From: Kornel Dulęba korneld@chromium.org

commit 534e465845ebfb4a97eb5459d3931a0b35e3b9a5 upstream.

This reverts commit b26cd9325be4c1fcd331b77f10acb627c560d4d7.

This patch introduces a regression on Lenovo Z13, which can't wake from the lid with it applied; and some unspecified AMD based Dell platforms are unable to wake from hitting the power button

Signed-off-by: Kornel Dulęba korneld@chromium.org Reviewed-by: Mario Limonciello mario.limonciello@amd.com Link: https://lore.kernel.org/r/20230411134932.292287-1-korneld@chromium.org Signed-off-by: Linus Walleij linus.walleij@linaro.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/pinctrl/pinctrl-amd.c | 36 ++++++++++++++++-------------------- 1 file changed, 16 insertions(+), 20 deletions(-)

--- a/drivers/pinctrl/pinctrl-amd.c +++ b/drivers/pinctrl/pinctrl-amd.c @@ -865,34 +865,32 @@ static const struct pinconf_ops amd_pinc .pin_config_group_set = amd_pinconf_group_set, };

-static void amd_gpio_irq_init_pin(struct amd_gpio *gpio_dev, int pin) +static void amd_gpio_irq_init(struct amd_gpio *gpio_dev) { - const struct pin_desc *pd; + struct pinctrl_desc *desc = gpio_dev->pctrl->desc; unsigned long flags; u32 pin_reg, mask; + int i;

mask = BIT(WAKE_CNTRL_OFF_S0I3) | BIT(WAKE_CNTRL_OFF_S3) | BIT(INTERRUPT_MASK_OFF) | BIT(INTERRUPT_ENABLE_OFF) | BIT(WAKE_CNTRL_OFF_S4);

- pd = pin_desc_get(gpio_dev->pctrl, pin); - if (!pd) - return; + for (i = 0; i < desc->npins; i++) { + int pin = desc->pins[i].number; + const struct pin_desc *pd = pin_desc_get(gpio_dev->pctrl, pin);

- raw_spin_lock_irqsave(&gpio_dev->lock, flags); - pin_reg = readl(gpio_dev->base + pin * 4); - pin_reg &= ~mask; - writel(pin_reg, gpio_dev->base + pin * 4); - raw_spin_unlock_irqrestore(&gpio_dev->lock, flags); -} + if (!pd) + continue;

-static void amd_gpio_irq_init(struct amd_gpio *gpio_dev) -{ - struct pinctrl_desc *desc = gpio_dev->pctrl->desc; - int i; + raw_spin_lock_irqsave(&gpio_dev->lock, flags);

- for (i = 0; i < desc->npins; i++) - amd_gpio_irq_init_pin(gpio_dev, i); + pin_reg = readl(gpio_dev->base + i * 4); + pin_reg &= ~mask; + writel(pin_reg, gpio_dev->base + i * 4); + + raw_spin_unlock_irqrestore(&gpio_dev->lock, flags); + } }

#ifdef CONFIG_PM_SLEEP @@ -945,10 +943,8 @@ static int amd_gpio_resume(struct device for (i = 0; i < desc->npins; i++) { int pin = desc->pins[i].number;

- if (!amd_gpio_should_save(gpio_dev, pin)) { - amd_gpio_irq_init_pin(gpio_dev, pin); + if (!amd_gpio_should_save(gpio_dev, pin)) continue; - }

raw_spin_lock_irqsave(&gpio_dev->lock, flags); gpio_dev->saved_regs[i] |= readl(gpio_dev->base + pin * 4) & PIN_IRQ_PENDING;

From: Ville Syrjälä ville.syrjala@linux.intel.com

commit 4d4e766f8b7dbdefa7a78e91eb9c7a29d0d818b8 upstream.

Unlike SKL/GLK the ICL CSC unit suffers from a new issue where CSC_MODE arming is sticky. That is, once armed it remains armed causing the CSC coeff/offset registers to become effectively self-arming.

CSC coeff/offset registers writes no longer disarm the CSC, but fortunately register read still do. So we can use that to disarm the CSC unit once the registers for the current frame have been latched. This avoid s the self-arming behaviour from persisting into the next frame's .color_commit_noarm() call.

Cc: stable@vger.kernel.org #v5.19+ Cc: Manasi Navare navaremanasi@google.com Cc: Drew Davenport ddavenport@chromium.org Cc: Imre Deak imre.deak@intel.com Cc: Jouni Högander jouni.hogander@intel.com Fixes: d13dde449580 ("drm/i915: Split pipe+output CSC programming to noarm+arm pair") Signed-off-by: Ville Syrjälä ville.syrjala@linux.intel.com Link: https://patchwork.freedesktop.org/patch/msgid/20230320095438.17328-5-ville.s... Reviewed-by: Imre Deak imre.deak@intel.com (cherry picked from commit 92736f1b452bbb8a66bdb5b1d263ad00e04dd3b8) Signed-off-by: Jani Nikula jani.nikula@intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/gpu/drm/i915/display/intel_color.c | 43 ++++++++++++++++++++++++++++- 1 file changed, 42 insertions(+), 1 deletion(-)

--- a/drivers/gpu/drm/i915/display/intel_color.c +++ b/drivers/gpu/drm/i915/display/intel_color.c @@ -516,6 +516,14 @@ static void ilk_lut_12p4_pack(struct drm

static void icl_color_commit_noarm(const struct intel_crtc_state *crtc_state) { + /* + * Despite Wa_1406463849, ICL no longer suffers from the SKL + * DC5/PSR CSC black screen issue (see skl_color_commit_noarm()). + * Possibly due to the extra sticky CSC arming + * (see icl_color_post_update()). + * + * On TGL+ all CSC arming issues have been properly fixed. + */ icl_load_csc_matrix(crtc_state); }

@@ -617,6 +625,28 @@ static void icl_color_commit_arm(const s crtc_state->csc_mode); }

+static void icl_color_post_update(const struct intel_crtc_state *crtc_state) +{ + struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); + struct drm_i915_private *i915 = to_i915(crtc->base.dev); + + /* + * Despite Wa_1406463849, ICL CSC is no longer disarmed by + * coeff/offset register *writes*. Instead, once CSC_MODE + * is armed it stays armed, even after it has been latched. + * Afterwards the coeff/offset registers become effectively + * self-arming. That self-arming must be disabled before the + * next icl_color_commit_noarm() tries to write the next set + * of coeff/offset registers. Fortunately register *reads* + * do still disarm the CSC. Naturally this must not be done + * until the previously written CSC registers have actually + * been latched. + * + * TGL+ no longer need this workaround. + */ + intel_de_read_fw(i915, PIPE_CSC_PREOFF_HI(crtc->pipe)); +} + static struct drm_property_blob * create_linear_lut(struct drm_i915_private *i915, int lut_size) { @@ -2345,10 +2375,19 @@ static const struct intel_color_funcs i9 .read_luts = i9xx_read_luts, };

+static const struct intel_color_funcs tgl_color_funcs = { + .color_check = icl_color_check, + .color_commit_noarm = icl_color_commit_noarm, + .color_commit_arm = icl_color_commit_arm, + .load_luts = icl_load_luts, + .read_luts = icl_read_luts, +}; + static const struct intel_color_funcs icl_color_funcs = { .color_check = icl_color_check, .color_commit_noarm = icl_color_commit_noarm, .color_commit_arm = icl_color_commit_arm, + .color_post_update = icl_color_post_update, .load_luts = icl_load_luts, .read_luts = icl_read_luts, }; @@ -2440,7 +2479,9 @@ void intel_color_init_hooks(struct drm_i else i915->display.funcs.color = &i9xx_color_funcs; } else { - if (DISPLAY_VER(i915) >= 11) + if (DISPLAY_VER(i915) >= 12) + i915->display.funcs.color = &tgl_color_funcs; + else if (DISPLAY_VER(i915) == 11) i915->display.funcs.color = &icl_color_funcs; else if (DISPLAY_VER(i915) == 10) i915->display.funcs.color = &glk_color_funcs;

From: Oswald Buddenhagen oswald.buddenhagen@gmx.de

commit c17f8fd31700392b1bb9e7b66924333568cb3700 upstream.

Like the other boards from the D*45* series, this one sets up the outputs not quite correctly.

Signed-off-by: Oswald Buddenhagen oswald.buddenhagen@gmx.de Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230405201220.2197826-1-oswald.buddenhagen@gmx.de Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- Documentation/sound/hd-audio/models.rst | 2 +- sound/pci/hda/patch_sigmatel.c | 2 ++ 2 files changed, 3 insertions(+), 1 deletion(-)

--- a/Documentation/sound/hd-audio/models.rst +++ b/Documentation/sound/hd-audio/models.rst @@ -704,7 +704,7 @@ ref no-jd BIOS setup but without jack-detection intel - Intel DG45* mobos + Intel D*45* mobos dell-m6-amic Dell desktops/laptops with analog mics dell-m6-dmic --- a/sound/pci/hda/patch_sigmatel.c +++ b/sound/pci/hda/patch_sigmatel.c @@ -1955,6 +1955,8 @@ static const struct snd_pci_quirk stac92 "DFI LanParty", STAC_92HD73XX_REF), SND_PCI_QUIRK(PCI_VENDOR_ID_DFI, 0x3101, "DFI LanParty", STAC_92HD73XX_REF), + SND_PCI_QUIRK(PCI_VENDOR_ID_INTEL, 0x5001, + "Intel DP45SG", STAC_92HD73XX_INTEL), SND_PCI_QUIRK(PCI_VENDOR_ID_INTEL, 0x5002, "Intel DG45ID", STAC_92HD73XX_INTEL), SND_PCI_QUIRK(PCI_VENDOR_ID_INTEL, 0x5003,

From: Pierre-Louis Bossart pierre-louis.bossart@linux.intel.com

commit e959f2beec8e655dba79c5a7111beedae5e757e0 upstream.

Add pins and verbs needed to enable speakers and jack.

The pins and verbs configurations were identified by snooping the Windows driver commands, with a nice write-up here: https://brakkee.org/site/2023/02/07/fixing-sound-on-the-asus-n7601zm/

Reported-by: Erik Brakkee erik@brakkee.org Link: https://github.com/thesofproject/linux/issues/4176 Tested-by: Erik Brakkee erik@brakkee.org Signed-off-by: Pierre-Louis Bossart pierre-louis.bossart@linux.intel.com Reviewed-by: Kai Vehmanen kai.vehmanen@linux.intel.com Reviewed-by: Bard Liao yung-chuan.liao@linux.intel.com Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230406152725.15191-1-pierre-louis.bossart@linux.... Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- sound/pci/hda/patch_realtek.c | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+)

--- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -6960,6 +6960,8 @@ enum { ALC269_FIXUP_DELL_M101Z, ALC269_FIXUP_SKU_IGNORE, ALC269_FIXUP_ASUS_G73JW, + ALC269_FIXUP_ASUS_N7601ZM_PINS, + ALC269_FIXUP_ASUS_N7601ZM, ALC269_FIXUP_LENOVO_EAPD, ALC275_FIXUP_SONY_HWEQ, ALC275_FIXUP_SONY_DISABLE_AAMIX, @@ -7256,6 +7258,29 @@ static const struct hda_fixup alc269_fix { } } }, + [ALC269_FIXUP_ASUS_N7601ZM_PINS] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x19, 0x03A11050 }, + { 0x1a, 0x03A11C30 }, + { 0x21, 0x03211420 }, + { } + } + }, + [ALC269_FIXUP_ASUS_N7601ZM] = { + .type = HDA_FIXUP_VERBS, + .v.verbs = (const struct hda_verb[]) { + {0x20, AC_VERB_SET_COEF_INDEX, 0x62}, + {0x20, AC_VERB_SET_PROC_COEF, 0xa007}, + {0x20, AC_VERB_SET_COEF_INDEX, 0x10}, + {0x20, AC_VERB_SET_PROC_COEF, 0x8420}, + {0x20, AC_VERB_SET_COEF_INDEX, 0x0f}, + {0x20, AC_VERB_SET_PROC_COEF, 0x7774}, + { } + }, + .chained = true, + .chain_id = ALC269_FIXUP_ASUS_N7601ZM_PINS, + }, [ALC269_FIXUP_LENOVO_EAPD] = { .type = HDA_FIXUP_VERBS, .v.verbs = (const struct hda_verb[]) { @@ -9465,6 +9490,7 @@ static const struct snd_pci_quirk alc269 SND_PCI_QUIRK(0x1043, 0x1271, "ASUS X430UN", ALC256_FIXUP_ASUS_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1043, 0x1290, "ASUS X441SA", ALC233_FIXUP_EAPD_COEF_AND_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1043, 0x12a0, "ASUS X441UV", ALC233_FIXUP_EAPD_COEF_AND_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1043, 0x12a3, "Asus N7691ZM", ALC269_FIXUP_ASUS_N7601ZM), SND_PCI_QUIRK(0x1043, 0x12af, "ASUS UX582ZS", ALC245_FIXUP_CS35L41_SPI_2), SND_PCI_QUIRK(0x1043, 0x12e0, "ASUS X541SA", ALC256_FIXUP_ASUS_MIC), SND_PCI_QUIRK(0x1043, 0x12f0, "ASUS X541UV", ALC256_FIXUP_ASUS_MIC),

From: Xu Biang xubiang@hust.edu.cn

commit fb4a624f88f658c7b7ae124452bd42eaa8ac7168 upstream.

Smatch Warns: sound/firewire/tascam/tascam-stream.c:493 snd_tscm_stream_start_duplex() warn: missing unwind goto?

The direct return will cause the stream list of "&tscm->domain" unemptied and the session in "tscm" unfinished if amdtp_domain_start() returns with an error.

Fix this by changing the direct return to a goto which will empty the stream list of "&tscm->domain" and finish the session in "tscm".

The snd_tscm_stream_start_duplex() function is called in the prepare callback of PCM. According to "ALSA Kernel API Documentation", the prepare callback of PCM will be called many times at each setup. So, if the "&d->streams" list is not emptied, when the prepare callback is called next time, snd_tscm_stream_start_duplex() will receive -EBUSY from amdtp_domain_add_stream() that tries to add an existing stream to the domain. The error handling code after the "error" label will be executed in this case, and the "&d->streams" list will be emptied. So not emptying the "&d->streams" list will not cause an issue. But it is more efficient and readable to empty it on the first error by changing the direct return to a goto statement.

The session in "tscm" has been begun before amdtp_domain_start(), so it needs to be finished when amdtp_domain_start() fails.

Fixes: c281d46a51e3 ("ALSA: firewire-tascam: support AMDTP domain") Signed-off-by: Xu Biang xubiang@hust.edu.cn Reviewed-by: Dan Carpenter error27@gmail.com Acked-by: Takashi Sakamoto o-takashi@sakamocchi.jp Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230406132801.105108-1-xubiang@hust.edu.cn Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- sound/firewire/tascam/tascam-stream.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/sound/firewire/tascam/tascam-stream.c +++ b/sound/firewire/tascam/tascam-stream.c @@ -490,7 +490,7 @@ int snd_tscm_stream_start_duplex(struct // packet is important for media clock recovery. err = amdtp_domain_start(&tscm->domain, tx_init_skip_cycles, true, true); if (err < 0) - return err; + goto error;

if (!amdtp_domain_wait_ready(&tscm->domain, READY_TIMEOUT_MS)) { err = -ETIMEDOUT;

From: Oswald Buddenhagen oswald.buddenhagen@gmx.de

commit f342ac00da1064eb4f94b1f4bcacbdfea955797a upstream.

The BIOS botches this one completely - it says the 2nd S/PDIF output is used, while in fact it's the 1st one. This is tested on DP45SG, but I'm assuming it's valid for the other boards in the series as well.

Also add some comments regarding the pins. FWIW, the codec is apparently still sold by Tempo Semiconductor, Inc., where one can download the documentation.

Signed-off-by: Oswald Buddenhagen oswald.buddenhagen@gmx.de Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230405201220.2197826-2-oswald.buddenhagen@gmx.de Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- sound/pci/hda/patch_sigmatel.c | 8 ++++++++ 1 file changed, 8 insertions(+)

--- a/sound/pci/hda/patch_sigmatel.c +++ b/sound/pci/hda/patch_sigmatel.c @@ -1707,6 +1707,7 @@ static const struct snd_pci_quirk stac92 };

static const struct hda_pintbl ref92hd73xx_pin_configs[] = { + // Port A-H { 0x0a, 0x02214030 }, { 0x0b, 0x02a19040 }, { 0x0c, 0x01a19020 }, @@ -1715,9 +1716,12 @@ static const struct hda_pintbl ref92hd73 { 0x0f, 0x01014010 }, { 0x10, 0x01014020 }, { 0x11, 0x01014030 }, + // CD in { 0x12, 0x02319040 }, + // Digial Mic ins { 0x13, 0x90a000f0 }, { 0x14, 0x90a000f0 }, + // Digital outs { 0x22, 0x01452050 }, { 0x23, 0x01452050 }, {} @@ -1758,6 +1762,7 @@ static const struct hda_pintbl alienware };

static const struct hda_pintbl intel_dg45id_pin_configs[] = { + // Analog outputs { 0x0a, 0x02214230 }, { 0x0b, 0x02A19240 }, { 0x0c, 0x01013214 }, @@ -1765,6 +1770,9 @@ static const struct hda_pintbl intel_dg4 { 0x0e, 0x01A19250 }, { 0x0f, 0x01011212 }, { 0x10, 0x01016211 }, + // Digital output + { 0x22, 0x01451380 }, + { 0x23, 0x40f000f0 }, {} };

From: Luiz Augusto von Dentz luiz.von.dentz@intel.com

commit a2a9339e1c9deb7e1e079e12e27a0265aea8421a upstream.

Similar to commit d0be8347c623 ("Bluetooth: L2CAP: Fix use-after-free caused by l2cap_chan_put"), just use l2cap_chan_hold_unless_zero to prevent referencing a channel that is about to be destroyed.

Cc: stable@kernel.org Signed-off-by: Luiz Augusto von Dentz luiz.von.dentz@intel.com Signed-off-by: Min Li lm0963hack@gmail.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/bluetooth/l2cap_core.c | 24 ++++++------------------ 1 file changed, 6 insertions(+), 18 deletions(-)

--- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -4652,33 +4652,27 @@ static inline int l2cap_disconnect_req(s

BT_DBG("scid 0x%4.4x dcid 0x%4.4x", scid, dcid);

- mutex_lock(&conn->chan_lock); - - chan = __l2cap_get_chan_by_scid(conn, dcid); + chan = l2cap_get_chan_by_scid(conn, dcid); if (!chan) { - mutex_unlock(&conn->chan_lock); cmd_reject_invalid_cid(conn, cmd->ident, dcid, scid); return 0; }

- l2cap_chan_hold(chan); - l2cap_chan_lock(chan); - rsp.dcid = cpu_to_le16(chan->scid); rsp.scid = cpu_to_le16(chan->dcid); l2cap_send_cmd(conn, cmd->ident, L2CAP_DISCONN_RSP, sizeof(rsp), &rsp);

chan->ops->set_shutdown(chan);

+ mutex_lock(&conn->chan_lock); l2cap_chan_del(chan, ECONNRESET); + mutex_unlock(&conn->chan_lock);

chan->ops->close(chan);

l2cap_chan_unlock(chan); l2cap_chan_put(chan);

- mutex_unlock(&conn->chan_lock); - return 0; }

@@ -4698,33 +4692,27 @@ static inline int l2cap_disconnect_rsp(s

BT_DBG("dcid 0x%4.4x scid 0x%4.4x", dcid, scid);

- mutex_lock(&conn->chan_lock); - - chan = __l2cap_get_chan_by_scid(conn, scid); + chan = l2cap_get_chan_by_scid(conn, scid); if (!chan) { mutex_unlock(&conn->chan_lock); return 0; }

- l2cap_chan_hold(chan); - l2cap_chan_lock(chan); - if (chan->state != BT_DISCONN) { l2cap_chan_unlock(chan); l2cap_chan_put(chan); - mutex_unlock(&conn->chan_lock); return 0; }

+ mutex_lock(&conn->chan_lock); l2cap_chan_del(chan, 0); + mutex_unlock(&conn->chan_lock);

chan->ops->close(chan);

l2cap_chan_unlock(chan); l2cap_chan_put(chan);

- mutex_unlock(&conn->chan_lock); - return 0; }

From: Sasha Finkelstein fnkl.kernel@gmail.com

commit b76abe4648c1acc791a207e7c08d1719eb9f4ea8 upstream.

This patch fixes an incorrect loop exit condition in code that replaces '/' symbols in the board name. There might also be a memory corruption issue here, but it is unlikely to be a real problem.

Cc: stable@vger.kernel.org Signed-off-by: Sasha Finkelstein fnkl.kernel@gmail.com Signed-off-by: Luiz Augusto von Dentz luiz.von.dentz@intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/bluetooth/btbcm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/drivers/bluetooth/btbcm.c +++ b/drivers/bluetooth/btbcm.c @@ -511,7 +511,7 @@ static const char *btbcm_get_board_name( len = strlen(tmp) + 1; board_type = devm_kzalloc(dev, len, GFP_KERNEL); strscpy(board_type, tmp, len); - for (i = 0; i < board_type[i]; i++) { + for (i = 0; i < len; i++) { if (board_type[i] == '/') board_type[i] = '-'; }

From: Luiz Augusto von Dentz luiz.von.dentz@intel.com

commit 5dc7d23e167e2882ef118456ceccd57873e876d8 upstream.

This fixes the following trace:

================================================================== BUG: KASAN: slab-use-after-free in hci_conn_del+0xba/0x3a0 Write of size 8 at addr ffff88800208e9c8 by task iso-tester/31

CPU: 0 PID: 31 Comm: iso-tester Not tainted 6.3.0-rc2-g991aa4a69a47 #4716 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.1-2.fc36 04/01/2014 Call Trace: <TASK> dump_stack_lvl+0x1d/0x70 print_report+0xce/0x610 ? __virt_addr_valid+0xd4/0x150 ? hci_conn_del+0xba/0x3a0 kasan_report+0xdd/0x110 ? hci_conn_del+0xba/0x3a0 hci_conn_del+0xba/0x3a0 hci_conn_hash_flush+0xf2/0x120 hci_dev_close_sync+0x388/0x920 hci_unregister_dev+0x122/0x260 vhci_release+0x4f/0x90 __fput+0x102/0x430 task_work_run+0xf1/0x160 ? __pfx_task_work_run+0x10/0x10 ? mark_held_locks+0x24/0x90 exit_to_user_mode_prepare+0x170/0x180 syscall_exit_to_user_mode+0x19/0x50 do_syscall_64+0x4e/0x90 entry_SYSCALL_64_after_hwframe+0x70/0xda

Fixes: 0f00cd322d22 ("Bluetooth: Free potentially unfreed SCO connection") Link: https://syzkaller.appspot.com/bug?extid=8bb72f86fc823817bc5d Cc: stable@vger.kernel.org Signed-off-by: Luiz Augusto von Dentz luiz.von.dentz@intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/bluetooth/hci_conn.c | 30 ++++++++++++++++++++++++------ 1 file changed, 24 insertions(+), 6 deletions(-)

--- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -1049,6 +1049,17 @@ struct hci_conn *hci_conn_add(struct hci return conn; }

+static bool hci_conn_unlink(struct hci_conn *conn) +{ + if (!conn->link) + return false; + + conn->link->link = NULL; + conn->link = NULL; + + return true; +} + int hci_conn_del(struct hci_conn *conn) { struct hci_dev *hdev = conn->hdev; @@ -1060,15 +1071,16 @@ int hci_conn_del(struct hci_conn *conn) cancel_delayed_work_sync(&conn->idle_work);

if (conn->type == ACL_LINK) { - struct hci_conn *sco = conn->link; - if (sco) { - sco->link = NULL; + struct hci_conn *link = conn->link; + + if (link) { + hci_conn_unlink(conn); /* Due to race, SCO connection might be not established * yet at this point. Delete it now, otherwise it is * possible for it to be stuck and can't be deleted. */ - if (sco->handle == HCI_CONN_HANDLE_UNSET) - hci_conn_del(sco); + if (link->handle == HCI_CONN_HANDLE_UNSET) + hci_conn_del(link); }

/* Unacked frames */ @@ -1084,7 +1096,7 @@ int hci_conn_del(struct hci_conn *conn) struct hci_conn *acl = conn->link;

if (acl) { - acl->link = NULL; + hci_conn_unlink(conn); hci_conn_drop(acl); }

@@ -2436,6 +2448,12 @@ void hci_conn_hash_flush(struct hci_dev c->state = BT_CLOSED;

hci_disconn_cfm(c, HCI_ERROR_LOCAL_HOST_TERM); + + /* Unlink before deleting otherwise it is possible that + * hci_conn_del removes the link which may cause the list to + * contain items already freed. + */ + hci_conn_unlink(c); hci_conn_del(c); } }

From: Christoph Hellwig hch@lst.de

commit 68d99ab0e9221ef54506f827576c5a914680eeaf upstream.

The BTRFS_FS_CSUM_IMPL_FAST flag is currently set whenever a non-generic crc32c is detected, which is the incorrect check if the file system uses a different checksumming algorithm. Refactor the code to only check this if crc32c is actually used. Note that in an ideal world the information if an algorithm is hardware accelerated or not should be provided by the crypto API instead, but that's left for another day.

