From: Jarkko Sakkinen jarkko@kernel.org

commit e630af7dfb450d1c00c30077314acf33032ff9e4 upstream.

The earlier fix (linked) only partially fixed the locality handling bug in tpm_tis_gen_interrupt(), i.e. only for TPM 1.x.

Extend the locality handling to cover TPM2.

Cc: Hans de Goede hdegoede@redhat.com Cc: stable@vger.kernel.org Link: https://lore.kernel.org/linux-integrity/20210220125534.20707-1-jarkko@kernel... Fixes: a3fbfae82b4c ("tpm: take TPM chip power gating out of tpm_transmit()") Reported-by: Lino Sanfilippo LinoSanfilippo@gmx.de Signed-off-by: Jarkko Sakkinen jarkko@kernel.org Tested-by: Lino Sanfilippo LinoSanfilippo@gmx.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/char/tpm/tpm_tis_core.c | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-)

--- a/drivers/char/tpm/tpm_tis_core.c +++ b/drivers/char/tpm/tpm_tis_core.c @@ -620,16 +620,14 @@ static int tpm_tis_gen_interrupt(struct cap_t cap; int ret;

- /* TPM 2.0 */ - if (chip->flags & TPM_CHIP_FLAG_TPM2) - return tpm2_get_tpm_pt(chip, 0x100, &cap2, desc); - - /* TPM 1.2 */ ret = request_locality(chip, 0); if (ret < 0) return ret;

- ret = tpm1_getcap(chip, TPM_CAP_PROP_TIS_TIMEOUT, &cap, desc, 0); + if (chip->flags & TPM_CHIP_FLAG_TPM2) + ret = tpm2_get_tpm_pt(chip, 0x100, &cap2, desc); + else + ret = tpm1_getcap(chip, TPM_CAP_PROP_TIS_TIMEOUT, &cap, desc, 0);

release_locality(chip, 0);

From: Sean Christopherson seanjc@google.com

commit c5e2184d1544f9e56140791eff1a351bea2e63b9 upstream.

Remove the update_pte() shadow paging logic, which was obsoleted by commit 4731d4c7a077 ("KVM: MMU: out of sync shadow core"), but never removed. As pointed out by Yu, KVM never write protects leaf page tables for the purposes of shadow paging, and instead marks their associated shadow page as unsync so that the guest can write PTEs at will.

The update_pte() path, which predates the unsync logic, optimizes COW scenarios by refreshing leaf SPTEs when they are written, as opposed to zapping the SPTE, restarting the guest, and installing the new SPTE on the subsequent fault. Since KVM no longer write-protects leaf page tables, update_pte() is unreachable and can be dropped.

Reported-by: Yu Zhang yu.c.zhang@intel.com Signed-off-by: Sean Christopherson seanjc@google.com Message-Id: 20210115004051.4099250-1-seanjc@google.com Signed-off-by: Paolo Bonzini pbonzini@redhat.com (jwang: backport to 5.4 to fix a warning on AMD nested Virtualization) Signed-off-by: Jack Wang jinpu.wang@ionos.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/x86/include/asm/kvm_host.h | 3 --- arch/x86/kvm/mmu.c | 33 ++------------------------------- arch/x86/kvm/x86.c | 1 - 3 files changed, 2 insertions(+), 35 deletions(-)

--- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -391,8 +391,6 @@ struct kvm_mmu { int (*sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp); void (*invlpg)(struct kvm_vcpu *vcpu, gva_t gva, hpa_t root_hpa); - void (*update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, - u64 *spte, const void *pte); hpa_t root_hpa; gpa_t root_cr3; union kvm_mmu_role mmu_role; @@ -944,7 +942,6 @@ struct kvm_arch { struct kvm_vm_stat { ulong mmu_shadow_zapped; ulong mmu_pte_write; - ulong mmu_pte_updated; ulong mmu_pde_zapped; ulong mmu_flooded; ulong mmu_recycled; --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -2243,13 +2243,6 @@ static void nonpaging_invlpg(struct kvm_ { }

-static void nonpaging_update_pte(struct kvm_vcpu *vcpu, - struct kvm_mmu_page *sp, u64 *spte, - const void *pte) -{ - WARN_ON(1); -} - #define KVM_PAGE_ARRAY_NR 16

struct kvm_mmu_pages { @@ -4356,7 +4349,6 @@ static void nonpaging_init_context(struc context->gva_to_gpa = nonpaging_gva_to_gpa; context->sync_page = nonpaging_sync_page; context->invlpg = nonpaging_invlpg; - context->update_pte = nonpaging_update_pte; context->root_level = 0; context->shadow_root_level = PT32E_ROOT_LEVEL; context->direct_map = true; @@ -4935,7 +4927,6 @@ static void paging64_init_context_common context->gva_to_gpa = paging64_gva_to_gpa; context->sync_page = paging64_sync_page; context->invlpg = paging64_invlpg; - context->update_pte = paging64_update_pte; context->shadow_root_level = level; context->direct_map = false; } @@ -4964,7 +4955,6 @@ static void paging32_init_context(struct context->gva_to_gpa = paging32_gva_to_gpa; context->sync_page = paging32_sync_page; context->invlpg = paging32_invlpg; - context->update_pte = paging32_update_pte; context->shadow_root_level = PT32E_ROOT_LEVEL; context->direct_map = false; } @@ -5039,7 +5029,6 @@ static void init_kvm_tdp_mmu(struct kvm_ context->page_fault = tdp_page_fault; context->sync_page = nonpaging_sync_page; context->invlpg = nonpaging_invlpg; - context->update_pte = nonpaging_update_pte; context->shadow_root_level = kvm_x86_ops->get_tdp_level(vcpu); context->direct_map = true; context->set_cr3 = kvm_x86_ops->set_tdp_cr3; @@ -5172,7 +5161,6 @@ void kvm_init_shadow_ept_mmu(struct kvm_ context->gva_to_gpa = ept_gva_to_gpa; context->sync_page = ept_sync_page; context->invlpg = ept_invlpg; - context->update_pte = ept_update_pte; context->root_level = PT64_ROOT_4LEVEL; context->direct_map = false; context->mmu_role.as_u64 = new_role.as_u64; @@ -5312,19 +5300,6 @@ void kvm_mmu_unload(struct kvm_vcpu *vcp } EXPORT_SYMBOL_GPL(kvm_mmu_unload);

-static void mmu_pte_write_new_pte(struct kvm_vcpu *vcpu, - struct kvm_mmu_page *sp, u64 *spte, - const void *new) -{ - if (sp->role.level != PT_PAGE_TABLE_LEVEL) { - ++vcpu->kvm->stat.mmu_pde_zapped; - return; - } - - ++vcpu->kvm->stat.mmu_pte_updated; - vcpu->arch.mmu->update_pte(vcpu, sp, spte, new); -} - static bool need_remote_flush(u64 old, u64 new) { if (!is_shadow_present_pte(old)) @@ -5490,14 +5465,10 @@ static void kvm_mmu_pte_write(struct kvm

local_flush = true; while (npte--) { - u32 base_role = vcpu->arch.mmu->mmu_role.base.word; - entry = *spte; mmu_page_zap_pte(vcpu->kvm, sp, spte); - if (gentry && - !((sp->role.word ^ base_role) - & mmu_base_role_mask.word) && rmap_can_add(vcpu)) - mmu_pte_write_new_pte(vcpu, sp, spte, &gentry); + if (gentry && sp->role.level != PG_LEVEL_4K) + ++vcpu->kvm->stat.mmu_pde_zapped; if (need_remote_flush(entry, *spte)) remote_flush = true; ++spte; --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -208,7 +208,6 @@ struct kvm_stats_debugfs_item debugfs_en { "l1d_flush", VCPU_STAT(l1d_flush) }, { "mmu_shadow_zapped", VM_STAT(mmu_shadow_zapped) }, { "mmu_pte_write", VM_STAT(mmu_pte_write) }, - { "mmu_pte_updated", VM_STAT(mmu_pte_updated) }, { "mmu_pde_zapped", VM_STAT(mmu_pde_zapped) }, { "mmu_flooded", VM_STAT(mmu_flooded) }, { "mmu_recycled", VM_STAT(mmu_recycled) },

From: Alexander Aring aahringo@redhat.com

[ Upstream commit 92c48950b43f4a767388cf87709d8687151a641f ]

This patch fixes the following message which randomly pops up during glocktop call:

seq_file: buggy .next function table_seq_next did not update position index

The issue is that seq_read_iter() in fs/seq_file.c also needs an increment of the index in an non next record case as well which this patch fixes otherwise seq_read_iter() will print out the above message.

Signed-off-by: Alexander Aring aahringo@redhat.com Signed-off-by: David Teigland teigland@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/dlm/debug_fs.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/fs/dlm/debug_fs.c b/fs/dlm/debug_fs.c index d6bbccb0ed15..d5bd990bcab8 100644 --- a/fs/dlm/debug_fs.c +++ b/fs/dlm/debug_fs.c @@ -542,6 +542,7 @@ static void *table_seq_next(struct seq_file *seq, void *iter_ptr, loff_t *pos)

if (bucket >= ls->ls_rsbtbl_size) { kfree(ri); + ++*pos; return NULL; } tree = toss ? &ls->ls_rsbtbl[bucket].toss : &ls->ls_rsbtbl[bucket].keep;

From: Hans de Goede hdegoede@redhat.com

[ Upstream commit b7c7203a1f751348f35fc4bcb157572d303f7573 ]

The Asus T100TAF uses the same jack-detect settings as the T100TA, this has been confirmed on actual hardware.

Add these settings to the T100TAF quirks to enable jack-detect support on the T100TAF.

Signed-off-by: Hans de Goede hdegoede@redhat.com Acked-by: Pierre-Louis Bossart pierre-louis.bossart@linux.intel.com Link: https://lore.kernel.org/r/20210312114850.13832-1-hdegoede@redhat.com Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- sound/soc/intel/boards/bytcr_rt5640.c | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/sound/soc/intel/boards/bytcr_rt5640.c b/sound/soc/intel/boards/bytcr_rt5640.c index cfd307717473..006cf1e8b602 100644 --- a/sound/soc/intel/boards/bytcr_rt5640.c +++ b/sound/soc/intel/boards/bytcr_rt5640.c @@ -476,6 +476,9 @@ static const struct dmi_system_id byt_rt5640_quirk_table[] = { DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "T100TAF"), }, .driver_data = (void *)(BYT_RT5640_IN1_MAP | + BYT_RT5640_JD_SRC_JD2_IN4N | + BYT_RT5640_OVCD_TH_2000UA | + BYT_RT5640_OVCD_SF_0P75 | BYT_RT5640_MONO_SPEAKER | BYT_RT5640_DIFF_MIC | BYT_RT5640_SSP0_AIF2 |

From: Mikhail Durnev mikhail_durnev@mentor.com

[ Upstream commit 19c6a63ced5e07e40f3a5255cb1f0fe0d3be7b14 ]

snd_pcm_hw_params_set_rate_near can return incorrect sample rate in some cases, e.g. when the backend output rate is set to some value higher than 48000 Hz and the input rate is 8000 Hz. So passing the value returned by snd_pcm_hw_params_set_rate_near to snd_pcm_hw_params will result in "FSO/FSI ratio error" and playing no audio at all while the userland is not properly notified about the issue.

If SRC is unable to convert the requested sample rate to the sample rate the backend is using, then the requested sample rate should be adjusted in rsnd_hw_params. The userland will be notified about that change in the returned hw_params structure.

Signed-off-by: Mikhail Durnev mikhail_durnev@mentor.com Link: https://lore.kernel.org/r/1615870055-13954-1-git-send-email-mikhail_durnev@m... Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- sound/soc/sh/rcar/core.c | 69 +++++++++++++++++++++++++++++++++++++++- 1 file changed, 68 insertions(+), 1 deletion(-)

diff --git a/sound/soc/sh/rcar/core.c b/sound/soc/sh/rcar/core.c index a6c1cf987e6e..df8d7b53b760 100644 --- a/sound/soc/sh/rcar/core.c +++ b/sound/soc/sh/rcar/core.c @@ -1426,8 +1426,75 @@ static int rsnd_hw_params(struct snd_pcm_substream *substream, } if (io->converted_chan) dev_dbg(dev, "convert channels = %d\n", io->converted_chan); - if (io->converted_rate) + if (io->converted_rate) { + /* + * SRC supports convert rates from params_rate(hw_params)/k_down + * to params_rate(hw_params)*k_up, where k_up is always 6, and + * k_down depends on number of channels and SRC unit. + * So all SRC units can upsample audio up to 6 times regardless + * its number of channels. And all SRC units can downsample + * 2 channel audio up to 6 times too. + */ + int k_up = 6; + int k_down = 6; + int channel; + struct rsnd_mod *src_mod = rsnd_io_to_mod_src(io); + dev_dbg(dev, "convert rate = %d\n", io->converted_rate); + + channel = io->converted_chan ? io->converted_chan : + params_channels(hw_params); + + switch (rsnd_mod_id(src_mod)) { + /* + * SRC0 can downsample 4, 6 and 8 channel audio up to 4 times. + * SRC1, SRC3 and SRC4 can downsample 4 channel audio + * up to 4 times. + * SRC1, SRC3 and SRC4 can downsample 6 and 8 channel audio + * no more than twice. + */ + case 1: + case 3: + case 4: + if (channel > 4) { + k_down = 2; + break; + } + fallthrough; + case 0: + if (channel > 2) + k_down = 4; + break; + + /* Other SRC units do not support more than 2 channels */ + default: + if (channel > 2) + return -EINVAL; + } + + if (params_rate(hw_params) > io->converted_rate * k_down) { + hw_param_interval(hw_params, SNDRV_PCM_HW_PARAM_RATE)->min = + io->converted_rate * k_down; + hw_param_interval(hw_params, SNDRV_PCM_HW_PARAM_RATE)->max = + io->converted_rate * k_down; + hw_params->cmask |= SNDRV_PCM_HW_PARAM_RATE; + } else if (params_rate(hw_params) * k_up < io->converted_rate) { + hw_param_interval(hw_params, SNDRV_PCM_HW_PARAM_RATE)->min = + (io->converted_rate + k_up - 1) / k_up; + hw_param_interval(hw_params, SNDRV_PCM_HW_PARAM_RATE)->max = + (io->converted_rate + k_up - 1) / k_up; + hw_params->cmask |= SNDRV_PCM_HW_PARAM_RATE; + } + + /* + * TBD: Max SRC input and output rates also depend on number + * of channels and SRC unit: + * SRC1, SRC3 and SRC4 do not support more than 128kHz + * for 6 channel and 96kHz for 8 channel audio. + * Perhaps this function should return EINVAL if the input or + * the output rate exceeds the limitation. + */ + } }

ret = rsnd_dai_call(hw_params, io, substream, hw_params);

From: Tong Zhang ztong0001@gmail.com

[ Upstream commit 507cdb9adba006a7798c358456426e1aea3d9c4f ]

hdsp wants to disable a not enabled pci device, which makes kernel throw a warning. Make sure the device is enabled before calling disable.

[ 1.758292] snd_hdsp 0000:00:03.0: disabling already-disabled device [ 1.758327] WARNING: CPU: 0 PID: 180 at drivers/pci/pci.c:2146 pci_disable_device+0x91/0xb0 [ 1.766985] Call Trace: [ 1.767121] snd_hdsp_card_free+0x94/0xf0 [snd_hdsp] [ 1.767388] release_card_device+0x4b/0x80 [snd] [ 1.767639] device_release+0x3b/0xa0 [ 1.767838] kobject_put+0x94/0x1b0 [ 1.768027] put_device+0x13/0x20 [ 1.768207] snd_card_free+0x61/0x90 [snd] [ 1.768430] snd_hdsp_probe+0x524/0x5e0 [snd_hdsp]

Suggested-by: Takashi Iwai tiwai@suse.de Signed-off-by: Tong Zhang ztong0001@gmail.com Link: https://lore.kernel.org/r/20210321153840.378226-2-ztong0001@gmail.com Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Sasha Levin sashal@kernel.org --- sound/pci/rme9652/hdsp.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/sound/pci/rme9652/hdsp.c b/sound/pci/rme9652/hdsp.c index 5cbdc9be9c7e..c7b3e76ea2d2 100644 --- a/sound/pci/rme9652/hdsp.c +++ b/sound/pci/rme9652/hdsp.c @@ -5326,7 +5326,8 @@ static int snd_hdsp_free(struct hdsp *hdsp) if (hdsp->port) pci_release_regions(hdsp->pci);

- pci_disable_device(hdsp->pci); + if (pci_is_enabled(hdsp->pci)) + pci_disable_device(hdsp->pci); return 0; }

From: Tong Zhang ztong0001@gmail.com

[ Upstream commit f57a741874bb6995089020e97a1dcdf9b165dcbe ]

rme9652 wants to disable a not enabled pci device, which makes kernel throw a warning. Make sure the device is enabled before calling disable.

[ 1.751595] snd_rme9652 0000:00:03.0: disabling already-disabled device [ 1.751605] WARNING: CPU: 0 PID: 174 at drivers/pci/pci.c:2146 pci_disable_device+0x91/0xb0 [ 1.759968] Call Trace: [ 1.760145] snd_rme9652_card_free+0x76/0xa0 [snd_rme9652] [ 1.760434] release_card_device+0x4b/0x80 [snd] [ 1.760679] device_release+0x3b/0xa0 [ 1.760874] kobject_put+0x94/0x1b0 [ 1.761059] put_device+0x13/0x20 [ 1.761235] snd_card_free+0x61/0x90 [snd] [ 1.761454] snd_rme9652_probe+0x3be/0x700 [snd_rme9652]

Suggested-by: Takashi Iwai tiwai@suse.de Signed-off-by: Tong Zhang ztong0001@gmail.com Link: https://lore.kernel.org/r/20210321153840.378226-4-ztong0001@gmail.com Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Sasha Levin sashal@kernel.org --- sound/pci/rme9652/rme9652.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/sound/pci/rme9652/rme9652.c b/sound/pci/rme9652/rme9652.c index 4c851f8dcaf8..73ad6e74aac9 100644 --- a/sound/pci/rme9652/rme9652.c +++ b/sound/pci/rme9652/rme9652.c @@ -1745,7 +1745,8 @@ static int snd_rme9652_free(struct snd_rme9652 *rme9652) if (rme9652->port) pci_release_regions(rme9652->pci);

- pci_disable_device(rme9652->pci); + if (pci_is_enabled(rme9652->pci)) + pci_disable_device(rme9652->pci); return 0; }

From: Archie Pusaka apusaka@chromium.org

[ Upstream commit 3a9d54b1947ecea8eea9a902c0b7eb58a98add8a ]

Currently l2cap_chan_set_defaults() reset chan->conf_state to zero. However, there is a flag CONF_NOT_COMPLETE which is set when creating the l2cap_chan. It is suggested that the flag should be cleared when l2cap_chan is ready, but when l2cap_chan_set_defaults() is called, l2cap_chan is not yet ready. Therefore, we must set this flag as the default.

Example crash call trace: __dump_stack lib/dump_stack.c:15 [inline] dump_stack+0xc4/0x118 lib/dump_stack.c:56 panic+0x1c6/0x38b kernel/panic.c:117 __warn+0x170/0x1b9 kernel/panic.c:471 warn_slowpath_fmt+0xc7/0xf8 kernel/panic.c:494 debug_print_object+0x175/0x193 lib/debugobjects.c:260 debug_object_assert_init+0x171/0x1bf lib/debugobjects.c:614 debug_timer_assert_init kernel/time/timer.c:629 [inline] debug_assert_init kernel/time/timer.c:677 [inline] del_timer+0x7c/0x179 kernel/time/timer.c:1034 try_to_grab_pending+0x81/0x2e5 kernel/workqueue.c:1230 cancel_delayed_work+0x7c/0x1c4 kernel/workqueue.c:2929 l2cap_clear_timer+0x1e/0x41 include/net/bluetooth/l2cap.h:834 l2cap_chan_del+0x2d8/0x37e net/bluetooth/l2cap_core.c:640 l2cap_chan_close+0x532/0x5d8 net/bluetooth/l2cap_core.c:756 l2cap_sock_shutdown+0x806/0x969 net/bluetooth/l2cap_sock.c:1174 l2cap_sock_release+0x64/0x14d net/bluetooth/l2cap_sock.c:1217 __sock_release+0xda/0x217 net/socket.c:580 sock_close+0x1b/0x1f net/socket.c:1039 __fput+0x322/0x55c fs/file_table.c:208 ____fput+0x17/0x19 fs/file_table.c:244 task_work_run+0x19b/0x1d3 kernel/task_work.c:115 exit_task_work include/linux/task_work.h:21 [inline] do_exit+0xe4c/0x204a kernel/exit.c:766 do_group_exit+0x291/0x291 kernel/exit.c:891 get_signal+0x749/0x1093 kernel/signal.c:2396 do_signal+0xa5/0xcdb arch/x86/kernel/signal.c:737 exit_to_usermode_loop arch/x86/entry/common.c:243 [inline] prepare_exit_to_usermode+0xed/0x235 arch/x86/entry/common.c:277 syscall_return_slowpath+0x3a7/0x3b3 arch/x86/entry/common.c:348 int_ret_from_sys_call+0x25/0xa3

Signed-off-by: Archie Pusaka apusaka@chromium.org Reported-by: syzbot+338f014a98367a08a114@syzkaller.appspotmail.com Reviewed-by: Alain Michaud alainm@chromium.org Reviewed-by: Abhishek Pandit-Subedi abhishekpandit@chromium.org Reviewed-by: Guenter Roeck groeck@chromium.org Signed-off-by: Marcel Holtmann marcel@holtmann.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/bluetooth/l2cap_core.c | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 3499bace25ec..f5039700d927 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -515,7 +515,9 @@ void l2cap_chan_set_defaults(struct l2cap_chan *chan) chan->flush_to = L2CAP_DEFAULT_FLUSH_TO; chan->retrans_timeout = L2CAP_DEFAULT_RETRANS_TO; chan->monitor_timeout = L2CAP_DEFAULT_MONITOR_TO; + chan->conf_state = 0; + set_bit(CONF_NOT_COMPLETE, &chan->conf_state);

set_bit(FLAG_FORCE_ACTIVE, &chan->flags); }

From: Nikolay Aleksandrov nikolay@nvidia.com

[ Upstream commit 0353b4a96b7a9f60fe20d1b3ebd4931a4085f91c ]

Recently we had an interop issue where RARP packets got suppressed with bridge neigh suppression enabled, but the check in the code was meant to suppress GARP. Exclude RARP packets from it which would allow some VMWare setups to work, to quote the report: "Those RARP packets usually get generated by vMware to notify physical switches when vMotion occurs. vMware may use random sip/tip or just use sip=tip=0. So the RARP packet sometimes get properly flooded by the vtep and other times get dropped by the logic"

Reported-by: Amer Abdalamer amer@nvidia.com Signed-off-by: Nikolay Aleksandrov nikolay@nvidia.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/bridge/br_arp_nd_proxy.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/bridge/br_arp_nd_proxy.c b/net/bridge/br_arp_nd_proxy.c index b18cdf03edb3..c4e0f4777df5 100644 --- a/net/bridge/br_arp_nd_proxy.c +++ b/net/bridge/br_arp_nd_proxy.c @@ -155,7 +155,9 @@ void br_do_proxy_suppress_arp(struct sk_buff *skb, struct net_bridge *br, if (br_opt_get(br, BROPT_NEIGH_SUPPRESS_ENABLED)) { if (p && (p->flags & BR_NEIGH_SUPPRESS)) return; - if (ipv4_is_zeronet(sip) || sip == tip) { + if (parp->ar_op != htons(ARPOP_RREQUEST) && + parp->ar_op != htons(ARPOP_RREPLY) && + (ipv4_is_zeronet(sip) || sip == tip)) { /* prevent flooding to neigh suppress ports */ BR_INPUT_SKB_CB(skb)->proxyarp_replied = 1; return;

From: Eric Dumazet edumazet@google.com

[ Upstream commit 40cb881b5aaa0b69a7d93dec8440d5c62dae299f ]

After adopting CONFIG_PCPU_DEV_REFCNT=n option, syzbot was able to trigger a warning [1]

Issue here is that:

- all dev_put() should be paired with a corresponding prior dev_hold().

- A driver doing a dev_put() in its ndo_uninit() MUST also do a dev_hold() in its ndo_init(), only when ndo_init() is returning 0.

Otherwise, register_netdevice() would call ndo_uninit() in its error path and release a refcount too soon.

Therefore, we need to move dev_hold() call from vti6_tnl_create2() to vti6_dev_init_gen()

[1] WARNING: CPU: 0 PID: 15951 at lib/refcount.c:31 refcount_warn_saturate+0xbf/0x1e0 lib/refcount.c:31 Modules linked in: CPU: 0 PID: 15951 Comm: syz-executor.3 Not tainted 5.12.0-rc4-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 RIP: 0010:refcount_warn_saturate+0xbf/0x1e0 lib/refcount.c:31 Code: 1d 6a 5a e8 09 31 ff 89 de e8 8d 1a ab fd 84 db 75 e0 e8 d4 13 ab fd 48 c7 c7 a0 e1 c1 89 c6 05 4a 5a e8 09 01 e8 2e 36 fb 04 <0f> 0b eb c4 e8 b8 13 ab fd 0f b6 1d 39 5a e8 09 31 ff 89 de e8 58 RSP: 0018:ffffc90001eaef28 EFLAGS: 00010282 RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000000 RDX: 0000000000040000 RSI: ffffffff815c51f5 RDI: fffff520003d5dd7 RBP: 0000000000000004 R08: 0000000000000000 R09: 0000000000000000 R10: ffffffff815bdf8e R11: 0000000000000000 R12: ffff88801bb1c568 R13: ffff88801f69e800 R14: 00000000ffffffff R15: ffff888050889d40 FS: 00007fc79314e700(0000) GS:ffff8880b9c00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f1c1ff47108 CR3: 0000000020fd5000 CR4: 00000000001506f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: __refcount_dec include/linux/refcount.h:344 [inline] refcount_dec include/linux/refcount.h:359 [inline] dev_put include/linux/netdevice.h:4135 [inline] vti6_dev_uninit+0x31a/0x360 net/ipv6/ip6_vti.c:297 register_netdevice+0xadf/0x1500 net/core/dev.c:10308 vti6_tnl_create2+0x1b5/0x400 net/ipv6/ip6_vti.c:190 vti6_newlink+0x9d/0xd0 net/ipv6/ip6_vti.c:1020 __rtnl_newlink+0x1062/0x1710 net/core/rtnetlink.c:3443 rtnl_newlink+0x64/0xa0 net/core/rtnetlink.c:3491 rtnetlink_rcv_msg+0x44e/0xad0 net/core/rtnetlink.c:5553 netlink_rcv_skb+0x153/0x420 net/netlink/af_netlink.c:2502 netlink_unicast_kernel net/netlink/af_netlink.c:1312 [inline] netlink_unicast+0x533/0x7d0 net/netlink/af_netlink.c:1338 netlink_sendmsg+0x856/0xd90 net/netlink/af_netlink.c:1927 sock_sendmsg_nosec net/socket.c:654 [inline] sock_sendmsg+0xcf/0x120 net/socket.c:674 ____sys_sendmsg+0x331/0x810 net/socket.c:2350 ___sys_sendmsg+0xf3/0x170 net/socket.c:2404 __sys_sendmmsg+0x195/0x470 net/socket.c:2490 __do_sys_sendmmsg net/socket.c:2519 [inline] __se_sys_sendmmsg net/socket.c:2516 [inline] __x64_sys_sendmmsg+0x99/0x100 net/socket.c:2516

Signed-off-by: Eric Dumazet edumazet@google.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/ipv6/ip6_vti.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index cc6180e08a4f..01ddb0f70c57 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -192,7 +192,6 @@ static int vti6_tnl_create2(struct net_device *dev)

strcpy(t->parms.name, dev->name);

- dev_hold(dev); vti6_tnl_link(ip6n, t);

return 0; @@ -921,6 +920,7 @@ static inline int vti6_dev_init_gen(struct net_device *dev) dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); if (!dev->tstats) return -ENOMEM; + dev_hold(dev); return 0; }

From: Bence Csókás bence98@sch.bme.hu

[ Upstream commit aca01415e076aa96cca0f801f4420ee5c10c660d ]

This quirk signifies that the adapter cannot do a repeated START, it always issues a STOP condition after transfers.

Suggested-by: Wolfram Sang wsa@kernel.org Signed-off-by: Bence Csókás bence98@sch.bme.hu Signed-off-by: Wolfram Sang wsa@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- include/linux/i2c.h | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 1361637c369d..af2b799d7a66 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -677,6 +677,8 @@ struct i2c_adapter_quirks { #define I2C_AQ_NO_ZERO_LEN_READ BIT(5) #define I2C_AQ_NO_ZERO_LEN_WRITE BIT(6) #define I2C_AQ_NO_ZERO_LEN (I2C_AQ_NO_ZERO_LEN_READ | I2C_AQ_NO_ZERO_LEN_WRITE) +/* adapter cannot do repeated START */ +#define I2C_AQ_NO_REP_START BIT(7)

/* * i2c_adapter is the structure used to identify a physical i2c bus along

From: Krzysztof Kozlowski krzysztof.kozlowski@canonical.com

[ Upstream commit fa0c10a5f3a49130dd11281aa27e7e1c8654abc7 ]

The Special Function Registers on all Exynos SoC, including ARM64, are 32-bit wide, so entire driver uses matching functions like readl() or writel(). On 64-bit ARM using unsigned long for register masks: 1. makes little sense as immediately after bitwise operation it will be cast to 32-bit value when calling writel(), 2. is actually error-prone because it might promote other operands to 64-bit.

Addresses-Coverity: Unintentional integer overflow Signed-off-by: Krzysztof Kozlowski krzysztof.kozlowski@canonical.com Reviewed-by: Sylwester Nawrocki s.nawrocki@samsung.com Link: https://lore.kernel.org/r/20210408195029.69974-1-krzysztof.kozlowski@canonic... Signed-off-by: Linus Walleij linus.walleij@linaro.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/pinctrl/samsung/pinctrl-exynos.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/pinctrl/samsung/pinctrl-exynos.c b/drivers/pinctrl/samsung/pinctrl-exynos.c index 84501c785473..1cf31fe2674d 100644 --- a/drivers/pinctrl/samsung/pinctrl-exynos.c +++ b/drivers/pinctrl/samsung/pinctrl-exynos.c @@ -55,7 +55,7 @@ static void exynos_irq_mask(struct irq_data *irqd) struct exynos_irq_chip *our_chip = to_exynos_irq_chip(chip); struct samsung_pin_bank *bank = irq_data_get_irq_chip_data(irqd); unsigned long reg_mask = our_chip->eint_mask + bank->eint_offset; - unsigned long mask; + unsigned int mask; unsigned long flags;

spin_lock_irqsave(&bank->slock, flags); @@ -83,7 +83,7 @@ static void exynos_irq_unmask(struct irq_data *irqd) struct exynos_irq_chip *our_chip = to_exynos_irq_chip(chip); struct samsung_pin_bank *bank = irq_data_get_irq_chip_data(irqd); unsigned long reg_mask = our_chip->eint_mask + bank->eint_offset; - unsigned long mask; + unsigned int mask; unsigned long flags;

/* @@ -474,7 +474,7 @@ static void exynos_irq_eint0_15(struct irq_desc *desc) chained_irq_exit(chip, desc); }

-static inline void exynos_irq_demux_eint(unsigned long pend, +static inline void exynos_irq_demux_eint(unsigned int pend, struct irq_domain *domain) { unsigned int irq; @@ -491,8 +491,8 @@ static void exynos_irq_demux_eint16_31(struct irq_desc *desc) { struct irq_chip *chip = irq_desc_get_chip(desc); struct exynos_muxed_weint_data *eintd = irq_desc_get_handler_data(desc); - unsigned long pend; - unsigned long mask; + unsigned int pend; + unsigned int mask; int i;

chained_irq_enter(chip, desc);

From: Miklos Szeredi mszeredi@redhat.com

[ Upstream commit 8217673d07256b22881127bf50dce874d0e51653 ]

For cloned connections cuse_channel_release() will be called more than once, resulting in use after free.

Prevent device cloning for CUSE, which does not make sense at this point, and highly unlikely to be used in real life.

Signed-off-by: Miklos Szeredi mszeredi@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/fuse/cuse.c | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/fs/fuse/cuse.c b/fs/fuse/cuse.c index 00015d851382..e51b7019e887 100644 --- a/fs/fuse/cuse.c +++ b/fs/fuse/cuse.c @@ -624,6 +624,8 @@ static int __init cuse_init(void) cuse_channel_fops.owner = THIS_MODULE; cuse_channel_fops.open = cuse_channel_open; cuse_channel_fops.release = cuse_channel_release; + /* CUSE is not prepared for FUSE_DEV_IOC_CLONE */ + cuse_channel_fops.unlocked_ioctl = NULL;

cuse_class = class_create(THIS_MODULE, "cuse"); if (IS_ERR(cuse_class))

From: Paul Menzel pmenzel@molgen.mpg.de

[ Upstream commit 715601e4e36903a653cd4294dfd3ed0019101991 ]

This reverts commit 6778ff5b21bd8e78c8bd547fd66437cf2657fd9b.

The original commit tries to address an issue, where PMC power-gating causing the IOMMU PMC pre-init test to fail on certain desktop/mobile platforms where the power-gating is normally enabled.

There have been several reports that the workaround still does not guarantee to work, and can add up to 100 ms (on the worst case) to the boot process on certain platforms such as the MSI B350M MORTAR with AMD Ryzen 3 2200G.

Therefore, revert this commit as a prelude to removing the pre-init test.

Link: https://lore.kernel.org/linux-iommu/alpine.LNX.3.20.13.2006030935570.3181@mo... Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=201753 Cc: Tj (Elloe Linux) ml.linux@elloe.vision Cc: Shuah Khan skhan@linuxfoundation.org Cc: Alexander Monakov amonakov@ispras.ru Cc: David Coe david.coe@live.co.uk Signed-off-by: Paul Menzel pmenzel@molgen.mpg.de Signed-off-by: Suravee Suthikulpanit suravee.suthikulpanit@amd.com Link: https://lore.kernel.org/r/20210409085848.3908-2-suravee.suthikulpanit@amd.co... Signed-off-by: Joerg Roedel jroedel@suse.de Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/iommu/amd_iommu_init.c | 45 +++++++++------------------------- 1 file changed, 11 insertions(+), 34 deletions(-)

diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c index ad714ff375f8..31d7e2d4f304 100644 --- a/drivers/iommu/amd_iommu_init.c +++ b/drivers/iommu/amd_iommu_init.c @@ -12,7 +12,6 @@ #include <linux/acpi.h> #include <linux/list.h> #include <linux/bitmap.h> -#include <linux/delay.h> #include <linux/slab.h> #include <linux/syscore_ops.h> #include <linux/interrupt.h> @@ -254,8 +253,6 @@ static enum iommu_init_state init_state = IOMMU_START_STATE; static int amd_iommu_enable_interrupts(void); static int __init iommu_go_to_state(enum iommu_init_state state); static void init_device_table_dma(void); -static int iommu_pc_get_set_reg(struct amd_iommu *iommu, u8 bank, u8 cntr, - u8 fxn, u64 *value, bool is_write);

static bool amd_iommu_pre_enabled = true;

@@ -1675,11 +1672,13 @@ static int __init init_iommu_all(struct acpi_table_header *table) return 0; }

-static void __init init_iommu_perf_ctr(struct amd_iommu *iommu) +static int iommu_pc_get_set_reg(struct amd_iommu *iommu, u8 bank, u8 cntr, + u8 fxn, u64 *value, bool is_write); + +static void init_iommu_perf_ctr(struct amd_iommu *iommu) { - int retry; struct pci_dev *pdev = iommu->dev; - u64 val = 0xabcd, val2 = 0, save_reg, save_src; + u64 val = 0xabcd, val2 = 0, save_reg = 0;

if (!iommu_feature(iommu, FEATURE_PC)) return; @@ -1687,39 +1686,17 @@ static void __init init_iommu_perf_ctr(struct amd_iommu *iommu) amd_iommu_pc_present = true;

/* save the value to restore, if writable */ - if (iommu_pc_get_set_reg(iommu, 0, 0, 0, &save_reg, false) || - iommu_pc_get_set_reg(iommu, 0, 0, 8, &save_src, false)) - goto pc_false; - - /* - * Disable power gating by programing the performance counter - * source to 20 (i.e. counts the reads and writes from/to IOMMU - * Reserved Register [MMIO Offset 1FF8h] that are ignored.), - * which never get incremented during this init phase. - * (Note: The event is also deprecated.) - */ - val = 20; - if (iommu_pc_get_set_reg(iommu, 0, 0, 8, &val, true)) + if (iommu_pc_get_set_reg(iommu, 0, 0, 0, &save_reg, false)) goto pc_false;

/* Check if the performance counters can be written to */ - val = 0xabcd; - for (retry = 5; retry; retry--) { - if (iommu_pc_get_set_reg(iommu, 0, 0, 0, &val, true) || - iommu_pc_get_set_reg(iommu, 0, 0, 0, &val2, false) || - val2) - break; - - /* Wait about 20 msec for power gating to disable and retry. */ - msleep(20); - } - - /* restore */ - if (iommu_pc_get_set_reg(iommu, 0, 0, 0, &save_reg, true) || - iommu_pc_get_set_reg(iommu, 0, 0, 8, &save_src, true)) + if ((iommu_pc_get_set_reg(iommu, 0, 0, 0, &val, true)) || + (iommu_pc_get_set_reg(iommu, 0, 0, 0, &val2, false)) || + (val != val2)) goto pc_false;

- if (val != val2) + /* restore */ + if (iommu_pc_get_set_reg(iommu, 0, 0, 0, &save_reg, true)) goto pc_false;

pci_info(pdev, "IOMMU performance counters supported\n");

From: Anthony Wang anthony1.wang@amd.com

[ Upstream commit 56d63782af9bbd1271bff1422a6a013123eade4d ]

[Why] Underflow observed when disabling PIP overlay in-game when vsync is disabled, due to OTC master lock not working with game pipe which is immediate flip.

[How] When performing a full update, override flip_immediate value to false for all planes, so that flip occurs on vsync.

Signed-off-by: Anthony Wang anthony1.wang@amd.com Acked-by: Bindu Ramamurthy bindur12@amd.com Tested-by: Daniel Wheeler daniel.wheeler@amd.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/amd/display/dc/core/dc.c | 4 ++++ 1 file changed, 4 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index 092db590087c..14dc1b8719a9 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -2050,6 +2050,10 @@ static void commit_planes_for_stream(struct dc *dc, plane_state->triplebuffer_flips = true; } } + if (update_type == UPDATE_TYPE_FULL) { + /* force vsync flip when reconfiguring pipes to prevent underflow */ + plane_state->flip_immediate = false; + } } } #endif

From: Mihai Moldovan ionic@ionic.de

[ Upstream commit 8c94b430b9f6213dec84e309bb480a71778c4213 ]

If the user selects the very first entry in a page and performs a search-up operation, or selects the very last entry in a page and performs a search-down operation that will not succeed (e.g., via [/]asdfzzz[Up Arrow]), nconf will never terminate searching the page.

The reason is that in this case, the starting point will be set to -1 or n, which is then translated into (n - 1) (i.e., the last entry of the page) or 0 (i.e., the first entry of the page) and finally the search begins. This continues to work fine until the index reaches 0 or (n - 1), at which point it will be decremented to -1 or incremented to n, but not checked against the starting point right away. Instead, it's wrapped around to the bottom or top again, after which the starting point check occurs... and naturally fails.

My original implementation added another check for -1 before wrapping the running index variable around, but Masahiro Yamada pointed out that the actual issue is that the comparison point (starting point) exceeds bounds (i.e., the [0,n-1] interval) in the first place and that, instead, the starting point should be fixed.

This has the welcome side-effect of also fixing the case where the starting point was n while searching down, which also lead to an infinite loop.

OTOH, this code is now essentially all his work.

Amazingly, nobody seems to have been hit by this for 11 years - or at the very least nobody bothered to debug and fix this.

Signed-off-by: Mihai Moldovan ionic@ionic.de Signed-off-by: Masahiro Yamada masahiroy@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- scripts/kconfig/nconf.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/scripts/kconfig/nconf.c b/scripts/kconfig/nconf.c index b7c1ef757178..331b2cc917ec 100644 --- a/scripts/kconfig/nconf.c +++ b/scripts/kconfig/nconf.c @@ -503,8 +503,8 @@ static int get_mext_match(const char *match_str, match_f flag) else if (flag == FIND_NEXT_MATCH_UP) --match_start;

+ match_start = (match_start + items_num) % items_num; index = match_start; - index = (index + items_num) % items_num; while (true) { char *str = k_menu_items[index].str; if (strcasestr(str, match_str) != NULL)

From: Gustavo A. R. Silva gustavoars@kernel.org

[ Upstream commit e5272ad4aab347dde5610c0aedb786219e3ff793 ]

Fix the following out-of-bounds warning:

net/sctp/sm_make_chunk.c:3150:4: warning: 'memcpy' offset [17, 28] from the object at 'addr' is out of the bounds of referenced subobject 'v4' with type 'struct sockaddr_in' at offset 0 [-Warray-bounds]

This helps with the ongoing efforts to globally enable -Warray-bounds and get us closer to being able to tighten the FORTIFY_SOURCE routines on memcpy().

Link: https://github.com/KSPP/linux/issues/109 Reported-by: kernel test robot lkp@intel.com Signed-off-by: Gustavo A. R. Silva gustavoars@kernel.org Reviewed-by: Kees Cook keescook@chromium.org Acked-by: Marcelo Ricardo Leitner marcelo.leitner@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/sctp/sm_make_chunk.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index d5eda966a706..4ffb9116b6f2 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -3134,7 +3134,7 @@ static __be16 sctp_process_asconf_param(struct sctp_association *asoc, * primary. */ if (af->is_any(&addr)) - memcpy(&addr.v4, sctp_source(asconf), sizeof(addr)); + memcpy(&addr, sctp_source(asconf), sizeof(addr));

if (security_sctp_bind_connect(asoc->ep->base.sk, SCTP_PARAM_SET_PRIMARY,

From: Srikar Dronamraju srikar@linux.vnet.ibm.com

[ Upstream commit 6980d13f0dd189846887bbbfa43793d9a41768d3 ]

Geethika reported a trace when doing a dlpar CPU add.

------------[ cut here ]------------ WARNING: CPU: 152 PID: 1134 at kernel/sched/topology.c:2057 CPU: 152 PID: 1134 Comm: kworker/152:1 Not tainted 5.12.0-rc5-master #5 Workqueue: events cpuset_hotplug_workfn NIP: c0000000001cfc14 LR: c0000000001cfc10 CTR: c0000000007e3420 REGS: c0000034a08eb260 TRAP: 0700 Not tainted (5.12.0-rc5-master+) MSR: 8000000000029033 <SF,EE,ME,IR,DR,RI,LE> CR: 28828422 XER: 00000020 CFAR: c0000000001fd888 IRQMASK: 0 #012GPR00: c0000000001cfc10 c0000034a08eb500 c000000001f35400 0000000000000027 #012GPR04: c0000035abaa8010 c0000035abb30a00 0000000000000027 c0000035abaa8018 #012GPR08: 0000000000000023 c0000035abaaef48 00000035aa540000 c0000035a49dffe8 #012GPR12: 0000000028828424 c0000035bf1a1c80 0000000000000497 0000000000000004 #012GPR16: c00000000347a258 0000000000000140 c00000000203d468 c000000001a1a490 #012GPR20: c000000001f9c160 c0000034adf70920 c0000034aec9fd20 0000000100087bd3 #012GPR24: 0000000100087bd3 c0000035b3de09f8 0000000000000030 c0000035b3de09f8 #012GPR28: 0000000000000028 c00000000347a280 c0000034aefe0b00 c0000000010a2a68 NIP [c0000000001cfc14] build_sched_domains+0x6a4/0x1500 LR [c0000000001cfc10] build_sched_domains+0x6a0/0x1500 Call Trace: [c0000034a08eb500] [c0000000001cfc10] build_sched_domains+0x6a0/0x1500 (unreliable) [c0000034a08eb640] [c0000000001d1e6c] partition_sched_domains_locked+0x3ec/0x530 [c0000034a08eb6e0] [c0000000002936d4] rebuild_sched_domains_locked+0x524/0xbf0 [c0000034a08eb7e0] [c000000000296bb0] rebuild_sched_domains+0x40/0x70 [c0000034a08eb810] [c000000000296e74] cpuset_hotplug_workfn+0x294/0xe20 [c0000034a08ebc30] [c000000000178dd0] process_one_work+0x300/0x670 [c0000034a08ebd10] [c0000000001791b8] worker_thread+0x78/0x520 [c0000034a08ebda0] [c000000000185090] kthread+0x1a0/0x1b0 [c0000034a08ebe10] [c00000000000ccec] ret_from_kernel_thread+0x5c/0x70 Instruction dump: 7d2903a6 4e800421 e8410018 7f67db78 7fe6fb78 7f45d378 7f84e378 7c681b78 3c62ff1a 3863c6f8 4802dc35 60000000 <0fe00000> 3920fff4 f9210070 e86100a0 ---[ end trace 532d9066d3d4d7ec ]---

Some of the per-CPU masks use cpu_cpu_mask as a filter to limit the search for related CPUs. On a dlpar add of a CPU, update cpu_cpu_mask before updating the per-CPU masks. This will ensure the cpu_cpu_mask is updated correctly before its used in setting the masks. Setting the numa_node will ensure that when cpu_cpu_mask() gets called, the correct node number is used. This code movement helped fix the above call trace.

Reported-by: Geetika Moolchandani Geetika.Moolchandani1@ibm.com Signed-off-by: Srikar Dronamraju srikar@linux.vnet.ibm.com Reviewed-by: Nathan Lynch nathanl@linux.ibm.com Signed-off-by: Michael Ellerman mpe@ellerman.id.au Link: https://lore.kernel.org/r/20210401154200.150077-1-srikar@linux.vnet.ibm.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/powerpc/kernel/smp.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index ea6adbf6a221..b24d860bbab9 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -1254,6 +1254,9 @@ void start_secondary(void *unused)

vdso_getcpu_init(); #endif + set_numa_node(numa_cpu_lookup_table[cpu]); + set_numa_mem(local_memory_node(numa_cpu_lookup_table[cpu])); + /* Update topology CPU masks */ add_cpu_to_masks(cpu);

@@ -1266,9 +1269,6 @@ void start_secondary(void *unused) if (!cpumask_equal(cpu_l2_cache_mask(cpu), sibling_mask(cpu))) shared_caches = true;

- set_numa_node(numa_cpu_lookup_table[cpu]); - set_numa_mem(local_memory_node(numa_cpu_lookup_table[cpu])); - smp_wmb(); notify_cpu_starting(cpu); set_cpu_online(cpu, true);

From: Gustavo A. R. Silva gustavoars@kernel.org

[ Upstream commit c1d9e34e11281a8ba1a1c54e4db554232a461488 ]

Fix the following out-of-bounds warning:

net/ethtool/ioctl.c:492:2: warning: 'memcpy' offset [49, 84] from the object at 'link_usettings' is out of the bounds of referenced subobject 'base' with type 'struct ethtool_link_settings' at offset 0 [-Warray-bounds]

The problem is that the original code is trying to copy data into a some struct members adjacent to each other in a single call to memcpy(). This causes a legitimate compiler warning because memcpy() overruns the length of &link_usettings.base. Fix this by directly using &link_usettings and _from_ as destination and source addresses, instead.

This helps with the ongoing efforts to globally enable -Warray-bounds and get us closer to being able to tighten the FORTIFY_SOURCE routines on memcpy().

Link: https://github.com/KSPP/linux/issues/109 Reported-by: kernel test robot lkp@intel.com Signed-off-by: Gustavo A. R. Silva gustavoars@kernel.org Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/core/ethtool.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/ethtool.c b/net/core/ethtool.c index cd9bc67381b2..76506975d59a 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -589,7 +589,7 @@ store_link_ksettings_for_user(void __user *to, { struct ethtool_link_usettings link_usettings;

- memcpy(&link_usettings.base, &from->base, sizeof(link_usettings)); + memcpy(&link_usettings, from, sizeof(link_usettings)); bitmap_to_arr32(link_usettings.link_modes.supported, from->link_modes.supported, __ETHTOOL_LINK_MODE_MASK_NBITS);

From: Yaqi Chen chendotjs@gmail.com

[ Upstream commit 137733d08f4ab14a354dacaa9a8fc35217747605 ]

From commit c0bbbdc32feb ("__netif_receive_skb_core: pass skb by

reference"), the first argument passed into __netif_receive_skb_core has changed to reference of a skb pointer.

This commit fixes by using bpf_probe_read_kernel.

Signed-off-by: Yaqi Chen chendotjs@gmail.com Signed-off-by: Alexei Starovoitov ast@kernel.org Acked-by: Yonghong Song yhs@fb.com Link: https://lore.kernel.org/bpf/20210416154803.37157-1-chendotjs@gmail.com Signed-off-by: Sasha Levin sashal@kernel.org --- samples/bpf/tracex1_kern.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/samples/bpf/tracex1_kern.c b/samples/bpf/tracex1_kern.c index 107da148820f..9c74b45c5720 100644 --- a/samples/bpf/tracex1_kern.c +++ b/samples/bpf/tracex1_kern.c @@ -20,7 +20,7 @@ SEC("kprobe/__netif_receive_skb_core") int bpf_prog1(struct pt_regs *ctx) { - /* attaches to kprobe netif_receive_skb, + /* attaches to kprobe __netif_receive_skb_core, * looks for packets on loobpack device and prints them */ char devname[IFNAMSIZ]; @@ -29,7 +29,7 @@ int bpf_prog1(struct pt_regs *ctx) int len;

/* non-portable! works for the given kernel only */ - skb = (struct sk_buff *) PT_REGS_PARM1(ctx); + bpf_probe_read_kernel(&skb, sizeof(skb), (void *)PT_REGS_PARM1(ctx)); dev = _(skb->dev); len = _(skb->len);

From: Robin Singh robin.singh@amd.com

[ Upstream commit 19cc1f3829567e7dca21c1389ea6407b8f5efab4 ]

[why] During dsc enable, a divide by zero condition triggered the kernel crash.

[how] An IGT test, which enable the DSC, was crashing at the time of restore the default dsc status, becaue of h_totals value becoming 0. So add a check before divide condition. If h_total is zero, gracefully ignore and set the default value.

kernel panic log:

[ 128.758827] divide error: 0000 [#1] PREEMPT SMP NOPTI [ 128.762714] CPU: 5 PID: 4562 Comm: amd_dp_dsc Tainted: G W 5.4.19-android-x86_64 #1 [ 128.769728] Hardware name: ADVANCED MICRO DEVICES, INC. Mauna/Mauna, BIOS WMN0B13N Nov 11 2020 [ 128.777695] RIP: 0010:hubp2_vready_at_or_After_vsync+0x37/0x7a [amdgpu] [ 128.785707] Code: 80 02 00 00 48 89 f3 48 8b 7f 08 b ...... [ 128.805696] RSP: 0018:ffffad8f82d43628 EFLAGS: 00010246 ...... [ 128.857707] CR2: 00007106d8465000 CR3: 0000000426530000 CR4: 0000000000140ee0 [ 128.865695] Call Trace: [ 128.869712] hubp3_setup+0x1f/0x7f [amdgpu] [ 128.873705] dcn20_update_dchubp_dpp+0xc8/0x54a [amdgpu] [ 128.877706] dcn20_program_front_end_for_ctx+0x31d/0x463 [amdgpu] [ 128.885706] dc_commit_state+0x3d2/0x658 [amdgpu] [ 128.889707] amdgpu_dm_atomic_commit_tail+0x4b3/0x1e7c [amdgpu] [ 128.897699] ? dm_read_reg_func+0x41/0xb5 [amdgpu] [ 128.901707] ? dm_read_reg_func+0x41/0xb5 [amdgpu] [ 128.905706] ? __is_insn_slot_addr+0x43/0x48 [ 128.909706] ? fill_plane_buffer_attributes+0x29e/0x3dc [amdgpu] [ 128.917705] ? dm_plane_helper_prepare_fb+0x255/0x284 [amdgpu] [ 128.921700] ? usleep_range+0x7c/0x7c [ 128.925705] ? preempt_count_sub+0xf/0x18 [ 128.929706] ? _raw_spin_unlock_irq+0x13/0x24 [ 128.933732] ? __wait_for_common+0x11e/0x18f [ 128.937705] ? _raw_spin_unlock_irq+0x13/0x24 [ 128.941706] ? __wait_for_common+0x11e/0x18f [ 128.945705] commit_tail+0x8b/0xd2 [drm_kms_helper] [ 128.949707] drm_atomic_helper_commit+0xd8/0xf5 [drm_kms_helper] [ 128.957706] amdgpu_dm_atomic_commit+0x337/0x360 [amdgpu] [ 128.961705] ? drm_atomic_check_only+0x543/0x68d [drm] [ 128.969705] ? drm_atomic_set_property+0x760/0x7af [drm] [ 128.973704] ? drm_mode_atomic_ioctl+0x6f3/0x85a [drm] [ 128.977705] drm_mode_atomic_ioctl+0x6f3/0x85a [drm] [ 128.985705] ? drm_atomic_set_property+0x7af/0x7af [drm] [ 128.989706] drm_ioctl_kernel+0x82/0xda [drm] [ 128.993706] drm_ioctl+0x225/0x319 [drm] [ 128.997707] ? drm_atomic_set_property+0x7af/0x7af [drm] [ 129.001706] ? preempt_count_sub+0xf/0x18 [ 129.005713] amdgpu_drm_ioctl+0x4b/0x76 [amdgpu] [ 129.009705] vfs_ioctl+0x1d/0x2a [ 129.013705] do_vfs_ioctl+0x419/0x43d [ 129.017707] ksys_ioctl+0x52/0x71 [ 129.021707] __x64_sys_ioctl+0x16/0x19 [ 129.025706] do_syscall_64+0x78/0x85 [ 129.029705] entry_SYSCALL_64_after_hwframe+0x44/0xa9

Signed-off-by: Robin Singh robin.singh@amd.com Reviewed-by: Harry Wentland Harry.Wentland@amd.com Reviewed-by: Robin Singh Robin.Singh@amd.com Acked-by: Aurabindo Pillai aurabindo.pillai@amd.com Tested-by: Daniel Wheeler daniel.wheeler@amd.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c index 69e2aae42394..b250ef75c163 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c @@ -1,5 +1,5 @@ /* - * Copyright 2012-17 Advanced Micro Devices, Inc. + * Copyright 2012-2021 Advanced Micro Devices, Inc. * * Permission is hereby granted, free of charge, to any person obtaining a * copy of this software and associated documentation files (the "Software"), @@ -179,11 +179,14 @@ void hubp2_vready_at_or_After_vsync(struct hubp *hubp, else Set HUBP_VREADY_AT_OR_AFTER_VSYNC = 0 */ - if ((pipe_dest->vstartup_start - (pipe_dest->vready_offset+pipe_dest->vupdate_width - + pipe_dest->vupdate_offset) / pipe_dest->htotal) <= pipe_dest->vblank_end) { - value = 1; - } else - value = 0; + if (pipe_dest->htotal != 0) { + if ((pipe_dest->vstartup_start - (pipe_dest->vready_offset+pipe_dest->vupdate_width + + pipe_dest->vupdate_offset) / pipe_dest->htotal) <= pipe_dest->vblank_end) { + value = 1; + } else + value = 0; + } + REG_UPDATE(DCHUBP_CNTL, HUBP_VREADY_AT_OR_AFTER_VSYNC, value); }

From: Gustavo A. R. Silva gustavoars@kernel.org

[ Upstream commit bb43e5718d8f1b46e7a77e7b39be3c691f293050 ]

Fix the following out-of-bounds warnings by adding a new structure wl3501_req instead of duplicating the same members in structure wl3501_join_req and wl3501_scan_confirm:

arch/x86/include/asm/string_32.h:182:25: warning: '__builtin_memcpy' offset [39, 108] from the object at 'sig' is out of the bounds of referenced subobject 'beacon_period' with type 'short unsigned int' at offset 36 [-Warray-bounds] arch/x86/include/asm/string_32.h:182:25: warning: '__builtin_memcpy' offset [25, 95] from the object at 'sig' is out of the bounds of referenced subobject 'beacon_period' with type 'short unsigned int' at offset 22 [-Warray-bounds]

Refactor the code, accordingly:

$ pahole -C wl3501_req drivers/net/wireless/wl3501_cs.o struct wl3501_req { u16 beacon_period; /* 0 2 */ u16 dtim_period; /* 2 2 */ u16 cap_info; /* 4 2 */ u8 bss_type; /* 6 1 */ u8 bssid[6]; /* 7 6 */ struct iw_mgmt_essid_pset ssid; /* 13 34 */ struct iw_mgmt_ds_pset ds_pset; /* 47 3 */ struct iw_mgmt_cf_pset cf_pset; /* 50 8 */ struct iw_mgmt_ibss_pset ibss_pset; /* 58 4 */ struct iw_mgmt_data_rset bss_basic_rset; /* 62 10 */

/* size: 72, cachelines: 2, members: 10 */ /* last cacheline: 8 bytes */ };

$ pahole -C wl3501_join_req drivers/net/wireless/wl3501_cs.o struct wl3501_join_req { u16 next_blk; /* 0 2 */ u8 sig_id; /* 2 1 */ u8 reserved; /* 3 1 */ struct iw_mgmt_data_rset operational_rset; /* 4 10 */ u16 reserved2; /* 14 2 */ u16 timeout; /* 16 2 */ u16 probe_delay; /* 18 2 */ u8 timestamp[8]; /* 20 8 */ u8 local_time[8]; /* 28 8 */ struct wl3501_req req; /* 36 72 */

/* size: 108, cachelines: 2, members: 10 */ /* last cacheline: 44 bytes */ };

$ pahole -C wl3501_scan_confirm drivers/net/wireless/wl3501_cs.o struct wl3501_scan_confirm { u16 next_blk; /* 0 2 */ u8 sig_id; /* 2 1 */ u8 reserved; /* 3 1 */ u16 status; /* 4 2 */ char timestamp[8]; /* 6 8 */ char localtime[8]; /* 14 8 */ struct wl3501_req req; /* 22 72 */ /* --- cacheline 1 boundary (64 bytes) was 30 bytes ago --- */ u8 rssi; /* 94 1 */

/* size: 96, cachelines: 2, members: 8 */ /* padding: 1 */ /* last cacheline: 32 bytes */ };

The problem is that the original code is trying to copy data into a bunch of struct members adjacent to each other in a single call to memcpy(). Now that a new struct wl3501_req enclosing all those adjacent members is introduced, memcpy() doesn't overrun the length of &sig.beacon_period and &this->bss_set[i].beacon_period, because the address of the new struct object _req_ is used as the destination, instead.

This helps with the ongoing efforts to globally enable -Warray-bounds and get us closer to being able to tighten the FORTIFY_SOURCE routines on memcpy().

Link: https://github.com/KSPP/linux/issues/109 Reported-by: kernel test robot lkp@intel.com Signed-off-by: Gustavo A. R. Silva gustavoars@kernel.org Reviewed-by: Kees Cook keescook@chromium.org Signed-off-by: Kalle Valo kvalo@codeaurora.org Link: https://lore.kernel.org/r/1fbaf516da763b50edac47d792a9145aa4482e29.161844226... Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/wireless/wl3501.h | 35 +++++++++++-------------- drivers/net/wireless/wl3501_cs.c | 44 +++++++++++++++++--------------- 2 files changed, 38 insertions(+), 41 deletions(-)

diff --git a/drivers/net/wireless/wl3501.h b/drivers/net/wireless/wl3501.h index 077a934ae3b5..a10ee5a68012 100644 --- a/drivers/net/wireless/wl3501.h +++ b/drivers/net/wireless/wl3501.h @@ -379,16 +379,7 @@ struct wl3501_get_confirm { u8 mib_value[100]; };

-struct wl3501_join_req { - u16 next_blk; - u8 sig_id; - u8 reserved; - struct iw_mgmt_data_rset operational_rset; - u16 reserved2; - u16 timeout; - u16 probe_delay; - u8 timestamp[8]; - u8 local_time[8]; +struct wl3501_req { u16 beacon_period; u16 dtim_period; u16 cap_info; @@ -401,6 +392,19 @@ struct wl3501_join_req { struct iw_mgmt_data_rset bss_basic_rset; };

+struct wl3501_join_req { + u16 next_blk; + u8 sig_id; + u8 reserved; + struct iw_mgmt_data_rset operational_rset; + u16 reserved2; + u16 timeout; + u16 probe_delay; + u8 timestamp[8]; + u8 local_time[8]; + struct wl3501_req req; +}; + struct wl3501_join_confirm { u16 next_blk; u8 sig_id; @@ -443,16 +447,7 @@ struct wl3501_scan_confirm { u16 status; char timestamp[8]; char localtime[8]; - u16 beacon_period; - u16 dtim_period; - u16 cap_info; - u8 bss_type; - u8 bssid[ETH_ALEN]; - struct iw_mgmt_essid_pset ssid; - struct iw_mgmt_ds_pset ds_pset; - struct iw_mgmt_cf_pset cf_pset; - struct iw_mgmt_ibss_pset ibss_pset; - struct iw_mgmt_data_rset bss_basic_rset; + struct wl3501_req req; u8 rssi; };

diff --git a/drivers/net/wireless/wl3501_cs.c b/drivers/net/wireless/wl3501_cs.c index 96eb69678855..122d36439319 100644 --- a/drivers/net/wireless/wl3501_cs.c +++ b/drivers/net/wireless/wl3501_cs.c @@ -590,7 +590,7 @@ static int wl3501_mgmt_join(struct wl3501_card *this, u16 stas) struct wl3501_join_req sig = { .sig_id = WL3501_SIG_JOIN_REQ, .timeout = 10, - .ds_pset = { + .req.ds_pset = { .el = { .id = IW_MGMT_INFO_ELEMENT_DS_PARAMETER_SET, .len = 1, @@ -599,7 +599,7 @@ static int wl3501_mgmt_join(struct wl3501_card *this, u16 stas) }, };

- memcpy(&sig.beacon_period, &this->bss_set[stas].beacon_period, 72); + memcpy(&sig.req, &this->bss_set[stas].req, sizeof(sig.req)); return wl3501_esbq_exec(this, &sig, sizeof(sig)); }

@@ -667,35 +667,37 @@ static void wl3501_mgmt_scan_confirm(struct wl3501_card *this, u16 addr) if (sig.status == WL3501_STATUS_SUCCESS) { pr_debug("success"); if ((this->net_type == IW_MODE_INFRA && - (sig.cap_info & WL3501_MGMT_CAPABILITY_ESS)) || + (sig.req.cap_info & WL3501_MGMT_CAPABILITY_ESS)) || (this->net_type == IW_MODE_ADHOC && - (sig.cap_info & WL3501_MGMT_CAPABILITY_IBSS)) || + (sig.req.cap_info & WL3501_MGMT_CAPABILITY_IBSS)) || this->net_type == IW_MODE_AUTO) { if (!this->essid.el.len) matchflag = 1; else if (this->essid.el.len == 3 && !memcmp(this->essid.essid, "ANY", 3)) matchflag = 1; - else if (this->essid.el.len != sig.ssid.el.len) + else if (this->essid.el.len != sig.req.ssid.el.len) matchflag = 0; - else if (memcmp(this->essid.essid, sig.ssid.essid, + else if (memcmp(this->essid.essid, sig.req.ssid.essid, this->essid.el.len)) matchflag = 0; else matchflag = 1; if (matchflag) { for (i = 0; i < this->bss_cnt; i++) { - if (ether_addr_equal_unaligned(this->bss_set[i].bssid, sig.bssid)) { + if (ether_addr_equal_unaligned(this->bss_set[i].req.bssid, + sig.req.bssid)) { matchflag = 0; break; } } } if (matchflag && (i < 20)) { - memcpy(&this->bss_set[i].beacon_period, - &sig.beacon_period, 73); + memcpy(&this->bss_set[i].req, + &sig.req, sizeof(sig.req)); this->bss_cnt++; this->rssi = sig.rssi; + this->bss_set[i].rssi = sig.rssi; } } } else if (sig.status == WL3501_STATUS_TIMEOUT) { @@ -887,19 +889,19 @@ static void wl3501_mgmt_join_confirm(struct net_device *dev, u16 addr) if (this->join_sta_bss < this->bss_cnt) { const int i = this->join_sta_bss; memcpy(this->bssid, - this->bss_set[i].bssid, ETH_ALEN); - this->chan = this->bss_set[i].ds_pset.chan; + this->bss_set[i].req.bssid, ETH_ALEN); + this->chan = this->bss_set[i].req.ds_pset.chan; iw_copy_mgmt_info_element(&this->keep_essid.el, - &this->bss_set[i].ssid.el); + &this->bss_set[i].req.ssid.el); wl3501_mgmt_auth(this); } } else { const int i = this->join_sta_bss;

- memcpy(&this->bssid, &this->bss_set[i].bssid, ETH_ALEN); - this->chan = this->bss_set[i].ds_pset.chan; + memcpy(&this->bssid, &this->bss_set[i].req.bssid, ETH_ALEN); + this->chan = this->bss_set[i].req.ds_pset.chan; iw_copy_mgmt_info_element(&this->keep_essid.el, - &this->bss_set[i].ssid.el); + &this->bss_set[i].req.ssid.el); wl3501_online(dev); } } else { @@ -1575,30 +1577,30 @@ static int wl3501_get_scan(struct net_device *dev, struct iw_request_info *info, for (i = 0; i < this->bss_cnt; ++i) { iwe.cmd = SIOCGIWAP; iwe.u.ap_addr.sa_family = ARPHRD_ETHER; - memcpy(iwe.u.ap_addr.sa_data, this->bss_set[i].bssid, ETH_ALEN); + memcpy(iwe.u.ap_addr.sa_data, this->bss_set[i].req.bssid, ETH_ALEN); current_ev = iwe_stream_add_event(info, current_ev, extra + IW_SCAN_MAX_DATA, &iwe, IW_EV_ADDR_LEN); iwe.cmd = SIOCGIWESSID; iwe.u.data.flags = 1; - iwe.u.data.length = this->bss_set[i].ssid.el.len; + iwe.u.data.length = this->bss_set[i].req.ssid.el.len; current_ev = iwe_stream_add_point(info, current_ev, extra + IW_SCAN_MAX_DATA, &iwe, - this->bss_set[i].ssid.essid); + this->bss_set[i].req.ssid.essid); iwe.cmd = SIOCGIWMODE; - iwe.u.mode = this->bss_set[i].bss_type; + iwe.u.mode = this->bss_set[i].req.bss_type; current_ev = iwe_stream_add_event(info, current_ev, extra + IW_SCAN_MAX_DATA, &iwe, IW_EV_UINT_LEN); iwe.cmd = SIOCGIWFREQ; - iwe.u.freq.m = this->bss_set[i].ds_pset.chan; + iwe.u.freq.m = this->bss_set[i].req.ds_pset.chan; iwe.u.freq.e = 0; current_ev = iwe_stream_add_event(info, current_ev, extra + IW_SCAN_MAX_DATA, &iwe, IW_EV_FREQ_LEN); iwe.cmd = SIOCGIWENCODE; - if (this->bss_set[i].cap_info & WL3501_MGMT_CAPABILITY_PRIVACY) + if (this->bss_set[i].req.cap_info & WL3501_MGMT_CAPABILITY_PRIVACY) iwe.u.data.flags = IW_ENCODE_ENABLED | IW_ENCODE_NOKEY; else iwe.u.data.flags = IW_ENCODE_DISABLED;

From: Alexey Kardashevskiy aik@ozlabs.ru

[ Upstream commit cc7130bf119add37f36238343a593b71ef6ecc1e ]

The IOMMU table is divided into pools for concurrent mappings and each pool has a separate spinlock. When taking the ownership of an IOMMU group to pass through a device to a VM, we lock these spinlocks which triggers a false negative warning in lockdep (below).

This fixes it by annotating the large pool's spinlock as a nest lock which makes lockdep not complaining when locking nested locks if the nest lock is locked already.

=== WARNING: possible recursive locking detected 5.11.0-le_syzkaller_a+fstn1 #100 Not tainted -------------------------------------------- qemu-system-ppc/4129 is trying to acquire lock: c0000000119bddb0 (&(p->lock)/1){....}-{2:2}, at: iommu_take_ownership+0xac/0x1e0

but task is already holding lock: c0000000119bdd30 (&(p->lock)/1){....}-{2:2}, at: iommu_take_ownership+0xac/0x1e0

other info that might help us debug this: Possible unsafe locking scenario:

CPU0 ---- lock(&(p->lock)/1); lock(&(p->lock)/1); ===

Signed-off-by: Alexey Kardashevskiy aik@ozlabs.ru Signed-off-by: Michael Ellerman mpe@ellerman.id.au Link: https://lore.kernel.org/r/20210301063653.51003-1-aik@ozlabs.ru Signed-off-by: Sasha Levin sashal@kernel.org --- arch/powerpc/kernel/iommu.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index 9704f3f76e63..d7d42bd448c4 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -1057,7 +1057,7 @@ int iommu_take_ownership(struct iommu_table *tbl)

spin_lock_irqsave(&tbl->large_pool.lock, flags); for (i = 0; i < tbl->nr_pools; i++) - spin_lock(&tbl->pools[i].lock); + spin_lock_nest_lock(&tbl->pools[i].lock, &tbl->large_pool.lock);

iommu_table_release_pages(tbl);

@@ -1085,7 +1085,7 @@ void iommu_release_ownership(struct iommu_table *tbl)

spin_lock_irqsave(&tbl->large_pool.lock, flags); for (i = 0; i < tbl->nr_pools; i++) - spin_lock(&tbl->pools[i].lock); + spin_lock_nest_lock(&tbl->pools[i].lock, &tbl->large_pool.lock);

memset(tbl->it_map, 0, sz);

From: Felix Fietkau nbd@nbd.name

[ Upstream commit 3f57d8c40fea9b20543cab4da12f4680d2ef182c ]

The VLAN ID in the rx descriptor is only valid if the RX_DMA_VTAG bit is set. Fixes frames wrongly marked with VLAN tags.

Signed-off-by: Felix Fietkau nbd@nbd.name [Ilya: fix commit message] Signed-off-by: Ilya Lipnitskiy ilya.lipnitskiy@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/mediatek/mtk_eth_soc.c | 2 +- drivers/net/ethernet/mediatek/mtk_eth_soc.h | 1 + 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index d01b3a1b40f4..7e3806fd70b2 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -1315,7 +1315,7 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget, skb->protocol = eth_type_trans(skb, netdev);

if (netdev->features & NETIF_F_HW_VLAN_CTAG_RX && - RX_DMA_VID(trxd.rxd3)) + (trxd.rxd2 & RX_DMA_VTAG)) __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), RX_DMA_VID(trxd.rxd3)); skb_record_rx_queue(skb, 0); diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h index 1e787f3577aa..1e9202b34d35 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h @@ -293,6 +293,7 @@ #define RX_DMA_LSO BIT(30) #define RX_DMA_PLEN0(_x) (((_x) & 0x3fff) << 16) #define RX_DMA_GET_PLEN0(_x) (((_x) >> 16) & 0x3fff) +#define RX_DMA_VTAG BIT(15)

/* QDMA descriptor rxd3 */ #define RX_DMA_VID(_x) ((_x) & 0xfff)

From: Sergei Trofimovich slyfox@gentoo.org

[ Upstream commit 99e729bd40fb3272fa4b0140839d5e957b58588a ]

Noticed failure as a crash on ia64 when tried to symbolize all backtraces collected by page_owner=on:

$ cat /sys/kernel/debug/page_owner <oops>

CPU: 1 PID: 2074 Comm: cat Not tainted 5.12.0-rc4 #226 Hardware name: hp server rx3600, BIOS 04.03 04/08/2008 ip is at dereference_module_function_descriptor+0x41/0x100

Crash happens at dereference_module_function_descriptor() due to use-after-free when dereferencing ".opd" section header.

All section headers are already freed after module is laoded successfully.

To keep symbolizer working the change stores ".opd" address and size after module is relocated to a new place and before section headers are discarded.

To make similar errors less obscure module_finalize() now zeroes out all variables relevant to module loading only.

Link: https://lkml.kernel.org/r/20210403074803.3309096-1-slyfox@gentoo.org Signed-off-by: Sergei Trofimovich slyfox@gentoo.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- arch/ia64/include/asm/module.h | 6 +++++- arch/ia64/kernel/module.c | 29 +++++++++++++++++++++++++---- 2 files changed, 30 insertions(+), 5 deletions(-)

diff --git a/arch/ia64/include/asm/module.h b/arch/ia64/include/asm/module.h index f319144260ce..9fbf32e6e881 100644 --- a/arch/ia64/include/asm/module.h +++ b/arch/ia64/include/asm/module.h @@ -14,16 +14,20 @@ struct elf64_shdr; /* forward declration */

struct mod_arch_specific { + /* Used only at module load time. */ struct elf64_shdr *core_plt; /* core PLT section */ struct elf64_shdr *init_plt; /* init PLT section */ struct elf64_shdr *got; /* global offset table */ struct elf64_shdr *opd; /* official procedure descriptors */ struct elf64_shdr *unwind; /* unwind-table section */ unsigned long gp; /* global-pointer for module */ + unsigned int next_got_entry; /* index of next available got entry */

+ /* Used at module run and cleanup time. */ void *core_unw_table; /* core unwind-table cookie returned by unwinder */ void *init_unw_table; /* init unwind-table cookie returned by unwinder */ - unsigned int next_got_entry; /* index of next available got entry */ + void *opd_addr; /* symbolize uses .opd to get to actual function */ + unsigned long opd_size; };

#define MODULE_PROC_FAMILY "ia64" diff --git a/arch/ia64/kernel/module.c b/arch/ia64/kernel/module.c index 1a42ba885188..ee693c8cec49 100644 --- a/arch/ia64/kernel/module.c +++ b/arch/ia64/kernel/module.c @@ -905,9 +905,31 @@ register_unwind_table (struct module *mod) int module_finalize (const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs, struct module *mod) { + struct mod_arch_specific *mas = &mod->arch; + DEBUGP("%s: init: entry=%p\n", __func__, mod->init); - if (mod->arch.unwind) + if (mas->unwind) register_unwind_table(mod); + + /* + * ".opd" was already relocated to the final destination. Store + * it's address for use in symbolizer. + */ + mas->opd_addr = (void *)mas->opd->sh_addr; + mas->opd_size = mas->opd->sh_size; + + /* + * Module relocation was already done at this point. Section + * headers are about to be deleted. Wipe out load-time context. + */ + mas->core_plt = NULL; + mas->init_plt = NULL; + mas->got = NULL; + mas->opd = NULL; + mas->unwind = NULL; + mas->gp = 0; + mas->next_got_entry = 0; + return 0; }

@@ -926,10 +948,9 @@ module_arch_cleanup (struct module *mod)

void *dereference_module_function_descriptor(struct module *mod, void *ptr) { - Elf64_Shdr *opd = mod->arch.opd; + struct mod_arch_specific *mas = &mod->arch;

- if (ptr < (void *)opd->sh_addr || - ptr >= (void *)(opd->sh_addr + opd->sh_size)) + if (ptr < mas->opd_addr || ptr >= mas->opd_addr + mas->opd_size) return ptr;

return dereference_function_descriptor(ptr);

From: Jia-Ju Bai baijiaju1990@gmail.com

[ Upstream commit 45c7eaeb29d67224db4ba935deb575586a1fda09 ]

When kcalloc() returns NULL to __tcbp or of_count_phandle_with_args() returns zero or -ENOENT to count, no error return code of thermal_of_populate_bind_params() is assigned. To fix these bugs, ret is assigned with -ENOMEM and -ENOENT in these cases, respectively.

Fixes: a92bab8919e3 ("of: thermal: Allow multiple devices to share cooling map") Reported-by: TOTE Robot oslab@tsinghua.edu.cn Signed-off-by: Jia-Ju Bai baijiaju1990@gmail.com Signed-off-by: Daniel Lezcano daniel.lezcano@linaro.org Link: https://lore.kernel.org/r/20210310122423.3266-1-baijiaju1990@gmail.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/thermal/of-thermal.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/thermal/of-thermal.c b/drivers/thermal/of-thermal.c index dc5093be553e..68d0c181ec7b 100644 --- a/drivers/thermal/of-thermal.c +++ b/drivers/thermal/of-thermal.c @@ -712,14 +712,17 @@ static int thermal_of_populate_bind_params(struct device_node *np,

count = of_count_phandle_with_args(np, "cooling-device", "#cooling-cells"); - if (!count) { + if (count <= 0) { pr_err("Add a cooling_device property with at least one device\n"); + ret = -ENOENT; goto end; }

__tcbp = kcalloc(count, sizeof(*__tcbp), GFP_KERNEL); - if (!__tcbp) + if (!__tcbp) { + ret = -ENOMEM; goto end; + }

for (i = 0; i < count; i++) { ret = of_parse_phandle_with_args(np, "cooling-device",

From: Pali Rohár pali@kernel.org

[ Upstream commit 1e83130f01b04c16579ed5a5e03d729bcffc4c5d ]

IRQ domain alloc function should return zero on success. Non-zero value indicates failure.

Link: https://lore.kernel.org/r/20210303142202.25780-1-pali@kernel.org Fixes: fc54bae28818 ("PCI: iproc: Allow allocation of multiple MSIs") Signed-off-by: Pali Rohár pali@kernel.org Signed-off-by: Lorenzo Pieralisi lorenzo.pieralisi@arm.com Reviewed-by: Krzysztof Wilczyński kw@linux.com Acked-by: Ray Jui ray.jui@broadcom.com Acked-by: Marc Zyngier maz@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/pci/controller/pcie-iproc-msi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pci/controller/pcie-iproc-msi.c b/drivers/pci/controller/pcie-iproc-msi.c index a1298f6784ac..f40d17b285c5 100644 --- a/drivers/pci/controller/pcie-iproc-msi.c +++ b/drivers/pci/controller/pcie-iproc-msi.c @@ -271,7 +271,7 @@ static int iproc_msi_irq_domain_alloc(struct irq_domain *domain, NULL, NULL); }

- return hwirq; + return 0; }

static void iproc_msi_irq_domain_free(struct irq_domain *domain,

From: Zhen Lei thunder.leizhen@huawei.com

[ Upstream commit a506bd5756290821a4314f502b4bafc2afcf5260 ]

The commit 1879445dfa7b ("perf/core: Set event's default ::overflow_handler()") set a default event->overflow_handler in perf_event_alloc(), and replace the check event->overflow_handler with is_default_overflow_handler(), but one is missing.

Currently, the bp->overflow_handler can not be NULL. As a result, enable_single_step() is always not invoked.

Comments from Zhen Lei:

https://patchwork.kernel.org/project/linux-arm-kernel/patch/20210207105934.2...

Fixes: 1879445dfa7b ("perf/core: Set event's default ::overflow_handler()") Signed-off-by: Zhen Lei thunder.leizhen@huawei.com Cc: Wang Nan wangnan0@huawei.com Acked-by: Will Deacon will@kernel.org Signed-off-by: Russell King rmk+kernel@armlinux.org.uk Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm/kernel/hw_breakpoint.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c index 7021ef0b4e71..b06d9ea07c84 100644 --- a/arch/arm/kernel/hw_breakpoint.c +++ b/arch/arm/kernel/hw_breakpoint.c @@ -883,7 +883,7 @@ static void breakpoint_handler(unsigned long unknown, struct pt_regs *regs) info->trigger = addr; pr_debug("breakpoint fired: address = 0x%x\n", addr); perf_bp_event(bp, regs); - if (!bp->overflow_handler) + if (is_default_overflow_handler(bp)) enable_single_step(bp, addr); goto unlock; }

From: Trond Myklebust trond.myklebust@hammerspace.com

[ Upstream commit 99f23783224355e7022ceea9b8d9f62c0fd01bd8 ]

Whether we're allocating or delallocating space, we should flush out the pending writes in order to avoid races with attribute updates.

Fixes: 1e564d3dbd68 ("NFSv4.2: Fix a race in nfs42_proc_deallocate()") Signed-off-by: Trond Myklebust trond.myklebust@hammerspace.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/nfs/nfs42proc.c | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-)

diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c index 9b61c80a93e9..5c84e5b8c0d6 100644 --- a/fs/nfs/nfs42proc.c +++ b/fs/nfs/nfs42proc.c @@ -59,7 +59,8 @@ static int _nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep, static int nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep, loff_t offset, loff_t len) { - struct nfs_server *server = NFS_SERVER(file_inode(filep)); + struct inode *inode = file_inode(filep); + struct nfs_server *server = NFS_SERVER(inode); struct nfs4_exception exception = { }; struct nfs_lock_context *lock; int err; @@ -68,9 +69,13 @@ static int nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep, if (IS_ERR(lock)) return PTR_ERR(lock);

- exception.inode = file_inode(filep); + exception.inode = inode; exception.state = lock->open_context->state;

+ err = nfs_sync_inode(inode); + if (err) + goto out; + do { err = _nfs42_proc_fallocate(msg, filep, lock, offset, len); if (err == -ENOTSUPP) { @@ -79,7 +84,7 @@ static int nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep, } err = nfs4_handle_exception(server, err, &exception); } while (exception.retry); - +out: nfs_put_lock_context(lock); return err; } @@ -117,16 +122,13 @@ int nfs42_proc_deallocate(struct file *filep, loff_t offset, loff_t len) return -EOPNOTSUPP;

inode_lock(inode); - err = nfs_sync_inode(inode); - if (err) - goto out_unlock;

err = nfs42_proc_fallocate(&msg, filep, offset, len); if (err == 0) truncate_pagecache_range(inode, offset, (offset + len) -1); if (err == -EOPNOTSUPP) NFS_SERVER(inode)->caps &= ~NFS_CAP_DEALLOCATE; -out_unlock: + inode_unlock(inode); return err; }

From: Yang Yingliang yangyingliang@huawei.com

[ Upstream commit acaef7981a218813e3617edb9c01837808de063c ]

Add the missing destroy_workqueue() before return from pci_epf_test_init() in the error handling case and add destroy_workqueue() in pci_epf_test_exit().

Link: https://lore.kernel.org/r/20210331084012.2091010-1-yangyingliang@huawei.com Fixes: 349e7a85b25fa ("PCI: endpoint: functions: Add an EP function to test PCI") Reported-by: Hulk Robot hulkci@huawei.com Signed-off-by: Yang Yingliang yangyingliang@huawei.com Signed-off-by: Lorenzo Pieralisi lorenzo.pieralisi@arm.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/pci/endpoint/functions/pci-epf-test.c | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/drivers/pci/endpoint/functions/pci-epf-test.c b/drivers/pci/endpoint/functions/pci-epf-test.c index 1cfe3687a211..6dcee39b364a 100644 --- a/drivers/pci/endpoint/functions/pci-epf-test.c +++ b/drivers/pci/endpoint/functions/pci-epf-test.c @@ -604,6 +604,7 @@ static int __init pci_epf_test_init(void)

ret = pci_epf_register_driver(&test_driver); if (ret) { + destroy_workqueue(kpcitest_workqueue); pr_err("Failed to register pci epf test driver --> %d\n", ret); return ret; } @@ -614,6 +615,8 @@ module_init(pci_epf_test_init);

static void __exit pci_epf_test_exit(void) { + if (kpcitest_workqueue) + destroy_workqueue(kpcitest_workqueue); pci_epf_unregister_driver(&test_driver); } module_exit(pci_epf_test_exit);

From: Olga Kornievskaia kolga@netapp.com

[ Upstream commit 73f5c88f521a630ea1628beb9c2d48a2e777a419 ]

Currently the client ignores the value of the sr_eof of the SEEK operation. According to the spec, if the server didn't find the requested extent and reached the end of the file, the server would return sr_eof=true. In case the request for DATA and no data was found (ie in the middle of the hole), then the lseek expects that ENXIO would be returned.

Fixes: 1c6dcbe5ceff8 ("NFS: Implement SEEK") Signed-off-by: Olga Kornievskaia kolga@netapp.com Signed-off-by: Trond Myklebust trond.myklebust@hammerspace.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/nfs/nfs42proc.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c index 5c84e5b8c0d6..6b7c926824ae 100644 --- a/fs/nfs/nfs42proc.c +++ b/fs/nfs/nfs42proc.c @@ -500,7 +500,10 @@ static loff_t _nfs42_proc_llseek(struct file *filep, if (status) return status;

- return vfs_setpos(filep, res.sr_offset, inode->i_sb->s_maxbytes); + if (whence == SEEK_DATA && res.sr_eof) + return -NFS4ERR_NXIO; + else + return vfs_setpos(filep, res.sr_offset, inode->i_sb->s_maxbytes); }

loff_t nfs42_proc_llseek(struct file *filep, loff_t offset, int whence)

From: Jeff Layton jlayton@kernel.org

[ Upstream commit 1775c7ddacfcea29051c67409087578f8f4d751b ]

Fixes: 878dabb64117 ("ceph: don't return -ESTALE if there's still an open file") Signed-off-by: Jeff Layton jlayton@kernel.org Reviewed-by: Xiubo Li xiubli@redhat.com Signed-off-by: Ilya Dryomov idryomov@gmail.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/ceph/export.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/fs/ceph/export.c b/fs/ceph/export.c index e088843a7734..baa6368bece5 100644 --- a/fs/ceph/export.c +++ b/fs/ceph/export.c @@ -178,8 +178,10 @@ static struct dentry *__fh_to_dentry(struct super_block *sb, u64 ino) return ERR_CAST(inode); /* We need LINK caps to reliably check i_nlink */ err = ceph_do_getattr(inode, CEPH_CAP_LINK_SHARED, false); - if (err) + if (err) { + iput(inode); return ERR_PTR(err); + } /* -ESTALE if inode as been unlinked and no file is open */ if ((inode->i_nlink == 0) && (atomic_read(&inode->i_count) == 1)) { iput(inode);

From: Yufeng Mo moyufeng@huawei.com

[ Upstream commit 2867298dd49ee84214b8721521dc7a5a6382520c ]

According to the UM, the type and enable status of igu_egu_hw_err should be configured separately. Currently, the type field is incorrect when disable this error. So fix it by configuring these two fields separately.

Fixes: bf1faf9415dd ("net: hns3: Add enable and process hw errors from IGU, EGU and NCSI") Signed-off-by: Yufeng Mo moyufeng@huawei.com Signed-off-by: Huazhong Tan tanhuazhong@huawei.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c | 3 ++- drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h | 3 ++- 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c index 87dece0e745d..53fd6e4d9e2d 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c @@ -753,8 +753,9 @@ static int hclge_config_igu_egu_hw_err_int(struct hclge_dev *hdev, bool en)

/* configure IGU,EGU error interrupts */ hclge_cmd_setup_basic_desc(&desc, HCLGE_IGU_COMMON_INT_EN, false); + desc.data[0] = cpu_to_le32(HCLGE_IGU_ERR_INT_TYPE); if (en) - desc.data[0] = cpu_to_le32(HCLGE_IGU_ERR_INT_EN); + desc.data[0] |= cpu_to_le32(HCLGE_IGU_ERR_INT_EN);

desc.data[1] = cpu_to_le32(HCLGE_IGU_ERR_INT_EN_MASK);

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h index 876fd81ad2f1..8eccdb651a3c 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h @@ -33,7 +33,8 @@ #define HCLGE_TQP_ECC_ERR_INT_EN_MASK 0x0FFF #define HCLGE_MSIX_SRAM_ECC_ERR_INT_EN_MASK 0x0F000000 #define HCLGE_MSIX_SRAM_ECC_ERR_INT_EN 0x0F000000 -#define HCLGE_IGU_ERR_INT_EN 0x0000066F +#define HCLGE_IGU_ERR_INT_EN 0x0000000F +#define HCLGE_IGU_ERR_INT_TYPE 0x00000660 #define HCLGE_IGU_ERR_INT_EN_MASK 0x000F #define HCLGE_IGU_TNL_ERR_INT_EN 0x0002AABF #define HCLGE_IGU_TNL_ERR_INT_EN_MASK 0x003F

From: Jian Shen shenjian15@huawei.com

[ Upstream commit b4047aac4ec1066bab6c71950623746d7bcf7154 ]

In some cases, the device is not initialized because reset failed. If another task calls hns3_reset_notify_up_enet() before reset retry, it will cause an error since uninitialized pointer access. So add check for HNS3_NIC_STATE_INITED before calling hns3_nic_net_open() in hns3_reset_notify_up_enet().

Fixes: bb6b94a896d4 ("net: hns3: Add reset interface implementation in client") Signed-off-by: Jian Shen shenjian15@huawei.com Signed-off-by: Huazhong Tan tanhuazhong@huawei.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 5 +++++ 1 file changed, 5 insertions(+)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index 696f21543aa7..6b43cbf4f909 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -4280,6 +4280,11 @@ static int hns3_reset_notify_up_enet(struct hnae3_handle *handle) struct hns3_nic_priv *priv = netdev_priv(kinfo->netdev); int ret = 0;

+ if (!test_bit(HNS3_NIC_STATE_INITED, &priv->state)) { + netdev_err(kinfo->netdev, "device is not initialized yet\n"); + return -EFAULT; + } + clear_bit(HNS3_NIC_STATE_RESETTING, &priv->state);

if (netif_running(kinfo->netdev)) {

From: Peng Li lipeng321@huawei.com

[ Upstream commit b416e872be06fdace3c36cf5210130509d0f0e72 ]

Currently, netif_tx_stop_all_queues() is used to ensure that the xmit is not running, but for the concurrent case it will not take effect, since netif_tx_stop_all_queues() just sets a flag without locking to indicate that the xmit queue(s) should not be run.

So use netif_tx_disable() to replace netif_tx_stop_all_queues(), it takes the xmit queue lock while marking the queue stopped.

Fixes: 76ad4f0ee747 ("net: hns3: Add support of HNS3 Ethernet Driver for hip08 SoC") Signed-off-by: Peng Li lipeng321@huawei.com Signed-off-by: Huazhong Tan tanhuazhong@huawei.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index 3dd3b8047968..5f2948bafff2 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -539,8 +539,8 @@ static int hns3_nic_net_stop(struct net_device *netdev) if (h->ae_algo->ops->set_timer_task) h->ae_algo->ops->set_timer_task(priv->ae_handle, false);

- netif_tx_stop_all_queues(netdev); netif_carrier_off(netdev); + netif_tx_disable(netdev);

hns3_nic_net_down(netdev);

From: Xin Long lucien.xin@gmail.com

[ Upstream commit 35b4f24415c854cd718ccdf38dbea6297f010aae ]

There's a panic that occurs in a few of envs, the call trace is as below:

[] general protection fault, ... 0x29acd70f1000a: 0000 [#1] SMP PTI [] RIP: 0010:sctp_ulpevent_notify_peer_addr_change+0x4b/0x1fa [sctp] [] sctp_assoc_control_transport+0x1b9/0x210 [sctp] [] sctp_do_8_2_transport_strike.isra.16+0x15c/0x220 [sctp] [] sctp_cmd_interpreter.isra.21+0x1231/0x1a10 [sctp] [] sctp_do_sm+0xc3/0x2a0 [sctp] [] sctp_generate_timeout_event+0x81/0xf0 [sctp]

This is caused by a transport use-after-free issue. When processing a duplicate COOKIE-ECHO chunk in sctp_sf_do_dupcook_a(), both COOKIE-ACK and SHUTDOWN chunks are allocated with the transort from the new asoc. However, later in the sideeffect machine, the old asoc is used to send them out and old asoc's shutdown_last_sent_to is set to the transport that SHUTDOWN chunk attached to in sctp_cmd_setup_t2(), which actually belongs to the new asoc. After the new_asoc is freed and the old asoc T2 timeout, the old asoc's shutdown_last_sent_to that is already freed would be accessed in sctp_sf_t2_timer_expire().

Thanks Alexander and Jere for helping dig into this issue.

To fix it, this patch is to do the asoc update first, then allocate the COOKIE-ACK and SHUTDOWN chunks with the 'updated' old asoc. This would make more sense, as a chunk from an asoc shouldn't be sent out with another asoc. We had fixed quite a few issues caused by this.

Fixes: 145cb2f7177d ("sctp: Fix bundling of SHUTDOWN with COOKIE-ACK") Reported-by: Alexander Sverdlin alexander.sverdlin@nokia.com Reported-by: syzbot+bbe538efd1046586f587@syzkaller.appspotmail.com Reported-by: Michal Tesar mtesar@redhat.com Signed-off-by: Xin Long lucien.xin@gmail.com Acked-by: Marcelo Ricardo Leitner marcelo.leitner@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/sctp/sm_statefuns.c | 25 ++++++++++++++++++++----- 1 file changed, 20 insertions(+), 5 deletions(-)

diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 84138a07e936..72e4eaffacdb 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -1841,20 +1841,35 @@ static enum sctp_disposition sctp_sf_do_dupcook_a( SCTP_TO(SCTP_EVENT_TIMEOUT_T4_RTO)); sctp_add_cmd_sf(commands, SCTP_CMD_PURGE_ASCONF_QUEUE, SCTP_NULL());

- repl = sctp_make_cookie_ack(new_asoc, chunk); + /* Update the content of current association. */ + if (sctp_assoc_update((struct sctp_association *)asoc, new_asoc)) { + struct sctp_chunk *abort; + + abort = sctp_make_abort(asoc, NULL, sizeof(struct sctp_errhdr)); + if (abort) { + sctp_init_cause(abort, SCTP_ERROR_RSRC_LOW, 0); + sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(abort)); + } + sctp_add_cmd_sf(commands, SCTP_CMD_SET_SK_ERR, SCTP_ERROR(ECONNABORTED)); + sctp_add_cmd_sf(commands, SCTP_CMD_ASSOC_FAILED, + SCTP_PERR(SCTP_ERROR_RSRC_LOW)); + SCTP_INC_STATS(net, SCTP_MIB_ABORTEDS); + SCTP_DEC_STATS(net, SCTP_MIB_CURRESTAB); + goto nomem; + } + + repl = sctp_make_cookie_ack(asoc, chunk); if (!repl) goto nomem;

/* Report association restart to upper layer. */ ev = sctp_ulpevent_make_assoc_change(asoc, 0, SCTP_RESTART, 0, - new_asoc->c.sinit_num_ostreams, - new_asoc->c.sinit_max_instreams, + asoc->c.sinit_num_ostreams, + asoc->c.sinit_max_instreams, NULL, GFP_ATOMIC); if (!ev) goto nomem_ev;

- /* Update the content of current association. */ - sctp_add_cmd_sf(commands, SCTP_CMD_UPDATE_ASSOC, SCTP_ASOC(new_asoc)); sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP, SCTP_ULPEVENT(ev)); if ((sctp_state(asoc, SHUTDOWN_PENDING) || sctp_state(asoc, SHUTDOWN_SENT)) &&

From: Baptiste Lepers baptiste.lepers@gmail.com

[ Upstream commit f8f7e0fb22b2e75be55f2f0c13e229e75b0eac07 ]

Fix a misplaced barrier in call_decode. The struct rpc_rqst is modified as follows by xprt_complete_rqst:

req->rq_private_buf.len = copied; /* Ensure all writes are done before we update */ /* req->rq_reply_bytes_recvd */ smp_wmb(); req->rq_reply_bytes_recvd = copied;

And currently read as follows by call_decode:

smp_rmb(); // misplaced if (!req->rq_reply_bytes_recvd) goto out; req->rq_rcv_buf.len = req->rq_private_buf.len;

This patch places the smp_rmb after the if to ensure that rq_reply_bytes_recvd and rq_private_buf.len are read in order.

Fixes: 9ba828861c56a ("SUNRPC: Don't try to parse incomplete RPC messages") Signed-off-by: Baptiste Lepers baptiste.lepers@gmail.com Signed-off-by: Trond Myklebust trond.myklebust@hammerspace.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/sunrpc/clnt.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-)

diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index f1088ca39d44..b6039642df67 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -2505,12 +2505,6 @@ call_decode(struct rpc_task *task) task->tk_flags &= ~RPC_CALL_MAJORSEEN; }

- /* - * Ensure that we see all writes made by xprt_complete_rqst() - * before it changed req->rq_reply_bytes_recvd. - */ - smp_rmb(); - /* * Did we ever call xprt_complete_rqst()? If not, we should assume * the message is incomplete. @@ -2519,6 +2513,11 @@ call_decode(struct rpc_task *task) if (!req->rq_reply_bytes_recvd) goto out;

+ /* Ensure that we see all writes made by xprt_complete_rqst() + * before it changed req->rq_reply_bytes_recvd. + */ + smp_rmb(); + req->rq_rcv_buf.len = req->rq_private_buf.len;

/* Check that the softirq receive buffer is valid */

From: Xin Long lucien.xin@gmail.com

[ Upstream commit f282df0391267fb2b263da1cc3233aa6fb81defc ]

Normally SCTP_MIB_CURRESTAB is always incremented once asoc enter into ESTABLISHED from the state < ESTABLISHED and decremented when the asoc is being deleted.

However, in sctp_sf_do_dupcook_b(), the asoc's state can be changed to ESTABLISHED from the state >= ESTABLISHED where it shouldn't increment SCTP_MIB_CURRESTAB. Otherwise, one asoc may increment MIB_CURRESTAB multiple times but only decrement once at the end.

I was able to reproduce it by using scapy to do the 4-way shakehands, after that I replayed the COOKIE-ECHO chunk with 'peer_vtag' field changed to different values, and SCTP_MIB_CURRESTAB was incremented multiple times and never went back to 0 even when the asoc was freed.

This patch is to fix it by only incrementing SCTP_MIB_CURRESTAB when the state < ESTABLISHED in sctp_sf_do_dupcook_b().

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-by: Marcelo Ricardo Leitner marcelo.leitner@gmail.com Signed-off-by: Xin Long lucien.xin@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/sctp/sm_statefuns.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 72e4eaffacdb..82a202d71a31 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -1933,7 +1933,8 @@ static enum sctp_disposition sctp_sf_do_dupcook_b( sctp_add_cmd_sf(commands, SCTP_CMD_UPDATE_ASSOC, SCTP_ASOC(new_asoc)); sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE, SCTP_STATE(SCTP_STATE_ESTABLISHED)); - SCTP_INC_STATS(net, SCTP_MIB_CURRESTAB); + if (asoc->state < SCTP_STATE_ESTABLISHED) + SCTP_INC_STATS(net, SCTP_MIB_CURRESTAB); sctp_add_cmd_sf(commands, SCTP_CMD_HB_TIMERS_START, SCTP_NULL());

repl = sctp_make_cookie_ack(new_asoc, chunk);

From: Kees Cook keescook@chromium.org

[ Upstream commit 5bbf219328849e83878bddb7c226d8d42e84affc ]

An out of bounds write happens when setting the default power state. KASAN sees this as:

[drm] radeon: 512M of GTT memory ready. [drm] GART: num cpu pages 131072, num gpu pages 131072 ================================================================== BUG: KASAN: slab-out-of-bounds in radeon_atombios_parse_power_table_1_3+0x1837/0x1998 [radeon] Write of size 4 at addr ffff88810178d858 by task systemd-udevd/157

CPU: 0 PID: 157 Comm: systemd-udevd Not tainted 5.12.0-E620 #50 Hardware name: eMachines eMachines E620 /Nile , BIOS V1.03 09/30/2008 Call Trace: dump_stack+0xa5/0xe6 print_address_description.constprop.0+0x18/0x239 kasan_report+0x170/0x1a8 radeon_atombios_parse_power_table_1_3+0x1837/0x1998 [radeon] radeon_atombios_get_power_modes+0x144/0x1888 [radeon] radeon_pm_init+0x1019/0x1904 [radeon] rs690_init+0x76e/0x84a [radeon] radeon_device_init+0x1c1a/0x21e5 [radeon] radeon_driver_load_kms+0xf5/0x30b [radeon] drm_dev_register+0x255/0x4a0 [drm] radeon_pci_probe+0x246/0x2f6 [radeon] pci_device_probe+0x1aa/0x294 really_probe+0x30e/0x850 driver_probe_device+0xe6/0x135 device_driver_attach+0xc1/0xf8 __driver_attach+0x13f/0x146 bus_for_each_dev+0xfa/0x146 bus_add_driver+0x2b3/0x447 driver_register+0x242/0x2c1 do_one_initcall+0x149/0x2fd do_init_module+0x1ae/0x573 load_module+0x4dee/0x5cca __do_sys_finit_module+0xf1/0x140 do_syscall_64+0x33/0x40 entry_SYSCALL_64_after_hwframe+0x44/0xae

Without KASAN, this will manifest later when the kernel attempts to allocate memory that was stomped, since it collides with the inline slab freelist pointer:

invalid opcode: 0000 [#1] SMP NOPTI CPU: 0 PID: 781 Comm: openrc-run.sh Tainted: G W 5.10.12-gentoo-E620 #2 Hardware name: eMachines eMachines E620 /Nile , BIOS V1.03 09/30/2008 RIP: 0010:kfree+0x115/0x230 Code: 89 c5 e8 75 ea ff ff 48 8b 00 0f ba e0 09 72 63 e8 1f f4 ff ff 41 89 c4 48 8b 45 00 0f ba e0 10 72 0a 48 8b 45 08 a8 01 75 02 <0f> 0b 44 89 e1 48 c7 c2 00 f0 ff ff be 06 00 00 00 48 d3 e2 48 c7 RSP: 0018:ffffb42f40267e10 EFLAGS: 00010246 RAX: ffffd61280ee8d88 RBX: 0000000000000004 RCX: 000000008010000d RDX: 4000000000000000 RSI: ffffffffba1360b0 RDI: ffffd61280ee8d80 RBP: ffffd61280ee8d80 R08: ffffffffb91bebdf R09: 0000000000000000 R10: ffff8fe2c1047ac8 R11: 0000000000000000 R12: 0000000000000000 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000100 FS: 00007fe80eff6b68(0000) GS:ffff8fe339c00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fe80eec7bc0 CR3: 0000000038012000 CR4: 00000000000006f0 Call Trace: __free_fdtable+0x16/0x1f put_files_struct+0x81/0x9b do_exit+0x433/0x94d do_group_exit+0xa6/0xa6 __x64_sys_exit_group+0xf/0xf do_syscall_64+0x33/0x40 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0033:0x7fe80ef64bea Code: Unable to access opcode bytes at RIP 0x7fe80ef64bc0. RSP: 002b:00007ffdb1c47528 EFLAGS: 00000246 ORIG_RAX: 00000000000000e7 RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 00007fe80ef64bea RDX: 00007fe80ef64f60 RSI: 0000000000000000 RDI: 0000000000000000 RBP: 0000000000000000 R08: 0000000000000001 R09: 0000000000000000 R10: 00007fe80ee2c620 R11: 0000000000000246 R12: 00007fe80eff41e0 R13: 00000000ffffffff R14: 0000000000000024 R15: 00007fe80edf9cd0 Modules linked in: radeon(+) ath5k(+) snd_hda_codec_realtek ...

Use a valid power_state index when initializing the "flags" and "misc" and "misc2" fields.

Bug: https://bugzilla.kernel.org/show_bug.cgi?id=211537 Reported-by: Erhard F. erhard_f@mailbox.org Fixes: a48b9b4edb8b ("drm/radeon/kms/pm: add asic specific callbacks for getting power state (v2)") Fixes: 79daedc94281 ("drm/radeon/kms: minor pm cleanups") Signed-off-by: Kees Cook keescook@chromium.org Signed-off-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/radeon/radeon_atombios.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/radeon/radeon_atombios.c b/drivers/gpu/drm/radeon/radeon_atombios.c index 226a7bf0eb7a..97703449e049 100644 --- a/drivers/gpu/drm/radeon/radeon_atombios.c +++ b/drivers/gpu/drm/radeon/radeon_atombios.c @@ -2266,10 +2266,10 @@ static int radeon_atombios_parse_power_table_1_3(struct radeon_device *rdev) rdev->pm.default_power_state_index = state_index - 1; rdev->pm.power_state[state_index - 1].default_clock_mode = &rdev->pm.power_state[state_index - 1].clock_info[0]; - rdev->pm.power_state[state_index].flags &= + rdev->pm.power_state[state_index - 1].flags &= ~RADEON_PM_STATE_SINGLE_DISPLAY_ONLY; - rdev->pm.power_state[state_index].misc = 0; - rdev->pm.power_state[state_index].misc2 = 0; + rdev->pm.power_state[state_index - 1].misc = 0; + rdev->pm.power_state[state_index - 1].misc2 = 0; } return state_index; }

From: Miaohe Lin linmiaohe@huawei.com

[ Upstream commit 74e579bf231a337ab3786d59e64bc94f45ca7b3f ]

In writable and !referenced case, the result value should be SCAN_LACK_REFERENCED_PAGE for trace_mm_collapse_huge_page_isolate() instead of default 0 (SCAN_FAIL) here.

Link: https://lkml.kernel.org/r/20210306032947.35921-5-linmiaohe@huawei.com Fixes: 7d2eba0557c1 ("mm: add tracepoint for scanning pages") Signed-off-by: Miaohe Lin linmiaohe@huawei.com Acked-by: Kirill A. Shutemov kirill.shutemov@linux.intel.com Cc: Dan Carpenter dan.carpenter@oracle.com Cc: Ebru Akagunduz ebru.akagunduz@gmail.com Cc: Mike Kravetz mike.kravetz@oracle.com Cc: Rik van Riel riel@redhat.com Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- mm/khugepaged.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/mm/khugepaged.c b/mm/khugepaged.c index f0d7e6483ba3..3c2326568193 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -628,17 +628,17 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma, mmu_notifier_test_young(vma->vm_mm, address)) referenced++; } - if (likely(writable)) { - if (likely(referenced)) { - result = SCAN_SUCCEED; - trace_mm_collapse_huge_page_isolate(page, none_or_zero, - referenced, writable, result); - return 1; - } - } else { + + if (unlikely(!writable)) { result = SCAN_PAGE_RO; + } else if (unlikely(!referenced)) { + result = SCAN_LACK_REFERENCED_PAGE; + } else { + result = SCAN_SUCCEED; + trace_mm_collapse_huge_page_isolate(page, none_or_zero, + referenced, writable, result); + return 1; } - out: release_pte_pages(pte, _pte); trace_mm_collapse_huge_page_isolate(page, none_or_zero,

From: Miaohe Lin linmiaohe@huawei.com

[ Upstream commit 34f5e9b9d1990d286199084efa752530ee3d8297 ]

If the zone device page does not belong to un-addressable device memory, the variable entry will be uninitialized and lead to indeterminate pte entry ultimately. Fix this unexpected case and warn about it.

Link: https://lkml.kernel.org/r/20210325131524.48181-4-linmiaohe@huawei.com Fixes: df6ad69838fc ("mm/device-public-memory: device memory cache coherent with CPU") Signed-off-by: Miaohe Lin linmiaohe@huawei.com Reviewed-by: David Hildenbrand david@redhat.com Cc: Alistair Popple apopple@nvidia.com Cc: Jerome Glisse jglisse@redhat.com Cc: Rafael Aquini aquini@redhat.com Cc: Yang Shi shy828301@gmail.com Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- mm/migrate.c | 7 +++++++ 1 file changed, 7 insertions(+)

diff --git a/mm/migrate.c b/mm/migrate.c index c4c313e47f12..00bbe57c1ce2 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -2771,6 +2771,13 @@ static void migrate_vma_insert_page(struct migrate_vma *migrate,

swp_entry = make_device_private_entry(page, vma->vm_flags & VM_WRITE); entry = swp_entry_to_pte(swp_entry); + } else { + /* + * For now we only support migrating to un-addressable + * device memory. + */ + pr_warn_once("Unsupported ZONE_DEVICE page type.\n"); + goto abort; } } else { entry = mk_pte(page, vma->vm_page_prot);

From: Maciej Żenczykowski maze@google.com

[ Upstream commit 2c16db6c92b0ee4aa61e88366df82169e83c3f7e ]

Android userspace has been using TCA_KIND with a char[IFNAMESIZ] many-null-terminated buffer containing the string 'bpf'.

This works on 4.19 and ceases to work on 5.10.

I'm not entirely sure what fixes tag to use, but I think the issue was likely introduced in the below mentioned 5.4 commit.

Reported-by: Nucca Chen nuccachen@google.com Cc: Cong Wang xiyou.wangcong@gmail.com Cc: David Ahern dsahern@gmail.com Cc: David S. Miller davem@davemloft.net Cc: Jakub Kicinski jakub.kicinski@netronome.com Cc: Jamal Hadi Salim jhs@mojatatu.com Cc: Jiri Pirko jiri@mellanox.com Cc: Jiri Pirko jiri@resnulli.us Fixes: 62794fc4fbf5 ("net_sched: add max len check for TCA_KIND") Change-Id: I66dc281f165a2858fc29a44869a270a2d698a82b Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- lib/nlattr.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/lib/nlattr.c b/lib/nlattr.c index cace9b307781..0d84f79cb4b5 100644 --- a/lib/nlattr.c +++ b/lib/nlattr.c @@ -609,7 +609,7 @@ int nla_strcmp(const struct nlattr *nla, const char *str) int attrlen = nla_len(nla); int d;

- if (attrlen > 0 && buf[attrlen - 1] == '\0') + while (attrlen > 0 && buf[attrlen - 1] == '\0') attrlen--;

d = attrlen - len;

From: Pablo Neira Ayuso pablo@netfilter.org

[ Upstream commit 5e024c325406470d1165a09c6feaf8ec897936be ]

Do not assume that the tcph->doff field is correct when parsing for TCP options, skb_header_pointer() might fail to fetch these bits.

Fixes: 11eeef41d5f6 ("netfilter: passive OS fingerprint xtables match") Signed-off-by: Pablo Neira Ayuso pablo@netfilter.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/netfilter/nfnetlink_osf.c | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/net/netfilter/nfnetlink_osf.c b/net/netfilter/nfnetlink_osf.c index 916a3c7f9eaf..79fbf37291f3 100644 --- a/net/netfilter/nfnetlink_osf.c +++ b/net/netfilter/nfnetlink_osf.c @@ -186,6 +186,8 @@ static const struct tcphdr *nf_osf_hdr_ctx_init(struct nf_osf_hdr_ctx *ctx,

ctx->optp = skb_header_pointer(skb, ip_hdrlen(skb) + sizeof(struct tcphdr), ctx->optsize, opts); + if (!ctx->optp) + return NULL; }

return tcp;

From: Quentin Perret qperret@google.com

[ Upstream commit 6d2f8909a5fabb73fe2a63918117943986c39b6c ]

Util-clamp places tasks in different buckets based on their clamp values for performance reasons. However, the size of buckets is currently computed using a rounding division, which can lead to an off-by-one error in some configurations.

For instance, with 20 buckets, the bucket size will be 1024/20=51. A task with a clamp of 1024 will be mapped to bucket id 1024/51=20. Sadly, correct indexes are in range [0,19], hence leading to an out of bound memory access.

Clamp the bucket id to fix the issue.

Fixes: 69842cba9ace ("sched/uclamp: Add CPU's clamp buckets refcounting") Suggested-by: Qais Yousef qais.yousef@arm.com Signed-off-by: Quentin Perret qperret@google.com Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Reviewed-by: Vincent Guittot vincent.guittot@linaro.org Reviewed-by: Dietmar Eggemann dietmar.eggemann@arm.com Link: https://lkml.kernel.org/r/20210430151412.160913-1-qperret@google.com Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/sched/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 2ce61018e33b..a3e95d7779e1 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -820,7 +820,7 @@ DEFINE_STATIC_KEY_FALSE(sched_uclamp_used);

static inline unsigned int uclamp_bucket_id(unsigned int clamp_value) { - return clamp_value / UCLAMP_BUCKET_DELTA; + return min_t(unsigned int, clamp_value / UCLAMP_BUCKET_DELTA, UCLAMP_BUCKETS - 1); }

static inline unsigned int uclamp_bucket_base_value(unsigned int clamp_value)

From: Jia-Ju Bai baijiaju1990@gmail.com

[ Upstream commit 31d82c2c787d5cf65fedd35ebbc0c1bd95c1a679 ]

When vzalloc() returns NULL to sha_regions, no error return code of kexec_calculate_store_digests() is assigned. To fix this bug, ret is assigned with -ENOMEM in this case.

Link: https://lkml.kernel.org/r/20210309083904.24321-1-baijiaju1990@gmail.com Fixes: a43cac0d9dc2 ("kexec: split kexec_file syscall code to kexec_file.c") Signed-off-by: Jia-Ju Bai baijiaju1990@gmail.com Reported-by: TOTE Robot oslab@tsinghua.edu.cn Acked-by: Baoquan He bhe@redhat.com Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/kexec_file.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c index 4e74db89bd23..b17998fa03f1 100644 --- a/kernel/kexec_file.c +++ b/kernel/kexec_file.c @@ -740,8 +740,10 @@ static int kexec_calculate_store_digests(struct kimage *image)

sha_region_sz = KEXEC_SEGMENT_MAX * sizeof(struct kexec_sha_region); sha_regions = vzalloc(sha_region_sz); - if (!sha_regions) + if (!sha_regions) { + ret = -ENOMEM; goto out_free_desc; + }

desc->tfm = tfm;

From: Yunjian Wang wangyunjian@huawei.com

[ Upstream commit 38318f23a7ef86a8b1862e5e8078c4de121960c3 ]

Currently the call to i40e_client_del_instance frees the object pf->cinst, however pf->cinst->lan_info is being accessed after the free. Fix this by adding the missing return.

Addresses-Coverity: ("Read from pointer after free") Fixes: 7b0b1a6d0ac9 ("i40e: Disable iWARP VSI PETCP_ENA flag on netdev down events") Signed-off-by: Yunjian Wang wangyunjian@huawei.com Signed-off-by: Tony Nguyen anthony.l.nguyen@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/intel/i40e/i40e_client.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_client.c b/drivers/net/ethernet/intel/i40e/i40e_client.c index e81530ca08d0..5706abb3c0ea 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_client.c +++ b/drivers/net/ethernet/intel/i40e/i40e_client.c @@ -377,6 +377,7 @@ void i40e_client_subtask(struct i40e_pf *pf) clear_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state); i40e_client_del_instance(pf); + return; } } }

From: Mateusz Palczewski mateusz.palczewski@intel.com

[ Upstream commit 15395ec4685bd45a43d1b54b8fd9846b87e2c621 ]

Unlike other supported adapters, 2.5G and 5G use different PHY type identifiers for reading/writing PHY settings and for reading link status. This commit introduces separate PHY identifiers for these two operation types.

Fixes: 2e45d3f4677a ("i40e: Add support for X710 B/P & SFP+ cards") Signed-off-by: Dawid Lukwinski dawid.lukwinski@intel.com Signed-off-by: Mateusz Palczewski mateusz.palczewski@intel.com Reviewed-by: Aleksandr Loktionov aleksandr.loktionov@intel.com Tested-by: Dave Switzer david.switzer@intel.com Signed-off-by: Tony Nguyen anthony.l.nguyen@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h | 6 ++++-- drivers/net/ethernet/intel/i40e/i40e_common.c | 4 ++-- drivers/net/ethernet/intel/i40e/i40e_ethtool.c | 4 ++-- drivers/net/ethernet/intel/i40e/i40e_type.h | 7 ++----- 4 files changed, 10 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h index d7684ac2522e..57a8328e9b4f 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h +++ b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h @@ -1893,8 +1893,10 @@ enum i40e_aq_phy_type { I40E_PHY_TYPE_25GBASE_LR = 0x22, I40E_PHY_TYPE_25GBASE_AOC = 0x23, I40E_PHY_TYPE_25GBASE_ACC = 0x24, - I40E_PHY_TYPE_2_5GBASE_T = 0x30, - I40E_PHY_TYPE_5GBASE_T = 0x31, + I40E_PHY_TYPE_2_5GBASE_T = 0x26, + I40E_PHY_TYPE_5GBASE_T = 0x27, + I40E_PHY_TYPE_2_5GBASE_T_LINK_STATUS = 0x30, + I40E_PHY_TYPE_5GBASE_T_LINK_STATUS = 0x31, I40E_PHY_TYPE_MAX, I40E_PHY_TYPE_NOT_SUPPORTED_HIGH_TEMP = 0xFD, I40E_PHY_TYPE_EMPTY = 0xFE, diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c index 66f7deaf46ae..6475f78e85f6 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_common.c +++ b/drivers/net/ethernet/intel/i40e/i40e_common.c @@ -1156,8 +1156,8 @@ static enum i40e_media_type i40e_get_media_type(struct i40e_hw *hw) break; case I40E_PHY_TYPE_100BASE_TX: case I40E_PHY_TYPE_1000BASE_T: - case I40E_PHY_TYPE_2_5GBASE_T: - case I40E_PHY_TYPE_5GBASE_T: + case I40E_PHY_TYPE_2_5GBASE_T_LINK_STATUS: + case I40E_PHY_TYPE_5GBASE_T_LINK_STATUS: case I40E_PHY_TYPE_10GBASE_T: media = I40E_MEDIA_TYPE_BASET; break; diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index 502b4abc0aab..e4d0b7747e84 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -839,8 +839,8 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw, 10000baseT_Full); break; case I40E_PHY_TYPE_10GBASE_T: - case I40E_PHY_TYPE_5GBASE_T: - case I40E_PHY_TYPE_2_5GBASE_T: + case I40E_PHY_TYPE_5GBASE_T_LINK_STATUS: + case I40E_PHY_TYPE_2_5GBASE_T_LINK_STATUS: case I40E_PHY_TYPE_1000BASE_T: case I40E_PHY_TYPE_100BASE_TX: ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); diff --git a/drivers/net/ethernet/intel/i40e/i40e_type.h b/drivers/net/ethernet/intel/i40e/i40e_type.h index b43ec94a0f29..666a251e8c72 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_type.h +++ b/drivers/net/ethernet/intel/i40e/i40e_type.h @@ -253,11 +253,8 @@ struct i40e_phy_info { #define I40E_CAP_PHY_TYPE_25GBASE_ACC BIT_ULL(I40E_PHY_TYPE_25GBASE_ACC + \ I40E_PHY_TYPE_OFFSET) /* Offset for 2.5G/5G PHY Types value to bit number conversion */ -#define I40E_PHY_TYPE_OFFSET2 (-10) -#define I40E_CAP_PHY_TYPE_2_5GBASE_T BIT_ULL(I40E_PHY_TYPE_2_5GBASE_T + \ - I40E_PHY_TYPE_OFFSET2) -#define I40E_CAP_PHY_TYPE_5GBASE_T BIT_ULL(I40E_PHY_TYPE_5GBASE_T + \ - I40E_PHY_TYPE_OFFSET2) +#define I40E_CAP_PHY_TYPE_2_5GBASE_T BIT_ULL(I40E_PHY_TYPE_2_5GBASE_T) +#define I40E_CAP_PHY_TYPE_5GBASE_T BIT_ULL(I40E_PHY_TYPE_5GBASE_T) #define I40E_HW_CAP_MAX_GPIO 30 /* Capabilities of a PF or a VF or the whole device */ struct i40e_hw_capabilities {

From: Vladimir Isaev isaev@synopsys.com

commit c5f756d8c6265ebb1736a7787231f010a3b782e5 upstream.

32-bit PAGE_MASK can not be used as a mask for physical addresses when PAE is enabled. PAGE_MASK_PHYS must be used for physical addresses instead of PAGE_MASK.

Without this, init gets SIGSEGV if pte_modify was called:

| potentially unexpected fatal signal 11. | Path: /bin/busybox | CPU: 0 PID: 1 Comm: init Not tainted 5.12.0-rc5-00003-g1e43c377a79f-dirty | Insn could not be fetched | @No matching VMA found | ECR: 0x00040000 EFA: 0x00000000 ERET: 0x00000000 | STAT: 0x80080082 [IE U ] BTA: 0x00000000 | SP: 0x5f9ffe44 FP: 0x00000000 BLK: 0xaf3d4 | LPS: 0x000d093e LPE: 0x000d0950 LPC: 0x00000000 | r00: 0x00000002 r01: 0x5f9fff14 r02: 0x5f9fff20 | ... | Kernel panic - not syncing: Attempted to kill init! exitcode=0x0000000b

Signed-off-by: Vladimir Isaev isaev@synopsys.com Reported-by: kernel test robot lkp@intel.com Cc: Vineet Gupta vgupta@synopsys.com Cc: stable@vger.kernel.org Signed-off-by: Vineet Gupta vgupta@synopsys.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/arc/include/asm/page.h | 12 ++++++++++++ arch/arc/include/asm/pgtable.h | 12 +++--------- arch/arc/include/uapi/asm/page.h | 1 - arch/arc/mm/ioremap.c | 5 +++-- arch/arc/mm/tlb.c | 2 +- 5 files changed, 19 insertions(+), 13 deletions(-)

--- a/arch/arc/include/asm/page.h +++ b/arch/arc/include/asm/page.h @@ -7,6 +7,18 @@

#include <uapi/asm/page.h>

+#ifdef CONFIG_ARC_HAS_PAE40 + +#define MAX_POSSIBLE_PHYSMEM_BITS 40 +#define PAGE_MASK_PHYS (0xff00000000ull | PAGE_MASK) + +#else /* CONFIG_ARC_HAS_PAE40 */ + +#define MAX_POSSIBLE_PHYSMEM_BITS 32 +#define PAGE_MASK_PHYS PAGE_MASK + +#endif /* CONFIG_ARC_HAS_PAE40 */ + #ifndef __ASSEMBLY__

#define clear_page(paddr) memset((paddr), 0, PAGE_SIZE) --- a/arch/arc/include/asm/pgtable.h +++ b/arch/arc/include/asm/pgtable.h @@ -108,8 +108,8 @@ #define ___DEF (_PAGE_PRESENT | _PAGE_CACHEABLE)

/* Set of bits not changed in pte_modify */ -#define _PAGE_CHG_MASK (PAGE_MASK | _PAGE_ACCESSED | _PAGE_DIRTY | _PAGE_SPECIAL) - +#define _PAGE_CHG_MASK (PAGE_MASK_PHYS | _PAGE_ACCESSED | _PAGE_DIRTY | \ + _PAGE_SPECIAL) /* More Abbrevaited helpers */ #define PAGE_U_NONE __pgprot(___DEF) #define PAGE_U_R __pgprot(___DEF | _PAGE_READ) @@ -133,13 +133,7 @@ #define PTE_BITS_IN_PD0 (_PAGE_GLOBAL | _PAGE_PRESENT | _PAGE_HW_SZ) #define PTE_BITS_RWX (_PAGE_EXECUTE | _PAGE_WRITE | _PAGE_READ)

-#ifdef CONFIG_ARC_HAS_PAE40 -#define PTE_BITS_NON_RWX_IN_PD1 (0xff00000000 | PAGE_MASK | _PAGE_CACHEABLE) -#define MAX_POSSIBLE_PHYSMEM_BITS 40 -#else -#define PTE_BITS_NON_RWX_IN_PD1 (PAGE_MASK | _PAGE_CACHEABLE) -#define MAX_POSSIBLE_PHYSMEM_BITS 32 -#endif +#define PTE_BITS_NON_RWX_IN_PD1 (PAGE_MASK_PHYS | _PAGE_CACHEABLE)

/************************************************************************** * Mapping of vm_flags (Generic VM) to PTE flags (arch specific) --- a/arch/arc/include/uapi/asm/page.h +++ b/arch/arc/include/uapi/asm/page.h @@ -33,5 +33,4 @@

#define PAGE_MASK (~(PAGE_SIZE-1))

- #endif /* _UAPI__ASM_ARC_PAGE_H */ --- a/arch/arc/mm/ioremap.c +++ b/arch/arc/mm/ioremap.c @@ -53,9 +53,10 @@ EXPORT_SYMBOL(ioremap); void __iomem *ioremap_prot(phys_addr_t paddr, unsigned long size, unsigned long flags) { + unsigned int off; unsigned long vaddr; struct vm_struct *area; - phys_addr_t off, end; + phys_addr_t end; pgprot_t prot = __pgprot(flags);

/* Don't allow wraparound, zero size */ @@ -72,7 +73,7 @@ void __iomem *ioremap_prot(phys_addr_t p

/* Mappings have to be page-aligned */ off = paddr & ~PAGE_MASK; - paddr &= PAGE_MASK; + paddr &= PAGE_MASK_PHYS; size = PAGE_ALIGN(end + 1) - paddr;

/* --- a/arch/arc/mm/tlb.c +++ b/arch/arc/mm/tlb.c @@ -597,7 +597,7 @@ void update_mmu_cache(struct vm_area_str pte_t *ptep) { unsigned long vaddr = vaddr_unaligned & PAGE_MASK; - phys_addr_t paddr = pte_val(*ptep) & PAGE_MASK; + phys_addr_t paddr = pte_val(*ptep) & PAGE_MASK_PHYS; struct page *page = pfn_to_page(pte_pfn(*ptep));

create_tlb(vma, vaddr, ptep);

From: Michael Ellerman mpe@ellerman.id.au

commit aec86b052df6541cc97c5fca44e5934cbea4963b upstream.

The entry flush mitigation can be enabled/disabled at runtime via a debugfs file (entry_flush), which causes the kernel to patch itself to enable/disable the relevant mitigations.

However depending on which mitigation we're using, it may not be safe to do that patching while other CPUs are active. For example the following crash:

sleeper[15639]: segfault (11) at c000000000004c20 nip c000000000004c20 lr c000000000004c20

Shows that we returned to userspace with a corrupted LR that points into the kernel, due to executing the partially patched call to the fallback entry flush (ie. we missed the LR restore).

Fix it by doing the patching under stop machine. The CPUs that aren't doing the patching will be spinning in the core of the stop machine logic. That is currently sufficient for our purposes, because none of the patching we do is to that code or anywhere in the vicinity.

Fixes: f79643787e0a ("powerpc/64s: flush L1D on kernel entry") Cc: stable@vger.kernel.org # v5.10+ Signed-off-by: Michael Ellerman mpe@ellerman.id.au Link: https://lore.kernel.org/r/20210506044959.1298123-2-mpe@ellerman.id.au Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/powerpc/lib/feature-fixups.c | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-)

--- a/arch/powerpc/lib/feature-fixups.c +++ b/arch/powerpc/lib/feature-fixups.c @@ -293,8 +293,9 @@ void do_uaccess_flush_fixups(enum l1d_fl : "unknown"); }

-void do_entry_flush_fixups(enum l1d_flush_type types) +static int __do_entry_flush_fixups(void *data) { + enum l1d_flush_type types = *(enum l1d_flush_type *)data; unsigned int instrs[3], *dest; long *start, *end; int i; @@ -345,6 +346,19 @@ void do_entry_flush_fixups(enum l1d_flus : "ori type" : (types & L1D_FLUSH_MTTRIG) ? "mttrig type" : "unknown"); + + return 0; +} + +void do_entry_flush_fixups(enum l1d_flush_type types) +{ + /* + * The call to the fallback flush can not be safely patched in/out while + * other CPUs are executing it. So call __do_entry_flush_fixups() on one + * CPU while all other CPUs spin in the stop machine core with interrupts + * hard disabled. + */ + stop_machine(__do_entry_flush_fixups, &types, NULL); }

void do_rfi_flush_fixups(enum l1d_flush_type types)

From: Phillip Lougher phillip@squashfs.org.uk

commit d6e621de1fceb3b098ebf435ef7ea91ec4838a1a upstream.

Sysbot has reported a "divide error" which has been identified as being caused by a corrupted file_size value within the file inode. This value has been corrupted to a much larger value than expected.

Calculate_skip() is passed i_size_read(inode) >> msblk->block_log. Due to the file_size value corruption this overflows the int argument/variable in that function, leading to the divide error.

This patch changes the function to use u64. This will accommodate any unexpectedly large values due to corruption.

The value returned from calculate_skip() is clamped to be never more than SQUASHFS_CACHED_BLKS - 1, or 7. So file_size corruption does not lead to an unexpectedly large return result here.

Link: https://lkml.kernel.org/r/20210507152618.9447-1-phillip@squashfs.org.uk Signed-off-by: Phillip Lougher phillip@squashfs.org.uk Reported-by: syzbot+e8f781243ce16ac2f962@syzkaller.appspotmail.com Reported-by: syzbot+7b98870d4fec9447b951@syzkaller.appspotmail.com Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/squashfs/file.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)

--- a/fs/squashfs/file.c +++ b/fs/squashfs/file.c @@ -211,11 +211,11 @@ failure: * If the skip factor is limited in this way then the file will use multiple * slots. */ -static inline int calculate_skip(int blocks) +static inline int calculate_skip(u64 blocks) { - int skip = blocks / ((SQUASHFS_META_ENTRIES + 1) + u64 skip = blocks / ((SQUASHFS_META_ENTRIES + 1) * SQUASHFS_META_INDEXES); - return min(SQUASHFS_CACHED_BLKS - 1, skip + 1); + return min((u64) SQUASHFS_CACHED_BLKS - 1, skip + 1); }

From: Peter Xu peterx@redhat.com

commit 22247efd822e6d263f3c8bd327f3f769aea9b1d9 upstream.

Patch series "mm/hugetlb: Fix issues on file sealing and fork", v2.

Hugh reported issue with F_SEAL_FUTURE_WRITE not applied correctly to hugetlbfs, which I can easily verify using the memfd_test program, which seems that the program is hardly run with hugetlbfs pages (as by default shmem).

Meanwhile I found another probably even more severe issue on that hugetlb fork won't wr-protect child cow pages, so child can potentially write to parent private pages. Patch 2 addresses that.

After this series applied, "memfd_test hugetlbfs" should start to pass.

This patch (of 2):

F_SEAL_FUTURE_WRITE is missing for hugetlb starting from the first day. There is a test program for that and it fails constantly.

$ ./memfd_test hugetlbfs memfd-hugetlb: CREATE memfd-hugetlb: BASIC memfd-hugetlb: SEAL-WRITE memfd-hugetlb: SEAL-FUTURE-WRITE mmap() didn't fail as expected Aborted (core dumped)

I think it's probably because no one is really running the hugetlbfs test.

Fix it by checking FUTURE_WRITE also in hugetlbfs_file_mmap() as what we do in shmem_mmap(). Generalize a helper for that.

Link: https://lkml.kernel.org/r/20210503234356.9097-1-peterx@redhat.com Link: https://lkml.kernel.org/r/20210503234356.9097-2-peterx@redhat.com Fixes: ab3948f58ff84 ("mm/memfd: add an F_SEAL_FUTURE_WRITE seal to memfd") Signed-off-by: Peter Xu peterx@redhat.com Reported-by: Hugh Dickins hughd@google.com Reviewed-by: Mike Kravetz mike.kravetz@oracle.com Cc: Joel Fernandes (Google) joel@joelfernandes.org Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/hugetlbfs/inode.c | 5 +++++ include/linux/mm.h | 32 ++++++++++++++++++++++++++++++++ mm/shmem.c | 22 ++++------------------ 3 files changed, 41 insertions(+), 18 deletions(-)

--- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -135,6 +135,7 @@ static void huge_pagevec_release(struct static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma) { struct inode *inode = file_inode(file); + struct hugetlbfs_inode_info *info = HUGETLBFS_I(inode); loff_t len, vma_len; int ret; struct hstate *h = hstate_file(file); @@ -150,6 +151,10 @@ static int hugetlbfs_file_mmap(struct fi vma->vm_flags |= VM_HUGETLB | VM_DONTEXPAND; vma->vm_ops = &hugetlb_vm_ops;

+ ret = seal_check_future_write(info->seals, vma); + if (ret) + return ret; + /* * page based offset in vm_pgoff could be sufficiently large to * overflow a loff_t when converted to byte offset. This can --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2925,5 +2925,37 @@ static inline int pages_identical(struct return !memcmp_pages(page1, page2); }

+/** + * seal_check_future_write - Check for F_SEAL_FUTURE_WRITE flag and handle it + * @seals: the seals to check + * @vma: the vma to operate on + * + * Check whether F_SEAL_FUTURE_WRITE is set; if so, do proper check/handling on + * the vma flags. Return 0 if check pass, or <0 for errors. + */ +static inline int seal_check_future_write(int seals, struct vm_area_struct *vma) +{ + if (seals & F_SEAL_FUTURE_WRITE) { + /* + * New PROT_WRITE and MAP_SHARED mmaps are not allowed when + * "future write" seal active. + */ + if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_WRITE)) + return -EPERM; + + /* + * Since an F_SEAL_FUTURE_WRITE sealed memfd can be mapped as + * MAP_SHARED and read-only, take care to not allow mprotect to + * revert protections on such mappings. Do this only for shared + * mappings. For private mappings, don't need to mask + * VM_MAYWRITE as we still want them to be COW-writable. + */ + if (vma->vm_flags & VM_SHARED) + vma->vm_flags &= ~(VM_MAYWRITE); + } + + return 0; +} + #endif /* __KERNEL__ */ #endif /* _LINUX_MM_H */ --- a/mm/shmem.c +++ b/mm/shmem.c @@ -2208,25 +2208,11 @@ out_nomem: static int shmem_mmap(struct file *file, struct vm_area_struct *vma) { struct shmem_inode_info *info = SHMEM_I(file_inode(file)); + int ret;

- if (info->seals & F_SEAL_FUTURE_WRITE) { - /* - * New PROT_WRITE and MAP_SHARED mmaps are not allowed when - * "future write" seal active. - */ - if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_WRITE)) - return -EPERM; - - /* - * Since an F_SEAL_FUTURE_WRITE sealed memfd can be mapped as - * MAP_SHARED and read-only, take care to not allow mprotect to - * revert protections on such mappings. Do this only for shared - * mappings. For private mappings, don't need to mask - * VM_MAYWRITE as we still want them to be COW-writable. - */ - if (vma->vm_flags & VM_SHARED) - vma->vm_flags &= ~(VM_MAYWRITE); - } + ret = seal_check_future_write(info->seals, vma); + if (ret) + return ret;

file_accessed(file); vma->vm_ops = &shmem_vm_ops;

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

commit 4819d16d91145966ce03818a95169df1fd56b299 upstream.

Gen2 tiles are 2KiB in size so i915_gem_object_get_tile_row_size() can in fact return <4KiB, which leads to div-by-zero here. Avoid that.

Not sure i915_gem_object_get_tile_row_size() is entirely sane anyway since it doesn't account for the different tile layouts on i8xx/i915...

I'm not able to hit this before commit 6846895fde05 ("drm/i915: Replace PIN_NONFAULT with calls to PIN_NOEVICT") and it looks like I also need to run recent version of Mesa. With those in place xonotic trips on this quite easily on my 85x.

Cc: stable@vger.kernel.org Reviewed-by: Chris Wilson chris@chris-wilson.co.uk Signed-off-by: Ville Syrjälä ville.syrjala@linux.intel.com Link: https://patchwork.freedesktop.org/patch/msgid/20210421153401.13847-2-ville.s... (cherry picked from commit ed52c62d386f764194e0184fdb905d5f24194cae) Signed-off-by: Jani Nikula jani.nikula@intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/gpu/drm/i915/gem/i915_gem_mman.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c @@ -181,7 +181,7 @@ compute_partial_view(const struct drm_i9 struct i915_ggtt_view view;

if (i915_gem_object_is_tiled(obj)) - chunk = roundup(chunk, tile_row_pages(obj)); + chunk = roundup(chunk, tile_row_pages(obj) ?: 1);

view.type = I915_GGTT_VIEW_PARTIAL; view.partial.offset = rounddown(page_offset, chunk);

From: Christophe JAILLET christophe.jaillet@wanadoo.fr

[ Upstream commit a60a34366e0d09ca002c966dd7c43a68c28b1f82 ]

'retval' is known to be -ENODEV here. This is a hard-coded default error code which is not useful in the error message. Moreover, another error message is printed at the end of the error handling path. The corresponding error code (-ENOMEM) is more informative.

So remove simplify the first error message.

While at it, also remove the useless initialization of 'retval'.

Fixes: 7d50195f6c50 ("usb: host: Faraday fotg210-hcd driver") Signed-off-by: Christophe JAILLET christophe.jaillet@wanadoo.fr Link: https://lore.kernel.org/r/94531bcff98e46d4f9c20183a90b7f47f699126c.162033341... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/usb/host/fotg210-hcd.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/usb/host/fotg210-hcd.c b/drivers/usb/host/fotg210-hcd.c index 9e0c98d6bdb0..c3f74d6674e1 100644 --- a/drivers/usb/host/fotg210-hcd.c +++ b/drivers/usb/host/fotg210-hcd.c @@ -5571,7 +5571,7 @@ static int fotg210_hcd_probe(struct platform_device *pdev) struct usb_hcd *hcd; struct resource *res; int irq; - int retval = -ENODEV; + int retval; struct fotg210_hcd *fotg210;

if (usb_disabled()) @@ -5591,7 +5591,7 @@ static int fotg210_hcd_probe(struct platform_device *pdev) hcd = usb_create_hcd(&fotg210_fotg210_hc_driver, dev, dev_name(dev)); if (!hcd) { - dev_err(dev, "failed to create hcd with err %d\n", retval); + dev_err(dev, "failed to create hcd\n"); retval = -ENOMEM; goto fail_create_hcd; }

From: Christophe JAILLET christophe.jaillet@wanadoo.fr

[ Upstream commit 0c8bd174f0fc131bc9dfab35cd8784f59045da87 ]

If 'acpi_device_set_name()' fails, we must free 'acpi_device_bus_id->bus_id' or there is a (potential) memory leak.

Fixes: eb50aaf960e3 ("ACPI: scan: Use unique number for instance_no") Signed-off-by: Christophe JAILLET christophe.jaillet@wanadoo.fr Reviewed-by: Andy Shevchenko andriy.shevchenko@linux.intel.com Signed-off-by: Rafael J. Wysocki rafael.j.wysocki@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/acpi/scan.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c index dbb5919f23e2..95d119ff76b6 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -706,6 +706,7 @@ int acpi_device_add(struct acpi_device *device,

result = acpi_device_set_name(device, acpi_device_bus_id); if (result) { + kfree_const(acpi_device_bus_id->bus_id); kfree(acpi_device_bus_id); goto err_unlock; }

From: Sun Ke sunke32@huawei.com

[ Upstream commit 79ebe9110fa458d58f1fceb078e2068d7ad37390 ]

Open /dev/nbdX first, the config_refs will be 1 and the pointers in nbd_device are still null. Disconnect /dev/nbdX, then reference a null recv_workq. The protection by config_refs in nbd_genl_disconnect is useless.

[ 656.366194] BUG: kernel NULL pointer dereference, address: 0000000000000020 [ 656.368943] #PF: supervisor write access in kernel mode [ 656.369844] #PF: error_code(0x0002) - not-present page [ 656.370717] PGD 10cc87067 P4D 10cc87067 PUD 1074b4067 PMD 0 [ 656.371693] Oops: 0002 [#1] SMP [ 656.372242] CPU: 5 PID: 7977 Comm: nbd-client Not tainted 5.11.0-rc5-00040-g76c057c84d28 #1 [ 656.373661] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS ?-20190727_073836-buildvm-ppc64le-16.ppc.fedoraproject.org-3.fc31 04/01/2014 [ 656.375904] RIP: 0010:mutex_lock+0x29/0x60 [ 656.376627] Code: 00 0f 1f 44 00 00 55 48 89 fd 48 83 05 6f d7 fe 08 01 e8 7a c3 ff ff 48 83 05 6a d7 fe 08 01 31 c0 65 48 8b 14 25 00 6d 01 00 <f0> 48 0f b1 55 d [ 656.378934] RSP: 0018:ffffc900005eb9b0 EFLAGS: 00010246 [ 656.379350] RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000000 [ 656.379915] RDX: ffff888104cf2600 RSI: ffffffffaae8f452 RDI: 0000000000000020 [ 656.380473] RBP: 0000000000000020 R08: 0000000000000000 R09: ffff88813bd6b318 [ 656.381039] R10: 00000000000000c7 R11: fefefefefefefeff R12: ffff888102710b40 [ 656.381599] R13: ffffc900005eb9e0 R14: ffffffffb2930680 R15: ffff88810770ef00 [ 656.382166] FS: 00007fdf117ebb40(0000) GS:ffff88813bd40000(0000) knlGS:0000000000000000 [ 656.382806] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 656.383261] CR2: 0000000000000020 CR3: 0000000100c84000 CR4: 00000000000006e0 [ 656.383819] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 656.384370] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 656.384927] Call Trace: [ 656.385111] flush_workqueue+0x92/0x6c0 [ 656.385395] nbd_disconnect_and_put+0x81/0xd0 [ 656.385716] nbd_genl_disconnect+0x125/0x2a0 [ 656.386034] genl_family_rcv_msg_doit.isra.0+0x102/0x1b0 [ 656.386422] genl_rcv_msg+0xfc/0x2b0 [ 656.386685] ? nbd_ioctl+0x490/0x490 [ 656.386954] ? genl_family_rcv_msg_doit.isra.0+0x1b0/0x1b0 [ 656.387354] netlink_rcv_skb+0x62/0x180 [ 656.387638] genl_rcv+0x34/0x60 [ 656.387874] netlink_unicast+0x26d/0x590 [ 656.388162] netlink_sendmsg+0x398/0x6c0 [ 656.388451] ? netlink_rcv_skb+0x180/0x180 [ 656.388750] ____sys_sendmsg+0x1da/0x320 [ 656.389038] ? ____sys_recvmsg+0x130/0x220 [ 656.389334] ___sys_sendmsg+0x8e/0xf0 [ 656.389605] ? ___sys_recvmsg+0xa2/0xf0 [ 656.389889] ? handle_mm_fault+0x1671/0x21d0 [ 656.390201] __sys_sendmsg+0x6d/0xe0 [ 656.390464] __x64_sys_sendmsg+0x23/0x30 [ 656.390751] do_syscall_64+0x45/0x70 [ 656.391017] entry_SYSCALL_64_after_hwframe+0x44/0xa9

To fix it, just add if (nbd->recv_workq) to nbd_disconnect_and_put().

Fixes: e9e006f5fcf2 ("nbd: fix max number of supported devs") Signed-off-by: Sun Ke sunke32@huawei.com Reviewed-by: Josef Bacik josef@toxicpanda.com Link: https://lore.kernel.org/r/20210512114331.1233964-2-sunke32@huawei.com Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/block/nbd.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index e11fddcb73b9..839364371f9a 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -2016,7 +2016,8 @@ static void nbd_disconnect_and_put(struct nbd_device *nbd) * config ref and try to destroy the workqueue from inside the work * queue. */ - flush_workqueue(nbd->recv_workq); + if (nbd->recv_workq) + flush_workqueue(nbd->recv_workq); if (test_and_clear_bit(NBD_RT_HAS_CONFIG_REF, &nbd->config->runtime_flags)) nbd_config_put(nbd);

From: Christoph Hellwig hch@lst.de

commit 1cea335d1db1ce6ab71b3d2f94a807112b738a0f upstream.

bio completions can race when a page spans more than one file system block. Add a spinlock to synchronize marking the page uptodate.

Fixes: 9dc55f1389f9 ("iomap: add support for sub-pagesize buffered I/O without buffer heads") Reported-by: Jan Stancek jstancek@redhat.com Signed-off-by: Christoph Hellwig hch@lst.de Reviewed-by: Dave Chinner dchinner@redhat.com Reviewed-by: Darrick J. Wong darrick.wong@oracle.com Signed-off-by: Darrick J. Wong darrick.wong@oracle.com Cc: "Matthew Wilcox (Oracle)" willy@infradead.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/iomap/buffered-io.c | 34 ++++++++++++++++++++++++---------- include/linux/iomap.h | 1 + 2 files changed, 25 insertions(+), 10 deletions(-)

--- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -30,6 +30,7 @@ iomap_page_create(struct inode *inode, s iop = kmalloc(sizeof(*iop), GFP_NOFS | __GFP_NOFAIL); atomic_set(&iop->read_count, 0); atomic_set(&iop->write_count, 0); + spin_lock_init(&iop->uptodate_lock); bitmap_zero(iop->uptodate, PAGE_SIZE / SECTOR_SIZE);

/* @@ -118,25 +119,38 @@ iomap_adjust_read_range(struct inode *in }

static void -iomap_set_range_uptodate(struct page *page, unsigned off, unsigned len) +iomap_iop_set_range_uptodate(struct page *page, unsigned off, unsigned len) { struct iomap_page *iop = to_iomap_page(page); struct inode *inode = page->mapping->host; unsigned first = off >> inode->i_blkbits; unsigned last = (off + len - 1) >> inode->i_blkbits; - unsigned int i; bool uptodate = true; + unsigned long flags; + unsigned int i;

- if (iop) { - for (i = 0; i < PAGE_SIZE / i_blocksize(inode); i++) { - if (i >= first && i <= last) - set_bit(i, iop->uptodate); - else if (!test_bit(i, iop->uptodate)) - uptodate = false; - } + spin_lock_irqsave(&iop->uptodate_lock, flags); + for (i = 0; i < PAGE_SIZE / i_blocksize(inode); i++) { + if (i >= first && i <= last) + set_bit(i, iop->uptodate); + else if (!test_bit(i, iop->uptodate)) + uptodate = false; }

- if (uptodate && !PageError(page)) + if (uptodate) + SetPageUptodate(page); + spin_unlock_irqrestore(&iop->uptodate_lock, flags); +} + +static void +iomap_set_range_uptodate(struct page *page, unsigned off, unsigned len) +{ + if (PageError(page)) + return; + + if (page_has_private(page)) + iomap_iop_set_range_uptodate(page, off, len); + else SetPageUptodate(page); }

--- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -139,6 +139,7 @@ loff_t iomap_apply(struct inode *inode, struct iomap_page { atomic_t read_count; atomic_t write_count; + spinlock_t uptodate_lock; DECLARE_BITMAP(uptodate, PAGE_SIZE / 512); };

From: Ferry Toth ftoth@exalondelft.nl

commit 04357fafea9c7ed34525eb9680c760245c3bb958 upstream.

On Intel Merrifield LPM is causing host to reset port after a timeout. By disabling LPM entirely this is prevented.

Fixes: 066c09593454 ("usb: dwc3: pci: Enable extcon driver for Intel Merrifield") Reviewed-by: Andy Shevchenko andy.shevchenko@gmail.com Signed-off-by: Ferry Toth ftoth@exalondelft.nl Cc: stable stable@vger.kernel.org Link: https://lore.kernel.org/r/20210425150947.5862-1-ftoth@exalondelft.nl Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/usb/dwc3/dwc3-pci.c | 1 + 1 file changed, 1 insertion(+)

--- a/drivers/usb/dwc3/dwc3-pci.c +++ b/drivers/usb/dwc3/dwc3-pci.c @@ -138,6 +138,7 @@ static const struct property_entry dwc3_ PROPERTY_ENTRY_BOOL("snps,disable_scramble_quirk"), PROPERTY_ENTRY_BOOL("snps,dis_u3_susphy_quirk"), PROPERTY_ENTRY_BOOL("snps,dis_u2_susphy_quirk"), + PROPERTY_ENTRY_BOOL("snps,usb2-gadget-lpm-disable"), PROPERTY_ENTRY_BOOL("linux,sysdev_is_parent"), {} };

From: Phil Elwell phil@raspberrypi.com

commit 75a41ce46bae6cbe7d3bb2584eb844291d642874 upstream.

The dwc2 gadget support maps and unmaps DMA buffers as necessary. When mapping and unmapping it uses the direction of the endpoint to select the direction of the DMA transfer, but this fails for Control OUT transfers because the unmap occurs after the endpoint direction has been reversed for the status phase.

A possible solution would be to unmap the buffer before the direction is changed, but a safer, less invasive fix is to remember the buffer direction independently of the endpoint direction.

Fixes: fe0b94abcdf6 ("usb: dwc2: gadget: manage ep0 state in software") Acked-by: Minas Harutyunyan Minas.Harutyunyan@synopsys.com Cc: stable stable@vger.kernel.org Signed-off-by: Phil Elwell phil@raspberrypi.com Link: https://lore.kernel.org/r/20210506112200.2893922-1-phil@raspberrypi.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/usb/dwc2/core.h | 2 ++ drivers/usb/dwc2/gadget.c | 3 ++- 2 files changed, 4 insertions(+), 1 deletion(-)

--- a/drivers/usb/dwc2/core.h +++ b/drivers/usb/dwc2/core.h @@ -112,6 +112,7 @@ struct dwc2_hsotg_req; * @debugfs: File entry for debugfs file for this endpoint. * @dir_in: Set to true if this endpoint is of the IN direction, which * means that it is sending data to the Host. + * @map_dir: Set to the value of dir_in when the DMA buffer is mapped. * @index: The index for the endpoint registers. * @mc: Multi Count - number of transactions per microframe * @interval: Interval for periodic endpoints, in frames or microframes. @@ -161,6 +162,7 @@ struct dwc2_hsotg_ep { unsigned short fifo_index;

unsigned char dir_in; + unsigned char map_dir; unsigned char index; unsigned char mc; u16 interval; --- a/drivers/usb/dwc2/gadget.c +++ b/drivers/usb/dwc2/gadget.c @@ -421,7 +421,7 @@ static void dwc2_hsotg_unmap_dma(struct { struct usb_request *req = &hs_req->req;

- usb_gadget_unmap_request(&hsotg->gadget, req, hs_ep->dir_in); + usb_gadget_unmap_request(&hsotg->gadget, req, hs_ep->map_dir); }

/* @@ -1242,6 +1242,7 @@ static int dwc2_hsotg_map_dma(struct dwc { int ret;

+ hs_ep->map_dir = hs_ep->dir_in; ret = usb_gadget_map_request(&hsotg->gadget, req, hs_ep->dir_in); if (ret) goto dma_error;

From: Wesley Cheng wcheng@codeaurora.org

commit 18ffa988dbae69cc6e9949cddd9606f6fe533894 upstream.

If an error is received when issuing a start or update transfer command, the error handler will stop all active requests (including the current USB request), and call dwc3_gadget_giveback() to notify function drivers of the requests which have been stopped. Avoid returning an error for kick transfer during EP queue, to remove duplicate cleanup operations on the request being queued.

Fixes: 8d99087c2db8 ("usb: dwc3: gadget: Properly handle failed kick_transfer") cc: stable@vger.kernel.org Signed-off-by: Wesley Cheng wcheng@codeaurora.org Link: https://lore.kernel.org/r/1620410119-24971-1-git-send-email-wcheng@codeauror... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/usb/dwc3/gadget.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

--- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -1566,7 +1566,9 @@ static int __dwc3_gadget_ep_queue(struct } }

- return __dwc3_gadget_kick_transfer(dep); + __dwc3_gadget_kick_transfer(dep); + + return 0; }

static int dwc3_gadget_ep_queue(struct usb_ep *ep, struct usb_request *request,

From: Sandeep Singh sandeep.singh@amd.com

commit 3c128781d8da463761495aaf8898c9ecb4e71528 upstream.

One of AMD xhci controller require reset on resume. Occasionally AMD xhci controller does not respond to Stop endpoint command. Once the issue happens controller goes into bad state and in that case controller needs to be reset.

Cc: stable@vger.kernel.org Signed-off-by: Sandeep Singh sandeep.singh@amd.com Signed-off-by: Mathias Nyman mathias.nyman@linux.intel.com Link: https://lore.kernel.org/r/20210512080816.866037-6-mathias.nyman@linux.intel.... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/usb/host/xhci-pci.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

--- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -153,8 +153,10 @@ static void xhci_pci_quirks(struct devic (pdev->device == 0x15e0 || pdev->device == 0x15e1)) xhci->quirks |= XHCI_SNPS_BROKEN_SUSPEND;

- if (pdev->vendor == PCI_VENDOR_ID_AMD && pdev->device == 0x15e5) + if (pdev->vendor == PCI_VENDOR_ID_AMD && pdev->device == 0x15e5) { xhci->quirks |= XHCI_DISABLE_SPARSE; + xhci->quirks |= XHCI_RESET_ON_RESUME; + }

if (pdev->vendor == PCI_VENDOR_ID_AMD) xhci->quirks |= XHCI_TRUST_TX_LENGTH;

From: Colin Ian King colin.king@canonical.com

commit af0e1871d79cfbb91f732d2c6fa7558e45c31038 upstream.

The lux_val returned from tsl2583_get_lux can potentially be zero, so check for this to avoid a division by zero and an overflowed gain_trim_val.

Fixes clang scan-build warning:

drivers/iio/light/tsl2583.c:345:40: warning: Either the condition 'lux_val<0' is redundant or there is division by zero at line 345. [zerodivcond]

Fixes: ac4f6eee8fe8 ("staging: iio: TAOS tsl258x: Device driver") Signed-off-by: Colin Ian King colin.king@canonical.com Cc: Stable@vger.kernel.org Signed-off-by: Jonathan Cameron Jonathan.Cameron@huawei.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/iio/light/tsl2583.c | 8 ++++++++ 1 file changed, 8 insertions(+)

--- a/drivers/iio/light/tsl2583.c +++ b/drivers/iio/light/tsl2583.c @@ -341,6 +341,14 @@ static int tsl2583_als_calibrate(struct return lux_val; }

+ /* Avoid division by zero of lux_value later on */ + if (lux_val == 0) { + dev_err(&chip->client->dev, + "%s: lux_val of 0 will produce out of range trim_value\n", + __func__); + return -ENODATA; + } + gain_trim_val = (unsigned int)(((chip->als_settings.als_cal_target) * chip->als_settings.als_gain_trim) / lux_val); if ((gain_trim_val < 250) || (gain_trim_val > 4000)) {

From: Thomas Gleixner tglx@linutronix.de

commit 594b27e677b35f9734b1969d175ebc6146741109 upstream.

Nothing prevents the following:

pvclock_gtod_notify() queue_work(system_long_wq, &pvclock_gtod_work); ... remove_module(kvm); ... work_queue_run() pvclock_gtod_work() <- UAF

Ditto for any other operation on that workqueue list head which touches pvclock_gtod_work after module removal.

Cancel the work in kvm_arch_exit() to prevent that.

Fixes: 16e8d74d2da9 ("KVM: x86: notifier for clocksource changes") Signed-off-by: Thomas Gleixner tglx@linutronix.de Message-Id: 87czu4onry.ffs@nanos.tec.linutronix.de Cc: stable@vger.kernel.org Signed-off-by: Paolo Bonzini pbonzini@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/kvm/x86.c | 1 + 1 file changed, 1 insertion(+)

--- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -7356,6 +7356,7 @@ void kvm_arch_exit(void) cpuhp_remove_state_nocalls(CPUHP_AP_X86_KVM_CLK_ONLINE); #ifdef CONFIG_X86_64 pvclock_gtod_unregister_notifier(&pvclock_gtod_notifier); + cancel_work_sync(&pvclock_gtod_work); #endif kvm_x86_ops = NULL; kvm_mmu_module_exit();

From: Maciej W. Rozycki macro@orcam.me.uk

commit 193ced4a79599352d63cb8c9e2f0c6043106eb6a upstream.

Recent versions of the PCI Express specification have deprecated support for I/O transactions and actually some PCIe host bridges, such as Power Systems Host Bridge 4 (PHB4), do not implement them.

The default kernel configuration choice for the defxx driver is the use of I/O ports rather than MMIO for PCI and EISA systems. It may have made sense as a conservative backwards compatible choice back when MMIO operation support was added to the driver as a part of TURBOchannel bus support. However nowadays this configuration choice makes the driver unusable with systems that do not implement I/O transactions for PCIe.

Make DEFXX_MMIO the configuration default then, except where configured for EISA. This exception is because an EISA adapter can have its MMIO decoding disabled with ECU (EISA Configuration Utility) and therefore not available with the resource allocation infrastructure we implement, while port I/O is always readily available as it uses slot-specific addressing, directly mapped to the slot an option card has been placed in and handled with our EISA bus support core. Conversely a kernel that supports modern systems which may not have I/O transactions implemented for PCIe will usually not be expected to handle legacy EISA systems.

The change of the default will make it easier for people, including but not limited to distribution packagers, to make a working choice for the driver.

Update the option description accordingly and while at it replace the potentially ambiguous PIO acronym with IOP for "port I/O" vs "I/O ports" according to our nomenclature used elsewhere.

Signed-off-by: Maciej W. Rozycki macro@orcam.me.uk Fixes: e89a2cfb7d7b ("[TC] defxx: TURBOchannel support") Cc: stable@vger.kernel.org # v2.6.21+ Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/fddi/Kconfig | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-)

--- a/drivers/net/fddi/Kconfig +++ b/drivers/net/fddi/Kconfig @@ -40,17 +40,20 @@ config DEFXX

config DEFXX_MMIO bool - prompt "Use MMIO instead of PIO" if PCI || EISA + prompt "Use MMIO instead of IOP" if PCI || EISA depends on DEFXX - default n if PCI || EISA + default n if EISA default y ---help--- This instructs the driver to use EISA or PCI memory-mapped I/O - (MMIO) as appropriate instead of programmed I/O ports (PIO). + (MMIO) as appropriate instead of programmed I/O ports (IOP). Enabling this gives an improvement in processing time in parts - of the driver, but it may cause problems with EISA (DEFEA) - adapters. TURBOchannel does not have the concept of I/O ports, - so MMIO is always used for these (DEFTA) adapters. + of the driver, but it requires a memory window to be configured + for EISA (DEFEA) adapters that may not always be available. + Conversely some PCIe host bridges do not support IOP, so MMIO + may be required to access PCI (DEFPA) adapters on downstream PCI + buses with some systems. TURBOchannel does not have the concept + of I/O ports, so MMIO is always used for these (DEFTA) adapters.

If unsure, say N.

From: Maciej W. Rozycki macro@orcam.me.uk

commit c1d337d45ec0a802299688e17d568c4e3a585895 upstream.

We already check the high part of the divident against zero to avoid the costly DIVU instruction in that case, needed to reduce the high part of the divident, so we may well check against the divisor instead and set the high part of the quotient to zero right away. We need to treat the high part the divident in that case though as the remainder that would be calculated by the DIVU instruction we avoided.

This has passed correctness verification with test_div64 and reduced the module's average execution time down to 1.0445s and 0.2619s from 1.0668s and 0.2629s respectively for an R3400 CPU @40MHz and a 5Kc CPU @160MHz.

Signed-off-by: Maciej W. Rozycki macro@orcam.me.uk Signed-off-by: Thomas Bogendoerfer tsbogend@alpha.franken.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/mips/include/asm/div64.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)

--- a/arch/mips/include/asm/div64.h +++ b/arch/mips/include/asm/div64.h @@ -68,9 +68,11 @@ \ __high = __div >> 32; \ __low = __div; \ - __upper = __high; \ \ - if (__high) { \ + if (__high < __radix) { \ + __upper = __high; \ + __high = 0; \ + } else { \ __asm__("divu $0, %z1, %z2" \ : "=x" (__modquot) \ : "Jr" (__high), "Jr" (__radix)); \

From: Lukasz Luba lukasz.luba@arm.com

commit fef05776eb02238dcad8d5514e666a42572c3f32 upstream.

The tz->lock must be hold during the looping over the instances in that thermal zone. This lock was missing in the governor code since the beginning, so it's hard to point into a particular commit.

CC: stable@vger.kernel.org # 4.4+ Signed-off-by: Lukasz Luba lukasz.luba@arm.com Signed-off-by: Daniel Lezcano daniel.lezcano@linaro.org Link: https://lore.kernel.org/r/20210422153624.6074-2-lukasz.luba@arm.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/thermal/fair_share.c | 4 ++++ 1 file changed, 4 insertions(+)

--- a/drivers/thermal/fair_share.c +++ b/drivers/thermal/fair_share.c @@ -82,6 +82,8 @@ static int fair_share_throttle(struct th int total_instance = 0; int cur_trip_level = get_trip_level(tz);

+ mutex_lock(&tz->lock); + list_for_each_entry(instance, &tz->thermal_instances, tz_node) { if (instance->trip != trip) continue; @@ -110,6 +112,8 @@ static int fair_share_throttle(struct th mutex_unlock(&instance->cdev->lock); thermal_cdev_update(cdev); } + + mutex_unlock(&tz->lock); return 0; }

From: Ard Biesheuvel ardb@kernel.org

commit e9a2f8b599d0bc22a1b13e69527246ac39c697b4 upstream

Before moving the DT mapping out of the linear region, let's prepare for this change by removing all the phys-to-virt translations of the __atags_pointer variable, and perform this translation only once at setup time.

Tested-by: Linus Walleij linus.walleij@linaro.org Reviewed-by: Linus Walleij linus.walleij@linaro.org Acked-by: Nicolas Pitre nico@fluxnic.net Signed-off-by: Ard Biesheuvel ardb@kernel.org Signed-off-by: Russell King rmk+kernel@armlinux.org.uk Signed-off-by: Florian Fainelli f.fainelli@gmail.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/arm/include/asm/prom.h | 4 ++-- arch/arm/kernel/atags.h | 4 ++-- arch/arm/kernel/atags_parse.c | 6 +++--- arch/arm/kernel/devtree.c | 6 +++--- arch/arm/kernel/setup.c | 14 +++++++++----- arch/arm/mm/mmu.c | 4 ++-- 6 files changed, 21 insertions(+), 17 deletions(-)

--- a/arch/arm/include/asm/prom.h +++ b/arch/arm/include/asm/prom.h @@ -9,12 +9,12 @@

#ifdef CONFIG_OF

-extern const struct machine_desc *setup_machine_fdt(unsigned int dt_phys); +extern const struct machine_desc *setup_machine_fdt(void *dt_virt); extern void __init arm_dt_init_cpu_maps(void);

#else /* CONFIG_OF */

-static inline const struct machine_desc *setup_machine_fdt(unsigned int dt_phys) +static inline const struct machine_desc *setup_machine_fdt(void *dt_virt) { return NULL; } --- a/arch/arm/kernel/atags.h +++ b/arch/arm/kernel/atags.h @@ -2,11 +2,11 @@ void convert_to_tag_list(struct tag *tags);

#ifdef CONFIG_ATAGS -const struct machine_desc *setup_machine_tags(phys_addr_t __atags_pointer, +const struct machine_desc *setup_machine_tags(void *__atags_vaddr, unsigned int machine_nr); #else static inline const struct machine_desc * __init __noreturn -setup_machine_tags(phys_addr_t __atags_pointer, unsigned int machine_nr) +setup_machine_tags(void *__atags_vaddr, unsigned int machine_nr) { early_print("no ATAGS support: can't continue\n"); while (true); --- a/arch/arm/kernel/atags_parse.c +++ b/arch/arm/kernel/atags_parse.c @@ -176,7 +176,7 @@ static void __init squash_mem_tags(struc }

const struct machine_desc * __init -setup_machine_tags(phys_addr_t __atags_pointer, unsigned int machine_nr) +setup_machine_tags(void *atags_vaddr, unsigned int machine_nr) { struct tag *tags = (struct tag *)&default_tags; const struct machine_desc *mdesc = NULL, *p; @@ -197,8 +197,8 @@ setup_machine_tags(phys_addr_t __atags_p if (!mdesc) return NULL;

- if (__atags_pointer) - tags = phys_to_virt(__atags_pointer); + if (atags_vaddr) + tags = atags_vaddr; else if (mdesc->atag_offset) tags = (void *)(PAGE_OFFSET + mdesc->atag_offset);

--- a/arch/arm/kernel/devtree.c +++ b/arch/arm/kernel/devtree.c @@ -203,12 +203,12 @@ static const void * __init arch_get_next

/** * setup_machine_fdt - Machine setup when an dtb was passed to the kernel - * @dt_phys: physical address of dt blob + * @dt_virt: virtual address of dt blob * * If a dtb was passed to the kernel in r2, then use it to choose the * correct machine_desc and to setup the system. */ -const struct machine_desc * __init setup_machine_fdt(unsigned int dt_phys) +const struct machine_desc * __init setup_machine_fdt(void *dt_virt) { const struct machine_desc *mdesc, *mdesc_best = NULL;

@@ -221,7 +221,7 @@ const struct machine_desc * __init setup mdesc_best = &__mach_desc_GENERIC_DT; #endif

- if (!dt_phys || !early_init_dt_verify(phys_to_virt(dt_phys))) + if (!dt_virt || !early_init_dt_verify(dt_virt)) return NULL;

mdesc = of_flat_dt_match_machine(mdesc_best, arch_get_next_mach); --- a/arch/arm/kernel/setup.c +++ b/arch/arm/kernel/setup.c @@ -89,6 +89,7 @@ unsigned int cacheid __read_mostly; EXPORT_SYMBOL(cacheid);

unsigned int __atags_pointer __initdata; +void *atags_vaddr __initdata;

unsigned int system_rev; EXPORT_SYMBOL(system_rev); @@ -1075,19 +1076,22 @@ void __init hyp_mode_check(void)

void __init setup_arch(char **cmdline_p) { - const struct machine_desc *mdesc; + const struct machine_desc *mdesc = NULL; + + if (__atags_pointer) + atags_vaddr = phys_to_virt(__atags_pointer);

setup_processor(); - mdesc = setup_machine_fdt(__atags_pointer); + if (atags_vaddr) + mdesc = setup_machine_fdt(atags_vaddr); if (!mdesc) - mdesc = setup_machine_tags(__atags_pointer, __machine_arch_type); + mdesc = setup_machine_tags(atags_vaddr, __machine_arch_type); if (!mdesc) { early_print("\nError: invalid dtb and unrecognized/unsupported machine ID\n"); early_print(" r1=0x%08x, r2=0x%08x\n", __machine_arch_type, __atags_pointer); if (__atags_pointer) - early_print(" r2[]=%*ph\n", 16, - phys_to_virt(__atags_pointer)); + early_print(" r2[]=%*ph\n", 16, atags_vaddr); dump_machine_table(); }

--- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -1512,7 +1512,7 @@ static void __init map_lowmem(void) }

#ifdef CONFIG_ARM_PV_FIXUP -extern unsigned long __atags_pointer; +extern void *atags_vaddr; typedef void pgtables_remap(long long offset, unsigned long pgd, void *bdata); pgtables_remap lpae_pgtables_remap_asm;

@@ -1543,7 +1543,7 @@ static void __init early_paging_init(con */ lpae_pgtables_remap = (pgtables_remap *)(unsigned long)__pa(lpae_pgtables_remap_asm); pa_pgd = __pa(swapper_pg_dir); - boot_data = __va(__atags_pointer); + boot_data = atags_vaddr; barrier();

pr_info("Switching physical address space to 0x%08llx\n",

From: Ard Biesheuvel ardb@kernel.org

commit fc2933c133744305236793025b00c2f7d258b687 upstream

Commit

149a3ffe62b9dbc3 ("9012/1: move device tree mapping out of linear region")

created a permanent, read-only section mapping of the device tree blob provided by the firmware, and added a set of macros to get the base and size of the virtually mapped FDT based on the physical address. However, while the mapping code uses the SECTION_SIZE macro correctly, the macros use PMD_SIZE instead, which means something entirely different on ARM when using short descriptors, and is therefore not the right quantity to use here. So replace PMD_SIZE with SECTION_SIZE. While at it, change the names of the macro and its parameter to clarify that it returns the virtual address of the start of the FDT, based on the physical address in memory.

Tested-by: Joel Stanley joel@jms.id.au Tested-by: Marek Szyprowski m.szyprowski@samsung.com Signed-off-by: Ard Biesheuvel ardb@kernel.org Signed-off-by: Russell King rmk+kernel@armlinux.org.uk Signed-off-by: Florian Fainelli f.fainelli@gmail.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/arm/include/asm/memory.h | 6 +++--- arch/arm/kernel/setup.c | 2 +- 2 files changed, 4 insertions(+), 4 deletions(-)

--- a/arch/arm/include/asm/memory.h +++ b/arch/arm/include/asm/memory.h @@ -68,8 +68,8 @@ #define XIP_VIRT_ADDR(physaddr) (MODULES_VADDR + ((physaddr) & 0x000fffff))

#define FDT_FIXED_BASE UL(0xff800000) -#define FDT_FIXED_SIZE (2 * PMD_SIZE) -#define FDT_VIRT_ADDR(physaddr) ((void *)(FDT_FIXED_BASE | (physaddr) % PMD_SIZE)) +#define FDT_FIXED_SIZE (2 * SECTION_SIZE) +#define FDT_VIRT_BASE(physbase) ((void *)(FDT_FIXED_BASE | (physbase) % SECTION_SIZE))

#if !defined(CONFIG_SMP) && !defined(CONFIG_ARM_LPAE) /* @@ -111,7 +111,7 @@ extern unsigned long vectors_base; #define MODULES_VADDR PAGE_OFFSET

#define XIP_VIRT_ADDR(physaddr) (physaddr) -#define FDT_VIRT_ADDR(physaddr) ((void *)(physaddr)) +#define FDT_VIRT_BASE(physbase) ((void *)(physbase))

#endif /* !CONFIG_MMU */

--- a/arch/arm/kernel/setup.c +++ b/arch/arm/kernel/setup.c @@ -1080,7 +1080,7 @@ void __init setup_arch(char **cmdline_p) void *atags_vaddr = NULL;

if (__atags_pointer) - atags_vaddr = FDT_VIRT_ADDR(__atags_pointer); + atags_vaddr = FDT_VIRT_BASE(__atags_pointer);

setup_processor(); if (atags_vaddr) {

From: Badhri Jagan Sridharan badhri@google.com

commit 374157ff88ae1a7f7927331cbc72c1ec11994e8a upstream.

"usb: typec: tcpm: Address incorrect values of tcpm psy for pps supply" introduced a regression for req_out_volt and req_op_curr calculation.

req_out_volt should consider the newly calculated max voltage instead of previously accepted max voltage by the port partner. Likewise, req_op_curr should consider the newly calculated max current instead of previously accepted max current by the port partner.

Fixes: e3a072022487 ("usb: typec: tcpm: Address incorrect values of tcpm psy for pps supply") Reviewed-by: Guenter Roeck linux@roeck-us.net Signed-off-by: Badhri Jagan Sridharan badhri@google.com Link: https://lore.kernel.org/r/20210415050121.1928298-1-badhri@google.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/usb/typec/tcpm/tcpm.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)

--- a/drivers/usb/typec/tcpm/tcpm.c +++ b/drivers/usb/typec/tcpm/tcpm.c @@ -2339,10 +2339,10 @@ static unsigned int tcpm_pd_select_pps_a port->pps_data.req_max_volt = min(pdo_pps_apdo_max_voltage(src), pdo_pps_apdo_max_voltage(snk)); port->pps_data.req_max_curr = min_pps_apdo_current(src, snk); - port->pps_data.req_out_volt = min(port->pps_data.max_volt, - max(port->pps_data.min_volt, + port->pps_data.req_out_volt = min(port->pps_data.req_max_volt, + max(port->pps_data.req_min_volt, port->pps_data.req_out_volt)); - port->pps_data.req_op_curr = min(port->pps_data.max_curr, + port->pps_data.req_op_curr = min(port->pps_data.req_max_curr, port->pps_data.req_op_curr); }

From: Jonathon Reinhart jonathon.reinhart@gmail.com

commit 2671fa4dc0109d3fb581bc3078fdf17b5d9080f6 upstream.

These sysctls point to global variables: - NF_SYSCTL_CT_MAX (&nf_conntrack_max) - NF_SYSCTL_CT_EXPECT_MAX (&nf_ct_expect_max) - NF_SYSCTL_CT_BUCKETS (&nf_conntrack_htable_size_user)

Because their data pointers are not updated to point to per-netns structures, they must be marked read-only in a non-init_net ns. Otherwise, changes in any net namespace are reflected in (leaked into) all other net namespaces. This problem has existed since the introduction of net namespaces.

The current logic marks them read-only only if the net namespace is owned by an unprivileged user (other than init_user_ns).

Commit d0febd81ae77 ("netfilter: conntrack: re-visit sysctls in unprivileged namespaces") "exposes all sysctls even if the namespace is unpriviliged." Since we need to mark them readonly in any case, we can forego the unprivileged user check altogether.

Fixes: d0febd81ae77 ("netfilter: conntrack: re-visit sysctls in unprivileged namespaces") Signed-off-by: Jonathon Reinhart Jonathon.Reinhart@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/netfilter/nf_conntrack_standalone.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)

--- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -1071,8 +1071,11 @@ static int nf_conntrack_standalone_init_ #endif }

- if (!net_eq(&init_net, net)) + if (!net_eq(&init_net, net)) { + table[NF_SYSCTL_CT_MAX].mode = 0444; + table[NF_SYSCTL_CT_EXPECT_MAX].mode = 0444; table[NF_SYSCTL_CT_BUCKETS].mode = 0444; + }

net->ct.sysctl_header = register_net_sysctl(net, "net/netfilter", table); if (!net->ct.sysctl_header)

From: Christoph Hellwig hch@lst.de

commit 53fe2a30bc168db9700e00206d991ff934973cf1 upstream.

Do not call nvme_configure_apst when the controller is not live, given that nvme_configure_apst will fail due the lack of an admin queue when the controller is being torn down and nvme_set_latency_tolerance is called from dev_pm_qos_hide_latency_tolerance.

Fixes: 510a405d945b("nvme: fix memory leak for power latency tolerance") Reported-by: Peng Liu liupeng17@lenovo.com Signed-off-by: Christoph Hellwig hch@lst.de Reviewed-by: Keith Busch kbusch@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/nvme/host/core.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

--- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -2414,7 +2414,8 @@ static void nvme_set_latency_tolerance(s

if (ctrl->ps_max_latency_us != latency) { ctrl->ps_max_latency_us = latency; - nvme_configure_apst(ctrl); + if (ctrl->state == NVME_CTRL_LIVE) + nvme_configure_apst(ctrl); } }