From: John Baldwin <jhb@FreeBSD.org>
To: gdb-patches@sourceware.org
Subject: [PATCH v5 19/19] gdbserver: Simplify handling of ZMM registers.
Date: Thu, 27 Apr 2023 14:01:13 -0700 [thread overview]
Message-ID: <20230427210113.45380-20-jhb@FreeBSD.org> (raw)
In-Reply-To: <20230427210113.45380-1-jhb@FreeBSD.org>
- Reuse num_xmm_registers directly for the count of ZMM0-15 registers
as is already done for the YMM registers for AVX rather than using
a new variable that is always the same.
- Replace 3 identical variables for the count of upper ZMM16-31
registers with a single variable. Make use of this to merge
various loops working on the ZMM XSAVE region so that all of the
handling for the various sub-registers in this region are always
handled in a single loop.
- While here, fix some bugs in i387_cache_to_xsave on where if
X86_XSTATE_ZMM was set on i386 (e.g. a 32-bit process on a 64-bit
kernel), the -1 register nums would wrap around and store the
value of GPRs in the XSAVE area. This should be harmless, but
is definitely odd. Instead, check num_zmm_high_registers directly
when checking X86_XSTATE_ZMM and skip the ZMM region handling
entirely if the register count is 0.
---
gdbserver/i387-fp.cc | 132 +++++++++++++++----------------------------
1 file changed, 46 insertions(+), 86 deletions(-)
diff --git a/gdbserver/i387-fp.cc b/gdbserver/i387-fp.cc
index f53a6cfc477..91d3a0b8ca3 100644
--- a/gdbserver/i387-fp.cc
+++ b/gdbserver/i387-fp.cc
@@ -267,12 +267,8 @@ i387_cache_to_xsave (struct regcache *regcache, void *buf)
/* Amd64 has 16 xmm regs; I386 has 8 xmm regs. */
int num_xmm_registers = amd64 ? 16 : 8;
- /* AVX512 extends the existing xmm/ymm registers to a wider mode: zmm. */
- int num_avx512_zmmh_low_registers = num_xmm_registers;
- /* AVX512 adds 16 extra regs in Amd64 mode, but none in I386 mode.*/
- int num_avx512_zmmh_high_registers = amd64 ? 16 : 0;
- int num_avx512_ymmh_registers = amd64 ? 16 : 0;
- int num_avx512_xmm_registers = amd64 ? 16 : 0;
+ /* AVX512 adds 16 extra ZMM regs in Amd64 mode, but none in I386 mode.*/
+ int num_zmm_high_registers = amd64 ? 16 : 0;
/* The supported bits in `xstat_bv' are 8 bytes. Clear part in
vector registers if its bit in xstat_bv is zero. */
@@ -321,18 +317,12 @@ i387_cache_to_xsave (struct regcache *regcache, void *buf)
memset (fp->k_space () + i * 8, 0, 8);
if ((clear_bv & X86_XSTATE_ZMM_H))
- for (i = 0; i < num_avx512_zmmh_low_registers; i++)
+ for (i = 0; i < num_xmm_registers; i++)
memset (fp->zmmh_space () + i * 32, 0, 32);
if ((clear_bv & X86_XSTATE_ZMM))
- {
- for (i = 0; i < num_avx512_zmmh_high_registers; i++)
- memset (fp->zmm_space () + 32 + i * 64, 0, 32);
- for (i = 0; i < num_avx512_xmm_registers; i++)
- memset (fp->zmm_space () + i * 64, 0, 16);
- for (i = 0; i < num_avx512_ymmh_registers; i++)
- memset (fp->zmm_space () + 16 + i * 64, 0, 16);
- }
+ for (i = 0; i < num_zmm_high_registers; i++)
+ memset (fp->zmm_space () + i * 64, 0, 64);
if ((clear_bv & X86_XSTATE_PKRU))
for (i = 0; i < num_pkeys_registers; i++)
@@ -446,7 +436,7 @@ i387_cache_to_xsave (struct regcache *regcache, void *buf)
{
int zmm0h_regnum = find_regno (regcache->tdesc, "zmm0h");
- for (i = 0; i < num_avx512_zmmh_low_registers; i++)
+ for (i = 0; i < num_xmm_registers; i++)
{
collect_register (regcache, i + zmm0h_regnum, raw);
p = fp->zmmh_space () + i * 32;
@@ -458,55 +448,35 @@ i387_cache_to_xsave (struct regcache *regcache, void *buf)
}
}
- /* Check if any of ZMM16H-ZMM31H registers are changed. */
- if ((x86_xcr0 & X86_XSTATE_ZMM))
+ /* Check if any of ZMM16-ZMM31 registers are changed. */
+ if ((x86_xcr0 & X86_XSTATE_ZMM) && num_zmm_high_registers != 0)
{
- int zmm16h_regnum = (num_avx512_zmmh_high_registers == 0
- ? -1
- : find_regno (regcache->tdesc, "zmm16h"));