CC: stable@vger.kernel.org # 5.4.x: c8a5f8ca9a9c: btrfs: print checksum type and implementation at mount time CC: stable@vger.kernel.org # 5.4.x Signed-off-by: Christoph Hellwig hch@lst.de Reviewed-by: David Sterba dsterba@suse.com Signed-off-by: David Sterba dsterba@suse.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/btrfs/disk-io.c | 14 ++++++++++++++ fs/btrfs/super.c | 2 -- 2 files changed, 14 insertions(+), 2 deletions(-)

--- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2433,6 +2433,20 @@ static int btrfs_init_csum_hash(struct b

fs_info->csum_shash = csum_shash;

+ /* + * Check if the checksum implementation is a fast accelerated one. + * As-is this is a bit of a hack and should be replaced once the csum + * implementations provide that information themselves. + */ + switch (csum_type) { + case BTRFS_CSUM_TYPE_CRC32: + if (!strstr(crypto_shash_driver_name(csum_shash), "generic")) + set_bit(BTRFS_FS_CSUM_IMPL_FAST, &fs_info->flags); + break; + default: + break; + } + btrfs_info(fs_info, "using %s (%s) checksum algorithm", btrfs_super_csum_name(csum_type), crypto_shash_driver_name(csum_shash)); --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -1515,8 +1515,6 @@ static struct dentry *btrfs_mount_root(s shrinker_debugfs_rename(&s->s_shrink, "sb-%s:%s", fs_type->name, s->s_id); btrfs_sb(s)->bdev_holder = fs_type; - if (!strstr(crc32c_impl(), "generic")) - set_bit(BTRFS_FS_CSUM_IMPL_FAST, &fs_info->flags); error = btrfs_fill_super(s, fs_devices, data); } if (!error)

From: Bang Li libang.linuxer@gmail.com

commit 0c3089601f064d80b3838eceb711fcac04bceaad upstream.

mtd_read() may return -EUCLEAN in case of corrected bit-flips.This particular condition should not be treated like an error.

Signed-off-by: Bang Li libang.linuxer@gmail.com Fixes: e47f68587b82 ("mtd: check for max_bitflips in mtd_read_oob()") Cc: stable@vger.kernel.org # v3.7 Acked-by: Richard Weinberger richard@nod.at Signed-off-by: Miquel Raynal miquel.raynal@bootlin.com Link: https://lore.kernel.org/linux-mtd/20230328163012.4264-1-libang.linuxer@gmail... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/mtd/mtdblock.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-)

--- a/drivers/mtd/mtdblock.c +++ b/drivers/mtd/mtdblock.c @@ -153,7 +153,7 @@ static int do_cached_write (struct mtdbl mtdblk->cache_state = STATE_EMPTY; ret = mtd_read(mtd, sect_start, sect_size, &retlen, mtdblk->cache_data); - if (ret) + if (ret && !mtd_is_bitflip(ret)) return ret; if (retlen != sect_size) return -EIO; @@ -188,8 +188,12 @@ static int do_cached_read (struct mtdblk pr_debug("mtdblock: read on "%s" at 0x%lx, size 0x%x\n", mtd->name, pos, len);

- if (!sect_size) - return mtd_read(mtd, pos, len, &retlen, buf); + if (!sect_size) { + ret = mtd_read(mtd, pos, len, &retlen, buf); + if (ret && !mtd_is_bitflip(ret)) + return ret; + return 0; + }

while (len > 0) { unsigned long sect_start = (pos/sect_size)*sect_size; @@ -209,7 +213,7 @@ static int do_cached_read (struct mtdblk memcpy (buf, mtdblk->cache_data + offset, size); } else { ret = mtd_read(mtd, pos, size, &retlen, buf); - if (ret) + if (ret && !mtd_is_bitflip(ret)) return ret; if (retlen != size) return -EIO;

From: Christophe Kerello christophe.kerello@foss.st.com

commit f71e0e329c152c7f11ddfd97ffc62aba152fad3f upstream.

Remove the EDO mode support from as the FMC2 controller does not support the feature.

Signed-off-by: Christophe Kerello christophe.kerello@foss.st.com Fixes: 2cd457f328c1 ("mtd: rawnand: stm32_fmc2: add STM32 FMC2 NAND flash controller driver") Cc: stable@vger.kernel.org #v5.4+ Reviewed-by: Tudor Ambarus tudor.ambarus@linaro.org Signed-off-by: Miquel Raynal miquel.raynal@bootlin.com Link: https://lore.kernel.org/linux-mtd/20230328155819.225521-2-christophe.kerello... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/mtd/nand/raw/stm32_fmc2_nand.c | 3 +++ 1 file changed, 3 insertions(+)

--- a/drivers/mtd/nand/raw/stm32_fmc2_nand.c +++ b/drivers/mtd/nand/raw/stm32_fmc2_nand.c @@ -1531,6 +1531,9 @@ static int stm32_fmc2_nfc_setup_interfac if (IS_ERR(sdrt)) return PTR_ERR(sdrt);

+ if (sdrt->tRC_min < 30000) + return -EOPNOTSUPP; + if (chipnr == NAND_DATA_IFACE_CHECK_ONLY) return 0;

From: Reiji Watanabe reijiw@google.com

commit f9ea835e99bc8d049bf2a3ec8fa5a7cb4fcade23 upstream.

Currently, with VHE, KVM enables the EL0 event counting for the guest on vcpu_load() or KVM enables it as a part of the PMU register emulation process, when needed. However, in the migration case (with VHE), the same handling is lacking, as vPMU register values that were restored by userspace haven't been propagated yet (the PMU events haven't been created) at the vcpu load-time on the first KVM_RUN (kvm_vcpu_pmu_restore_guest() called from vcpu_load() on the first KVM_RUN won't do anything as events_{guest,host} of kvm_pmu_events are still zero).

So, with VHE, enable the guest's EL0 event counting on the first KVM_RUN (after the migration) when needed. More specifically, have kvm_pmu_handle_pmcr() call kvm_vcpu_pmu_restore_guest() so that kvm_pmu_handle_pmcr() on the first KVM_RUN can take care of it.

Fixes: d0c94c49792c ("KVM: arm64: Restore PMU configuration on first run") Cc: stable@vger.kernel.org Reviewed-by: Marc Zyngier maz@kernel.org Signed-off-by: Reiji Watanabe reijiw@google.com Link: https://lore.kernel.org/r/20230329023944.2488484-1-reijiw@google.com Signed-off-by: Oliver Upton oliver.upton@linux.dev Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/arm64/kvm/pmu-emul.c | 1 + arch/arm64/kvm/sys_regs.c | 1 - 2 files changed, 1 insertion(+), 1 deletion(-)

--- a/arch/arm64/kvm/pmu-emul.c +++ b/arch/arm64/kvm/pmu-emul.c @@ -558,6 +558,7 @@ void kvm_pmu_handle_pmcr(struct kvm_vcpu for_each_set_bit(i, &mask, 32) kvm_pmu_set_pmc_value(kvm_vcpu_idx_to_pmc(vcpu, i), 0, true); } + kvm_vcpu_pmu_restore_guest(vcpu); }

static bool kvm_pmu_counter_is_enabled(struct kvm_pmc *pmc) --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -703,7 +703,6 @@ static bool access_pmcr(struct kvm_vcpu if (!kvm_supports_32bit_el0()) val |= ARMV8_PMU_PMCR_LC; kvm_pmu_handle_pmcr(vcpu, val); - kvm_vcpu_pmu_restore_guest(vcpu); } else { /* PMCR.P & PMCR.C are RAZ */ val = __vcpu_sys_reg(vcpu, PMCR_EL0)

From: Daniel Vetter daniel.vetter@ffwll.ch

commit fffb0b52d5258554c645c966c6cbef7de50b851d upstream.

I got really badly confused in d443d9386472 ("fbcon: move more common code into fb_open()") because we set the con2fb_map before the failure points, which didn't look good.

But in trying to fix that I moved the assignment into the wrong path - we need to do it for _all_ vc we take over, not just the first one (which additionally requires the call to con2fb_acquire_newinfo).

I've figured this out because of a KASAN bug report, where the fbcon_registered_fb and fbcon_display arrays went out of sync in fbcon_mode_deleted() because the con2fb_map pointed at the old fb_info, but the modes and everything was updated for the new one.

Signed-off-by: Daniel Vetter daniel.vetter@intel.com Reviewed-by: Javier Martinez Canillas javierm@redhat.com Acked-by: Helge Deller deller@gmx.de Tested-by: Xingyuan Mo hdthky0@gmail.com Fixes: d443d9386472 ("fbcon: move more common code into fb_open()") Reported-by: Xingyuan Mo hdthky0@gmail.com Cc: Thomas Zimmermann tzimmermann@suse.de Cc: Sam Ravnborg sam@ravnborg.org Cc: Xingyuan Mo hdthky0@gmail.com Cc: Thomas Zimmermann tzimmermann@suse.de Cc: Helge Deller deller@gmx.de Cc: stable@vger.kernel.org # v5.19+ Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/video/fbdev/core/fbcon.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

--- a/drivers/video/fbdev/core/fbcon.c +++ b/drivers/video/fbdev/core/fbcon.c @@ -846,10 +846,11 @@ static int set_con2fb_map(int unit, int if (err) return err;

- con2fb_map[unit] = newidx; fbcon_add_cursor_work(info); }

+ con2fb_map[unit] = newidx; + /* * If old fb is not mapped to any of the consoles, * fbcon should release it.

From: Ming Lei ming.lei@redhat.com

commit 860e1c7f8b0b43fbf91b4d689adfaa13adb89452 upstream.

So far io_req_complete_post() only covers DEFER_TASKRUN by completing request via task work when the request is completed from IOWQ.

However, uring command could be completed from any context, and if io uring is setup with DEFER_TASKRUN, the command is required to be completed from current context, otherwise wait on IORING_ENTER_GETEVENTS can't be wakeup, and may hang forever.

The issue can be observed on removing ublk device, but turns out it is one generic issue for uring command & DEFER_TASKRUN, so solve it in io_uring core code.

Fixes: e6aeb2721d3b ("io_uring: complete all requests in task context") Cc: stable@vger.kernel.org Link: https://lore.kernel.org/linux-block/b3fc9991-4c53-9218-a8cc-5b4dd3952108@ker... Reported-by: Jens Axboe axboe@kernel.dk Cc: Kanchan Joshi joshi.k@samsung.com Signed-off-by: Ming Lei ming.lei@redhat.com Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- io_uring/io_uring.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -962,7 +962,7 @@ static void __io_req_complete_post(struc

void io_req_complete_post(struct io_kiocb *req, unsigned issue_flags) { - if (req->ctx->task_complete && (issue_flags & IO_URING_F_IOWQ)) { + if (req->ctx->task_complete && req->ctx->submitter_task != current) { req->io_task_work.func = io_req_task_complete; io_req_task_work_add(req); } else if (!(issue_flags & IO_URING_F_UNLOCKED) ||

From: Mustafa Ismail mustafa.ismail@intel.com

[ Upstream commit 30ed9ee9a10a90ae719dcfcacead1d0506fa45ed ]

Currently, artificial SW completions are generated for NOP wqes which can generate unexpected completions with wr_id = 0. Skip the generation of artificial completions for NOPs.

Fixes: 81091d7696ae ("RDMA/irdma: Add SW mechanism to generate completions on error") Signed-off-by: Mustafa Ismail mustafa.ismail@intel.com Signed-off-by: Shiraz Saleem shiraz.saleem@intel.com Link: https://lore.kernel.org/r/20230315145231.931-2-shiraz.saleem@intel.com Signed-off-by: Leon Romanovsky leon@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/infiniband/hw/irdma/utils.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/infiniband/hw/irdma/utils.c b/drivers/infiniband/hw/irdma/utils.c index 445e69e864097..7887230c867b1 100644 --- a/drivers/infiniband/hw/irdma/utils.c +++ b/drivers/infiniband/hw/irdma/utils.c @@ -2595,7 +2595,10 @@ void irdma_generate_flush_completions(struct irdma_qp *iwqp) /* remove the SQ WR by moving SQ tail*/ IRDMA_RING_SET_TAIL(*sq_ring, sq_ring->tail + qp->sq_wrtrk_array[sq_ring->tail].quanta); - + if (cmpl->cpi.op_type == IRDMAQP_OP_NOP) { + kfree(cmpl); + continue; + } ibdev_dbg(iwqp->iwscq->ibcq.device, "DEV: %s: adding wr_id = 0x%llx SQ Completion to list qp_id=%d\n", __func__, cmpl->cpi.wr_id, qp->qp_id);

From: Mustafa Ismail mustafa.ismail@intel.com

[ Upstream commit 8385a875c9eecc429b2f72970efcbb0e5cb5b547 ]

When running perftest with large number of connections in iWARP mode, the passive side could be slow to respond. Increase the rexmit counter default to allow scaling connections.

Fixes: 146b9756f14c ("RDMA/irdma: Add connection manager") Signed-off-by: Mustafa Ismail mustafa.ismail@intel.com Signed-off-by: Shiraz Saleem shiraz.saleem@intel.com Link: https://lore.kernel.org/r/20230315145231.931-4-shiraz.saleem@intel.com Signed-off-by: Leon Romanovsky leon@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/infiniband/hw/irdma/cm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/infiniband/hw/irdma/cm.h b/drivers/infiniband/hw/irdma/cm.h index 19c284975fc7c..7feadb3e1eda3 100644 --- a/drivers/infiniband/hw/irdma/cm.h +++ b/drivers/infiniband/hw/irdma/cm.h @@ -41,7 +41,7 @@ #define TCP_OPTIONS_PADDING 3

#define IRDMA_DEFAULT_RETRYS 64 -#define IRDMA_DEFAULT_RETRANS 8 +#define IRDMA_DEFAULT_RETRANS 32 #define IRDMA_DEFAULT_TTL 0x40 #define IRDMA_DEFAULT_RTT_VAR 6 #define IRDMA_DEFAULT_SS_THRESH 0x3fffffff

From: Maher Sanalla msanalla@nvidia.com

[ Upstream commit 88c9483faf15ada14eca82714114656893063458 ]

Currently, when driver queries PTYS to report which link speed is being used on its RoCE ports, it does not check the case of having 400Gbps transmitted over 8 lanes. Thus it fails to report the said speed and instead it defaults to report 10G over 4 lanes.

Add a check for the said speed when querying PTYS and report it back correctly when needed.

Fixes: 08e8676f1607 ("IB/mlx5: Add support for 50Gbps per lane link modes") Signed-off-by: Maher Sanalla msanalla@nvidia.com Reviewed-by: Aya Levin ayal@nvidia.com Reviewed-by: Saeed Mahameed saeedm@nvidia.com Link: https://lore.kernel.org/r/ec9040548d119d22557d6a4b4070d6f421701fd4.167897399... Signed-off-by: Leon Romanovsky leon@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/infiniband/hw/mlx5/main.c | 4 ++++ 1 file changed, 4 insertions(+)

diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index c669ef6e47e73..eaa35e1df2a85 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -442,6 +442,10 @@ static int translate_eth_ext_proto_oper(u32 eth_proto_oper, u16 *active_speed, *active_width = IB_WIDTH_2X; *active_speed = IB_SPEED_NDR; break; + case MLX5E_PROT_MASK(MLX5E_400GAUI_8): + *active_width = IB_WIDTH_8X; + *active_speed = IB_SPEED_HDR; + break; case MLX5E_PROT_MASK(MLX5E_400GAUI_4_400GBASE_CR4_KR4): *active_width = IB_WIDTH_4X; *active_speed = IB_SPEED_NDR;

From: Cheng Xu chengyou@linux.alibaba.com

[ Upstream commit 6256aa9ae955d10ec73a434533ca62034eff1b76 ]

Max EQ depth of hardware is 32K, the current default EQ depth is too small for some applications, so change the default depth to 4096. Max send WRs the hardware can support is 8K, but the driver limits the value to 4K. Remove this limitation.

Fixes: be3cff0f242d ("RDMA/erdma: Add the hardware related definitions") Fixes: db23ae64caac ("RDMA/erdma: Add verbs header file") Signed-off-by: Cheng Xu chengyou@linux.alibaba.com Link: https://lore.kernel.org/r/20230320084652.16807-3-chengyou@linux.alibaba.com Signed-off-by: Leon Romanovsky leon@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/infiniband/hw/erdma/erdma_hw.h | 2 +- drivers/infiniband/hw/erdma/erdma_verbs.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/infiniband/hw/erdma/erdma_hw.h b/drivers/infiniband/hw/erdma/erdma_hw.h index cbeb6909580cf..8a8d4539a006b 100644 --- a/drivers/infiniband/hw/erdma/erdma_hw.h +++ b/drivers/infiniband/hw/erdma/erdma_hw.h @@ -441,7 +441,7 @@ struct erdma_reg_mr_sqe { };

/* EQ related. */ -#define ERDMA_DEFAULT_EQ_DEPTH 256 +#define ERDMA_DEFAULT_EQ_DEPTH 4096

/* ceqe */ #define ERDMA_CEQE_HDR_DB_MASK BIT_ULL(63) diff --git a/drivers/infiniband/hw/erdma/erdma_verbs.h b/drivers/infiniband/hw/erdma/erdma_verbs.h index e0a993bc032a4..131cf5f409822 100644 --- a/drivers/infiniband/hw/erdma/erdma_verbs.h +++ b/drivers/infiniband/hw/erdma/erdma_verbs.h @@ -11,7 +11,7 @@

/* RDMA Capability. */ #define ERDMA_MAX_PD (128 * 1024) -#define ERDMA_MAX_SEND_WR 4096 +#define ERDMA_MAX_SEND_WR 8192 #define ERDMA_MAX_ORD 128 #define ERDMA_MAX_IRD 128 #define ERDMA_MAX_SGE_RD 1

From: Cheng Xu chengyou@linux.alibaba.com

[ Upstream commit 6bd1bca858f1734a75572a788213d1e1143f2f0a ]

ERDMA device may be probed before its associated netdevice, returning -EPROBE_DEFER allows OS try to probe erdma device later.

Fixes: d55e6fb4803c ("RDMA/erdma: Add the erdma module") Signed-off-by: Cheng Xu chengyou@linux.alibaba.com Link: https://lore.kernel.org/r/20230320084652.16807-5-chengyou@linux.alibaba.com Signed-off-by: Leon Romanovsky leon@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/infiniband/hw/erdma/erdma_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/infiniband/hw/erdma/erdma_main.c b/drivers/infiniband/hw/erdma/erdma_main.c index 5dc31e5df5cba..4a29a53a6652e 100644 --- a/drivers/infiniband/hw/erdma/erdma_main.c +++ b/drivers/infiniband/hw/erdma/erdma_main.c @@ -56,7 +56,7 @@ static int erdma_netdev_event(struct notifier_block *nb, unsigned long event, static int erdma_enum_and_get_netdev(struct erdma_dev *dev) { struct net_device *netdev; - int ret = -ENODEV; + int ret = -EPROBE_DEFER;

/* Already binded to a net_device, so we skip. */ if (dev->netdev)

From: Mark Zhang markzhang@nvidia.com

[ Upstream commit 58e84f6b3e84e46524b7e5a916b53c1ad798bc8f ]

As for multicast: - The SIDR is the only mode that makes sense; - Besides PS_UDP, other port spaces like PS_IB is also allowed, as it is UD compatible. In this case qkey also needs to be set [1].

This patch allows only UD qp_type to join multicast, and set qkey to default if it's not set, to fix an uninit-value error: the ib->rec.qkey field is accessed without being initialized.

===================================================== BUG: KMSAN: uninit-value in cma_set_qkey drivers/infiniband/core/cma.c:510 [inline] BUG: KMSAN: uninit-value in cma_make_mc_event+0xb73/0xe00 drivers/infiniband/core/cma.c:4570 cma_set_qkey drivers/infiniband/core/cma.c:510 [inline] cma_make_mc_event+0xb73/0xe00 drivers/infiniband/core/cma.c:4570 cma_iboe_join_multicast drivers/infiniband/core/cma.c:4782 [inline] rdma_join_multicast+0x2b83/0x30a0 drivers/infiniband/core/cma.c:4814 ucma_process_join+0xa76/0xf60 drivers/infiniband/core/ucma.c:1479 ucma_join_multicast+0x1e3/0x250 drivers/infiniband/core/ucma.c:1546 ucma_write+0x639/0x6d0 drivers/infiniband/core/ucma.c:1732 vfs_write+0x8ce/0x2030 fs/read_write.c:588 ksys_write+0x28c/0x520 fs/read_write.c:643 __do_sys_write fs/read_write.c:655 [inline] __se_sys_write fs/read_write.c:652 [inline] __ia32_sys_write+0xdb/0x120 fs/read_write.c:652 do_syscall_32_irqs_on arch/x86/entry/common.c:114 [inline] __do_fast_syscall_32+0x96/0xf0 arch/x86/entry/common.c:180 do_fast_syscall_32+0x34/0x70 arch/x86/entry/common.c:205 do_SYSENTER_32+0x1b/0x20 arch/x86/entry/common.c:248 entry_SYSENTER_compat_after_hwframe+0x4d/0x5c

Local variable ib.i created at: cma_iboe_join_multicast drivers/infiniband/core/cma.c:4737 [inline] rdma_join_multicast+0x586/0x30a0 drivers/infiniband/core/cma.c:4814 ucma_process_join+0xa76/0xf60 drivers/infiniband/core/ucma.c:1479

CPU: 0 PID: 29874 Comm: syz-executor.3 Not tainted 5.16.0-rc3-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 =====================================================

[1] https://lore.kernel.org/linux-rdma/20220117183832.GD84788@nvidia.com/

Fixes: b5de0c60cc30 ("RDMA/cma: Fix use after free race in roce multicast join") Reported-by: syzbot+8fcbb77276d43cc8b693@syzkaller.appspotmail.com Signed-off-by: Mark Zhang markzhang@nvidia.com Link: https://lore.kernel.org/r/58a4a98323b5e6b1282e83f6b76960d06e43b9fa.167930990... Signed-off-by: Leon Romanovsky leon@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/infiniband/core/cma.c | 60 ++++++++++++++++++++--------------- 1 file changed, 34 insertions(+), 26 deletions(-)

diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index 7e508b15e7761..00c9529c3143f 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -624,22 +624,11 @@ static inline unsigned short cma_family(struct rdma_id_private *id_priv) return id_priv->id.route.addr.src_addr.ss_family; }

-static int cma_set_qkey(struct rdma_id_private *id_priv, u32 qkey) +static int cma_set_default_qkey(struct rdma_id_private *id_priv) { struct ib_sa_mcmember_rec rec; int ret = 0;

- if (id_priv->qkey) { - if (qkey && id_priv->qkey != qkey) - return -EINVAL; - return 0; - } - - if (qkey) { - id_priv->qkey = qkey; - return 0; - } - switch (id_priv->id.ps) { case RDMA_PS_UDP: case RDMA_PS_IB: @@ -659,6 +648,16 @@ static int cma_set_qkey(struct rdma_id_private *id_priv, u32 qkey) return ret; }

+static int cma_set_qkey(struct rdma_id_private *id_priv, u32 qkey) +{ + if (!qkey || + (id_priv->qkey && (id_priv->qkey != qkey))) + return -EINVAL; + + id_priv->qkey = qkey; + return 0; +} + static void cma_translate_ib(struct sockaddr_ib *sib, struct rdma_dev_addr *dev_addr) { dev_addr->dev_type = ARPHRD_INFINIBAND; @@ -1229,7 +1228,7 @@ static int cma_ib_init_qp_attr(struct rdma_id_private *id_priv, *qp_attr_mask = IB_QP_STATE | IB_QP_PKEY_INDEX | IB_QP_PORT;

if (id_priv->id.qp_type == IB_QPT_UD) { - ret = cma_set_qkey(id_priv, 0); + ret = cma_set_default_qkey(id_priv); if (ret) return ret;

@@ -4558,7 +4557,10 @@ static int cma_send_sidr_rep(struct rdma_id_private *id_priv, memset(&rep, 0, sizeof rep); rep.status = status; if (status == IB_SIDR_SUCCESS) { - ret = cma_set_qkey(id_priv, qkey); + if (qkey) + ret = cma_set_qkey(id_priv, qkey); + else + ret = cma_set_default_qkey(id_priv); if (ret) return ret; rep.qp_num = id_priv->qp_num; @@ -4763,9 +4765,7 @@ static void cma_make_mc_event(int status, struct rdma_id_private *id_priv, enum ib_gid_type gid_type; struct net_device *ndev;

- if (!status) - status = cma_set_qkey(id_priv, be32_to_cpu(multicast->rec.qkey)); - else + if (status) pr_debug_ratelimited("RDMA CM: MULTICAST_ERROR: failed to join multicast. status %d\n", status);

@@ -4793,7 +4793,7 @@ static void cma_make_mc_event(int status, struct rdma_id_private *id_priv, }

event->param.ud.qp_num = 0xFFFFFF; - event->param.ud.qkey = be32_to_cpu(multicast->rec.qkey); + event->param.ud.qkey = id_priv->qkey;

out: if (ndev) @@ -4812,8 +4812,11 @@ static int cma_ib_mc_handler(int status, struct ib_sa_multicast *multicast) READ_ONCE(id_priv->state) == RDMA_CM_DESTROYING) goto out;

- cma_make_mc_event(status, id_priv, multicast, &event, mc); - ret = cma_cm_event_handler(id_priv, &event); + ret = cma_set_qkey(id_priv, be32_to_cpu(multicast->rec.qkey)); + if (!ret) { + cma_make_mc_event(status, id_priv, multicast, &event, mc); + ret = cma_cm_event_handler(id_priv, &event); + } rdma_destroy_ah_attr(&event.param.ud.ah_attr); WARN_ON(ret);

@@ -4866,9 +4869,11 @@ static int cma_join_ib_multicast(struct rdma_id_private *id_priv, if (ret) return ret;

- ret = cma_set_qkey(id_priv, 0); - if (ret) - return ret; + if (!id_priv->qkey) { + ret = cma_set_default_qkey(id_priv); + if (ret) + return ret; + }

cma_set_mgid(id_priv, (struct sockaddr *) &mc->addr, &rec.mgid); rec.qkey = cpu_to_be32(id_priv->qkey); @@ -4945,9 +4950,6 @@ static int cma_iboe_join_multicast(struct rdma_id_private *id_priv, cma_iboe_set_mgid(addr, &ib.rec.mgid, gid_type);

ib.rec.pkey = cpu_to_be16(0xffff); - if (id_priv->id.ps == RDMA_PS_UDP) - ib.rec.qkey = cpu_to_be32(RDMA_UDP_QKEY); - if (dev_addr->bound_dev_if) ndev = dev_get_by_index(dev_addr->net, dev_addr->bound_dev_if); if (!ndev) @@ -4973,6 +4975,9 @@ static int cma_iboe_join_multicast(struct rdma_id_private *id_priv, if (err || !ib.rec.mtu) return err ?: -EINVAL;

+ if (!id_priv->qkey) + cma_set_default_qkey(id_priv); + rdma_ip2gid((struct sockaddr *)&id_priv->id.route.addr.src_addr, &ib.rec.port_gid); INIT_WORK(&mc->iboe_join.work, cma_iboe_join_work_handler); @@ -4998,6 +5003,9 @@ int rdma_join_multicast(struct rdma_cm_id *id, struct sockaddr *addr, READ_ONCE(id_priv->state) != RDMA_CM_ADDR_RESOLVED)) return -EINVAL;

+ if (id_priv->id.qp_type != IB_QPT_UD) + return -EINVAL; + mc = kzalloc(sizeof(*mc), GFP_KERNEL); if (!mc) return -ENOMEM;

From: George Guo guodongtai@kylinos.cn

[ Upstream commit a6f6a95f25803500079513780d11a911ce551d76 ]

Just skip the opcode(BPF_ST | BPF_NOSPEC) in the BPF JIT instead of failing to JIT the entire program, given LoongArch currently has no couterpart of a speculation barrier instruction. To verify the issue, use the ltp testcase as shown below.

Also, Wang says:

I can confirm there's currently no speculation barrier equivalent on LonogArch. (Loongson says there are builtin mitigations for Spectre-V1 and V2 on their chips, and AFAIK efforts to port the exploits to mips/LoongArch have all failed a few years ago.)

Without this patch:

$ ./bpf_prog02 [...] bpf_common.c:123: TBROK: Failed verification: ??? (524) [...] Summary: passed 0 failed 0 broken 1 skipped 0 warnings 0

With this patch:

$ ./bpf_prog02 [...] Summary: passed 0 failed 0 broken 0 skipped 0 warnings 0

Fixes: 5dc615520c4d ("LoongArch: Add BPF JIT support") Signed-off-by: George Guo guodongtai@kylinos.cn Signed-off-by: Daniel Borkmann daniel@iogearbox.net Acked-by: WANG Xuerui git@xen0n.name Cc: Tiezhu Yang yangtiezhu@loongson.cn Link: https://lore.kernel.org/bpf/20230328071335.2664966-1-guodongtai@kylinos.cn Signed-off-by: Sasha Levin sashal@kernel.org --- arch/loongarch/net/bpf_jit.c | 4 ++++ 1 file changed, 4 insertions(+)

diff --git a/arch/loongarch/net/bpf_jit.c b/arch/loongarch/net/bpf_jit.c index 288003a9f0cae..d586df48ecc64 100644 --- a/arch/loongarch/net/bpf_jit.c +++ b/arch/loongarch/net/bpf_jit.c @@ -1022,6 +1022,10 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, bool ext emit_atomic(insn, ctx); break;

+ /* Speculation barrier */ + case BPF_ST | BPF_NOSPEC: + break; + default: pr_err("bpf_jit: unknown opcode %02x\n", code); return -EINVAL;

From: Martin Povišer povik+lin@cutebit.org

[ Upstream commit 6e96adcaa7a29827ac8ee8df290a44957a4823ec ]

Add missing setting of 'src_addr_widths', which is the same as for the other direction.

Fixes: b127315d9a78 ("dmaengine: apple-admac: Add Apple ADMAC driver") Signed-off-by: Martin Povišer povik+lin@cutebit.org Link: https://lore.kernel.org/r/20230224152222.26732-3-povik+lin@cutebit.org Signed-off-by: Vinod Koul vkoul@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/dma/apple-admac.c | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/drivers/dma/apple-admac.c b/drivers/dma/apple-admac.c index 00cbfafe0ed9d..b9132b495d181 100644 --- a/drivers/dma/apple-admac.c +++ b/drivers/dma/apple-admac.c @@ -858,6 +858,9 @@ static int admac_probe(struct platform_device *pdev)

dma->directions = BIT(DMA_MEM_TO_DEV) | BIT(DMA_DEV_TO_MEM); dma->residue_granularity = DMA_RESIDUE_GRANULARITY_BURST; + dma->src_addr_widths = BIT(DMA_SLAVE_BUSWIDTH_1_BYTE) | + BIT(DMA_SLAVE_BUSWIDTH_2_BYTES) | + BIT(DMA_SLAVE_BUSWIDTH_4_BYTES); dma->dst_addr_widths = BIT(DMA_SLAVE_BUSWIDTH_1_BYTE) | BIT(DMA_SLAVE_BUSWIDTH_2_BYTES) | BIT(DMA_SLAVE_BUSWIDTH_4_BYTES);

From: Zheng Wang zyytlz.wz@163.com

[ Upstream commit ea4f1009408efb4989a0f139b70fb338e7f687d0 ]

In xen_9pfs_front_probe, it calls xen_9pfs_front_alloc_dataring to init priv->rings and bound &ring->work with p9_xen_response.

When it calls xen_9pfs_front_event_handler to handle IRQ requests, it will finally call schedule_work to start the work.

When we call xen_9pfs_front_remove to remove the driver, there may be a sequence as follows:

Fix it by finishing the work before cleanup in xen_9pfs_front_free.

Note that, this bug is found by static analysis, which might be false positive.

CPU0 CPU1

|p9_xen_response xen_9pfs_front_remove| xen_9pfs_front_free| kfree(priv) | //free priv | |p9_tag_lookup |//use priv->client

Fixes: 71ebd71921e4 ("xen/9pfs: connect to the backend") Signed-off-by: Zheng Wang zyytlz.wz@163.com Reviewed-by: Michal Swiatkowski michal.swiatkowski@linux.intel.com Signed-off-by: Eric Van Hensbergen ericvh@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/9p/trans_xen.c | 4 ++++ 1 file changed, 4 insertions(+)

diff --git a/net/9p/trans_xen.c b/net/9p/trans_xen.c index c64050e839ac6..1fffe2bed5b02 100644 --- a/net/9p/trans_xen.c +++ b/net/9p/trans_xen.c @@ -280,6 +280,10 @@ static void xen_9pfs_front_free(struct xen_9pfs_front_priv *priv) write_unlock(&xen_9pfs_lock);

for (i = 0; i < priv->num_rings; i++) { + struct xen_9pfs_dataring *ring = &priv->rings[i]; + + cancel_work_sync(&ring->work); + if (!priv->rings[i].intf) break; if (priv->rings[i].irq > 0)

From: Fuad Tabba tabba@google.com

[ Upstream commit e81625218bf7986ba1351a98c43d346b15601d26 ]

The existing pKVM code attempts to advertise CSV2/3 using values initialized to 0, but never set. To advertise CSV2/3 to protected guests, pass the CSV2/3 values to hyp when initializing hyp's view of guests' ID_AA64PFR0_EL1.

Similar to non-protected KVM, these are system-wide, rather than per cpu, for simplicity.

Fixes: 6c30bfb18d0b ("KVM: arm64: Add handlers for protected VM System Registers") Signed-off-by: Fuad Tabba tabba@google.com Link: https://lore.kernel.org/r/20230404152321.413064-1-tabba@google.com Signed-off-by: Oliver Upton oliver.upton@linux.dev Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm64/kvm/arm.c | 26 ++++++++++++++++++- .../arm64/kvm/hyp/include/nvhe/fixed_config.h | 5 +++- arch/arm64/kvm/hyp/nvhe/sys_regs.c | 7 ----- 3 files changed, 29 insertions(+), 9 deletions(-)

diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 9c5573bc46145..e57f8ae093875 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -1877,9 +1877,33 @@ static int do_pkvm_init(u32 hyp_va_bits) return ret; }

+static u64 get_hyp_id_aa64pfr0_el1(void) +{ + /* + * Track whether the system isn't affected by spectre/meltdown in the + * hypervisor's view of id_aa64pfr0_el1, used for protected VMs. + * Although this is per-CPU, we make it global for simplicity, e.g., not + * to have to worry about vcpu migration. + * + * Unlike for non-protected VMs, userspace cannot override this for + * protected VMs. + */ + u64 val = read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1); + + val &= ~(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_CSV2) | + ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_CSV3)); + + val |= FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_CSV2), + arm64_get_spectre_v2_state() == SPECTRE_UNAFFECTED); + val |= FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_CSV3), + arm64_get_meltdown_state() == SPECTRE_UNAFFECTED); + + return val; +} + static void kvm_hyp_init_symbols(void) { - kvm_nvhe_sym(id_aa64pfr0_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1); + kvm_nvhe_sym(id_aa64pfr0_el1_sys_val) = get_hyp_id_aa64pfr0_el1(); kvm_nvhe_sym(id_aa64pfr1_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64PFR1_EL1); kvm_nvhe_sym(id_aa64isar0_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64ISAR0_EL1); kvm_nvhe_sym(id_aa64isar1_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64ISAR1_EL1); diff --git a/arch/arm64/kvm/hyp/include/nvhe/fixed_config.h b/arch/arm64/kvm/hyp/include/nvhe/fixed_config.h index 07edfc7524c94..37440e1dda930 100644 --- a/arch/arm64/kvm/hyp/include/nvhe/fixed_config.h +++ b/arch/arm64/kvm/hyp/include/nvhe/fixed_config.h @@ -33,11 +33,14 @@ * Allow for protected VMs: * - Floating-point and Advanced SIMD * - Data Independent Timing + * - Spectre/Meltdown Mitigation */ #define PVM_ID_AA64PFR0_ALLOW (\ ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_FP) | \ ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_AdvSIMD) | \ - ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_DIT) \ + ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_DIT) | \ + ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_CSV2) | \ + ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_CSV3) \ )

/* diff --git a/arch/arm64/kvm/hyp/nvhe/sys_regs.c b/arch/arm64/kvm/hyp/nvhe/sys_regs.c index 0f9ac25afdf40..3d5121ee39777 100644 --- a/arch/arm64/kvm/hyp/nvhe/sys_regs.c +++ b/arch/arm64/kvm/hyp/nvhe/sys_regs.c @@ -84,19 +84,12 @@ static u64 get_restricted_features_unsigned(u64 sys_reg_val,

static u64 get_pvm_id_aa64pfr0(const struct kvm_vcpu *vcpu) { - const struct kvm *kvm = (const struct kvm *)kern_hyp_va(vcpu->kvm); u64 set_mask = 0; u64 allow_mask = PVM_ID_AA64PFR0_ALLOW;

set_mask |= get_restricted_features_unsigned(id_aa64pfr0_el1_sys_val, PVM_ID_AA64PFR0_RESTRICT_UNSIGNED);

- /* Spectre and Meltdown mitigation in KVM */ - set_mask |= FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_CSV2), - (u64)kvm->arch.pfr0_csv2); - set_mask |= FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_CSV3), - (u64)kvm->arch.pfr0_csv3); - return (id_aa64pfr0_el1_sys_val & allow_mask) | set_mask; }

From: YueHaibing yuehaibing@huawei.com

[ Upstream commit dc5110c2d959c1707e12df5f792f41d90614adaa ]

UBSAN: shift-out-of-bounds in net/ipv4/tcp_input.c:555:23 shift exponent 255 is too large for 32-bit type 'int' CPU: 1 PID: 7907 Comm: ssh Not tainted 6.3.0-rc4-00161-g62bad54b26db-dirty #206 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014 Call Trace: <TASK> dump_stack_lvl+0x136/0x150 __ubsan_handle_shift_out_of_bounds+0x21f/0x5a0 tcp_init_transfer.cold+0x3a/0xb9 tcp_finish_connect+0x1d0/0x620 tcp_rcv_state_process+0xd78/0x4d60 tcp_v4_do_rcv+0x33d/0x9d0 __release_sock+0x133/0x3b0 release_sock+0x58/0x1b0

'maxwin' is int, shifting int for 32 or more bits is undefined behaviour.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: YueHaibing yuehaibing@huawei.com Reviewed-by: Eric Dumazet edumazet@google.com Reviewed-by: Kuniyuki Iwashima kuniyu@amazon.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- Documentation/networking/ip-sysctl.rst | 2 ++ net/ipv4/sysctl_net_ipv4.c | 3 +++ 2 files changed, 5 insertions(+)

diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst index 7fbd060d60470..afed49280b52e 100644 --- a/Documentation/networking/ip-sysctl.rst +++ b/Documentation/networking/ip-sysctl.rst @@ -337,6 +337,8 @@ tcp_app_win - INTEGER Reserve max(window/2^tcp_app_win, mss) of window for application buffer. Value 0 is special, it means that nothing is reserved.

+ Possible values are [0, 31], inclusive. + Default: 31

tcp_autocorking - BOOLEAN diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 0d0cc4ef2b85a..40fe70fc2015d 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -25,6 +25,7 @@ static int ip_local_port_range_min[] = { 1, 1 }; static int ip_local_port_range_max[] = { 65535, 65535 }; static int tcp_adv_win_scale_min = -31; static int tcp_adv_win_scale_max = 31; +static int tcp_app_win_max = 31; static int tcp_min_snd_mss_min = TCP_MIN_SND_MSS; static int tcp_min_snd_mss_max = 65535; static int ip_privileged_port_min; @@ -1198,6 +1199,8 @@ static struct ctl_table ipv4_net_table[] = { .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = &tcp_app_win_max, }, { .procname = "tcp_adv_win_scale",

From: Ahmed Zaki ahmed.zaki@intel.com

[ Upstream commit 0c0da0e951053fda20412cd284e2714bbbb31bff ]

The VLAN filter states are currently being saved as individual bits. This is error prone as multiple bits might be mistakenly set.

Fix by replacing the bits with a single state enum. Also, add an "ACTIVE" state for filters that are accepted by the PF.

Signed-off-by: Ahmed Zaki ahmed.zaki@intel.com Tested-by: Rafal Romanowski rafal.romanowski@intel.com Signed-off-by: Tony Nguyen anthony.l.nguyen@intel.com Stable-dep-of: 9c85b7fa12ef ("iavf: remove active_cvlans and active_svlans bitmaps") Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/intel/iavf/iavf.h | 15 +++++---- drivers/net/ethernet/intel/iavf/iavf_main.c | 8 ++--- .../net/ethernet/intel/iavf/iavf_virtchnl.c | 31 +++++++++---------- 3 files changed, 28 insertions(+), 26 deletions(-)

diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h index 2a9f1eeeb7015..fdbb5d9a554cf 100644 --- a/drivers/net/ethernet/intel/iavf/iavf.h +++ b/drivers/net/ethernet/intel/iavf/iavf.h @@ -157,15 +157,18 @@ struct iavf_vlan { u16 tpid; };

+enum iavf_vlan_state_t { + IAVF_VLAN_INVALID, + IAVF_VLAN_ADD, /* filter needs to be added */ + IAVF_VLAN_IS_NEW, /* filter is new, wait for PF answer */ + IAVF_VLAN_ACTIVE, /* filter is accepted by PF */ + IAVF_VLAN_REMOVE, /* filter needs to be removed */ +}; + struct iavf_vlan_filter { struct list_head list; struct iavf_vlan vlan; - struct { - u8 is_new_vlan:1; /* filter is new, wait for PF answer */ - u8 remove:1; /* filter needs to be removed */ - u8 add:1; /* filter needs to be added */ - u8 padding:5; - }; + enum iavf_vlan_state_t state; };

#define IAVF_MAX_TRAFFIC_CLASS 4 diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 8bbdf66c51f6a..3faa9e4d0ba5b 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -791,7 +791,7 @@ iavf_vlan_filter *iavf_add_vlan(struct iavf_adapter *adapter, f->vlan = vlan;

list_add_tail(&f->list, &adapter->vlan_filter_list); - f->add = true; + f->state = IAVF_VLAN_ADD; adapter->aq_required |= IAVF_FLAG_AQ_ADD_VLAN_FILTER; }

@@ -813,7 +813,7 @@ static void iavf_del_vlan(struct iavf_adapter *adapter, struct iavf_vlan vlan)

f = iavf_find_vlan(adapter, vlan); if (f) { - f->remove = true; + f->state = IAVF_VLAN_REMOVE; adapter->aq_required |= IAVF_FLAG_AQ_DEL_VLAN_FILTER; }

@@ -1296,11 +1296,11 @@ static void iavf_clear_mac_vlan_filters(struct iavf_adapter *adapter) /* remove all VLAN filters */ list_for_each_entry_safe(vlf, vlftmp, &adapter->vlan_filter_list, list) { - if (vlf->add) { + if (vlf->state == IAVF_VLAN_ADD) { list_del(&vlf->list); kfree(vlf); } else { - vlf->remove = true; + vlf->state = IAVF_VLAN_REMOVE; } } spin_unlock_bh(&adapter->mac_vlan_list_lock); diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c index 0fea6b9b599fb..fd0239832ffc7 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c +++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c @@ -642,7 +642,7 @@ static void iavf_vlan_add_reject(struct iavf_adapter *adapter)

spin_lock_bh(&adapter->mac_vlan_list_lock); list_for_each_entry_safe(f, ftmp, &adapter->vlan_filter_list, list) { - if (f->is_new_vlan) { + if (f->state == IAVF_VLAN_IS_NEW) { if (f->vlan.tpid == ETH_P_8021Q) clear_bit(f->vlan.vid, adapter->vsi.active_cvlans); @@ -679,7 +679,7 @@ void iavf_add_vlans(struct iavf_adapter *adapter) spin_lock_bh(&adapter->mac_vlan_list_lock);

list_for_each_entry(f, &adapter->vlan_filter_list, list) { - if (f->add) + if (f->state == IAVF_VLAN_ADD) count++; } if (!count || !VLAN_FILTERING_ALLOWED(adapter)) { @@ -710,11 +710,10 @@ void iavf_add_vlans(struct iavf_adapter *adapter) vvfl->vsi_id = adapter->vsi_res->vsi_id; vvfl->num_elements = count; list_for_each_entry(f, &adapter->vlan_filter_list, list) { - if (f->add) { + if (f->state == IAVF_VLAN_ADD) { vvfl->vlan_id[i] = f->vlan.vid; i++; - f->add = false; - f->is_new_vlan = true; + f->state = IAVF_VLAN_IS_NEW; if (i == count) break; } @@ -760,7 +759,7 @@ void iavf_add_vlans(struct iavf_adapter *adapter) vvfl_v2->vport_id = adapter->vsi_res->vsi_id; vvfl_v2->num_elements = count; list_for_each_entry(f, &adapter->vlan_filter_list, list) { - if (f->add) { + if (f->state == IAVF_VLAN_ADD) { struct virtchnl_vlan_supported_caps *filtering_support = &adapter->vlan_v2_caps.filtering.filtering_support; struct virtchnl_vlan *vlan; @@ -778,8 +777,7 @@ void iavf_add_vlans(struct iavf_adapter *adapter) vlan->tpid = f->vlan.tpid;

i++; - f->add = false; - f->is_new_vlan = true; + f->state = IAVF_VLAN_IS_NEW; } }

@@ -822,10 +820,11 @@ void iavf_del_vlans(struct iavf_adapter *adapter) * filters marked for removal to enable bailing out before * sending a virtchnl message */ - if (f->remove && !VLAN_FILTERING_ALLOWED(adapter)) { + if (f->state == IAVF_VLAN_REMOVE && + !VLAN_FILTERING_ALLOWED(adapter)) { list_del(&f->list); kfree(f); - } else if (f->remove) { + } else if (f->state == IAVF_VLAN_REMOVE) { count++; } } @@ -857,7 +856,7 @@ void iavf_del_vlans(struct iavf_adapter *adapter) vvfl->vsi_id = adapter->vsi_res->vsi_id; vvfl->num_elements = count; list_for_each_entry_safe(f, ftmp, &adapter->vlan_filter_list, list) { - if (f->remove) { + if (f->state == IAVF_VLAN_REMOVE) { vvfl->vlan_id[i] = f->vlan.vid; i++; list_del(&f->list); @@ -901,7 +900,7 @@ void iavf_del_vlans(struct iavf_adapter *adapter) vvfl_v2->vport_id = adapter->vsi_res->vsi_id; vvfl_v2->num_elements = count; list_for_each_entry_safe(f, ftmp, &adapter->vlan_filter_list, list) { - if (f->remove) { + if (f->state == IAVF_VLAN_REMOVE) { struct virtchnl_vlan_supported_caps *filtering_support = &adapter->vlan_v2_caps.filtering.filtering_support; struct virtchnl_vlan *vlan; @@ -2192,7 +2191,7 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, list_for_each_entry(vlf, &adapter->vlan_filter_list, list) - vlf->add = true; + vlf->state = IAVF_VLAN_ADD;

adapter->aq_required |= IAVF_FLAG_AQ_ADD_VLAN_FILTER; @@ -2260,7 +2259,7 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, list_for_each_entry(vlf, &adapter->vlan_filter_list, list) - vlf->add = true; + vlf->state = IAVF_VLAN_ADD;

aq_required |= IAVF_FLAG_AQ_ADD_VLAN_FILTER; } @@ -2444,8 +2443,8 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter,

spin_lock_bh(&adapter->mac_vlan_list_lock); list_for_each_entry(f, &adapter->vlan_filter_list, list) { - if (f->is_new_vlan) { - f->is_new_vlan = false; + if (f->state == IAVF_VLAN_IS_NEW) { + f->state = IAVF_VLAN_ACTIVE; if (f->vlan.tpid == ETH_P_8021Q) set_bit(f->vlan.vid, adapter->vsi.active_cvlans);

From: Felix Huettner felix.huettner@mail.schwarz

[ Upstream commit 066b86787fa3d97b7aefb5ac0a99a22dad2d15f8 ]

assume the following setup on a single machine: 1. An openvswitch instance with one bridge and default flows 2. two network namespaces "server" and "client" 3. two ovs interfaces "server" and "client" on the bridge 4. for each ovs interface a veth pair with a matching name and 32 rx and tx queues 5. move the ends of the veth pairs to the respective network namespaces 6. assign ip addresses to each of the veth ends in the namespaces (needs to be the same subnet) 7. start some http server on the server network namespace 8. test if a client in the client namespace can reach the http server

when following the actions below the host has a chance of getting a cpu stuck in a infinite loop: 1. send a large amount of parallel requests to the http server (around 3000 curls should work) 2. in parallel delete the network namespace (do not delete interfaces or stop the server, just kill the namespace)

there is a low chance that this will cause the below kernel cpu stuck message. If this does not happen just retry. Below there is also the output of bpftrace for the functions mentioned in the output.

The series of events happening here is: 1. the network namespace is deleted calling `unregister_netdevice_many_notify` somewhere in the process 2. this sets first `NETREG_UNREGISTERING` on both ends of the veth and then runs `synchronize_net` 3. it then calls `call_netdevice_notifiers` with `NETDEV_UNREGISTER` 4. this is then handled by `dp_device_event` which calls `ovs_netdev_detach_dev` (if a vport is found, which is the case for the veth interface attached to ovs) 5. this removes the rx_handlers of the device but does not prevent packages to be sent to the device 6. `dp_device_event` then queues the vport deletion to work in background as a ovs_lock is needed that we do not hold in the unregistration path 7. `unregister_netdevice_many_notify` continues to call `netdev_unregister_kobject` which sets `real_num_tx_queues` to 0 8. port deletion continues (but details are not relevant for this issue) 9. at some future point the background task deletes the vport

If after 7. but before 9. a packet is send to the ovs vport (which is not deleted at this point in time) which forwards it to the `dev_queue_xmit` flow even though the device is unregistering. In `skb_tx_hash` (which is called in the `dev_queue_xmit`) path there is a while loop (if the packet has a rx_queue recorded) that is infinite if `dev->real_num_tx_queues` is zero.

To prevent this from happening we update `do_output` to handle devices without carrier the same as if the device is not found (which would be the code path after 9. is done).

Additionally we now produce a warning in `skb_tx_hash` if we will hit the infinite loop.

bpftrace (first word is function name):

__dev_queue_xmit server: real_num_tx_queues: 1, cpu: 2, pid: 28024, tid: 28024, skb_addr: 0xffff9edb6f207000, reg_state: 1 netdev_core_pick_tx server: addr: 0xffff9f0a46d4a000 real_num_tx_queues: 1, cpu: 2, pid: 28024, tid: 28024, skb_addr: 0xffff9edb6f207000, reg_state: 1 dp_device_event server: real_num_tx_queues: 1 cpu 9, pid: 21024, tid: 21024, event 2, reg_state: 1 synchronize_rcu_expedited: cpu 9, pid: 21024, tid: 21024 synchronize_rcu_expedited: cpu 9, pid: 21024, tid: 21024 synchronize_rcu_expedited: cpu 9, pid: 21024, tid: 21024 synchronize_rcu_expedited: cpu 9, pid: 21024, tid: 21024 dp_device_event server: real_num_tx_queues: 1 cpu 9, pid: 21024, tid: 21024, event 6, reg_state: 2 ovs_netdev_detach_dev server: real_num_tx_queues: 1 cpu 9, pid: 21024, tid: 21024, reg_state: 2 netdev_rx_handler_unregister server: real_num_tx_queues: 1, cpu: 9, pid: 21024, tid: 21024, reg_state: 2 synchronize_rcu_expedited: cpu 9, pid: 21024, tid: 21024 netdev_rx_handler_unregister ret server: real_num_tx_queues: 1, cpu: 9, pid: 21024, tid: 21024, reg_state: 2 dp_device_event server: real_num_tx_queues: 1 cpu 9, pid: 21024, tid: 21024, event 27, reg_state: 2 dp_device_event server: real_num_tx_queues: 1 cpu 9, pid: 21024, tid: 21024, event 22, reg_state: 2 dp_device_event server: real_num_tx_queues: 1 cpu 9, pid: 21024, tid: 21024, event 18, reg_state: 2 netdev_unregister_kobject: real_num_tx_queues: 1, cpu: 9, pid: 21024, tid: 21024 synchronize_rcu_expedited: cpu 9, pid: 21024, tid: 21024 ovs_vport_send server: real_num_tx_queues: 0, cpu: 2, pid: 28024, tid: 28024, skb_addr: 0xffff9edb6f207000, reg_state: 2 __dev_queue_xmit server: real_num_tx_queues: 0, cpu: 2, pid: 28024, tid: 28024, skb_addr: 0xffff9edb6f207000, reg_state: 2 netdev_core_pick_tx server: addr: 0xffff9f0a46d4a000 real_num_tx_queues: 0, cpu: 2, pid: 28024, tid: 28024, skb_addr: 0xffff9edb6f207000, reg_state: 2 broken device server: real_num_tx_queues: 0, cpu: 2, pid: 28024, tid: 28024 ovs_dp_detach_port server: real_num_tx_queues: 0 cpu 9, pid: 9124, tid: 9124, reg_state: 2 synchronize_rcu_expedited: cpu 9, pid: 33604, tid: 33604

stuck message:

watchdog: BUG: soft lockup - CPU#5 stuck for 26s! [curl:1929279] Modules linked in: veth pktgen bridge stp llc ip_set_hash_net nft_counter xt_set nft_compat nf_tables ip_set_hash_ip ip_set nfnetlink_cttimeout nfnetlink openvswitch nsh nf_conncount nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 tls binfmt_misc nls_iso8859_1 input_leds joydev serio_raw dm_multipath scsi_dh_rdac scsi_dh_emc scsi_dh_alua sch_fq_codel drm efi_pstore virtio_rng ip_tables x_tables autofs4 btrfs blake2b_generic zstd_compress raid10 raid456 async_raid6_recov async_memcpy async_pq async_xor async_tx xor raid6_pq libcrc32c raid1 raid0 multipath linear hid_generic usbhid hid crct10dif_pclmul crc32_pclmul ghash_clmulni_intel aesni_intel virtio_net ahci net_failover crypto_simd cryptd psmouse libahci virtio_blk failover CPU: 5 PID: 1929279 Comm: curl Not tainted 5.15.0-67-generic #74-Ubuntu Hardware name: OpenStack Foundation OpenStack Nova, BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014 RIP: 0010:netdev_pick_tx+0xf1/0x320 Code: 00 00 8d 48 ff 0f b7 c1 66 39 ca 0f 86 e9 01 00 00 45 0f b7 ff 41 39 c7 0f 87 5b 01 00 00 44 29 f8 41 39 c7 0f 87 4f 01 00 00 <eb> f2 0f 1f 44 00 00 49 8b 94 24 28 04 00 00 48 85 d2 0f 84 53 01 RSP: 0018:ffffb78b40298820 EFLAGS: 00000246 RAX: 0000000000000000 RBX: ffff9c8773adc2e0 RCX: 000000000000083f RDX: 0000000000000000 RSI: ffff9c8773adc2e0 RDI: ffff9c870a25e000 RBP: ffffb78b40298858 R08: 0000000000000001 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: ffff9c870a25e000 R13: ffff9c870a25e000 R14: ffff9c87fe043480 R15: 0000000000000000 FS: 00007f7b80008f00(0000) GS:ffff9c8e5f740000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f7b80f6a0b0 CR3: 0000000329d66000 CR4: 0000000000350ee0 Call Trace: <IRQ> netdev_core_pick_tx+0xa4/0xb0 __dev_queue_xmit+0xf8/0x510 ? __bpf_prog_exit+0x1e/0x30 dev_queue_xmit+0x10/0x20 ovs_vport_send+0xad/0x170 [openvswitch] do_output+0x59/0x180 [openvswitch] do_execute_actions+0xa80/0xaa0 [openvswitch] ? kfree+0x1/0x250 ? kfree+0x1/0x250 ? kprobe_perf_func+0x4f/0x2b0 ? flow_lookup.constprop.0+0x5c/0x110 [openvswitch] ovs_execute_actions+0x4c/0x120 [openvswitch] ovs_dp_process_packet+0xa1/0x200 [openvswitch] ? ovs_ct_update_key.isra.0+0xa8/0x120 [openvswitch] ? ovs_ct_fill_key+0x1d/0x30 [openvswitch] ? ovs_flow_key_extract+0x2db/0x350 [openvswitch] ovs_vport_receive+0x77/0xd0 [openvswitch] ? __htab_map_lookup_elem+0x4e/0x60 ? bpf_prog_680e8aff8547aec1_kfree+0x3b/0x714 ? trace_call_bpf+0xc8/0x150 ? kfree+0x1/0x250 ? kfree+0x1/0x250 ? kprobe_perf_func+0x4f/0x2b0 ? kprobe_perf_func+0x4f/0x2b0 ? __mod_memcg_lruvec_state+0x63/0xe0 netdev_port_receive+0xc4/0x180 [openvswitch] ? netdev_port_receive+0x180/0x180 [openvswitch] netdev_frame_hook+0x1f/0x40 [openvswitch] __netif_receive_skb_core.constprop.0+0x23d/0xf00 __netif_receive_skb_one_core+0x3f/0xa0 __netif_receive_skb+0x15/0x60 process_backlog+0x9e/0x170 __napi_poll+0x33/0x180 net_rx_action+0x126/0x280 ? ttwu_do_activate+0x72/0xf0 __do_softirq+0xd9/0x2e7 ? rcu_report_exp_cpu_mult+0x1b0/0x1b0 do_softirq+0x7d/0xb0 </IRQ> <TASK> __local_bh_enable_ip+0x54/0x60 ip_finish_output2+0x191/0x460 __ip_finish_output+0xb7/0x180 ip_finish_output+0x2e/0xc0 ip_output+0x78/0x100 ? __ip_finish_output+0x180/0x180 ip_local_out+0x5e/0x70 __ip_queue_xmit+0x184/0x440 ? tcp_syn_options+0x1f9/0x300 ip_queue_xmit+0x15/0x20 __tcp_transmit_skb+0x910/0x9c0 ? __mod_memcg_state+0x44/0xa0 tcp_connect+0x437/0x4e0 ? ktime_get_with_offset+0x60/0xf0 tcp_v4_connect+0x436/0x530 __inet_stream_connect+0xd4/0x3a0 ? kprobe_perf_func+0x4f/0x2b0 ? aa_sk_perm+0x43/0x1c0 inet_stream_connect+0x3b/0x60 __sys_connect_file+0x63/0x70 __sys_connect+0xa6/0xd0 ? setfl+0x108/0x170 ? do_fcntl+0xe8/0x5a0 __x64_sys_connect+0x18/0x20 do_syscall_64+0x5c/0xc0 ? __x64_sys_fcntl+0xa9/0xd0 ? exit_to_user_mode_prepare+0x37/0xb0 ? syscall_exit_to_user_mode+0x27/0x50 ? do_syscall_64+0x69/0xc0 ? __sys_setsockopt+0xea/0x1e0 ? exit_to_user_mode_prepare+0x37/0xb0 ? syscall_exit_to_user_mode+0x27/0x50 ? __x64_sys_setsockopt+0x1f/0x30 ? do_syscall_64+0x69/0xc0 ? irqentry_exit+0x1d/0x30 ? exc_page_fault+0x89/0x170 entry_SYSCALL_64_after_hwframe+0x61/0xcb RIP: 0033:0x7f7b8101c6a7 Code: 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa 64 8b 04 25 18 00 00 00 85 c0 75 10 b8 2a 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 51 c3 48 83 ec 18 89 54 24 0c 48 89 34 24 89 RSP: 002b:00007ffffd6b2198 EFLAGS: 00000246 ORIG_RAX: 000000000000002a RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f7b8101c6a7 RDX: 0000000000000010 RSI: 00007ffffd6b2360 RDI: 0000000000000005 RBP: 0000561f1370d560 R08: 00002795ad21d1ac R09: 0030312e302e302e R10: 00007ffffd73f080 R11: 0000000000000246 R12: 0000561f1370c410 R13: 0000000000000000 R14: 0000000000000005 R15: 0000000000000000 </TASK>

Fixes: 7f8a436eaa2c ("openvswitch: Add conntrack action") Co-developed-by: Luca Czesla luca.czesla@mail.schwarz Signed-off-by: Luca Czesla luca.czesla@mail.schwarz Signed-off-by: Felix Huettner felix.huettner@mail.schwarz Reviewed-by: Eric Dumazet edumazet@google.com Reviewed-by: Simon Horman simon.horman@corigine.com Link: https://lore.kernel.org/r/ZC0pBXBAgh7c76CA@kernel-bug-kernel-bug Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/core/dev.c | 1 + net/openvswitch/actions.c | 2 +- 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/core/dev.c b/net/core/dev.c index fce980d531bdc..127815273ce3c 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3196,6 +3196,7 @@ static u16 skb_tx_hash(const struct net_device *dev, }

if (skb_rx_queue_recorded(skb)) { + DEBUG_NET_WARN_ON_ONCE(qcount == 0); hash = skb_get_rx_queue(skb); if (hash >= qoffset) hash -= qoffset; diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index ca3ebfdb30231..a8cf9a88758ef 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -913,7 +913,7 @@ static void do_output(struct datapath *dp, struct sk_buff *skb, int out_port, { struct vport *vport = ovs_vport_rcu(dp, out_port);

- if (likely(vport)) { + if (likely(vport && netif_carrier_ok(vport->dev))) { u16 mru = OVS_CB(skb)->mru; u32 cutlen = OVS_CB(skb)->cutlen;

From: Luiz Augusto von Dentz luiz.von.dentz@intel.com

[ Upstream commit b62e72200eaad523f08d8319bba50fc652e032a8 ]

This fixes errors like bellow when LE Connection times out since that is actually not a controller error:

Bluetooth: hci0: Opcode 0x200d failed: -110 Bluetooth: hci0: request failed to create LE connection: err -110

Instead the code shall properly detect if -ETIMEDOUT is returned and send HCI_OP_LE_CREATE_CONN_CANCEL to give up on the connection.

Link: https://github.com/bluez/bluez/issues/340 Fixes: 8e8b92ee60de ("Bluetooth: hci_sync: Add hci_le_create_conn_sync") Signed-off-by: Luiz Augusto von Dentz luiz.von.dentz@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- include/net/bluetooth/hci_core.h | 1 + net/bluetooth/hci_conn.c | 7 +++++-- net/bluetooth/hci_event.c | 16 ++++++---------- net/bluetooth/hci_sync.c | 13 ++++++++++--- 4 files changed, 22 insertions(+), 15 deletions(-)

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 7254edfba4c9c..ffb89b98b2714 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -954,6 +954,7 @@ enum { HCI_CONN_STK_ENCRYPT, HCI_CONN_AUTH_INITIATOR, HCI_CONN_DROP, + HCI_CONN_CANCEL, HCI_CONN_PARAM_REMOVAL_PEND, HCI_CONN_NEW_LINK_KEY, HCI_CONN_SCANNING, diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 6fbc1fe7b1dcb..bd38e36e5a58a 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -1245,6 +1245,8 @@ static void create_le_conn_complete(struct hci_dev *hdev, void *data, int err) { struct hci_conn *conn = data;

+ bt_dev_dbg(hdev, "err %d", err); + hci_dev_lock(hdev);

if (!err) { @@ -1252,8 +1254,6 @@ static void create_le_conn_complete(struct hci_dev *hdev, void *data, int err) goto done; }

- bt_dev_err(hdev, "request failed to create LE connection: err %d", err); - /* Check if connection is still pending */ if (conn != hci_lookup_le_connect(hdev)) goto done; @@ -2787,6 +2787,9 @@ int hci_abort_conn(struct hci_conn *conn, u8 reason) { int r = 0;

+ if (test_and_set_bit(HCI_CONN_CANCEL, &conn->flags)) + return 0; + switch (conn->state) { case BT_CONNECTED: case BT_CONFIG: diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index ad92a4be58517..e68f2a7d863ac 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -2881,16 +2881,6 @@ static void cs_le_create_conn(struct hci_dev *hdev, bdaddr_t *peer_addr,

conn->resp_addr_type = peer_addr_type; bacpy(&conn->resp_addr, peer_addr); - - /* We don't want the connection attempt to stick around - * indefinitely since LE doesn't have a page timeout concept - * like BR/EDR. Set a timer for any connection that doesn't use - * the accept list for connecting. - */ - if (filter_policy == HCI_LE_USE_PEER_ADDR) - queue_delayed_work(conn->hdev->workqueue, - &conn->le_conn_timeout, - conn->conn_timeout); }

static void hci_cs_le_create_conn(struct hci_dev *hdev, u8 status) @@ -5902,6 +5892,12 @@ static void le_conn_complete_evt(struct hci_dev *hdev, u8 status, if (status) goto unlock;

+ /* Drop the connection if it has been aborted */ + if (test_bit(HCI_CONN_CANCEL, &conn->flags)) { + hci_conn_drop(conn); + goto unlock; + } + if (conn->dst_type == ADDR_LE_DEV_PUBLIC) addr_type = BDADDR_LE_PUBLIC; else diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index 5a6aa1627791b..632be12672887 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -246,8 +246,9 @@ int __hci_cmd_sync_status_sk(struct hci_dev *hdev, u16 opcode, u32 plen,

skb = __hci_cmd_sync_sk(hdev, opcode, plen, param, event, timeout, sk); if (IS_ERR(skb)) { - bt_dev_err(hdev, "Opcode 0x%4x failed: %ld", opcode, - PTR_ERR(skb)); + if (!event) + bt_dev_err(hdev, "Opcode 0x%4x failed: %ld", opcode, + PTR_ERR(skb)); return PTR_ERR(skb); }

@@ -5126,8 +5127,11 @@ static int hci_le_connect_cancel_sync(struct hci_dev *hdev, if (test_bit(HCI_CONN_SCANNING, &conn->flags)) return 0;

+ if (test_and_set_bit(HCI_CONN_CANCEL, &conn->flags)) + return 0; + return __hci_cmd_sync_status(hdev, HCI_OP_LE_CREATE_CONN_CANCEL, - 6, &conn->dst, HCI_CMD_TIMEOUT); + 0, NULL, HCI_CMD_TIMEOUT); }

static int hci_connect_cancel_sync(struct hci_dev *hdev, struct hci_conn *conn) @@ -6102,6 +6106,9 @@ int hci_le_create_conn_sync(struct hci_dev *hdev, struct hci_conn *conn) conn->conn_timeout, NULL);

done: + if (err == -ETIMEDOUT) + hci_le_connect_cancel_sync(hdev, conn); + /* Re-enable advertising after the connection attempt is finished. */ hci_resume_advertising_sync(hdev); return err;

From: Claudia Draghicescu claudia.rosu@nxp.com

[ Upstream commit d2e4f1b1cba8742db66aaf77374cab7c0c7c8656 ]

This patch enables ISO data rx on broadcast sink.

Fixes: eca0ae4aea66 ("Bluetooth: Add initial implementation of BIS connections") Signed-off-by: Claudia Draghicescu claudia.rosu@nxp.com Signed-off-by: Luiz Augusto von Dentz luiz.von.dentz@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/bluetooth/hci_event.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index e68f2a7d863ac..e87c928c9e17a 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -6991,7 +6991,7 @@ static void hci_le_big_sync_established_evt(struct hci_dev *hdev, void *data, bis->iso_qos.in.latency = le16_to_cpu(ev->interval) * 125 / 100; bis->iso_qos.in.sdu = le16_to_cpu(ev->max_pdu);

- hci_connect_cfm(bis, ev->status); + hci_iso_setup_path(bis); }

hci_dev_unlock(hdev);

From: Christophe JAILLET christophe.jaillet@wanadoo.fr

[ Upstream commit b89ce1177d42d5c124e83f3858818cd4e6a2c46f ]

'priv' is a managed resource, so there is no need to free it explicitly or there will be a double free().

Fixes: 90ad200b4cbc ("drm/armada: Use devm_drm_dev_alloc") Signed-off-by: Christophe JAILLET christophe.jaillet@wanadoo.fr Signed-off-by: Daniel Vetter daniel.vetter@ffwll.ch Link: https://patchwork.freedesktop.org/patch/msgid/c4f3c9207a9fce35cb6dd2cc60e755... Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/armada/armada_drv.c | 1 - 1 file changed, 1 deletion(-)

diff --git a/drivers/gpu/drm/armada/armada_drv.c b/drivers/gpu/drm/armada/armada_drv.c index 0643887800b4d..142668cd6d7cd 100644 --- a/drivers/gpu/drm/armada/armada_drv.c +++ b/drivers/gpu/drm/armada/armada_drv.c @@ -99,7 +99,6 @@ static int armada_drm_bind(struct device *dev) if (ret) { dev_err(dev, "[" DRM_NAME ":%s] can't kick out simple-fb: %d\n", __func__, ret); - kfree(priv); return ret; }

From: Kuniyuki Iwashima kuniyu@amazon.com

[ Upstream commit 9744d2bf19762703704ecba885b7ac282c02eacf ]

With Eric's ref tracker, syzbot finally found a repro for use-after-free in tcp_write_timer_handler() by kernel TCP sockets. [0]

If SMC creates a kernel socket in __smc_create(), the kernel socket is supposed to be freed in smc_clcsock_release() by calling sock_release() when we close() the parent SMC socket.

However, at the end of smc_clcsock_release(), the kernel socket's sk_state might not be TCP_CLOSE. This means that we have not called inet_csk_destroy_sock() in __tcp_close() and have not stopped the TCP timers.

The kernel socket's TCP timers can be fired later, so we need to hold a refcnt for net as we do for MPTCP subflows in mptcp_subflow_create_socket().

[0]: leaked reference. sk_alloc (./include/net/net_namespace.h:335 net/core/sock.c:2108) inet_create (net/ipv4/af_inet.c:319 net/ipv4/af_inet.c:244) __sock_create (net/socket.c:1546) smc_create (net/smc/af_smc.c:3269 net/smc/af_smc.c:3284) __sock_create (net/socket.c:1546) __sys_socket (net/socket.c:1634 net/socket.c:1618 net/socket.c:1661) __x64_sys_socket (net/socket.c:1672) do_syscall_64 (arch/x86/entry/common.c:50 arch/x86/entry/common.c:80) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:120) ================================================================== BUG: KASAN: slab-use-after-free in tcp_write_timer_handler (net/ipv4/tcp_timer.c:378 net/ipv4/tcp_timer.c:624 net/ipv4/tcp_timer.c:594) Read of size 1 at addr ffff888052b65e0d by task syzrepro/18091

CPU: 0 PID: 18091 Comm: syzrepro Tainted: G W 6.3.0-rc4-01174-gb5d54eb5899a #7 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.0-1.amzn2022.0.1 04/01/2014 Call Trace: <IRQ> dump_stack_lvl (lib/dump_stack.c:107) print_report (mm/kasan/report.c:320 mm/kasan/report.c:430) kasan_report (mm/kasan/report.c:538) tcp_write_timer_handler (net/ipv4/tcp_timer.c:378 net/ipv4/tcp_timer.c:624 net/ipv4/tcp_timer.c:594) tcp_write_timer (./include/linux/spinlock.h:390 net/ipv4/tcp_timer.c:643) call_timer_fn (./arch/x86/include/asm/jump_label.h:27 ./include/linux/jump_label.h:207 ./include/trace/events/timer.h:127 kernel/time/timer.c:1701) __run_timers.part.0 (kernel/time/timer.c:1752 kernel/time/timer.c:2022) run_timer_softirq (kernel/time/timer.c:2037) __do_softirq (./arch/x86/include/asm/jump_label.h:27 ./include/linux/jump_label.h:207 ./include/trace/events/irq.h:142 kernel/softirq.c:572) __irq_exit_rcu (kernel/softirq.c:445 kernel/softirq.c:650) irq_exit_rcu (kernel/softirq.c:664) sysvec_apic_timer_interrupt (arch/x86/kernel/apic/apic.c:1107 (discriminator 14)) </IRQ>

Fixes: ac7138746e14 ("smc: establish new socket family") Reported-by: syzbot+7e1e1bdb852961150198@syzkaller.appspotmail.com Link: https://lore.kernel.org/netdev/000000000000a3f51805f8bcc43a@google.com/ Signed-off-by: Kuniyuki Iwashima kuniyu@amazon.com Reviewed-by: Tony Lu tonylu@linux.alibaba.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/smc/af_smc.c | 11 +++++++++++ 1 file changed, 11 insertions(+)

diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index e8018b0fb7676..bdeaee727538d 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -3257,6 +3257,17 @@ static int __smc_create(struct net *net, struct socket *sock, int protocol, sk_common_release(sk); goto out; } + + /* smc_clcsock_release() does not wait smc->clcsock->sk's + * destruction; its sk_state might not be TCP_CLOSE after + * smc->sk is close()d, and TCP timers can be fired later, + * which need net ref. + */ + sk = smc->clcsock->sk; + __netns_tracker_free(net, &sk->ns_tracker, false); + sk->sk_net_refcnt = 1; + get_net_track(net, &sk->ns_tracker, GFP_KERNEL); + sock_inuse_add(net, 1); } else { smc->clcsock = clcsock; }

From: Tetsuo Handa penguin-kernel@I-love.SAKURA.ne.jp

[ Upstream commit 57dcd64c7e036299ef526b400a8d12b8a2352f26 ]

syzbot is reporting circular locking dependency between cpu_hotplug_lock and freezer_mutex, for commit f5d39b020809 ("freezer,sched: Rewrite core freezer logic") replaced atomic_inc() in freezer_apply_state() with static_branch_inc() which holds cpu_hotplug_lock.

cpu_hotplug_lock => cgroup_threadgroup_rwsem => freezer_mutex

cgroup_file_write() { cgroup_procs_write() { __cgroup_procs_write() { cgroup_procs_write_start() { cgroup_attach_lock() { cpus_read_lock() { percpu_down_read(&cpu_hotplug_lock); } percpu_down_write(&cgroup_threadgroup_rwsem); } } cgroup_attach_task() { cgroup_migrate() { cgroup_migrate_execute() { freezer_attach() { mutex_lock(&freezer_mutex); (...snipped...) } } } } (...snipped...) } } }

freezer_mutex => cpu_hotplug_lock

cgroup_file_write() { freezer_write() { freezer_change_state() { mutex_lock(&freezer_mutex); freezer_apply_state() { static_branch_inc(&freezer_active) { static_key_slow_inc() { cpus_read_lock(); static_key_slow_inc_cpuslocked(); cpus_read_unlock(); } } } mutex_unlock(&freezer_mutex); } } }

Swap locking order by moving cpus_read_lock() in freezer_apply_state() to before mutex_lock(&freezer_mutex) in freezer_change_state().

Reported-by: syzbot syzbot+c39682e86c9d84152f93@syzkaller.appspotmail.com Link: https://syzkaller.appspot.com/bug?extid=c39682e86c9d84152f93 Suggested-by: Hillf Danton hdanton@sina.com Fixes: f5d39b020809 ("freezer,sched: Rewrite core freezer logic") Signed-off-by: Tetsuo Handa penguin-kernel@I-love.SAKURA.ne.jp Acked-by: Peter Zijlstra (Intel) peterz@infradead.org Reviewed-by: Mukesh Ojha quic_mojha@quicinc.com Signed-off-by: Tejun Heo tj@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/cgroup/legacy_freezer.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/kernel/cgroup/legacy_freezer.c b/kernel/cgroup/legacy_freezer.c index 1b6b21851e9d4..936473203a6b5 100644 --- a/kernel/cgroup/legacy_freezer.c +++ b/kernel/cgroup/legacy_freezer.c @@ -22,6 +22,7 @@ #include <linux/freezer.h> #include <linux/seq_file.h> #include <linux/mutex.h> +#include <linux/cpu.h>

/* * A cgroup is freezing if any FREEZING flags are set. FREEZING_SELF is @@ -350,7 +351,7 @@ static void freezer_apply_state(struct freezer *freezer, bool freeze,

if (freeze) { if (!(freezer->state & CGROUP_FREEZING)) - static_branch_inc(&freezer_active); + static_branch_inc_cpuslocked(&freezer_active); freezer->state |= state; freeze_cgroup(freezer); } else { @@ -361,7 +362,7 @@ static void freezer_apply_state(struct freezer *freezer, bool freeze, if (!(freezer->state & CGROUP_FREEZING)) { freezer->state &= ~CGROUP_FROZEN; if (was_freezing) - static_branch_dec(&freezer_active); + static_branch_dec_cpuslocked(&freezer_active); unfreeze_cgroup(freezer); } } @@ -379,6 +380,7 @@ static void freezer_change_state(struct freezer *freezer, bool freeze) { struct cgroup_subsys_state *pos;

+ cpus_read_lock(); /* * Update all its descendants in pre-order traversal. Each * descendant will try to inherit its parent's FREEZING state as @@ -407,6 +409,7 @@ static void freezer_change_state(struct freezer *freezer, bool freeze) } rcu_read_unlock(); mutex_unlock(&freezer_mutex); + cpus_read_unlock(); }

static ssize_t freezer_write(struct kernfs_open_file *of,

From: Ziyang Xuan william.xuanziyang@huawei.com

[ Upstream commit 6417070918de3bcdbe0646e7256dae58fd8083ba ]

Syzbot reported a bug as following:

===================================================== BUG: KMSAN: uninit-value in qrtr_tx_resume+0x185/0x1f0 net/qrtr/af_qrtr.c:230 qrtr_tx_resume+0x185/0x1f0 net/qrtr/af_qrtr.c:230 qrtr_endpoint_post+0xf85/0x11b0 net/qrtr/af_qrtr.c:519 qrtr_tun_write_iter+0x270/0x400 net/qrtr/tun.c:108 call_write_iter include/linux/fs.h:2189 [inline] aio_write+0x63a/0x950 fs/aio.c:1600 io_submit_one+0x1d1c/0x3bf0 fs/aio.c:2019 __do_sys_io_submit fs/aio.c:2078 [inline] __se_sys_io_submit+0x293/0x770 fs/aio.c:2048 __x64_sys_io_submit+0x92/0xd0 fs/aio.c:2048 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3d/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd

Uninit was created at: slab_post_alloc_hook mm/slab.h:766 [inline] slab_alloc_node mm/slub.c:3452 [inline] __kmem_cache_alloc_node+0x71f/0xce0 mm/slub.c:3491 __do_kmalloc_node mm/slab_common.c:967 [inline] __kmalloc_node_track_caller+0x114/0x3b0 mm/slab_common.c:988 kmalloc_reserve net/core/skbuff.c:492 [inline] __alloc_skb+0x3af/0x8f0 net/core/skbuff.c:565 __netdev_alloc_skb+0x120/0x7d0 net/core/skbuff.c:630 qrtr_endpoint_post+0xbd/0x11b0 net/qrtr/af_qrtr.c:446 qrtr_tun_write_iter+0x270/0x400 net/qrtr/tun.c:108 call_write_iter include/linux/fs.h:2189 [inline] aio_write+0x63a/0x950 fs/aio.c:1600 io_submit_one+0x1d1c/0x3bf0 fs/aio.c:2019 __do_sys_io_submit fs/aio.c:2078 [inline] __se_sys_io_submit+0x293/0x770 fs/aio.c:2048 __x64_sys_io_submit+0x92/0xd0 fs/aio.c:2048 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3d/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd

It is because that skb->len requires at least sizeof(struct qrtr_ctrl_pkt) in qrtr_tx_resume(). And skb->len equals to size in qrtr_endpoint_post(). But size is less than sizeof(struct qrtr_ctrl_pkt) when qrtr_cb->type equals to QRTR_TYPE_RESUME_TX in qrtr_endpoint_post() under the syzbot scenario. This triggers the uninit variable access bug.

Add size check when qrtr_cb->type equals to QRTR_TYPE_RESUME_TX in qrtr_endpoint_post() to fix the bug.

Fixes: 5fdeb0d372ab ("net: qrtr: Implement outgoing flow control") Reported-by: syzbot+4436c9630a45820fda76@syzkaller.appspotmail.com Link: https://syzkaller.appspot.com/bug?id=c14607f0963d27d5a3d5f4c8639b500909e4354... Suggested-by: Manivannan Sadhasivam mani@kernel.org Signed-off-by: Ziyang Xuan william.xuanziyang@huawei.com Reviewed-by: Simon Horman simon.horman@corigine.com Link: https://lore.kernel.org/r/20230410012352.3997823-1-william.xuanziyang@huawei... Signed-off-by: Paolo Abeni pabeni@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/qrtr/af_qrtr.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/net/qrtr/af_qrtr.c b/net/qrtr/af_qrtr.c index 3a70255c8d02f..76f0434d3d06a 100644 --- a/net/qrtr/af_qrtr.c +++ b/net/qrtr/af_qrtr.c @@ -498,6 +498,11 @@ int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len) if (!size || len != ALIGN(size, 4) + hdrlen) goto err;

+ if ((cb->type == QRTR_TYPE_NEW_SERVER || + cb->type == QRTR_TYPE_RESUME_TX) && + size < sizeof(struct qrtr_ctrl_pkt)) + goto err; + if (cb->dst_port != QRTR_PORT_CTRL && cb->type != QRTR_TYPE_DATA && cb->type != QRTR_TYPE_RESUME_TX) goto err; @@ -510,9 +515,6 @@ int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len) /* Remote node endpoint can bridge other distant nodes */ const struct qrtr_ctrl_pkt *pkt;

- if (size < sizeof(*pkt)) - goto err; - pkt = data + hdrlen; qrtr_node_assign(node, le32_to_cpu(pkt->server.node)); }

From: Saravanan Vajravel saravanan.vajravel@broadcom.com

[ Upstream commit aca3b0fa3d04b40c96934d86cc224cccfa7ea8e0 ]

If AH create request fails, release sgid_attr to avoid GID entry referrence leak reported while releasing GID table

Fixes: 1a1f460ff151 ("RDMA: Hold the sgid_attr inside the struct ib_ah/qp") Link: https://lore.kernel.org/r/20230401063424.342204-1-saravanan.vajravel@broadco... Reviewed-by: Selvin Xavier selvin.xavier@broadcom.com Signed-off-by: Saravanan Vajravel saravanan.vajravel@broadcom.com Signed-off-by: Jason Gunthorpe jgg@nvidia.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/infiniband/core/verbs.c | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c index 11b1c1603aeb4..b99b3cc283b65 100644 --- a/drivers/infiniband/core/verbs.c +++ b/drivers/infiniband/core/verbs.c @@ -532,6 +532,8 @@ static struct ib_ah *_rdma_create_ah(struct ib_pd *pd, else ret = device->ops.create_ah(ah, &init_attr, NULL); if (ret) { + if (ah->sgid_attr) + rdma_put_gid_attr(ah->sgid_attr); kfree(ah); return ERR_PTR(ret); }

From: Eric Dumazet edumazet@google.com

[ Upstream commit 1c5950fc6fe996235f1d18539b9c6b64b597f50f ]

lena wang reported an issue caused by udpv6_sendmsg() mangling msg->msg_name and msg->msg_namelen, which are later read from ____sys_sendmsg() :

/* * If this is sendmmsg() and sending to current destination address was * successful, remember it. */ if (used_address && err >= 0) { used_address->name_len = msg_sys->msg_namelen; if (msg_sys->msg_name) memcpy(&used_address->name, msg_sys->msg_name, used_address->name_len); }

udpv6_sendmsg() wants to pretend the remote address family is AF_INET in order to call udp_sendmsg().

A fix would be to modify the address in-place, instead of using a local variable, but this could have other side effects.

Instead, restore initial values before we return from udpv6_sendmsg().

Fixes: c71d8ebe7a44 ("net: Fix security_socket_sendmsg() bypass problem.") Reported-by: lena wang lena.wang@mediatek.com Signed-off-by: Eric Dumazet edumazet@google.com Reviewed-by: Maciej Żenczykowski maze@google.com Link: https://lore.kernel.org/r/20230412130308.1202254-1-edumazet@google.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/ipv6/udp.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 9fb2f33ee3a76..a675acfb901d1 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1395,9 +1395,11 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) msg->msg_name = &sin; msg->msg_namelen = sizeof(sin); do_udp_sendmsg: - if (ipv6_only_sock(sk)) - return -ENETUNREACH; - return udp_sendmsg(sk, msg, len); + err = ipv6_only_sock(sk) ? + -ENETUNREACH : udp_sendmsg(sk, msg, len); + msg->msg_name = sin6; + msg->msg_namelen = addr_len; + return err; } }

From: Roman Gushchin roman.gushchin@linux.dev

[ Upstream commit e8b74453555872851bdd7ea43a7c0ec39659834f ]

For quite some time we were chasing a bug which looked like a sudden permanent failure of networking and mmc on some of our devices. The bug was very sensitive to any software changes and even more to any kernel debug options.

Finally we got a setup where the problem was reproducible with CONFIG_DMA_API_DEBUG=y and it revealed the issue with the rx dma:

[ 16.992082] ------------[ cut here ]------------ [ 16.996779] DMA-API: macb ff0b0000.ethernet: device driver tries to free DMA memory it has not allocated [device address=0x0000000875e3e244] [size=1536 bytes] [ 17.011049] WARNING: CPU: 0 PID: 85 at kernel/dma/debug.c:1011 check_unmap+0x6a0/0x900 [ 17.018977] Modules linked in: xxxxx [ 17.038823] CPU: 0 PID: 85 Comm: irq/55-8000f000 Not tainted 5.4.0 #28 [ 17.045345] Hardware name: xxxxx [ 17.049528] pstate: 60000005 (nZCv daif -PAN -UAO) [ 17.054322] pc : check_unmap+0x6a0/0x900 [ 17.058243] lr : check_unmap+0x6a0/0x900 [ 17.062163] sp : ffffffc010003c40 [ 17.065470] x29: ffffffc010003c40 x28: 000000004000c03c [ 17.070783] x27: ffffffc010da7048 x26: ffffff8878e38800 [ 17.076095] x25: ffffff8879d22810 x24: ffffffc010003cc8 [ 17.081407] x23: 0000000000000000 x22: ffffffc010a08750 [ 17.086719] x21: ffffff8878e3c7c0 x20: ffffffc010acb000 [ 17.092032] x19: 0000000875e3e244 x18: 0000000000000010 [ 17.097343] x17: 0000000000000000 x16: 0000000000000000 [ 17.102647] x15: ffffff8879e4a988 x14: 0720072007200720 [ 17.107959] x13: 0720072007200720 x12: 0720072007200720 [ 17.113261] x11: 0720072007200720 x10: 0720072007200720 [ 17.118565] x9 : 0720072007200720 x8 : 000000000000022d [ 17.123869] x7 : 0000000000000015 x6 : 0000000000000098 [ 17.129173] x5 : 0000000000000000 x4 : 0000000000000000 [ 17.134475] x3 : 00000000ffffffff x2 : ffffffc010a1d370 [ 17.139778] x1 : b420c9d75d27bb00 x0 : 0000000000000000 [ 17.145082] Call trace: [ 17.147524] check_unmap+0x6a0/0x900 [ 17.151091] debug_dma_unmap_page+0x88/0x90 [ 17.155266] gem_rx+0x114/0x2f0 [ 17.158396] macb_poll+0x58/0x100 [ 17.161705] net_rx_action+0x118/0x400 [ 17.165445] __do_softirq+0x138/0x36c [ 17.169100] irq_exit+0x98/0xc0 [ 17.172234] __handle_domain_irq+0x64/0xc0 [ 17.176320] gic_handle_irq+0x5c/0xc0 [ 17.179974] el1_irq+0xb8/0x140 [ 17.183109] xiic_process+0x5c/0xe30 [ 17.186677] irq_thread_fn+0x28/0x90 [ 17.190244] irq_thread+0x208/0x2a0 [ 17.193724] kthread+0x130/0x140 [ 17.196945] ret_from_fork+0x10/0x20 [ 17.200510] ---[ end trace 7240980785f81d6f ]---

[ 237.021490] ------------[ cut here ]------------ [ 237.026129] DMA-API: exceeded 7 overlapping mappings of cacheline 0x0000000021d79e7b [ 237.033886] WARNING: CPU: 0 PID: 0 at kernel/dma/debug.c:499 add_dma_entry+0x214/0x240 [ 237.041802] Modules linked in: xxxxx [ 237.061637] CPU: 0 PID: 0 Comm: swapper/0 Tainted: G W 5.4.0 #28 [ 237.068941] Hardware name: xxxxx [ 237.073116] pstate: 80000085 (Nzcv daIf -PAN -UAO) [ 237.077900] pc : add_dma_entry+0x214/0x240 [ 237.081986] lr : add_dma_entry+0x214/0x240 [ 237.086072] sp : ffffffc010003c30 [ 237.089379] x29: ffffffc010003c30 x28: ffffff8878a0be00 [ 237.094683] x27: 0000000000000180 x26: ffffff8878e387c0 [ 237.099987] x25: 0000000000000002 x24: 0000000000000000 [ 237.105290] x23: 000000000000003b x22: ffffffc010a0fa00 [ 237.110594] x21: 0000000021d79e7b x20: ffffffc010abe600 [ 237.115897] x19: 00000000ffffffef x18: 0000000000000010 [ 237.121201] x17: 0000000000000000 x16: 0000000000000000 [ 237.126504] x15: ffffffc010a0fdc8 x14: 0720072007200720 [ 237.131807] x13: 0720072007200720 x12: 0720072007200720 [ 237.137111] x11: 0720072007200720 x10: 0720072007200720 [ 237.142415] x9 : 0720072007200720 x8 : 0000000000000259 [ 237.147718] x7 : 0000000000000001 x6 : 0000000000000000 [ 237.153022] x5 : ffffffc010003a20 x4 : 0000000000000001 [ 237.158325] x3 : 0000000000000006 x2 : 0000000000000007 [ 237.163628] x1 : 8ac721b3a7dc1c00 x0 : 0000000000000000 [ 237.168932] Call trace: [ 237.171373] add_dma_entry+0x214/0x240 [ 237.175115] debug_dma_map_page+0xf8/0x120 [ 237.179203] gem_rx_refill+0x190/0x280 [ 237.182942] gem_rx+0x224/0x2f0 [ 237.186075] macb_poll+0x58/0x100 [ 237.189384] net_rx_action+0x118/0x400 [ 237.193125] __do_softirq+0x138/0x36c [ 237.196780] irq_exit+0x98/0xc0 [ 237.199914] __handle_domain_irq+0x64/0xc0 [ 237.204000] gic_handle_irq+0x5c/0xc0 [ 237.207654] el1_irq+0xb8/0x140 [ 237.210789] arch_cpu_idle+0x40/0x200 [ 237.214444] default_idle_call+0x18/0x30 [ 237.218359] do_idle+0x200/0x280 [ 237.221578] cpu_startup_entry+0x20/0x30 [ 237.225493] rest_init+0xe4/0xf0 [ 237.228713] arch_call_rest_init+0xc/0x14 [ 237.232714] start_kernel+0x47c/0x4a8 [ 237.236367] ---[ end trace 7240980785f81d70 ]---

Lars was fast to find an explanation: according to the datasheet bit 2 of the rx buffer descriptor entry has a different meaning in the extended mode: Address [2] of beginning of buffer, or in extended buffer descriptor mode (DMA configuration register [28] = 1), indicates a valid timestamp in the buffer descriptor entry.

The macb driver didn't mask this bit while getting an address and it eventually caused a memory corruption and a dma failure.

The problem is resolved by explicitly clearing the problematic bit if hw timestamping is used.

Fixes: 7b4296148066 ("net: macb: Add support for PTP timestamps in DMA descriptors") Signed-off-by: Roman Gushchin roman.gushchin@linux.dev Co-developed-by: Lars-Peter Clausen lars@metafoo.de Signed-off-by: Lars-Peter Clausen lars@metafoo.de Acked-by: Nicolas Ferre nicolas.ferre@microchip.com Reviewed-by: Jacob Keller jacob.e.keller@intel.com Link: https://lore.kernel.org/r/20230412232144.770336-1-roman.gushchin@linux.dev Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/cadence/macb_main.c | 4 ++++ 1 file changed, 4 insertions(+)

diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 6cda31520c425..5b230831a4551 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -1009,6 +1009,10 @@ static dma_addr_t macb_get_addr(struct macb *bp, struct macb_dma_desc *desc) } #endif addr |= MACB_BF(RX_WADDR, MACB_BFEXT(RX_WADDR, desc->addr)); +#ifdef CONFIG_MACB_USE_HWSTAMP + if (bp->hw_dma_cap & HW_DMA_CAP_PTP) + addr &= ~GEM_BIT(DMA_RXVALID); +#endif return addr; }

From: Andrew Jeffery andrew@aj.id.au

[ Upstream commit ceac10c83b330680cc01ceaaab86cd49f4f30d81 ]

__copy_to_user_memcpy() and __clear_user_memset() had been calling memcpy() and memset() respectively, leading to false-positive KASAN reports when starting userspace:

[ 10.707901] Run /init as init process [ 10.731892] process '/bin/busybox' started with executable stack [ 10.745234] ================================================================== [ 10.745796] BUG: KASAN: user-memory-access in __clear_user_memset+0x258/0x3ac [ 10.747260] Write of size 2687 at addr 000de581 by task init/1

Use __memcpy() and __memset() instead to allow userspace access, which is of course the intent of these functions.

Signed-off-by: Andrew Jeffery andrew@aj.id.au Signed-off-by: Zev Weiss zev@bewilderbeest.net Reviewed-by: Arnd Bergmann arnd@arndb.de Signed-off-by: Russell King (Oracle) rmk+kernel@armlinux.org.uk Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm/lib/uaccess_with_memcpy.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/arm/lib/uaccess_with_memcpy.c b/arch/arm/lib/uaccess_with_memcpy.c index 14eecaaf295fa..e4c2677cc1e9e 100644 --- a/arch/arm/lib/uaccess_with_memcpy.c +++ b/arch/arm/lib/uaccess_with_memcpy.c @@ -116,7 +116,7 @@ __copy_to_user_memcpy(void __user *to, const void *from, unsigned long n) tocopy = n;

ua_flags = uaccess_save_and_enable(); - memcpy((void *)to, from, tocopy); + __memcpy((void *)to, from, tocopy); uaccess_restore(ua_flags); to += tocopy; from += tocopy; @@ -178,7 +178,7 @@ __clear_user_memset(void __user *addr, unsigned long n) tocopy = n;

ua_flags = uaccess_save_and_enable(); - memset((void *)addr, 0, tocopy); + __memset((void *)addr, 0, tocopy); uaccess_restore(ua_flags); addr += tocopy; n -= tocopy;

From: Brian Masney bmasney@redhat.com

[ Upstream commit b891251b40d4dc4cfd28341f62f6784c02ad3a78 ]

The cdsp.mbn firmware that's referenced in sa8540p-ride.dts is actually named cdsp0.mbn in the deliverables from Qualcomm. Let's go ahead and correct the name to match what's in Qualcomm's deliverable.

Signed-off-by: Brian Masney bmasney@redhat.com Signed-off-by: Bjorn Andersson andersson@kernel.org Link: https://lore.kernel.org/r/20230307232340.2370476-1-bmasney@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm64/boot/dts/qcom/sa8540p-ride.dts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm64/boot/dts/qcom/sa8540p-ride.dts b/arch/arm64/boot/dts/qcom/sa8540p-ride.dts index 6c547f1b13dc4..0f560a4661eba 100644 --- a/arch/arm64/boot/dts/qcom/sa8540p-ride.dts +++ b/arch/arm64/boot/dts/qcom/sa8540p-ride.dts @@ -177,7 +177,7 @@ };

&remoteproc_nsp0 { - firmware-name = "qcom/sa8540p/cdsp.mbn"; + firmware-name = "qcom/sa8540p/cdsp0.mbn"; status = "okay"; };

From: Grant Grundler grundler@chromium.org

[ Upstream commit 14c76b2e75bca4d96e2b85a0c12aa43e84fe3f74 ]

This doesn't need to be printed every second as an error: ... <3>[17438.628385] cros-usbpd-charger cros-usbpd-charger.3.auto: Port 1: default case! <3>[17439.634176] cros-usbpd-charger cros-usbpd-charger.3.auto: Port 1: default case! <3>[17440.640298] cros-usbpd-charger cros-usbpd-charger.3.auto: Port 1: default case! ...

Reduce priority from ERROR to DEBUG.

Signed-off-by: Grant Grundler grundler@chromium.org Reviewed-by: Guenter Roeck groeck@chromium.org Signed-off-by: Sebastian Reichel sebastian.reichel@collabora.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/power/supply/cros_usbpd-charger.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/power/supply/cros_usbpd-charger.c b/drivers/power/supply/cros_usbpd-charger.c index cadb6a0c2cc7e..b6c96376776a9 100644 --- a/drivers/power/supply/cros_usbpd-charger.c +++ b/drivers/power/supply/cros_usbpd-charger.c @@ -276,7 +276,7 @@ static int cros_usbpd_charger_get_power_info(struct port_data *port) port->psy_current_max = 0; break; default: - dev_err(dev, "Port %d: default case!\n", port->port_number); + dev_dbg(dev, "Port %d: default case!\n", port->port_number); port->psy_usb_type = POWER_SUPPLY_USB_TYPE_SDP; }

From: Alexei Starovoitov ast@kernel.org

[ Upstream commit 32513d40d908b267508d37994753d9bd1600914b ]

The commit 11e456cae91e ("selftests/bpf: Fix compilation errors: Assign a value to a constant") fixed the issue cleanly in bpf-next. This is an alternative fix in bpf tree to avoid merge conflict between bpf and bpf-next.

Signed-off-by: Alexei Starovoitov ast@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- tools/testing/selftests/bpf/progs/find_vma_fail1.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/tools/testing/selftests/bpf/progs/find_vma_fail1.c b/tools/testing/selftests/bpf/progs/find_vma_fail1.c index b3b326b8e2d1c..6dab9cffda132 100644 --- a/tools/testing/selftests/bpf/progs/find_vma_fail1.c +++ b/tools/testing/selftests/bpf/progs/find_vma_fail1.c @@ -2,6 +2,7 @@ /* Copyright (c) 2021 Facebook */ #include "vmlinux.h" #include <bpf/bpf_helpers.h> +#define vm_flags vm_start

char _license[] SEC("license") = "GPL";

From: Alexander Stein alexander.stein@ew.tq-group.com

[ Upstream commit 987dd36c0141f6ab9f0fbf14d6b2ec3342dedb2f ]

When start sending a new message clear the Rx & Tx buffer pointers in order to avoid using stale pointers.

Signed-off-by: Alexander Stein alexander.stein@ew.tq-group.com Tested-by: Emanuele Ghidoli emanuele.ghidoli@toradex.com Signed-off-by: Wolfram Sang wsa@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/i2c/busses/i2c-imx-lpi2c.c | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/drivers/i2c/busses/i2c-imx-lpi2c.c b/drivers/i2c/busses/i2c-imx-lpi2c.c index 9b2f9544c5681..a49b14d52a986 100644 --- a/drivers/i2c/busses/i2c-imx-lpi2c.c +++ b/drivers/i2c/busses/i2c-imx-lpi2c.c @@ -463,6 +463,8 @@ static int lpi2c_imx_xfer(struct i2c_adapter *adapter, if (num == 1 && msgs[0].len == 0) goto stop;

+ lpi2c_imx->rx_buf = NULL; + lpi2c_imx->tx_buf = NULL; lpi2c_imx->delivered = 0; lpi2c_imx->msglen = msgs[i].len; init_completion(&lpi2c_imx->complete);

From: Hans de Goede hdegoede@redhat.com

[ Upstream commit 5ed213dd64681f84a01ceaa82fb336cf7d59ddcf ]

Another Lenovo convertable which reports a landscape resolution of 1920x1200 with a pitch of (1920 * 4) bytes, while the actual framebuffer has a resolution of 1200x1920 with a pitch of (1200 * 4) bytes.

Signed-off-by: Hans de Goede hdegoede@redhat.com Reviewed-by: Javier Martinez Canillas javierm@redhat.com Signed-off-by: Ard Biesheuvel ardb@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/firmware/efi/sysfb_efi.c | 8 ++++++++ 1 file changed, 8 insertions(+)

diff --git a/drivers/firmware/efi/sysfb_efi.c b/drivers/firmware/efi/sysfb_efi.c index e76d6803bdd08..456d0e5eaf78b 100644 --- a/drivers/firmware/efi/sysfb_efi.c +++ b/drivers/firmware/efi/sysfb_efi.c @@ -272,6 +272,14 @@ static const struct dmi_system_id efifb_dmi_swap_width_height[] __initconst = { "IdeaPad Duet 3 10IGL5"), }, }, + { + /* Lenovo Yoga Book X91F / X91L */ + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "LENOVO"), + /* Non exact match to match F + L versions */ + DMI_MATCH(DMI_PRODUCT_NAME, "Lenovo YB1-X91"), + }, + }, {}, };

From: Hans de Goede hdegoede@redhat.com

[ Upstream commit 5e7a3bf65db57461d0f47955248fcadf37321a74 ]

The Acer Aspire 3830TG predates Windows 8, so it defaults to using acpi_video# for backlight control, but this is non functional on this model.

Add a DMI quirk to use the native backlight interface which does work properly.

Signed-off-by: Hans de Goede hdegoede@redhat.com Signed-off-by: Rafael J. Wysocki rafael.j.wysocki@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/acpi/video_detect.c | 8 ++++++++ 1 file changed, 8 insertions(+)

diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c index b3b0b06971df5..e85729fc481fd 100644 --- a/drivers/acpi/video_detect.c +++ b/drivers/acpi/video_detect.c @@ -532,6 +532,14 @@ static const struct dmi_system_id video_detect_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "Precision 7510"), }, }, + { + .callback = video_detect_force_native, + /* Acer Aspire 3830TG */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 3830TG"), + }, + }, { .callback = video_detect_force_native, /* Acer Aspire 4810T */

From: Iwona Winiarska iwona.winiarska@intel.com

[ Upstream commit 2b91c4a870c9830eaf95e744454c9c218cccb736 ]

For Skylake, DTS temperature of the CPU is reported in S10.6 format instead of S8.8.

Reported-by: Paul Fertser fercerpav@gmail.com Link: https://lore.kernel.org/lkml/ZBhHS7v+98NK56is@home.paul.comp/ Signed-off-by: Iwona Winiarska iwona.winiarska@intel.com Link: https://lore.kernel.org/r/20230321090410.866766-1-iwona.winiarska@intel.com Signed-off-by: Guenter Roeck linux@roeck-us.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/hwmon/peci/cputemp.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/hwmon/peci/cputemp.c b/drivers/hwmon/peci/cputemp.c index 30850a479f61f..87d56f0fc888c 100644 --- a/drivers/hwmon/peci/cputemp.c +++ b/drivers/hwmon/peci/cputemp.c @@ -537,6 +537,12 @@ static const struct cpu_info cpu_hsx = { .thermal_margin_to_millidegree = &dts_eight_dot_eight_to_millidegree, };

+static const struct cpu_info cpu_skx = { + .reg = &resolved_cores_reg_hsx, + .min_peci_revision = 0x33, + .thermal_margin_to_millidegree = &dts_ten_dot_six_to_millidegree, +}; + static const struct cpu_info cpu_icx = { .reg = &resolved_cores_reg_icx, .min_peci_revision = 0x40, @@ -558,7 +564,7 @@ static const struct auxiliary_device_id peci_cputemp_ids[] = { }, { .name = "peci_cpu.cputemp.skx", - .driver_data = (kernel_ulong_t)&cpu_hsx, + .driver_data = (kernel_ulong_t)&cpu_skx, }, { .name = "peci_cpu.cputemp.icx",

From: Robbie Harwood rharwood@redhat.com

[ Upstream commit 4fc5c74dde69a7eda172514aaeb5a7df3600adb3 ]

The PE Format Specification (section "The Attribute Certificate Table (Image Only)") states that `dwLength` is to be rounded up to 8-byte alignment when used for traversal. Therefore, the field is not required to be an 8-byte multiple in the first place.

Accordingly, pesign has not performed this alignment since version 0.110. This causes kexec failure on pesign'd binaries with "PEFILE: Signature wrapper len wrong". Update the comment and relax the check.

Signed-off-by: Robbie Harwood rharwood@redhat.com Signed-off-by: David Howells dhowells@redhat.com cc: Jarkko Sakkinen jarkko@kernel.org cc: Eric Biederman ebiederm@xmission.com cc: Herbert Xu herbert@gondor.apana.org.au cc: keyrings@vger.kernel.org cc: linux-crypto@vger.kernel.org cc: kexec@lists.infradead.org Link: https://learn.microsoft.com/en-us/windows/win32/debug/pe-format#the-attribut... Link: https://github.com/rhboot/pesign Link: https://lore.kernel.org/r/20230220171254.592347-2-rharwood@redhat.com/ # v2 Signed-off-by: Sasha Levin sashal@kernel.org --- crypto/asymmetric_keys/verify_pefile.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/crypto/asymmetric_keys/verify_pefile.c b/crypto/asymmetric_keys/verify_pefile.c index 7553ab18db898..fe1bb374239d7 100644 --- a/crypto/asymmetric_keys/verify_pefile.c +++ b/crypto/asymmetric_keys/verify_pefile.c @@ -135,11 +135,15 @@ static int pefile_strip_sig_wrapper(const void *pebuf, pr_debug("sig wrapper = { %x, %x, %x }\n", wrapper.length, wrapper.revision, wrapper.cert_type);

- /* Both pesign and sbsign round up the length of certificate table - * (in optional header data directories) to 8 byte alignment. + /* sbsign rounds up the length of certificate table (in optional + * header data directories) to 8 byte alignment. However, the PE + * specification states that while entries are 8-byte aligned, this is + * not included in their length, and as a result, pesign has not + * rounded up since 0.110. */ - if (round_up(wrapper.length, 8) != ctx->sig_len) { - pr_debug("Signature wrapper len wrong\n"); + if (wrapper.length > ctx->sig_len) { + pr_debug("Signature wrapper bigger than sig len (%x > %x)\n", + ctx->sig_len, wrapper.length); return -ELIBBAD; } if (wrapper.revision != WIN_CERT_REVISION_2_0) {

From: Martin George martinus.gpy@gmail.com

[ Upstream commit def84ab600b71ea3fcc422a876d5d0d0daa7d4f3 ]

Identify CNS 06h (I/O Command Set Specific Identify Controller data structure) is supported only on i/o controllers.

But nvme_init_non_mdts_limits() currently invokes this on all controllers. Correct this by ensuring this is sent to I/O controllers only.

Signed-off-by: Martin George marting@netapp.com Signed-off-by: Christoph Hellwig hch@lst.de Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/nvme/host/core.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index ee1b075d12cfc..c0429f9f50920 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -3106,7 +3106,8 @@ static int nvme_init_non_mdts_limits(struct nvme_ctrl *ctrl) else ctrl->max_zeroes_sectors = 0;

- if (nvme_ctrl_limited_cns(ctrl)) + if (ctrl->subsys->subtype != NVME_NQN_NVME || + nvme_ctrl_limited_cns(ctrl)) return 0;

id = kzalloc(sizeof(*id), GFP_KERNEL);

From: Johannes Berg johannes.berg@intel.com

[ Upstream commit 923bf981eb6ecc027227716e30701bdcc1845fbf ]

Some recent upstream debugging uncovered the fact that in iwlwifi, the TXQ list manipulation is racy.

Introduce a new state bit for when the TXQ is completely ready and can be used without locking, and if that's not set yet acquire the lock to check everything correctly.

Reviewed-by: Benjamin Berg benjamin.berg@intel.com Tested-by: Jose Ignacio Tornos Martinez jtornosm@redhat.com Signed-off-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- .../net/wireless/intel/iwlwifi/mvm/mac80211.c | 45 ++++++------------- drivers/net/wireless/intel/iwlwifi/mvm/mvm.h | 2 + drivers/net/wireless/intel/iwlwifi/mvm/ops.c | 1 + drivers/net/wireless/intel/iwlwifi/mvm/sta.c | 25 +++++++++-- 4 files changed, 39 insertions(+), 34 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c index 5b4974181ff1c..1d46a2b345eb3 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c @@ -760,42 +760,25 @@ static void iwl_mvm_mac_wake_tx_queue(struct ieee80211_hw *hw, struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw); struct iwl_mvm_txq *mvmtxq = iwl_mvm_txq_from_mac80211(txq);

- /* - * Please note that racing is handled very carefully here: - * mvmtxq->txq_id is updated during allocation, and mvmtxq->list is - * deleted afterwards. - * This means that if: - * mvmtxq->txq_id != INVALID_QUEUE && list_empty(&mvmtxq->list): - * queue is allocated and we can TX. - * mvmtxq->txq_id != INVALID_QUEUE && !list_empty(&mvmtxq->list): - * a race, should defer the frame. - * mvmtxq->txq_id == INVALID_QUEUE && list_empty(&mvmtxq->list): - * need to allocate the queue and defer the frame. - * mvmtxq->txq_id == INVALID_QUEUE && !list_empty(&mvmtxq->list): - * queue is already scheduled for allocation, no need to allocate, - * should defer the frame. - */ - - /* If the queue is allocated TX and return. */ - if (!txq->sta || mvmtxq->txq_id != IWL_MVM_INVALID_QUEUE) { - /* - * Check that list is empty to avoid a race where txq_id is - * already updated, but the queue allocation work wasn't - * finished - */ - if (unlikely(txq->sta && !list_empty(&mvmtxq->list))) - return; - + if (likely(test_bit(IWL_MVM_TXQ_STATE_READY, &mvmtxq->state)) || + !txq->sta) { iwl_mvm_mac_itxq_xmit(hw, txq); return; }

- /* The list is being deleted only after the queue is fully allocated. */ - if (!list_empty(&mvmtxq->list)) - return; + /* iwl_mvm_mac_itxq_xmit() will later be called by the worker + * to handle any packets we leave on the txq now + */

- list_add_tail(&mvmtxq->list, &mvm->add_stream_txqs); - schedule_work(&mvm->add_stream_wk); + spin_lock_bh(&mvm->add_stream_lock); + /* The list is being deleted only after the queue is fully allocated. */ + if (list_empty(&mvmtxq->list) && + /* recheck under lock */ + !test_bit(IWL_MVM_TXQ_STATE_READY, &mvmtxq->state)) { + list_add_tail(&mvmtxq->list, &mvm->add_stream_txqs); + schedule_work(&mvm->add_stream_wk); + } + spin_unlock_bh(&mvm->add_stream_lock); }

#define CHECK_BA_TRIGGER(_mvm, _trig, _tid_bm, _tid, _fmt...) \ diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h index 3146b3d02bae8..157de77e129e4 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h @@ -731,6 +731,7 @@ struct iwl_mvm_txq { atomic_t tx_request; #define IWL_MVM_TXQ_STATE_STOP_FULL 0 #define IWL_MVM_TXQ_STATE_STOP_REDIRECT 1 +#define IWL_MVM_TXQ_STATE_READY 2 unsigned long state; };

@@ -829,6 +830,7 @@ struct iwl_mvm { struct iwl_mvm_tvqm_txq_info tvqm_info[IWL_MAX_TVQM_QUEUES]; }; struct work_struct add_stream_wk; /* To add streams to queues */ + spinlock_t add_stream_lock;

const char *nvm_file_name; struct iwl_nvm_data *nvm_data; diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c index f43e617fb451f..c49a2a1ee4867 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c @@ -1194,6 +1194,7 @@ iwl_op_mode_mvm_start(struct iwl_trans *trans, const struct iwl_cfg *cfg, INIT_DELAYED_WORK(&mvm->scan_timeout_dwork, iwl_mvm_scan_timeout_wk); INIT_WORK(&mvm->add_stream_wk, iwl_mvm_add_new_dqa_stream_wk); INIT_LIST_HEAD(&mvm->add_stream_txqs); + spin_lock_init(&mvm->add_stream_lock);

init_waitqueue_head(&mvm->rx_sync_waitq);

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c index 21ad7b85c434c..9caae77995ca9 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c @@ -384,8 +384,11 @@ static int iwl_mvm_disable_txq(struct iwl_mvm *mvm, struct ieee80211_sta *sta, struct iwl_mvm_txq *mvmtxq = iwl_mvm_txq_from_tid(sta, tid);

- mvmtxq->txq_id = IWL_MVM_INVALID_QUEUE; + spin_lock_bh(&mvm->add_stream_lock); list_del_init(&mvmtxq->list); + clear_bit(IWL_MVM_TXQ_STATE_READY, &mvmtxq->state); + mvmtxq->txq_id = IWL_MVM_INVALID_QUEUE; + spin_unlock_bh(&mvm->add_stream_lock); }

/* Regardless if this is a reserved TXQ for a STA - mark it as false */ @@ -479,8 +482,11 @@ static int iwl_mvm_remove_sta_queue_marking(struct iwl_mvm *mvm, int queue) disable_agg_tids |= BIT(tid); mvmsta->tid_data[tid].txq_id = IWL_MVM_INVALID_QUEUE;

- mvmtxq->txq_id = IWL_MVM_INVALID_QUEUE; + spin_lock_bh(&mvm->add_stream_lock); list_del_init(&mvmtxq->list); + clear_bit(IWL_MVM_TXQ_STATE_READY, &mvmtxq->state); + mvmtxq->txq_id = IWL_MVM_INVALID_QUEUE; + spin_unlock_bh(&mvm->add_stream_lock); }

mvmsta->tfd_queue_msk &= ~BIT(queue); /* Don't use this queue anymore */ @@ -1444,12 +1450,22 @@ void iwl_mvm_add_new_dqa_stream_wk(struct work_struct *wk) * a queue in the function itself. */ if (iwl_mvm_sta_alloc_queue(mvm, txq->sta, txq->ac, tid)) { + spin_lock_bh(&mvm->add_stream_lock); list_del_init(&mvmtxq->list); + spin_unlock_bh(&mvm->add_stream_lock); continue; }

- list_del_init(&mvmtxq->list); + /* now we're ready, any remaining races/concurrency will be + * handled in iwl_mvm_mac_itxq_xmit() + */ + set_bit(IWL_MVM_TXQ_STATE_READY, &mvmtxq->state); + local_bh_disable(); + spin_lock(&mvm->add_stream_lock); + list_del_init(&mvmtxq->list); + spin_unlock(&mvm->add_stream_lock); + iwl_mvm_mac_itxq_xmit(mvm->hw, txq); local_bh_enable(); } @@ -1864,8 +1880,11 @@ static void iwl_mvm_disable_sta_queues(struct iwl_mvm *mvm, struct iwl_mvm_txq *mvmtxq = iwl_mvm_txq_from_mac80211(sta->txq[i]);

+ spin_lock_bh(&mvm->add_stream_lock); mvmtxq->txq_id = IWL_MVM_INVALID_QUEUE; list_del_init(&mvmtxq->list); + clear_bit(IWL_MVM_TXQ_STATE_READY, &mvmtxq->state); + spin_unlock_bh(&mvm->add_stream_lock); } }

From: YuBiao Wang YuBiao.Wang@amd.com

[ Upstream commit 033c56474acf567a450f8bafca50e0b610f2b716 ]

[Why] For engines not supporting soft reset, i.e. VCN, there will be a failed ib test before mode 1 reset during asic reset. The fences in this case are never signaled and next time when we try to free the sa_bo, kernel will hang.

[How] During pre_asic_reset, driver will clear job fences and afterwards the fences' refcount will be reduced to 1. For drm_sched_jobs it will be released in job_free_cb, and for non-sched jobs like ib_test, it's meant to be released in sa_bo_free but only when the fences are signaled. So we have to force signal the non_sched bad job's fence during pre_asic_reset or the clear is not complete.

Signed-off-by: YuBiao Wang YuBiao.Wang@amd.com Acked-by: Luben Tuikov luben.tuikov@amd.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c | 9 +++++++++ 1 file changed, 9 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c index faff4a3f96e6e..f52d0ba91a770 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c @@ -678,6 +678,15 @@ void amdgpu_fence_driver_clear_job_fences(struct amdgpu_ring *ring) ptr = &ring->fence_drv.fences[i]; old = rcu_dereference_protected(*ptr, 1); if (old && old->ops == &amdgpu_job_fence_ops) { + struct amdgpu_job *job; + + /* For non-scheduler bad job, i.e. failed ib test, we need to signal + * it right here or we won't be able to track them in fence_drv + * and they will remain unsignaled during sa_bo free. + */ + job = container_of(old, struct amdgpu_job, hw_fence); + if (!job->base.s_fence && !dma_fence_is_signaled(old)) + dma_fence_signal(old); RCU_INIT_POINTER(*ptr, NULL); dma_fence_put(old); }

From: Aymeric Wibo obiwac@gmail.com

[ Upstream commit 2d0ab14634a26e54f8d6d231b47b7ef233e84599 ]

Add DMI info of the Medion S17413 (board M1xA) to the IRQ override quirk table. This fixes the keyboard not working on these laptops.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=213031 Signed-off-by: Aymeric Wibo obiwac@gmail.com [ rjw: Fixed up white space ] Signed-off-by: Rafael J. Wysocki rafael.j.wysocki@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/acpi/resource.c | 7 +++++++ 1 file changed, 7 insertions(+)

diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c index a222bda7e15b0..d08818baea88f 100644 --- a/drivers/acpi/resource.c +++ b/drivers/acpi/resource.c @@ -400,6 +400,13 @@ static const struct dmi_system_id medion_laptop[] = { DMI_MATCH(DMI_BOARD_NAME, "M17T"), }, }, + { + .ident = "MEDION S17413", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "MEDION"), + DMI_MATCH(DMI_BOARD_NAME, "M1xA"), + }, + }, { } };

From: Steven Rostedt (Google) rostedt@goodmis.org

[ Upstream commit 9d52727f8043cfda241ae96896628d92fa9c50bb ]

If a trace instance has a failure with its snapshot code, the error message is to be written to that instance's buffer. But currently, the message is written to the top level buffer. Worse yet, it may also disable the top level buffer and not the instance that had the issue.

Link: https://lkml.kernel.org/r/20230405022341.688730321@goodmis.org

Cc: stable@vger.kernel.org Cc: Masami Hiramatsu mhiramat@kernel.org Cc: Mark Rutland mark.rutland@arm.com Cc: Andrew Morton akpm@linux-foundation.org Cc: Ross Zwisler zwisler@google.com Fixes: 2824f50332486 ("tracing: Make the snapshot trigger work with instances") Signed-off-by: Steven Rostedt (Google) rostedt@goodmis.org Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/trace/trace.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 13c46787ba5fa..13b324f008256 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1111,22 +1111,22 @@ static void tracing_snapshot_instance_cond(struct trace_array *tr, unsigned long flags;

if (in_nmi()) { - internal_trace_puts("*** SNAPSHOT CALLED FROM NMI CONTEXT ***\n"); - internal_trace_puts("*** snapshot is being ignored ***\n"); + trace_array_puts(tr, "*** SNAPSHOT CALLED FROM NMI CONTEXT ***\n"); + trace_array_puts(tr, "*** snapshot is being ignored ***\n"); return; }

if (!tr->allocated_snapshot) { - internal_trace_puts("*** SNAPSHOT NOT ALLOCATED ***\n"); - internal_trace_puts("*** stopping trace here! ***\n"); - tracing_off(); + trace_array_puts(tr, "*** SNAPSHOT NOT ALLOCATED ***\n"); + trace_array_puts(tr, "*** stopping trace here! ***\n"); + tracer_tracing_off(tr); return; }

/* Note, snapshot can not be used when the tracer uses it */ if (tracer->use_max_tr) { - internal_trace_puts("*** LATENCY TRACER ACTIVE ***\n"); - internal_trace_puts("*** Can not use snapshot (sorry) ***\n"); + trace_array_puts(tr, "*** LATENCY TRACER ACTIVE ***\n"); + trace_array_puts(tr, "*** Can not use snapshot (sorry) ***\n"); return; }

From: David Disseldorp ddiss@suse.de

commit e7067a446264a7514fa1cfaa4052cdb6803bc6a2 upstream.

Confirm that the accessed pneg_ctxt->HashAlgorithms address sits within the SMB request boundary; deassemble_neg_contexts() only checks that the eight byte smb2_neg_context header + (client controlled) DataLength are within the packet boundary, which is insufficient.

Checking for sizeof(struct smb2_preauth_neg_context) is overkill given that the type currently assumes SMB311_SALT_SIZE bytes of trailing Salt.

Signed-off-by: David Disseldorp ddiss@suse.de Acked-by: Namjae Jeon linkinjeon@kernel.org Cc: stable@vger.kernel.org Signed-off-by: Steve French stfrench@microsoft.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/ksmbd/smb2pdu.c | 23 ++++++++++++++--------- 1 file changed, 14 insertions(+), 9 deletions(-)

--- a/fs/ksmbd/smb2pdu.c +++ b/fs/ksmbd/smb2pdu.c @@ -872,17 +872,21 @@ static void assemble_neg_contexts(struct }

static __le32 decode_preauth_ctxt(struct ksmbd_conn *conn, - struct smb2_preauth_neg_context *pneg_ctxt) + struct smb2_preauth_neg_context *pneg_ctxt, + int len_of_ctxts) { - __le32 err = STATUS_NO_PREAUTH_INTEGRITY_HASH_OVERLAP; + /* + * sizeof(smb2_preauth_neg_context) assumes SMB311_SALT_SIZE Salt, + * which may not be present. Only check for used HashAlgorithms[1]. + */ + if (len_of_ctxts < MIN_PREAUTH_CTXT_DATA_LEN) + return STATUS_INVALID_PARAMETER;

- if (pneg_ctxt->HashAlgorithms == SMB2_PREAUTH_INTEGRITY_SHA512) { - conn->preauth_info->Preauth_HashId = - SMB2_PREAUTH_INTEGRITY_SHA512; - err = STATUS_SUCCESS; - } + if (pneg_ctxt->HashAlgorithms != SMB2_PREAUTH_INTEGRITY_SHA512) + return STATUS_NO_PREAUTH_INTEGRITY_HASH_OVERLAP;

- return err; + conn->preauth_info->Preauth_HashId = SMB2_PREAUTH_INTEGRITY_SHA512; + return STATUS_SUCCESS; }

static void decode_encrypt_ctxt(struct ksmbd_conn *conn, @@ -1010,7 +1014,8 @@ static __le32 deassemble_neg_contexts(st break;

status = decode_preauth_ctxt(conn, - (struct smb2_preauth_neg_context *)pctx); + (struct smb2_preauth_neg_context *)pctx, + len_of_ctxts); if (status != STATUS_SUCCESS) break; } else if (pctx->ContextType == SMB2_ENCRYPTION_CAPABILITIES) {

From: Alexandre Ghiti alexghiti@rivosinc.com

commit ef69d2559fe91f23d27a3d6fd640b5641787d22e upstream.

riscv establishes 2 virtual mappings:

- early_pg_dir maps the kernel which allows to discover the system memory - swapper_pg_dir installs the final mapping (linear mapping included)

We used to map the dtb in early_pg_dir using DTB_EARLY_BASE_VA, and this mapping was not carried over in swapper_pg_dir. It happens that early_init_fdt_scan_reserved_mem() must be called before swapper_pg_dir is setup otherwise we could allocate reserved memory defined in the dtb. And this function initializes reserved_mem variable with addresses that lie in the early_pg_dir dtb mapping: when those addresses are reused with swapper_pg_dir, this mapping does not exist and then we trap.

The previous "fix" was incorrect as early_init_fdt_scan_reserved_mem() must be called before swapper_pg_dir is set up otherwise we could allocate in reserved memory defined in the dtb.

So move the dtb mapping in the fixmap region which is established in early_pg_dir and handed over to swapper_pg_dir.

Fixes: 922b0375fc93 ("riscv: Fix memblock reservation for device tree blob") Fixes: 8f3a2b4a96dc ("RISC-V: Move DT mapping outof fixmap") Fixes: 50e63dd8ed92 ("riscv: fix reserved memory setup") Reported-by: Conor Dooley conor.dooley@microchip.com Link: https://lore.kernel.org/all/f8e67f82-103d-156c-deb0-d6d6e2756f5e@microchip.c... Signed-off-by: Alexandre Ghiti alexghiti@rivosinc.com Reviewed-by: Conor Dooley conor.dooley@microchip.com Tested-by: Conor Dooley conor.dooley@microchip.com Link: https://lore.kernel.org/r/20230329081932.79831-2-alexghiti@rivosinc.com Cc: stable@vger.kernel.org Signed-off-by: Palmer Dabbelt palmer@rivosinc.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- Documentation/riscv/vm-layout.rst | 6 +-- arch/riscv/include/asm/fixmap.h | 8 ++++ arch/riscv/include/asm/pgtable.h | 8 +++- arch/riscv/kernel/setup.c | 1 arch/riscv/mm/init.c | 61 +++++++++++++++++++++----------------- 5 files changed, 51 insertions(+), 33 deletions(-)

--- a/Documentation/riscv/vm-layout.rst +++ b/Documentation/riscv/vm-layout.rst @@ -47,7 +47,7 @@ RISC-V Linux Kernel SV39 | Kernel-space virtual memory, shared between all processes: ____________________________________________________________|___________________________________________________________ | | | | - ffffffc6fee00000 | -228 GB | ffffffc6feffffff | 2 MB | fixmap + ffffffc6fea00000 | -228 GB | ffffffc6feffffff | 6 MB | fixmap ffffffc6ff000000 | -228 GB | ffffffc6ffffffff | 16 MB | PCI io ffffffc700000000 | -228 GB | ffffffc7ffffffff | 4 GB | vmemmap ffffffc800000000 | -224 GB | ffffffd7ffffffff | 64 GB | vmalloc/ioremap space @@ -83,7 +83,7 @@ RISC-V Linux Kernel SV48 | Kernel-space virtual memory, shared between all processes: ____________________________________________________________|___________________________________________________________ | | | | - ffff8d7ffee00000 | -114.5 TB | ffff8d7ffeffffff | 2 MB | fixmap + ffff8d7ffea00000 | -114.5 TB | ffff8d7ffeffffff | 6 MB | fixmap ffff8d7fff000000 | -114.5 TB | ffff8d7fffffffff | 16 MB | PCI io ffff8d8000000000 | -114.5 TB | ffff8f7fffffffff | 2 TB | vmemmap ffff8f8000000000 | -112.5 TB | ffffaf7fffffffff | 32 TB | vmalloc/ioremap space @@ -119,7 +119,7 @@ RISC-V Linux Kernel SV57 | Kernel-space virtual memory, shared between all processes: ____________________________________________________________|___________________________________________________________ | | | | - ff1bfffffee00000 | -57 PB | ff1bfffffeffffff | 2 MB | fixmap + ff1bfffffea00000 | -57 PB | ff1bfffffeffffff | 6 MB | fixmap ff1bffffff000000 | -57 PB | ff1bffffffffffff | 16 MB | PCI io ff1c000000000000 | -57 PB | ff1fffffffffffff | 1 PB | vmemmap ff20000000000000 | -56 PB | ff5fffffffffffff | 16 PB | vmalloc/ioremap space --- a/arch/riscv/include/asm/fixmap.h +++ b/arch/riscv/include/asm/fixmap.h @@ -22,6 +22,14 @@ */ enum fixed_addresses { FIX_HOLE, + /* + * The fdt fixmap mapping must be PMD aligned and will be mapped + * using PMD entries in fixmap_pmd in 64-bit and a PGD entry in 32-bit. + */ + FIX_FDT_END, + FIX_FDT = FIX_FDT_END + FIX_FDT_SIZE / PAGE_SIZE - 1, + + /* Below fixmaps will be mapped using fixmap_pte */ FIX_PTE, FIX_PMD, FIX_PUD, --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -87,9 +87,13 @@

#define FIXADDR_TOP PCI_IO_START #ifdef CONFIG_64BIT -#define FIXADDR_SIZE PMD_SIZE +#define MAX_FDT_SIZE PMD_SIZE +#define FIX_FDT_SIZE (MAX_FDT_SIZE + SZ_2M) +#define FIXADDR_SIZE (PMD_SIZE + FIX_FDT_SIZE) #else -#define FIXADDR_SIZE PGDIR_SIZE +#define MAX_FDT_SIZE PGDIR_SIZE +#define FIX_FDT_SIZE MAX_FDT_SIZE +#define FIXADDR_SIZE (PGDIR_SIZE + FIX_FDT_SIZE) #endif #define FIXADDR_START (FIXADDR_TOP - FIXADDR_SIZE)

--- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -280,7 +280,6 @@ void __init setup_arch(char **cmdline_p) #else unflatten_device_tree(); #endif - early_init_fdt_scan_reserved_mem(); misc_mem_init();

init_resources(); --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -57,7 +57,6 @@ unsigned long empty_zero_page[PAGE_SIZE EXPORT_SYMBOL(empty_zero_page);

extern char _start[]; -#define DTB_EARLY_BASE_VA PGDIR_SIZE void *_dtb_early_va __initdata; uintptr_t _dtb_early_pa __initdata;

@@ -236,6 +235,14 @@ static void __init setup_bootmem(void) set_max_mapnr(max_low_pfn - ARCH_PFN_OFFSET);

reserve_initrd_mem(); + + /* + * No allocation should be done before reserving the memory as defined + * in the device tree, otherwise the allocation could end up in a + * reserved region. + */ + early_init_fdt_scan_reserved_mem(); + /* * If DTB is built in, no need to reserve its memblock. * Otherwise, do reserve it but avoid using @@ -279,9 +286,6 @@ pgd_t trampoline_pg_dir[PTRS_PER_PGD] __ static pte_t fixmap_pte[PTRS_PER_PTE] __page_aligned_bss;

pgd_t early_pg_dir[PTRS_PER_PGD] __initdata __aligned(PAGE_SIZE); -static p4d_t __maybe_unused early_dtb_p4d[PTRS_PER_P4D] __initdata __aligned(PAGE_SIZE); -static pud_t __maybe_unused early_dtb_pud[PTRS_PER_PUD] __initdata __aligned(PAGE_SIZE); -static pmd_t __maybe_unused early_dtb_pmd[PTRS_PER_PMD] __initdata __aligned(PAGE_SIZE);

#ifdef CONFIG_XIP_KERNEL #define pt_ops (*(struct pt_alloc_ops *)XIP_FIXUP(&pt_ops)) @@ -626,9 +630,6 @@ static void __init create_p4d_mapping(p4 #define trampoline_pgd_next (pgtable_l5_enabled ? \ (uintptr_t)trampoline_p4d : (pgtable_l4_enabled ? \ (uintptr_t)trampoline_pud : (uintptr_t)trampoline_pmd)) -#define early_dtb_pgd_next (pgtable_l5_enabled ? \ - (uintptr_t)early_dtb_p4d : (pgtable_l4_enabled ? \ - (uintptr_t)early_dtb_pud : (uintptr_t)early_dtb_pmd)) #else #define pgd_next_t pte_t #define alloc_pgd_next(__va) pt_ops.alloc_pte(__va) @@ -636,7 +637,6 @@ static void __init create_p4d_mapping(p4 #define create_pgd_next_mapping(__nextp, __va, __pa, __sz, __prot) \ create_pte_mapping(__nextp, __va, __pa, __sz, __prot) #define fixmap_pgd_next ((uintptr_t)fixmap_pte) -#define early_dtb_pgd_next ((uintptr_t)early_dtb_pmd) #define create_p4d_mapping(__pmdp, __va, __pa, __sz, __prot) do {} while(0) #define create_pud_mapping(__pmdp, __va, __pa, __sz, __prot) do {} while(0) #define create_pmd_mapping(__pmdp, __va, __pa, __sz, __prot) do {} while(0) @@ -860,32 +860,28 @@ static void __init create_kernel_page_ta * this means 2 PMD entries whereas for 32-bit kernel, this is only 1 PGDIR * entry. */ -static void __init create_fdt_early_page_table(pgd_t *pgdir, uintptr_t dtb_pa) +static void __init create_fdt_early_page_table(pgd_t *pgdir, + uintptr_t fix_fdt_va, + uintptr_t dtb_pa) { -#ifndef CONFIG_BUILTIN_DTB uintptr_t pa = dtb_pa & ~(PMD_SIZE - 1);

- create_pgd_mapping(early_pg_dir, DTB_EARLY_BASE_VA, - IS_ENABLED(CONFIG_64BIT) ? early_dtb_pgd_next : pa, - PGDIR_SIZE, - IS_ENABLED(CONFIG_64BIT) ? PAGE_TABLE : PAGE_KERNEL); - - if (pgtable_l5_enabled) - create_p4d_mapping(early_dtb_p4d, DTB_EARLY_BASE_VA, - (uintptr_t)early_dtb_pud, P4D_SIZE, PAGE_TABLE); - - if (pgtable_l4_enabled) - create_pud_mapping(early_dtb_pud, DTB_EARLY_BASE_VA, - (uintptr_t)early_dtb_pmd, PUD_SIZE, PAGE_TABLE); +#ifndef CONFIG_BUILTIN_DTB + /* Make sure the fdt fixmap address is always aligned on PMD size */ + BUILD_BUG_ON(FIX_FDT % (PMD_SIZE / PAGE_SIZE));

- if (IS_ENABLED(CONFIG_64BIT)) { - create_pmd_mapping(early_dtb_pmd, DTB_EARLY_BASE_VA, + /* In 32-bit only, the fdt lies in its own PGD */ + if (!IS_ENABLED(CONFIG_64BIT)) { + create_pgd_mapping(early_pg_dir, fix_fdt_va, + pa, MAX_FDT_SIZE, PAGE_KERNEL); + } else { + create_pmd_mapping(fixmap_pmd, fix_fdt_va, pa, PMD_SIZE, PAGE_KERNEL); - create_pmd_mapping(early_dtb_pmd, DTB_EARLY_BASE_VA + PMD_SIZE, + create_pmd_mapping(fixmap_pmd, fix_fdt_va + PMD_SIZE, pa + PMD_SIZE, PMD_SIZE, PAGE_KERNEL); }

- dtb_early_va = (void *)DTB_EARLY_BASE_VA + (dtb_pa & (PMD_SIZE - 1)); + dtb_early_va = (void *)fix_fdt_va + (dtb_pa & (PMD_SIZE - 1)); #else /* * For 64-bit kernel, __va can't be used since it would return a linear @@ -1055,7 +1051,8 @@ asmlinkage void __init setup_vm(uintptr_ create_kernel_page_table(early_pg_dir, true);

/* Setup early mapping for FDT early scan */ - create_fdt_early_page_table(early_pg_dir, dtb_pa); + create_fdt_early_page_table(early_pg_dir, + __fix_to_virt(FIX_FDT), dtb_pa);

/* * Bootime fixmap only can handle PMD_SIZE mapping. Thus, boot-ioremap @@ -1097,6 +1094,16 @@ static void __init setup_vm_final(void) u64 i;

/* Setup swapper PGD for fixmap */ +#if !defined(CONFIG_64BIT) + /* + * In 32-bit, the device tree lies in a pgd entry, so it must be copied + * directly in swapper_pg_dir in addition to the pgd entry that points + * to fixmap_pte. + */ + unsigned long idx = pgd_index(__fix_to_virt(FIX_FDT)); + + set_pgd(&swapper_pg_dir[idx], early_pg_dir[idx]); +#endif create_pgd_mapping(swapper_pg_dir, FIXADDR_START, __pa_symbol(fixmap_pgd_next), PGDIR_SIZE, PAGE_TABLE);

From: Tanu Malhotra tanu.malhotra@intel.com

commit 38518593ec55e897abda4b4be77b2ec8ec4447d1 upstream.

During warm reset device->fw_client is set to NULL. If a bus driver is registered after this NULL setting and before new firmware clients are enumerated by ISHTP, kernel panic will result in the function ishtp_cl_bus_match(). This is because of reference to device->fw_client->props.protocol_name.

ISH firmware after getting successfully loaded, sends a warm reset notification to remove all clients from the bus and sets device->fw_client to NULL. Until kernel v5.15, all enabled ISHTP kernel module drivers were loaded right after any of the first ISHTP device was registered, regardless of whether it was a matched or an unmatched device. This resulted in all drivers getting registered much before the warm reset notification from ISH.

Starting kernel v5.16, this issue got exposed after the change was introduced to load only bus drivers for the respective matching devices. In this scenario, cros_ec_ishtp device and cros_ec_ishtp driver are registered after the warm reset device fw_client NULL setting. cros_ec_ishtp driver_register() triggers the callback to ishtp_cl_bus_match() to match ISHTP driver to the device and causes kernel panic in guid_equal() when dereferencing fw_client NULL pointer to get protocol_name.

Fixes: f155dfeaa4ee ("platform/x86: isthp_eclite: only load for matching devices") Fixes: facfe0a4fdce ("platform/chrome: chros_ec_ishtp: only load for matching devices") Fixes: 0d0cccc0fd83 ("HID: intel-ish-hid: hid-client: only load for matching devices") Fixes: 44e2a58cb880 ("HID: intel-ish-hid: fw-loader: only load for matching devices") Cc: stable@vger.kernel.org # 5.16+ Signed-off-by: Tanu Malhotra tanu.malhotra@intel.com Tested-by: Shaunak Saha shaunak.saha@intel.com Acked-by: Srinivas Pandruvada srinivas.pandruvada@linux.intel.com Signed-off-by: Jiri Kosina jkosina@suse.cz Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/hid/intel-ish-hid/ishtp/bus.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

--- a/drivers/hid/intel-ish-hid/ishtp/bus.c +++ b/drivers/hid/intel-ish-hid/ishtp/bus.c @@ -241,8 +241,8 @@ static int ishtp_cl_bus_match(struct dev struct ishtp_cl_device *device = to_ishtp_cl_device(dev); struct ishtp_cl_driver *driver = to_ishtp_cl_driver(drv);

- return guid_equal(&driver->id[0].guid, - &device->fw_client->props.protocol_name); + return(device->fw_client ? guid_equal(&driver->id[0].guid, + &device->fw_client->props.protocol_name) : 0); }

/**

From: Radu Pirea (OSS) radu-nicolae.pirea@oss.nxp.com

commit a4506722dc39ca840593f14e3faa4c9ba9408211 upstream.

Unregister PTP clock when the driver is removed. Purge the RX and TX skb queues.

Fixes: 514def5dd339 ("phy: nxp-c45-tja11xx: add timestamping support") CC: stable@vger.kernel.org # 5.15+ Signed-off-by: Radu Pirea (OSS) radu-nicolae.pirea@oss.nxp.com Reviewed-by: Andrew Lunn andrew@lunn.ch Link: https://lore.kernel.org/r/20230406095904.75456-1-radu-nicolae.pirea@oss.nxp.... Signed-off-by: Paolo Abeni pabeni@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/phy/nxp-c45-tja11xx.c | 12 ++++++++++++ 1 file changed, 12 insertions(+)

--- a/drivers/net/phy/nxp-c45-tja11xx.c +++ b/drivers/net/phy/nxp-c45-tja11xx.c @@ -1337,6 +1337,17 @@ no_ptp_support: return ret; }

+static void nxp_c45_remove(struct phy_device *phydev) +{ + struct nxp_c45_phy *priv = phydev->priv; + + if (priv->ptp_clock) + ptp_clock_unregister(priv->ptp_clock); + + skb_queue_purge(&priv->tx_queue); + skb_queue_purge(&priv->rx_queue); +} + static struct phy_driver nxp_c45_driver[] = { { PHY_ID_MATCH_MODEL(PHY_ID_TJA_1103), @@ -1359,6 +1370,7 @@ static struct phy_driver nxp_c45_driver[ .set_loopback = genphy_c45_loopback, .get_sqi = nxp_c45_get_sqi, .get_sqi_max = nxp_c45_get_sqi_max, + .remove = nxp_c45_remove, }, };

From: Jiri Kosina jkosina@suse.cz

commit c8e22b7a1694bb8d025ea636816472739d859145 upstream.

This reverts commit 3fe97ff3d949 ("scsi: ses: Don't attach if enclosure has no components") and introduces proper handling of case where there are no detected secondary components, but primary component (enumerated in num_enclosures) does exist. That fix was originally proposed by Ding Hui dinghui@sangfor.com.cn.

Completely ignoring devices that have one primary enclosure and no secondary one results in ses_intf_add() bailing completely

scsi 2:0:0:254: enclosure has no enumerated components scsi 2:0:0:254: Failed to bind enclosure -12ven in valid configurations such

even on valid configurations with 1 primary and 0 secondary enclosures as below:

# sg_ses /dev/sg0 3PARdata SES 3321 Supported diagnostic pages: Supported Diagnostic Pages [sdp] [0x0] Configuration (SES) [cf] [0x1] Short Enclosure Status (SES) [ses] [0x8] # sg_ses -p cf /dev/sg0 3PARdata SES 3321 Configuration diagnostic page: number of secondary subenclosures: 0 generation code: 0x0 enclosure descriptor list Subenclosure identifier: 0 [primary] relative ES process id: 0, number of ES processes: 1 number of type descriptor headers: 1 enclosure logical identifier (hex): 20000002ac02068d enclosure vendor: 3PARdata product: VV rev: 3321 type descriptor header and text list Element type: Unspecified, subenclosure id: 0 number of possible elements: 1

The changelog for the original fix follows

===== We can get a crash when disconnecting the iSCSI session, the call trace like this:

[ffff00002a00fb70] kfree at ffff00000830e224 [ffff00002a00fba0] ses_intf_remove at ffff000001f200e4 [ffff00002a00fbd0] device_del at ffff0000086b6a98 [ffff00002a00fc50] device_unregister at ffff0000086b6d58 [ffff00002a00fc70] __scsi_remove_device at ffff00000870608c [ffff00002a00fca0] scsi_remove_device at ffff000008706134 [ffff00002a00fcc0] __scsi_remove_target at ffff0000087062e4 [ffff00002a00fd10] scsi_remove_target at ffff0000087064c0 [ffff00002a00fd70] __iscsi_unbind_session at ffff000001c872c4 [ffff00002a00fdb0] process_one_work at ffff00000810f35c [ffff00002a00fe00] worker_thread at ffff00000810f648 [ffff00002a00fe70] kthread at ffff000008116e98

In ses_intf_add, components count could be 0, and kcalloc 0 size scomp, but not saved in edev->component[i].scratch

In this situation, edev->component[0].scratch is an invalid pointer, when kfree it in ses_intf_remove_enclosure, a crash like above would happen The call trace also could be other random cases when kfree cannot catch the invalid pointer

We should not use edev->component[] array when the components count is 0 We also need check index when use edev->component[] array in ses_enclosure_data_process =====

Reported-by: Michal Kolar mich.k@seznam.cz Originally-by: Ding Hui dinghui@sangfor.com.cn Cc: stable@vger.kernel.org Fixes: 3fe97ff3d949 ("scsi: ses: Don't attach if enclosure has no components") Signed-off-by: Jiri Kosina jkosina@suse.cz Link: https://lore.kernel.org/r/nycvar.YFH.7.76.2304042122270.29760@cbobk.fhfr.pm Tested-by: Michal Kolar mich.k@seznam.cz Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/scsi/ses.c | 20 ++++++++------------ 1 file changed, 8 insertions(+), 12 deletions(-)

--- a/drivers/scsi/ses.c +++ b/drivers/scsi/ses.c @@ -503,9 +503,6 @@ static int ses_enclosure_find_by_addr(st int i; struct ses_component *scomp;

- if (!edev->component[0].scratch) - return 0; - for (i = 0; i < edev->components; i++) { scomp = edev->component[i].scratch; if (scomp->addr != efd->addr) @@ -596,8 +593,10 @@ static void ses_enclosure_data_process(s components++, type_ptr[0], name); - else + else if (components < edev->components) ecomp = &edev->component[components++]; + else + ecomp = ERR_PTR(-EINVAL);

if (!IS_ERR(ecomp)) { if (addl_desc_ptr) { @@ -728,11 +727,6 @@ static int ses_intf_add(struct device *c components += type_ptr[1]; }

- if (components == 0) { - sdev_printk(KERN_WARNING, sdev, "enclosure has no enumerated components\n"); - goto err_free; - } - ses_dev->page1 = buf; ses_dev->page1_len = len; buf = NULL; @@ -774,9 +768,11 @@ static int ses_intf_add(struct device *c buf = NULL; } page2_not_supported: - scomp = kcalloc(components, sizeof(struct ses_component), GFP_KERNEL); - if (!scomp) - goto err_free; + if (components > 0) { + scomp = kcalloc(components, sizeof(struct ses_component), GFP_KERNEL); + if (!scomp) + goto err_free; + }

edev = enclosure_register(cdev->parent, dev_name(&sdev->sdev_gendev), components, &ses_enclosure_callbacks);

From: Evan Quan evan.quan@amd.com

commit b9a24d8bd51e2db425602fa82d7f4c06aa3db852 upstream.

Update the driver implementations to fit those data exposed by PMFW.

Signed-off-by: Evan Quan evan.quan@amd.com Acked-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Cc: stable@vger.kernel.org # 6.1.x Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h | 6 ++++++ drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c | 4 ++-- drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c | 4 ++-- 3 files changed, 10 insertions(+), 4 deletions(-)

--- a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h @@ -61,6 +61,12 @@ #define CTF_OFFSET_HOTSPOT 5 #define CTF_OFFSET_MEM 5

+static const int pmfw_decoded_link_speed[5] = {1, 2, 3, 4, 5}; +static const int pmfw_decoded_link_width[7] = {0, 1, 2, 4, 8, 12, 16}; + +#define DECODE_GEN_SPEED(gen_speed_idx) (pmfw_decoded_link_speed[gen_speed_idx]) +#define DECODE_LANE_WIDTH(lane_width_idx) (pmfw_decoded_link_width[lane_width_idx]) + struct smu_13_0_max_sustainable_clocks { uint32_t display_clock; uint32_t phy_clock; --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c @@ -1125,8 +1125,8 @@ static int smu_v13_0_0_print_clk_levels( (pcie_table->pcie_lane[i] == 5) ? "x12" : (pcie_table->pcie_lane[i] == 6) ? "x16" : "", pcie_table->clk_freq[i], - ((gen_speed - 1) == pcie_table->pcie_gen[i]) && - (lane_width == link_width[pcie_table->pcie_lane[i]]) ? + (gen_speed == DECODE_GEN_SPEED(pcie_table->pcie_gen[i])) && + (lane_width == DECODE_LANE_WIDTH(link_width[pcie_table->pcie_lane[i]])) ? "*" : ""); break;

--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c @@ -1074,8 +1074,8 @@ static int smu_v13_0_7_print_clk_levels( (pcie_table->pcie_lane[i] == 5) ? "x12" : (pcie_table->pcie_lane[i] == 6) ? "x16" : "", pcie_table->clk_freq[i], - (gen_speed == pcie_table->pcie_gen[i]) && - (lane_width == pcie_table->pcie_lane[i]) ? + (gen_speed == DECODE_GEN_SPEED(pcie_table->pcie_gen[i])) && + (lane_width == DECODE_LANE_WIDTH(pcie_table->pcie_lane[i])) ? "*" : ""); break;

From: Reinette Chatre reinette.chatre@intel.com

commit 195d8e5da3acb17c5357526494f818a21e97cd10 upstream.

pci_msix_can_alloc_dyn() is not declared when CONFIG_PCI_MSI is disabled.

There is no existing user of pci_msix_can_alloc_dyn() but work is in progress to change this. This work encounters the following error when CONFIG_PCI_MSI is disabled:

drivers/vfio/pci/vfio_pci_intrs.c:427:21: error: implicit declaration of function 'pci_msix_can_alloc_dyn' [-Werror=implicit-function-declaration]

Provide definition for pci_msix_can_alloc_dyn() in preparation for users that need to compile when CONFIG_PCI_MSI is disabled.

[bhelgaas: Also reported by Arnd Bergmann arnd@kernel.org in drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c; added his Fixes: line]

Fixes: fb0a6a268dcd ("net/mlx5: Provide external API for allocating vectors") Fixes: 34026364df8e ("PCI/MSI: Provide post-enable dynamic allocation interfaces for MSI-X") Link: https://lore.kernel.org/oe-kbuild-all/202303291000.PWFqGCxH-lkp@intel.com/ Link: https://lore.kernel.org/r/310ecc4815dae4174031062f525245f0755c70e2.168011992... Reported-by: kernel test robot lkp@intel.com Signed-off-by: Reinette Chatre reinette.chatre@intel.com Signed-off-by: Bjorn Helgaas bhelgaas@google.com Reviewed-by: Kuppuswamy Sathyanarayanan sathyanarayanan.kuppuswamy@linux.intel.com Cc: stable@vger.kernel.org # v6.2+ Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/linux/pci.h | 2 ++ 1 file changed, 2 insertions(+)

--- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1623,6 +1623,8 @@ pci_alloc_irq_vectors(struct pci_dev *de flags, NULL); }

+static inline bool pci_msix_can_alloc_dyn(struct pci_dev *dev) +{ return false; } static inline struct msi_map pci_msix_alloc_irq_at(struct pci_dev *dev, unsigned int index, const struct irq_affinity_desc *affdesc) {

From: Josh Don joshdon@google.com

commit fcdb1eda5302599045bb366e679cccb4216f3873 upstream.

We need to reset forceidle_sum to 0 when reading from root, since the bstat we accumulate into is stack allocated.

To make this more robust, just replace the existing cputime reset with a memset of the overall bstat.

Signed-off-by: Josh Don joshdon@google.com Fixes: 1fcf54deb767 ("sched/core: add forced idle accounting for cgroups") Cc: stable@vger.kernel.org # v6.0+ Signed-off-by: Tejun Heo tj@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/cgroup/rstat.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-)

--- a/kernel/cgroup/rstat.c +++ b/kernel/cgroup/rstat.c @@ -457,9 +457,7 @@ static void root_cgroup_cputime(struct c struct task_cputime *cputime = &bstat->cputime; int i;

- cputime->stime = 0; - cputime->utime = 0; - cputime->sum_exec_runtime = 0; + memset(bstat, 0, sizeof(*bstat)); for_each_possible_cpu(i) { struct kernel_cpustat kcpustat; u64 *cpustat = kcpustat.cpustat;

From: Waiman Long longman@redhat.com

commit ba9182a89626d5f83c2ee4594f55cb9c1e60f0e2 upstream.

After a successful cpuset_can_attach() call which increments the attach_in_progress flag, either cpuset_cancel_attach() or cpuset_attach() will be called later. In cpuset_attach(), tasks in cpuset_attach_wq, if present, will be woken up at the end. That is not the case in cpuset_cancel_attach(). So missed wakeup is possible if the attach operation is somehow cancelled. Fix that by doing the wakeup in cpuset_cancel_attach() as well.

Fixes: e44193d39e8d ("cpuset: let hotplug propagation work wait for task attaching") Signed-off-by: Waiman Long longman@redhat.com Reviewed-by: Michal Koutný mkoutny@suse.com Cc: stable@vger.kernel.org # v3.11+ Signed-off-by: Tejun Heo tj@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/cgroup/cpuset.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-)

--- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -2502,11 +2502,15 @@ out_unlock: static void cpuset_cancel_attach(struct cgroup_taskset *tset) { struct cgroup_subsys_state *css; + struct cpuset *cs;

cgroup_taskset_first(tset, &css); + cs = css_cs(css);

percpu_down_write(&cpuset_rwsem); - css_cs(css)->attach_in_progress--; + cs->attach_in_progress--; + if (!cs->attach_in_progress) + wake_up(&cpuset_attach_wq); percpu_up_write(&cpuset_rwsem); }

From: Waiman Long longman@redhat.com

commit eee87853794187f6adbe19533ed79c8b44b36a91 upstream.

In the case of CLONE_INTO_CGROUP, not all cpusets are ready to accept new tasks. It is too late to check that in cpuset_fork(). So we need to add the cpuset_can_fork() and cpuset_cancel_fork() methods to pre-check it before we can allow attachment to a different cpuset.

We also need to set the attach_in_progress flag to alert other code that a new task is going to be added to the cpuset.

Fixes: ef2c41cf38a7 ("clone3: allow spawning processes into cgroups") Suggested-by: Michal Koutný mkoutny@suse.com Signed-off-by: Waiman Long longman@redhat.com Cc: stable@vger.kernel.org # v5.7+ Signed-off-by: Tejun Heo tj@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/cgroup/cpuset.c | 97 +++++++++++++++++++++++++++++++++++++++++++------ 1 file changed, 86 insertions(+), 11 deletions(-)

--- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -2453,6 +2453,20 @@ static int fmeter_getrate(struct fmeter

static struct cpuset *cpuset_attach_old_cs;

+/* + * Check to see if a cpuset can accept a new task + * For v1, cpus_allowed and mems_allowed can't be empty. + * For v2, effective_cpus can't be empty. + * Note that in v1, effective_cpus = cpus_allowed. + */ +static int cpuset_can_attach_check(struct cpuset *cs) +{ + if (cpumask_empty(cs->effective_cpus) || + (!is_in_v2_mode() && nodes_empty(cs->mems_allowed))) + return -ENOSPC; + return 0; +} + /* Called by cgroups to determine if a cpuset is usable; cpuset_rwsem held */ static int cpuset_can_attach(struct cgroup_taskset *tset) { @@ -2467,16 +2481,9 @@ static int cpuset_can_attach(struct cgro

percpu_down_write(&cpuset_rwsem);

- /* allow moving tasks into an empty cpuset if on default hierarchy */ - ret = -ENOSPC; - if (!is_in_v2_mode() && - (cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed))) - goto out_unlock; - - /* - * Task cannot be moved to a cpuset with empty effective cpus. - */ - if (cpumask_empty(cs->effective_cpus)) + /* Check to see if task is allowed in the cpuset */ + ret = cpuset_can_attach_check(cs); + if (ret) goto out_unlock;

cgroup_taskset_for_each(task, css, tset) { @@ -2493,7 +2500,6 @@ static int cpuset_can_attach(struct cgro * changes which zero cpus/mems_allowed. */ cs->attach_in_progress++; - ret = 0; out_unlock: percpu_up_write(&cpuset_rwsem); return ret; @@ -3265,6 +3271,68 @@ static void cpuset_bind(struct cgroup_su }

/* + * In case the child is cloned into a cpuset different from its parent, + * additional checks are done to see if the move is allowed. + */ +static int cpuset_can_fork(struct task_struct *task, struct css_set *cset) +{ + struct cpuset *cs = css_cs(cset->subsys[cpuset_cgrp_id]); + bool same_cs; + int ret; + + rcu_read_lock(); + same_cs = (cs == task_cs(current)); + rcu_read_unlock(); + + if (same_cs) + return 0; + + lockdep_assert_held(&cgroup_mutex); + percpu_down_write(&cpuset_rwsem); + + /* Check to see if task is allowed in the cpuset */ + ret = cpuset_can_attach_check(cs); + if (ret) + goto out_unlock; + + ret = task_can_attach(task, cs->effective_cpus); + if (ret) + goto out_unlock; + + ret = security_task_setscheduler(task); + if (ret) + goto out_unlock; + + /* + * Mark attach is in progress. This makes validate_change() fail + * changes which zero cpus/mems_allowed. + */ + cs->attach_in_progress++; +out_unlock: + percpu_up_write(&cpuset_rwsem); + return ret; +} + +static void cpuset_cancel_fork(struct task_struct *task, struct css_set *cset) +{ + struct cpuset *cs = css_cs(cset->subsys[cpuset_cgrp_id]); + bool same_cs; + + rcu_read_lock(); + same_cs = (cs == task_cs(current)); + rcu_read_unlock(); + + if (same_cs) + return; + + percpu_down_write(&cpuset_rwsem); + cs->attach_in_progress--; + if (!cs->attach_in_progress) + wake_up(&cpuset_attach_wq); + percpu_up_write(&cpuset_rwsem); +} + +/* * Make sure the new task conform to the current state of its parent, * which could have been changed by cpuset just after it inherits the * state from the parent and before it sits on the cgroup's task list. @@ -3292,6 +3360,11 @@ static void cpuset_fork(struct task_stru percpu_down_write(&cpuset_rwsem); guarantee_online_mems(cs, &cpuset_attach_nodemask_to); cpuset_attach_task(cs, task); + + cs->attach_in_progress--; + if (!cs->attach_in_progress) + wake_up(&cpuset_attach_wq); + percpu_up_write(&cpuset_rwsem); }

@@ -3305,6 +3378,8 @@ struct cgroup_subsys cpuset_cgrp_subsys .attach = cpuset_attach, .post_attach = cpuset_post_attach, .bind = cpuset_bind, + .can_fork = cpuset_can_fork, + .cancel_fork = cpuset_cancel_fork, .fork = cpuset_fork, .legacy_cftypes = legacy_files, .dfl_cftypes = dfl_files,

From: Horatio Zhang Hongkun.Zhang@amd.com

commit 85e0689eb6b10cd3b2fb455d1b3f4d4d0b13ff78 upstream.

Correct the max shader clock reporting on SMU 13.0.7.

Signed-off-by: Horatio Zhang Hongkun.Zhang@amd.com Reviewed-by: Kenneth Feng kenneth.feng@amd.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Cc: stable@vger.kernel.org # 6.1.x Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c | 61 ++++++++++++++++++- 1 file changed, 60 insertions(+), 1 deletion(-)

--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c @@ -575,6 +575,14 @@ static int smu_v13_0_7_set_default_dpm_t dpm_table); if (ret) return ret; + + if (skutable->DriverReportedClocks.GameClockAc && + (dpm_table->dpm_levels[dpm_table->count - 1].value > + skutable->DriverReportedClocks.GameClockAc)) { + dpm_table->dpm_levels[dpm_table->count - 1].value = + skutable->DriverReportedClocks.GameClockAc; + dpm_table->max = skutable->DriverReportedClocks.GameClockAc; + } } else { dpm_table->count = 1; dpm_table->dpm_levels[0].value = smu->smu_table.boot_values.gfxclk / 100; @@ -828,6 +836,57 @@ static int smu_v13_0_7_get_smu_metrics_d return ret; }

+static int smu_v13_0_7_get_dpm_ultimate_freq(struct smu_context *smu, + enum smu_clk_type clk_type, + uint32_t *min, + uint32_t *max) +{ + struct smu_13_0_dpm_context *dpm_context = + smu->smu_dpm.dpm_context; + struct smu_13_0_dpm_table *dpm_table; + + switch (clk_type) { + case SMU_MCLK: + case SMU_UCLK: + /* uclk dpm table */ + dpm_table = &dpm_context->dpm_tables.uclk_table; + break; + case SMU_GFXCLK: + case SMU_SCLK: + /* gfxclk dpm table */ + dpm_table = &dpm_context->dpm_tables.gfx_table; + break; + case SMU_SOCCLK: + /* socclk dpm table */ + dpm_table = &dpm_context->dpm_tables.soc_table; + break; + case SMU_FCLK: + /* fclk dpm table */ + dpm_table = &dpm_context->dpm_tables.fclk_table; + break; + case SMU_VCLK: + case SMU_VCLK1: + /* vclk dpm table */ + dpm_table = &dpm_context->dpm_tables.vclk_table; + break; + case SMU_DCLK: + case SMU_DCLK1: + /* dclk dpm table */ + dpm_table = &dpm_context->dpm_tables.dclk_table; + break; + default: + dev_err(smu->adev->dev, "Unsupported clock type!\n"); + return -EINVAL; + } + + if (min) + *min = dpm_table->min; + if (max) + *max = dpm_table->max; + + return 0; +} + static int smu_v13_0_7_read_sensor(struct smu_context *smu, enum amd_pp_sensors sensor, void *data, @@ -1684,7 +1743,7 @@ static const struct pptable_funcs smu_v1 .dpm_set_jpeg_enable = smu_v13_0_set_jpeg_enable, .init_pptable_microcode = smu_v13_0_init_pptable_microcode, .populate_umd_state_clk = smu_v13_0_7_populate_umd_state_clk, - .get_dpm_ultimate_freq = smu_v13_0_get_dpm_ultimate_freq, + .get_dpm_ultimate_freq = smu_v13_0_7_get_dpm_ultimate_freq, .get_vbios_bootup_values = smu_v13_0_get_vbios_bootup_values, .read_sensor = smu_v13_0_7_read_sensor, .feature_is_enabled = smu_cmn_feature_is_enabled,

From: Paolo Abeni pabeni@redhat.com

commit d6a0443733434408f2cbd4c53fea6910599bab9e upstream.

As reported by Christoph, the mptcp protocol can run the worker when the relevant msk socket is in an unexpected state:

connect() // incoming reset + fastclose // the mptcp worker is scheduled mptcp_disconnect() // msk is now CLOSED listen() mptcp_worker()

Leading to the following splat:

divide error: 0000 [#1] PREEMPT SMP CPU: 1 PID: 21 Comm: kworker/1:0 Not tainted 6.3.0-rc1-gde5e8fd0123c #11 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.11.0-2.el7 04/01/2014 Workqueue: events mptcp_worker RIP: 0010:__tcp_select_window+0x22c/0x4b0 net/ipv4/tcp_output.c:3018 RSP: 0018:ffffc900000b3c98 EFLAGS: 00010293 RAX: 000000000000ffd7 RBX: 000000000000ffd7 RCX: 0000000000000000 RDX: 0000000000000000 RSI: ffffffff8214ce97 RDI: 0000000000000004 RBP: 000000000000ffd7 R08: 0000000000000004 R09: 0000000000010000 R10: 000000000000ffd7 R11: ffff888005afa148 R12: 000000000000ffd7 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 FS: 0000000000000000(0000) GS:ffff88803ed00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000405270 CR3: 000000003011e006 CR4: 0000000000370ee0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: <TASK> tcp_select_window net/ipv4/tcp_output.c:262 [inline] __tcp_transmit_skb+0x356/0x1280 net/ipv4/tcp_output.c:1345 tcp_transmit_skb net/ipv4/tcp_output.c:1417 [inline] tcp_send_active_reset+0x13e/0x320 net/ipv4/tcp_output.c:3459 mptcp_check_fastclose net/mptcp/protocol.c:2530 [inline] mptcp_worker+0x6c7/0x800 net/mptcp/protocol.c:2705 process_one_work+0x3bd/0x950 kernel/workqueue.c:2390 worker_thread+0x5b/0x610 kernel/workqueue.c:2537 kthread+0x138/0x170 kernel/kthread.c:376 ret_from_fork+0x2c/0x50 arch/x86/entry/entry_64.S:308 </TASK>

This change addresses the issue explicitly checking for bad states before running the mptcp worker.

Fixes: e16163b6e2b7 ("mptcp: refactor shutdown and close") Cc: stable@vger.kernel.org Reported-by: Christoph Paasch cpaasch@apple.com Link: https://github.com/multipath-tcp/mptcp_net-next/issues/374 Signed-off-by: Paolo Abeni pabeni@redhat.com Reviewed-by: Matthieu Baerts matthieu.baerts@tessares.net Tested-by: Christoph Paasch cpaasch@apple.com Signed-off-by: Matthieu Baerts matthieu.baerts@tessares.net Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/mptcp/protocol.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -2627,7 +2627,7 @@ static void mptcp_worker(struct work_str

lock_sock(sk); state = sk->sk_state; - if (unlikely(state == TCP_CLOSE)) + if (unlikely((1 << state) & (TCPF_CLOSE | TCPF_LISTEN))) goto unlock;

mptcp_check_data_fin_ack(sk);

From: Matthieu Baerts matthieu.baerts@tessares.net

commit 711ae788cbbb82818531b55e32b09518ee09a11a upstream.

Simply adding a "sleep" before checking something is usually not a good idea because the time that has been picked can not be enough or too much. The best is to wait for events with a timeout.

In this selftest, 'sleep 0.5' is used more than 40 times. It is always used before calling a 'verify_*' function except for this verify_listener_events which has been added later.

At the end, using all these 'sleep 0.5' seems to work: the slow CIs don't complain so far. Also because it doesn't take too much time, we can just add two more 'sleep 0.5' to uniform what is done before calling a 'verify_*' function. For the same reasons, we can also delay a bigger refactoring to replace all these 'sleep 0.5' by functions waiting for events instead of waiting for a fix time and hope for the best.

Fixes: 6c73008aa301 ("selftests: mptcp: listener test for userspace PM") Cc: stable@vger.kernel.org Suggested-by: Paolo Abeni pabeni@redhat.com Signed-off-by: Matthieu Baerts matthieu.baerts@tessares.net Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- tools/testing/selftests/net/mptcp/userspace_pm.sh | 2 ++ 1 file changed, 2 insertions(+)

--- a/tools/testing/selftests/net/mptcp/userspace_pm.sh +++ b/tools/testing/selftests/net/mptcp/userspace_pm.sh @@ -884,6 +884,7 @@ test_listener() $client4_port > /dev/null 2>&1 & local listener_pid=$!

+ sleep 0.5 verify_listener_events $client_evts $LISTENER_CREATED $AF_INET 10.0.2.2 $client4_port

# ADD_ADDR from client to server machine reusing the subflow port @@ -899,6 +900,7 @@ test_listener() # Delete the listener from the client ns, if one was created kill_wait $listener_pid

+ sleep 0.5 verify_listener_events $client_evts $LISTENER_CLOSED $AF_INET 10.0.2.2 $client4_port }

From: ZhaoLong Wang wangzhaolong1@huawei.com

[ Upstream commit f773f0a331d6c41733b17bebbc1b6cae12e016f5 ]

During the processing of the bgt, if the sync_erase() return -EBUSY or some other error code in __erase_worker(),schedule_erase() called again lead to the down_read(ubi->work_sem) hold twice and may get block by down_write(ubi->work_sem) in ubi_update_fastmap(), which cause deadlock.

ubi bgt other task do_work down_read(&ubi->work_sem) ubi_update_fastmap erase_worker # Blocked by down_read __erase_worker down_write(&ubi->work_sem) schedule_erase schedule_ubi_work down_read(&ubi->work_sem)

Fix this by changing input parameter @nested of the schedule_erase() to 'true' to avoid recursively acquiring the down_read(&ubi->work_sem).

Also, fix the incorrect comment about @nested parameter of the schedule_erase() because when down_write(ubi->work_sem) is held, the @nested is also need be true.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=217093 Fixes: 2e8f08deabbc ("ubi: Fix races around ubi_refill_pools()") Signed-off-by: ZhaoLong Wang wangzhaolong1@huawei.com Reviewed-by: Zhihao Cheng chengzhihao1@huawei.com Signed-off-by: Richard Weinberger richard@nod.at Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/mtd/ubi/wl.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/mtd/ubi/wl.c b/drivers/mtd/ubi/wl.c index 9e14319225c97..6049ab9e46479 100644 --- a/drivers/mtd/ubi/wl.c +++ b/drivers/mtd/ubi/wl.c @@ -575,7 +575,7 @@ static int erase_worker(struct ubi_device *ubi, struct ubi_work *wl_wrk, * @vol_id: the volume ID that last used this PEB * @lnum: the last used logical eraseblock number for the PEB * @torture: if the physical eraseblock has to be tortured - * @nested: denotes whether the work_sem is already held in read mode + * @nested: denotes whether the work_sem is already held * * This function returns zero in case of success and a %-ENOMEM in case of * failure. @@ -1131,7 +1131,7 @@ static int __erase_worker(struct ubi_device *ubi, struct ubi_work *wl_wrk) int err1;

/* Re-schedule the LEB for erasure */ - err1 = schedule_erase(ubi, e, vol_id, lnum, 0, false); + err1 = schedule_erase(ubi, e, vol_id, lnum, 0, true); if (err1) { spin_lock(&ubi->wl_lock); wl_entry_destroy(ubi, e);

From: Aneesh Kumar K.V aneesh.kumar@linux.ibm.com

[ Upstream commit b277fc793daf258877b4c0744b52f69d6e6ba22e ]

Platform device helper routines won't update the NUMA distance table while creating a platform device, even if the device is present on a NUMA node that doesn't have memory or CPU. This is especially true for pmem devices. If the target node of the pmem device is not online, we find the nearest online node to the device and associate the pmem device with that online node. To find the nearest online node, we should have the numa distance table updated correctly. Update the distance information during the device probe.

For a papr scm device on NUMA node 3 distance_lookup_table value for distance_ref_points_depth = 2 before and after fix is below:

Before fix: node 3 distance depth 0 - 0 node 3 distance depth 1 - 0 node 4 distance depth 0 - 4 node 4 distance depth 1 - 2 node 5 distance depth 0 - 5 node 5 distance depth 1 - 1

After fix node 3 distance depth 0 - 3 node 3 distance depth 1 - 1 node 4 distance depth 0 - 4 node 4 distance depth 1 - 2 node 5 distance depth 0 - 5 node 5 distance depth 1 - 1

Without the fix, the nearest numa node to the pmem device (NUMA node 3) will be picked as 4. After the fix, we get the correct numa node which is 5.

Fixes: da1115fdbd6e ("powerpc/nvdimm: Pick nearby online node if the device node is not online") Signed-off-by: Aneesh Kumar K.V aneesh.kumar@linux.ibm.com Signed-off-by: Michael Ellerman mpe@ellerman.id.au Link: https://msgid.link/20230404041433.1781804-1-aneesh.kumar@linux.ibm.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/powerpc/mm/numa.c | 1 + arch/powerpc/platforms/pseries/papr_scm.c | 7 +++++++ 2 files changed, 8 insertions(+)

diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index b44ce71917d75..16cfe56be05bb 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -366,6 +366,7 @@ void update_numa_distance(struct device_node *node) WARN(numa_distance_table[nid][nid] == -1, "NUMA distance details for node %d not provided\n", nid); } +EXPORT_SYMBOL_GPL(update_numa_distance);

/* * ibm,numa-lookup-index-table= {N, domainid1, domainid2, ..... domainidN} diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c index 2f8385523a132..1a53e048ceb76 100644 --- a/arch/powerpc/platforms/pseries/papr_scm.c +++ b/arch/powerpc/platforms/pseries/papr_scm.c @@ -1428,6 +1428,13 @@ static int papr_scm_probe(struct platform_device *pdev) return -ENODEV; }

+ /* + * open firmware platform device create won't update the NUMA + * distance table. For PAPR SCM devices we use numa_map_to_online_node() + * to find the nearest online NUMA node and that requires correct + * distance table information. + */ + update_numa_distance(dn);

p = kzalloc(sizeof(*p), GFP_KERNEL); if (!p)

From: Matija Glavinic Pecotic matija.glavinic-pecotic.ext@nokia.com

[ Upstream commit 775d3c514c5b2763a50ab7839026d7561795924d ]

set_rtc_noop(), get_rtc_noop() are after booting, therefore their __init annotation is wrong.

A crash was observed on an x86 platform where CMOS RTC is unused and disabled via device tree. set_rtc_noop() was invoked from ntp: sync_hw_clock(), although CONFIG_RTC_SYSTOHC=n, however sync_cmos_clock() doesn't honour that.

Workqueue: events_power_efficient sync_hw_clock RIP: 0010:set_rtc_noop Call Trace: update_persistent_clock64 sync_hw_clock

Fix this by dropping the __init annotation from set/get_rtc_noop().

Fixes: c311ed6183f4 ("x86/init: Allow DT configured systems to disable RTC at boot time") Signed-off-by: Matija Glavinic Pecotic matija.glavinic-pecotic.ext@nokia.com Signed-off-by: Thomas Gleixner tglx@linutronix.de Reviewed-by: Andy Shevchenko andriy.shevchenko@linux.intel.com Link: https://lore.kernel.org/r/59f7ceb1-446b-1d3d-0bc8-1f0ee94b1e18@nokia.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/kernel/x86_init.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index ef80d361b4632..10622cf2b30f4 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -33,8 +33,8 @@ static int __init iommu_init_noop(void) { return 0; } static void iommu_shutdown_noop(void) { } bool __init bool_x86_init_noop(void) { return false; } void x86_op_int_noop(int cpu) { } -static __init int set_rtc_noop(const struct timespec64 *now) { return -EINVAL; } -static __init void get_rtc_noop(struct timespec64 *now) { } +static int set_rtc_noop(const struct timespec64 *now) { return -EINVAL; } +static void get_rtc_noop(struct timespec64 *now) { }

static __initconst const struct of_device_id of_cmos_match[] = { { .compatible = "motorola,mc146818" },

From: David Disseldorp ddiss@suse.de

[ Upstream commit 5105a7ffce19160e7062aee67fb6b3b8a1b56d78 ]

smb311_decode_neg_context() doesn't properly check against SMB packet boundaries prior to accessing individual negotiate context entries. This is due to the length check omitting the eight byte smb2_neg_context header, as well as incorrect decrementing of len_of_ctxts.

Fixes: 5100d8a3fe03 ("SMB311: Improve checking of negotiate security contexts") Reported-by: Volker Lendecke vl@samba.org Reviewed-by: Paulo Alcantara (SUSE) pc@manguebit.com Signed-off-by: David Disseldorp ddiss@suse.de Signed-off-by: Steve French stfrench@microsoft.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/cifs/smb2pdu.c | 41 +++++++++++++++++++++++++++++++---------- 1 file changed, 31 insertions(+), 10 deletions(-)

diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index b37379b62cc77..ab59faf8a06a7 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -588,11 +588,15 @@ assemble_neg_contexts(struct smb2_negotiate_req *req,

}

+/* If invalid preauth context warn but use what we requested, SHA-512 */ static void decode_preauth_context(struct smb2_preauth_neg_context *ctxt) { unsigned int len = le16_to_cpu(ctxt->DataLength);

- /* If invalid preauth context warn but use what we requested, SHA-512 */ + /* + * Caller checked that DataLength remains within SMB boundary. We still + * need to confirm that one HashAlgorithms member is accounted for. + */ if (len < MIN_PREAUTH_CTXT_DATA_LEN) { pr_warn_once("server sent bad preauth context\n"); return; @@ -611,7 +615,11 @@ static void decode_compress_ctx(struct TCP_Server_Info *server, { unsigned int len = le16_to_cpu(ctxt->DataLength);

- /* sizeof compress context is a one element compression capbility struct */ + /* + * Caller checked that DataLength remains within SMB boundary. We still + * need to confirm that one CompressionAlgorithms member is accounted + * for. + */ if (len < 10) { pr_warn_once("server sent bad compression cntxt\n"); return; @@ -633,6 +641,11 @@ static int decode_encrypt_ctx(struct TCP_Server_Info *server, unsigned int len = le16_to_cpu(ctxt->DataLength);

cifs_dbg(FYI, "decode SMB3.11 encryption neg context of len %d\n", len); + /* + * Caller checked that DataLength remains within SMB boundary. We still + * need to confirm that one Cipher flexible array member is accounted + * for. + */ if (len < MIN_ENCRYPT_CTXT_DATA_LEN) { pr_warn_once("server sent bad crypto ctxt len\n"); return -EINVAL; @@ -679,6 +692,11 @@ static void decode_signing_ctx(struct TCP_Server_Info *server, { unsigned int len = le16_to_cpu(pctxt->DataLength);

+ /* + * Caller checked that DataLength remains within SMB boundary. We still + * need to confirm that one SigningAlgorithms flexible array member is + * accounted for. + */ if ((len < 4) || (len > 16)) { pr_warn_once("server sent bad signing negcontext\n"); return; @@ -720,14 +738,19 @@ static int smb311_decode_neg_context(struct smb2_negotiate_rsp *rsp, for (i = 0; i < ctxt_cnt; i++) { int clen; /* check that offset is not beyond end of SMB */ - if (len_of_ctxts == 0) - break; - if (len_of_ctxts < sizeof(struct smb2_neg_context)) break;

pctx = (struct smb2_neg_context *)(offset + (char *)rsp); - clen = le16_to_cpu(pctx->DataLength); + clen = sizeof(struct smb2_neg_context) + + le16_to_cpu(pctx->DataLength); + /* + * 2.2.4 SMB2 NEGOTIATE Response + * Subsequent negotiate contexts MUST appear at the first 8-byte + * aligned offset following the previous negotiate context. + */ + if (i + 1 != ctxt_cnt) + clen = ALIGN(clen, 8); if (clen > len_of_ctxts) break;

@@ -748,12 +771,10 @@ static int smb311_decode_neg_context(struct smb2_negotiate_rsp *rsp, else cifs_server_dbg(VFS, "unknown negcontext of type %d ignored\n", le16_to_cpu(pctx->ContextType)); - if (rc) break; - /* offsets must be 8 byte aligned */ - clen = ALIGN(clen, 8); - offset += clen + sizeof(struct smb2_neg_context); + + offset += clen; len_of_ctxts -= clen; } return rc;

From: Alyssa Ross hi@alyssa.is

[ Upstream commit d83806c4c0cccc0d6d3c3581a11983a9c186a138 ]

Since 32ef9e5054ec, -Wa,-gdwarf-2 is no longer used in KBUILD_AFLAGS. Instead, it includes -g, the appropriate -gdwarf-* flag, and also the -Wa versions of both of those if building with Clang and GNU as. As a result, debug info was being generated for the purgatory objects, even though the intention was that it not be.

Fixes: 32ef9e5054ec ("Makefile.debug: re-enable debug info for .S files") Signed-off-by: Alyssa Ross hi@alyssa.is Cc: stable@vger.kernel.org Acked-by: Nick Desaulniers ndesaulniers@google.com Signed-off-by: Masahiro Yamada masahiroy@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- arch/riscv/purgatory/Makefile | 7 +------ arch/x86/purgatory/Makefile | 3 +-- 2 files changed, 2 insertions(+), 8 deletions(-)

diff --git a/arch/riscv/purgatory/Makefile b/arch/riscv/purgatory/Makefile index d16bf715a586b..5730797a6b402 100644 --- a/arch/riscv/purgatory/Makefile +++ b/arch/riscv/purgatory/Makefile @@ -84,12 +84,7 @@ CFLAGS_string.o += $(PURGATORY_CFLAGS) CFLAGS_REMOVE_ctype.o += $(PURGATORY_CFLAGS_REMOVE) CFLAGS_ctype.o += $(PURGATORY_CFLAGS)

-AFLAGS_REMOVE_entry.o += -Wa,-gdwarf-2 -AFLAGS_REMOVE_memcpy.o += -Wa,-gdwarf-2 -AFLAGS_REMOVE_memset.o += -Wa,-gdwarf-2 -AFLAGS_REMOVE_strcmp.o += -Wa,-gdwarf-2 -AFLAGS_REMOVE_strlen.o += -Wa,-gdwarf-2 -AFLAGS_REMOVE_strncmp.o += -Wa,-gdwarf-2 +asflags-remove-y += $(foreach x, -g -gdwarf-4 -gdwarf-5, $(x) -Wa,$(x))

$(obj)/purgatory.ro: $(PURGATORY_OBJS) FORCE $(call if_changed,ld) diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile index 17f09dc263811..82fec66d46d29 100644 --- a/arch/x86/purgatory/Makefile +++ b/arch/x86/purgatory/Makefile @@ -69,8 +69,7 @@ CFLAGS_sha256.o += $(PURGATORY_CFLAGS) CFLAGS_REMOVE_string.o += $(PURGATORY_CFLAGS_REMOVE) CFLAGS_string.o += $(PURGATORY_CFLAGS)

-AFLAGS_REMOVE_setup-x86_$(BITS).o += -Wa,-gdwarf-2 -AFLAGS_REMOVE_entry64.o += -Wa,-gdwarf-2 +asflags-remove-y += $(foreach x, -g -gdwarf-4 -gdwarf-5, $(x) -Wa,$(x))

$(obj)/purgatory.ro: $(PURGATORY_OBJS) FORCE $(call if_changed,ld)

From: Duy Truong dory@dory.moe

[ Upstream commit 74391b3e69855e7dd65a9cef36baf5fc1345affd ]

Added a quirk to fix the TeamGroup T-Force Cardea Zero Z330 SSDs reporting duplicate NGUIDs.

Signed-off-by: Duy Truong dory@dory.moe Cc: stable@vger.kernel.org Signed-off-by: Christoph Hellwig hch@lst.de Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/nvme/host/pci.c | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 2e3fae6e1fb30..989f31471da69 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -3496,6 +3496,8 @@ static const struct pci_device_id nvme_id_table[] = { { PCI_DEVICE(0x1d97, 0x2269), /* Lexar NM760 */ .driver_data = NVME_QUIRK_BOGUS_NID | NVME_QUIRK_IGNORE_DEV_SUBNQN, }, + { PCI_DEVICE(0x10ec, 0x5763), /* TEAMGROUP T-FORCE CARDEA ZERO Z330 SSD */ + .driver_data = NVME_QUIRK_BOGUS_NID, }, { PCI_DEVICE(PCI_VENDOR_ID_AMAZON, 0x0061), .driver_data = NVME_QUIRK_DMA_ADDRESS_BITS_48, }, { PCI_DEVICE(PCI_VENDOR_ID_AMAZON, 0x0065),