeing since EVO push buffers were moved to VRAM by default on Pascal GPUs. Fixes: d00ddd9da ("drm/nouveau/kms/nv50-: allocate push buffers in vidmem on pascal") Signed-off-by: Ben Skeggs Cc: # 4.19+ --- drivers/gpu/drm/nouveau/dispnv50/disp.c | 29 ++++++++++++++++++----------- 1 file changed, 18 insertions(+), 11 deletions(-) diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c index 5f163a025e89..03e3ce9e6f28 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/disp.c +++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c @@ -198,6 +198,22 @@ nv50_dmac_create(struct nvif_device *device, struct nvif_object *disp, /****************************************************************************** * EVO channel helpers *****************************************************************************/ +static void +evo_flush(struct nv50_dmac *dmac) +{ + /* Push buffer fetches are not coherent with BAR1, we need to ensure + * writes have been flushed right through to VRAM before writing PUT. + */ + if (dmac->push.type & NVIF_MEM_VRAM) { + struct nvif_device *device = dmac->base.device; + nvif_wr32(&device->object, 0x070000, 0x00000001); + nvif_msec(device, 2000, + if (!(nvif_rd32(&device->object, 0x070000) & 0x00000002)) + break; + ); + } +} + u32 * evo_wait(struct nv50_dmac *evoc, int nr) { @@ -208,6 +224,7 @@ evo_wait(struct nv50_dmac *evoc, int nr) mutex_lock(&dmac->lock); if (put + nr >= (PAGE_SIZE / 4) - 8) { dmac->ptr[put] = 0x20000000; + evo_flush(dmac); nvif_wr32(&dmac->base.user, 0x0000, 0x00000000); if (nvif_msec(device, 2000, @@ -230,17 +247,7 @@ evo_kick(u32 *push, struct nv50_dmac *evoc) { struct nv50_dmac *dmac = evoc; - /* Push buffer fetches are not coherent with BAR1, we need to ensure - * writes have been flushed right through to VRAM before writing PUT. - */ - if (dmac->push.type & NVIF_MEM_VRAM) { - struct nvif_device *device = dmac->base.device; - nvif_wr32(&device->object, 0x070000, 0x00000001); - nvif_msec(device, 2000, - if (!(nvif_rd32(&device->object, 0x070000) & 0x00000002)) - break; - ); - } + evo_flush(dmac); nvif_wr32(&dmac->base.user, 0x0000, (push - dmac->ptr) << 2); mutex_unlock(&dmac->lock); -- cgit v1.2.3 From 24199c5436f267399afed0c4f1f57663c0408f57 Mon Sep 17 00:00:00 2001 From: Lyude Paul Date: Tue, 11 Dec 2018 18:56:20 -0500 Subject: drm/nouveau/kms: Fix memory leak in nv50_mstm_del() Noticed this while working on redoing the reference counting scheme in the DP MST helpers. Nouveau doesn't attempt to call drm_dp_mst_topology_mgr_destroy() at all, which leaves it leaking all of the resources for drm_dp_mst_topology_mgr and it's children mstbs+ports. Fixes: f479c0ba4a17 ("drm/nouveau/kms/nv50: initial support for DP 1.2 multi-stream") Signed-off-by: Lyude Paul Cc: # v4.10+ Signed-off-by: Ben Skeggs --- drivers/gpu/drm/nouveau/dispnv50/disp.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c index 03e3ce9e6f28..b7fc471056ad 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/disp.c +++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c @@ -1264,6 +1264,7 @@ nv50_mstm_del(struct nv50_mstm **pmstm) { struct nv50_mstm *mstm = *pmstm; if (mstm) { + drm_dp_mst_topology_mgr_destroy(&mstm->mgr); kfree(*pmstm); *pmstm = NULL; } -- cgit v1.2.3 From cf66b8a0ba142fbd1bf10ac8f3ae92d1b0cb7b8f Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Thu, 6 Dec 2018 08:44:31 +0000 Subject: drm/i915/execlists: Apply a full mb before execution for Braswell Braswell is really picky about having our writes posted to memory before we execute or else the GPU may see stale values. A wmb() is insufficient as it only ensures the writes are visible to other cores, we need a full mb() to ensure the writes are in memory and visible to the GPU. The most frequent failure in flushing before execution is that we see stale PTE values and execute the wrong pages. References: 987abd5c62f9 ("drm/i915/execlists: Force write serialisation into context image vs execution") Signed-off-by: Chris Wilson Cc: Mika Kuoppala Cc: Tvrtko Ursulin Cc: Joonas Lahtinen Cc: stable@vger.kernel.org Reviewed-by: Tvrtko Ursulin Link: https://patchwork.freedesktop.org/patch/msgid/20181206084431.9805-3-chris@chris-wilson.co.uk (cherry picked from commit 490b8c65b9db45896769e1095e78725775f47b3e) Signed-off-by: Joonas Lahtinen --- drivers/gpu/drm/i915/intel_lrc.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c index 4acb24c90c68..e2cf4f750c66 100644 --- a/drivers/gpu/drm/i915/intel_lrc.c +++ b/drivers/gpu/drm/i915/intel_lrc.c @@ -442,8 +442,13 @@ static u64 execlists_update_context(struct i915_request *rq) * may not be visible to the HW prior to the completion of the UC * register write and that we may begin execution from the context * before its image is complete leading to invalid PD chasing. + * + * Furthermore, Braswell, at least, wants a full mb to be sure that + * the writes are coherent in memory (visible to the GPU) prior to + * execution, and not just visible to other CPUs (as is the result of + * wmb). */ - wmb(); + mb(); return ce->lrc_desc; } -- cgit v1.2.3 From fe78742d7f84e3803b760cdbb1ddbdedfca9640b Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Tue, 4 Dec 2018 14:15:16 +0000 Subject: drm/i915: Allocate a common scratch page Currently we allocate a scratch page for each engine, but since we only ever write into it for post-sync operations, it is not exposed to userspace nor do we care for coherency. As we then do not care about its contents, we can use one page for all, reducing our allocations and avoid complications by not assuming per-engine isolation. For later use, it simplifies engine initialisation (by removing the allocation that required struct_mutex!) and means that we can always rely on there being a scratch page. v2: Check that we allocated a large enough scratch for I830 w/a Fixes: 06e562e7f515 ("drm/i915/ringbuffer: Delay after EMIT_INVALIDATE for gen4/gen5") # v4.18.20 Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=108850 Signed-off-by: Chris Wilson Cc: Tvrtko Ursulin Cc: Mika Kuoppala Reviewed-by: Mika Kuoppala Link: https://patchwork.freedesktop.org/patch/msgid/20181204141522.13640-1-chris@chris-wilson.co.uk Cc: Joonas Lahtinen Cc: # v4.18.20+ (cherry picked from commit 5179749925933575a67f9d8f16d0cc204f98a29f) [Joonas: Use new function in gen9_init_indirectctx_bb too] Signed-off-by: Joonas Lahtinen --- drivers/gpu/drm/i915/i915_drv.h | 7 +++++ drivers/gpu/drm/i915/i915_gem.c | 50 ++++++++++++++++++++++++++++++++- drivers/gpu/drm/i915/i915_gpu_error.c | 2 +- drivers/gpu/drm/i915/intel_engine_cs.c | 42 --------------------------- drivers/gpu/drm/i915/intel_lrc.c | 19 ++++--------- drivers/gpu/drm/i915/intel_ringbuffer.c | 37 ++++++++---------------- drivers/gpu/drm/i915/intel_ringbuffer.h | 5 ---- 7 files changed, 75 insertions(+), 87 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 1331cde79c2e..872a2e159a5f 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -2150,6 +2150,8 @@ struct drm_i915_private { struct delayed_work idle_work; ktime_t last_init_time; + + struct i915_vma *scratch; } gt; /* perform PHY state sanity checks? */ @@ -3872,4 +3874,9 @@ static inline int intel_hws_csb_write_index(struct drm_i915_private *i915) return I915_HWS_CSB_WRITE_INDEX; } +static inline u32 i915_scratch_offset(const struct drm_i915_private *i915) +{ + return i915_ggtt_offset(i915->gt.scratch); +} + #endif diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index ba371712c560..6ae9a6080cc8 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -5500,6 +5500,44 @@ err_active: goto out_ctx; } +static int +i915_gem_init_scratch(struct drm_i915_private *i915, unsigned int size) +{ + struct drm_i915_gem_object *obj; + struct i915_vma *vma; + int ret; + + obj = i915_gem_object_create_stolen(i915, size); + if (!obj) + obj = i915_gem_object_create_internal(i915, size); + if (IS_ERR(obj)) { + DRM_ERROR("Failed to allocate scratch page\n"); + return PTR_ERR(obj); + } + + vma = i915_vma_instance(obj, &i915->ggtt.vm, NULL); + if (IS_ERR(vma)) { + ret = PTR_ERR(vma); + goto err_unref; + } + + ret = i915_vma_pin(vma, 0, 0, PIN_GLOBAL | PIN_HIGH); + if (ret) + goto err_unref; + + i915->gt.scratch = vma; + return 0; + +err_unref: + i915_gem_object_put(obj); + return ret; +} + +static void i915_gem_fini_scratch(struct drm_i915_private *i915) +{ + i915_vma_unpin_and_release(&i915->gt.scratch, 0); +} + int i915_gem_init(struct drm_i915_private *dev_priv) { int ret; @@ -5546,12 +5584,19 @@ int i915_gem_init(struct drm_i915_private *dev_priv) goto err_unlock; } - ret = i915_gem_contexts_init(dev_priv); + ret = i915_gem_init_scratch(dev_priv, + IS_GEN2(dev_priv) ? SZ_256K : PAGE_SIZE); if (ret) { GEM_BUG_ON(ret == -EIO); goto err_ggtt; } + ret = i915_gem_contexts_init(dev_priv); + if (ret) { + GEM_BUG_ON(ret == -EIO); + goto err_scratch; + } + ret = intel_engines_init(dev_priv); if (ret) { GEM_BUG_ON(ret == -EIO); @@ -5624,6 +5669,8 @@ err_pm: err_context: if (ret != -EIO) i915_gem_contexts_fini(dev_priv); +err_scratch: + i915_gem_fini_scratch(dev_priv); err_ggtt: err_unlock: intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL); @@ -5675,6 +5722,7 @@ void i915_gem_fini(struct drm_i915_private *dev_priv) intel_uc_fini(dev_priv); i915_gem_cleanup_engines(dev_priv); i915_gem_contexts_fini(dev_priv); + i915_gem_fini_scratch(dev_priv); mutex_unlock(&dev_priv->drm.struct_mutex); intel_wa_list_free(&dev_priv->gt_wa_list); diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c index 3eb33e000d6f..db4128d6c09b 100644 --- a/drivers/gpu/drm/i915/i915_gpu_error.c +++ b/drivers/gpu/drm/i915/i915_gpu_error.c @@ -1495,7 +1495,7 @@ static void gem_record_rings(struct i915_gpu_state *error) if (HAS_BROKEN_CS_TLB(i915)) ee->wa_batchbuffer = i915_error_object_create(i915, - engine->scratch); + i915->gt.scratch); request_record_user_bo(request, ee); ee->ctx = diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c index cdfa6b21cbff..76b5f94ea6cb 100644 --- a/drivers/gpu/drm/i915/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/intel_engine_cs.c @@ -490,46 +490,6 @@ void intel_engine_setup_common(struct intel_engine_cs *engine) intel_engine_init_cmd_parser(engine); } -int intel_engine_create_scratch(struct intel_engine_cs *engine, - unsigned int size) -{ - struct drm_i915_gem_object *obj; - struct i915_vma *vma; - int ret; - - WARN_ON(engine->scratch); - - obj = i915_gem_object_create_stolen(engine->i915, size); - if (!obj) - obj = i915_gem_object_create_internal(engine->i915, size); - if (IS_ERR(obj)) { - DRM_ERROR("Failed to allocate scratch page\n"); - return PTR_ERR(obj); - } - - vma = i915_vma_instance(obj, &engine->i915->ggtt.vm, NULL); - if (IS_ERR(vma)) { - ret = PTR_ERR(vma); - goto err_unref; - } - - ret = i915_vma_pin(vma, 0, 0, PIN_GLOBAL | PIN_HIGH); - if (ret) - goto err_unref; - - engine->scratch = vma; - return 0; - -err_unref: - i915_gem_object_put(obj); - return ret; -} - -void intel_engine_cleanup_scratch(struct intel_engine_cs *engine) -{ - i915_vma_unpin_and_release(&engine->scratch, 0); -} - static void cleanup_status_page(struct intel_engine_cs *engine) { if (HWS_NEEDS_PHYSICAL(engine->i915)) { @@ -704,8 +664,6 @@ void intel_engine_cleanup_common(struct intel_engine_cs *engine) { struct drm_i915_private *i915 = engine->i915; - intel_engine_cleanup_scratch(engine); - cleanup_status_page(engine); intel_engine_fini_breadcrumbs(engine); diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c index e2cf4f750c66..58d1d3d47dd3 100644 --- a/drivers/gpu/drm/i915/intel_lrc.c +++ b/drivers/gpu/drm/i915/intel_lrc.c @@ -1448,9 +1448,10 @@ static int execlists_request_alloc(struct i915_request *request) static u32 * gen8_emit_flush_coherentl3_wa(struct intel_engine_cs *engine, u32 *batch) { + /* NB no one else is allowed to scribble over scratch + 256! */ *batch++ = MI_STORE_REGISTER_MEM_GEN8 | MI_SRM_LRM_GLOBAL_GTT; *batch++ = i915_mmio_reg_offset(GEN8_L3SQCREG4); - *batch++ = i915_ggtt_offset(engine->scratch) + 256; + *batch++ = i915_scratch_offset(engine->i915) + 256; *batch++ = 0; *batch++ = MI_LOAD_REGISTER_IMM(1); @@ -1464,7 +1465,7 @@ gen8_emit_flush_coherentl3_wa(struct intel_engine_cs *engine, u32 *batch) *batch++ = MI_LOAD_REGISTER_MEM_GEN8 | MI_SRM_LRM_GLOBAL_GTT; *batch++ = i915_mmio_reg_offset(GEN8_L3SQCREG4); - *batch++ = i915_ggtt_offset(engine->scratch) + 256; + *batch++ = i915_scratch_offset(engine->i915) + 256; *batch++ = 0; return batch; @@ -1501,7 +1502,7 @@ static u32 *gen8_init_indirectctx_bb(struct intel_engine_cs *engine, u32 *batch) PIPE_CONTROL_GLOBAL_GTT_IVB | PIPE_CONTROL_CS_STALL | PIPE_CONTROL_QW_WRITE, - i915_ggtt_offset(engine->scratch) + + i915_scratch_offset(engine->i915) + 2 * CACHELINE_BYTES); *batch++ = MI_ARB_ON_OFF | MI_ARB_ENABLE; @@ -1578,7 +1579,7 @@ static u32 *gen9_init_indirectctx_bb(struct intel_engine_cs *engine, u32 *batch) PIPE_CONTROL_GLOBAL_GTT_IVB | PIPE_CONTROL_CS_STALL | PIPE_CONTROL_QW_WRITE, - i915_ggtt_offset(engine->scratch) + i915_scratch_offset(engine->i915) + 2 * CACHELINE_BYTES); } @@ -2146,7 +2147,7 @@ static int gen8_emit_flush_render(struct i915_request *request, { struct intel_engine_cs *engine = request->engine; u32 scratch_addr = - i915_ggtt_offset(engine->scratch) + 2 * CACHELINE_BYTES; + i915_scratch_offset(engine->i915) + 2 * CACHELINE_BYTES; bool vf_flush_wa = false, dc_flush_wa = false; u32 *cs, flags = 0; int len; @@ -2483,10 +2484,6 @@ int logical_render_ring_init(struct intel_engine_cs *engine) if (ret) return ret; - ret = intel_engine_create_scratch(engine, PAGE_SIZE); - if (ret) - goto err_cleanup_common; - ret = intel_init_workaround_bb(engine); if (ret) { /* @@ -2501,10 +2498,6 @@ int logical_render_ring_init(struct intel_engine_cs *engine) intel_engine_init_workarounds(engine); return 0; - -err_cleanup_common: - intel_engine_cleanup_common(engine); - return ret; } int logical_xcs_ring_init(struct intel_engine_cs *engine) diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c index 187bb0ceb4ac..2046f108d1cc 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.c +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c @@ -150,8 +150,7 @@ gen4_render_ring_flush(struct i915_request *rq, u32 mode) */ if (mode & EMIT_INVALIDATE) { *cs++ = GFX_OP_PIPE_CONTROL(4) | PIPE_CONTROL_QW_WRITE; - *cs++ = i915_ggtt_offset(rq->engine->scratch) | - PIPE_CONTROL_GLOBAL_GTT; + *cs++ = i915_scratch_offset(rq->i915) | PIPE_CONTROL_GLOBAL_GTT; *cs++ = 0; *cs++ = 0; @@ -159,8 +158,7 @@ gen4_render_ring_flush(struct i915_request *rq, u32 mode) *cs++ = MI_FLUSH; *cs++ = GFX_OP_PIPE_CONTROL(4) | PIPE_CONTROL_QW_WRITE; - *cs++ = i915_ggtt_offset(rq->engine->scratch) | - PIPE_CONTROL_GLOBAL_GTT; + *cs++ = i915_scratch_offset(rq->i915) | PIPE_CONTROL_GLOBAL_GTT; *cs++ = 0; *cs++ = 0; } @@ -212,8 +210,7 @@ gen4_render_ring_flush(struct i915_request *rq, u32 mode) static int intel_emit_post_sync_nonzero_flush(struct i915_request *rq) { - u32 scratch_addr = - i915_ggtt_offset(rq->engine->scratch) + 2 * CACHELINE_BYTES; + u32 scratch_addr = i915_scratch_offset(rq->i915) + 2 * CACHELINE_BYTES; u32 *cs; cs = intel_ring_begin(rq, 6); @@ -246,8 +243,7 @@ intel_emit_post_sync_nonzero_flush(struct i915_request *rq) static int gen6_render_ring_flush(struct i915_request *rq, u32 mode) { - u32 scratch_addr = - i915_ggtt_offset(rq->engine->scratch) + 2 * CACHELINE_BYTES; + u32 scratch_addr = i915_scratch_offset(rq->i915) + 2 * CACHELINE_BYTES; u32 *cs, flags = 0; int ret; @@ -316,8 +312,7 @@ gen7_render_ring_cs_stall_wa(struct i915_request *rq) static int gen7_render_ring_flush(struct i915_request *rq, u32 mode) { - u32 scratch_addr = - i915_ggtt_offset(rq->engine->scratch) + 2 * CACHELINE_BYTES; + u32 scratch_addr = i915_scratch_offset(rq->i915) + 2 * CACHELINE_BYTES; u32 *cs, flags = 0; /* @@ -971,7 +966,7 @@ i965_emit_bb_start(struct i915_request *rq, } /* Just userspace ABI convention to limit the wa batch bo to a resonable size */ -#define I830_BATCH_LIMIT (256*1024) +#define I830_BATCH_LIMIT SZ_256K #define I830_TLB_ENTRIES (2) #define I830_WA_SIZE max(I830_TLB_ENTRIES*4096, I830_BATCH_LIMIT) static int @@ -979,7 +974,9 @@ i830_emit_bb_start(struct i915_request *rq, u64 offset, u32 len, unsigned int dispatch_flags) { - u32 *cs, cs_offset = i915_ggtt_offset(rq->engine->scratch); + u32 *cs, cs_offset = i915_scratch_offset(rq->i915); + + GEM_BUG_ON(rq->i915->gt.scratch->size < I830_WA_SIZE); cs = intel_ring_begin(rq, 6); if (IS_ERR(cs)) @@ -1437,7 +1434,6 @@ static int intel_init_ring_buffer(struct intel_engine_cs *engine) { struct i915_timeline *timeline; struct intel_ring *ring; - unsigned int size; int err; intel_engine_setup_common(engine); @@ -1462,21 +1458,12 @@ static int intel_init_ring_buffer(struct intel_engine_cs *engine) GEM_BUG_ON(engine->buffer); engine->buffer = ring; - size = PAGE_SIZE; - if (HAS_BROKEN_CS_TLB(engine->i915)) - size = I830_WA_SIZE; - err = intel_engine_create_scratch(engine, size); - if (err) - goto err_unpin; - err = intel_engine_init_common(engine); if (err) - goto err_scratch; + goto err_unpin; return 0; -err_scratch: - intel_engine_cleanup_scratch(engine); err_unpin: intel_ring_unpin(ring); err_ring: @@ -1550,7 +1537,7 @@ static int flush_pd_dir(struct i915_request *rq) /* Stall until the page table load is complete */ *cs++ = MI_STORE_REGISTER_MEM | MI_SRM_LRM_GLOBAL_GTT; *cs++ = i915_mmio_reg_offset(RING_PP_DIR_BASE(engine)); - *cs++ = i915_ggtt_offset(engine->scratch); + *cs++ = i915_scratch_offset(rq->i915); *cs++ = MI_NOOP; intel_ring_advance(rq, cs); @@ -1659,7 +1646,7 @@ static inline int mi_set_context(struct i915_request *rq, u32 flags) /* Insert a delay before the next switch! */ *cs++ = MI_STORE_REGISTER_MEM | MI_SRM_LRM_GLOBAL_GTT; *cs++ = i915_mmio_reg_offset(last_reg); - *cs++ = i915_ggtt_offset(engine->scratch); + *cs++ = i915_scratch_offset(rq->i915); *cs++ = MI_NOOP; } *cs++ = MI_ARB_ON_OFF | MI_ARB_ENABLE; diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h index 04c61307f4d1..767a7192c969 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.h +++ b/drivers/gpu/drm/i915/intel_ringbuffer.h @@ -442,7 +442,6 @@ struct intel_engine_cs { struct intel_hw_status_page status_page; struct i915_ctx_workarounds wa_ctx; struct i915_wa_list wa_list; - struct i915_vma *scratch; u32 irq_keep_mask; /* always keep these interrupts */ u32 irq_enable_mask; /* bitmask to enable ring interrupt */ @@ -900,10 +899,6 @@ void intel_engine_setup_common(struct intel_engine_cs *engine); int intel_engine_init_common(struct intel_engine_cs *engine); void intel_engine_cleanup_common(struct intel_engine_cs *engine); -int intel_engine_create_scratch(struct intel_engine_cs *engine, - unsigned int size); -void intel_engine_cleanup_scratch(struct intel_engine_cs *engine); - int intel_init_render_ring_buffer(struct intel_engine_cs *engine); int intel_init_bsd_ring_buffer(struct intel_engine_cs *engine); int intel_init_blt_ring_buffer(struct intel_engine_cs *engine); -- cgit v1.2.3 From 5b2e31201c268c2331a209af799d667619216d40 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Fri, 7 Dec 2018 13:40:37 +0000 Subject: drm/i915: Flush GPU relocs harder for gen3 Adding an extra MI_STORE_DWORD_IMM to the gpu relocation path for gen3 was good, but still not good enough. To survive 24+ hours under test we needed to perform not one, not two but three extra store-dw. Doing so for each GPU relocation was a little unsightly and since we need to worry about userspace hitting the same issues, we should apply the dummy store-dw into the EMIT_FLUSH. Fixes: 7dd4f6729f92 ("drm/i915: Async GPU relocation processing") References: 7fa28e146994 ("drm/i915: Write GPU relocs harder with gen3") Testcase: igt/gem_tiled_fence_blits # blb/pnv Signed-off-by: Chris Wilson Cc: Joonas Lahtinen Reviewed-by: Joonas Lahtinen Link: https://patchwork.freedesktop.org/patch/msgid/20181207134037.11848-1-chris@chris-wilson.co.uk (cherry picked from commit a889580c087a9cf91fddb3832ece284174214183) Signed-off-by: Joonas Lahtinen --- drivers/gpu/drm/i915/i915_gem_execbuffer.c | 7 +------ drivers/gpu/drm/i915/intel_ringbuffer.c | 15 ++++++++++++--- 2 files changed, 13 insertions(+), 9 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c index d4fac09095f8..1aaccbe7e1de 100644 --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c @@ -1268,7 +1268,7 @@ relocate_entry(struct i915_vma *vma, else if (gen >= 4) len = 4; else - len = 6; + len = 3; batch = reloc_gpu(eb, vma, len); if (IS_ERR(batch)) @@ -1309,11 +1309,6 @@ relocate_entry(struct i915_vma *vma, *batch++ = MI_STORE_DWORD_IMM | MI_MEM_VIRTUAL; *batch++ = addr; *batch++ = target_offset; - - /* And again for good measure (blb/pnv) */ - *batch++ = MI_STORE_DWORD_IMM | MI_MEM_VIRTUAL; - *batch++ = addr; - *batch++ = target_offset; } goto out; diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c index 2046f108d1cc..1f8d2a66c791 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.c +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c @@ -69,19 +69,28 @@ unsigned int intel_ring_update_space(struct intel_ring *ring) static int gen2_render_ring_flush(struct i915_request *rq, u32 mode) { + unsigned int num_store_dw; u32 cmd, *cs; cmd = MI_FLUSH; - + num_store_dw = 0; if (mode & EMIT_INVALIDATE) cmd |= MI_READ_FLUSH; + if (mode & EMIT_FLUSH) + num_store_dw = 4; - cs = intel_ring_begin(rq, 2); + cs = intel_ring_begin(rq, 2 + 3 * num_store_dw); if (IS_ERR(cs)) return PTR_ERR(cs); *cs++ = cmd; - *cs++ = MI_NOOP; + while (num_store_dw--) { + *cs++ = MI_STORE_DWORD_IMM | MI_MEM_VIRTUAL; + *cs++ = i915_scratch_offset(rq->i915); + *cs++ = 0; + } + *cs++ = MI_FLUSH | MI_NO_WRITE_FLUSH; + intel_ring_advance(rq, cs); return 0; -- cgit v1.2.3 From e06d45d8c165a0b1a7aaa1b794c78d2db911c8f6 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Thu, 4 Oct 2018 18:49:53 +0100 Subject: drm/vmwgfx: remove redundant return ret statement The return statement is redundant as there is a return statement immediately before it so we have dead code that can be removed. Also remove the unused declaration of ret. Detected by CoverityScan, CID#1473793 ("Structurally dead code") Signed-off-by: Colin Ian King Reviewed-by: Thomas Hellstrom Signed-off-by: Thomas Hellstrom --- drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c index 5a6b70ba137a..260650bb5560 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c @@ -1738,7 +1738,6 @@ static int vmw_cmd_check_define_gmrfb(struct vmw_private *dev_priv, void *buf) { struct vmw_buffer_object *vmw_bo; - int ret; struct { uint32_t header; @@ -1748,7 +1747,6 @@ static int vmw_cmd_check_define_gmrfb(struct vmw_private *dev_priv, return vmw_translate_guest_ptr(dev_priv, sw_context, &cmd->body.ptr, &vmw_bo); - return ret; } -- cgit v1.2.3 From 2af6c0703d75fc3ff2e6de19b4b3adab96acc12d Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Wed, 12 Dec 2018 09:39:54 -0500 Subject: dm thin: bump target version Decoupled version bump from commit f6c367585d0 ("dm thin: send event about thin-pool state change _after_ making it") because version bumps just create conflicts when backporting to the stable trees. Signed-off-by: Mike Snitzer --- drivers/md/dm-thin.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index 53f8d03f76f7..dadd9696340c 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -4025,7 +4025,7 @@ static struct target_type pool_target = { .name = "thin-pool", .features = DM_TARGET_SINGLETON | DM_TARGET_ALWAYS_WRITEABLE | DM_TARGET_IMMUTABLE, - .version = {1, 20, 0}, + .version = {1, 21, 0}, .module = THIS_MODULE, .ctr = pool_ctr, .dtr = pool_dtr, @@ -4399,7 +4399,7 @@ static void thin_io_hints(struct dm_target *ti, struct queue_limits *limits) static struct target_type thin_target = { .name = "thin", - .version = {1, 20, 0}, + .version = {1, 21, 0}, .module = THIS_MODULE, .ctr = thin_ctr, .dtr = thin_dtr, -- cgit v1.2.3 From 70a7444c550a75584ffcfae95267058817eff6a7 Mon Sep 17 00:00:00 2001 From: Jörgen Storvist Date: Tue, 11 Dec 2018 18:28:28 +0100 Subject: USB: serial: option: add GosunCn ZTE WeLink ME3630 Added USB serial option driver support for GosunCn ZTE WeLink ME3630 series cellular modules for USB modes ECM/NCM and MBIM. usb-devices output MBIM mode: T: Bus=01 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#= 10 Spd=480 MxCh= 0 D: Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs= 1 P: Vendor=19d2 ProdID=0602 Rev=03.18 S: Manufacturer=Android S: Product=Android S: SerialNumber= C: #Ifs= 5 Cfg#= 1 Atr=a0 MxPwr=500mA I: If#= 0 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option I: If#= 1 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option I: If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option I: If#= 3 Alt= 0 #EPs= 1 Cls=02(commc) Sub=0e Prot=00 Driver=cdc_mbim I: If#= 4 Alt= 1 #EPs= 2 Cls=0a(data ) Sub=00 Prot=02 Driver=cdc_mbim usb-devices output ECM/NCM mode: T: Bus=01 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#= 11 Spd=480 MxCh= 0 D: Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs= 1 P: Vendor=19d2 ProdID=1476 Rev=03.18 S: Manufacturer=Android S: Product=Android S: SerialNumber= C: #Ifs= 5 Cfg#= 1 Atr=a0 MxPwr=500mA I: If#= 0 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option I: If#= 1 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option I: If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option I: If#= 3 Alt= 0 #EPs= 1 Cls=02(commc) Sub=06 Prot=00 Driver=cdc_ether I: If#= 4 Alt= 1 #EPs= 2 Cls=0a(data ) Sub=00 Prot=00 Driver=cdc_ether Signed-off-by: Jörgen Storvist Cc: stable Signed-off-by: Johan Hovold --- drivers/usb/serial/option.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 642624fc75ad..f7b96f15d938 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -1328,6 +1328,7 @@ static const struct usb_device_id option_ids[] = { .driver_info = RSVD(4) }, { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0414, 0xff, 0xff, 0xff) }, { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0417, 0xff, 0xff, 0xff) }, + { USB_DEVICE_INTERFACE_CLASS(ZTE_VENDOR_ID, 0x0602, 0xff) }, /* GosunCn ZTE WeLink ME3630 (MBIM mode) */ { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1008, 0xff, 0xff, 0xff), .driver_info = RSVD(4) }, { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1010, 0xff, 0xff, 0xff), @@ -1531,6 +1532,7 @@ static const struct usb_device_id option_ids[] = { .driver_info = RSVD(2) }, { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1428, 0xff, 0xff, 0xff), /* Telewell TW-LTE 4G v2 */ .driver_info = RSVD(2) }, + { USB_DEVICE_INTERFACE_CLASS(ZTE_VENDOR_ID, 0x1476, 0xff) }, /* GosunCn ZTE WeLink ME3630 (ECM/NCM mode) */ { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1533, 0xff, 0xff, 0xff) }, { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1534, 0xff, 0xff, 0xff) }, { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1535, 0xff, 0xff, 0xff) }, -- cgit v1.2.3 From cc6730df08a291e51e145bc65e24ffb5e2f17ab6 Mon Sep 17 00:00:00 2001 From: Jörgen Storvist Date: Wed, 12 Dec 2018 08:39:39 +0100 Subject: USB: serial: option: add Simcom SIM7500/SIM7600 (MBIM mode) Added USB serial option driver support for Simcom SIM7500/SIM7600 series cellular modules exposing MBIM interface (VID 0x1e0e,PID 0x9003) T: Bus=01 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#= 14 Spd=480 MxCh= 0 D: Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs= 1 P: Vendor=1e0e ProdID=9003 Rev=03.18 S: Manufacturer=SimTech, Incorporated S: Product=SimTech, Incorporated S: SerialNumber=0123456789ABCDEF C: #Ifs= 7 Cfg#= 1 Atr=a0 MxPwr=500mA I: If#= 0 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option I: If#= 1 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option I: If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option I: If#= 3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option I: If#= 4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option I: If#= 5 Alt= 0 #EPs= 1 Cls=02(commc) Sub=0e Prot=00 Driver=cdc_mbim I: If#= 6 Alt= 1 #EPs= 2 Cls=0a(data ) Sub=00 Prot=02 Driver=cdc_mbim Signed-off-by: Jörgen Storvist Cc: stable Signed-off-by: Johan Hovold --- drivers/usb/serial/option.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index f7b96f15d938..53e8de5f8acd 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -1760,6 +1760,7 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(ALINK_VENDOR_ID, ALINK_PRODUCT_3GU, 0xff, 0xff, 0xff) }, { USB_DEVICE(ALINK_VENDOR_ID, SIMCOM_PRODUCT_SIM7100E), .driver_info = RSVD(5) | RSVD(6) }, + { USB_DEVICE_INTERFACE_CLASS(0x1e0e, 0x9003, 0xff) }, /* Simcom SIM7500/SIM7600 MBIM mode */ { USB_DEVICE(ALCATEL_VENDOR_ID, ALCATEL_PRODUCT_X060S_X200), .driver_info = NCTRL(0) | NCTRL(1) | RSVD(4) }, { USB_DEVICE(ALCATEL_VENDOR_ID, ALCATEL_PRODUCT_X220_X500D), -- cgit v1.2.3 From 37fbd834b4e492dc41743830cbe435f35120abd8 Mon Sep 17 00:00:00 2001 From: Mark Zhang Date: Wed, 5 Dec 2018 15:50:49 +0200 Subject: IB/core: Fix oops in netdev_next_upper_dev_rcu() When support for bonding of RoCE devices was added, there was necessarily a link between the RoCE device and the paired netdevice that was part of the bond. If you remove the mlx4_en module, that paired association is broken (the RoCE device is still present but the paired netdevice has been released). We need to account for this in is_upper_ndev_bond_master_filter() and filter out those links with a broken pairing or else we later oops in netdev_next_upper_dev_rcu(). Fixes: 408f1242d940 ("IB/core: Delete lower netdevice default GID entries in bonding scenario") Signed-off-by: Mark Zhang Reviewed-by: Parav Pandit Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford --- drivers/infiniband/core/roce_gid_mgmt.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/infiniband/core/roce_gid_mgmt.c b/drivers/infiniband/core/roce_gid_mgmt.c index 25d43c8f1c2a..558de0b9895c 100644 --- a/drivers/infiniband/core/roce_gid_mgmt.c +++ b/drivers/infiniband/core/roce_gid_mgmt.c @@ -267,6 +267,9 @@ is_upper_ndev_bond_master_filter(struct ib_device *ib_dev, u8 port, struct net_device *cookie_ndev = cookie; bool match = false; + if (!rdma_ndev) + return false; + rcu_read_lock(); if (netif_is_bond_master(cookie_ndev) && rdma_is_upper_dev_rcu(rdma_ndev, cookie_ndev)) -- cgit v1.2.3 From 676fff1a5512e7971aa9a235052d253df8f5284a Mon Sep 17 00:00:00 2001 From: Evan Quan Date: Wed, 12 Dec 2018 14:56:14 +0800 Subject: drm/amdgpu: drop fclk/gfxclk ratio setting Since this is not needed any more on the latest SMC firmware. Signed-off-by: Evan Quan Acked-by: Feifei Xu Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c index 3367dd30cdd0..3b7fce5d7258 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c @@ -130,7 +130,7 @@ static void vega20_set_default_registry_data(struct pp_hwmgr *hwmgr) data->registry_data.disable_auto_wattman = 1; data->registry_data.auto_wattman_debug = 0; data->registry_data.auto_wattman_sample_period = 100; - data->registry_data.fclk_gfxclk_ratio = 0x3F6CCCCD; + data->registry_data.fclk_gfxclk_ratio = 0; data->registry_data.auto_wattman_threshold = 50; data->registry_data.gfxoff_controlled_by_driver = 1; data->gfxoff_allowed = false; -- cgit v1.2.3 From 158daed16efb1170694e420ae06ba8ba954d82e5 Mon Sep 17 00:00:00 2001 From: Stefan Assmann Date: Tue, 4 Dec 2018 15:18:52 +0100 Subject: i40e: fix mac filter delete when setting mac address A previous commit moved the ether_addr_copy() in i40e_set_mac() before the mac filter del/add to avoid a race. However it wasn't taken into account that this alters the mac address being handed to i40e_del_mac_filter(). Also changed i40e_add_mac_filter() to operate on netdev->dev_addr, hopefully that makes the code easier to read. Fixes: 458867b2ca0c ("i40e: don't remove netdev->dev_addr when syncing uc list") Signed-off-by: Stefan Assmann Tested-by: Andrew Bowers Acked-by: Jacob Keller Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e_main.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index a3f45335437c..0e5dc74b4ef2 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -1543,17 +1543,17 @@ static int i40e_set_mac(struct net_device *netdev, void *p) netdev_info(netdev, "set new mac address %pM\n", addr->sa_data); /* Copy the address first, so that we avoid a possible race with - * .set_rx_mode(). If we copy after changing the address in the filter - * list, we might open ourselves to a narrow race window where - * .set_rx_mode could delete our dev_addr filter and prevent traffic - * from passing. + * .set_rx_mode(). + * - Remove old address from MAC filter + * - Copy new address + * - Add new address to MAC filter */ - ether_addr_copy(netdev->dev_addr, addr->sa_data); - spin_lock_bh(&vsi->mac_filter_hash_lock); i40e_del_mac_filter(vsi, netdev->dev_addr); - i40e_add_mac_filter(vsi, addr->sa_data); + ether_addr_copy(netdev->dev_addr, addr->sa_data); + i40e_add_mac_filter(vsi, netdev->dev_addr); spin_unlock_bh(&vsi->mac_filter_hash_lock); + if (vsi->type == I40E_VSI_MAIN) { i40e_status ret; -- cgit v1.2.3 From 28adac6f74ef2b3dc0bd10df9fccb2e3d3e52acc Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Mon, 10 Dec 2018 11:30:01 +0100 Subject: MAINTAINERS: Daniel for drm co-maintainer lkml and Linus gained a CoC, and it's serious this time. Which means my no 1 reason for declining to officially step up as drm maintainer is gone, and I didn't find any new good excuse. I chatted with a few people in private already, and the biggest concern is that I mislay my community hat and start running around with my intel hat only. Or some other convenient abuse of trust. That's why this patch doesn't just need a lot of acks that mean "yeah seems fine to me", but a lot of acks that mean "yeah we'll tell you when you're over the line and usurp you from that comfy chair if you don't get it". Which I think we've been done a fairly good job here at dri-devel in general, but better to be clear. Rough idea is that I'll do this for maybe 2-3 years, helping Dave figure out a group model for drm overall. And getting the tooling and infrastructure for that off the ground. Then step down again because some other shiny thing that needs chasing. Of course as plans tend to do, this one will probably pan out a bit different in reality. Cc: David Airlie Cc: Linus Torvalds Signed-off-by: Daniel Vetter Acked-by: Christian König Acked-by: Rodrigo Vivi Acked-by: Alex Deucher Acked-by: Eric Anholt Acked-by: Gerd Hoffmann Acked-by: Daniel Stone Signed-off-by: Daniel Vetter Acked-by: Neil Armstrong Acked-by: Thierry Reding Acked-by: Thomas Hellstrom Acked-by: Sean Paul Signed-off-by: Dave Airlie Link: https://patchwork.freedesktop.org/patch/msgid/20181210103001.30549-1-daniel.vetter@ffwll.ch --- MAINTAINERS | 1 + 1 file changed, 1 insertion(+) diff --git a/MAINTAINERS b/MAINTAINERS index 8119141a926f..b578b47ccc8a 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -4843,6 +4843,7 @@ F: include/uapi/drm/vmwgfx_drm.h DRM DRIVERS M: David Airlie +M: Daniel Vetter L: dri-devel@lists.freedesktop.org T: git git://anongit.freedesktop.org/drm/drm B: https://bugs.freedesktop.org/ -- cgit v1.2.3 From 2a508c64ad278d022543ec3360449c7f243eb56b Mon Sep 17 00:00:00 2001 From: Michał Mirosław Date: Tue, 4 Dec 2018 18:31:14 +0100 Subject: i40e: fix VLAN.TCI == 0 RX HW offload This fixes two bugs in hardware VLAN offload: 1. VLAN.TCI == 0 was being dropped 2. there was a race between disabling of VLAN RX feature in hardware and processing RX queue, where packets processed in this window could have their VLAN information dropped Fix moves the VLAN handling into i40e_process_skb_fields() to save on duplicated code. i40e_receive_skb() becomes trivial and so is removed. Signed-off-by: Michał Mirosław Signed-off-by: Michał Mirosław Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e_txrx.c | 31 ++++++---------------- drivers/net/ethernet/intel/i40e/i40e_txrx_common.h | 2 -- drivers/net/ethernet/intel/i40e/i40e_xsk.c | 6 +---- 3 files changed, 9 insertions(+), 30 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index aef3c89ee79c..bc6a873ec574 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -1558,24 +1558,6 @@ static bool i40e_alloc_mapped_page(struct i40e_ring *rx_ring, return true; } -/** - * i40e_receive_skb - Send a completed packet up the stack - * @rx_ring: rx ring in play - * @skb: packet to send up - * @vlan_tag: vlan tag for packet - **/ -void i40e_receive_skb(struct i40e_ring *rx_ring, - struct sk_buff *skb, u16 vlan_tag) -{ - struct i40e_q_vector *q_vector = rx_ring->q_vector; - - if ((rx_ring->netdev->features & NETIF_F_HW_VLAN_CTAG_RX) && - (vlan_tag & VLAN_VID_MASK)) - __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vlan_tag); - - napi_gro_receive(&q_vector->napi, skb); -} - /** * i40e_alloc_rx_buffers - Replace used receive buffers * @rx_ring: ring to place buffers on @@ -1812,6 +1794,13 @@ void i40e_process_skb_fields(struct i40e_ring *rx_ring, skb_record_rx_queue(skb, rx_ring->queue_index); + if (qword & BIT(I40E_RX_DESC_STATUS_L2TAG1P_SHIFT)) { + u16 vlan_tag = rx_desc->wb.qword0.lo_dword.l2tag1; + + __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), + le16_to_cpu(vlan_tag)); + } + /* modifies the skb - consumes the enet header */ skb->protocol = eth_type_trans(skb, rx_ring->netdev); } @@ -2350,7 +2339,6 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) struct i40e_rx_buffer *rx_buffer; union i40e_rx_desc *rx_desc; unsigned int size; - u16 vlan_tag; u8 rx_ptype; u64 qword; @@ -2451,11 +2439,8 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) /* populate checksum, VLAN, and protocol */ i40e_process_skb_fields(rx_ring, rx_desc, skb, rx_ptype); - vlan_tag = (qword & BIT(I40E_RX_DESC_STATUS_L2TAG1P_SHIFT)) ? - le16_to_cpu(rx_desc->wb.qword0.lo_dword.l2tag1) : 0; - i40e_trace(clean_rx_irq_rx, rx_ring, rx_desc, skb); - i40e_receive_skb(rx_ring, skb, vlan_tag); + napi_gro_receive(&rx_ring->q_vector->napi, skb); skb = NULL; /* update budget accounting */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx_common.h b/drivers/net/ethernet/intel/i40e/i40e_txrx_common.h index 09809dffe399..2c077f1c4eca 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx_common.h +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx_common.h @@ -14,8 +14,6 @@ struct i40e_rx_buffer *i40e_clean_programming_status( void i40e_process_skb_fields(struct i40e_ring *rx_ring, union i40e_rx_desc *rx_desc, struct sk_buff *skb, u8 rx_ptype); -void i40e_receive_skb(struct i40e_ring *rx_ring, - struct sk_buff *skb, u16 vlan_tag); void i40e_xdp_ring_update_tail(struct i40e_ring *xdp_ring); void i40e_update_rx_stats(struct i40e_ring *rx_ring, unsigned int total_rx_bytes, diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c index 433c8e688c78..a6ea2b249471 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c @@ -634,7 +634,6 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget) struct i40e_rx_buffer *bi; union i40e_rx_desc *rx_desc; unsigned int size; - u16 vlan_tag; u8 rx_ptype; u64 qword; @@ -717,10 +716,7 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget) rx_ptype = (qword & I40E_RXD_QW1_PTYPE_MASK) >> I40E_RXD_QW1_PTYPE_SHIFT; i40e_process_skb_fields(rx_ring, rx_desc, skb, rx_ptype); - - vlan_tag = (qword & BIT(I40E_RX_DESC_STATUS_L2TAG1P_SHIFT)) ? - le16_to_cpu(rx_desc->wb.qword0.lo_dword.l2tag1) : 0; - i40e_receive_skb(rx_ring, skb, vlan_tag); + napi_gro_receive(&rx_ring->q_vector->napi, skb); } i40e_finalize_xdp_rx(rx_ring, xdp_xmit); -- cgit v1.2.3 From 5146f95df782b0ac61abde36567e718692725c89 Mon Sep 17 00:00:00 2001 From: Hui Peng Date: Wed, 12 Dec 2018 12:42:24 +0100 Subject: USB: hso: Fix OOB memory access in hso_probe/hso_get_config_data The function hso_probe reads if_num from the USB device (as an u8) and uses it without a length check to index an array, resulting in an OOB memory read in hso_probe or hso_get_config_data. Add a length check for both locations and updated hso_probe to bail on error. This issue has been assigned CVE-2018-19985. Reported-by: Hui Peng Reported-by: Mathias Payer Signed-off-by: Hui Peng Signed-off-by: Mathias Payer Reviewed-by: Sebastian Andrzej Siewior Signed-off-by: Greg Kroah-Hartman Signed-off-by: David S. Miller --- drivers/net/usb/hso.c | 18 ++++++++++++++++-- 1 file changed, 16 insertions(+), 2 deletions(-) diff --git a/drivers/net/usb/hso.c b/drivers/net/usb/hso.c index 184c24baca15..d6916f787fce 100644 --- a/drivers/net/usb/hso.c +++ b/drivers/net/usb/hso.c @@ -2807,6 +2807,12 @@ static int hso_get_config_data(struct usb_interface *interface) return -EIO; } + /* check if we have a valid interface */ + if (if_num > 16) { + kfree(config_data); + return -EINVAL; + } + switch (config_data[if_num]) { case 0x0: result = 0; @@ -2877,10 +2883,18 @@ static int hso_probe(struct usb_interface *interface, /* Get the interface/port specification from either driver_info or from * the device itself */ - if (id->driver_info) + if (id->driver_info) { + /* if_num is controlled by the device, driver_info is a 0 terminated + * array. Make sure, the access is in bounds! */ + for (i = 0; i <= if_num; ++i) + if (((u32 *)(id->driver_info))[i] == 0) + goto exit; port_spec = ((u32 *)(id->driver_info))[if_num]; - else + } else { port_spec = hso_get_config_data(interface); + if (port_spec < 0) + goto exit; + } /* Check if we need to switch to alt interfaces prior to port * configuration */ -- cgit v1.2.3 From 800b8f637d07cc00a05e2e0d847d8d7c61745654 Mon Sep 17 00:00:00 2001 From: Michał Mirosław Date: Tue, 4 Dec 2018 18:31:15 +0100 Subject: i40e: DRY rx_ptype handling code Move rx_ptype extracting to i40e_process_skb_fields() to avoid duplicating the code. Signed-off-by: Michał Mirosław Signed-off-by: Michał Mirosław Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e_txrx.c | 12 ++++-------- drivers/net/ethernet/intel/i40e/i40e_txrx_common.h | 3 +-- drivers/net/ethernet/intel/i40e/i40e_xsk.c | 6 +----- 3 files changed, 6 insertions(+), 15 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index bc6a873ec574..d0a95424ce58 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -1775,8 +1775,7 @@ static inline void i40e_rx_hash(struct i40e_ring *ring, * other fields within the skb. **/ void i40e_process_skb_fields(struct i40e_ring *rx_ring, - union i40e_rx_desc *rx_desc, struct sk_buff *skb, - u8 rx_ptype) + union i40e_rx_desc *rx_desc, struct sk_buff *skb) { u64 qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len); u32 rx_status = (qword & I40E_RXD_QW1_STATUS_MASK) >> @@ -1784,6 +1783,8 @@ void i40e_process_skb_fields(struct i40e_ring *rx_ring, u32 tsynvalid = rx_status & I40E_RXD_QW1_STATUS_TSYNVALID_MASK; u32 tsyn = (rx_status & I40E_RXD_QW1_STATUS_TSYNINDX_MASK) >> I40E_RXD_QW1_STATUS_TSYNINDX_SHIFT; + u8 rx_ptype = (qword & I40E_RXD_QW1_PTYPE_MASK) >> + I40E_RXD_QW1_PTYPE_SHIFT; if (unlikely(tsynvalid)) i40e_ptp_rx_hwtstamp(rx_ring->vsi->back, skb, tsyn); @@ -2339,7 +2340,6 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) struct i40e_rx_buffer *rx_buffer; union i40e_rx_desc *rx_desc; unsigned int size; - u8 rx_ptype; u64 qword; /* return some buffers to hardware, one at a time is too slow */ @@ -2432,12 +2432,8 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) /* probably a little skewed due to removing CRC */ total_rx_bytes += skb->len; - qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len); - rx_ptype = (qword & I40E_RXD_QW1_PTYPE_MASK) >> - I40E_RXD_QW1_PTYPE_SHIFT; - /* populate checksum, VLAN, and protocol */ - i40e_process_skb_fields(rx_ring, rx_desc, skb, rx_ptype); + i40e_process_skb_fields(rx_ring, rx_desc, skb); i40e_trace(clean_rx_irq_rx, rx_ring, rx_desc, skb); napi_gro_receive(&rx_ring->q_vector->napi, skb); diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx_common.h b/drivers/net/ethernet/intel/i40e/i40e_txrx_common.h index 2c077f1c4eca..8af0e99c6c0d 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx_common.h +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx_common.h @@ -12,8 +12,7 @@ struct i40e_rx_buffer *i40e_clean_programming_status( union i40e_rx_desc *rx_desc, u64 qw); void i40e_process_skb_fields(struct i40e_ring *rx_ring, - union i40e_rx_desc *rx_desc, struct sk_buff *skb, - u8 rx_ptype); + union i40e_rx_desc *rx_desc, struct sk_buff *skb); void i40e_xdp_ring_update_tail(struct i40e_ring *xdp_ring); void i40e_update_rx_stats(struct i40e_ring *rx_ring, unsigned int total_rx_bytes, diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c index a6ea2b249471..870cf654e436 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c @@ -634,7 +634,6 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget) struct i40e_rx_buffer *bi; union i40e_rx_desc *rx_desc; unsigned int size; - u8 rx_ptype; u64 qword; if (cleaned_count >= I40E_RX_BUFFER_WRITE) { @@ -712,10 +711,7 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget) total_rx_bytes += skb->len; total_rx_packets++; - qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len); - rx_ptype = (qword & I40E_RXD_QW1_PTYPE_MASK) >> - I40E_RXD_QW1_PTYPE_SHIFT; - i40e_process_skb_fields(rx_ring, rx_desc, skb, rx_ptype); + i40e_process_skb_fields(rx_ring, rx_desc, skb); napi_gro_receive(&rx_ring->q_vector->napi, skb); } -- cgit v1.2.3 From 96d1a731611f711f0cb82cea93363ae2ea8cb028 Mon Sep 17 00:00:00 2001 From: Ross Lagerwall Date: Wed, 5 Dec 2018 13:54:26 +0000 Subject: ixgbe: Fix race when the VF driver does a reset When the VF driver does a reset, it (at least the Linux one) writes to the VFCTRL register to issue a reset and then immediately sends a reset message using the mailbox API. This is racy because when the PF driver detects that the VFCTRL register reset pin has been asserted, it clears the mailbox memory. Depending on ordering, the reset message sent by the VF could be cleared by the PF driver. It then responds to the cleared message with a NACK which causes the VF driver to malfunction. Fix this by deferring clearing the mailbox memory until the reset message is received. Fixes: 939b701ad633 ("ixgbe: fix driver behaviour after issuing VFLR") Signed-off-by: Ross Lagerwall Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c index 5dacfc870259..345701af7749 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c @@ -700,7 +700,6 @@ static inline void ixgbe_vf_reset_event(struct ixgbe_adapter *adapter, u32 vf) u8 num_tcs = adapter->hw_tcs; u32 reg_val; u32 queue; - u32 word; /* remove VLAN filters beloning to this VF */ ixgbe_clear_vf_vlans(adapter, vf); @@ -758,6 +757,14 @@ static inline void ixgbe_vf_reset_event(struct ixgbe_adapter *adapter, u32 vf) } } + IXGBE_WRITE_FLUSH(hw); +} + +static void ixgbe_vf_clear_mbx(struct ixgbe_adapter *adapter, u32 vf) +{ + struct ixgbe_hw *hw = &adapter->hw; + u32 word; + /* Clear VF's mailbox memory */ for (word = 0; word < IXGBE_VFMAILBOX_SIZE; word++) IXGBE_WRITE_REG_ARRAY(hw, IXGBE_PFMBMEM(vf), word, 0); @@ -831,6 +838,8 @@ static int ixgbe_vf_reset_msg(struct ixgbe_adapter *adapter, u32 vf) /* reset the filters for the device */ ixgbe_vf_reset_event(adapter, vf); + ixgbe_vf_clear_mbx(adapter, vf); + /* set vf mac address */ if (!is_zero_ether_addr(vf_mac)) ixgbe_set_vf_mac(adapter, vf, vf_mac); -- cgit v1.2.3 From 708abf74dd87f8640871b814faa195fb5970b0e3 Mon Sep 17 00:00:00 2001 From: Pan Bian Date: Mon, 10 Dec 2018 14:39:37 +0100 Subject: netfilter: ipset: do not call ipset_nest_end after nla_nest_cancel In the error handling block, nla_nest_cancel(skb, atd) is called to cancel the nest operation. But then, ipset_nest_end(skb, atd) is unexpected called to end the nest operation. This patch calls the ipset_nest_end only on the branch that nla_nest_cancel is not called. Fixes: 45040978c899 ("netfilter: ipset: Fix set:list type crash when flush/dump set in parallel") Signed-off-by: Pan Bian Signed-off-by: Jozsef Kadlecsik Signed-off-by: Pablo Neira Ayuso --- net/netfilter/ipset/ip_set_list_set.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c index 4eef55da0878..8da228da53ae 100644 --- a/net/netfilter/ipset/ip_set_list_set.c +++ b/net/netfilter/ipset/ip_set_list_set.c @@ -531,8 +531,8 @@ nla_put_failure: ret = -EMSGSIZE; } else { cb->args[IPSET_CB_ARG0] = i; + ipset_nest_end(skb, atd); } - ipset_nest_end(skb, atd); out: rcu_read_unlock(); return ret; -- cgit v1.2.3 From 542fbda0f08f1cbbc250f9e59f7537649651d0c8 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 11 Dec 2018 07:45:29 +0100 Subject: netfilter: nat: can't use dst_hold on noref dst The dst entry might already have a zero refcount, waiting on rcu list to be free'd. Using dst_hold() transitions its reference count to 1, and next dst release will try to free it again -- resulting in a double free: WARNING: CPU: 1 PID: 0 at include/net/dst.h:239 nf_xfrm_me_harder+0xe7/0x130 [nf_nat] RIP: 0010:nf_xfrm_me_harder+0xe7/0x130 [nf_nat] Code: 48 8b 5c 24 60 65 48 33 1c 25 28 00 00 00 75 53 48 83 c4 68 5b 5d 41 5c c3 85 c0 74 0d 8d 48 01 f0 0f b1 0a 74 86 85 c0 75 f3 <0f> 0b e9 7b ff ff ff 29 c6 31 d2 b9 20 00 48 00 4c 89 e7 e8 31 27 Call Trace: nf_nat_ipv4_out+0x78/0x90 [nf_nat_ipv4] nf_hook_slow+0x36/0xd0 ip_output+0x9f/0xd0 ip_forward+0x328/0x440 ip_rcv+0x8a/0xb0 Use dst_hold_safe instead and bail out if we cannot take a reference. Fixes: a4c2fd7f7891 ("net: remove DST_NOCACHE flag") Reported-by: Martin Zaharinov Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_nat_core.