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

[PATCH v5] arm64: mm: Populate vmemmap/linear at the page level for hotplugged sections

by Zhenhua Huang

On the arm64 platform with 4K base page config, SECTION_SIZE_BITS is set to 27, making one section 128M. The related page struct which vmemmap points to is 2M then. Commit c1cc1552616d ("arm64: MMU initialisation") optimizes the vmemmap to populate at the PMD section level which was suitable initially since hot plug granule is always one section(128M). However, commit ba72b4c8cf60 ("mm/sparsemem: support sub-section hotplug") introduced a 2M(SUBSECTION_SIZE) hot plug granule, which disrupted the existing arm64 assumptions. Considering the vmemmap_free -> unmap_hotplug_pmd_range path, when pmd_sect() is true, the entire PMD section is cleared, even if there is other effective subsection. For example page_struct_map1 and page_strcut_map2 are part of a single PMD entry and they are hot-added sequentially. Then page_struct_map1 is removed, vmemmap_free() will clear the entire PMD entry freeing the struct page map for the whole section, even though page_struct_map2 is still active. Similar problem exists with linear mapping as well, for 16K base page(PMD size = 32M) or 64K base page(PMD = 512M), their block mappings exceed SUBSECTION_SIZE. Tearing down the entire PMD mapping too will leave other subsections unmapped in the linear mapping. To address the issue, we need to prevent PMD/PUD/CONT mappings for both linear and vmemmap for non-boot sections if corresponding size on the given base page exceeds SUBSECTION_SIZE(2MB now). Cc: stable(a)vger.kernel.org # v5.4+ Fixes: ba72b4c8cf60 ("mm/sparsemem: support sub-section hotplug") Signed-off-by: Zhenhua Huang <quic_zhenhuah(a)quicinc.com> --- Hi Catalin and Anshuman, I have addressed comments so far, please help review. One outstanding point which not finalized is in vmemmap_populate(): how to judge hotplug section. Currently I am using system_state, discussion: https://lore.kernel.org/linux-mm/1515dae4-cb53-4645-8c72-d33b27ede7eb@quici… arch/arm64/mm/mmu.c | 46 ++++++++++++++++++++++++++++++++++++--------- 1 file changed, 37 insertions(+), 9 deletions(-) diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index e2739b69e11b..8718d6e454c5 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -42,9 +42,13 @@ #include <asm/pgalloc.h> #include <asm/kfence.h> -#define NO_BLOCK_MAPPINGS BIT(0) -#define NO_CONT_MAPPINGS BIT(1) -#define NO_EXEC_MAPPINGS BIT(2) /* assumes FEAT_HPDS is not used */ +#define NO_PMD_BLOCK_MAPPINGS BIT(0) +#define NO_PUD_BLOCK_MAPPINGS BIT(1) /* Hotplug case: do not want block mapping for PUD */ +#define NO_BLOCK_MAPPINGS (NO_PMD_BLOCK_MAPPINGS | NO_PUD_BLOCK_MAPPINGS) +#define NO_PTE_CONT_MAPPINGS BIT(2) +#define NO_PMD_CONT_MAPPINGS BIT(3) /* Hotplug case: do not want cont mapping for PMD */ +#define NO_CONT_MAPPINGS (NO_PTE_CONT_MAPPINGS | NO_PMD_CONT_MAPPINGS) +#define NO_EXEC_MAPPINGS BIT(4) /* assumes FEAT_HPDS is not used */ u64 kimage_voffset __ro_after_init; EXPORT_SYMBOL(kimage_voffset); @@ -224,7 +228,7 @@ static void alloc_init_cont_pte(pmd_t *pmdp, unsigned long addr, /* use a contiguous mapping if the range is suitably aligned */ if ((((addr | next | phys) & ~CONT_PTE_MASK) == 0) && - (flags & NO_CONT_MAPPINGS) == 0) + (flags & NO_PTE_CONT_MAPPINGS) == 0) __prot = __pgprot(pgprot_val(prot) | PTE_CONT); init_pte(ptep, addr, next, phys, __prot); @@ -254,7 +258,7 @@ static void init_pmd(pmd_t *pmdp, unsigned long addr, unsigned long end, /* try section mapping first */ if (((addr | next | phys) & ~PMD_MASK) == 0 && - (flags & NO_BLOCK_MAPPINGS) == 0) { + (flags & NO_PMD_BLOCK_MAPPINGS) == 0) { pmd_set_huge(pmdp, phys, prot); /* @@ -311,7 +315,7 @@ static void alloc_init_cont_pmd(pud_t *pudp, unsigned long addr, /* use a contiguous mapping if the range is suitably aligned */ if ((((addr | next | phys) & ~CONT_PMD_MASK) == 0) && - (flags & NO_CONT_MAPPINGS) == 0) + (flags & NO_PMD_CONT_MAPPINGS) == 0) __prot = __pgprot(pgprot_val(prot) | PTE_CONT); init_pmd(pmdp, addr, next, phys, __prot, pgtable_alloc, flags); @@ -358,8 +362,8 @@ static void alloc_init_pud(p4d_t *p4dp, unsigned long addr, unsigned long end, * For 4K granule only, attempt to put down a 1GB block */ if (pud_sect_supported() && - ((addr | next | phys) & ~PUD_MASK) == 0 && - (flags & NO_BLOCK_MAPPINGS) == 0) { + ((addr | next | phys) & ~PUD_MASK) == 0 && + (flags & NO_PUD_BLOCK_MAPPINGS) == 0) { pud_set_huge(pudp, phys, prot); /* @@ -1177,7 +1181,13 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, { WARN_ON((start < VMEMMAP_START) || (end > VMEMMAP_END)); - if (!IS_ENABLED(CONFIG_ARM64_4K_PAGES)) + /* + * Hotplugged section does not support hugepages as + * PMD_SIZE (hence PUD_SIZE) section mapping covers + * struct page range that exceeds a SUBSECTION_SIZE + * i.e 2MB - for all available base page sizes. + */ + if (!IS_ENABLED(CONFIG_ARM64_4K_PAGES) || system_state != SYSTEM_BOOTING) return vmemmap_populate_basepages(start, end, node, altmap); else return vmemmap_populate_hugepages(start, end, node, altmap); @@ -1339,9 +1349,27 @@ int arch_add_memory(int nid, u64 start, u64 size, struct mhp_params *params) { int ret, flags = NO_EXEC_MAPPINGS; + unsigned long start_pfn = PFN_DOWN(start); + struct mem_section *ms = __pfn_to_section(start_pfn); VM_BUG_ON(!mhp_range_allowed(start, size, true)); + /* should not be invoked by early section */ + WARN_ON(early_section(ms)); + + /* + * Disallow BlOCK/CONT mappings if the corresponding size exceeds + * SUBSECTION_SIZE which now is 2MB. + * + * PUD_BLOCK or PMD_CONT should consistently exceed SUBSECTION_SIZE + * across all variable page size configurations, so add them directly + */ + flags |= NO_PUD_BLOCK_MAPPINGS | NO_PMD_CONT_MAPPINGS; + if (SUBSECTION_SHIFT < PMD_SHIFT) + flags |= NO_PMD_BLOCK_MAPPINGS; + if (SUBSECTION_SHIFT < CONT_PTE_SHIFT) + flags |= NO_PTE_CONT_MAPPINGS; + if (can_set_direct_map()) flags |= NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS; -- 2.25.1

2 weeks, 2 days

1
1
0 0

[PATCH v1] usb: dwc3: core: Defer the probe until USB power supply ready

by Kyle Tso

Currently, DWC3 driver attempts to acquire the USB power supply only once during the probe. If the USB power supply is not ready at that time, the driver simply ignores the failure and continues the probe, leading to permanent non-functioning of the gadget vbus_draw callback. Address this problem by delaying the dwc3 driver initialization until the USB power supply is registered. Fixes: 6f0764b5adea ("usb: dwc3: add a power supply for current control") Cc: stable(a)vger.kernel.org Signed-off-by: Kyle Tso <kyletso(a)google.com> --- Note: This is a follow-up of https://lore.kernel.org/all/20240804084612.2561230-1-kyletso@google.com/ --- drivers/usb/dwc3/core.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c index 7578c5133568..1550c39e792a 100644 --- a/drivers/usb/dwc3/core.c +++ b/drivers/usb/dwc3/core.c @@ -1669,7 +1669,7 @@ static void dwc3_get_software_properties(struct dwc3 *dwc) } } -static void dwc3_get_properties(struct dwc3 *dwc) +static int dwc3_get_properties(struct dwc3 *dwc) { struct device *dev = dwc->dev; u8 lpm_nyet_threshold; @@ -1724,7 +1724,7 @@ static void dwc3_get_properties(struct dwc3 *dwc) if (ret >= 0) { dwc->usb_psy = power_supply_get_by_name(usb_psy_name); if (!dwc->usb_psy) - dev_err(dev, "couldn't get usb power supply\n"); + return dev_err_probe(dev, -EPROBE_DEFER, "couldn't get usb power supply\n"); } dwc->has_lpm_erratum = device_property_read_bool(dev, @@ -1847,6 +1847,8 @@ static void dwc3_get_properties(struct dwc3 *dwc) dwc->imod_interval = 0; dwc->tx_fifo_resize_max_num = tx_fifo_resize_max_num; + + return 0; } /* check whether the core supports IMOD */ @@ -2181,7 +2183,9 @@ static int dwc3_probe(struct platform_device *pdev) dwc->regs = regs; dwc->regs_size = resource_size(&dwc_res); - dwc3_get_properties(dwc); + ret = dwc3_get_properties(dwc); + if (ret) + return ret; dwc3_get_software_properties(dwc); -- 2.47.1.688.g23fc6f90ad-goog

2 weeks, 2 days

2
1
0 0

[PATCH 1/2] alloc_tag: avoid current->alloc_tag manipulations when profiling is disabled

