> In pcc_mbox_probe(), the PCCT table acquired via acpi_get_table() > is only released in error paths but not in the success path. This > leads to a permanent ACPI memory leak when the driver successfully > initializes. * You may occasionally put more than 66 characters into text lines of such a change description. https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/Documentation/process/submitting-patches.rst?h=v6.16#n658 * See also once more: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/Documentation/process/submitting-patches.rst?h=v6.16#n94 …> --- > Changes in v2: > - Add tags of 'Fixes' and 'Cc' > - Change goto target from out_put_pcct to e_nomem …> +++ b/drivers/mailbox/pcc.c > @@ -763,19 +763,19 @@ static int pcc_mbox_probe(struct platform_device *pdev) > GFP_KERNEL); > if (!pcc_mbox_channels) { > rc = -ENOMEM; > - goto err; > + goto e_nomem; > } … Why do you not move the assignment statement accordingly? …> @@ -796,17 +796,17 @@ static int pcc_mbox_probe(struct platform_device *pdev) > !pcc_mbox_ctrl->txdone_irq) { > pr_err("Platform Interrupt flag must be set to 1"); > rc = -EINVAL; > - goto err; > + goto e_nomem; > } … You misunderstood one of my development suggestions. …> @@ -827,9 +827,8 @@ static int pcc_mbox_probe(struct platform_device *pdev) …> - return 0; > -err: > + > +e_nomem: > acpi_put_table(pcct_tbl); > return rc; > } Would an other code variant be more reasonable? e_nomem: rc = -ENOMEM; goto err; Regards, Markus