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index e2b196054dfc..2268b10a9dcf 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -117,7 +117,8 @@ int nf_xfrm_me_harder(struct net *net, struct sk_buff *skb, unsigned int family) dst = skb_dst(skb); if (dst->xfrm) dst = ((struct xfrm_dst *)dst)->route; - dst_hold(dst); + if (!dst_hold_safe(dst)) + return -EHOSTUNREACH; if (sk && !net_eq(net, sock_net(sk))) sk = NULL; -- cgit v1.2.3 From d4e7df16567b80836a78d31b42f1a9355a636d67 Mon Sep 17 00:00:00 2001 From: Taehee Yoo Date: Sat, 8 Dec 2018 11:03:01 +0900 Subject: netfilter: nf_conncount: use rb_link_node_rcu() instead of rb_link_node() rbnode in insert_tree() is rcu protected pointer. So, in order to handle this pointer, _rcu function should be used. rb_link_node_rcu() is a rcu version of rb_link_node(). Fixes: 34848d5c896e ("netfilter: nf_conncount: Split insert and traversal") Signed-off-by: Taehee Yoo Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_conncount.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/netfilter/nf_conncount.c b/net/netfilter/nf_conncount.c index b6d0f6deea86..9cd180bda092 100644 --- a/net/netfilter/nf_conncount.c +++ b/net/netfilter/nf_conncount.c @@ -427,7 +427,7 @@ insert_tree(struct net *net, count = 1; rbconn->list.count = count; - rb_link_node(&rbconn->node, parent, rbnode); + rb_link_node_rcu(&rbconn->node, parent, rbnode); rb_insert_color(&rbconn->node, root); out_unlock: spin_unlock_bh(&nf_conncount_locks[hash % CONNCOUNT_LOCK_SLOTS]); -- cgit v1.2.3 From bbf666c1af916ed74795493c564df6fad462cc80 Mon Sep 17 00:00:00 2001 From: Sudarsana Reddy Kalluru Date: Wed, 12 Dec 2018 08:57:00 -0800 Subject: bnx2x: Clear fip MAC when fcoe offload support is disabled On some customer setups it was observed that shmem contains a non-zero fip MAC for 57711 which would lead to enabling of SW FCoE. Add a software workaround to clear the bad fip mac address if no FCoE connections are supported. Signed-off-by: Sudarsana Reddy Kalluru Signed-off-by: Ariel Elior Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index 95309b27c7d1..9052d57895d5 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -11750,8 +11750,10 @@ static void bnx2x_get_fcoe_info(struct bnx2x *bp) * If maximum allowed number of connections is zero - * disable the feature. */ - if (!bp->cnic_eth_dev.max_fcoe_conn) + if (!bp->cnic_eth_dev.max_fcoe_conn) { bp->flags |= NO_FCOE_FLAG; + eth_zero_addr(bp->fip_mac); + } } static void bnx2x_get_cnic_info(struct bnx2x *bp) -- cgit v1.2.3 From 04f05230c5c13b1384f66f5186a68d7499e34622 Mon Sep 17 00:00:00 2001 From: Sudarsana Reddy Kalluru Date: Wed, 12 Dec 2018 08:57:01 -0800 Subject: bnx2x: Remove configured vlans as part of unload sequence. Vlans are not getting removed when drivers are unloaded. The recent storm firmware versions had added safeguards against re-configuring an already configured vlan. As a result, PF inner reload flows (e.g., mtu change) might trigger an assertion. This change is going to remove vlans (same as we do for MACs) when doing a chip cleanup during unload. Signed-off-by: Sudarsana Reddy Kalluru Signed-off-by: Ariel Elior Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c | 34 +++++++++++++++++++----- drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.h | 4 ++- 2 files changed, 30 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index 9052d57895d5..01a973e05356 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -8472,6 +8472,7 @@ int bnx2x_set_vlan_one(struct bnx2x *bp, u16 vlan, /* Fill a user request section if needed */ if (!test_bit(RAMROD_CONT, ramrod_flags)) { ramrod_param.user_req.u.vlan.vlan = vlan; + __set_bit(BNX2X_VLAN, &ramrod_param.user_req.vlan_mac_flags); /* Set the command: ADD or DEL */ if (set) ramrod_param.user_req.cmd = BNX2X_VLAN_MAC_ADD; @@ -8492,6 +8493,27 @@ int bnx2x_set_vlan_one(struct bnx2x *bp, u16 vlan, return rc; } +static int bnx2x_del_all_vlans(struct bnx2x *bp) +{ + struct bnx2x_vlan_mac_obj *vlan_obj = &bp->sp_objs[0].vlan_obj; + unsigned long ramrod_flags = 0, vlan_flags = 0; + struct bnx2x_vlan_entry *vlan; + int rc; + + __set_bit(RAMROD_COMP_WAIT, &ramrod_flags); + __set_bit(BNX2X_VLAN, &vlan_flags); + rc = vlan_obj->delete_all(bp, vlan_obj, &vlan_flags, &ramrod_flags); + if (rc) + return rc; + + /* Mark that hw forgot all entries */ + list_for_each_entry(vlan, &bp->vlan_reg, link) + vlan->hw = false; + bp->vlan_cnt = 0; + + return 0; +} + int bnx2x_del_all_macs(struct bnx2x *bp, struct bnx2x_vlan_mac_obj *mac_obj, int mac_type, bool wait_for_comp) @@ -9330,6 +9352,11 @@ void bnx2x_chip_cleanup(struct bnx2x *bp, int unload_mode, bool keep_link) BNX2X_ERR("Failed to schedule DEL commands for UC MACs list: %d\n", rc); + /* Remove all currently configured VLANs */ + rc = bnx2x_del_all_vlans(bp); + if (rc < 0) + BNX2X_ERR("Failed to delete all VLANs\n"); + /* Disable LLH */ if (!CHIP_IS_E1(bp)) REG_WR(bp, NIG_REG_LLH0_FUNC_EN + port*8, 0); @@ -13026,13 +13053,6 @@ static void bnx2x_vlan_configure(struct bnx2x *bp, bool set_rx_mode) int bnx2x_vlan_reconfigure_vid(struct bnx2x *bp) { - struct bnx2x_vlan_entry *vlan; - - /* The hw forgot all entries after reload */ - list_for_each_entry(vlan, &bp->vlan_reg, link) - vlan->hw = false; - bp->vlan_cnt = 0; - /* Don't set rx mode here. Our caller will do it. */ bnx2x_vlan_configure(bp, false); diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.h index 0bf2fd470819..7a6e82db4231 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.h @@ -265,6 +265,7 @@ enum { BNX2X_ETH_MAC, BNX2X_ISCSI_ETH_MAC, BNX2X_NETQ_ETH_MAC, + BNX2X_VLAN, BNX2X_DONT_CONSUME_CAM_CREDIT, BNX2X_DONT_CONSUME_CAM_CREDIT_DEST, }; @@ -272,7 +273,8 @@ enum { #define BNX2X_VLAN_MAC_CMP_MASK (1 << BNX2X_UC_LIST_MAC | \ 1 << BNX2X_ETH_MAC | \ 1 << BNX2X_ISCSI_ETH_MAC | \ - 1 << BNX2X_NETQ_ETH_MAC) + 1 << BNX2X_NETQ_ETH_MAC | \ + 1 << BNX2X_VLAN) #define BNX2X_VLAN_MAC_CMP_FLAGS(flags) \ ((flags) & BNX2X_VLAN_MAC_CMP_MASK) -- cgit v1.2.3 From 07f12622a66320d5f56a71a921cf70a43e7a6b87 Mon Sep 17 00:00:00 2001 From: Sudarsana Reddy Kalluru Date: Wed, 12 Dec 2018 08:57:02 -0800 Subject: bnx2x: Enable PTP only on the PF that initializes the port There will be only one PHC clock per port. PTP should be enabled only on one PF per port. The change enables PTP functionality on the PF that initializes the port. The change is useful in multi-function modes e.g., NPAR where a port can have more than one PF. Signed-off-by: Sudarsana Reddy Kalluru Signed-off-by: Ariel Elior Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnx2x/bnx2x.h | 1 + drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c | 1 + drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c | 22 ++++++++++------------ 3 files changed, 12 insertions(+), 12 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h index 0de487a8f0eb..7ea9066ce126 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h @@ -2520,6 +2520,7 @@ void bnx2x_update_mfw_dump(struct bnx2x *bp); void bnx2x_init_ptp(struct bnx2x *bp); int bnx2x_configure_ptp_filters(struct bnx2x *bp); void bnx2x_set_rx_ts(struct bnx2x *bp, struct sk_buff *skb); +void bnx2x_register_phc(struct bnx2x *bp); #define BNX2X_MAX_PHC_DRIFT 31000000 #define BNX2X_PTP_TX_TIMEOUT diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c index 686899d7e555..ecb1bd7eb508 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c @@ -2842,6 +2842,7 @@ int bnx2x_nic_load(struct bnx2x *bp, int load_mode) bnx2x_set_rx_mode_inner(bp); if (bp->flags & PTP_SUPPORTED) { + bnx2x_register_phc(bp); bnx2x_init_ptp(bp); bnx2x_configure_ptp_filters(bp); } diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index 01a973e05356..6b54eb1ad8ba 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -7723,6 +7723,9 @@ static int bnx2x_init_hw_port(struct bnx2x *bp) REG_WR(bp, reg_addr, val); } + if (CHIP_IS_E3B0(bp)) + bp->flags |= PTP_SUPPORTED; + return 0; } @@ -9444,8 +9447,13 @@ unload_error: * function stop ramrod is sent, since as part of this ramrod FW access * PTP registers. */ - if (bp->flags & PTP_SUPPORTED) + if (bp->flags & PTP_SUPPORTED) { bnx2x_stop_ptp(bp); + if (bp->ptp_clock) { + ptp_clock_unregister(bp->ptp_clock); + bp->ptp_clock = NULL; + } + } /* Disable HW interrupts, NAPI */ bnx2x_netif_stop(bp, 1); @@ -12523,9 +12531,6 @@ static int bnx2x_init_bp(struct bnx2x *bp) bp->dump_preset_idx = 1; - if (CHIP_IS_E3B0(bp)) - bp->flags |= PTP_SUPPORTED; - return rc; } @@ -13917,7 +13922,7 @@ static int bnx2x_ptp_enable(struct ptp_clock_info *ptp, return -ENOTSUPP; } -static void bnx2x_register_phc(struct bnx2x *bp) +void bnx2x_register_phc(struct bnx2x *bp) { /* Fill the ptp_clock_info struct and register PTP clock*/ bp->ptp_clock_info.owner = THIS_MODULE; @@ -14119,8 +14124,6 @@ static int bnx2x_init_one(struct pci_dev *pdev, dev->base_addr, bp->pdev->irq, dev->dev_addr); pcie_print_link_status(bp->pdev); - bnx2x_register_phc(bp); - if (!IS_MF_SD_STORAGE_PERSONALITY_ONLY(bp)) bnx2x_set_os_driver_state(bp, OS_DRIVER_STATE_DISABLED); @@ -14153,11 +14156,6 @@ static void __bnx2x_remove(struct pci_dev *pdev, struct bnx2x *bp, bool remove_netdev) { - if (bp->ptp_clock) { - ptp_clock_unregister(bp->ptp_clock); - bp->ptp_clock = NULL; - } - /* Delete storage MAC address */ if (!NO_FCOE(bp)) { rtnl_lock(); -- cgit v1.2.3 From 9061193c4ee065d3240fde06767c2e06ec61decc Mon Sep 17 00:00:00 2001 From: Sudarsana Reddy Kalluru Date: Wed, 12 Dec 2018 08:57:03 -0800 Subject: bnx2x: Send update-svid ramrod with retry/poll flags enabled Driver sends update-SVID ramrod in the MFW notification path. If there is a pending ramrod, driver doesn't retry the command and storm firmware will never be updated with the SVID value. The patch adds changes to send update-svid ramrod in process context with retry/poll flags set. Signed-off-by: Sudarsana Reddy Kalluru Signed-off-by: Ariel Elior Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnx2x/bnx2x.h | 1 + drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c | 10 +++++++++- 2 files changed, 10 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h index 7ea9066ce126..5cd3135dfe30 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h @@ -1282,6 +1282,7 @@ enum sp_rtnl_flag { BNX2X_SP_RTNL_TX_STOP, BNX2X_SP_RTNL_GET_DRV_VERSION, BNX2X_SP_RTNL_CHANGE_UDP_PORT, + BNX2X_SP_RTNL_UPDATE_SVID, }; enum bnx2x_iov_flag { diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index 6b54eb1ad8ba..b164f705709d 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -2925,6 +2925,10 @@ static void bnx2x_handle_update_svid_cmd(struct bnx2x *bp) func_params.f_obj = &bp->func_obj; func_params.cmd = BNX2X_F_CMD_SWITCH_UPDATE; + /* Prepare parameters for function state transitions */ + __set_bit(RAMROD_COMP_WAIT, &func_params.ramrod_flags); + __set_bit(RAMROD_RETRY, &func_params.ramrod_flags); + if (IS_MF_UFP(bp) || IS_MF_BD(bp)) { int func = BP_ABS_FUNC(bp); u32 val; @@ -4311,7 +4315,8 @@ static void bnx2x_attn_int_deasserted3(struct bnx2x *bp, u32 attn) bnx2x_handle_eee_event(bp); if (val & DRV_STATUS_OEM_UPDATE_SVID) - bnx2x_handle_update_svid_cmd(bp); + bnx2x_schedule_sp_rtnl(bp, + BNX2X_SP_RTNL_UPDATE_SVID, 0); if (bp->link_vars.periodic_flags & PERIODIC_FLAGS_LINK_EVENT) { @@ -10394,6 +10399,9 @@ sp_rtnl_not_reset: &bp->sp_rtnl_state)) bnx2x_update_mng_version(bp); + if (test_and_clear_bit(BNX2X_SP_RTNL_UPDATE_SVID, &bp->sp_rtnl_state)) + bnx2x_handle_update_svid_cmd(bp); + if (test_and_clear_bit(BNX2X_SP_RTNL_CHANGE_UDP_PORT, &bp->sp_rtnl_state)) { if (bnx2x_udp_port_update(bp)) { -- cgit v1.2.3 From 841df922417eb82c835e93d4b93eb6a68c99d599 Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Thu, 13 Dec 2018 10:53:37 +0800 Subject: vhost: make sure used idx is seen before log in vhost_add_used_n() We miss a write barrier that guarantees used idx is updated and seen before log. This will let userspace sync and copy used ring before used idx is update. Fix this by adding a barrier before log_write(). Fixes: 8dd014adfea6f ("vhost-net: mergeable buffers support") Acked-by: Michael S. Tsirkin Signed-off-by: Jason Wang Signed-off-by: David S. Miller --- drivers/vhost/vhost.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index 6b98d8e3a5bf..5915f240275a 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -2220,6 +2220,8 @@ int vhost_add_used_n(struct vhost_virtqueue *vq, struct vring_used_elem *heads, return -EFAULT; } if (unlikely(vq->log_used)) { + /* Make sure used idx is seen before log. */ + smp_wmb(); /* Log used index update. */ log_write(vq->log_base, vq->log_addr + offsetof(struct vring_used, idx), -- cgit v1.2.3 From 476e8ba712fa6a479192dfc4301cd3765d9ba713 Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Thu, 13 Dec 2018 10:53:38 +0800 Subject: vhost_net: switch to use mutex_trylock() in vhost_net_busy_poll() We used to hold the mutex of paired virtqueue in vhost_net_busy_poll(). But this will results an inconsistent lock order which may cause deadlock if we try to bring back the protection of device IOTLB with vq mutex that requires to hold mutex of all virtqueues at the same time. Fix this simply by switching to use mutex_trylock(), when fail just skip the busy polling. This can happen when device IOTLB is under updating which should be rare. Fixes: commit 78139c94dc8c ("net: vhost: lock the vqs one by one") Cc: Tonghao Zhang Acked-by: Michael S. Tsirkin Signed-off-by: Jason Wang Signed-off-by: David S. Miller --- drivers/vhost/net.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index ab11b2bee273..ad7a6f475a44 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -513,7 +513,13 @@ static void vhost_net_busy_poll(struct vhost_net *net, struct socket *sock; struct vhost_virtqueue *vq = poll_rx ? tvq : rvq; - mutex_lock_nested(&vq->mutex, poll_rx ? VHOST_NET_VQ_TX: VHOST_NET_VQ_RX); + /* Try to hold the vq mutex of the paired virtqueue. We can't + * use mutex_lock() here since we could not guarantee a + * consistenet lock ordering. + */ + if (!mutex_trylock(&vq->mutex)) + return; + vhost_disable_notify(&net->dev, vq); sock = rvq->private_data; -- cgit v1.2.3 From 86a07da34380bc9467fa407dc3e484488a8ad40d Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Thu, 13 Dec 2018 10:53:39 +0800 Subject: Revert "net: vhost: lock the vqs one by one" This reverts commit 78139c94dc8c96a478e67dab3bee84dc6eccb5fd. We don't protect device IOTLB with vq mutex, which will lead e.g use after free for device IOTLB entries. And since we've switched to use mutex_trylock() in previous patch, it's safe to revert it without having deadlock. Fixes: commit 78139c94dc8c ("net: vhost: lock the vqs one by one") Cc: Tonghao Zhang Acked-by: Michael S. Tsirkin Signed-off-by: Jason Wang Signed-off-by: David S. Miller --- drivers/vhost/vhost.c | 21 +++++++++++++++++---- 1 file changed, 17 insertions(+), 4 deletions(-) diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index 5915f240275a..55e5aa662ad5 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -295,11 +295,8 @@ static void vhost_vq_meta_reset(struct vhost_dev *d) { int i; - for (i = 0; i < d->nvqs; ++i) { - mutex_lock(&d->vqs[i]->mutex); + for (i = 0; i < d->nvqs; ++i) __vhost_vq_meta_reset(d->vqs[i]); - mutex_unlock(&d->vqs[i]->mutex); - } } static void vhost_vq_reset(struct vhost_dev *dev, @@ -895,6 +892,20 @@ static inline void __user *__vhost_get_user(struct vhost_virtqueue *vq, #define vhost_get_used(vq, x, ptr) \ vhost_get_user(vq, x, ptr, VHOST_ADDR_USED) +static void vhost_dev_lock_vqs(struct vhost_dev *d) +{ + int i = 0; + for (i = 0; i < d->nvqs; ++i) + mutex_lock_nested(&d->vqs[i]->mutex, i); +} + +static void vhost_dev_unlock_vqs(struct vhost_dev *d) +{ + int i = 0; + for (i = 0; i < d->nvqs; ++i) + mutex_unlock(&d->vqs[i]->mutex); +} + static int vhost_new_umem_range(struct vhost_umem *umem, u64 start, u64 size, u64 end, u64 userspace_addr, int perm) @@ -976,6 +987,7 @@ static int vhost_process_iotlb_msg(struct vhost_dev *dev, int ret = 0; mutex_lock(&dev->mutex); + vhost_dev_lock_vqs(dev); switch (msg->type) { case VHOST_IOTLB_UPDATE: if (!dev->iotlb) { @@ -1009,6 +1021,7 @@ static int vhost_process_iotlb_msg(struct vhost_dev *dev, break; } + vhost_dev_unlock_vqs(dev); mutex_unlock(&dev->mutex); return ret; -- cgit v1.2.3 From 663f146f2ecfcc47934cb9f9543f664eeb6adb46 Mon Sep 17 00:00:00 2001 From: Vu Pham Date: Wed, 31 Oct 2018 16:03:21 +0200 Subject: net/mlx5: E-Switch, Fix fdb cap bits swap The cap bits locations for the fdb caps of multi path to table (used for local mirroring) and multi encap (used for prio/chains) were wrongly used in swapped locations. This went unnoted so far b/c we tested the offending patch with CX5 FW that supports both of them. On different environments where not both caps are supported, we will be messed up, fix that. Fixes: b9aa0ba17af5 ('net/mlx5: Add cap bits for multi fdb encap') Signed-off-by: Vu Pham Reviewed-by: Or Gerlitz Tested-by: Or Gerlitz Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 34e17e6f8942..4e77bfe0b580 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -582,11 +582,13 @@ struct mlx5_ifc_flow_table_nic_cap_bits { }; struct mlx5_ifc_flow_table_eswitch_cap_bits { - u8 reserved_at_0[0x1c]; - u8 fdb_multi_path_to_table[0x1]; - u8 reserved_at_1d[0x1]; + u8 reserved_at_0[0x1a]; u8 multi_fdb_encap[0x1]; - u8 reserved_at_1e[0x1e1]; + u8 reserved_at_1b[0x1]; + u8 fdb_multi_path_to_table[0x1]; + u8 reserved_at_1d[0x3]; + + u8 reserved_at_20[0x1e0]; struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_nic_esw_fdb; -- cgit v1.2.3 From 8956f0014ea5ed824aae3816fd9e52cf3c85b9d4 Mon Sep 17 00:00:00 2001 From: Gavi Teitz Date: Mon, 19 Nov 2018 17:22:30 +0200 Subject: net/mlx5e: Fix default amount of channels for VF representors The default amount of channels a representor opens was erroneously changed from one to the maximum amount of channels, restore to its intended value. Fixes: 779d986d60de ("net/mlx5e: Do not ignore netdevice TX/RX queues number") Signed-off-by: Gavi Teitz Reviewed-by: Or Gerlitz Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index c3c657548824..6a4d782c1de1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -46,6 +46,7 @@ #define MLX5E_REP_PARAMS_LOG_SQ_SIZE \ max(0x6, MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE) +#define MLX5E_REP_PARAMS_DEF_NUM_CHANNELS 1 static const char mlx5e_rep_driver_name[] = "mlx5e_rep"; @@ -1083,9 +1084,7 @@ static int mlx5e_init_rep(struct mlx5_core_dev *mdev, if (err) return err; - - priv->channels.params.num_channels = - mlx5e_get_netdev_max_channels(netdev); + priv->channels.params.num_channels = MLX5E_REP_PARAMS_DEF_NUM_CHANNELS; mlx5e_build_rep_params(mdev, &priv->channels.params, netdev->mtu); mlx5e_build_rep_netdev(netdev); -- cgit v1.2.3 From e1c15b62b7015119d3e5915cd2ae3b89d59c2576 Mon Sep 17 00:00:00 2001 From: Moshe Shemesh Date: Fri, 2 Nov 2018 06:10:49 +0200 Subject: net/mlx5e: RX, Verify MPWQE stride size is in range Add check of MPWQE stride size is within range supported by HW. In case calculated MPWQE stride size exceed range, linear SKB can't be used and we should use non linear MPWQE instead. Fixes: 619a8f2a42f1 ("net/mlx5e: Use linear SKB in Striding RQ") Signed-off-by: Moshe Shemesh Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 871313d6b34d..c17de6a990ff 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -128,6 +128,8 @@ static bool mlx5e_rx_is_linear_skb(struct mlx5_core_dev *mdev, return !params->lro_en && frag_sz <= PAGE_SIZE; } +#define MLX5_MAX_MPWQE_LOG_WQE_STRIDE_SZ ((BIT(__mlx5_bit_sz(wq, log_wqe_stride_size)) - 1) + \ + MLX5_MPWQE_LOG_STRIDE_SZ_BASE) static bool mlx5e_rx_mpwqe_is_linear_skb(struct mlx5_core_dev *mdev, struct mlx5e_params *params) { @@ -138,6 +140,9 @@ static bool mlx5e_rx_mpwqe_is_linear_skb(struct mlx5_core_dev *mdev, if (!mlx5e_rx_is_linear_skb(mdev, params)) return false; + if (order_base_2(frag_sz) > MLX5_MAX_MPWQE_LOG_WQE_STRIDE_SZ) + return false; + if (MLX5_CAP_GEN(mdev, ext_stride_num_range)) return true; -- cgit v1.2.3 From e88afe759a49f8d51d6cc5fc89d65b4a5768703f Mon Sep 17 00:00:00 2001 From: Or Gerlitz Date: Sun, 9 Dec 2018 17:03:36 +0200 Subject: net/mlx5e: Err if asked to mirror a goto chain tc eswitch rule Currently we are not supporting this and not err-ing on that either. For now, just err if asked to do that. Fixes: bf07aa730a04 ('net/mlx5e: Support offloading tc priorities and chains for eswitch flows') Signed-off-by: Or Gerlitz Reported-by: Eli Britstein Reviewed-by: Eli Britstein Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index fca6f4132c91..1f01c905a042 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -2966,8 +2966,7 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts, NL_SET_ERR_MSG(extack, "Requested destination chain is out of supported range"); return -EOPNOTSUPP; } - action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | - MLX5_FLOW_CONTEXT_ACTION_COUNT; + action |= MLX5_FLOW_CONTEXT_ACTION_COUNT; attr->dest_chain = dest_chain; continue; @@ -2980,6 +2979,14 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts, if (!actions_match_supported(priv, exts, parse_attr, flow, extack)) return -EOPNOTSUPP; + if (attr->dest_chain) { + if (attr->action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) { + NL_SET_ERR_MSG(extack, "Mirroring goto chain rules isn't supported"); + return -EOPNOTSUPP; + } + attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; + } + if (attr->mirror_count > 0 && !mlx5_esw_has_fwd_fdb(priv->mdev)) { NL_SET_ERR_MSG_MOD(extack, "current firmware doesn't support split rule for port mirroring"); -- cgit v1.2.3 From d14f6f2a84326dd2751962167b2293fc91751ff8 Mon Sep 17 00:00:00 2001 From: Or Gerlitz Date: Sun, 9 Dec 2018 17:15:23 +0200 Subject: net/mlx5e: Avoid overriding the user provided priority for offloaded tc rules Just a leftover which was wrongly left there, remove it while spawning a message to suggest firmware upgrade. Fixes: bf07aa730a04 ('net/mlx5e: Support offloading tc priorities and chains for eswitch flows') Signed-off-by: Or Gerlitz Reviewed-by: Paul Blakey Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 1f01c905a042..e6170ddf2cc4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -907,11 +907,10 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, struct mlx5e_priv *out_priv; int err = 0, encap_err = 0; - /* if prios are not supported, keep the old behaviour of using same prio - * for all offloaded rules. - */ - if (!mlx5_eswitch_prios_supported(esw)) - attr->prio = 1; + if (!mlx5_eswitch_prios_supported(esw) && attr->prio != 1) { + NL_SET_ERR_MSG(extack, "E-switch priorities unsupported, upgrade FW"); + return -EOPNOTSUPP; + } if (attr->chain > max_chain) { NL_SET_ERR_MSG(extack, "Requested chain is out of supported range"); -- cgit v1.2.3 From 154e62abe9cd07c9b71735d8456a03a7c5251280 Mon Sep 17 00:00:00 2001 From: Or Gerlitz Date: Mon, 10 Dec 2018 12:31:42 +0200 Subject: net/mlx5e: Properly initialize flow attributes for slow path eswitch rule deletion When a neighbour is resolved, we delete the goto slow path rule from HW. The eswitch flow attributes where not properly initialized on that case, hence we mess up the eswitch refcounts for chain zero (the default one). Fix that along with making sure to use semicolons and not commas on that code; Fixes: 5dbe906ff1d5 ('net/mlx5e: Use a slow path rule instead if vxlan neighbour isn't available') Signed-off-by: Or Gerlitz Reviewed-by: Paul Blakey Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index e6170ddf2cc4..3b732c02b5e1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -870,9 +870,9 @@ mlx5e_tc_offload_to_slow_path(struct mlx5_eswitch *esw, struct mlx5_flow_handle *rule; memcpy(slow_attr, flow->esw_attr, sizeof(*slow_attr)); - slow_attr->action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST, - slow_attr->mirror_count = 0, - slow_attr->dest_chain = FDB_SLOW_PATH_CHAIN, + slow_attr->action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; + slow_attr->mirror_count = 0; + slow_attr->dest_chain = FDB_SLOW_PATH_CHAIN; rule = mlx5e_tc_offload_fdb_rules(esw, flow, spec, slow_attr); if (!IS_ERR(rule)) @@ -887,6 +887,9 @@ mlx5e_tc_unoffload_from_slow_path(struct mlx5_eswitch *esw, struct mlx5_esw_flow_attr *slow_attr) { memcpy(slow_attr, flow->esw_attr, sizeof(*slow_attr)); + slow_attr->action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; + slow_attr->mirror_count = 0; + slow_attr->dest_chain = FDB_SLOW_PATH_CHAIN; mlx5e_tc_unoffload_fdb_rules(esw, flow, slow_attr); flow->flags &= ~MLX5E_TC_FLOW_SLOW; } -- cgit v1.2.3 From 61c806dafe81c58f41fec10fb5cad0d3a4390e3e Mon Sep 17 00:00:00 2001 From: Or Gerlitz Date: Mon, 10 Dec 2018 17:05:59 +0200 Subject: net/mlx5e: Avoid encap flows deletion attempt the 1st time a neigh is resolved Currently, we are deleting offloaded encap flows in case the relevant neigh becomes unconnected while the encap is valid (a sign that it used to be connected), or if the curr neigh mac is different from the cached mac (a sign that the remote side changed their mac). The 2nd check also applies when the neigh becomes connected on the 1st time (we start with zero mac). Before the offending commit, the deleting handler was practically no op, as no flows were offloaded. But since that commit, we offload neigh-less encap flows to slow path. Under mirroring scheme, we go into the delete handler, attempt to unoffload a mirror rule which was never set (as we were offloading to slow path) and crash. Fix that by calling the delete handler only when the encap is valid, which covers both cases mentioned above. Fixes: 5dbe906ff1d5 ('net/mlx5e: Use a slow path rule instead if vxlan neighbour isn't available') Signed-off-by: Or Gerlitz Signed-off-by: Eli Britstein Reviewed-by: Paul Blakey Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 4 ++-- drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 7 +++---- 2 files changed, 5 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 6a4d782c1de1..820fe85100b0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -467,8 +467,8 @@ static void mlx5e_rep_update_flows(struct mlx5e_priv *priv, ASSERT_RTNL(); - if ((!neigh_connected && (e->flags & MLX5_ENCAP_ENTRY_VALID)) || - !ether_addr_equal(e->h_dest, ha)) + if ((e->flags & MLX5_ENCAP_ENTRY_VALID) && + (!neigh_connected || !ether_addr_equal(e->h_dest, ha))) mlx5e_tc_encap_flows_del(priv, e); if (neigh_connected && !(e->flags & MLX5_ENCAP_ENTRY_VALID)) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 3b732c02b5e1..9dabe9d4b279 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -1096,10 +1096,9 @@ void mlx5e_tc_encap_flows_del(struct mlx5e_priv *priv, flow->rule[0] = rule; } - if (e->flags & MLX5_ENCAP_ENTRY_VALID) { - e->flags &= ~MLX5_ENCAP_ENTRY_VALID; - mlx5_packet_reformat_dealloc(priv->mdev, e->encap_id); - } + /* we know that the encap is valid */ + e->flags &= ~MLX5_ENCAP_ENTRY_VALID; + mlx5_packet_reformat_dealloc(priv->mdev, e->encap_id); } static struct mlx5_fc *mlx5e_tc_get_counter(struct mlx5e_tc_flow *flow) -- cgit v1.2.3 From d13b224f431579fe2d712871d4265d7a22ca6c9c Mon Sep 17 00:00:00 2001 From: Mikhael Goikhman Date: Mon, 19 Nov 2018 19:11:12 +0200 Subject: net/mlx5e: Remove unused UDP GSO remaining counter Remove tx_udp_seg_rem counter from ethtool output, as it is no longer being updated in the driver's data flow. Fixes: 3f44899ef2ce ("net/mlx5e: Use PARTIAL_GSO for UDP segmentation") Signed-off-by: Mikhael Goikhman Reviewed-by: Eran Ben Elisha Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_stats.c | 2 -- drivers/net/ethernet/mellanox/mlx5/core/en_stats.h | 2 -- 2 files changed, 4 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c index 3e99d0728b2f..4337afd610d7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c @@ -74,7 +74,6 @@ static const struct counter_desc sw_stats_desc[] = { { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_recover) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_cqes) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_queue_wake) }, - { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_udp_seg_rem) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_cqe_err) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_xmit) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_full) }, @@ -198,7 +197,6 @@ void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv) s->tx_nop += sq_stats->nop; s->tx_queue_stopped += sq_stats->stopped; s->tx_queue_wake += sq_stats->wake; - s->tx_udp_seg_rem += sq_stats->udp_seg_rem; s->tx_queue_dropped += sq_stats->dropped; s->tx_cqe_err += sq_stats->cqe_err; s->tx_recover += sq_stats->recover; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h index 3f8e870ef4c9..3ff69ddae2d3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h @@ -87,7 +87,6 @@ struct mlx5e_sw_stats { u64 tx_recover; u64 tx_cqes; u64 tx_queue_wake; - u64 tx_udp_seg_rem; u64 tx_cqe_err; u64 tx_xdp_xmit; u64 tx_xdp_full; @@ -221,7 +220,6 @@ struct mlx5e_sq_stats { u64 csum_partial_inner; u64 added_vlan_packets; u64 nop; - u64 udp_seg_rem; #ifdef CONFIG_MLX5_EN_TLS u64 tls_ooo; u64 tls_resync_bytes; -- cgit v1.2.3 From fa2bf86bab4bbc61e5678a42a14e40075093a98f Mon Sep 17 00:00:00 2001 From: Tal Gilboa Date: Thu, 22 Nov 2018 14:20:45 +0200 Subject: net/mlx5e: Cancel DIM work on close SQ TXQ SQ closure is followed by closing the corresponding CQ. A pending DIM work would try to modify the now non-existing CQ. This would trigger an error: [85535.835926] mlx5_core 0000:af:00.0: mlx5_cmd_check:769:(pid 124399): MODIFY_CQ(0x403) op_mod(0x0) failed, status bad resource state(0x9), syndrome (0x1d7771) Fix by making sure to cancel any pending DIM work before destroying the SQ. Fixes: cbce4f444798 ("net/mlx5e: Enable adaptive-TX moderation") Signed-off-by: Tal Gilboa Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index c17de6a990ff..b70cb6fd164c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -1401,6 +1401,7 @@ static void mlx5e_close_txqsq(struct mlx5e_txqsq *sq) struct mlx5_core_dev *mdev = c->mdev; struct mlx5_rate_limit rl = {0}; + cancel_work_sync(&sq->dim.work); mlx5e_destroy_sq(mdev, sq->sqn); if (sq->rate_limit) { rl.rate = sq->rate_limit; -- cgit v1.2.3 From 30360224441ce89a98ed627861e735beb4010775 Mon Sep 17 00:00:00 2001 From: Jörgen Storvist Date: Wed, 12 Dec 2018 21:47:36 +0100 Subject: USB: serial: option: add Fibocom NL668 series Added USB serial option driver support for Fibocom NL668 series cellular modules. Reserved USB endpoints 4, 5 and 6 for network + ADB interfaces. usb-devices output (QMI mode) T: Bus=01 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#= 16 Spd=480 MxCh= 0 D: Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs= 1 P: Vendor=1508 ProdID=1001 Rev=03.18 S: Manufacturer=Nodecom NL668 Modem S: Product=Nodecom NL668-CN Modem S: SerialNumber= C: #Ifs= 6 Cfg#= 1 Atr=a0 MxPwr=500mA I: If#= 0 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option I: If#= 1 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option I: If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option I: If#= 3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option I: If#= 4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=qmi_wwan I: If#= 5 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=42 Prot=01 Driver=(none) usb-devices output (ECM mode) T: Bus=01 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#= 17 Spd=480 MxCh= 0 D: Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs= 1 P: Vendor=1508 ProdID=1001 Rev=03.18 S: Manufacturer=Nodecom NL668 Modem S: Product=Nodecom NL668-CN Modem S: SerialNumber= C: #Ifs= 7 Cfg#= 1 Atr=a0 MxPwr=500mA I: If#= 0 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option I: If#= 1 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option I: If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option I: If#= 3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option I: If#= 4 Alt= 0 #EPs= 1 Cls=02(commc) Sub=06 Prot=00 Driver=cdc_ether I: If#= 5 Alt= 1 #EPs= 2 Cls=0a(data ) Sub=00 Prot=00 Driver=cdc_ether I: If#= 6 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=42 Prot=01 Driver=(none) Signed-off-by: Jörgen Storvist Cc: stable Signed-off-by: Johan Hovold --- drivers/usb/serial/option.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 53e8de5f8acd..2304433d5021 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -1949,6 +1949,8 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(0x03f0, 0xa31d, 0xff, 0x06, 0x13) }, { USB_DEVICE_AND_INTERFACE_INFO(0x03f0, 0xa31d, 0xff, 0x06, 0x14) }, { USB_DEVICE_AND_INTERFACE_INFO(0x03f0, 0xa31d, 0xff, 0x06, 0x1b) }, + { USB_DEVICE(0x1508, 0x1001), /* Fibocom NL668 */ + .driver_info = RSVD(4) | RSVD(5) | RSVD(6) }, { } /* Terminating entry */ }; MODULE_DEVICE_TABLE(usb, option_ids); -- cgit v1.2.3 From fd567467753fac9f9f477550065018e7f4e3c8f3 Mon Sep 17 00:00:00 2001 From: Thomas Hellstrom Date: Wed, 12 Dec 2018 11:52:08 +0100 Subject: drm/vmwgfx: Protect from excessive execbuf kernel memory allocations v3 With the new validation code, a malicious user-space app could potentially submit command streams with enough buffer-object and resource references in them to have the resulting allocated validion nodes and relocations make the kernel run out of GFP_KERNEL memory. Protect from this by having the validation code reserve TTM graphics memory when allocating. Signed-off-by: Thomas Hellstrom Reviewed-by: Deepak Rawat --- v2: Removed leftover debug printouts --- drivers/gpu/drm/vmwgfx/vmwgfx_drv.c | 4 +++- drivers/gpu/drm/vmwgfx/vmwgfx_drv.h | 5 ++++ drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c | 2 ++ drivers/gpu/drm/vmwgfx/vmwgfx_ttm_glue.c | 36 +++++++++++++++++++++++++++++ drivers/gpu/drm/vmwgfx/vmwgfx_validation.c | 21 ++++++++++++++++- drivers/gpu/drm/vmwgfx/vmwgfx_validation.h | 37 ++++++++++++++++++++++++++++++ 6 files changed, 103 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c index 61a84b958d67..d7a2dfb8ee9b 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c @@ -49,6 +49,8 @@ #define VMWGFX_REPO "In Tree" +#define VMWGFX_VALIDATION_MEM_GRAN (16*PAGE_SIZE) + /** * Fully encoded drm commands. Might move to vmw_drm.h @@ -918,7 +920,7 @@ static int vmw_driver_load(struct drm_device *dev, unsigned long chipset) spin_unlock(&dev_priv->cap_lock); } - + vmw_validation_mem_init_ttm(dev_priv, VMWGFX_VALIDATION_MEM_GRAN); ret = vmw_kms_init(dev_priv); if (unlikely(ret != 0)) goto out_no_kms; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h index 59f614225bcd..aca974b14b55 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h @@ -606,6 +606,9 @@ struct vmw_private { struct vmw_cmdbuf_man *cman; DECLARE_BITMAP(irqthread_pending, VMW_IRQTHREAD_MAX); + + /* Validation memory reservation */ + struct vmw_validation_mem vvm; }; static inline struct vmw_surface *vmw_res_to_srf(struct vmw_resource *res) @@ -846,6 +849,8 @@ extern int vmw_ttm_global_init(struct vmw_private *dev_priv); extern void vmw_ttm_global_release(struct vmw_private *dev_priv); extern int vmw_mmap(struct file *filp, struct vm_area_struct *vma); +extern void vmw_validation_mem_init_ttm(struct vmw_private *dev_priv, + size_t gran); /** * TTM buffer object driver - vmwgfx_ttm_buffer.c */ diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c index 260650bb5560..f2d13a72c05d 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c @@ -3835,6 +3835,8 @@ int vmw_execbuf_process(struct drm_file *file_priv, struct sync_file *sync_file = NULL; DECLARE_VAL_CONTEXT(val_ctx, &sw_context->res_ht, 1); + vmw_validation_set_val_mem(&val_ctx, &dev_priv->vvm); + if (flags & DRM_VMW_EXECBUF_FLAG_EXPORT_FENCE_FD) { out_fence_fd = get_unused_fd_flags(O_CLOEXEC); if (out_fence_fd < 0) { diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_glue.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_glue.c index 7b1e5a5cbd2c..f88247046721 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_glue.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_glue.c @@ -96,3 +96,39 @@ void vmw_ttm_global_release(struct vmw_private *dev_priv) drm_global_item_unref(&dev_priv->bo_global_ref.ref); drm_global_item_unref(&dev_priv->mem_global_ref); } + +/* struct vmw_validation_mem callback */ +static int vmw_vmt_reserve(struct vmw_validation_mem *m, size_t size) +{ + static struct ttm_operation_ctx ctx = {.interruptible = false, + .no_wait_gpu = false}; + struct vmw_private *dev_priv = container_of(m, struct vmw_private, vvm); + + return ttm_mem_global_alloc(vmw_mem_glob(dev_priv), size, &ctx); +} + +/* struct vmw_validation_mem callback */ +static void vmw_vmt_unreserve(struct vmw_validation_mem *m, size_t size) +{ + struct vmw_private *dev_priv = container_of(m, struct vmw_private, vvm); + + return ttm_mem_global_free(vmw_mem_glob(dev_priv), size); +} + +/** + * vmw_validation_mem_init_ttm - Interface the validation memory tracker + * to ttm. + * @dev_priv: Pointer to struct vmw_private. The reason we choose a vmw private + * rather than a struct vmw_validation_mem is to make sure assumption in the + * callbacks that struct vmw_private derives from struct vmw_validation_mem + * holds true. + * @gran: The recommended allocation granularity + */ +void vmw_validation_mem_init_ttm(struct vmw_private *dev_priv, size_t gran) +{ + struct vmw_validation_mem *vvm = &dev_priv->vvm; + + vvm->reserve_mem = vmw_vmt_reserve; + vvm->unreserve_mem = vmw_vmt_unreserve; + vvm->gran = gran; +} diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_validation.c b/drivers/gpu/drm/vmwgfx/vmwgfx_validation.c index 184025fa938e..f116f092e00b 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_validation.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_validation.c @@ -104,11 +104,25 @@ void *vmw_validation_mem_alloc(struct vmw_validation_context *ctx, return NULL; if (ctx->mem_size_left < size) { - struct page *page = alloc_page(GFP_KERNEL | __GFP_ZERO); + struct page *page; + if (ctx->vm && ctx->vm_size_left < PAGE_SIZE) { + int ret = ctx->vm->reserve_mem(ctx->vm, ctx->vm->gran); + + if (ret) + return NULL; + + ctx->vm_size_left += ctx->vm->gran; + ctx->total_mem += ctx->vm->gran; + } + + page = alloc_page(GFP_KERNEL | __GFP_ZERO); if (!page) return NULL; + if (ctx->vm) + ctx->vm_size_left -= PAGE_SIZE; + list_add_tail(&page->lru, &ctx->page_list); ctx->page_address = page_address(page); ctx->mem_size_left = PAGE_SIZE; @@ -138,6 +152,11 @@ static void vmw_validation_mem_free(struct vmw_validation_context *ctx) } ctx->mem_size_left = 0; + if (ctx->vm && ctx->total_mem) { + ctx->vm->unreserve_mem(ctx->vm, ctx->total_mem); + ctx->total_mem = 0; + ctx->vm_size_left = 0; + } } /** diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_validation.h b/drivers/gpu/drm/vmwgfx/vmwgfx_validation.h index b57e3292c386..3b396fea40d7 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_validation.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_validation.h @@ -33,6 +33,21 @@ #include #include +/** + * struct vmw_validation_mem - Custom interface to provide memory reservations + * for the validation code. + * @reserve_mem: Callback to reserve memory + * @unreserve_mem: Callback to unreserve memory + * @gran: Reservation granularity. Contains a hint how much memory should + * be reserved in each call to @reserve_mem(). A slow implementation may want + * reservation to be done in large batches. + */ +struct vmw_validation_mem { + int (*reserve_mem)(struct vmw_validation_mem *m, size_t size); + void (*unreserve_mem)(struct vmw_validation_mem *m, size_t size); + size_t gran; +}; + /** * struct vmw_validation_context - Per command submission validation context * @ht: Hash table used to find resource- or buffer object duplicates @@ -47,6 +62,10 @@ * buffer objects * @mem_size_left: Free memory left in the last page in @page_list * @page_address: Kernel virtual address of the last page in @page_list + * @vm: A pointer to the memory reservation interface or NULL if no + * memory reservation is needed. + * @vm_size_left: Amount of reserved memory that so far has not been allocated. + * @total_mem: Amount of reserved memory. */ struct vmw_validation_context { struct drm_open_hash *ht; @@ -59,6 +78,9 @@ struct vmw_validation_context { unsigned int merge_dups; unsigned int mem_size_left; u8 *page_address; + struct vmw_validation_mem *vm; + size_t vm_size_left; + size_t total_mem; }; struct vmw_buffer_object; @@ -101,6 +123,21 @@ vmw_validation_has_bos(struct vmw_validation_context *ctx) return !list_empty(&ctx->bo_list); } +/** + * vmw_validation_set_val_mem - Register a validation mem object for + * validation memory reservation + * @ctx: The validation context + * @vm: Pointer to a struct vmw_validation_mem + * + * Must be set before the first attempt to allocate validation memory. + */ +static inline void +vmw_validation_set_val_mem(struct vmw_validation_context *ctx, + struct vmw_validation_mem *vm) +{ + ctx->vm = vm; +} + /** * vmw_validation_set_ht - Register a hash table for duplicate finding * @ctx: The validation context -- cgit v1.2.3 From 8cfa272b0d321160ebb5b45073e39ef0a6ad73f2 Mon Sep 17 00:00:00 2001 From: Larry Finger Date: Sat, 17 Nov 2018 20:55:03 -0600 Subject: rtlwifi: Fix leak of skb when processing C2H_BT_INFO With commit 0a9f8f0a1ba9 ("rtlwifi: fix btmpinfo timeout while processing C2H_BT_INFO"), calling rtl_c2hcmd_enqueue() with rtl_c2h_fast_cmd() true, the routine returns without freeing that skb, thereby leaking it. This issue has been discussed at https://github.com/lwfinger/rtlwifi_new/issues/401 and the fix tested there. Fixes: 0a9f8f0a1ba9 ("rtlwifi: fix btmpinfo timeout while processing C2H_BT_INFO") Reported-and-tested-by: Francisco Machado Magalhães Neto Cc: Francisco Machado Magalhães Neto Cc: Ping-Ke Shih Cc: Stable # 4.18+ Signed-off-by: Larry Finger Signed-off-by: Kalle Valo --- drivers/net/wireless/realtek/rtlwifi/base.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/wireless/realtek/rtlwifi/base.c b/drivers/net/wireless/realtek/rtlwifi/base.c index f4122c8fdd97..ef9b502ce576 100644 --- a/drivers/net/wireless/realtek/rtlwifi/base.c +++ b/drivers/net/wireless/realtek/rtlwifi/base.c @@ -2289,6 +2289,7 @@ void rtl_c2hcmd_enqueue(struct ieee80211_hw *hw, struct sk_buff *skb) if (rtl_c2h_fast_cmd(hw, skb)) { rtl_c2h_content_parsing(hw, skb); + kfree_skb(skb); return; } -- cgit v1.2.3 From 1aa48f088615ebfa5e139951a0d3e7dc2c2af4ec Mon Sep 17 00:00:00 2001 From: Brian Norris Date: Fri, 30 Nov 2018 09:59:57 -0800 Subject: Revert "mwifiex: restructure rx_reorder_tbl_lock usage" This reverts commit 5188d5453bc9380ccd4ae1086138dd485d13aef2, because it introduced lock recursion: BUG: spinlock recursion on CPU#2, kworker/u13:1/395 lock: 0xffffffc0e28a47f0, .magic: dead4ead, .owner: kworker/u13:1/395, .owner_cpu: 2 CPU: 2 PID: 395 Comm: kworker/u13:1 Not tainted 4.20.0-rc4+ #2 Hardware name: Google Kevin (DT) Workqueue: MWIFIEX_RX_WORK_QUEUE mwifiex_rx_work_queue [mwifiex] Call trace: dump_backtrace+0x0/0x140 show_stack+0x20/0x28 dump_stack+0x84/0xa4 spin_bug+0x98/0xa4 do_raw_spin_lock+0x5c/0xdc _raw_spin_lock_irqsave+0x38/0x48 mwifiex_flush_data+0x2c/0xa4 [mwifiex] call_timer_fn+0xcc/0x1c4 run_timer_softirq+0x264/0x4f0 __do_softirq+0x1a8/0x35c do_softirq+0x54/0x64 netif_rx_ni+0xe8/0x120 mwifiex_recv_packet+0xfc/0x10c [mwifiex] mwifiex_process_rx_packet+0x1d4/0x238 [mwifiex] mwifiex_11n_dispatch_pkt+0x190/0x1ac [mwifiex] mwifiex_11n_rx_reorder_pkt+0x28c/0x354 [mwifiex] mwifiex_process_sta_rx_packet+0x204/0x26c [mwifiex] mwifiex_handle_rx_packet+0x15c/0x16c [mwifiex] mwifiex_rx_work_queue+0x104/0x134 [mwifiex] worker_thread+0x4cc/0x72c kthread+0x134/0x13c ret_from_fork+0x10/0x18 This was clearly not tested well at all. I simply performed 'wget' in a loop and it fell over within a few seconds. Fixes: 5188d5453bc9 ("mwifiex: restructure rx_reorder_tbl_lock usage") Cc: Cc: Ganapathi Bhat Signed-off-by: Brian Norris Signed-off-by: Kalle Valo --- drivers/net/wireless/marvell/mwifiex/11n.c | 5 +- .../net/wireless/marvell/mwifiex/11n_rxreorder.c | 96 +++++++++++----------- drivers/net/wireless/marvell/mwifiex/uap_txrx.c | 3 - 3 files changed, 51 insertions(+), 53 deletions(-) diff --git a/drivers/net/wireless/marvell/mwifiex/11n.c b/drivers/net/wireless/marvell/mwifiex/11n.c index e2addd8b878b..5d75c971004b 100644 --- a/drivers/net/wireless/marvell/mwifiex/11n.c +++ b/drivers/net/wireless/marvell/mwifiex/11n.c @@ -696,11 +696,10 @@ void mwifiex_11n_delba(struct mwifiex_private *priv, int tid) "Send delba to tid=%d, %pM\n", tid, rx_reor_tbl_ptr->ta); mwifiex_send_delba(priv, tid, rx_reor_tbl_ptr->ta, 0); - spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock, - flags); - return; + goto exit; } } +exit: spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock, flags); } diff --git a/drivers/net/wireless/marvell/mwifiex/11n_rxreorder.c b/drivers/net/wireless/marvell/mwifiex/11n_rxreorder.c index 8e63d14c1e1c..5380fba652cc 100644 --- a/drivers/net/wireless/marvell/mwifiex/11n_rxreorder.c +++ b/drivers/net/wireless/marvell/mwifiex/11n_rxreorder.c @@ -103,8 +103,6 @@ static int mwifiex_11n_dispatch_pkt(struct mwifiex_private *priv, void *payload) * There could be holes in the buffer, which are skipped by the function. * Since the buffer is linear, the function uses rotation to simulate * circular buffer. - * - * The caller must hold rx_reorder_tbl_lock spinlock. */ static void mwifiex_11n_dispatch_pkt_until_start_win(struct mwifiex_private *priv, @@ -113,21 +111,25 @@ mwifiex_11n_dispatch_pkt_until_start_win(struct mwifiex_private *priv, { int pkt_to_send, i; void *rx_tmp_ptr; + unsigned long flags; pkt_to_send = (start_win > tbl->start_win) ? min((start_win - tbl->start_win), tbl->win_size) : tbl->win_size; for (i = 0; i < pkt_to_send; ++i) { + spin_lock_irqsave(&priv->rx_reorder_tbl_lock, flags); rx_tmp_ptr = NULL; if (tbl->rx_reorder_ptr[i]) { rx_tmp_ptr = tbl->rx_reorder_ptr[i]; tbl->rx_reorder_ptr[i] = NULL; } + spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock, flags); if (rx_tmp_ptr) mwifiex_11n_dispatch_pkt(priv, rx_tmp_ptr); } + spin_lock_irqsave(&priv->rx_reorder_tbl_lock, flags); /* * We don't have a circular buffer, hence use rotation to simulate * circular buffer @@ -138,6 +140,7 @@ mwifiex_11n_dispatch_pkt_until_start_win(struct mwifiex_private *priv, } tbl->start_win = start_win; + spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock, flags); } /* @@ -147,8 +150,6 @@ mwifiex_11n_dispatch_pkt_until_start_win(struct mwifiex_private *priv, * The start window is adjusted automatically when a hole is located. * Since the buffer is linear, the function uses rotation to simulate * circular buffer. - * - * The caller must hold rx_reorder_tbl_lock spinlock. */ static void mwifiex_11n_scan_and_dispatch(struct mwifiex_private *priv, @@ -156,15 +157,22 @@ mwifiex_11n_scan_and_dispatch(struct mwifiex_private *priv, { int i, j, xchg; void *rx_tmp_ptr; + unsigned long flags; for (i = 0; i < tbl->win_size; ++i) { - if (!tbl->rx_reorder_ptr[i]) + spin_lock_irqsave(&priv->rx_reorder_tbl_lock, flags); + if (!tbl->rx_reorder_ptr[i]) { + spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock, + flags); break; + } rx_tmp_ptr = tbl->rx_reorder_ptr[i]; tbl->rx_reorder_ptr[i] = NULL; + spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock, flags); mwifiex_11n_dispatch_pkt(priv, rx_tmp_ptr); } + spin_lock_irqsave(&priv->rx_reorder_tbl_lock, flags); /* * We don't have a circular buffer, hence use rotation to simulate * circular buffer @@ -177,6 +185,7 @@ mwifiex_11n_scan_and_dispatch(struct mwifiex_private *priv, } } tbl->start_win = (tbl->start_win + i) & (MAX_TID_VALUE - 1); + spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock, flags); } /* @@ -184,8 +193,6 @@ mwifiex_11n_scan_and_dispatch(struct mwifiex_private *priv, * * The function stops the associated timer and dispatches all the * pending packets in the Rx reorder table before deletion. - * - * The caller must hold rx_reorder_tbl_lock spinlock. */ static void mwifiex_del_rx_reorder_entry(struct mwifiex_private *priv, @@ -211,7 +218,11 @@ mwifiex_del_rx_reorder_entry(struct mwifiex_private *priv, del_timer_sync(&tbl->timer_context.timer); tbl->timer_context.timer_is_set = false; + + spin_lock_irqsave(&priv->rx_reorder_tbl_lock, flags); list_del(&tbl->list); + spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock, flags); + kfree(tbl->rx_reorder_ptr); kfree(tbl); @@ -224,17 +235,22 @@ mwifiex_del_rx_reorder_entry(struct mwifiex_private *priv, /* * This function returns the pointer to an entry in Rx reordering * table which matches the given TA/TID pair. - * - * The caller must hold rx_reorder_tbl_lock spinlock. */ struct mwifiex_rx_reorder_tbl * mwifiex_11n_get_rx_reorder_tbl(struct mwifiex_private *priv, int tid, u8 *ta) { struct mwifiex_rx_reorder_tbl *tbl; + unsigned long flags; - list_for_each_entry(tbl, &priv->rx_reorder_tbl_ptr, list) - if (!memcmp(tbl->ta, ta, ETH_ALEN) && tbl->tid == tid) + spin_lock_irqsave(&priv->rx_reorder_tbl_lock, flags); + list_for_each_entry(tbl, &priv->rx_reorder_tbl_ptr, list) { + if (!memcmp(tbl->ta, ta, ETH_ALEN) && tbl->tid == tid) { + spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock, + flags); return tbl; + } + } + spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock, flags); return NULL; } @@ -251,9 +267,14 @@ void mwifiex_11n_del_rx_reorder_tbl_by_ta(struct mwifiex_private *priv, u8 *ta) return; spin_lock_irqsave(&priv->rx_reorder_tbl_lock, flags); - list_for_each_entry_safe(tbl, tmp, &priv->rx_reorder_tbl_ptr, list) - if (!memcmp(tbl->ta, ta, ETH_ALEN)) + list_for_each_entry_safe(tbl, tmp, &priv->rx_reorder_tbl_ptr, list) { + if (!memcmp(tbl->ta, ta, ETH_ALEN)) { + spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock, + flags); mwifiex_del_rx_reorder_entry(priv, tbl); + spin_lock_irqsave(&priv->rx_reorder_tbl_lock, flags); + } + } spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock, flags); return; @@ -262,18 +283,24 @@ void mwifiex_11n_del_rx_reorder_tbl_by_ta(struct mwifiex_private *priv, u8 *ta) /* * This function finds the last sequence number used in the packets * buffered in Rx reordering table. - * - * The caller must hold rx_reorder_tbl_lock spinlock. */ static int mwifiex_11n_find_last_seq_num(struct reorder_tmr_cnxt *ctx) { struct mwifiex_rx_reorder_tbl *rx_reorder_tbl_ptr = ctx->ptr; + struct mwifiex_private *priv = ctx->priv; + unsigned long flags; int i; - for (i = rx_reorder_tbl_ptr->win_size - 1; i >= 0; --i) - if (rx_reorder_tbl_ptr->rx_reorder_ptr[i]) + spin_lock_irqsave(&priv->rx_reorder_tbl_lock, flags); + for (i = rx_reorder_tbl_ptr->win_size - 1; i >= 0; --i) { + if (rx_reorder_tbl_ptr->rx_reorder_ptr[i]) { + spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock, + flags); return i; + } + } + spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock, flags); return -1; } @@ -291,22 +318,17 @@ mwifiex_flush_data(struct timer_list *t) struct reorder_tmr_cnxt *ctx = from_timer(ctx, t, timer); int start_win, seq_num; - unsigned long flags; ctx->timer_is_set = false; - spin_lock_irqsave(&ctx->priv->rx_reorder_tbl_lock, flags); seq_num = mwifiex_11n_find_last_seq_num(ctx); - if (seq_num < 0) { - spin_unlock_irqrestore(&ctx->priv->rx_reorder_tbl_lock, flags); + if (seq_num < 0) return; - } mwifiex_dbg(ctx->priv->adapter, INFO, "info: flush data %d\n", seq_num); start_win = (ctx->ptr->start_win + seq_num + 1) & (MAX_TID_VALUE - 1); mwifiex_11n_dispatch_pkt_until_start_win(ctx->priv, ctx->ptr, start_win); - spin_unlock_irqrestore(&ctx->priv->rx_reorder_tbl_lock, flags); } /* @@ -333,14 +355,11 @@ mwifiex_11n_create_rx_reorder_tbl(struct mwifiex_private *priv, u8 *ta, * If we get a TID, ta pair which is already present dispatch all the * the packets and move the window size until the ssn */ - spin_lock_irqsave(&priv->rx_reorder_tbl_lock, flags); tbl = mwifiex_11n_get_rx_reorder_tbl(priv, tid, ta); if (tbl) { mwifiex_11n_dispatch_pkt_until_start_win(priv, tbl, seq_num); - spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock, flags); return; } - spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock, flags); /* if !tbl then create one */ new_node = kzalloc(sizeof(struct mwifiex_rx_reorder_tbl), GFP_KERNEL); if (!new_node) @@ -551,20 +570,16 @@ int mwifiex_11n_rx_reorder_pkt(struct mwifiex_private *priv, int prev_start_win, start_win, end_win, win_size; u16 pkt_index; bool init_window_shift = false; - unsigned long flags; int ret = 0; - spin_lock_irqsave(&priv->rx_reorder_tbl_lock, flags); tbl = mwifiex_11n_get_rx_reorder_tbl(priv, tid, ta); if (!tbl) { - spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock, flags); if (pkt_type != PKT_TYPE_BAR) mwifiex_11n_dispatch_pkt(priv, payload); return ret; } if ((pkt_type == PKT_TYPE_AMSDU) && !tbl->amsdu) { - spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock, flags); mwifiex_11n_dispatch_pkt(priv, payload); return ret; } @@ -651,8 +666,6 @@ done: if (!tbl->timer_context.timer_is_set || prev_start_win != tbl->start_win) mwifiex_11n_rxreorder_timer_restart(tbl); - - spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock, flags); return ret; } @@ -681,18 +694,14 @@ mwifiex_del_ba_tbl(struct mwifiex_private *priv, int tid, u8 *peer_mac, peer_mac, tid, initiator); if (cleanup_rx_reorder_tbl) { - spin_lock_irqsave(&priv->rx_reorder_tbl_lock, flags); tbl = mwifiex_11n_get_rx_reorder_tbl(priv, tid, peer_mac); if (!tbl) { - spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock, - flags); mwifiex_dbg(priv->adapter, EVENT, "event: TID, TA not found in table\n"); return; } mwifiex_del_rx_reorder_entry(priv, tbl); - spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock, flags); } else { ptx_tbl = mwifiex_get_ba_tbl(priv, tid, peer_mac); if (!ptx_tbl) { @@ -726,7 +735,6 @@ int mwifiex_ret_11n_addba_resp(struct mwifiex_private *priv, int tid, win_size; struct mwifiex_rx_reorder_tbl *tbl; uint16_t block_ack_param_set; - unsigned long flags; block_ack_param_set = le16_to_cpu(add_ba_rsp->block_ack_param_set); @@ -740,20 +748,17 @@ int mwifiex_ret_11n_addba_resp(struct mwifiex_private *priv, mwifiex_dbg(priv->adapter, ERROR, "ADDBA RSP: failed %pM tid=%d)\n", add_ba_rsp->peer_mac_addr, tid); - spin_lock_irqsave(&priv->rx_reorder_tbl_lock, flags); tbl = mwifiex_11n_get_rx_reorder_tbl(priv, tid, add_ba_rsp->peer_mac_addr); if (tbl) mwifiex_del_rx_reorder_entry(priv, tbl); - spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock, flags); return 0; } win_size = (block_ack_param_set & IEEE80211_ADDBA_PARAM_BUF_SIZE_MASK) >> BLOCKACKPARAM_WINSIZE_POS; - spin_lock_irqsave(&priv->rx_reorder_tbl_lock, flags); tbl = mwifiex_11n_get_rx_reorder_tbl(priv, tid, add_ba_rsp->peer_mac_addr); if (tbl) { @@ -764,7 +769,6 @@ int mwifiex_ret_11n_addba_resp(struct mwifiex_private *priv, else tbl->amsdu = false; } - spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock, flags); mwifiex_dbg(priv->adapter, CMD, "cmd: ADDBA RSP: %pM tid=%d ssn=%d win_size=%d\n", @@ -804,8 +808,11 @@ void mwifiex_11n_cleanup_reorder_tbl(struct mwifiex_private *priv) spin_lock_irqsave(&priv->rx_reorder_tbl_lock, flags); list_for_each_entry_safe(del_tbl_ptr, tmp_node, - &priv->rx_reorder_tbl_ptr, list) + &priv->rx_reorder_tbl_ptr, list) { + spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock, flags); mwifiex_del_rx_reorder_entry(priv, del_tbl_ptr); + spin_lock_irqsave(&priv->rx_reorder_tbl_lock, flags); + } INIT_LIST_HEAD(&priv->rx_reorder_tbl_ptr); spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock, flags); @@ -929,7 +936,6 @@ void mwifiex_11n_rxba_sync_event(struct mwifiex_private *priv, int tlv_buf_left = len; int ret; u8 *tmp; - unsigned long flags; mwifiex_dbg_dump(priv->adapter, EVT_D, "RXBA_SYNC event:", event_buf, len); @@ -949,18 +955,14 @@ void mwifiex_11n_rxba_sync_event(struct mwifiex_private *priv, tlv_rxba->mac, tlv_rxba->tid, tlv_seq_num, tlv_bitmap_len); - spin_lock_irqsave(&priv->rx_reorder_tbl_lock, flags); rx_reor_tbl_ptr = mwifiex_11n_get_rx_reorder_tbl(priv, tlv_rxba->tid, tlv_rxba->mac); if (!rx_reor_tbl_ptr) { - spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock, - flags); mwifiex_dbg(priv->adapter, ERROR, "Can not find rx_reorder_tbl!"); return; } - spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock, flags); for (i = 0; i < tlv_bitmap_len; i++) { for (j = 0 ; j < 8; j++) { diff --git a/drivers/net/wireless/marvell/mwifiex/uap_txrx.c b/drivers/net/wireless/marvell/mwifiex/uap_txrx.c index a83c5afc256a..5ce85d5727e4 100644 --- a/drivers/net/wireless/marvell/mwifiex/uap_txrx.c +++ b/drivers/net/wireless/marvell/mwifiex/uap_txrx.c @@ -421,15 +421,12 @@ int mwifiex_process_uap_rx_packet(struct mwifiex_private *priv, spin_unlock_irqrestore(&priv->sta_list_spinlock, flags); } - spin_lock_irqsave(&priv->rx_reorder_tbl_lock, flags); if (!priv->ap_11n_enabled || (!mwifiex_11n_get_rx_reorder_tbl(priv, uap_rx_pd->priority, ta) && (le16_to_cpu(uap_rx_pd->rx_pkt_type) != PKT_TYPE_AMSDU))) { ret = mwifiex_handle_uap_rx_forward(priv, skb); - spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock, flags); return ret; } - spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock, flags); /* Reorder and send to kernel */ pkt_type = (u8)le16_to_cpu(uap_rx_pd->rx_pkt_type); -- cgit v1.2.3 From 7c250f4612ae97aa04500c0d0cff69bb87046e3a Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Fri, 16 Nov 2018 17:19:21 +0100 Subject: mt76: fix potential NULL pointer dereference in mt76_stop_tx_queues Starting from mac80211 commit adf8ed01e4fd ("mac80211: add an optional TXQ for other PS-buffered frames") and commit 0eeb2b674f05 ("mac80211: add an option for station management TXQ") a new per-sta queue has been introduced for bufferable management frames. sta->txq[IEEE80211_NUM_TIDS] is initialized just if the driver reports the following hw flags: - IEEE80211_HW_STA_MMPDU_TXQ - IEEE80211_HW_BUFF_MMPDU_TXQ This can produce a NULL pointer dereference in mt76_stop_tx_queues since mt76 iterates on all available sta tx queues assuming they are initialized by mac80211. This issue has been spotted analyzing the code (it has not triggered any crash yet) Signed-off-by: Lorenzo Bianconi Signed-off-by: Kalle Valo --- drivers/net/wireless/mediatek/mt76/tx.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/net/wireless/mediatek/mt76/tx.c b/drivers/net/wireless/mediatek/mt76/tx.c index 7cbce03aa65b..aa426b838ffa 100644 --- a/drivers/net/wireless/mediatek/mt76/tx.c +++ b/drivers/net/wireless/mediatek/mt76/tx.c @@ -400,7 +400,12 @@ void mt76_stop_tx_queues(struct mt76_dev *dev, struct ieee80211_sta *sta, for (i = 0; i < ARRAY_SIZE(sta->txq); i++) { struct ieee80211_txq *txq = sta->txq[i]; - struct mt76_txq *mtxq = (struct mt76_txq *) txq->drv_priv; + struct mt76_txq *mtxq; + + if (!txq) + continue; + + mtxq = (struct mt76_txq *)txq->drv_priv; spin_lock_bh(&mtxq->hwq->lock); mtxq->send_bar = mtxq->aggr && send_bar; -- cgit v1.2.3 From cddfb283af7e5700760362ec6f6ab3a039636e64 Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Mon, 10 Dec 2018 16:46:28 +0100 Subject: mt76: add entry in MAINTAINERS file Add entry for mt76 driver in MAINTAINERS file Signed-off-by: Lorenzo Bianconi Signed-off-by: Kalle Valo --- MAINTAINERS | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index 380e43f585d3..3e1e51d84544 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -9378,6 +9378,13 @@ F: drivers/media/platform/mtk-vpu/ F: Documentation/devicetree/bindings/media/mediatek-vcodec.txt F: Documentation/devicetree/bindings/media/mediatek-vpu.txt +MEDIATEK MT76 WIRELESS LAN DRIVER +M: Felix Fietkau +M: Lorenzo Bianconi +L: linux-wireless@vger.kernel.org +S: Maintained +F: drivers/net/wireless/mediatek/mt76/ + MEDIATEK MT7601U WIRELESS LAN DRIVER M: Jakub Kicinski L: linux-wireless@vger.kernel.org -- cgit v1.2.3 From 7640ead939247e91e84b7ec6ec001f30193cc7df Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 12 Dec 2018 16:29:07 -0800 Subject: bpf: verifier: make sure callees don't prune with caller differences Currently for liveness and state pruning the register parentage chains don't include states of the callee. This makes some sense as the callee can't access those registers. However, this means that READs done after the callee returns will not propagate into the states of the callee. Callee will then perform pruning disregarding differences in caller state. Example: 0: (85) call bpf_user_rnd_u32 1: (b7) r8 = 0 2: (55) if r0 != 0x0 goto pc+1 3: (b7) r8 = 1 4: (bf) r1 = r8 5: (85) call pc+4 6: (15) if r8 == 0x1 goto pc+1 7: (05) *(u64 *)(r9 - 8) = r3 8: (b7) r0 = 0 9: (95) exit 10: (15) if r1 == 0x0 goto pc+0 11: (95) exit Here we acquire unknown state with call to get_random() [1]. Then we store this random state in r8 (either 0 or 1) [1 - 3], and make a call on line 5. Callee does nothing but a trivial conditional jump (to create a pruning point). Upon return caller checks the state of r8 and either performs an unsafe read or not. Verifier will first explore the path with r8 == 1, creating a pruning point at [11]. The parentage chain for r8 will include only callers states so once verifier reaches [6] it will mark liveness only on states in the caller, and not [11]. Now when verifier walks the paths with r8 == 0 it will reach [11] and since REG_LIVE_READ on r8 was not propagated there it will prune the walk entirely (stop walking the entire program, not just the callee). Since [6] was never walked with r8 == 0, [7] will be considered dead and replaced with "goto -1" causing hang at runtime. This patch weaves the callee's explored states onto the callers parentage chain. Rough parentage for r8 would have looked like this before: [0] [1] [2] [3] [4] [5] [10] [11] [6] [7] | | ,---|----. | | | sl0: sl0: / sl0: \ sl0: sl0: sl0: fr0: r8 <-- fr0: r8<+--fr0: r8 `fr0: r8 ,fr0: r8<-fr0: r8 \ fr1: r8 <- fr1: r8 / \__________________/ after: [0] [1] [2] [3] [4] [5] [10] [11] [6] [7] | | | | | | sl0: sl0: sl0: sl0: sl0: sl0: fr0: r8 <-- fr0: r8 <- fr0: r8 <- fr0: r8 <-fr0: r8<-fr0: r8 fr1: r8 <- fr1: r8 Now the mark from instruction 6 will travel through callees states. Note that we don't have to connect r0 because its overwritten by callees state on return and r1 - r5 because those are not alive any more once a call is made. v2: - don't connect the callees registers twice (Alexei: suggestion & code) - add more details to the comment (Ed & Alexei) v1: don't unnecessarily link caller saved regs (Jiong) Fixes: f4d7e40a5b71 ("bpf: introduce function calls (verification)") Reported-by: David Beckett Signed-off-by: Jakub Kicinski Reviewed-by: Jiong Wang Reviewed-by: Edward Cree Signed-off-by: Alexei Starovoitov --- kernel/bpf/verifier.c | 13 ++++++++++--- tools/testing/selftests/bpf/test_verifier.c | 28 ++++++++++++++++++++++++++++ 2 files changed, 38 insertions(+), 3 deletions(-) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index fc760d00a38c..51ba84d4d34a 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -5102,9 +5102,16 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) } new_sl->next = env->explored_states[insn_idx]; env->explored_states[insn_idx] = new_sl; - /* connect new state to parentage chain */ - for (i = 0; i < BPF_REG_FP; i++) - cur_regs(env)[i].parent = &new->frame[new->curframe]->regs[i]; + /* connect new state to parentage chain. Current frame needs all + * registers connected. Only r6 - r9 of the callers are alive (pushed + * to the stack implicitly by JITs) so in callers' frames connect just + * r6 - r9 as an optimization. Callers will have r1 - r5 connected to + * the state of the call instruction (with WRITTEN set), and r0 comes + * from callee with its full parentage chain, anyway. + */ + for (j = 0; j <= cur->curframe; j++) + for (i = j < cur->curframe ? BPF_REG_6 : 0; i < BPF_REG_FP; i++) + cur->frame[j]->regs[i].parent = &new->frame[j]->regs[i]; /* clear write marks in current state: the writes we did are not writes * our child did, so they don't screen off its reads from us. * (There are no read marks in current state, because reads always mark diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index 37583267bdbc..f8eac4a544f4 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -13915,6 +13915,34 @@ static struct bpf_test tests[] = { .result_unpriv = REJECT, .result = ACCEPT, }, + { + "calls: cross frame pruning", + .insns = { + /* r8 = !!random(); + * call pruner() + * if (r8) + * do something bad; + */ + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_get_prandom_u32), + BPF_MOV64_IMM(BPF_REG_8, 0), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_MOV64_IMM(BPF_REG_8, 1), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_8), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 4), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_8, 1, 1), + BPF_LDX_MEM(BPF_B, BPF_REG_9, BPF_REG_1, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SOCKET_FILTER, + .errstr_unpriv = "function calls to other bpf functions are allowed for root only", + .result_unpriv = REJECT, + .errstr = "!read_ok", + .result = REJECT, + }, }; static int probe_filter_length(const struct bpf_insn *fp) -- cgit v1.2.3 From 48483614de97c4f5219abeda630e62b2bebdce62 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Thu, 13 Dec 2018 13:57:42 -0500 Subject: XArray: Fix xa_alloc when id exceeds max Specifying a starting ID greater than the maximum ID isn't something attempted very often, but it should fail. It was succeeding due to xas_find_marked() returning the wrong error state, so add tests for both xa_alloc() and xas_find_marked(). Fixes: b803b42823d0 ("xarray: Add XArray iterators") Signed-off-by: Matthew Wilcox --- lib/test_xarray.c | 33 +++++++++++++++++++++++++++++++++ lib/xarray.c | 8 +++----- 2 files changed, 36 insertions(+), 5 deletions(-) diff --git a/lib/test_xarray.c b/lib/test_xarray.c index 6f09c845187e..4676c0a1eeca 100644 --- a/lib/test_xarray.c +++ b/lib/test_xarray.c @@ -633,6 +633,15 @@ static noinline void check_xa_alloc(void) GFP_KERNEL) != -ENOSPC); XA_BUG_ON(&xa0, id != 0xffffffffU); xa_destroy(&xa0); + + id = 10; + XA_BUG_ON(&xa0, xa_alloc(&xa0, &id, 5, xa_mk_index(id), + GFP_KERNEL) != -ENOSPC); + XA_BUG_ON(&xa0, xa_store_index(&xa0, 3, GFP_KERNEL) != 0); + XA_BUG_ON(&xa0, xa_alloc(&xa0, &id, 5, xa_mk_index(id), + GFP_KERNEL) != -ENOSPC); + xa_erase_index(&xa0, 3); + XA_BUG_ON(&xa0, !xa_empty(&xa0)); } static noinline void __check_store_iter(struct xarray *xa, unsigned long start, @@ -822,10 +831,34 @@ static noinline void check_find_2(struct xarray *xa) xa_destroy(xa); } +static noinline void check_find_3(struct xarray *xa) +{ + XA_STATE(xas, xa, 0); + unsigned long i, j, k; + void *entry; + + for (i = 0; i < 100; i++) { + for (j = 0; j < 100; j++) { + for (k = 0; k < 100; k++) { + xas_set(&xas, j); + xas_for_each_marked(&xas, entry, k, XA_MARK_0) + ; + if (j > k) + XA_BUG_ON(xa, + xas.xa_node != XAS_RESTART); + } + } + xa_store_index(xa, i, GFP_KERNEL); + xa_set_mark(xa, i, XA_MARK_0); + } + xa_destroy(xa); +} + static noinline void check_find(struct xarray *xa) { check_find_1(xa); check_find_2(xa); + check_find_3(xa); check_multi_find(xa); check_multi_find_2(xa); } diff --git a/lib/xarray.c b/lib/xarray.c index bbacca576593..5f3f9311de89 100644 --- a/lib/xarray.c +++ b/lib/xarray.c @@ -1131,7 +1131,7 @@ void *xas_find_marked(struct xa_state *xas, unsigned long max, xa_mark_t mark) entry = xa_head(xas->xa); xas->xa_node = NULL; if (xas->xa_index > max_index(entry)) - goto bounds; + goto out; if (!xa_is_node(entry)) { if (xa_marked(xas->xa, mark)) return entry; @@ -1180,11 +1180,9 @@ void *xas_find_marked(struct xa_state *xas, unsigned long max, xa_mark_t mark) } out: - if (!max) + if (xas->xa_index > max) goto max; -bounds: - xas->xa_node = XAS_BOUNDS; - return NULL; + return set_bounds(xas); max: xas->xa_node = XAS_RESTART; return NULL; -- cgit v1.2.3 From 28a86092b1753b802ef7e3de8a4c4a69a9c1bb03 Mon Sep 17 00:00:00 2001 From: Jörgen Storvist Date: Thu, 13 Dec 2018 17:32:08 +0100 Subject: USB: serial: option: add Telit LN940 series Added USB serial option driver support for Telit LN940 series cellular modules. Covering both QMI and MBIM modes. usb-devices output (0x1900): T: Bus=01 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#= 21 Spd=480 MxCh= 0 D: Ver= 2.00 Cls=ef(misc ) Sub=02 Prot=01 MxPS=64 #Cfgs= 1 P: Vendor=1bc7 ProdID=1900 Rev=03.10 S: Manufacturer=Telit S: Product=Telit LN940 Mobile Broadband S: SerialNumber=0123456789ABCDEF C: #Ifs= 5 Cfg#= 1 Atr=a0 MxPwr=500mA I: If#= 0 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option I: If#= 1 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=qmi_wwan I: If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option I: If#= 3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option I: If#= 4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option usb-devices output (0x1901): T: Bus=01 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#= 20 Spd=480 MxCh= 0 D: Ver= 2.00 Cls=ef(misc ) Sub=02 Prot=01 MxPS=64 #Cfgs= 1 P: Vendor=1bc7 ProdID=1901 Rev=03.10 S: Manufacturer=Telit S: Product=Telit LN940 Mobile Broadband S: SerialNumber=0123456789ABCDEF C: #Ifs= 6 Cfg#= 1 Atr=a0 MxPwr=500mA I: If#= 0 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option I: If#= 1 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option I: If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option I: If#= 3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option I: If#= 4 Alt= 0 #EPs= 1 Cls=02(commc) Sub=0e Prot=00 Driver=cdc_mbim I: If#= 5 Alt= 1 #EPs= 2 Cls=0a(data ) Sub=00 Prot=02 Driver=cdc_mbim Signed-off-by: Jörgen Storvist Cc: stable Signed-off-by: Johan Hovold --- drivers/usb/serial/option.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 2304433d5021..1ce27f3ff7a7 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -1164,6 +1164,10 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, TELIT_PRODUCT_LE920A4_1213, 0xff) }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE920A4_1214), .driver_info = NCTRL(0) | RSVD(1) | RSVD(2) | RSVD(3) }, + { USB_DEVICE(TELIT_VENDOR_ID, 0x1900), /* Telit LN940 (QMI) */ + .driver_info = NCTRL(0) | RSVD(1) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1901, 0xff), /* Telit LN940 (MBIM) */ + .driver_info = NCTRL(0) }, { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_MF622, 0xff, 0xff, 0xff) }, /* ZTE WCDMA products */ { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0002, 0xff, 0xff, 0xff), .driver_info = RSVD(1) }, -- cgit v1.2.3 From c629421a990033ba539eb8585e73a2e6fa9ea631 Mon Sep 17 00:00:00 2001 From: Sinan Kaya Date: Sat, 1 Dec 2018 21:40:38 +0000 Subject: x86, hyperv: remove PCI dependency Need to be able to boot without PCI devices present. Signed-off-by: Sinan Kaya Signed-off-by: Sasha Levin --- drivers/hv/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/hv/Kconfig b/drivers/hv/Kconfig index 97954f575c3f..1c1a2514d6f3 100644 --- a/drivers/hv/Kconfig +++ b/drivers/hv/Kconfig @@ -4,7 +4,7 @@ menu "Microsoft Hyper-V guest support" config HYPERV tristate "Microsoft Hyper-V client drivers" - depends on X86 && ACPI && PCI && X86_LOCAL_APIC && HYPERVISOR_GUEST + depends on X86 && ACPI && X86_LOCAL_APIC && HYPERVISOR_GUEST select PARAVIRT help Select this option to run Linux as a Hyper-V client operating -- cgit v1.2.3 From fc96df16a1ce80cbb3c316ab7d4dc8cd5c2852ce Mon Sep 17 00:00:00 2001 From: Dexuan Cui Date: Thu, 13 Dec 2018 16:35:43 +0000 Subject: Drivers: hv: vmbus: Return -EINVAL for the sys files for unopened channels Before 98f4c651762c, we returned zeros for unopened channels. With 98f4c651762c, we started to return random on-stack values. We'd better return -EINVAL instead. Fixes: 98f4c651762c ("hv: move ringbuffer bus attributes to dev_groups") Cc: stable@vger.kernel.org Cc: K. Y. Srinivasan Cc: Haiyang Zhang Cc: Stephen Hemminger Signed-off-by: Dexuan Cui Signed-off-by: Sasha Levin --- drivers/hv/vmbus_drv.c | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index 283d184280af..d0ff65675292 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -316,6 +316,8 @@ static ssize_t out_intr_mask_show(struct device *dev, if (!hv_dev->channel) return -ENODEV; + if (hv_dev->channel->state != CHANNEL_OPENED_STATE) + return -EINVAL; hv_ringbuffer_get_debuginfo(&hv_dev->channel->outbound, &outbound); return sprintf(buf, "%d\n", outbound.current_interrupt_mask); } @@ -329,6 +331,8 @@ static ssize_t out_read_index_show(struct device *dev, if (!hv_dev->channel) return -ENODEV; + if (hv_dev->channel->state != CHANNEL_OPENED_STATE) + return -EINVAL; hv_ringbuffer_get_debuginfo(&hv_dev->channel->outbound, &outbound); return sprintf(buf, "%d\n", outbound.current_read_index); } @@ -343,6 +347,8 @@ static ssize_t out_write_index_show(struct device *dev, if (!hv_dev->channel) return -ENODEV; + if (hv_dev->channel->state != CHANNEL_OPENED_STATE) + return -EINVAL; hv_ringbuffer_get_debuginfo(&hv_dev->channel->outbound, &outbound); return sprintf(buf, "%d\n", outbound.current_write_index); } @@ -357,6 +363,8 @@ static ssize_t out_read_bytes_avail_show(struct device *dev, if (!hv_dev->channel) return -ENODEV; + if (hv_dev->channel->state != CHANNEL_OPENED_STATE) + return -EINVAL; hv_ringbuffer_get_debuginfo(&hv_dev->channel->outbound, &outbound); return sprintf(buf, "%d\n", outbound.bytes_avail_toread); } @@ -371,6 +379,8 @@ static ssize_t out_write_bytes_avail_show(struct device *dev, if (!hv_dev->channel) return -ENODEV; + if (hv_dev->channel->state != CHANNEL_OPENED_STATE) + return -EINVAL; hv_ringbuffer_get_debuginfo(&hv_dev->channel->outbound, &outbound); return sprintf(buf, "%d\n", outbound.bytes_avail_towrite); } @@ -384,6 +394,8 @@ static ssize_t in_intr_mask_show(struct device *dev, if (!hv_dev->channel) return -ENODEV; + if (hv_dev->channel->state != CHANNEL_OPENED_STATE) + return -EINVAL; hv_ringbuffer_get_debuginfo(&hv_dev->channel->inbound, &inbound); return sprintf(buf, "%d\n", inbound.current_interrupt_mask); } @@ -397,6 +409,8 @@ static ssize_t in_read_index_show(struct device *dev, if (!hv_dev->channel) return -ENODEV; + if (hv_dev->channel->state != CHANNEL_OPENED_STATE) + return -EINVAL; hv_ringbuffer_get_debuginfo(&hv_dev->channel->inbound, &inbound); return sprintf(buf, "%d\n", inbound.current_read_index); } @@ -410,6 +424,8 @@ static ssize_t in_write_index_show(struct device *dev, if (!hv_dev->channel) return -ENODEV; + if (hv_dev->channel->state != CHANNEL_OPENED_STATE) + return -EINVAL; hv_ringbuffer_get_debuginfo(&hv_dev->channel->inbound, &inbound); return sprintf(buf, "%d\n", inbound.current_write_index); } @@ -424,6 +440,8 @@ static ssize_t in_read_bytes_avail_show(struct device *dev, if (!hv_dev->channel) return -ENODEV; + if (hv_dev->channel->state != CHANNEL_OPENED_STATE) + return -EINVAL; hv_ringbuffer_get_debuginfo(&hv_dev->channel->inbound, &inbound); return sprintf(buf, "%d\n", inbound.bytes_avail_toread); } @@ -438,6 +456,8 @@ static ssize_t in_write_bytes_avail_show(struct device *dev, if (!hv_dev->channel) return -ENODEV; + if (hv_dev->channel->state != CHANNEL_OPENED_STATE) + return -EINVAL; hv_ringbuffer_get_debuginfo(&hv_dev->channel->inbound, &inbound); return sprintf(buf, "%d\n", inbound.bytes_avail_towrite); } -- cgit v1.2.3 From c3db8d531045774aeee6e0f731ab15b0c450de45 Mon Sep 17 00:00:00 2001 From: Sudarsana Reddy Kalluru Date: Sun, 9 Dec 2018 23:27:01 -0800 Subject: qed: Fix command number mismatch between driver and the mfw The value for OEM_CFG_UPDATE command differs between driver and the Management firmware (mfw). Fix this gap with adding a reserved field. Fixes: cac6f691546b ("qed: Add support for Unified Fabric Port.") Signed-off-by: Sudarsana Reddy Kalluru Signed-off-by: Ariel Elior Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed_hsi.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/qlogic/qed/qed_hsi.h b/drivers/net/ethernet/qlogic/qed/qed_hsi.h index 5c221ebaa7b3..b38e12c9de9d 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_hsi.h +++ b/drivers/net/ethernet/qlogic/qed/qed_hsi.h @@ -12831,8 +12831,9 @@ enum MFW_DRV_MSG_TYPE { MFW_DRV_MSG_BW_UPDATE10, MFW_DRV_MSG_TRANSCEIVER_STATE_CHANGE, MFW_DRV_MSG_BW_UPDATE11, - MFW_DRV_MSG_OEM_CFG_UPDATE, + MFW_DRV_MSG_RESERVED, MFW_DRV_MSG_GET_TLV_REQ, + MFW_DRV_MSG_OEM_CFG_UPDATE, MFW_DRV_MSG_MAX }; -- cgit v1.2.3 From 45f750c16cae3625014c14c77bd9005eda975d35 Mon Sep 17 00:00:00 2001 From: Mathias Nyman Date: Fri, 14 Dec 2018 10:54:43 +0200 Subject: xhci: Don't prevent USB2 bus suspend in state check intended for USB3 only The code to prevent a bus suspend if a USB3 port was still in link training also reacted to USB2 port polling state. This caused bus suspend to busyloop in some cases. USB2 polling state is different from USB3, and should not prevent bus suspend. Limit the USB3 link training state check to USB3 root hub ports only. The origial commit went to stable so this need to be applied there as well Fixes: 2f31a67f01a8 ("usb: xhci: Prevent bus suspend if a port connect change or polling state is detected") Cc: stable@vger.kernel.org Signed-off-by: Mathias Nyman Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci-hub.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c index 94aca1b5ac8a..01b5818a4be5 100644 --- a/drivers/usb/host/xhci-hub.c +++ b/drivers/usb/host/xhci-hub.c @@ -1507,7 +1507,8 @@ int xhci_bus_suspend(struct usb_hcd *hcd) portsc_buf[port_index] = 0; /* Bail out if a USB3 port has a new device in link training */ - if ((t1 & PORT_PLS_MASK) == XDEV_POLLING) { + if ((hcd->speed >= HCD_USB3) && + (t1 & PORT_PLS_MASK) == XDEV_POLLING) { bus_state->bus_suspended = 0; spin_unlock_irqrestore(&xhci->lock, flags); xhci_dbg(xhci, "Bus suspend bailout, port in polling\n"); -- cgit v1.2.3 From 1063a5148ac9d1606e80886fa53ee57d45fb4589 Mon Sep 17 00:00:00 2001 From: Yanjiang Jin Date: Fri, 14 Dec 2018 11:29:37 -0600 Subject: PCI/AER: Queue one GHES event, not several uninitialized ones ecae65e133f2 ("PCI/AER: Use kfifo_in_spinlocked() to insert locked elements") replaced kfifo_put() with kfifo_in_spinlocked(), but passed the *size* of the queue entry, where kfifo_in_spinlocked() expects the *number* of entries to be copied. We want to insert only one element into kfifo, not "sizeof(entry) = 16". Without this patch, we would get 15 uninitialized elements. Fixes: ecae65e133f2 ("PCI/AER: Use kfifo_in_spinlocked() to insert locked elements") Signed-off-by: Yanjiang Jin [bhelgaas: changelog] Signed-off-by: Bjorn Helgaas Reviewed-by: Keith Busch --- drivers/pci/pcie/aer.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c index a90a9194ac4a..fed29de783e0 100644 --- a/drivers/pci/pcie/aer.c +++ b/drivers/pci/pcie/aer.c @@ -1064,7 +1064,7 @@ void aer_recover_queue(int domain, unsigned int bus, unsigned int devfn, .regs = aer_regs, }; - if (kfifo_in_spinlocked(&aer_recover_ring, &entry, sizeof(entry), + if (kfifo_in_spinlocked(&aer_recover_ring, &entry, 1, &aer_recover_ring_lock)) schedule_work(&aer_recover_work); else -- cgit v1.2.3 From d3e8869ec82645599e6497d6974593bf00f7b19b Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 14 Dec 2018 11:38:48 -0800 Subject: net: netlink: rename NETLINK_DUMP_STRICT_CHK -> NETLINK_GET_STRICT_CHK NETLINK_DUMP_STRICT_CHK can be used for all GET requests, dumps as well as doit handlers. Replace the DUMP in the name with GET make that clearer. Signed-off-by: Jakub Kicinski Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/uapi/linux/netlink.h | 2 +- net/netlink/af_netlink.c | 4 ++-- tools/include/uapi/linux/netlink.h | 2 +- 3 files changed, 4 insertions(+), 4 deletions(-) diff --git a/include/uapi/linux/netlink.h b/include/uapi/linux/netlink.h index 486ed1f0c0bc..0a4d73317759 100644 --- a/include/uapi/linux/netlink.h +++ b/include/uapi/linux/netlink.h @@ -155,7 +155,7 @@ enum nlmsgerr_attrs { #define NETLINK_LIST_MEMBERSHIPS 9 #define NETLINK_CAP_ACK 10 #define NETLINK_EXT_ACK 11 -#define NETLINK_DUMP_STRICT_CHK 12 +#define NETLINK_GET_STRICT_CHK 12 struct nl_pktinfo { __u32 group; diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 6bb9f3cde0b0..3c023d6120f6 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1706,7 +1706,7 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname, nlk->flags &= ~NETLINK_F_EXT_ACK; err = 0; break; - case NETLINK_DUMP_STRICT_CHK: + case NETLINK_GET_STRICT_CHK: if (val) nlk->flags |= NETLINK_F_STRICT_CHK; else @@ -1806,7 +1806,7 @@ static int netlink_getsockopt(struct socket *sock, int level, int optname, return -EFAULT; err = 0; break; - case NETLINK_DUMP_STRICT_CHK: + case NETLINK_GET_STRICT_CHK: if (len < sizeof(int)) return -EINVAL; len = sizeof(int); diff --git a/tools/include/uapi/linux/netlink.h b/tools/include/uapi/linux/netlink.h index 486ed1f0c0bc..0a4d73317759 100644 --- a/tools/include/uapi/linux/netlink.h +++ b/tools/include/uapi/linux/netlink.h @@ -155,7 +155,7 @@ enum nlmsgerr_attrs { #define NETLINK_LIST_MEMBERSHIPS 9 #define NETLINK_CAP_ACK 10 #define NETLINK_EXT_ACK 11 -#define NETLINK_DUMP_STRICT_CHK 12 +#define NETLINK_GET_STRICT_CHK 12 struct nl_pktinfo { __u32 group; -- cgit v1.2.3 From 15ef70e286176165d28b0b8a969b422561a68dfc Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Mon, 10 Dec 2018 11:49:55 -0800 Subject: tipc: use lock_sock() in tipc_sk_reinit() lock_sock() must be used in process context to be race-free with other lock_sock() callers, for example, tipc_release(). Otherwise using the spinlock directly can't serialize a parallel tipc_release(). As it is blocking, we have to hold the sock refcnt before rhashtable_walk_stop() and release it after rhashtable_walk_start(). Fixes: 07f6c4bc048a ("tipc: convert tipc reference table to use generic rhashtable") Reported-by: Dmitry Vyukov Cc: Ying Xue Cc: Jon Maloy Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- net/tipc/socket.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/net/tipc/socket.c b/net/tipc/socket.c index b57b1be7252b..e1396fb87779 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -2724,11 +2724,15 @@ void tipc_sk_reinit(struct net *net) rhashtable_walk_start(&iter); while ((tsk = rhashtable_walk_next(&iter)) && !IS_ERR(tsk)) { - spin_lock_bh(&tsk->sk.sk_lock.slock); + sock_hold(&tsk->sk); + rhashtable_walk_stop(&iter); + lock_sock(&tsk->sk); msg = &tsk->phdr; msg_set_prevnode(msg, tipc_own_addr(net)); msg_set_orignode(msg, tipc_own_addr(net)); - spin_unlock_bh(&tsk->sk.sk_lock.slock); + release_sock(&tsk->sk); + rhashtable_walk_start(&iter); + sock_put(&tsk->sk); } rhashtable_walk_stop(&iter); -- cgit v1.2.3 From acb4a33e9856d5fa3384b87d3d8369229be06d31 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Mon, 10 Dec 2018 12:45:45 -0800 Subject: tipc: fix a double kfree_skb() tipc_udp_xmit() drops the packet on error, there is no need to drop it again. Fixes: ef20cd4dd163 ("tipc: introduce UDP replicast") Reported-and-tested-by: syzbot+eae585ba2cc2752d3704@syzkaller.appspotmail.com Cc: Ying Xue Cc: Jon Maloy Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- net/tipc/udp_media.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c index 10dc59ce9c82..1b1ba1310ea7 100644 --- a/net/tipc/udp_media.c +++ b/net/tipc/udp_media.c @@ -245,10 +245,8 @@ static int tipc_udp_send_msg(struct net *net, struct sk_buff *skb, } err = tipc_udp_xmit(net, _skb, ub, src, &rcast->addr); - if (err) { - kfree_skb(_skb); + if (err) goto out; - } } err = 0; out: -- cgit v1.2.3 From fb83ed496b9a654f60cd1d58a0e1e79ec5694808 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Mon, 10 Dec 2018 15:23:30 -0800 Subject: tipc: compare remote and local protocols in tipc_udp_enable() When TIPC_NLA_UDP_REMOTE is an IPv6 mcast address but TIPC_NLA_UDP_LOCAL is an IPv4 address, a NULL-ptr deref is triggered as the UDP tunnel sock is initialized to IPv4 or IPv6 sock merely based on the protocol in local address. We should just error out when the remote address and local address have different protocols. Reported-by: syzbot+eb4da3a20fad2e52555d@syzkaller.appspotmail.com Cc: Ying Xue Cc: Jon Maloy Signed-off-by: Cong Wang Acked-by: Jon Maloy Signed-off-by: David S. Miller --- net/tipc/udp_media.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c index 1b1ba1310ea7..4d85d71f16e2 100644 --- a/net/tipc/udp_media.c +++ b/net/tipc/udp_media.c @@ -679,6 +679,11 @@ static int tipc_udp_enable(struct net *net, struct tipc_bearer *b, if (err) goto err; + if (remote.proto != local.proto) { + err = -EINVAL; + goto err; + } + /* Checking remote ip address */ rmcast = tipc_udp_is_mcast_addr(&remote); -- cgit v1.2.3 From 2ab4c3426c0cf711d7147e3f559638e4ab88960e Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Mon, 10 Dec 2018 21:20:30 -0700 Subject: drivers: net: xgene: Remove unnecessary forward declarations Clang warns: drivers/net/ethernet/apm/xgene/xgene_enet_main.c:33:36: warning: tentative array definition assumed to have one element static const struct acpi_device_id xgene_enet_acpi_match[]; ^ 1 warning generated. Both xgene_enet_acpi_match and xgene_enet_of_match are defined before their uses at the bottom of the file so this is unnecessary. When CONFIG_ACPI is disabled, ACPI_PTR becomes NULL so xgene_enet_acpi_match doesn't need to be defined. Signed-off-by: Nathan Chancellor Signed-off-by: David S. Miller --- drivers/net/ethernet/apm/xgene/xgene_enet_main.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c index 3b889efddf78..50dd6bf176d0 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c @@ -29,9 +29,6 @@ #define RES_RING_CSR 1 #define RES_RING_CMD 2 -static const struct of_device_id xgene_enet_of_match[]; -static const struct acpi_device_id xgene_enet_acpi_match[]; - static void xgene_enet_init_bufpool(struct xgene_enet_desc_ring *buf_pool) { struct xgene_enet_raw_desc16 *raw_desc; -- cgit v1.2.3 From 6c0563e442528733219afe15c749eb2cc365da3f Mon Sep 17 00:00:00 2001 From: Atul Gupta Date: Tue, 11 Dec 2018 02:19:40 -0800 Subject: net/tls: Init routines in create_ctx create_ctx is called from tls_init and tls_hw_prot hence initialize function pointers in common routine. Signed-off-by: Atul Gupta Signed-off-by: David S. Miller --- net/tls/tls_main.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index 311cec8e533d..492080306edc 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -543,6 +543,9 @@ static struct tls_context *create_ctx(struct sock *sk) return NULL; icsk->icsk_ulp_data = ctx; + ctx->setsockopt = sk->sk_prot->setsockopt; + ctx->getsockopt = sk->sk_prot->getsockopt; + ctx->sk_proto_close = sk->sk_prot->close; return ctx; } @@ -675,9 +678,6 @@ static int tls_init(struct sock *sk) rc = -ENOMEM; goto out; } - ctx->setsockopt = sk->sk_prot->setsockopt; - ctx->getsockopt = sk->sk_prot->getsockopt; - ctx->sk_proto_close = sk->sk_prot->close; /* Build IPv6 TLS whenever the address of tcpv6 _prot changes */ if (ip_ver == TLSV6 && -- cgit v1.2.3 From df9d4a1780223c3ddd4bf0810079b5a75251554e Mon Sep 17 00:00:00 2001 From: Atul Gupta Date: Tue, 11 Dec 2018 02:20:09 -0800 Subject: net/tls: sleeping function from invalid context HW unhash within mutex for registered tls devices cause sleep when called from tcp_set_state for TCP_CLOSE. Release lock and re-acquire after function call with ref count incr/dec. defined kref and fp release for tls_device to ensure device is not released outside lock. BUG: sleeping function called from invalid context at kernel/locking/mutex.c:748 in_atomic(): 1, irqs_disabled(): 0, pid: 0, name: swapper/7 INFO: lockdep is turned off. CPU: 7 PID: 0 Comm: swapper/7 Tainted: G W O Call Trace: dump_stack+0x5e/0x8b ___might_sleep+0x222/0x260 __mutex_lock+0x5c/0xa50 ? vprintk_emit+0x1f3/0x440 ? kmem_cache_free+0x22d/0x2a0 ? tls_hw_unhash+0x2f/0x80 ? printk+0x52/0x6e ? tls_hw_unhash+0x2f/0x80 tls_hw_unhash+0x2f/0x80 tcp_set_state+0x5f/0x180 tcp_done+0x2e/0xe0 tcp_rcv_state_process+0x92c/0xdd3 ? lock_acquire+0xf5/0x1f0 ? tcp_v4_rcv+0xa7c/0xbe0 ? tcp_v4_do_rcv+0x70/0x1e0 Signed-off-by: Atul Gupta Signed-off-by: David S. Miller --- drivers/crypto/chelsio/chtls/chtls_main.c | 55 ++++++++++++++++++------------- include/net/tls.h | 6 ++++ net/tls/tls_main.c | 36 ++++++++++++-------- 3 files changed, 61 insertions(+), 36 deletions(-) diff --git a/drivers/crypto/chelsio/chtls/chtls_main.c b/drivers/crypto/chelsio/chtls/chtls_main.c index f472c51abe56..db40ab6dd410 100644 --- a/drivers/crypto/chelsio/chtls/chtls_main.c +++ b/drivers/crypto/chelsio/chtls/chtls_main.c @@ -149,6 +149,30 @@ static void chtls_destroy_hash(struct tls_device *dev, struct sock *sk) chtls_stop_listen(sk); } +static void chtls_free_uld(struct chtls_dev *cdev) +{ + int i; + + tls_unregister_device(&cdev->tlsdev); + kvfree(cdev->kmap.addr); + idr_destroy(&cdev->hwtid_idr); + for (i = 0; i < (1 << RSPQ_HASH_BITS); i++) + kfree_skb(cdev->rspq_skb_cache[i]); + kfree(cdev->lldi); + kfree_skb(cdev->askb); + kfree(cdev); +} + +static inline void chtls_dev_release(struct kref *kref) +{ + struct chtls_dev *cdev; + struct tls_device *dev; + + dev = container_of(kref, struct tls_device, kref); + cdev = to_chtls_dev(dev); + chtls_free_uld(cdev); +} + static void chtls_register_dev(struct chtls_dev *cdev) { struct tls_device *tlsdev = &cdev->tlsdev; @@ -159,15 +183,12 @@ static void chtls_register_dev(struct chtls_dev *cdev) tlsdev->feature = chtls_inline_feature; tlsdev->hash = chtls_create_hash; tlsdev->unhash = chtls_destroy_hash; - tls_register_device(&cdev->tlsdev); + tlsdev->release = chtls_dev_release; + kref_init(&tlsdev->kref); + tls_register_device(tlsdev); cdev->cdev_state = CHTLS_CDEV_STATE_UP; } -static void chtls_unregister_dev(struct chtls_dev *cdev) -{ - tls_unregister_device(&cdev->tlsdev); -} - static void process_deferq(struct work_struct *task_param) { struct chtls_dev *cdev = container_of(task_param, @@ -262,28 +283,16 @@ out: return NULL; } -static void chtls_free_uld(struct chtls_dev *cdev) -{ - int i; - - chtls_unregister_dev(cdev); - kvfree(cdev->kmap.addr); - idr_destroy(&cdev->hwtid_idr); - for (i = 0; i < (1 << RSPQ_HASH_BITS); i++) - kfree_skb(cdev->rspq_skb_cache[i]); - kfree(cdev->lldi); - kfree_skb(cdev->askb); - kfree(cdev); -} - static void chtls_free_all_uld(void) { struct chtls_dev *cdev, *tmp; mutex_lock(&cdev_mutex); list_for_each_entry_safe(cdev, tmp, &cdev_list, list) { - if (cdev->cdev_state == CHTLS_CDEV_STATE_UP) - chtls_free_uld(cdev); + if (cdev->cdev_state == CHTLS_CDEV_STATE_UP) { + list_del(&cdev->list); + kref_put(&cdev->tlsdev.kref, cdev->tlsdev.release); + } } mutex_unlock(&cdev_mutex); } @@ -304,7 +313,7 @@ static int chtls_uld_state_change(void *handle, enum cxgb4_state new_state) mutex_lock(&cdev_mutex); list_del(&cdev->list); mutex_unlock(&cdev_mutex); - chtls_free_uld(cdev); + kref_put(&cdev->tlsdev.kref, cdev->tlsdev.release); break; default: break; diff --git a/include/net/tls.h b/include/net/tls.h index bab5627ff5e3..3cbcd12303fd 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -76,6 +76,10 @@ * * void (*unhash)(struct tls_device *device, struct sock *sk); * This function cleans listen state set by Inline TLS driver + * + * void (*release)(struct kref *kref); + * Release the registered device and allocated resources + * @kref: Number of reference to tls_device */ struct tls_device { char name[TLS_DEVICE_NAME_MAX]; @@ -83,6 +87,8 @@ struct tls_device { int (*feature)(struct tls_device *device); int (*hash)(struct tls_device *device, struct sock *sk); void (*unhash)(struct tls_device *device, struct sock *sk); + void (*release)(struct kref *kref); + struct kref kref; }; enum { diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index 492080306edc..1428bd74638c 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -56,7 +56,7 @@ enum { static struct proto *saved_tcpv6_prot; static DEFINE_MUTEX(tcpv6_prot_mutex); static LIST_HEAD(device_list); -static DEFINE_MUTEX(device_mutex); +static DEFINE_SPINLOCK(device_spinlock); static struct proto tls_prots[TLS_NUM_PROTS][TLS_NUM_CONFIG][TLS_NUM_CONFIG]; static struct proto_ops tls_sw_proto_ops; @@ -555,7 +555,7 @@ static int tls_hw_prot(struct sock *sk) struct tls_device *dev; int rc = 0; - mutex_lock(&device_mutex); + spin_lock_bh(&device_spinlock); list_for_each_entry(dev, &device_list, dev_list) { if (dev->feature && dev->feature(dev)) { ctx = create_ctx(sk); @@ -573,7 +573,7 @@ static int tls_hw_prot(struct sock *sk) } } out: - mutex_unlock(&device_mutex); + spin_unlock_bh(&device_spinlock); return rc; } @@ -582,12 +582,17 @@ static void tls_hw_unhash(struct sock *sk) struct tls_context *ctx = tls_get_ctx(sk); struct tls_device *dev; - mutex_lock(&device_mutex); + spin_lock_bh(&device_spinlock); list_for_each_entry(dev, &device_list, dev_list) { - if (dev->unhash) + if (dev->unhash) { + kref_get(&dev->kref); + spin_unlock_bh(&device_spinlock); dev->unhash(dev, sk); + kref_put(&dev->kref, dev->release); + spin_lock_bh(&device_spinlock); + } } - mutex_unlock(&device_mutex); + spin_unlock_bh(&device_spinlock); ctx->unhash(sk); } @@ -598,12 +603,17 @@ static int tls_hw_hash(struct sock *sk) int err; err = ctx->hash(sk); - mutex_lock(&device_mutex); + spin_lock_bh(&device_spinlock); list_for_each_entry(dev, &device_list, dev_list) { - if (dev->hash) + if (dev->hash) { + kref_get(&dev->kref); + spin_unlock_bh(&device_spinlock); err |= dev->hash(dev, sk); + kref_put(&dev->kref, dev->release); + spin_lock_bh(&device_spinlock); + } } - mutex_unlock(&device_mutex); + spin_unlock_bh(&device_spinlock); if (err) tls_hw_unhash(sk); @@ -699,17 +709,17 @@ out: void tls_register_device(struct tls_device *device) { - mutex_lock(&device_mutex); + spin_lock_bh(&device_spinlock); list_add_tail(&device->dev_list, &device_list); - mutex_unlock(&device_mutex); + spin_unlock_bh(&device_spinlock); } EXPORT_SYMBOL(tls_register_device); void tls_unregister_device(struct tls_device *device) { - mutex_lock(&device_mutex); + spin_lock_bh(&device_spinlock); list_del(&device->dev_list); - mutex_unlock(&device_mutex); + spin_unlock_bh(&device_spinlock); } EXPORT_SYMBOL(tls_unregister_device); -- cgit v1.2.3 From 6422ccc5fbefbd219f3fab133f698e58f5aa44eb Mon Sep 17 00:00:00 2001 From: Atul Gupta Date: Tue, 11 Dec 2018 02:20:26 -0800 Subject: crypto/chelsio/chtls: listen fails with multiadapt listen fails when more than one tls capable device is registered. tls_hw_hash is called for each dev which loops again for each cdev_list causing listen failure. Hence call chtls_listen_start/stop for specific device than loop over all devices. Signed-off-by: Atul Gupta Signed-off-by: David S. Miller --- drivers/crypto/chelsio/chtls/chtls.h | 5 ++++ drivers/crypto/chelsio/chtls/chtls_main.c | 50 +++++++++++++++++++------------ 2 files changed, 36 insertions(+), 19 deletions(-) diff --git a/drivers/crypto/chelsio/chtls/chtls.h b/drivers/crypto/chelsio/chtls/chtls.h index 7725b6ee14ef..fcb6747ed29e 100644 --- a/drivers/crypto/chelsio/chtls/chtls.h +++ b/drivers/crypto/chelsio/chtls/chtls.h @@ -153,6 +153,11 @@ struct chtls_dev { unsigned int cdev_state; }; +struct chtls_listen { + struct chtls_dev *cdev; + struct sock *sk; +}; + struct chtls_hws { struct sk_buff_head sk_recv_queue; u8 txqid; diff --git a/drivers/crypto/chelsio/chtls/chtls_main.c b/drivers/crypto/chelsio/chtls/chtls_main.c index db40ab6dd410..563f8fe7686a 100644 --- a/drivers/crypto/chelsio/chtls/chtls_main.c +++ b/drivers/crypto/chelsio/chtls/chtls_main.c @@ -55,24 +55,19 @@ static void unregister_listen_notifier(struct notifier_block *nb) static int listen_notify_handler(struct notifier_block *this, unsigned long event, void *data) { - struct chtls_dev *cdev; - struct sock *sk; - int ret; + struct chtls_listen *clisten; + int ret = NOTIFY_DONE; - sk = data; - ret = NOTIFY_DONE; + clisten = (struct chtls_listen *)data; switch (event) { case CHTLS_LISTEN_START: + ret = chtls_listen_start(clisten->cdev, clisten->sk); + kfree(clisten); + break; case CHTLS_LISTEN_STOP: - mutex_lock(&cdev_list_lock); - list_for_each_entry(cdev, &cdev_list, list) { - if (event == CHTLS_LISTEN_START) - ret = chtls_listen_start(cdev, sk); - else - chtls_listen_stop(cdev, sk); - } - mutex_unlock(&cdev_list_lock); + chtls_listen_stop(clisten->cdev, clisten->sk); + kfree(clisten); break; } return ret; @@ -90,8 +85,9 @@ static int listen_backlog_rcv(struct sock *sk, struct sk_buff *skb) return 0; } -static int chtls_start_listen(struct sock *sk) +static int chtls_start_listen(struct chtls_dev *cdev, struct sock *sk) { + struct chtls_listen *clisten; int err; if (sk->sk_protocol != IPPROTO_TCP) @@ -102,21 +98,33 @@ static int chtls_start_listen(struct sock *sk) return -EADDRNOTAVAIL; sk->sk_backlog_rcv = listen_backlog_rcv; + clisten = kmalloc(sizeof(*clisten), GFP_KERNEL); + if (!clisten) + return -ENOMEM; + clisten->cdev = cdev; + clisten->sk = sk; mutex_lock(¬ify_mutex); err = raw_notifier_call_chain(&listen_notify_list, - CHTLS_LISTEN_START, sk); + CHTLS_LISTEN_START, clisten); mutex_unlock(¬ify_mutex); return err; } -static void chtls_stop_listen(struct sock *sk) +static void chtls_stop_listen(struct chtls_dev *cdev, struct sock *sk) { + struct chtls_listen *clisten; + if (sk->sk_protocol != IPPROTO_TCP) return; + clisten = kmalloc(sizeof(*clisten), GFP_KERNEL); + if (!clisten) + return; + clisten->cdev = cdev; + clisten->sk = sk; mutex_lock(¬ify_mutex); raw_notifier_call_chain(&listen_notify_list, - CHTLS_LISTEN_STOP, sk); + CHTLS_LISTEN_STOP, clisten); mutex_unlock(¬ify_mutex); } @@ -138,15 +146,19 @@ static int chtls_inline_feature(struct tls_device *dev) static int chtls_create_hash(struct tls_device *dev, struct sock *sk) { + struct chtls_dev *cdev = to_chtls_dev(dev); + if (sk->sk_state == TCP_LISTEN) - return chtls_start_listen(sk); + return chtls_start_listen(cdev, sk); return 0; } static void chtls_destroy_hash(struct tls_device *dev, struct sock *sk) { + struct chtls_dev *cdev = to_chtls_dev(dev); + if (sk->sk_state == TCP_LISTEN) - chtls_stop_listen(sk); + chtls_stop_listen(cdev, sk); } static void chtls_free_uld(struct chtls_dev *cdev) -- cgit v1.2.3 From 848dd1c1cbc5a16ceae46f04722f9eb1f4b7bb4e Mon Sep 17 00:00:00 2001 From: Atul Gupta Date: Tue, 11 Dec 2018 02:20:40 -0800 Subject: crypto/chelsio/chtls: macro correction in tx path corrected macro used in tx path. removed redundant hdrlen and check for !page in chtls_sendmsg Signed-off-by: Atul Gupta Signed-off-by: David S. Miller --- drivers/crypto/chelsio/chtls/chtls_io.c | 20 ++++++++------------ drivers/net/ethernet/chelsio/cxgb4/t4_msg.h | 3 +++ 2 files changed, 11 insertions(+), 12 deletions(-) diff --git a/drivers/crypto/chelsio/chtls/chtls_io.c b/drivers/crypto/chelsio/chtls/chtls_io.c index afebbd87c4aa..18f553fcc167 100644 --- a/drivers/crypto/chelsio/chtls/chtls_io.c +++ b/drivers/crypto/chelsio/chtls/chtls_io.c @@ -397,7 +397,7 @@ static void tls_tx_data_wr(struct sock *sk, struct sk_buff *skb, req_wr->lsodisable_to_flags = htonl(TX_ULP_MODE_V(ULP_MODE_TLS) | - FW_OFLD_TX_DATA_WR_URGENT_V(skb_urgent(skb)) | + TX_URG_V(skb_urgent(skb)) | T6_TX_FORCE_F | wr_ulp_mode_force | TX_SHOVE_V((!csk_flag(sk, CSK_TX_MORE_DATA)) && skb_queue_empty(&csk->txq))); @@ -534,10 +534,9 @@ static void make_tx_data_wr(struct sock *sk, struct sk_buff *skb, FW_OFLD_TX_DATA_WR_SHOVE_F); req->tunnel_to_proxy = htonl(wr_ulp_mode_force | - FW_OFLD_TX_DATA_WR_URGENT_V(skb_urgent(skb)) | - FW_OFLD_TX_DATA_WR_SHOVE_V((!csk_flag - (sk, CSK_TX_MORE_DATA)) && - skb_queue_empty(&csk->txq))); + TX_URG_V(skb_urgent(skb)) | + TX_SHOVE_V((!csk_flag(sk, CSK_TX_MORE_DATA)) && + skb_queue_empty(&csk->txq))); req->plen = htonl(len); } @@ -995,7 +994,6 @@ int chtls_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) int mss, flags, err; int recordsz = 0; int copied = 0; - int hdrlen = 0; long timeo; lock_sock(sk); @@ -1032,7 +1030,7 @@ int chtls_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) recordsz = tls_header_read(&hdr, &msg->msg_iter); size -= TLS_HEADER_LENGTH; - hdrlen += TLS_HEADER_LENGTH; + copied += TLS_HEADER_LENGTH; csk->tlshws.txleft = recordsz; csk->tlshws.type = hdr.type; if (skb) @@ -1083,10 +1081,8 @@ new_buf: int off = TCP_OFF(sk); bool merge; - if (!page) - goto wait_for_memory; - - pg_size <<= compound_order(page); + if (page) + pg_size <<= compound_order(page); if (off < pg_size && skb_can_coalesce(skb, i, page, off)) { merge = 1; @@ -1187,7 +1183,7 @@ out: chtls_tcp_push(sk, flags); done: release_sock(sk); - return copied + hdrlen; + return copied; do_fault: if (!skb->len) { __skb_unlink(skb, &csk->txq); diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h b/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h index f152da1ce046..c62a0c830705 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h @@ -1453,6 +1453,9 @@ struct cpl_tx_data { #define T6_TX_FORCE_V(x) ((x) << T6_TX_FORCE_S) #define T6_TX_FORCE_F T6_TX_FORCE_V(1U) +#define TX_URG_S 16 +#define TX_URG_V(x) ((x) << TX_URG_S) + #define TX_SHOVE_S 14 #define TX_SHOVE_V(x) ((x) << TX_SHOVE_S) -- cgit v1.2.3 From 0c3a16be700ea008e1aa8843453bfc182e04b58a Mon Sep 17 00:00:00 2001 From: Atul Gupta Date: Tue, 11 Dec 2018 02:20:53 -0800 Subject: crypto/chelsio/chtls: send/recv window update recalculated send and receive window using linkspeed. Determine correct value of eck_ok from SYN received and option configured on local system. Signed-off-by: Atul Gupta Signed-off-by: David S. Miller --- drivers/crypto/chelsio/chtls/chtls.h | 2 + drivers/crypto/chelsio/chtls/chtls_cm.c | 78 ++++++++++++++++++++++----------- 2 files changed, 54 insertions(+), 26 deletions(-) diff --git a/drivers/crypto/chelsio/chtls/chtls.h b/drivers/crypto/chelsio/chtls/chtls.h index fcb6747ed29e..59bb67d5a7ce 100644 --- a/drivers/crypto/chelsio/chtls/chtls.h +++ b/drivers/crypto/chelsio/chtls/chtls.h @@ -220,6 +220,8 @@ struct chtls_sock { u16 resv2; u32 delack_mode; u32 delack_seq; + u32 snd_win; + u32 rcv_win; void *passive_reap_next; /* placeholder for passive */ struct chtls_hws tlshws; diff --git a/drivers/crypto/chelsio/chtls/chtls_cm.c b/drivers/crypto/chelsio/chtls/chtls_cm.c index 20209e29f814..931b96c220af 100644 --- a/drivers/crypto/chelsio/chtls/chtls_cm.c +++ b/drivers/crypto/chelsio/chtls/chtls_cm.c @@ -21,6 +21,7 @@ #include #include #include +#include #include #include @@ -887,24 +888,6 @@ static unsigned int chtls_select_mss(const struct chtls_sock *csk, return mtu_idx; } -static unsigned int select_rcv_wnd(struct chtls_sock *csk) -{ - unsigned int rcvwnd; - unsigned int wnd; - struct sock *sk; - - sk = csk->sk; - wnd = tcp_full_space(sk); - - if (wnd < MIN_RCV_WND) - wnd = MIN_RCV_WND; - - rcvwnd = MAX_RCV_WND; - - csk_set_flag(csk, CSK_UPDATE_RCV_WND); - return min(wnd, rcvwnd); -} - static unsigned int select_rcv_wscale(int space, int wscale_ok, int win_clamp) { int wscale = 0; @@ -951,7 +934,7 @@ static void chtls_pass_accept_rpl(struct sk_buff *skb, csk->mtu_idx = chtls_select_mss(csk, dst_mtu(__sk_dst_get(sk)), req); opt0 = TCAM_BYPASS_F | - WND_SCALE_V((tp)->rx_opt.rcv_wscale) | + WND_SCALE_V(RCV_WSCALE(tp)) | MSS_IDX_V(csk->mtu_idx) | L2T_IDX_V(csk->l2t_entry->idx) | NAGLE_V(!(tp->nonagle & TCP_NAGLE_OFF)) | @@ -1005,6 +988,25 @@ static int chtls_backlog_rcv(struct sock *sk, struct sk_buff *skb) return 0; } +static void chtls_set_tcp_window(struct chtls_sock *csk) +{ + struct net_device *ndev = csk->egress_dev; + struct port_info *pi = netdev_priv(ndev); + unsigned int linkspeed; + u8 scale; + + linkspeed = pi->link_cfg.speed; + scale = linkspeed / SPEED_10000; +#define CHTLS_10G_RCVWIN (256 * 1024) + csk->rcv_win = CHTLS_10G_RCVWIN; + if (scale) + csk->rcv_win *= scale; +#define CHTLS_10G_SNDWIN (256 * 1024) + csk->snd_win = CHTLS_10G_SNDWIN; + if (scale) + csk->snd_win *= scale; +} + static struct sock *chtls_recv_sock(struct sock *lsk, struct request_sock *oreq, void *network_hdr, @@ -1067,6 +1069,9 @@ static struct sock *chtls_recv_sock(struct sock *lsk, csk->port_id = port_id; csk->egress_dev = ndev; csk->tos = PASS_OPEN_TOS_G(ntohl(req->tos_stid)); + chtls_set_tcp_window(csk); + tp->rcv_wnd = csk->rcv_win; + csk->sndbuf = csk->snd_win; csk->ulp_mode = ULP_MODE_TLS; step = cdev->lldi->nrxq / cdev->lldi->nchan; csk->rss_qid = cdev->lldi->rxq_ids[port_id * step]; @@ -1076,9 +1081,9 @@ static struct sock *chtls_recv_sock(struct sock *lsk, csk->sndbuf = newsk->sk_sndbuf; csk->smac_idx = cxgb4_tp_smt_idx(cdev->lldi->adapter_type, cxgb4_port_viid(ndev)); - tp->rcv_wnd = select_rcv_wnd(csk); RCV_WSCALE(tp) = select_rcv_wscale(tcp_full_space(newsk), - WSCALE_OK(tp), + sock_net(newsk)-> + ipv4.sysctl_tcp_window_scaling, tp->window_clamp); neigh_release(n); inet_inherit_port(&tcp_hashinfo, lsk, newsk); @@ -1130,6 +1135,7 @@ static void chtls_pass_accept_request(struct sock *sk, struct cpl_t5_pass_accept_rpl *rpl; struct cpl_pass_accept_req *req; struct listen_ctx *listen_ctx; + struct vlan_ethhdr *vlan_eh; struct request_sock *oreq; struct sk_buff *reply_skb; struct chtls_sock *csk; @@ -1142,6 +1148,10 @@ static void chtls_pass_accept_request(struct sock *sk, unsigned int stid; unsigned int len; unsigned int tid; + bool th_ecn, ect; + __u8 ip_dsfield; /* IPv4 tos or IPv6 dsfield */ + u16 eth_hdr_len; + bool ecn_ok; req = cplhdr(skb) + RSS_HDR; tid = GET_TID(req); @@ -1180,24 +1190,40 @@ static void chtls_pass_accept_request(struct sock *sk, oreq->mss = 0; oreq->ts_recent = 0; - eh = (struct ethhdr *)(req + 1); - iph = (struct iphdr *)(eh + 1); + eth_hdr_len = T6_ETH_HDR_LEN_G(ntohl(req->hdr_len)); + if (eth_hdr_len == ETH_HLEN) { + eh = (struct ethhdr *)(req + 1); + iph = (struct iphdr *)(eh + 1); + network_hdr = (void *)(eh + 1); + } else { + vlan_eh = (struct vlan_ethhdr *)(req + 1); + iph = (struct iphdr *)(vlan_eh + 1); + network_hdr = (void *)(vlan_eh + 1); + } if (iph->version != 0x4) goto free_oreq; - network_hdr = (void *)(eh + 1); tcph = (struct tcphdr *)(iph + 1); + skb_set_network_header(skb, (void *)iph - (void *)req); tcp_rsk(oreq)->tfo_listener = false; tcp_rsk(oreq)->rcv_isn = ntohl(tcph->seq); chtls_set_req_port(oreq, tcph->source, tcph->dest); - inet_rsk(oreq)->ecn_ok = 0; chtls_set_req_addr(oreq, iph->daddr, iph->saddr); - if (req->tcpopt.wsf <= 14) { + ip_dsfield = ipv4_get_dsfield(iph); + if (req->tcpopt.wsf <= 14 && + sock_net(sk)->ipv4.sysctl_tcp_window_scaling) { inet_rsk(oreq)->wscale_ok = 1; inet_rsk(oreq)->snd_wscale = req->tcpopt.wsf; } inet_rsk(oreq)->ir_iif = sk->sk_bound_dev_if; + th_ecn = tcph->ece && tcph->cwr; + if (th_ecn) { + ect = !INET_ECN_is_not_ect(ip_dsfield); + ecn_ok = sock_net(sk)->ipv4.sysctl_tcp_ecn; + if ((!ect && ecn_ok) || tcp_ca_needs_ecn(sk)) + inet_rsk(oreq)->ecn_ok = 1; + } newsk = chtls_recv_sock(sk, oreq, network_hdr, req, cdev); if (!newsk) -- cgit v1.2.3 From 9c27369f4a1393452c17e8708c1b0beb8ac59501 Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Tue, 11 Dec 2018 08:16:14 -0600 Subject: r8152: Add support for MAC address pass through on RTL8153-BND All previous docks and dongles that have supported this feature use the RTL8153-AD chip. RTL8153-BND is a new chip that will be used in upcoming Dell type-C docks. It should be added to the whitelist of devices to activate MAC address pass through. Per confirming with Realtek all devices containing RTL8153-BND should activate MAC pass through and there won't use pass through bit on efuse like in RTL8153-AD. Signed-off-by: Mario Limonciello Signed-off-by: David S. Miller --- drivers/net/usb/r8152.c | 33 ++++++++++++++++++++++----------- 1 file changed, 22 insertions(+), 11 deletions(-) diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index f1b5201cc320..60dd1ec1665f 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -129,6 +129,7 @@ #define USB_UPS_CTRL 0xd800 #define USB_POWER_CUT 0xd80a #define USB_MISC_0 0xd81a +#define USB_MISC_1 0xd81f #define USB_AFE_CTRL2 0xd824 #define USB_UPS_CFG 0xd842 #define USB_UPS_FLAGS 0xd848 @@ -555,6 +556,7 @@ enum spd_duplex { /* MAC PASSTHRU */ #define AD_MASK 0xfee0 +#define BND_MASK 0x0004 #define EFUSE 0xcfdb #define PASS_THRU_MASK 0x1 @@ -1150,7 +1152,7 @@ out1: return ret; } -/* Devices containing RTL8153-AD can support a persistent +/* Devices containing proper chips can support a persistent * host system provided MAC address. * Examples of this are Dell TB15 and Dell WD15 docks */ @@ -1165,13 +1167,23 @@ static int vendor_mac_passthru_addr_read(struct r8152 *tp, struct sockaddr *sa) /* test for -AD variant of RTL8153 */ ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_MISC_0); - if ((ocp_data & AD_MASK) != 0x1000) - return -ENODEV; - - /* test for MAC address pass-through bit */ - ocp_data = ocp_read_byte(tp, MCU_TYPE_USB, EFUSE); - if ((ocp_data & PASS_THRU_MASK) != 1) - return -ENODEV; + if ((ocp_data & AD_MASK) == 0x1000) { + /* test for MAC address pass-through bit */ + ocp_data = ocp_read_byte(tp, MCU_TYPE_USB, EFUSE); + if ((ocp_data & PASS_THRU_MASK) != 1) { + netif_dbg(tp, probe, tp->netdev, + "No efuse for RTL8153-AD MAC pass through\n"); + return -ENODEV; + } + } else { + /* test for RTL8153-BND */ + ocp_data = ocp_read_byte(tp, MCU_TYPE_USB, USB_MISC_1); + if ((ocp_data & BND_MASK) == 0) { + netif_dbg(tp, probe, tp->netdev, + "Invalid variant for MAC pass through\n"); + return -ENODEV; + } + } /* returns _AUXMAC_#AABBCCDDEEFF# */ status = acpi_evaluate_object(NULL, "\\_SB.AMAC", NULL, &buffer); @@ -1217,9 +1229,8 @@ static int set_ethernet_addr(struct r8152 *tp) if (tp->version == RTL_VER_01) { ret = pla_ocp_read(tp, PLA_IDR, 8, sa.sa_data); } else { - /* if this is not an RTL8153-AD, no eFuse mac pass thru set, - * or system doesn't provide valid _SB.AMAC this will be - * be expected to non-zero + /* if device doesn't support MAC pass through this will + * be expected to be non-zero */ ret = vendor_mac_passthru_addr_read(tp, &sa); if (ret < 0) -- cgit v1.2.3 From 8236b08cf50f85bbfaf48910a0b3ee68318b7c4b Mon Sep 17 00:00:00 2001 From: Lepton Wu Date: Tue, 11 Dec 2018 11:12:55 -0800 Subject: VSOCK: bind to random port for VMADDR_PORT_ANY The old code always starts from fixed port for VMADDR_PORT_ANY. Sometimes when VMM crashed, there is still orphaned vsock which is waiting for close timer, then it could cause connection time out for new started VM if they are trying to connect to same port with same guest cid since the new packets could hit that orphaned vsock. We could also fix this by doing more in vhost_vsock_reset_orphans, but any way, it should be better to start from a random local port instead of a fixed one. Signed-off-by: Lepton Wu Reviewed-by: Jorgen Hansen Signed-off-by: David S. Miller --- net/vmw_vsock/af_vsock.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index ab27a2872935..43a1dec08825 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -107,6 +107,7 @@ #include #include #include +#include #include #include #include @@ -504,9 +505,13 @@ out: static int __vsock_bind_stream(struct vsock_sock *vsk, struct sockaddr_vm *addr) { - static u32 port = LAST_RESERVED_PORT + 1; + static u32 port = 0; struct sockaddr_vm new_addr; + if (!port) + port = LAST_RESERVED_PORT + 1 + + prandom_u32_max(U32_MAX - LAST_RESERVED_PORT); + vsock_addr_init(&new_addr, addr->svm_cid, addr->svm_port); if (addr->svm_port == VMADDR_PORT_ANY) { -- cgit v1.2.3 From 51367e423c6501a26e67d91a655d2bc892303462 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 10 Dec 2018 21:45:07 +0100 Subject: w90p910_ether: remove incorrect __init annotation The get_mac_address() function is normally inline, but when it is not, we get a warning that this configuration is broken: WARNING: vmlinux.o(.text+0x4aff00): Section mismatch in reference from the function w90p910_ether_setup() to the function .init.text:get_mac_address() The function w90p910_ether_setup() references the function __init get_mac_address(). This is often because w90p910_ether_setup lacks a __init Remove the __init to make it always do the right thing. Signed-off-by: Arnd Bergmann Signed-off-by: David S. Miller --- drivers/net/ethernet/nuvoton/w90p910_ether.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/nuvoton/w90p910_ether.c b/drivers/net/ethernet/nuvoton/w90p910_ether.c index 052b3d2c07a1..c662c6f5bee3 100644 --- a/drivers/net/ethernet/nuvoton/w90p910_ether.c +++ b/drivers/net/ethernet/nuvoton/w90p910_ether.c @@ -912,7 +912,7 @@ static const struct net_device_ops w90p910_ether_netdev_ops = { .ndo_validate_addr = eth_validate_addr, }; -static void __init get_mac_address(struct net_device *dev) +static void get_mac_address(struct net_device *dev) { struct w90p910_ether *ether = netdev_priv(dev); struct platform_device *pdev; -- cgit v1.2.3 From 5b5260902af4cf7d2b8da06ba395a722f6d490fa Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Fri, 14 Dec 2018 14:16:50 -0800 Subject: alpha: fix hang caused by the bootmem removal The conversion of alpha to memblock as the early memory manager caused boot to hang as described at [1]. The issue is caused because for CONFIG_DISCTONTIGMEM=y case, memblock_add() is called using memory start PFN that had been rounded down to the nearest 8Mb and it caused memblock to see more memory that is actually present in the system. Besides, memblock allocates memory from high addresses while bootmem was using low memory, which broke the assumption that early allocations are always accessible by the hardware. This patch ensures that memblock_add() is using the correct PFN for the memory start and forces memblock to use bottom-up allocations. [1] https://lkml.org/lkml/2018/11/22/1032 Link: http://lkml.kernel.org/r/1543233216-25833-1-git-send-email-rppt@linux.ibm.com Reported-by: Meelis Roos Signed-off-by: Mike Rapoport Tested-by: Meelis Roos Cc: Richard Henderson Cc: Ivan Kokshaysky Cc: Matt Turner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/alpha/kernel/setup.c | 1 + arch/alpha/mm/numa.c | 6 +++--- 2 files changed, 4 insertions(+), 3 deletions(-) diff --git a/arch/alpha/kernel/setup.c b/arch/alpha/kernel/setup.c index a37fd990bd55..4b5b1b244f86 100644 --- a/arch/alpha/kernel/setup.c +++ b/arch/alpha/kernel/setup.c @@ -634,6 +634,7 @@ setup_arch(char **cmdline_p) /* Find our memory. */ setup_memory(kernel_end); + memblock_set_bottom_up(true); /* First guess at cpu cache sizes. Do this before init_arch. */ determine_cpu_caches(cpu->type); diff --git a/arch/alpha/mm/numa.c b/arch/alpha/mm/numa.c index 74846553e3f1..d0b73371e985 100644 --- a/arch/alpha/mm/numa.c +++ b/arch/alpha/mm/numa.c @@ -144,14 +144,14 @@ setup_memory_node(int nid, void *kernel_end) if (!nid && (node_max_pfn < end_kernel_pfn || node_min_pfn > start_kernel_pfn)) panic("kernel loaded out of ram"); + memblock_add(PFN_PHYS(node_min_pfn), + (node_max_pfn - node_min_pfn) << PAGE_SHIFT); + /* Zone start phys-addr must be 2^(MAX_ORDER-1) aligned. Note that we round this down, not up - node memory has much larger alignment than 8Mb, so it's safe. */ node_min_pfn &= ~((1UL << (MAX_ORDER-1))-1); - memblock_add(PFN_PHYS(node_min_pfn), - (node_max_pfn - node_min_pfn) << PAGE_SHIFT); - NODE_DATA(nid)->node_start_pfn = node_min_pfn; NODE_DATA(nid)->node_present_pages = node_max_pfn - node_min_pfn; -- cgit v1.2.3 From d1402fc708e4c355813e49df6d15bc3466ba5114 Mon Sep 17 00:00:00 2001 From: Logan Gunthorpe Date: Fri, 14 Dec 2018 14:16:53 -0800 Subject: mm: introduce common STRUCT_PAGE_MAX_SHIFT define This define is used by arm64 to calculate the size of the vmemmap region. It is defined as the log2 of the upper bound on the size of a struct page. We move it into mm_types.h so it can be defined properly instead of set and checked with a build bug. This also allows us to use the same define for riscv. Link: http://lkml.kernel.org/r/20181107205433.3875-2-logang@deltatee.com Signed-off-by: Logan Gunthorpe Acked-by: Will Deacon Acked-by: Andrew Morton Acked-by: Ard Biesheuvel Acked-by: Catalin Marinas Cc: Arnd Bergmann Cc: Christoph Hellwig Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arm64/include/asm/memory.h | 9 --------- arch/arm64/mm/init.c | 8 -------- include/asm-generic/fixmap.h | 1 + include/linux/mm_types.h | 5 +++++ 4 files changed, 6 insertions(+), 17 deletions(-) diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h index b96442960aea..f0a5c9531e8b 100644 --- a/arch/arm64/include/asm/memory.h +++ b/arch/arm64/include/asm/memory.h @@ -34,15 +34,6 @@ */ #define PCI_IO_SIZE SZ_16M -/* - * Log2 of the upper bound of the size of a struct page. Used for sizing - * the vmemmap region only, does not affect actual memory footprint. - * We don't use sizeof(struct page) directly since taking its size here - * requires its definition to be available at this point in the inclusion - * chain, and it may not be a power of 2 in the first place. - */ -#define STRUCT_PAGE_MAX_SHIFT 6 - /* * VMEMMAP_SIZE - allows the whole linear region to be covered by * a struct page array diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 9b432d9fcada..0340e45655c6 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -610,14 +610,6 @@ void __init mem_init(void) BUILD_BUG_ON(TASK_SIZE_32 > TASK_SIZE_64); #endif -#ifdef CONFIG_SPARSEMEM_VMEMMAP - /* - * Make sure we chose the upper bound of sizeof(struct page) - * correctly when sizing the VMEMMAP array. - */ - BUILD_BUG_ON(sizeof(struct page) > (1 << STRUCT_PAGE_MAX_SHIFT)); -#endif - if (PAGE_SIZE >= 16384 && get_num_physpages() <= 128) { extern int sysctl_overcommit_memory; /* diff --git a/include/asm-generic/fixmap.h b/include/asm-generic/fixmap.h index 827e4d3bbc7a..8cc7b09c1bc7 100644 --- a/include/asm-generic/fixmap.h +++ b/include/asm-generic/fixmap.h @@ -16,6 +16,7 @@ #define __ASM_GENERIC_FIXMAP_H #include +#include #define __fix_to_virt(x) (FIXADDR_TOP - ((x) << PAGE_SHIFT)) #define __virt_to_fix(x) ((FIXADDR_TOP - ((x)&PAGE_MASK)) >> PAGE_SHIFT) diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 5ed8f6292a53..2c471a2c43fa 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -206,6 +206,11 @@ struct page { #endif } _struct_page_alignment; +/* + * Used for sizing the vmemmap region on some architectures + */ +#define STRUCT_PAGE_MAX_SHIFT (order_base_2(sizeof(struct page))) + #define PAGE_FRAG_CACHE_MAX_SIZE __ALIGN_MASK(32768, ~PAGE_MASK) #define PAGE_FRAG_CACHE_MAX_ORDER get_order(PAGE_FRAG_CACHE_MAX_SIZE) -- cgit v1.2.3 From 9def36e0fa9a0d9c5393c039db59f1f2d3a388b3 Mon Sep 17 00:00:00 2001 From: Logan Gunthorpe Date: Fri, 14 Dec 2018 14:16:57 -0800 Subject: mm/sparse: add common helper to mark all memblocks present Presently the arches arm64, arm and sh have a function which loops through each memblock and calls memory present. riscv will require a similar function. Introduce a common memblocks_present() function that can be used by all the arches. Subsequent patches will cleanup the arches that make use of this. Link: http://lkml.kernel.org/r/20181107205433.3875-3-logang@deltatee.com Signed-off-by: Logan Gunthorpe Acked-by: Andrew Morton Cc: Michal Hocko Cc: Vlastimil Babka Cc: Oscar Salvador Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 6 ++++++ mm/sparse.c | 16 ++++++++++++++++ 2 files changed, 22 insertions(+) diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 847705a6d0ec..db023a92f3a4 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -783,6 +783,12 @@ void memory_present(int nid, unsigned long start, unsigned long end); static inline void memory_present(int nid, unsigned long start, unsigned long end) {} #endif +#if defined(CONFIG_SPARSEMEM) +void memblocks_present(void); +#else +static inline void memblocks_present(void) {} +#endif + #ifdef CONFIG_HAVE_MEMORYLESS_NODES int local_memory_node(int node_id); #else diff --git a/mm/sparse.c b/mm/sparse.c index 33307fc05c4d..3abc8cc50201 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -239,6 +239,22 @@ void __init memory_present(int nid, unsigned long start, unsigned long end) } } +/* + * Mark all memblocks as present using memory_present(). This is a + * convienence function that is useful for a number of arches + * to mark all of the systems memory as present during initialization. + */ +void __init memblocks_present(void) +{ + struct memblock_region *reg; + + for_each_memblock(memory, reg) { + memory_present(memblock_get_region_node(reg), + memblock_region_memory_base_pfn(reg), + memblock_region_memory_end_pfn(reg)); + } +} + /* * Subtle, we encode the real pfn into the mem_map such that * the identity pfn - section_mem_map will return the actual -- cgit v1.2.3 From 915c9e1b6d008fdaebca91b83fa0d2596121d588 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Fri, 14 Dec 2018 14:17:00 -0800 Subject: arch/sh/include/asm/io.h: provide prototypes for PCI I/O mapping in asm/io.h Most architectures provide prototypes for the PCI I/O mapping operations when asm/io.h is included but SH doesn't currently do that, leading to for example warnings in sound/pci/hda/patch_ca0132.c when pci_iomap() is used on current -next. Make SH more consistent with other architectures by including asm-generic/pci_iomap.h in asm/io.h. Link: http://lkml.kernel.org/r/20181106175142.27988-1-broonie@kernel.org Signed-off-by: Mark Brown Reported-by: kbuild test robot Cc: Geert Uytterhoeven Cc: Yoshinori Sato Cc: Rich Felker Cc: Arnd Bergmann Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/sh/include/asm/io.h | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/sh/include/asm/io.h b/arch/sh/include/asm/io.h index 98cb8c802b1a..4f7f235f15f8 100644 --- a/arch/sh/include/asm/io.h +++ b/arch/sh/include/asm/io.h @@ -24,6 +24,7 @@ #define __IO_PREFIX generic #include #include +#include #include #define __raw_writeb(v,a) (__chk_io_ptr(a), *(volatile u8 __force *)(a) = (v)) -- cgit v1.2.3 From 428a1cb4baeb9e5c7feda93af7372ba6d2491558 Mon Sep 17 00:00:00 2001 From: Baruch Siach Date: Fri, 14 Dec 2018 14:17:03 -0800 Subject: psi: fix reference to kernel commandline enable The kernel commandline parameter named in CONFIG_PSI_DEFAULT_DISABLED help text contradicts the documentation in kernel-parameters.txt, and the code. Fix that. Link: http://lkml.kernel.org/r/20181203213416.GA12627@cmpxchg.org Fixes: e0c274472d ("psi: make disabling/enabling easier for vendor kernels") Signed-off-by: Baruch Siach Acked-by: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- init/Kconfig | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/init/Kconfig b/init/Kconfig index cf5b5a0dcbc2..ed9352513c32 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -515,8 +515,8 @@ config PSI_DEFAULT_DISABLED depends on PSI help If set, pressure stall information tracking will be disabled - per default but can be enabled through passing psi_enable=1 - on the kernel commandline during boot. + per default but can be enabled through passing psi=1 on the + kernel commandline during boot. endmenu # "CPU/Task time and stats accounting" -- cgit v1.2.3 From f5a222dc2f0e893cc6b0fa34d421a41ca7dfb72e Mon Sep 17 00:00:00 2001 From: Yueyi Li Date: Fri, 14 Dec 2018 14:17:06 -0800 Subject: memblock: annotate memblock_is_reserved() with __init_memblock Found warning: WARNING: EXPORT symbol "gsi_write_channel_scratch" [vmlinux] version generation failed, symbol will not be versioned. WARNING: vmlinux.o(.text+0x1e0a0): Section mismatch in reference from the function valid_phys_addr_range() to the function .init.text:memblock_is_reserved() The function valid_phys_addr_range() references the function __init memblock_is_reserved(). This is often because valid_phys_addr_range lacks a __init annotation or the annotation of memblock_is_reserved is wrong. Use __init_memblock instead of __init. Link: http://lkml.kernel.org/r/BLUPR13MB02893411BF12EACB61888E80DFAE0@BLUPR13MB0289.namprd13.prod.outlook.com Signed-off-by: Yueyi Li Acked-by: Michal Hocko Reviewed-by: David Hildenbrand Acked-by: Mike Rapoport Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memblock.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/memblock.c b/mm/memblock.c index 9a2d5ae81ae1..81ae63ca78d0 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -1727,7 +1727,7 @@ static int __init_memblock memblock_search(struct memblock_type *type, phys_addr return -1; } -bool __init memblock_is_reserved(phys_addr_t addr) +bool __init_memblock memblock_is_reserved(phys_addr_t addr) { return memblock_search(&memblock.reserved, addr) != -1; } -- cgit v1.2.3 From 8ace22bce84014957da37e6b8baa49ee81c03366 Mon Sep 17 00:00:00 2001 From: Yongkai Wu Date: Fri, 14 Dec 2018 14:17:10 -0800 Subject: hugetlbfs: call VM_BUG_ON_PAGE earlier in free_huge_page() A stack trace was triggered by VM_BUG_ON_PAGE(page_mapcount(page), page) in free_huge_page(). Unfortunately, the page->mapping field was set to NULL before this test. This made it more difficult to determine the root cause of the problem. Move the VM_BUG_ON_PAGE tests earlier in the function so that if they do trigger more information is present in the page struct. Link: http://lkml.kernel.org/r/1543491843-23438-1-git-send-email-nic_w@163.com Signed-off-by: Yongkai Wu Acked-by: Michal Hocko Acked-by: Mike Kravetz Reviewed-by: William Kucharski Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/hugetlb.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 705a3e9cc910..a80832487981 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1248,10 +1248,11 @@ void free_huge_page(struct page *page) (struct hugepage_subpool *)page_private(page); bool restore_reserve; - set_page_private(page, 0); - page->mapping = NULL; VM_BUG_ON_PAGE(page_count(page), page); VM_BUG_ON_PAGE(page_mapcount(page), page); + + set_page_private(page, 0); + page->mapping = NULL; restore_reserve = PagePrivate(page); ClearPagePrivate(page); -- cgit v1.2.3 From 61c6de667263184125d5ca75e894fcad632b0dd3 Mon Sep 17 00:00:00 2001 From: Piotr Jaroszynski Date: Fri, 14 Dec 2018 14:17:14 -0800 Subject: fs/iomap.c: get/put the page in iomap_page_create/release() migrate_page_move_mapping() expects pages with private data set to have a page_count elevated by 1. This is what used to happen for xfs through the buffer_heads code before the switch to iomap in commit 82cb14175e7d ("xfs: add support for sub-pagesize writeback without buffer_heads"). Not having the count elevated causes move_pages() to fail on memory mapped files coming from xfs. Make iomap compatible with the migrate_page_move_mapping() assumption by elevating the page count as part of iomap_page_create() and lowering it in iomap_page_release(). It causes the move_pages() syscall to misbehave on memory mapped files from xfs. It does not not move any pages, which I suppose is "just" a perf issue, but it also ends up returning a positive number which is out of spec for the syscall. Talking to Michal Hocko, it sounds like returning positive numbers might be a necessary update to move_pages() anyway though (https://lkml.kernel.org/r/20181116114955.GJ14706@dhcp22.suse.cz). I only hit this in tests that verify that move_pages() actually moved the pages. The test also got confused by the positive return from move_pages() (it got treated as a success as positive numbers were not expected and not handled) making it a bit harder to track down what's going on. Link: http://lkml.kernel.org/r/20181115184140.1388751-1-pjaroszynski@nvidia.com Fixes: 82cb14175e7d ("xfs: add support for sub-pagesize writeback without buffer_heads") Signed-off-by: Piotr Jaroszynski Reviewed-by: Christoph Hellwig Cc: William Kucharski Cc: Darrick J. Wong Cc: Brian Foster Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/iomap.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/fs/iomap.c b/fs/iomap.c index d6bc98ae8d35..5bc172f3dfe8 100644 --- a/fs/iomap.c +++ b/fs/iomap.c @@ -116,6 +116,12 @@ iomap_page_create(struct inode *inode, struct page *page) atomic_set(&iop->read_count, 0); atomic_set(&iop->write_count, 0); bitmap_zero(iop->uptodate, PAGE_SIZE / SECTOR_SIZE); + + /* + * migrate_page_move_mapping() assumes that pages with private data have + * their count elevated by 1. + */ + get_page(page); set_page_private(page, (unsigned long)iop); SetPagePrivate(page); return iop; @@ -132,6 +138,7 @@ iomap_page_release(struct page *page) WARN_ON_ONCE(atomic_read(&iop->write_count)); ClearPagePrivate(page); set_page_private(page, 0); + put_page(page); kfree(iop); } -- cgit v1.2.3 From 01e881f5a1fca4677e82733061868c6d6ea05ca7 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Fri, 14 Dec 2018 14:17:17 -0800 Subject: userfaultfd: check VM_MAYWRITE was set after verifying the uffd is registered Calling UFFDIO_UNREGISTER on virtual ranges not yet registered in uffd could trigger an harmless false positive WARN_ON. Check the vma is already registered before checking VM_MAYWRITE to shut off the false positive warning. Link: http://lkml.kernel.org/r/20181206212028.18726-2-aarcange@redhat.com Cc: Fixes: 29ec90660d68 ("userfaultfd: shmem/hugetlbfs: only allow to register VM_MAYWRITE vmas") Signed-off-by: Andrea Arcangeli Reported-by: syzbot+06c7092e7d71218a2c16@syzkaller.appspotmail.com Acked-by: Mike Rapoport Acked-by: Hugh Dickins Acked-by: Peter Xu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/userfaultfd.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index cd58939dc977..7a85e609fc27 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -1566,7 +1566,6 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx, cond_resched(); BUG_ON(!vma_can_userfault(vma)); - WARN_ON(!(vma->vm_flags & VM_MAYWRITE)); /* * Nothing to do: this vma is already registered into this @@ -1575,6 +1574,8 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx, if (!vma->vm_userfaultfd_ctx.ctx) goto skip; + WARN_ON(!(vma->vm_flags & VM_MAYWRITE)); + if (vma->vm_start > start) start = vma->vm_start; vma_end = min(end, vma->vm_end); -- cgit v1.2.3 From f1733a1d3cd32a9492f4cf866be37bb46e10163d Mon Sep 17 00:00:00 2001 From: Qian Cai Date: Fri, 14 Dec 2018 14:17:20 -0800 Subject: checkstack.pl: fix for aarch64 There is actually a space after "sp," like this, ffff2000080813c8: a9bb7bfd stp x29, x30, [sp, #-80]! Right now, checkstack.pl isn't able to print anything on aarch64, because it won't be able to match the stating objdump line of a function due to this missing space. Hence, it displays every stack as zero-size. After this patch, checkpatch.pl is able to match the start of a function's objdump, and is then able to calculate each function's stack correctly. Link: http://lkml.kernel.org/r/20181207195843.38528-1-cai@lca.pw Signed-off-by: Qian Cai Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- scripts/checkstack.pl | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/scripts/checkstack.pl b/scripts/checkstack.pl index 8081b6cf67d2..34414c6efad6 100755 --- a/scripts/checkstack.pl +++ b/scripts/checkstack.pl @@ -47,8 +47,8 @@ my (@stack, $re, $dre, $x, $xs, $funcre); $xs = "[0-9a-f ]"; # hex character or space $funcre = qr/^$x* <(.*)>:$/; if ($arch eq 'aarch64') { - #ffffffc0006325cc: a9bb7bfd stp x29, x30, [sp,#-80]! - $re = qr/^.*stp.*sp,\#-([0-9]{1,8})\]\!/o; + #ffffffc0006325cc: a9bb7bfd stp x29, x30, [sp, #-80]! + $re = qr/^.*stp.*sp, \#-([0-9]{1,8})\]\!/o; } elsif ($arch eq 'arm') { #c0008ffc: e24dd064 sub sp, sp, #100 ; 0x64 $re = qr/.*sub.*sp, sp, #(([0-9]{2}|[3-9])[0-9]{2})/o; -- cgit v1.2.3 From 3a6ab5c7dc114057fd67750e308e1745dafc0e6a Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Fri, 14 Dec 2018 14:17:24 -0800 Subject: scripts/spdxcheck.py: always open files in binary mode The spdxcheck script currently falls over when confronted with a binary file (such as Documentation/logo.gif). To avoid that, always open files in binary mode and decode line-by-line, ignoring encoding errors. One tricky case is when piping data into the script and reading it from standard input. By default, standard input will be opened in text mode, so we need to reopen it in binary mode. The breakage only happens with python3 and results in a UnicodeDecodeError (according to Uwe). Link: http://lkml.kernel.org/r/20181212131210.28024-1-thierry.reding@gmail.com Fixes: 6f4d29df66ac ("scripts/spdxcheck.py: make python3 compliant") Signed-off-by: Thierry Reding Reviewed-by: Jeremy Cline Cc: Thomas Gleixner Cc: Jonathan Corbet Cc: Joe Perches Cc: Uwe Kleine-König Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- scripts/spdxcheck.py | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/scripts/spdxcheck.py b/scripts/spdxcheck.py index 5056fb3b897d..e559c6294c39 100755 --- a/scripts/spdxcheck.py +++ b/scripts/spdxcheck.py @@ -168,6 +168,7 @@ class id_parser(object): self.curline = 0 try: for line in fd: + line = line.decode(locale.getpreferredencoding(False), errors='ignore') self.curline += 1 if self.curline > maxlines: break @@ -249,12 +250,13 @@ if __name__ == '__main__': try: if len(args.path) and args.path[0] == '-': - parser.parse_lines(sys.stdin, args.maxlines, '-') + stdin = os.fdopen(sys.stdin.fileno(), 'rb') + parser.parse_lines(stdin, args.maxlines, '-') else: if args.path: for p in args.path: if os.path.isfile(p): - parser.parse_lines(open(p), args.maxlines, p) + parser.parse_lines(open(p, 'rb'), args.maxlines, p) elif os.path.isdir(p): scan_git_subtree(repo.head.reference.commit.tree, p) else: -- cgit v1.2.3 From 69d2c86766da2ded2b70281f1bf242cb0d58a778 Mon Sep 17 00:00:00 2001 From: Gustavo A. R. Silva Date: Tue, 11 Dec 2018 14:10:08 -0600 Subject: ip6mr: Fix potential Spectre v1 vulnerability vr.mifi is indirectly controlled by user-space, hence leading to a potential exploitation of the Spectre variant 1 vulnerability. This issue was detected with the help of Smatch: net/ipv6/ip6mr.c:1845 ip6mr_ioctl() warn: potential spectre issue 'mrt->vif_table' [r] (local cap) net/ipv6/ip6mr.c:1919 ip6mr_compat_ioctl() warn: potential spectre issue 'mrt->vif_table' [r] (local cap) Fix this by sanitizing vr.mifi before using it to index mrt->vif_table' Notice that given that speculation windows are large, the policy is to kill the speculation on the first load and not worry if it can be completed with a dependent load/store [1]. [1] https://marc.info/?l=linux-kernel&m=152449131114778&w=2 Signed-off-by: Gustavo A. R. Silva Signed-off-by: David S. Miller --- net/ipv6/ip6mr.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index e2ea691e42c6..377a2ee5d9ad 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -52,6 +52,8 @@ #include #include +#include + struct ip6mr_rule { struct fib_rule common; }; @@ -1841,6 +1843,7 @@ int ip6mr_ioctl(struct sock *sk, int cmd, void __user *arg) return -EFAULT; if (vr.mifi >= mrt->maxvif) return -EINVAL; + vr.mifi = array_index_nospec(vr.mifi, mrt->maxvif); read_lock(&mrt_lock); vif = &mrt->vif_table[vr.mifi]; if (VIF_EXISTS(mrt, vr.mifi)) { @@ -1915,6 +1918,7 @@ int ip6mr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg) return -EFAULT; if (vr.mifi >= mrt->maxvif) return -EINVAL; + vr.mifi = array_index_nospec(vr.mifi, mrt->maxvif); read_lock(&mrt_lock); vif = &mrt->vif_table[vr.mifi]; if (VIF_EXISTS(mrt, vr.mifi)) { -- cgit v1.2.3 From 65cab850f0eeaa9180bd2e10a231964f33743edf Mon Sep 17 00:00:00 2001 From: Dave Taht Date: Tue, 11 Dec 2018 15:30:34 -0800 Subject: net: Allow class-e address assignment via ifconfig ioctl While most distributions long ago switched to the iproute2 suite of utilities, which allow class-e (240.0.0.0/4) address assignment, distributions relying on busybox, toybox and other forms of ifconfig cannot assign class-e addresses without this kernel patch. While CIDR has been obsolete for 2 decades, and a survey of all the open source code in the world shows the IN_whatever macros are also obsolete... rather than obsolete CIDR from this ioctl entirely, this patch merely enables class-e assignment, sanely. Signed-off-by: Dave Taht Signed-off-by: David S. Miller --- include/uapi/linux/in.h | 10 +++++++--- net/ipv4/devinet.c | 5 +++-- net/ipv4/ipconfig.c | 2 ++ 3 files changed, 12 insertions(+), 5 deletions(-) diff --git a/include/uapi/linux/in.h b/include/uapi/linux/in.h index 48e8a225b985..f6052e70bf40 100644 --- a/include/uapi/linux/in.h +++ b/include/uapi/linux/in.h @@ -266,10 +266,14 @@ struct sockaddr_in { #define IN_CLASSD(a) ((((long int) (a)) & 0xf0000000) == 0xe0000000) #define IN_MULTICAST(a) IN_CLASSD(a) -#define IN_MULTICAST_NET 0xF0000000 +#define IN_MULTICAST_NET 0xe0000000 -#define IN_EXPERIMENTAL(a) ((((long int) (a)) & 0xf0000000) == 0xf0000000) -#define IN_BADCLASS(a) IN_EXPERIMENTAL((a)) +#define IN_BADCLASS(a) ((((long int) (a) ) == 0xffffffff) +#define IN_EXPERIMENTAL(a) IN_BADCLASS((a)) + +#define IN_CLASSE(a) ((((long int) (a)) & 0xf0000000) == 0xf0000000) +#define IN_CLASSE_NET 0xffffffff +#define IN_CLASSE_NSHIFT 0 /* Address to accept any incoming messages. */ #define INADDR_ANY ((unsigned long int) 0x00000000) diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index a34602ae27de..608a6f4223fb 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -952,17 +952,18 @@ static int inet_abc_len(__be32 addr) { int rc = -1; /* Something else, probably a multicast. */ - if (ipv4_is_zeronet(addr)) + if (ipv4_is_zeronet(addr) || ipv4_is_lbcast(addr)) rc = 0; else { __u32 haddr = ntohl(addr); - if (IN_CLASSA(haddr)) rc = 8; else if (IN_CLASSB(haddr)) rc = 16; else if (IN_CLASSC(haddr)) rc = 24; + else if (IN_CLASSE(haddr)) + rc = 32; } return rc; diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index 88212615bf4c..2393e5c106bf 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -429,6 +429,8 @@ static int __init ic_defaults(void) ic_netmask = htonl(IN_CLASSB_NET); else if (IN_CLASSC(ntohl(ic_myaddr))) ic_netmask = htonl(IN_CLASSC_NET); + else if (IN_CLASSE(ntohl(ic_myaddr))) + ic_netmask = htonl(IN_CLASSE_NET); else { pr_err("IP-Config: Unable to guess netmask for address %pI4\n", &ic_myaddr); -- cgit v1.2.3 From 143ece654f9f5b37bedea252a990be37e48ae3a5 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Tue, 11 Dec 2018 21:43:51 -0800 Subject: tipc: check tsk->group in tipc_wait_for_cond() tipc_wait_for_cond() drops socket lock before going to sleep, but tsk->group could be freed right after that release_sock(). So we have to re-check and reload tsk->group after it wakes up. After this patch, tipc_wait_for_cond() returns -ERESTARTSYS when tsk->group is NULL, instead of continuing with the assumption of a non-NULL tsk->group. (It looks like 'dsts' should be re-checked and reloaded too, but it is a different bug.) Similar for tipc_send_group_unicast() and tipc_send_group_anycast(). Reported-by: syzbot+10a9db47c3a0e13eb31c@syzkaller.appspotmail.com Fixes: b7d42635517f ("tipc: introduce flow control for group broadcast messages") Fixes: ee106d7f942d ("tipc: introduce group anycast messaging") Fixes: 27bd9ec027f3 ("tipc: introduce group unicast messaging") Cc: Ying Xue Cc: Jon Maloy Signed-off-by: Cong Wang Acked-by: Ying Xue Signed-off-by: David S. Miller --- net/tipc/socket.c | 25 ++++++++++++++----------- 1 file changed, 14 insertions(+), 11 deletions(-) diff --git a/net/tipc/socket.c b/net/tipc/socket.c index e1396fb87779..656940692a44 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -880,7 +880,6 @@ static int tipc_send_group_unicast(struct socket *sock, struct msghdr *m, DECLARE_SOCKADDR(struct sockaddr_tipc *, dest, m->msg_name); int blks = tsk_blocks(GROUP_H_SIZE + dlen); struct tipc_sock *tsk = tipc_sk(sk); - struct tipc_group *grp = tsk->group; struct net *net = sock_net(sk); struct tipc_member *mb = NULL; u32 node, port; @@ -894,7 +893,9 @@ static int tipc_send_group_unicast(struct socket *sock, struct msghdr *m, /* Block or return if destination link or member is congested */ rc = tipc_wait_for_cond(sock, &timeout, !tipc_dest_find(&tsk->cong_links, node, 0) && - !tipc_group_cong(grp, node, port, blks, &mb)); + tsk->group && + !tipc_group_cong(tsk->group, node, port, blks, + &mb)); if (unlikely(rc)) return rc; @@ -924,7 +925,6 @@ static int tipc_send_group_anycast(struct socket *sock, struct msghdr *m, struct tipc_sock *tsk = tipc_sk(sk); struct list_head *cong_links = &tsk->cong_links; int blks = tsk_blocks(GROUP_H_SIZE + dlen); - struct tipc_group *grp = tsk->group; struct tipc_msg *hdr = &tsk->phdr; struct tipc_member *first = NULL; struct tipc_member *mbr = NULL; @@ -941,9 +941,10 @@ static int tipc_send_group_anycast(struct socket *sock, struct msghdr *m, type = msg_nametype(hdr); inst = dest->addr.name.name.instance; scope = msg_lookup_scope(hdr); - exclude = tipc_group_exclude(grp); while (++lookups < 4) { + exclude = tipc_group_exclude(tsk->group); + first = NULL; /* Look for a non-congested destination member, if any */ @@ -952,7 +953,8 @@ static int tipc_send_group_anycast(struct socket *sock, struct msghdr *m, &dstcnt, exclude, false)) return -EHOSTUNREACH; tipc_dest_pop(&dsts, &node, &port); - cong = tipc_group_cong(grp, node, port, blks, &mbr); + cong = tipc_group_cong(tsk->group, node, port, blks, + &mbr); if (!cong) break; if (mbr == first) @@ -971,7 +973,8 @@ static int tipc_send_group_anycast(struct socket *sock, struct msghdr *m, /* Block or return if destination link or member is congested */ rc = tipc_wait_for_cond(sock, &timeout, !tipc_dest_find(cong_links, node, 0) && - !tipc_group_cong(grp, node, port, + tsk->group && + !tipc_group_cong(tsk->group, node, port, blks, &mbr)); if (unlikely(rc)) return rc; @@ -1006,8 +1009,7 @@ static int tipc_send_group_bcast(struct socket *sock, struct msghdr *m, struct sock *sk = sock->sk; struct net *net = sock_net(sk); struct tipc_sock *tsk = tipc_sk(sk); - struct tipc_group *grp = tsk->group; - struct tipc_nlist *dsts = tipc_group_dests(grp); + struct tipc_nlist *dsts = tipc_group_dests(tsk->group); struct tipc_mc_method *method = &tsk->mc_method; bool ack = method->mandatory && method->rcast; int blks = tsk_blocks(MCAST_H_SIZE + dlen); @@ -1020,8 +1022,9 @@ static int tipc_send_group_bcast(struct socket *sock, struct msghdr *m, return -EHOSTUNREACH; /* Block or return if any destination link or member is congested */ - rc = tipc_wait_for_cond(sock, &timeout, !tsk->cong_link_cnt && - !tipc_group_bc_cong(grp, blks)); + rc = tipc_wait_for_cond(sock, &timeout, + !tsk->cong_link_cnt && tsk->group && + !tipc_group_bc_cong(tsk->group, blks)); if (unlikely(rc)) return rc; @@ -1036,7 +1039,7 @@ static int tipc_send_group_bcast(struct socket *sock, struct msghdr *m, msg_set_hdr_sz(hdr, GROUP_H_SIZE); msg_set_destport(hdr, 0); msg_set_destnode(hdr, 0); - msg_set_grp_bc_seqno(hdr, tipc_group_bc_snd_nxt(grp)); + msg_set_grp_bc_seqno(hdr, tipc_group_bc_snd_nxt(tsk->group)); /* Avoid getting stuck with repeated forced replicasts */ msg_set_grp_bc_ack_req(hdr, ack); -- cgit v1.2.3 From 110a1cc28bc383adb4885eff27e18c61ddebffb4 Mon Sep 17 00:00:00 2001 From: Jörgen Storvist Date: Wed, 12 Dec 2018 22:45:34 +0100 Subject: qmi_wwan: Added support for Fibocom NL668 series Added support for Fibocom NL668 series QMI interface. Using QMI_QUIRK_SET_DTR required for Qualcomm MDM9x07 chipsets. Signed-off-by: Jörgen Storvist Signed-off-by: David S. Miller --- drivers/net/usb/qmi_wwan.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 72a55b6b4211..dada68f279bc 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1117,6 +1117,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x1435, 0xd181, 4)}, /* Wistron NeWeb D18Q1 */ {QMI_FIXED_INTF(0x1435, 0xd181, 5)}, /* Wistron NeWeb D18Q1 */ {QMI_FIXED_INTF(0x1435, 0xd191, 4)}, /* Wistron NeWeb D19Q1 */ + {QMI_QUIRK_SET_DTR(0x1508, 0x1001, 4)}, /* Fibocom NL668 series */ {QMI_FIXED_INTF(0x16d8, 0x6003, 0)}, /* CMOTech 6003 */ {QMI_FIXED_INTF(0x16d8, 0x6007, 0)}, /* CMOTech CHE-628S */ {QMI_FIXED_INTF(0x16d8, 0x6008, 0)}, /* CMOTech CMU-301 */ -- cgit v1.2.3 From 1986af16e8ed355822600c24b3d2f0be46b573df Mon Sep 17 00:00:00 2001 From: Jörgen Storvist Date: Thu, 13 Dec 2018 17:00:35 +0100 Subject: qmi_wwan: Added support for Telit LN940 series Added support for the Telit LN940 series cellular modules QMI interface. QMI_QUIRK_SET_DTR quirk requied for Qualcomm MDM9x40 chipset. Signed-off-by: Jörgen Storvist Acked-by: Bjørn Mork Signed-off-by: David S. Miller --- drivers/net/usb/qmi_wwan.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index dada68f279bc..c8872dd5ff5e 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1230,6 +1230,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x1bc7, 0x1101, 3)}, /* Telit ME910 dual modem */ {QMI_FIXED_INTF(0x1bc7, 0x1200, 5)}, /* Telit LE920 */ {QMI_QUIRK_SET_DTR(0x1bc7, 0x1201, 2)}, /* Telit LE920, LE920A4 */ + {QMI_QUIRK_SET_DTR(0x1bc7, 0x1900, 1)}, /* Telit LN940 series */ {QMI_FIXED_INTF(0x1c9e, 0x9801, 3)}, /* Telewell TW-3G HSPA+ */ {QMI_FIXED_INTF(0x1c9e, 0x9803, 4)}, /* Telewell TW-3G HSPA+ */ {QMI_FIXED_INTF(0x1c9e, 0x9b01, 3)}, /* XS Stick W100-2 from 4G Systems */ -- cgit v1.2.3 From ade446403bfb79d3528d56071a84b15351a139ad Mon Sep 17 00:00:00 2001 From: Michal Kubecek Date: Thu, 13 Dec 2018 17:23:32 +0100 Subject: net: ipv4: do not handle duplicate fragments as overlapping Since commit 7969e5c40dfd ("ip: discard IPv4 datagrams with overlapping segments.") IPv4 reassembly code drops the whole queue whenever an overlapping fragment is received. However, the test is written in a way which detects duplicate fragments as overlapping so that in environments with many duplicate packets, fragmented packets may be undeliverable. Add an extra test and for (potentially) duplicate fragment, only drop the new fragment rather than the whole queue. Only starting offset and length are checked, not the contents of the fragments as that would be too expensive. For similar reason, linear list ("run") of a rbtree node is not iterated, we only check if the new fragment is a subset of the interval covered by existing consecutive fragments. v2: instead of an exact check iterating through linear list of an rbtree node, only check if the new fragment is subset of the "run" (suggested by Eric Dumazet) Fixes: 7969e5c40dfd ("ip: discard IPv4 datagrams with overlapping segments.") Signed-off-by: Michal Kubecek Signed-off-by: David S. Miller --- net/ipv4/ip_fragment.c | 18 ++++++++++++------ 1 file changed, 12 insertions(+), 6 deletions(-) diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index aa0b22697998..867be8f7f1fa 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -346,10 +346,10 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) struct net *net = container_of(qp->q.net, struct net, ipv4.frags); struct rb_node **rbn, *parent; struct sk_buff *skb1, *prev_tail; + int ihl, end, skb1_run_end; struct net_device *dev; unsigned int fragsize; int flags, offset; - int ihl, end; int err = -ENOENT; u8 ecn; @@ -419,7 +419,9 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) * overlapping fragment, the entire datagram (and any constituent * fragments) MUST be silently discarded. * - * We do the same here for IPv4 (and increment an snmp counter). + * We do the same here for IPv4 (and increment an snmp counter) but + * we do not want to drop the whole queue in response to a duplicate + * fragment. */ err = -EINVAL; @@ -444,13 +446,17 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) do { parent = *rbn; skb1 = rb_to_skb(parent); + skb1_run_end = skb1->ip_defrag_offset + + FRAG_CB(skb1)->frag_run_len; if (end <= skb1->ip_defrag_offset) rbn = &parent->rb_left; - else if (offset >= skb1->ip_defrag_offset + - FRAG_CB(skb1)->frag_run_len) + else if (offset >= skb1_run_end) rbn = &parent->rb_right; - else /* Found an overlap with skb1. */ - goto overlap; + else if (offset >= skb1->ip_defrag_offset && + end <= skb1_run_end) + goto err; /* No new data, potential duplicate */ + else + goto overlap; /* Found an overlap */ } while (*rbn); /* Here we have parent properly set, and rbn pointing to * one of its NULL left/right children. Insert skb. -- cgit v1.2.3 From 15c6d8e565943a904172de69cc13c53f724fa16c Mon Sep 17 00:00:00 2001 From: Robert P. J. Day Date: Thu, 13 Dec 2018 15:00:11 -0500 Subject: mod_devicetable.h: correct kerneldoc typo, "PHYSID2" -> "MII_PHYSID2" Signed-off-by: Robert P. J. Day Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/mod_devicetable.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index 01797cb4587e..a0dcc9b6a723 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -565,7 +565,7 @@ struct platform_device_id { /** * struct mdio_device_id - identifies PHY devices on an MDIO/MII bus * @phy_id: The result of - * (mdio_read(&MII_PHYSID1) << 16 | mdio_read(&PHYSID2)) & @phy_id_mask + * (mdio_read(&MII_PHYSID1) << 16 | mdio_read(&MII_PHYSID2)) & @phy_id_mask * for this PHY type * @phy_id_mask: Defines the significant bits of @phy_id. A value of 0 * is used to terminate an array of struct mdio_device_id. -- cgit v1.2.3 From 8203e2d844d34af247a151d8ebd68553a6e91785 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 14 Dec 2018 06:46:49 -0800 Subject: net: clear skb->tstamp in forwarding paths Sergey reported that forwarding was no longer working if fq packet scheduler was used. This is caused by the recent switch to EDT model, since incoming packets might have been timestamped by __net_timestamp() __net_timestamp() uses ktime_get_real(), while fq expects packets using CLOCK_MONOTONIC base. The fix is to clear skb->tstamp in forwarding paths. Fixes: 80b14dee2bea ("net: Add a new socket option for a future transmit time.") Fixes: fb420d5d91c1 ("tcp/fq: move back to CLOCK_MONOTONIC") Signed-off-by: Eric Dumazet Reported-by: Sergey Matyukevich Tested-by: Sergey Matyukevich Signed-off-by: David S. Miller --- net/ipv4/ip_forward.c | 1 + net/ipv6/ip6_output.c | 1 + 2 files changed, 2 insertions(+) diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c index 32662e9e5d21..d5984d31ab93 100644 --- a/net/ipv4/ip_forward.c +++ b/net/ipv4/ip_forward.c @@ -72,6 +72,7 @@ static int ip_forward_finish(struct net *net, struct sock *sk, struct sk_buff *s if (unlikely(opt->optlen)) ip_forward_options(skb); + skb->tstamp = 0; return dst_output(net, sk, skb); } diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index fcd3c66ded16..4591ca4bdbe8 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -378,6 +378,7 @@ static inline int ip6_forward_finish(struct net *net, struct sock *sk, __IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTFORWDATAGRAMS); __IP6_ADD_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTOCTETS, skb->len); + skb->tstamp = 0; return dst_output(net, sk, skb); } -- cgit v1.2.3 From 4e1d4be681b2c26fd874adbf584bf034573ac45d Mon Sep 17 00:00:00 2001 From: Yonglong Liu Date: Sat, 15 Dec 2018 11:53:20 +0800 Subject: net: hns: Incorrect offset address used for some registers. According to the hip06 Datasheet: 1. The offset of INGRESS_SW_VLAN_TAG_DISC should be 0x1A00+4*all_chn_num 2. The offset of INGRESS_IN_DATA_STP_DISC should be 0x1A50+4*all_chn_num Signed-off-by: Yonglong Liu Signed-off-by: Peng Li Signed-off-by: David S. Miller --- drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c index e557a4ef5996..dc9215a565c9 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c @@ -2166,9 +2166,9 @@ void hns_dsaf_update_stats(struct dsaf_device *dsaf_dev, u32 node_num) DSAF_INODE_LOCAL_ADDR_FALSE_NUM_0_REG + 0x80 * (u64)node_num); hw_stats->vlan_drop += dsaf_read_dev(dsaf_dev, - DSAF_INODE_SW_VLAN_TAG_DISC_0_REG + 0x80 * (u64)node_num); + DSAF_INODE_SW_VLAN_TAG_DISC_0_REG + 4 * (u64)node_num); hw_stats->stp_drop += dsaf_read_dev(dsaf_dev, - DSAF_INODE_IN_DATA_STP_DISC_0_REG + 0x80 * (u64)node_num); + DSAF_INODE_IN_DATA_STP_DISC_0_REG + 4 * (u64)node_num); /* pfc pause frame statistics stored in dsaf inode*/ if ((node_num < DSAF_SERVICE_NW_NUM) && !is_ver1) { -- cgit v1.2.3 From 308c6cafde0147616da45e3a928adae55c428deb Mon Sep 17 00:00:00 2001 From: Yonglong Liu Date: Sat, 15 Dec 2018 11:53:21 +0800 Subject: net: hns: All ports can not work when insmod hns ko after rmmod. There are two test cases: 1. Remove the 4 modules:hns_enet_drv/hns_dsaf/hnae/hns_mdio, and install them again, must use "ifconfig down/ifconfig up" command pair to bring port to work. This patch calls phy_stop function when init phy to fix this bug. 2. Remove the 2 modules:hns_enet_drv/hns_dsaf, and install them again, all ports can not use anymore, because of the phy devices register failed(phy devices already exists). Phy devices are registered when hns_dsaf installed, this patch removes them when hns_dsaf removed. The two cases are sometimes related, fixing the second case also requires fixing the first case, so fix them together. Signed-off-by: Yonglong Liu Signed-off-by: Peng Li Signed-off-by: David S. Miller --- drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c | 15 +++++++++++++++ drivers/net/ethernet/hisilicon/hns/hns_enet.c | 3 +++ 2 files changed, 18 insertions(+) diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c index 3613e400e816..a97228c93831 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c @@ -778,6 +778,17 @@ static int hns_mac_register_phy(struct hns_mac_cb *mac_cb) return rc; } +static void hns_mac_remove_phydev(struct hns_mac_cb *mac_cb) +{ + if (!to_acpi_device_node(mac_cb->fw_port) || !mac_cb->phy_dev) + return; + + phy_device_remove(mac_cb->phy_dev); + phy_device_free(mac_cb->phy_dev); + + mac_cb->phy_dev = NULL; +} + #define MAC_MEDIA_TYPE_MAX_LEN 16 static const struct { @@ -1117,7 +1128,11 @@ void hns_mac_uninit(struct dsaf_device *dsaf_dev) int max_port_num = hns_mac_get_max_port_num(dsaf_dev); for (i = 0; i < max_port_num; i++) { + if (!dsaf_dev->mac_cb[i]) + continue; + dsaf_dev->misc_op->cpld_reset_led(dsaf_dev->mac_cb[i]); + hns_mac_remove_phydev(dsaf_dev->mac_cb[i]); dsaf_dev->mac_cb[i] = NULL; } } diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c index 28e907831b0e..c205a0e4b64b 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c @@ -1186,6 +1186,9 @@ int hns_nic_init_phy(struct net_device *ndev, struct hnae_handle *h) if (h->phy_if == PHY_INTERFACE_MODE_XGMII) phy_dev->autoneg = false; + if (h->phy_if == PHY_INTERFACE_MODE_SGMII) + phy_stop(phy_dev); + return 0; } -- cgit v1.2.3 From 4ad26f117b6ea0f5d5f1592127bafb5ec65904d3 Mon Sep 17 00:00:00 2001 From: Yonglong Liu Date: Sat, 15 Dec 2018 11:53:22 +0800 Subject: net: hns: Some registers use wrong address according to the datasheet. According to the hip06 datasheet: 1.Six registers use wrong address: RCB_COM_SF_CFG_INTMASK_RING RCB_COM_SF_CFG_RING_STS RCB_COM_SF_CFG_RING RCB_COM_SF_CFG_INTMASK_BD RCB_COM_SF_CFG_BD_RINT_STS DSAF_INODE_VC1_IN_PKT_NUM_0_REG 2.The offset of DSAF_INODE_VC1_IN_PKT_NUM_0_REG should be 0x103C + 0x80 * all_chn_num 3.The offset to show the value of DSAF_INODE_IN_DATA_STP_DISC_0_REG is wrong, so the value of DSAF_INODE_SW_VLAN_TAG_DISC_0_REG will be overwrite These registers are only used in "ethtool -d", so that did not cause ndev to misfunction. Signed-off-by: Yonglong Liu Signed-off-by: Peng Li Signed-off-by: David S. Miller --- drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c | 242 ++++++++++----------- drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h | 12 +- 2 files changed, 127 insertions(+), 127 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c index dc9215a565c9..97d62decba19 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c @@ -2285,237 +2285,237 @@ void hns_dsaf_get_regs(struct dsaf_device *ddev, u32 port, void *data) DSAF_INODE_BD_ORDER_STATUS_0_REG + j * 4); p[223 + i] = dsaf_read_dev(ddev, DSAF_INODE_SW_VLAN_TAG_DISC_0_REG + j * 4); - p[224 + i] = dsaf_read_dev(ddev, + p[226 + i] = dsaf_read_dev(ddev, DSAF_INODE_IN_DATA_STP_DISC_0_REG + j * 4); } - p[227] = dsaf_read_dev(ddev, DSAF_INODE_GE_FC_EN_0_REG + port * 4); + p[229] = dsaf_read_dev(ddev, DSAF_INODE_GE_FC_EN_0_REG + port * 4); for (i = 0; i < DSAF_INODE_NUM / DSAF_COMM_CHN; i++) { j = i * DSAF_COMM_CHN + port; - p[228 + i] = dsaf_read_dev(ddev, + p[230 + i] = dsaf_read_dev(ddev, DSAF_INODE_VC0_IN_PKT_NUM_0_REG + j * 4); } - p[231] = dsaf_read_dev(ddev, - DSAF_INODE_VC1_IN_PKT_NUM_0_REG + port * 4); + p[233] = dsaf_read_dev(ddev, + DSAF_INODE_VC1_IN_PKT_NUM_0_REG + port * 0x80); /* dsaf inode registers */ for (i = 0; i < HNS_DSAF_SBM_NUM(ddev) / DSAF_COMM_CHN; i++) { j = i * DSAF_COMM_CHN + port; - p[232 + i] = dsaf_read_dev(ddev, + p[234 + i] = dsaf_read_dev(ddev, DSAF_SBM_CFG_REG_0_REG + j * 0x80); - p[235 + i] = dsaf_read_dev(ddev, + p[237 + i] = dsaf_read_dev(ddev, DSAF_SBM_BP_CFG_0_XGE_REG_0_REG + j * 0x80); - p[238 + i] = dsaf_read_dev(ddev, + p[240 + i] = dsaf_read_dev(ddev, DSAF_SBM_BP_CFG_1_REG_0_REG + j * 0x80); - p[241 + i] = dsaf_read_dev(ddev, + p[243 + i] = dsaf_read_dev(ddev, DSAF_SBM_BP_CFG_2_XGE_REG_0_REG + j * 0x80); - p[244 + i] = dsaf_read_dev(ddev, + p[246 + i] = dsaf_read_dev(ddev, DSAF_SBM_FREE_CNT_0_0_REG + j * 0x80); - p[245 + i] = dsaf_read_dev(ddev, + p[249 + i] = dsaf_read_dev(ddev, DSAF_SBM_FREE_CNT_1_0_REG + j * 0x80); - p[248 + i] = dsaf_read_dev(ddev, + p[252 + i] = dsaf_read_dev(ddev, DSAF_SBM_BP_CNT_0_0_REG + j * 0x80); - p[251 + i] = dsaf_read_dev(ddev, + p[255 + i] = dsaf_read_dev(ddev, DSAF_SBM_BP_CNT_1_0_REG + j * 0x80); - p[254 + i] = dsaf_read_dev(ddev, + p[258 + i] = dsaf_read_dev(ddev, DSAF_SBM_BP_CNT_2_0_REG + j * 0x80); - p[257 + i] = dsaf_read_dev(ddev, + p[261 + i] = dsaf_read_dev(ddev, DSAF_SBM_BP_CNT_3_0_REG + j * 0x80); - p[260 + i] = dsaf_read_dev(ddev, + p[264 + i] = dsaf_read_dev(ddev, DSAF_SBM_INER_ST_0_REG + j * 0x80); - p[263 + i] = dsaf_read_dev(ddev, + p[267 + i] = dsaf_read_dev(ddev, DSAF_SBM_MIB_REQ_FAILED_TC_0_REG + j * 0x80); - p[266 + i] = dsaf_read_dev(ddev, + p[270 + i] = dsaf_read_dev(ddev, DSAF_SBM_LNK_INPORT_CNT_0_REG + j * 0x80); - p[269 + i] = dsaf_read_dev(ddev, + p[273 + i] = dsaf_read_dev(ddev, DSAF_SBM_LNK_DROP_CNT_0_REG + j * 0x80); - p[272 + i] = dsaf_read_dev(ddev, + p[276 + i] = dsaf_read_dev(ddev, DSAF_SBM_INF_OUTPORT_CNT_0_REG + j * 0x80); - p[275 + i] = dsaf_read_dev(ddev, + p[279 + i] = dsaf_read_dev(ddev, DSAF_SBM_LNK_INPORT_TC0_CNT_0_REG + j * 0x80); - p[278 + i] = dsaf_read_dev(ddev, + p[282 + i] = dsaf_read_dev(ddev, DSAF_SBM_LNK_INPORT_TC1_CNT_0_REG + j * 0x80); - p[281 + i] = dsaf_read_dev(ddev, + p[285 + i] = dsaf_read_dev(ddev, DSAF_SBM_LNK_INPORT_TC2_CNT_0_REG + j * 0x80); - p[284 + i] = dsaf_read_dev(ddev, + p[288 + i] = dsaf_read_dev(ddev, DSAF_SBM_LNK_INPORT_TC3_CNT_0_REG + j * 0x80); - p[287 + i] = dsaf_read_dev(ddev, + p[291 + i] = dsaf_read_dev(ddev, DSAF_SBM_LNK_INPORT_TC4_CNT_0_REG + j * 0x80); - p[290 + i] = dsaf_read_dev(ddev, + p[294 + i] = dsaf_read_dev(ddev, DSAF_SBM_LNK_INPORT_TC5_CNT_0_REG + j * 0x80); - p[293 + i] = dsaf_read_dev(ddev, + p[297 + i] = dsaf_read_dev(ddev, DSAF_SBM_LNK_INPORT_TC6_CNT_0_REG + j * 0x80); - p[296 + i] = dsaf_read_dev(ddev, + p[300 + i] = dsaf_read_dev(ddev, DSAF_SBM_LNK_INPORT_TC7_CNT_0_REG + j * 0x80); - p[299 + i] = dsaf_read_dev(ddev, + p[303 + i] = dsaf_read_dev(ddev, DSAF_SBM_LNK_REQ_CNT_0_REG + j * 0x80); - p[302 + i] = dsaf_read_dev(ddev, + p[306 + i] = dsaf_read_dev(ddev, DSAF_SBM_LNK_RELS_CNT_0_REG + j * 0x80); - p[305 + i] = dsaf_read_dev(ddev, + p[309 + i] = dsaf_read_dev(ddev, DSAF_SBM_BP_CFG_3_REG_0_REG + j * 0x80); - p[308 + i] = dsaf_read_dev(ddev, + p[312 + i] = dsaf_read_dev(ddev, DSAF_SBM_BP_CFG_4_REG_0_REG + j * 0x80); } /* dsaf onode registers */ for (i = 0; i < DSAF_XOD_NUM; i++) { - p[311 + i] = dsaf_read_dev(ddev, + p[315 + i] = dsaf_read_dev(ddev, DSAF_XOD_ETS_TSA_TC0_TC3_CFG_0_REG + i * 0x90); - p[319 + i] = dsaf_read_dev(ddev, + p[323 + i] = dsaf_read_dev(ddev, DSAF_XOD_ETS_TSA_TC4_TC7_CFG_0_REG + i * 0x90); - p[327 + i] = dsaf_read_dev(ddev, + p[331 + i] = dsaf_read_dev(ddev, DSAF_XOD_ETS_BW_TC0_TC3_CFG_0_REG + i * 0x90); - p[335 + i] = dsaf_read_dev(ddev, + p[339 + i] = dsaf_read_dev(ddev, DSAF_XOD_ETS_BW_TC4_TC7_CFG_0_REG + i * 0x90); - p[343 + i] = dsaf_read_dev(ddev, + p[347 + i] = dsaf_read_dev(ddev, DSAF_XOD_ETS_BW_OFFSET_CFG_0_REG + i * 0x90); - p[351 + i] = dsaf_read_dev(ddev, + p[355 + i] = dsaf_read_dev(ddev, DSAF_XOD_ETS_TOKEN_CFG_0_REG + i * 0x90); } - p[359] = dsaf_read_dev(ddev, DSAF_XOD_PFS_CFG_0_0_REG + port * 0x90); - p[360] = dsaf_read_dev(ddev, DSAF_XOD_PFS_CFG_1_0_REG + port * 0x90); - p[361] = dsaf_read_dev(ddev, DSAF_XOD_PFS_CFG_2_0_REG + port * 0x90); + p[363] = dsaf_read_dev(ddev, DSAF_XOD_PFS_CFG_0_0_REG + port * 0x90); + p[364] = dsaf_read_dev(ddev, DSAF_XOD_PFS_CFG_1_0_REG + port * 0x90); + p[365] = dsaf_read_dev(ddev, DSAF_XOD_PFS_CFG_2_0_REG + port * 0x90); for (i = 0; i < DSAF_XOD_BIG_NUM / DSAF_COMM_CHN; i++) { j = i * DSAF_COMM_CHN + port; - p[362 + i] = dsaf_read_dev(ddev, + p[366 + i] = dsaf_read_dev(ddev, DSAF_XOD_GNT_L_0_REG + j * 0x90); - p[365 + i] = dsaf_read_dev(ddev, + p[369 + i] = dsaf_read_dev(ddev, DSAF_XOD_GNT_H_0_REG + j * 0x90); - p[368 + i] = dsaf_read_dev(ddev, + p[372 + i] = dsaf_read_dev(ddev, DSAF_XOD_CONNECT_STATE_0_REG + j * 0x90); - p[371 + i] = dsaf_read_dev(ddev, + p[375 + i] = dsaf_read_dev(ddev, DSAF_XOD_RCVPKT_CNT_0_REG + j * 0x90); - p[374 + i] = dsaf_read_dev(ddev, + p[378 + i] = dsaf_read_dev(ddev, DSAF_XOD_RCVTC0_CNT_0_REG + j * 0x90); - p[377 + i] = dsaf_read_dev(ddev, + p[381 + i] = dsaf_read_dev(ddev, DSAF_XOD_RCVTC1_CNT_0_REG + j * 0x90); - p[380 + i] = dsaf_read_dev(ddev, + p[384 + i] = dsaf_read_dev(ddev, DSAF_XOD_RCVTC2_CNT_0_REG + j * 0x90); - p[383 + i] = dsaf_read_dev(ddev, + p[387 + i] = dsaf_read_dev(ddev, DSAF_XOD_RCVTC3_CNT_0_REG + j * 0x90); - p[386 + i] = dsaf_read_dev(ddev, + p[390 + i] = dsaf_read_dev(ddev, DSAF_XOD_RCVVC0_CNT_0_REG + j * 0x90); - p[389 + i] = dsaf_read_dev(ddev, + p[393 + i] = dsaf_read_dev(ddev, DSAF_XOD_RCVVC1_CNT_0_REG + j * 0x90); } - p[392] = dsaf_read_dev(ddev, + p[396] = dsaf_read_dev(ddev, DSAF_XOD_XGE_RCVIN0_CNT_0_REG + port * 0x90); - p[393] = dsaf_read_dev(ddev, + p[397] = dsaf_read_dev(ddev, DSAF_XOD_XGE_RCVIN1_CNT_0_REG + port * 0x90); - p[394] = dsaf_read_dev(ddev, + p[398] = dsaf_read_dev(ddev, DSAF_XOD_XGE_RCVIN2_CNT_0_REG + port * 0x90); - p[395] = dsaf_read_dev(ddev, + p[399] = dsaf_read_dev(ddev, DSAF_XOD_XGE_RCVIN3_CNT_0_REG + port * 0x90); - p[396] = dsaf_read_dev(ddev, + p[400] = dsaf_read_dev(ddev, DSAF_XOD_XGE_RCVIN4_CNT_0_REG + port * 0x90); - p[397] = dsaf_read_dev(ddev, + p[401] = dsaf_read_dev(ddev, DSAF_XOD_XGE_RCVIN5_CNT_0_REG + port * 0x90); - p[398] = dsaf_read_dev(ddev, + p[402] = dsaf_read_dev(ddev, DSAF_XOD_XGE_RCVIN6_CNT_0_REG + port * 0x90); - p[399] = dsaf_read_dev(ddev, + p[403] = dsaf_read_dev(ddev, DSAF_XOD_XGE_RCVIN7_CNT_0_REG + port * 0x90); - p[400] = dsaf_read_dev(ddev, + p[404] = dsaf_read_dev(ddev, DSAF_XOD_PPE_RCVIN0_CNT_0_REG + port * 0x90); - p[401] = dsaf_read_dev(ddev, + p[405] = dsaf_read_dev(ddev, DSAF_XOD_PPE_RCVIN1_CNT_0_REG + port * 0x90); - p[402] = dsaf_read_dev(ddev, + p[406] = dsaf_read_dev(ddev, DSAF_XOD_ROCEE_RCVIN0_CNT_0_REG + port * 0x90); - p[403] = dsaf_read_dev(ddev, + p[407] = dsaf_read_dev(ddev, DSAF_XOD_ROCEE_RCVIN1_CNT_0_REG + port * 0x90); - p[404] = dsaf_read_dev(ddev, + p[408] = dsaf_read_dev(ddev, DSAF_XOD_FIFO_STATUS_0_REG + port * 0x90); /* dsaf voq registers */ for (i = 0; i < DSAF_VOQ_NUM / DSAF_COMM_CHN; i++) { j = (i * DSAF_COMM_CHN + port) * 0x90; - p[405 + i] = dsaf_read_dev(ddev, + p[409 + i] = dsaf_read_dev(ddev, DSAF_VOQ_ECC_INVERT_EN_0_REG + j); - p[408 + i] = dsaf_read_dev(ddev, + p[412 + i] = dsaf_read_dev(ddev, DSAF_VOQ_SRAM_PKT_NUM_0_REG + j); - p[411 + i] = dsaf_read_dev(ddev, DSAF_VOQ_IN_PKT_NUM_0_REG + j); - p[414 + i] = dsaf_read_dev(ddev, + p[415 + i] = dsaf_read_dev(ddev, DSAF_VOQ_IN_PKT_NUM_0_REG + j); + p[418 + i] = dsaf_read_dev(ddev, DSAF_VOQ_OUT_PKT_NUM_0_REG + j); - p[417 + i] = dsaf_read_dev(ddev, + p[421 + i] = dsaf_read_dev(ddev, DSAF_VOQ_ECC_ERR_ADDR_0_REG + j); - p[420 + i] = dsaf_read_dev(ddev, DSAF_VOQ_BP_STATUS_0_REG + j); - p[423 + i] = dsaf_read_dev(ddev, DSAF_VOQ_SPUP_IDLE_0_REG + j); - p[426 + i] = dsaf_read_dev(ddev, + p[424 + i] = dsaf_read_dev(ddev, DSAF_VOQ_BP_STATUS_0_REG + j); + p[427 + i] = dsaf_read_dev(ddev, DSAF_VOQ_SPUP_IDLE_0_REG + j); + p[430 + i] = dsaf_read_dev(ddev, DSAF_VOQ_XGE_XOD_REQ_0_0_REG + j); - p[429 + i] = dsaf_read_dev(ddev, + p[433 + i] = dsaf_read_dev(ddev, DSAF_VOQ_XGE_XOD_REQ_1_0_REG + j); - p[432 + i] = dsaf_read_dev(ddev, + p[436 + i] = dsaf_read_dev(ddev, DSAF_VOQ_PPE_XOD_REQ_0_REG + j); - p[435 + i] = dsaf_read_dev(ddev, + p[439 + i] = dsaf_read_dev(ddev, DSAF_VOQ_ROCEE_XOD_REQ_0_REG + j); - p[438 + i] = dsaf_read_dev(ddev, + p[442 + i] = dsaf_read_dev(ddev, DSAF_VOQ_BP_ALL_THRD_0_REG + j); } /* dsaf tbl registers */ - p[441] = dsaf_read_dev(ddev, DSAF_TBL_CTRL_0_REG); - p[442] = dsaf_read_dev(ddev, DSAF_TBL_INT_MSK_0_REG); - p[443] = dsaf_read_dev(ddev, DSAF_TBL_INT_SRC_0_REG); - p[444] = dsaf_read_dev(ddev, DSAF_TBL_INT_STS_0_REG); - p[445] = dsaf_read_dev(ddev, DSAF_TBL_TCAM_ADDR_0_REG); - p[446] = dsaf_read_dev(ddev, DSAF_TBL_LINE_ADDR_0_REG); - p[447] = dsaf_read_dev(ddev, DSAF_TBL_TCAM_HIGH_0_REG); - p[448] = dsaf_read_dev(ddev, DSAF_TBL_TCAM_LOW_0_REG); - p[449] = dsaf_read_dev(ddev, DSAF_TBL_TCAM_MCAST_CFG_4_0_REG); - p[450] = dsaf_read_dev(ddev, DSAF_TBL_TCAM_MCAST_CFG_3_0_REG); - p[451] = dsaf_read_dev(ddev, DSAF_TBL_TCAM_MCAST_CFG_2_0_REG); - p[452] = dsaf_read_dev(ddev, DSAF_TBL_TCAM_MCAST_CFG_1_0_REG); - p[453] = dsaf_read_dev(ddev, DSAF_TBL_TCAM_MCAST_CFG_0_0_REG); - p[454] = dsaf_read_dev(ddev, DSAF_TBL_TCAM_UCAST_CFG_0_REG); - p[455] = dsaf_read_dev(ddev, DSAF_TBL_LIN_CFG_0_REG); - p[456] = dsaf_read_dev(ddev, DSAF_TBL_TCAM_RDATA_HIGH_0_REG); - p[457] = dsaf_read_dev(ddev, DSAF_TBL_TCAM_RDATA_LOW_0_REG); - p[458] = dsaf_read_dev(ddev, DSAF_TBL_TCAM_RAM_RDATA4_0_REG); - p[459] = dsaf_read_dev(ddev, DSAF_TBL_TCAM_RAM_RDATA3_0_REG); - p[460] = dsaf_read_dev(ddev, DSAF_TBL_TCAM_RAM_RDATA2_0_REG); - p[461] = dsaf_read_dev(ddev, DSAF_TBL_TCAM_RAM_RDATA1_0_REG); - p[462] = dsaf_read_dev(ddev, DSAF_TBL_TCAM_RAM_RDATA0_0_REG); - p[463] = dsaf_read_dev(ddev, DSAF_TBL_LIN_RDATA_0_REG); + p[445] = dsaf_read_dev(ddev, DSAF_TBL_CTRL_0_REG); + p[446] = dsaf_read_dev(ddev, DSAF_TBL_INT_MSK_0_REG); + p[447] = dsaf_read_dev(ddev, DSAF_TBL_INT_SRC_0_REG); + p[448] = dsaf_read_dev(ddev, DSAF_TBL_INT_STS_0_REG); + p[449] = dsaf_read_dev(ddev, DSAF_TBL_TCAM_ADDR_0_REG); + p[450] = dsaf_read_dev(ddev, DSAF_TBL_LINE_ADDR_0_REG); + p[451] = dsaf_read_dev(ddev, DSAF_TBL_TCAM_HIGH_0_REG); + p[452] = dsaf_read_dev(ddev, DSAF_TBL_TCAM_LOW_0_REG); + p[453] = dsaf_read_dev(ddev, DSAF_TBL_TCAM_MCAST_CFG_4_0_REG); + p[454] = dsaf_read_dev(ddev, DSAF_TBL_TCAM_MCAST_CFG_3_0_REG); + p[455] = dsaf_read_dev(ddev, DSAF_TBL_TCAM_MCAST_CFG_2_0_REG); + p[456] = dsaf_read_dev(ddev, DSAF_TBL_TCAM_MCAST_CFG_1_0_REG); + p[457] = dsaf_read_dev(ddev, DSAF_TBL_TCAM_MCAST_CFG_0_0_REG); + p[458] = dsaf_read_dev(ddev, DSAF_TBL_TCAM_UCAST_CFG_0_REG); + p[459] = dsaf_read_dev(ddev, DSAF_TBL_LIN_CFG_0_REG); + p[460] = dsaf_read_dev(ddev, DSAF_TBL_TCAM_RDATA_HIGH_0_REG); + p[461] = dsaf_read_dev(ddev, DSAF_TBL_TCAM_RDATA_LOW_0_REG); + p[462] = dsaf_read_dev(ddev, DSAF_TBL_TCAM_RAM_RDATA4_0_REG); + p[463] = dsaf_read_dev(ddev, DSAF_TBL_TCAM_RAM_RDATA3_0_REG); + p[464] = dsaf_read_dev(ddev, DSAF_TBL_TCAM_RAM_RDATA2_0_REG); + p[465] = dsaf_read_dev(ddev, DSAF_TBL_TCAM_RAM_RDATA1_0_REG); + p[466] = dsaf_read_dev(ddev, DSAF_TBL_TCAM_RAM_RDATA0_0_REG); + p[467] = dsaf_read_dev(ddev, DSAF_TBL_LIN_RDATA_0_REG); for (i = 0; i < DSAF_SW_PORT_NUM; i++) { j = i * 0x8; - p[464 + 2 * i] = dsaf_read_dev(ddev, + p[468 + 2 * i] = dsaf_read_dev(ddev, DSAF_TBL_DA0_MIS_INFO1_0_REG + j); - p[465 + 2 * i] = dsaf_read_dev(ddev, + p[469 + 2 * i] = dsaf_read_dev(ddev, DSAF_TBL_DA0_MIS_INFO0_0_REG + j); } - p[480] = dsaf_read_dev(ddev, DSAF_TBL_SA_MIS_INFO2_0_REG); - p[481] = dsaf_read_dev(ddev, DSAF_TBL_SA_MIS_INFO1_0_REG); - p[482] = dsaf_read_dev(ddev, DSAF_TBL_SA_MIS_INFO0_0_REG); - p[483] = dsaf_read_dev(ddev, DSAF_TBL_PUL_0_REG); - p[484] = dsaf_read_dev(ddev, DSAF_TBL_OLD_RSLT_0_REG); - p[485] = dsaf_read_dev(ddev, DSAF_TBL_OLD_SCAN_VAL_0_REG); - p[486] = dsaf_read_dev(ddev, DSAF_TBL_DFX_CTRL_0_REG); - p[487] = dsaf_read_dev(ddev, DSAF_TBL_DFX_STAT_0_REG); - p[488] = dsaf_read_dev(ddev, DSAF_TBL_DFX_STAT_2_0_REG); - p[489] = dsaf_read_dev(ddev, DSAF_TBL_LKUP_NUM_I_0_REG); - p[490] = dsaf_read_dev(ddev, DSAF_TBL_LKUP_NUM_O_0_REG); - p[491] = dsaf_read_dev(ddev, DSAF_TBL_UCAST_BCAST_MIS_INFO_0_0_REG); + p[484] = dsaf_read_dev(ddev, DSAF_TBL_SA_MIS_INFO2_0_REG); + p[485] = dsaf_read_dev(ddev, DSAF_TBL_SA_MIS_INFO1_0_REG); + p[486] = dsaf_read_dev(ddev, DSAF_TBL_SA_MIS_INFO0_0_REG); + p[487] = dsaf_read_dev(ddev, DSAF_TBL_PUL_0_REG); + p[488] = dsaf_read_dev(ddev, DSAF_TBL_OLD_RSLT_0_REG); + p[489] = dsaf_read_dev(ddev, DSAF_TBL_OLD_SCAN_VAL_0_REG); + p[490] = dsaf_read_dev(ddev, DSAF_TBL_DFX_CTRL_0_REG); + p[491] = dsaf_read_dev(ddev, DSAF_TBL_DFX_STAT_0_REG); + p[492] = dsaf_read_dev(ddev, DSAF_TBL_DFX_STAT_2_0_REG); + p[493] = dsaf_read_dev(ddev, DSAF_TBL_LKUP_NUM_I_0_REG); + p[494] = dsaf_read_dev(ddev, DSAF_TBL_LKUP_NUM_O_0_REG); + p[495] = dsaf_read_dev(ddev, DSAF_TBL_UCAST_BCAST_MIS_INFO_0_0_REG); /* dsaf other registers */ - p[492] = dsaf_read_dev(ddev, DSAF_INODE_FIFO_WL_0_REG + port * 0x4); - p[493] = dsaf_read_dev(ddev, DSAF_ONODE_FIFO_WL_0_REG + port * 0x4); - p[494] = dsaf_read_dev(ddev, DSAF_XGE_GE_WORK_MODE_0_REG + port * 0x4); - p[495] = dsaf_read_dev(ddev, + p[496] = dsaf_read_dev(ddev, DSAF_INODE_FIFO_WL_0_REG + port * 0x4); + p[497] = dsaf_read_dev(ddev, DSAF_ONODE_FIFO_WL_0_REG + port * 0x4); + p[498] = dsaf_read_dev(ddev, DSAF_XGE_GE_WORK_MODE_0_REG + port * 0x4); + p[499] = dsaf_read_dev(ddev, DSAF_XGE_APP_RX_LINK_UP_0_REG + port * 0x4); - p[496] = dsaf_read_dev(ddev, DSAF_NETPORT_CTRL_SIG_0_REG + port * 0x4); - p[497] = dsaf_read_dev(ddev, DSAF_XGE_CTRL_SIG_CFG_0_REG + port * 0x4); + p[500] = dsaf_read_dev(ddev, DSAF_NETPORT_CTRL_SIG_0_REG + port * 0x4); + p[501] = dsaf_read_dev(ddev, DSAF_XGE_CTRL_SIG_CFG_0_REG + port * 0x4); if (!is_ver1) - p[498] = dsaf_read_dev(ddev, DSAF_PAUSE_CFG_REG + port * 0x4); + p[502] = dsaf_read_dev(ddev, DSAF_PAUSE_CFG_REG + port * 0x4); /* mark end of dsaf regs */ - for (i = 499; i < 504; i++) + for (i = 503; i < 504; i++) p[i] = 0xdddddddd; } diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h index 74d935d82cbc..f171d11b9b44 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h @@ -176,7 +176,7 @@ #define DSAF_INODE_IN_DATA_STP_DISC_0_REG 0x1A50 #define DSAF_INODE_GE_FC_EN_0_REG 0x1B00 #define DSAF_INODE_VC0_IN_PKT_NUM_0_REG 0x1B50 -#define DSAF_INODE_VC1_IN_PKT_NUM_0_REG 0x1C00 +#define DSAF_INODE_VC1_IN_PKT_NUM_0_REG 0x103C #define DSAF_INODE_IN_PRIO_PAUSE_BASE_REG 0x1C00 #define DSAF_INODE_IN_PRIO_PAUSE_BASE_OFFSET 0x100 #define DSAF_INODE_IN_PRIO_PAUSE_OFFSET 0x50 @@ -404,11 +404,11 @@ #define RCB_ECC_ERR_ADDR4_REG 0x460 #define RCB_ECC_ERR_ADDR5_REG 0x464 -#define RCB_COM_SF_CFG_INTMASK_RING 0x480 -#define RCB_COM_SF_CFG_RING_STS 0x484 -#define RCB_COM_SF_CFG_RING 0x488 -#define RCB_COM_SF_CFG_INTMASK_BD 0x48C -#define RCB_COM_SF_CFG_BD_RINT_STS 0x470 +#define RCB_COM_SF_CFG_INTMASK_RING 0x470 +#define RCB_COM_SF_CFG_RING_STS 0x474 +#define RCB_COM_SF_CFG_RING 0x478 +#define RCB_COM_SF_CFG_INTMASK_BD 0x47C +#define RCB_COM_SF_CFG_BD_RINT_STS 0x480 #define RCB_COM_RCB_RD_BD_BUSY 0x490 #define RCB_COM_RCB_FBD_CRT_EN 0x494 #define RCB_COM_AXI_WR_ERR_INTMASK 0x498 -- cgit v1.2.3 From 5778b13b64eca5549d242686f2f91a2c80c8fa40 Mon Sep 17 00:00:00 2001 From: Yonglong Liu Date: Sat, 15 Dec 2018 11:53:23 +0800 Subject: net: hns: Fixed bug that netdev was opened twice After resetting dsaf to try to repair chip error such as ecc error, the net device will be open if net interface is up. But at this time if there is the users set the net device up with the command ifconfig, the net device will be opened twice consecutively. Function napi_enable was called when open device. And Kernel panic will be occurred if it was called twice consecutively. Such as follow: static inline void napi_enable(struct napi_struct *n) { BUG_ON(!test_bit(NAPI_STATE_SCHED, &n->state)); smp_mb__before_clear_bit(); clear_bit(NAPI_STATE_SCHED, &n->state); } [37255.571996] Kernel panic - not syncing: BUG! [37255.595234] Call trace: [37255.597694] [] dump_backtrace+0x0/0x1a0 [37255.603114] [] show_stack+0x20/0x28 [37255.608187] [] dump_stack+0x98/0xb8 [37255.613258] [] panic+0x10c/0x26c [37255.618070] [] hns_nic_net_up+0x30c/0x4e0 [37255.623664] [] hns_nic_net_open+0x94/0x12c [37255.629346] [] __dev_open+0xf4/0x168 [37255.634504] [] __dev_change_flags+0x98/0x15c [37255.640359] [] dev_change_flags+0x2c/0x68 [37255.769580] [] devinet_ioctl+0x650/0x704 [37255.775086] [] inet_ioctl+0x98/0xb4 [37255.780159] [] sock_do_ioctl+0x44/0x84 [37255.785490] [] sock_ioctl+0x248/0x30c [37255.790737] [] do_vfs_ioctl+0x480/0x618 [37255.796156] [] SyS_ioctl+0x90/0xa4 [37255.801139] SMP: stopping secondary CPUs [37255.805079] kbox: catch panic event. [37255.809586] collected_len = 128928, LOG_BUF_LEN_LOCAL = 131072 [37255.816103] flush cache 0xffff80003f000000 size 0x800000 [37255.822192] flush cache 0xffff80003f000000 size 0x800000 [37255.828289] flush cache 0xffff80003f000000 size 0x800000 [37255.834378] kbox: no notify die func register. no need to notify [37255.840413] ---[ end Kernel panic - not syncing: BUG! This patchset fix this bug according to the flag NIC_STATE_DOWN. Signed-off-by: Yonglong Liu Signed-off-by: Peng Li Signed-off-by: David S. Miller --- drivers/net/ethernet/hisilicon/hns/hns_enet.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c index c205a0e4b64b..c9454c4784cb 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c @@ -1333,6 +1333,9 @@ static int hns_nic_net_up(struct net_device *ndev) int i, j; int ret; + if (!test_bit(NIC_STATE_DOWN, &priv->state)) + return 0; + ret = hns_nic_init_irq(priv); if (ret != 0) { netdev_err(ndev, "hns init irq failed! ret=%d\n", ret); -- cgit v1.2.3 From 31f6b61d810654fb3ef43f4d8afda0f44b142fad Mon Sep 17 00:00:00 2001 From: Yonglong Liu Date: Sat, 15 Dec 2018 11:53:24 +0800 Subject: net: hns: Clean rx fbd when ae stopped. If there are packets in hardware when changing the speed or duplex, it may cause hardware hang up. This patch adds the code to wait rx fbd clean up when ae stopped. Signed-off-by: Yonglong Liu Signed-off-by: Peng Li Signed-off-by: David S. Miller --- drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c index b52029e26d15..ad1779fc410e 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c @@ -379,6 +379,9 @@ static void hns_ae_stop(struct hnae_handle *handle) hns_ae_ring_enable_all(handle, 0); + /* clean rx fbd. */ + hns_rcb_wait_fbd_clean(handle->qs, handle->q_num, RCB_INT_FLAG_RX); + (void)hns_mac_vm_config_bc_en(mac_cb, 0, false); } -- cgit v1.2.3 From c82bd077e1ba3dd586569c733dc6d3dd4b0e43cd Mon Sep 17 00:00:00 2001 From: Yonglong Liu Date: Sat, 15 Dec 2018 11:53:25 +0800 Subject: net: hns: Free irq when exit from abnormal branch 1.In "hns_nic_init_irq", if request irq fail at index i, the function return directly without releasing irq resources that already requested. 2.In "hns_nic_net_up" after "hns_nic_init_irq", if exceptional branch occurs, irqs that already requested are not release. Signed-off-by: Yonglong Liu Signed-off-by: Peng Li Signed-off-by: David S. Miller --- drivers/net/ethernet/hisilicon/hns/hns_enet.c | 23 ++++++++++++++++++++++- 1 file changed, 22 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c index c9454c4784cb..03d959c7a39f 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c @@ -1284,6 +1284,22 @@ static int hns_nic_init_affinity_mask(int q_num, int ring_idx, return cpu; } +static void hns_nic_free_irq(int q_num, struct hns_nic_priv *priv) +{ + int i; + + for (i = 0; i < q_num * 2; i++) { + if (priv->ring_data[i].ring->irq_init_flag == RCB_IRQ_INITED) { + irq_set_affinity_hint(priv->ring_data[i].ring->irq, + NULL); + free_irq(priv->ring_data[i].ring->irq, + &priv->ring_data[i]); + priv->ring_data[i].ring->irq_init_flag = + RCB_IRQ_NOT_INITED; + } + } +} + static int hns_nic_init_irq(struct hns_nic_priv *priv) { struct hnae_handle *h = priv->ae_handle; @@ -1309,7 +1325,7 @@ static int hns_nic_init_irq(struct hns_nic_priv *priv) if (ret) { netdev_err(priv->netdev, "request irq(%d) fail\n", rd->ring->irq); - return ret; + goto out_free_irq; } disable_irq(rd->ring->irq); @@ -1324,6 +1340,10 @@ static int hns_nic_init_irq(struct hns_nic_priv *priv) } return 0; + +out_free_irq: + hns_nic_free_irq(h->q_num, priv); + return ret; } static int hns_nic_net_up(struct net_device *ndev) @@ -1371,6 +1391,7 @@ out_has_some_queues: for (j = i - 1; j >= 0; j--) hns_nic_ring_close(ndev, j); + hns_nic_free_irq(h->q_num, priv); set_bit(NIC_STATE_DOWN, &priv->state); return ret; -- cgit v1.2.3 From a57275d35576fdd89d8c771eedf1e7cf97e0dfa6 Mon Sep 17 00:00:00 2001 From: Yonglong Liu Date: Sat, 15 Dec 2018 11:53:26 +0800 Subject: net: hns: Avoid net reset caused by pause frames storm There will be a large number of MAC pause frames on the net, which caused tx timeout of net device. And then the net device was reset to try to recover it. So that is not useful, and will cause some other problems. So need doubled ndev->watchdog_timeo if device watchdog occurred until watchdog_timeo up to 40s and then try resetting to recover it. When collecting dfx information such as hardware registers when tx timeout. Some registers for count were cleared when read. So need move this task before update net state which also read the count registers. Signed-off-by: Yonglong Liu Signed-off-by: Peng Li Signed-off-by: David S. Miller --- drivers/net/ethernet/hisilicon/hns/hns_enet.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c index 03d959c7a39f..8a53c82c72b4 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c @@ -1509,11 +1509,19 @@ static int hns_nic_net_stop(struct net_device *ndev) } static void hns_tx_timeout_reset(struct hns_nic_priv *priv); +#define HNS_TX_TIMEO_LIMIT (40 * HZ) static void hns_nic_net_timeout(struct net_device *ndev) { struct hns_nic_priv *priv = netdev_priv(ndev); - hns_tx_timeout_reset(priv); + if (ndev->watchdog_timeo < HNS_TX_TIMEO_LIMIT) { + ndev->watchdog_timeo *= 2; + netdev_info(ndev, "watchdog_timo changed to %d.\n", + ndev->watchdog_timeo); + } else { + ndev->watchdog_timeo = HNS_NIC_TX_TIMEOUT; + hns_tx_timeout_reset(priv); + } } static int hns_nic_do_ioctl(struct net_device *netdev, struct ifreq *ifr, @@ -2076,11 +2084,11 @@ static void hns_nic_service_task(struct work_struct *work) = container_of(work, struct hns_nic_priv, service_task); struct hnae_handle *h = priv->ae_handle; + hns_nic_reset_subtask(priv); hns_nic_update_link_status(priv->netdev); h->dev->ops->update_led_status(h); hns_nic_update_stats(priv->netdev); - hns_nic_reset_subtask(priv); hns_nic_service_event_complete(priv); } -- cgit v1.2.3 From 7e74a19ca522aec7c2be201a7ae1d1d57ded409b Mon Sep 17 00:00:00 2001 From: Yonglong Liu Date: Sat, 15 Dec 2018 11:53:27 +0800 Subject: net: hns: Fix ntuple-filters status error. The ntuple-filters features is forced on by chip. But it shows "ntuple-filters: off [fixed]" when use ethtool. This patch make it correct with "ntuple-filters: on [fixed]". Signed-off-by: Yonglong Liu Signed-off-by: Peng Li Signed-off-by: David S. Miller --- drivers/net/ethernet/hisilicon/hns/hns_enet.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c index 8a53c82c72b4..6242249c9f4c 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c @@ -2374,7 +2374,7 @@ static int hns_nic_dev_probe(struct platform_device *pdev) ndev->min_mtu = MAC_MIN_MTU; switch (priv->enet_ver) { case AE_VERSION_2: - ndev->features |= NETIF_F_TSO | NETIF_F_TSO6; + ndev->features |= NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_NTUPLE; ndev->hw_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_RXCSUM | NETIF_F_SG | NETIF_F_GSO | NETIF_F_GRO | NETIF_F_TSO | NETIF_F_TSO6; -- cgit v1.2.3 From 726ae5c9e5f0c18eca8ea5296b526242c3e89822 Mon Sep 17 00:00:00 2001 From: Yonglong Liu Date: Sat, 15 Dec 2018 11:53:28 +0800 Subject: net: hns: Add mac pcs config when enable|disable mac In some case, when mac enable|disable and adjust link, may cause hard to link(or abnormal) between mac and phy. This patch adds the code for rx PCS to avoid this bug. Disable the rx PCS when driver disable the gmac, and enable the rx PCS when driver enable the mac. Signed-off-by: Yonglong Liu Signed-off-by: Peng Li Signed-off-by: David S. Miller --- drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c | 14 ++++++++++---- drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h | 1 + 2 files changed, 11 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c index aaf72c055711..1790cdafd9b8 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c @@ -67,11 +67,14 @@ static void hns_gmac_enable(void *mac_drv, enum mac_commom_mode mode) struct mac_driver *drv = (struct mac_driver *)mac_drv; /*enable GE rX/tX */ - if ((mode == MAC_COMM_MODE_TX) || (mode == MAC_COMM_MODE_RX_AND_TX)) + if (mode == MAC_COMM_MODE_TX || mode == MAC_COMM_MODE_RX_AND_TX) dsaf_set_dev_bit(drv, GMAC_PORT_EN_REG, GMAC_PORT_TX_EN_B, 1); - if ((mode == MAC_COMM_MODE_RX) || (mode == MAC_COMM_MODE_RX_AND_TX)) + if (mode == MAC_COMM_MODE_RX || mode == MAC_COMM_MODE_RX_AND_TX) { + /* enable rx pcs */ + dsaf_set_dev_bit(drv, GMAC_PCS_RX_EN_REG, 0, 0); dsaf_set_dev_bit(drv, GMAC_PORT_EN_REG, GMAC_PORT_RX_EN_B, 1); + } } static void hns_gmac_disable(void *mac_drv, enum mac_commom_mode mode) @@ -79,11 +82,14 @@ static void hns_gmac_disable(void *mac_drv, enum mac_commom_mode mode) struct mac_driver *drv = (struct mac_driver *)mac_drv; /*disable GE rX/tX */ - if ((mode == MAC_COMM_MODE_TX) || (mode == MAC_COMM_MODE_RX_AND_TX)) + if (mode == MAC_COMM_MODE_TX || mode == MAC_COMM_MODE_RX_AND_TX) dsaf_set_dev_bit(drv, GMAC_PORT_EN_REG, GMAC_PORT_TX_EN_B, 0); - if ((mode == MAC_COMM_MODE_RX) || (mode == MAC_COMM_MODE_RX_AND_TX)) + if (mode == MAC_COMM_MODE_RX || mode == MAC_COMM_MODE_RX_AND_TX) { + /* disable rx pcs */ + dsaf_set_dev_bit(drv, GMAC_PCS_RX_EN_REG, 0, 1); dsaf_set_dev_bit(drv, GMAC_PORT_EN_REG, GMAC_PORT_RX_EN_B, 0); + } } /* hns_gmac_get_en - get port enable diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h index f171d11b9b44..b9733b0b8482 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h @@ -534,6 +534,7 @@ #define GMAC_LD_LINK_COUNTER_REG 0x01D0UL #define GMAC_LOOP_REG 0x01DCUL #define GMAC_RECV_CONTROL_REG 0x01E0UL +#define GMAC_PCS_RX_EN_REG 0x01E4UL #define GMAC_VLAN_CODE_REG 0x01E8UL #define GMAC_RX_OVERRUN_CNT_REG 0x01ECUL #define GMAC_RX_LENGTHFIELD_ERR_CNT_REG 0x01F4UL -- cgit v1.2.3 From 6adafc356e20189193b38ee6b9af7743078bf6b4 Mon Sep 17 00:00:00 2001 From: Yonglong Liu Date: Sat, 15 Dec 2018 11:53:29 +0800 Subject: net: hns: Fix ping failed when use net bridge and send multicast Create a net bridge, add eth and vnet to the bridge. The vnet is used by a virtual machine. When ping the virtual machine from the outside host and the virtual machine send multicast at the same time, the ping package will lost. The multicast package send to the eth, eth will send it to the bridge too, and the bridge learn the mac of eth. When outside host ping the virtual mechine, it will match the promisc entry of the eth which is not expected, and the bridge send it to eth not to vnet, cause ping lost. So this patch change promisc tcam entry position to the END of 512 tcam entries, which indicate lower priority. And separate one promisc entry to two: mc & uc, to avoid package match the wrong tcam entry. Signed-off-by: Yonglong Liu Signed-off-by: Peng Li Signed-off-by: David S. Miller --- drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c | 257 +++++++++++++++++---- 1 file changed, 216 insertions(+), 41 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c index 97d62decba19..3b9e74be5fbd 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c @@ -934,6 +934,62 @@ static void hns_dsaf_tcam_mc_cfg( spin_unlock_bh(&dsaf_dev->tcam_lock); } +/** + * hns_dsaf_tcam_uc_cfg_vague - INT + * @dsaf_dev: dsa fabric device struct pointer + * @address, + * @ptbl_tcam_data, + */ +static void hns_dsaf_tcam_uc_cfg_vague(struct dsaf_device *dsaf_dev, + u32 address, + struct dsaf_tbl_tcam_data *tcam_data, + struct dsaf_tbl_tcam_data *tcam_mask, + struct dsaf_tbl_tcam_ucast_cfg *tcam_uc) +{ + spin_lock_bh(&dsaf_dev->tcam_lock); + hns_dsaf_tbl_tcam_addr_cfg(dsaf_dev, address); + hns_dsaf_tbl_tcam_data_cfg(dsaf_dev, tcam_data); + hns_dsaf_tbl_tcam_ucast_cfg(dsaf_dev, tcam_uc); + hns_dsaf_tbl_tcam_match_cfg(dsaf_dev, tcam_mask); + hns_dsaf_tbl_tcam_data_ucast_pul(dsaf_dev); + + /*Restore Match Data*/ + tcam_mask->tbl_tcam_data_high = 0xffffffff; + tcam_mask->tbl_tcam_data_low = 0xffffffff; + hns_dsaf_tbl_tcam_match_cfg(dsaf_dev, tcam_mask); + + spin_unlock_bh(&dsaf_dev->tcam_lock); +} + +/** + * hns_dsaf_tcam_mc_cfg_vague - INT + * @dsaf_dev: dsa fabric device struct pointer + * @address, + * @ptbl_tcam_data, + * @ptbl_tcam_mask + * @ptbl_tcam_mcast + */ +static void hns_dsaf_tcam_mc_cfg_vague(struct dsaf_device *dsaf_dev, + u32 address, + struct dsaf_tbl_tcam_data *tcam_data, + struct dsaf_tbl_tcam_data *tcam_mask, + struct dsaf_tbl_tcam_mcast_cfg *tcam_mc) +{ + spin_lock_bh(&dsaf_dev->tcam_lock); + hns_dsaf_tbl_tcam_addr_cfg(dsaf_dev, address); + hns_dsaf_tbl_tcam_data_cfg(dsaf_dev, tcam_data); + hns_dsaf_tbl_tcam_mcast_cfg(dsaf_dev, tcam_mc); + hns_dsaf_tbl_tcam_match_cfg(dsaf_dev, tcam_mask); + hns_dsaf_tbl_tcam_data_mcast_pul(dsaf_dev); + + /*Restore Match Data*/ + tcam_mask->tbl_tcam_data_high = 0xffffffff; + tcam_mask->tbl_tcam_data_low = 0xffffffff; + hns_dsaf_tbl_tcam_match_cfg(dsaf_dev, tcam_mask); + + spin_unlock_bh(&dsaf_dev->tcam_lock); +} + /** * hns_dsaf_tcam_mc_invld - INT * @dsaf_id: dsa fabric id @@ -1492,6 +1548,27 @@ static u16 hns_dsaf_find_empty_mac_entry(struct dsaf_device *dsaf_dev) return DSAF_INVALID_ENTRY_IDX; } +/** + * hns_dsaf_find_empty_mac_entry_reverse + * search dsa fabric soft empty-entry from the end + * @dsaf_dev: dsa fabric device struct pointer + */ +static u16 hns_dsaf_find_empty_mac_entry_reverse(struct dsaf_device *dsaf_dev) +{ + struct dsaf_drv_priv *priv = hns_dsaf_dev_priv(dsaf_dev); + struct dsaf_drv_soft_mac_tbl *soft_mac_entry; + int i; + + soft_mac_entry = priv->soft_mac_tbl + (DSAF_TCAM_SUM - 1); + for (i = (DSAF_TCAM_SUM - 1); i > 0; i--) { + /* search all entry from end to start.*/ + if (soft_mac_entry->index == DSAF_INVALID_ENTRY_IDX) + return i; + soft_mac_entry--; + } + return DSAF_INVALID_ENTRY_IDX; +} + /** * hns_dsaf_set_mac_key - set mac key * @dsaf_dev: dsa fabric device struct pointer @@ -2673,58 +2750,156 @@ int hns_dsaf_get_regs_count(void) return DSAF_DUMP_REGS_NUM; } -/* Reserve the last TCAM entry for promisc support */ -#define dsaf_promisc_tcam_entry(port) \ - (DSAF_TCAM_SUM - DSAFV2_MAC_FUZZY_TCAM_NUM + (port)) -void hns_dsaf_set_promisc_tcam(struct dsaf_device *dsaf_dev, - u32 port, bool enable) +static void set_promisc_tcam_enable(struct dsaf_device *dsaf_dev, u32 port) { + struct dsaf_tbl_tcam_ucast_cfg tbl_tcam_ucast = {0, 1, 0, 0, 0x80}; + struct dsaf_tbl_tcam_data tbl_tcam_data_mc = {0x01000000, port}; + struct dsaf_tbl_tcam_data tbl_tcam_mask_uc = {0x01000000, 0xf}; + struct dsaf_tbl_tcam_mcast_cfg tbl_tcam_mcast = {0, 0, {0} }; struct dsaf_drv_priv *priv = hns_dsaf_dev_priv(dsaf_dev); - struct dsaf_drv_soft_mac_tbl *soft_mac_entry = priv->soft_mac_tbl; - u16 entry_index; - struct dsaf_drv_tbl_tcam_key tbl_tcam_data, tbl_tcam_mask; - struct dsaf_tbl_tcam_mcast_cfg mac_data = {0}; + struct dsaf_tbl_tcam_data tbl_tcam_data_uc = {0, port}; + struct dsaf_drv_mac_single_dest_entry mask_entry; + struct dsaf_drv_tbl_tcam_key temp_key, mask_key; + struct dsaf_drv_soft_mac_tbl *soft_mac_entry; + u16 entry_index = DSAF_INVALID_ENTRY_IDX; + struct dsaf_drv_tbl_tcam_key mac_key; + struct hns_mac_cb *mac_cb; + u8 addr[ETH_ALEN] = {0}; + u8 port_num; + u16 mskid; - if ((AE_IS_VER1(dsaf_dev->dsaf_ver)) || HNS_DSAF_IS_DEBUG(dsaf_dev)) + /* promisc use vague table match with vlanid = 0 & macaddr = 0 */ + hns_dsaf_set_mac_key(dsaf_dev, &mac_key, 0x00, port, addr); + entry_index = hns_dsaf_find_soft_mac_entry(dsaf_dev, &mac_key); + if (entry_index != DSAF_INVALID_ENTRY_IDX) return; - /* find the tcam entry index for promisc */ - entry_index = dsaf_promisc_tcam_entry(port); - - memset(&tbl_tcam_data, 0, sizeof(tbl_tcam_data)); - memset(&tbl_tcam_mask, 0, sizeof(tbl_tcam_mask)); - - /* config key mask */ - if (enable) { - dsaf_set_field(tbl_tcam_data.low.bits.port_vlan, - DSAF_TBL_TCAM_KEY_PORT_M, - DSAF_TBL_TCAM_KEY_PORT_S, port); - dsaf_set_field(tbl_tcam_mask.low.bits.port_vlan, - DSAF_TBL_TCAM_KEY_PORT_M, - DSAF_TBL_TCAM_KEY_PORT_S, 0xf); - - /* SUB_QID */ - dsaf_set_bit(mac_data.tbl_mcast_port_msk[0], - DSAF_SERVICE_NW_NUM, true); - mac_data.tbl_mcast_item_vld = true; /* item_vld bit */ + /* put promisc tcam entry in the end. */ + /* 1. set promisc unicast vague tcam entry. */ + entry_index = hns_dsaf_find_empty_mac_entry_reverse(dsaf_dev); + if (entry_index == DSAF_INVALID_ENTRY_IDX) { + dev_err(dsaf_dev->dev, + "enable uc promisc failed (port:%#x)\n", + port); + return; + } + + mac_cb = dsaf_dev->mac_cb[port]; + (void)hns_mac_get_inner_port_num(mac_cb, 0, &port_num); + tbl_tcam_ucast.tbl_ucast_out_port = port_num; + + /* config uc vague table */ + hns_dsaf_tcam_uc_cfg_vague(dsaf_dev, entry_index, &tbl_tcam_data_uc, + &tbl_tcam_mask_uc, &tbl_tcam_ucast); + + /* update software entry */ + soft_mac_entry = priv->soft_mac_tbl; + soft_mac_entry += entry_index; + soft_mac_entry->index = entry_index; + soft_mac_entry->tcam_key.high.val = mac_key.high.val; + soft_mac_entry->tcam_key.low.val = mac_key.low.val; + /* step back to the START for mc. */ + soft_mac_entry = priv->soft_mac_tbl; + + /* 2. set promisc multicast vague tcam entry. */ + entry_index = hns_dsaf_find_empty_mac_entry_reverse(dsaf_dev); + if (entry_index == DSAF_INVALID_ENTRY_IDX) { + dev_err(dsaf_dev->dev, + "enable mc promisc failed (port:%#x)\n", + port); + return; + } + + memset(&mask_entry, 0x0, sizeof(mask_entry)); + memset(&mask_key, 0x0, sizeof(mask_key)); + memset(&temp_key, 0x0, sizeof(temp_key)); + mask_entry.addr[0] = 0x01; + hns_dsaf_set_mac_key(dsaf_dev, &mask_key, mask_entry.in_vlan_id, + port, mask_entry.addr); + tbl_tcam_mcast.tbl_mcast_item_vld = 1; + tbl_tcam_mcast.tbl_mcast_old_en = 0; + + if (port < DSAF_SERVICE_NW_NUM) { + mskid = port; + } else if (port >= DSAF_BASE_INNER_PORT_NUM) { + mskid = port - DSAF_BASE_INNER_PORT_NUM + DSAF_SERVICE_NW_NUM; } else { - mac_data.tbl_mcast_item_vld = false; /* item_vld bit */ + dev_err(dsaf_dev->dev, "%s,pnum(%d)error,key(%#x:%#x)\n", + dsaf_dev->ae_dev.name, port, + mask_key.high.val, mask_key.low.val); + return; } - dev_dbg(dsaf_dev->dev, - "set_promisc_entry, %s Mac key(%#x:%#x) entry_index%d\n", - dsaf_dev->ae_dev.name, tbl_tcam_data.high.val, - tbl_tcam_data.low.val, entry_index); + dsaf_set_bit(tbl_tcam_mcast.tbl_mcast_port_msk[mskid / 32], + mskid % 32, 1); + memcpy(&temp_key, &mask_key, sizeof(mask_key)); + hns_dsaf_tcam_mc_cfg_vague(dsaf_dev, entry_index, &tbl_tcam_data_mc, + (struct dsaf_tbl_tcam_data *)(&mask_key), + &tbl_tcam_mcast); - /* config promisc entry with mask */ - hns_dsaf_tcam_mc_cfg(dsaf_dev, entry_index, - (struct dsaf_tbl_tcam_data *)&tbl_tcam_data, - (struct dsaf_tbl_tcam_data *)&tbl_tcam_mask, - &mac_data); + /* update software entry */ + soft_mac_entry += entry_index; + soft_mac_entry->index = entry_index; + soft_mac_entry->tcam_key.high.val = temp_key.high.val; + soft_mac_entry->tcam_key.low.val = temp_key.low.val; +} - /* config software entry */ +static void set_promisc_tcam_disable(struct dsaf_device *dsaf_dev, u32 port) +{ + struct dsaf_tbl_tcam_data tbl_tcam_data_mc = {0x01000000, port}; + struct dsaf_tbl_tcam_ucast_cfg tbl_tcam_ucast = {0, 0, 0, 0, 0}; + struct dsaf_tbl_tcam_mcast_cfg tbl_tcam_mcast = {0, 0, {0} }; + struct dsaf_drv_priv *priv = hns_dsaf_dev_priv(dsaf_dev); + struct dsaf_tbl_tcam_data tbl_tcam_data_uc = {0, 0}; + struct dsaf_tbl_tcam_data tbl_tcam_mask = {0, 0}; + struct dsaf_drv_soft_mac_tbl *soft_mac_entry; + u16 entry_index = DSAF_INVALID_ENTRY_IDX; + struct dsaf_drv_tbl_tcam_key mac_key; + u8 addr[ETH_ALEN] = {0}; + + /* 1. delete uc vague tcam entry. */ + /* promisc use vague table match with vlanid = 0 & macaddr = 0 */ + hns_dsaf_set_mac_key(dsaf_dev, &mac_key, 0x00, port, addr); + entry_index = hns_dsaf_find_soft_mac_entry(dsaf_dev, &mac_key); + + if (entry_index == DSAF_INVALID_ENTRY_IDX) + return; + + /* config uc vague table */ + hns_dsaf_tcam_uc_cfg_vague(dsaf_dev, entry_index, &tbl_tcam_data_uc, + &tbl_tcam_mask, &tbl_tcam_ucast); + /* update soft management table. */ + soft_mac_entry = priv->soft_mac_tbl; soft_mac_entry += entry_index; - soft_mac_entry->index = enable ? entry_index : DSAF_INVALID_ENTRY_IDX; + soft_mac_entry->index = DSAF_INVALID_ENTRY_IDX; + /* step back to the START for mc. */ + soft_mac_entry = priv->soft_mac_tbl; + + /* 2. delete mc vague tcam entry. */ + addr[0] = 0x01; + memset(&mac_key, 0x0, sizeof(mac_key)); + hns_dsaf_set_mac_key(dsaf_dev, &mac_key, 0x00, port, addr); + entry_index = hns_dsaf_find_soft_mac_entry(dsaf_dev, &mac_key); + + if (entry_index == DSAF_INVALID_ENTRY_IDX) + return; + + /* config mc vague table */ + hns_dsaf_tcam_mc_cfg_vague(dsaf_dev, entry_index, &tbl_tcam_data_mc, + &tbl_tcam_mask, &tbl_tcam_mcast); + /* update soft management table. */ + soft_mac_entry += entry_index; + soft_mac_entry->index = DSAF_INVALID_ENTRY_IDX; +} + +/* Reserve the last TCAM entry for promisc support */ +void hns_dsaf_set_promisc_tcam(struct dsaf_device *dsaf_dev, + u32 port, bool enable) +{ + if (enable) + set_promisc_tcam_enable(dsaf_dev, port); + else + set_promisc_tcam_disable(dsaf_dev, port); } int hns_dsaf_wait_pkt_clean(struct dsaf_device *dsaf_dev, int port) -- cgit v1.2.3 From e735fd55b94bb48363737db3b1d57627c1a16b47 Mon Sep 17 00:00:00 2001 From: Marcin Wojtas Date: Tue, 11 Dec 2018 13:56:49 +0100 Subject: net: mvneta: fix operation for 64K PAGE_SIZE Recent changes in the mvneta driver reworked allocation and handling of the ingress buffers to use entire pages. Apart from that in SW BM scenario the HW must be informed via PRXDQS about the biggest possible incoming buffer that can be propagated by RX descriptors. The BufferSize field was filled according to the MTU-dependent pkt_size value. Later change to PAGE_SIZE broke RX operation when usin 64K pages, as the field is simply too small. This patch conditionally limits the value passed to the BufferSize of the PRXDQS register, depending on the PAGE_SIZE used. On the occasion remove now unused frag_size field of the mvneta_port structure. Fixes: 562e2f467e71 ("net: mvneta: Improve the buffer allocation method for SWBM") Signed-off-by: Marcin Wojtas Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/mvneta.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index e5397c8197b9..61b23497f836 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -408,7 +408,6 @@ struct mvneta_port { struct mvneta_pcpu_stats __percpu *stats; int pkt_size; - unsigned int frag_size; void __iomem *base; struct mvneta_rx_queue *rxqs; struct mvneta_tx_queue *txqs; @@ -2905,7 +2904,9 @@ static void mvneta_rxq_hw_init(struct mvneta_port *pp, if (!pp->bm_priv) { /* Set Offset */ mvneta_rxq_offset_set(pp, rxq, 0); - mvneta_rxq_buf_size_set(pp, rxq, pp->frag_size); + mvneta_rxq_buf_size_set(pp, rxq, PAGE_SIZE < SZ_64K ? + PAGE_SIZE : + MVNETA_RX_BUF_SIZE(pp->pkt_size)); mvneta_rxq_bm_disable(pp, rxq); mvneta_rxq_fill(pp, rxq, rxq->size); } else { @@ -3760,7 +3761,6 @@ static int mvneta_open(struct net_device *dev) int ret; pp->pkt_size = MVNETA_RX_PKT_SIZE(pp->dev->mtu); - pp->frag_size = PAGE_SIZE; ret = mvneta_setup_rxqs(pp); if (ret) -- cgit v1.2.3 From 7566ec393f4161572ba6f11ad5171fd5d59b0fbd Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 16 Dec 2018 15:46:55 -0800 Subject: Linux 4.20-rc7 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index f2c3423c3062..56d5270f22f8 100644 --- a/Makefile +++ b/Makefile @@ -2,7 +2,7 @@ VERSION = 4 PATCHLEVEL = 20 SUBLEVEL = 0 -EXTRAVERSION = -rc6 +EXTRAVERSION = -rc7 NAME = Shy Crocodile # *DOCUMENTATION* -- cgit v1.2.3 From 98256376f81ab7afd8dd233b99c78356159c21d5 Mon Sep 17 00:00:00 2001 From: Dmitry V. Levin Date: Sun, 16 Dec 2018 04:49:52 +0300 Subject: uapi: linux/blkzoned.h: fix BLKGETZONESZ and BLKGETNRZONES definitions According to the documentation in include/uapi/asm-generic/ioctl.h, _IOW means userspace is writing and kernel is reading, and _IOR means userspace is reading and kernel is writing. In case of these two ioctls, kernel is writing and userspace is reading, so they have to be _IOR instead of _IOW. Fixes: 72cd87576d1d8 ("block: Introduce BLKGETZONESZ ioctl") Fixes: 65e4e3eee83d7 ("block: Introduce BLKGETNRZONES ioctl") Reviewed-by: Damien Le Moal Signed-off-by: Dmitry V. Levin Signed-off-by: Jens Axboe --- include/uapi/linux/blkzoned.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/include/uapi/linux/blkzoned.h b/include/uapi/linux/blkzoned.h index 8f08ff9bdea0..6fa38d001d84 100644 --- a/include/uapi/linux/blkzoned.h +++ b/include/uapi/linux/blkzoned.h @@ -141,7 +141,7 @@ struct blk_zone_range { */ #define BLKREPORTZONE _IOWR(0x12, 130, struct blk_zone_report) #define BLKRESETZONE _IOW(0x12, 131, struct blk_zone_range) -#define BLKGETZONESZ _IOW(0x12, 132, __u32) -#define BLKGETNRZONES _IOW(0x12, 133, __u32) +#define BLKGETZONESZ _IOR(0x12, 132, __u32) +#define BLKGETNRZONES _IOR(0x12, 133, __u32) #endif /* _UAPI_BLKZONED_H */ -- cgit v1.2.3 From 97207c12780d749770825f62c292c3140e57d79c Mon Sep 17 00:00:00 2001 From: Sowjanya Komatineni Date: Thu, 13 Dec 2018 12:34:06 -0800 Subject: mmc: sdhci: Fix sdhci_do_enable_v4_mode V4_MODE is Bit-15 of SDHCI_HOST_CONTROL2 register. Need to perform word access to this register. Signed-off-by: Sowjanya Komatineni Fixes: b3f80b434f72 ("mmc: sdhci: Add sd host v4 mode") Acked-by: Adrian Hunter Signed-off-by: Ulf Hansson --- drivers/mmc/host/sdhci.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c index 451b08a818a9..df05352b6a4a 100644 --- a/drivers/mmc/host/sdhci.c +++ b/drivers/mmc/host/sdhci.c @@ -127,12 +127,12 @@ static void sdhci_do_enable_v4_mode(struct sdhci_host *host) { u16 ctrl2; - ctrl2 = sdhci_readb(host, SDHCI_HOST_CONTROL2); + ctrl2 = sdhci_readw(host, SDHCI_HOST_CONTROL2); if (ctrl2 & SDHCI_CTRL_V4_MODE) return; ctrl2 |= SDHCI_CTRL_V4_MODE; - sdhci_writeb(host, ctrl2, SDHCI_HOST_CONTROL); + sdhci_writew(host, ctrl2, SDHCI_HOST_CONTROL2); } /* -- cgit v1.2.3 From 5ccf7f5505f4c250b97d8d7ecee7397a94b637fa Mon Sep 17 00:00:00 2001 From: Sowjanya Komatineni Date: Thu, 13 Dec 2018 12:25:43 -0800 Subject: mmc: tegra: Fix for SDMMC pads autocal parsing from dt Some of the SDMMC pads auto calibration values parsed from devicetree are assigned incorrectly. This patch fixes it. Signed-off-by: Sowjanya Komatineni Acked-by: Adrian Hunter Acked-by: Thierry Reding Fixes: 51b77c8ea784 ("mmc: tegra: Program pad autocal offsets from dt") Signed-off-by: Ulf Hansson --- drivers/mmc/host/sdhci-tegra.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/mmc/host/sdhci-tegra.c b/drivers/mmc/host/sdhci-tegra.c index 7b95d088fdef..e6ace31e2a41 100644 --- a/drivers/mmc/host/sdhci-tegra.c +++ b/drivers/mmc/host/sdhci-tegra.c @@ -510,25 +510,25 @@ static void tegra_sdhci_parse_pad_autocal_dt(struct sdhci_host *host) err = device_property_read_u32(host->mmc->parent, "nvidia,pad-autocal-pull-up-offset-3v3-timeout", - &autocal->pull_up_3v3); + &autocal->pull_up_3v3_timeout); if (err) autocal->pull_up_3v3_timeout = 0; err = device_property_read_u32(host->mmc->parent, "nvidia,pad-autocal-pull-down-offset-3v3-timeout", - &autocal->pull_down_3v3); + &autocal->pull_down_3v3_timeout); if (err) autocal->pull_down_3v3_timeout = 0; err = device_property_read_u32(host->mmc->parent, "nvidia,pad-autocal-pull-up-offset-1v8-timeout", - &autocal->pull_up_1v8); + &autocal->pull_up_1v8_timeout); if (err) autocal->pull_up_1v8_timeout = 0; err = device_property_read_u32(host->mmc->parent, "nvidia,pad-autocal-pull-down-offset-1v8-timeout", - &autocal->pull_down_1v8); + &autocal->pull_down_1v8_timeout); if (err) autocal->pull_down_1v8_timeout = 0; -- cgit v1.2.3 From 0b479790684192ab7024ce6a621f93f6d0a64d92 Mon Sep 17 00:00:00 2001 From: Russell King Date: Tue, 11 Dec 2018 14:41:31 +0000 Subject: mmc: omap_hsmmc: fix DMA API warning While booting with rootfs on MMC, the following warning is encountered on OMAP4430: omap-dma-engine 4a056000.dma-controller: DMA-API: mapping sg segment longer than device claims to support [len=69632] [max=65536] This is because the DMA engine has a default maximum segment size of 64K but HSMMC sets: mmc->max_blk_size = 512; /* Block Length at max can be 1024 */ mmc->max_blk_count = 0xFFFF; /* No. of Blocks is 16 bits */ mmc->max_req_size = mmc->max_blk_size * mmc->max_blk_count; mmc->max_seg_size = mmc->max_req_size; which ends up telling the block layer that we support a maximum segment size of 65535*512, which exceeds the advertised DMA engine capabilities. Fix this by clamping the maximum segment size to the lower of the maximum request size and of the DMA engine device used for either DMA channel. Signed-off-by: Russell King Cc: Signed-off-by: Ulf Hansson --- drivers/mmc/host/omap_hsmmc.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/drivers/mmc/host/omap_hsmmc.c b/drivers/mmc/host/omap_hsmmc.c index 467d889a1638..3f4ea8f624be 100644 --- a/drivers/mmc/host/omap_hsmmc.c +++ b/drivers/mmc/host/omap_hsmmc.c @@ -1909,7 +1909,6 @@ static int omap_hsmmc_probe(struct platform_device *pdev) mmc->max_blk_size = 512; /* Block Length at max can be 1024 */ mmc->max_blk_count = 0xFFFF; /* No. of Blocks is 16 bits */ mmc->max_req_size = mmc->max_blk_size * mmc->max_blk_count; - mmc->max_seg_size = mmc->max_req_size; mmc->caps |= MMC_CAP_MMC_HIGHSPEED | MMC_CAP_SD_HIGHSPEED | MMC_CAP_WAIT_WHILE_BUSY | MMC_CAP_ERASE | MMC_CAP_CMD23; @@ -1939,6 +1938,17 @@ static int omap_hsmmc_probe(struct platform_device *pdev) goto err_irq; } + /* + * Limit the maximum segment size to the lower of the request size + * and the DMA engine device segment size limits. In reality, with + * 32-bit transfers, the DMA engine can do longer segments than this + * but there is no way to represent that in the DMA model - if we + * increase this figure here, we get warnings from the DMA API debug. + */ + mmc->max_seg_size = min3(mmc->max_req_size, + dma_get_max_seg_size(host->rx_chan->device->dev), + dma_get_max_seg_size(host->tx_chan->device->dev)); + /* Request IRQ for MMC operations */ ret = devm_request_irq(&pdev->dev, host->irq, omap_hsmmc_irq, 0, mmc_hostname(mmc), host); -- cgit v1.2.3 From a0741ba40a009f97c019ae7541dc61c1fdf41efb Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Mon, 10 Dec 2018 17:52:36 +0100 Subject: mmc: core: Reset HPI enabled state during re-init and in case of errors During a re-initialization of the eMMC card, we may fail to re-enable HPI. In these cases, that isn't properly reflected in the card->ext_csd.hpi_en bit, as it keeps being set. This may cause following attempts to use HPI, even if's not enabled. Let's fix this! Fixes: eb0d8f135b67 ("mmc: core: support HPI send command") Cc: Signed-off-by: Ulf Hansson --- drivers/mmc/core/mmc.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c index bc1bd2c25613..f0e8e39a7938 100644 --- a/drivers/mmc/core/mmc.c +++ b/drivers/mmc/core/mmc.c @@ -1782,9 +1782,11 @@ static int mmc_init_card(struct mmc_host *host, u32 ocr, if (err) { pr_warn("%s: Enabling HPI failed\n", mmc_hostname(card->host)); + card->ext_csd.hpi_en = 0; err = 0; - } else + } else { card->ext_csd.hpi_en = 1; + } } /* -- cgit v1.2.3 From ba9f39a785a9977e72233000711ef1eb48203551 Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Mon, 10 Dec 2018 17:52:37 +0100 Subject: mmc: core: Allow BKOPS and CACHE ctrl even if no HPI support In commit 5320226a0512 ("mmc: core: Disable HPI for certain Hynix eMMC cards"), then intent was to prevent HPI from being used for some eMMC cards, which didn't properly support it. However, that went too far, as even BKOPS and CACHE ctrl became prevented. Let's restore those parts and allow BKOPS and CACHE ctrl even if HPI isn't supported. Fixes: 5320226a0512 ("mmc: core: Disable HPI for certain Hynix eMMC cards") Cc: Pratibhasagar V Cc: Signed-off-by: Ulf Hansson --- drivers/mmc/core/mmc.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c index f0e8e39a7938..a9b6e64cdcd7 100644 --- a/drivers/mmc/core/mmc.c +++ b/drivers/mmc/core/mmc.c @@ -526,8 +526,7 @@ static int mmc_decode_ext_csd(struct mmc_card *card, u8 *ext_csd) card->cid.year += 16; /* check whether the eMMC card supports BKOPS */ - if (!mmc_card_broken_hpi(card) && - ext_csd[EXT_CSD_BKOPS_SUPPORT] & 0x1) { + if (ext_csd[EXT_CSD_BKOPS_SUPPORT] & 0x1) { card->ext_csd.bkops = 1; card->ext_csd.man_bkops_en = (ext_csd[EXT_CSD_BKOPS_EN] & @@ -1793,8 +1792,7 @@ static int mmc_init_card(struct mmc_host *host, u32 ocr, * If cache size is higher than 0, this indicates * the existence of cache and it can be turned on. */ - if (!mmc_card_broken_hpi(card) && - card->ext_csd.cache_size > 0) { + if (card->ext_csd.cache_size > 0) { err = mmc_switch(card, EXT_CSD_CMD_SET_NORMAL, EXT_CSD_CACHE_CTRL, 1, card->ext_csd.generic_cmd6_time); -- cgit v1.2.3 From e3ae3401aa19432ee4943eb0bbc2ec704d07d793 Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Mon, 10 Dec 2018 17:52:38 +0100 Subject: mmc: core: Use a minimum 1600ms timeout when enabling CACHE ctrl Some eMMCs from Micron have been reported to need ~800 ms timeout, while enabling the CACHE ctrl after running sudden power failure tests. The needed timeout is greater than what the card specifies as its generic CMD6 timeout, through the EXT_CSD register, hence the problem. Normally we would introduce a card quirk to extend the timeout for these specific Micron cards. However, due to the rather complicated debug process needed to find out the error, let's simply use a minimum timeout of 1600ms, the double of what has been reported, for all cards when enabling CACHE ctrl. Reported-by: Sjoerd Simons Reported-by: Andreas Dannenberg Reported-by: Faiz Abbas Cc: Signed-off-by: Ulf Hansson --- drivers/mmc/core/mmc.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c index a9b6e64cdcd7..55997cf84b39 100644 --- a/drivers/mmc/core/mmc.c +++ b/drivers/mmc/core/mmc.c @@ -30,6 +30,7 @@ #include "pwrseq.h" #define DEFAULT_CMD6_TIMEOUT_MS 500 +#define MIN_CACHE_EN_TIMEOUT_MS 1600 static const unsigned int tran_exp[] = { 10000, 100000, 1000000, 10000000, @@ -1789,13 +1790,18 @@ static int mmc_init_card(struct mmc_host *host, u32 ocr, } /* - * If cache size is higher than 0, this indicates - * the existence of cache and it can be turned on. + * If cache size is higher than 0, this indicates the existence of cache + * and it can be turned on. Note that some eMMCs from Micron has been + * reported to need ~800 ms timeout, while enabling the cache after + * sudden power failure tests. Let's extend the timeout to a minimum of + * DEFAULT_CACHE_EN_TIMEOUT_MS and do it for all cards. */ if (card->ext_csd.cache_size > 0) { + unsigned int timeout_ms = MIN_CACHE_EN_TIMEOUT_MS; + + timeout_ms = max(card->ext_csd.generic_cmd6_time, timeout_ms); err = mmc_switch(card, EXT_CSD_CMD_SET_NORMAL, - EXT_CSD_CACHE_CTRL, 1, - card->ext_csd.generic_cmd6_time); + EXT_CSD_CACHE_CTRL, 1, timeout_ms); if (err && err != -EBADMSG) goto free_card; -- cgit v1.2.3 From eca1e56ceedd9cc185eb18baf307d3ff2e4af376 Mon Sep 17 00:00:00 2001 From: Emmanuel Grumbach Date: Fri, 14 Dec 2018 18:30:22 +0200 Subject: iwlwifi: mvm: don't send GEO_TX_POWER_LIMIT to old firmwares Old firmware versions don't support this command. Sending it to any firmware before -41.ucode will crash the firmware. This fixes https://bugzilla.kernel.org/show_bug.cgi?id=201975 Fixes: 66e839030fd6 ("iwlwifi: fix wrong WGDS_WIFI_DATA_SIZE") CC: #4.19+ Signed-off-by: Emmanuel Grumbach Signed-off-by: Luca Coelho Signed-off-by: Kalle Valo --- drivers/net/wireless/intel/iwlwifi/mvm/fw.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c index 2ba890445c35..1689bead1b4f 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c @@ -881,6 +881,15 @@ static int iwl_mvm_sar_geo_init(struct iwl_mvm *mvm) int ret, i, j; u16 cmd_wide_id = WIDE_ID(PHY_OPS_GROUP, GEO_TX_POWER_LIMIT); + /* + * This command is not supported on earlier firmware versions. + * Unfortunately, we don't have a TLV API flag to rely on, so + * rely on the major version which is in the first byte of + * ucode_ver. + */ + if (IWL_UCODE_SERIAL(mvm->fw->ucode_ver) < 41) + return 0; + ret = iwl_mvm_sar_get_wgds_table(mvm); if (ret < 0) { IWL_DEBUG_RADIO(mvm, -- cgit v1.2.3 From 2419f30a4a4fcaa5f35111563b4c61f1b2b26841 Mon Sep 17 00:00:00 2001 From: Nicolas Saenz Julienne Date: Mon, 17 Dec 2018 14:37:40 +0100 Subject: USB: xhci: fix 'broken_suspend' placement in struct xchi_hcd As commented in the struct's definition there shouldn't be anything underneath its 'priv[0]' member as it would break some macros. The patch converts the broken_suspend into a bit-field and relocates it next to to the rest of bit-fields. Fixes: a7d57abcc8a5 ("xhci: workaround CSS timeout on AMD SNPS 3.0 xHC") Reported-by: Oliver Neukum Signed-off-by: Nicolas Saenz Julienne Acked-by: Mathias Nyman Cc: stable Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h index c3515bad5dbb..011dd45f8718 100644 --- a/drivers/usb/host/xhci.h +++ b/drivers/usb/host/xhci.h @@ -1863,6 +1863,8 @@ struct xhci_hcd { unsigned sw_lpm_support:1; /* support xHCI 1.0 spec USB2 hardware LPM */ unsigned hw_lpm_support:1; + /* Broken Suspend flag for SNPS Suspend resume issue */ + unsigned broken_suspend:1; /* cached usb2 extened protocol capabilites */ u32 *ext_caps; unsigned int num_ext_caps; @@ -1880,8 +1882,6 @@ struct xhci_hcd { void *dbc; /* platform-specific data -- must come last */ unsigned long priv[0] __aligned(sizeof(s64)); - /* Broken Suspend flag for SNPS Suspend resume issue */ - u8 broken_suspend; }; /* Platform specific overrides to generic XHCI hc_driver ops */ -- cgit v1.2.3 From 3c9dc275dba1124c1e16e7037226038451286813 Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Sun, 16 Dec 2018 20:10:01 +0000 Subject: Revert "serial: 8250: Fix clearing FIFOs in RS485 mode again" Commit f6aa5beb45be ("serial: 8250: Fix clearing FIFOs in RS485 mode again") makes a change to FIFO clearing code which its commit message suggests was intended to be specific to use with RS485 mode, however: 1) The change made does not just affect __do_stop_tx_rs485(), it also affects other uses of serial8250_clear_fifos() including paths for starting up, shutting down or auto-configuring a port regardless of whether it's an RS485 port or not. 2) It makes the assumption that resetting the FIFOs is a no-op when FIFOs are disabled, and as such it checks for this case & explicitly avoids setting the FIFO reset bits when the FIFO enable bit is clear. A reading of the PC16550D manual would suggest that this is OK since the FIFO should automatically be reset if it is later enabled, but we support many 16550-compatible devices and have never required this auto-reset behaviour for at least the whole git era. Starting to rely on it now seems risky, offers no benefit, and indeed breaks at least the Ingenic JZ4780's UARTs which reads garbage when the RX FIFO is enabled if we don't explicitly reset it. 3) By only resetting the FIFOs if they're enabled, the behaviour of serial8250_do_startup() during boot now depends on what the value of FCR is before the 8250 driver is probed. This in itself seems questionable and leaves us with FCR=0 & no FIFO reset if the UART was used by 8250_early, otherwise it depends upon what the bootloader left behind. 4) Although the naming of serial8250_clear_fifos() may be unclear, it is clear that callers of it expect that it will disable FIFOs. Both serial8250_do_startup() & serial8250_do_shutdown() contain comments to that effect, and other callers explicitly re-enable the FIFOs after calling serial8250_clear_fifos(). The premise of that patch that disabling the FIFOs is incorrect therefore seems wrong. For these reasons, this reverts commit f6aa5beb45be ("serial: 8250: Fix clearing FIFOs in RS485 mode again"). Signed-off-by: Paul Burton Fixes: f6aa5beb45be ("serial: 8250: Fix clearing FIFOs in RS485 mode again"). Cc: Greg Kroah-Hartman Cc: Daniel Jedrychowski Cc: Marek Vasut Cc: linux-mips@vger.kernel.org Cc: linux-serial@vger.kernel.org Cc: stable # 4.10+ Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/8250/8250_port.c | 29 +++++------------------------ 1 file changed, 5 insertions(+), 24 deletions(-) diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c index f776b3eafb96..3f779d25ec0c 100644 --- a/drivers/tty/serial/8250/8250_port.c +++ b/drivers/tty/serial/8250/8250_port.c @@ -552,30 +552,11 @@ static unsigned int serial_icr_read(struct uart_8250_port *up, int offset) */ static void serial8250_clear_fifos(struct uart_8250_port *p) { - unsigned char fcr; - unsigned char clr_mask = UART_FCR_CLEAR_RCVR | UART_FCR_CLEAR_XMIT; - if (p->capabilities & UART_CAP_FIFO) { - /* - * Make sure to avoid changing FCR[7:3] and ENABLE_FIFO bits. - * In case ENABLE_FIFO is not set, there is nothing to flush - * so just return. Furthermore, on certain implementations of - * the 8250 core, the FCR[7:3] bits may only be changed under - * specific conditions and changing them if those conditions - * are not met can have nasty side effects. One such core is - * the 8250-omap present in TI AM335x. - */ - fcr = serial_in(p, UART_FCR); - - /* FIFO is not enabled, there's nothing to clear. */ - if (!(fcr & UART_FCR_ENABLE_FIFO)) - return; - - fcr |= clr_mask; - serial_out(p, UART_FCR, fcr); - - fcr &= ~clr_mask; - serial_out(p, UART_FCR, fcr); + serial_out(p, UART_FCR, UART_FCR_ENABLE_FIFO); + serial_out(p, UART_FCR, UART_FCR_ENABLE_FIFO | + UART_FCR_CLEAR_RCVR | UART_FCR_CLEAR_XMIT); + serial_out(p, UART_FCR, 0); } } @@ -1467,7 +1448,7 @@ static void __do_stop_tx_rs485(struct uart_8250_port *p) * Enable previously disabled RX interrupts. */ if (!(p->port.rs485.flags & SER_RS485_RX_DURING_TX)) { - serial8250_clear_fifos(p); + serial8250_clear_and_reinit_fifos(p); p->ier |= UART_IER_RLSI | UART_IER_RDI; serial_port_out(&p->port, UART_IER, p->ier); -- cgit v1.2.3 From c92a54cfa0257e8ffd66b2a17d49e9c0bd4b769f Mon Sep 17 00:00:00 2001 From: Lendacky, Thomas Date: Mon, 17 Dec 2018 14:39:16 +0000 Subject: dma-direct: do not include SME mask in the DMA supported check The dma_direct_supported() function intends to check the DMA mask against specific values. However, the phys_to_dma() function includes the SME encryption mask, which defeats the intended purpose of the check. This results in drivers that support less than 48-bit DMA (SME encryption mask is bit 47) from being able to set the DMA mask successfully when SME is active, which results in the driver failing to initialize. Change the function used to check the mask from phys_to_dma() to __phys_to_dma() so that the SME encryption mask is not part of the check. Fixes: c1d0af1a1d5d ("kernel/dma/direct: take DMA offset into account in dma_direct_supported") Signed-off-by: Tom Lendacky Signed-off-by: Christoph Hellwig --- kernel/dma/direct.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index 22a12ab5a5e9..375c77e8d52f 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -309,7 +309,12 @@ int dma_direct_supported(struct device *dev, u64 mask) min_mask = min_t(u64, min_mask, (max_pfn - 1) << PAGE_SHIFT); - return mask >= phys_to_dma(dev, min_mask); + /* + * This check needs to be against the actual bit mask value, so + * use __phys_to_dma() here so that the SME encryption mask isn't + * part of the check. + */ + return mask >= __phys_to_dma(dev, min_mask); } int dma_direct_mapping_error(struct device *dev, dma_addr_t dma_addr) -- cgit v1.2.3 From bcb671c2fa0e238eea087fdcb7eba72376ba3697 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Mon, 17 Dec 2018 00:04:40 +0900 Subject: bpf: promote bpf_perf_event.h to mandatory UAPI header Since commit c895f6f703ad ("bpf: correct broken uapi for BPF_PROG_TYPE_PERF_EVENT program type"), all architectures (except um) are required to have bpf_perf_event.h in uapi/asm. Add it to mandatory-y so "make headers_install" can check it. Signed-off-by: Masahiro Yamada Signed-off-by: Daniel Borkmann --- include/uapi/asm-generic/Kbuild.asm | 1 + 1 file changed, 1 insertion(+) diff --git a/include/uapi/asm-generic/Kbuild.asm b/include/uapi/asm-generic/Kbuild.asm index 21381449d98a..355c4ac2c0b0 100644 --- a/include/uapi/asm-generic/Kbuild.asm +++ b/include/uapi/asm-generic/Kbuild.asm @@ -3,6 +3,7 @@ # mandatory-y += auxvec.h mandatory-y += bitsperlong.h +mandatory-y += bpf_perf_event.h mandatory-y += byteorder.h mandatory-y += errno.h mandatory-y += fcntl.h -- cgit v1.2.3 From 255fe81a6ad420258b6dac8c509c99cd1c233390 Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Mon, 17 Dec 2018 16:29:01 -0500 Subject: MAINTAINERS: change my email address Make my Gmail address the primary one from now on. Signed-off-by: Vivien Didelot Signed-off-by: David S. Miller --- MAINTAINERS | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index 8119141a926f..2fbe569fb76c 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -8938,7 +8938,7 @@ F: arch/mips/boot/dts/img/pistachio_marduk.dts MARVELL 88E6XXX ETHERNET SWITCH FABRIC DRIVER M: Andrew Lunn -M: Vivien Didelot +M: Vivien Didelot L: netdev@vger.kernel.org S: Maintained F: drivers/net/dsa/mv88e6xxx/ @@ -10416,7 +10416,7 @@ F: drivers/net/wireless/ NETWORKING [DSA] M: Andrew Lunn -M: Vivien Didelot +M: Vivien Didelot M: Florian Fainelli S: Maintained F: Documentation/devicetree/bindings/net/dsa/ -- cgit v1.2.3 From 94c13f66e13ca0f3d5b7b9e7e385fe5db35abe3c Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 17 Dec 2018 11:39:57 -0800 Subject: security: don't use a negative Opt_err token index The code uses a bitmap to check for duplicate tokens during parsing, and that doesn't work at all for the negative Opt_err token case. There is absolutely no reason to make Opt_err be negative, and in fact it only confuses things, since some of the affected functions actually return a positive Opt_xyz enum _or_ a regular negative error code (eg -EINVAL), and using -1 for Opt_err makes no sense. There are similar problems in ima_policy.c and key encryption, but they don't have the immediate bug wrt bitmap handing, and ima_policy.c in particular needs a different patch to make the enum values match the token array index. Mimi is sending that separately. Reported-by: syzbot+a22e0dc07567662c50bc@syzkaller.appspotmail.com Reported-by: Eric Biggers Fixes: 5208cc83423d ("keys, trusted: fix: *do not* allow duplicate key options") Fixes: 00d60fd3b932 ("KEYS: Provide keyctls to drive the new key type ops for asymmetric keys [ver #2]") Cc: James Morris James Morris Cc: Mimi Zohar Cc: Jarkko Sakkinen Cc: Peter Huewe Signed-off-by: Linus Torvalds --- security/keys/keyctl_pkey.c | 2 +- security/keys/trusted.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/security/keys/keyctl_pkey.c b/security/keys/keyctl_pkey.c index 783978842f13..70e65a2ff207 100644 --- a/security/keys/keyctl_pkey.c +++ b/security/keys/keyctl_pkey.c @@ -25,7 +25,7 @@ static void keyctl_pkey_params_free(struct kernel_pkey_params *params) } enum { - Opt_err = -1, + Opt_err, Opt_enc, /* "enc=" eg. "enc=oaep" */ Opt_hash, /* "hash=" eg. "hash=sha1" */ }; diff --git a/security/keys/trusted.c b/security/keys/trusted.c index ff6789365a12..697bfc6c8192 100644 --- a/security/keys/trusted.c +++ b/security/keys/trusted.c @@ -711,7 +711,7 @@ static int key_unseal(struct trusted_key_payload *p, } enum { - Opt_err = -1, + Opt_err, Opt_new, Opt_load, Opt_update, Opt_keyhandle, Opt_keyauth, Opt_blobauth, Opt_pcrinfo, Opt_pcrlock, Opt_migratable, -- cgit v1.2.3 From 1a9430db2835c0c00acc87d915b573496998c1bf Mon Sep 17 00:00:00 2001 From: Mimi Zohar Date: Mon, 17 Dec 2018 19:14:49 -0500 Subject: ima: cleanup the match_token policy code Start the policy_tokens and the associated enumeration from zero, simplifying the pt macro. Signed-off-by: Mimi Zohar Signed-off-by: Linus Torvalds --- security/integrity/ima/ima_policy.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/security/integrity/ima/ima_policy.c b/security/integrity/ima/ima_policy.c index 8c9499867c91..7489cb7de6dc 100644 --- a/security/integrity/ima/ima_policy.c +++ b/security/integrity/ima/ima_policy.c @@ -580,9 +580,9 @@ void ima_update_policy(void) ima_update_policy_flag(); } +/* Keep the enumeration in sync with the policy_tokens! */ enum { - Opt_err = -1, - Opt_measure = 1, Opt_dont_measure, + Opt_measure, Opt_dont_measure, Opt_appraise, Opt_dont_appraise, Opt_audit, Opt_hash, Opt_dont_hash, Opt_obj_user, Opt_obj_role, Opt_obj_type, @@ -592,10 +592,10 @@ enum { Opt_uid_gt, Opt_euid_gt, Opt_fowner_gt, Opt_uid_lt, Opt_euid_lt, Opt_fowner_lt, Opt_appraise_type, Opt_permit_directio, - Opt_pcr + Opt_pcr, Opt_err }; -static match_table_t policy_tokens = { +static const match_table_t policy_tokens = { {Opt_measure, "measure"}, {Opt_dont_measure, "dont_measure"}, {Opt_appraise, "appraise"}, @@ -1103,7 +1103,7 @@ void ima_policy_stop(struct seq_file *m, void *v) { } -#define pt(token) policy_tokens[token + Opt_err].pattern +#define pt(token) policy_tokens[token].pattern #define mt(token) mask_tokens[token] /* -- cgit v1.2.3 From fbfb2321e950918b430e7225546296b2dcadf725 Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Mon, 17 Dec 2018 12:23:59 -0500 Subject: ipv6: add missing tx timestamping on IPPROTO_RAW Raw sockets support tx timestamping, but one case is missing. IPPROTO_RAW takes a separate packet construction path. raw_send_hdrinc has an explicit call to sock_tx_timestamp, but rawv6_send_hdrinc does not. Add it. Fixes: 11878b40ed5c ("net-timestamp: SOCK_RAW and PING timestamping") Signed-off-by: Willem de Bruijn Acked-by: Soheil Hassas Yeganeh Signed-off-by: David S. Miller --- net/ipv6/raw.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 5e0efd3954e9..c8562432fcc3 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -658,6 +658,8 @@ static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length, skb->ip_summed = CHECKSUM_NONE; + sock_tx_timestamp(sk, sockc->tsflags, &skb_shinfo(skb)->tx_flags); + if (flags & MSG_CONFIRM) skb_set_dst_pending_confirm(skb, 1); -- cgit v1.2.3 From 8f932f762e7928d250e21006b00ff9b7718b0a64 Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Mon, 17 Dec 2018 12:24:00 -0500 Subject: net: add missing SOF_TIMESTAMPING_OPT_ID support SOF_TIMESTAMPING_OPT_ID is supported on TCP, UDP and RAW sockets. But it was missing on RAW with IPPROTO_IP, PF_PACKET and CAN. Add skb_setup_tx_timestamp that configures both tx_flags and tskey for these paths that do not need corking or use bytestream keys. Fixes: 09c2d251b707 ("net-timestamp: add key to disambiguate concurrent datagrams") Signed-off-by: Willem de Bruijn Acked-by: Soheil Hassas Yeganeh Signed-off-by: David S. Miller --- include/net/sock.h | 25 +++++++++++++++++++++---- net/can/raw.c | 2 +- net/ipv4/raw.c | 2 +- net/ipv6/raw.c | 2 +- net/packet/af_packet.c | 6 +++--- 5 files changed, 27 insertions(+), 10 deletions(-) diff --git a/include/net/sock.h b/include/net/sock.h index f665d74ae509..0e3a09380655 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2340,22 +2340,39 @@ static inline void sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk, void __sock_tx_timestamp(__u16 tsflags, __u8 *tx_flags); /** - * sock_tx_timestamp - checks whether the outgoing packet is to be time stamped + * _sock_tx_timestamp - checks whether the outgoing packet is to be time stamped * @sk: socket sending this packet * @tsflags: timestamping flags to use * @tx_flags: completed with instructions for time stamping + * @tskey: filled in with next sk_tskey (not for TCP, which uses seqno) * * Note: callers should take care of initial ``*tx_flags`` value (usually 0) */ -static inline void sock_tx_timestamp(const struct sock *sk, __u16 tsflags, - __u8 *tx_flags) +static inline void _sock_tx_timestamp(struct sock *sk, __u16 tsflags, + __u8 *tx_flags, __u32 *tskey) { - if (unlikely(tsflags)) + if (unlikely(tsflags)) { __sock_tx_timestamp(tsflags, tx_flags); + if (tsflags & SOF_TIMESTAMPING_OPT_ID && tskey && + tsflags & SOF_TIMESTAMPING_TX_RECORD_MASK) + *tskey = sk->sk_tskey++; + } if (unlikely(sock_flag(sk, SOCK_WIFI_STATUS))) *tx_flags |= SKBTX_WIFI_STATUS; } +static inline void sock_tx_timestamp(struct sock *sk, __u16 tsflags, + __u8 *tx_flags) +{ + _sock_tx_timestamp(sk, tsflags, tx_flags, NULL); +} + +static inline void skb_setup_tx_timestamp(struct sk_buff *skb, __u16 tsflags) +{ + _sock_tx_timestamp(skb->sk, tsflags, &skb_shinfo(skb)->tx_flags, + &skb_shinfo(skb)->tskey); +} + /** * sk_eat_skb - Release a skb if it is no longer needed * @sk: socket to eat this skb from diff --git a/net/can/raw.c b/net/can/raw.c index 3aab7664933f..c70207537488 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -771,7 +771,7 @@ static int raw_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) if (err < 0) goto free_skb; - sock_tx_timestamp(sk, sk->sk_tsflags, &skb_shinfo(skb)->tx_flags); + skb_setup_tx_timestamp(skb, sk->sk_tsflags); skb->dev = dev; skb->sk = sk; diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 8ca3eb06ba04..169a652b3dd1 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -391,7 +391,7 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4, skb->ip_summed = CHECKSUM_NONE; - sock_tx_timestamp(sk, sockc->tsflags, &skb_shinfo(skb)->tx_flags); + skb_setup_tx_timestamp(skb, sockc->tsflags); if (flags & MSG_CONFIRM) skb_set_dst_pending_confirm(skb, 1); diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index c8562432fcc3..fc2b5e845fdf 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -658,7 +658,7 @@ static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length, skb->ip_summed = CHECKSUM_NONE; - sock_tx_timestamp(sk, sockc->tsflags, &skb_shinfo(skb)->tx_flags); + skb_setup_tx_timestamp(skb, sockc->tsflags); if (flags & MSG_CONFIRM) skb_set_dst_pending_confirm(skb, 1); diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index a74650e98f42..6655793765b2 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -1965,7 +1965,7 @@ retry: skb->mark = sk->sk_mark; skb->tstamp = sockc.transmit_time; - sock_tx_timestamp(sk, sockc.tsflags, &skb_shinfo(skb)->tx_flags); + skb_setup_tx_timestamp(skb, sockc.tsflags); if (unlikely(extra_len == 4)) skb->no_fcs = 1; @@ -2460,7 +2460,7 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb, skb->priority = po->sk.sk_priority; skb->mark = po->sk.sk_mark; skb->tstamp = sockc->transmit_time; - sock_tx_timestamp(&po->sk, sockc->tsflags, &skb_shinfo(skb)->tx_flags); + skb_setup_tx_timestamp(skb, sockc->tsflags); skb_zcopy_set_nouarg(skb, ph.raw); skb_reserve(skb, hlen); @@ -2898,7 +2898,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) goto out_free; } - sock_tx_timestamp(sk, sockc.tsflags, &skb_shinfo(skb)->tx_flags); + skb_setup_tx_timestamp(skb, sockc.tsflags); if (!vnet_hdr.gso_type && (len > dev->mtu + reserve + extra_len) && !packet_extra_vlan_len_allowed(dev, skb)) { -- cgit v1.2.3 From a5f3932646a74e690ed532a1f421f75c3b8cf1ec Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Mon, 17 Dec 2018 16:05:21 -0500 Subject: net: dsa: mv88e6xxx: set ethtool regs version Currently the ethtool_regs version is set to 0 for all DSA drivers. Use this field to store the chip ID to simplify the pretty dump of any interfaces registered by the "dsa" driver. Signed-off-by: Vivien Didelot Reviewed-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/dsa/mv88e6xxx/chip.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index e05d4eddc935..24fb6a685039 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -1124,7 +1124,7 @@ static void mv88e6xxx_get_regs(struct dsa_switch *ds, int port, u16 *p = _p; int i; - regs->version = 0; + regs->version = chip->info->prod_num; memset(p, 0xff, 32 * sizeof(u16)); -- cgit v1.2.3 From a50e5fb8db83c5b57392204c21ea6c5c4ccefde6 Mon Sep 17 00:00:00 2001 From: Sara Sharon Date: Sat, 15 Dec 2018 11:03:10 +0200 Subject: mac80211: fix a kernel panic when TXing after TXQ teardown Recently TXQ teardown was moved earlier in ieee80211_unregister_hw(), to avoid a use-after-free of the netdev data. However, interfaces aren't fully removed at the point, and cfg80211_shutdown_all_interfaces can for example, TX a deauth frame. Move the TXQ teardown to the point between cfg80211_shutdown_all_interfaces and the free of netdev queues, so we can be sure they are torn down before netdev is freed, but after there is no ongoing TX. Fixes: 77cfaf52eca5 ("mac80211: Run TXQ teardown code before de-registering interfaces") Signed-off-by: Sara Sharon Signed-off-by: Luca Coelho Signed-off-by: Johannes Berg --- net/mac80211/iface.c | 3 +++ net/mac80211/main.c | 2 -- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 5f3c81e705c7..3a0171a65db3 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -7,6 +7,7 @@ * Copyright 2008, Johannes Berg * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright (c) 2016 Intel Deutschland GmbH + * Copyright (C) 2018 Intel Corporation * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -1951,6 +1952,8 @@ void ieee80211_remove_interfaces(struct ieee80211_local *local) WARN(local->open_count, "%s: open count remains %d\n", wiphy_name(local->hw.wiphy), local->open_count); + ieee80211_txq_teardown_flows(local); + mutex_lock(&local->iflist_mtx); list_for_each_entry_safe(sdata, tmp, &local->interfaces, list) { list_del(&sdata->list); diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 83e71e6b2ebe..7b8320d4a8e4 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -1262,7 +1262,6 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) rtnl_unlock(); ieee80211_led_exit(local); ieee80211_wep_free(local); - ieee80211_txq_teardown_flows(local); fail_flows: destroy_workqueue(local->workqueue); fail_workqueue: @@ -1288,7 +1287,6 @@ void ieee80211_unregister_hw(struct ieee80211_hw *hw) #if IS_ENABLED(CONFIG_IPV6) unregister_inet6addr_notifier(&local->ifa6_notifier); #endif - ieee80211_txq_teardown_flows(local); rtnl_lock(); -- cgit v1.2.3 From 0445f92c5d537c173a54446b80d2052145de5148 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 17 Dec 2018 13:34:59 -0500 Subject: SUNRPC: Fix disconnection races When the socket is closed, we need to call xprt_disconnect_done() in order to clean up the XPRT_WRITE_SPACE flag, and wake up the sleeping tasks. However, we also want to ensure that we don't wake them up before the socket is closed, since that would cause thundering herd issues with everyone piling up to retransmit before the TCP shutdown dance has completed. Only the task that holds XPRT_LOCKED needs to wake up early in order to allow the close to complete. Reported-by: Dave Wysochanski Reported-by: Scott Mayhew Cc: Chuck Lever Signed-off-by: Trond Myklebust Tested-by: Chuck Lever --- net/sunrpc/clnt.c | 1 + net/sunrpc/xprt.c | 5 ++++- net/sunrpc/xprtsock.c | 6 ++---- 3 files changed, 7 insertions(+), 5 deletions(-) diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index c6782aa47525..24cbddc44c88 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -1952,6 +1952,7 @@ call_connect_status(struct rpc_task *task) /* retry with existing socket, after a delay */ rpc_delay(task, 3*HZ); /* fall through */ + case -ENOTCONN: case -EAGAIN: /* Check for timeouts before looping back to call_bind */ case -ETIMEDOUT: diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index ce927002862a..3fb001dff670 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -680,7 +680,9 @@ void xprt_force_disconnect(struct rpc_xprt *xprt) /* Try to schedule an autoclose RPC call */ if (test_and_set_bit(XPRT_LOCKED, &xprt->state) == 0) queue_work(xprtiod_workqueue, &xprt->task_cleanup); - xprt_wake_pending_tasks(xprt, -EAGAIN); + else if (xprt->snd_task) + rpc_wake_up_queued_task_set_status(&xprt->pending, + xprt->snd_task, -ENOTCONN); spin_unlock_bh(&xprt->transport_lock); } EXPORT_SYMBOL_GPL(xprt_force_disconnect); @@ -852,6 +854,7 @@ static void xprt_connect_status(struct rpc_task *task) case -ENETUNREACH: case -EHOSTUNREACH: case -EPIPE: + case -ENOTCONN: case -EAGAIN: dprintk("RPC: %5u xprt_connect_status: retrying\n", task->tk_pid); break; diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 8a5e823e0b33..4c471b4235ba 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -1217,6 +1217,8 @@ static void xs_reset_transport(struct sock_xprt *transport) trace_rpc_socket_close(xprt, sock); sock_release(sock); + + xprt_disconnect_done(xprt); } /** @@ -1237,8 +1239,6 @@ static void xs_close(struct rpc_xprt *xprt) xs_reset_transport(transport); xprt->reestablish_timeout = 0; - - xprt_disconnect_done(xprt); } static void xs_inject_disconnect(struct rpc_xprt *xprt) @@ -1489,8 +1489,6 @@ static void xs_tcp_state_change(struct sock *sk) &transport->sock_state)) xprt_clear_connecting(xprt); clear_bit(XPRT_CLOSING, &xprt->state); - if (sk->sk_err) - xprt_wake_pending_tasks(xprt, -sk->sk_err); /* Trigger the socket release */ xs_tcp_force_close(xprt); } -- cgit v1.2.3 From cf76785d30712d90185455e752337acdb53d2a5d Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 17 Dec 2018 17:38:51 -0500 Subject: SUNRPC: Fix a race with XPRT_CONNECTING Ensure that we clear XPRT_CONNECTING before releasing the XPRT_LOCK so that we don't have races between the (asynchronous) socket setup code and tasks in xprt_connect(). Signed-off-by: Trond Myklebust Tested-by: Chuck Lever --- net/sunrpc/xprtsock.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 4c471b4235ba..f0b3700cec95 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -2090,8 +2090,8 @@ static void xs_udp_setup_socket(struct work_struct *work) trace_rpc_socket_connect(xprt, sock, 0); status = 0; out: - xprt_unlock_connect(xprt, transport); xprt_clear_connecting(xprt); + xprt_unlock_connect(xprt, transport); xprt_wake_pending_tasks(xprt, status); } @@ -2327,8 +2327,8 @@ static void xs_tcp_setup_socket(struct work_struct *work) } status = -EAGAIN; out: - xprt_unlock_connect(xprt, transport); xprt_clear_connecting(xprt); + xprt_unlock_connect(xprt, transport); xprt_wake_pending_tasks(xprt, status); } -- cgit v1.2.3 From abc13275771fac77e2d7b129c289522dacb644b6 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 17 Dec 2018 17:33:33 -0500 Subject: SUNRPC: Remove xprt_connect_status() Over the years, xprt_connect_status() has been superseded by call_connect_status(), which now handles all the errors that xprt_connect_status() does and more. Since the latter converts all errors that it doesn't recognise to EIO, then it is time for it to be retired. Reported-by: Chuck Lever Signed-off-by: Trond Myklebust Tested-by: Chuck Lever --- net/sunrpc/xprt.c | 32 +------------------------------- 1 file changed, 1 insertion(+), 31 deletions(-) diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 3fb001dff670..73547d17d3c6 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -67,7 +67,6 @@ */ static void xprt_init(struct rpc_xprt *xprt, struct net *net); static __be32 xprt_alloc_xid(struct rpc_xprt *xprt); -static void xprt_connect_status(struct rpc_task *task); static void xprt_destroy(struct rpc_xprt *xprt); static DEFINE_SPINLOCK(xprt_list_lock); @@ -822,7 +821,7 @@ void xprt_connect(struct rpc_task *task) if (!xprt_connected(xprt)) { task->tk_timeout = task->tk_rqstp->rq_timeout; task->tk_rqstp->rq_connect_cookie = xprt->connect_cookie; - rpc_sleep_on(&xprt->pending, task, xprt_connect_status); + rpc_sleep_on(&xprt->pending, task, NULL); if (test_bit(XPRT_CLOSING, &xprt->state)) return; @@ -841,35 +840,6 @@ void xprt_connect(struct rpc_task *task) xprt_release_write(xprt, task); } -static void xprt_connect_status(struct rpc_task *task) -{ - switch (task->tk_status) { - case 0: - dprintk("RPC: %5u xprt_connect_status: connection established\n", - task->tk_pid); - break; - case -ECONNREFUSED: - case -ECONNRESET: - case -ECONNABORTED: - case -ENETUNREACH: - case -EHOSTUNREACH: - case -EPIPE: - case -ENOTCONN: - case -EAGAIN: - dprintk("RPC: %5u xprt_connect_status: retrying\n", task->tk_pid); - break; - case -ETIMEDOUT: - dprintk("RPC: %5u xprt_connect_status: connect attempt timed " - "out\n", task->tk_pid); - break; - default: - dprintk("RPC: %5u xprt_connect_status: error %d connecting to " - "server %s\n", task->tk_pid, -task->tk_status, - task->tk_rqstp->rq_xprt->servername); - task->tk_status = -EIO; - } -} - enum xprt_xid_rb_cmp { XID_RB_EQUAL, XID_RB_LEFT, -- cgit v1.2.3 From cf0b70e71b32137ccf9c1f3dd9fb30cbf89b4322 Mon Sep 17 00:00:00 2001 From: Shalom Toledo Date: Tue, 18 Dec 2018 15:59:20 +0000 Subject: mlxsw: core: Increase timeout during firmware flash process During the firmware flash process, some of the EMADs get timed out, which causes the driver to send them again with a limit of 5 retries. There are some situations in which 5 retries is not enough and the EMAD access fails. If the failed EMAD was related to the flashing process, the driver fails the flashing. The reason for these timeouts during firmware flashing is cache misses in the CPU running the firmware. In case the CPU needs to fetch instructions from the flash when a firmware is flashed, it needs to wait for the flashing to complete. Since flashing takes time, it is possible for pending EMADs to timeout. Fix by increasing EMADs' timeout while flashing firmware. Fixes: ce6ef68f433f ("mlxsw: spectrum: Implement the ethtool flash_device callback") Signed-off-by: Shalom Toledo Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/core.c | 19 ++++++++++++++++++- drivers/net/ethernet/mellanox/mlxsw/core.h | 3 +++ drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 7 ++++++- 3 files changed, 27 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c index 30f751e69698..f7154f358f27 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core.c @@ -81,6 +81,7 @@ struct mlxsw_core { struct mlxsw_core_port *ports; unsigned int max_ports; bool reload_fail; + bool fw_flash_in_progress; unsigned long driver_priv[0]; /* driver_priv has to be always the last item */ }; @@ -428,12 +429,16 @@ struct mlxsw_reg_trans { struct rcu_head rcu; }; -#define MLXSW_EMAD_TIMEOUT_MS 200 +#define MLXSW_EMAD_TIMEOUT_DURING_FW_FLASH_MS 3000 +#define MLXSW_EMAD_TIMEOUT_MS 200 static void mlxsw_emad_trans_timeout_schedule(struct mlxsw_reg_trans *trans) { unsigned long timeout = msecs_to_jiffies(MLXSW_EMAD_TIMEOUT_MS); + if (trans->core->fw_flash_in_progress) + timeout = msecs_to_jiffies(MLXSW_EMAD_TIMEOUT_DURING_FW_FLASH_MS); + queue_delayed_work(trans->core->emad_wq, &trans->timeout_dw, timeout); } @@ -1854,6 +1859,18 @@ int mlxsw_core_kvd_sizes_get(struct mlxsw_core *mlxsw_core, } EXPORT_SYMBOL(mlxsw_core_kvd_sizes_get); +void mlxsw_core_fw_flash_start(struct mlxsw_core *mlxsw_core) +{ + mlxsw_core->fw_flash_in_progress = true; +} +EXPORT_SYMBOL(mlxsw_core_fw_flash_start); + +void mlxsw_core_fw_flash_end(struct mlxsw_core *mlxsw_core) +{ + mlxsw_core->fw_flash_in_progress = false; +} +EXPORT_SYMBOL(mlxsw_core_fw_flash_end); + static int __init mlxsw_core_module_init(void) { int err; diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.h b/drivers/net/ethernet/mellanox/mlxsw/core.h index c35be477856f..c4e4971764e5 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.h +++ b/drivers/net/ethernet/mellanox/mlxsw/core.h @@ -292,6 +292,9 @@ int mlxsw_core_kvd_sizes_get(struct mlxsw_core *mlxsw_core, u64 *p_single_size, u64 *p_double_size, u64 *p_linear_size); +void mlxsw_core_fw_flash_start(struct mlxsw_core *mlxsw_core); +void mlxsw_core_fw_flash_end(struct mlxsw_core *mlxsw_core); + bool mlxsw_core_res_valid(struct mlxsw_core *mlxsw_core, enum mlxsw_res_id res_id); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 9bec940330a4..75a2f1495455 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -309,8 +309,13 @@ static int mlxsw_sp_firmware_flash(struct mlxsw_sp *mlxsw_sp, }, .mlxsw_sp = mlxsw_sp }; + int err; + + mlxsw_core_fw_flash_start(mlxsw_sp->core); + err = mlxfw_firmware_flash(&mlxsw_sp_mlxfw_dev.mlxfw_dev, firmware); + mlxsw_core_fw_flash_end(mlxsw_sp->core); - return mlxfw_firmware_flash(&mlxsw_sp_mlxfw_dev.mlxfw_dev, firmware); + return err; } static int mlxsw_sp_fw_rev_validate(struct mlxsw_sp *mlxsw_sp) -- cgit v1.2.3 From 5d5043917a28438df163c4e6e56e77ef6d981089 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Tue, 18 Dec 2018 15:59:22 +0000 Subject: mlxsw: spectrum: Add trap for decapsulated ARP packets After a packet was decapsulated it is classified to the relevant FID based on its VNI and undergoes L2 forwarding. Unlike regular (non-encapsulated) ARP packets, Spectrum does not trap decapsulated ARP packets during L2 forwarding and instead can only trap such packets in the underlay router during decapsulation. Add this missing packet trap, which is required for VXLAN routing when the MAC of the target host is not known. Fixes: b02597d513a9 ("mlxsw: spectrum: Add NVE packet traps") Signed-off-by: Ido Schimmel Reviewed-by: Petr Machata Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 1 + drivers/net/ethernet/mellanox/mlxsw/trap.h | 1 + 2 files changed, 2 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 75a2f1495455..f84b9c02fcc5 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -3526,6 +3526,7 @@ static const struct mlxsw_listener mlxsw_sp_listener[] = { MLXSW_SP_RXL_MR_MARK(ACL2, TRAP_TO_CPU, MULTICAST, false), /* NVE traps */ MLXSW_SP_RXL_MARK(NVE_ENCAP_ARP, TRAP_TO_CPU, ARP, false), + MLXSW_SP_RXL_NO_MARK(NVE_DECAP_ARP, TRAP_TO_CPU, ARP, false), }; static int mlxsw_sp_cpu_policers_set(struct mlxsw_core *mlxsw_core) diff --git a/drivers/net/ethernet/mellanox/mlxsw/trap.h b/drivers/net/ethernet/mellanox/mlxsw/trap.h index 6f18f4d3322a..451216dd7f6b 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/trap.h +++ b/drivers/net/ethernet/mellanox/mlxsw/trap.h @@ -60,6 +60,7 @@ enum { MLXSW_TRAP_ID_IPV6_MC_LINK_LOCAL_DEST = 0x91, MLXSW_TRAP_ID_HOST_MISS_IPV6 = 0x92, MLXSW_TRAP_ID_IPIP_DECAP_ERROR = 0xB1, + MLXSW_TRAP_ID_NVE_DECAP_ARP = 0xB8, MLXSW_TRAP_ID_NVE_ENCAP_ARP = 0xBD, MLXSW_TRAP_ID_ROUTER_ALERT_IPV4 = 0xD6, MLXSW_TRAP_ID_ROUTER_ALERT_IPV6 = 0xD7, -- cgit v1.2.3 From 5edb7e8bd52cd79634d1d7fbc97c5960a21b2873 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Tue, 18 Dec 2018 15:59:23 +0000 Subject: mlxsw: spectrum_nve: Fix memory leak upon driver reload The pointer was NULLed before freeing the memory, resulting in a memory leak. Trace from kmemleak: unreferenced object 0xffff88820ae36528 (size 512): comm "devlink", pid 5374, jiffies 4295354033 (age 10829.296s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<00000000a43f5195>] kmem_cache_alloc_trace+0x1be/0x330 [<00000000312f8140>] mlxsw_sp_nve_init+0xcb/0x1ae0 [<0000000009201d22>] mlxsw_sp_init+0x1382/0x2690 [<000000007227d877>] mlxsw_sp1_init+0x1b5/0x260 [<000000004a16feec>] __mlxsw_core_bus_device_register+0x776/0x1360 [<0000000070ab954c>] mlxsw_devlink_core_bus_device_reload+0x129/0x220 [<00000000432313d5>] devlink_nl_cmd_reload+0x119/0x1e0 [<000000003821a06b>] genl_family_rcv_msg+0x813/0x1150 [<00000000d54d04c0>] genl_rcv_msg+0xd1/0x180 [<0000000040543d12>] netlink_rcv_skb+0x152/0x3c0 [<00000000efc4eae8>] genl_rcv+0x2d/0x40 [<00000000ea645603>] netlink_unicast+0x52f/0x740 [<00000000641fca1a>] netlink_sendmsg+0x9c7/0xf50 [<00000000fed4a4b8>] sock_sendmsg+0xbe/0x120 [<00000000d85795a9>] __sys_sendto+0x397/0x620 [<00000000c5f84622>] __x64_sys_sendto+0xe6/0x1a0 Fixes: 6e6030bd5412 ("mlxsw: spectrum_nve: Implement common NVE core") Signed-off-by: Ido Schimmel Reviewed-by: Petr Machata Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c index 5c13674439f1..b5b54b41349a 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c @@ -977,6 +977,6 @@ void mlxsw_sp_nve_fini(struct mlxsw_sp *mlxsw_sp) { WARN_ON(mlxsw_sp->nve->num_nve_tunnels); rhashtable_destroy(&mlxsw_sp->nve->mc_list_ht); - mlxsw_sp->nve = NULL; kfree(mlxsw_sp->nve); + mlxsw_sp->nve = NULL; } -- cgit v1.2.3 From a915b982d8f5e4295f64b8dd37ce753874867e88 Mon Sep 17 00:00:00 2001 From: Jorgen Hansen Date: Tue, 18 Dec 2018 00:34:06 -0800 Subject: VSOCK: Send reset control packet when socket is partially bound If a server side socket is bound to an address, but not in the listening state yet, incoming connection requests should receive a reset control packet in response. However, the function used to send the reset silently drops the reset packet if the sending socket isn't bound to a remote address (as is the case for a bound socket not yet in the listening state). This change fixes this by using the src of the incoming packet as destination for the reset packet in this case. Fixes: d021c344051a ("VSOCK: Introduce VM Sockets") Reviewed-by: Adit Ranadive Reviewed-by: Vishnu Dasa Signed-off-by: Jorgen Hansen Signed-off-by: David S. Miller --- net/vmw_vsock/vmci_transport.c | 67 +++++++++++++++++++++++++++++++----------- 1 file changed, 50 insertions(+), 17 deletions(-) diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c index cb332adb84cd..c361ce782412 100644 --- a/net/vmw_vsock/vmci_transport.c +++ b/net/vmw_vsock/vmci_transport.c @@ -263,6 +263,31 @@ vmci_transport_send_control_pkt_bh(struct sockaddr_vm *src, false); } +static int +vmci_transport_alloc_send_control_pkt(struct sockaddr_vm *src, + struct sockaddr_vm *dst, + enum vmci_transport_packet_type type, + u64 size, + u64 mode, + struct vmci_transport_waiting_info *wait, + u16 proto, + struct vmci_handle handle) +{ + struct vmci_transport_packet *pkt; + int err; + + pkt = kmalloc(sizeof(*pkt), GFP_KERNEL); + if (!pkt) + return -ENOMEM; + + err = __vmci_transport_send_control_pkt(pkt, src, dst, type, size, + mode, wait, proto, handle, + true); + kfree(pkt); + + return err; +} + static int vmci_transport_send_control_pkt(struct sock *sk, enum vmci_transport_packet_type type, @@ -272,9 +297,7 @@ vmci_transport_send_control_pkt(struct sock *sk, u16 proto, struct vmci_handle handle) { - struct vmci_transport_packet *pkt; struct vsock_sock *vsk; - int err; vsk = vsock_sk(sk); @@ -284,17 +307,10 @@ vmci_transport_send_control_pkt(struct sock *sk, if (!vsock_addr_bound(&vsk->remote_addr)) return -EINVAL; - pkt = kmalloc(sizeof(*pkt), GFP_KERNEL); - if (!pkt) - return -ENOMEM; - - err = __vmci_transport_send_control_pkt(pkt, &vsk->local_addr, - &vsk->remote_addr, type, size, - mode, wait, proto, handle, - true); - kfree(pkt); - - return err; + return vmci_transport_alloc_send_control_pkt(&vsk->local_addr, + &vsk->remote_addr, + type, size, mode, + wait, proto, handle); } static int vmci_transport_send_reset_bh(struct sockaddr_vm *dst, @@ -312,12 +328,29 @@ static int vmci_transport_send_reset_bh(struct sockaddr_vm *dst, static int vmci_transport_send_reset(struct sock *sk, struct vmci_transport_packet *pkt) { + struct sockaddr_vm *dst_ptr; + struct sockaddr_vm dst; + struct vsock_sock *vsk; + if (pkt->type == VMCI_TRANSPORT_PACKET_TYPE_RST) return 0; - return vmci_transport_send_control_pkt(sk, - VMCI_TRANSPORT_PACKET_TYPE_RST, - 0, 0, NULL, VSOCK_PROTO_INVALID, - VMCI_INVALID_HANDLE); + + vsk = vsock_sk(sk); + + if (!vsock_addr_bound(&vsk->local_addr)) + return -EINVAL; + + if (vsock_addr_bound(&vsk->remote_addr)) { + dst_ptr = &vsk->remote_addr; + } else { + vsock_addr_init(&dst, pkt->dg.src.context, + pkt->src_port); + dst_ptr = &dst; + } + return vmci_transport_alloc_send_control_pkt(&vsk->local_addr, dst_ptr, + VMCI_TRANSPORT_PACKET_TYPE_RST, + 0, 0, NULL, VSOCK_PROTO_INVALID, + VMCI_INVALID_HANDLE); } static int vmci_transport_send_negotiate(struct sock *sk, size_t size) -- cgit v1.2.3 From 987d1149be7ddcc1380ff946cf236874421a7e1b Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Mon, 17 Dec 2018 09:36:19 -0800 Subject: KVM: fix unregistering coalesced mmio zone from wrong bus If you register a kvm_coalesced_mmio_zone with '.pio = 0' but then unregister it with '.pio = 1', KVM_UNREGISTER_COALESCED_MMIO will try to unregister it from KVM_PIO_BUS rather than KVM_MMIO_BUS, which is a no-op. But it frees the kvm_coalesced_mmio_dev anyway, causing a use-after-free. Fix it by only unregistering and freeing the zone if the correct value of 'pio' is provided. Reported-by: syzbot+f87f60bb6f13f39b54e3@syzkaller.appspotmail.com Fixes: 0804c849f1df ("kvm/x86 : add coalesced pio support") Signed-off-by: Eric Biggers Signed-off-by: Paolo Bonzini --- virt/kvm/coalesced_mmio.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/virt/kvm/coalesced_mmio.c b/virt/kvm/coalesced_mmio.c index 3710342cf6ad..6855cce3e528 100644 --- a/virt/kvm/coalesced_mmio.c +++ b/virt/kvm/coalesced_mmio.c @@ -175,10 +175,14 @@ int kvm_vm_ioctl_unregister_coalesced_mmio(struct kvm *kvm, { struct kvm_coalesced_mmio_dev *dev, *tmp; + if (zone->pio != 1 && zone->pio != 0) + return -EINVAL; + mutex_lock(&kvm->slots_lock); list_for_each_entry_safe(dev, tmp, &kvm->coalesced_zones, list) - if (coalesced_mmio_in_range(dev, zone->addr, zone->size)) { + if (zone->pio == dev->zone.pio && + coalesced_mmio_in_range(dev, zone->addr, zone->size)) { kvm_io_bus_unregister_dev(kvm, zone->pio ? KVM_PIO_BUS : KVM_MMIO_BUS, &dev->dev); kvm_iodevice_destructor(&dev->dev); -- cgit v1.2.3 From c2dd5146e9fe1f22c77c1b011adf84eea0245806 Mon Sep 17 00:00:00 2001 From: Cfir Cohen Date: Tue, 18 Dec 2018 08:18:41 -0800 Subject: KVM: Fix UAF in nested posted interrupt processing nested_get_vmcs12_pages() processes the posted_intr address in vmcs12. It caches the kmap()ed page object and pointer, however, it doesn't handle errors correctly: it's possible to cache a valid pointer, then release the page and later dereference the dangling pointer. I was able to reproduce with the following steps: 1. Call vmlaunch with valid posted_intr_desc_addr but an invalid MSR_EFER. This causes nested_get_vmcs12_pages() to cache the kmap()ed pi_desc_page and pi_desc. Later the invalid EFER value fails check_vmentry_postreqs() which fails the first vmlaunch. 2. Call vmlanuch with a valid EFER but an invalid posted_intr_desc_addr (I set it to 2G - 0x80). The second time we call nested_get_vmcs12_pages pi_desc_page is unmapped and released and pi_desc_page is set to NULL (the "shouldn't happen" clause). Due to the invalid posted_intr_desc_addr, kvm_vcpu_gpa_to_page() fails and nested_get_vmcs12_pages() returns. It doesn't return an error value so vmlaunch proceeds. Note that at this time we have a dangling pointer in vmx->nested.pi_desc and POSTED_INTR_DESC_ADDR in L0's vmcs. 3. Issue an IPI in L2 guest code. This triggers a call to vmx_complete_nested_posted_interrupt() and pi_test_and_clear_on() which dereferences the dangling pointer. Vulnerable code requires nested and enable_apicv variables to be set to true. The host CPU must also support posted interrupts. Fixes: 5e2f30b756a37 "KVM: nVMX: get rid of nested_get_page()" Cc: stable@vger.kernel.org Reviewed-by: Andy Honig Signed-off-by: Cfir Cohen Reviewed-by: Liran Alon Signed-off-by: Paolo Bonzini --- arch/x86/kvm/vmx.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 02edd9960e9d..8d5d984541be 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -11985,6 +11985,8 @@ static void nested_get_vmcs12_pages(struct kvm_vcpu *vcpu) kunmap(vmx->nested.pi_desc_page); kvm_release_page_dirty(vmx->nested.pi_desc_page); vmx->nested.pi_desc_page = NULL; + vmx->nested.pi_desc = NULL; + vmcs_write64(POSTED_INTR_DESC_ADDR, -1ull); } page = kvm_vcpu_gpa_to_page(vcpu, vmcs12->posted_intr_desc_addr); if (is_error_page(page)) -- cgit v1.2.3 From dcbd3e49c2f0b2c2d8a321507ff8f3de4af76d7c Mon Sep 17 00:00:00 2001 From: Wanpeng Li Date: Mon, 17 Dec 2018 10:43:23 +0800 Subject: KVM: X86: Fix NULL deref in vcpu_scan_ioapic Reported by syzkaller: CPU: 1 PID: 5962 Comm: syz-executor118 Not tainted 4.20.0-rc6+ #374 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 RIP: 0010:kvm_apic_hw_enabled arch/x86/kvm/lapic.h:169 [inline] RIP: 0010:vcpu_scan_ioapic arch/x86/kvm/x86.c:7449 [inline] RIP: 0010:vcpu_enter_guest arch/x86/kvm/x86.c:7602 [inline] RIP: 0010:vcpu_run arch/x86/kvm/x86.c:7874 [inline] RIP: 0010:kvm_arch_vcpu_ioctl_run+0x5296/0x7320 arch/x86/kvm/x86.c:8074 Call Trace: kvm_vcpu_ioctl+0x5c8/0x1150 arch/x86/kvm/../../../virt/kvm/kvm_main.c:2596 vfs_ioctl fs/ioctl.c:46 [inline] file_ioctl fs/ioctl.c:509 [inline] do_vfs_ioctl+0x1de/0x1790 fs/ioctl.c:696 ksys_ioctl+0xa9/0xd0 fs/ioctl.c:713 __do_sys_ioctl fs/ioctl.c:720 [inline] __se_sys_ioctl fs/ioctl.c:718 [inline] __x64_sys_ioctl+0x73/0xb0 fs/ioctl.c:718 do_syscall_64+0x1b9/0x820 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe The reason is that the testcase writes hyperv synic HV_X64_MSR_SINT14 msr and triggers scan ioapic logic to load synic vectors into EOI exit bitmap. However, irqchip is not initialized by this simple testcase, ioapic/apic objects should not be accessed. This patch fixes it by also considering whether or not apic is present. Reported-by: syzbot+39810e6c400efadfef71@syzkaller.appspotmail.com Cc: stable@vger.kernel.org Cc: Paolo Bonzini Cc: Radim Krčmář Signed-off-by: Wanpeng Li Signed-off-by: Paolo Bonzini --- arch/x86/kvm/x86.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index d02937760c3b..477563e7ccbd 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -7446,7 +7446,7 @@ void kvm_make_scan_ioapic_request(struct kvm *kvm) static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu) { - if (!kvm_apic_hw_enabled(vcpu->arch.apic)) + if (!kvm_apic_present(vcpu)) return; bitmap_zero(vcpu->arch.ioapic_handled_vectors, 256); -- cgit v1.2.3 From 0e1b869fff60c81b510c2d00602d778f8f59dd9a Mon Sep 17 00:00:00 2001 From: Eduardo Habkost Date: Mon, 17 Dec 2018 22:34:18 -0200 Subject: kvm: x86: Add AMD's EX_CFG to the list of ignored MSRs Some guests OSes (including Windows 10) write to MSR 0xc001102c on some cases (possibly while trying to apply a CPU errata). Make KVM ignore reads and writes to that MSR, so the guest won't crash. The MSR is documented as "Execution Unit Configuration (EX_CFG)", at AMD's "BIOS and Kernel Developer's Guide (BKDG) for AMD Family 15h Models 00h-0Fh Processors". Cc: stable@vger.kernel.org Signed-off-by: Eduardo Habkost Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/msr-index.h | 1 + arch/x86/kvm/x86.c | 2 ++ 2 files changed, 3 insertions(+) diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index c8f73efb4ece..9e39cc8bd989 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -390,6 +390,7 @@ #define MSR_F15H_NB_PERF_CTR 0xc0010241 #define MSR_F15H_PTSC 0xc0010280 #define MSR_F15H_IC_CFG 0xc0011021 +#define MSR_F15H_EX_CFG 0xc001102c /* Fam 10h MSRs */ #define MSR_FAM10H_MMIO_CONF_BASE 0xc0010058 diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 477563e7ccbd..f049ecfac7bb 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -2426,6 +2426,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_AMD64_PATCH_LOADER: case MSR_AMD64_BU_CFG2: case MSR_AMD64_DC_CFG: + case MSR_F15H_EX_CFG: break; case MSR_IA32_UCODE_REV: @@ -2721,6 +2722,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_AMD64_BU_CFG2: case MSR_IA32_PERF_CTL: case MSR_AMD64_DC_CFG: + case MSR_F15H_EX_CFG: msr_info->data = 0; break; case MSR_F15H_PERF_CTL0 ... MSR_F15H_PERF_CTR5: -- cgit v1.2.3 From 006791772084383de779ef29f2e06f3a6e111e7d Mon Sep 17 00:00:00 2001 From: Antoine Tenart Date: Tue, 11 Dec 2018 17:32:28 +0100 Subject: net: mvpp2: 10G modes aren't supported on all ports The mvpp2_phylink_validate() function sets all modes that are supported by a given PPv2 port. A recent change made all ports to advertise they support 10G modes in certain cases. This is not true, as only the port #0 can do so. This patch fixes it. Fixes: 01b3fd5ac97c ("net: mvpp2: fix detection of 10G SFP modules") Cc: Baruch Siach Signed-off-by: Antoine Tenart Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index 125ea99418df..88aa488054a8 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -4405,12 +4405,14 @@ static void mvpp2_phylink_validate(struct net_device *dev, case PHY_INTERFACE_MODE_10GKR: case PHY_INTERFACE_MODE_XAUI: case PHY_INTERFACE_MODE_NA: - phylink_set(mask, 10000baseCR_Full); - phylink_set(mask, 10000baseSR_Full); - phylink_set(mask, 10000baseLR_Full); - phylink_set(mask, 10000baseLRM_Full); - phylink_set(mask, 10000baseER_Full); - phylink_set(mask, 10000baseKR_Full); + if (port->gop_id == 0) { + phylink_set(mask, 10000baseCR_Full); + phylink_set(mask, 10000baseSR_Full); + phylink_set(mask, 10000baseLR_Full); + phylink_set(mask, 10000baseLRM_Full); + phylink_set(mask, 10000baseER_Full); + phylink_set(mask, 10000baseKR_Full); + } /* Fall-through */ case PHY_INTERFACE_MODE_RGMII: case PHY_INTERFACE_MODE_RGMII_ID: -- cgit v1.2.3 From f07d4276892d97671e880190ff195a288b2d8d92 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Mon, 17 Dec 2018 10:05:13 +0300 Subject: qed: Fix an error code qed_ll2_start_xmit() We accidentally deleted the code to set "rc = -ENOMEM;" and this patch adds it back. Fixes: d2201a21598a ("qed: No need for LL2 frags indication") Signed-off-by: Dan Carpenter Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed_ll2.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.c b/drivers/net/ethernet/qlogic/qed/qed_ll2.c index aa633381aa47..c6f4bab67a5f 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_ll2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.c @@ -2496,6 +2496,7 @@ static int qed_ll2_start_xmit(struct qed_dev *cdev, struct sk_buff *skb, if (unlikely(dma_mapping_error(&cdev->pdev->dev, mapping))) { DP_NOTICE(cdev, "Unable to map frag - dropping packet\n"); + rc = -ENOMEM; goto err; } -- cgit v1.2.3 From 3c6306d44082ef007a258ae1b86ea58e6974ee3f Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Sun, 16 Dec 2018 23:25:12 -0800 Subject: tipc: check group dests after tipc_wait_for_cond() Similar to commit 143ece654f9f ("tipc: check tsk->group in tipc_wait_for_cond()") we have to reload grp->dests too after we re-take the sock lock. This means we need to move the dsts check after tipc_wait_for_cond() too. Fixes: 75da2163dbb6 ("tipc: introduce communication groups") Reported-and-tested-by: syzbot+99f20222fc5018d2b97a@syzkaller.appspotmail.com Cc: Ying Xue Cc: Jon Maloy Signed-off-by: Cong Wang Acked-by: Jon Maloy Signed-off-by: David S. Miller --- net/tipc/socket.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 656940692a44..8f34db2a9785 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -1009,7 +1009,7 @@ static int tipc_send_group_bcast(struct socket *sock, struct msghdr *m, struct sock *sk = sock->sk; struct net *net = sock_net(sk); struct tipc_sock *tsk = tipc_sk(sk); - struct tipc_nlist *dsts = tipc_group_dests(tsk->group); + struct tipc_nlist *dsts; struct tipc_mc_method *method = &tsk->mc_method; bool ack = method->mandatory && method->rcast; int blks = tsk_blocks(MCAST_H_SIZE + dlen); @@ -1018,9 +1018,6 @@ static int tipc_send_group_bcast(struct socket *sock, struct msghdr *m, struct sk_buff_head pkts; int rc = -EHOSTUNREACH; - if (!dsts->local && !dsts->remote) - return -EHOSTUNREACH; - /* Block or return if any destination link or member is congested */ rc = tipc_wait_for_cond(sock, &timeout, !tsk->cong_link_cnt && tsk->group && @@ -1028,6 +1025,10 @@ static int tipc_send_group_bcast(struct socket *sock, struct msghdr *m, if (unlikely(rc)) return rc; + dsts = tipc_group_dests(tsk->group); + if (!dsts->local && !dsts->remote) + return -EHOSTUNREACH; + /* Complete message header */ if (dest) { msg_set_type(hdr, TIPC_GRP_MCAST_MSG); -- cgit v1.2.3 From b26322d2ac6c1c1087af73856531bb836f6963ca Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Mon, 17 Dec 2018 11:06:06 +0300 Subject: net: stmmac: Fix an error code in probe() The function should return an error if create_singlethread_workqueue() fails. Fixes: 34877a15f787 ("net: stmmac: Rework and fix TX Timeout code") Signed-off-by: Dan Carpenter Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 5551fead8f66..c4a35e932f05 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -4250,6 +4250,7 @@ int stmmac_dvr_probe(struct device *device, priv->wq = create_singlethread_workqueue("stmmac_wq"); if (!priv->wq) { dev_err(priv->device, "failed to create workqueue\n"); + ret = -ENOMEM; goto error_wq; } -- cgit v1.2.3 From 4298388574dae6168fa8940b3edc7ba965e8a7ab Mon Sep 17 00:00:00 2001 From: Claudiu Beznea Date: Mon, 17 Dec 2018 10:02:42 +0000 Subject: net: macb: restart tx after tx used bit read On some platforms (currently detected only on SAMA5D4) TX might stuck even the pachets are still present in DMA memories and TX start was issued for them. This happens due to race condition between MACB driver updating next TX buffer descriptor to be used and IP reading the same descriptor. In such a case, the "TX USED BIT READ" interrupt is asserted. GEM/MACB user guide specifies that if a "TX USED BIT READ" interrupt is asserted TX must be restarted. Restart TX if used bit is read and packets are present in software TX queue. Packets are removed from software TX queue if TX was successful for them (see macb_tx_interrupt()). Signed-off-by: Claudiu Beznea Acked-by: Nicolas Ferre Signed-off-by: David S. Miller --- drivers/net/ethernet/cadence/macb_main.c | 21 ++++++++++++++++++++- 1 file changed, 20 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 1d86b4d5645a..dfaefe91b96a 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -61,7 +61,8 @@ #define MACB_TX_ERR_FLAGS (MACB_BIT(ISR_TUND) \ | MACB_BIT(ISR_RLE) \ | MACB_BIT(TXERR)) -#define MACB_TX_INT_FLAGS (MACB_TX_ERR_FLAGS | MACB_BIT(TCOMP)) +#define MACB_TX_INT_FLAGS (MACB_TX_ERR_FLAGS | MACB_BIT(TCOMP) \ + | MACB_BIT(TXUBR)) /* Max length of transmit frame must be a multiple of 8 bytes */ #define MACB_TX_LEN_ALIGN 8 @@ -1312,6 +1313,21 @@ static void macb_hresp_error_task(unsigned long data) netif_tx_start_all_queues(dev); } +static void macb_tx_restart(struct macb_queue *queue) +{ + unsigned int head = queue->tx_head; + unsigned int tail = queue->tx_tail; + struct macb *bp = queue->bp; + + if (bp->caps & MACB_CAPS_ISR_CLEAR_ON_WRITE) + queue_writel(queue, ISR, MACB_BIT(TXUBR)); + + if (head == tail) + return; + + macb_writel(bp, NCR, macb_readl(bp, NCR) | MACB_BIT(TSTART)); +} + static irqreturn_t macb_interrupt(int irq, void *dev_id) { struct macb_queue *queue = dev_id; @@ -1369,6 +1385,9 @@ static irqreturn_t macb_interrupt(int irq, void *dev_id) if (status & MACB_BIT(TCOMP)) macb_tx_interrupt(queue); + if (status & MACB_BIT(TXUBR)) + macb_tx_restart(queue); + /* Link change detection isn't possible with RMII, so we'll * add that if/when we get our hands on a full-blown MII PHY. */ -- cgit v1.2.3 From e2c4cf7f98a519eb4d95532bfa06bcaf3562fed5 Mon Sep 17 00:00:00 2001 From: Davide Caratti Date: Mon, 17 Dec 2018 11:26:38 +0100 Subject: net: Use __kernel_clockid_t in uapi net_stamp.h Herton reports the following error when building a userspace program that includes net_stamp.h: In file included from foo.c:2: /usr/include/linux/net_tstamp.h:158:2: error: unknown type name ‘clockid_t’ clockid_t clockid; /* reference clockid */ ^~~~~~~~~ Fix it by using __kernel_clockid_t in place of clockid_t. Fixes: 80b14dee2bea ("net: Add a new socket option for a future transmit time.") Cc: Timothy Redaelli Reported-by: Herton R. Krzesinski Signed-off-by: Davide Caratti Tested-by: Paolo Abeni Signed-off-by: David S. Miller --- include/uapi/linux/net_tstamp.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/include/uapi/linux/net_tstamp.h b/include/uapi/linux/net_tstamp.h index 97ff3c17ec4d..e5b39721c6e4 100644 --- a/include/uapi/linux/net_tstamp.h +++ b/include/uapi/linux/net_tstamp.h @@ -155,8 +155,8 @@ enum txtime_flags { }; struct sock_txtime { - clockid_t clockid; /* reference clockid */ - __u32 flags; /* as defined by enum txtime_flags */ + __kernel_clockid_t clockid;/* reference clockid */ + __u32 flags; /* as defined by enum txtime_flags */ }; #endif /* _NET_TIMESTAMPING_H */ -- cgit v1.2.3 From e100a897bf9b19089e57f236f2398c9e0538900e Mon Sep 17 00:00:00 2001 From: Anssi Hannula Date: Mon, 17 Dec 2018 15:05:39 +0200 Subject: net: macb: fix random memory corruption on RX with 64-bit DMA 64-bit DMA addresses are split in upper and lower halves that are written in separate fields on GEM. For RX, bit 0 of the address is used as the ownership bit (RX_USED). When the RX_USED bit is unset the controller is allowed to write data to the buffer. The driver does not guarantee that the controller already sees the upper half when the RX_USED bit is cleared, possibly resulting in the controller writing an incoming frame to an address with an incorrect upper half and therefore possibly corrupting unrelated system memory. Fix that by adding the necessary DMA memory barrier between the writes. This corruption was observed on a ZynqMP based system. Fixes: fff8019a08b6 ("net: macb: Add 64 bit addressing support for GEM") Signed-off-by: Anssi Hannula Acked-by: Harini Katakam Tested-by: Claudiu Beznea Cc: Nicolas Ferre Cc: Michal Simek Signed-off-by: David S. Miller --- drivers/net/ethernet/cadence/macb_main.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index dfaefe91b96a..c2f03c60f84b 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -681,6 +681,11 @@ static void macb_set_addr(struct macb *bp, struct macb_dma_desc *desc, dma_addr_ if (bp->hw_dma_cap & HW_DMA_CAP_64B) { desc_64 = macb_64b_desc(bp, desc); desc_64->addrh = upper_32_bits(addr); + /* The low bits of RX address contain the RX_USED bit, clearing + * of which allows packet RX. Make sure the high bits are also + * visible to HW at that point. + */ + dma_wmb(); } #endif desc->addr = lower_32_bits(addr); -- cgit v1.2.3 From 8159ecab0db9095902d4c73605fb8787f5c7d653 Mon Sep 17 00:00:00 2001 From: Anssi Hannula Date: Mon, 17 Dec 2018 15:05:40 +0200 Subject: net: macb: fix dropped RX frames due to a race Bit RX_USED set to 0 in the address field allows the controller to write data to the receive buffer descriptor. The driver does not ensure the ctrl field is ready (cleared) when the controller sees the RX_USED=0 written by the driver. The ctrl field might only be cleared after the controller has already updated it according to a newly received frame, causing the frame to be discarded in gem_rx() due to unexpected ctrl field contents. A message is logged when the above scenario occurs: macb ff0b0000.ethernet eth0: not whole frame pointed by descriptor Fix the issue by ensuring that when the controller sees RX_USED=0 the ctrl field is already cleared. This issue was observed on a ZynqMP based system. Fixes: 4df95131ea80 ("net/macb: change RX path for GEM") Signed-off-by: Anssi Hannula Tested-by: Claudiu Beznea Cc: Nicolas Ferre Signed-off-by: David S. Miller --- drivers/net/ethernet/cadence/macb_main.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index c2f03c60f84b..f531c1eae4ff 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -934,14 +934,19 @@ static void gem_rx_refill(struct macb_queue *queue) if (entry == bp->rx_ring_size - 1) paddr |= MACB_BIT(RX_WRAP); - macb_set_addr(bp, desc, paddr); desc->ctrl = 0; + /* Setting addr clears RX_USED and allows reception, + * make sure ctrl is cleared first to avoid a race. + */ + dma_wmb(); + macb_set_addr(bp, desc, paddr); /* properly align Ethernet header */ skb_reserve(skb, NET_IP_ALIGN); } else { - desc->addr &= ~MACB_BIT(RX_USED); desc->ctrl = 0; + dma_wmb(); + desc->addr &= ~MACB_BIT(RX_USED); } } -- cgit v1.2.3 From 6e0af298066f3b6d99f58989bb0dca6f764b4c6d Mon Sep 17 00:00:00 2001 From: Anssi Hannula Date: Mon, 17 Dec 2018 15:05:41 +0200 Subject: net: macb: add missing barriers when reading descriptors When reading buffer descriptors on RX or on TX completion, an RX_USED/TX_USED bit is checked first to ensure that the descriptors have been populated, i.e. the ownership has been transferred. However, there are no memory barriers to ensure that the data protected by the RX_USED/TX_USED bit is up-to-date with respect to that bit. Specifically: - TX timestamp descriptors may be loaded before ctrl is loaded for the TX_USED check, which is racy as the descriptors may be updated between the loads, causing old timestamp descriptor data to be used. - RX ctrl may be loaded before addr is loaded for the RX_USED check, which is racy as a new frame may be written between the loads, causing old ctrl descriptor data to be used. This issue exists for both macb_rx() and gem_rx() variants. Fix the races by adding DMA read memory barriers on those paths and reordering the reads in macb_rx(). I have not observed any actual problems in practice caused by these being missing, though. Tested on a ZynqMP based system. Fixes: 89e5785fc8a6 ("[PATCH] Atmel MACB ethernet driver") Signed-off-by: Anssi Hannula Cc: Nicolas Ferre Signed-off-by: David S. Miller --- drivers/net/ethernet/cadence/macb_main.c | 13 ++++++++++--- drivers/net/ethernet/cadence/macb_ptp.c | 2 ++ 2 files changed, 12 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index f531c1eae4ff..4c816e5a841f 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -1000,11 +1000,15 @@ static int gem_rx(struct macb_queue *queue, int budget) rxused = (desc->addr & MACB_BIT(RX_USED)) ? true : false; addr = macb_get_addr(bp, desc); - ctrl = desc->ctrl; if (!rxused) break; + /* Ensure ctrl is at least as up-to-date as rxused */ + dma_rmb(); + + ctrl = desc->ctrl; + queue->rx_tail++; count++; @@ -1179,11 +1183,14 @@ static int macb_rx(struct macb_queue *queue, int budget) /* Make hw descriptor updates visible to CPU */ rmb(); - ctrl = desc->ctrl; - if (!(desc->addr & MACB_BIT(RX_USED))) break; + /* Ensure ctrl is at least as up-to-date as addr */ + dma_rmb(); + + ctrl = desc->ctrl; + if (ctrl & MACB_BIT(RX_SOF)) { if (first_frag != -1) discard_partial_frame(queue, first_frag, tail); diff --git a/drivers/net/ethernet/cadence/macb_ptp.c b/drivers/net/ethernet/cadence/macb_ptp.c index cd5296b84229..a6dc47edc4cf 100644 --- a/drivers/net/ethernet/cadence/macb_ptp.c +++ b/drivers/net/ethernet/cadence/macb_ptp.c @@ -319,6 +319,8 @@ int gem_ptp_txstamp(struct macb_queue *queue, struct sk_buff *skb, desc_ptp = macb_ptp_desc(queue->bp, desc); tx_timestamp = &queue->tx_timestamps[head]; tx_timestamp->skb = skb; + /* ensure ts_1/ts_2 is loaded after ctrl (TX_USED check) */ + dma_rmb(); tx_timestamp->desc_ptp.ts_1 = desc_ptp->ts_1; tx_timestamp->desc_ptp.ts_2 = desc_ptp->ts_2; /* move head */ -- cgit v1.2.3 From 6ad0b5a4e03dc5cc0c1ed6be093bdcefdc794a6f Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Tue, 18 Dec 2018 13:15:59 +0000 Subject: vxlan: Unmark offloaded bit on replaced FDB entries When rdst of an offloaded FDB entry is replaced, it certainly isn't offloaded anymore. Drivers are notified about such replacements, and can re-mark the entry as offloaded again if they so wish. However until a driver does so explicitly, assume a replaced FDB entry is not offloaded. Note that replaces coming via vxlan_fdb_external_learn_add() are always immediately followed by an explicit offload marking. Fixes: 0efe11733356 ("vxlan: Support marking RDSTs as offloaded") Signed-off-by: Petr Machata Signed-off-by: David S. Miller --- drivers/net/vxlan.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 297cdeaef479..c9956c08edf5 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -568,6 +568,7 @@ static int vxlan_fdb_replace(struct vxlan_fdb *f, rd->remote_port = port; rd->remote_vni = vni; rd->remote_ifindex = ifindex; + rd->offloaded = false; return 1; } -- cgit v1.2.3 From 6db9246871394b3a136cd52001a0763676563840 Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Tue, 18 Dec 2018 13:16:00 +0000 Subject: vxlan: Fix error path in __vxlan_dev_create() When a failure occurs in rtnl_configure_link(), the current code calls unregister_netdevice() to roll back the earlier call to register_netdevice(), and jumps to errout, which calls vxlan_fdb_destroy(). However unregister_netdevice() calls transitively ndo_uninit, which is vxlan_uninit(), and that already takes care of deleting the default FDB entry by calling vxlan_fdb_delete_default(). Since the entry added earlier in __vxlan_dev_create() is exactly the default entry, the cleanup code in the errout block always leads to double free and thus a panic. Besides, since vxlan_fdb_delete_default() always destroys the FDB entry with notification enabled, the deletion of the default entry is notified even before the addition was notified. Instead, move the unregister_netdevice() call after the manual destroy, which solves both problems. Fixes: 0241b836732f ("vxlan: fix default fdb entry netlink notify ordering during netdev create") Signed-off-by: Petr Machata Signed-off-by: David S. Miller --- drivers/net/vxlan.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index c9956c08edf5..82e78d6fd9ae 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -3259,6 +3259,7 @@ static int __vxlan_dev_create(struct net *net, struct net_device *dev, struct vxlan_net *vn = net_generic(net, vxlan_net_id); struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_fdb *f = NULL; + bool unregister = false; int err; err = vxlan_dev_configure(net, dev, conf, false, extack); @@ -3284,12 +3285,11 @@ static int __vxlan_dev_create(struct net *net, struct net_device *dev, err = register_netdevice(dev); if (err) goto errout; + unregister = true; err = rtnl_configure_link(dev, NULL); - if (err) { - unregister_netdevice(dev); + if (err) goto errout; - } /* notify default fdb entry */ if (f) @@ -3297,9 +3297,16 @@ static int __vxlan_dev_create(struct net *net, struct net_device *dev, list_add(&vxlan->next, &vn->vxlan_list); return 0; + errout: + /* unregister_netdevice() destroys the default FDB entry with deletion + * notification. But the addition notification was not sent yet, so + * destroy the entry by hand here. + */ if (f) vxlan_fdb_destroy(vxlan, f, false); + if (unregister) + unregister_netdevice(dev); return err; } -- cgit v1.2.3 From ce5e098f7a10b4bf8e948c12fa350320c5c3afad Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Tue, 18 Dec 2018 13:16:02 +0000 Subject: vxlan: changelink: Fix handling of default remotes Default remotes are stored as FDB entries with an Ethernet address of 00:00:00:00:00:00. When a request is made to change a remote address of a VXLAN device, vxlan_changelink() first deletes the existing default remote, and then creates a new FDB entry. This works well as long as the list of default remotes matches exactly the configuration of a VXLAN remote address. Thus when the VXLAN device has a remote of X, there should be exactly one default remote FDB entry X. If the VXLAN device has no remote address, there should be no such entry. Besides using "ip link set", it is possible to manipulate the list of default remotes by using the "bridge fdb". It is therefore easy to break the above condition. Under such circumstances, the __vxlan_fdb_delete() call doesn't delete the FDB entry itself, but just one remote. The following vxlan_fdb_create() then creates a new FDB entry, leading to a situation where two entries exist for the address 00:00:00:00:00:00, each with a different subset of default remotes. An even more obvious breakage rooted in the same cause can be observed when a remote address is configured for a VXLAN device that did not have one before. In that case vxlan_changelink() doesn't remove any remote, and just creates a new FDB entry for the new address: $ ip link add name vx up type vxlan id 2000 dstport 4789 $ bridge fdb ap dev vx 00:00:00:00:00:00 dst 192.0.2.20 self permanent $ bridge fdb ap dev vx 00:00:00:00:00:00 dst 192.0.2.30 self permanent $ ip link set dev vx type vxlan remote 192.0.2.30 $ bridge fdb sh dev vx | grep 00:00:00:00:00:00 00:00:00:00:00:00 dst 192.0.2.30 self permanent <- new entry, 1 rdst 00:00:00:00:00:00 dst 192.0.2.20 self permanent <- orig. entry, 2 rdsts 00:00:00:00:00:00 dst 192.0.2.30 self permanent To fix this, instead of calling vxlan_fdb_create() directly, defer to vxlan_fdb_update(). That has logic to handle the duplicates properly. Additionally, it also handles notifications, so drop that call from changelink as well. Fixes: 0241b836732f ("vxlan: fix default fdb entry netlink notify ordering during netdev create") Signed-off-by: Petr Machata Acked-by: Roopa Prabhu Signed-off-by: David S. Miller --- drivers/net/vxlan.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 82e78d6fd9ae..0565f8880199 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -3542,7 +3542,6 @@ static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[], struct vxlan_rdst *dst = &vxlan->default_dst; struct vxlan_rdst old_dst; struct vxlan_config conf; - struct vxlan_fdb *f = NULL; int err; err = vxlan_nl2conf(tb, data, @@ -3568,19 +3567,19 @@ static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[], old_dst.remote_ifindex, 0); if (!vxlan_addr_any(&dst->remote_ip)) { - err = vxlan_fdb_create(vxlan, all_zeros_mac, + err = vxlan_fdb_update(vxlan, all_zeros_mac, &dst->remote_ip, NUD_REACHABLE | NUD_PERMANENT, + NLM_F_APPEND | NLM_F_CREATE, vxlan->cfg.dst_port, dst->remote_vni, dst->remote_vni, dst->remote_ifindex, - NTF_SELF, &f); + NTF_SELF); if (err) { spin_unlock_bh(&vxlan->hash_lock); return err; } - vxlan_fdb_notify(vxlan, f, first_remote_rtnl(f), RTM_NEWNEIGH); } spin_unlock_bh(&vxlan->hash_lock); } -- cgit v1.2.3 From 55cbe0794294031d9b36984d4529f416e7e0a40a Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Tue, 18 Dec 2018 13:16:03 +0000 Subject: selftests: net: Add test_vxlan_fdb_changelink.sh Add a test to exercise the fix from the previous patch. Signed-off-by: Petr Machata Signed-off-by: David S. Miller --- tools/testing/selftests/net/Makefile | 1 + .../selftests/net/test_vxlan_fdb_changelink.sh | 29 ++++++++++++++++++++++ 2 files changed, 30 insertions(+) create mode 100755 tools/testing/selftests/net/test_vxlan_fdb_changelink.sh diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 256d82d5fa87..923570a9708a 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -7,6 +7,7 @@ CFLAGS += -I../../../../usr/include/ TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh netdevice.sh rtnetlink.sh TEST_PROGS += fib_tests.sh fib-onlink-tests.sh pmtu.sh udpgso.sh ip_defrag.sh TEST_PROGS += udpgso_bench.sh fib_rule_tests.sh msg_zerocopy.sh psock_snd.sh +TEST_PROGS += test_vxlan_fdb_changelink.sh TEST_PROGS_EXTENDED := in_netns.sh TEST_GEN_FILES = socket TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy diff --git a/tools/testing/selftests/net/test_vxlan_fdb_changelink.sh b/tools/testing/selftests/net/test_vxlan_fdb_changelink.sh new file mode 100755 index 000000000000..2d442cdab11e --- /dev/null +++ b/tools/testing/selftests/net/test_vxlan_fdb_changelink.sh @@ -0,0 +1,29 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# Check FDB default-remote handling across "ip link set". + +check_remotes() +{ + local what=$1; shift + local N=$(bridge fdb sh dev vx | grep 00:00:00:00:00:00 | wc -l) + + echo -ne "expected two remotes after $what\t" + if [[ $N != 2 ]]; then + echo "[FAIL]" + EXIT_STATUS=1 + else + echo "[ OK ]" + fi +} + +ip link add name vx up type vxlan id 2000 dstport 4789 +bridge fdb ap dev vx 00:00:00:00:00:00 dst 192.0.2.20 self permanent +bridge fdb ap dev vx 00:00:00:00:00:00 dst 192.0.2.30 self permanent +check_remotes "fdb append" + +ip link set dev vx type vxlan remote 192.0.2.30 +check_remotes "link set" + +ip link del dev vx +exit $EXIT_STATUS -- cgit v1.2.3 From 0db7d253e9f0ff1a41c602429bea93df221be6ed Mon Sep 17 00:00:00 2001 From: Bryan Whitehead Date: Mon, 17 Dec 2018 16:44:50 -0500 Subject: lan743x: Expand phy search for LAN7431 The LAN7431 uses an external phy, and it can be found anywhere in the phy address space. This patch uses phy address 1 for LAN7430 only. And searches all addresses otherwise. Signed-off-by: Bryan Whitehead Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/ethernet/microchip/lan743x_main.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c index e8ca98c070f6..1ba8ea07dc4f 100644 --- a/drivers/net/ethernet/microchip/lan743x_main.c +++ b/drivers/net/ethernet/microchip/lan743x_main.c @@ -2719,8 +2719,9 @@ static int lan743x_mdiobus_init(struct lan743x_adapter *adapter) snprintf(adapter->mdiobus->id, MII_BUS_ID_SIZE, "pci-%s", pci_name(adapter->pdev)); - /* set to internal PHY id */ - adapter->mdiobus->phy_mask = ~(u32)BIT(1); + if ((adapter->csr.id_rev & ID_REV_ID_MASK_) == ID_REV_ID_LAN7430_) + /* LAN7430 uses internal phy at address 1 */ + adapter->mdiobus->phy_mask = ~(u32)BIT(1); /* register mdiobus */ ret = mdiobus_register(adapter->mdiobus); -- cgit v1.2.3 From 15515aaaa69659c502003926a2067ee76176148a Mon Sep 17 00:00:00 2001 From: Jason Martinsen Date: Tue, 18 Dec 2018 05:38:22 +0000 Subject: lan78xx: Resolve issue with changing MAC address Current state for the lan78xx driver does not allow for changing the MAC address of the interface, without either removing the module (if you compiled it that way) or rebooting the machine. If you attempt to change the MAC address, ifconfig will show the new address, however, the system/interface will not respond to any traffic using that configuration. A few short-term options to work around this are to unload the module and reload it with the new MAC address, change the interface to "promisc", or reboot with the correct configuration to change the MAC. This patch enables the ability to change the MAC address via fairly normal means... ifdown modify entry in /etc/network/interfaces OR a similar method ifup Then test via any network communication, such as ICMP requests to gateway. My only test platform for this patch has been a raspberry pi model 3b+. Signed-off-by: Jason Martinsen ----- Signed-off-by: David S. Miller --- drivers/net/usb/lan78xx.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index be1917be28f2..77d3c85febf1 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -2320,6 +2320,10 @@ static int lan78xx_set_mac_addr(struct net_device *netdev, void *p) ret = lan78xx_write_reg(dev, RX_ADDRL, addr_lo); ret = lan78xx_write_reg(dev, RX_ADDRH, addr_hi); + /* Added to support MAC address changes */ + ret = lan78xx_write_reg(dev, MAF_LO(0), addr_lo); + ret = lan78xx_write_reg(dev, MAF_HI(0), addr_hi | MAF_HI_VALID_); + return 0; } -- cgit v1.2.3 From 8742beb50f2db903d3b6d69ddd81d67ce9914453 Mon Sep 17 00:00:00 2001 From: Kunihiko Hayashi Date: Tue, 18 Dec 2018 16:57:04 +0900 Subject: net: phy: Fix the issue that netif always links up after resuming Even though the link is down before entering hibernation, there is an issue that the network interface always links up after resuming from hibernation. If the link is still down before enabling the network interface, and after resuming from hibernation, the phydev->state is forcibly set to PHY_UP in mdio_bus_phy_restore(), and the link becomes up. In suspend sequence, only if the PHY is attached, mdio_bus_phy_suspend() calls phy_stop_machine(), and mdio_bus_phy_resume() calls phy_start_machine(). In resume sequence, it's enough to do the same as mdio_bus_phy_resume() because the state has been preserved. This patch fixes the issue by calling phy_start_machine() in mdio_bus_phy_restore() in the same way as mdio_bus_phy_resume(). Fixes: bc87922ff59d ("phy: Move PHY PM operations into phy_device") Suggested-by: Heiner Kallweit Signed-off-by: Kunihiko Hayashi Signed-off-by: David S. Miller --- drivers/net/phy/phy_device.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 18e92c19c5ab..26c41ede54a4 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -308,11 +308,8 @@ static int mdio_bus_phy_restore(struct device *dev) if (ret < 0) return ret; - /* The PHY needs to renegotiate. */ - phydev->link = 0; - phydev->state = PHY_UP; - - phy_start_machine(phydev); + if (phydev->attached_dev && phydev->adjust_link) + phy_start_machine(phydev); return 0; } -- cgit v1.2.3 From d81c5054a5d1d4999c7cdead7636b6cd4af83d36 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Tue, 18 Dec 2018 16:06:19 +0100 Subject: xen/netfront: tolerate frags with no data At least old Xen net backends seem to send frags with no real data sometimes. In case such a fragment happens to occur with the frag limit already reached the frontend will BUG currently even if this situation is easily recoverable. Modify the BUG_ON() condition accordingly. Tested-by: Dietmar Hahn Signed-off-by: Juergen Gross Signed-off-by: David S. Miller --- drivers/net/xen-netfront.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index f17f602e6171..5b97cc946d70 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -905,7 +905,7 @@ static RING_IDX xennet_fill_frags(struct netfront_queue *queue, if (skb_shinfo(skb)->nr_frags == MAX_SKB_FRAGS) { unsigned int pull_to = NETFRONT_SKB_CB(skb)->pull_to; - BUG_ON(pull_to <= skb_headlen(skb)); + BUG_ON(pull_to < skb_headlen(skb)); __pskb_pull_tail(skb, pull_to - skb_headlen(skb)); } if (unlikely(skb_shinfo(skb)->nr_frags >= MAX_SKB_FRAGS)) { -- cgit v1.2.3 From f7db2beb4c2c6cc8111f5ab90fc7363ca91107b6 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Tue, 18 Dec 2018 15:19:47 +0000 Subject: vxge: ensure data0 is initialized in when fetching firmware version information Currently variable data0 is not being initialized so a garbage value is being passed to vxge_hw_vpath_fw_api and this value is being written to the rts_access_steer_data0 register. There are other occurrances where data0 is being initialized to zero (e.g. in function vxge_hw_upgrade_read_version) so I think it makes sense to ensure data0 is initialized likewise to 0. Detected by CoverityScan, CID#140696 ("Uninitialized scalar variable") Fixes: 8424e00dfd52 ("vxge: serialize access to steering control register") Signed-off-by: Colin Ian King Signed-off-by: David S. Miller --- drivers/net/ethernet/neterion/vxge/vxge-config.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/neterion/vxge/vxge-config.c b/drivers/net/ethernet/neterion/vxge/vxge-config.c index 4c1fb7e57888..7cde387e5ec6 100644 --- a/drivers/net/ethernet/neterion/vxge/vxge-config.c +++ b/drivers/net/ethernet/neterion/vxge/vxge-config.c @@ -808,7 +808,7 @@ __vxge_hw_vpath_fw_ver_get(struct __vxge_hw_virtualpath *vpath, struct vxge_hw_device_date *fw_date = &hw_info->fw_date; struct vxge_hw_device_version *flash_version = &hw_info->flash_version; struct vxge_hw_device_date *flash_date = &hw_info->flash_date; - u64 data0, data1 = 0, steer_ctrl = 0; + u64 data0 = 0, data1 = 0, steer_ctrl = 0; enum vxge_hw_status status; status = vxge_hw_vpath_fw_api(vpath, -- cgit v1.2.3 From 78abe3d0dfad196959b1246003366e2610775ea6 Mon Sep 17 00:00:00 2001 From: Myungho Jung Date: Tue, 18 Dec 2018 09:02:25 -0800 Subject: net/smc: fix TCP fallback socket release clcsock can be released while kernel_accept() references it in TCP listen worker. Also, clcsock needs to wake up before released if TCP fallback is used and the clcsock is blocked by accept. Add a lock to safely release clcsock and call kernel_sock_shutdown() to wake up clcsock from accept in smc_release(). Reported-by: syzbot+0bf2e01269f1274b4b03@syzkaller.appspotmail.com Reported-by: syzbot+e3132895630f957306bc@syzkaller.appspotmail.com Signed-off-by: Myungho Jung Signed-off-by: David S. Miller --- net/smc/af_smc.c | 14 ++++++++++++-- net/smc/smc.h | 4 ++++ 2 files changed, 16 insertions(+), 2 deletions(-) diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 5fbaf1901571..82cb0e5634bc 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -147,8 +147,14 @@ static int smc_release(struct socket *sock) sk->sk_shutdown |= SHUTDOWN_MASK; } if (smc->clcsock) { + if (smc->use_fallback && sk->sk_state == SMC_LISTEN) { + /* wake up clcsock accept */ + rc = kernel_sock_shutdown(smc->clcsock, SHUT_RDWR); + } + mutex_lock(&smc->clcsock_release_lock); sock_release(smc->clcsock); smc->clcsock = NULL; + mutex_unlock(&smc->clcsock_release_lock); } if (smc->use_fallback) { if (sk->sk_state != SMC_LISTEN && sk->sk_state != SMC_INIT) @@ -205,6 +211,7 @@ static struct sock *smc_sock_alloc(struct net *net, struct socket *sock, spin_lock_init(&smc->conn.send_lock); sk->sk_prot->hash(sk); sk_refcnt_debug_inc(sk); + mutex_init(&smc->clcsock_release_lock); return sk; } @@ -821,7 +828,7 @@ static int smc_clcsock_accept(struct smc_sock *lsmc, struct smc_sock **new_smc) struct socket *new_clcsock = NULL; struct sock *lsk = &lsmc->sk; struct sock *new_sk; - int rc; + int rc = -EINVAL; release_sock(lsk); new_sk = smc_sock_alloc(sock_net(lsk), NULL, lsk->sk_protocol); @@ -834,7 +841,10 @@ static int smc_clcsock_accept(struct smc_sock *lsmc, struct smc_sock **new_smc) } *new_smc = smc_sk(new_sk); - rc = kernel_accept(lsmc->clcsock, &new_clcsock, 0); + mutex_lock(&lsmc->clcsock_release_lock); + if (lsmc->clcsock) + rc = kernel_accept(lsmc->clcsock, &new_clcsock, 0); + mutex_unlock(&lsmc->clcsock_release_lock); lock_sock(lsk); if (rc < 0) lsk->sk_err = -rc; diff --git a/net/smc/smc.h b/net/smc/smc.h index 08786ace6010..5721416d0605 100644 --- a/net/smc/smc.h +++ b/net/smc/smc.h @@ -219,6 +219,10 @@ struct smc_sock { /* smc sock container */ * started, waiting for unsent * data to be sent */ + struct mutex clcsock_release_lock; + /* protects clcsock of a listen + * socket + * */ }; static inline struct smc_sock *smc_sk(const struct sock *sk) -- cgit v1.2.3 From d350a0f431189517b1af0dbbb605c273231a8966 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Sat, 15 Dec 2018 11:03:22 +0200 Subject: nl80211: fix memory leak if validate_pae_over_nl80211() fails If validate_pae_over_nl80211() were to fail in nl80211_crypto_settings(), we might leak the 'connkeys' allocation. Fix this. Fixes: 64bf3d4bc2b0 ("nl80211: Add CONTROL_PORT_OVER_NL80211 attribute") Signed-off-by: Johannes Berg --- net/wireless/nl80211.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 8d763725498c..2317727d6413 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -8930,8 +8930,10 @@ static int nl80211_join_ibss(struct sk_buff *skb, struct genl_info *info) if (info->attrs[NL80211_ATTR_CONTROL_PORT_OVER_NL80211]) { int r = validate_pae_over_nl80211(rdev, info); - if (r < 0) + if (r < 0) { + kzfree(connkeys); return r; + } ibss.control_port_over_nl80211 = true; } -- cgit v1.2.3 From 34b1e0e9efe101822e83cc62d22443ed3867ae7a Mon Sep 17 00:00:00 2001 From: Sara Sharon Date: Sat, 15 Dec 2018 11:03:06 +0200 Subject: mac80211: free skb fraglist before freeing the skb mac80211 uses the frag list to build AMSDU. When freeing the skb, it may not be really freed, since someone is still holding a reference to it. In that case, when TCP skb is being retransmitted, the pointer to the frag list is being reused, while the data in there is no longer valid. Since we will never get frag list from the network stack, as mac80211 doesn't advertise the capability, we can safely free and nullify it before releasing the SKB. Signed-off-by: Sara Sharon Signed-off-by: Luca Coelho Signed-off-by: Johannes Berg --- net/mac80211/status.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/net/mac80211/status.c b/net/mac80211/status.c index a794ca729000..3f0b96e1e02f 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -556,6 +556,11 @@ static void ieee80211_report_used_skb(struct ieee80211_local *local, } ieee80211_led_tx(local); + + if (skb_has_frag_list(skb)) { + kfree_skb_list(skb_shinfo(skb)->frag_list); + skb_shinfo(skb)->frag_list = NULL; + } } /* -- cgit v1.2.3 From 53884577fbcef33a7d15ad664e664a3dabe35171 Mon Sep 17 00:00:00 2001 From: Rakesh Pillai Date: Fri, 14 Dec 2018 12:17:46 +0200 Subject: ath10k: skip sending quiet mode cmd for WCN3990 HL2.0 firmware does not support setting quiet mode. If the host driver sends the quiet mode setting command to the HL2.0 firmware, it crashes with the below signature. fatal error received: err_qdi.c:456:EX:wlan_process:1:WLAN RT:207a:PC=b001b4f0 The quiet mode command support is exposed by the firmware via thermal throttle wmi service. Enable ath10k thermal support if thermal throttle wmi service bit is set. 10.x firmware versions support this feature by default, but unfortunately do not advertise the support via service flags, hence have to manually set the service flag in ath10k_core_compat_services(). Tested on QCA988X with 10.2.4.70.9-2. Also tested on WCN3990. Co-developed-by: Govind Singh Co-developed-by: Kalle Valo Signed-off-by: Rakesh Pillai Signed-off-by: Govind Singh Signed-off-by: Kalle Valo --- drivers/net/wireless/ath/ath10k/core.c | 28 ++++++++++++++++++++++++++++ drivers/net/wireless/ath/ath10k/debug.c | 5 +++-- drivers/net/wireless/ath/ath10k/thermal.c | 9 +++++++++ drivers/net/wireless/ath/ath10k/wmi-tlv.h | 3 +++ drivers/net/wireless/ath/ath10k/wmi.h | 1 + 5 files changed, 44 insertions(+), 2 deletions(-) diff --git a/drivers/net/wireless/ath/ath10k/core.c b/drivers/net/wireless/ath/ath10k/core.c index da607febfd82..d210b0ed59be 100644 --- a/drivers/net/wireless/ath/ath10k/core.c +++ b/drivers/net/wireless/ath/ath10k/core.c @@ -2418,6 +2418,28 @@ static int ath10k_core_reset_rx_filter(struct ath10k *ar) return 0; } +static int ath10k_core_compat_services(struct ath10k *ar) +{ + struct ath10k_fw_file *fw_file = &ar->normal_mode_fw.fw_file; + + /* all 10.x firmware versions support thermal throttling but don't + * advertise the support via service flags so we have to hardcode + * it here + */ + switch (fw_file->wmi_op_version) { + case ATH10K_FW_WMI_OP_VERSION_10_1: + case ATH10K_FW_WMI_OP_VERSION_10_2: + case ATH10K_FW_WMI_OP_VERSION_10_2_4: + case ATH10K_FW_WMI_OP_VERSION_10_4: + set_bit(WMI_SERVICE_THERM_THROT, ar->wmi.svc_map); + break; + default: + break; + } + + return 0; +} + int ath10k_core_start(struct ath10k *ar, enum ath10k_firmware_mode mode, const struct ath10k_fw_components *fw) { @@ -2617,6 +2639,12 @@ int ath10k_core_start(struct ath10k *ar, enum ath10k_firmware_mode mode, goto err_hif_stop; } + status = ath10k_core_compat_services(ar); + if (status) { + ath10k_err(ar, "compat services failed: %d\n", status); + goto err_hif_stop; + } + /* Some firmware revisions do not properly set up hardware rx filter * registers. * diff --git a/drivers/net/wireless/ath/ath10k/debug.c b/drivers/net/wireless/ath/ath10k/debug.c index 15964b374f68..02988fc378a1 100644 --- a/drivers/net/wireless/ath/ath10k/debug.c +++ b/drivers/net/wireless/ath/ath10k/debug.c @@ -2578,8 +2578,9 @@ int ath10k_debug_register(struct ath10k *ar) debugfs_create_file("pktlog_filter", 0644, ar->debug.debugfs_phy, ar, &fops_pktlog_filter); - debugfs_create_file("quiet_period", 0644, ar->debug.debugfs_phy, ar, - &fops_quiet_period); + if (test_bit(WMI_SERVICE_THERM_THROT, ar->wmi.svc_map)) + debugfs_create_file("quiet_period", 0644, ar->debug.debugfs_phy, ar, + &fops_quiet_period); debugfs_create_file("tpc_stats", 0400, ar->debug.debugfs_phy, ar, &fops_tpc_stats); diff --git a/drivers/net/wireless/ath/ath10k/thermal.c b/drivers/net/wireless/ath/ath10k/thermal.c index aa8978a8d751..fe35edcd3ec8 100644 --- a/drivers/net/wireless/ath/ath10k/thermal.c +++ b/drivers/net/wireless/ath/ath10k/thermal.c @@ -140,6 +140,9 @@ void ath10k_thermal_set_throttling(struct ath10k *ar) lockdep_assert_held(&ar->conf_mutex); + if (!test_bit(WMI_SERVICE_THERM_THROT, ar->wmi.svc_map)) + return; + if (!ar->wmi.ops->gen_pdev_set_quiet_mode) return; @@ -165,6 +168,9 @@ int ath10k_thermal_register(struct ath10k *ar) struct device *hwmon_dev; int ret; + if (!test_bit(WMI_SERVICE_THERM_THROT, ar->wmi.svc_map)) + return 0; + cdev = thermal_cooling_device_register("ath10k_thermal", ar, &ath10k_thermal_ops); @@ -216,6 +222,9 @@ err_cooling_destroy: void ath10k_thermal_unregister(struct ath10k *ar) { + if (!test_bit(WMI_SERVICE_THERM_THROT, ar->wmi.svc_map)) + return; + sysfs_remove_link(&ar->dev->kobj, "cooling_device"); thermal_cooling_device_unregister(ar->thermal.cdev); } diff --git a/drivers/net/wireless/ath/ath10k/wmi-tlv.h b/drivers/net/wireless/ath/ath10k/wmi-tlv.h index 92c25f51bf86..c2cb413392ee 100644 --- a/drivers/net/wireless/ath/ath10k/wmi-tlv.h +++ b/drivers/net/wireless/ath/ath10k/wmi-tlv.h @@ -1564,6 +1564,9 @@ wmi_tlv_svc_map_ext(const __le32 *in, unsigned long *out, size_t len) SVCMAP(WMI_TLV_SERVICE_SPOOF_MAC_SUPPORT, WMI_SERVICE_SPOOF_MAC_SUPPORT, WMI_TLV_MAX_SERVICE); + SVCMAP(WMI_TLV_SERVICE_THERM_THROT, + WMI_SERVICE_THERM_THROT, + WMI_TLV_MAX_SERVICE); } #undef SVCMAP diff --git a/drivers/net/wireless/ath/ath10k/wmi.h b/drivers/net/wireless/ath/ath10k/wmi.h index f7badd079051..c5a343c93013 100644 --- a/drivers/net/wireless/ath/ath10k/wmi.h +++ b/drivers/net/wireless/ath/ath10k/wmi.h @@ -205,6 +205,7 @@ enum wmi_service { WMI_SERVICE_SPOOF_MAC_SUPPORT, WMI_SERVICE_TX_DATA_ACK_RSSI, WMI_SERVICE_VDEV_DIFFERENT_BEACON_INTERVAL_SUPPORT, + WMI_SERVICE_THERM_THROT, /* keep last */ WMI_SERVICE_MAX, -- cgit v1.2.3 From ef7cfd00b2caf6edeb7f169682b64be2d0a798cf Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Tue, 18 Dec 2018 14:25:41 +0900 Subject: kbuild: fix false positive warning/error about missing libelf For the same reason as commit 25896d073d8a ("x86/build: Fix compiler support check for CONFIG_RETPOLINE"), you cannot put this $(error ...) into the parse stage of the top Makefile. Perhaps I'd propose a more sophisticated solution later, but this is the best I can do for now. Link: https://lkml.org/lkml/2017/12/25/211 Reported-by: Paul Gortmaker Reported-by: Bernd Edlinger Reported-by: Qian Cai Cc: Josh Poimboeuf Signed-off-by: Masahiro Yamada Tested-by: Qian Cai --- Makefile | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/Makefile b/Makefile index 2f36db897895..7336f7098129 100644 --- a/Makefile +++ b/Makefile @@ -962,11 +962,6 @@ ifdef CONFIG_STACK_VALIDATION ifeq ($(has_libelf),1) objtool_target := tools/objtool FORCE else - ifdef CONFIG_UNWINDER_ORC - $(error "Cannot generate ORC metadata for CONFIG_UNWINDER_ORC=y, please install libelf-dev, libelf-devel or elfutils-libelf-devel") - else - $(warning "Cannot use CONFIG_STACK_VALIDATION=y, please install libelf-dev, libelf-devel or elfutils-libelf-devel") - endif SKIP_STACK_VALIDATION := 1 export SKIP_STACK_VALIDATION endif @@ -1125,6 +1120,14 @@ uapi-asm-generic: PHONY += prepare-objtool prepare-objtool: $(objtool_target) +ifeq ($(SKIP_STACK_VALIDATION),1) +ifdef CONFIG_UNWINDER_ORC + @echo "error: Cannot generate ORC metadata for CONFIG_UNWINDER_ORC=y, please install libelf-dev, libelf-devel or elfutils-libelf-devel" >&2 + @false +else + @echo "warning: Cannot use CONFIG_STACK_VALIDATION=y, please install libelf-dev, libelf-devel or elfutils-libelf-devel" >&2 +endif +endif # Generate some files # --------------------------------------------------------------------------- -- cgit v1.2.3 From bed1369f51901b17108a4bb4f7210aab183bea42 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Mon, 3 Dec 2018 12:53:51 +0100 Subject: m68k: Fix memblock-related crashes When running the kernel in Fast RAM on Atari: Ignoring memory chunk at 0x0:0xe00000 before the first chunk ... Unable to handle kernel NULL pointer dereference at virtual address (ptrval) Oops: 00000000 Modules linked in: PC: [<0069dbac>] free_all_bootmem+0x12c/0x186 SR: 2714 SP: (ptrval) a2: 005e3314 d0: 00000000 d1: 0000000a d2: 00000e00 d3: 00000000 d4: 005e1fc0 d5: 0000001a a0: 01000000 a1: 00000000 Process swapper (pid: 0, task=(ptrval)) Frame format=7 eff addr=00000736 ssw=0505 faddr=00000736 wb 1 stat/addr/data: 0000 00000000 00000000 wb 2 stat/addr/data: 0000 00000000 00000000 wb 3 stat/addr/data: 0000 00000736 00000000 push data: 00000000 00000000 00000000 00000000 Stack from 005e1f84: 00000000 0000000a 027d3260 006b5006 00000000 00000000 00000000 00000000 0004f062 0003a220 0069e272 005e1ff8 0000054c 00000000 00e00000 00000000 00000001 00693cd8 027d3260 0004f062 0003a220 00691be6 00000000 00000000 00000000 00000000 00000000 00000000 006b5006 00000000 00690872 Call Trace: [<0004f062>] printk+0x0/0x18 [<0003a220>] parse_args+0x0/0x2d4 [<0069e272>] memblock_virt_alloc_try_nid+0x0/0xa4 [<00693cd8>] mem_init+0xa/0x5c [<0004f062>] printk+0x0/0x18 [<0003a220>] parse_args+0x0/0x2d4 [<00691be6>] start_kernel+0x1ca/0x462 [<00690872>] _sinittext+0x872/0x11f8 Code: 7a1a eaae 2270 6db0 0061 ef14 2f01 2f03 <96a9> 0736 2203 e589 d681 e78b d6a9 0732 2f03 2f40 0034 4eb9 0069 b8d0 260e 4fef Disabling lock debugging due to kernel taint Kernel panic - not syncing: Attempted to kill the idle task! As the kernel must run in the memory chunk with the lowest address, ST-RAM is ignored, and removed from the m68k_memory[] array. However, it is not removed from memblock, causing a crash later. More investigation shows that there are 3 places where memory chunks are ignored, all after the calls to memblock_add() in m68k_parse_bootinfo(), and thus causing crashes: 1. On classic m68k CPUs with a MMU, paging_init() ignores all memory chunks below the first chunk, cfr. above, 2. On Amigas equipped with a Zorro III bus, config_amiga() ignores all Zorro II memory, 3. If CONFIG_SINGLE_MEMORY_CHUNK=y, m68k_parse_bootinfo() ignores all but the first memory chunk. Fix this by moving the calls to memblock_add() from m68k_parse_bootinfo() to paging_init(), after all ignored memory chunks have been removed from m68k_memory[]. Reported-by: Andreas Schwab Fixes: 1008a11590b966b4 ("m68k: switch to MEMBLOCK + NO_BOOTMEM") Signed-off-by: Geert Uytterhoeven --- arch/m68k/kernel/setup_mm.c | 2 -- arch/m68k/mm/motorola.c | 2 ++ 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/m68k/kernel/setup_mm.c b/arch/m68k/kernel/setup_mm.c index 5d3596c180f9..de44899c0e61 100644 --- a/arch/m68k/kernel/setup_mm.c +++ b/arch/m68k/kernel/setup_mm.c @@ -165,8 +165,6 @@ static void __init m68k_parse_bootinfo(const struct bi_record *record) be32_to_cpu(m->addr); m68k_memory[m68k_num_memory].size = be32_to_cpu(m->size); - memblock_add(m68k_memory[m68k_num_memory].addr, - m68k_memory[m68k_num_memory].size); m68k_num_memory++; } else pr_warn("%s: too many memory chunks\n", diff --git a/arch/m68k/mm/motorola.c b/arch/m68k/mm/motorola.c index 4e17ecb5928a..2eb2b31fb16a 100644 --- a/arch/m68k/mm/motorola.c +++ b/arch/m68k/mm/motorola.c @@ -228,6 +228,7 @@ void __init paging_init(void) min_addr = m68k_memory[0].addr; max_addr = min_addr + m68k_memory[0].size; + memblock_add(m68k_memory[0].addr, m68k_memory[0].size); for (i = 1; i < m68k_num_memory;) { if (m68k_memory[i].addr < min_addr) { printk("Ignoring memory chunk at 0x%lx:0x%lx before the first chunk\n", @@ -238,6 +239,7 @@ void __init paging_init(void) (m68k_num_memory - i) * sizeof(struct m68k_mem_info)); continue; } + memblock_add(m68k_memory[i].addr, m68k_memory[i].size); addr = m68k_memory[i].addr + m68k_memory[i].size; if (addr > max_addr) max_addr = addr; -- cgit v1.2.3 From ea010070d0a7497253d5a6f919f6dd107450b31a Mon Sep 17 00:00:00 2001 From: shamir rabinovitch Date: Sun, 16 Dec 2018 09:01:08 +0200 Subject: net/rds: fix warn in rds_message_alloc_sgs redundant copy_from_user in rds_sendmsg system call expose rds to issue where rds_rdma_extra_size walk the rds iovec and and calculate the number pf pages (sgs) it need to add to the tail of rds message and later rds_cmsg_rdma_args copy the rds iovec again and re calculate the same number and get different result causing WARN_ON in rds_message_alloc_sgs. fix this by doing the copy_from_user only once per rds_sendmsg system call. When issue occur the below dump is seen: WARNING: CPU: 0 PID: 19789 at net/rds/message.c:316 rds_message_alloc_sgs+0x10c/0x160 net/rds/message.c:316 Kernel panic - not syncing: panic_on_warn set ... CPU: 0 PID: 19789 Comm: syz-executor827 Not tainted 4.19.0-next-20181030+ #101 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+0x244/0x39d lib/dump_stack.c:113 panic+0x2ad/0x55c kernel/panic.c:188 __warn.cold.8+0x20/0x45 kernel/panic.c:540 report_bug+0x254/0x2d0 lib/bug.c:186 fixup_bug arch/x86/kernel/traps.c:178 [inline] do_error_trap+0x11b/0x200 arch/x86/kernel/traps.c:271 do_invalid_op+0x36/0x40 arch/x86/kernel/traps.c:290 invalid_op+0x14/0x20 arch/x86/entry/entry_64.S:969 RIP: 0010:rds_message_alloc_sgs+0x10c/0x160 net/rds/message.c:316 Code: c0 74 04 3c 03 7e 6c 44 01 ab 78 01 00 00 e8 2b 9e 35 fa 4c 89 e0 48 83 c4 08 5b 41 5c 41 5d 41 5e 41 5f 5d c3 e8 14 9e 35 fa <0f> 0b 31 ff 44 89 ee e8 18 9f 35 fa 45 85 ed 75 1b e8 fe 9d 35 fa RSP: 0018:ffff8801c51b7460 EFLAGS: 00010293 RAX: ffff8801bc412080 RBX: ffff8801d7bf4040 RCX: ffffffff8749c9e6 RDX: 0000000000000000 RSI: ffffffff8749ca5c RDI: 0000000000000004 RBP: ffff8801c51b7490 R08: ffff8801bc412080 R09: ffffed003b5c5b67 R10: ffffed003b5c5b67 R11: ffff8801dae2db3b R12: 0000000000000000 R13: 000000000007165c R14: 000000000007165c R15: 0000000000000005 rds_cmsg_rdma_args+0x82d/0x1510 net/rds/rdma.c:623 rds_cmsg_send net/rds/send.c:971 [inline] rds_sendmsg+0x19a2/0x3180 net/rds/send.c:1273 sock_sendmsg_nosec net/socket.c:622 [inline] sock_sendmsg+0xd5/0x120 net/socket.c:632 ___sys_sendmsg+0x7fd/0x930 net/socket.c:2117 __sys_sendmsg+0x11d/0x280 net/socket.c:2155 __do_sys_sendmsg net/socket.c:2164 [inline] __se_sys_sendmsg net/socket.c:2162 [inline] __x64_sys_sendmsg+0x78/0xb0 net/socket.c:2162 do_syscall_64+0x1b9/0x820 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x44a859 Code: e8 dc e6 ff ff 48 83 c4 18 c3 0f 1f 80 00 00 00 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 6b cb fb ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007f1d4710ada8 EFLAGS: 00000297 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 00000000006dcc28 RCX: 000000000044a859 RDX: 0000000000000000 RSI: 0000000020001600 RDI: 0000000000000003 RBP: 00000000006dcc20 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000297 R12: 00000000006dcc2c R13: 646e732f7665642f R14: 00007f1d4710b9c0 R15: 00000000006dcd2c Kernel Offset: disabled Rebooting in 86400 seconds.. Reported-by: syzbot+26de17458aeda9d305d8@syzkaller.appspotmail.com Acked-by: Santosh Shilimkar Signed-off-by: shamir rabinovitch Signed-off-by: David S. Miller --- net/rds/rdma.c | 63 +++++++++++++++++++++++++++++----------------------------- net/rds/rds.h | 20 +++++++++++++++---- net/rds/send.c | 50 +++++++++++++++++++++++++++++++++++++++------- 3 files changed, 91 insertions(+), 42 deletions(-) diff --git a/net/rds/rdma.c b/net/rds/rdma.c index 98237feb607a..e1965d9cbcf8 100644 --- a/net/rds/rdma.c +++ b/net/rds/rdma.c @@ -517,9 +517,10 @@ static int rds_rdma_pages(struct rds_iovec iov[], int nr_iovecs) return tot_pages; } -int rds_rdma_extra_size(struct rds_rdma_args *args) +int rds_rdma_extra_size(struct rds_rdma_args *args, + struct rds_iov_vector *iov) { - struct rds_iovec vec; + struct rds_iovec *vec; struct rds_iovec __user *local_vec; int tot_pages = 0; unsigned int nr_pages; @@ -530,13 +531,23 @@ int rds_rdma_extra_size(struct rds_rdma_args *args) if (args->nr_local == 0) return -EINVAL; + iov->iov = kcalloc(args->nr_local, + sizeof(struct rds_iovec), + GFP_KERNEL); + if (!iov->iov) + return -ENOMEM; + + vec = &iov->iov[0]; + + if (copy_from_user(vec, local_vec, args->nr_local * + sizeof(struct rds_iovec))) + return -EFAULT; + iov->len = args->nr_local; + /* figure out the number of pages in the vector */ - for (i = 0; i < args->nr_local; i++) { - if (copy_from_user(&vec, &local_vec[i], - sizeof(struct rds_iovec))) - return -EFAULT; + for (i = 0; i < args->nr_local; i++, vec++) { - nr_pages = rds_pages_in_vec(&vec); + nr_pages = rds_pages_in_vec(vec); if (nr_pages == 0) return -EINVAL; @@ -558,15 +569,15 @@ int rds_rdma_extra_size(struct rds_rdma_args *args) * Extract all arguments and set up the rdma_op */ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm, - struct cmsghdr *cmsg) + struct cmsghdr *cmsg, + struct rds_iov_vector *vec) { struct rds_rdma_args *args; struct rm_rdma_op *op = &rm->rdma; int nr_pages; unsigned int nr_bytes; struct page **pages = NULL; - struct rds_iovec iovstack[UIO_FASTIOV], *iovs = iovstack; - int iov_size; + struct rds_iovec *iovs; unsigned int i, j; int ret = 0; @@ -586,31 +597,23 @@ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm, goto out_ret; } - /* Check whether to allocate the iovec area */ - iov_size = args->nr_local * sizeof(struct rds_iovec); - if (args->nr_local > UIO_FASTIOV) { - iovs = sock_kmalloc(rds_rs_to_sk(rs), iov_size, GFP_KERNEL); - if (!iovs) { - ret = -ENOMEM; - goto out_ret; - } + if (vec->len != args->nr_local) { + ret = -EINVAL; + goto out_ret; } - if (copy_from_user(iovs, (struct rds_iovec __user *)(unsigned long) args->local_vec_addr, iov_size)) { - ret = -EFAULT; - goto out; - } + iovs = vec->iov; nr_pages = rds_rdma_pages(iovs, args->nr_local); if (nr_pages < 0) { ret = -EINVAL; - goto out; + goto out_ret; } pages = kcalloc(nr_pages, sizeof(struct page *), GFP_KERNEL); if (!pages) { ret = -ENOMEM; - goto out; + goto out_ret; } op->op_write = !!(args->flags & RDS_RDMA_READWRITE); @@ -623,7 +626,7 @@ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm, op->op_sg = rds_message_alloc_sgs(rm, nr_pages); if (!op->op_sg) { ret = -ENOMEM; - goto out; + goto out_pages; } if (op->op_notify || op->op_recverr) { @@ -635,7 +638,7 @@ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm, op->op_notifier = kmalloc(sizeof(struct rds_notifier), GFP_KERNEL); if (!op->op_notifier) { ret = -ENOMEM; - goto out; + goto out_pages; } op->op_notifier->n_user_token = args->user_token; op->op_notifier->n_status = RDS_RDMA_SUCCESS; @@ -681,7 +684,7 @@ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm, */ ret = rds_pin_pages(iov->addr, nr, pages, !op->op_write); if (ret < 0) - goto out; + goto out_pages; else ret = 0; @@ -714,13 +717,11 @@ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm, nr_bytes, (unsigned int) args->remote_vec.bytes); ret = -EINVAL; - goto out; + goto out_pages; } op->op_bytes = nr_bytes; -out: - if (iovs != iovstack) - sock_kfree_s(rds_rs_to_sk(rs), iovs, iov_size); +out_pages: kfree(pages); out_ret: if (ret) diff --git a/net/rds/rds.h b/net/rds/rds.h index 6bfaf05b63b2..4d2523100093 100644 --- a/net/rds/rds.h +++ b/net/rds/rds.h @@ -386,6 +386,18 @@ static inline void rds_message_zcopy_queue_init(struct rds_msg_zcopy_queue *q) INIT_LIST_HEAD(&q->zcookie_head); } +struct rds_iov_vector { + struct rds_iovec *iov; + int len; +}; + +struct rds_iov_vector_arr { + struct rds_iov_vector *vec; + int len; + int indx; + int incr; +}; + struct rds_message { refcount_t m_refcount; struct list_head m_sock_item; @@ -904,13 +916,13 @@ int rds_get_mr(struct rds_sock *rs, char __user *optval, int optlen); int rds_get_mr_for_dest(struct rds_sock *rs, char __user *optval, int optlen); int rds_free_mr(struct rds_sock *rs, char __user *optval, int optlen); void rds_rdma_drop_keys(struct rds_sock *rs); -int rds_rdma_extra_size(struct rds_rdma_args *args); -int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm, - struct cmsghdr *cmsg); +int rds_rdma_extra_size(struct rds_rdma_args *args, + struct rds_iov_vector *iov); int rds_cmsg_rdma_dest(struct rds_sock *rs, struct rds_message *rm, struct cmsghdr *cmsg); int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm, - struct cmsghdr *cmsg); + struct cmsghdr *cmsg, + struct rds_iov_vector *vec); int rds_cmsg_rdma_map(struct rds_sock *rs, struct rds_message *rm, struct cmsghdr *cmsg); void rds_rdma_free_op(struct rm_rdma_op *ro); diff --git a/net/rds/send.c b/net/rds/send.c index fe785ee819dd..ec2267cbf85f 100644 --- a/net/rds/send.c +++ b/net/rds/send.c @@ -876,13 +876,15 @@ out: * rds_message is getting to be quite complicated, and we'd like to allocate * it all in one go. This figures out how big it needs to be up front. */ -static int rds_rm_size(struct msghdr *msg, int num_sgs) +static int rds_rm_size(struct msghdr *msg, int num_sgs, + struct rds_iov_vector_arr *vct) { struct cmsghdr *cmsg; int size = 0; int cmsg_groups = 0; int retval; bool zcopy_cookie = false; + struct rds_iov_vector *iov, *tmp_iov; for_each_cmsghdr(cmsg, msg) { if (!CMSG_OK(msg, cmsg)) @@ -893,8 +895,24 @@ static int rds_rm_size(struct msghdr *msg, int num_sgs) switch (cmsg->cmsg_type) { case RDS_CMSG_RDMA_ARGS: + if (vct->indx >= vct->len) { + vct->len += vct->incr; + tmp_iov = + krealloc(vct->vec, + vct->len * + sizeof(struct rds_iov_vector), + GFP_KERNEL); + if (!tmp_iov) { + vct->len -= vct->incr; + return -ENOMEM; + } + vct->vec = tmp_iov; + } + iov = &vct->vec[vct->indx]; + memset(iov, 0, sizeof(struct rds_iov_vector)); + vct->indx++; cmsg_groups |= 1; - retval = rds_rdma_extra_size(CMSG_DATA(cmsg)); + retval = rds_rdma_extra_size(CMSG_DATA(cmsg), iov); if (retval < 0) return retval; size += retval; @@ -951,10 +969,11 @@ static int rds_cmsg_zcopy(struct rds_sock *rs, struct rds_message *rm, } static int rds_cmsg_send(struct rds_sock *rs, struct rds_message *rm, - struct msghdr *msg, int *allocated_mr) + struct msghdr *msg, int *allocated_mr, + struct rds_iov_vector_arr *vct) { struct cmsghdr *cmsg; - int ret = 0; + int ret = 0, ind = 0; for_each_cmsghdr(cmsg, msg) { if (!CMSG_OK(msg, cmsg)) @@ -968,7 +987,10 @@ static int rds_cmsg_send(struct rds_sock *rs, struct rds_message *rm, */ switch (cmsg->cmsg_type) { case RDS_CMSG_RDMA_ARGS: - ret = rds_cmsg_rdma_args(rs, rm, cmsg); + if (ind >= vct->indx) + return -ENOMEM; + ret = rds_cmsg_rdma_args(rs, rm, cmsg, &vct->vec[ind]); + ind++; break; case RDS_CMSG_RDMA_DEST: @@ -1084,6 +1106,11 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len) sock_flag(rds_rs_to_sk(rs), SOCK_ZEROCOPY)); int num_sgs = ceil(payload_len, PAGE_SIZE); int namelen; + struct rds_iov_vector_arr vct = {0}; + int ind; + + /* expect 1 RDMA CMSG per rds_sendmsg. can still grow if more needed. */ + vct.incr = 1; /* Mirror Linux UDP mirror of BSD error message compatibility */ /* XXX: Perhaps MSG_MORE someday */ @@ -1220,7 +1247,7 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len) num_sgs = iov_iter_npages(&msg->msg_iter, INT_MAX); } /* size of rm including all sgs */ - ret = rds_rm_size(msg, num_sgs); + ret = rds_rm_size(msg, num_sgs, &vct); if (ret < 0) goto out; @@ -1270,7 +1297,7 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len) rm->m_conn_path = cpath; /* Parse any control messages the user may have included. */ - ret = rds_cmsg_send(rs, rm, msg, &allocated_mr); + ret = rds_cmsg_send(rs, rm, msg, &allocated_mr, &vct); if (ret) { /* Trigger connection so that its ready for the next retry */ if (ret == -EAGAIN) @@ -1348,9 +1375,18 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len) if (ret) goto out; rds_message_put(rm); + + for (ind = 0; ind < vct.indx; ind++) + kfree(vct.vec[ind].iov); + kfree(vct.vec); + return payload_len; out: + for (ind = 0; ind < vct.indx; ind++) + kfree(vct.vec[ind].iov); + kfree(vct.vec); + /* If the user included a RDMA_MAP cmsg, we allocated a MR on the fly. * If the sendmsg goes through, we keep the MR. If it fails with EAGAIN * or in any other way, we need to destroy the MR again */ -- cgit v1.2.3 From c75ab8a55ac1083c232e4407f52b0cadae6c1e0e Mon Sep 17 00:00:00 2001 From: shamir rabinovitch Date: Sun, 16 Dec 2018 09:01:09 +0200 Subject: net/rds: remove user triggered WARN_ON in rds_sendmsg per comment from Leon in rdma mailing list https://lkml.org/lkml/2018/10/31/312 : Please don't forget to remove user triggered WARN_ON. https://lwn.net/Articles/769365/ "Greg Kroah-Hartman raised the problem of core kernel API code that will use WARN_ON_ONCE() to complain about bad usage; that will not generate the desired result if WARN_ON_ONCE() is configured to crash the machine. He was told that the code should just call pr_warn() instead, and that the called function should return an error in such situations. It was generally agreed that any WARN_ON() or WARN_ON_ONCE() calls that can be triggered from user space need to be fixed." in addition harden rds_sendmsg to detect and overcome issues with invalid sg count and fail the sendmsg. Suggested-by: Leon Romanovsky Acked-by: Santosh Shilimkar Signed-off-by: shamir rabinovitch Signed-off-by: David S. Miller --- net/rds/message.c | 24 ++++++++++++++++++------ net/rds/rdma.c | 12 ++++-------- net/rds/rds.h | 3 ++- net/rds/send.c | 9 +++++---- 4 files changed, 29 insertions(+), 19 deletions(-) diff --git a/net/rds/message.c b/net/rds/message.c index 4b00b1152a5f..f139420ba1f6 100644 --- a/net/rds/message.c +++ b/net/rds/message.c @@ -308,16 +308,27 @@ out: /* * RDS ops use this to grab SG entries from the rm's sg pool. */ -struct scatterlist *rds_message_alloc_sgs(struct rds_message *rm, int nents) +struct scatterlist *rds_message_alloc_sgs(struct rds_message *rm, int nents, + int *ret) { struct scatterlist *sg_first = (struct scatterlist *) &rm[1]; struct scatterlist *sg_ret; - WARN_ON(rm->m_used_sgs + nents > rm->m_total_sgs); - WARN_ON(!nents); + if (WARN_ON(!ret)) + return NULL; - if (rm->m_used_sgs + nents > rm->m_total_sgs) + if (nents <= 0) { + pr_warn("rds: alloc sgs failed! nents <= 0\n"); + *ret = -EINVAL; return NULL; + } + + if (rm->m_used_sgs + nents > rm->m_total_sgs) { + pr_warn("rds: alloc sgs failed! total %d used %d nents %d\n", + rm->m_total_sgs, rm->m_used_sgs, nents); + *ret = -ENOMEM; + return NULL; + } sg_ret = &sg_first[rm->m_used_sgs]; sg_init_table(sg_ret, nents); @@ -332,6 +343,7 @@ struct rds_message *rds_message_map_pages(unsigned long *page_addrs, unsigned in unsigned int i; int num_sgs = ceil(total_len, PAGE_SIZE); int extra_bytes = num_sgs * sizeof(struct scatterlist); + int ret; rm = rds_message_alloc(extra_bytes, GFP_NOWAIT); if (!rm) @@ -340,10 +352,10 @@ struct rds_message *rds_message_map_pages(unsigned long *page_addrs, unsigned in set_bit(RDS_MSG_PAGEVEC, &rm->m_flags); rm->m_inc.i_hdr.h_len = cpu_to_be32(total_len); rm->data.op_nents = ceil(total_len, PAGE_SIZE); - rm->data.op_sg = rds_message_alloc_sgs(rm, num_sgs); + rm->data.op_sg = rds_message_alloc_sgs(rm, num_sgs, &ret); if (!rm->data.op_sg) { rds_message_put(rm); - return ERR_PTR(-ENOMEM); + return ERR_PTR(ret); } for (i = 0; i < rm->data.op_nents; ++i) { diff --git a/net/rds/rdma.c b/net/rds/rdma.c index e1965d9cbcf8..182ab8430594 100644 --- a/net/rds/rdma.c +++ b/net/rds/rdma.c @@ -623,11 +623,9 @@ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm, op->op_active = 1; op->op_recverr = rs->rs_recverr; WARN_ON(!nr_pages); - op->op_sg = rds_message_alloc_sgs(rm, nr_pages); - if (!op->op_sg) { - ret = -ENOMEM; + op->op_sg = rds_message_alloc_sgs(rm, nr_pages, &ret); + if (!op->op_sg) goto out_pages; - } if (op->op_notify || op->op_recverr) { /* We allocate an uninitialized notifier here, because @@ -839,11 +837,9 @@ int rds_cmsg_atomic(struct rds_sock *rs, struct rds_message *rm, rm->atomic.op_silent = !!(args->flags & RDS_RDMA_SILENT); rm->atomic.op_active = 1; rm->atomic.op_recverr = rs->rs_recverr; - rm->atomic.op_sg = rds_message_alloc_sgs(rm, 1); - if (!rm->atomic.op_sg) { - ret = -ENOMEM; + rm->atomic.op_sg = rds_message_alloc_sgs(rm, 1, &ret); + if (!rm->atomic.op_sg) goto err; - } /* verify 8 byte-aligned */ if (args->local_addr & 0x7) { diff --git a/net/rds/rds.h b/net/rds/rds.h index 4d2523100093..02ec4a3b2799 100644 --- a/net/rds/rds.h +++ b/net/rds/rds.h @@ -839,7 +839,8 @@ rds_conn_connecting(struct rds_connection *conn) /* message.c */ struct rds_message *rds_message_alloc(unsigned int nents, gfp_t gfp); -struct scatterlist *rds_message_alloc_sgs(struct rds_message *rm, int nents); +struct scatterlist *rds_message_alloc_sgs(struct rds_message *rm, int nents, + int *ret); int rds_message_copy_from_user(struct rds_message *rm, struct iov_iter *from, bool zcopy); struct rds_message *rds_message_map_pages(unsigned long *page_addrs, unsigned int total_len); diff --git a/net/rds/send.c b/net/rds/send.c index ec2267cbf85f..b39b30706210 100644 --- a/net/rds/send.c +++ b/net/rds/send.c @@ -886,6 +886,9 @@ static int rds_rm_size(struct msghdr *msg, int num_sgs, bool zcopy_cookie = false; struct rds_iov_vector *iov, *tmp_iov; + if (num_sgs < 0) + return -EINVAL; + for_each_cmsghdr(cmsg, msg) { if (!CMSG_OK(msg, cmsg)) return -EINVAL; @@ -1259,11 +1262,9 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len) /* Attach data to the rm */ if (payload_len) { - rm->data.op_sg = rds_message_alloc_sgs(rm, num_sgs); - if (!rm->data.op_sg) { - ret = -ENOMEM; + rm->data.op_sg = rds_message_alloc_sgs(rm, num_sgs, &ret); + if (!rm->data.op_sg) goto out; - } ret = rds_message_copy_from_user(rm, &msg->msg_iter, zcopy); if (ret) goto out; -- cgit v1.2.3 From 84404d5fd5858588bbf694b0300dbc6310d02737 Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Wed, 19 Dec 2018 13:46:50 -0500 Subject: bnxt_en: Fix ethtool self-test loopback. The current code has 2 problems. It assumes that the RX ring for the loopback packet is combined with the TX ring. This is not true if the ethtool channels are set to non-combined mode. The second problem is that it won't work on 57500 chips without adjusting the logic to get the proper completion ring (cpr) pointer. Fix both issues by locating the proper cpr pointer through the RX ring. Fixes: e44758b78ae8 ("bnxt_en: Use bnxt_cp_ring_info struct pointer as parameter for RX path.") Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index 6cc69a58478a..6b51f4de6017 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -2572,6 +2572,7 @@ static int bnxt_poll_loopback(struct bnxt *bp, struct bnxt_cp_ring_info *cpr, static int bnxt_run_loopback(struct bnxt *bp) { struct bnxt_tx_ring_info *txr = &bp->tx_ring[0]; + struct bnxt_rx_ring_info *rxr = &bp->rx_ring[0]; struct bnxt_cp_ring_info *cpr; int pkt_size, i = 0; struct sk_buff *skb; @@ -2579,7 +2580,9 @@ static int bnxt_run_loopback(struct bnxt *bp) u8 *data; int rc; - cpr = &txr->bnapi->cp_ring; + cpr = &rxr->bnapi->cp_ring; + if (bp->flags & BNXT_FLAG_CHIP_P5) + cpr = cpr->cp_ring_arr[BNXT_RX_HDL]; pkt_size = min(bp->dev->mtu + ETH_HLEN, bp->rx_copy_thresh); skb = netdev_alloc_skb(bp->dev, pkt_size); if (!skb) -- cgit v1.2.3 From fb24274546310872eeeaf3d1d53799d8414aa0f2 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Tue, 18 Dec 2018 21:17:44 -0800 Subject: ipv6: explicitly initialize udp6_addr in udp_sock_create6() syzbot reported the use of uninitialized udp6_addr::sin6_scope_id. We can just set ::sin6_scope_id to zero, as tunnels are unlikely to use an IPv6 address that needs a scope id and there is no interface to bind in this context. For net-next, it looks different as we have cfg->bind_ifindex there so we can probably call ipv6_iface_scope_id(). Same for ::sin6_flowinfo, tunnels don't use it. Fixes: 8024e02879dd ("udp: Add udp_sock_create for UDP tunnels to open listener socket") Reported-by: syzbot+c56449ed3652e6720f30@syzkaller.appspotmail.com Cc: Jon Maloy Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- net/ipv6/ip6_udp_tunnel.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/ipv6/ip6_udp_tunnel.c b/net/ipv6/ip6_udp_tunnel.c index b283f293ee4a..caad40d6e74d 100644 --- a/net/ipv6/ip6_udp_tunnel.c +++ b/net/ipv6/ip6_udp_tunnel.c @@ -15,7 +15,7 @@ int udp_sock_create6(struct net *net, struct udp_port_cfg *cfg, struct socket **sockp) { - struct sockaddr_in6 udp6_addr; + struct sockaddr_in6 udp6_addr = {}; int err; struct socket *sock = NULL; @@ -42,6 +42,7 @@ int udp_sock_create6(struct net *net, struct udp_port_cfg *cfg, goto error; if (cfg->peer_udp_port) { + memset(&udp6_addr, 0, sizeof(udp6_addr)); udp6_addr.sin6_family = AF_INET6; memcpy(&udp6_addr.sin6_addr, &cfg->peer_ip6, sizeof(udp6_addr.sin6_addr)); -- cgit v1.2.3 From bfc698254ba97b3e3e4ebbfae0ffa1f7e2fa0717 Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Sun, 2 Dec 2018 15:45:53 +0200 Subject: net/mlx5e: RX, Fix wrong early return in receive queue poll When the completion queue of the RQ is empty, do not immediately return. If left-over decompressed CQEs (from the previous cycle) were processed, need to go to the finalization part of the poll function. Bug exists only when CQE compression is turned ON. This solves the following issue: mlx5_core 0000:82:00.1: mlx5_eq_int:544:(pid 0): CQ error on CQN 0xc08, syndrome 0x1 mlx5_core 0000:82:00.1 p4p2: mlx5e_cq_error_event: cqn=0x000c08 event=0x04 Fixes: 4b7dfc992514 ("net/mlx5e: Early-return on empty completion queues") Signed-off-by: Tariq Toukan Reviewed-by: Eran Ben Elisha Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 624eed345b5d..0b5ef6d4e815 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -1190,7 +1190,7 @@ mpwrq_cqe_out: int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget) { struct mlx5e_rq *rq = container_of(cq, struct mlx5e_rq, cq); - struct mlx5e_xdpsq *xdpsq; + struct mlx5e_xdpsq *xdpsq = &rq->xdpsq; struct mlx5_cqe64 *cqe; int work_done = 0; @@ -1201,10 +1201,11 @@ int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget) work_done += mlx5e_decompress_cqes_cont(rq, cq, 0, budget); cqe = mlx5_cqwq_get_cqe(&cq->wq); - if (!cqe) + if (!cqe) { + if (unlikely(work_done)) + goto out; return 0; - - xdpsq = &rq->xdpsq; + } do { if (mlx5_get_cqe_format(cqe) == MLX5_COMPRESSED) { @@ -1219,6 +1220,7 @@ int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget) rq->handle_rx_cqe(rq, cqe); } while ((++work_done < budget) && (cqe = mlx5_cqwq_get_cqe(&cq->wq))); +out: if (xdpsq->doorbell) { mlx5e_xmit_xdp_doorbell(xdpsq); xdpsq->doorbell = false; -- cgit v1.2.3 From f0337889147c956721696553ffcc97212b0948fe Mon Sep 17 00:00:00 2001 From: Yuval Avnery Date: Thu, 13 Dec 2018 02:26:46 +0200 Subject: net/mlx5: Typo fix in del_sw_hw_rule Expression terminated with "," instead of ";", resulted in set_fte getting bad value for modify_enable_mask field. Fixes: bd5251dbf156 ("net/mlx5_core: Introduce flow steering destination of type counter") Signed-off-by: Yuval Avnery Reviewed-by: Daniel Jurgens Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 9d73eb955f75..08233cf44871 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -452,7 +452,7 @@ static void del_sw_hw_rule(struct fs_node *node) if ((fte->action.action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) && --fte->dests_size) { - modify_mask = BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_DESTINATION_LIST), + modify_mask = BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_DESTINATION_LIST); update_fte = true; } out: -- cgit v1.2.3 From 4765420439e758bfa4808392d18b0a4cb6f06065 Mon Sep 17 00:00:00 2001 From: Alaa Hleihel Date: Sun, 25 Nov 2018 11:46:09 +0200 Subject: net/mlx5e: Remove the false indication of software timestamping support mlx5 driver falsely advertises support of software timestamping. Fix it by removing the false indication. Fixes: ef9814deafd0 ("net/mlx5e: Add HW timestamping (TS) support") Signed-off-by: Alaa Hleihel Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c | 11 +++-------- 1 file changed, 3 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 25c1c4f96841..f480763dcd0d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -1190,11 +1190,6 @@ int mlx5e_ethtool_get_ts_info(struct mlx5e_priv *priv, struct ethtool_ts_info *info) { struct mlx5_core_dev *mdev = priv->mdev; - int ret; - - ret = ethtool_op_get_ts_info(priv->netdev, info); - if (ret) - return ret; info->phc_index = mlx5_clock_get_ptp_index(mdev); @@ -1202,9 +1197,9 @@ int mlx5e_ethtool_get_ts_info(struct mlx5e_priv *priv, info->phc_index == -1) return 0; - info->so_timestamping |= SOF_TIMESTAMPING_TX_HARDWARE | - SOF_TIMESTAMPING_RX_HARDWARE | - SOF_TIMESTAMPING_RAW_HARDWARE; + info->so_timestamping = SOF_TIMESTAMPING_TX_HARDWARE | + SOF_TIMESTAMPING_RX_HARDWARE | + SOF_TIMESTAMPING_RAW_HARDWARE; info->tx_types = BIT(HWTSTAMP_TX_OFF) | BIT(HWTSTAMP_TX_ON); -- cgit v1.2.3 From c5c08bed843c2b2c048c16d1296d7631d7c1620e Mon Sep 17 00:00:00 2001 From: Michael S. Tsirkin Date: Wed, 19 Dec 2018 18:21:51 -0500 Subject: virtio: fix test build after uio.h change Fixes: d38499530e5 ("fs: decouple READ and WRITE from the block layer ops") Signed-off-by: Michael S. Tsirkin --- tools/virtio/linux/kernel.h | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/tools/virtio/linux/kernel.h b/tools/virtio/linux/kernel.h index fb22bccfbc8a..7ef45a4a3cba 100644 --- a/tools/virtio/linux/kernel.h +++ b/tools/virtio/linux/kernel.h @@ -23,6 +23,10 @@ #define PAGE_MASK (~(PAGE_SIZE-1)) #define PAGE_ALIGN(x) ((x + PAGE_SIZE - 1) & PAGE_MASK) +/* generic data direction definitions */ +#define READ 0 +#define WRITE 1 + typedef unsigned long long phys_addr_t; typedef unsigned long long dma_addr_t; typedef size_t __kernel_size_t; -- cgit v1.2.3 From e0e587878f538c9e3400219b6c516b8199dc2042 Mon Sep 17 00:00:00 2001 From: Bryan Whitehead Date: Wed, 19 Dec 2018 16:55:15 -0500 Subject: lan743x: Remove MAC Reset from initialization The MAC Reset was noticed to erase important EEPROM settings. It is also unnecessary since a chip wide reset was done earlier in initialization, and that reset preserves EEPROM settings. There for this patch removes the unnecessary MAC specific reset. Signed-off-by: Bryan Whitehead Signed-off-by: David S. Miller --- drivers/net/ethernet/microchip/lan743x_main.c | 6 ------ 1 file changed, 6 deletions(-) diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c index 1ba8ea07dc4f..20c9377e99cb 100644 --- a/drivers/net/ethernet/microchip/lan743x_main.c +++ b/drivers/net/ethernet/microchip/lan743x_main.c @@ -802,14 +802,8 @@ static int lan743x_mac_init(struct lan743x_adapter *adapter) u32 mac_addr_hi = 0; u32 mac_addr_lo = 0; u32 data; - int ret; netdev = adapter->netdev; - lan743x_csr_write(adapter, MAC_CR, MAC_CR_RST_); - ret = lan743x_csr_wait_for_bit(adapter, MAC_CR, MAC_CR_RST_, - 0, 1000, 20000, 100); - if (ret) - return ret; /* setup auto duplex, and speed detection */ data = lan743x_csr_read(adapter, MAC_CR); -- cgit v1.2.3 From 8e1da73acded4751a93d4166458a7e640f37d26c Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Wed, 19 Dec 2018 23:23:00 +0100 Subject: gro_cell: add napi_disable in gro_cells_destroy Add napi_disable routine in gro_cells_destroy since starting from commit c42858eaf492 ("gro_cells: remove spinlock protecting receive queues") gro_cell_poll and gro_cells_destroy can run concurrently on napi_skbs list producing a kernel Oops if the tunnel interface is removed while gro_cell_poll is running. The following Oops has been triggered removing a vxlan device while the interface is receiving traffic [ 5628.948853] BUG: unable to handle kernel NULL pointer dereference at 0000000000000008 [ 5628.949981] PGD 0 P4D 0 [ 5628.950308] Oops: 0002 [#1] SMP PTI [ 5628.950748] CPU: 0 PID: 9 Comm: ksoftirqd/0 Not tainted 4.20.0-rc6+ #41 [ 5628.952940] RIP: 0010:gro_cell_poll+0x49/0x80 [ 5628.955615] RSP: 0018:ffffc9000004fdd8 EFLAGS: 00010202 [ 5628.956250] RAX: 0000000000000000 RBX: ffffe8ffffc08150 RCX: 0000000000000000 [ 5628.957102] RDX: 0000000000000000 RSI: ffff88802356bf00 RDI: ffffe8ffffc08150 [ 5628.957940] RBP: 0000000000000026 R08: 0000000000000000 R09: 0000000000000000 [ 5628.958803] R10: 0000000000000001 R11: 0000000000000000 R12: 0000000000000040 [ 5628.959661] R13: ffffe8ffffc08100 R14: 0000000000000000 R15: 0000000000000040 [ 5628.960682] FS: 0000000000000000(0000) GS:ffff88803ea00000(0000) knlGS:0000000000000000 [ 5628.961616] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 5628.962359] CR2: 0000000000000008 CR3: 000000000221c000 CR4: 00000000000006b0 [ 5628.963188] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 5628.964034] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 5628.964871] Call Trace: [ 5628.965179] net_rx_action+0xf0/0x380 [ 5628.965637] __do_softirq+0xc7/0x431 [ 5628.966510] run_ksoftirqd+0x24/0x30 [ 5628.966957] smpboot_thread_fn+0xc5/0x160 [ 5628.967436] kthread+0x113/0x130 [ 5628.968283] ret_from_fork+0x3a/0x50 [ 5628.968721] Modules linked in: [ 5628.969099] CR2: 0000000000000008 [ 5628.969510] ---[ end trace 9d9dedc7181661fe ]--- [ 5628.970073] RIP: 0010:gro_cell_poll+0x49/0x80 [ 5628.972965] RSP: 0018:ffffc9000004fdd8 EFLAGS: 00010202 [ 5628.973611] RAX: 0000000000000000 RBX: ffffe8ffffc08150 RCX: 0000000000000000 [ 5628.974504] RDX: 0000000000000000 RSI: ffff88802356bf00 RDI: ffffe8ffffc08150 [ 5628.975462] RBP: 0000000000000026 R08: 0000000000000000 R09: 0000000000000000 [ 5628.976413] R10: 0000000000000001 R11: 0000000000000000 R12: 0000000000000040 [ 5628.977375] R13: ffffe8ffffc08100 R14: 0000000000000000 R15: 0000000000000040 [ 5628.978296] FS: 0000000000000000(0000) GS:ffff88803ea00000(0000) knlGS:0000000000000000 [ 5628.979327] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 5628.980044] CR2: 0000000000000008 CR3: 000000000221c000 CR4: 00000000000006b0 [ 5628.980929] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 5628.981736] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 5628.982409] Kernel panic - not syncing: Fatal exception in interrupt [ 5628.983307] Kernel Offset: disabled Fixes: c42858eaf492 ("gro_cells: remove spinlock protecting receive queues") Signed-off-by: Lorenzo Bianconi Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- net/core/gro_cells.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/core/gro_cells.c b/net/core/gro_cells.c index 4b54e5f107c6..acf45ddbe924 100644 --- a/net/core/gro_cells.c +++ b/net/core/gro_cells.c @@ -84,6 +84,7 @@ void gro_cells_destroy(struct gro_cells *gcells) for_each_possible_cpu(i) { struct gro_cell *cell = per_cpu_ptr(gcells->cells, i); + napi_disable(&cell->napi); netif_napi_del(&cell->napi); __skb_queue_purge(&cell->napi_skbs); } -- cgit v1.2.3 From 1875a9ab01dfa96b06cb6649cb1ce56efa86c7cb Mon Sep 17 00:00:00 2001 From: wenxu Date: Wed, 19 Dec 2018 14:11:15 +0800 Subject: iptunnel: make TUNNEL_FLAGS available in uapi ip l add dev tun type gretap external ip r a 10.0.0.1 encap ip dst 192.168.152.171 id 1000 dev gretap For gretap Key example when the command set the id but don't set the TUNNEL_KEY flags. There is no key field in the send packet In the lwtunnel situation, some TUNNEL_FLAGS should can be set by userspace Signed-off-by: wenxu Signed-off-by: David S. Miller --- include/net/ip_tunnels.h | 19 ------------------- include/uapi/linux/if_tunnel.h | 20 ++++++++++++++++++++ 2 files changed, 20 insertions(+), 19 deletions(-) diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index b0d022ff6ea1..5ce926701bd0 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -144,25 +144,6 @@ struct ip_tunnel { bool ignore_df; }; -#define TUNNEL_CSUM __cpu_to_be16(0x01) -#define TUNNEL_ROUTING __cpu_to_be16(0x02) -#define TUNNEL_KEY __cpu_to_be16(0x04) -#define TUNNEL_SEQ __cpu_to_be16(0x08) -#define TUNNEL_STRICT __cpu_to_be16(0x10) -#define TUNNEL_REC __cpu_to_be16(0x20) -#define TUNNEL_VERSION __cpu_to_be16(0x40) -#define TUNNEL_NO_KEY __cpu_to_be16(0x80) -#define TUNNEL_DONT_FRAGMENT __cpu_to_be16(0x0100) -#define TUNNEL_OAM __cpu_to_be16(0x0200) -#define TUNNEL_CRIT_OPT __cpu_to_be16(0x0400) -#define TUNNEL_GENEVE_OPT __cpu_to_be16(0x0800) -#define TUNNEL_VXLAN_OPT __cpu_to_be16(0x1000) -#define TUNNEL_NOCACHE __cpu_to_be16(0x2000) -#define TUNNEL_ERSPAN_OPT __cpu_to_be16(0x4000) - -#define TUNNEL_OPTIONS_PRESENT \ - (TUNNEL_GENEVE_OPT | TUNNEL_VXLAN_OPT | TUNNEL_ERSPAN_OPT) - struct tnl_ptk_info { __be16 flags; __be16 proto; diff --git a/include/uapi/linux/if_tunnel.h b/include/uapi/linux/if_tunnel.h index 1b3d148c4560..7d9105533c7b 100644 --- a/include/uapi/linux/if_tunnel.h +++ b/include/uapi/linux/if_tunnel.h @@ -160,4 +160,24 @@ enum { }; #define IFLA_VTI_MAX (__IFLA_VTI_MAX - 1) + +#define TUNNEL_CSUM __cpu_to_be16(0x01) +#define TUNNEL_ROUTING __cpu_to_be16(0x02) +#define TUNNEL_KEY __cpu_to_be16(0x04) +#define TUNNEL_SEQ __cpu_to_be16(0x08) +#define TUNNEL_STRICT __cpu_to_be16(0x10) +#define TUNNEL_REC __cpu_to_be16(0x20) +#define TUNNEL_VERSION __cpu_to_be16(0x40) +#define TUNNEL_NO_KEY __cpu_to_be16(0x80) +#define TUNNEL_DONT_FRAGMENT __cpu_to_be16(0x0100) +#define TUNNEL_OAM __cpu_to_be16(0x0200) +#define TUNNEL_CRIT_OPT __cpu_to_be16(0x0400) +#define TUNNEL_GENEVE_OPT __cpu_to_be16(0x0800) +#define TUNNEL_VXLAN_OPT __cpu_to_be16(0x1000) +#define TUNNEL_NOCACHE __cpu_to_be16(0x2000) +#define TUNNEL_ERSPAN_OPT __cpu_to_be16(0x4000) + +#define TUNNEL_OPTIONS_PRESENT \ + (TUNNEL_GENEVE_OPT | TUNNEL_VXLAN_OPT | TUNNEL_ERSPAN_OPT) + #endif /* _UAPI_IF_TUNNEL_H_ */ -- cgit v1.2.3 From c6ec179a0082e2e76e3a72050c2b99d3d0f3da3f Mon Sep 17 00:00:00 2001 From: Ganesh Goudar Date: Wed, 19 Dec 2018 17:18:22 +0530 Subject: net/tls: allocate tls context using GFP_ATOMIC create_ctx can be called from atomic context, hence use GFP_ATOMIC instead of GFP_KERNEL. [ 395.962599] BUG: sleeping function called from invalid context at mm/slab.h:421 [ 395.979896] in_atomic(): 1, irqs_disabled(): 0, pid: 16254, name: openssl [ 395.996564] 2 locks held by openssl/16254: [ 396.010492] #0: 00000000347acb52 (sk_lock-AF_INET){+.+.}, at: do_tcp_setsockopt.isra.44+0x13b/0x9a0 [ 396.029838] #1: 000000006c9552b5 (device_spinlock){+...}, at: tls_init+0x1d/0x280 [ 396.047675] CPU: 5 PID: 16254 Comm: openssl Tainted: G O 4.20.0-rc6+ #25 [ 396.066019] Hardware name: Supermicro X10SRA-F/X10SRA-F, BIOS 2.0c 09/25/2017 [ 396.083537] Call Trace: [ 396.096265] dump_stack+0x5e/0x8b [ 396.109876] ___might_sleep+0x216/0x250 [ 396.123940] kmem_cache_alloc_trace+0x1b0/0x240 [ 396.138800] create_ctx+0x1f/0x60 [ 396.152504] tls_init+0xbd/0x280 [ 396.166135] tcp_set_ulp+0x191/0x2d0 [ 396.180035] ? tcp_set_ulp+0x2c/0x2d0 [ 396.193960] do_tcp_setsockopt.isra.44+0x148/0x9a0 [ 396.209013] __sys_setsockopt+0x7c/0xe0 [ 396.223054] __x64_sys_setsockopt+0x20/0x30 [ 396.237378] do_syscall_64+0x4a/0x180 [ 396.251200] entry_SYSCALL_64_after_hwframe+0x49/0xbe Fixes: df9d4a178022 ("net/tls: sleeping function from invalid context") Signed-off-by: Ganesh Goudar Signed-off-by: David S. Miller --- net/tls/tls_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index 1428bd74638c..28887cf628b8 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -538,7 +538,7 @@ static struct tls_context *create_ctx(struct sock *sk) struct inet_connection_sock *icsk = inet_csk(sk); struct tls_context *ctx; - ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); + ctx = kzalloc(sizeof(*ctx), GFP_ATOMIC); if (!ctx) return NULL; -- cgit v1.2.3 From 599d2570b2da7c2f5419332b42b7999d79c85959 Mon Sep 17 00:00:00 2001 From: Roi Dayan Date: Wed, 19 Dec 2018 18:07:56 +0200 Subject: net/sched: cls_flower: Remove old entries from rhashtable When replacing a rule we add the new rule to the rhashtable but only remove the old if not in skip_sw. This commit fix this and remove the old rule anyway. Fixes: 35cc3cefc4de ("net/sched: cls_flower: Reject duplicated rules also under skip_sw") Signed-off-by: Roi Dayan Reviewed-by: Vlad Buslov Acked-by: Or Gerlitz Signed-off-by: David S. Miller --- net/sched/cls_flower.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 71312d7bd8f4..208d940464d7 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -1258,10 +1258,9 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, fnew->flags |= TCA_CLS_FLAGS_NOT_IN_HW; if (fold) { - if (!tc_skip_sw(fold->flags)) - rhashtable_remove_fast(&fold->mask->ht, - &fold->ht_node, - fold->mask->filter_ht_params); + rhashtable_remove_fast(&fold->mask->ht, + &fold->ht_node, + fold->mask->filter_ht_params); if (!tc_skip_hw(fold->flags)) fl_hw_destroy_filter(tp, fold, NULL); } -- cgit v1.2.3 From 1b451fb2051b464b9758c09a3492104403252e2b Mon Sep 17 00:00:00 2001 From: Antoine Tenart Date: Wed, 19 Dec 2018 18:00:12 +0100 Subject: net: mvpp2: fix the phylink mode validation The mvpp2_phylink_validate() sets all modes that are supported by a given PPv2 port. An mistake made the 10000baseT_Full mode being advertised in some cases when a port wasn't configured to perform at 10G. This patch fixes this. Fixes: d97c9f4ab000 ("net: mvpp2: 1000baseX support") Reported-by: Russell King Signed-off-by: Antoine Tenart Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index 88aa488054a8..f1dab0b55769 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -4406,6 +4406,7 @@ static void mvpp2_phylink_validate(struct net_device *dev, case PHY_INTERFACE_MODE_XAUI: case PHY_INTERFACE_MODE_NA: if (port->gop_id == 0) { + phylink_set(mask, 10000baseT_Full); phylink_set(mask, 10000baseCR_Full); phylink_set(mask, 10000baseSR_Full); phylink_set(mask, 10000baseLR_Full); @@ -4423,7 +4424,6 @@ static void mvpp2_phylink_validate(struct net_device *dev, phylink_set(mask, 10baseT_Full); phylink_set(mask, 100baseT_Half); phylink_set(mask, 100baseT_Full); - phylink_set(mask, 10000baseT_Full); /* Fall-through */ case PHY_INTERFACE_MODE_1000BASEX: case PHY_INTERFACE_MODE_2500BASEX: -- cgit v1.2.3 From c0fde870d96e42bbdcc0d9af7ae5e190c767aab8 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Wed, 19 Dec 2018 16:54:38 -0800 Subject: neighbor: NTF_PROXY is a valid ndm_flag for a dump request When dumping proxy entries the dump request has NTF_PROXY set in ndm_flags. strict mode checking needs to be updated to allow this flag. Fixes: 51183d233b5a ("net/neighbor: Update neigh_dump_info for strict data checking") Signed-off-by: David Ahern Signed-off-by: David S. Miller --- net/core/neighbour.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 41954e42a2de..5fa32c064baf 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -2494,11 +2494,16 @@ static int neigh_valid_dump_req(const struct nlmsghdr *nlh, ndm = nlmsg_data(nlh); if (ndm->ndm_pad1 || ndm->ndm_pad2 || ndm->ndm_ifindex || - ndm->ndm_state || ndm->ndm_flags || ndm->ndm_type) { + ndm->ndm_state || ndm->ndm_type) { NL_SET_ERR_MSG(extack, "Invalid values in header for neighbor dump request"); return -EINVAL; } + if (ndm->ndm_flags & ~NTF_PROXY) { + NL_SET_ERR_MSG(extack, "Invalid flags in header for neighbor dump request"); + return -EINVAL; + } + err = nlmsg_parse_strict(nlh, sizeof(struct ndmsg), tb, NDA_MAX, NULL, extack); } else { -- cgit v1.2.3 From d84e7bc0595a7e146ad0ddb80b240cea77825245 Mon Sep 17 00:00:00 2001 From: David S. Miller Date: Wed, 19 Dec 2018 20:53:18 -0800 Subject: rds: Fix warning. >> net/rds/send.c:1109:42: warning: Using plain integer as NULL pointer Fixes: ea010070d0a7 ("net/rds: fix warn in rds_message_alloc_sgs") Reported-by: kbuild test robot Signed-off-by: David S. Miller --- net/rds/send.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/net/rds/send.c b/net/rds/send.c index b39b30706210..3d822bad7de9 100644 --- a/net/rds/send.c +++ b/net/rds/send.c @@ -1109,9 +1109,11 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len) sock_flag(rds_rs_to_sk(rs), SOCK_ZEROCOPY)); int num_sgs = ceil(payload_len, PAGE_SIZE); int namelen; - struct rds_iov_vector_arr vct = {0}; + struct rds_iov_vector_arr vct; int ind; + memset(&vct, 0, sizeof(vct)); + /* expect 1 RDMA CMSG per rds_sendmsg. can still grow if more needed. */ vct.incr = 1; -- cgit v1.2.3 From a837eca2412051628c0529768c9bc4f3580b040e Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Thu, 20 Dec 2018 23:23:24 +1100 Subject: iomap: Revert "fs/iomap.c: get/put the page in iomap_page_create/release()" This reverts commit 61c6de667263184125d5ca75e894fcad632b0dd3. The reverted commit added page reference counting to iomap page structures that are used to track block size < page size state. This was supposed to align the code with page migration page accounting assumptions, but what it has done instead is break XFS filesystems. Every fstests run I've done on sub-page block size XFS filesystems has since picking up this commit 2 days ago has failed with bad page state errors such as: # ./run_check.sh "-m rmapbt=1,reflink=1 -i sparse=1 -b size=1k" "generic/038" .... SECTION -- xfs FSTYP -- xfs (debug) PLATFORM -- Linux/x86_64 test1 4.20.0-rc6-dgc+ MKFS_OPTIONS -- -f -m rmapbt=1,reflink=1 -i sparse=1 -b size=1k /dev/sdc MOUNT_OPTIONS -- /dev/sdc /mnt/scratch generic/038 454s ... run fstests generic/038 at 2018-12-20 18:43:05 XFS (sdc): Unmounting Filesystem XFS (sdc): Mounting V5 Filesystem XFS (sdc): Ending clean mount BUG: Bad page state in process kswapd0 pfn:3a7fa page:ffffea0000ccbeb0 count:0 mapcount:0 mapping:ffff88800d9b6360 index:0x1 flags: 0xfffffc0000000() raw: 000fffffc0000000 dead000000000100 dead000000000200 ffff88800d9b6360 raw: 0000000000000001 0000000000000000 00000000ffffffff page dumped because: non-NULL mapping CPU: 0 PID: 676 Comm: kswapd0 Not tainted 4.20.0-rc6-dgc+ #915 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.11.1-1 04/01/2014 Call Trace: dump_stack+0x67/0x90 bad_page.cold.116+0x8a/0xbd free_pcppages_bulk+0x4bf/0x6a0 free_unref_page_list+0x10f/0x1f0 shrink_page_list+0x49d/0xf50 shrink_inactive_list+0x19d/0x3b0 shrink_node_memcg.constprop.77+0x398/0x690 ? shrink_slab.constprop.81+0x278/0x3f0 shrink_node+0x7a/0x2f0 kswapd+0x34b/0x6d0 ? node_reclaim+0x240/0x240 kthread+0x11f/0x140 ? __kthread_bind_mask+0x60/0x60 ret_from_fork+0x24/0x30 Disabling lock debugging due to kernel taint .... The failures are from anyway that frees pages and empties the per-cpu page magazines, so it's not a predictable failure or an easy to debug failure. generic/038 is a reliable reproducer of this problem - it has a 9 in 10 failure rate on one of my test machines. Failure on other machines have been at random points in fstests runs but every run has ended up tripping this problem. Hence generic/038 was used to bisect the failure because it was the most reliable failure. It is too close to the 4.20 release (not to mention holidays) to try to diagnose, fix and test the underlying cause of the problem, so reverting the commit is the only option we have right now. The revert has been tested against a current tot 4.20-rc7+ kernel across multiple machines running sub-page block size XFs filesystems and none of the bad page state failures have been seen. Signed-off-by: Dave Chinner Cc: Piotr Jaroszynski Cc: Christoph Hellwig Cc: William Kucharski Cc: Darrick J. Wong Cc: Brian Foster Signed-off-by: Linus Torvalds --- fs/iomap.c | 7 ------- 1 file changed, 7 deletions(-) diff --git a/fs/iomap.c b/fs/iomap.c index 5bc172f3dfe8..d6bc98ae8d35 100644 --- a/fs/iomap.c +++ b/fs/iomap.c @@ -116,12 +116,6 @@ iomap_page_create(struct inode *inode, struct page *page) atomic_set(&iop->read_count, 0); atomic_set(&iop->write_count, 0); bitmap_zero(iop->uptodate, PAGE_SIZE / SECTOR_SIZE); - - /* - * migrate_page_move_mapping() assumes that pages with private data have - * their count elevated by 1. - */ - get_page(page); set_page_private(page, (unsigned long)iop); SetPagePrivate(page); return iop; @@ -138,7 +132,6 @@ iomap_page_release(struct page *page) WARN_ON_ONCE(atomic_read(&iop->write_count)); ClearPagePrivate(page); set_page_private(page, 0); - put_page(page); kfree(iop); } -- cgit v1.2.3