by Suren Baghdasaryan

When memory allocation profiling is disabled there is no need to update current->alloc_tag and these manipulations add unnecessary overhead. Fix the overhead by skipping these extra updates. Fixes: b951aaff5035 ("mm: enable page allocation tagging") Signed-off-by: Suren Baghdasaryan <surenb(a)google.com> Cc: stable(a)vger.kernel.org --- include/linux/alloc_tag.h | 11 ++++++++--- lib/alloc_tag.c | 2 ++ 2 files changed, 10 insertions(+), 3 deletions(-) diff --git a/include/linux/alloc_tag.h b/include/linux/alloc_tag.h index 0bbbe537c5f9..a946e0203e6d 100644 --- a/include/linux/alloc_tag.h +++ b/include/linux/alloc_tag.h @@ -224,9 +224,14 @@ static inline void alloc_tag_sub(union codetag_ref *ref, size_t bytes) {} #define alloc_hooks_tag(_tag, _do_alloc) \ ({ \ - struct alloc_tag * __maybe_unused _old = alloc_tag_save(_tag); \ - typeof(_do_alloc) _res = _do_alloc; \ - alloc_tag_restore(_tag, _old); \ + typeof(_do_alloc) _res; \ + if (mem_alloc_profiling_enabled()) { \ + struct alloc_tag * __maybe_unused _old; \ + _old = alloc_tag_save(_tag); \ + _res = _do_alloc; \ + alloc_tag_restore(_tag, _old); \ + } else \ + _res = _do_alloc; \ _res; \ }) diff --git a/lib/alloc_tag.c b/lib/alloc_tag.c index 7dcebf118a3e..4c373f444eb1 100644 --- a/lib/alloc_tag.c +++ b/lib/alloc_tag.c @@ -29,6 +29,8 @@ EXPORT_SYMBOL(_shared_alloc_tag); DEFINE_STATIC_KEY_MAYBE(CONFIG_MEM_ALLOC_PROFILING_ENABLED_BY_DEFAULT, mem_alloc_profiling_key); +EXPORT_SYMBOL(mem_alloc_profiling_key); + DEFINE_STATIC_KEY_FALSE(mem_profiling_compressed); struct alloc_tag_kernel_section kernel_tags = { NULL, 0 }; base-commit: 431614f1580a03c1a653340c55ea76bd12a9403f -- 2.47.1.613.gc27f4b7a9f-goog

2 weeks, 2 days

3
14
0 0

[PATCH] can: ctucanfd: handle skb allocation failure

by Fedor Pchelkin

If skb allocation fails, the pointer to struct can_frame is NULL. This is actually handled everywhere inside ctucan_err_interrupt() except for the only place. Add the missed NULL check. Found by Linux Verification Center (linuxtesting.org) with SVACE static analysis tool. Fixes: 2dcb8e8782d8 ("can: ctucanfd: add support for CTU CAN FD open-source IP core - bus independent part.") Cc: stable(a)vger.kernel.org Signed-off-by: Fedor Pchelkin <pchelkin(a)ispras.ru> --- drivers/net/can/ctucanfd/ctucanfd_base.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/drivers/net/can/ctucanfd/ctucanfd_base.c b/drivers/net/can/ctucanfd/ctucanfd_base.c index 64c349fd4600..f65c1a1e05cc 100644 --- a/drivers/net/can/ctucanfd/ctucanfd_base.c +++ b/drivers/net/can/ctucanfd/ctucanfd_base.c @@ -867,10 +867,12 @@ static void ctucan_err_interrupt(struct net_device *ndev, u32 isr) } break; case CAN_STATE_ERROR_ACTIVE: - cf->can_id |= CAN_ERR_CNT; - cf->data[1] = CAN_ERR_CRTL_ACTIVE; - cf->data[6] = bec.txerr; - cf->data[7] = bec.rxerr; + if (skb) { + cf->can_id |= CAN_ERR_CNT; + cf->data[1] = CAN_ERR_CRTL_ACTIVE; + cf->data[6] = bec.txerr; + cf->data[7] = bec.rxerr; + } break; default: netdev_warn(ndev, "unhandled error state (%d:%s)!\n", -- 2.39.5

2 weeks, 2 days

3
2
0 0

[PATCH v2] drm/i915/guc: Debug print LRC state entries only if the context is pinned

by Daniele Ceraolo Spurio

After the context is unpinned the backing memory can also be unpinned, so any accesses via the lrc_reg_state pointer can end up in unmapped memory. To avoid that, make sure to only access that memory if the context is pinned when printing its info. v2: fix newline alignment Fixes: 28ff6520a34d ("drm/i915/guc: Update GuC debugfs to support new GuC") Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio(a)intel.com> Cc: John Harrison <John.C.Harrison(a)Intel.com> Cc: Matthew Brost <matthew.brost(a)intel.com> Cc: <stable(a)vger.kernel.org> # v5.15+ Reviewed-by: John Harrison <John.C.Harrison(a)Intel.com> --- .../gpu/drm/i915/gt/uc/intel_guc_submission.c | 20 +++++++++++++------ 1 file changed, 14 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c index 12f1ba7ca9c1..158f78a0941f 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c @@ -5519,12 +5519,20 @@ static inline void guc_log_context(struct drm_printer *p, { drm_printf(p, "GuC lrc descriptor %u:\n", ce->guc_id.id); drm_printf(p, "\tHW Context Desc: 0x%08x\n", ce->lrc.lrca); - drm_printf(p, "\t\tLRC Head: Internal %u, Memory %u\n", - ce->ring->head, - ce->lrc_reg_state[CTX_RING_HEAD]); - drm_printf(p, "\t\tLRC Tail: Internal %u, Memory %u\n", - ce->ring->tail, - ce->lrc_reg_state[CTX_RING_TAIL]); + if (intel_context_pin_if_active(ce)) { + drm_printf(p, "\t\tLRC Head: Internal %u, Memory %u\n", + ce->ring->head, + ce->lrc_reg_state[CTX_RING_HEAD]); + drm_printf(p, "\t\tLRC Tail: Internal %u, Memory %u\n", + ce->ring->tail, + ce->lrc_reg_state[CTX_RING_TAIL]); + intel_context_unpin(ce); + } else { + drm_printf(p, "\t\tLRC Head: Internal %u, Memory not pinned\n", + ce->ring->head); + drm_printf(p, "\t\tLRC Tail: Internal %u, Memory not pinned\n", + ce->ring->tail); + } drm_printf(p, "\t\tContext Pin Count: %u\n", atomic_read(&ce->pin_count)); drm_printf(p, "\t\tGuC ID Ref Count: %u\n", -- 2.43.0

2 weeks, 2 days

1
0
0 0

[PATCH v3] usb: gadget: ncm: Avoid dropping datagrams of properly parsed NTBs

by Krishna Kurapati

It is observed sometimes when tethering is used over NCM with Windows 11 as host, at some instances, the gadget_giveback has one byte appended at the end of a proper NTB. When the NTB is parsed, unwrap call looks for any leftover bytes in SKB provided by u_ether and if there are any pending bytes, it treats them as a separate NTB and parses it. But in case the second NTB (as per unwrap call) is faulty/corrupt, all the datagrams that were parsed properly in the first NTB and saved in rx_list are dropped. Adding a few custom traces showed the following: [002] d..1 7828.532866: dwc3_gadget_giveback: ep1out: req 000000003868811a length 1025/16384 zsI ==> 0 [002] d..1 7828.532867: ncm_unwrap_ntb: K: ncm_unwrap_ntb toprocess: 1025 [002] d..1 7828.532867: ncm_unwrap_ntb: K: ncm_unwrap_ntb nth: 1751999342 [002] d..1 7828.532868: ncm_unwrap_ntb: K: ncm_unwrap_ntb seq: 0xce67 [002] d..1 7828.532868: ncm_unwrap_ntb: K: ncm_unwrap_ntb blk_len: 0x400 [002] d..1 7828.532868: ncm_unwrap_ntb: K: ncm_unwrap_ntb ndp_len: 0x10 [002] d..1 7828.532869: ncm_unwrap_ntb: K: Parsed NTB with 1 frames In this case, the giveback is of 1025 bytes and block length is 1024. The rest 1 byte (which is 0x00) won't be parsed resulting in drop of all datagrams in rx_list. Same is case with packets of size 2048: [002] d..1 7828.557948: dwc3_gadget_giveback: ep1out: req 0000000011dfd96e length 2049/16384 zsI ==> 0 [002] d..1 7828.557949: ncm_unwrap_ntb: K: ncm_unwrap_ntb nth: 1751999342 [002] d..1 7828.557950: ncm_unwrap_ntb: K: ncm_unwrap_ntb blk_len: 0x800 Lecroy shows one byte coming in extra confirming that the byte is coming in from PC: Transfer 2959 - Bytes Transferred(1025) Timestamp((18.524 843 590) - Transaction 8391 - Data(1025 bytes) Timestamp(18.524 843 590) --- Packet 4063861 Data(1024 bytes) Duration(2.117us) Idle(14.700ns) Timestamp(18.524 843 590) --- Packet 4063863 Data(1 byte) Duration(66.160ns) Time(282.000ns) Timestamp(18.524 845 722) According to Windows driver, no ZLP is needed if wBlockLength is non-zero, because the non-zero wBlockLength has already told the function side the size of transfer to be expected. However, there are in-market NCM devices that rely on ZLP as long as the wBlockLength is multiple of wMaxPacketSize. To deal with such devices, it pads an extra 0 at end so the transfer is no longer multiple of wMaxPacketSize. Cc: <stable(a)vger.kernel.org> Fixes: 9f6ce4240a2b ("usb: gadget: f_ncm.c added") Signed-off-by: Krishna Kurapati <quic_kriskura(a)quicinc.com> --- Link to v2: https://lore.kernel.org/all/20240131150332.1326523-1-quic_kriskura@quicinc.… Changes in v2: Added check to see if the padded byte is 0x00. Changes in v3: Removed wMaxPacketSize check from v2. drivers/usb/gadget/function/f_ncm.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/drivers/usb/gadget/function/f_ncm.c b/drivers/usb/gadget/function/f_ncm.c index ca5d5f564998..e2a059cfda2c 100644 --- a/drivers/usb/gadget/function/f_ncm.c +++ b/drivers/usb/gadget/function/f_ncm.c @@ -1338,7 +1338,15 @@ static int ncm_unwrap_ntb(struct gether *port, "Parsed NTB with %d frames\n", dgram_counter); to_process -= block_len; - if (to_process != 0) { + + /* + * Windows NCM driver avoids USB ZLPs by adding a 1-byte + * zero pad as needed. + */ + if (to_process == 1 && + (*(unsigned char *)(ntb_ptr + block_len) == 0x00)) { + to_process--; + } else if (to_process > 0) { ntb_ptr = (unsigned char *)(ntb_ptr + block_len); goto parse_ntb; } -- 2.34.1

2 weeks, 2 days

3
9
0 0

[PATCH net 0/3] mptcp: fixes for connect selftest flakes

by Matthieu Baerts (NGI0)

Last week, Jakub reported [1] that the MPTCP Connect selftest was unstable. It looked like it started after the introduction of some fixes [2]. After analysis from Paolo, these patches revealed existing bugs, that should be fixed by the following patches. - Patch 1: Make sure ACK are sent when MPTCP-level window re-opens. In some corner cases, the other peer was not notified when more data could be sent. A fix for v5.11, but depending on a feature introduced in v5.19. - Patch 2: Fix spurious wake-up under memory pressure. In this situation, the userspace could be invited to read data not being there yet. A fix for v6.7. - Patch 3: Fix a false positive error when running the MPTCP Connect selftest with the "disconnect" cases. The userspace could disconnect the socket too soon, which would reset (MP_FASTCLOSE) the connection, interpreted as an error by the test. A fix for v5.17. Link: https://lore.kernel.org/20250107131845.5e5de3c5@kernel.org [1] Link: https://lore.kernel.org/20241230-net-mptcp-rbuf-fixes-v1-0-8608af434ceb@ker… [2] Signed-off-by: Matthieu Baerts (NGI0) <matttbe(a)kernel.org> --- Paolo Abeni (3): mptcp: be sure to send ack when mptcp-level window re-opens mptcp: fix spurious wake-up on under memory pressure selftests: mptcp: avoid spurious errors on disconnect net/mptcp/options.c | 6 ++-- net/mptcp/protocol.h | 9 +++-- tools/testing/selftests/net/mptcp/mptcp_connect.c | 43 +++++++++++++++++------ 3 files changed, 43 insertions(+), 15 deletions(-) --- base-commit: 76201b5979768500bca362871db66d77cb4c225e change-id: 20250113-net-mptcp-connect-st-flakes-4af6389808de Best regards, -- Matthieu Baerts (NGI0) <matttbe(a)kernel.org>

2 weeks, 2 days

2
4
0 0

[PATCH v2] scsi: ufs: fix use-after free in init error and remove paths

by André Draszik

devm_blk_crypto_profile_init() registers a cleanup handler to run when the associated (platform-) device is being released. For UFS, the crypto private data and pointers are stored as part of the ufs_hba's data structure 'struct ufs_hba::crypto_profile'. This structure is allocated as part of the underlying ufshd allocation. During driver release or during error handling in ufshcd_pltfrm_init(), this structure is released as part of ufshcd_dealloc_host() before the (platform-) device associated with the crypto call above is released. Once this device is released, the crypto cleanup code will run, using the just-released 'struct ufs_hba::crypto_profile'. This causes a use-after-free situation: exynos-ufshc 14700000.ufs: ufshcd_pltfrm_init() failed -11 exynos-ufshc 14700000.ufs: probe with driver exynos-ufshc failed with error -11 Unable to handle kernel paging request at virtual address 01adafad6dadad88 Mem abort info: ESR = 0x0000000096000004 EC = 0x25: DABT (current EL), IL = 32 bits SET = 0, FnV = 0 EA = 0, S1PTW = 0 FSC = 0x04: level 0 translation fault Data abort info: ISV = 0, ISS = 0x00000004, ISS2 = 0x00000000 CM = 0, WnR = 0, TnD = 0, TagAccess = 0 GCS = 0, Overlay = 0, DirtyBit = 0, Xs = 0 [01adafad6dadad88] address between user and kernel address ranges Internal error: Oops: 0000000096000004 [#1] PREEMPT SMP Modules linked in: CPU: 0 UID: 0 PID: 1 Comm: swapper/0 Tainted: G W 6.13.0-rc5-next-20250106+ #70 Tainted: [W]=WARN Hardware name: Oriole (DT) pstate: 20400005 (nzCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : kfree+0x60/0x2d8 lr : kvfree+0x44/0x60 sp : ffff80008009ba80 x29: ffff80008009ba90 x28: 0000000000000000 x27: ffffbcc6591e0130 x26: ffffbcc659309960 x25: ffffbcc658f89c50 x24: ffffbcc659539d80 x23: ffff22e000940040 x22: ffff22e001539010 x21: ffffbcc65714b22c x20: 6b6b6b6b6b6b6b6b x19: 01adafad6dadad80 x18: 0000000000000000 x17: ffffbcc6579fbac8 x16: ffffbcc657a04300 x15: ffffbcc657a027f4 x14: ffffbcc656f969cc x13: ffffbcc6579fdc80 x12: ffffbcc6579fb194 x11: ffffbcc6579fbc34 x10: 0000000000000000 x9 : ffffbcc65714b22c x8 : ffff80008009b880 x7 : 0000000000000000 x6 : ffff80008009b940 x5 : ffff80008009b8c0 x4 : ffff22e000940518 x3 : ffff22e006f54f40 x2 : ffffbcc657a02268 x1 : ffff80007fffffff x0 : ffffc1ffc0000000 Call trace: kfree+0x60/0x2d8 (P) kvfree+0x44/0x60 blk_crypto_profile_destroy_callback+0x28/0x70 devm_action_release+0x1c/0x30 release_nodes+0x6c/0x108 devres_release_all+0x98/0x100 device_unbind_cleanup+0x20/0x70 really_probe+0x218/0x2d0 In other words, the initialisation code flow is: platform-device probe ufshcd_pltfrm_init() ufshcd_alloc_host() scsi_host_alloc() allocation of struct ufs_hba creation of scsi-host devices devm_blk_crypto_profile_init() devm registration of cleanup handler using platform-device and during error handling of ufshcd_pltfrm_init() or during driver removal: ufshcd_dealloc_host() scsi_host_put() put_device(scsi-host) release of struct ufs_hba put_device(platform-device) crypto cleanup handler To fix this use-after free, change ufshcd_alloc_host() to register a devres action to automatically cleanup the underlying SCSI device on ufshcd destruction, without requiring explicit calls to ufshcd_dealloc_host(). This way: * the crypto profile and all other ufs_hba-owned resources are destroyed before SCSI (as they've been registered after) * a memleak is plugged in tc-dwc-g210-pci.c as a side-effect * EXPORT_SYMBOL_GPL(ufshcd_dealloc_host) can be removed fully as it's not needed anymore * no future drivers using ufshcd_alloc_host() could ever forget adding the cleanup Fixes: cb77cb5abe1f ("blk-crypto: rename blk_keyslot_manager to blk_crypto_profile") Fixes: d76d9d7d1009 ("scsi: ufs: use devm_blk_ksm_init()") Cc: stable(a)vger.kernel.org Signed-off-by: André Draszik <andre.draszik(a)linaro.org> --- Changes in v2: - completely new approach using devres action for Scsi_host cleanup, to ensure ordering - add Fixes: and CC: stable tags (Eric) - Link to v1: https://lore.kernel.org/r/20250113-ufshcd-fix-v1-1-ca63d1d4bd55@linaro.org --- In my case, as per above trace I initially encountered an error in ufshcd_verify_dev_init(), which made me notice this problem. For reproducing, it'd be possible to change that function to just return an error. Other approaches for solving this issue I see are the following, but I believe this one here is the cleanest: * turn 'struct ufs_hba::crypto_profile' into a dynamically allocated pointer, in which case it doesn't matter if cleanup runs after scsi_host_put() * add an explicit devm_blk_crypto_profile_deinit() to be called by API users when necessary, e.g. before ufshcd_dealloc_host() in this case * register the crypto cleanup handler against the scsi-host device instead, like in v1 of this patch --- drivers/ufs/core/ufshcd.c | 27 +++++++++++++++++---------- drivers/ufs/host/ufshcd-pci.c | 2 -- drivers/ufs/host/ufshcd-pltfrm.c | 11 ++++------- include/ufs/ufshcd.h | 1 - 4 files changed, 21 insertions(+), 20 deletions(-) diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index 43ddae7318cb..84089f3f62b0 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -10279,16 +10279,6 @@ int ufshcd_system_thaw(struct device *dev) EXPORT_SYMBOL_GPL(ufshcd_system_thaw); #endif /* CONFIG_PM_SLEEP */ -/** - * ufshcd_dealloc_host - deallocate Host Bus Adapter (HBA) - * @hba: pointer to Host Bus Adapter (HBA) - */ -void ufshcd_dealloc_host(struct ufs_hba *hba) -{ - scsi_host_put(hba->host); -} -EXPORT_SYMBOL_GPL(ufshcd_dealloc_host); - /** * ufshcd_set_dma_mask - Set dma mask based on the controller * addressing capability @@ -10307,6 +10297,16 @@ static int ufshcd_set_dma_mask(struct ufs_hba *hba) return dma_set_mask_and_coherent(hba->dev, DMA_BIT_MASK(32)); } +/** + * ufshcd_scsi_host_put_callback - deallocate underlying Scsi_Host and + * thereby the Host Bus Adapter (HBA) + * @host: pointer to SCSI host + */ +static void ufshcd_scsi_host_put_callback(void *host) +{ + scsi_host_put(host); +} + /** * ufshcd_alloc_host - allocate Host Bus Adapter (HBA) * @dev: pointer to device handle @@ -10334,6 +10334,13 @@ int ufshcd_alloc_host(struct device *dev, struct ufs_hba **hba_handle) err = -ENOMEM; goto out_error; } + + err = devm_add_action_or_reset(dev, ufshcd_scsi_host_put_callback, + host); + if (err) + return dev_err_probe(dev, err, + "failed to add ufshcd dealloc action\n"); + host->nr_maps = HCTX_TYPE_POLL + 1; hba = shost_priv(host); hba->host = host; diff --git a/drivers/ufs/host/ufshcd-pci.c b/drivers/ufs/host/ufshcd-pci.c index ea39c5d5b8cf..9cfcaad23cf9 100644 --- a/drivers/ufs/host/ufshcd-pci.c +++ b/drivers/ufs/host/ufshcd-pci.c @@ -562,7 +562,6 @@ static void ufshcd_pci_remove(struct pci_dev *pdev) pm_runtime_forbid(&pdev->dev); pm_runtime_get_noresume(&pdev->dev); ufshcd_remove(hba); - ufshcd_dealloc_host(hba); } /** @@ -605,7 +604,6 @@ ufshcd_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) err = ufshcd_init(hba, mmio_base, pdev->irq); if (err) { dev_err(&pdev->dev, "Initialization failed\n"); - ufshcd_dealloc_host(hba); return err; } diff --git a/drivers/ufs/host/ufshcd-pltfrm.c b/drivers/ufs/host/ufshcd-pltfrm.c index 505572d4fa87..adb0a65d9df5 100644 --- a/drivers/ufs/host/ufshcd-pltfrm.c +++ b/drivers/ufs/host/ufshcd-pltfrm.c @@ -488,13 +488,13 @@ int ufshcd_pltfrm_init(struct platform_device *pdev, if (err) { dev_err(dev, "%s: clock parse failed %d\n", __func__, err); - goto dealloc_host; + goto out; } err = ufshcd_parse_regulator_info(hba); if (err) { dev_err(dev, "%s: regulator init failed %d\n", __func__, err); - goto dealloc_host; + goto out; } ufshcd_init_lanes_per_dir(hba); @@ -502,14 +502,14 @@ int ufshcd_pltfrm_init(struct platform_device *pdev, err = ufshcd_parse_operating_points(hba); if (err) { dev_err(dev, "%s: OPP parse failed %d\n", __func__, err); - goto dealloc_host; + goto out; } err = ufshcd_init(hba, mmio_base, irq); if (err) { dev_err_probe(dev, err, "Initialization failed with error %d\n", err); - goto dealloc_host; + goto out; } pm_runtime_set_active(dev); @@ -517,8 +517,6 @@ int ufshcd_pltfrm_init(struct platform_device *pdev, return 0; -dealloc_host: - ufshcd_dealloc_host(hba); out: return err; } @@ -534,7 +532,6 @@ void ufshcd_pltfrm_remove(struct platform_device *pdev) pm_runtime_get_sync(&pdev->dev); ufshcd_remove(hba); - ufshcd_dealloc_host(hba); pm_runtime_disable(&pdev->dev); pm_runtime_put_noidle(&pdev->dev); } diff --git a/include/ufs/ufshcd.h b/include/ufs/ufshcd.h index da0fa5c65081..58eb6e897827 100644 --- a/include/ufs/ufshcd.h +++ b/include/ufs/ufshcd.h @@ -1311,7 +1311,6 @@ static inline void ufshcd_rmwl(struct ufs_hba *hba, u32 mask, u32 val, u32 reg) void ufshcd_enable_irq(struct ufs_hba *hba); void ufshcd_disable_irq(struct ufs_hba *hba); int ufshcd_alloc_host(struct device *, struct ufs_hba **); -void ufshcd_dealloc_host(struct ufs_hba *); int ufshcd_hba_enable(struct ufs_hba *hba); int ufshcd_init(struct ufs_hba *, void __iomem *, unsigned int); int ufshcd_link_recovery(struct ufs_hba *hba); --- base-commit: 4e16367cfe0ce395f29d0482b78970cce8e1db73 change-id: 20250113-ufshcd-fix-52409f2d32ff Best regards, -- André Draszik <andre.draszik(a)linaro.org>

2 weeks, 3 days

2
4
0 0

[PATCH v5 0/2] riscv/ptrace: add new regset to access original a0 register

by Celeste Liu

The orig_a0 is missing in struct user_regs_struct of riscv, and there is no way to add it without breaking UAPI. (See Link tag below) Like NT_ARM_SYSTEM_CALL do, we add a new regset name NT_RISCV_ORIG_A0 to access original a0 register from userspace via ptrace API. Link: https://lore.kernel.org/all/59505464-c84a-403d-972f-d4b2055eeaac@gmail.com/ Signed-off-by: Celeste Liu <uwu(a)coelacanthus.name> --- Changes in v5: - Fix wrong usage in selftests. - Link to v4: https://lore.kernel.org/r/20241226-riscv-new-regset-v4-0-4496a29d0436@coela… Changes in v4: - Fix a copy paste error in selftest. (Forget to commit...) - Link to v3: https://lore.kernel.org/r/20241226-riscv-new-regset-v3-0-f5b96465826b@coela… Changes in v3: - Use return 0 directly for readability. - Fix test for modify a0. - Add Fixes: tag - Remove useless Cc: stable. - Selftest will check both a0 and orig_a0, but depends on the correctness of PTRACE_GET_SYSCALL_INFO. - Link to v2: https://lore.kernel.org/r/20241203-riscv-new-regset-v2-0-d37da8c0cba6@coela… Changes in v2: - Fix integer width. - Add selftest. - Link to v1: https://lore.kernel.org/r/20241201-riscv-new-regset-v1-1-c83c58abcc7b@coela… --- Celeste Liu (2): riscv/ptrace: add new regset to access original a0 register riscv: selftests: Add a ptrace test to verify a0 and orig_a0 access arch/riscv/kernel/ptrace.c | 32 +++++ include/uapi/linux/elf.h | 1 + tools/testing/selftests/riscv/abi/.gitignore | 1 + tools/testing/selftests/riscv/abi/Makefile | 6 +- tools/testing/selftests/riscv/abi/ptrace.c | 201 +++++++++++++++++++++++++++ 5 files changed, 240 insertions(+), 1 deletion(-) --- base-commit: 0e287d31b62bb53ad81d5e59778384a40f8b6f56 change-id: 20241201-riscv-new-regset-d529b952ad0d Best regards, -- Celeste Liu <uwu(a)coelacanthus.name>

2 weeks, 3 days

1
1
0 0

FAILED: patch "[PATCH] drm/mediatek: Only touch DISP_REG_OVL_PITCH_MSB if AFBC is" failed to apply to 6.12-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.12-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.12.y git checkout FETCH_HEAD git cherry-pick -x f8d9b91739e1fb436447c437a346a36deb676a36 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025011258-registrar-obsessed-eb25@gregkh' --subject-prefix 'PATCH 6.12.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From f8d9b91739e1fb436447c437a346a36deb676a36 Mon Sep 17 00:00:00 2001 From: Daniel Golle <daniel(a)makrotopia.org> Date: Tue, 17 Dec 2024 01:18:01 +0000 Subject: [PATCH] drm/mediatek: Only touch DISP_REG_OVL_PITCH_MSB if AFBC is supported Touching DISP_REG_OVL_PITCH_MSB leads to video overlay on MT2701, MT7623N and probably other older SoCs being broken. Move setting up AFBC layer configuration into a separate function only being called on hardware which actually supports AFBC which restores the behavior as it was before commit c410fa9b07c3 ("drm/mediatek: Add AFBC support to Mediatek DRM driver") on non-AFBC hardware. Fixes: c410fa9b07c3 ("drm/mediatek: Add AFBC support to Mediatek DRM driver") Cc: stable(a)vger.kernel.org Signed-off-by: Daniel Golle <daniel(a)makrotopia.org> Reviewed-by: CK Hu <ck.hu(a)mediatek.com> Link: https://patchwork.kernel.org/project/dri-devel/patch/c7fbd3c3e633c0b7dd6d1c… Signed-off-by: Chun-Kuang Hu <chunkuang.hu(a)kernel.org> diff --git a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c index e0c0bb01f65a..0e4da239cbeb 100644 --- a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c +++ b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c @@ -460,6 +460,29 @@ static unsigned int mtk_ovl_fmt_convert(struct mtk_disp_ovl *ovl, } } +static void mtk_ovl_afbc_layer_config(struct mtk_disp_ovl *ovl, + unsigned int idx, + struct mtk_plane_pending_state *pending, + struct cmdq_pkt *cmdq_pkt) +{ + unsigned int pitch_msb = pending->pitch >> 16; + unsigned int hdr_pitch = pending->hdr_pitch; + unsigned int hdr_addr = pending->hdr_addr; + + if (pending->modifier != DRM_FORMAT_MOD_LINEAR) { + mtk_ddp_write_relaxed(cmdq_pkt, hdr_addr, &ovl->cmdq_reg, ovl->regs, + DISP_REG_OVL_HDR_ADDR(ovl, idx)); + mtk_ddp_write_relaxed(cmdq_pkt, + OVL_PITCH_MSB_2ND_SUBBUF | pitch_msb, + &ovl->cmdq_reg, ovl->regs, DISP_REG_OVL_PITCH_MSB(idx)); + mtk_ddp_write_relaxed(cmdq_pkt, hdr_pitch, &ovl->cmdq_reg, ovl->regs, + DISP_REG_OVL_HDR_PITCH(ovl, idx)); + } else { + mtk_ddp_write_relaxed(cmdq_pkt, pitch_msb, + &ovl->cmdq_reg, ovl->regs, DISP_REG_OVL_PITCH_MSB(idx)); + } +} + void mtk_ovl_layer_config(struct device *dev, unsigned int idx, struct mtk_plane_state *state, struct cmdq_pkt *cmdq_pkt) @@ -467,25 +490,13 @@ void mtk_ovl_layer_config(struct device *dev, unsigned int idx, struct mtk_disp_ovl *ovl = dev_get_drvdata(dev); struct mtk_plane_pending_state *pending = &state->pending; unsigned int addr = pending->addr; - unsigned int hdr_addr = pending->hdr_addr; - unsigned int pitch = pending->pitch; - unsigned int hdr_pitch = pending->hdr_pitch; + unsigned int pitch_lsb = pending->pitch & GENMASK(15, 0); unsigned int fmt = pending->format; unsigned int offset = (pending->y << 16) | pending->x; unsigned int src_size = (pending->height << 16) | pending->width; unsigned int blend_mode = state->base.pixel_blend_mode; unsigned int ignore_pixel_alpha = 0; unsigned int con; - bool is_afbc = pending->modifier != DRM_FORMAT_MOD_LINEAR; - union overlay_pitch { - struct split_pitch { - u16 lsb; - u16 msb; - } split_pitch; - u32 pitch; - } overlay_pitch; - - overlay_pitch.pitch = pitch; if (!pending->enable) { mtk_ovl_layer_off(dev, idx, cmdq_pkt); @@ -524,11 +535,12 @@ void mtk_ovl_layer_config(struct device *dev, unsigned int idx, } if (ovl->data->supports_afbc) - mtk_ovl_set_afbc(ovl, cmdq_pkt, idx, is_afbc); + mtk_ovl_set_afbc(ovl, cmdq_pkt, idx, + pending->modifier != DRM_FORMAT_MOD_LINEAR); mtk_ddp_write_relaxed(cmdq_pkt, con, &ovl->cmdq_reg, ovl->regs, DISP_REG_OVL_CON(idx)); - mtk_ddp_write_relaxed(cmdq_pkt, overlay_pitch.split_pitch.lsb | ignore_pixel_alpha, + mtk_ddp_write_relaxed(cmdq_pkt, pitch_lsb | ignore_pixel_alpha, &ovl->cmdq_reg, ovl->regs, DISP_REG_OVL_PITCH(idx)); mtk_ddp_write_relaxed(cmdq_pkt, src_size, &ovl->cmdq_reg, ovl->regs, DISP_REG_OVL_SRC_SIZE(idx)); @@ -537,19 +549,8 @@ void mtk_ovl_layer_config(struct device *dev, unsigned int idx, mtk_ddp_write_relaxed(cmdq_pkt, addr, &ovl->cmdq_reg, ovl->regs, DISP_REG_OVL_ADDR(ovl, idx)); - if (is_afbc) { - mtk_ddp_write_relaxed(cmdq_pkt, hdr_addr, &ovl->cmdq_reg, ovl->regs, - DISP_REG_OVL_HDR_ADDR(ovl, idx)); - mtk_ddp_write_relaxed(cmdq_pkt, - OVL_PITCH_MSB_2ND_SUBBUF | overlay_pitch.split_pitch.msb, - &ovl->cmdq_reg, ovl->regs, DISP_REG_OVL_PITCH_MSB(idx)); - mtk_ddp_write_relaxed(cmdq_pkt, hdr_pitch, &ovl->cmdq_reg, ovl->regs, - DISP_REG_OVL_HDR_PITCH(ovl, idx)); - } else { - mtk_ddp_write_relaxed(cmdq_pkt, - overlay_pitch.split_pitch.msb, - &ovl->cmdq_reg, ovl->regs, DISP_REG_OVL_PITCH_MSB(idx)); - } + if (ovl->data->supports_afbc) + mtk_ovl_afbc_layer_config(ovl, idx, pending, cmdq_pkt); mtk_ovl_set_bit_depth(dev, idx, fmt, cmdq_pkt); mtk_ovl_layer_on(dev, idx, cmdq_pkt);

2 weeks, 3 days

2
1
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror