* [PATCH v3 4/7] kexec_elf: remove PURGATORY_STACK_SIZE
From: Sven Schnelle @ 2019-07-10 14:29 UTC (permalink / raw)
To: kexec; +Cc: Sven Schnelle, deller, linuxppc-dev
In-Reply-To: <20190710142944.2774-1-svens@stackframe.org>
It's not used anywhere so just drop it.
Signed-off-by: Sven Schnelle <svens@stackframe.org>
---
kernel/kexec_elf.c | 2 --
1 file changed, 2 deletions(-)
diff --git a/kernel/kexec_elf.c b/kernel/kexec_elf.c
index effe9dc0b055..70d31b8feeae 100644
--- a/kernel/kexec_elf.c
+++ b/kernel/kexec_elf.c
@@ -8,8 +8,6 @@
#include <linux/slab.h>
#include <linux/types.h>
-#define PURGATORY_STACK_SIZE (16 * 1024)
-
#define elf_addr_to_cpu elf64_to_cpu
#ifndef Elf_Rel
--
2.20.1
^ permalink raw reply related
* [PATCH v3 5/7] kexec_elf: remove elf_addr_to_cpu macro
From: Sven Schnelle @ 2019-07-10 14:29 UTC (permalink / raw)
To: kexec; +Cc: Sven Schnelle, deller, linuxppc-dev
In-Reply-To: <20190710142944.2774-1-svens@stackframe.org>
It had only one definition, so just use the function directly.
Signed-off-by: Sven Schnelle <svens@stackframe.org>
---
kernel/kexec_elf.c | 20 +++++++++-----------
1 file changed, 9 insertions(+), 11 deletions(-)
diff --git a/kernel/kexec_elf.c b/kernel/kexec_elf.c
index 70d31b8feeae..99e6d63b5dfc 100644
--- a/kernel/kexec_elf.c
+++ b/kernel/kexec_elf.c
@@ -8,8 +8,6 @@
#include <linux/slab.h>
#include <linux/types.h>
-#define elf_addr_to_cpu elf64_to_cpu
-
#ifndef Elf_Rel
#define Elf_Rel Elf64_Rel
#endif /* Elf_Rel */
@@ -143,9 +141,9 @@ static int elf_read_ehdr(const char *buf, size_t len, struct elfhdr *ehdr)
ehdr->e_type = elf16_to_cpu(ehdr, buf_ehdr->e_type);
ehdr->e_machine = elf16_to_cpu(ehdr, buf_ehdr->e_machine);
ehdr->e_version = elf32_to_cpu(ehdr, buf_ehdr->e_version);
- ehdr->e_entry = elf_addr_to_cpu(ehdr, buf_ehdr->e_entry);
- ehdr->e_phoff = elf_addr_to_cpu(ehdr, buf_ehdr->e_phoff);
- ehdr->e_shoff = elf_addr_to_cpu(ehdr, buf_ehdr->e_shoff);
+ ehdr->e_entry = elf64_to_cpu(ehdr, buf_ehdr->e_entry);
+ ehdr->e_phoff = elf64_to_cpu(ehdr, buf_ehdr->e_phoff);
+ ehdr->e_shoff = elf64_to_cpu(ehdr, buf_ehdr->e_shoff);
ehdr->e_flags = elf32_to_cpu(ehdr, buf_ehdr->e_flags);
ehdr->e_phentsize = elf16_to_cpu(ehdr, buf_ehdr->e_phentsize);
ehdr->e_phnum = elf16_to_cpu(ehdr, buf_ehdr->e_phnum);
@@ -190,18 +188,18 @@ static int elf_read_phdr(const char *buf, size_t len,
buf_phdr = (struct elf_phdr *) pbuf;
phdr->p_type = elf32_to_cpu(elf_info->ehdr, buf_phdr->p_type);
- phdr->p_offset = elf_addr_to_cpu(elf_info->ehdr, buf_phdr->p_offset);
- phdr->p_paddr = elf_addr_to_cpu(elf_info->ehdr, buf_phdr->p_paddr);
- phdr->p_vaddr = elf_addr_to_cpu(elf_info->ehdr, buf_phdr->p_vaddr);
+ phdr->p_offset = elf64_to_cpu(elf_info->ehdr, buf_phdr->p_offset);
+ phdr->p_paddr = elf64_to_cpu(elf_info->ehdr, buf_phdr->p_paddr);
+ phdr->p_vaddr = elf64_to_cpu(elf_info->ehdr, buf_phdr->p_vaddr);
phdr->p_flags = elf32_to_cpu(elf_info->ehdr, buf_phdr->p_flags);
/*
* The following fields have a type equivalent to Elf_Addr
* both in 32 bit and 64 bit ELF.
*/
- phdr->p_filesz = elf_addr_to_cpu(elf_info->ehdr, buf_phdr->p_filesz);
- phdr->p_memsz = elf_addr_to_cpu(elf_info->ehdr, buf_phdr->p_memsz);
- phdr->p_align = elf_addr_to_cpu(elf_info->ehdr, buf_phdr->p_align);
+ phdr->p_filesz = elf64_to_cpu(elf_info->ehdr, buf_phdr->p_filesz);
+ phdr->p_memsz = elf64_to_cpu(elf_info->ehdr, buf_phdr->p_memsz);
+ phdr->p_align = elf64_to_cpu(elf_info->ehdr, buf_phdr->p_align);
return elf_is_phdr_sane(phdr, len) ? 0 : -ENOEXEC;
}
--
2.20.1
^ permalink raw reply related
* [PATCH v3 7/7] kexec_elf: remove unused variable in kexec_elf_load()
From: Sven Schnelle @ 2019-07-10 14:29 UTC (permalink / raw)
To: kexec; +Cc: Sven Schnelle, deller, linuxppc-dev
In-Reply-To: <20190710142944.2774-1-svens@stackframe.org>
base was never unsigned, so we can remove it.
Signed-off-by: Sven Schnelle <svens@stackframe.org>
---
kernel/kexec_elf.c | 7 ++-----
1 file changed, 2 insertions(+), 5 deletions(-)
diff --git a/kernel/kexec_elf.c b/kernel/kexec_elf.c
index b7e47ddd7cad..a56ec5481e71 100644
--- a/kernel/kexec_elf.c
+++ b/kernel/kexec_elf.c
@@ -348,7 +348,7 @@ int kexec_elf_load(struct kimage *image, struct elfhdr *ehdr,
struct kexec_buf *kbuf,
unsigned long *lowest_load_addr)
{
- unsigned long base = 0, lowest_addr = UINT_MAX;
+ unsigned long lowest_addr = UINT_MAX;
int ret;
size_t i;
@@ -370,7 +370,7 @@ int kexec_elf_load(struct kimage *image, struct elfhdr *ehdr,
kbuf->bufsz = size;
kbuf->memsz = phdr->p_memsz;
kbuf->buf_align = phdr->p_align;
- kbuf->buf_min = phdr->p_paddr + base;
+ kbuf->buf_min = phdr->p_paddr;
ret = kexec_add_buffer(kbuf);
if (ret)
goto out;
@@ -380,9 +380,6 @@ int kexec_elf_load(struct kimage *image, struct elfhdr *ehdr,
lowest_addr = load_addr;
}
- /* Update entry point to reflect new load address. */
- ehdr->e_entry += base;
-
*lowest_load_addr = lowest_addr;
ret = 0;
out:
--
2.20.1
^ permalink raw reply related
* [PATCH v3 3/7] kexec_elf: remove parsing of section headers
From: Sven Schnelle @ 2019-07-10 14:29 UTC (permalink / raw)
To: kexec; +Cc: Sven Schnelle, deller, linuxppc-dev
In-Reply-To: <20190710142944.2774-1-svens@stackframe.org>
We're not using them, so we can drop the parsing.
Signed-off-by: Sven Schnelle <svens@stackframe.org>
---
include/linux/kexec.h | 1 -
kernel/kexec_elf.c | 137 ------------------------------------------
2 files changed, 138 deletions(-)
diff --git a/include/linux/kexec.h b/include/linux/kexec.h
index da2a6b1d69e7..f0b809258ed3 100644
--- a/include/linux/kexec.h
+++ b/include/linux/kexec.h
@@ -226,7 +226,6 @@ struct kexec_elf_info {
const struct elfhdr *ehdr;
const struct elf_phdr *proghdrs;
- struct elf_shdr *sechdrs;
};
int kexec_build_elf_info(const char *buf, size_t len, struct elfhdr *ehdr,
diff --git a/kernel/kexec_elf.c b/kernel/kexec_elf.c
index 76e7df64d715..effe9dc0b055 100644
--- a/kernel/kexec_elf.c
+++ b/kernel/kexec_elf.c
@@ -244,134 +244,6 @@ static int elf_read_phdrs(const char *buf, size_t len,
return 0;
}
-/**
- * elf_is_shdr_sane - check that it is safe to use the section header
- * @buf_len: size of the buffer in which the ELF file is loaded.
- */
-static bool elf_is_shdr_sane(const struct elf_shdr *shdr, size_t buf_len)
-{
- bool size_ok;
-
- /* SHT_NULL headers have undefined values, so we can't check them. */
- if (shdr->sh_type == SHT_NULL)
- return true;
-
- /* Now verify sh_entsize */
- switch (shdr->sh_type) {
- case SHT_SYMTAB:
- size_ok = shdr->sh_entsize == sizeof(Elf_Sym);
- break;
- case SHT_RELA:
- size_ok = shdr->sh_entsize == sizeof(Elf_Rela);
- break;
- case SHT_DYNAMIC:
- size_ok = shdr->sh_entsize == sizeof(Elf_Dyn);
- break;
- case SHT_REL:
- size_ok = shdr->sh_entsize == sizeof(Elf_Rel);
- break;
- case SHT_NOTE:
- case SHT_PROGBITS:
- case SHT_HASH:
- case SHT_NOBITS:
- default:
- /*
- * This is a section whose entsize requirements
- * I don't care about. If I don't know about
- * the section I can't care about it's entsize
- * requirements.
- */
- size_ok = true;
- break;
- }
-
- if (!size_ok) {
- pr_debug("ELF section with wrong entry size.\n");
- return false;
- } else if (shdr->sh_addr + shdr->sh_size < shdr->sh_addr) {
- pr_debug("ELF section address wraps around.\n");
- return false;
- }
-
- if (shdr->sh_type != SHT_NOBITS) {
- if (shdr->sh_offset + shdr->sh_size < shdr->sh_offset) {
- pr_debug("ELF section location wraps around.\n");
- return false;
- } else if (shdr->sh_offset + shdr->sh_size > buf_len) {
- pr_debug("ELF section not in file.\n");
- return false;
- }
- }
-
- return true;
-}
-
-static int elf_read_shdr(const char *buf, size_t len,
- struct kexec_elf_info *elf_info,
- int idx)
-{
- struct elf_shdr *shdr = &elf_info->sechdrs[idx];
- const struct elfhdr *ehdr = elf_info->ehdr;
- const char *sbuf;
- struct elf_shdr *buf_shdr;
-
- sbuf = buf + ehdr->e_shoff + idx * sizeof(*buf_shdr);
- buf_shdr = (struct elf_shdr *) sbuf;
-
- shdr->sh_name = elf32_to_cpu(ehdr, buf_shdr->sh_name);
- shdr->sh_type = elf32_to_cpu(ehdr, buf_shdr->sh_type);
- shdr->sh_addr = elf_addr_to_cpu(ehdr, buf_shdr->sh_addr);
- shdr->sh_offset = elf_addr_to_cpu(ehdr, buf_shdr->sh_offset);
- shdr->sh_link = elf32_to_cpu(ehdr, buf_shdr->sh_link);
- shdr->sh_info = elf32_to_cpu(ehdr, buf_shdr->sh_info);
-
- /*
- * The following fields have a type equivalent to Elf_Addr
- * both in 32 bit and 64 bit ELF.
