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

FAILED: patch "[PATCH] bpf, sockmap: Fix panic when calling skb_linearize" 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 5ca2e29f6834c64c0e5a9ccf1278c21fb49b827e # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025071437-unloaded-unstitch-e838@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 5ca2e29f6834c64c0e5a9ccf1278c21fb49b827e Mon Sep 17 00:00:00 2001 From: Jiayuan Chen <jiayuan.chen(a)linux.dev> Date: Mon, 7 Apr 2025 22:21:22 +0800 Subject: [PATCH] bpf, sockmap: Fix panic when calling skb_linearize MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The panic can be reproduced by executing the command: ./bench sockmap -c 2 -p 1 -a --rx-verdict-ingress --rx-strp 100000 Then a kernel panic was captured: ''' [ 657.460555] kernel BUG at net/core/skbuff.c:2178! [ 657.462680] Tainted: [W]=WARN [ 657.463287] Workqueue: events sk_psock_backlog ... [ 657.469610] <TASK> [ 657.469738] ? die+0x36/0x90 [ 657.469916] ? do_trap+0x1d0/0x270 [ 657.470118] ? pskb_expand_head+0x612/0xf40 [ 657.470376] ? pskb_expand_head+0x612/0xf40 [ 657.470620] ? do_error_trap+0xa3/0x170 [ 657.470846] ? pskb_expand_head+0x612/0xf40 [ 657.471092] ? handle_invalid_op+0x2c/0x40 [ 657.471335] ? pskb_expand_head+0x612/0xf40 [ 657.471579] ? exc_invalid_op+0x2d/0x40 [ 657.471805] ? asm_exc_invalid_op+0x1a/0x20 [ 657.472052] ? pskb_expand_head+0xd1/0xf40 [ 657.472292] ? pskb_expand_head+0x612/0xf40 [ 657.472540] ? lock_acquire+0x18f/0x4e0 [ 657.472766] ? find_held_lock+0x2d/0x110 [ 657.472999] ? __pfx_pskb_expand_head+0x10/0x10 [ 657.473263] ? __kmalloc_cache_noprof+0x5b/0x470 [ 657.473537] ? __pfx___lock_release.isra.0+0x10/0x10 [ 657.473826] __pskb_pull_tail+0xfd/0x1d20 [ 657.474062] ? __kasan_slab_alloc+0x4e/0x90 [ 657.474707] sk_psock_skb_ingress_enqueue+0x3bf/0x510 [ 657.475392] ? __kasan_kmalloc+0xaa/0xb0 [ 657.476010] sk_psock_backlog+0x5cf/0xd70 [ 657.476637] process_one_work+0x858/0x1a20 ''' The panic originates from the assertion BUG_ON(skb_shared(skb)) in skb_linearize(). A previous commit(see Fixes tag) introduced skb_get() to avoid race conditions between skb operations in the backlog and skb release in the recvmsg path. However, this caused the panic to always occur when skb_linearize is executed. The "--rx-strp 100000" parameter forces the RX path to use the strparser module which aggregates data until it reaches 100KB before calling sockmap logic. The 100KB payload exceeds MAX_MSG_FRAGS, triggering skb_linearize. To fix this issue, just move skb_get into sk_psock_skb_ingress_enqueue. ''' sk_psock_backlog: sk_psock_handle_skb skb_get(skb) <== we move it into 'sk_psock_skb_ingress_enqueue' sk_psock_skb_ingress____________ ↓ | | → sk_psock_skb_ingress_self | sk_psock_skb_ingress_enqueue sk_psock_verdict_apply_________________↑ skb_linearize ''' Note that for verdict_apply path, the skb_get operation is unnecessary so we add 'take_ref' param to control it's behavior. Fixes: a454d84ee20b ("bpf, sockmap: Fix skb refcnt race after locking changes") Signed-off-by: Jiayuan Chen <jiayuan.chen(a)linux.dev> Link: https://lore.kernel.org/r/20250407142234.47591-4-jiayuan.chen@linux.dev Signed-off-by: Alexei Starovoitov <ast(a)kernel.org> diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 9533b3e40ad7..276934673066 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -530,16 +530,22 @@ static int sk_psock_skb_ingress_enqueue(struct sk_buff *skb, u32 off, u32 len, struct sk_psock *psock, struct sock *sk, - struct sk_msg *msg) + struct sk_msg *msg, + bool take_ref) { int num_sge, copied; + /* skb_to_sgvec will fail when the total number of fragments in + * frag_list and frags exceeds MAX_MSG_FRAGS. For example, the + * caller may aggregate multiple skbs. + */ num_sge = skb_to_sgvec(skb, msg->sg.data, off, len); if (num_sge < 0) { /* skb linearize may fail with ENOMEM, but lets simply try again * later if this happens. Under memory pressure we don't want to * drop the skb. We need to linearize the skb so that the mapping * in skb_to_sgvec can not error. + * Note that skb_linearize requires the skb not to be shared. */ if (skb_linearize(skb)) return -EAGAIN; @@ -556,7 +562,7 @@ static int sk_psock_skb_ingress_enqueue(struct sk_buff *skb, msg->sg.start = 0; msg->sg.size = copied; msg->sg.end = num_sge; - msg->skb = skb; + msg->skb = take_ref ? skb_get(skb) : skb; sk_psock_queue_msg(psock, msg); sk_psock_data_ready(sk, psock); @@ -564,7 +570,7 @@ static int sk_psock_skb_ingress_enqueue(struct sk_buff *skb, } static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb, - u32 off, u32 len); + u32 off, u32 len, bool take_ref); static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb, u32 off, u32 len) @@ -578,7 +584,7 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb, * correctly. */ if (unlikely(skb->sk == sk)) - return sk_psock_skb_ingress_self(psock, skb, off, len); + return sk_psock_skb_ingress_self(psock, skb, off, len, true); msg = sk_psock_create_ingress_msg(sk, skb); if (!msg) return -EAGAIN; @@ -590,7 +596,7 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb, * into user buffers. */ skb_set_owner_r(skb, sk); - err = sk_psock_skb_ingress_enqueue(skb, off, len, psock, sk, msg); + err = sk_psock_skb_ingress_enqueue(skb, off, len, psock, sk, msg, true); if (err < 0) kfree(msg); return err; @@ -601,7 +607,7 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb, * because the skb is already accounted for here. */ static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb, - u32 off, u32 len) + u32 off, u32 len, bool take_ref) { struct sk_msg *msg = alloc_sk_msg(GFP_ATOMIC); struct sock *sk = psock->sk; @@ -610,7 +616,7 @@ static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb if (unlikely(!msg)) return -EAGAIN; skb_set_owner_r(skb, sk); - err = sk_psock_skb_ingress_enqueue(skb, off, len, psock, sk, msg); + err = sk_psock_skb_ingress_enqueue(skb, off, len, psock, sk, msg, take_ref); if (err < 0) kfree(msg); return err; @@ -619,18 +625,13 @@ static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb static int sk_psock_handle_skb(struct sk_psock *psock, struct sk_buff *skb, u32 off, u32 len, bool ingress) { - int err = 0; - if (!ingress) { if (!sock_writeable(psock->sk)) return -EAGAIN; return skb_send_sock(psock->sk, skb, off, len); } - skb_get(skb); - err = sk_psock_skb_ingress(psock, skb, off, len); - if (err < 0) - kfree_skb(skb); - return err; + + return sk_psock_skb_ingress(psock, skb, off, len); } static void sk_psock_skb_state(struct sk_psock *psock, @@ -1019,7 +1020,7 @@ static int sk_psock_verdict_apply(struct sk_psock *psock, struct sk_buff *skb, off = stm->offset; len = stm->full_len; } - err = sk_psock_skb_ingress_self(psock, skb, off, len); + err = sk_psock_skb_ingress_self(psock, skb, off, len, false); } if (err < 0) { spin_lock_bh(&psock->ingress_lock);

3 months, 2 weeks

2
1
0 0

[PATCH] misc: rtsx: usb: Ensure mmc child device is active when card is present

by Ricky Wu

When a card is present in the reader, the driver currently defers autosuspend by returning -EAGAIN during the suspend callback to trigger USB remote wakeup signaling. However, this does not guarantee that the mmc child device has been resumed, which may cause issues if it remains suspended while the card is accessible. This patch ensures that all child devices, including the mmc host controller, are explicitly resumed before returning -EAGAIN. This fixes a corner case introduced by earlier remote wakeup handling, improving reliability of runtime PM when a card is inserted. Fixes: 883a87ddf2f1 ("misc: rtsx_usb: Use USB remote wakeup signaling for card insertion detection") Cc: stable(a)vger.kernel.org Signed-off-by: Ricky Wu <ricky_wu(a)realtek.com> --- drivers/misc/cardreader/rtsx_usb.c | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) diff --git a/drivers/misc/cardreader/rtsx_usb.c b/drivers/misc/cardreader/rtsx_usb.c index 148107a4547c..d007a4455ce5 100644 --- a/drivers/misc/cardreader/rtsx_usb.c +++ b/drivers/misc/cardreader/rtsx_usb.c @@ -698,6 +698,12 @@ static void rtsx_usb_disconnect(struct usb_interface *intf) } #ifdef CONFIG_PM +static int rtsx_usb_resume_child(struct device *dev, void *data) +{ + pm_request_resume(dev); + return 0; +} + static int rtsx_usb_suspend(struct usb_interface *intf, pm_message_t message) { struct rtsx_ucr *ucr = @@ -713,8 +719,10 @@ static int rtsx_usb_suspend(struct usb_interface *intf, pm_message_t message) mutex_unlock(&ucr->dev_mutex); /* Defer the autosuspend if card exists */ - if (val & (SD_CD | MS_CD)) + if (val & (SD_CD | MS_CD)) { + device_for_each_child(&intf->dev, NULL, rtsx_usb_resume_child); return -EAGAIN; + } } else { /* There is an ongoing operation*/ return -EAGAIN; @@ -724,12 +732,6 @@ static int rtsx_usb_suspend(struct usb_interface *intf, pm_message_t message) return 0; } -static int rtsx_usb_resume_child(struct device *dev, void *data) -{ - pm_request_resume(dev); - return 0; -} - static int rtsx_usb_resume(struct usb_interface *intf) { device_for_each_child(&intf->dev, NULL, rtsx_usb_resume_child); -- 2.25.1

3 months, 2 weeks

3
2
0 0

[REGRESSION] [PATCH v2] drm/amd/display: fix initial backlight brightness calculation

by Lauri Tirkkonen

DIV_ROUND_CLOSEST(x, 100) returns either 0 or 1 if 0<x<=100, so the division needs to be performed after the multiplication and not the other way around, to properly scale the value. Fixes: 8b5f3a229a70 ("drm/amd/display: Fix default DC and AC levels") Signed-off-by: Lauri Tirkkonen <lauri(a)hacktheplanet.fi> Cc: stable(a)vger.kernel.org --- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index f58fa5da7fe5..8a5b5dfad1ab 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -4941,9 +4941,9 @@ amdgpu_dm_register_backlight_device(struct amdgpu_dm_connector *aconnector) caps = &dm->backlight_caps[aconnector->bl_idx]; if (get_brightness_range(caps, &min, &max)) { if (power_supply_is_system_supplied() > 0) - props.brightness = (max - min) * DIV_ROUND_CLOSEST(caps->ac_level, 100); + props.brightness = DIV_ROUND_CLOSEST((max - min) * caps->ac_level, 100); else - props.brightness = (max - min) * DIV_ROUND_CLOSEST(caps->dc_level, 100); + props.brightness = DIV_ROUND_CLOSEST((max - min) * caps->dc_level, 100); /* min is zero, so max needs to be adjusted */ props.max_brightness = max - min; drm_dbg(drm, "Backlight caps: min: %d, max: %d, ac %d, dc %d\n", min, max, -- 2.50.1 -- Lauri Tirkkonen | lotheac @ IRCnet

3 months, 2 weeks

2
1
0 0

FAILED: patch "[PATCH] platform/x86: think-lmi: Fix kobject cleanup" 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 9110056fe10b0519529bdbbac37311a5037ea0c2 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025070812-scorpion-thicken-4f6f@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 9110056fe10b0519529bdbbac37311a5037ea0c2 Mon Sep 17 00:00:00 2001 From: Kurt Borja <kuurtb(a)gmail.com> Date: Mon, 30 Jun 2025 14:31:20 -0300 Subject: [PATCH] platform/x86: think-lmi: Fix kobject cleanup MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In tlmi_analyze(), allocated structs with an embedded kobject are freed in error paths after the they were already initialized. Fix this by first by avoiding the initialization of kobjects in tlmi_analyze() and then by correctly cleaning them up in tlmi_release_attr() using their kset's kobject list. Fixes: a40cd7ef22fb ("platform/x86: think-lmi: Add WMI interface support on Lenovo platforms") Fixes: 30e78435d3bf ("platform/x86: think-lmi: Split kobject_init() and kobject_add() calls") Cc: stable(a)vger.kernel.org Reviewed-by: Mark Pearson <mpearson-lenovo(a)squebb.ca> Reviewed-by: Ilpo Järvinen <ilpo.jarvinen(a)linux.intel.com> Signed-off-by: Kurt Borja <kuurtb(a)gmail.com> Link: https://lore.kernel.org/r/20250630-lmi-fix-v3-2-ce4f81c9c481@gmail.com Signed-off-by: Ilpo Järvinen <ilpo.jarvinen(a)linux.intel.com> diff --git a/drivers/platform/x86/think-lmi.c b/drivers/platform/x86/think-lmi.c index 39306951f234..69f361f21f0f 100644 --- a/drivers/platform/x86/think-lmi.c +++ b/drivers/platform/x86/think-lmi.c @@ -1380,13 +1380,13 @@ static struct kobj_attribute debug_cmd = __ATTR_WO(debug_cmd); /* ---- Initialisation --------------------------------------------------------- */ static void tlmi_release_attr(void) { + struct kobject *pos, *n; int i; /* Attribute structures */ for (i = 0; i < TLMI_SETTINGS_COUNT; i++) { if (tlmi_priv.setting[i]) { sysfs_remove_group(&tlmi_priv.setting[i]->kobj, &tlmi_attr_group); - kobject_put(&tlmi_priv.setting[i]->kobj); } } sysfs_remove_file(&tlmi_priv.attribute_kset->kobj, &pending_reboot.attr); @@ -1395,6 +1395,9 @@ static void tlmi_release_attr(void) if (tlmi_priv.can_debug_cmd && debug_support) sysfs_remove_file(&tlmi_priv.attribute_kset->kobj, &debug_cmd.attr); + list_for_each_entry_safe(pos, n, &tlmi_priv.attribute_kset->list, entry) + kobject_put(pos); + kset_unregister(tlmi_priv.attribute_kset); /* Free up any saved signatures */ @@ -1403,19 +1406,17 @@ static void tlmi_release_attr(void) /* Authentication structures */ sysfs_remove_group(&tlmi_priv.pwd_admin->kobj, &auth_attr_group); - kobject_put(&tlmi_priv.pwd_admin->kobj); sysfs_remove_group(&tlmi_priv.pwd_power->kobj, &auth_attr_group); - kobject_put(&tlmi_priv.pwd_power->kobj); if (tlmi_priv.opcode_support) { sysfs_remove_group(&tlmi_priv.pwd_system->kobj, &auth_attr_group); - kobject_put(&tlmi_priv.pwd_system->kobj); sysfs_remove_group(&tlmi_priv.pwd_hdd->kobj, &auth_attr_group); - kobject_put(&tlmi_priv.pwd_hdd->kobj); sysfs_remove_group(&tlmi_priv.pwd_nvme->kobj, &auth_attr_group); - kobject_put(&tlmi_priv.pwd_nvme->kobj); } + list_for_each_entry_safe(pos, n, &tlmi_priv.authentication_kset->list, entry) + kobject_put(pos); + kset_unregister(tlmi_priv.authentication_kset); } @@ -1479,8 +1480,8 @@ static int tlmi_sysfs_init(void) /* Build attribute */ tlmi_priv.setting[i]->kobj.kset = tlmi_priv.attribute_kset; - ret = kobject_add(&tlmi_priv.setting[i]->kobj, NULL, - "%s", tlmi_priv.setting[i]->display_name); + ret = kobject_init_and_add(&tlmi_priv.setting[i]->kobj, &tlmi_attr_setting_ktype, + NULL, "%s", tlmi_priv.setting[i]->display_name); if (ret) goto fail_create_attr; @@ -1505,7 +1506,8 @@ static int tlmi_sysfs_init(void) /* Create authentication entries */ tlmi_priv.pwd_admin->kobj.kset = tlmi_priv.authentication_kset; - ret = kobject_add(&tlmi_priv.pwd_admin->kobj, NULL, "%s", "Admin"); + ret = kobject_init_and_add(&tlmi_priv.pwd_admin->kobj, &tlmi_pwd_setting_ktype, + NULL, "%s", "Admin"); if (ret) goto fail_create_attr; @@ -1514,7 +1516,8 @@ static int tlmi_sysfs_init(void) goto fail_create_attr; tlmi_priv.pwd_power->kobj.kset = tlmi_priv.authentication_kset; - ret = kobject_add(&tlmi_priv.pwd_power->kobj, NULL, "%s", "Power-on"); + ret = kobject_init_and_add(&tlmi_priv.pwd_power->kobj, &tlmi_pwd_setting_ktype, + NULL, "%s", "Power-on"); if (ret) goto fail_create_attr; @@ -1524,7 +1527,8 @@ static int tlmi_sysfs_init(void) if (tlmi_priv.opcode_support) { tlmi_priv.pwd_system->kobj.kset = tlmi_priv.authentication_kset; - ret = kobject_add(&tlmi_priv.pwd_system->kobj, NULL, "%s", "System"); + ret = kobject_init_and_add(&tlmi_priv.pwd_system->kobj, &tlmi_pwd_setting_ktype, + NULL, "%s", "System"); if (ret) goto fail_create_attr; @@ -1533,7 +1537,8 @@ static int tlmi_sysfs_init(void) goto fail_create_attr; tlmi_priv.pwd_hdd->kobj.kset = tlmi_priv.authentication_kset; - ret = kobject_add(&tlmi_priv.pwd_hdd->kobj, NULL, "%s", "HDD"); + ret = kobject_init_and_add(&tlmi_priv.pwd_hdd->kobj, &tlmi_pwd_setting_ktype, + NULL, "%s", "HDD"); if (ret) goto fail_create_attr; @@ -1542,7 +1547,8 @@ static int tlmi_sysfs_init(void) goto fail_create_attr; tlmi_priv.pwd_nvme->kobj.kset = tlmi_priv.authentication_kset; - ret = kobject_add(&tlmi_priv.pwd_nvme->kobj, NULL, "%s", "NVMe"); + ret = kobject_init_and_add(&tlmi_priv.pwd_nvme->kobj, &tlmi_pwd_setting_ktype, + NULL, "%s", "NVMe"); if (ret) goto fail_create_attr; @@ -1579,8 +1585,6 @@ static struct tlmi_pwd_setting *tlmi_create_auth(const char *pwd_type, new_pwd->maxlen = tlmi_priv.pwdcfg.core.max_length; new_pwd->index = 0; - kobject_init(&new_pwd->kobj, &tlmi_pwd_setting_ktype); - return new_pwd; } @@ -1685,7 +1689,6 @@ static int tlmi_analyze(struct wmi_device *wdev) if (setting->possible_values) strreplace(setting->possible_values, ',', ';'); - kobject_init(&setting->kobj, &tlmi_attr_setting_ktype); tlmi_priv.setting[i] = setting; kfree(item); }

3 months, 2 weeks

2
1
0 0

[REGRESSION] drm/amd/display: backlight brightness set to 0 at amdgpu initialization

by Lauri Tirkkonen

Hi, I hit this regression on the stable kernel on Alpine with a Lenovo Yoga Slim 7 Pro 17ACH5. During early boot, when the amdgpu module gets loaded, backlight brightness is set to zero, resulting in a black screen (and nothing in userspace is running yet to handle brightness keys; I need to use an external monitor or type in my rootfs passphrase blind). #regzbot introduced: 6c56c8ec6f9762c33bd22f31d43af4194d12da53 bisect log: git bisect start # status: waiting for both good and bad commits # good: [e60eb441596d1c70e4a264d2bac726c6cd2da067] Linux 6.15.4 git bisect good e60eb441596d1c70e4a264d2bac726c6cd2da067 # status: waiting for bad commit, 1 good commit known # bad: [1562d948232546cfad45a1beddc70fe0c7b34950] Linux 6.15.6 git bisect bad 1562d948232546cfad45a1beddc70fe0c7b34950 # good: [5e10620cb8e76279fd86411536c3fa0f486cd634] drm/xe/vm: move rebind_work init earlier git bisect good 5e10620cb8e76279fd86411536c3fa0f486cd634 # bad: [ece85751c3e46c0e3c4f772113f691b7aec81d5d] btrfs: record new subvolume in parent dir earlier to avoid dir logging races git bisect bad ece85751c3e46c0e3c4f772113f691b7aec81d5d # bad: [9f5d2487a9fad1d36bcf107d1f3b1ebc8b6796cf] iommufd/selftest: Add asserts testing global mfd git bisect bad 9f5d2487a9fad1d36bcf107d1f3b1ebc8b6796cf # good: [c0687ec5625b2261d48936d03c761e38657f4a4b] rust: completion: implement initial abstraction git bisect good c0687ec5625b2261d48936d03c761e38657f4a4b # bad: [889906e6eb5fab990c9b6b5fe8f1122b2416fc22] drm/amd/display: Export full brightness range to userspace git bisect bad 889906e6eb5fab990c9b6b5fe8f1122b2416fc22 # good: [c7d15ba11c8561c5f325ffeb27ed8a4e82d4d322] io_uring/kbuf: flag partial buffer mappings git bisect good c7d15ba11c8561c5f325ffeb27ed8a4e82d4d322 # good: [66089fa8c9ed162744037ab0375e38cc74c7f7ed] drm/amd/display: Add debugging message for brightness caps git bisect good 66089fa8c9ed162744037ab0375e38cc74c7f7ed # bad: [cd711c87c2862be5e71eee79901f94e1c943f9fc] drm/amd/display: Only read ACPI backlight caps once git bisect bad cd711c87c2862be5e71eee79901f94e1c943f9fc # bad: [6c56c8ec6f9762c33bd22f31d43af4194d12da53] drm/amd/display: Fix default DC and AC levels git bisect bad 6c56c8ec6f9762c33bd22f31d43af4194d12da53 # first bad commit: [6c56c8ec6f9762c33bd22f31d43af4194d12da53] drm/amd/display: Fix default DC and AC levels 'dmesg|grep amd' on 6.15.7 on this machine: [ 0.319726] perf/amd_iommu: Detected AMD IOMMU #0 (2 banks, 4 counters/bank). [ 4.090573] [drm] amdgpu kernel modesetting enabled. [ 4.094238] amdgpu: Virtual CRAT table created for CPU [ 4.095389] amdgpu: Topology: Add CPU node [ 4.096451] amdgpu 0000:03:00.0: enabling device (0006 -> 0007) [ 4.174815] amdgpu 0000:03:00.0: amdgpu: detected ip block number 0 <soc15_common> [ 4.176034] amdgpu 0000:03:00.0: amdgpu: detected ip block number 1 <gmc_v9_0> [ 4.176992] amdgpu 0000:03:00.0: amdgpu: detected ip block number 2 <vega10_ih> [ 4.177911] amdgpu 0000:03:00.0: amdgpu: detected ip block number 3 <psp> [ 4.178799] amdgpu 0000:03:00.0: amdgpu: detected ip block number 4 <smu> [ 4.179704] amdgpu 0000:03:00.0: amdgpu: detected ip block number 5 <dm> [ 4.180594] amdgpu 0000:03:00.0: amdgpu: detected ip block number 6 <gfx_v9_0> [ 4.181445] amdgpu 0000:03:00.0: amdgpu: detected ip block number 7 <sdma_v4_0> [ 4.182299] amdgpu 0000:03:00.0: amdgpu: detected ip block number 8 <vcn_v2_0> [ 4.183114] amdgpu 0000:03:00.0: amdgpu: detected ip block number 9 <jpeg_v2_0> [ 4.183910] amdgpu 0000:03:00.0: amdgpu: Fetched VBIOS from VFCT [ 4.184800] amdgpu: ATOM BIOS: 113-CEZANNE-017 [ 4.208484] amdgpu 0000:03:00.0: vgaarb: deactivate vga console [ 4.208493] amdgpu 0000:03:00.0: amdgpu: Trusted Memory Zone (TMZ) feature enabled [ 4.208509] amdgpu 0000:03:00.0: amdgpu: MODE2 reset [ 4.209086] amdgpu 0000:03:00.0: amdgpu: VRAM: 2048M 0x000000F400000000 - 0x000000F47FFFFFFF (2048M used) [ 4.209099] amdgpu 0000:03:00.0: amdgpu: GART: 1024M 0x0000000000000000 - 0x000000003FFFFFFF [ 4.209376] [drm] amdgpu: 2048M of VRAM memory ready [ 4.209386] [drm] amdgpu: 6912M of GTT memory ready. [ 4.210517] amdgpu 0000:03:00.0: amdgpu: Found VCN firmware Version ENC: 1.24 DEC: 8 VEP: 0 Revision: 3 [ 4.927350] amdgpu 0000:03:00.0: amdgpu: reserve 0x400000 from 0xf47f400000 for PSP TMR [ 5.010609] amdgpu 0000:03:00.0: amdgpu: RAS: optional ras ta ucode is not available [ 5.021347] amdgpu 0000:03:00.0: amdgpu: RAP: optional rap ta ucode is not available [ 5.021357] amdgpu 0000:03:00.0: amdgpu: SECUREDISPLAY: securedisplay ta ucode is not available [ 5.021725] amdgpu 0000:03:00.0: amdgpu: SMU is initialized successfully! [ 5.131949] amdgpu 0000:03:00.0: amdgpu: [drm] Using ACPI provided EDID for eDP-1 [ 5.385266] kfd kfd: amdgpu: Allocated 3969056 bytes on gart [ 5.385286] kfd kfd: amdgpu: Total number of KFD nodes to be created: 1 [ 5.385435] amdgpu: Virtual CRAT table created for GPU [ 5.385562] amdgpu: Topology: Add dGPU node [0x1638:0x1002] [ 5.385569] kfd kfd: amdgpu: added device 1002:1638 [ 5.385582] amdgpu 0000:03:00.0: amdgpu: SE 1, SH per SE 1, CU per SH 8, active_cu_number 8 [ 5.385592] amdgpu 0000:03:00.0: amdgpu: ring gfx uses VM inv eng 0 on hub 0 [ 5.385598] amdgpu 0000:03:00.0: amdgpu: ring comp_1.0.0 uses VM inv eng 1 on hub 0 [ 5.385605] amdgpu 0000:03:00.0: amdgpu: ring comp_1.1.0 uses VM inv eng 4 on hub 0 [ 5.385612] amdgpu 0000:03:00.0: amdgpu: ring comp_1.2.0 uses VM inv eng 5 on hub 0 [ 5.385619] amdgpu 0000:03:00.0: amdgpu: ring comp_1.3.0 uses VM inv eng 6 on hub 0 [ 5.385625] amdgpu 0000:03:00.0: amdgpu: ring comp_1.0.1 uses VM inv eng 7 on hub 0 [ 5.385632] amdgpu 0000:03:00.0: amdgpu: ring comp_1.1.1 uses VM inv eng 8 on hub 0 [ 5.385639] amdgpu 0000:03:00.0: amdgpu: ring comp_1.2.1 uses VM inv eng 9 on hub 0 [ 5.385645] amdgpu 0000:03:00.0: amdgpu: ring comp_1.3.1 uses VM inv eng 10 on hub 0 [ 5.385652] amdgpu 0000:03:00.0: amdgpu: ring kiq_0.2.1.0 uses VM inv eng 11 on hub 0 [ 5.385659] amdgpu 0000:03:00.0: amdgpu: ring sdma0 uses VM inv eng 0 on hub 8 [ 5.385665] amdgpu 0000:03:00.0: amdgpu: ring vcn_dec uses VM inv eng 1 on hub 8 [ 5.385672] amdgpu 0000:03:00.0: amdgpu: ring vcn_enc0 uses VM inv eng 4 on hub 8 [ 5.385679] amdgpu 0000:03:00.0: amdgpu: ring vcn_enc1 uses VM inv eng 5 on hub 8 [ 5.385685] amdgpu 0000:03:00.0: amdgpu: ring jpeg_dec uses VM inv eng 6 on hub 8 [ 5.454665] amdgpu 0000:03:00.0: amdgpu: Runtime PM not available [ 5.455003] amdgpu 0000:03:00.0: amdgpu: [drm] Using custom brightness curve [ 5.455339] [drm] Initialized amdgpu 3.63.0 for 0000:03:00.0 on minor 1 [ 5.480731] fbcon: amdgpudrmfb (fb0) is primary device [ 6.796057] amdgpu 0000:03:00.0: [drm] fb0: amdgpudrmfb frame buffer device -- Lauri Tirkkonen | lotheac @ IRCnet

3 months, 2 weeks

3
13
0 0

[PATCH V2] efi/tpm: Fix the issue where the CC platforms event log header can't be correctly identified

by yangge1116＠126.com

From: Ge Yang <yangge1116(a)126.com> Since commit d228814b1913 ("efi/libstub: Add get_event_log() support for CC platforms") reuses TPM2 support code for the CC platforms, when launching a TDX virtual machine with coco measurement enabled, the following error log is generated: [Firmware Bug]: Failed to parse event in TPM Final Events Log Call Trace: efi_config_parse_tables() efi_tpm_eventlog_init() tpm2_calc_event_log_size() __calc_tpm2_event_size() The pcr_idx value in the Intel TDX log header is 1, causing the function __calc_tpm2_event_size() to fail to recognize the log header, ultimately leading to the "Failed to parse event in TPM Final Events Log" error. According to UEFI Specification 2.10, Section 38.4.1: For TDX, TPM PCR 0 maps to MRTD, so the log header uses TPM PCR 1 instead. To successfully parse the TDX event log header, the check for a pcr_idx value of 0 must be skipped. According to Table 6 in Section 10.2.1 of the TCG PC Client Specification, the index field does not require the PCR index to be fixed at zero. Therefore, skipping the check for a pcr_idx value of 0 for CC platforms is safe. Link: https://uefi.org/specs/UEFI/2.10/38_Confidential_Computing.html#intel-trust… Link: https://trustedcomputinggroup.org/wp-content/uploads/TCG_PCClient_PFP_r1p05… Fixes: d228814b1913 ("efi/libstub: Add get_event_log() support for CC platforms") Signed-off-by: Ge Yang <yangge1116(a)126.com> Cc: stable(a)vger.kernel.org --- V2: - limit the fix for CC only suggested by Jarkko and Sathyanarayanan drivers/char/tpm/eventlog/tpm2.c | 3 ++- drivers/firmware/efi/libstub/tpm.c | 13 +++++++++---- drivers/firmware/efi/tpm.c | 3 ++- include/linux/tpm_eventlog.h | 14 +++++++++++--- 4 files changed, 24 insertions(+), 9 deletions(-) diff --git a/drivers/char/tpm/eventlog/tpm2.c b/drivers/char/tpm/eventlog/tpm2.c index 37a0580..87a8b7f 100644 --- a/drivers/char/tpm/eventlog/tpm2.c +++ b/drivers/char/tpm/eventlog/tpm2.c @@ -36,7 +36,8 @@ static size_t calc_tpm2_event_size(struct tcg_pcr_event2_head *event, struct tcg_pcr_event *event_header) { - return __calc_tpm2_event_size(event, event_header, false); + return __calc_tpm2_event_size(event, event_header, false, + cc_platform_has(CC_ATTR_GUEST_STATE_ENCRYPT)); } static void *tpm2_bios_measurements_start(struct seq_file *m, loff_t *pos) diff --git a/drivers/firmware/efi/libstub/tpm.c b/drivers/firmware/efi/libstub/tpm.c index a5c6c4f..9728060 100644 --- a/drivers/firmware/efi/libstub/tpm.c +++ b/drivers/firmware/efi/libstub/tpm.c @@ -50,7 +50,8 @@ void efi_enable_reset_attack_mitigation(void) static void efi_retrieve_tcg2_eventlog(int version, efi_physical_addr_t log_location, efi_physical_addr_t log_last_entry, efi_bool_t truncated, - struct efi_tcg2_final_events_table *final_events_table) + struct efi_tcg2_final_events_table *final_events_table, + bool is_cc_event) { efi_guid_t linux_eventlog_guid = LINUX_EFI_TPM_EVENT_LOG_GUID; efi_status_t status; @@ -87,7 +88,8 @@ static void efi_retrieve_tcg2_eventlog(int version, efi_physical_addr_t log_loca last_entry_size = __calc_tpm2_event_size((void *)last_entry_addr, (void *)(long)log_location, - false); + false, + is_cc_event); } else { last_entry_size = sizeof(struct tcpa_event) + ((struct tcpa_event *) last_entry_addr)->event_size; @@ -123,7 +125,8 @@ static void efi_retrieve_tcg2_eventlog(int version, efi_physical_addr_t log_loca header = data + offset + final_events_size; event_size = __calc_tpm2_event_size(header, (void *)(long)log_location, - false); + false, + is_cc_event); /* If calc fails this is a malformed log */ if (!event_size) break; @@ -157,6 +160,7 @@ void efi_retrieve_eventlog(void) efi_tcg2_protocol_t *tpm2 = NULL; efi_bool_t truncated; efi_status_t status; + bool is_cc_event = false; status = efi_bs_call(locate_protocol, &tpm2_guid, NULL, (void **)&tpm2); if (status == EFI_SUCCESS) { @@ -186,11 +190,12 @@ void efi_retrieve_eventlog(void) final_events_table = get_efi_config_table(EFI_CC_FINAL_EVENTS_TABLE_GUID); + is_cc_event = true; } if (status != EFI_SUCCESS || !log_location) return; efi_retrieve_tcg2_eventlog(version, log_location, log_last_entry, - truncated, final_events_table); + truncated, final_events_table, is_cc_event); } diff --git a/drivers/firmware/efi/tpm.c b/drivers/firmware/efi/tpm.c index cdd4310..a94816d 100644 --- a/drivers/firmware/efi/tpm.c +++ b/drivers/firmware/efi/tpm.c @@ -23,7 +23,8 @@ static int __init tpm2_calc_event_log_size(void *data, int count, void *size_inf while (count > 0) { header = data + size; - event_size = __calc_tpm2_event_size(header, size_info, true); + event_size = __calc_tpm2_event_size(header, size_info, true, + cc_platform_has(CC_ATTR_GUEST_STATE_ENCRYPT)); if (event_size == 0) return -1; size += event_size; diff --git a/include/linux/tpm_eventlog.h b/include/linux/tpm_eventlog.h index 891368e..b3380c9 100644 --- a/include/linux/tpm_eventlog.h +++ b/include/linux/tpm_eventlog.h @@ -143,6 +143,7 @@ struct tcg_algorithm_info { * @event: Pointer to the event whose size should be calculated * @event_header: Pointer to the initial event containing the digest lengths * @do_mapping: Whether or not the event needs to be mapped + * @is_cc_event: Whether or not the event is from a CC platform * * The TPM2 event log format can contain multiple digests corresponding to * separate PCR banks, and also contains a variable length of the data that @@ -159,7 +160,8 @@ struct tcg_algorithm_info { static __always_inline u32 __calc_tpm2_event_size(struct tcg_pcr_event2_head *event, struct tcg_pcr_event *event_header, - bool do_mapping) + bool do_mapping, + bool is_cc_event) { struct tcg_efi_specid_event_head *efispecid; struct tcg_event_field *event_field; @@ -201,8 +203,14 @@ static __always_inline u32 __calc_tpm2_event_size(struct tcg_pcr_event2_head *ev count = event->count; event_type = event->event_type; - /* Verify that it's the log header */ - if (event_header->pcr_idx != 0 || + /* + * Verify that it's the log header. According to the TCG PC Client + * Specification, when identifying a log header, the check for a + * pcr_idx value of 0 is not required. For CC platforms, skipping + * this check during log header is necessary; otherwise, the CC + * platform's log header may fail to be recognized. + */ + if ((!is_cc_event && event_header->pcr_idx != 0) || event_header->event_type != NO_ACTION || memcmp(event_header->digest, zero_digest, sizeof(zero_digest))) { size = 0; -- 2.7.4

3 months, 2 weeks

4
3
0 0

[PATCH 1/3] scsi: ufs: ufs-mediatek: Add UFS host support for MT8195 SoC

by Macpaul Lin

Add "mediatek,mt8195-ufshci" to the of_device_id table to enable support for MediaTek MT8195/MT8395 UFS host controller. This matches the device node entry in the MT8195/MT8395 device tree and allows proper driver binding. Signed-off-by: Macpaul Lin <macpaul.lin(a)mediatek.com> --- drivers/ufs/host/ufs-mediatek.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/ufs/host/ufs-mediatek.c b/drivers/ufs/host/ufs-mediatek.c index 182f58d0c9db..e1dbf0231c5e 100644 --- a/drivers/ufs/host/ufs-mediatek.c +++ b/drivers/ufs/host/ufs-mediatek.c @@ -50,6 +50,7 @@ static const struct ufs_dev_quirk ufs_mtk_dev_fixups[] = { static const struct of_device_id ufs_mtk_of_match[] = { { .compatible = "mediatek,mt8183-ufshci" }, + { .compatible = "mediatek,mt8195-ufshci" }, {}, }; MODULE_DEVICE_TABLE(of, ufs_mtk_of_match); -- 2.45.2

3 months, 2 weeks

3
4
0 0

[PATCH v2 mm-hotfixes 5/5] x86/mm: drop unnecessary calls to sync_global_pgds() and fold into its sole user

by Harry Yoo

Now that p*d_populate_kernel{,init}() handles page table synchronization, calling sync_global_pgds() is no longer necessary. Remove those redundant calls. Additionally, since arch_sync_kernel_mappings() is now the only remaining caller of sync_global_pgds(), fold the function into its user. Cc: stable(a)vger.kernel.org Suggested-by: Dave Hansen <dave.hansen(a)linux.intel.com> Signed-off-by: Harry Yoo <harry.yoo(a)oracle.com> --- arch/x86/mm/init_64.c | 17 ++--------------- 1 file changed, 2 insertions(+), 15 deletions(-) diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index e4922b9c8403..f1507de3b7a3 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -228,7 +228,7 @@ static void sync_global_pgds_l4(unsigned long start, unsigned long end) * When memory was added make sure all the processes MM have * suitable PGD entries in the local PGD level page. */ -static void sync_global_pgds(unsigned long start, unsigned long end) +void arch_sync_kernel_mappings(unsigned long start, unsigned long end) { if (pgtable_l5_enabled()) sync_global_pgds_l5(start, end); @@ -236,11 +236,6 @@ static void sync_global_pgds(unsigned long start, unsigned long end) sync_global_pgds_l4(start, end); } -void arch_sync_kernel_mappings(unsigned long start, unsigned long end) -{ - sync_global_pgds(start, end); -} - /* * NOTE: This function is marked __ref because it calls __init function * (alloc_bootmem_pages). It's safe to do it ONLY when after_bootmem == 0. @@ -746,13 +741,11 @@ __kernel_physical_mapping_init(unsigned long paddr_start, unsigned long page_size_mask, pgprot_t prot, bool init) { - bool pgd_changed = false; - unsigned long vaddr, vaddr_start, vaddr_end, vaddr_next, paddr_last; + unsigned long vaddr, vaddr_end, vaddr_next, paddr_last; paddr_last = paddr_end; vaddr = (unsigned long)__va(paddr_start); vaddr_end = (unsigned long)__va(paddr_end); - vaddr_start = vaddr; for (; vaddr < vaddr_end; vaddr = vaddr_next) { pgd_t *pgd = pgd_offset_k(vaddr); @@ -781,12 +774,8 @@ __kernel_physical_mapping_init(unsigned long paddr_start, (pud_t *) p4d, init); spin_unlock(&init_mm.page_table_lock); - pgd_changed = true; } - if (pgd_changed) - sync_global_pgds(vaddr_start, vaddr_end - 1); - return paddr_last; } @@ -1580,8 +1569,6 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, err = -ENOMEM; } else err = vmemmap_populate_basepages(start, end, node, NULL); - if (!err) - sync_global_pgds(start, end - 1); return err; } -- 2.43.0

3 months, 2 weeks

1
0
0 0

[PATCH v2 mm-hotfixes 4/5] x86/mm: convert p*d_populate{,_init} to _kernel variants

by Harry Yoo

Introduce p*d_populate_kernel_safe() and convert p*d_populate{,_init}() to p*d_populate_kernel{,_init}() to ensure synchronization of kernel mappings when populating PGD entries. By converting them, we eliminate the risk of forgetting to synchronize top-level page tables after populating PGD entries. Cc: stable(a)vger.kernel.org Suggested-by: Dave Hansen <dave.hansen(a)linux.intel.com> Signed-off-by: Harry Yoo <harry.yoo(a)oracle.com> --- arch/x86/include/asm/pgalloc.h | 20 ++++++++++++++++++++ arch/x86/mm/init_64.c | 25 +++++++++++++++++++------ arch/x86/mm/kasan_init_64.c | 8 ++++---- 3 files changed, 43 insertions(+), 10 deletions(-) diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h index ead834e8141a..aea3b16e7a35 100644 --- a/arch/x86/include/asm/pgalloc.h +++ b/arch/x86/include/asm/pgalloc.h @@ -122,6 +122,15 @@ static inline void p4d_populate_safe(struct mm_struct *mm, p4d_t *p4d, pud_t *pu set_p4d_safe(p4d, __p4d(_PAGE_TABLE | __pa(pud))); } +static inline void p4d_populate_kernel_safe(unsigned long addr, + p4d_t *p4d, pud_t *pud) +{ + paravirt_alloc_pud(&init_mm, __pa(pud) >> PAGE_SHIFT); + set_p4d_safe(p4d, __p4d(_PAGE_TABLE | __pa(pud))); + if (ARCH_PAGE_TABLE_SYNC_MASK & PGTBL_P4D_MODIFIED) + arch_sync_kernel_mappings(addr, addr); +} + extern void ___pud_free_tlb(struct mmu_gather *tlb, pud_t *pud); static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pud, @@ -147,6 +156,17 @@ static inline void pgd_populate_safe(struct mm_struct *mm, pgd_t *pgd, p4d_t *p4 set_pgd_safe(pgd, __pgd(_PAGE_TABLE | __pa(p4d))); } +static inline void pgd_populate_kernel_safe(unsigned long addr, + pgd_t *pgd, p4d_t *p4d) +{ + if (!pgtable_l5_enabled()) + return; + paravirt_alloc_p4d(&init_mm, __pa(p4d) >> PAGE_SHIFT); + set_pgd_safe(pgd, __pgd(_PAGE_TABLE | __pa(p4d))); + if (ARCH_PAGE_TABLE_SYNC_MASK & PGTBL_PGD_MODIFIED) + arch_sync_kernel_mappings(addr, addr); +} + extern void ___p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d); static inline void __p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d, diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 3800479022e4..e4922b9c8403 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -75,6 +75,19 @@ DEFINE_POPULATE(pgd_populate, pgd, p4d, init) DEFINE_POPULATE(pud_populate, pud, pmd, init) DEFINE_POPULATE(pmd_populate_kernel, pmd, pte, init) +#define DEFINE_POPULATE_KERNEL(fname, type1, type2, init) \ +static inline void fname##_init(unsigned long addr, \ + type1##_t *arg1, type2##_t *arg2, bool init) \ +{ \ + if (init) \ + fname##_safe(addr, arg1, arg2); \ + else \ + fname(addr, arg1, arg2); \ +} + +DEFINE_POPULATE_KERNEL(pgd_populate_kernel, pgd, p4d, init) +DEFINE_POPULATE_KERNEL(p4d_populate_kernel, p4d, pud, init) + #define DEFINE_ENTRY(type1, type2, init) \ static inline void set_##type1##_init(type1##_t *arg1, \ type2##_t arg2, bool init) \ @@ -255,7 +268,7 @@ static p4d_t *fill_p4d(pgd_t *pgd, unsigned long vaddr) { if (pgd_none(*pgd)) { p4d_t *p4d = (p4d_t *)spp_getpage(); - pgd_populate(&init_mm, pgd, p4d); + pgd_populate_kernel(vaddr, pgd, p4d); if (p4d != p4d_offset(pgd, 0)) printk(KERN_ERR "PAGETABLE BUG #00! %p <-> %p\n", p4d, p4d_offset(pgd, 0)); @@ -267,7 +280,7 @@ static pud_t *fill_pud(p4d_t *p4d, unsigned long vaddr) { if (p4d_none(*p4d)) { pud_t *pud = (pud_t *)spp_getpage(); - p4d_populate(&init_mm, p4d, pud); + p4d_populate_kernel(vaddr, p4d, pud); if (pud != pud_offset(p4d, 0)) printk(KERN_ERR "PAGETABLE BUG #01! %p <-> %p\n", pud, pud_offset(p4d, 0)); @@ -720,7 +733,7 @@ phys_p4d_init(p4d_t *p4d_page, unsigned long paddr, unsigned long paddr_end, page_size_mask, prot, init); spin_lock(&init_mm.page_table_lock); - p4d_populate_init(&init_mm, p4d, pud, init); + p4d_populate_kernel_init(vaddr, p4d, pud, init); spin_unlock(&init_mm.page_table_lock); } @@ -762,10 +775,10 @@ __kernel_physical_mapping_init(unsigned long paddr_start, spin_lock(&init_mm.page_table_lock); if (pgtable_l5_enabled()) - pgd_populate_init(&init_mm, pgd, p4d, init); + pgd_populate_kernel_init(vaddr, pgd, p4d, init); else - p4d_populate_init(&init_mm, p4d_offset(pgd, vaddr), - (pud_t *) p4d, init); + p4d_populate_kernel_init(vaddr, p4d_offset(pgd, vaddr), + (pud_t *) p4d, init); spin_unlock(&init_mm.page_table_lock); pgd_changed = true; diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c index 0539efd0d216..e825952d25b2 100644 --- a/arch/x86/mm/kasan_init_64.c +++ b/arch/x86/mm/kasan_init_64.c @@ -108,7 +108,7 @@ static void __init kasan_populate_p4d(p4d_t *p4d, unsigned long addr, if (p4d_none(*p4d)) { void *p = early_alloc(PAGE_SIZE, nid, true); - p4d_populate(&init_mm, p4d, p); + p4d_populate_kernel(addr, p4d, p); } pud = pud_offset(p4d, addr); @@ -128,7 +128,7 @@ static void __init kasan_populate_pgd(pgd_t *pgd, unsigned long addr, if (pgd_none(*pgd)) { p = early_alloc(PAGE_SIZE, nid, true); - pgd_populate(&init_mm, pgd, p); + pgd_populate_kernel(addr, pgd, p); } p4d = p4d_offset(pgd, addr); @@ -255,7 +255,7 @@ static void __init kasan_shallow_populate_p4ds(pgd_t *pgd, if (p4d_none(*p4d)) { p = early_alloc(PAGE_SIZE, NUMA_NO_NODE, true); - p4d_populate(&init_mm, p4d, p); + p4d_populate_kernel(addr, p4d, p); } } while (p4d++, addr = next, addr != end); } @@ -273,7 +273,7 @@ static void __init kasan_shallow_populate_pgds(void *start, void *end) if (pgd_none(*pgd)) { p = early_alloc(PAGE_SIZE, NUMA_NO_NODE, true); - pgd_populate(&init_mm, pgd, p); + pgd_populate_kernel(addr, pgd, p); } /* -- 2.43.0

3 months, 2 weeks

1
0
0 0

[PATCH v2 mm-hotfixes 3/5] x86/mm: define ARCH_PAGE_TABLE_SYNC_MASK and arch_sync_kernel_mappings()

by Harry Yoo

Define ARCH_PAGE_TABLE_SYNC_MASK and arch_sync_kernel_mappings() to ensure page tables are properly synchronized when calling p*d_populate_kernel(). It is inteneded to synchronize page tables via pgd_pouplate_kernel() when 5-level paging is in use and via p4d_pouplate_kernel() when 4-level paging is used. This fixes intermittent boot failures on systems using 4-level paging and a large amount of persistent memory: BUG: unable to handle page fault for address: ffffe70000000034 #PF: supervisor write access in kernel mode #PF: error_code(0x0002) - not-present page PGD 0 P4D 0 Oops: 0002 [#1] SMP NOPTI RIP: 0010:__init_single_page+0x9/0x6d Call Trace: <TASK> __init_zone_device_page+0x17/0x5d memmap_init_zone_device+0x154/0x1bb pagemap_range+0x2e0/0x40f memremap_pages+0x10b/0x2f0 devm_memremap_pages+0x1e/0x60 dev_dax_probe+0xce/0x2ec [device_dax] dax_bus_probe+0x6d/0xc9 [... snip ...] </TASK> It also fixes a crash in vmemmap_set_pmd() caused by accessing vmemmap before sync_global_pgds() [1]: BUG: unable to handle page fault for address: ffffeb3ff1200000 #PF: supervisor write access in kernel mode #PF: error_code(0x0002) - not-present page PGD 0 P4D 0 Oops: Oops: 0002 [#1] PREEMPT SMP NOPTI Tainted: [W]=WARN RIP: 0010:vmemmap_set_pmd+0xff/0x230 <TASK> vmemmap_populate_hugepages+0x176/0x180 vmemmap_populate+0x34/0x80 __populate_section_memmap+0x41/0x90 sparse_add_section+0x121/0x3e0 __add_pages+0xba/0x150 add_pages+0x1d/0x70 memremap_pages+0x3dc/0x810 devm_memremap_pages+0x1c/0x60 xe_devm_add+0x8b/0x100 [xe] xe_tile_init_noalloc+0x6a/0x70 [xe] xe_device_probe+0x48c/0x740 [xe] [... snip ...] Cc: stable(a)vger.kernel.org Fixes: 8d400913c231 ("x86/vmemmap: handle unpopulated sub-pmd ranges") Closes: https://lore.kernel.org/linux-mm/20250311114420.240341-1-gwan-gyeong.mun@in… [1] Suggested-by: Dave Hansen <dave.hansen(a)linux.intel.com> Signed-off-by: Harry Yoo <harry.yoo(a)oracle.com> --- arch/x86/include/asm/pgalloc.h | 2 ++ arch/x86/mm/init_64.c | 5 +++++ 2 files changed, 7 insertions(+) diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h index c88691b15f3c..ead834e8141a 100644 --- a/arch/x86/include/asm/pgalloc.h +++ b/arch/x86/include/asm/pgalloc.h @@ -10,6 +10,8 @@ #define __HAVE_ARCH_PTE_ALLOC_ONE #define __HAVE_ARCH_PGD_FREE +#define ARCH_PAGE_TABLE_SYNC_MASK \ + (pgtable_l5_enabled() ? PGTBL_PGD_MODIFIED : PGTBL_P4D_MODIFIED) #include <asm-generic/pgalloc.h> static inline int __paravirt_pgd_alloc(struct mm_struct *mm) { return 0; } diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index fdb6cab524f0..3800479022e4 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -223,6 +223,11 @@ static void sync_global_pgds(unsigned long start, unsigned long end) sync_global_pgds_l4(start, end); } +void arch_sync_kernel_mappings(unsigned long start, unsigned long end) +{ + sync_global_pgds(start, end); +} + /* * NOTE: This function is marked __ref because it calls __init function * (alloc_bootmem_pages). It's safe to do it ONLY when after_bootmem == 0. -- 2.43.0

3 months, 2 weeks

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror