While the first kernel boots, it registers memory regions for fadump
such as:
* CPU state data (has to be populated by the platform)
* HPTE state data (has to be populated by the platform)
* Real Mode Regions (platform should copy it to requested
destination addresses)
* OS defined regions (such as parameter save area)
Platform is also expected to modify the 'bytes_dumped' to the length of
data preserved/copied by platform (ideally same as the source length
passed by kernel).
The kernel passes source address and length for the memory regions, and
a destination address to where the memory is to be copied.
Implement the preserving/copying of the Real Mode Regions and the
Parameter Save Area in QEMU Pseries
The regions are copied in chunks instead of copying all at once.
Signed-off-by: Aditya Gupta <adityag@linux.ibm.com>
---
hw/ppc/spapr_fadump.c | 183 +++++++++++++++++++++++++++++++++-
include/hw/ppc/spapr_fadump.h | 18 ++++
2 files changed, 196 insertions(+), 5 deletions(-)
diff --git a/hw/ppc/spapr_fadump.c b/hw/ppc/spapr_fadump.c
index 53e5c12c7641..5068a9d83dce 100644
--- a/hw/ppc/spapr_fadump.c
+++ b/hw/ppc/spapr_fadump.c
@@ -7,7 +7,9 @@
#include "qemu/osdep.h"
#include "qemu/log.h"
#include "hw/ppc/spapr.h"
+#include "qemu/units.h"
#include "system/cpus.h"
+#include <math.h>
/*
* Handle the "FADUMP_CMD_REGISTER" command in 'ibm,configure-kernel-dump'
@@ -123,14 +125,185 @@ uint32_t do_fadump_register(SpaprMachineState *spapr, target_ulong args)
return RTAS_OUT_SUCCESS;
}
+/*
+ * Copy the source region of given fadump section, to the destination
+ * address mentioned in the region
+ *
+ * Also set the region's error flag, if the copy fails due to non-existent
+ * address (MEMTX_DECODE_ERROR) or permission issues (MEMTX_ACCESS_ERROR)
+ *
+ * Returns true if successful copy
+ *
+ * Returns false in case of any other error, being treated as hardware
+ * error for fadump purposes
+ */
+static bool do_preserve_region(FadumpSection *region)
+{
+ AddressSpace *default_as = &address_space_memory;
+ MemTxResult io_result;
+ MemTxAttrs attrs;
+ uint64_t src_addr, src_len, dest_addr;
+ uint64_t num_chunks;
+ g_autofree void *copy_buffer = NULL;
+
+ src_addr = be64_to_cpu(region->source_address);
+ src_len = be64_to_cpu(region->source_len);
+ dest_addr = be64_to_cpu(region->destination_address);
+
+ /* Mark the memory transaction as privileged memory access */
+ attrs.user = 0;
+ attrs.memory = 1;
+
+ /*
+ * Optimisation: Skip copy if source and destination are same
+ * (eg. param area)
+ */
+ if (src_addr == dest_addr) {
+ region->bytes_dumped = cpu_to_be64(src_len);
+ return true;
+ }
+
+#define FADUMP_CHUNK_SIZE ((size_t)(32 * MiB))
+ copy_buffer = g_try_malloc(FADUMP_CHUNK_SIZE);
+ if (copy_buffer == NULL) {
+ qemu_log_mask(LOG_GUEST_ERROR,
+ "FADump: Failed allocating memory (size: %zu) for copying"
+ " reserved memory regions\n", FADUMP_CHUNK_SIZE);
+ }
+
+ num_chunks = ceil((src_len * 1.0f) / FADUMP_CHUNK_SIZE);
+ for (uint64_t chunk_id = 0; chunk_id < num_chunks; ++chunk_id) {
+ /* Take minimum of bytes left to copy, and chunk size */
+ uint64_t copy_len = MIN(
+ src_len - (chunk_id * FADUMP_CHUNK_SIZE),
+ FADUMP_CHUNK_SIZE
+ );
+
+ /* Copy the source region to destination */
+ io_result = address_space_read(default_as, src_addr, attrs,
+ copy_buffer, copy_len);
+ if ((io_result & MEMTX_DECODE_ERROR) ||
+ (io_result & MEMTX_ACCESS_ERROR)) {
+ qemu_log_mask(LOG_GUEST_ERROR,
+ "FADump: Failed to decode/access address in section: %d\n",
+ region->source_data_type);
+
+ /*
+ * Invalid source address is not an hardware error, instead
+ * wrong parameter from the kernel.