+ int zmm16h_regnum = find_regno (regcache->tdesc, "zmm16h");
+ int ymm16h_regnum = find_regno (regcache->tdesc, "ymm16h");
+ int xmm16_regnum = find_regno (regcache->tdesc, "xmm16");
- for (i = 0; i < num_avx512_zmmh_high_registers; i++)
+ for (i = 0; i < num_zmm_high_registers; i++)
{
- collect_register (regcache, i + zmm16h_regnum, raw);
- p = fp->zmm_space () + 32 + i * 64;
- if (memcmp (raw, p, 32) != 0)
- {
- xstate_bv |= X86_XSTATE_ZMM;
- memcpy (p, raw, 32);
- }
- }
- }
-
- /* Check if any XMM_AVX512 registers are changed. */
- if ((x86_xcr0 & X86_XSTATE_ZMM))
- {
- int xmm_avx512_regnum = (num_avx512_xmm_registers == 0
- ? -1
- : find_regno (regcache->tdesc, "xmm16"));
-
- for (i = 0; i < num_avx512_xmm_registers; i++)
- {
- collect_register (regcache, i + xmm_avx512_regnum, raw);
p = fp->zmm_space () + i * 64;
- if (memcmp (raw, p, 16) != 0)
+
+ /* ZMMH sub-register. */
+ collect_register (regcache, i + zmm16h_regnum, raw);
+ if (memcmp (raw, p + 32, 32) != 0)
+ {
+ xstate_bv |= X86_XSTATE_ZMM;
+ memcpy (p, raw, 32);
+ }
+
+ /* YMMH sub-register. */
+ collect_register (regcache, i + ymm16h_regnum, raw);
+ if (memcmp (raw, p + 16, 16) != 0)
{
xstate_bv |= X86_XSTATE_ZMM;
memcpy (p, raw, 16);
}
- }
- }
- /* Check if any YMMH_AVX512 registers are changed. */
- if ((x86_xcr0 & X86_XSTATE_ZMM))
- {
- int ymmh_avx512_regnum = (num_avx512_ymmh_registers == 0
- ? -1
- : find_regno (regcache->tdesc, "ymm16h"));
-
- for (i = 0; i < num_avx512_ymmh_registers; i++)
- {
- collect_register (regcache, i + ymmh_avx512_regnum, raw);
- p = fp->zmm_space () + 16 + i * 64;
+ /* XMM sub-register. */
+ collect_register (regcache, i + xmm16_regnum, raw);
if (memcmp (raw, p, 16) != 0)
{
xstate_bv |= X86_XSTATE_ZMM;
@@ -732,12 +702,8 @@ i387_xsave_to_cache (struct regcache *regcache, const void *buf)
/* Amd64 has 16 xmm regs; I386 has 8 xmm regs. */
int num_xmm_registers = amd64 ? 16 : 8;
- /* AVX512 extends the existing xmm/ymm registers to a wider mode: zmm. */
- int num_avx512_zmmh_low_registers = num_xmm_registers;
- /* AVX512 adds 16 extra regs in Amd64 mode, but none in I386 mode.*/
- int num_avx512_zmmh_high_registers = amd64 ? 16 : 0;
- int num_avx512_ymmh_registers = amd64 ? 16 : 0;
- int num_avx512_xmm_registers = amd64 ? 16 : 0;
+ /* AVX512 adds 16 extra ZMM regs in Amd64 mode, but none in I386 mode.*/
+ int num_zmm_high_registers = amd64 ? 16 : 0;
/* The supported bits in `xstat_bv' are 8 bytes. Clear part in
vector registers if its bit in xstat_bv is zero. */
@@ -854,47 +820,41 @@ i387_xsave_to_cache (struct regcache *regcache, const void *buf)
if ((clear_bv & X86_XSTATE_ZMM_H) != 0)
{
- for (i = 0; i < num_avx512_zmmh_low_registers; i++)
+ for (i = 0; i < num_xmm_registers; i++)
supply_register_zeroed (regcache, i + zmm0h_regnum);
}
else
{
p = fp->zmmh_space ();
- for (i = 0; i < num_avx512_zmmh_low_registers; i++)
+ for (i = 0; i < num_xmm_registers; i++)
supply_register (regcache, i + zmm0h_regnum, p + i * 32);
}
}
- if ((x86_xcr0 & X86_XSTATE_ZMM) != 0)
+ if ((x86_xcr0 & X86_XSTATE_ZMM) != 0 && num_zmm_high_registers != 0)
{
- int zmm16h_regnum = (num_avx512_zmmh_high_registers == 0
- ? -1
- : find_regno (regcache->tdesc, "zmm16h"));
- int ymm16h_regnum = (num_avx512_ymmh_registers == 0
- ? -1
- : find_regno (regcache->tdesc, "ymm16h"));
- int xmm16_regnum = (num_avx512_xmm_registers == 0
- ? -1
- : find_regno (regcache->tdesc, "xmm16"));
+ int zmm16h_regnum = find_regno (regcache->tdesc, "zmm16h");
+ int ymm16h_regnum = find_regno (regcache->tdesc, "ymm16h");
+ int xmm16_regnum = find_regno (regcache->tdesc, "xmm16");
if ((clear_bv & X86_XSTATE_ZMM) != 0)
{
- for (i = 0; i < num_avx512_zmmh_high_registers; i++)
- supply_register_zeroed (regcache, i + zmm16h_regnum);
- for (i = 0; i < num_avx512_ymmh_registers; i++)
- supply_register_zeroed (regcache, i + ymm16h_regnum);
- for (i = 0; i < num_avx512_xmm_registers; i++)
- supply_register_zeroed (regcache, i + xmm16_regnum);
+ for (i = 0; i < num_zmm_high_registers; i++)
+ {
+ supply_register_zeroed (regcache, i + zmm16h_regnum);
+ supply_register_zeroed (regcache, i + ymm16h_regnum);
+ supply_register_zeroed (regcache, i + xmm16_regnum);
+ }
}
else
{
p = fp->zmm_space ();
- for (i = 0; i < num_avx512_zmmh_high_registers; i++)
- supply_register (regcache, i + zmm16h_regnum, p + 32 + i * 64);
- for (i = 0; i < num_avx512_ymmh_registers; i++)
- supply_register (regcache, i + ymm16h_regnum, p + 16 + i * 64);
- for (i = 0; i < num_avx512_xmm_registers; i++)
- supply_register (regcache, i + xmm16_regnum, p + i * 64);
+ for (i = 0; i < num_zmm_high_registers; i++)
+ {
+ supply_register (regcache, i + zmm16h_regnum, p + 32 + i * 64);
+ supply_register (regcache, i + ymm16h_regnum, p + 16 + i * 64);
+ supply_register (regcache, i + xmm16_regnum, p + i * 64);
+ }
}
}
--
2.40.0
prev parent reply other threads:[~2023-04-27 21:01 UTC|newest]
Thread overview: 31+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-04-27 21:00 [PATCH v5 00/19] Handle variable XSAVE layouts John Baldwin
2023-04-27 21:00 ` [PATCH v5 01/19] x86: Add an x86_xsave_layout structure to handle " John Baldwin
2023-04-27 21:00 ` [PATCH v5 02/19] gdb: Store an x86_xsave_layout in i386_gdbarch_tdep John Baldwin
2023-05-03 16:22 ` Simon Marchi
2023-05-08 16:51 ` John Baldwin
2023-04-27 21:00 ` [PATCH v5 03/19] core: Support fetching x86 XSAVE layout from architectures John Baldwin
2023-04-27 21:00 ` [PATCH v5 04/19] nat/x86-cpuid.h: Add x86_cpuid_count wrapper around __get_cpuid_count John Baldwin
2023-04-27 21:00 ` [PATCH v5 05/19] x86 nat: Add helper functions to save the XSAVE layout for the host John Baldwin
2023-04-27 21:01 ` [PATCH v5 06/19] x86-fbsd-nat: Add missing public label John Baldwin
2023-04-27 21:01 ` [PATCH v5 07/19] *-fbsd-nat: Handle null inferior in read_description John Baldwin
2023-04-27 21:01 ` [PATCH v5 08/19] *-linux-nat: " John Baldwin
2023-05-03 16:38 ` Simon Marchi
2023-05-08 17:24 ` John Baldwin
2023-04-27 21:01 ` [PATCH v5 09/19] gdb: Update x86 FreeBSD architectures to support XSAVE layouts John Baldwin
2023-05-03 17:14 ` Simon Marchi
2023-05-03 17:20 ` Simon Marchi
2023-05-03 23:45 ` John Baldwin
2023-05-04 17:20 ` Simon Marchi
2023-05-08 17:33 ` John Baldwin
2023-04-27 21:01 ` [PATCH v5 10/19] gdb: Support XSAVE layouts for the current host in the FreeBSD x86 targets John Baldwin
2023-04-27 21:01 ` [PATCH v5 11/19] gdb: Update x86 Linux architectures to support XSAVE layouts John Baldwin
2023-04-27 21:01 ` [PATCH v5 12/19] gdb: Support XSAVE layouts for the current host in the Linux x86 targets John Baldwin
2023-04-27 21:01 ` [PATCH v5 13/19] gdb: Use x86_xstate_layout to parse the XSAVE extended state area John Baldwin
2023-04-27 21:01 ` [PATCH v5 14/19] gdbserver: Add a function to set the XSAVE mask and size John Baldwin
2023-04-27 21:01 ` [PATCH v5 15/19] gdbserver: Refactor the legacy region within the xsave struct John Baldwin
2023-04-27 21:01 ` [PATCH v5 16/19] gdbserver: Clear upper ZMM registers in the right location John Baldwin
2023-05-03 17:49 ` Simon Marchi
2023-05-03 23:47 ` John Baldwin
2023-04-27 21:01 ` [PATCH v5 17/19] gdbserver: Use x86_xstate_layout to parse the XSAVE extended state area John Baldwin
2023-04-27 21:01 ` [PATCH v5 18/19] x86: Remove X86_XSTATE_SIZE and related constants John Baldwin
2023-04-27 21:01 ` John Baldwin [this message]
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20230427210113.45380-20-jhb@FreeBSD.org \
--to=jhb@freebsd.org \
--cc=gdb-patches@sourceware.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).