- */
- shdr->sh_flags = elf_addr_to_cpu(ehdr, buf_shdr->sh_flags);
- shdr->sh_size = elf_addr_to_cpu(ehdr, buf_shdr->sh_size);
- shdr->sh_addralign = elf_addr_to_cpu(ehdr, buf_shdr->sh_addralign);
- shdr->sh_entsize = elf_addr_to_cpu(ehdr, buf_shdr->sh_entsize);
-
- return elf_is_shdr_sane(shdr, len) ? 0 : -ENOEXEC;
-}
-
-/**
- * elf_read_shdrs - read the section headers from the buffer
- *
- * This function assumes that the section header table was checked for sanity.
- * Use elf_is_ehdr_sane() if it wasn't.
- */
-static int elf_read_shdrs(const char *buf, size_t len,
- struct kexec_elf_info *elf_info)
-{
- size_t shdr_size, i;
-
- /*
- * e_shnum is at most 65536 so calculating
- * the size of the section header cannot overflow.
- */
- shdr_size = sizeof(struct elf_shdr) * elf_info->ehdr->e_shnum;
-
- elf_info->sechdrs = kzalloc(shdr_size, GFP_KERNEL);
- if (!elf_info->sechdrs)
- return -ENOMEM;
-
- for (i = 0; i < elf_info->ehdr->e_shnum; i++) {
- int ret;
-
- ret = elf_read_shdr(buf, len, elf_info, i);
- if (ret) {
- kfree(elf_info->sechdrs);
- elf_info->sechdrs = NULL;
- return ret;
- }
- }
-
- return 0;
-}
-
/**
* elf_read_from_buffer - read ELF file and sets up ELF header and ELF info
* @buf: Buffer to read ELF file from.
@@ -404,14 +276,6 @@ static int elf_read_from_buffer(const char *buf, size_t len,
if (ret)
return ret;
}
- if (ehdr->e_shoff > 0 && ehdr->e_shnum > 0) {
- ret = elf_read_shdrs(buf, len, elf_info);
- if (ret) {
- kfree(elf_info->proghdrs);
- return ret;
- }
- }
-
return 0;
}
@@ -421,7 +285,6 @@ static int elf_read_from_buffer(const char *buf, size_t len,
void kexec_free_elf_info(struct kexec_elf_info *elf_info)
{
kfree(elf_info->proghdrs);
- kfree(elf_info->sechdrs);
memset(elf_info, 0, sizeof(*elf_info));
}
/**
--
2.20.1
^ permalink raw reply related
* Re: [PATCH v3 7/7] kexec_elf: remove unused variable in kexec_elf_load()
From: Christophe Leroy @ 2019-07-10 14:55 UTC (permalink / raw)
To: Sven Schnelle, kexec; +Cc: deller, linuxppc-dev
In-Reply-To: <20190710142944.2774-8-svens@stackframe.org>
Le 10/07/2019 à 16:29, Sven Schnelle a écrit :
> base was never unsigned, so we can remove it.
Do you mean never assigned ?
>
> Signed-off-by: Sven Schnelle <svens@stackframe.org>
Reviewed-by: Christophe Leroy <christophe.leroy@c-s.fr>
> ---
> kernel/kexec_elf.c | 7 ++-----
> 1 file changed, 2 insertions(+), 5 deletions(-)
>
> diff --git a/kernel/kexec_elf.c b/kernel/kexec_elf.c
> index b7e47ddd7cad..a56ec5481e71 100644
> --- a/kernel/kexec_elf.c
> +++ b/kernel/kexec_elf.c
> @@ -348,7 +348,7 @@ int kexec_elf_load(struct kimage *image, struct elfhdr *ehdr,
> struct kexec_buf *kbuf,
> unsigned long *lowest_load_addr)
> {
> - unsigned long base = 0, lowest_addr = UINT_MAX;
> + unsigned long lowest_addr = UINT_MAX;
> int ret;
> size_t i;
>
> @@ -370,7 +370,7 @@ int kexec_elf_load(struct kimage *image, struct elfhdr *ehdr,
> kbuf->bufsz = size;
> kbuf->memsz = phdr->p_memsz;
> kbuf->buf_align = phdr->p_align;
> - kbuf->buf_min = phdr->p_paddr + base;
> + kbuf->buf_min = phdr->p_paddr;
> ret = kexec_add_buffer(kbuf);
> if (ret)
> goto out;
> @@ -380,9 +380,6 @@ int kexec_elf_load(struct kimage *image, struct elfhdr *ehdr,
> lowest_addr = load_addr;
> }
>
> - /* Update entry point to reflect new load address. */
> - ehdr->e_entry += base;
> -
> *lowest_load_addr = lowest_addr;
> ret = 0;
> out:
>
^ permalink raw reply
* Re: [PATCH v3 6/7] kexec_elf: remove Elf_Rel macro
From: Christophe Leroy @ 2019-07-10 15:02 UTC (permalink / raw)
To: Sven Schnelle, kexec; +Cc: deller, linuxppc-dev
In-Reply-To: <20190710142944.2774-7-svens@stackframe.org>
Le 10/07/2019 à 16:29, Sven Schnelle a écrit :
> It wasn't used anywhere, so lets drop it.
And also, it is already defined in asm-generic/module.h
>
> Signed-off-by: Sven Schnelle <svens@stackframe.org>
Reviewed-by: Christophe Leroy <christophe.leroy@c-s.fr>
> ---
> kernel/kexec_elf.c | 4 ----
> 1 file changed, 4 deletions(-)
>
> diff --git a/kernel/kexec_elf.c b/kernel/kexec_elf.c
> index 99e6d63b5dfc..b7e47ddd7cad 100644
> --- a/kernel/kexec_elf.c
> +++ b/kernel/kexec_elf.c
> @@ -8,10 +8,6 @@
> #include <linux/slab.h>
> #include <linux/types.h>
>
> -#ifndef Elf_Rel
> -#define Elf_Rel Elf64_Rel
> -#endif /* Elf_Rel */
> -
> static inline bool elf_is_elf_file(const struct elfhdr *ehdr)
> {
> return memcmp(ehdr->e_ident, ELFMAG, SELFMAG) == 0;
>
^ permalink raw reply
* Re: [PATCH] ocxl: Update for AFU descriptor template version 1.1
From: Michael Ellerman @ 2019-07-10 15:05 UTC (permalink / raw)
To: Frederic Barrat, linuxppc-dev, alastair, ajd, clombard; +Cc: groug
In-Reply-To: <20190605111545.19762-1-fbarrat@linux.ibm.com>
On Wed, 2019-06-05 at 11:15:45 UTC, Frederic Barrat wrote:
> From: Alastair D'Silva <alastair@d-silva.org>
>
> The OpenCAPI discovery and configuration specification has been
> updated and introduces version 1.1 of the AFU descriptor template,
> with new fields to better define the memory layout of an OpenCAPI
> adapter.
>
> The ocxl driver doesn't do much yet to support LPC memory but as we
> start seeing (non-LPC) AFU images using the new template, this patch
> updates the config space parsing code to avoid spitting a warning.
>
> Signed-off-by: Alastair D'Silva <alastair@d-silva.org>
> Signed-off-by: Frederic Barrat <fbarrat@linux.ibm.com>
> Reviewed-by: Christophe Lombard <clombard@linux.vnet.ibm.com>
> Acked-by: Andrew Donnellan <ajd@linux.ibm.com>
Applied to powerpc next, thanks.
https://git.kernel.org/powerpc/c/73a2b047c81046a7f734a5759ab5fdedbb6968fd
cheers
^ permalink raw reply
* Re: [PATCH v3 1/2] powerpc/boot: add {get, put}_unaligned_be32 to xz_config.h
From: Michael Ellerman @ 2019-07-10 15:05 UTC (permalink / raw)
To: Masahiro Yamada, linuxppc-dev
Cc: Masahiro Yamada, Paul Mackerras, linux-kernel
In-Reply-To: <20190705100144.28785-1-yamada.masahiro@socionext.com>
On Fri, 2019-07-05 at 10:01:43 UTC, Masahiro Yamada wrote:
> The next commit will make the way of passing CONFIG options more robust.
> Unfortunately, it would uncover another hidden issue; without this
> commit, skiroot_defconfig would be broken like this:
>
> | WRAP arch/powerpc/boot/zImage.pseries
> | arch/powerpc/boot/wrapper.a(decompress.o): In function `bcj_powerpc.isra.10':
> | decompress.c:(.text+0x720): undefined reference to `get_unaligned_be32'
> | decompress.c:(.text+0x7a8): undefined reference to `put_unaligned_be32'
> | make[1]: *** [arch/powerpc/boot/Makefile;383: arch/powerpc/boot/zImage.pseries] Error 1
> | make: *** [arch/powerpc/Makefile;295: zImage] Error 2
>
> skiroot_defconfig is the only defconfig that enables CONFIG_KERNEL_XZ
> for ppc, which has never been correctly built before.
>
> I figured out the root cause in lib/decompress_unxz.c:
>
> | #ifdef CONFIG_PPC
> | # define XZ_DEC_POWERPC
> | #endif
>
> CONFIG_PPC is undefined here in the ppc bootwrapper because autoconf.h
> is not included except by arch/powerpc/boot/serial.c
>
> XZ_DEC_POWERPC is not defined, therefore, bcj_powerpc() is not compiled
> for the bootwrapper.
>
> With the next commit passing CONFIG_PPC correctly, we would realize that
> {get,put}_unaligned_be32 was missing.
>
> Unlike the other decompressors, the ppc bootwrapper duplicates all the
> necessary helpers in arch/powerpc/boot/.
>
> The other architectures define __KERNEL__ and pull in helpers for
> building the decompressors.
>
> If ppc bootwrapper had defined __KERNEL__, lib/xz/xz_private.h would
> have included <asm/unaligned.h>:
>
> | #ifdef __KERNEL__
> | # include <linux/xz.h>
> | # include <linux/kernel.h>
> | # include <asm/unaligned.h>
>
> However, doing so would cause tons of definition conflicts since the
> bootwrapper has duplicated everything.
>
> I just added copies of {get,put}_unaligned_be32, following the
> bootwrapper coding convention.
>
> Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
Series applied to powerpc next, thanks.
https://git.kernel.org/powerpc/c/9e005b761e7ad153dcf40a6cba1d681fe0830ac6
cheers
^ permalink raw reply
* [PATCH] powerpc/eeh: Handle hugepages in ioremap space
From: Oliver O'Halloran @ 2019-07-10 15:05 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Sachin Sant, Oliver O'Halloran, Nicholas Piggin
In commit 4a7b06c157a2 ("powerpc/eeh: Handle hugepages in ioremap
space") support for using hugepages in the vmalloc and ioremap areas was
enabled for radix. Unfortunately this broke EEH MMIO error checking.
Detection works by inserting a hook which checks the results of the
ioreadXX() set of functions. When a read returns a 0xFFs response we
need to check for an error which we do by mapping the (virtual) MMIO
address back to a physical address, then mapping physical address to a
PCI device via an interval tree.
When translating virt -> phys we currently assume the ioremap space is
only populated by PAGE_SIZE mappings. If a hugepage mapping is found we
emit a WARN_ON(), but otherwise handles the check as though a normal
page was found. In pathalogical cases such as copying a buffer
containing a lot of 0xFFs from BAR memory this can result in the system
not booting because it's too busy printing WARN_ON()s.
There's no real reason to assume huge pages can't be present and we're
prefectly capable of handling them, so do that.
Cc: Nicholas Piggin <npiggin@gmail.com>
Fixes: 4a7b06c157a2 ("powerpc/eeh: Handle hugepages in ioremap space")
Reported-by: Sachin Sant <sachinp@linux.vnet.ibm.com>
Signed-off-by: Oliver O'Halloran <oohall@gmail.com>
---
I'm assuming that we aren't going to be doing THP in the ioremap area.
---
arch/powerpc/kernel/eeh.c | 15 ++++++++++++---
1 file changed, 12 insertions(+), 3 deletions(-)
diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index 4557fb1aeb2c..976ca0496442 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -354,10 +354,19 @@ static inline unsigned long eeh_token_to_phys(unsigned long token)
ptep = find_init_mm_pte(token, &hugepage_shift);
if (!ptep)
return token;
- WARN_ON(hugepage_shift);
- pa = pte_pfn(*ptep) << PAGE_SHIFT;
- return pa | (token & (PAGE_SIZE-1));
+ pa = pte_pfn(*ptep);
+
+ /* On radix we can do hugepage mappings for io, so handle that */
+ if (hugepage_shift) {
+ pa <<= hugepage_shift;
+ pa |= token & ((1ul << hugepage_shift) - 1);
+ } else {
+ pa <<= PAGE_SHIFT;
+ pa |= token & (PAGE_SIZE - 1);
+ }
+
+ return pa;
}
/*
--
2.21.0
^ permalink raw reply related
* Re: [PATCH] powerpc/irq: Don't WARN continuously in arch_local_irq_restore()
From: Michael Ellerman @ 2019-07-10 15:05 UTC (permalink / raw)
To: Michael Ellerman, linuxppc-dev; +Cc: npiggin
In-Reply-To: <20190708061046.7075-1-mpe@ellerman.id.au>
On Mon, 2019-07-08 at 06:10:46 UTC, Michael Ellerman wrote:
> When CONFIG_PPC_IRQ_SOFT_MASK_DEBUG is enabled (uncommon), we have a
> series of WARN_ON's in arch_local_irq_restore().
>
> These are "should never happen" conditions, but if they do happen they
> can flood the console and render the system unusable. So switch them
> to WARN_ON_ONCE().
>
> Fixes: e2b36d591720 ("powerpc/64: Don't trace code that runs with the soft irq mask unreconciled")
> Fixes: 9b81c0211c24 ("powerpc/64s: make PACA_IRQ_HARD_DIS track MSR[EE] closely")
> Fixes: 7c0482e3d055 ("powerpc/irq: Fix another case of lazy IRQ state getting out of sync")
> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Applied to powerpc next.
https://git.kernel.org/powerpc/c/0fc12c022ad25532b66bf6f6c818ee1c1d63e702
cheers
^ permalink raw reply
* Re: [PATCH v3 5/7] kexec_elf: remove elf_addr_to_cpu macro
From: Christophe Leroy @ 2019-07-10 15:09 UTC (permalink / raw)
To: Sven Schnelle, kexec; +Cc: deller, linuxppc-dev
In-Reply-To: <20190710142944.2774-6-svens@stackframe.org>
Le 10/07/2019 à 16:29, Sven Schnelle a écrit :
> It had only one definition, so just use the function directly.
It had only one definition because it was for ppc64 only.
But as far as I understand (at least from the name of the new file), you
want it to be generic, don't you ? Therefore I get on 32 bits it would
be elf32_to_cpu().
Christophe
>
> Signed-off-by: Sven Schnelle <svens@stackframe.org>
> ---
> kernel/kexec_elf.c | 20 +++++++++-----------
> 1 file changed, 9 insertions(+), 11 deletions(-)
>
> diff --git a/kernel/kexec_elf.c b/kernel/kexec_elf.c
> index 70d31b8feeae..99e6d63b5dfc 100644
> --- a/kernel/kexec_elf.c
> +++ b/kernel/kexec_elf.c
> @@ -8,8 +8,6 @@
> #include <linux/slab.h>
> #include <linux/types.h>
>
> -#define elf_addr_to_cpu elf64_to_cpu
> -
> #ifndef Elf_Rel
> #define Elf_Rel Elf64_Rel
> #endif /* Elf_Rel */
> @@ -143,9 +141,9 @@ static int elf_read_ehdr(const char *buf, size_t len, struct elfhdr *ehdr)
> ehdr->e_type = elf16_to_cpu(ehdr, buf_ehdr->e_type);
> ehdr->e_machine = elf16_to_cpu(ehdr, buf_ehdr->e_machine);
> ehdr->e_version = elf32_to_cpu(ehdr, buf_ehdr->e_version);
> - ehdr->e_entry = elf_addr_to_cpu(ehdr, buf_ehdr->e_entry);
> - ehdr->e_phoff = elf_addr_to_cpu(ehdr, buf_ehdr->e_phoff);
> - ehdr->e_shoff = elf_addr_to_cpu(ehdr, buf_ehdr->e_shoff);
> + ehdr->e_entry = elf64_to_cpu(ehdr, buf_ehdr->e_entry);
> + ehdr->e_phoff = elf64_to_cpu(ehdr, buf_ehdr->e_phoff);
> + ehdr->e_shoff = elf64_to_cpu(ehdr, buf_ehdr->e_shoff);
> ehdr->e_flags = elf32_to_cpu(ehdr, buf_ehdr->e_flags);
> ehdr->e_phentsize = elf16_to_cpu(ehdr, buf_ehdr->e_phentsize);
> ehdr->e_phnum = elf16_to_cpu(ehdr, buf_ehdr->e_phnum);
> @@ -190,18 +188,18 @@ static int elf_read_phdr(const char *buf, size_t len,
> buf_phdr = (struct elf_phdr *) pbuf;
>
> phdr->p_type = elf32_to_cpu(elf_info->ehdr, buf_phdr->p_type);
> - phdr->p_offset = elf_addr_to_cpu(elf_info->ehdr, buf_phdr->p_offset);
> - phdr->p_paddr = elf_addr_to_cpu(elf_info->ehdr, buf_phdr->p_paddr);
> - phdr->p_vaddr = elf_addr_to_cpu(elf_info->ehdr, buf_phdr->p_vaddr);
> + phdr->p_offset = elf64_to_cpu(elf_info->ehdr, buf_phdr->p_offset);
> + phdr->p_paddr = elf64_to_cpu(elf_info->ehdr, buf_phdr->p_paddr);
> + phdr->p_vaddr = elf64_to_cpu(elf_info->ehdr, buf_phdr->p_vaddr);
> phdr->p_flags = elf32_to_cpu(elf_info->ehdr, buf_phdr->p_flags);
>
> /*
> * The following fields have a type equivalent to Elf_Addr
> * both in 32 bit and 64 bit ELF.
> */
> - phdr->p_filesz = elf_addr_to_cpu(elf_info->ehdr, buf_phdr->p_filesz);
> - phdr->p_memsz = elf_addr_to_cpu(elf_info->ehdr, buf_phdr->p_memsz);
> - phdr->p_align = elf_addr_to_cpu(elf_info->ehdr, buf_phdr->p_align);
> + phdr->p_filesz = elf64_to_cpu(elf_info->ehdr, buf_phdr->p_filesz);
> + phdr->p_memsz = elf64_to_cpu(elf_info->ehdr, buf_phdr->p_memsz);
> + phdr->p_align = elf64_to_cpu(elf_info->ehdr, buf_phdr->p_align);
>
> return elf_is_phdr_sane(phdr, len) ? 0 : -ENOEXEC;
> }
>
^ permalink raw reply
* Re: Coccinelle: Checking of_node_put() calls with SmPL
From: Markus Elfring @ 2019-07-10 15:15 UTC (permalink / raw)
To: Wen Yang, Rafael J. Wysocki, Daniel Lezcano, linux-pm,
kernel-janitors
Cc: Yi Wang, Cheng Shengyu, linux-kernel, Scott Wood, Paul Mackerras,
Xue Zhihong, linuxppc-dev
In-Reply-To: <201907101533443009168@zte.com.cn>
> we developed a coccinelle script to detect such problems.
Would you find the implementation of the function “dt_init_idle_driver”
suspicious according to discussed source code search patterns?
https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/drivers/cpuidle/dt_idle_states.c?id=e9a83bd2322035ed9d7dcf35753d3f984d76c6a5#n208
https://elixir.bootlin.com/linux/v5.2/source/drivers/cpuidle/dt_idle_states.c#L208
> This script is still being improved.
Will corresponding software development challenges become more interesting?
Regards,
Markus
^ permalink raw reply
* [PATCH v2 00/16] powerpc/64s: machine check cleanup series
From: Nicholas Piggin @ 2019-07-10 15:19 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Mahesh Salgaonkar, Nicholas Piggin, Aravinda Prasad
This series is mostly unchanged from last time, except that it
adjusts the pseries machine check handler to use machine check events
for queueing, which fixes some corner cases and allows the interrupt
code to be consolidated nicely.
Thanks,
Nick
Nicholas Piggin (16):
powerpc/64s/exception: machine check fwnmi remove HV case
powerpc/64s/exception: machine check remove bitrotted comment
powerpc/64s/exception: machine check fix KVM guest test
powerpc/64s/exception: machine check adjust RFI target
powerpc/64s/exception: machine check pseries should always run the
early handler
powerpc/64s/exception: machine check remove machine_check_pSeries_0
branch
powerpc/64s/exception: machine check use correct cfar for late handler
powerpc/64s/powernv: machine check dump SLB contents
powerpc/64s/pseries: machine check convert to use common event code
powerpc/64s/exception: machine check pseries should skip the late
handler for host kernel MCEs
powerpc/64s/exception: machine check restructure to reuse common
macros
powerpc/64s/exception: machine check move tramp code
powerpc/64s/exception: simplify machine check early path
powerpc/64s/exception: machine check move unrecoverable handling out
of line
powerpc/64s/exception: untangle early machine check handler branch
powerpc/64s/exception: machine check improve labels and comments
arch/powerpc/include/asm/mce.h | 6 +
arch/powerpc/kernel/exceptions-64s.S | 371 ++++++++++----------
arch/powerpc/kernel/mce.c | 40 ++-
arch/powerpc/kernel/mce_power.c | 4 +
arch/powerpc/platforms/powernv/setup.c | 9 +
arch/powerpc/platforms/pseries/ras.c | 457 +++++++++++--------------
arch/powerpc/platforms/pseries/setup.c | 24 +-
7 files changed, 439 insertions(+), 472 deletions(-)
--
2.20.1
^ permalink raw reply
* [PATCH v2 01/16] powerpc/64s/exception: machine check fwnmi remove HV case
From: Nicholas Piggin @ 2019-07-10 15:19 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Mahesh Salgaonkar, Nicholas Piggin, Aravinda Prasad
In-Reply-To: <20190710151950.31906-1-npiggin@gmail.com>
fwnmi does not trigger in HV mode, so remove always-true feature test.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kernel/exceptions-64s.S | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 53c1b0a2ebce..db7ef8c8566f 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -1026,9 +1026,8 @@ TRAMP_REAL_BEGIN(machine_check_pSeries)
.globl machine_check_fwnmi
machine_check_fwnmi:
EXCEPTION_PROLOG_0 PACA_EXMC
-BEGIN_FTR_SECTION
b machine_check_common_early
-END_FTR_SECTION_IFCLR(CPU_FTR_HVMODE)
+
machine_check_pSeries_0:
EXCEPTION_PROLOG_1 EXC_STD, PACA_EXMC, 1, 0x200, 1, 1, 0
/*
--
2.20.1
^ permalink raw reply related
* [PATCH v2 02/16] powerpc/64s/exception: machine check remove bitrotted comment
From: Nicholas Piggin @ 2019-07-10 15:19 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Mahesh Salgaonkar, Nicholas Piggin, Aravinda Prasad
In-Reply-To: <20190710151950.31906-1-npiggin@gmail.com>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kernel/exceptions-64s.S | 4 ----
1 file changed, 4 deletions(-)
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index db7ef8c8566f..e8734a1dfdb9 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -933,10 +933,6 @@ EXC_COMMON_BEGIN(system_reset_common)
EXC_REAL_BEGIN(machine_check, 0x200, 0x100)
- /* This is moved out of line as it can be patched by FW, but
- * some code path might still want to branch into the original
- * vector
- */
EXCEPTION_PROLOG_0 PACA_EXMC
BEGIN_FTR_SECTION
b machine_check_common_early
--
2.20.1
^ permalink raw reply related
* [PATCH v2 03/16] powerpc/64s/exception: machine check fix KVM guest test
From: Nicholas Piggin @ 2019-07-10 15:19 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Mahesh Salgaonkar, Nicholas Piggin, Aravinda Prasad
In-Reply-To: <20190710151950.31906-1-npiggin@gmail.com>
The machine_check_handle_early hypervisor guest test is skipped if
!HVMODE or MSR[HV]=0, which is wrong for PR or nested hypervisors
that could be running a guest in this state.
Test HSTATE_IN_GUEST up front and use that to branch out to the KVM
handler, then MSR[PR] alone can test for this kernel's userspace.
This matches all other interrupt handling.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kernel/exceptions-64s.S | 33 +++++++++++-----------------
1 file changed, 13 insertions(+), 20 deletions(-)
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index e8734a1dfdb9..5789a00691f9 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -1108,11 +1108,8 @@ EXC_COMMON_BEGIN(machine_check_handle_early)
bl machine_check_early
std r3,RESULT(r1) /* Save result */
ld r12,_MSR(r1)
-BEGIN_FTR_SECTION
- b 4f
-END_FTR_SECTION_IFCLR(CPU_FTR_HVMODE)
-#ifdef CONFIG_PPC_P7_NAP
+#ifdef CONFIG_PPC_P7_NAP
/*
* Check if thread was in power saving mode. We come here when any
* of the following is true:
@@ -1128,30 +1125,26 @@ BEGIN_FTR_SECTION
END_FTR_SECTION_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
#endif
- /*
- * Check if we are coming from hypervisor userspace. If yes then we
- * continue in host kernel in V mode to deliver the MC event.
- */
- rldicl. r11,r12,4,63 /* See if MC hit while in HV mode. */
- beq 5f
-4: andi. r11,r12,MSR_PR /* See if coming from user. */
- bne 9f /* continue in V mode if we are. */
-
-5:
#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
-BEGIN_FTR_SECTION
/*
- * We are coming from kernel context. Check if we are coming from
- * guest. if yes, then we can continue. We will fall through
- * do_kvm_200->kvmppc_interrupt to deliver the MC event to guest.
+ * Check if we are coming from guest. If yes, then run the normal
+ * exception handler which will take the do_kvm_200->kvmppc_interrupt
+ * branch to deliver the MC event to guest.
*/
lbz r11,HSTATE_IN_GUEST(r13)
cmpwi r11,0 /* Check if coming from guest */
bne 9f /* continue if we are. */
-END_FTR_SECTION_IFSET(CPU_FTR_HVMODE)
#endif
+
+ /*
+ * Check if we are coming from userspace. If yes, then run the normal
+ * exception handler which will deliver the MC event to this kernel.
+ */
+ andi. r11,r12,MSR_PR /* See if coming from user. */
+ bne 9f /* continue in V mode if we are. */
+
/*
- * At this point we are not sure about what context we come from.
+ * At this point we are coming from kernel context.
* Queue up the MCE event and return from the interrupt.
* But before that, check if this is an un-recoverable exception.
* If yes, then stay on emergency stack and panic.
--
2.20.1
^ permalink raw reply related
* [PATCH v2 04/16] powerpc/64s/exception: machine check adjust RFI target
From: Nicholas Piggin @ 2019-07-10 15:19 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Mahesh Salgaonkar, Nicholas Piggin, Aravinda Prasad
In-Reply-To: <20190710151950.31906-1-npiggin@gmail.com>
The host kernel delivery case for powernv does RFI_TO_USER_OR_KERNEL,
but should just use RFI_TO_KERNEL which makes it clear this is not a
user case.
This is not a bug because RFI_TO_USER_OR_KERNEL deals with kernel
returns just fine.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kernel/exceptions-64s.S | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 5789a00691f9..0186a44bb981 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -1184,7 +1184,7 @@ BEGIN_FTR_SECTION
*/
bl machine_check_queue_event
MACHINE_CHECK_HANDLER_WINDUP
- RFI_TO_USER_OR_KERNEL
+ RFI_TO_KERNEL
FTR_SECTION_ELSE
/*
* pSeries: Return from MC interrupt. Before that stay on emergency
--
2.20.1
^ permalink raw reply related
* [PATCH v2 05/16] powerpc/64s/exception: machine check pseries should always run the early handler
From: Nicholas Piggin @ 2019-07-10 15:19 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Mahesh Salgaonkar, Nicholas Piggin, Aravinda Prasad
In-Reply-To: <20190710151950.31906-1-npiggin@gmail.com>
Now that pseries with fwnmi registered runs the early machine check
handler, there is no good reason to special case the non-fwnmi case
and skip the early handler. Reducing the code and number of paths is
a top priority for asm code, it's better to handle this in C where
possible (and the pseries early handler is a no-op if fwnmi is not
registered).
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kernel/exceptions-64s.S | 4 ----
1 file changed, 4 deletions(-)
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 0186a44bb981..a69ceb28cf4c 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -934,11 +934,7 @@ EXC_COMMON_BEGIN(system_reset_common)
EXC_REAL_BEGIN(machine_check, 0x200, 0x100)
EXCEPTION_PROLOG_0 PACA_EXMC
-BEGIN_FTR_SECTION
b machine_check_common_early
-FTR_SECTION_ELSE
- b machine_check_pSeries_0
-ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE)
EXC_REAL_END(machine_check, 0x200, 0x100)
EXC_VIRT_NONE(0x4200, 0x100)
TRAMP_REAL_BEGIN(machine_check_common_early)
--
2.20.1
^ permalink raw reply related
* [PATCH v2 06/16] powerpc/64s/exception: machine check remove machine_check_pSeries_0 branch
From: Nicholas Piggin @ 2019-07-10 15:19 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Mahesh Salgaonkar, Nicholas Piggin, Aravinda Prasad
In-Reply-To: <20190710151950.31906-1-npiggin@gmail.com>
This label has only one caller, so unwind the branch and move it
inline. The location of the comment is adjusted to match similar
one in system reset.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kernel/exceptions-64s.S | 23 ++++++++++-------------
1 file changed, 10 insertions(+), 13 deletions(-)
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index a69ceb28cf4c..54ca2b189d43 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -1014,20 +1014,11 @@ END_FTR_SECTION_IFSET(CPU_FTR_HVMODE)
b 1b
b . /* prevent speculative execution */
-TRAMP_REAL_BEGIN(machine_check_pSeries)
- .globl machine_check_fwnmi
-machine_check_fwnmi:
+#ifdef CONFIG_PPC_PSERIES
+TRAMP_REAL_BEGIN(machine_check_fwnmi)
EXCEPTION_PROLOG_0 PACA_EXMC
b machine_check_common_early
-
-machine_check_pSeries_0:
- EXCEPTION_PROLOG_1 EXC_STD, PACA_EXMC, 1, 0x200, 1, 1, 0
- /*
- * MSR_RI is not enabled, because PACA_EXMC is being used, so a
- * nested machine check corrupts it. machine_check_common enables
- * MSR_RI.
- */
- EXCEPTION_PROLOG_2_REAL machine_check_common, EXC_STD, 0
+#endif
TRAMP_KVM_SKIP(PACA_EXMC, 0x200)
@@ -1197,7 +1188,13 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE)
/* Deliver the machine check to host kernel in V mode. */
MACHINE_CHECK_HANDLER_WINDUP
EXCEPTION_PROLOG_0 PACA_EXMC
- b machine_check_pSeries_0
+ EXCEPTION_PROLOG_1 EXC_STD, PACA_EXMC, 1, 0x200, 1, 1, 0
+ EXCEPTION_PROLOG_2_REAL machine_check_common, EXC_STD, 0
+ /*
+ * MSR_RI is not enabled, because PACA_EXMC is being used, so a
+ * nested machine check corrupts it. machine_check_common enables
+ * MSR_RI.
+ */
EXC_COMMON_BEGIN(unrecover_mce)
/* Invoke machine_check_exception to print MCE event and panic. */
--
2.20.1
^ permalink raw reply related
* [PATCH v2 07/16] powerpc/64s/exception: machine check use correct cfar for late handler
From: Nicholas Piggin @ 2019-07-10 15:19 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Mahesh Salgaonkar, Nicholas Piggin, Aravinda Prasad
In-Reply-To: <20190710151950.31906-1-npiggin@gmail.com>
Bare metal machine checks run an "early" handler in real mode before
running the main handler which reports the event.
The main handler runs exactly as a normal interrupt handler, after the
"windup" which sets registers back as they were at interrupt entry.
CFAR does not get restored by the windup code, so that will be wrong
when the handler is run.
Restore the CFAR to the saved value before running the late handler.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kernel/exceptions-64s.S | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 54ca2b189d43..f2c24a4ae723 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -1186,6 +1186,10 @@ FTR_SECTION_ELSE
ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE)
9:
/* Deliver the machine check to host kernel in V mode. */
+BEGIN_FTR_SECTION
+ ld r10,ORIG_GPR3(r1)
+ mtspr SPRN_CFAR,r10
+END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
MACHINE_CHECK_HANDLER_WINDUP
EXCEPTION_PROLOG_0 PACA_EXMC
EXCEPTION_PROLOG_1 EXC_STD, PACA_EXMC, 1, 0x200, 1, 1, 0
--
2.20.1
^ permalink raw reply related
* [PATCH v2 08/16] powerpc/64s/powernv: machine check dump SLB contents
From: Nicholas Piggin @ 2019-07-10 15:19 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Mahesh Salgaonkar, Nicholas Piggin, Aravinda Prasad
In-Reply-To: <20190710151950.31906-1-npiggin@gmail.com>
Re-use the code introduced in pseries to save and dump the contents
of the SLB in the case of an SLB involved machine check exception.
This patch also avoids allocating the SLB save array on pseries radix.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kernel/mce.c | 6 ++++++
arch/powerpc/kernel/mce_power.c | 4 ++++
arch/powerpc/platforms/powernv/setup.c | 9 +++++++++
arch/powerpc/platforms/pseries/setup.c | 24 +++++++++++++-----------
4 files changed, 32 insertions(+), 11 deletions(-)
diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c
index b18df633eae9..38b560f92d12 100644
--- a/arch/powerpc/kernel/mce.c
+++ b/arch/powerpc/kernel/mce.c
@@ -486,6 +486,12 @@ void machine_check_print_event_info(struct machine_check_event *evt,
subtype = evt->error_class < ARRAY_SIZE(mc_error_class) ?
mc_error_class[evt->error_class] : "Unknown";
printk("%sMCE: CPU%d: %s\n", level, evt->cpu, subtype);
+
+#ifdef CONFIG_PPC_BOOK3S_64
+ /* Display faulty slb contents for SLB errors. */
+ if (evt->error_type == MCE_ERROR_TYPE_SLB)
+ slb_dump_contents(local_paca->mce_faulty_slbs);
+#endif
}
EXPORT_SYMBOL_GPL(machine_check_print_event_info);
diff --git a/arch/powerpc/kernel/mce_power.c b/arch/powerpc/kernel/mce_power.c
index e39536aad30d..c4d0e0c6e7d3 100644
--- a/arch/powerpc/kernel/mce_power.c
+++ b/arch/powerpc/kernel/mce_power.c
@@ -398,6 +398,8 @@ static int mce_handle_ierror(struct pt_regs *regs,
/* attempt to correct the error */
switch (table[i].error_type) {
case MCE_ERROR_TYPE_SLB:
+ if (local_paca->in_mce == 1)
+ slb_save_contents(local_paca->mce_faulty_slbs);
handled = mce_flush(MCE_FLUSH_SLB);
break;
case MCE_ERROR_TYPE_ERAT:
@@ -483,6 +485,8 @@ static int mce_handle_derror(struct pt_regs *regs,
/* attempt to correct the error */
switch (table[i].error_type) {
case MCE_ERROR_TYPE_SLB:
+ if (local_paca->in_mce == 1)
+ slb_save_contents(local_paca->mce_faulty_slbs);
if (mce_flush(MCE_FLUSH_SLB))
handled = 1;
break;
diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c
index a5e52f9eed3c..83498604d322 100644
--- a/arch/powerpc/platforms/powernv/setup.c
+++ b/arch/powerpc/platforms/powernv/setup.c
@@ -24,6 +24,7 @@
#include <linux/bug.h>
#include <linux/pci.h>
#include <linux/cpufreq.h>
+#include <linux/memblock.h>
#include <asm/machdep.h>
#include <asm/firmware.h>
@@ -166,6 +167,14 @@ static void __init pnv_init(void)
else
#endif
add_preferred_console("hvc", 0, NULL);
+
+ if (!radix_enabled()) {
+ int i;
+
+ /* Allocate per cpu area to save old slb contents during MCE */
+ for_each_possible_cpu(i)
+ paca_ptrs[i]->mce_faulty_slbs = memblock_alloc_node(mmu_slb_size, __alignof__(*paca_ptrs[i]->mce_faulty_slbs), cpu_to_node(i));
+ }
}
static void __init pnv_init_IRQ(void)
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index ab38a6c8dffb..637d59f4c5ce 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -139,17 +139,19 @@ static void __init fwnmi_init(void)
}
#ifdef CONFIG_PPC_BOOK3S_64
- /* Allocate per cpu slb area to save old slb contents during MCE */
- size = sizeof(struct slb_entry) * mmu_slb_size * nr_cpus;
- slb_ptr = memblock_alloc_try_nid_raw(size, sizeof(struct slb_entry),
- MEMBLOCK_LOW_LIMIT, ppc64_rma_size,
- NUMA_NO_NODE);
- if (!slb_ptr)
- panic("Failed to allocate %zu bytes below %pa for slb area\n",
- size, &ppc64_rma_size);
-
- for_each_possible_cpu(i)
- paca_ptrs[i]->mce_faulty_slbs = slb_ptr + (mmu_slb_size * i);
+ if (!radix_enabled()) {
+ /* Allocate per cpu area to save old slb contents during MCE */
+ size = sizeof(struct slb_entry) * mmu_slb_size * nr_cpus;
+ slb_ptr = memblock_alloc_try_nid_raw(size,
+ sizeof(struct slb_entry), MEMBLOCK_LOW_LIMIT,
+ ppc64_rma_size, NUMA_NO_NODE);
+ if (!slb_ptr)
+ panic("Failed to allocate %zu bytes below %pa for slb area\n",
+ size, &ppc64_rma_size);
+
+ for_each_possible_cpu(i)
+ paca_ptrs[i]->mce_faulty_slbs = slb_ptr + (mmu_slb_size * i);
+ }
#endif
}
--
2.20.1
^ permalink raw reply related
* [PATCH v2 09/16] powerpc/64s/pseries: machine check convert to use common event code
From: Nicholas Piggin @ 2019-07-10 15:19 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Mahesh Salgaonkar, Nicholas Piggin, Aravinda Prasad
In-Reply-To: <20190710151950.31906-1-npiggin@gmail.com>
The common machine_check_event data structures and queues are mostly
platform independent, with powernv decoding SRR1/DSISR/etc., into
machine_check_event objects.
This patch converts pseries to use this infrastructure by decoding
fwnmi/rtas data into machine_check_event objects.
This allows queueing to be used by a subsequent change to delay the
virtual mode handling of machine checks that occur in kernel space
where it is unsafe to switch immediately to virtual mode, similarly
to powernv.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/mce.h | 6 +
arch/powerpc/kernel/mce.c | 34 +-
arch/powerpc/platforms/pseries/ras.c | 457 +++++++++++----------------
3 files changed, 230 insertions(+), 267 deletions(-)
diff --git a/arch/powerpc/include/asm/mce.h b/arch/powerpc/include/asm/mce.h
index a4c6a74ad2fb..6f56b2d350b2 100644
--- a/arch/powerpc/include/asm/mce.h
+++ b/arch/powerpc/include/asm/mce.h
@@ -30,6 +30,10 @@ enum MCE_Disposition {
enum MCE_Initiator {
MCE_INITIATOR_UNKNOWN = 0,
MCE_INITIATOR_CPU = 1,
+ MCE_INITIATOR_PCI = 2,
+ MCE_INITIATOR_ISA = 3,
+ MCE_INITIATOR_MEMORY= 4,
+ MCE_INITIATOR_POWERMGM = 5,
};
enum MCE_ErrorType {
@@ -41,6 +45,8 @@ enum MCE_ErrorType {
MCE_ERROR_TYPE_USER = 5,
MCE_ERROR_TYPE_RA = 6,
MCE_ERROR_TYPE_LINK = 7,
+ MCE_ERROR_TYPE_DCACHE = 8,
+ MCE_ERROR_TYPE_ICACHE = 9,
};
enum MCE_ErrorClass {
diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c
index 38b560f92d12..5b4f766a68e9 100644
--- a/arch/powerpc/kernel/mce.c
+++ b/arch/powerpc/kernel/mce.c
@@ -300,7 +300,7 @@ static void machine_check_process_queued_event(struct irq_work *work)
void machine_check_print_event_info(struct machine_check_event *evt,
bool user_mode, bool in_guest)
{
- const char *level, *sevstr, *subtype, *err_type;
+ const char *level, *sevstr, *subtype, *err_type, *initiator;
uint64_t ea = 0, pa = 0;
int n = 0;
char dar_str[50];
@@ -385,6 +385,28 @@ void machine_check_print_event_info(struct machine_check_event *evt,
break;
}
+ switch(evt->initiator) {
+ case MCE_INITIATOR_CPU:
+ initiator = "CPU";
+ break;
+ case MCE_INITIATOR_PCI:
+ initiator = "PCI";
+ break;
+ case MCE_INITIATOR_ISA:
+ initiator = "ISA";
+ break;
+ case MCE_INITIATOR_MEMORY:
+ initiator = "Memory";
+ break;
+ case MCE_INITIATOR_POWERMGM:
+ initiator = "Power Management";
+ break;
+ case MCE_INITIATOR_UNKNOWN:
+ default:
+ initiator = "Unknown";
+ break;
+ }
+
switch (evt->error_type) {
case MCE_ERROR_TYPE_UE:
err_type = "UE";
@@ -451,6 +473,14 @@ void machine_check_print_event_info(struct machine_check_event *evt,
if (evt->u.link_error.effective_address_provided)
ea = evt->u.link_error.effective_address;
break;
+ case MCE_ERROR_TYPE_DCACHE:
+ err_type = "D-Cache";
+ subtype = "Unknown";
+ break;
+ case MCE_ERROR_TYPE_ICACHE:
+ err_type = "I-Cache";
+ subtype = "Unknown";
+ break;
default:
case MCE_ERROR_TYPE_UNKNOWN:
err_type = "Unknown";
@@ -483,6 +513,8 @@ void machine_check_print_event_info(struct machine_check_event *evt,
level, evt->cpu, evt->srr0, (void *)evt->srr0, pa_str);
}
+ printk("%sMCE: CPU%d: Initiator %s\n", level, evt->cpu, initiator);
+
subtype = evt->error_class < ARRAY_SIZE(mc_error_class) ?
mc_error_class[evt->error_class] : "Unknown";
printk("%sMCE: CPU%d: %s\n", level, evt->cpu, subtype);
diff --git a/arch/powerpc/platforms/pseries/ras.c b/arch/powerpc/platforms/pseries/ras.c
index f16fdd0f71f7..e03c3389692e 100644
--- a/arch/powerpc/platforms/pseries/ras.c
+++ b/arch/powerpc/platforms/pseries/ras.c
@@ -76,6 +76,7 @@ struct pseries_mc_errorlog {
#define MC_ERROR_TYPE_UE 0x00
#define MC_ERROR_TYPE_SLB 0x01
#define MC_ERROR_TYPE_ERAT 0x02
+#define MC_ERROR_TYPE_UNKNOWN 0x03
#define MC_ERROR_TYPE_TLB 0x04
#define MC_ERROR_TYPE_D_CACHE 0x05
#define MC_ERROR_TYPE_I_CACHE 0x07
@@ -87,6 +88,9 @@ struct pseries_mc_errorlog {
#define MC_ERROR_UE_LOAD_STORE 3
#define MC_ERROR_UE_PAGE_TABLE_WALK_LOAD_STORE 4
+#define UE_EFFECTIVE_ADDR_PROVIDED 0x40
+#define UE_LOGICAL_ADDR_PROVIDED 0x20
+
#define MC_ERROR_SLB_PARITY 0
#define MC_ERROR_SLB_MULTIHIT 1
#define MC_ERROR_SLB_INDETERMINATE 2
@@ -113,27 +117,6 @@ static inline u8 rtas_mc_error_sub_type(const struct pseries_mc_errorlog *mlog)
}
}
-static
-inline u64 rtas_mc_get_effective_addr(const struct pseries_mc_errorlog *mlog)
-{
- __be64 addr = 0;
-
- switch (mlog->error_type) {
- case MC_ERROR_TYPE_UE:
- if (mlog->sub_err_type & 0x40)
- addr = mlog->effective_address;
- break;
- case MC_ERROR_TYPE_SLB:
- case MC_ERROR_TYPE_ERAT:
- case MC_ERROR_TYPE_TLB:
- if (mlog->sub_err_type & 0x80)
- addr = mlog->effective_address;
- default:
- break;
- }
- return be64_to_cpu(addr);
-}
-
/*
* Enable the hotplug interrupt late because processing them may touch other
* devices or systems (e.g. hugepages) that have not been initialized at the
@@ -511,160 +494,162 @@ int pSeries_system_reset_exception(struct pt_regs *regs)
return 0; /* need to perform reset */
}
-#define VAL_TO_STRING(ar, val) \
- (((val) < ARRAY_SIZE(ar)) ? ar[(val)] : "Unknown")
-static void pseries_print_mce_info(struct pt_regs *regs,
- struct rtas_error_log *errp)
+static int mce_handle_error(struct pt_regs *regs, struct rtas_error_log *errp)
{
- const char *level, *sevstr;
+ struct mce_error_info mce_err = { 0 };
+ unsigned long eaddr = 0, paddr = 0;
struct pseries_errorlog *pseries_log;
struct pseries_mc_errorlog *mce_log;
- u8 error_type, err_sub_type;
- u64 addr;
- u8 initiator = rtas_error_initiator(errp);
int disposition = rtas_error_disposition(errp);
+ int initiator = rtas_error_initiator(errp);
+ int severity = rtas_error_severity(errp);
+ u8 error_type, err_sub_type;
- static const char * const initiators[] = {
- [0] = "Unknown",
- [1] = "CPU",
- [2] = "PCI",
- [3] = "ISA",
- [4] = "Memory",
- [5] = "Power Mgmt",
- };
- static const char * const mc_err_types[] = {
- [0] = "UE",
- [1] = "SLB",
- [2] = "ERAT",
- [3] = "Unknown",
- [4] = "TLB",
- [5] = "D-Cache",
- [6] = "Unknown",
- [7] = "I-Cache",
- };
- static const char * const mc_ue_types[] = {
- [0] = "Indeterminate",
- [1] = "Instruction fetch",
- [2] = "Page table walk ifetch",
- [3] = "Load/Store",
- [4] = "Page table walk Load/Store",
- };
-
- /* SLB sub errors valid values are 0x0, 0x1, 0x2 */
- static const char * const mc_slb_types[] = {
- [0] = "Parity",
- [1] = "Multihit",
- [2] = "Indeterminate",
- };
-
- /* TLB and ERAT sub errors valid values are 0x1, 0x2, 0x3 */
- static const char * const mc_soft_types[] = {
- [0] = "Unknown",
- [1] = "Parity",
- [2] = "Multihit",
- [3] = "Indeterminate",
- };
-
- if (!rtas_error_extended(errp)) {
- pr_err("Machine check interrupt: Missing extended error log\n");
- return;
- }
+ if (initiator == RTAS_INITIATOR_UNKNOWN)
+ mce_err.initiator = MCE_INITIATOR_UNKNOWN;
+ else if (initiator == RTAS_INITIATOR_CPU)
+ mce_err.initiator = MCE_INITIATOR_CPU;
+ else if (initiator == RTAS_INITIATOR_PCI)
+ mce_err.initiator = MCE_INITIATOR_PCI;
+ else if (initiator == RTAS_INITIATOR_ISA)
+ mce_err.initiator = MCE_INITIATOR_ISA;
+ else if (initiator == RTAS_INITIATOR_MEMORY)
+ mce_err.initiator = MCE_INITIATOR_MEMORY;
+ else if (initiator == RTAS_INITIATOR_POWERMGM)
+ mce_err.initiator = MCE_INITIATOR_POWERMGM;
+ else
+ mce_err.initiator = MCE_INITIATOR_UNKNOWN;
+
+ if (severity == RTAS_SEVERITY_NO_ERROR)
+ mce_err.severity = MCE_SEV_NO_ERROR;
+ else if (severity == RTAS_SEVERITY_EVENT)
+ mce_err.severity = MCE_SEV_WARNING;
+ else if (severity == RTAS_SEVERITY_WARNING)
+ mce_err.severity = MCE_SEV_WARNING;
+ else if (severity == RTAS_SEVERITY_ERROR_SYNC)
+ mce_err.severity = MCE_SEV_SEVERE;
+ else if (severity == RTAS_SEVERITY_ERROR)
+ mce_err.severity = MCE_SEV_SEVERE;
+ else if (severity == RTAS_SEVERITY_FATAL)
+ mce_err.severity = MCE_SEV_FATAL;
+ else
+ mce_err.severity = MCE_SEV_FATAL;
+
+ if (severity <= RTAS_SEVERITY_ERROR_SYNC)
+ mce_err.sync_error = true;
+ else
+ mce_err.sync_error = false;
+
+ mce_err.error_type = MCE_ERROR_TYPE_UNKNOWN;
+ mce_err.error_class = MCE_ECLASS_UNKNOWN;
+
+ if (!rtas_error_extended(errp))
+ goto out;
pseries_log = get_pseries_errorlog(errp, PSERIES_ELOG_SECT_ID_MCE);
if (pseries_log == NULL)
- return;
+ goto out;
mce_log = (struct pseries_mc_errorlog *)pseries_log->data;
-
error_type = mce_log->error_type;
err_sub_type = rtas_mc_error_sub_type(mce_log);
- switch (rtas_error_severity(errp)) {
- case RTAS_SEVERITY_NO_ERROR:
- level = KERN_INFO;
- sevstr = "Harmless";
- break;
- case RTAS_SEVERITY_WARNING:
- level = KERN_WARNING;
- sevstr = "";
- break;
- case RTAS_SEVERITY_ERROR:
- case RTAS_SEVERITY_ERROR_SYNC:
- level = KERN_ERR;
- sevstr = "Severe";
- break;
- case RTAS_SEVERITY_FATAL:
- default:
- level = KERN_ERR;
- sevstr = "Fatal";
- break;
- }
+ switch (mce_log->error_type) {
+ case MC_ERROR_TYPE_UE:
+ mce_err.error_type = MCE_ERROR_TYPE_UE;
+ switch (err_sub_type) {
+ case MC_ERROR_UE_IFETCH:
+ mce_err.u.ue_error_type = MCE_UE_ERROR_IFETCH;
+ case MC_ERROR_UE_PAGE_TABLE_WALK_IFETCH:
+ mce_err.u.ue_error_type = MCE_UE_ERROR_PAGE_TABLE_WALK_IFETCH;
+ case MC_ERROR_UE_LOAD_STORE:
+ mce_err.u.ue_error_type = MCE_UE_ERROR_LOAD_STORE;
+ case MC_ERROR_UE_PAGE_TABLE_WALK_LOAD_STORE:
+ mce_err.u.ue_error_type = MCE_UE_ERROR_PAGE_TABLE_WALK_LOAD_STORE;
+ case MC_ERROR_UE_INDETERMINATE:
+ default:
+ mce_err.u.ue_error_type = MCE_UE_ERROR_INDETERMINATE;
+ break;
+ }
+ if (mce_log->sub_err_type & UE_EFFECTIVE_ADDR_PROVIDED)
+ eaddr = be64_to_cpu(mce_log->effective_address);
-#ifdef CONFIG_PPC_BOOK3S_64
- /* Display faulty slb contents for SLB errors. */
- if (error_type == MC_ERROR_TYPE_SLB)
- slb_dump_contents(local_paca->mce_faulty_slbs);
-#endif
+ if (mce_log->sub_err_type & UE_LOGICAL_ADDR_PROVIDED) {
+ paddr = be64_to_cpu(mce_log->logical_address);
+ } else if (mce_log->sub_err_type & UE_EFFECTIVE_ADDR_PROVIDED) {
+ unsigned long pfn;
+
+ pfn = addr_to_pfn(regs, eaddr);
+ if (pfn != ULONG_MAX)
+ paddr = pfn << PAGE_SHIFT;
+ }
- printk("%s%s Machine check interrupt [%s]\n", level, sevstr,
- disposition == RTAS_DISP_FULLY_RECOVERED ?
- "Recovered" : "Not recovered");
- if (user_mode(regs)) {
- printk("%s NIP: [%016lx] PID: %d Comm: %s\n", level,
- regs->nip, current->pid, current->comm);
- } else {
- printk("%s NIP [%016lx]: %pS\n", level, regs->nip,
- (void *)regs->nip);
- }
- printk("%s Initiator: %s\n", level,
- VAL_TO_STRING(initiators, initiator));
- switch (error_type) {
- case MC_ERROR_TYPE_UE:
- printk("%s Error type: %s [%s]\n", level,
- VAL_TO_STRING(mc_err_types, error_type),
- VAL_TO_STRING(mc_ue_types, err_sub_type));
break;
case MC_ERROR_TYPE_SLB:
- printk("%s Error type: %s [%s]\n", level,
- VAL_TO_STRING(mc_err_types, error_type),
- VAL_TO_STRING(mc_slb_types, err_sub_type));
+ mce_err.error_type = MCE_ERROR_TYPE_SLB;
+ switch (err_sub_type) {
+ case MC_ERROR_SLB_PARITY:
+ mce_err.u.slb_error_type = MCE_SLB_ERROR_PARITY;
+ break;
+ case MC_ERROR_SLB_MULTIHIT:
+ mce_err.u.slb_error_type = MCE_SLB_ERROR_MULTIHIT;
+ break;
+ case MC_ERROR_SLB_INDETERMINATE:
+ default:
+ mce_err.u.slb_error_type = MCE_SLB_ERROR_INDETERMINATE;
+ break;
+ }
+ if (mce_log->sub_err_type & 0x80)
+ eaddr = be64_to_cpu(mce_log->effective_address);
break;
case MC_ERROR_TYPE_ERAT:
+ mce_err.error_type = MCE_ERROR_TYPE_ERAT;
+ switch (err_sub_type) {
+ case MC_ERROR_ERAT_PARITY:
+ mce_err.u.erat_error_type = MCE_ERAT_ERROR_PARITY;
+ break;
+ case MC_ERROR_ERAT_MULTIHIT:
+ mce_err.u.erat_error_type = MCE_ERAT_ERROR_MULTIHIT;
+ break;
+ case MC_ERROR_ERAT_INDETERMINATE:
+ default:
+ mce_err.u.erat_error_type = MCE_ERAT_ERROR_INDETERMINATE;
+ break;
+ }
+ if (mce_log->sub_err_type & 0x80)
+ eaddr = be64_to_cpu(mce_log->effective_address);
+ break;
case MC_ERROR_TYPE_TLB:
- printk("%s Error type: %s [%s]\n", level,
- VAL_TO_STRING(mc_err_types, error_type),
- VAL_TO_STRING(mc_soft_types, err_sub_type));
+ mce_err.error_type = MCE_ERROR_TYPE_TLB;
+ switch (err_sub_type) {
+ case MC_ERROR_TLB_PARITY:
+ mce_err.u.tlb_error_type = MCE_TLB_ERROR_PARITY;
+ break;
+ case MC_ERROR_TLB_MULTIHIT:
+ mce_err.u.tlb_error_type = MCE_TLB_ERROR_MULTIHIT;
+ break;
+ case MC_ERROR_TLB_INDETERMINATE:
+ default:
+ mce_err.u.tlb_error_type = MCE_TLB_ERROR_INDETERMINATE;
+ break;
+ }
+ if (mce_log->sub_err_type & 0x80)
+ eaddr = be64_to_cpu(mce_log->effective_address);
break;
+ case MC_ERROR_TYPE_D_CACHE:
+ mce_err.error_type = MCE_ERROR_TYPE_DCACHE;
+ break;
+ case MC_ERROR_TYPE_I_CACHE:
+ mce_err.error_type = MCE_ERROR_TYPE_DCACHE;
+ break;
+ case MC_ERROR_TYPE_UNKNOWN:
default:
- printk("%s Error type: %s\n", level,
- VAL_TO_STRING(mc_err_types, error_type));
+ mce_err.error_type = MCE_ERROR_TYPE_UNKNOWN;
break;
}
- addr = rtas_mc_get_effective_addr(mce_log);
- if (addr)
- printk("%s Effective address: %016llx\n", level, addr);
-}
-
-static int mce_handle_error(struct rtas_error_log *errp)
-{
- struct pseries_errorlog *pseries_log;
- struct pseries_mc_errorlog *mce_log;
- int disposition = rtas_error_disposition(errp);
- u8 error_type;
-
- if (!rtas_error_extended(errp))
- goto out;
-
- pseries_log = get_pseries_errorlog(errp, PSERIES_ELOG_SECT_ID_MCE);
- if (pseries_log == NULL)
- goto out;
-
- mce_log = (struct pseries_mc_errorlog *)pseries_log->data;
- error_type = mce_log->error_type;
-
#ifdef CONFIG_PPC_BOOK3S_64
if (disposition == RTAS_DISP_NOT_RECOVERED) {
switch (error_type) {
@@ -682,98 +667,24 @@ static int mce_handle_error(struct rtas_error_log *errp)
slb_save_contents(local_paca->mce_faulty_slbs);
flush_and_reload_slb();
disposition = RTAS_DISP_FULLY_RECOVERED;
- rtas_set_disposition_recovered(errp);
break;
default:
break;
}
+ } else if (disposition == RTAS_DISP_LIMITED_RECOVERY) {
+ /* Platform corrected itself but could be degraded */
+ printk(KERN_ERR "MCE: limited recovery, system may "
+ "be degraded\n");
+ disposition = RTAS_DISP_FULLY_RECOVERED;
}
#endif
out:
- return disposition;
-}
-
-#ifdef CONFIG_MEMORY_FAILURE
-
-static DEFINE_PER_CPU(int, rtas_ue_count);
-static DEFINE_PER_CPU(unsigned long, rtas_ue_paddr[MAX_MC_EVT]);
-
-#define UE_EFFECTIVE_ADDR_PROVIDED 0x40
-#define UE_LOGICAL_ADDR_PROVIDED 0x20
-
-
-static void pseries_hwpoison_work_fn(struct work_struct *work)
-{
- unsigned long paddr;
- int index;
-
- while (__this_cpu_read(rtas_ue_count) > 0) {
- index = __this_cpu_read(rtas_ue_count) - 1;
- paddr = __this_cpu_read(rtas_ue_paddr[index]);
- memory_failure(paddr >> PAGE_SHIFT, 0);
- __this_cpu_dec(rtas_ue_count);
- }
-}
+ save_mce_event(regs, disposition == RTAS_DISP_FULLY_RECOVERED,
+ &mce_err, regs->nip, eaddr, paddr);
-static DECLARE_WORK(hwpoison_work, pseries_hwpoison_work_fn);
-
-static void queue_ue_paddr(unsigned long paddr)
-{
- int index;
-
- index = __this_cpu_inc_return(rtas_ue_count) - 1;
- if (index >= MAX_MC_EVT) {
- __this_cpu_dec(rtas_ue_count);
- return;
- }
- this_cpu_write(rtas_ue_paddr[index], paddr);
- schedule_work(&hwpoison_work);
-}
-
-static void pseries_do_memory_failure(struct pt_regs *regs,
- struct pseries_mc_errorlog *mce_log)
-{
- unsigned long paddr;
-
- if (mce_log->sub_err_type & UE_LOGICAL_ADDR_PROVIDED) {
- paddr = be64_to_cpu(mce_log->logical_address);
- } else if (mce_log->sub_err_type & UE_EFFECTIVE_ADDR_PROVIDED) {
- unsigned long pfn;
-
- pfn = addr_to_pfn(regs,
- be64_to_cpu(mce_log->effective_address));
- if (pfn == ULONG_MAX)
- return;
- paddr = pfn << PAGE_SHIFT;
- } else {
- return;
- }
- queue_ue_paddr(paddr);
-}
-
-static void pseries_process_ue(struct pt_regs *regs,
- struct rtas_error_log *errp)
-{
- struct pseries_errorlog *pseries_log;
- struct pseries_mc_errorlog *mce_log;
-
- if (!rtas_error_extended(errp))
- return;
-
- pseries_log = get_pseries_errorlog(errp, PSERIES_ELOG_SECT_ID_MCE);
- if (!pseries_log)
- return;
-
- mce_log = (struct pseries_mc_errorlog *)pseries_log->data;
-
- if (mce_log->error_type == MC_ERROR_TYPE_UE)
- pseries_do_memory_failure(regs, mce_log);
+ return disposition;
}
-#else
-static inline void pseries_process_ue(struct pt_regs *regs,
- struct rtas_error_log *errp) { }
-#endif /*CONFIG_MEMORY_FAILURE */
/*
* Process MCE rtas errlog event.
@@ -795,49 +706,51 @@ static void mce_process_errlog_event(struct irq_work *work)
* Return 1 if corrected (or delivered a signal).
* Return 0 if there is nothing we can do.
*/
-static int recover_mce(struct pt_regs *regs, struct rtas_error_log *err)
+static int recover_mce(struct pt_regs *regs, struct machine_check_event *evt)
{
int recovered = 0;
- int disposition = rtas_error_disposition(err);
-
- pseries_print_mce_info(regs, err);
if (!(regs->msr & MSR_RI)) {
/* If MSR_RI isn't set, we cannot recover */
pr_err("Machine check interrupt unrecoverable: MSR(RI=0)\n");
recovered = 0;
-
- } else if (disposition == RTAS_DISP_FULLY_RECOVERED) {
+ } else if (evt->disposition == MCE_DISPOSITION_RECOVERED) {
/* Platform corrected itself */
recovered = 1;
+ } else if (evt->severity == MCE_SEV_FATAL) {
+ /* Fatal machine check */
+ pr_err("Machine check interrupt is fatal\n");
+ recovered = 0;
+ }
- } else if (disposition == RTAS_DISP_LIMITED_RECOVERY) {
- /* Platform corrected itself but could be degraded */
- printk(KERN_ERR "MCE: limited recovery, system may "
- "be degraded\n");
- recovered = 1;
-
- } else if (user_mode(regs) && !is_global_init(current) &&
- rtas_error_severity(err) == RTAS_SEVERITY_ERROR_SYNC) {
-
+ if (!recovered && evt->sync_error) {
/*
- * If we received a synchronous error when in userspace
- * kill the task. Firmware may report details of the fail
- * asynchronously, so we can't rely on the target and type
- * fields being valid here.
+ * Try to kill processes if we get a synchronous machine check
+ * (e.g., one caused by execution of this instruction). This
+ * will devolve into a panic if we try to kill init or are in
+ * an interrupt etc.
+ *
+ * TODO: Queue up this address for hwpoisioning later.
+ * TODO: This is not quite right for d-side machine
+ * checks ->nip is not necessarily the important
+ * address.
*/
- printk(KERN_ERR "MCE: uncorrectable error, killing task "
- "%s:%d\n", current->comm, current->pid);
-
- _exception(SIGBUS, regs, BUS_MCEERR_AR, regs->nip);
- recovered = 1;
+ if ((user_mode(regs))) {
+ _exception(SIGBUS, regs, BUS_MCEERR_AR, regs->nip);
+ recovered = 1;
+ } else if (die_will_crash()) {
+ /*
+ * die() would kill the kernel, so better to go via
+ * the platform reboot code that will log the
+ * machine check.
+ */
+ recovered = 0;
+ } else {
+ die("Machine check", regs, SIGBUS);
+ recovered = 1;
+ }
}
- pseries_process_ue(regs, err);
-
- /* Queue irq work to log this rtas event later. */
- irq_work_queue(&mce_errlog_process_work);
-
return recovered;
}
@@ -853,14 +766,21 @@ static int recover_mce(struct pt_regs *regs, struct rtas_error_log *err)
*/
int pSeries_machine_check_exception(struct pt_regs *regs)
{
- struct rtas_error_log *errp;
+ struct machine_check_event evt;
- if (fwnmi_active) {
- fwnmi_release_errinfo();
- errp = fwnmi_get_errlog();
- if (errp && recover_mce(regs, errp))
- return 1;
+ if (!get_mce_event(&evt, MCE_EVENT_RELEASE))
+ return 0;
+
+ /* Print things out */
+ if (evt.version != MCE_V1) {
+ pr_err("Machine Check Exception, Unknown event version %d !\n",
+ evt.version);
+ return 0;
}
+ machine_check_print_event_info(&evt, user_mode(regs), false);
+
+ if (recover_mce(regs, &evt))
+ return 1;
return 0;
}
@@ -877,7 +797,12 @@ long pseries_machine_check_realmode(struct pt_regs *regs)
* to panic. Hence we will call it as soon as we go into
* virtual mode.
*/
- disposition = mce_handle_error(errp);
+ disposition = mce_handle_error(regs, errp);
+ fwnmi_release_errinfo();
+
+ /* Queue irq work to log this rtas event later. */
+ irq_work_queue(&mce_errlog_process_work);
+
if (disposition == RTAS_DISP_FULLY_RECOVERED)
return 1;
}
--
2.20.1
^ permalink raw reply related
* [PATCH v2 10/16] powerpc/64s/exception: machine check pseries should skip the late handler for host kernel MCEs
From: Nicholas Piggin @ 2019-07-10 15:19 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Mahesh Salgaonkar, Nicholas Piggin, Aravinda Prasad
In-Reply-To: <20190710151950.31906-1-npiggin@gmail.com>
The powernv machine check handler copes with taking a MCE from one of
three contexts, guest, host kernel, and host user. In each case the
early handler runs first on a special stack. Then:
- The guest case branches to the KVM interrupt handler (via standard
interrupt macros).
- The host user case will run the "late" handler which is like a
normal interrupt that runs in virtual mode and uses the regular
kernel stack.
- The host kernel case queues the event and schedules it for
processing with irq work.
The last case is important, it must not enable virtual memory because
the MMU state may not be set up to deal with that (e.g., SLB might be
clear), it must not use the regular kernel stack for similar reasons
(e.g., might be in OPAL with OPAL stack in r1), and the kernel does
not expect anything to touch its stack if interrupts are disabled.
The pseries handler does not do this queueing, but instead it always
runs the late handler for host MCEs, which has some of the same
problems.
Now that pseries is using machine_check_events, it can just do the
same as powernv and queue up kernel-mode MCE events.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kernel/exceptions-64s.S | 22 ++--------------------
1 file changed, 2 insertions(+), 20 deletions(-)
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index f2c24a4ae723..ac7b5bb614d9 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -1163,7 +1163,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
cmpdi r3,0 /* see if we handled MCE successfully */
beq 1b /* if !handled then panic */
-BEGIN_FTR_SECTION
+
/*
* Return from MC interrupt.
* Queue up the MCE event so that we can log it later, while
@@ -1172,18 +1172,7 @@ BEGIN_FTR_SECTION
bl machine_check_queue_event
MACHINE_CHECK_HANDLER_WINDUP
RFI_TO_KERNEL
-FTR_SECTION_ELSE
- /*
- * pSeries: Return from MC interrupt. Before that stay on emergency
- * stack and call machine_check_exception to log the MCE event.
- */
- LOAD_HANDLER(r10,mce_return)
- mtspr SPRN_SRR0,r10
- ld r10,PACAKMSR(r13)
- mtspr SPRN_SRR1,r10
- RFI_TO_KERNEL
- b .
-ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE)
+
9:
/* Deliver the machine check to host kernel in V mode. */
BEGIN_FTR_SECTION
@@ -1212,13 +1201,6 @@ EXC_COMMON_BEGIN(unrecover_mce)
bl unrecoverable_exception
b 1b
-EXC_COMMON_BEGIN(mce_return)
- /* Invoke machine_check_exception to print MCE event and return. */
- addi r3,r1,STACK_FRAME_OVERHEAD
- bl machine_check_exception
- MACHINE_CHECK_HANDLER_WINDUP
- RFI_TO_KERNEL
- b .
EXC_REAL_BEGIN(data_access, 0x300, 0x80)
EXCEPTION_PROLOG_0 PACA_EXGEN
--
2.20.1
^ permalink raw reply related
* [PATCH v2 11/16] powerpc/64s/exception: machine check restructure to reuse common macros
From: Nicholas Piggin @ 2019-07-10 15:19 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Mahesh Salgaonkar, Nicholas Piggin, Aravinda Prasad
In-Reply-To: <20190710151950.31906-1-npiggin@gmail.com>
Follow the pattern of sreset and HMI handlers more closely: use
EXCEPTION_PROLOG_COMMON_1 rather than open-coding it, and run the
handler at the relocated location.
This helps later simplification and code sharing.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kernel/exceptions-64s.S | 71 ++++++++++++++--------------
1 file changed, 36 insertions(+), 35 deletions(-)
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index ac7b5bb614d9..3cc5ee6e4b56 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -934,17 +934,23 @@ EXC_COMMON_BEGIN(system_reset_common)
EXC_REAL_BEGIN(machine_check, 0x200, 0x100)
EXCEPTION_PROLOG_0 PACA_EXMC
- b machine_check_common_early
+ EXCEPTION_PROLOG_1 EXC_STD, PACA_EXMC, 0, 0x200, 1, 1, 0
+ mfctr r10 /* save ctr, even for !RELOCATABLE */
+ BRANCH_TO_C000(r11, machine_check_early_common)
+ /*
+ * MSR_RI is not enabled, because PACA_EXMC is being used, so a
+ * nested machine check corrupts it. machine_check_common enables
+ * MSR_RI.
+ */
EXC_REAL_END(machine_check, 0x200, 0x100)
EXC_VIRT_NONE(0x4200, 0x100)
-TRAMP_REAL_BEGIN(machine_check_common_early)
- EXCEPTION_PROLOG_1 EXC_STD, PACA_EXMC, 0, 0x200, 0, 0, 0
+
+EXC_COMMON_BEGIN(machine_check_early_common)
+ mtctr r10 /* Restore ctr */
+ mfspr r11,SPRN_SRR0
+ mfspr r12,SPRN_SRR1
+
/*
- * Register contents:
- * R13 = PACA
- * R9 = CR
- * Original R9 to R13 is saved on PACA_EXMC
- *
* Switch to mc_emergency stack and handle re-entrancy (we limit
* the nested MCE upto level 4 to avoid stack overflow).
* Save MCE registers srr1, srr0, dar and dsisr and then set ME=1
@@ -965,32 +971,30 @@ TRAMP_REAL_BEGIN(machine_check_common_early)
* the machine check is handled then the idle wakeup code is called
* to restore state.
*/
- mr r11,r1 /* Save r1 */
lhz r10,PACA_IN_MCE(r13)
cmpwi r10,0 /* Are we in nested machine check */
- bne 0f /* Yes, we are. */
- /* First machine check entry */
- ld r1,PACAMCEMERGSP(r13) /* Use MC emergency stack */
-0: subi r1,r1,INT_FRAME_SIZE /* alloc stack frame */
+ cmpwi cr1,r10,MAX_MCE_DEPTH /* Are we at maximum nesting */
addi r10,r10,1 /* increment paca->in_mce */
sth r10,PACA_IN_MCE(r13)
+
+ mr r10,r1 /* Save r1 */
+ bne 1f
+ /* First machine check entry */
+ ld r1,PACAMCEMERGSP(r13) /* Use MC emergency stack */
+1: subi r1,r1,INT_FRAME_SIZE /* alloc stack frame */
/* Limit nested MCE to level 4 to avoid stack overflow */
- cmpwi r10,MAX_MCE_DEPTH
- bgt 2f /* Check if we hit limit of 4 */
- std r11,GPR1(r1) /* Save r1 on the stack. */
- std r11,0(r1) /* make stack chain pointer */
- mfspr r11,SPRN_SRR0 /* Save SRR0 */
- std r11,_NIP(r1)
- mfspr r11,SPRN_SRR1 /* Save SRR1 */
- std r11,_MSR(r1)
- mfspr r11,SPRN_DAR /* Save DAR */
- std r11,_DAR(r1)
- mfspr r11,SPRN_DSISR /* Save DSISR */
- std r11,_DSISR(r1)
- std r9,_CCR(r1) /* Save CR in stackframe */
+ bge cr1,2f /* Check if we hit limit of 4 */
+
+ EXCEPTION_PROLOG_COMMON_1()
/* We don't touch AMR here, we never go to virtual mode */
- /* Save r9 through r13 from EXMC save area to stack frame. */
EXCEPTION_PROLOG_COMMON_2(PACA_EXMC)
+ EXCEPTION_PROLOG_COMMON_3(0x200)
+
+ ld r3,PACA_EXMC+EX_DAR(r13)
+ lwz r4,PACA_EXMC+EX_DSISR(r13)
+ std r3,_DAR(r1)
+ std r4,_DSISR(r1)
+
mfmsr r11 /* get MSR value */
BEGIN_FTR_SECTION
ori r11,r11,MSR_ME /* turn on ME bit */
@@ -1016,8 +1020,11 @@ END_FTR_SECTION_IFSET(CPU_FTR_HVMODE)
#ifdef CONFIG_PPC_PSERIES
TRAMP_REAL_BEGIN(machine_check_fwnmi)
+ /* See comment at machine_check exception, don't turn on RI */
EXCEPTION_PROLOG_0 PACA_EXMC
- b machine_check_common_early
+ EXCEPTION_PROLOG_1 EXC_STD, PACA_EXMC, 0, 0x200, 1, 1, 0
+ mfctr r10 /* save ctr */
+ BRANCH_TO_C000(r11, machine_check_early_common)
#endif
TRAMP_KVM_SKIP(PACA_EXMC, 0x200)
@@ -1088,8 +1095,6 @@ EXC_COMMON_BEGIN(machine_check_idle_common)
* ME=1, MMU (IR=0 and DR=0) off and using MC emergency stack.
*/
EXC_COMMON_BEGIN(machine_check_handle_early)
- std r0,GPR0(r1) /* Save r0 */
- EXCEPTION_PROLOG_COMMON_3(0x200)
bl save_nvgprs
addi r3,r1,STACK_FRAME_OVERHEAD
bl machine_check_early
@@ -1180,14 +1185,10 @@ BEGIN_FTR_SECTION
mtspr SPRN_CFAR,r10
END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
MACHINE_CHECK_HANDLER_WINDUP
+ /* See comment at machine_check exception, don't turn on RI */
EXCEPTION_PROLOG_0 PACA_EXMC
EXCEPTION_PROLOG_1 EXC_STD, PACA_EXMC, 1, 0x200, 1, 1, 0
EXCEPTION_PROLOG_2_REAL machine_check_common, EXC_STD, 0
- /*
- * MSR_RI is not enabled, because PACA_EXMC is being used, so a
- * nested machine check corrupts it. machine_check_common enables
- * MSR_RI.
- */
EXC_COMMON_BEGIN(unrecover_mce)
/* Invoke machine_check_exception to print MCE event and panic. */
--
2.20.1
^ permalink raw reply related
* [PATCH v2 12/16] powerpc/64s/exception: machine check move tramp code
From: Nicholas Piggin @ 2019-07-10 15:19 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Mahesh Salgaonkar, Nicholas Piggin, Aravinda Prasad
In-Reply-To: <20190710151950.31906-1-npiggin@gmail.com>
Following convention, move the tramp code (unrelocated) above the
common handlers (relocated).
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kernel/exceptions-64s.S | 22 +++++++++++-----------
1 file changed, 11 insertions(+), 11 deletions(-)
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 3cc5ee6e4b56..9bb8c89e9e77 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -945,6 +945,17 @@ EXC_REAL_BEGIN(machine_check, 0x200, 0x100)
EXC_REAL_END(machine_check, 0x200, 0x100)
EXC_VIRT_NONE(0x4200, 0x100)
+#ifdef CONFIG_PPC_PSERIES
+TRAMP_REAL_BEGIN(machine_check_fwnmi)
+ /* See comment at machine_check exception, don't turn on RI */
+ EXCEPTION_PROLOG_0 PACA_EXMC
+ EXCEPTION_PROLOG_1 EXC_STD, PACA_EXMC, 0, 0x200, 1, 1, 0
+ mfctr r10 /* save ctr */
+ BRANCH_TO_C000(r11, machine_check_early_common)
+#endif
+
+TRAMP_KVM_SKIP(PACA_EXMC, 0x200)
+
EXC_COMMON_BEGIN(machine_check_early_common)
mtctr r10 /* Restore ctr */
mfspr r11,SPRN_SRR0
@@ -1018,17 +1029,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_HVMODE)
b 1b
b . /* prevent speculative execution */
-#ifdef CONFIG_PPC_PSERIES
-TRAMP_REAL_BEGIN(machine_check_fwnmi)
- /* See comment at machine_check exception, don't turn on RI */
- EXCEPTION_PROLOG_0 PACA_EXMC
- EXCEPTION_PROLOG_1 EXC_STD, PACA_EXMC, 0, 0x200, 1, 1, 0
- mfctr r10 /* save ctr */
- BRANCH_TO_C000(r11, machine_check_early_common)
-#endif
-
-TRAMP_KVM_SKIP(PACA_EXMC, 0x200)
-
EXC_COMMON_BEGIN(machine_check_common)
/*
* Machine check is different because we use a different
--
2.20.1
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox