| Message ID | 20210427045120.2109980-1-sourabhjain@linux.ibm.com |
|---|---|
| State | Accepted |
| Commit | 40c753993e3aad51a12c21233486e2037417a4d6 |
| Headers | show |
| Series | [v6] powerpc/kexec_file: use current CPU info while setting up FDT | expand |
On 4/26/21 9:51 PM, Sourabh Jain wrote: > kexec_file_load uses initial_boot_params in setting up the device-tree > for the kernel to be loaded. Though initial_boot_params holds info > about CPUs at the time of boot, it doesn't account for hot added CPUs. > > So, kexec'ing with kexec_file_load syscall would leave the kexec'ed > kernel with inaccurate CPU info. Also, if kdump kernel is loaded with > kexec_file_load syscall and the system crashes on a hot added CPU, > capture kernel hangs failing to identify the boot CPU. > > Kernel panic - not syncing: sysrq triggered crash > CPU: 24 PID: 6065 Comm: echo Kdump: loaded Not tainted 5.12.0-rc5upstream #54 > Call Trace: > [c0000000e590fac0] [c0000000007b2400] dump_stack+0xc4/0x114 (unreliable) > [c0000000e590fb00] [c000000000145290] panic+0x16c/0x41c > [c0000000e590fba0] [c0000000008892e0] sysrq_handle_crash+0x30/0x40 > [c0000000e590fc00] [c000000000889cdc] __handle_sysrq+0xcc/0x1f0 > [c0000000e590fca0] [c00000000088a538] write_sysrq_trigger+0xd8/0x178 > [c0000000e590fce0] [c0000000005e9b7c] proc_reg_write+0x10c/0x1b0 > [c0000000e590fd10] [c0000000004f26d0] vfs_write+0xf0/0x330 > [c0000000e590fd60] [c0000000004f2aec] ksys_write+0x7c/0x140 > [c0000000e590fdb0] [c000000000031ee0] system_call_exception+0x150/0x290 > [c0000000e590fe10] [c00000000000ca5c] system_call_common+0xec/0x278 > --- interrupt: c00 at 0x7fff905b9664 > NIP: 00007fff905b9664 LR: 00007fff905320c4 CTR: 0000000000000000 > REGS: c0000000e590fe80 TRAP: 0c00 Not tainted (5.12.0-rc5upstream) > MSR: 800000000280f033 <SF,VEC,VSX,EE,PR,FP,ME,IR,DR,RI,LE> CR: 28000242 > XER: 00000000 > IRQMASK: 0 > GPR00: 0000000000000004 00007ffff5fedf30 00007fff906a7300 0000000000000001 > GPR04: 000001002a7355b0 0000000000000002 0000000000000001 00007ffff5fef616 > GPR08: 0000000000000001 0000000000000000 0000000000000000 0000000000000000 > GPR12: 0000000000000000 00007fff9073a160 0000000000000000 0000000000000000 > GPR16: 0000000000000000 0000000000000000 0000000000000000 0000000000000000 > GPR20: 0000000000000000 00007fff906a4ee0 0000000000000002 0000000000000001 > GPR24: 00007fff906a0898 0000000000000000 0000000000000002 000001002a7355b0 > GPR28: 0000000000000002 00007fff906a1790 000001002a7355b0 0000000000000002 > NIP [00007fff905b9664] 0x7fff905b9664 > LR [00007fff905320c4] 0x7fff905320c4 > --- interrupt: c00 > > To avoid this from happening, extract current CPU info from of_root > device node and use it for setting up the fdt in kexec_file_load case. > > Fixes: 6ecd0163d360 ("powerpc/kexec_file: Add appropriate regions for memory reserve map") > > Signed-off-by: Sourabh Jain <sourabhjain@linux.ibm.com> > Reviewed-by: Hari Bathini <hbathini@linux.ibm.com> > Cc: <stable@vger.kernel.org> > --- > arch/powerpc/kexec/file_load_64.c | 88 +++++++++++++++++++++++++++++++ > 1 file changed, 88 insertions(+) > > --- > Changelog: > > v1 -> v5 > - https://lists.ozlabs.org/pipermail/linuxppc-dev/2021-April/227950.html > > v5 -> v6 > - use exiting macro (for_each_property_of_node) to loop through all > properties of a node. > - removed devtree_lock while accessing the node properties. > - function name update, add_node_prop to add_node_props. > --- > > diff --git a/arch/powerpc/kexec/file_load_64.c b/arch/powerpc/kexec/file_load_64.c > index 02b9e4d0dc40..4f7d4c10f939 100644 > --- a/arch/powerpc/kexec/file_load_64.c > +++ b/arch/powerpc/kexec/file_load_64.c > @@ -960,6 +960,89 @@ unsigned int kexec_fdt_totalsize_ppc64(struct kimage *image) > return fdt_size; > } > > +/** > + * add_node_props - Reads node properties from device node structure and add > + * them to fdt. > + * @fdt: Flattened device tree of the kernel > + * @node_offset: offset of the node to add a property at > + * @dn: device node pointer > + * > + * Returns 0 on success, negative errno on error. > + */ > +static int add_node_props(void *fdt, int node_offset, const struct device_node *dn) > +{ > + int ret = 0; > + struct property *pp; > + > + if (!dn) > + return -EINVAL; > + > + for_each_property_of_node(dn, pp) { > + ret = fdt_setprop(fdt, node_offset, pp->name, pp->value, pp->length); > + if (ret < 0) { > + pr_err("Unable to add %s property: %s\n", pp->name, fdt_strerror(ret)); > + return ret; > + } > + } > + return ret; > +} > + > +/** > + * update_cpus_node - Update cpus node of flattened device tree using of_root > + * device node. > + * @fdt: Flattened device tree of the kernel. > + * > + * Returns 0 on success, negative errno on error. > + */ > +static int update_cpus_node(void *fdt) > +{ > + struct device_node *cpus_node, *dn; > + int cpus_offset, cpus_subnode_offset, ret = 0; > + > + cpus_offset = fdt_path_offset(fdt, "/cpus"); > + if (cpus_offset < 0 && cpus_offset != -FDT_ERR_NOTFOUND) { > + pr_err("Malformed device tree: error reading /cpus node: %s\n", > + fdt_strerror(cpus_offset)); > + return cpus_offset; > + } > + > + if (cpus_offset > 0) { > + ret = fdt_del_node(fdt, cpus_offset); > + if (ret < 0) { > + pr_err("Error deleting /cpus node: %s\n", fdt_strerror(ret)); > + return -EINVAL; > + } > + } > + > + /* Add cpus node to fdt */ > + cpus_offset = fdt_add_subnode(fdt, fdt_path_offset(fdt, "/"), "cpus"); > + if (cpus_offset < 0) { > + pr_err("Error creating /cpus node: %s\n", fdt_strerror(cpus_offset)); > + return -EINVAL; > + } > + > + /* Add cpus node properties */ > + cpus_node = of_find_node_by_path("/cpus"); Pretty sure that of_find_node_by_path() returns a device_node with its refcount incremented. > + ret = add_node_props(fdt, cpus_offset, cpus_node); Need a of_node_put(cpus_node) here. -Tyrel > + if (ret < 0) > + return ret; > + > + /* Loop through all subnodes of cpus and add them to fdt */ > + for_each_node_by_type(dn, "cpu") { > + cpus_subnode_offset = fdt_add_subnode(fdt, cpus_offset, dn->full_name); > + if (cpus_subnode_offset < 0) { > + pr_err("Unable to add %s subnode: %s\n", dn->full_name, > + fdt_strerror(cpus_subnode_offset)); > + return cpus_subnode_offset; > + } > + ret = add_node_props(fdt, cpus_subnode_offset, dn); > + if (ret < 0) > + return ret; > + } > + of_node_put(dn); > + return ret; > +} > + > /** > * setup_new_fdt_ppc64 - Update the flattend device-tree of the kernel > * being loaded. > @@ -1020,6 +1103,11 @@ int setup_new_fdt_ppc64(const struct kimage *image, void *fdt, > } > } > > + /* Update cpus nodes information to account hotplug CPUs. */ > + ret = update_cpus_node(fdt); > + if (ret < 0) > + return ret; > + > /* Update memory reserve map */ > ret = get_reserved_memory_ranges(&rmem); > if (ret) >
On 28/04/21 6:02 am, Tyrel Datwyler wrote: > On 4/26/21 9:51 PM, Sourabh Jain wrote: >> kexec_file_load uses initial_boot_params in setting up the device-tree >> for the kernel to be loaded. Though initial_boot_params holds info >> about CPUs at the time of boot, it doesn't account for hot added CPUs. >> >> So, kexec'ing with kexec_file_load syscall would leave the kexec'ed >> kernel with inaccurate CPU info. Also, if kdump kernel is loaded with >> kexec_file_load syscall and the system crashes on a hot added CPU, >> capture kernel hangs failing to identify the boot CPU. >> >> Kernel panic - not syncing: sysrq triggered crash >> CPU: 24 PID: 6065 Comm: echo Kdump: loaded Not tainted 5.12.0-rc5upstream #54 >> Call Trace: >> [c0000000e590fac0] [c0000000007b2400] dump_stack+0xc4/0x114 (unreliable) >> [c0000000e590fb00] [c000000000145290] panic+0x16c/0x41c >> [c0000000e590fba0] [c0000000008892e0] sysrq_handle_crash+0x30/0x40 >> [c0000000e590fc00] [c000000000889cdc] __handle_sysrq+0xcc/0x1f0 >> [c0000000e590fca0] [c00000000088a538] write_sysrq_trigger+0xd8/0x178 >> [c0000000e590fce0] [c0000000005e9b7c] proc_reg_write+0x10c/0x1b0 >> [c0000000e590fd10] [c0000000004f26d0] vfs_write+0xf0/0x330 >> [c0000000e590fd60] [c0000000004f2aec] ksys_write+0x7c/0x140 >> [c0000000e590fdb0] [c000000000031ee0] system_call_exception+0x150/0x290 >> [c0000000e590fe10] [c00000000000ca5c] system_call_common+0xec/0x278 >> --- interrupt: c00 at 0x7fff905b9664 >> NIP: 00007fff905b9664 LR: 00007fff905320c4 CTR: 0000000000000000 >> REGS: c0000000e590fe80 TRAP: 0c00 Not tainted (5.12.0-rc5upstream) >> MSR: 800000000280f033 <SF,VEC,VSX,EE,PR,FP,ME,IR,DR,RI,LE> CR: 28000242 >> XER: 00000000 >> IRQMASK: 0 >> GPR00: 0000000000000004 00007ffff5fedf30 00007fff906a7300 0000000000000001 >> GPR04: 000001002a7355b0 0000000000000002 0000000000000001 00007ffff5fef616 >> GPR08: 0000000000000001 0000000000000000 0000000000000000 0000000000000000 >> GPR12: 0000000000000000 00007fff9073a160 0000000000000000 0000000000000000 >> GPR16: 0000000000000000 0000000000000000 0000000000000000 0000000000000000 >> GPR20: 0000000000000000 00007fff906a4ee0 0000000000000002 0000000000000001 >> GPR24: 00007fff906a0898 0000000000000000 0000000000000002 000001002a7355b0 >> GPR28: 0000000000000002 00007fff906a1790 000001002a7355b0 0000000000000002 >> NIP [00007fff905b9664] 0x7fff905b9664 >> LR [00007fff905320c4] 0x7fff905320c4 >> --- interrupt: c00 >> >> To avoid this from happening, extract current CPU info from of_root >> device node and use it for setting up the fdt in kexec_file_load case. >> >> Fixes: 6ecd0163d360 ("powerpc/kexec_file: Add appropriate regions for memory reserve map") >> >> Signed-off-by: Sourabh Jain <sourabhjain@linux.ibm.com> >> Reviewed-by: Hari Bathini <hbathini@linux.ibm.com> >> Cc: <stable@vger.kernel.org> >> --- >> arch/powerpc/kexec/file_load_64.c | 88 +++++++++++++++++++++++++++++++ >> 1 file changed, 88 insertions(+) >> >> --- >> Changelog: >> >> v1 -> v5 >> - https://lists.ozlabs.org/pipermail/linuxppc-dev/2021-April/227950.html >> >> v5 -> v6 >> - use exiting macro (for_each_property_of_node) to loop through all >> properties of a node. >> - removed devtree_lock while accessing the node properties. >> - function name update, add_node_prop to add_node_props. >> --- >> >> diff --git a/arch/powerpc/kexec/file_load_64.c b/arch/powerpc/kexec/file_load_64.c >> index 02b9e4d0dc40..4f7d4c10f939 100644 >> --- a/arch/powerpc/kexec/file_load_64.c >> +++ b/arch/powerpc/kexec/file_load_64.c >> @@ -960,6 +960,89 @@ unsigned int kexec_fdt_totalsize_ppc64(struct kimage *image) >> return fdt_size; >> } >> >> +/** >> + * add_node_props - Reads node properties from device node structure and add >> + * them to fdt. >> + * @fdt: Flattened device tree of the kernel >> + * @node_offset: offset of the node to add a property at >> + * @dn: device node pointer >> + * >> + * Returns 0 on success, negative errno on error. >> + */ >> +static int add_node_props(void *fdt, int node_offset, const struct device_node *dn) >> +{ >> + int ret = 0; >> + struct property *pp; >> + >> + if (!dn) >> + return -EINVAL; >> + >> + for_each_property_of_node(dn, pp) { >> + ret = fdt_setprop(fdt, node_offset, pp->name, pp->value, pp->length); >> + if (ret < 0) { >> + pr_err("Unable to add %s property: %s\n", pp->name, fdt_strerror(ret)); >> + return ret; >> + } >> + } >> + return ret; >> +} >> + >> +/** >> + * update_cpus_node - Update cpus node of flattened device tree using of_root >> + * device node. >> + * @fdt: Flattened device tree of the kernel. >> + * >> + * Returns 0 on success, negative errno on error. >> + */ >> +static int update_cpus_node(void *fdt) >> +{ >> + struct device_node *cpus_node, *dn; >> + int cpus_offset, cpus_subnode_offset, ret = 0; >> + >> + cpus_offset = fdt_path_offset(fdt, "/cpus"); >> + if (cpus_offset < 0 && cpus_offset != -FDT_ERR_NOTFOUND) { >> + pr_err("Malformed device tree: error reading /cpus node: %s\n", >> + fdt_strerror(cpus_offset)); >> + return cpus_offset; >> + } >> + >> + if (cpus_offset > 0) { >> + ret = fdt_del_node(fdt, cpus_offset); >> + if (ret < 0) { >> + pr_err("Error deleting /cpus node: %s\n", fdt_strerror(ret)); >> + return -EINVAL; >> + } >> + } >> + >> + /* Add cpus node to fdt */ >> + cpus_offset = fdt_add_subnode(fdt, fdt_path_offset(fdt, "/"), "cpus"); >> + if (cpus_offset < 0) { >> + pr_err("Error creating /cpus node: %s\n", fdt_strerror(cpus_offset)); >> + return -EINVAL; >> + } >> + >> + /* Add cpus node properties */ >> + cpus_node = of_find_node_by_path("/cpus"); > Pretty sure that of_find_node_by_path() returns a device_node with its refcount > incremented. > >> + ret = add_node_props(fdt, cpus_offset, cpus_node); > Need a of_node_put(cpus_node) here. > > Thanks for the review Tyrel. updated in v7. > > - Sourabh
diff --git a/arch/powerpc/kexec/file_load_64.c b/arch/powerpc/kexec/file_load_64.c index 02b9e4d0dc40..4f7d4c10f939 100644 --- a/arch/powerpc/kexec/file_load_64.c +++ b/arch/powerpc/kexec/file_load_64.c @@ -960,6 +960,89 @@ unsigned int kexec_fdt_totalsize_ppc64(struct kimage *image) return fdt_size; } +/** + * add_node_props - Reads node properties from device node structure and add + * them to fdt. + * @fdt: Flattened device tree of the kernel + * @node_offset: offset of the node to add a property at + * @dn: device node pointer + * + * Returns 0 on success, negative errno on error. + */ +static int add_node_props(void *fdt, int node_offset, const struct device_node *dn) +{ + int ret = 0; + struct property *pp; + + if (!dn) + return -EINVAL; + + for_each_property_of_node(dn, pp) { + ret = fdt_setprop(fdt, node_offset, pp->name, pp->value, pp->length); + if (ret < 0) { + pr_err("Unable to add %s property: %s\n", pp->name, fdt_strerror(ret)); + return ret; + } + } + return ret; +} + +/** + * update_cpus_node - Update cpus node of flattened device tree using of_root + * device node. + * @fdt: Flattened device tree of the kernel. + * + * Returns 0 on success, negative errno on error. + */ +static int update_cpus_node(void *fdt) +{ + struct device_node *cpus_node, *dn; + int cpus_offset, cpus_subnode_offset, ret = 0; + + cpus_offset = fdt_path_offset(fdt, "/cpus"); + if (cpus_offset < 0 && cpus_offset != -FDT_ERR_NOTFOUND) { + pr_err("Malformed device tree: error reading /cpus node: %s\n", + fdt_strerror(cpus_offset)); + return cpus_offset; + } + + if (cpus_offset > 0) { + ret = fdt_del_node(fdt, cpus_offset); + if (ret < 0) { + pr_err("Error deleting /cpus node: %s\n", fdt_strerror(ret)); + return -EINVAL; + } + } + + /* Add cpus node to fdt */ + cpus_offset = fdt_add_subnode(fdt, fdt_path_offset(fdt, "/"), "cpus"); + if (cpus_offset < 0) { + pr_err("Error creating /cpus node: %s\n", fdt_strerror(cpus_offset)); + return -EINVAL; + } + + /* Add cpus node properties */ + cpus_node = of_find_node_by_path("/cpus"); + ret = add_node_props(fdt, cpus_offset, cpus_node); + if (ret < 0) + return ret; + + /* Loop through all subnodes of cpus and add them to fdt */ + for_each_node_by_type(dn, "cpu") { + cpus_subnode_offset = fdt_add_subnode(fdt, cpus_offset, dn->full_name); + if (cpus_subnode_offset < 0) { + pr_err("Unable to add %s subnode: %s\n", dn->full_name, + fdt_strerror(cpus_subnode_offset)); + return cpus_subnode_offset; + } + ret = add_node_props(fdt, cpus_subnode_offset, dn); + if (ret < 0) + return ret; + } + of_node_put(dn); + return ret; +} + /** * setup_new_fdt_ppc64 - Update the flattend device-tree of the kernel * being loaded. @@ -1020,6 +1103,11 @@ int setup_new_fdt_ppc64(const struct kimage *image, void *fdt, } } + /* Update cpus nodes information to account hotplug CPUs. */ + ret = update_cpus_node(fdt); + if (ret < 0) + return ret; + /* Update memory reserve map */ ret = get_reserved_memory_ranges(&rmem); if (ret)
kexec_file_load uses initial_boot_params in setting up the device-tree for the kernel to be loaded. Though initial_boot_params holds info about CPUs at the time of boot, it doesn't account for hot added CPUs. So, kexec'ing with kexec_file_load syscall would leave the kexec'ed kernel with inaccurate CPU info. Also, if kdump kernel is loaded with kexec_file_load syscall and the system crashes on a hot added CPU, capture kernel hangs failing to identify the boot CPU. Kernel panic - not syncing: sysrq triggered crash CPU: 24 PID: 6065 Comm: echo Kdump: loaded Not tainted 5.12.0-rc5upstream #54 Call Trace: [c0000000e590fac0] [c0000000007b2400] dump_stack+0xc4/0x114 (unreliable) [c0000000e590fb00] [c000000000145290] panic+0x16c/0x41c [c0000000e590fba0] [c0000000008892e0] sysrq_handle_crash+0x30/0x40 [c0000000e590fc00] [c000000000889cdc] __handle_sysrq+0xcc/0x1f0 [c0000000e590fca0] [c00000000088a538] write_sysrq_trigger+0xd8/0x178 [c0000000e590fce0] [c0000000005e9b7c] proc_reg_write+0x10c/0x1b0 [c0000000e590fd10] [c0000000004f26d0] vfs_write+0xf0/0x330 [c0000000e590fd60] [c0000000004f2aec] ksys_write+0x7c/0x140 [c0000000e590fdb0] [c000000000031ee0] system_call_exception+0x150/0x290 [c0000000e590fe10] [c00000000000ca5c] system_call_common+0xec/0x278 --- interrupt: c00 at 0x7fff905b9664 NIP: 00007fff905b9664 LR: 00007fff905320c4 CTR: 0000000000000000 REGS: c0000000e590fe80 TRAP: 0c00 Not tainted (5.12.0-rc5upstream) MSR: 800000000280f033 <SF,VEC,VSX,EE,PR,FP,ME,IR,DR,RI,LE> CR: 28000242 XER: 00000000 IRQMASK: 0 GPR00: 0000000000000004 00007ffff5fedf30 00007fff906a7300 0000000000000001 GPR04: 000001002a7355b0 0000000000000002 0000000000000001 00007ffff5fef616 GPR08: 0000000000000001 0000000000000000 0000000000000000 0000000000000000 GPR12: 0000000000000000 00007fff9073a160 0000000000000000 0000000000000000 GPR16: 0000000000000000 0000000000000000 0000000000000000 0000000000000000 GPR20: 0000000000000000 00007fff906a4ee0 0000000000000002 0000000000000001 GPR24: 00007fff906a0898 0000000000000000 0000000000000002 000001002a7355b0 GPR28: 0000000000000002 00007fff906a1790 000001002a7355b0 0000000000000002 NIP [00007fff905b9664] 0x7fff905b9664 LR [00007fff905320c4] 0x7fff905320c4 --- interrupt: c00 To avoid this from happening, extract current CPU info from of_root device node and use it for setting up the fdt in kexec_file_load case. Fixes: 6ecd0163d360 ("powerpc/kexec_file: Add appropriate regions for memory reserve map") Signed-off-by: Sourabh Jain <sourabhjain@linux.ibm.com> Reviewed-by: Hari Bathini <hbathini@linux.ibm.com> Cc: <stable@vger.kernel.org> --- arch/powerpc/kexec/file_load_64.c | 88 +++++++++++++++++++++++++++++++ 1 file changed, 88 insertions(+) --- Changelog: v1 -> v5 - https://lists.ozlabs.org/pipermail/linuxppc-dev/2021-April/227950.html v5 -> v6 - use exiting macro (for_each_property_of_node) to loop through all properties of a node. - removed devtree_lock while accessing the node properties. - function name update, add_node_prop to add_node_props. ---