November 2024 - Linux-stable-mirror

[PATCH 1/4] drm/i915/dsb: Don't use indexed register writes needlessly

by Ville Syrjala

From: Ville Syrjälä <ville.syrjala(a)linux.intel.com> Turns out the DSB indexed register write command has rather significant initial overhead compared to the normal MMIO write command. Based on some quick experiments on TGL you have to write the register at least ~5 times for the indexed write command to come out ahead. If you write the register less times than that the MMIO write is faster. So it seems my automagic indexed write logic was a bit misguided. Go back to the original approach only use indexed writes for the cases we know will benefit from it (indexed LUT register updates). Currently we shouldn't have any cases where this truly matters (just some rare double writes to the precision LUT index registers), but we will need to switch the legacy LUT updates to write each LUT register twice (to avoid some palette anti-collision logic troubles). This would be close to the worst case for using indexed writes (two writes per register, and 256 separate registers). Using the MMIO write command should shave off around 30% of the execution time compared to using the indexed write command. Cc: stable(a)vger.kernel.org Fixes: 34d8311f4a1c ("drm/i915/dsb: Re-instate DSB for LUT updates") Fixes: 25ea3411bd23 ("drm/i915/dsb: Use non-posted register writes for legacy LUT") Signed-off-by: Ville Syrjälä <ville.syrjala(a)linux.intel.com> --- drivers/gpu/drm/i915/display/intel_color.c | 51 +++++++++++++--------- drivers/gpu/drm/i915/display/intel_dsb.c | 19 ++++++-- drivers/gpu/drm/i915/display/intel_dsb.h | 2 + 3 files changed, 49 insertions(+), 23 deletions(-) diff --git a/drivers/gpu/drm/i915/display/intel_color.c b/drivers/gpu/drm/i915/display/intel_color.c index 174753625bca..6ea3d5c58cb1 100644 --- a/drivers/gpu/drm/i915/display/intel_color.c +++ b/drivers/gpu/drm/i915/display/intel_color.c @@ -1343,6 +1343,17 @@ static void ilk_lut_write(const struct intel_crtc_state *crtc_state, intel_de_write_fw(display, reg, val); } +static void ilk_lut_write_indexed(const struct intel_crtc_state *crtc_state, + i915_reg_t reg, u32 val) +{ + struct intel_display *display = to_intel_display(crtc_state); + + if (crtc_state->dsb_color_vblank) + intel_dsb_reg_write_indexed(crtc_state->dsb_color_vblank, reg, val); + else + intel_de_write_fw(display, reg, val); +} + static void ilk_load_lut_8(const struct intel_crtc_state *crtc_state, const struct drm_property_blob *blob) { @@ -1458,8 +1469,8 @@ static void bdw_load_lut_10(const struct intel_crtc_state *crtc_state, prec_index); for (i = 0; i < lut_size; i++) - ilk_lut_write(crtc_state, PREC_PAL_DATA(pipe), - ilk_lut_10(&lut[i])); + ilk_lut_write_indexed(crtc_state, PREC_PAL_DATA(pipe), + ilk_lut_10(&lut[i])); /* * Reset the index, otherwise it prevents the legacy palette to be @@ -1612,16 +1623,16 @@ static void glk_load_degamma_lut(const struct intel_crtc_state *crtc_state, * ToDo: Extend to max 7.0. Enable 32 bit input value * as compared to just 16 to achieve this. */ - ilk_lut_write(crtc_state, PRE_CSC_GAMC_DATA(pipe), - DISPLAY_VER(display) >= 14 ? - mtl_degamma_lut(&lut[i]) : glk_degamma_lut(&lut[i])); + ilk_lut_write_indexed(crtc_state, PRE_CSC_GAMC_DATA(pipe), + DISPLAY_VER(display) >= 14 ? + mtl_degamma_lut(&lut[i]) : glk_degamma_lut(&lut[i])); } /* Clamp values > 1.0. */ while (i++ < glk_degamma_lut_size(display)) - ilk_lut_write(crtc_state, PRE_CSC_GAMC_DATA(pipe), - DISPLAY_VER(display) >= 14 ? - 1 << 24 : 1 << 16); + ilk_lut_write_indexed(crtc_state, PRE_CSC_GAMC_DATA(pipe), + DISPLAY_VER(display) >= 14 ? + 1 << 24 : 1 << 16); ilk_lut_write(crtc_state, PRE_CSC_GAMC_INDEX(pipe), 0); } @@ -1687,10 +1698,10 @@ icl_program_gamma_superfine_segment(const struct intel_crtc_state *crtc_state) for (i = 0; i < 9; i++) { const struct drm_color_lut *entry = &lut[i]; - ilk_lut_write(crtc_state, PREC_PAL_MULTI_SEG_DATA(pipe), - ilk_lut_12p4_ldw(entry)); - ilk_lut_write(crtc_state, PREC_PAL_MULTI_SEG_DATA(pipe), - ilk_lut_12p4_udw(entry)); + ilk_lut_write_indexed(crtc_state, PREC_PAL_MULTI_SEG_DATA(pipe), + ilk_lut_12p4_ldw(entry)); + ilk_lut_write_indexed(crtc_state, PREC_PAL_MULTI_SEG_DATA(pipe), + ilk_lut_12p4_udw(entry)); } ilk_lut_write(crtc_state, PREC_PAL_MULTI_SEG_INDEX(pipe), @@ -1726,10 +1737,10 @@ icl_program_gamma_multi_segment(const struct intel_crtc_state *crtc_state) for (i = 1; i < 257; i++) { entry = &lut[i * 8]; - ilk_lut_write(crtc_state, PREC_PAL_DATA(pipe), - ilk_lut_12p4_ldw(entry)); - ilk_lut_write(crtc_state, PREC_PAL_DATA(pipe), - ilk_lut_12p4_udw(entry)); + ilk_lut_write_indexed(crtc_state, PREC_PAL_DATA(pipe), + ilk_lut_12p4_ldw(entry)); + ilk_lut_write_indexed(crtc_state, PREC_PAL_DATA(pipe), + ilk_lut_12p4_udw(entry)); } /* @@ -1747,10 +1758,10 @@ icl_program_gamma_multi_segment(const struct intel_crtc_state *crtc_state) for (i = 0; i < 256; i++) { entry = &lut[i * 8 * 128]; - ilk_lut_write(crtc_state, PREC_PAL_DATA(pipe), - ilk_lut_12p4_ldw(entry)); - ilk_lut_write(crtc_state, PREC_PAL_DATA(pipe), - ilk_lut_12p4_udw(entry)); + ilk_lut_write_indexed(crtc_state, PREC_PAL_DATA(pipe), + ilk_lut_12p4_ldw(entry)); + ilk_lut_write_indexed(crtc_state, PREC_PAL_DATA(pipe), + ilk_lut_12p4_udw(entry)); } ilk_lut_write(crtc_state, PREC_PAL_INDEX(pipe), diff --git a/drivers/gpu/drm/i915/display/intel_dsb.c b/drivers/gpu/drm/i915/display/intel_dsb.c index b7b44399adaa..4d3785f5cb52 100644 --- a/drivers/gpu/drm/i915/display/intel_dsb.c +++ b/drivers/gpu/drm/i915/display/intel_dsb.c @@ -273,16 +273,20 @@ static bool intel_dsb_prev_ins_is_indexed_write(struct intel_dsb *dsb, i915_reg_ } /** - * intel_dsb_reg_write() - Emit register wriite to the DSB context + * intel_dsb_reg_write_indexed() - Emit register wriite to the DSB context * @dsb: DSB context * @reg: register address. * @val: value. * * This function is used for writing register-value pair in command * buffer of DSB. + * + * Note that indexed writes are slower than normal MMIO writes + * for a small number (less than 5 or so) of writes to the same + * register. */ -void intel_dsb_reg_write(struct intel_dsb *dsb, - i915_reg_t reg, u32 val) +void intel_dsb_reg_write_indexed(struct intel_dsb *dsb, + i915_reg_t reg, u32 val) { /* * For example the buffer will look like below for 3 dwords for auto @@ -340,6 +344,15 @@ void intel_dsb_reg_write(struct intel_dsb *dsb, } } +void intel_dsb_reg_write(struct intel_dsb *dsb, + i915_reg_t reg, u32 val) +{ + intel_dsb_emit(dsb, val, + (DSB_OPCODE_MMIO_WRITE << DSB_OPCODE_SHIFT) | + (DSB_BYTE_EN << DSB_BYTE_EN_SHIFT) | + i915_mmio_reg_offset(reg)); +} + static u32 intel_dsb_mask_to_byte_en(u32 mask) { return (!!(mask & 0xff000000) << 3 | diff --git a/drivers/gpu/drm/i915/display/intel_dsb.h b/drivers/gpu/drm/i915/display/intel_dsb.h index 33e0fc2ab380..da6df07a3c83 100644 --- a/drivers/gpu/drm/i915/display/intel_dsb.h +++ b/drivers/gpu/drm/i915/display/intel_dsb.h @@ -34,6 +34,8 @@ void intel_dsb_finish(struct intel_dsb *dsb); void intel_dsb_cleanup(struct intel_dsb *dsb); void intel_dsb_reg_write(struct intel_dsb *dsb, i915_reg_t reg, u32 val); +void intel_dsb_reg_write_indexed(struct intel_dsb *dsb, + i915_reg_t reg, u32 val); void intel_dsb_reg_write_masked(struct intel_dsb *dsb, i915_reg_t reg, u32 mask, u32 val); void intel_dsb_noop(struct intel_dsb *dsb, int count); -- 2.45.2

7 months

2
1
0 0

[PATCH 3/9] serial: sh-sci: Clean sci_ports[0] after at earlycon exit

by Claudiu

From: Claudiu Beznea <claudiu.beznea.uj(a)bp.renesas.com> The early_console_setup() function initializes the sci_ports[0].port with an object of type struct uart_port obtained from the object of type struct earlycon_device received as argument by the early_console_setup(). It may happen that later, when the rest of the serial ports are probed, the serial port that was used as earlycon (e.g., port A) to be mapped to a different position in sci_ports[] and the slot 0 to be used by a different serial port (e.g., port B), as follows: sci_ports[0] = port A sci_ports[X] = port B In this case, the new port mapped at index zero will have associated data that was used for earlycon. In case this happens, after Linux boot, any access to the serial port that maps on sci_ports[0] (port A) will block the serial port that was used as earlycon (port B). To fix this, add early_console_exit() that clean the sci_ports[0] at earlycon exit time. Fixes: 0b0cced19ab1 ("serial: sh-sci: Add CONFIG_SERIAL_EARLYCON support") Cc: stable(a)vger.kernel.org Signed-off-by: Claudiu Beznea <claudiu.beznea.uj(a)bp.renesas.com> --- drivers/tty/serial/sh-sci.c | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) diff --git a/drivers/tty/serial/sh-sci.c b/drivers/tty/serial/sh-sci.c index 8e2d534401fa..2f8188bdb251 100644 --- a/drivers/tty/serial/sh-sci.c +++ b/drivers/tty/serial/sh-sci.c @@ -3546,6 +3546,32 @@ sh_early_platform_init_buffer("earlyprintk", &sci_driver, #ifdef CONFIG_SERIAL_SH_SCI_EARLYCON static struct plat_sci_port port_cfg __initdata; +static int early_console_exit(struct console *co) +{ + struct sci_port *sci_port = &sci_ports[0]; + struct uart_port *port = &sci_port->port; + unsigned long flags; + int locked = 1; + + if (port->sysrq) + locked = 0; + else if (oops_in_progress) + locked = uart_port_trylock_irqsave(port, &flags); + else + uart_port_lock_irqsave(port, &flags); + + /* + * Clean the slot used by earlycon. A new SCI device might + * map to this slot. + */ + memset(sci_ports, 0, sizeof(*sci_port)); + + if (locked) + uart_port_unlock_irqrestore(port, flags); + + return 0; +} + static int __init early_console_setup(struct earlycon_device *device, int type) { @@ -3562,6 +3588,8 @@ static int __init early_console_setup(struct earlycon_device *device, SCSCR_RE | SCSCR_TE | port_cfg.scscr); device->con->write = serial_console_write; + device->con->exit = early_console_exit; + return 0; } static int __init sci_early_console_setup(struct earlycon_device *device, -- 2.39.2

7 months

3
2
0 0

[PATCH 6.1 1/1] scsi: lpfc: Validate hdwq pointers before dereferencing in reset/errata paths

by Xiangyu Chen

From: Justin Tee <justin.tee(a)broadcom.com> [ Upstream commit 2be1d4f11944cd6283cb97268b3e17c4424945ca ] When the HBA is undergoing a reset or is handling an errata event, NULL ptr dereference crashes may occur in routines such as lpfc_sli_flush_io_rings(), lpfc_dev_loss_tmo_callbk(), or lpfc_abort_handler(). Add NULL ptr checks before dereferencing hdwq pointers that may have been freed due to operations colliding with a reset or errata event handler. Signed-off-by: Justin Tee <justin.tee(a)broadcom.com> Link: https://lore.kernel.org/r/20240726231512.92867-4-justintee8345@gmail.com Signed-off-by: Martin K. Petersen <martin.petersen(a)oracle.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> [Xiangyu: BP to fix CVE: CVE-2024-49891, no test_bit() conflict resolution] Signed-off-by: Xiangyu Chen <xiangyu.chen(a)windriver.com> --- drivers/scsi/lpfc/lpfc_hbadisc.c | 3 ++- drivers/scsi/lpfc/lpfc_scsi.c | 13 +++++++++++-- drivers/scsi/lpfc/lpfc_sli.c | 11 +++++++++++ 3 files changed, 24 insertions(+), 3 deletions(-) diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c index aaa98a006fdc..d3a5f10b8b83 100644 --- a/drivers/scsi/lpfc/lpfc_hbadisc.c +++ b/drivers/scsi/lpfc/lpfc_hbadisc.c @@ -177,7 +177,8 @@ lpfc_dev_loss_tmo_callbk(struct fc_rport *rport) /* Don't schedule a worker thread event if the vport is going down. * The teardown process cleans up the node via lpfc_drop_node. */ - if (vport->load_flag & FC_UNLOADING) { + if ((vport->load_flag & FC_UNLOADING) || + !(phba->hba_flag & HBA_SETUP)) { ((struct lpfc_rport_data *)rport->dd_data)->pnode = NULL; ndlp->rport = NULL; diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c index 2a81a42de5c1..ed32aa01c711 100644 --- a/drivers/scsi/lpfc/lpfc_scsi.c +++ b/drivers/scsi/lpfc/lpfc_scsi.c @@ -5554,11 +5554,20 @@ lpfc_abort_handler(struct scsi_cmnd *cmnd) iocb = &lpfc_cmd->cur_iocbq; if (phba->sli_rev == LPFC_SLI_REV4) { - pring_s4 = phba->sli4_hba.hdwq[iocb->hba_wqidx].io_wq->pring; - if (!pring_s4) { + /* if the io_wq & pring are gone, the port was reset. */ + if (!phba->sli4_hba.hdwq[iocb->hba_wqidx].io_wq || + !phba->sli4_hba.hdwq[iocb->hba_wqidx].io_wq->pring) { + lpfc_printf_vlog(vport, KERN_WARNING, LOG_FCP, + "2877 SCSI Layer I/O Abort Request " + "IO CMPL Status x%x ID %d LUN %llu " + "HBA_SETUP %d\n", FAILED, + cmnd->device->id, + (u64)cmnd->device->lun, + (HBA_SETUP & phba->hba_flag)); ret = FAILED; goto out_unlock_hba; } + pring_s4 = phba->sli4_hba.hdwq[iocb->hba_wqidx].io_wq->pring; spin_lock(&pring_s4->ring_lock); } /* the command is in process of being cancelled */ diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c index 587e3c2f7c48..1e04b6fc127a 100644 --- a/drivers/scsi/lpfc/lpfc_sli.c +++ b/drivers/scsi/lpfc/lpfc_sli.c @@ -4668,6 +4668,17 @@ lpfc_sli_flush_io_rings(struct lpfc_hba *phba) /* Look on all the FCP Rings for the iotag */ if (phba->sli_rev >= LPFC_SLI_REV4) { for (i = 0; i < phba->cfg_hdw_queue; i++) { + if (!phba->sli4_hba.hdwq || + !phba->sli4_hba.hdwq[i].io_wq) { + lpfc_printf_log(phba, KERN_ERR, LOG_SLI, + "7777 hdwq's deleted %lx " + "%lx %x %x\n", + (unsigned long)phba->pport->load_flag, + (unsigned long)phba->hba_flag, + phba->link_state, + phba->sli.sli_flag); + return; + } pring = phba->sli4_hba.hdwq[i].io_wq->pring; spin_lock_irq(&pring->ring_lock); -- 2.25.1

7 months

2
3
0 0

[PATCH 6.6] dm: fix a crash if blk_alloc_disk fails

by Bin Lan

From: Mikulas Patocka <mpatocka(a)redhat.com> [ Upstream commit fed13a5478680614ba97fc87e71f16e2e197912e ] If blk_alloc_disk fails, the variable md->disk is set to an error value. cleanup_mapped_device will see that md->disk is non-NULL and it will attempt to access it, causing a crash on this statement "md->disk->private_data = NULL;". Signed-off-by: Mikulas Patocka <mpatocka(a)redhat.com> Reported-by: Chenyuan Yang <chenyuan0y(a)gmail.com> Closes: https://marc.info/?l=dm-devel&m=172824125004329&w=2 Cc: stable(a)vger.kernel.org Reviewed-by: Nitesh Shetty <nj.shetty(a)samsung.com> Signed-off-by: Bin Lan <bin.lan.cn(a)windriver.com> --- drivers/md/dm.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 5dd0a42463a2..f45427291ea6 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -2077,8 +2077,10 @@ static struct mapped_device *alloc_dev(int minor) * override accordingly. */ md->disk = blk_alloc_disk(md->numa_node_id); - if (!md->disk) + if (!md->disk){ + md->disk = NULL; goto bad; + } md->queue = md->disk->queue; init_waitqueue_head(&md->wait); -- 2.34.1

7 months

3
2
0 0

[PATCH 6.1.y] rcu-tasks: Fix access non-existent percpu rtpcp variable in rcu_tasks_need_gpcb()

by Xiangyu Chen

From: Zqiang <qiang.zhang1211(a)gmail.com> [ Upstream commit fd70e9f1d85f5323096ad313ba73f5fe3d15ea41 ] For kernels built with CONFIG_FORCE_NR_CPUS=y, the nr_cpu_ids is defined as NR_CPUS instead of the number of possible cpus, this will cause the following system panic: smpboot: Allowing 4 CPUs, 0 hotplug CPUs ... setup_percpu: NR_CPUS:512 nr_cpumask_bits:512 nr_cpu_ids:512 nr_node_ids:1 ... BUG: unable to handle page fault for address: ffffffff9911c8c8 Oops: 0000 [#1] PREEMPT SMP PTI CPU: 0 PID: 15 Comm: rcu_tasks_trace Tainted: G W 6.6.21 #1 5dc7acf91a5e8e9ac9dcfc35bee0245691283ea6 RIP: 0010:rcu_tasks_need_gpcb+0x25d/0x2c0 RSP: 0018:ffffa371c00a3e60 EFLAGS: 00010082 CR2: ffffffff9911c8c8 CR3: 000000040fa20005 CR4: 00000000001706f0 Call Trace: <TASK> ? __die+0x23/0x80 ? page_fault_oops+0xa4/0x180 ? exc_page_fault+0x152/0x180 ? asm_exc_page_fault+0x26/0x40 ? rcu_tasks_need_gpcb+0x25d/0x2c0 ? __pfx_rcu_tasks_kthread+0x40/0x40 rcu_tasks_one_gp+0x69/0x180 rcu_tasks_kthread+0x94/0xc0 kthread+0xe8/0x140 ? __pfx_kthread+0x40/0x40 ret_from_fork+0x34/0x80 ? __pfx_kthread+0x40/0x40 ret_from_fork_asm+0x1b/0x80 </TASK> Considering that there may be holes in the CPU numbers, use the maximum possible cpu number, instead of nr_cpu_ids, for configuring enqueue and dequeue limits. [ neeraj.upadhyay: Fix htmldocs build error reported by Stephen Rothwell ] Closes: https://lore.kernel.org/linux-input/CALMA0xaTSMN+p4xUXkzrtR5r6k7hgoswcaXx7b… Reported-by: Zhixu Liu <zhixu.liu(a)gmail.com> Signed-off-by: Zqiang <qiang.zhang1211(a)gmail.com> Signed-off-by: Neeraj Upadhyay <neeraj.upadhyay(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> [Xiangyu: BP to fix CVE:CVE-2024-49926, minor conflict resolution] Signed-off-by: Xiangyu Chen <xiangyu.chen(a)windriver.com> --- kernel/rcu/tasks.h | 82 ++++++++++++++++++++++++++++++---------------- 1 file changed, 54 insertions(+), 28 deletions(-) diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h index bb6b037ef30f..46b207eac171 100644 --- a/kernel/rcu/tasks.h +++ b/kernel/rcu/tasks.h @@ -31,6 +31,7 @@ typedef void (*postgp_func_t)(struct rcu_tasks *rtp); * @barrier_q_head: RCU callback for barrier operation. * @rtp_blkd_tasks: List of tasks blocked as readers. * @cpu: CPU number corresponding to this entry. + * @index: Index of this CPU in rtpcp_array of the rcu_tasks structure. * @rtpp: Pointer to the rcu_tasks structure. */ struct rcu_tasks_percpu { @@ -43,6 +44,7 @@ struct rcu_tasks_percpu { struct rcu_head barrier_q_head; struct list_head rtp_blkd_tasks; int cpu; + int index; struct rcu_tasks *rtpp; }; @@ -68,6 +70,7 @@ struct rcu_tasks_percpu { * @postgp_func: This flavor's post-grace-period function (optional). * @call_func: This flavor's call_rcu()-equivalent function. * @rtpcpu: This flavor's rcu_tasks_percpu structure. + * @rtpcp_array: Array of pointers to rcu_tasks_percpu structure of CPUs in cpu_possible_mask. * @percpu_enqueue_shift: Shift down CPU ID this much when enqueuing callbacks. * @percpu_enqueue_lim: Number of per-CPU callback queues in use for enqueuing. * @percpu_dequeue_lim: Number of per-CPU callback queues in use for dequeuing. @@ -100,6 +103,7 @@ struct rcu_tasks { postgp_func_t postgp_func; call_rcu_func_t call_func; struct rcu_tasks_percpu __percpu *rtpcpu; + struct rcu_tasks_percpu **rtpcp_array; int percpu_enqueue_shift; int percpu_enqueue_lim; int percpu_dequeue_lim; @@ -164,6 +168,8 @@ module_param(rcu_task_contend_lim, int, 0444); static int rcu_task_collapse_lim __read_mostly = 10; module_param(rcu_task_collapse_lim, int, 0444); +static int rcu_task_cpu_ids; + /* RCU tasks grace-period state for debugging. */ #define RTGS_INIT 0 #define RTGS_WAIT_WAIT_CBS 1 @@ -228,6 +234,8 @@ static void cblist_init_generic(struct rcu_tasks *rtp) unsigned long flags; int lim; int shift; + int maxcpu; + int index = 0; raw_spin_lock_irqsave(&rtp->cbs_gbl_lock, flags); if (rcu_task_enqueue_lim < 0) { @@ -238,14 +246,9 @@ static void cblist_init_generic(struct rcu_tasks *rtp) } lim = rcu_task_enqueue_lim; - if (lim > nr_cpu_ids) - lim = nr_cpu_ids; - shift = ilog2(nr_cpu_ids / lim); - if (((nr_cpu_ids - 1) >> shift) >= lim) - shift++; - WRITE_ONCE(rtp->percpu_enqueue_shift, shift); - WRITE_ONCE(rtp->percpu_dequeue_lim, lim); - smp_store_release(&rtp->percpu_enqueue_lim, lim); + rtp->rtpcp_array = kcalloc(num_possible_cpus(), sizeof(struct rcu_tasks_percpu *), GFP_KERNEL); + BUG_ON(!rtp->rtpcp_array); + for_each_possible_cpu(cpu) { struct rcu_tasks_percpu *rtpcp = per_cpu_ptr(rtp->rtpcpu, cpu); @@ -258,16 +261,33 @@ static void cblist_init_generic(struct rcu_tasks *rtp) INIT_WORK(&rtpcp->rtp_work, rcu_tasks_invoke_cbs_wq); rtpcp->cpu = cpu; rtpcp->rtpp = rtp; + rtpcp->index = index; + rtp->rtpcp_array[index] = rtpcp; + index++; if (!rtpcp->rtp_blkd_tasks.next) INIT_LIST_HEAD(&rtpcp->rtp_blkd_tasks); raw_spin_unlock_rcu_node(rtpcp); // irqs remain disabled. + maxcpu = cpu; } raw_spin_unlock_irqrestore(&rtp->cbs_gbl_lock, flags); if (rcu_task_cb_adjust) pr_info("%s: Setting adjustable number of callback queues.\n", __func__); - pr_info("%s: Setting shift to %d and lim to %d.\n", __func__, data_race(rtp->percpu_enqueue_shift), data_race(rtp->percpu_enqueue_lim)); + rcu_task_cpu_ids = maxcpu + 1; + if (lim > rcu_task_cpu_ids) + lim = rcu_task_cpu_ids; + shift = ilog2(rcu_task_cpu_ids / lim); + if (((rcu_task_cpu_ids - 1) >> shift) >= lim) + shift++; + WRITE_ONCE(rtp->percpu_enqueue_shift, shift); + WRITE_ONCE(rtp->percpu_dequeue_lim, lim); + smp_store_release(&rtp->percpu_enqueue_lim, lim); + + pr_info("%s: Setting shift to %d and lim to %d rcu_task_cb_adjust=%d rcu_task_cpu_ids=%d.\n", + rtp->name, data_race(rtp->percpu_enqueue_shift), data_race(rtp->percpu_enqueue_lim), + rcu_task_cb_adjust, rcu_task_cpu_ids); + } // IRQ-work handler that does deferred wakeup for call_rcu_tasks_generic(). @@ -307,7 +327,7 @@ static void call_rcu_tasks_generic(struct rcu_head *rhp, rcu_callback_t func, rtpcp->rtp_n_lock_retries = 0; } if (rcu_task_cb_adjust && ++rtpcp->rtp_n_lock_retries > rcu_task_contend_lim && - READ_ONCE(rtp->percpu_enqueue_lim) != nr_cpu_ids) + READ_ONCE(rtp->percpu_enqueue_lim) != rcu_task_cpu_ids) needadjust = true; // Defer adjustment to avoid deadlock. } if (!rcu_segcblist_is_enabled(&rtpcp->cblist)) { @@ -320,10 +340,10 @@ static void call_rcu_tasks_generic(struct rcu_head *rhp, rcu_callback_t func, raw_spin_unlock_irqrestore_rcu_node(rtpcp, flags); if (unlikely(needadjust)) { raw_spin_lock_irqsave(&rtp->cbs_gbl_lock, flags); - if (rtp->percpu_enqueue_lim != nr_cpu_ids) { + if (rtp->percpu_enqueue_lim != rcu_task_cpu_ids) { WRITE_ONCE(rtp->percpu_enqueue_shift, 0); - WRITE_ONCE(rtp->percpu_dequeue_lim, nr_cpu_ids); - smp_store_release(&rtp->percpu_enqueue_lim, nr_cpu_ids); + WRITE_ONCE(rtp->percpu_dequeue_lim, rcu_task_cpu_ids); + smp_store_release(&rtp->percpu_enqueue_lim, rcu_task_cpu_ids); pr_info("Switching %s to per-CPU callback queuing.\n", rtp->name); } raw_spin_unlock_irqrestore(&rtp->cbs_gbl_lock, flags); @@ -394,6 +414,8 @@ static int rcu_tasks_need_gpcb(struct rcu_tasks *rtp) int needgpcb = 0; for (cpu = 0; cpu < smp_load_acquire(&rtp->percpu_dequeue_lim); cpu++) { + if (!cpu_possible(cpu)) + continue; struct rcu_tasks_percpu *rtpcp = per_cpu_ptr(rtp->rtpcpu, cpu); /* Advance and accelerate any new callbacks. */ @@ -426,7 +448,7 @@ static int rcu_tasks_need_gpcb(struct rcu_tasks *rtp) if (rcu_task_cb_adjust && ncbs <= rcu_task_collapse_lim) { raw_spin_lock_irqsave(&rtp->cbs_gbl_lock, flags); if (rtp->percpu_enqueue_lim > 1) { - WRITE_ONCE(rtp->percpu_enqueue_shift, order_base_2(nr_cpu_ids)); + WRITE_ONCE(rtp->percpu_enqueue_shift, order_base_2(rcu_task_cpu_ids)); smp_store_release(&rtp->percpu_enqueue_lim, 1); rtp->percpu_dequeue_gpseq = get_state_synchronize_rcu(); gpdone = false; @@ -441,7 +463,9 @@ static int rcu_tasks_need_gpcb(struct rcu_tasks *rtp) pr_info("Completing switch %s to CPU-0 callback queuing.\n", rtp->name); } if (rtp->percpu_dequeue_lim == 1) { - for (cpu = rtp->percpu_dequeue_lim; cpu < nr_cpu_ids; cpu++) { + for (cpu = rtp->percpu_dequeue_lim; cpu < rcu_task_cpu_ids; cpu++) { + if (!cpu_possible(cpu)) + continue; struct rcu_tasks_percpu *rtpcp = per_cpu_ptr(rtp->rtpcpu, cpu); WARN_ON_ONCE(rcu_segcblist_n_cbs(&rtpcp->cblist)); @@ -456,30 +480,32 @@ static int rcu_tasks_need_gpcb(struct rcu_tasks *rtp) // Advance callbacks and invoke any that are ready. static void rcu_tasks_invoke_cbs(struct rcu_tasks *rtp, struct rcu_tasks_percpu *rtpcp) { - int cpu; - int cpunext; int cpuwq; unsigned long flags; int len; + int index; struct rcu_head *rhp; struct rcu_cblist rcl = RCU_CBLIST_INITIALIZER(rcl); struct rcu_tasks_percpu *rtpcp_next; - cpu = rtpcp->cpu; - cpunext = cpu * 2 + 1; - if (cpunext < smp_load_acquire(&rtp->percpu_dequeue_lim)) { - rtpcp_next = per_cpu_ptr(rtp->rtpcpu, cpunext); - cpuwq = rcu_cpu_beenfullyonline(cpunext) ? cpunext : WORK_CPU_UNBOUND; - queue_work_on(cpuwq, system_wq, &rtpcp_next->rtp_work); - cpunext++; - if (cpunext < smp_load_acquire(&rtp->percpu_dequeue_lim)) { - rtpcp_next = per_cpu_ptr(rtp->rtpcpu, cpunext); - cpuwq = rcu_cpu_beenfullyonline(cpunext) ? cpunext : WORK_CPU_UNBOUND; + index = rtpcp->index * 2 + 1; + if (index < num_possible_cpus()) { + rtpcp_next = rtp->rtpcp_array[index]; + if (rtpcp_next->cpu < smp_load_acquire(&rtp->percpu_dequeue_lim)) { + cpuwq = rcu_cpu_beenfullyonline(rtpcp_next->cpu) ? rtpcp_next->cpu : WORK_CPU_UNBOUND; queue_work_on(cpuwq, system_wq, &rtpcp_next->rtp_work); + index++; + if (index < num_possible_cpus()) { + rtpcp_next = rtp->rtpcp_array[index]; + if (rtpcp_next->cpu < smp_load_acquire(&rtp->percpu_dequeue_lim)) { + cpuwq = rcu_cpu_beenfullyonline(rtpcp_next->cpu) ? rtpcp_next->cpu : WORK_CPU_UNBOUND; + queue_work_on(cpuwq, system_wq, &rtpcp_next->rtp_work); + } + } } } - if (rcu_segcblist_empty(&rtpcp->cblist) || !cpu_possible(cpu)) + if (rcu_segcblist_empty(&rtpcp->cblist)) return; raw_spin_lock_irqsave_rcu_node(rtpcp, flags); rcu_segcblist_advance(&rtpcp->cblist, rcu_seq_current(&rtp->tasks_gp_seq)); -- 2.43.0

7 months

2
1
0 0

[PATCH 6.6] xfs: add bounds checking to xlog_recover_process_data

by Bin Lan

From: lei lu <llfamsec(a)gmail.com> [ Upstream commit fb63435b7c7dc112b1ae1baea5486e0a6e27b196 ] There is a lack of verification of the space occupied by fixed members of xlog_op_header in the xlog_recover_process_data. We can create a crafted image to trigger an out of bounds read by following these steps: 1) Mount an image of xfs, and do some file operations to leave records 2) Before umounting, copy the image for subsequent steps to simulate abnormal exit. Because umount will ensure that tail_blk and head_blk are the same, which will result in the inability to enter xlog_recover_process_data 3) Write a tool to parse and modify the copied image in step 2 4) Make the end of the xlog_op_header entries only 1 byte away from xlog_rec_header->h_size 5) xlog_rec_header->h_num_logops++ 6) Modify xlog_rec_header->h_crc Fix: Add a check to make sure there is sufficient space to access fixed members of xlog_op_header. Signed-off-by: lei lu <llfamsec(a)gmail.com> Reviewed-by: Dave Chinner <dchinner(a)redhat.com> Reviewed-by: Darrick J. Wong <djwong(a)kernel.org> Signed-off-by: Chandan Babu R <chandanbabu(a)kernel.org> Signed-off-by: Bin Lan <bin.lan.cn(a)windriver.com> --- fs/xfs/xfs_log_recover.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c index 9f9d3abad2cf..d11de0fa5c5f 100644 --- a/fs/xfs/xfs_log_recover.c +++ b/fs/xfs/xfs_log_recover.c @@ -2456,7 +2456,10 @@ xlog_recover_process_data( ohead = (struct xlog_op_header *)dp; dp += sizeof(*ohead); - ASSERT(dp <= end); + if (dp > end) { + xfs_warn(log->l_mp, "%s: op header overrun", __func__); + return -EFSCORRUPTED; + } /* errors will abort recovery */ error = xlog_recover_process_ophdr(log, rhash, rhead, ohead, -- 2.34.1

7 months

2
1
0 0

[PATCH 6.1] wifi: iwlwifi: mvm: avoid NULL pointer dereference

by Xiangyu Chen

From: Miri Korenblit <miriam.rachel.korenblit(a)intel.com> [ Upstream commit 557a6cd847645e667f3b362560bd7e7c09aac284 ] iwl_mvm_tx_skb_sta() and iwl_mvm_tx_mpdu() verify that the mvmvsta pointer is not NULL. It retrieves this pointer using iwl_mvm_sta_from_mac80211, which is dereferencing the ieee80211_sta pointer. If sta is NULL, iwl_mvm_sta_from_mac80211 will dereference a NULL pointer. Fix this by checking the sta pointer before retrieving the mvmsta from it. If sta is not NULL, then mvmsta isn't either. Signed-off-by: Miri Korenblit <miriam.rachel.korenblit(a)intel.com> Reviewed-by: Johannes Berg <johannes.berg(a)intel.com> Link: https://patch.msgid.link/20240825191257.880921ce23b7.I340052d70ab6d3410724c… Signed-off-by: Johannes Berg <johannes.berg(a)intel.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Xiangyu Chen <xiangyu.chen(a)windriver.com> --- drivers/net/wireless/intel/iwlwifi/mvm/tx.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c index 76219486b9c2..43a732b0c168 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c @@ -1105,6 +1105,9 @@ static int iwl_mvm_tx_mpdu(struct iwl_mvm *mvm, struct sk_buff *skb, bool is_ampdu = false; int hdrlen; + if (WARN_ON_ONCE(!sta)) + return -1; + mvmsta = iwl_mvm_sta_from_mac80211(sta); fc = hdr->frame_control; hdrlen = ieee80211_hdrlen(fc); @@ -1112,9 +1115,6 @@ static int iwl_mvm_tx_mpdu(struct iwl_mvm *mvm, struct sk_buff *skb, if (IWL_MVM_NON_TRANSMITTING_AP && ieee80211_is_probe_resp(fc)) return -1; - if (WARN_ON_ONCE(!mvmsta)) - return -1; - if (WARN_ON_ONCE(mvmsta->sta_id == IWL_MVM_INVALID_STA)) return -1; @@ -1242,16 +1242,18 @@ static int iwl_mvm_tx_mpdu(struct iwl_mvm *mvm, struct sk_buff *skb, int iwl_mvm_tx_skb_sta(struct iwl_mvm *mvm, struct sk_buff *skb, struct ieee80211_sta *sta) { - struct iwl_mvm_sta *mvmsta = iwl_mvm_sta_from_mac80211(sta); + struct iwl_mvm_sta *mvmsta; struct ieee80211_tx_info info; struct sk_buff_head mpdus_skbs; unsigned int payload_len; int ret; struct sk_buff *orig_skb = skb; - if (WARN_ON_ONCE(!mvmsta)) + if (WARN_ON_ONCE(!sta)) return -1; + mvmsta = iwl_mvm_sta_from_mac80211(sta); + if (WARN_ON_ONCE(mvmsta->sta_id == IWL_MVM_INVALID_STA)) return -1; -- 2.25.1

7 months

2
1
0 0

[PATCH 5.15] ksmbd: fix slab-use-after-free in smb3_preauth_hash_rsp

by mingli.yu＠windriver.com

From: Namjae Jeon <linkinjeon(a)kernel.org> commit b8fc56fbca7482c1e5c0e3351c6ae78982e25ada upstream. ksmbd_user_session_put should be called under smb3_preauth_hash_rsp(). It will avoid freeing session before calling smb3_preauth_hash_rsp(). Cc: stable(a)vger.kernel.org # v5.15+ Reported-by: Norbert Szetei <norbert(a)doyensec.com> Tested-by: Norbert Szetei <norbert(a)doyensec.com> Signed-off-by: Namjae Jeon <linkinjeon(a)kernel.org> Signed-off-by: Steve French <stfrench(a)microsoft.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Mingli Yu <mingli.yu(a)windriver.com> --- fs/ksmbd/server.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/ksmbd/server.c b/fs/ksmbd/server.c index 09ebcf39d5bc..da5b9678ad05 100644 --- a/fs/ksmbd/server.c +++ b/fs/ksmbd/server.c @@ -238,11 +238,11 @@ static void __handle_ksmbd_work(struct ksmbd_work *work, } while (is_chained == true); send: - if (work->sess) - ksmbd_user_session_put(work->sess); if (work->tcon) ksmbd_tree_connect_put(work->tcon); smb3_preauth_hash_rsp(work); + if (work->sess) + ksmbd_user_session_put(work->sess); if (work->sess && work->sess->enc && work->encrypted && conn->ops->encrypt_resp) { rc = conn->ops->encrypt_resp(work); -- 2.34.1

7 months

2
1
0 0

[PATCH 6.1/6.6] drm/amd/display: Check phantom_stream before it is used

by Xiangyu Chen

From: Alex Hung <alex.hung(a)amd.com> [ Upstream commit 3718a619a8c0a53152e76bb6769b6c414e1e83f4 ] dcn32_enable_phantom_stream can return null, so returned value must be checked before used. This fixes 1 NULL_RETURNS issue reported by Coverity. Reviewed-by: Rodrigo Siqueira <rodrigo.siqueira(a)amd.com> Signed-off-by: Jerry Zuo <jerry.zuo(a)amd.com> Signed-off-by: Alex Hung <alex.hung(a)amd.com> Tested-by: Daniel Wheeler <daniel.wheeler(a)amd.com> Signed-off-by: Alex Deucher <alexander.deucher(a)amd.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> [Xiangyu: BP to fix CVE: CVE-2024-49897, modified the source path] Signed-off-by: Xiangyu Chen <xiangyu.chen(a)windriver.com> --- drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c index 2b8700b291a4..ef47fb2f6905 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c @@ -1796,6 +1796,9 @@ void dcn32_add_phantom_pipes(struct dc *dc, struct dc_state *context, // be a valid candidate for SubVP (i.e. has a plane, stream, doesn't // already have phantom pipe assigned, etc.) by previous checks. phantom_stream = dcn32_enable_phantom_stream(dc, context, pipes, pipe_cnt, index); + if (!phantom_stream) + return; + dcn32_enable_phantom_plane(dc, context, phantom_stream, index); for (i = 0; i < dc->res_pool->pipe_count; i++) { -- 2.25.1

7 months

2
1
0 0

[PATCH 6.6.y/6.1.y] drm/amd/display: Add NULL check for function pointer in dcn20_set_output_transfer_func

by Xiangyu Chen

From: Srinivasan Shanmugam <srinivasan.shanmugam(a)amd.com> [ Upstream commit 62ed6f0f198da04e884062264df308277628004f ] This commit adds a null check for the set_output_gamma function pointer in the dcn20_set_output_transfer_func function. Previously, set_output_gamma was being checked for null at line 1030, but then it was being dereferenced without any null check at line 1048. This could potentially lead to a null pointer dereference error if set_output_gamma is null. To fix this, we now ensure that set_output_gamma is not null before dereferencing it. We do this by adding a null check for set_output_gamma before the call to set_output_gamma at line 1048. Cc: Tom Chung <chiahsuan.chung(a)amd.com> Cc: Rodrigo Siqueira <Rodrigo.Siqueira(a)amd.com> Cc: Roman Li <roman.li(a)amd.com> Cc: Alex Hung <alex.hung(a)amd.com> Cc: Aurabindo Pillai <aurabindo.pillai(a)amd.com> Cc: Harry Wentland <harry.wentland(a)amd.com> Cc: Hamza Mahfooz <hamza.mahfooz(a)amd.com> Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam(a)amd.com> Reviewed-by: Tom Chung <chiahsuan.chung(a)amd.com> Signed-off-by: Alex Deucher <alexander.deucher(a)amd.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Xiangyu Chen <xiangyu.chen(a)windriver.com> --- drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c index 9bd6a5716cdc..81b1ab55338a 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c @@ -856,7 +856,8 @@ bool dcn20_set_output_transfer_func(struct dc *dc, struct pipe_ctx *pipe_ctx, /* * if above if is not executed then 'params' equal to 0 and set in bypass */ - mpc->funcs->set_output_gamma(mpc, mpcc_id, params); + if (mpc->funcs->set_output_gamma) + mpc->funcs->set_output_gamma(mpc, mpcc_id, params); return true; } -- 2.43.0

7 months

2
1
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror November 2024