The address of external symbols will locate more than 32-bit offset. We
were using the `-Wa,-mla-global-with-abs` and `-Wa,-mla-local-with-abs`
to prevent the compiler and assembler from generating GOT relocations,
but these options are undocumented hacks and do not work anymore with
GAS 2.40 and GCC 13.
Let the module loader emit GOT entries for data symbols so we would be
able to handle GOT relocations. The GOT entry is just the data symbol
address.
Signed-off-by: Xi Ruoyao <[email protected]>
---
arch/loongarch/include/asm/module.h | 23 +++++++++++++
arch/loongarch/include/asm/module.lds.h | 1 +
arch/loongarch/kernel/module-sections.c | 43 ++++++++++++++++++++++---
3 files changed, 63 insertions(+), 4 deletions(-)
diff --git a/arch/loongarch/include/asm/module.h b/arch/loongarch/include/asm/module.h
index 9f6718df1854..76a98a0ab8a0 100644
--- a/arch/loongarch/include/asm/module.h
+++ b/arch/loongarch/include/asm/module.h
@@ -19,6 +19,7 @@ struct mod_section {
struct mod_arch_specific {
struct mod_section plt;
struct mod_section plt_idx;
+ struct mod_section got;
};
struct plt_entry {
@@ -28,11 +29,16 @@ struct plt_entry {
u32 inst_jirl;
};
+struct got_entry {
+ Elf_Addr symbol_addr;
+};
+
struct plt_idx_entry {
unsigned long symbol_addr;
};
Elf_Addr module_emit_plt_entry(struct module *mod, unsigned long val);
+Elf_Addr module_emit_got_entry(struct module *mod, Elf_Addr val);
static inline struct plt_entry emit_plt_entry(unsigned long val)
{
@@ -51,6 +57,11 @@ static inline struct plt_idx_entry emit_plt_idx_entry(unsigned long val)
return (struct plt_idx_entry) { val };
}
+static inline struct got_entry emit_got_entry(Elf_Addr val)
+{
+ return (struct got_entry) { val };
+}
+
static inline int get_plt_idx(unsigned long val, const struct mod_section *sec)
{
int i;
@@ -77,4 +88,16 @@ static inline struct plt_entry *get_plt_entry(unsigned long val,
return plt + plt_idx;
}
+static inline struct got_entry *get_got_entry(Elf_Addr val,
+ const struct mod_section *sec)
+{
+ struct got_entry *got = (struct got_entry *)sec->shdr->sh_addr;
+ int i;
+
+ for (i = 0; i < sec->num_entries; i++)
+ if (got[i].symbol_addr == val)
+ return &got[i];
+ return NULL;
+}
+
#endif /* _ASM_MODULE_H */
diff --git a/arch/loongarch/include/asm/module.lds.h b/arch/loongarch/include/asm/module.lds.h
index 31c1c0db11a3..57bbd0cedd26 100644
--- a/arch/loongarch/include/asm/module.lds.h
+++ b/arch/loongarch/include/asm/module.lds.h
@@ -4,4 +4,5 @@ SECTIONS {
. = ALIGN(4);
.plt : { BYTE(0) }
.plt.idx : { BYTE(0) }
+ .got : { BYTE(0) }
}
diff --git a/arch/loongarch/kernel/module-sections.c b/arch/loongarch/kernel/module-sections.c
index 6d498288977d..509c0b86b1e9 100644
--- a/arch/loongarch/kernel/module-sections.c
+++ b/arch/loongarch/kernel/module-sections.c
@@ -33,6 +33,25 @@ Elf_Addr module_emit_plt_entry(struct module *mod, unsigned long val)
return (Elf_Addr)&plt[nr];
}
+Elf_Addr module_emit_got_entry(struct module *mod, Elf_Addr val)
+{
+ struct mod_section *got_sec = &mod->arch.got;
+ int i = got_sec->num_entries;
+ struct got_entry *got = get_got_entry(val, got_sec);
+
+ if (got)
+ return (Elf_Addr)got;
+
+ /* There is no GOT entry existing for val yet. Create a new one. */
+ got = (struct got_entry *)got_sec->shdr->sh_addr;
+ got[i] = emit_got_entry(val);
+
+ got_sec->num_entries++;
+ BUG_ON(got_sec->num_entries > got_sec->max_entries);
+
+ return (Elf_Addr)&got[i];
+}
+
static int is_rela_equal(const Elf_Rela *x, const Elf_Rela *y)
{
return x->r_info == y->r_info && x->r_addend == y->r_addend;
@@ -50,7 +69,8 @@ static bool duplicate_rela(const Elf_Rela *rela, int idx)
return false;
}
-static void count_max_entries(Elf_Rela *relas, int num, unsigned int *plts)
+static void count_max_entries(Elf_Rela *relas, int num,
+ unsigned int *plts, unsigned int *gots)
{
unsigned int i, type;
@@ -59,14 +79,16 @@ static void count_max_entries(Elf_Rela *relas, int num, unsigned int *plts)
if (type == R_LARCH_SOP_PUSH_PLT_PCREL) {
if (!duplicate_rela(relas, i))
(*plts)++;
- }
+ } else if (type == R_LARCH_SOP_PUSH_GPREL)
+ if (!duplicate_rela(relas, i))
+ (*gots)++;
}
}
int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
char *secstrings, struct module *mod)
{
- unsigned int i, num_plts = 0;
+ unsigned int i, num_plts = 0, num_gots = 0;
/*
* Find the empty .plt sections.
@@ -76,6 +98,8 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
mod->arch.plt.shdr = sechdrs + i;
else if (!strcmp(secstrings + sechdrs[i].sh_name, ".plt.idx"))
mod->arch.plt_idx.shdr = sechdrs + i;
+ else if (!strcmp(secstrings + sechdrs[i].sh_name, ".got"))
+ mod->arch.got.shdr = sechdrs + i;
}
if (!mod->arch.plt.shdr) {
@@ -86,6 +110,10 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
pr_err("%s: module PLT.IDX section(s) missing\n", mod->name);
return -ENOEXEC;
}
+ if (!mod->arch.got.shdr) {
+ pr_err("%s: module GOT section(s) missing\n", mod->name);
+ return -ENOEXEC;
+ }
/* Calculate the maxinum number of entries */
for (i = 0; i < ehdr->e_shnum; i++) {
@@ -100,7 +128,7 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
if (!(dst_sec->sh_flags & SHF_EXECINSTR))
continue;
- count_max_entries(relas, num_rela, &num_plts);
+ count_max_entries(relas, num_rela, &num_plts, &num_gots);
}
mod->arch.plt.shdr->sh_type = SHT_NOBITS;
@@ -117,5 +145,12 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
mod->arch.plt_idx.num_entries = 0;
mod->arch.plt_idx.max_entries = num_plts;
+ mod->arch.got.shdr->sh_type = SHT_NOBITS;
+ mod->arch.got.shdr->sh_flags = SHF_ALLOC;
+ mod->arch.got.shdr->sh_addralign = L1_CACHE_BYTES;
+ mod->arch.got.shdr->sh_size = (num_plts + 1) * sizeof(struct plt_entry);
+ mod->arch.got.num_entries = 0;
+ mod->arch.got.max_entries = num_plts;
+
return 0;
}
--
2.37.0
On Thu, 2022-07-28 at 16:29 +0800, Youling Tang wrote:
> On 07/28/2022 12:26 AM, Xi Ruoyao wrote:
> > + mod->arch.got.shdr->sh_type = SHT_NOBITS;
> > + mod->arch.got.shdr->sh_flags = SHF_ALLOC;
> > + mod->arch.got.shdr->sh_addralign = L1_CACHE_BYTES;
> > + mod->arch.got.shdr->sh_size = (num_plts + 1) *
> > sizeof(struct plt_entry);
> > + mod->arch.got.num_entries = 0;
> > + mod->arch.got.max_entries = num_plts;
> Hi, Ruoyao
>
> We should use num_gots instead of num_plts when creating .got
> section.
Yes, it's a stupid error and I'll fix it in V2.
But why didn't this cause a malfunction on my system? :(.
--
Xi Ruoyao <[email protected]>
School of Aerospace Science and Technology, Xidian University
On 07/28/2022 05:02 PM, Xi Ruoyao wrote:
> On Thu, 2022-07-28 at 16:29 +0800, Youling Tang wrote:
>> On 07/28/2022 12:26 AM, Xi Ruoyao wrote:
>>> + mod->arch.got.shdr->sh_type = SHT_NOBITS;
>>> + mod->arch.got.shdr->sh_flags = SHF_ALLOC;
>>> + mod->arch.got.shdr->sh_addralign = L1_CACHE_BYTES;
>>> + mod->arch.got.shdr->sh_size = (num_plts + 1) *
>>> sizeof(struct plt_entry);
>>> + mod->arch.got.num_entries = 0;
>>> + mod->arch.got.max_entries = num_plts;
>> Hi, Ruoyao
>>
>> We should use num_gots instead of num_plts when creating .got
>> section.
>
> Yes, it's a stupid error and I'll fix it in V2.
>
> But why didn't this cause a malfunction on my system? :(.
Maybe num_plts is greater than num_gots, and the size of plt_entry is
equivalent to the size of four got_entry, so that when the module is
loaded, it just allocates a larger space without causing the module to
fail to load.
Thanks,
Youling
>
On Thu, 2022-07-28 at 17:21 +0800, Youling Tang wrote:
>
>
> On 07/28/2022 05:02 PM, Xi Ruoyao wrote:
> > On Thu, 2022-07-28 at 16:29 +0800, Youling Tang wrote:
> > > On 07/28/2022 12:26 AM, Xi Ruoyao wrote:
> > > > + mod->arch.got.shdr->sh_type = SHT_NOBITS;
> > > > + mod->arch.got.shdr->sh_flags = SHF_ALLOC;
> > > > + mod->arch.got.shdr->sh_addralign = L1_CACHE_BYTES;
> > > > + mod->arch.got.shdr->sh_size = (num_plts + 1) *
> > > > sizeof(struct plt_entry);
> > > > + mod->arch.got.num_entries = 0;
> > > > + mod->arch.got.max_entries = num_plts;
> > > Hi, Ruoyao
> > >
> > > We should use num_gots instead of num_plts when creating .got
> > > section.
> >
> > Yes, it's a stupid error and I'll fix it in V2.
> >
> > But why didn't this cause a malfunction on my system? :(.
>
> Maybe num_plts is greater than num_gots, and the size of plt_entry is
> equivalent to the size of four got_entry, so that when the module is
> loaded, it just allocates a larger space without causing the module to
> fail to load.
I'll write a module to load address of 10 kernel symbols with only one
printk call to test before sending V2 :).
--
Xi Ruoyao <[email protected]>
School of Aerospace Science and Technology, Xidian University