firmware: dmi: Use the proper accessor for the version field
Subsystems (9)
Sasha Levin
maintainerPATCH 1/23 firmware: dmi: Use the proper accessor for the version field
From: Andy Shevchenko <[email protected]>
[ Upstream commit d2139dfca361a1f5bfc4d4a23455b1a409a69cd4 ]
The byte at offset 6 represents length. Don't take it and drop it immediately by using proper accessor, i.e. get_unaligned_be24().
[JD: Change the subject to something less frightening]
--- drivers/firmware/dmi_scan.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/firmware/dmi_scan.c +1 -1
@@ -630,7 +630,7 @@ static int __init dmi_smbios3_present(const u8 *buf) {if (memcmp (buf,"_SM3_" ,5 ) ==0 && buf[6 ] <32 &&dmi_checksum (buf, buf[6 ])) { - dmi_ver =get_unaligned_be32 (buf +6 ) &0xFFFFFF ; + dmi_ver =get_unaligned_be24 (buf +7 ); dmi_num =0 ;/* No longer specified */ dmi_len =get_unaligned_le32 (buf +12 ); dmi_base =get_unaligned_le64 (buf +16 );
Signature · 1 line
2.35.1
Sasha Levin
maintainerPATCH 2/23 scsi: qla2xxx: Disable ATIO interrupt coalesce for quad port ISP27XX
From: Tony Battersby <[email protected]>
[ Upstream commit 53661ded2460b414644532de6b99bd87f71987e9 ]
This partially reverts commit d2b292c3f6fd ("scsi: qla2xxx: Enable ATIO interrupt handshake for ISP27XX")
For some workloads where the host sends a batch of commands and then pauses, ATIO interrupt coalesce can cause some incoming ATIO entries to be ignored for extended periods of time, resulting in slow performance, timeouts, and aborted commands.
Disable interrupt coalesce and re-enable the dedicated ATIO MSI-X interrupt.
--- drivers/scsi/qla2xxx/qla_target.c | 10 ++-------- 1 file changed, 2 insertions(+), 8 deletions(-)
drivers/scsi/qla2xxx/qla_target.c +2 -8
@@ -6961,14 +6961,8 @@ qlt_24xx_config_rings(struct scsi_qla_host *vha)if (ha->flags.msix_enabled) {if (IS_QLA83XX (ha) ||IS_QLA27XX (ha) ||IS_QLA28XX (ha)) { -if (IS_QLA2071 (ha)) { -/* 4 ports Baker: Enable Interrupt Handshake */ - icb->msix_atio =0 ; - icb->firmware_options_2 |=cpu_to_le32 (BIT_26 ); - }else { - icb->msix_atio =cpu_to_le16 (msix->entry); - icb->firmware_options_2 &=cpu_to_le32 (~BIT_26 ); - } + icb->msix_atio =cpu_to_le16 (msix->entry); + icb->firmware_options_2 &=cpu_to_le32 (~BIT_26 );ql_dbg (ql_dbg_init, vha,0xf072 ,"Registering ICB vector 0x%x for atio que.\n" , msix->entry);
Signature · 1 line
2.35.1
Sasha Levin
maintainerPATCH 3/23 scsi: megaraid_sas: Fix double kfree()
In reply to Sasha LevinFrom: Guixin Liu <[email protected]>
[ Upstream commit 8c499e49240bd93628368c3588975cfb94169b8b ]
When allocating log_to_span fails, kfree(instance->ctrl_context) is called twice. Remove redundant call.
--- drivers/scsi/megaraid/megaraid_sas_fusion.c | 1 - 1 file changed, 1 deletion(-)
drivers/scsi/megaraid/megaraid_sas_fusion.c +0 -1
@@ -5279,7 +5279,6 @@ megasas_alloc_fusion_context(struct megasas_instance *instance)if (!fusion->log_to_span) {dev_err (&instance->pdev->dev,"Failed from %s %d\n" , __func__, __LINE__); -kfree (instance->ctrl_context);return -ENOMEM ; } }
Signature · 1 line
2.35.1
Sasha Levin
maintainerPATCH 4/23 drm/gem: Fix GEM handle release errors
In reply to Sasha LevinFrom: Jeffy Chen <[email protected]>
[ Upstream commit ea2aa97ca37a9044ade001aef71dbc06318e8d44 ]
Currently we are assuming a one to one mapping between dmabuf and GEM handle when releasing GEM handles.
But that is not always true, since we would create extra handles for the GEM obj in cases like gem_open() and getfb{,2}().
A similar issue was reported at:
https://lore.kernel.org/all/[email protected]/
Another problem is that the imported dmabuf might not always have gem_obj->dma_buf set, which would cause leaks in drm_gem_remove_prime_handles().
Let's fix these for now by using handle to find the exact map to remove.
--- drivers/gpu/drm/drm_gem.c | 17 +---------------- drivers/gpu/drm/drm_internal.h | 4 ++-- drivers/gpu/drm/drm_prime.c | 20 ++++++++++++-------- 3 files changed, 15 insertions(+), 26 deletions(-)
drivers/gpu/drm/drm_gem.c +1 -16
@@ -167,21 +167,6 @@ void drm_gem_private_object_init(struct drm_device *dev, }EXPORT_SYMBOL (drm_gem_private_object_init); -static void -drm_gem_remove_prime_handles (struct drm_gem_object *obj,struct drm_file *filp) -{ -/* -* Note: obj->dma_buf can't disappear as long as we still hold a -* handle reference in obj->handle_count. -*/ -mutex_lock (&filp->prime.lock); -if (obj->dma_buf) { -drm_prime_remove_buf_handle_locked (&filp->prime, - obj->dma_buf); - } -mutex_unlock (&filp->prime.lock); -} -/** * drm_gem_object_handle_free - release resources bound to userspace handles * @obj: GEM object to clean up.
