January 2025 - Linux-stable-mirror

FAILED: patch "[PATCH] net/ncsi: fix locking in Get MAC Address handling" failed to apply to 5.15-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.15-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.15.y git checkout FETCH_HEAD git cherry-pick -x 9e2bbab94b88295dcc57c7580393c9ee08d7314d # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025012017-prancing-barracuda-8925@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 9e2bbab94b88295dcc57c7580393c9ee08d7314d Mon Sep 17 00:00:00 2001 From: Paul Fertser <fercerpav(a)gmail.com> Date: Thu, 9 Jan 2025 17:50:54 +0300 Subject: [PATCH] net/ncsi: fix locking in Get MAC Address handling Obtaining RTNL lock in a response handler is not allowed since it runs in an atomic softirq context. Postpone setting the MAC address by adding a dedicated step to the configuration FSM. Fixes: 790071347a0a ("net/ncsi: change from ndo_set_mac_address to dev_set_mac_address") Cc: stable(a)vger.kernel.org Link: https://lore.kernel.org/20241129-potin-revert-ncsi-set-mac-addr-v1-1-94ea2c… Signed-off-by: Paul Fertser <fercerpav(a)gmail.com> Tested-by: Potin Lai <potin.lai.pt(a)gmail.com> Link: https://patch.msgid.link/20250109145054.30925-1-fercerpav@gmail.com Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> diff --git a/net/ncsi/internal.h b/net/ncsi/internal.h index ef0f8f73826f..4e0842df5234 100644 --- a/net/ncsi/internal.h +++ b/net/ncsi/internal.h @@ -289,6 +289,7 @@ enum { ncsi_dev_state_config_sp = 0x0301, ncsi_dev_state_config_cis, ncsi_dev_state_config_oem_gma, + ncsi_dev_state_config_apply_mac, ncsi_dev_state_config_clear_vids, ncsi_dev_state_config_svf, ncsi_dev_state_config_ev, @@ -322,6 +323,7 @@ struct ncsi_dev_priv { #define NCSI_DEV_RESHUFFLE 4 #define NCSI_DEV_RESET 8 /* Reset state of NC */ unsigned int gma_flag; /* OEM GMA flag */ + struct sockaddr pending_mac; /* MAC address received from GMA */ spinlock_t lock; /* Protect the NCSI device */ unsigned int package_probe_id;/* Current ID during probe */ unsigned int package_num; /* Number of packages */ diff --git a/net/ncsi/ncsi-manage.c b/net/ncsi/ncsi-manage.c index 5cf55bde366d..bf276eaf9330 100644 --- a/net/ncsi/ncsi-manage.c +++ b/net/ncsi/ncsi-manage.c @@ -1038,7 +1038,7 @@ static void ncsi_configure_channel(struct ncsi_dev_priv *ndp) : ncsi_dev_state_config_clear_vids; break; case ncsi_dev_state_config_oem_gma: - nd->state = ncsi_dev_state_config_clear_vids; + nd->state = ncsi_dev_state_config_apply_mac; nca.package = np->id; nca.channel = nc->id; @@ -1050,10 +1050,22 @@ static void ncsi_configure_channel(struct ncsi_dev_priv *ndp) nca.type = NCSI_PKT_CMD_OEM; ret = ncsi_gma_handler(&nca, nc->version.mf_id); } - if (ret < 0) + if (ret < 0) { + nd->state = ncsi_dev_state_config_clear_vids; schedule_work(&ndp->work); + } break; + case ncsi_dev_state_config_apply_mac: + rtnl_lock(); + ret = dev_set_mac_address(dev, &ndp->pending_mac, NULL); + rtnl_unlock(); + if (ret < 0) + netdev_warn(dev, "NCSI: 'Writing MAC address to device failed\n"); + + nd->state = ncsi_dev_state_config_clear_vids; + + fallthrough; case ncsi_dev_state_config_clear_vids: case ncsi_dev_state_config_svf: case ncsi_dev_state_config_ev: diff --git a/net/ncsi/ncsi-rsp.c b/net/ncsi/ncsi-rsp.c index e28be33bdf2c..14bd66909ca4 100644 --- a/net/ncsi/ncsi-rsp.c +++ b/net/ncsi/ncsi-rsp.c @@ -628,16 +628,14 @@ static int ncsi_rsp_handler_snfc(struct ncsi_request *nr) static int ncsi_rsp_handler_oem_gma(struct ncsi_request *nr, int mfr_id) { struct ncsi_dev_priv *ndp = nr->ndp; + struct sockaddr *saddr = &ndp->pending_mac; struct net_device *ndev = ndp->ndev.dev; struct ncsi_rsp_oem_pkt *rsp; - struct sockaddr saddr; u32 mac_addr_off = 0; - int ret = 0; /* Get the response header */ rsp = (struct ncsi_rsp_oem_pkt *)skb_network_header(nr->rsp); - saddr.sa_family = ndev->type; ndev->priv_flags |= IFF_LIVE_ADDR_CHANGE; if (mfr_id == NCSI_OEM_MFR_BCM_ID) mac_addr_off = BCM_MAC_ADDR_OFFSET; @@ -646,22 +644,17 @@ static int ncsi_rsp_handler_oem_gma(struct ncsi_request *nr, int mfr_id) else if (mfr_id == NCSI_OEM_MFR_INTEL_ID) mac_addr_off = INTEL_MAC_ADDR_OFFSET; - memcpy(saddr.sa_data, &rsp->data[mac_addr_off], ETH_ALEN); + saddr->sa_family = ndev->type; + memcpy(saddr->sa_data, &rsp->data[mac_addr_off], ETH_ALEN); if (mfr_id == NCSI_OEM_MFR_BCM_ID || mfr_id == NCSI_OEM_MFR_INTEL_ID) - eth_addr_inc((u8 *)saddr.sa_data); - if (!is_valid_ether_addr((const u8 *)saddr.sa_data)) + eth_addr_inc((u8 *)saddr->sa_data); + if (!is_valid_ether_addr((const u8 *)saddr->sa_data)) return -ENXIO; /* Set the flag for GMA command which should only be called once */ ndp->gma_flag = 1; - rtnl_lock(); - ret = dev_set_mac_address(ndev, &saddr, NULL); - rtnl_unlock(); - if (ret < 0) - netdev_warn(ndev, "NCSI: 'Writing mac address to device failed\n"); - - return ret; + return 0; } /* Response handler for Mellanox card */

3 months

1
0
0 0

FAILED: patch "[PATCH] net/ncsi: fix locking in Get MAC Address handling" failed to apply to 6.6-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.6-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.6.y git checkout FETCH_HEAD git cherry-pick -x 9e2bbab94b88295dcc57c7580393c9ee08d7314d # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025012016-wireless-premium-a086@gregkh' --subject-prefix 'PATCH 6.6.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 9e2bbab94b88295dcc57c7580393c9ee08d7314d Mon Sep 17 00:00:00 2001 From: Paul Fertser <fercerpav(a)gmail.com> Date: Thu, 9 Jan 2025 17:50:54 +0300 Subject: [PATCH] net/ncsi: fix locking in Get MAC Address handling Obtaining RTNL lock in a response handler is not allowed since it runs in an atomic softirq context. Postpone setting the MAC address by adding a dedicated step to the configuration FSM. Fixes: 790071347a0a ("net/ncsi: change from ndo_set_mac_address to dev_set_mac_address") Cc: stable(a)vger.kernel.org Link: https://lore.kernel.org/20241129-potin-revert-ncsi-set-mac-addr-v1-1-94ea2c… Signed-off-by: Paul Fertser <fercerpav(a)gmail.com> Tested-by: Potin Lai <potin.lai.pt(a)gmail.com> Link: https://patch.msgid.link/20250109145054.30925-1-fercerpav@gmail.com Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> diff --git a/net/ncsi/internal.h b/net/ncsi/internal.h index ef0f8f73826f..4e0842df5234 100644 --- a/net/ncsi/internal.h +++ b/net/ncsi/internal.h @@ -289,6 +289,7 @@ enum { ncsi_dev_state_config_sp = 0x0301, ncsi_dev_state_config_cis, ncsi_dev_state_config_oem_gma, + ncsi_dev_state_config_apply_mac, ncsi_dev_state_config_clear_vids, ncsi_dev_state_config_svf, ncsi_dev_state_config_ev, @@ -322,6 +323,7 @@ struct ncsi_dev_priv { #define NCSI_DEV_RESHUFFLE 4 #define NCSI_DEV_RESET 8 /* Reset state of NC */ unsigned int gma_flag; /* OEM GMA flag */ + struct sockaddr pending_mac; /* MAC address received from GMA */ spinlock_t lock; /* Protect the NCSI device */ unsigned int package_probe_id;/* Current ID during probe */ unsigned int package_num; /* Number of packages */ diff --git a/net/ncsi/ncsi-manage.c b/net/ncsi/ncsi-manage.c index 5cf55bde366d..bf276eaf9330 100644 --- a/net/ncsi/ncsi-manage.c +++ b/net/ncsi/ncsi-manage.c @@ -1038,7 +1038,7 @@ static void ncsi_configure_channel(struct ncsi_dev_priv *ndp) : ncsi_dev_state_config_clear_vids; break; case ncsi_dev_state_config_oem_gma: - nd->state = ncsi_dev_state_config_clear_vids; + nd->state = ncsi_dev_state_config_apply_mac; nca.package = np->id; nca.channel = nc->id; @@ -1050,10 +1050,22 @@ static void ncsi_configure_channel(struct ncsi_dev_priv *ndp) nca.type = NCSI_PKT_CMD_OEM; ret = ncsi_gma_handler(&nca, nc->version.mf_id); } - if (ret < 0) + if (ret < 0) { + nd->state = ncsi_dev_state_config_clear_vids; schedule_work(&ndp->work); + } break; + case ncsi_dev_state_config_apply_mac: + rtnl_lock(); + ret = dev_set_mac_address(dev, &ndp->pending_mac, NULL); + rtnl_unlock(); + if (ret < 0) + netdev_warn(dev, "NCSI: 'Writing MAC address to device failed\n"); + + nd->state = ncsi_dev_state_config_clear_vids; + + fallthrough; case ncsi_dev_state_config_clear_vids: case ncsi_dev_state_config_svf: case ncsi_dev_state_config_ev: diff --git a/net/ncsi/ncsi-rsp.c b/net/ncsi/ncsi-rsp.c index e28be33bdf2c..14bd66909ca4 100644 --- a/net/ncsi/ncsi-rsp.c +++ b/net/ncsi/ncsi-rsp.c @@ -628,16 +628,14 @@ static int ncsi_rsp_handler_snfc(struct ncsi_request *nr) static int ncsi_rsp_handler_oem_gma(struct ncsi_request *nr, int mfr_id) { struct ncsi_dev_priv *ndp = nr->ndp; + struct sockaddr *saddr = &ndp->pending_mac; struct net_device *ndev = ndp->ndev.dev; struct ncsi_rsp_oem_pkt *rsp; - struct sockaddr saddr; u32 mac_addr_off = 0; - int ret = 0; /* Get the response header */ rsp = (struct ncsi_rsp_oem_pkt *)skb_network_header(nr->rsp); - saddr.sa_family = ndev->type; ndev->priv_flags |= IFF_LIVE_ADDR_CHANGE; if (mfr_id == NCSI_OEM_MFR_BCM_ID) mac_addr_off = BCM_MAC_ADDR_OFFSET; @@ -646,22 +644,17 @@ static int ncsi_rsp_handler_oem_gma(struct ncsi_request *nr, int mfr_id) else if (mfr_id == NCSI_OEM_MFR_INTEL_ID) mac_addr_off = INTEL_MAC_ADDR_OFFSET; - memcpy(saddr.sa_data, &rsp->data[mac_addr_off], ETH_ALEN); + saddr->sa_family = ndev->type; + memcpy(saddr->sa_data, &rsp->data[mac_addr_off], ETH_ALEN); if (mfr_id == NCSI_OEM_MFR_BCM_ID || mfr_id == NCSI_OEM_MFR_INTEL_ID) - eth_addr_inc((u8 *)saddr.sa_data); - if (!is_valid_ether_addr((const u8 *)saddr.sa_data)) + eth_addr_inc((u8 *)saddr->sa_data); + if (!is_valid_ether_addr((const u8 *)saddr->sa_data)) return -ENXIO; /* Set the flag for GMA command which should only be called once */ ndp->gma_flag = 1; - rtnl_lock(); - ret = dev_set_mac_address(ndev, &saddr, NULL); - rtnl_unlock(); - if (ret < 0) - netdev_warn(ndev, "NCSI: 'Writing mac address to device failed\n"); - - return ret; + return 0; } /* Response handler for Mellanox card */

3 months

1
0
0 0

FAILED: patch "[PATCH] mm: zswap: move allocations during CPU init outside the lock" failed to apply to 5.15-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.15-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.15.y git checkout FETCH_HEAD git cherry-pick -x 779b9955f64327c339a16f68055af98252fd3315 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025012002-spent-fervor-ada9@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 779b9955f64327c339a16f68055af98252fd3315 Mon Sep 17 00:00:00 2001 From: Yosry Ahmed <yosryahmed(a)google.com> Date: Mon, 13 Jan 2025 21:44:58 +0000 Subject: [PATCH] mm: zswap: move allocations during CPU init outside the lock In zswap_cpu_comp_prepare(), allocations are made and assigned to various members of acomp_ctx under acomp_ctx->mutex. However, allocations may recurse into zswap through reclaim, trying to acquire the same mutex and deadlocking. Move the allocations before the mutex critical section. Only the initialization of acomp_ctx needs to be done with the mutex held. Link: https://lkml.kernel.org/r/20250113214458.2123410-1-yosryahmed@google.com Fixes: 12dcb0ef5406 ("mm: zswap: properly synchronize freeing resources during CPU hotunplug") Signed-off-by: Yosry Ahmed <yosryahmed(a)google.com> Reviewed-by: Chengming Zhou <chengming.zhou(a)linux.dev> Cc: Johannes Weiner <hannes(a)cmpxchg.org> Cc: Nhat Pham <nphamcs(a)gmail.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/mm/zswap.c b/mm/zswap.c index 30f5a27a6862..b84c20d889b1 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -820,15 +820,15 @@ static int zswap_cpu_comp_prepare(unsigned int cpu, struct hlist_node *node) { struct zswap_pool *pool = hlist_entry(node, struct zswap_pool, node); struct crypto_acomp_ctx *acomp_ctx = per_cpu_ptr(pool->acomp_ctx, cpu); - struct crypto_acomp *acomp; - struct acomp_req *req; + struct crypto_acomp *acomp = NULL; + struct acomp_req *req = NULL; + u8 *buffer = NULL; int ret; - mutex_lock(&acomp_ctx->mutex); - acomp_ctx->buffer = kmalloc_node(PAGE_SIZE * 2, GFP_KERNEL, cpu_to_node(cpu)); - if (!acomp_ctx->buffer) { + buffer = kmalloc_node(PAGE_SIZE * 2, GFP_KERNEL, cpu_to_node(cpu)); + if (!buffer) { ret = -ENOMEM; - goto buffer_fail; + goto fail; } acomp = crypto_alloc_acomp_node(pool->tfm_name, 0, 0, cpu_to_node(cpu)); @@ -836,21 +836,25 @@ static int zswap_cpu_comp_prepare(unsigned int cpu, struct hlist_node *node) pr_err("could not alloc crypto acomp %s : %ld\n", pool->tfm_name, PTR_ERR(acomp)); ret = PTR_ERR(acomp); - goto acomp_fail; + goto fail; } - acomp_ctx->acomp = acomp; - acomp_ctx->is_sleepable = acomp_is_async(acomp); - req = acomp_request_alloc(acomp_ctx->acomp); + req = acomp_request_alloc(acomp); if (!req) { pr_err("could not alloc crypto acomp_request %s\n", pool->tfm_name); ret = -ENOMEM; - goto req_fail; + goto fail; } - acomp_ctx->req = req; + /* + * Only hold the mutex after completing allocations, otherwise we may + * recurse into zswap through reclaim and attempt to hold the mutex + * again resulting in a deadlock. + */ + mutex_lock(&acomp_ctx->mutex); crypto_init_wait(&acomp_ctx->wait); + /* * if the backend of acomp is async zip, crypto_req_done() will wakeup * crypto_wait_req(); if the backend of acomp is scomp, the callback @@ -859,15 +863,17 @@ static int zswap_cpu_comp_prepare(unsigned int cpu, struct hlist_node *node) acomp_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG, crypto_req_done, &acomp_ctx->wait); + acomp_ctx->buffer = buffer; + acomp_ctx->acomp = acomp; + acomp_ctx->is_sleepable = acomp_is_async(acomp); + acomp_ctx->req = req; mutex_unlock(&acomp_ctx->mutex); return 0; -req_fail: - crypto_free_acomp(acomp_ctx->acomp); -acomp_fail: - kfree(acomp_ctx->buffer); -buffer_fail: - mutex_unlock(&acomp_ctx->mutex); +fail: + if (acomp) + crypto_free_acomp(acomp); + kfree(buffer); return ret; }

3 months

1
0
0 0

FAILED: patch "[PATCH] mm: zswap: move allocations during CPU init outside the lock" failed to apply to 6.1-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.1-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y git checkout FETCH_HEAD git cherry-pick -x 779b9955f64327c339a16f68055af98252fd3315 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025012002-overstep-numbness-cf60@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 779b9955f64327c339a16f68055af98252fd3315 Mon Sep 17 00:00:00 2001 From: Yosry Ahmed <yosryahmed(a)google.com> Date: Mon, 13 Jan 2025 21:44:58 +0000 Subject: [PATCH] mm: zswap: move allocations during CPU init outside the lock In zswap_cpu_comp_prepare(), allocations are made and assigned to various members of acomp_ctx under acomp_ctx->mutex. However, allocations may recurse into zswap through reclaim, trying to acquire the same mutex and deadlocking. Move the allocations before the mutex critical section. Only the initialization of acomp_ctx needs to be done with the mutex held. Link: https://lkml.kernel.org/r/20250113214458.2123410-1-yosryahmed@google.com Fixes: 12dcb0ef5406 ("mm: zswap: properly synchronize freeing resources during CPU hotunplug") Signed-off-by: Yosry Ahmed <yosryahmed(a)google.com> Reviewed-by: Chengming Zhou <chengming.zhou(a)linux.dev> Cc: Johannes Weiner <hannes(a)cmpxchg.org> Cc: Nhat Pham <nphamcs(a)gmail.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/mm/zswap.c b/mm/zswap.c index 30f5a27a6862..b84c20d889b1 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -820,15 +820,15 @@ static int zswap_cpu_comp_prepare(unsigned int cpu, struct hlist_node *node) { struct zswap_pool *pool = hlist_entry(node, struct zswap_pool, node); struct crypto_acomp_ctx *acomp_ctx = per_cpu_ptr(pool->acomp_ctx, cpu); - struct crypto_acomp *acomp; - struct acomp_req *req; + struct crypto_acomp *acomp = NULL; + struct acomp_req *req = NULL; + u8 *buffer = NULL; int ret; - mutex_lock(&acomp_ctx->mutex); - acomp_ctx->buffer = kmalloc_node(PAGE_SIZE * 2, GFP_KERNEL, cpu_to_node(cpu)); - if (!acomp_ctx->buffer) { + buffer = kmalloc_node(PAGE_SIZE * 2, GFP_KERNEL, cpu_to_node(cpu)); + if (!buffer) { ret = -ENOMEM; - goto buffer_fail; + goto fail; } acomp = crypto_alloc_acomp_node(pool->tfm_name, 0, 0, cpu_to_node(cpu)); @@ -836,21 +836,25 @@ static int zswap_cpu_comp_prepare(unsigned int cpu, struct hlist_node *node) pr_err("could not alloc crypto acomp %s : %ld\n", pool->tfm_name, PTR_ERR(acomp)); ret = PTR_ERR(acomp); - goto acomp_fail; + goto fail; } - acomp_ctx->acomp = acomp; - acomp_ctx->is_sleepable = acomp_is_async(acomp); - req = acomp_request_alloc(acomp_ctx->acomp); + req = acomp_request_alloc(acomp); if (!req) { pr_err("could not alloc crypto acomp_request %s\n", pool->tfm_name); ret = -ENOMEM; - goto req_fail; + goto fail; } - acomp_ctx->req = req; + /* + * Only hold the mutex after completing allocations, otherwise we may + * recurse into zswap through reclaim and attempt to hold the mutex + * again resulting in a deadlock. + */ + mutex_lock(&acomp_ctx->mutex); crypto_init_wait(&acomp_ctx->wait); + /* * if the backend of acomp is async zip, crypto_req_done() will wakeup * crypto_wait_req(); if the backend of acomp is scomp, the callback @@ -859,15 +863,17 @@ static int zswap_cpu_comp_prepare(unsigned int cpu, struct hlist_node *node) acomp_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG, crypto_req_done, &acomp_ctx->wait); + acomp_ctx->buffer = buffer; + acomp_ctx->acomp = acomp; + acomp_ctx->is_sleepable = acomp_is_async(acomp); + acomp_ctx->req = req; mutex_unlock(&acomp_ctx->mutex); return 0; -req_fail: - crypto_free_acomp(acomp_ctx->acomp); -acomp_fail: - kfree(acomp_ctx->buffer); -buffer_fail: - mutex_unlock(&acomp_ctx->mutex); +fail: + if (acomp) + crypto_free_acomp(acomp); + kfree(buffer); return ret; }

3 months

1
0
0 0

FAILED: patch "[PATCH] mm: zswap: move allocations during CPU init outside the lock" failed to apply to 6.6-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.6-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.6.y git checkout FETCH_HEAD git cherry-pick -x 779b9955f64327c339a16f68055af98252fd3315 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025012001-elbow-configure-d7c7@gregkh' --subject-prefix 'PATCH 6.6.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 779b9955f64327c339a16f68055af98252fd3315 Mon Sep 17 00:00:00 2001 From: Yosry Ahmed <yosryahmed(a)google.com> Date: Mon, 13 Jan 2025 21:44:58 +0000 Subject: [PATCH] mm: zswap: move allocations during CPU init outside the lock In zswap_cpu_comp_prepare(), allocations are made and assigned to various members of acomp_ctx under acomp_ctx->mutex. However, allocations may recurse into zswap through reclaim, trying to acquire the same mutex and deadlocking. Move the allocations before the mutex critical section. Only the initialization of acomp_ctx needs to be done with the mutex held. Link: https://lkml.kernel.org/r/20250113214458.2123410-1-yosryahmed@google.com Fixes: 12dcb0ef5406 ("mm: zswap: properly synchronize freeing resources during CPU hotunplug") Signed-off-by: Yosry Ahmed <yosryahmed(a)google.com> Reviewed-by: Chengming Zhou <chengming.zhou(a)linux.dev> Cc: Johannes Weiner <hannes(a)cmpxchg.org> Cc: Nhat Pham <nphamcs(a)gmail.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/mm/zswap.c b/mm/zswap.c index 30f5a27a6862..b84c20d889b1 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -820,15 +820,15 @@ static int zswap_cpu_comp_prepare(unsigned int cpu, struct hlist_node *node) { struct zswap_pool *pool = hlist_entry(node, struct zswap_pool, node); struct crypto_acomp_ctx *acomp_ctx = per_cpu_ptr(pool->acomp_ctx, cpu); - struct crypto_acomp *acomp; - struct acomp_req *req; + struct crypto_acomp *acomp = NULL; + struct acomp_req *req = NULL; + u8 *buffer = NULL; int ret; - mutex_lock(&acomp_ctx->mutex); - acomp_ctx->buffer = kmalloc_node(PAGE_SIZE * 2, GFP_KERNEL, cpu_to_node(cpu)); - if (!acomp_ctx->buffer) { + buffer = kmalloc_node(PAGE_SIZE * 2, GFP_KERNEL, cpu_to_node(cpu)); + if (!buffer) { ret = -ENOMEM; - goto buffer_fail; + goto fail; } acomp = crypto_alloc_acomp_node(pool->tfm_name, 0, 0, cpu_to_node(cpu)); @@ -836,21 +836,25 @@ static int zswap_cpu_comp_prepare(unsigned int cpu, struct hlist_node *node) pr_err("could not alloc crypto acomp %s : %ld\n", pool->tfm_name, PTR_ERR(acomp)); ret = PTR_ERR(acomp); - goto acomp_fail; + goto fail; } - acomp_ctx->acomp = acomp; - acomp_ctx->is_sleepable = acomp_is_async(acomp); - req = acomp_request_alloc(acomp_ctx->acomp); + req = acomp_request_alloc(acomp); if (!req) { pr_err("could not alloc crypto acomp_request %s\n", pool->tfm_name); ret = -ENOMEM; - goto req_fail; + goto fail; } - acomp_ctx->req = req; + /* + * Only hold the mutex after completing allocations, otherwise we may + * recurse into zswap through reclaim and attempt to hold the mutex + * again resulting in a deadlock. + */ + mutex_lock(&acomp_ctx->mutex); crypto_init_wait(&acomp_ctx->wait); + /* * if the backend of acomp is async zip, crypto_req_done() will wakeup * crypto_wait_req(); if the backend of acomp is scomp, the callback @@ -859,15 +863,17 @@ static int zswap_cpu_comp_prepare(unsigned int cpu, struct hlist_node *node) acomp_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG, crypto_req_done, &acomp_ctx->wait); + acomp_ctx->buffer = buffer; + acomp_ctx->acomp = acomp; + acomp_ctx->is_sleepable = acomp_is_async(acomp); + acomp_ctx->req = req; mutex_unlock(&acomp_ctx->mutex); return 0; -req_fail: - crypto_free_acomp(acomp_ctx->acomp); -acomp_fail: - kfree(acomp_ctx->buffer); -buffer_fail: - mutex_unlock(&acomp_ctx->mutex); +fail: + if (acomp) + crypto_free_acomp(acomp); + kfree(buffer); return ret; }

3 months

1
0
0 0

FAILED: patch "[PATCH] mm: zswap: move allocations during CPU init outside the lock" failed to apply to 6.12-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.12-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.12.y git checkout FETCH_HEAD git cherry-pick -x 779b9955f64327c339a16f68055af98252fd3315 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025012057-carrousel-marbled-221b@gregkh' --subject-prefix 'PATCH 6.12.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 779b9955f64327c339a16f68055af98252fd3315 Mon Sep 17 00:00:00 2001 From: Yosry Ahmed <yosryahmed(a)google.com> Date: Mon, 13 Jan 2025 21:44:58 +0000 Subject: [PATCH] mm: zswap: move allocations during CPU init outside the lock In zswap_cpu_comp_prepare(), allocations are made and assigned to various members of acomp_ctx under acomp_ctx->mutex. However, allocations may recurse into zswap through reclaim, trying to acquire the same mutex and deadlocking. Move the allocations before the mutex critical section. Only the initialization of acomp_ctx needs to be done with the mutex held. Link: https://lkml.kernel.org/r/20250113214458.2123410-1-yosryahmed@google.com Fixes: 12dcb0ef5406 ("mm: zswap: properly synchronize freeing resources during CPU hotunplug") Signed-off-by: Yosry Ahmed <yosryahmed(a)google.com> Reviewed-by: Chengming Zhou <chengming.zhou(a)linux.dev> Cc: Johannes Weiner <hannes(a)cmpxchg.org> Cc: Nhat Pham <nphamcs(a)gmail.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/mm/zswap.c b/mm/zswap.c index 30f5a27a6862..b84c20d889b1 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -820,15 +820,15 @@ static int zswap_cpu_comp_prepare(unsigned int cpu, struct hlist_node *node) { struct zswap_pool *pool = hlist_entry(node, struct zswap_pool, node); struct crypto_acomp_ctx *acomp_ctx = per_cpu_ptr(pool->acomp_ctx, cpu); - struct crypto_acomp *acomp; - struct acomp_req *req; + struct crypto_acomp *acomp = NULL; + struct acomp_req *req = NULL; + u8 *buffer = NULL; int ret; - mutex_lock(&acomp_ctx->mutex); - acomp_ctx->buffer = kmalloc_node(PAGE_SIZE * 2, GFP_KERNEL, cpu_to_node(cpu)); - if (!acomp_ctx->buffer) { + buffer = kmalloc_node(PAGE_SIZE * 2, GFP_KERNEL, cpu_to_node(cpu)); + if (!buffer) { ret = -ENOMEM; - goto buffer_fail; + goto fail; } acomp = crypto_alloc_acomp_node(pool->tfm_name, 0, 0, cpu_to_node(cpu)); @@ -836,21 +836,25 @@ static int zswap_cpu_comp_prepare(unsigned int cpu, struct hlist_node *node) pr_err("could not alloc crypto acomp %s : %ld\n", pool->tfm_name, PTR_ERR(acomp)); ret = PTR_ERR(acomp); - goto acomp_fail; + goto fail; } - acomp_ctx->acomp = acomp; - acomp_ctx->is_sleepable = acomp_is_async(acomp); - req = acomp_request_alloc(acomp_ctx->acomp); + req = acomp_request_alloc(acomp); if (!req) { pr_err("could not alloc crypto acomp_request %s\n", pool->tfm_name); ret = -ENOMEM; - goto req_fail; + goto fail; } - acomp_ctx->req = req; + /* + * Only hold the mutex after completing allocations, otherwise we may + * recurse into zswap through reclaim and attempt to hold the mutex + * again resulting in a deadlock. + */ + mutex_lock(&acomp_ctx->mutex); crypto_init_wait(&acomp_ctx->wait); + /* * if the backend of acomp is async zip, crypto_req_done() will wakeup * crypto_wait_req(); if the backend of acomp is scomp, the callback @@ -859,15 +863,17 @@ static int zswap_cpu_comp_prepare(unsigned int cpu, struct hlist_node *node) acomp_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG, crypto_req_done, &acomp_ctx->wait); + acomp_ctx->buffer = buffer; + acomp_ctx->acomp = acomp; + acomp_ctx->is_sleepable = acomp_is_async(acomp); + acomp_ctx->req = req; mutex_unlock(&acomp_ctx->mutex); return 0; -req_fail: - crypto_free_acomp(acomp_ctx->acomp); -acomp_fail: - kfree(acomp_ctx->buffer); -buffer_fail: - mutex_unlock(&acomp_ctx->mutex); +fail: + if (acomp) + crypto_free_acomp(acomp); + kfree(buffer); return ret; }

3 months

1
0
0 0

FAILED: patch "[PATCH] mm: zswap: properly synchronize freeing resources during CPU" failed to apply to 5.15-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.15-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.15.y git checkout FETCH_HEAD git cherry-pick -x 12dcb0ef540629a281533f9dedc1b6b8e14cfb65 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025012015-siren-backyard-e676@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 12dcb0ef540629a281533f9dedc1b6b8e14cfb65 Mon Sep 17 00:00:00 2001 From: Yosry Ahmed <yosryahmed(a)google.com> Date: Wed, 8 Jan 2025 22:24:41 +0000 Subject: [PATCH] mm: zswap: properly synchronize freeing resources during CPU hotunplug In zswap_compress() and zswap_decompress(), the per-CPU acomp_ctx of the current CPU at the beginning of the operation is retrieved and used throughout. However, since neither preemption nor migration are disabled, it is possible that the operation continues on a different CPU. If the original CPU is hotunplugged while the acomp_ctx is still in use, we run into a UAF bug as some of the resources attached to the acomp_ctx are freed during hotunplug in zswap_cpu_comp_dead() (i.e. acomp_ctx.buffer, acomp_ctx.req, or acomp_ctx.acomp). The problem was introduced in commit 1ec3b5fe6eec ("mm/zswap: move to use crypto_acomp API for hardware acceleration") when the switch to the crypto_acomp API was made. Prior to that, the per-CPU crypto_comp was retrieved using get_cpu_ptr() which disables preemption and makes sure the CPU cannot go away from under us. Preemption cannot be disabled with the crypto_acomp API as a sleepable context is needed. Use the acomp_ctx.mutex to synchronize CPU hotplug callbacks allocating and freeing resources with compression/decompression paths. Make sure that acomp_ctx.req is NULL when the resources are freed. In the compression/decompression paths, check if acomp_ctx.req is NULL after acquiring the mutex (meaning the CPU was offlined) and retry on the new CPU. The initialization of acomp_ctx.mutex is moved from the CPU hotplug callback to the pool initialization where it belongs (where the mutex is allocated). In addition to adding clarity, this makes sure that CPU hotplug cannot reinitialize a mutex that is already locked by compression/decompression. Previously a fix was attempted by holding cpus_read_lock() [1]. This would have caused a potential deadlock as it is possible for code already holding the lock to fall into reclaim and enter zswap (causing a deadlock). A fix was also attempted using SRCU for synchronization, but Johannes pointed out that synchronize_srcu() cannot be used in CPU hotplug notifiers [2]. Alternative fixes that were considered/attempted and could have worked: - Refcounting the per-CPU acomp_ctx. This involves complexity in handling the race between the refcount dropping to zero in zswap_[de]compress() and the refcount being re-initialized when the CPU is onlined. - Disabling migration before getting the per-CPU acomp_ctx [3], but that's discouraged and is a much bigger hammer than needed, and could result in subtle performance issues. [1]https://lkml.kernel.org/20241219212437.2714151-1-yosryahmed@google.com/ [2]https://lkml.kernel.org/20250107074724.1756696-2-yosryahmed@google.com/ [3]https://lkml.kernel.org/20250107222236.2715883-2-yosryahmed@google.com/ [yosryahmed(a)google.com: remove comment] Link: https://lkml.kernel.org/r/CAJD7tkaxS1wjn+swugt8QCvQ-rVF5RZnjxwPGX17k8x9zSMa… Link: https://lkml.kernel.org/r/20250108222441.3622031-1-yosryahmed@google.com Fixes: 1ec3b5fe6eec ("mm/zswap: move to use crypto_acomp API for hardware acceleration") Signed-off-by: Yosry Ahmed <yosryahmed(a)google.com> Reported-by: Johannes Weiner <hannes(a)cmpxchg.org> Closes: https://lore.kernel.org/lkml/20241113213007.GB1564047@cmpxchg.org/ Reported-by: Sam Sun <samsun1006219(a)gmail.com> Closes: https://lore.kernel.org/lkml/CAEkJfYMtSdM5HceNsXUDf5haghD5+o2e7Qv4OcuruL4tP… Cc: Barry Song <baohua(a)kernel.org> Cc: Chengming Zhou <chengming.zhou(a)linux.dev> Cc: Kanchana P Sridhar <kanchana.p.sridhar(a)intel.com> Cc: Nhat Pham <nphamcs(a)gmail.com> Cc: Vitaly Wool <vitalywool(a)gmail.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/mm/zswap.c b/mm/zswap.c index f6316b66fb23..30f5a27a6862 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -251,7 +251,7 @@ static struct zswap_pool *zswap_pool_create(char *type, char *compressor) struct zswap_pool *pool; char name[38]; /* 'zswap' + 32 char (max) num + \0 */ gfp_t gfp = __GFP_NORETRY | __GFP_NOWARN | __GFP_KSWAPD_RECLAIM; - int ret; + int ret, cpu; if (!zswap_has_pool) { /* if either are unset, pool initialization failed, and we @@ -285,6 +285,9 @@ static struct zswap_pool *zswap_pool_create(char *type, char *compressor) goto error; } + for_each_possible_cpu(cpu) + mutex_init(&per_cpu_ptr(pool->acomp_ctx, cpu)->mutex); + ret = cpuhp_state_add_instance(CPUHP_MM_ZSWP_POOL_PREPARE, &pool->node); if (ret) @@ -821,11 +824,12 @@ static int zswap_cpu_comp_prepare(unsigned int cpu, struct hlist_node *node) struct acomp_req *req; int ret; - mutex_init(&acomp_ctx->mutex); - + mutex_lock(&acomp_ctx->mutex); acomp_ctx->buffer = kmalloc_node(PAGE_SIZE * 2, GFP_KERNEL, cpu_to_node(cpu)); - if (!acomp_ctx->buffer) - return -ENOMEM; + if (!acomp_ctx->buffer) { + ret = -ENOMEM; + goto buffer_fail; + } acomp = crypto_alloc_acomp_node(pool->tfm_name, 0, 0, cpu_to_node(cpu)); if (IS_ERR(acomp)) { @@ -855,12 +859,15 @@ static int zswap_cpu_comp_prepare(unsigned int cpu, struct hlist_node *node) acomp_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG, crypto_req_done, &acomp_ctx->wait); + mutex_unlock(&acomp_ctx->mutex); return 0; req_fail: crypto_free_acomp(acomp_ctx->acomp); acomp_fail: kfree(acomp_ctx->buffer); +buffer_fail: + mutex_unlock(&acomp_ctx->mutex); return ret; } @@ -869,17 +876,45 @@ static int zswap_cpu_comp_dead(unsigned int cpu, struct hlist_node *node) struct zswap_pool *pool = hlist_entry(node, struct zswap_pool, node); struct crypto_acomp_ctx *acomp_ctx = per_cpu_ptr(pool->acomp_ctx, cpu); + mutex_lock(&acomp_ctx->mutex); if (!IS_ERR_OR_NULL(acomp_ctx)) { if (!IS_ERR_OR_NULL(acomp_ctx->req)) acomp_request_free(acomp_ctx->req); + acomp_ctx->req = NULL; if (!IS_ERR_OR_NULL(acomp_ctx->acomp)) crypto_free_acomp(acomp_ctx->acomp); kfree(acomp_ctx->buffer); } + mutex_unlock(&acomp_ctx->mutex); return 0; } +static struct crypto_acomp_ctx *acomp_ctx_get_cpu_lock(struct zswap_pool *pool) +{ + struct crypto_acomp_ctx *acomp_ctx; + + for (;;) { + acomp_ctx = raw_cpu_ptr(pool->acomp_ctx); + mutex_lock(&acomp_ctx->mutex); + if (likely(acomp_ctx->req)) + return acomp_ctx; + /* + * It is possible that we were migrated to a different CPU after + * getting the per-CPU ctx but before the mutex was acquired. If + * the old CPU got offlined, zswap_cpu_comp_dead() could have + * already freed ctx->req (among other things) and set it to + * NULL. Just try again on the new CPU that we ended up on. + */ + mutex_unlock(&acomp_ctx->mutex); + } +} + +static void acomp_ctx_put_unlock(struct crypto_acomp_ctx *acomp_ctx) +{ + mutex_unlock(&acomp_ctx->mutex); +} + static bool zswap_compress(struct page *page, struct zswap_entry *entry, struct zswap_pool *pool) { @@ -893,10 +928,7 @@ static bool zswap_compress(struct page *page, struct zswap_entry *entry, gfp_t gfp; u8 *dst; - acomp_ctx = raw_cpu_ptr(pool->acomp_ctx); - - mutex_lock(&acomp_ctx->mutex); - + acomp_ctx = acomp_ctx_get_cpu_lock(pool); dst = acomp_ctx->buffer; sg_init_table(&input, 1); sg_set_page(&input, page, PAGE_SIZE, 0); @@ -949,7 +981,7 @@ static bool zswap_compress(struct page *page, struct zswap_entry *entry, else if (alloc_ret) zswap_reject_alloc_fail++; - mutex_unlock(&acomp_ctx->mutex); + acomp_ctx_put_unlock(acomp_ctx); return comp_ret == 0 && alloc_ret == 0; } @@ -960,9 +992,7 @@ static void zswap_decompress(struct zswap_entry *entry, struct folio *folio) struct crypto_acomp_ctx *acomp_ctx; u8 *src; - acomp_ctx = raw_cpu_ptr(entry->pool->acomp_ctx); - mutex_lock(&acomp_ctx->mutex); - + acomp_ctx = acomp_ctx_get_cpu_lock(entry->pool); src = zpool_map_handle(zpool, entry->handle, ZPOOL_MM_RO); /* * If zpool_map_handle is atomic, we cannot reliably utilize its mapped buffer @@ -986,10 +1016,10 @@ static void zswap_decompress(struct zswap_entry *entry, struct folio *folio) acomp_request_set_params(acomp_ctx->req, &input, &output, entry->length, PAGE_SIZE); BUG_ON(crypto_wait_req(crypto_acomp_decompress(acomp_ctx->req), &acomp_ctx->wait)); BUG_ON(acomp_ctx->req->dlen != PAGE_SIZE); - mutex_unlock(&acomp_ctx->mutex); if (src != acomp_ctx->buffer) zpool_unmap_handle(zpool, entry->handle); + acomp_ctx_put_unlock(acomp_ctx); } /*********************************

3 months

1
0
0 0

FAILED: patch "[PATCH] mm: zswap: properly synchronize freeing resources during CPU" failed to apply to 6.1-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.1-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y git checkout FETCH_HEAD git cherry-pick -x 12dcb0ef540629a281533f9dedc1b6b8e14cfb65 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025012014-sardine-hardwood-6828@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 12dcb0ef540629a281533f9dedc1b6b8e14cfb65 Mon Sep 17 00:00:00 2001 From: Yosry Ahmed <yosryahmed(a)google.com> Date: Wed, 8 Jan 2025 22:24:41 +0000 Subject: [PATCH] mm: zswap: properly synchronize freeing resources during CPU hotunplug In zswap_compress() and zswap_decompress(), the per-CPU acomp_ctx of the current CPU at the beginning of the operation is retrieved and used throughout. However, since neither preemption nor migration are disabled, it is possible that the operation continues on a different CPU. If the original CPU is hotunplugged while the acomp_ctx is still in use, we run into a UAF bug as some of the resources attached to the acomp_ctx are freed during hotunplug in zswap_cpu_comp_dead() (i.e. acomp_ctx.buffer, acomp_ctx.req, or acomp_ctx.acomp). The problem was introduced in commit 1ec3b5fe6eec ("mm/zswap: move to use crypto_acomp API for hardware acceleration") when the switch to the crypto_acomp API was made. Prior to that, the per-CPU crypto_comp was retrieved using get_cpu_ptr() which disables preemption and makes sure the CPU cannot go away from under us. Preemption cannot be disabled with the crypto_acomp API as a sleepable context is needed. Use the acomp_ctx.mutex to synchronize CPU hotplug callbacks allocating and freeing resources with compression/decompression paths. Make sure that acomp_ctx.req is NULL when the resources are freed. In the compression/decompression paths, check if acomp_ctx.req is NULL after acquiring the mutex (meaning the CPU was offlined) and retry on the new CPU. The initialization of acomp_ctx.mutex is moved from the CPU hotplug callback to the pool initialization where it belongs (where the mutex is allocated). In addition to adding clarity, this makes sure that CPU hotplug cannot reinitialize a mutex that is already locked by compression/decompression. Previously a fix was attempted by holding cpus_read_lock() [1]. This would have caused a potential deadlock as it is possible for code already holding the lock to fall into reclaim and enter zswap (causing a deadlock). A fix was also attempted using SRCU for synchronization, but Johannes pointed out that synchronize_srcu() cannot be used in CPU hotplug notifiers [2]. Alternative fixes that were considered/attempted and could have worked: - Refcounting the per-CPU acomp_ctx. This involves complexity in handling the race between the refcount dropping to zero in zswap_[de]compress() and the refcount being re-initialized when the CPU is onlined. - Disabling migration before getting the per-CPU acomp_ctx [3], but that's discouraged and is a much bigger hammer than needed, and could result in subtle performance issues. [1]https://lkml.kernel.org/20241219212437.2714151-1-yosryahmed@google.com/ [2]https://lkml.kernel.org/20250107074724.1756696-2-yosryahmed@google.com/ [3]https://lkml.kernel.org/20250107222236.2715883-2-yosryahmed@google.com/ [yosryahmed(a)google.com: remove comment] Link: https://lkml.kernel.org/r/CAJD7tkaxS1wjn+swugt8QCvQ-rVF5RZnjxwPGX17k8x9zSMa… Link: https://lkml.kernel.org/r/20250108222441.3622031-1-yosryahmed@google.com Fixes: 1ec3b5fe6eec ("mm/zswap: move to use crypto_acomp API for hardware acceleration") Signed-off-by: Yosry Ahmed <yosryahmed(a)google.com> Reported-by: Johannes Weiner <hannes(a)cmpxchg.org> Closes: https://lore.kernel.org/lkml/20241113213007.GB1564047@cmpxchg.org/ Reported-by: Sam Sun <samsun1006219(a)gmail.com> Closes: https://lore.kernel.org/lkml/CAEkJfYMtSdM5HceNsXUDf5haghD5+o2e7Qv4OcuruL4tP… Cc: Barry Song <baohua(a)kernel.org> Cc: Chengming Zhou <chengming.zhou(a)linux.dev> Cc: Kanchana P Sridhar <kanchana.p.sridhar(a)intel.com> Cc: Nhat Pham <nphamcs(a)gmail.com> Cc: Vitaly Wool <vitalywool(a)gmail.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/mm/zswap.c b/mm/zswap.c index f6316b66fb23..30f5a27a6862 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -251,7 +251,7 @@ static struct zswap_pool *zswap_pool_create(char *type, char *compressor) struct zswap_pool *pool; char name[38]; /* 'zswap' + 32 char (max) num + \0 */ gfp_t gfp = __GFP_NORETRY | __GFP_NOWARN | __GFP_KSWAPD_RECLAIM; - int ret; + int ret, cpu; if (!zswap_has_pool) { /* if either are unset, pool initialization failed, and we @@ -285,6 +285,9 @@ static struct zswap_pool *zswap_pool_create(char *type, char *compressor) goto error; } + for_each_possible_cpu(cpu) + mutex_init(&per_cpu_ptr(pool->acomp_ctx, cpu)->mutex); + ret = cpuhp_state_add_instance(CPUHP_MM_ZSWP_POOL_PREPARE, &pool->node); if (ret) @@ -821,11 +824,12 @@ static int zswap_cpu_comp_prepare(unsigned int cpu, struct hlist_node *node) struct acomp_req *req; int ret; - mutex_init(&acomp_ctx->mutex); - + mutex_lock(&acomp_ctx->mutex); acomp_ctx->buffer = kmalloc_node(PAGE_SIZE * 2, GFP_KERNEL, cpu_to_node(cpu)); - if (!acomp_ctx->buffer) - return -ENOMEM; + if (!acomp_ctx->buffer) { + ret = -ENOMEM; + goto buffer_fail; + } acomp = crypto_alloc_acomp_node(pool->tfm_name, 0, 0, cpu_to_node(cpu)); if (IS_ERR(acomp)) { @@ -855,12 +859,15 @@ static int zswap_cpu_comp_prepare(unsigned int cpu, struct hlist_node *node) acomp_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG, crypto_req_done, &acomp_ctx->wait); + mutex_unlock(&acomp_ctx->mutex); return 0; req_fail: crypto_free_acomp(acomp_ctx->acomp); acomp_fail: kfree(acomp_ctx->buffer); +buffer_fail: + mutex_unlock(&acomp_ctx->mutex); return ret; } @@ -869,17 +876,45 @@ static int zswap_cpu_comp_dead(unsigned int cpu, struct hlist_node *node) struct zswap_pool *pool = hlist_entry(node, struct zswap_pool, node); struct crypto_acomp_ctx *acomp_ctx = per_cpu_ptr(pool->acomp_ctx, cpu); + mutex_lock(&acomp_ctx->mutex); if (!IS_ERR_OR_NULL(acomp_ctx)) { if (!IS_ERR_OR_NULL(acomp_ctx->req)) acomp_request_free(acomp_ctx->req); + acomp_ctx->req = NULL; if (!IS_ERR_OR_NULL(acomp_ctx->acomp)) crypto_free_acomp(acomp_ctx->acomp); kfree(acomp_ctx->buffer); } + mutex_unlock(&acomp_ctx->mutex); return 0; } +static struct crypto_acomp_ctx *acomp_ctx_get_cpu_lock(struct zswap_pool *pool) +{ + struct crypto_acomp_ctx *acomp_ctx; + + for (;;) { + acomp_ctx = raw_cpu_ptr(pool->acomp_ctx); + mutex_lock(&acomp_ctx->mutex); + if (likely(acomp_ctx->req)) + return acomp_ctx; + /* + * It is possible that we were migrated to a different CPU after + * getting the per-CPU ctx but before the mutex was acquired. If + * the old CPU got offlined, zswap_cpu_comp_dead() could have + * already freed ctx->req (among other things) and set it to + * NULL. Just try again on the new CPU that we ended up on. + */ + mutex_unlock(&acomp_ctx->mutex); + } +} + +static void acomp_ctx_put_unlock(struct crypto_acomp_ctx *acomp_ctx) +{ + mutex_unlock(&acomp_ctx->mutex); +} + static bool zswap_compress(struct page *page, struct zswap_entry *entry, struct zswap_pool *pool) { @@ -893,10 +928,7 @@ static bool zswap_compress(struct page *page, struct zswap_entry *entry, gfp_t gfp; u8 *dst; - acomp_ctx = raw_cpu_ptr(pool->acomp_ctx); - - mutex_lock(&acomp_ctx->mutex); - + acomp_ctx = acomp_ctx_get_cpu_lock(pool); dst = acomp_ctx->buffer; sg_init_table(&input, 1); sg_set_page(&input, page, PAGE_SIZE, 0); @@ -949,7 +981,7 @@ static bool zswap_compress(struct page *page, struct zswap_entry *entry, else if (alloc_ret) zswap_reject_alloc_fail++; - mutex_unlock(&acomp_ctx->mutex); + acomp_ctx_put_unlock(acomp_ctx); return comp_ret == 0 && alloc_ret == 0; } @@ -960,9 +992,7 @@ static void zswap_decompress(struct zswap_entry *entry, struct folio *folio) struct crypto_acomp_ctx *acomp_ctx; u8 *src; - acomp_ctx = raw_cpu_ptr(entry->pool->acomp_ctx); - mutex_lock(&acomp_ctx->mutex); - + acomp_ctx = acomp_ctx_get_cpu_lock(entry->pool); src = zpool_map_handle(zpool, entry->handle, ZPOOL_MM_RO); /* * If zpool_map_handle is atomic, we cannot reliably utilize its mapped buffer @@ -986,10 +1016,10 @@ static void zswap_decompress(struct zswap_entry *entry, struct folio *folio) acomp_request_set_params(acomp_ctx->req, &input, &output, entry->length, PAGE_SIZE); BUG_ON(crypto_wait_req(crypto_acomp_decompress(acomp_ctx->req), &acomp_ctx->wait)); BUG_ON(acomp_ctx->req->dlen != PAGE_SIZE); - mutex_unlock(&acomp_ctx->mutex); if (src != acomp_ctx->buffer) zpool_unmap_handle(zpool, entry->handle); + acomp_ctx_put_unlock(acomp_ctx); } /*********************************

3 months

1
0
0 0

[PATCH 5.10] xfs: add bounds checking to xlog_recover_process_data

by Denis Arefev

From: lei lu <llfamsec(a)gmail.com> commit fb63435b7c7dc112b1ae1baea5486e0a6e27b196 upstream. There is a lack of verification of the space occupied by fixed members of xlog_op_header in the xlog_recover_process_data. We can create a crafted image to trigger an out of bounds read by following these steps: 1) Mount an image of xfs, and do some file operations to leave records 2) Before umounting, copy the image for subsequent steps to simulate abnormal exit. Because umount will ensure that tail_blk and head_blk are the same, which will result in the inability to enter xlog_recover_process_data 3) Write a tool to parse and modify the copied image in step 2 4) Make the end of the xlog_op_header entries only 1 byte away from xlog_rec_header->h_size 5) xlog_rec_header->h_num_logops++ 6) Modify xlog_rec_header->h_crc Fix: Add a check to make sure there is sufficient space to access fixed members of xlog_op_header. Signed-off-by: lei lu <llfamsec(a)gmail.com> Reviewed-by: Dave Chinner <dchinner(a)redhat.com> Reviewed-by: Darrick J. Wong <djwong(a)kernel.org> Signed-off-by: Chandan Babu R <chandanbabu(a)kernel.org> Signed-off-by: Denis Arefev <arefev(a)swemel.ru> --- Backport fix for CVE-2024-41014 Link: https://nvd.nist.gov/vuln/detail/cve-2024-41014 --- fs/xfs/xfs_log_recover.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c index e61f28ce3e44..eafe76f304ef 100644 --- a/fs/xfs/xfs_log_recover.c +++ b/fs/xfs/xfs_log_recover.c @@ -2419,7 +2419,10 @@ xlog_recover_process_data( ohead = (struct xlog_op_header *)dp; dp += sizeof(*ohead); - ASSERT(dp <= end); + if (dp > end) { + xfs_warn(log->l_mp, "%s: op header overrun", __func__); + return -EFSCORRUPTED; + } /* errors will abort recovery */ error = xlog_recover_process_ophdr(log, rhash, rhead, ohead, -- 2.43.0

3 months

1
0
0 0

[PATCH 5.10] drm/radeon: check bo_va->bo is non-NULL before using it

by Denis Arefev

From: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer(a)amd.com> commit 6fb15dcbcf4f212930350eaee174bb60ed40a536 upstream. The call to radeon_vm_clear_freed might clear bo_va->bo, so we have to check it before dereferencing it. Signed-off-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer(a)amd.com> Acked-by: Alex Deucher <alexander.deucher(a)amd.com> Signed-off-by: Alex Deucher <alexander.deucher(a)amd.com> [Denis: minor fix to resolve merge conflict.] Signed-off-by: Denis Arefev <arefev(a)swemel.ru> --- Backport fix CVE-2024-41060 Link: https://nvd.nist.gov/vuln/detail/CVE-2024-41060 --- drivers/gpu/drm/radeon/radeon_gem.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/radeon/radeon_gem.c b/drivers/gpu/drm/radeon/radeon_gem.c index 75053917d213..51b6f38b5c47 100644 --- a/drivers/gpu/drm/radeon/radeon_gem.c +++ b/drivers/gpu/drm/radeon/radeon_gem.c @@ -582,7 +582,7 @@ static void radeon_gem_va_update_vm(struct radeon_device *rdev, if (r) goto error_unlock; - if (bo_va->it.start) + if (bo_va->it.start && bo_va->bo) r = radeon_vm_bo_update(rdev, bo_va, &bo_va->bo->tbo.mem); error_unlock: -- 2.43.0

3 months

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror January 2025