+ * Return true to let caller know to continue reading other
+ * sections
+ */
+ region->error_flags = FADUMP_ERROR_INVALID_SOURCE_ADDR;
+ region->bytes_dumped = 0;
+ return true;
+ } else if (io_result != MEMTX_OK) {
+ qemu_log_mask(LOG_GUEST_ERROR,
+ "FADump: Failed to read source region in section: %d\n",
+ region->source_data_type);
+
+ return false;
+ }
+
+ io_result = address_space_write(default_as, dest_addr, attrs,
+ copy_buffer, copy_len);
+ if ((io_result & MEMTX_DECODE_ERROR) ||
+ (io_result & MEMTX_ACCESS_ERROR)) {
+ qemu_log_mask(LOG_GUEST_ERROR,
+ "FADump: Failed to decode/access address in section: %d\n",
+ region->source_data_type);
+
+ /*
+ * Invalid destination address is not an hardware error,
+ * instead wrong parameter from the kernel.
+ * Return true to let caller know to continue reading other
+ * sections
+ */
+ region->error_flags = FADUMP_ERROR_INVALID_DEST_ADDR;
+ region->bytes_dumped = 0;
+ return true;
+ } else if (io_result != MEMTX_OK) {
+ qemu_log_mask(LOG_GUEST_ERROR,
+ "FADump: Failed to write destination in section: %d\n",
+ region->source_data_type);
+
+ return false;
+ }
+
+ src_addr += FADUMP_CHUNK_SIZE;
+ dest_addr += FADUMP_CHUNK_SIZE;
+ }
+#undef FADUMP_CHUNK_SIZE
+
+ /*
+ * Considering address_space_write would have copied the
+ * complete region
+ */
+ region->bytes_dumped = cpu_to_be64(src_len);
+ return true;
+}
+
/* Preserve the memory locations registered for fadump */
-static bool fadump_preserve_mem(void)
+static bool fadump_preserve_mem(SpaprMachineState *spapr)
{
+ FadumpMemStruct *fdm = &spapr->registered_fdm;
+ uint16_t dump_num_sections, data_type;
+
+ assert(spapr->fadump_registered);
+
/*
- * TODO: Implement preserving memory regions requested during fadump
- * registration
+ * Handle all sections
+ *
+ * CPU State Data and HPTE regions are handled in their own cases
+ *
+ * RMR regions and any custom OS reserved regions such as parameter
+ * save area, are handled by simply copying the source region to
+ * destination address
*/
- return false;
+ dump_num_sections = be16_to_cpu(fdm->header.dump_num_sections);
+ for (int i = 0; i < dump_num_sections; ++i) {
+ data_type = be16_to_cpu(fdm->rgn[i].source_data_type);
+
+ /* Reset error_flags & bytes_dumped for now */
+ fdm->rgn[i].error_flags = 0;
+ fdm->rgn[i].bytes_dumped = 0;
+
+ /* If kernel did not request for the memory region, then skip it */
+ if (be32_to_cpu(fdm->rgn[i].request_flag) != FADUMP_REQUEST_FLAG) {
+ qemu_log_mask(LOG_UNIMP,
+ "FADump: Skipping copying region as not requested\n");
+ continue;
+ }
+
+ switch (data_type) {
+ case FADUMP_CPU_STATE_DATA:
+ /* TODO: Add CPU state data */
+ break;
+ case FADUMP_HPTE_REGION:
+ /* TODO: Add hpte state data */
+ break;
+ case FADUMP_REAL_MODE_REGION:
+ case FADUMP_PARAM_AREA:
+ /* Copy the memory region from region's source to its destination */
+ if (!do_preserve_region(&fdm->rgn[i])) {
+ qemu_log_mask(LOG_GUEST_ERROR,
+ "FADump: Failed to preserve dump section: %d\n",
+ be16_to_cpu(fdm->rgn[i].source_data_type));
+ fdm->header.dump_status_flag |=
+ cpu_to_be16(FADUMP_STATUS_DUMP_ERROR);
+ }
+
+ break;
+ default:
+ qemu_log_mask(LOG_GUEST_ERROR,
+ "FADump: Skipping unknown source data type: %d\n", data_type);
+
+ fdm->rgn[i].error_flags =
+ cpu_to_be16(FADUMP_ERROR_INVALID_DATA_TYPE);
+ }
+ }
+
+ return true;
}
/*
@@ -151,7 +324,7 @@ void trigger_fadump_boot(SpaprMachineState *spapr, target_ulong spapr_retcode)
pause_all_vcpus();
/* Preserve the memory locations registered for fadump */
- if (!fadump_preserve_mem()) {
+ if (!fadump_preserve_mem(spapr)) {
/* Failed to preserve the registered memory regions */
rtas_st(spapr_retcode, 0, RTAS_OUT_HW_ERROR);
diff --git a/include/hw/ppc/spapr_fadump.h b/include/hw/ppc/spapr_fadump.h
index 1cb90c9d63af..71be2ad92c11 100644
--- a/include/hw/ppc/spapr_fadump.h
+++ b/include/hw/ppc/spapr_fadump.h
@@ -16,11 +16,29 @@
#define FADUMP_VERSION 1
+/* Firmware provided dump sections */
+#define FADUMP_CPU_STATE_DATA 0x0001
+#define FADUMP_HPTE_REGION 0x0002
+#define FADUMP_REAL_MODE_REGION 0x0011
+
+/* OS defined sections */
+#define FADUMP_PARAM_AREA 0x0100
+
+/* Dump request flag */
+#define FADUMP_REQUEST_FLAG 0x00000001
+
/* Dump status flags */
#define FADUMP_STATUS_DUMP_PERFORMED 0x8000
#define FADUMP_STATUS_DUMP_TRIGGERED 0x4000
#define FADUMP_STATUS_DUMP_ERROR 0x2000
+/* Region dump error flags */
+#define FADUMP_ERROR_INVALID_DATA_TYPE 0x8000
+#define FADUMP_ERROR_INVALID_SOURCE_ADDR 0x4000
+#define FADUMP_ERROR_LENGTH_EXCEEDS_SOURCE 0x2000
+#define FADUMP_ERROR_INVALID_DEST_ADDR 0x1000
+#define FAUDMP_ERROR_DEST_TOO_SMALL 0x0800
+
/*
* The Firmware Assisted Dump Memory structure supports a maximum of 10 sections
* in the dump memory structure. Presently, three sections are used for
--
2.51.0
On 21/10/25 19:18, Aditya Gupta wrote:
> While the first kernel boots, it registers memory regions for fadump
> such as:
> * CPU state data (has to be populated by the platform)
> * HPTE state data (has to be populated by the platform)
> * Real Mode Regions (platform should copy it to requested
> destination addresses)
> * OS defined regions (such as parameter save area)
>
> Platform is also expected to modify the 'bytes_dumped' to the length of
> data preserved/copied by platform (ideally same as the source length
> passed by kernel).
>
> The kernel passes source address and length for the memory regions, and
> a destination address to where the memory is to be copied.
>
> Implement the preserving/copying of the Real Mode Regions and the
> Parameter Save Area in QEMU Pseries
>
> The regions are copied in chunks instead of copying all at once.
>
> Signed-off-by: Aditya Gupta <adityag@linux.ibm.com>
> ---
> hw/ppc/spapr_fadump.c | 183 +++++++++++++++++++++++++++++++++-
> include/hw/ppc/spapr_fadump.h | 18 ++++
> 2 files changed, 196 insertions(+), 5 deletions(-)
>
> diff --git a/hw/ppc/spapr_fadump.c b/hw/ppc/spapr_fadump.c
> index 53e5c12c7641..5068a9d83dce 100644
> --- a/hw/ppc/spapr_fadump.c
> +++ b/hw/ppc/spapr_fadump.c
> @@ -7,7 +7,9 @@
> #include "qemu/osdep.h"
> #include "qemu/log.h"
> #include "hw/ppc/spapr.h"
> +#include "qemu/units.h"
> #include "system/cpus.h"
> +#include <math.h>
>
> /*
> * Handle the "FADUMP_CMD_REGISTER" command in 'ibm,configure-kernel-dump'
> @@ -123,14 +125,185 @@ uint32_t do_fadump_register(SpaprMachineState *spapr, target_ulong args)
> return RTAS_OUT_SUCCESS;
> }
>
> +/*
> + * Copy the source region of given fadump section, to the destination
> + * address mentioned in the region
> + *
> + * Also set the region's error flag, if the copy fails due to non-existent
> + * address (MEMTX_DECODE_ERROR) or permission issues (MEMTX_ACCESS_ERROR)
> + *
> + * Returns true if successful copy
> + *
> + * Returns false in case of any other error, being treated as hardware
> + * error for fadump purposes
> + */
> +static bool do_preserve_region(FadumpSection *region)
> +{
> + AddressSpace *default_as = &address_space_memory;
> + MemTxResult io_result;
> + MemTxAttrs attrs;
> + uint64_t src_addr, src_len, dest_addr;
> + uint64_t num_chunks;
> + g_autofree void *copy_buffer = NULL;
> +
> + src_addr = be64_to_cpu(region->source_address);
> + src_len = be64_to_cpu(region->source_len);
> + dest_addr = be64_to_cpu(region->destination_address);
> +
> + /* Mark the memory transaction as privileged memory access */
> + attrs.user = 0;
> + attrs.memory = 1;
> +
> + /*
> + * Optimisation: Skip copy if source and destination are same
> + * (eg. param area)
> + */
> + if (src_addr == dest_addr) {
> + region->bytes_dumped = cpu_to_be64(src_len);
> + return true;
> + }
> +
> +#define FADUMP_CHUNK_SIZE ((size_t)(32 * MiB))
> + copy_buffer = g_try_malloc(FADUMP_CHUNK_SIZE);
> + if (copy_buffer == NULL) {
> + qemu_log_mask(LOG_GUEST_ERROR,
> + "FADump: Failed allocating memory (size: %zu) for copying"
> + " reserved memory regions\n", FADUMP_CHUNK_SIZE);
> + }
> +
> + num_chunks = ceil((src_len * 1.0f) / FADUMP_CHUNK_SIZE);
> + for (uint64_t chunk_id = 0; chunk_id < num_chunks; ++chunk_id) {
> + /* Take minimum of bytes left to copy, and chunk size */
> + uint64_t copy_len = MIN(
> + src_len - (chunk_id * FADUMP_CHUNK_SIZE),
> + FADUMP_CHUNK_SIZE
> + );
> +
> + /* Copy the source region to destination */
> + io_result = address_space_read(default_as, src_addr, attrs,
> + copy_buffer, copy_len);
> + if ((io_result & MEMTX_DECODE_ERROR) ||
> + (io_result & MEMTX_ACCESS_ERROR)) {
> + qemu_log_mask(LOG_GUEST_ERROR,
> + "FADump: Failed to decode/access address in section: %d\n",
> + region->source_data_type);
> +
> + /*
> + * Invalid source address is not an hardware error, instead
> + * wrong parameter from the kernel.
> + * Return true to let caller know to continue reading other
> + * sections
> + */
> + region->error_flags = FADUMP_ERROR_INVALID_SOURCE_ADDR;
> + region->bytes_dumped = 0;
> + return true;
> + } else if (io_result != MEMTX_OK) {
> + qemu_log_mask(LOG_GUEST_ERROR,
> + "FADump: Failed to read source region in section: %d\n",
> + region->source_data_type);
> +
> + return false;
> + }
> +
> + io_result = address_space_write(default_as, dest_addr, attrs,
> + copy_buffer, copy_len);
> + if ((io_result & MEMTX_DECODE_ERROR) ||
> + (io_result & MEMTX_ACCESS_ERROR)) {
> + qemu_log_mask(LOG_GUEST_ERROR,
> + "FADump: Failed to decode/access address in section: %d\n",
> + region->source_data_type);
> +
> + /*
> + * Invalid destination address is not an hardware error,
> + * instead wrong parameter from the kernel.
> + * Return true to let caller know to continue reading other
> + * sections
> + */
> + region->error_flags = FADUMP_ERROR_INVALID_DEST_ADDR;
> + region->bytes_dumped = 0;
> + return true;
> + } else if (io_result != MEMTX_OK) {
> + qemu_log_mask(LOG_GUEST_ERROR,
> + "FADump: Failed to write destination in section: %d\n",
> + region->source_data_type);
> +
> + return false;
> + }
> +
> + src_addr += FADUMP_CHUNK_SIZE;
> + dest_addr += FADUMP_CHUNK_SIZE;
> + }
> +#undef FADUMP_CHUNK_SIZE
> +
> + /*
> + * Considering address_space_write would have copied the
> + * complete region
> + */
> + region->bytes_dumped = cpu_to_be64(src_len);
> + return true;
> +}
> +
> /* Preserve the memory locations registered for fadump */
> -static bool fadump_preserve_mem(void)
> +static bool fadump_preserve_mem(SpaprMachineState *spapr)
> {
> + FadumpMemStruct *fdm = &spapr->registered_fdm;
> + uint16_t dump_num_sections, data_type;
> +
> + assert(spapr->fadump_registered);
> +
> /*
> - * TODO: Implement preserving memory regions requested during fadump
> - * registration
> + * Handle all sections
> + *
> + * CPU State Data and HPTE regions are handled in their own cases
> + *
> + * RMR regions and any custom OS reserved regions such as parameter
> + * save area, are handled by simply copying the source region to
> + * destination address
> */
> - return false;
> + dump_num_sections = be16_to_cpu(fdm->header.dump_num_sections);
> + for (int i = 0; i < dump_num_sections; ++i) {
> + data_type = be16_to_cpu(fdm->rgn[i].source_data_type);
> +
> + /* Reset error_flags & bytes_dumped for now */
> + fdm->rgn[i].error_flags = 0;
> + fdm->rgn[i].bytes_dumped = 0;
> +
> + /* If kernel did not request for the memory region, then skip it */
> + if (be32_to_cpu(fdm->rgn[i].request_flag) != FADUMP_REQUEST_FLAG) {
> + qemu_log_mask(LOG_UNIMP,
> + "FADump: Skipping copying region as not requested\n");
> + continue;
> + }
> +
> + switch (data_type) {
> + case FADUMP_CPU_STATE_DATA:
> + /* TODO: Add CPU state data */
> + break;
> + case FADUMP_HPTE_REGION:
> + /* TODO: Add hpte state data */
> + break;
> + case FADUMP_REAL_MODE_REGION:
> + case FADUMP_PARAM_AREA:
> + /* Copy the memory region from region's source to its destination */
> + if (!do_preserve_region(&fdm->rgn[i])) {
> + qemu_log_mask(LOG_GUEST_ERROR,
> + "FADump: Failed to preserve dump section: %d\n",
> + be16_to_cpu(fdm->rgn[i].source_data_type));
> + fdm->header.dump_status_flag |=
> + cpu_to_be16(FADUMP_STATUS_DUMP_ERROR);
> + }
> +
> + break;
> + default:
> + qemu_log_mask(LOG_GUEST_ERROR,
> + "FADump: Skipping unknown source data type: %d\n", data_type);
> +
> + fdm->rgn[i].error_flags =
> + cpu_to_be16(FADUMP_ERROR_INVALID_DATA_TYPE);
> + }
> + }
> +
> + return true;
> }
>
> /*
> @@ -151,7 +324,7 @@ void trigger_fadump_boot(SpaprMachineState *spapr, target_ulong spapr_retcode)
> pause_all_vcpus();
>
> /* Preserve the memory locations registered for fadump */
> - if (!fadump_preserve_mem()) {
> + if (!fadump_preserve_mem(spapr)) {
> /* Failed to preserve the registered memory regions */
> rtas_st(spapr_retcode, 0, RTAS_OUT_HW_ERROR);
>
> diff --git a/include/hw/ppc/spapr_fadump.h b/include/hw/ppc/spapr_fadump.h
> index 1cb90c9d63af..71be2ad92c11 100644
> --- a/include/hw/ppc/spapr_fadump.h
> +++ b/include/hw/ppc/spapr_fadump.h
> @@ -16,11 +16,29 @@
>
> #define FADUMP_VERSION 1
>
> +/* Firmware provided dump sections */
> +#define FADUMP_CPU_STATE_DATA 0x0001
> +#define FADUMP_HPTE_REGION 0x0002
> +#define FADUMP_REAL_MODE_REGION 0x0011
> +
> +/* OS defined sections */
> +#define FADUMP_PARAM_AREA 0x0100
> +
> +/* Dump request flag */
> +#define FADUMP_REQUEST_FLAG 0x00000001
> +
> /* Dump status flags */
> #define FADUMP_STATUS_DUMP_PERFORMED 0x8000
> #define FADUMP_STATUS_DUMP_TRIGGERED 0x4000
> #define FADUMP_STATUS_DUMP_ERROR 0x2000
>
> +/* Region dump error flags */
> +#define FADUMP_ERROR_INVALID_DATA_TYPE 0x8000
> +#define FADUMP_ERROR_INVALID_SOURCE_ADDR 0x4000
> +#define FADUMP_ERROR_LENGTH_EXCEEDS_SOURCE 0x2000
> +#define FADUMP_ERROR_INVALID_DEST_ADDR 0x1000
> +#define FAUDMP_ERROR_DEST_TOO_SMALL 0x0800
> +
> /*
> * The Firmware Assisted Dump Memory structure supports a maximum of 10 sections
> * in the dump memory structure. Presently, three sections are used for
LGTM
Reviewed-by: Sourabh Jain <sourabhjain@linux.ibm.com>
© 2016 - 2026 Red Hat, Inc.