@@ -252,7 +237,7 @@ drm_gem_object_release_handle(int id, void *ptr, void *data)if (obj->funcs->close) obj->funcs->close (obj, file_priv); -drm_gem_remove_prime_handles (obj, file_priv); +drm_prime_remove_buf_handle (&file_priv->prime, id);drm_vma_node_revoke (&obj->vma_node, file_priv);drm_gem_object_handle_put_unlocked (obj);
drivers/gpu/drm/drm_internal.h +2 -2
@@ -74,8 +74,8 @@ int drm_prime_fd_to_handle_ioctl(struct drm_device *dev, void *data,void drm_prime_init_file_private (struct drm_prime_file_private *prime_fpriv);void drm_prime_destroy_file_private (struct drm_prime_file_private *prime_fpriv); -void drm_prime_remove_buf_handle_locked (struct drm_prime_file_private *prime_fpriv, -struct dma_buf *dma_buf); +void drm_prime_remove_buf_handle (struct drm_prime_file_private *prime_fpriv, +uint32_t handle);/* drm_drv.c */ struct drm_minor *drm_minor_acquire (unsigned int minor_id);
drivers/gpu/drm/drm_prime.c +12 -8
@@ -187,29 +187,33 @@ static int drm_prime_lookup_buf_handle(struct drm_prime_file_private *prime_fprireturn -ENOENT ; } -void drm_prime_remove_buf_handle_locked (struct drm_prime_file_private *prime_fpriv, -struct dma_buf *dma_buf) +void drm_prime_remove_buf_handle (struct drm_prime_file_private *prime_fpriv, +uint32_t handle) {struct rb_node *rb; - rb = prime_fpriv->dmabufs.rb_node; +mutex_lock (&prime_fpriv->lock); + + rb = prime_fpriv->handles.rb_node;while (rb) {struct drm_prime_member *member; - member = rb_entry(rb, struct drm_prime_member, dmabuf_rb); -if (member->dma_buf == dma_buf) { + member = rb_entry(rb, struct drm_prime_member, handle_rb); +if (member->handle == handle) {rb_erase (&member->handle_rb, &prime_fpriv->handles);rb_erase (&member->dmabuf_rb, &prime_fpriv->dmabufs); -dma_buf_put (dma_buf); +dma_buf_put (member->dma_buf);kfree (member); -return ; - }else if (member->dma_buf < dma_buf) { +break ; + }else if (member->handle < handle) { rb = rb->rb_right; }else { rb = rb->rb_left; } } + +mutex_unlock (&prime_fpriv->lock); }void drm_prime_init_file_private (struct drm_prime_file_private *prime_fpriv)
Signature · 1 line
2.35.1
Sasha Levin
maintainerPATCH 5/23 perf/x86/core: Set pebs_capable and PMU_FL_PEBS_ALL for the Baseline
In reply to Sasha LevinFrom: Peter Zijlstra <[email protected]>
[ Upstream commit 7d3598868aaee05eb738d1c3115616b867e7530a ]
The SDM explicitly states that PEBS Baseline implies Extended PEBS. For cpu model forward compatibility (e.g. on ICX, SPR, ADL), it's safe to stop doing FMS table thing such as setting pebs_capable and PMU_FL_PEBS_ALL since it's already set in the intel_ds_init().
The Goldmont Plus is the only platform which supports extended PEBS but doesn't have Baseline. Keep the status quo.
--- arch/x86/events/intel/core.c | 2 -- arch/x86/events/intel/ds.c | 1 + 2 files changed, 1 insertion(+), 2 deletions(-)
arch/x86/events/intel/core.c +0 -2
@@ -6122,7 +6122,6 @@ __init int intel_pmu_init(void) x86_pmu.pebs_block = true; x86_pmu.flags |=PMU_FL_HAS_RSP_1 ; x86_pmu.flags |=PMU_FL_NO_HT_SHARING ; - x86_pmu.flags |=PMU_FL_PEBS_ALL ; x86_pmu.flags |=PMU_FL_INSTR_LATENCY ; x86_pmu.flags |=PMU_FL_MEM_LOADS_AUX ;
@@ -6164,7 +6163,6 @@ __init int intel_pmu_init(void) x86_pmu.pebs_block = true; x86_pmu.flags |=PMU_FL_HAS_RSP_1 ; x86_pmu.flags |=PMU_FL_NO_HT_SHARING ; - x86_pmu.flags |=PMU_FL_PEBS_ALL ; x86_pmu.flags |=PMU_FL_INSTR_LATENCY ; x86_pmu.flags |=PMU_FL_MEM_LOADS_AUX ; x86_pmu.lbr_pt_coexist = true;
arch/x86/events/intel/ds.c +1 -0
@@ -2211,6 +2211,7 @@ void __init intel_ds_init(void)PERF_SAMPLE_BRANCH_STACK |PERF_SAMPLE_TIME ; x86_pmu.flags |=PMU_FL_PEBS_ALL ; + x86_pmu.pebs_capable = ~0ULL ; pebs_qual ="-baseline" ;x86_get_pmu (smp_processor_id ())->capabilities |=PERF_PMU_CAP_EXTENDED_REGS ; }else {
Signature · 1 line
2.35.1
Sasha Levin
maintainerPATCH 6/23 drm/amdgpu: Move psp_xgmi_terminate call from amdgpu_xgmi_remove_device to psp_hw_fini
In reply to Sasha LevinFrom: YiPeng Chai <[email protected]>
[ Upstream commit 9d705d7741ae70764f3d6d87e67fad3b5c30ffd0 ]
V1:
The amdgpu_xgmi_remove_device function will send unload command to psp through psp ring to terminate xgmi, but psp ring has been destroyed in psp_hw_fini.
V2:
1. Change the commit title.
2. Restore amdgpu_xgmi_remove_device to its original calling location. Move psp_xgmi_terminate call from amdgpu_xgmi_remove_device to psp_hw_fini.
--- drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c | 3 +++ drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c | 2 +- 2 files changed, 4 insertions(+), 1 deletion(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c +3 -0
@@ -2729,6 +2729,9 @@ static int psp_hw_fini(void *handle)psp_rap_terminate (psp);psp_dtm_terminate (psp);psp_hdcp_terminate (psp); + +if (adev->gmc.xgmi.num_physical_nodes >1 ) +psp_xgmi_terminate (psp); }psp_asd_unload (psp);
drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c +1 -1
@@ -723,7 +723,7 @@ int amdgpu_xgmi_remove_device(struct amdgpu_device *adev)amdgpu_put_xgmi_hive (hive); } -return psp_xgmi_terminate (&adev->psp); +return 0 ; }static int amdgpu_xgmi_ras_late_init (struct amdgpu_device *adev)
Signature · 1 line
2.35.1
Sasha Levin
maintainerPATCH 7/23 drm/amdgpu: Check num_gfx_rings for gfx v9_0 rb setup.
In reply to Sasha LevinFrom: Candice Li <[email protected]>
[ Upstream commit c351938350ab9b5e978dede2c321da43de7eb70c ]
No need to set up rb when no gfx rings.
--- drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +2 -1
@@ -2624,7 +2624,8 @@ static void gfx_v9_0_constants_init(struct amdgpu_device *adev)gfx_v9_0_tiling_mode_table_init (adev); -gfx_v9_0_setup_rb (adev); +if (adev->gfx.num_gfx_rings) +gfx_v9_0_setup_rb (adev);gfx_v9_0_get_cu_info (adev, &adev->gfx.cu_info); adev->gfx.config.db_debug2 =RREG32_SOC15 (GC ,0 , mmDB_DEBUG2);
Signature · 1 line
2.35.1
Sasha Levin
maintainerPATCH 8/23 drm/radeon: add a force flush to delay work when radeon
In reply to Sasha LevinFrom: Zhenneng Li <[email protected]>
[ Upstream commit f461950fdc374a3ada5a63c669d997de4600dffe ]
Although radeon card fence and wait for gpu to finish processing current batch rings, there is still a corner case that radeon lockup work queue may not be fully flushed, and meanwhile the radeon_suspend_kms() function has called pci_set_power_state() to put device in D3hot state.
Per PCI spec rev 4.0 on 5.3.1.4.1 D3hot State.
Quoted 3 lines
Configuration and Message requests are the only TLPs accepted by a Function in the D3hot state. All other received Requests must be handled as Unsupported Requests, and all received Completions may optionally be handled as Unexpected Completions.
This issue will happen in following logs:
Unable to handle kernel paging request at virtual address 00008800e0008010
CPU 0 kworker/0:3(131): Oops 0
pc = [<ffffffff811bea5c>] ra = [<ffffffff81240844>] ps = 0000 Tainted: G W
pc is at si_gpu_check_soft_reset+0x3c/0x240
ra is at si_dma_is_lockup+0x34/0xd0
v0 = 0000000000000000 t0 = fff08800e0008010 t1 = 0000000000010000 t2 = 0000000000008010 t3 = fff00007e3c00000 t4 = fff00007e3c00258 t5 = 000000000000ffff t6 = 0000000000000001 t7 = fff00007ef078000 s0 = fff00007e3c016e8 s1 = fff00007e3c00000 s2 = fff00007e3c00018 s3 = fff00007e3c00000 s4 = fff00007fff59d80 s5 = 0000000000000000 s6 = fff00007ef07bd98 a0 = fff00007e3c00000 a1 = fff00007e3c016e8 a2 = 0000000000000008 a3 = 0000000000000001 a4 = 8f5c28f5c28f5c29 a5 = ffffffff810f4338 t8 = 0000000000000275 t9 = ffffffff809b66f8 t10 = ff6769c5d964b800 t11= 000000000000b886 pv = ffffffff811bea20 at = 0000000000000000 gp = ffffffff81d89690 sp = 00000000aa814126 Disabling lock debugging due to kernel taint Trace: [<ffffffff81240844>] si_dma_is_lockup+0x34/0xd0 [<ffffffff81119610>] radeon_fence_check_lockup+0xd0/0x290 [<ffffffff80977010>] process_one_work+0x280/0x550 [<ffffffff80977350>] worker_thread+0x70/0x7c0 [<ffffffff80977410>] worker_thread+0x130/0x7c0 [<ffffffff80982040>] kthread+0x200/0x210 [<ffffffff809772e0>] worker_thread+0x0/0x7c0 [<ffffffff80981f8c>] kthread+0x14c/0x210 [<ffffffff80911658>] ret_from_kernel_thread+0x18/0x20 [<ffffffff80981e40>] kthread+0x0/0x210 Code: ad3e0008 43f0074a ad7e0018 ad9e0020 8c3001e8 40230101 <88210000> 4821ed21
So force lockup work queue flush to fix this problem.
--- drivers/gpu/drm/radeon/radeon_device.c | 3 +++ 1 file changed, 3 insertions(+)
drivers/gpu/drm/radeon/radeon_device.c +3 -0
@@ -1617,6 +1617,9 @@ int radeon_suspend_kms(struct drm_device *dev, bool suspend,if (r) {/* delay GPU reset to resume */ radeon_fence_driver_force_completion (rdev, i); + }else { +/* finish executing delayed work */ +flush_delayed_work (&rdev->fence_drv[i].lockup_work); } }
Signature · 1 line
2.35.1
Sasha Levin
maintainerPATCH 9/23 scsi: ufs: core: Reduce the power mode change timeout
In reply to Sasha LevinFrom: Bart Van Assche <[email protected]>
[ Upstream commit 8f2c96420c6ec3dcb18c8be923e24c6feaa5ccf6 ]
The current power mode change timeout (180 s) is so large that it can cause a watchdog timer to fire. Reduce the power mode change timeout to 10 seconds.
--- drivers/scsi/ufs/ufshcd.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-)
drivers/scsi/ufs/ufshcd.c +8 -1
@@ -8476,6 +8476,8 @@ static int ufshcd_set_dev_pwr_mode(struct ufs_hba *hba,struct scsi_device *sdp;unsigned long flags;int ret, retries; +unsigned long deadline; +int32_t remaining;spin_lock_irqsave (hba->host->host_lock, flags); sdp = hba->sdev_ufs_device;
@@ -8508,9 +8510,14 @@ static int ufshcd_set_dev_pwr_mode(struct ufs_hba *hba,* callbacks hence set the RQF_PM flag so that it doesn't resume the * already suspended childs. */ + deadline = jiffies +10 *HZ ;for (retries =3 ; retries >0 ; --retries) { + ret = -ETIMEDOUT ; + remaining = deadline - jiffies; +if (remaining <=0 ) +break ; ret =scsi_execute (sdp, cmd,DMA_NONE ,NULL ,0 ,NULL , &sshdr, -START_STOP_TIMEOUT ,0 ,0 ,RQF_PM ,NULL ); + remaining /HZ ,0 ,0 ,RQF_PM ,NULL );if (!scsi_status_is_check_condition (ret) || !scsi_sense_valid (&sshdr) || sshdr.sense_key !=UNIT_ATTENTION )
Signature · 1 line
2.35.1
Sasha Levin
maintainerPATCH 10/23 Revert "parisc: Show error if wrong 32/64-bit compiler is being used"
In reply to Sasha LevinFrom: Helge Deller <[email protected]>
[ Upstream commit b4b18f47f4f9682fbf5827682645da7c8dde8f80 ]
This reverts commit b160628e9ebcdc85d0db9d7f423c26b3c7c179d0.
There is no need any longer to have this sanity check, because the previous commit ("parisc: Make CONFIG_64BIT available for ARCH=parisc64 only") prevents that CONFIG_64BIT is set if ARCH==parisc.
--- arch/parisc/include/asm/bitops.h | 8 -------- 1 file changed, 8 deletions(-)
arch/parisc/include/asm/bitops.h +0 -8
@@ -12,14 +12,6 @@#include <asm/barrier.h> #include <linux/atomic.h> -/* compiler build environment sanity checks: */ -#if !defined(CONFIG_64BIT ) && defined(__LP64__) -#error "Please use 'ARCH=parisc' to build the 32-bit kernel." -#endif -#if defined(CONFIG_64BIT ) && !defined(__LP64__) -#error "Please use 'ARCH=parisc64' to build the 64-bit kernel." -#endif -/* See http://marc.theaimsgroup.com/?t=108826637900003 for discussion * on use of volatile and __*_bit() (set/clear/change): * *_bit() want use of volatile.
Signature · 1 line
2.35.1
Sasha Levin
maintainerPATCH 11/23 parisc: ccio-dma: Handle kmalloc failure in ccio_init_resources()
In reply to Sasha LevinFrom: Li Qiong <[email protected]>
[ Upstream commit d46c742f827fa2326ab1f4faa1cccadb56912341 ]
As the possible failure of the kmalloc(), it should be better to fix this error path, check and return '-ENOMEM' error code.
--- drivers/parisc/ccio-dma.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-)
drivers/parisc/ccio-dma.c +8 -3
@@ -1380,15 +1380,17 @@ ccio_init_resource(struct resource *res, char *name, void __iomem *ioaddr) } } -static void __init ccio_init_resources (struct ioc *ioc) +static int __init ccio_init_resources (struct ioc *ioc) {struct resource *res = ioc->mmio_region;char *name =kmalloc (14 ,GFP_KERNEL ); - +if (unlikely (!name)) +return -ENOMEM ;snprintf (name,14 ,"GSC Bus [%d/]" , ioc->hw_path);ccio_init_resource (res, name, &ioc->ioc_regs->io_io_low);ccio_init_resource (res +1 , name, &ioc->ioc_regs->io_io_low_hv); +return 0 ; } static int new_ioc_area(struct resource *res, unsigned long size,
@@ -1543,7 +1545,10 @@ static int __init ccio_probe(struct parisc_device *dev)return -ENOMEM ; }ccio_ioc_init (ioc); -ccio_init_resources (ioc); +if (ccio_init_resources (ioc)) { +kfree (ioc); +return -ENOMEM ; + } hppa_dma_ops = &ccio_ops; hba =kzalloc (sizeof (*hba),GFP_KERNEL );
Signature · 1 line
2.35.1
Sasha Levin
maintainerPATCH 12/23 parisc: Add runtime check to prevent PA2.0 kernels on PA1.x machines
In reply to Sasha LevinFrom: Helge Deller <[email protected]>
[ Upstream commit 591d2108f3abc4db9f9073cae37cf3591fd250d6 ]
If a 32-bit kernel was compiled for PA2.0 CPUs, it won't be able to run on machines with PA1.x CPUs. Add a check and bail out early if a PA1.x machine is detected.
--- arch/parisc/kernel/head.S | 43 ++++++++++++++++++++++++++++++++++++++- 1 file changed, 42 insertions(+), 1 deletion(-)
arch/parisc/kernel/head.S +42 -1
@@ -22,7 +22,7 @@ #include <linux/init.h> #include <linux/pgtable.h> - .level PA_ASM_LEVEL + .level 1.1 __INITDATA ENTRY(boot_args)
@@ -69,6 +69,47 @@ $bss_loop: stw,ma %arg2,4(%r1) stw,ma %arg3,4(%r1) +#if !defined(CONFIG_64BIT) && defined(CONFIG_PA20) + /* This 32-bit kernel was compiled for PA2.0 CPUs. Check current CPU + * and halt kernel if we detect a PA1.x CPU. */ + ldi 32,%r10 + mtctl %r10,%cr11 + .level 2.0 + mfctl,w %cr11,%r10 + .level 1.1 + comib,<>,n 0,%r10,$cpu_ok + + load32 PA(msg1),%arg0 + ldi msg1_end-msg1,%arg1 +$iodc_panic: + copy %arg0, %r10 + copy %arg1, %r11 + load32 PA(init_stack),%sp +#define MEM_CONS 0x3A0 + ldw MEM_CONS+32(%r0),%arg0 // HPA + ldi ENTRY_IO_COUT,%arg1 + ldw MEM_CONS+36(%r0),%arg2 // SPA + ldw MEM_CONS+8(%r0),%arg3 // layers + load32 PA(__bss_start),%r1 + stw %r1,-52(%sp) // arg4 + stw %r0,-56(%sp) // arg5 + stw %r10,-60(%sp) // arg6 = ptr to text + stw %r11,-64(%sp) // arg7 = len + stw %r0,-68(%sp) // arg8 + load32 PA(.iodc_panic_ret), %rp + ldw MEM_CONS+40(%r0),%r1 // ENTRY_IODC + bv,n (%r1) +.iodc_panic_ret: + b . /* wait endless with ... */ + or %r10,%r10,%r10 /* qemu idle sleep */ +msg1: .ascii "Can't boot kernel which was built for PA8x00 CPUs on this machine.\r\n" +msg1_end: + +$cpu_ok: +#endif + + .level PA_ASM_LEVEL + /* Initialize startup VM. Just map first 16/32 MB of memory */ load32 PA(swapper_pg_dir),%r4 mtctl %r4,%cr24 /* Initialize kernel root pointer */
Signature · 1 line
2.35.1
Sasha Levin
maintainerPATCH 13/23 arm64: cacheinfo: Fix incorrect assignment of signed error value to unsigned fw_level
In reply to Sasha LevinFrom: Sudeep Holla <[email protected]>
[ Upstream commit e75d18cecbb3805895d8ed64da4f78575ec96043 ]
Though acpi_find_last_cache_level() always returned signed value and the document states it will return any errors caused by lack of a PPTT table, it never returned negative values before.
Commit 0c80f9e165f8 ("ACPI: PPTT: Leave the table mapped for the runtime usage") however changed it by returning -ENOENT if no PPTT was found. The value returned from acpi_find_last_cache_level() is then assigned to unsigned fw_level.
It will result in the number of cache leaves calculated incorrectly as a huge value which will then cause the following warning from __alloc_pages as the order would be great than MAX_ORDER because of incorrect and huge cache leaves value.
| WARNING: CPU: 0 PID: 1 at mm/page_alloc.c:5407 __alloc_pages+0x74/0x314 | Modules linked in: | CPU: 0 PID: 1 Comm: swapper/0 Not tainted 5.19.0-10393-g7c2a8d3ac4c0 #73 | pstate: 20000005 (nzCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--) | pc : __alloc_pages+0x74/0x314 | lr : alloc_pages+0xe8/0x318 | Call trace: | __alloc_pages+0x74/0x314 | alloc_pages+0xe8/0x318 | kmalloc_order_trace+0x68/0x1dc | __kmalloc+0x240/0x338 | detect_cache_attributes+0xe0/0x56c | update_siblings_masks+0x38/0x284 | store_cpu_topology+0x78/0x84 | smp_prepare_cpus+0x48/0x134 | kernel_init_freeable+0xc4/0x14c | kernel_init+0x2c/0x1b4 | ret_from_fork+0x10/0x20
Fix the same by changing fw_level to be signed integer and return the error from init_cache_level() early in case of error.
--- arch/arm64/kernel/cacheinfo.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-)
arch/arm64/kernel/cacheinfo.c +5 -1
@@ -45,7 +45,8 @@ static void ci_leaf_init(struct cacheinfo *this_leaf,int init_cache_level (unsigned int cpu) { -unsigned int ctype, level, leaves, fw_level; +unsigned int ctype, level, leaves; +int fw_level;struct cpu_cacheinfo *this_cpu_ci =get_cpu_cacheinfo (cpu);for (level =1 , leaves =0 ; level <=MAX_CACHE_LEVEL ; level++) {
@@ -63,6 +64,9 @@ int init_cache_level(unsigned int cpu)else fw_level =acpi_find_last_cache_level (cpu); +if (fw_level <0 ) +return fw_level; +if (level < fw_level) {/* * some external caches not specified in CLIDR_EL1
Signature · 7 lines
2.35.1 _______________________________________________ linux-arm-kernel mailing list [email protected] http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
Sasha Levin
maintainerPATCH 14/23 arm64/signal: Raise limit on stack frames
In reply to Sasha LevinFrom: Mark Brown <[email protected]>
[ Upstream commit 7ddcaf78e93c9282b4d92184f511b4d5bee75355 ]
The signal code has a limit of 64K on the size of a stack frame that it will generate, if this limit is exceeded then a process will be killed if it receives a signal. Unfortunately with the advent of SME this limit is too small - the maximum possible size of the ZA register alone is 64K. This is not an issue for practical systems at present but is easily seen using virtual platforms.
Raise the limit to 256K, this is substantially more than could be used by any current architecture extension.
--- arch/arm64/kernel/signal.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
arch/arm64/kernel/signal.c +1 -1
@@ -91,7 +91,7 @@ static size_t sigframe_size(struct rt_sigframe_user_layout const *user)* not taken into account. This limit is not a guarantee and is * NOT ABI. */ -#define SIGFRAME_MAXSZ SZ_64K +#define SIGFRAME_MAXSZ SZ_256Kstatic int __sigframe_alloc (struct rt_sigframe_user_layout *user,unsigned long *offset,size_t size,bool extend)
Signature · 7 lines
2.35.1 _______________________________________________ linux-arm-kernel mailing list [email protected] http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
Re: [PATCH AUTOSEL 5.15 14/23] arm64/signal: Raise limit on stack frames
Quoted 6 lines · Sasha Levin
From: Mark Brown <[email protected]>
[ Upstream commit
7ddcaf78e93c9282b4d92184f511b4d5bee75355]The signal code has a limit of 64K on the size of a stack frame that it will generate, if this limit is exceeded then a process will be killed if
I don't believe this is relevant to kernels without SME support.
Sasha Levin
maintainerRe: [PATCH AUTOSEL 5.15 14/23] arm64/signal: Raise limit on stack frames
Quoted 9 lines · Mark Brown
Quoted 6 lines · Sasha Levin
From: Mark Brown <[email protected]>
[ Upstream commit
7ddcaf78e93c9282b4d92184f511b4d5bee75355]The signal code has a limit of 64K on the size of a stack frame that it will generate, if this limit is exceeded then a process will be killed if
I don't believe this is relevant to kernels without SME support.
Ack, I'll drop it.
Signature · 2 lines
Thanks, Sasha
Sasha Levin
maintainerPATCH 15/23 netfilter: conntrack: work around exceeded receive window
In reply to Sasha LevinFrom: Florian Westphal <[email protected]>
[ Upstream commit cf97769c761abfeac8931b35fe0e1a8d5fabc9d8 ]
When a TCP sends more bytes than allowed by the receive window, all future packets can be marked as invalid.
This can clog up the conntrack table because of 5-day default timeout.
Sequence of packets:
01 initiator > responder: [S], seq 171, win 5840, options [mss 1330,sackOK,TS val 63 ecr 0,nop,wscale 1] 02 responder > initiator: [S.], seq 33211, ack 172, win 65535, options [mss 1460,sackOK,TS val 010 ecr 63,nop,wscale 8] 03 initiator > responder: [.], ack 33212, win 2920, options [nop,nop,TS val 068 ecr 010], length 0 04 initiator > responder: [P.], seq 172:240, ack 33212, win 2920, options [nop,nop,TS val 279 ecr 010], length 68
Window is 5840 starting from 33212 -> 39052.
05 responder > initiator: [.], ack 240, win 256, options [nop,nop,TS val 872 ecr 279], length 0 06 responder > initiator: [.], seq 33212:34530, ack 240, win 256, options [nop,nop,TS val 892 ecr 279], length 1318
This is fine, conntrack will flag the connection as having outstanding data (UNACKED), which lowers the conntrack timeout to 300s.
07 responder > initiator: [.], seq 34530:35848, ack 240, win 256, options [nop,nop,TS val 892 ecr 279], length 1318 08 responder > initiator: [.], seq 35848:37166, ack 240, win 256, options [nop,nop,TS val 892 ecr 279], length 1318 09 responder > initiator: [.], seq 37166:38484, ack 240, win 256, options [nop,nop,TS val 892 ecr 279], length 1318 10 responder > initiator: [.], seq 38484:39802, ack 240, win 256, options [nop,nop,TS val 892 ecr 279], length 1318
Packet 10 is already sending more than permitted, but conntrack doesn't validate this (only seq is tested vs. maxend, not 'seq+len').
38484 is acceptable, but only up to 39052, so this packet should not have been sent (or only 568 bytes, not 1318).
At this point, connection is still in '300s' mode.
Next packet however will get flagged:
11 responder > initiator: [P.], seq 39802:40128, ack 240, win 256, options [nop,nop,TS val 892 ecr 279], length 326
nf_ct_proto_6: SEQ is over the upper bound (over the window of the receiver) .. LEN=378 .. SEQ=39802 ACK=240 ACK PSH ..
Now, a couple of replies/acks comes in:
12 initiator > responder: [.], ack 34530, win 4368,
[.. irrelevant acks removed ]
16 initiator > responder: [.], ack 39802, win 8712, options [nop,nop,TS val 296201291 ecr 2982371892], length 0
This ack is significant -- this acks the last packet send by the responder that conntrack considered valid.
This means that ack == td_end. This will withdraw the 'unacked data' flag, the connection moves back to the 5-day timeout of established conntracks.
17 initiator > responder: ack 40128, win 10030, ...
This packet is also flagged as invalid.
Because conntrack only updates state based on packets that are considered valid, packet 11 'did not exist' and that gets us:
nf_ct_proto_6: ACK is over upper bound 39803 (ACKed data not seen yet) .. SEQ=240 ACK=40128 WINDOW=10030 RES=0x00 ACK URG
Because this received and processed by the endpoints, the conntrack entry remains in a bad state, no packets will ever be considered valid again:
30 responder > initiator: [F.], seq 40432, ack 2045, win 391, .. 31 initiator > responder: [.], ack 40433, win 11348, .. 32 initiator > responder: [F.], seq 2045, ack 40433, win 11348 ..
... all trigger 'ACK is over bound' test and we end up with non-early-evictable 5-day default timeout.
NB: This patch triggers a bunch of checkpatch warnings because of silly indent. I will resend the cleanup series linked below to reduce the indent level once this change has propagated to net-next.
I could route the cleanup via nf but that causes extra backport work for stable maintainers.
--- net/netfilter/nf_conntrack_proto_tcp.c | 31 ++++++++++++++++++++++++++ 1 file changed, 31 insertions(+)
net/netfilter/nf_conntrack_proto_tcp.c +31 -0
@@ -671,6 +671,37 @@ static bool tcp_in_window(struct nf_conn *ct, tn->tcp_be_liberal) res = true;if (!res) { +bool seq_ok =before (seq, sender->td_maxend +1 ); + +if (!seq_ok) { +u32 overshot = end - sender->td_maxend +1 ; +bool ack_ok; + + ack_ok =after (sack, receiver->td_end -MAXACKWINDOW (sender) -1 ); + +if (in_recv_win && + ack_ok && + overshot <= receiver->td_maxwin && +before (sack, receiver->td_end +1 )) { +/* Work around TCPs that send more bytes than allowed by +* the receive window. +* +* If the (marked as invalid) packet is allowed to pass by +* the ruleset and the peer acks this data, then its possible +* all future packets will trigger 'ACK is over upper bound' check. +* +* Thus if only the sequence check fails then do update td_end so +* possible ACK for this data can update internal state. +*/ + sender->td_end = end; + sender->flags |=IP_CT_TCP_FLAG_DATA_UNACKNOWLEDGED ; + +nf_ct_l4proto_log_invalid (skb, ct, hook_state, +"%u bytes more than expected" , overshot); +return res; + } + } + nf_ct_l4proto_log_invalid(skb, ct, hook_state, "%s", before(seq, sender->td_maxend + 1) ?
Signature · 1 line
2.35.1
Sasha Levin
maintainerPATCH 16/23 cpufreq: check only freq_table in __resolve_freq()
In reply to Sasha LevinFrom: Lukasz Luba <[email protected]>
[ Upstream commit 6ca7076fbfaeccce173aeab832d76b9e49e1034b ]
There is no need to check if the cpufreq driver implements callback cpufreq_driver::target_index. The logic in the __resolve_freq uses the frequency table available in the policy. It doesn't matter if the driver provides 'target_index' or 'target' callback. It just has to populate the 'policy->freq_table'.
Thus, check only frequency table during the frequency resolving call.
--- drivers/cpufreq/cpufreq.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/cpufreq/cpufreq.c +1 -1
@@ -532,7 +532,7 @@ static unsigned int __resolve_freq(struct cpufreq_policy *policy, target_freq =clamp_val (target_freq, policy->min, policy->max); -if (!cpufreq_driver->target_index) +if (!policy->freq_table)return target_freq; idx =cpufreq_frequency_table_target (policy, target_freq, relation);
Signature · 1 line
2.35.1
Sasha Levin
maintainerPATCH 17/23 fec: Restart PPS after link state change
In reply to Sasha LevinFrom: Csókás Bence <[email protected]>
[ Upstream commit f79959220fa5fbda939592bf91c7a9ea90419040 ]
On link state change, the controller gets reset, causing PPS to drop out and the PHC to lose its time and calibration. So we restart it if needed, restoring calibration and time registers.
Changes since v2:
* Add fec_ptp_save_state()/fec_ptp_restore_state()
* Use ktime_get_real_ns()
* Use BIT() macro
Changes since v1:
* More ECR #define's
* Stop PPS in fec_ptp_stop()
--- drivers/net/ethernet/freescale/fec.h | 10 ++++++ drivers/net/ethernet/freescale/fec_main.c | 42 ++++++++++++++++++++--- drivers/net/ethernet/freescale/fec_ptp.c | 29 ++++++++++++++++ 3 files changed, 77 insertions(+), 4 deletions(-)
drivers/net/ethernet/freescale/fec.h +10 -0
@@ -634,6 +634,13 @@ struct fec_enet_private {int pps_enable;unsigned int next_counter; +struct { +struct timespec64 ts_phc; +u64 ns_sys; +u32 at_corr; +u8 at_inc_corr; + } ptp_saved_state; +u64 ethtool_stats[]; };
@@ -644,5 +651,8 @@ void fec_ptp_disable_hwts(struct net_device *ndev);int fec_ptp_set (struct net_device *ndev,struct ifreq *ifr);int fec_ptp_get (struct net_device *ndev,struct ifreq *ifr); +void fec_ptp_save_state (struct fec_enet_private *fep); +int fec_ptp_restore_state (struct fec_enet_private *fep); +/****************************************************************************/ #endif /* FEC_H */
drivers/net/ethernet/freescale/fec_main.c +38 -4
89 lines not on this page · raw message
drivers/net/ethernet/freescale/fec_ptp.c +29 -0
@@ -638,7 +638,36 @@ void fec_ptp_stop(struct platform_device *pdev)struct net_device *ndev =platform_get_drvdata (pdev);struct fec_enet_private *fep =netdev_priv (ndev); +if (fep->pps_enable) +fec_ptp_enable_pps (fep,0 ); +cancel_delayed_work_sync (&fep->time_keep);if (fep->ptp_clock)ptp_clock_unregister (fep->ptp_clock); } + +void fec_ptp_save_state (struct fec_enet_private *fep) +{ +u32 atime_inc_corr; + +fec_ptp_gettime (&fep->ptp_caps, &fep->ptp_saved_state.ts_phc); + fep->ptp_saved_state.ns_sys =ktime_get_ns (); + + fep->ptp_saved_state.at_corr =readl (fep->hwp +FEC_ATIME_CORR ); + atime_inc_corr =readl (fep->hwp +FEC_ATIME_INC ) &FEC_T_INC_CORR_MASK ; + fep->ptp_saved_state.at_inc_corr = (u8)(atime_inc_corr >>FEC_T_INC_CORR_OFFSET ); +} + +int fec_ptp_restore_state (struct fec_enet_private *fep) +{ +u32 atime_inc =readl (fep->hwp +FEC_ATIME_INC ) &FEC_T_INC_MASK ; +u64 ns_sys; + +writel (fep->ptp_saved_state.at_corr, fep->hwp +FEC_ATIME_CORR ); + atime_inc |= ((u32 )fep->ptp_saved_state.at_inc_corr) <<FEC_T_INC_CORR_OFFSET ; +writel (atime_inc, fep->hwp +FEC_ATIME_INC ); + + ns_sys =ktime_get_ns () - fep->ptp_saved_state.ns_sys; +timespec64_add_ns (&fep->ptp_saved_state.ts_phc, ns_sys); +return fec_ptp_settime (&fep->ptp_caps, &fep->ptp_saved_state.ts_phc); +}
Signature · 1 line
2.35.1
Re: [PATCH AUTOSEL 5.15 17/23] fec: Restart PPS after link state change
Quoted 8 lines · Sasha Levin
From: Csókás Bence <[email protected]>
[ Upstream commit
f79959220fa5fbda939592bf91c7a9ea90419040]On link state change, the controller gets reset, causing PPS to drop out and the PHC to lose its time and calibration. So we restart it if needed, restoring calibration and time registers.
There is an ongoing investigation on netdev@ about a potential kernel panic on kernels newer than 5.12 with this patch applied. Please hold off on backporting to 5.15 until the bugfix is applied to upstream.
Sasha Levin
maintainerRe: [PATCH AUTOSEL 5.15 17/23] fec: Restart PPS after link state change
Quoted 4 lines · Csókás Bence
Quoted 2 lines · Sasha Levin
From: Csókás Bence <[email protected]>
Quoted 8 lines
Quoted 6 lines
[ Upstream commit
f79959220fa5fbda939592bf91c7a9ea90419040]On link state change, the controller gets reset, causing PPS to drop out and the PHC to lose its time and calibration. So we restart it if needed, restoring calibration and time registers.
There is an ongoing investigation on netdev@ about a potential kernel panic on kernels newer than 5.12 with this patch applied. Please hold off on backporting to 5.15 until the bugfix is applied to upstream.
Will do, thanks!
Signature · 2 lines
Thanks, Sasha
Sasha Levin
maintainerPATCH 18/23 net/core/skbuff: Check the return value of skb_copy_bits()
In reply to Sasha LevinFrom: lily <[email protected]>
[ Upstream commit c624c58e08b15105662b9ab9be23d14a6b945a49 ]
skb_copy_bits() could fail, which requires a check on the return value.
--- net/core/skbuff.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-)
net/core/skbuff.c +2 -3
@@ -4188,9 +4188,8 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb,SKB_GSO_CB (nskb)->csum_start =skb_headroom (nskb) + doffset; }else { -skb_copy_bits (head_skb, offset, -skb_put (nskb, len), - len); +if (skb_copy_bits (head_skb, offset,skb_put (nskb, len), len)) + goto err; }continue ; }
Signature · 1 line
2.35.1
Sasha Levin
maintainerPATCH 19/23 md: Flush workqueue md_rdev_misc_wq in md_alloc()
In reply to Sasha LevinFrom: David Sloan <[email protected]>
[ Upstream commit 5e8daf906f890560df430d30617c692a794acb73 ]
A race condition still exists when removing and re-creating md devices in test cases. However, it is only seen on some setups.
The race condition was tracked down to a reference still being held to the kobject by the rdev in the md_rdev_misc_wq which will be released in rdev_delayed_delete().
md_alloc() waits for previous deletions by waiting on the md_misc_wq, but the md_rdev_misc_wq may still be holding a reference to a recently removed device.
To fix this, also flush the md_rdev_misc_wq in md_alloc().
--- drivers/md/md.c | 1 + 1 file changed, 1 insertion(+)
drivers/md/md.c +1 -0
@@ -5651,6 +5651,7 @@ static int md_alloc(dev_t dev, char *name)* removed (mddev_delayed_delete). */ flush_workqueue (md_misc_wq); +flush_workqueue (md_rdev_misc_wq);mutex_lock (&disks_mutex); mddev =mddev_alloc (dev);
Signature · 1 line
2.35.1
Sasha Levin
maintainerPATCH 20/23 fbdev: fb_pm2fb: Avoid potential divide by zero error
In reply to Sasha LevinFrom: Letu Ren <[email protected]>
[ Upstream commit 19f953e7435644b81332dd632ba1b2d80b1e37af ]
In do_fb_ioctl() of fbmem.c, if cmd is FBIOPUT_VSCREENINFO, var will be copied from user, then go through fb_set_var() and info->fbops->fb_check_var() which could may be pm2fb_check_var(). Along the path, var->pixclock won't be modified. This function checks whether reciprocal of var->pixclock is too high. If var->pixclock is zero, there will be a divide by zero error. So, it is necessary to check whether denominator is zero to avoid crash. As this bug is found by Syzkaller, logs are listed below.
divide error in pm2fb_check_var
Call Trace: <TASK> fb_set_var+0x367/0xeb0 drivers/video/fbdev/core/fbmem.c:1015 do_fb_ioctl+0x234/0x670 drivers/video/fbdev/core/fbmem.c:1110 fb_ioctl+0xdd/0x130 drivers/video/fbdev/core/fbmem.c:1189
--- drivers/video/fbdev/pm2fb.c | 5 +++++ 1 file changed, 5 insertions(+)
drivers/video/fbdev/pm2fb.c +5 -0
@@ -617,6 +617,11 @@ static int pm2fb_check_var(struct fb_var_screeninfo *var, struct fb_info *info)return -EINVAL ; } +if (!var->pixclock) { +DPRINTK ("pixclock is zero\n" ); +return -EINVAL ; + } +if (PICOS2KHZ (var->pixclock) >PM2_MAX_PIXCLOCK ) {DPRINTK ("pixclock too high (%ldKHz)\n" ,PICOS2KHZ (var->pixclock));
Signature · 1 line
2.35.1
Sasha Levin
maintainerPATCH 21/23 fbdev: fbcon: Destroy mutex on freeing struct fb_info
In reply to Sasha LevinFrom: Shigeru Yoshida <[email protected]>
[ Upstream commit 58559dfc1ebba2ae0c7627dc8f8991ae1984c6e3 ]
It's needed to destroy bl_curve_mutex on freeing struct fb_info since the mutex is embedded in the structure and initialized when it's allocated.
--- drivers/video/fbdev/core/fbsysfs.c | 4 ++++ 1 file changed, 4 insertions(+)
drivers/video/fbdev/core/fbsysfs.c +4 -0
@@ -84,6 +84,10 @@ void framebuffer_release(struct fb_info *info)if (WARN_ON (refcount_read (&info->count)))return ; +#if IS_ENABLED (CONFIG_FB_BACKLIGHT ) +mutex_destroy (&info->bl_curve_mutex); +#endif +kfree (info->apertures);kfree (info); }
Signature · 1 line
2.35.1
Sasha Levin
maintainerPATCH 22/23 fbdev: chipsfb: Add missing pci_disable_device() in chipsfb_pci_init()
In reply to Sasha LevinFrom: Yang Yingliang <[email protected]>
[ Upstream commit 07c55c9803dea748d17a054000cbf1913ce06399 ]
Add missing pci_disable_device() in error path in chipsfb_pci_init().
--- drivers/video/fbdev/chipsfb.c | 1 + 1 file changed, 1 insertion(+)
drivers/video/fbdev/chipsfb.c +1 -0
@@ -430,6 +430,7 @@ static int chipsfb_pci_init(struct pci_dev *dp, const struct pci_device_id *ent) err_release_fb:framebuffer_release (p); err_disable: +pci_disable_device (dp); err_out:return rc; }
Signature · 1 line
2.35.1
Sasha Levin
maintainerPATCH 23/23 drm/amdgpu: mmVM_L2_CNTL3 register not initialized correctly
In reply to Sasha LevinFrom: Qu Huang <[email protected]>
[ Upstream commit b8983d42524f10ac6bf35bbce6a7cc8e45f61e04 ]
The mmVM_L2_CNTL3 register is not assigned an initial value
--- drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c | 1 + 1 file changed, 1 insertion(+)
drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c +1 -0
@@ -176,6 +176,7 @@ static void mmhub_v1_0_init_cache_regs(struct amdgpu_device *adev) tmp =REG_SET_FIELD (tmp,VM_L2_CNTL2 ,INVALIDATE_L2_CACHE ,1 );WREG32_SOC15 (MMHUB ,0 , mmVM_L2_CNTL2, tmp); + tmp = mmVM_L2_CNTL3_DEFAULT;if (adev->gmc.translate_further) { tmp =REG_SET_FIELD (tmp,VM_L2_CNTL3 ,BANK_SELECT ,12 ); tmp = REG_SET_FIELD(tmp, VM_L2_CNTL3,
Signature · 1 line
2.35.1