From: Jianqun Xu jay.xu@rock-chips.com

[ Upstream commit 02c84f91adb9a64b75ec97d772675c02a3e65ed7 ]

Fix the address in the spdif node name.

Fixes: 874e568e500a ("ARM: dts: rockchip: Add SPDIF transceiver for RK3288") Signed-off-by: Jianqun Xu jay.xu@rock-chips.com Reviewed-by: Sjoerd Simons sjoerd@collabora.com Link: https://lore.kernel.org/r/20230208091411.1603142-1-jay.xu@rock-chips.com Signed-off-by: Heiko Stuebner heiko@sntech.de Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm/boot/dts/rk3288.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm/boot/dts/rk3288.dtsi b/arch/arm/boot/dts/rk3288.dtsi index 8670c948ca8da..2e6138eeacd15 100644 --- a/arch/arm/boot/dts/rk3288.dtsi +++ b/arch/arm/boot/dts/rk3288.dtsi @@ -940,7 +940,7 @@ status = "disabled"; };

- spdif: sound@ff88b0000 { + spdif: sound@ff8b0000 { compatible = "rockchip,rk3288-spdif", "rockchip,rk3066-spdif"; reg = <0x0 0xff8b0000 0x0 0x10000>; #sound-dai-cells = <0>;

From: Marc Gonzalez mgonzalez@freebox.fr

[ Upstream commit aec4353114a408b3a831a22ba34942d05943e462 ]

According to S905X2 Datasheet - Revision 07: DRAM Memory Controller (DMC) register area spans ff638000-ff63a000.

According to DeviceTree Specification - Release v0.4-rc1: simple-bus nodes do not require reg property.

Fixes: 1499218c80c99a ("arm64: dts: move common G12A & G12B modes to meson-g12-common.dtsi") Signed-off-by: Marc Gonzalez mgonzalez@freebox.fr Reviewed-by: Martin Blumenstingl martin.blumenstingl@googlemail.com Link: https://lore.kernel.org/r/20230327120932.2158389-2-mgonzalez@freebox.fr Signed-off-by: Neil Armstrong neil.armstrong@linaro.org Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi b/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi index 899cfe416aef4..369334076467a 100644 --- a/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi @@ -1610,10 +1610,9 @@

dmc: bus@38000 { compatible = "simple-bus"; - reg = <0x0 0x38000 0x0 0x400>; #address-cells = <2>; #size-cells = <2>; - ranges = <0x0 0x0 0x0 0x38000 0x0 0x400>; + ranges = <0x0 0x0 0x0 0x38000 0x0 0x2000>;

canvas: video-lut@48 { compatible = "amlogic,canvas";

From: Florian Westphal fw@strlen.de

[ Upstream commit 94623f579ce338b5fa61b5acaa5beb8aa657fb9e ]

Recent attempt to ensure PREROUTING hook is executed again when a decrypted ipsec packet received on a bridge passes through the network stack a second time broke the physdev match in INPUT hook.

We can't discard the nf_bridge info strct from sabotage_in hook, as this is needed by the physdev match.

Keep the struct around and handle this with another conditional instead.

Fixes: 2b272bb558f1 ("netfilter: br_netfilter: disable sabotage_in hook after first suppression") Reported-and-tested-by: Farid BENAMROUCHE fariouche@yahoo.fr Signed-off-by: Florian Westphal fw@strlen.de Signed-off-by: Pablo Neira Ayuso pablo@netfilter.org Signed-off-by: Sasha Levin sashal@kernel.org --- include/linux/skbuff.h | 1 + net/bridge/br_netfilter_hooks.c | 17 +++++++++++------ 2 files changed, 12 insertions(+), 6 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 19e595cab23ac..ef00dd3108362 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -259,6 +259,7 @@ struct nf_bridge_info { u8 pkt_otherhost:1; u8 in_prerouting:1; u8 bridged_dnat:1; + u8 sabotage_in_done:1; __u16 frag_max_size; struct net_device *physindev;

diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index f3c7cfba31e1b..f14beb9a62edb 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -868,12 +868,17 @@ static unsigned int ip_sabotage_in(void *priv, { struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);

- if (nf_bridge && !nf_bridge->in_prerouting && - !netif_is_l3_master(skb->dev) && - !netif_is_l3_slave(skb->dev)) { - nf_bridge_info_free(skb); - state->okfn(state->net, state->sk, skb); - return NF_STOLEN; + if (nf_bridge) { + if (nf_bridge->sabotage_in_done) + return NF_ACCEPT; + + if (!nf_bridge->in_prerouting && + !netif_is_l3_master(skb->dev) && + !netif_is_l3_slave(skb->dev)) { + nf_bridge->sabotage_in_done = 1; + state->okfn(state->net, state->sk, skb); + return NF_STOLEN; + } }

return NF_ACCEPT;

From: Cristian Ciocaltea cristian.ciocaltea@collabora.com

[ Upstream commit c5d5b55b3c1a314137a251efc1001dfd435c6242 ]

The support for TCS4525 regulator has been introduced with a wrong ramp-rate mask, which has been defined as a logical expression instead of a bit shift operation.

For clarity, fix it using GENMASK() macro.

Fixes: 914df8faa7d6 ("regulator: fan53555: Add TCS4525 DCDC support") Signed-off-by: Cristian Ciocaltea cristian.ciocaltea@collabora.com Link: https://lore.kernel.org/r/20230406171806.948290-4-cristian.ciocaltea@collabo... Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/regulator/fan53555.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/regulator/fan53555.c b/drivers/regulator/fan53555.c index df53464afe3a0..ecd5a50c61660 100644 --- a/drivers/regulator/fan53555.c +++ b/drivers/regulator/fan53555.c @@ -61,7 +61,7 @@ #define TCS_VSEL1_MODE (1 << 6)

#define TCS_SLEW_SHIFT 3 -#define TCS_SLEW_MASK (0x3 < 3) +#define TCS_SLEW_MASK GENMASK(4, 3)

enum fan53555_vendor { FAN53526_VENDOR_FAIRCHILD = 0,

From: Xuan Zhuo xuanzhuo@linux.alibaba.com

[ Upstream commit 853618d5886bf94812f31228091cd37d308230f7 ]

Here we copy the data from the original buf to the new page. But we not check that it may be overflow.

As long as the size received(including vnethdr) is greater than 3840 (PAGE_SIZE -VIRTIO_XDP_HEADROOM). Then the memcpy will overflow.

And this is completely possible, as long as the MTU is large, such as 4096. In our test environment, this will cause crash. Since crash is caused by the written memory, it is meaningless, so I do not include it.

Fixes: 72979a6c3590 ("virtio_net: xdp, add slowpath case for non contiguous buffers") Signed-off-by: Xuan Zhuo xuanzhuo@linux.alibaba.com Acked-by: Jason Wang jasowang@redhat.com Acked-by: Michael S. Tsirkin mst@redhat.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/virtio_net.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 66ca2ea19ba60..8a380086ac257 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -679,8 +679,13 @@ static struct page *xdp_linearize_page(struct receive_queue *rq, int page_off, unsigned int *len) { - struct page *page = alloc_page(GFP_ATOMIC); + int tailroom = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); + struct page *page;

+ if (page_off + *len + tailroom > PAGE_SIZE) + return NULL; + + page = alloc_page(GFP_ATOMIC); if (!page) return NULL;

@@ -688,7 +693,6 @@ static struct page *xdp_linearize_page(struct receive_queue *rq, page_off += *len;

while (--*num_buf) { - int tailroom = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); unsigned int buflen; void *buf; int off;

From: Ding Hui dinghui@sangfor.com.cn

[ Upstream commit a80bb8e7233b2ad6ff119646b6e33fb3edcec37b ]

There is a use-after-free scenario that is:

When the NIC is down, user set mac address or vlan tag to VF, the xxx_set_vf_mac() or xxx_set_vf_vlan() will invoke efx_net_stop() and efx_net_open(), since netif_running() is false, the port will not start and keep port_enabled false, but selftest_work is scheduled in efx_net_open().

If we remove the device before selftest_work run, the efx_stop_port() will not be called since the NIC is down, and then efx is freed, we will soon get a UAF in run_timer_softirq() like this:

[ 1178.907941] ================================================================== [ 1178.907948] BUG: KASAN: use-after-free in run_timer_softirq+0xdea/0xe90 [ 1178.907950] Write of size 8 at addr ff11001f449cdc80 by task swapper/47/0 [ 1178.907950] [ 1178.907953] CPU: 47 PID: 0 Comm: swapper/47 Kdump: loaded Tainted: G O --------- -t - 4.18.0 #1 [ 1178.907954] Hardware name: SANGFOR X620G40/WI2HG-208T1061A, BIOS SPYH051032-U01 04/01/2022 [ 1178.907955] Call Trace: [ 1178.907956] <IRQ> [ 1178.907960] dump_stack+0x71/0xab [ 1178.907963] print_address_description+0x6b/0x290 [ 1178.907965] ? run_timer_softirq+0xdea/0xe90 [ 1178.907967] kasan_report+0x14a/0x2b0 [ 1178.907968] run_timer_softirq+0xdea/0xe90 [ 1178.907971] ? init_timer_key+0x170/0x170 [ 1178.907973] ? hrtimer_cancel+0x20/0x20 [ 1178.907976] ? sched_clock+0x5/0x10 [ 1178.907978] ? sched_clock_cpu+0x18/0x170 [ 1178.907981] __do_softirq+0x1c8/0x5fa [ 1178.907985] irq_exit+0x213/0x240 [ 1178.907987] smp_apic_timer_interrupt+0xd0/0x330 [ 1178.907989] apic_timer_interrupt+0xf/0x20 [ 1178.907990] </IRQ> [ 1178.907991] RIP: 0010:mwait_idle+0xae/0x370

If the NIC is not actually brought up, there is no need to schedule selftest_work, so let's move invoking efx_selftest_async_start() into efx_start_all(), and it will be canceled by broughting down.

Fixes: dd40781e3a4e ("sfc: Run event/IRQ self-test asynchronously when interface is brought up") Fixes: e340be923012 ("sfc: add ndo_set_vf_mac() function for EF10") Debugged-by: Huang Cun huangcun@sangfor.com.cn Cc: Donglin Peng pengdonglin@sangfor.com.cn Suggested-by: Martin Habets habetsm.xilinx@gmail.com Signed-off-by: Ding Hui dinghui@sangfor.com.cn Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/sfc/efx.c | 1 - drivers/net/ethernet/sfc/efx_common.c | 2 ++ 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c index 7ab592844df83..41eb6f9f5596e 100644 --- a/drivers/net/ethernet/sfc/efx.c +++ b/drivers/net/ethernet/sfc/efx.c @@ -540,7 +540,6 @@ int efx_net_open(struct net_device *net_dev) else efx->state = STATE_NET_UP;

- efx_selftest_async_start(efx); return 0; }

diff --git a/drivers/net/ethernet/sfc/efx_common.c b/drivers/net/ethernet/sfc/efx_common.c index 7c90e1e2d161b..6038b7e3e8236 100644 --- a/drivers/net/ethernet/sfc/efx_common.c +++ b/drivers/net/ethernet/sfc/efx_common.c @@ -542,6 +542,8 @@ void efx_start_all(struct efx_nic *efx) /* Start the hardware monitor if there is one */ efx_start_monitor(efx);

+ efx_selftest_async_start(efx); + /* Link state detection is normally event-driven; we have * to poll now because we could have missed a change */

From: Aleksandr Loktionov aleksandr.loktionov@intel.com

[ Upstream commit 8485d093b076e59baff424552e8aecfc5bd2d261 ]

Fix accessing vsi->active_filters without holding the mac_filter_hash_lock. Move vsi->active_filters = 0 inside critical section and move clear_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state) after the critical section to ensure the new filters from other threads can be added only after filters cleaning in the critical section is finished.

Fixes: 278e7d0b9d68 ("i40e: store MAC/VLAN filters in a hash with the MAC Address as key") Signed-off-by: Aleksandr Loktionov aleksandr.loktionov@intel.com Tested-by: Pucha Himasekhar Reddy himasekharx.reddy.pucha@intel.com (A Contingent worker at Intel) Signed-off-by: Tony Nguyen anthony.l.nguyen@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/intel/i40e/i40e_main.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 85d48efce1d00..cafbabc687565 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -13945,15 +13945,15 @@ static int i40e_add_vsi(struct i40e_vsi *vsi) vsi->id = ctxt.vsi_number; }

- vsi->active_filters = 0; - clear_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state); spin_lock_bh(&vsi->mac_filter_hash_lock); + vsi->active_filters = 0; /* If macvlan filters already exist, force them to get loaded */ hash_for_each_safe(vsi->mac_filter_hash, bkt, h, f, hlist) { f->state = I40E_FILTER_NEW; f_count++; } spin_unlock_bh(&vsi->mac_filter_hash_lock); + clear_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state);

if (f_count) { vsi->flags |= I40E_VSI_FLAG_FILTER_CHANGED;

From: Pablo Neira Ayuso pablo@netfilter.org

[ Upstream commit d46fc894147cf98dd6e8210aa99ed46854191840 ]

catch-all set element might jump/goto to chain that uses expressions that require validation.

Fixes: aaa31047a6d2 ("netfilter: nftables: add catch-all set element support") Signed-off-by: Pablo Neira Ayuso pablo@netfilter.org Signed-off-by: Sasha Levin sashal@kernel.org --- include/net/netfilter/nf_tables.h | 4 ++ net/netfilter/nf_tables_api.c | 64 ++++++++++++++++++++++++++++--- net/netfilter/nft_lookup.c | 36 ++--------------- 3 files changed, 66 insertions(+), 38 deletions(-)

diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 80df8ff5e6752..8def00a04541e 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -1030,6 +1030,10 @@ struct nft_chain { };

int nft_chain_validate(const struct nft_ctx *ctx, const struct nft_chain *chain); +int nft_setelem_validate(const struct nft_ctx *ctx, struct nft_set *set, + const struct nft_set_iter *iter, + struct nft_set_elem *elem); +int nft_set_catchall_validate(const struct nft_ctx *ctx, struct nft_set *set);

enum nft_chain_types { NFT_CHAIN_T_DEFAULT = 0, diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index dc276b6802ca9..aecb2f1e7af10 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -3294,6 +3294,64 @@ static int nft_table_validate(struct net *net, const struct nft_table *table) return 0; }

+int nft_setelem_validate(const struct nft_ctx *ctx, struct nft_set *set, + const struct nft_set_iter *iter, + struct nft_set_elem *elem) +{ + const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); + struct nft_ctx *pctx = (struct nft_ctx *)ctx; + const struct nft_data *data; + int err; + + if (nft_set_ext_exists(ext, NFT_SET_EXT_FLAGS) && + *nft_set_ext_flags(ext) & NFT_SET_ELEM_INTERVAL_END) + return 0; + + data = nft_set_ext_data(ext); + switch (data->verdict.code) { + case NFT_JUMP: + case NFT_GOTO: + pctx->level++; + err = nft_chain_validate(ctx, data->verdict.chain); + if (err < 0) + return err; + pctx->level--; + break; + default: + break; + } + + return 0; +} + +struct nft_set_elem_catchall { + struct list_head list; + struct rcu_head rcu; + void *elem; +}; + +int nft_set_catchall_validate(const struct nft_ctx *ctx, struct nft_set *set) +{ + u8 genmask = nft_genmask_next(ctx->net); + struct nft_set_elem_catchall *catchall; + struct nft_set_elem elem; + struct nft_set_ext *ext; + int ret = 0; + + list_for_each_entry_rcu(catchall, &set->catchall_list, list) { + ext = nft_set_elem_ext(set, catchall->elem); + if (!nft_set_elem_active(ext, genmask)) + continue; + + elem.priv = catchall->elem; + ret = nft_setelem_validate(ctx, set, NULL, &elem); + if (ret < 0) + return ret; + } + + return ret; +} + static struct nft_rule *nft_rule_lookup_byid(const struct net *net, const struct nft_chain *chain, const struct nlattr *nla); @@ -4598,12 +4656,6 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info, return err; }

-struct nft_set_elem_catchall { - struct list_head list; - struct rcu_head rcu; - void *elem; -}; - static void nft_set_catchall_destroy(const struct nft_ctx *ctx, struct nft_set *set) { diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c index 90becbf5bff3d..bd3485dd930f5 100644 --- a/net/netfilter/nft_lookup.c +++ b/net/netfilter/nft_lookup.c @@ -198,37 +198,6 @@ static int nft_lookup_dump(struct sk_buff *skb, const struct nft_expr *expr) return -1; }

-static int nft_lookup_validate_setelem(const struct nft_ctx *ctx, - struct nft_set *set, - const struct nft_set_iter *iter, - struct nft_set_elem *elem) -{ - const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); - struct nft_ctx *pctx = (struct nft_ctx *)ctx; - const struct nft_data *data; - int err; - - if (nft_set_ext_exists(ext, NFT_SET_EXT_FLAGS) && - *nft_set_ext_flags(ext) & NFT_SET_ELEM_INTERVAL_END) - return 0; - - data = nft_set_ext_data(ext); - switch (data->verdict.code) { - case NFT_JUMP: - case NFT_GOTO: - pctx->level++; - err = nft_chain_validate(ctx, data->verdict.chain); - if (err < 0) - return err; - pctx->level--; - break; - default: - break; - } - - return 0; -} - static int nft_lookup_validate(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nft_data **d) @@ -244,9 +213,12 @@ static int nft_lookup_validate(const struct nft_ctx *ctx, iter.skip = 0; iter.count = 0; iter.err = 0; - iter.fn = nft_lookup_validate_setelem; + iter.fn = nft_setelem_validate;

priv->set->ops->walk(ctx, priv->set, &iter); + if (!iter.err) + iter.err = nft_set_catchall_validate(ctx, priv->set); + if (iter.err < 0) return iter.err;

From: Michael Chan michael.chan@broadcom.com

[ Upstream commit e8b51a1a15d5a3cce231e0669f6a161dc5bb9b75 ]

The driver does not support PTP on these older chips and it is assuming that firmware on these older chips will not return the PORT_MAC_PTP_QCFG_RESP_FLAGS_HWRM_ACCESS flag in __bnxt_hwrm_ptp_qcfg(), causing the function to abort quietly.

But newer firmware now sets this flag and so __bnxt_hwrm_ptp_qcfg() will proceed further. Eventually it will fail in bnxt_ptp_init() -> bnxt_map_ptp_regs() because there is no code to support the older chips. The driver will then complain:

"PTP initialization failed.\n"

Fix it so that we abort quietly earlier without going through the unnecessary steps and alarming the user with the warning log.

Fixes: ae5c42f0b92c ("bnxt_en: Get PTP hardware capability from firmware") Signed-off-by: Michael Chan michael.chan@broadcom.com Signed-off-by: Paolo Abeni pabeni@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 4ef90e0cb8f8e..38fc2286f7cbd 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -7437,7 +7437,7 @@ static int __bnxt_hwrm_ptp_qcfg(struct bnxt *bp) u8 flags; int rc;

- if (bp->hwrm_spec_code < 0x10801) { + if (bp->hwrm_spec_code < 0x10801 || !BNXT_CHIP_P5_THOR(bp)) { rc = -ENODEV; goto no_ptp; }

From: Ido Schimmel idosch@nvidia.com

[ Upstream commit c484fcc058bada604d7e4e5228d4affb646ddbc2 ]

When a net device is put administratively up, its 'IFF_UP' flag is set (if not set already) and a 'NETDEV_UP' notification is emitted, which causes the 8021q driver to add VLAN ID 0 on the device. The reverse happens when a net device is put administratively down.

When changing the type of a bond to Ethernet, its 'IFF_UP' flag is incorrectly cleared, resulting in the kernel skipping the above process and VLAN ID 0 being leaked [1].

Fix by restoring the flag when changing the type to Ethernet, in a similar fashion to the restoration of the 'IFF_SLAVE' flag.

The issue can be reproduced using the script in [2], with example out before and after the fix in [3].

[1] unreferenced object 0xffff888103479900 (size 256): comm "ip", pid 329, jiffies 4294775225 (age 28.561s) hex dump (first 32 bytes): 00 a0 0c 15 81 88 ff ff 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: [<ffffffff81a6051a>] kmalloc_trace+0x2a/0xe0 [<ffffffff8406426c>] vlan_vid_add+0x30c/0x790 [<ffffffff84068e21>] vlan_device_event+0x1491/0x21a0 [<ffffffff81440c8e>] notifier_call_chain+0xbe/0x1f0 [<ffffffff8372383a>] call_netdevice_notifiers_info+0xba/0x150 [<ffffffff837590f2>] __dev_notify_flags+0x132/0x2e0 [<ffffffff8375ad9f>] dev_change_flags+0x11f/0x180 [<ffffffff8379af36>] do_setlink+0xb96/0x4060 [<ffffffff837adf6a>] __rtnl_newlink+0xc0a/0x18a0 [<ffffffff837aec6c>] rtnl_newlink+0x6c/0xa0 [<ffffffff837ac64e>] rtnetlink_rcv_msg+0x43e/0xe00 [<ffffffff839a99e0>] netlink_rcv_skb+0x170/0x440 [<ffffffff839a738f>] netlink_unicast+0x53f/0x810 [<ffffffff839a7fcb>] netlink_sendmsg+0x96b/0xe90 [<ffffffff8369d12f>] ____sys_sendmsg+0x30f/0xa70 [<ffffffff836a6d7a>] ___sys_sendmsg+0x13a/0x1e0 unreferenced object 0xffff88810f6a83e0 (size 32): comm "ip", pid 329, jiffies 4294775225 (age 28.561s) hex dump (first 32 bytes): a0 99 47 03 81 88 ff ff a0 99 47 03 81 88 ff ff ..G.......G..... 81 00 00 00 01 00 00 00 cc cc cc cc cc cc cc cc ................ backtrace: [<ffffffff81a6051a>] kmalloc_trace+0x2a/0xe0 [<ffffffff84064369>] vlan_vid_add+0x409/0x790 [<ffffffff84068e21>] vlan_device_event+0x1491/0x21a0 [<ffffffff81440c8e>] notifier_call_chain+0xbe/0x1f0 [<ffffffff8372383a>] call_netdevice_notifiers_info+0xba/0x150 [<ffffffff837590f2>] __dev_notify_flags+0x132/0x2e0 [<ffffffff8375ad9f>] dev_change_flags+0x11f/0x180 [<ffffffff8379af36>] do_setlink+0xb96/0x4060 [<ffffffff837adf6a>] __rtnl_newlink+0xc0a/0x18a0 [<ffffffff837aec6c>] rtnl_newlink+0x6c/0xa0 [<ffffffff837ac64e>] rtnetlink_rcv_msg+0x43e/0xe00 [<ffffffff839a99e0>] netlink_rcv_skb+0x170/0x440 [<ffffffff839a738f>] netlink_unicast+0x53f/0x810 [<ffffffff839a7fcb>] netlink_sendmsg+0x96b/0xe90 [<ffffffff8369d12f>] ____sys_sendmsg+0x30f/0xa70 [<ffffffff836a6d7a>] ___sys_sendmsg+0x13a/0x1e0

[2] ip link add name t-nlmon type nlmon ip link add name t-dummy type dummy ip link add name t-bond type bond mode active-backup

ip link set dev t-bond up ip link set dev t-nlmon master t-bond ip link set dev t-nlmon nomaster ip link show dev t-bond ip link set dev t-dummy master t-bond ip link show dev t-bond

ip link del dev t-bond ip link del dev t-dummy ip link del dev t-nlmon

[3] Before:

12: t-bond: <NO-CARRIER,BROADCAST,MULTICAST,MASTER,UP> mtu 1500 qdisc noqueue state DOWN mode DEFAULT group default qlen 1000 link/netlink 12: t-bond: <BROADCAST,MULTICAST,MASTER,LOWER_UP> mtu 1500 qdisc noqueue state UP mode DEFAULT group default qlen 1000 link/ether 46:57:39:a4:46:a2 brd ff:ff:ff:ff:ff:ff

After:

12: t-bond: <NO-CARRIER,BROADCAST,MULTICAST,MASTER,UP> mtu 1500 qdisc noqueue state DOWN mode DEFAULT group default qlen 1000 link/netlink 12: t-bond: <BROADCAST,MULTICAST,MASTER,UP,LOWER_UP> mtu 1500 qdisc noqueue state UP mode DEFAULT group default qlen 1000 link/ether 66:48:7b:74:b6:8a brd ff:ff:ff:ff:ff:ff

Fixes: e36b9d16c6a6 ("bonding: clean muticast addresses when device changes type") Fixes: 75c78500ddad ("bonding: remap muticast addresses without using dev_close() and dev_open()") Fixes: 9ec7eb60dcbc ("bonding: restore IFF_MASTER/SLAVE flags on bond enslave ether type change") Reported-by: Mirsad Goran Todorovac mirsad.todorovac@alu.unizg.hr Link: https://lore.kernel.org/netdev/78a8a03b-6070-3e6b-5042-f848dab16fb8@alu.uniz... Tested-by: Mirsad Goran Todorovac mirsad.todorovac@alu.unizg.hr Signed-off-by: Ido Schimmel idosch@nvidia.com Acked-by: Jay Vosburgh jay.vosburgh@canonical.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/bonding/bond_main.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index e1dc94f01cb5a..2816b6fc17392 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1746,14 +1746,15 @@ void bond_lower_state_changed(struct slave *slave)

/* The bonding driver uses ether_setup() to convert a master bond device * to ARPHRD_ETHER, that resets the target netdevice's flags so we always - * have to restore the IFF_MASTER flag, and only restore IFF_SLAVE if it was set + * have to restore the IFF_MASTER flag, and only restore IFF_SLAVE and IFF_UP + * if they were set */ static void bond_ether_setup(struct net_device *bond_dev) { - unsigned int slave_flag = bond_dev->flags & IFF_SLAVE; + unsigned int flags = bond_dev->flags & (IFF_SLAVE | IFF_UP);

ether_setup(bond_dev); - bond_dev->flags |= IFF_MASTER | slave_flag; + bond_dev->flags |= IFF_MASTER | flags; bond_dev->priv_flags &= ~IFF_TX_SKB_SHARING; }

From: Ido Schimmel idosch@nvidia.com

[ Upstream commit 1f64757ee2bb22a93ec89b4c71707297e8cca0ba ]

During initialization the driver issues a reset command via its command interface in order to remove previous configuration from the device.

After issuing the reset, the driver waits for 200ms before polling on the "system_status" register using memory-mapped IO until the device reaches a ready state (0x5E). The wait is necessary because the reset command only triggers the reset, but the reset itself happens asynchronously. If the driver starts polling too soon, the read of the "system_status" register will never return and the system will crash [1].

The issue was discovered when the device was flashed with a development firmware version where the reset routine took longer to complete. The issue was fixed in the firmware, but it exposed the fact that the current wait time is borderline.

Fix by increasing the wait time from 200ms to 400ms. With this patch and the buggy firmware version, the issue did not reproduce in 10 reboots whereas without the patch the issue is reproduced quite consistently.

[1] mce: CPUs not responding to MCE broadcast (may include false positives): 0,4 mce: CPUs not responding to MCE broadcast (may include false positives): 0,4 Kernel panic - not syncing: Timeout: Not all CPUs entered broadcast exception handler Shutting down cpus with NMI Kernel Offset: 0x12000000 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffffbfffffff)

Fixes: ac004e84164e ("mlxsw: pci: Wait longer before accessing the device after reset") Signed-off-by: Ido Schimmel idosch@nvidia.com Reviewed-by: Petr Machata petrm@nvidia.com Signed-off-by: Petr Machata petrm@nvidia.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/mellanox/mlxsw/pci_hw.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h b/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h index 7b531228d6c0f..25e9f47db2a62 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h +++ b/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h @@ -26,7 +26,7 @@ #define MLXSW_PCI_CIR_TIMEOUT_MSECS 1000

#define MLXSW_PCI_SW_RESET_TIMEOUT_MSECS 900000 -#define MLXSW_PCI_SW_RESET_WAIT_MSECS 200 +#define MLXSW_PCI_SW_RESET_WAIT_MSECS 400 #define MLXSW_PCI_FW_READY 0xA1844 #define MLXSW_PCI_FW_READY_MASK 0xFFFF #define MLXSW_PCI_FW_READY_MAGIC 0x5E

From: Daniel Borkmann daniel@iogearbox.net

[ Upstream commit 71b547f561247897a0a14f3082730156c0533fed ]

Juan Jose et al reported an issue found via fuzzing where the verifier's pruning logic prematurely marks a program path as safe.

Consider the following program:

0: (b7) r6 = 1024 1: (b7) r7 = 0 2: (b7) r8 = 0 3: (b7) r9 = -2147483648 4: (97) r6 %= 1025 5: (05) goto pc+0 6: (bd) if r6 <= r9 goto pc+2 7: (97) r6 %= 1 8: (b7) r9 = 0 9: (bd) if r6 <= r9 goto pc+1 10: (b7) r6 = 0 11: (b7) r0 = 0 12: (63) *(u32 *)(r10 -4) = r0 13: (18) r4 = 0xffff888103693400 // map_ptr(ks=4,vs=48) 15: (bf) r1 = r4 16: (bf) r2 = r10 17: (07) r2 += -4 18: (85) call bpf_map_lookup_elem#1 19: (55) if r0 != 0x0 goto pc+1 20: (95) exit 21: (77) r6 >>= 10 22: (27) r6 *= 8192 23: (bf) r1 = r0 24: (0f) r0 += r6 25: (79) r3 = *(u64 *)(r0 +0) 26: (7b) *(u64 *)(r1 +0) = r3 27: (95) exit

The verifier treats this as safe, leading to oob read/write access due to an incorrect verifier conclusion:

func#0 @0 0: R1=ctx(off=0,imm=0) R10=fp0 0: (b7) r6 = 1024 ; R6_w=1024 1: (b7) r7 = 0 ; R7_w=0 2: (b7) r8 = 0 ; R8_w=0 3: (b7) r9 = -2147483648 ; R9_w=-2147483648 4: (97) r6 %= 1025 ; R6_w=scalar() 5: (05) goto pc+0 6: (bd) if r6 <= r9 goto pc+2 ; R6_w=scalar(umin=18446744071562067969,var_off=(0xffffffff00000000; 0xffffffff)) R9_w=-2147483648 7: (97) r6 %= 1 ; R6_w=scalar() 8: (b7) r9 = 0 ; R9=0 9: (bd) if r6 <= r9 goto pc+1 ; R6=scalar(umin=1) R9=0 10: (b7) r6 = 0 ; R6_w=0 11: (b7) r0 = 0 ; R0_w=0 12: (63) *(u32 *)(r10 -4) = r0 last_idx 12 first_idx 9 regs=1 stack=0 before 11: (b7) r0 = 0 13: R0_w=0 R10=fp0 fp-8=0000???? 13: (18) r4 = 0xffff8ad3886c2a00 ; R4_w=map_ptr(off=0,ks=4,vs=48,imm=0) 15: (bf) r1 = r4 ; R1_w=map_ptr(off=0,ks=4,vs=48,imm=0) R4_w=map_ptr(off=0,ks=4,vs=48,imm=0) 16: (bf) r2 = r10 ; R2_w=fp0 R10=fp0 17: (07) r2 += -4 ; R2_w=fp-4 18: (85) call bpf_map_lookup_elem#1 ; R0=map_value_or_null(id=1,off=0,ks=4,vs=48,imm=0) 19: (55) if r0 != 0x0 goto pc+1 ; R0=0 20: (95) exit

from 19 to 21: R0=map_value(off=0,ks=4,vs=48,imm=0) R6=0 R7=0 R8=0 R9=0 R10=fp0 fp-8=mmmm???? 21: (77) r6 >>= 10 ; R6_w=0 22: (27) r6 *= 8192 ; R6_w=0 23: (bf) r1 = r0 ; R0=map_value(off=0,ks=4,vs=48,imm=0) R1_w=map_value(off=0,ks=4,vs=48,imm=0) 24: (0f) r0 += r6 last_idx 24 first_idx 19 regs=40 stack=0 before 23: (bf) r1 = r0 regs=40 stack=0 before 22: (27) r6 *= 8192 regs=40 stack=0 before 21: (77) r6 >>= 10 regs=40 stack=0 before 19: (55) if r0 != 0x0 goto pc+1 parent didn't have regs=40 stack=0 marks: R0_rw=map_value_or_null(id=1,off=0,ks=4,vs=48,imm=0) R6_rw=P0 R7=0 R8=0 R9=0 R10=fp0 fp-8=mmmm???? last_idx 18 first_idx 9 regs=40 stack=0 before 18: (85) call bpf_map_lookup_elem#1 regs=40 stack=0 before 17: (07) r2 += -4 regs=40 stack=0 before 16: (bf) r2 = r10 regs=40 stack=0 before 15: (bf) r1 = r4 regs=40 stack=0 before 13: (18) r4 = 0xffff8ad3886c2a00 regs=40 stack=0 before 12: (63) *(u32 *)(r10 -4) = r0 regs=40 stack=0 before 11: (b7) r0 = 0 regs=40 stack=0 before 10: (b7) r6 = 0 25: (79) r3 = *(u64 *)(r0 +0) ; R0_w=map_value(off=0,ks=4,vs=48,imm=0) R3_w=scalar() 26: (7b) *(u64 *)(r1 +0) = r3 ; R1_w=map_value(off=0,ks=4,vs=48,imm=0) R3_w=scalar() 27: (95) exit

from 9 to 11: R1=ctx(off=0,imm=0) R6=0 R7=0 R8=0 R9=0 R10=fp0 11: (b7) r0 = 0 ; R0_w=0 12: (63) *(u32 *)(r10 -4) = r0 last_idx 12 first_idx 11 regs=1 stack=0 before 11: (b7) r0 = 0 13: R0_w=0 R10=fp0 fp-8=0000???? 13: (18) r4 = 0xffff8ad3886c2a00 ; R4_w=map_ptr(off=0,ks=4,vs=48,imm=0) 15: (bf) r1 = r4 ; R1_w=map_ptr(off=0,ks=4,vs=48,imm=0) R4_w=map_ptr(off=0,ks=4,vs=48,imm=0) 16: (bf) r2 = r10 ; R2_w=fp0 R10=fp0 17: (07) r2 += -4 ; R2_w=fp-4 18: (85) call bpf_map_lookup_elem#1 frame 0: propagating r6 last_idx 19 first_idx 11 regs=40 stack=0 before 18: (85) call bpf_map_lookup_elem#1 regs=40 stack=0 before 17: (07) r2 += -4 regs=40 stack=0 before 16: (bf) r2 = r10 regs=40 stack=0 before 15: (bf) r1 = r4 regs=40 stack=0 before 13: (18) r4 = 0xffff8ad3886c2a00 regs=40 stack=0 before 12: (63) *(u32 *)(r10 -4) = r0 regs=40 stack=0 before 11: (b7) r0 = 0 parent didn't have regs=40 stack=0 marks: R1=ctx(off=0,imm=0) R6_r=P0 R7=0 R8=0 R9=0 R10=fp0 last_idx 9 first_idx 9 regs=40 stack=0 before 9: (bd) if r6 <= r9 goto pc+1 parent didn't have regs=40 stack=0 marks: R1=ctx(off=0,imm=0) R6_rw=Pscalar() R7_w=0 R8_w=0 R9_rw=0 R10=fp0 last_idx 8 first_idx 0 regs=40 stack=0 before 8: (b7) r9 = 0 regs=40 stack=0 before 7: (97) r6 %= 1 regs=40 stack=0 before 6: (bd) if r6 <= r9 goto pc+2 regs=40 stack=0 before 5: (05) goto pc+0 regs=40 stack=0 before 4: (97) r6 %= 1025 regs=40 stack=0 before 3: (b7) r9 = -2147483648 regs=40 stack=0 before 2: (b7) r8 = 0 regs=40 stack=0 before 1: (b7) r7 = 0 regs=40 stack=0 before 0: (b7) r6 = 1024 19: safe frame 0: propagating r6 last_idx 9 first_idx 0 regs=40 stack=0 before 6: (bd) if r6 <= r9 goto pc+2 regs=40 stack=0 before 5: (05) goto pc+0 regs=40 stack=0 before 4: (97) r6 %= 1025 regs=40 stack=0 before 3: (b7) r9 = -2147483648 regs=40 stack=0 before 2: (b7) r8 = 0 regs=40 stack=0 before 1: (b7) r7 = 0 regs=40 stack=0 before 0: (b7) r6 = 1024

from 6 to 9: safe verification time 110 usec stack depth 4 processed 36 insns (limit 1000000) max_states_per_insn 0 total_states 3 peak_states 3 mark_read 2

The verifier considers this program as safe by mistakenly pruning unsafe code paths. In the above func#0, code lines 0-10 are of interest. In line 0-3 registers r6 to r9 are initialized with known scalar values. In line 4 the register r6 is reset to an unknown scalar given the verifier does not track modulo operations. Due to this, the verifier can also not determine precisely which branches in line 6 and 9 are taken, therefore it needs to explore them both.

As can be seen, the verifier starts with exploring the false/fall-through paths first. The 'from 19 to 21' path has both r6=0 and r9=0 and the pointer arithmetic on r0 += r6 is therefore considered safe. Given the arithmetic, r6 is correctly marked for precision tracking where backtracking kicks in where it walks back the current path all the way where r6 was set to 0 in the fall-through branch.

Next, the pruning logics pops the path 'from 9 to 11' from the stack. Also here, the state of the registers is the same, that is, r6=0 and r9=0, so that at line 19 the path can be pruned as it is considered safe. It is interesting to note that the conditional in line 9 turned r6 into a more precise state, that is, in the fall-through path at the beginning of line 10, it is R6=scalar(umin=1), and in the branch-taken path (which is analyzed here) at the beginning of line 11, r6 turned into a known const r6=0 as r9=0 prior to that and therefore (unsigned) r6 <= 0 concludes that r6 must be 0 (**):

[...] ; R6_w=scalar() 9: (bd) if r6 <= r9 goto pc+1 ; R6=scalar(umin=1) R9=0 [...]

from 9 to 11: R1=ctx(off=0,imm=0) R6=0 R7=0 R8=0 R9=0 R10=fp0 [...]

The next path is 'from 6 to 9'. The verifier considers the old and current state equivalent, and therefore prunes the search incorrectly. Looking into the two states which are being compared by the pruning logic at line 9, the old state consists of R6_rwD=Pscalar() R9_rwD=0 R10=fp0 and the new state consists of R1=ctx(off=0,imm=0) R6_w=scalar(umax=18446744071562067968) R7_w=0 R8_w=0 R9_w=-2147483648 R10=fp0. While r6 had the reg->precise flag correctly set in the old state, r9 did not. Both r6'es are considered as equivalent given the old one is a superset of the current, more precise one, however, r9's actual values (0 vs 0x80000000) mismatch. Given the old r9 did not have reg->precise flag set, the verifier does not consider the register as contributing to the precision state of r6, and therefore it considered both r9 states as equivalent. However, for this specific pruned path (which is also the actual path taken at runtime), register r6 will be 0x400 and r9 0x80000000 when reaching line 21, thus oob-accessing the map.

The purpose of precision tracking is to initially mark registers (including spilled ones) as imprecise to help verifier's pruning logic finding equivalent states it can then prune if they don't contribute to the program's safety aspects. For example, if registers are used for pointer arithmetic or to pass constant length to a helper, then the verifier sets reg->precise flag and backtracks the BPF program instruction sequence and chain of verifier states to ensure that the given register or stack slot including their dependencies are marked as precisely tracked scalar. This also includes any other registers and slots that contribute to a tracked state of given registers/stack slot. This backtracking relies on recorded jmp_history and is able to traverse entire chain of parent states. This process ends only when all the necessary registers/slots and their transitive dependencies are marked as precise.

The backtrack_insn() is called from the current instruction up to the first instruction, and its purpose is to compute a bitmask of registers and stack slots that need precision tracking in the parent's verifier state. For example, if a current instruction is r6 = r7, then r6 needs precision after this instruction and r7 needs precision before this instruction, that is, in the parent state. Hence for the latter r7 is marked and r6 unmarked.

For the class of jmp/jmp32 instructions, backtrack_insn() today only looks at call and exit instructions and for all other conditionals the masks remain as-is. However, in the given situation register r6 has a dependency on r9 (as described above in **), so also that one needs to be marked for precision tracking. In other words, if an imprecise register influences a precise one, then the imprecise register should also be marked precise. Meaning, in the parent state both dest and src register need to be tracked for precision and therefore the marking must be more conservative by setting reg->precise flag for both. The precision propagation needs to cover both for the conditional: if the src reg was marked but not the dst reg and vice versa.

After the fix the program is correctly rejected:

func#0 @0 0: R1=ctx(off=0,imm=0) R10=fp0 0: (b7) r6 = 1024 ; R6_w=1024 1: (b7) r7 = 0 ; R7_w=0 2: (b7) r8 = 0 ; R8_w=0 3: (b7) r9 = -2147483648 ; R9_w=-2147483648 4: (97) r6 %= 1025 ; R6_w=scalar() 5: (05) goto pc+0 6: (bd) if r6 <= r9 goto pc+2 ; R6_w=scalar(umin=18446744071562067969,var_off=(0xffffffff80000000; 0x7fffffff),u32_min=-2147483648) R9_w=-2147483648 7: (97) r6 %= 1 ; R6_w=scalar() 8: (b7) r9 = 0 ; R9=0 9: (bd) if r6 <= r9 goto pc+1 ; R6=scalar(umin=1) R9=0 10: (b7) r6 = 0 ; R6_w=0 11: (b7) r0 = 0 ; R0_w=0 12: (63) *(u32 *)(r10 -4) = r0 last_idx 12 first_idx 9 regs=1 stack=0 before 11: (b7) r0 = 0 13: R0_w=0 R10=fp0 fp-8=0000???? 13: (18) r4 = 0xffff9290dc5bfe00 ; R4_w=map_ptr(off=0,ks=4,vs=48,imm=0) 15: (bf) r1 = r4 ; R1_w=map_ptr(off=0,ks=4,vs=48,imm=0) R4_w=map_ptr(off=0,ks=4,vs=48,imm=0) 16: (bf) r2 = r10 ; R2_w=fp0 R10=fp0 17: (07) r2 += -4 ; R2_w=fp-4 18: (85) call bpf_map_lookup_elem#1 ; R0=map_value_or_null(id=1,off=0,ks=4,vs=48,imm=0) 19: (55) if r0 != 0x0 goto pc+1 ; R0=0 20: (95) exit

from 19 to 21: R0=map_value(off=0,ks=4,vs=48,imm=0) R6=0 R7=0 R8=0 R9=0 R10=fp0 fp-8=mmmm???? 21: (77) r6 >>= 10 ; R6_w=0 22: (27) r6 *= 8192 ; R6_w=0 23: (bf) r1 = r0 ; R0=map_value(off=0,ks=4,vs=48,imm=0) R1_w=map_value(off=0,ks=4,vs=48,imm=0) 24: (0f) r0 += r6 last_idx 24 first_idx 19 regs=40 stack=0 before 23: (bf) r1 = r0 regs=40 stack=0 before 22: (27) r6 *= 8192 regs=40 stack=0 before 21: (77) r6 >>= 10 regs=40 stack=0 before 19: (55) if r0 != 0x0 goto pc+1 parent didn't have regs=40 stack=0 marks: R0_rw=map_value_or_null(id=1,off=0,ks=4,vs=48,imm=0) R6_rw=P0 R7=0 R8=0 R9=0 R10=fp0 fp-8=mmmm???? last_idx 18 first_idx 9 regs=40 stack=0 before 18: (85) call bpf_map_lookup_elem#1 regs=40 stack=0 before 17: (07) r2 += -4 regs=40 stack=0 before 16: (bf) r2 = r10 regs=40 stack=0 before 15: (bf) r1 = r4 regs=40 stack=0 before 13: (18) r4 = 0xffff9290dc5bfe00 regs=40 stack=0 before 12: (63) *(u32 *)(r10 -4) = r0 regs=40 stack=0 before 11: (b7) r0 = 0 regs=40 stack=0 before 10: (b7) r6 = 0 25: (79) r3 = *(u64 *)(r0 +0) ; R0_w=map_value(off=0,ks=4,vs=48,imm=0) R3_w=scalar() 26: (7b) *(u64 *)(r1 +0) = r3 ; R1_w=map_value(off=0,ks=4,vs=48,imm=0) R3_w=scalar() 27: (95) exit

from 9 to 11: R1=ctx(off=0,imm=0) R6=0 R7=0 R8=0 R9=0 R10=fp0 11: (b7) r0 = 0 ; R0_w=0 12: (63) *(u32 *)(r10 -4) = r0 last_idx 12 first_idx 11 regs=1 stack=0 before 11: (b7) r0 = 0 13: R0_w=0 R10=fp0 fp-8=0000???? 13: (18) r4 = 0xffff9290dc5bfe00 ; R4_w=map_ptr(off=0,ks=4,vs=48,imm=0) 15: (bf) r1 = r4 ; R1_w=map_ptr(off=0,ks=4,vs=48,imm=0) R4_w=map_ptr(off=0,ks=4,vs=48,imm=0) 16: (bf) r2 = r10 ; R2_w=fp0 R10=fp0 17: (07) r2 += -4 ; R2_w=fp-4 18: (85) call bpf_map_lookup_elem#1 frame 0: propagating r6 last_idx 19 first_idx 11 regs=40 stack=0 before 18: (85) call bpf_map_lookup_elem#1 regs=40 stack=0 before 17: (07) r2 += -4 regs=40 stack=0 before 16: (bf) r2 = r10 regs=40 stack=0 before 15: (bf) r1 = r4 regs=40 stack=0 before 13: (18) r4 = 0xffff9290dc5bfe00 regs=40 stack=0 before 12: (63) *(u32 *)(r10 -4) = r0 regs=40 stack=0 before 11: (b7) r0 = 0 parent didn't have regs=40 stack=0 marks: R1=ctx(off=0,imm=0) R6_r=P0 R7=0 R8=0 R9=0 R10=fp0 last_idx 9 first_idx 9 regs=40 stack=0 before 9: (bd) if r6 <= r9 goto pc+1 parent didn't have regs=240 stack=0 marks: R1=ctx(off=0,imm=0) R6_rw=Pscalar() R7_w=0 R8_w=0 R9_rw=P0 R10=fp0 last_idx 8 first_idx 0 regs=240 stack=0 before 8: (b7) r9 = 0 regs=40 stack=0 before 7: (97) r6 %= 1 regs=40 stack=0 before 6: (bd) if r6 <= r9 goto pc+2 regs=240 stack=0 before 5: (05) goto pc+0 regs=240 stack=0 before 4: (97) r6 %= 1025 regs=240 stack=0 before 3: (b7) r9 = -2147483648 regs=40 stack=0 before 2: (b7) r8 = 0 regs=40 stack=0 before 1: (b7) r7 = 0 regs=40 stack=0 before 0: (b7) r6 = 1024 19: safe

from 6 to 9: R1=ctx(off=0,imm=0) R6_w=scalar(umax=18446744071562067968) R7_w=0 R8_w=0 R9_w=-2147483648 R10=fp0 9: (bd) if r6 <= r9 goto pc+1 last_idx 9 first_idx 0 regs=40 stack=0 before 6: (bd) if r6 <= r9 goto pc+2 regs=240 stack=0 before 5: (05) goto pc+0 regs=240 stack=0 before 4: (97) r6 %= 1025 regs=240 stack=0 before 3: (b7) r9 = -2147483648 regs=40 stack=0 before 2: (b7) r8 = 0 regs=40 stack=0 before 1: (b7) r7 = 0 regs=40 stack=0 before 0: (b7) r6 = 1024 last_idx 9 first_idx 0 regs=200 stack=0 before 6: (bd) if r6 <= r9 goto pc+2 regs=240 stack=0 before 5: (05) goto pc+0 regs=240 stack=0 before 4: (97) r6 %= 1025 regs=240 stack=0 before 3: (b7) r9 = -2147483648 regs=40 stack=0 before 2: (b7) r8 = 0 regs=40 stack=0 before 1: (b7) r7 = 0 regs=40 stack=0 before 0: (b7) r6 = 1024 11: R6=scalar(umax=18446744071562067968) R9=-2147483648 11: (b7) r0 = 0 ; R0_w=0 12: (63) *(u32 *)(r10 -4) = r0 last_idx 12 first_idx 11 regs=1 stack=0 before 11: (b7) r0 = 0 13: R0_w=0 R10=fp0 fp-8=0000???? 13: (18) r4 = 0xffff9290dc5bfe00 ; R4_w=map_ptr(off=0,ks=4,vs=48,imm=0) 15: (bf) r1 = r4 ; R1_w=map_ptr(off=0,ks=4,vs=48,imm=0) R4_w=map_ptr(off=0,ks=4,vs=48,imm=0) 16: (bf) r2 = r10 ; R2_w=fp0 R10=fp0 17: (07) r2 += -4 ; R2_w=fp-4 18: (85) call bpf_map_lookup_elem#1 ; R0_w=map_value_or_null(id=3,off=0,ks=4,vs=48,imm=0) 19: (55) if r0 != 0x0 goto pc+1 ; R0_w=0 20: (95) exit

from 19 to 21: R0=map_value(off=0,ks=4,vs=48,imm=0) R6=scalar(umax=18446744071562067968) R7=0 R8=0 R9=-2147483648 R10=fp0 fp-8=mmmm???? 21: (77) r6 >>= 10 ; R6_w=scalar(umax=18014398507384832,var_off=(0x0; 0x3fffffffffffff)) 22: (27) r6 *= 8192 ; R6_w=scalar(smax=9223372036854767616,umax=18446744073709543424,var_off=(0x0; 0xffffffffffffe000),s32_max=2147475456,u32_max=-8192) 23: (bf) r1 = r0 ; R0=map_value(off=0,ks=4,vs=48,imm=0) R1_w=map_value(off=0,ks=4,vs=48,imm=0) 24: (0f) r0 += r6 last_idx 24 first_idx 21 regs=40 stack=0 before 23: (bf) r1 = r0 regs=40 stack=0 before 22: (27) r6 *= 8192 regs=40 stack=0 before 21: (77) r6 >>= 10 parent didn't have regs=40 stack=0 marks: R0_rw=map_value(off=0,ks=4,vs=48,imm=0) R6_r=Pscalar(umax=18446744071562067968) R7=0 R8=0 R9=-2147483648 R10=fp0 fp-8=mmmm???? last_idx 19 first_idx 11 regs=40 stack=0 before 19: (55) if r0 != 0x0 goto pc+1 regs=40 stack=0 before 18: (85) call bpf_map_lookup_elem#1 regs=40 stack=0 before 17: (07) r2 += -4 regs=40 stack=0 before 16: (bf) r2 = r10 regs=40 stack=0 before 15: (bf) r1 = r4 regs=40 stack=0 before 13: (18) r4 = 0xffff9290dc5bfe00 regs=40 stack=0 before 12: (63) *(u32 *)(r10 -4) = r0 regs=40 stack=0 before 11: (b7) r0 = 0 parent didn't have regs=40 stack=0 marks: R1=ctx(off=0,imm=0) R6_rw=Pscalar(umax=18446744071562067968) R7_w=0 R8_w=0 R9_w=-2147483648 R10=fp0 last_idx 9 first_idx 0 regs=40 stack=0 before 9: (bd) if r6 <= r9 goto pc+1 regs=240 stack=0 before 6: (bd) if r6 <= r9 goto pc+2 regs=240 stack=0 before 5: (05) goto pc+0 regs=240 stack=0 before 4: (97) r6 %= 1025 regs=240 stack=0 before 3: (b7) r9 = -2147483648 regs=40 stack=0 before 2: (b7) r8 = 0 regs=40 stack=0 before 1: (b7) r7 = 0 regs=40 stack=0 before 0: (b7) r6 = 1024 math between map_value pointer and register with unbounded min value is not allowed verification time 886 usec stack depth 4 processed 49 insns (limit 1000000) max_states_per_insn 1 total_states 5 peak_states 5 mark_read 2

Fixes: b5dc0163d8fd ("bpf: precise scalar_value tracking") Reported-by: Juan Jose Lopez Jaimez jjlopezjaimez@google.com Reported-by: Meador Inge meadori@google.com Reported-by: Simon Scannell simonscannell@google.com Reported-by: Nenad Stojanovski thenenadx@google.com Signed-off-by: Daniel Borkmann daniel@iogearbox.net Co-developed-by: Andrii Nakryiko andrii@kernel.org Signed-off-by: Andrii Nakryiko andrii@kernel.org Reviewed-by: John Fastabend john.fastabend@gmail.com Reviewed-by: Juan Jose Lopez Jaimez jjlopezjaimez@google.com Reviewed-by: Meador Inge meadori@google.com Reviewed-by: Simon Scannell simonscannell@google.com Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/bpf/verifier.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 1c95d97e7aa53..37d4b5f5ec0c3 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -2279,6 +2279,21 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, } } else if (opcode == BPF_EXIT) { return -ENOTSUPP; + } else if (BPF_SRC(insn->code) == BPF_X) { + if (!(*reg_mask & (dreg | sreg))) + return 0; + /* dreg <cond> sreg + * Both dreg and sreg need precision before + * this insn. If only sreg was marked precise + * before it would be equally necessary to + * propagate it to dreg. + */ + *reg_mask |= (sreg | dreg); + /* else dreg <cond> K + * Only dreg still needs precision before + * this insn, so for the K-based conditional + * there is nothing new to be marked. + */ } } else if (class == BPF_LD) { if (!(*reg_mask & dreg))

From: Douglas Raillard douglas.raillard@arm.com

[ Upstream commit 0b04d4c0542e8573a837b1d81b94209e48723b25 ]

Fix the nid_t field so that its size is correctly reported in the text format embedded in trace.dat files. As it stands, it is reported as being of size 4:

field:nid_t nid[3]; offset:24; size:4; signed:0;

Instead of 12:

field:nid_t nid[3]; offset:24; size:12; signed:0;

This also fixes the reported offset of subsequent fields so that they match with the actual struct layout.

Signed-off-by: Douglas Raillard douglas.raillard@arm.com Reviewed-by: Mukesh Ojha quic_mojha@quicinc.com Reviewed-by: Chao Yu chao@kernel.org Signed-off-by: Jaegeuk Kim jaegeuk@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- include/trace/events/f2fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h index 4cb055af1ec0b..f5dcf7c9b7076 100644 --- a/include/trace/events/f2fs.h +++ b/include/trace/events/f2fs.h @@ -513,7 +513,7 @@ TRACE_EVENT(f2fs_truncate_partial_nodes, TP_STRUCT__entry( __field(dev_t, dev) __field(ino_t, ino) - __field(nid_t, nid[3]) + __array(nid_t, nid, 3) __field(int, depth) __field(int, err) ),

From: Frank Crawford frank@crawford.emu.id.au

[ Upstream commit b7c994f8c35e916e27c60803bb21457bc1373500 ]

Add support for A320M-S2H V2. Tested using module force_load option.

Signed-off-by: Frank Crawford frank@crawford.emu.id.au Acked-by: Thomas Weißschuh linux@weissschuh.net Link: https://lore.kernel.org/r/20230318091441.1240921-1-frank@crawford.emu.id.au Reviewed-by: Hans de Goede hdegoede@redhat.com Signed-off-by: Hans de Goede hdegoede@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/platform/x86/gigabyte-wmi.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/drivers/platform/x86/gigabyte-wmi.c b/drivers/platform/x86/gigabyte-wmi.c index 0163e912fafec..aea4f3144b68f 100644 --- a/drivers/platform/x86/gigabyte-wmi.c +++ b/drivers/platform/x86/gigabyte-wmi.c @@ -140,6 +140,7 @@ static u8 gigabyte_wmi_detect_sensor_usability(struct wmi_device *wdev) }}

static const struct dmi_system_id gigabyte_wmi_known_working_platforms[] = { + DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("A320M-S2H V2-CF"), DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B450M DS3H-CF"), DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B450M DS3H WIFI-CF"), DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B450M S2H V2"),

From: Tomas Henzl thenzl@redhat.com

[ Upstream commit 0808ed6ebbc292222ca069d339744870f6d801da ]

If crash_dump_buf is not allocated then crash dump can't be available. Replace logical 'and' with 'or'.

Signed-off-by: Tomas Henzl thenzl@redhat.com Link: https://lore.kernel.org/r/20230324135249.9733-1-thenzl@redhat.com Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/scsi/megaraid/megaraid_sas_base.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c index 88e164e3d2eac..f7da1876e7a38 100644 --- a/drivers/scsi/megaraid/megaraid_sas_base.c +++ b/drivers/scsi/megaraid/megaraid_sas_base.c @@ -3302,7 +3302,7 @@ fw_crash_buffer_show(struct device *cdev,

spin_lock_irqsave(&instance->crashdump_lock, flags); buff_offset = instance->fw_crash_buffer_offset; - if (!instance->crash_dump_buf && + if (!instance->crash_dump_buf || !((instance->fw_crash_state == AVAILABLE) || (instance->fw_crash_state == COPYING))) { dev_err(&instance->pdev->dev,

From: Álvaro Fernández Rojas noltari@gmail.com

[ Upstream commit 45977e58ce65ed0459edc9a0466d9dfea09463f5 ]

Implement phy_read16() and phy_write16() ops for B53 MMAP to avoid accessing B53_PORT_MII_PAGE registers which hangs the device. This access should be done through the MDIO Mux bus controller.

Signed-off-by: Álvaro Fernández Rojas noltari@gmail.com Acked-by: Florian Fainelli f.fainelli@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/dsa/b53/b53_mmap.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+)

diff --git a/drivers/net/dsa/b53/b53_mmap.c b/drivers/net/dsa/b53/b53_mmap.c index 3388f620fac99..ca6f53c630676 100644 --- a/drivers/net/dsa/b53/b53_mmap.c +++ b/drivers/net/dsa/b53/b53_mmap.c @@ -216,6 +216,18 @@ static int b53_mmap_write64(struct b53_device *dev, u8 page, u8 reg, return 0; }

+static int b53_mmap_phy_read16(struct b53_device *dev, int addr, int reg, + u16 *value) +{ + return -EIO; +} + +static int b53_mmap_phy_write16(struct b53_device *dev, int addr, int reg, + u16 value) +{ + return -EIO; +} + static const struct b53_io_ops b53_mmap_ops = { .read8 = b53_mmap_read8, .read16 = b53_mmap_read16, @@ -227,6 +239,8 @@ static const struct b53_io_ops b53_mmap_ops = { .write32 = b53_mmap_write32, .write48 = b53_mmap_write48, .write64 = b53_mmap_write64, + .phy_read16 = b53_mmap_phy_read16, + .phy_write16 = b53_mmap_phy_write16, };

static int b53_mmap_probe_of(struct platform_device *pdev,

From: Sagi Grimberg sagi@grimberg.me

[ Upstream commit 88eaba80328b31ef81813a1207b4056efd7006a6 ]

When we allocate a nvme-tcp queue, we set the data_ready callback before we actually need to use it. This creates the potential that if a stray controller sends us data on the socket before we connect, we can trigger the io_work and start consuming the socket.

In this case reported: we failed to allocate one of the io queues, and as we start releasing the queues that we already allocated, we get a UAF [1] from the io_work which is running before it should really.

Fix this by setting the socket ops callbacks only before we start the queue, so that we can't accidentally schedule the io_work in the initialization phase before the queue started. While we are at it, rename nvme_tcp_restore_sock_calls to pair with nvme_tcp_setup_sock_ops.

[1]: [16802.107284] nvme nvme4: starting error recovery [16802.109166] nvme nvme4: Reconnecting in 10 seconds... [16812.173535] nvme nvme4: failed to connect socket: -111 [16812.173745] nvme nvme4: Failed reconnect attempt 1 [16812.173747] nvme nvme4: Reconnecting in 10 seconds... [16822.413555] nvme nvme4: failed to connect socket: -111 [16822.413762] nvme nvme4: Failed reconnect attempt 2 [16822.413765] nvme nvme4: Reconnecting in 10 seconds... [16832.661274] nvme nvme4: creating 32 I/O queues. [16833.919887] BUG: kernel NULL pointer dereference, address: 0000000000000088 [16833.920068] nvme nvme4: Failed reconnect attempt 3 [16833.920094] #PF: supervisor write access in kernel mode [16833.920261] nvme nvme4: Reconnecting in 10 seconds... [16833.920368] #PF: error_code(0x0002) - not-present page [16833.921086] Workqueue: nvme_tcp_wq nvme_tcp_io_work [nvme_tcp] [16833.921191] RIP: 0010:_raw_spin_lock_bh+0x17/0x30 ... [16833.923138] Call Trace: [16833.923271] <TASK> [16833.923402] lock_sock_nested+0x1e/0x50 [16833.923545] nvme_tcp_try_recv+0x40/0xa0 [nvme_tcp] [16833.923685] nvme_tcp_io_work+0x68/0xa0 [nvme_tcp] [16833.923824] process_one_work+0x1e8/0x390 [16833.923969] worker_thread+0x53/0x3d0 [16833.924104] ? process_one_work+0x390/0x390 [16833.924240] kthread+0x124/0x150 [16833.924376] ? set_kthread_struct+0x50/0x50 [16833.924518] ret_from_fork+0x1f/0x30 [16833.924655] </TASK>

Reported-by: Yanjun Zhang zhangyanjun@cestc.cn Signed-off-by: Sagi Grimberg sagi@grimberg.me Tested-by: Yanjun Zhang zhangyanjun@cestc.com Signed-off-by: Christoph Hellwig hch@lst.de Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/nvme/host/tcp.c | 46 +++++++++++++++++++++++------------------ 1 file changed, 26 insertions(+), 20 deletions(-)

diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 96d8d7844e846..fb47d0603e051 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -1563,22 +1563,7 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl, if (ret) goto err_init_connect;

- queue->rd_enabled = true; set_bit(NVME_TCP_Q_ALLOCATED, &queue->flags); - nvme_tcp_init_recv_ctx(queue); - - write_lock_bh(&queue->sock->sk->sk_callback_lock); - queue->sock->sk->sk_user_data = queue; - queue->state_change = queue->sock->sk->sk_state_change; - queue->data_ready = queue->sock->sk->sk_data_ready; - queue->write_space = queue->sock->sk->sk_write_space; - queue->sock->sk->sk_data_ready = nvme_tcp_data_ready; - queue->sock->sk->sk_state_change = nvme_tcp_state_change; - queue->sock->sk->sk_write_space = nvme_tcp_write_space; -#ifdef CONFIG_NET_RX_BUSY_POLL - queue->sock->sk->sk_ll_usec = 1; -#endif - write_unlock_bh(&queue->sock->sk->sk_callback_lock);

return 0;

@@ -1598,7 +1583,7 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl, return ret; }

-static void nvme_tcp_restore_sock_calls(struct nvme_tcp_queue *queue) +static void nvme_tcp_restore_sock_ops(struct nvme_tcp_queue *queue) { struct socket *sock = queue->sock;

@@ -1613,7 +1598,7 @@ static void nvme_tcp_restore_sock_calls(struct nvme_tcp_queue *queue) static void __nvme_tcp_stop_queue(struct nvme_tcp_queue *queue) { kernel_sock_shutdown(queue->sock, SHUT_RDWR); - nvme_tcp_restore_sock_calls(queue); + nvme_tcp_restore_sock_ops(queue); cancel_work_sync(&queue->io_work); }

@@ -1628,21 +1613,42 @@ static void nvme_tcp_stop_queue(struct nvme_ctrl *nctrl, int qid) mutex_unlock(&queue->queue_lock); }

+static void nvme_tcp_setup_sock_ops(struct nvme_tcp_queue *queue) +{ + write_lock_bh(&queue->sock->sk->sk_callback_lock); + queue->sock->sk->sk_user_data = queue; + queue->state_change = queue->sock->sk->sk_state_change; + queue->data_ready = queue->sock->sk->sk_data_ready; + queue->write_space = queue->sock->sk->sk_write_space; + queue->sock->sk->sk_data_ready = nvme_tcp_data_ready; + queue->sock->sk->sk_state_change = nvme_tcp_state_change; + queue->sock->sk->sk_write_space = nvme_tcp_write_space; +#ifdef CONFIG_NET_RX_BUSY_POLL + queue->sock->sk->sk_ll_usec = 1; +#endif + write_unlock_bh(&queue->sock->sk->sk_callback_lock); +} + static int nvme_tcp_start_queue(struct nvme_ctrl *nctrl, int idx) { struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(nctrl); + struct nvme_tcp_queue *queue = &ctrl->queues[idx]; int ret;

+ queue->rd_enabled = true; + nvme_tcp_init_recv_ctx(queue); + nvme_tcp_setup_sock_ops(queue); + if (idx) ret = nvmf_connect_io_queue(nctrl, idx); else ret = nvmf_connect_admin_queue(nctrl);

if (!ret) { - set_bit(NVME_TCP_Q_LIVE, &ctrl->queues[idx].flags); + set_bit(NVME_TCP_Q_LIVE, &queue->flags); } else { - if (test_bit(NVME_TCP_Q_ALLOCATED, &ctrl->queues[idx].flags)) - __nvme_tcp_stop_queue(&ctrl->queues[idx]); + if (test_bit(NVME_TCP_Q_ALLOCATED, &queue->flags)) + __nvme_tcp_stop_queue(queue); dev_err(nctrl->device, "failed to connect queue: %d ret=%d\n", idx, ret); }

From: Hans de Goede hdegoede@redhat.com

[ Upstream commit 52f91e51944808d83dfe2d5582601b5e84e472cc ]

Add "X570S AORUS ELITE" to known working boards

Reported-by: Brandon Nielsen nielsenb@jetfuse.net Link: https://lore.kernel.org/r/20230331014902.7864-1-nielsenb@jetfuse.net Signed-off-by: Hans de Goede hdegoede@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/platform/x86/gigabyte-wmi.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/drivers/platform/x86/gigabyte-wmi.c b/drivers/platform/x86/gigabyte-wmi.c index aea4f3144b68f..bf1b98dd00b99 100644 --- a/drivers/platform/x86/gigabyte-wmi.c +++ b/drivers/platform/x86/gigabyte-wmi.c @@ -156,6 +156,7 @@ static const struct dmi_system_id gigabyte_wmi_known_working_platforms[] = { DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("X570 GAMING X"), DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("X570 I AORUS PRO WIFI"), DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("X570 UD"), + DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("X570S AORUS ELITE"), DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("Z690M AORUS ELITE AX DDR4"), { } };

From: Brian Masney bmasney@redhat.com

commit b1cb00d51e361cf5af93649917d9790e1623647e upstream.

tsl2772_read_prox_diodes() will correctly parse the properties from device tree to determine which proximity diode(s) to read from, however it didn't actually set this value on the struct tsl2772_settings. Let's go ahead and fix that.

Reported-by: Tom Rix trix@redhat.com Link: https://lore.kernel.org/lkml/20230327120823.1369700-1-trix@redhat.com/ Fixes: 94cd1113aaa0 ("iio: tsl2772: add support for reading proximity led settings from device tree") Signed-off-by: Brian Masney bmasney@redhat.com Link: https://lore.kernel.org/r/20230404011455.339454-1-bmasney@redhat.com Cc: Stable@vger.kernel.org Signed-off-by: Jonathan Cameron Jonathan.Cameron@huawei.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/iio/light/tsl2772.c | 1 + 1 file changed, 1 insertion(+)

--- a/drivers/iio/light/tsl2772.c +++ b/drivers/iio/light/tsl2772.c @@ -606,6 +606,7 @@ static int tsl2772_read_prox_diodes(stru return -EINVAL; } } + chip->settings.prox_diode = prox_diode_mask;

return 0; }

From: Greg Kroah-Hartman gregkh@linuxfoundation.org

commit 4b6d621c9d859ff89e68cebf6178652592676013 upstream.

When calling dev_set_name() memory is allocated for the name for the struct device. Once that structure device is registered, or attempted to be registerd, with the driver core, the driver core will handle cleaning up that memory when the device is removed from the system.

Unfortunatly for the memstick code, there is an error path that causes the struct device to never be registered, and so the memory allocated in dev_set_name will be leaked. Fix that leak by manually freeing it right before the memory for the device is freed.

Cc: Maxim Levitsky maximlevitsky@gmail.com Cc: Alex Dubov oakad@yahoo.com Cc: Ulf Hansson ulf.hansson@linaro.org Cc: "Rafael J. Wysocki" rafael@kernel.org Cc: Hans de Goede hdegoede@redhat.com Cc: Kay Sievers kay.sievers@vrfy.org Cc: linux-mmc@vger.kernel.org Fixes: 0252c3b4f018 ("memstick: struct device - replace bus_id with dev_name(), dev_set_name()") Cc: stable stable@kernel.org Co-developed-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Co-developed-by: Mirsad Goran Todorovac mirsad.todorovac@alu.unizg.hr Signed-off-by: Mirsad Goran Todorovac mirsad.todorovac@alu.unizg.hr Link: https://lore.kernel.org/r/20230401200327.16800-1-gregkh@linuxfoundation.org Signed-off-by: Ulf Hansson ulf.hansson@linaro.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/memstick/core/memstick.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)

--- a/drivers/memstick/core/memstick.c +++ b/drivers/memstick/core/memstick.c @@ -410,6 +410,7 @@ static struct memstick_dev *memstick_all return card; err_out: host->card = old_card; + kfree_const(card->dev.kobj.name); kfree(card); return NULL; } @@ -468,8 +469,10 @@ static void memstick_check(struct work_s put_device(&card->dev); host->card = NULL; } - } else + } else { + kfree_const(card->dev.kobj.name); kfree(card); + } }

out_power_off:

From: Bhavya Kapoor b-kapoor@ti.com

commit 2265098fd6a6272fde3fd1be5761f2f5895bd99a upstream.

Timing Information in Datasheet assumes that HIGH_SPEED_ENA=1 should be set for SDR12 and SDR25 modes. But sdhci_am654 driver clears HIGH_SPEED_ENA register. Thus, Modify sdhci_am654 to not clear HIGH_SPEED_ENA (HOST_CONTROL[2]) bit for SDR12 and SDR25 speed modes.

Fixes: e374e87538f4 ("mmc: sdhci_am654: Clear HISPD_ENA in some lower speed modes") Signed-off-by: Bhavya Kapoor b-kapoor@ti.com Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230317092711.660897-1-b-kapoor@ti.com Signed-off-by: Ulf Hansson ulf.hansson@linaro.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/mmc/host/sdhci_am654.c | 2 -- 1 file changed, 2 deletions(-)

--- a/drivers/mmc/host/sdhci_am654.c +++ b/drivers/mmc/host/sdhci_am654.c @@ -351,8 +351,6 @@ static void sdhci_am654_write_b(struct s */ case MMC_TIMING_SD_HS: case MMC_TIMING_MMC_HS: - case MMC_TIMING_UHS_SDR12: - case MMC_TIMING_UHS_SDR25: val &= ~SDHCI_CTRL_HISPD; } }

From: Peter Xu peterx@redhat.com

commit dd47ac428c3f5f3bcabe845f36be870fe6c20784 upstream.

Khugepaged collapse an anonymous thp in two rounds of scans. The 2nd round done in __collapse_huge_page_isolate() after hpage_collapse_scan_pmd(), during which all the locks will be released temporarily. It means the pgtable can change during this phase before 2nd round starts.

It's logically possible some ptes got wr-protected during this phase, and we can errornously collapse a thp without noticing some ptes are wr-protected by userfault. e1e267c7928f wanted to avoid it but it only did that for the 1st phase, not the 2nd phase.

Since __collapse_huge_page_isolate() happens after a round of small page swapins, we don't need to worry on any !present ptes - if it existed khugepaged will already bail out. So we only need to check present ptes with uffd-wp bit set there.

This is something I found only but never had a reproducer, I thought it was one caused a bug in Muhammad's recent pagemap new ioctl work, but it turns out it's not the cause of that but an userspace bug. However this seems to still be a real bug even with a very small race window, still worth to have it fixed and copy stable.

Link: https://lkml.kernel.org/r/20230405155120.3608140-1-peterx@redhat.com Fixes: e1e267c7928f ("khugepaged: skip collapse if uffd-wp detected") Signed-off-by: Peter Xu peterx@redhat.com Reviewed-by: David Hildenbrand david@redhat.com Reviewed-by: Yang Shi shy828301@gmail.com Cc: Andrea Arcangeli aarcange@redhat.com Cc: Axel Rasmussen axelrasmussen@google.com Cc: Mike Rapoport rppt@linux.vnet.ibm.com Cc: Nadav Amit nadav.amit@gmail.com Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- mm/khugepaged.c | 4 ++++ 1 file changed, 4 insertions(+)

--- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -625,6 +625,10 @@ static int __collapse_huge_page_isolate( result = SCAN_PTE_NON_PRESENT; goto out; } + if (pte_uffd_wp(pteval)) { + result = SCAN_PTE_UFFD_WP; + goto out; + } page = vm_normal_page(vma, address, pteval); if (unlikely(!page)) { result = SCAN_PAGE_NULL;

From: Qais Yousef qais.yousef@arm.com

commit 244226035a1f9b2b6c326e55ae5188fab4f428cb upstream.

As reported by Yun Hsiang [1], if a task has its uclamp_min >= 0.8 * 1024, it'll always pick the previous CPU because fits_capacity() will always return false in this case.

The new util_fits_cpu() logic should handle this correctly for us beside more corner cases where similar failures could occur, like when using UCLAMP_MAX.

We open code uclamp_rq_util_with() except for the clamp() part, util_fits_cpu() needs the 'raw' values to be passed to it.

Also introduce uclamp_rq_{set, get}() shorthand accessors to get uclamp value for the rq. Makes the code more readable and ensures the right rules (use READ_ONCE/WRITE_ONCE) are respected transparently.

[1] https://lists.linaro.org/pipermail/eas-dev/2020-July/001488.html

Fixes: 1d42509e475c ("sched/fair: Make EAS wakeup placement consider uclamp restrictions") Reported-by: Yun Hsiang hsiang023167@gmail.com Signed-off-by: Qais Yousef qais.yousef@arm.com Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Link: https://lore.kernel.org/r/20220804143609.515789-4-qais.yousef@arm.com (cherry picked from commit 244226035a1f9b2b6c326e55ae5188fab4f428cb) [Conflict in kernel/sched/fair.c mainly due to new automatic variables being added on master vs 5.15] Signed-off-by: Qais Yousef (Google) qyousef@layalina.io Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/sched/core.c | 10 +++++----- kernel/sched/fair.c | 26 ++++++++++++++++++++++++-- kernel/sched/sched.h | 42 +++++++++++++++++++++++++++++++++++++++--- 3 files changed, 68 insertions(+), 10 deletions(-)

--- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1335,7 +1335,7 @@ static inline void uclamp_idle_reset(str if (!(rq->uclamp_flags & UCLAMP_FLAG_IDLE)) return;

- WRITE_ONCE(rq->uclamp[clamp_id].value, clamp_value); + uclamp_rq_set(rq, clamp_id, clamp_value); }

static inline @@ -1513,8 +1513,8 @@ static inline void uclamp_rq_inc_id(stru if (bucket->tasks == 1 || uc_se->value > bucket->value) bucket->value = uc_se->value;

- if (uc_se->value > READ_ONCE(uc_rq->value)) - WRITE_ONCE(uc_rq->value, uc_se->value); + if (uc_se->value > uclamp_rq_get(rq, clamp_id)) + uclamp_rq_set(rq, clamp_id, uc_se->value); }

/* @@ -1580,7 +1580,7 @@ static inline void uclamp_rq_dec_id(stru if (likely(bucket->tasks)) return;

- rq_clamp = READ_ONCE(uc_rq->value); + rq_clamp = uclamp_rq_get(rq, clamp_id); /* * Defensive programming: this should never happen. If it happens, * e.g. due to future modification, warn and fixup the expected value. @@ -1588,7 +1588,7 @@ static inline void uclamp_rq_dec_id(stru SCHED_WARN_ON(bucket->value > rq_clamp); if (bucket->value >= rq_clamp) { bkt_clamp = uclamp_rq_max_value(rq, clamp_id, uc_se->value); - WRITE_ONCE(uc_rq->value, bkt_clamp); + uclamp_rq_set(rq, clamp_id, bkt_clamp); } }

--- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -6985,6 +6985,8 @@ compute_energy(struct task_struct *p, in static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) { unsigned long prev_delta = ULONG_MAX, best_delta = ULONG_MAX; + unsigned long p_util_min = uclamp_is_used() ? uclamp_eff_value(p, UCLAMP_MIN) : 0; + unsigned long p_util_max = uclamp_is_used() ? uclamp_eff_value(p, UCLAMP_MAX) : 1024; struct root_domain *rd = cpu_rq(smp_processor_id())->rd; int cpu, best_energy_cpu = prev_cpu, target = -1; unsigned long cpu_cap, util, base_energy = 0; @@ -7014,6 +7016,8 @@ static int find_energy_efficient_cpu(str

for (; pd; pd = pd->next) { unsigned long cur_delta, spare_cap, max_spare_cap = 0; + unsigned long rq_util_min, rq_util_max; + unsigned long util_min, util_max; bool compute_prev_delta = false; unsigned long base_energy_pd; int max_spare_cap_cpu = -1; @@ -7034,8 +7038,26 @@ static int find_energy_efficient_cpu(str * much capacity we can get out of the CPU; this is * aligned with sched_cpu_util(). */ - util = uclamp_rq_util_with(cpu_rq(cpu), util, p); - if (!fits_capacity(util, cpu_cap)) + if (uclamp_is_used()) { + if (uclamp_rq_is_idle(cpu_rq(cpu))) { + util_min = p_util_min; + util_max = p_util_max; + } else { + /* + * Open code uclamp_rq_util_with() except for + * the clamp() part. Ie: apply max aggregation + * only. util_fits_cpu() logic requires to + * operate on non clamped util but must use the + * max-aggregated uclamp_{min, max}. + */ + rq_util_min = uclamp_rq_get(cpu_rq(cpu), UCLAMP_MIN); + rq_util_max = uclamp_rq_get(cpu_rq(cpu), UCLAMP_MAX); + + util_min = max(rq_util_min, p_util_min); + util_max = max(rq_util_max, p_util_max); + } + } + if (!util_fits_cpu(util, util_min, util_max, cpu)) continue;

if (cpu == prev_cpu) { --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -2855,6 +2855,23 @@ static inline void cpufreq_update_util(s #ifdef CONFIG_UCLAMP_TASK unsigned long uclamp_eff_value(struct task_struct *p, enum uclamp_id clamp_id);

+static inline unsigned long uclamp_rq_get(struct rq *rq, + enum uclamp_id clamp_id) +{ + return READ_ONCE(rq->uclamp[clamp_id].value); +} + +static inline void uclamp_rq_set(struct rq *rq, enum uclamp_id clamp_id, + unsigned int value) +{ + WRITE_ONCE(rq->uclamp[clamp_id].value, value); +} + +static inline bool uclamp_rq_is_idle(struct rq *rq) +{ + return rq->uclamp_flags & UCLAMP_FLAG_IDLE; +} + /** * uclamp_rq_util_with - clamp @util with @rq and @p effective uclamp values. * @rq: The rq to clamp against. Must not be NULL. @@ -2890,12 +2907,12 @@ unsigned long uclamp_rq_util_with(struct * Ignore last runnable task's max clamp, as this task will * reset it. Similarly, no need to read the rq's min clamp. */ - if (rq->uclamp_flags & UCLAMP_FLAG_IDLE) + if (uclamp_rq_is_idle(rq)) goto out; }

- min_util = max_t(unsigned long, min_util, READ_ONCE(rq->uclamp[UCLAMP_MIN].value)); - max_util = max_t(unsigned long, max_util, READ_ONCE(rq->uclamp[UCLAMP_MAX].value)); + min_util = max_t(unsigned long, min_util, uclamp_rq_get(rq, UCLAMP_MIN)); + max_util = max_t(unsigned long, max_util, uclamp_rq_get(rq, UCLAMP_MAX)); out: /* * Since CPU's {min,max}_util clamps are MAX aggregated considering @@ -2941,6 +2958,25 @@ static inline bool uclamp_is_used(void) { return false; } + +static inline unsigned long uclamp_rq_get(struct rq *rq, + enum uclamp_id clamp_id) +{ + if (clamp_id == UCLAMP_MIN) + return 0; + + return SCHED_CAPACITY_SCALE; +} + +static inline void uclamp_rq_set(struct rq *rq, enum uclamp_id clamp_id, + unsigned int value) +{ +} + +static inline bool uclamp_rq_is_idle(struct rq *rq) +{ + return false; +} #endif /* CONFIG_UCLAMP_TASK */

#ifdef arch_scale_freq_capacity

From: Qais Yousef qais.yousef@arm.com

commit d81304bc6193554014d4372a01debdf65e1e9a4d upstream.

If the utilization of the woken up task is 0, we skip the energy calculation because it has no impact.

But if the task is boosted (uclamp_min != 0) will have an impact on task placement and frequency selection. Only skip if the util is truly 0 after applying uclamp values.

Change uclamp_task_cpu() signature to avoid unnecessary additional calls to uclamp_eff_get(). feec() is the only user now.

Fixes: 732cd75b8c920 ("sched/fair: Select an energy-efficient CPU on task wake-up") Signed-off-by: Qais Yousef qais.yousef@arm.com Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Link: https://lore.kernel.org/r/20220804143609.515789-8-qais.yousef@arm.com (cherry picked from commit d81304bc6193554014d4372a01debdf65e1e9a4d) Signed-off-by: Qais Yousef (Google) qyousef@layalina.io Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/sched/fair.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-)

--- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -3974,14 +3974,16 @@ static inline unsigned long task_util_es }

#ifdef CONFIG_UCLAMP_TASK -static inline unsigned long uclamp_task_util(struct task_struct *p) +static inline unsigned long uclamp_task_util(struct task_struct *p, + unsigned long uclamp_min, + unsigned long uclamp_max) { - return clamp(task_util_est(p), - uclamp_eff_value(p, UCLAMP_MIN), - uclamp_eff_value(p, UCLAMP_MAX)); + return clamp(task_util_est(p), uclamp_min, uclamp_max); } #else -static inline unsigned long uclamp_task_util(struct task_struct *p) +static inline unsigned long uclamp_task_util(struct task_struct *p, + unsigned long uclamp_min, + unsigned long uclamp_max) { return task_util_est(p); } @@ -7014,7 +7016,7 @@ static int find_energy_efficient_cpu(str target = prev_cpu;

sync_entity_load_avg(&p->se); - if (!task_util_est(p)) + if (!uclamp_task_util(p, p_util_min, p_util_max)) goto unlock;

for (; pd; pd = pd->next) {

From: Qais Yousef qais.yousef@arm.com

commit aa69c36f31aadc1669bfa8a3de6a47b5e6c98ee8 upstream.

We do consider thermal pressure in util_fits_cpu() for uclamp_min only. With the exception of the biggest cores which by definition are the max performance point of the system and all tasks by definition should fit.

Even under thermal pressure, the capacity of the biggest CPU is the highest in the system and should still fit every task. Except when it reaches capacity inversion point, then this is no longer true.

We can handle this by using the inverted capacity as capacity_orig in util_fits_cpu(). Which not only addresses the problem above, but also ensure uclamp_max now considers the inverted capacity. Force fitting a task when a CPU is in this adverse state will contribute to making the thermal throttling last longer.

Signed-off-by: Qais Yousef qais.yousef@arm.com Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Link: https://lore.kernel.org/r/20220804143609.515789-10-qais.yousef@arm.com (cherry picked from commit aa69c36f31aadc1669bfa8a3de6a47b5e6c98ee8) Signed-off-by: Qais Yousef (Google) qyousef@layalina.io Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/sched/fair.c | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-)

--- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -4159,12 +4159,16 @@ static inline int util_fits_cpu(unsigned * For uclamp_max, we can tolerate a drop in performance level as the * goal is to cap the task. So it's okay if it's getting less. * - * In case of capacity inversion, which is not handled yet, we should - * honour the inverted capacity for both uclamp_min and uclamp_max all - * the time. + * In case of capacity inversion we should honour the inverted capacity + * for both uclamp_min and uclamp_max all the time. */ - capacity_orig = capacity_orig_of(cpu); - capacity_orig_thermal = capacity_orig - arch_scale_thermal_pressure(cpu); + capacity_orig = cpu_in_capacity_inversion(cpu); + if (capacity_orig) { + capacity_orig_thermal = capacity_orig; + } else { + capacity_orig = capacity_orig_of(cpu); + capacity_orig_thermal = capacity_orig - arch_scale_thermal_pressure(cpu); + }

/* * We want to force a task to fit a cpu as implied by uclamp_max.

From: Qais Yousef qyousef@layalina.io

commit da07d2f9c153e457e845d4dcfdd13568d71d18a4 upstream.

Traversing the Perf Domains requires rcu_read_lock() to be held and is conditional on sched_energy_enabled(). Ensure right protections applied.

Also skip capacity inversion detection for our own pd; which was an error.

Fixes: 44c7b80bffc3 ("sched/fair: Detect capacity inversion") Reported-by: Dietmar Eggemann dietmar.eggemann@arm.com Signed-off-by: Qais Yousef (Google) qyousef@layalina.io Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Reviewed-by: Vincent Guittot vincent.guittot@linaro.org Link: https://lore.kernel.org/r/20230112122708.330667-3-qyousef@layalina.io (cherry picked from commit da07d2f9c153e457e845d4dcfdd13568d71d18a4) Signed-off-by: Qais Yousef (Google) qyousef@layalina.io Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/sched/fair.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-)

--- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -8649,16 +8649,23 @@ static void update_cpu_capacity(struct s * * Thermal pressure will impact all cpus in this perf domain * equally. */ - if (static_branch_unlikely(&sched_asym_cpucapacity)) { + if (sched_energy_enabled()) { unsigned long inv_cap = capacity_orig - thermal_load_avg(rq); - struct perf_domain *pd = rcu_dereference(rq->rd->pd); + struct perf_domain *pd;

+ rcu_read_lock(); + + pd = rcu_dereference(rq->rd->pd); rq->cpu_capacity_inverted = 0;

for (; pd; pd = pd->next) { struct cpumask *pd_span = perf_domain_span(pd); unsigned long pd_cap_orig, pd_cap;

+ /* We can't be inverted against our own pd */ + if (cpumask_test_cpu(cpu_of(rq), pd_span)) + continue; + cpu = cpumask_any(pd_span); pd_cap_orig = arch_scale_cpu_capacity(cpu);

@@ -8683,6 +8690,8 @@ static void update_cpu_capacity(struct s break; } } + + rcu_read_unlock(); }

trace_sched_cpu_capacity_tp(rq);

From: Salvatore Bonaccorso carnil@debian.org

In upstream commit 77e52ae35463 ("futex: Move to kernel/futex/") the futex code from kernel/futex.c was moved into kernel/futex/core.c in preparation of the split-up of the implementation in various files.

Point kernel-doc references to the new files as otherwise the documentation shows errors on build:

[...] Error: Cannot open file ./kernel/futex.c Error: Cannot open file ./kernel/futex.c [...] WARNING: kernel-doc './scripts/kernel-doc -rst -enable-lineno -sphinx-version 3.4.3 -internal ./kernel/futex.c' failed with return code 2

There is no direct upstream commit for this change. It is made in analogy to commit bc67f1c454fb ("docs: futex: Fix kernel-doc references") applied as consequence of the restructuring of the futex code.

Fixes: 77e52ae35463 ("futex: Move to kernel/futex/") Signed-off-by: Salvatore Bonaccorso carnil@debian.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- Documentation/kernel-hacking/locking.rst | 2 +- Documentation/translations/it_IT/kernel-hacking/locking.rst | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-)

--- a/Documentation/kernel-hacking/locking.rst +++ b/Documentation/kernel-hacking/locking.rst @@ -1352,7 +1352,7 @@ Mutex API reference Futex API reference ===================

-.. kernel-doc:: kernel/futex.c +.. kernel-doc:: kernel/futex/core.c :internal:

Further reading --- a/Documentation/translations/it_IT/kernel-hacking/locking.rst +++ b/Documentation/translations/it_IT/kernel-hacking/locking.rst @@ -1396,7 +1396,7 @@ Riferimento per l'API dei Mutex Riferimento per l'API dei Futex ===============================

-.. kernel-doc:: kernel/futex.c +.. kernel-doc:: kernel/futex/core.c :internal:

Approfondimenti

From: Miklos Szeredi mszeredi@redhat.com

commit 484ce65715b06aead8c4901f01ca32c5a240bc71 upstream.

A READ request returning a short count is taken as indication of EOF, and the cached file size is modified accordingly.

Fix the attribute version checking to allow for changes to fc->attr_version on other inodes.

Signed-off-by: Miklos Szeredi mszeredi@redhat.com Signed-off-by: Yang Bo yb203166@antfin.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/fuse/file.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -793,7 +793,7 @@ static void fuse_read_update_size(struct struct fuse_inode *fi = get_fuse_inode(inode);

spin_lock(&fi->lock); - if (attr_ver == fi->attr_version && size < inode->i_size && + if (attr_ver >= fi->attr_version && size < inode->i_size && !test_bit(FUSE_I_SIZE_UNSTABLE, &fi->state)) { fi->attr_version = atomic64_inc_return(&fc->attr_version); i_size_write(inode, size);

From: Miklos Szeredi mszeredi@redhat.com

commit 2fdbb8dd01556e1501132b5ad3826e8f71e24a8b upstream.

fuse_finish_open() will be called with FUSE_NOWRITE set in case of atomic O_TRUNC open(), so commit 76224355db75 ("fuse: truncate pagecache on atomic_o_trunc") replaced invalidate_inode_pages2() by truncate_pagecache() in such a case to avoid the A-A deadlock. However, we found another A-B-B-A deadlock related to the case above, which will cause the xfstests generic/464 testcase hung in our virtio-fs test environment.

For example, consider two processes concurrently open one same file, one with O_TRUNC and another without O_TRUNC. The deadlock case is described below, if open(O_TRUNC) is already set_nowrite(acquired A), and is trying to lock a page (acquiring B), open() could have held the page lock (acquired B), and waiting on the page writeback (acquiring A). This would lead to deadlocks.

open(O_TRUNC) ---------------------------------------------------------------- fuse_open_common inode_lock [C acquire] fuse_set_nowrite [A acquire]

fuse_finish_open truncate_pagecache lock_page [B acquire] truncate_inode_page unlock_page [B release]

fuse_release_nowrite [A release] inode_unlock [C release] ----------------------------------------------------------------

open() ---------------------------------------------------------------- fuse_open_common fuse_finish_open invalidate_inode_pages2 lock_page [B acquire] fuse_launder_page fuse_wait_on_page_writeback [A acquire & release] unlock_page [B release] ----------------------------------------------------------------

Besides this case, all calls of invalidate_inode_pages2() and invalidate_inode_pages2_range() in fuse code also can deadlock with open(O_TRUNC).

Fix by moving the truncate_pagecache() call outside the nowrite protected region. The nowrite protection is only for delayed writeback (writeback_cache) case, where inode lock does not protect against truncation racing with writes on the server. Write syscalls racing with page cache truncation still get the inode lock protection.

This patch also changes the order of filemap_invalidate_lock() vs. fuse_set_nowrite() in fuse_open_common(). This new order matches the order found in fuse_file_fallocate() and fuse_do_setattr().

Reported-by: Jiachen Zhang zhangjiachen.jaycee@bytedance.com Tested-by: Jiachen Zhang zhangjiachen.jaycee@bytedance.com Fixes: e4648309b85a ("fuse: truncate pending writes on O_TRUNC") Cc: stable@vger.kernel.org Signed-off-by: Miklos Szeredi mszeredi@redhat.com Signed-off-by: Yang Bo yb203166@antfin.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/fuse/dir.c | 7 ++++++- fs/fuse/file.c | 29 +++++++++++++++++------------ 2 files changed, 23 insertions(+), 13 deletions(-)

--- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -476,6 +476,7 @@ static int fuse_create_open(struct inode struct fuse_entry_out outentry; struct fuse_inode *fi; struct fuse_file *ff; + bool trunc = flags & O_TRUNC;

/* Userspace expects S_IFREG in create mode */ BUG_ON((mode & S_IFMT) != S_IFREG); @@ -500,7 +501,7 @@ static int fuse_create_open(struct inode inarg.mode = mode; inarg.umask = current_umask();

- if (fm->fc->handle_killpriv_v2 && (flags & O_TRUNC) && + if (fm->fc->handle_killpriv_v2 && trunc && !(flags & O_EXCL) && !capable(CAP_FSETID)) { inarg.open_flags |= FUSE_OPEN_KILL_SUIDGID; } @@ -549,6 +550,10 @@ static int fuse_create_open(struct inode } else { file->private_data = ff; fuse_finish_open(inode, file); + if (fm->fc->atomic_o_trunc && trunc) + truncate_pagecache(inode, 0); + else if (!(ff->open_flags & FOPEN_KEEP_CACHE)) + invalidate_inode_pages2(inode->i_mapping); } return err;

--- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -210,12 +210,9 @@ void fuse_finish_open(struct inode *inod fi->attr_version = atomic64_inc_return(&fc->attr_version); i_size_write(inode, 0); spin_unlock(&fi->lock); - truncate_pagecache(inode, 0); fuse_invalidate_attr(inode); if (fc->writeback_cache) file_update_time(file); - } else if (!(ff->open_flags & FOPEN_KEEP_CACHE)) { - invalidate_inode_pages2(inode->i_mapping); }

if ((file->f_mode & FMODE_WRITE) && fc->writeback_cache) @@ -240,30 +237,38 @@ int fuse_open_common(struct inode *inode if (err) return err;

- if (is_wb_truncate || dax_truncate) { + if (is_wb_truncate || dax_truncate) inode_lock(inode); - fuse_set_nowrite(inode); - }

if (dax_truncate) { filemap_invalidate_lock(inode->i_mapping); err = fuse_dax_break_layouts(inode, 0, 0); if (err) - goto out; + goto out_inode_unlock; }

+ if (is_wb_truncate || dax_truncate) + fuse_set_nowrite(inode); + err = fuse_do_open(fm, get_node_id(inode), file, isdir); if (!err) fuse_finish_open(inode, file);

-out: + if (is_wb_truncate || dax_truncate) + fuse_release_nowrite(inode); + if (!err) { + struct fuse_file *ff = file->private_data; + + if (fc->atomic_o_trunc && (file->f_flags & O_TRUNC)) + truncate_pagecache(inode, 0); + else if (!(ff->open_flags & FOPEN_KEEP_CACHE)) + invalidate_inode_pages2(inode->i_mapping); + } if (dax_truncate) filemap_invalidate_unlock(inode->i_mapping); - - if (is_wb_truncate | dax_truncate) { - fuse_release_nowrite(inode); +out_inode_unlock: + if (is_wb_truncate || dax_truncate) inode_unlock(inode); - }

return err; }

From: Kuniyuki Iwashima kuniyu@amazon.com

commit d38afeec26ed4739c640bf286c270559aab2ba5f upstream.

Originally, inet6_sk(sk)->XXX were changed under lock_sock(), so we were able to clean them up by calling inet6_destroy_sock() during the IPv6 -> IPv4 conversion by IPV6_ADDRFORM. However, commit 03485f2adcde ("udpv6: Add lockless sendmsg() support") added a lockless memory allocation path, which could cause a memory leak:

setsockopt(IPV6_ADDRFORM) sendmsg() +-----------------------+ +-------+ - do_ipv6_setsockopt(sk, ...) - udpv6_sendmsg(sk, ...) - sockopt_lock_sock(sk) ^._ called via udpv6_prot - lock_sock(sk) before WRITE_ONCE() - WRITE_ONCE(sk->sk_prot, &tcp_prot) - inet6_destroy_sock() - if (!corkreq) - sockopt_release_sock(sk) - ip6_make_skb(sk, ...) - release_sock(sk) ^._ lockless fast path for the non-corking case

- __ip6_append_data(sk, ...) - ipv6_local_rxpmtu(sk, ...) - xchg(&np->rxpmtu, skb) ^._ rxpmtu is never freed.

- goto out_no_dst;

- lock_sock(sk)

For now, rxpmtu is only the case, but not to miss the future change and a similar bug fixed in commit e27326009a3d ("net: ping6: Fix memleak in ipv6_renew_options()."), let's set a new function to IPv6 sk->sk_destruct() and call inet6_cleanup_sock() there. Since the conversion does not change sk->sk_destruct(), we can guarantee that we can clean up IPv6 resources finally.

We can now remove all inet6_destroy_sock() calls from IPv6 protocol specific ->destroy() functions, but such changes are invasive to backport. So they can be posted as a follow-up later for net-next.

Fixes: 03485f2adcde ("udpv6: Add lockless sendmsg() support") Signed-off-by: Kuniyuki Iwashima kuniyu@amazon.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Ziyang Xuan william.xuanziyang@huawei.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/net/ipv6.h | 1 + include/net/udp.h | 2 +- include/net/udplite.h | 8 -------- net/ipv4/udp.c | 9 ++++++--- net/ipv4/udplite.c | 8 ++++++++ net/ipv6/af_inet6.c | 8 +++++++- net/ipv6/udp.c | 15 ++++++++++++++- net/ipv6/udp_impl.h | 1 + net/ipv6/udplite.c | 9 ++++++++- 9 files changed, 46 insertions(+), 15 deletions(-)

--- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -1119,6 +1119,7 @@ void ipv6_local_error(struct sock *sk, i void ipv6_local_rxpmtu(struct sock *sk, struct flowi6 *fl6, u32 mtu);

void inet6_cleanup_sock(struct sock *sk); +void inet6_sock_destruct(struct sock *sk); int inet6_release(struct socket *sock); int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len); int inet6_getname(struct socket *sock, struct sockaddr *uaddr, --- a/include/net/udp.h +++ b/include/net/udp.h @@ -270,7 +270,7 @@ static inline bool udp_sk_bound_dev_eq(s }

/* net/ipv4/udp.c */ -void udp_destruct_sock(struct sock *sk); +void udp_destruct_common(struct sock *sk); void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len); int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb); void udp_skb_destructor(struct sock *sk, struct sk_buff *skb); --- a/include/net/udplite.h +++ b/include/net/udplite.h @@ -24,14 +24,6 @@ static __inline__ int udplite_getfrag(vo return copy_from_iter_full(to, len, &msg->msg_iter) ? 0 : -EFAULT; }

-/* Designate sk as UDP-Lite socket */ -static inline int udplite_sk_init(struct sock *sk) -{ - udp_init_sock(sk); - udp_sk(sk)->pcflag = UDPLITE_BIT; - return 0; -} - /* * Checksumming routines */ --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1596,7 +1596,7 @@ drop: } EXPORT_SYMBOL_GPL(__udp_enqueue_schedule_skb);

-void udp_destruct_sock(struct sock *sk) +void udp_destruct_common(struct sock *sk) { /* reclaim completely the forward allocated memory */ struct udp_sock *up = udp_sk(sk); @@ -1609,10 +1609,14 @@ void udp_destruct_sock(struct sock *sk) kfree_skb(skb); } udp_rmem_release(sk, total, 0, true); +} +EXPORT_SYMBOL_GPL(udp_destruct_common);

+static void udp_destruct_sock(struct sock *sk) +{ + udp_destruct_common(sk); inet_sock_destruct(sk); } -EXPORT_SYMBOL_GPL(udp_destruct_sock);

int udp_init_sock(struct sock *sk) { @@ -1620,7 +1624,6 @@ int udp_init_sock(struct sock *sk) sk->sk_destruct = udp_destruct_sock; return 0; } -EXPORT_SYMBOL_GPL(udp_init_sock);

void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len) { --- a/net/ipv4/udplite.c +++ b/net/ipv4/udplite.c @@ -17,6 +17,14 @@ struct udp_table udplite_table __read_mostly; EXPORT_SYMBOL(udplite_table);

+/* Designate sk as UDP-Lite socket */ +static int udplite_sk_init(struct sock *sk) +{ + udp_init_sock(sk); + udp_sk(sk)->pcflag = UDPLITE_BIT; + return 0; +} + static int udplite_rcv(struct sk_buff *skb) { return __udp4_lib_rcv(skb, &udplite_table, IPPROTO_UDPLITE); --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -108,6 +108,12 @@ static __inline__ struct ipv6_pinfo *ine return (struct ipv6_pinfo *)(((u8 *)sk) + offset); }

+void inet6_sock_destruct(struct sock *sk) +{ + inet6_cleanup_sock(sk); + inet_sock_destruct(sk); +} + static int inet6_create(struct net *net, struct socket *sock, int protocol, int kern) { @@ -200,7 +206,7 @@ lookup_protocol: inet->hdrincl = 1; }

- sk->sk_destruct = inet_sock_destruct; + sk->sk_destruct = inet6_sock_destruct; sk->sk_family = PF_INET6; sk->sk_protocol = protocol;

--- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -55,6 +55,19 @@ #include <trace/events/skb.h> #include "udp_impl.h"

+static void udpv6_destruct_sock(struct sock *sk) +{ + udp_destruct_common(sk); + inet6_sock_destruct(sk); +} + +int udpv6_init_sock(struct sock *sk) +{ + skb_queue_head_init(&udp_sk(sk)->reader_queue); + sk->sk_destruct = udpv6_destruct_sock; + return 0; +} + static u32 udp6_ehashfn(const struct net *net, const struct in6_addr *laddr, const u16 lport, @@ -1721,7 +1734,7 @@ struct proto udpv6_prot = { .connect = ip6_datagram_connect, .disconnect = udp_disconnect, .ioctl = udp_ioctl, - .init = udp_init_sock, + .init = udpv6_init_sock, .destroy = udpv6_destroy_sock, .setsockopt = udpv6_setsockopt, .getsockopt = udpv6_getsockopt, --- a/net/ipv6/udp_impl.h +++ b/net/ipv6/udp_impl.h @@ -12,6 +12,7 @@ int __udp6_lib_rcv(struct sk_buff *, str int __udp6_lib_err(struct sk_buff *, struct inet6_skb_parm *, u8, u8, int, __be32, struct udp_table *);

+int udpv6_init_sock(struct sock *sk); int udp_v6_get_port(struct sock *sk, unsigned short snum); void udp_v6_rehash(struct sock *sk);

--- a/net/ipv6/udplite.c +++ b/net/ipv6/udplite.c @@ -12,6 +12,13 @@ #include <linux/proc_fs.h> #include "udp_impl.h"

+static int udplitev6_sk_init(struct sock *sk) +{ + udpv6_init_sock(sk); + udp_sk(sk)->pcflag = UDPLITE_BIT; + return 0; +} + static int udplitev6_rcv(struct sk_buff *skb) { return __udp6_lib_rcv(skb, &udplite_table, IPPROTO_UDPLITE); @@ -38,7 +45,7 @@ struct proto udplitev6_prot = { .connect = ip6_datagram_connect, .disconnect = udp_disconnect, .ioctl = udp_ioctl, - .init = udplite_sk_init, + .init = udplitev6_sk_init, .destroy = udpv6_destroy_sock, .setsockopt = udpv6_setsockopt, .getsockopt = udpv6_getsockopt,

From: Kuniyuki Iwashima kuniyu@amazon.com

commit 1651951ebea54970e0bda60c638fc2eee7a6218f upstream.

After commit d38afeec26ed ("tcp/udp: Call inet6_destroy_sock() in IPv6 sk->sk_destruct()."), we call inet6_destroy_sock() in sk->sk_destruct() by setting inet6_sock_destruct() to it to make sure we do not leak inet6-specific resources.

DCCP sets its own sk->sk_destruct() in the dccp_init_sock(), and DCCPv6 socket shares it by calling the same init function via dccp_v6_init_sock().

To call inet6_sock_destruct() from DCCPv6 sk->sk_destruct(), we export it and set dccp_v6_sk_destruct() in the init function.

Signed-off-by: Kuniyuki Iwashima kuniyu@amazon.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Ziyang Xuan william.xuanziyang@huawei.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/dccp/dccp.h | 1 + net/dccp/ipv6.c | 15 ++++++++------- net/dccp/proto.c | 8 +++++++- net/ipv6/af_inet6.c | 1 + 4 files changed, 17 insertions(+), 8 deletions(-)

--- a/net/dccp/dccp.h +++ b/net/dccp/dccp.h @@ -283,6 +283,7 @@ int dccp_rcv_state_process(struct sock * int dccp_rcv_established(struct sock *sk, struct sk_buff *skb, const struct dccp_hdr *dh, const unsigned int len);

+void dccp_destruct_common(struct sock *sk); int dccp_init_sock(struct sock *sk, const __u8 ctl_sock_initialized); void dccp_destroy_sock(struct sock *sk);

--- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -1002,6 +1002,12 @@ static const struct inet_connection_sock .sockaddr_len = sizeof(struct sockaddr_in6), };

+static void dccp_v6_sk_destruct(struct sock *sk) +{ + dccp_destruct_common(sk); + inet6_sock_destruct(sk); +} + /* NOTE: A lot of things set to zero explicitly by call to * sk_alloc() so need not be done here. */ @@ -1014,17 +1020,12 @@ static int dccp_v6_init_sock(struct sock if (unlikely(!dccp_v6_ctl_sock_initialized)) dccp_v6_ctl_sock_initialized = 1; inet_csk(sk)->icsk_af_ops = &dccp_ipv6_af_ops; + sk->sk_destruct = dccp_v6_sk_destruct; }

return err; }

-static void dccp_v6_destroy_sock(struct sock *sk) -{ - dccp_destroy_sock(sk); - inet6_destroy_sock(sk); -} - static struct timewait_sock_ops dccp6_timewait_sock_ops = { .twsk_obj_size = sizeof(struct dccp6_timewait_sock), }; @@ -1047,7 +1048,7 @@ static struct proto dccp_v6_prot = { .accept = inet_csk_accept, .get_port = inet_csk_get_port, .shutdown = dccp_shutdown, - .destroy = dccp_v6_destroy_sock, + .destroy = dccp_destroy_sock, .orphan_count = &dccp_orphan_count, .max_header = MAX_DCCP_HEADER, .obj_size = sizeof(struct dccp6_sock), --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -171,12 +171,18 @@ const char *dccp_packet_name(const int t

EXPORT_SYMBOL_GPL(dccp_packet_name);

-static void dccp_sk_destruct(struct sock *sk) +void dccp_destruct_common(struct sock *sk) { struct dccp_sock *dp = dccp_sk(sk);

ccid_hc_tx_delete(dp->dccps_hc_tx_ccid, sk); dp->dccps_hc_tx_ccid = NULL; +} +EXPORT_SYMBOL_GPL(dccp_destruct_common); + +static void dccp_sk_destruct(struct sock *sk) +{ + dccp_destruct_common(sk); inet_sock_destruct(sk); }

--- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -113,6 +113,7 @@ void inet6_sock_destruct(struct sock *sk inet6_cleanup_sock(sk); inet_sock_destruct(sk); } +EXPORT_SYMBOL_GPL(inet6_sock_destruct);

static int inet6_create(struct net *net, struct socket *sock, int protocol, int kern)

From: Uwe Kleine-König u.kleine-koenig@pengutronix.de

commit 8caa81eb950cb2e9d2d6959b37d853162d197f57 upstream.

The driver only supports normal polarity. Complete the implementation of .get_state() by setting .polarity accordingly.

This fixes a regression that was possible since commit c73a3107624d ("pwm: Handle .get_state() failures") which stopped to zero-initialize the state passed to the .get_state() callback. This was reported at https://forum.odroid.com/viewtopic.php?f=177&t=46360 . While this was an unintended side effect, the real issue is the driver's callback not setting the polarity.

There is a complicating fact, that the .apply() callback fakes support for inversed polarity. This is not (and cannot) be matched by .get_state(). As fixing this isn't easy, only point it out in a comment to prevent authors of other drivers from copying that approach.

Fixes: c375bcbaabdb ("pwm: meson: Read the full hardware state in meson_pwm_get_state()") Reported-by: Munehisa Kamata kamatam@amazon.com Acked-by: Martin Blumenstingl martin.blumenstingl@googlemail.com Link: https://lore.kernel.org/r/20230310191405.2606296-1-u.kleine-koenig@pengutron... Signed-off-by: Uwe Kleine-König u.kleine-koenig@pengutronix.de Signed-off-by: Thierry Reding thierry.reding@gmail.com Signed-off-by: Uwe Kleine-König u.kleine-koenig@pengutronix.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/pwm/pwm-meson.c | 7 +++++++ 1 file changed, 7 insertions(+)

--- a/drivers/pwm/pwm-meson.c +++ b/drivers/pwm/pwm-meson.c @@ -168,6 +168,12 @@ static int meson_pwm_calc(struct meson_p duty = state->duty_cycle; period = state->period;

+ /* + * Note this is wrong. The result is an output wave that isn't really + * inverted and so is wrongly identified by .get_state as normal. + * Fixing this needs some care however as some machines might rely on + * this. + */ if (state->polarity == PWM_POLARITY_INVERSED) duty = period - duty;

@@ -366,6 +372,7 @@ static void meson_pwm_get_state(struct p state->period = 0; state->duty_cycle = 0; } + state->polarity = PWM_POLARITY_NORMAL; }

static const struct pwm_ops meson_pwm_ops = {

From: "Uwe Kleine-K�nig" u.kleine-koenig@pengutronix.de

[ Upstream commit 6f57937980142715e927697a6ffd2050f38ed6f6 ]

The driver only both polarities. Complete the implementation of .get_state() by setting .polarity according to the configured hardware state.

Fixes: d09f00810850 ("pwm: Add PWM driver for HiSilicon BVT SOCs") Link: https://lore.kernel.org/r/20230228135508.1798428-2-u.kleine-koenig@pengutron... Signed-off-by: Uwe Kleine-König u.kleine-koenig@pengutronix.de Signed-off-by: Thierry Reding thierry.reding@gmail.com Signed-off-by: Uwe Kleine-König u.kleine-koenig@pengutronix.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/pwm/pwm-hibvt.c | 1 + 1 file changed, 1 insertion(+)

--- a/drivers/pwm/pwm-hibvt.c +++ b/drivers/pwm/pwm-hibvt.c @@ -146,6 +146,7 @@ static void hibvt_pwm_get_state(struct p

value = readl(base + PWM_CTRL_ADDR(pwm->hwpwm)); state->enabled = (PWM_ENABLE_MASK & value); + state->polarity = (PWM_POLARITY_MASK & value) ? PWM_POLARITY_INVERSED : PWM_POLARITY_NORMAL; }

static int hibvt_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm,

From: Dan Carpenter error27@gmail.com

commit 73a428b37b9b538f8f8fe61caa45e7f243bab87c upstream.

The at91_adc_allocate_trigger() function is supposed to return error pointers. Returning a NULL will cause an Oops.

Fixes: 5e1a1da0f8c9 ("iio: adc: at91-sama5d2_adc: add hw trigger and buffer support") Signed-off-by: Dan Carpenter error27@gmail.com Link: https://lore.kernel.org/r/5d728f9d-31d1-410d-a0b3-df6a63a2c8ba@kili.mountain Signed-off-by: Jonathan Cameron Jonathan.Cameron@huawei.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/iio/adc/at91-sama5d2_adc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/drivers/iio/adc/at91-sama5d2_adc.c +++ b/drivers/iio/adc/at91-sama5d2_adc.c @@ -1000,7 +1000,7 @@ static struct iio_trigger *at91_adc_allo trig = devm_iio_trigger_alloc(&indio->dev, "%s-dev%d-%s", indio->name, iio_device_id(indio), trigger_name); if (!trig) - return NULL; + return ERR_PTR(-ENOMEM);

trig->dev.parent = indio->dev.parent; iio_trigger_set_drvdata(trig, indio);

From: Nikita Zhandarovich n.zhandarovich@fintech.ru

commit 86a24e99c97234f87d9f70b528a691150e145197 upstream.

dma_request_slave_channel() may return NULL which will lead to NULL pointer dereference error in 'tmp_chan->private'.

Correct this behaviour by, first, switching from deprecated function dma_request_slave_channel() to dma_request_chan(). Secondly, enable sanity check for the resuling value of dma_request_chan(). Also, fix description that follows the enacted changes and that concerns the use of dma_request_slave_channel().

Fixes: 706e2c881158 ("ASoC: fsl_asrc_dma: Reuse the dma channel if available in Back-End") Co-developed-by: Natalia Petrova n.petrova@fintech.ru Signed-off-by: Nikita Zhandarovich n.zhandarovich@fintech.ru Acked-by: Shengjiu Wang shengjiu.wang@gmail.com Link: https://lore.kernel.org/r/20230417133242.53339-1-n.zhandarovich@fintech.ru Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- sound/soc/fsl/fsl_asrc_dma.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-)

--- a/sound/soc/fsl/fsl_asrc_dma.c +++ b/sound/soc/fsl/fsl_asrc_dma.c @@ -208,14 +208,19 @@ static int fsl_asrc_dma_hw_params(struct be_chan = soc_component_to_pcm(component_be)->chan[substream->stream]; tmp_chan = be_chan; } - if (!tmp_chan) - tmp_chan = dma_request_slave_channel(dev_be, tx ? "tx" : "rx"); + if (!tmp_chan) { + tmp_chan = dma_request_chan(dev_be, tx ? "tx" : "rx"); + if (IS_ERR(tmp_chan)) { + dev_err(dev, "failed to request DMA channel for Back-End\n"); + return -EINVAL; + } + }

/* * An EDMA DEV_TO_DEV channel is fixed and bound with DMA event of each * peripheral, unlike SDMA channel that is allocated dynamically. So no * need to configure dma_request and dma_request2, but get dma_chan of - * Back-End device directly via dma_request_slave_channel. + * Back-End device directly via dma_request_chan. */ if (!asrc->use_edma) { /* Get DMA request of Back-End */

From: Yang Yingliang yangyingliang@huawei.com

commit 73e770f085023da327dc9ffeb6cd96b0bb22d97e upstream.

Add missing iounmap() before return error from sifive_l2_init().

Fixes: a967a289f169 ("RISC-V: sifive_l2_cache: Add L2 cache controller driver for SiFive SoCs") Signed-off-by: Yang Yingliang yangyingliang@huawei.com Reviewed-by: Conor Dooley conor.dooley@microchip.com Signed-off-by: Conor Dooley conor.dooley@microchip.com [conor: ccache -> l2_cache] Signed-off-by: Conor Dooley conor.dooley@microchip.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/soc/sifive/sifive_l2_cache.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-)

--- a/drivers/soc/sifive/sifive_l2_cache.c +++ b/drivers/soc/sifive/sifive_l2_cache.c @@ -212,7 +212,8 @@ static int __init sifive_l2_init(void) intr_num = of_property_count_u32_elems(np, "interrupts"); if (!intr_num) { pr_err("L2CACHE: no interrupts property\n"); - return -ENODEV; + rc = -ENODEV; + goto err_unmap; }

for (i = 0; i < intr_num; i++) { @@ -220,7 +221,7 @@ static int __init sifive_l2_init(void) rc = request_irq(g_irq[i], l2_int_handler, 0, "l2_ecc", NULL); if (rc) { pr_err("L2CACHE: Could not request IRQ %d\n", g_irq[i]); - return rc; + goto err_unmap; } }

@@ -233,5 +234,9 @@ static int __init sifive_l2_init(void) setup_sifive_debug(); #endif return 0; + +err_unmap: + iounmap(l2_base); + return rc; } device_initcall(sifive_l2_init);

From: Yang Yingliang yangyingliang@huawei.com

commit 8fbf94fea0b4e187ca9100936c5429f96b8a4e44 upstream.

The device_node pointer returned by of_find_matching_node() with refcount incremented, when finish using it, the refcount need be decreased.

Fixes: a967a289f169 ("RISC-V: sifive_l2_cache: Add L2 cache controller driver for SiFive SoCs") Signed-off-by: Yang Yingliang yangyingliang@huawei.com Reviewed-by: Conor Dooley conor.dooley@microchip.com Signed-off-by: Conor Dooley conor.dooley@microchip.com [conor: cache -> l2_cache] Signed-off-by: Conor Dooley conor.dooley@microchip.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/soc/sifive/sifive_l2_cache.c | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-)

--- a/drivers/soc/sifive/sifive_l2_cache.c +++ b/drivers/soc/sifive/sifive_l2_cache.c @@ -202,12 +202,16 @@ static int __init sifive_l2_init(void) if (!np) return -ENODEV;

- if (of_address_to_resource(np, 0, &res)) - return -ENODEV; + if (of_address_to_resource(np, 0, &res)) { + rc = -ENODEV; + goto err_node_put; + }

l2_base = ioremap(res.start, resource_size(&res)); - if (!l2_base) - return -ENOMEM; + if (!l2_base) { + rc = -ENOMEM; + goto err_node_put; + }

intr_num = of_property_count_u32_elems(np, "interrupts"); if (!intr_num) { @@ -224,6 +228,7 @@ static int __init sifive_l2_init(void) goto err_free_irq; } } + of_node_put(np);

l2_config_read();

@@ -240,6 +245,8 @@ err_free_irq: free_irq(g_irq[i], NULL); err_unmap: iounmap(l2_base); +err_node_put: + of_node_put(np); return rc; } device_initcall(sifive_l2_init);